Merge branch 'for_3.0/pm-fixes' of ssh://master.kernel.org/pub/scm/linux/kernel/git/khilman/linux-omap-pm into fixes

529 files changed, 15348 insertions, 6583 deletions

diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index c078ad48f7a1..8173cec473aa 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -99,18 +99,11 @@ o	"qp" indicates that RCU still expects a quiescent state from
 
 o       "dt" is the current value of the dyntick counter that is incremented
         when entering or leaving dynticks idle state, either by the
-        scheduler or by irq.  The number after the "/" is the interrupt
-        nesting depth when in dyntick-idle state, or one greater than
-        the interrupt-nesting depth otherwise.
-
-        This field is displayed only for CONFIG_NO_HZ kernels.
-
-o       "dn" is the current value of the dyntick counter that is incremented
-        when entering or leaving dynticks idle state via NMI.  If both
-        the "dt" and "dn" values are even, then this CPU is in dynticks
-        idle mode and may be ignored by RCU.  If either of these two
-        counters is odd, then RCU must be alert to the possibility of
-        an RCU read-side critical section running on this CPU.
+        scheduler or by irq.  This number is even if the CPU is in
+        dyntick idle mode and odd otherwise.  The number after the first
+        "/" is the interrupt nesting depth when in dyntick-idle state,
+        or one greater than the interrupt-nesting depth otherwise.
+        The number after the second "/" is the NMI nesting depth.
 
         This field is displayed only for CONFIG_NO_HZ kernels.
 
diff --git a/Documentation/acpi/method-customizing.txt b/Documentation/acpi/method-customizing.txt
index 3e1d25aee3fb..5f55373dd53b 100644
--- a/Documentation/acpi/method-customizing.txt
+++ b/Documentation/acpi/method-customizing.txt
@@ -66,3 +66,8 @@ Note: We can use a kernel with multiple custom ACPI method running,
       But each individual write to debugfs can implement a SINGLE
       method override. i.e. if we want to insert/override multiple
       ACPI methods, we need to redo step c) ~ g) for multiple times.
+
+Note: Be aware that root can mis-use this driver to modify arbitrary
+      memory and gain additional rights, if root's privileges got
+      restricted (for example if root is not allowed to load additional
+      modules after boot).
diff --git a/Documentation/dmaengine.txt b/Documentation/dmaengine.txt
index 0c1c2f63c0a9..5a0cb1ef6164 100644
--- a/Documentation/dmaengine.txt
+++ b/Documentation/dmaengine.txt
@@ -1 +1,96 @@
-See Documentation/crypto/async-tx-api.txt
+                        DMA Engine API Guide
+                        ====================
+
+                 Vinod Koul <vinod dot koul at intel.com>
+
+NOTE: For DMA Engine usage in async_tx please see:
+        Documentation/crypto/async-tx-api.txt
+
+
+Below is a guide to device driver writers on how to use the Slave-DMA API of the
+DMA Engine. This is applicable only for slave DMA usage only.
+
+The slave DMA usage consists of following steps
+1. Allocate a DMA slave channel
+2. Set slave and controller specific parameters
+3. Get a descriptor for transaction
+4. Submit the transaction and wait for callback notification
+
+1. Allocate a DMA slave channel
+Channel allocation is slightly different in the slave DMA context, client
+drivers typically need a channel from a particular DMA controller only and even
+in some cases a specific channel is desired. To request a channel
+dma_request_channel() API is used.
+
+Interface:
+struct dma_chan *dma_request_channel(dma_cap_mask_t mask,
+                dma_filter_fn filter_fn,
+                void *filter_param);
+where dma_filter_fn is defined as:
+typedef bool (*dma_filter_fn)(struct dma_chan *chan, void *filter_param);
+
+When the optional 'filter_fn' parameter is set to NULL dma_request_channel
+simply returns the first channel that satisfies the capability mask.  Otherwise,
+when the mask parameter is insufficient for specifying the necessary channel,
+the filter_fn routine can be used to disposition the available channels in the
+system. The filter_fn routine is called once for each free channel in the
+system.  Upon seeing a suitable channel filter_fn returns DMA_ACK which flags
+that channel to be the return value from dma_request_channel.  A channel
+allocated via this interface is exclusive to the caller, until
+dma_release_channel() is called.
+
+2. Set slave and controller specific parameters
+Next step is always to pass some specific information to the DMA driver. Most of
+the generic information which a slave DMA can use is in struct dma_slave_config.
+It allows the clients to specify DMA direction, DMA addresses, bus widths, DMA
+burst lengths etc. If some DMA controllers have more parameters to be sent then
+they should try to embed struct dma_slave_config in their controller specific
+structure. That gives flexibility to client to pass more parameters, if
+required.
+
+Interface:
+int dmaengine_slave_config(struct dma_chan *chan,
+                                          struct dma_slave_config *config)
+
+3. Get a descriptor for transaction
+For slave usage the various modes of slave transfers supported by the
+DMA-engine are:
+slave_sg        - DMA a list of scatter gather buffers from/to a peripheral
+dma_cyclic      - Perform a cyclic DMA operation from/to a peripheral till the
+                  operation is explicitly stopped.
+The non NULL return of this transfer API represents a "descriptor" for the given
+transaction.
+
+Interface:
+struct dma_async_tx_descriptor *(*chan->device->device_prep_dma_sg)(
+                struct dma_chan *chan,
+                struct scatterlist *dst_sg, unsigned int dst_nents,
+                struct scatterlist *src_sg, unsigned int src_nents,
+                unsigned long flags);
+struct dma_async_tx_descriptor *(*chan->device->device_prep_dma_cyclic)(
+                struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
+                size_t period_len, enum dma_data_direction direction);
+
+4. Submit the transaction and wait for callback notification
+To schedule the transaction to be scheduled by dma device, the "descriptor"
+returned in above (3) needs to be submitted.
+To tell the dma driver that a transaction is ready to be serviced, the
+descriptor->submit() callback needs to be invoked. This chains the descriptor to
+the pending queue.
+The transactions in the pending queue can be activated by calling the
+issue_pending API. If channel is idle then the first transaction in queue is
+started and subsequent ones queued up.
+On completion of the DMA operation the next in queue is submitted and a tasklet
+triggered. The tasklet would then call the client driver completion callback
+routine for notification, if set.
+Interface:
+void dma_async_issue_pending(struct dma_chan *chan);
+
+==============================================================================
+
+Additional usage notes for dma driver writers
+1/ Although DMA engine specifies that completion callback routines cannot submit
+any new operations, but typically for slave DMA subsequent transaction may not
+be available for submit prior to callback routine being called. This requirement
+is not a requirement for DMA-slave devices. But they should take care to drop
+the spin-lock they might be holding before calling the callback routine
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index ff31b1cc50aa..1a9446b59153 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -6,6 +6,42 @@ be removed from this file.
 
 ---------------------------
 
+What:   x86 floppy disable_hlt
+When:   2012
+Why:    ancient workaround of dubious utility clutters the
+        code used by everybody else.
+Who:    Len Brown <len.brown@intel.com>
+
+---------------------------
+
+What:   CONFIG_APM_CPU_IDLE, and its ability to call APM BIOS in idle
+When:   2012
+Why:    This optional sub-feature of APM is of dubious reliability,
+        and ancient APM laptops are likely better served by calling HLT.
+        Deleting CONFIG_APM_CPU_IDLE allows x86 to stop exporting
+        the pm_idle function pointer to modules.
+Who:    Len Brown <len.brown@intel.com>
+
+----------------------------
+
+What:   x86_32 "no-hlt" cmdline param
+When:   2012
+Why:    remove a branch from idle path, simplify code used by everybody.
+        This option disabled the use of HLT in idle and machine_halt()
+        for hardware that was flakey 15-years ago.  Today we have
+        "idle=poll" that removed HLT from idle, and so if such a machine
+        is still running the upstream kernel, "idle=poll" is likely sufficient.
+Who:    Len Brown <len.brown@intel.com>
+
+----------------------------
+
+What:   x86 "idle=mwait" cmdline param
+When:   2012
+Why:    simplify x86 idle code
+Who:    Len Brown <len.brown@intel.com>
+
+----------------------------
+
 What:   PRISM54
 When:   2.6.34
 
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 61b31acb9176..57d827d6071d 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -104,7 +104,7 @@ of the locking scheme for directory operations.
 prototypes:
         struct inode *(*alloc_inode)(struct super_block *sb);
         void (*destroy_inode)(struct inode *);
-        void (*dirty_inode) (struct inode *);
+        void (*dirty_inode) (struct inode *, int flags);
         int (*write_inode) (struct inode *, struct writeback_control *wbc);
         int (*drop_inode) (struct inode *);
         void (*evict_inode) (struct inode *);
@@ -126,7 +126,7 @@ locking rules:
                         s_umount
 alloc_inode:
 destroy_inode:
-dirty_inode:                            (must not sleep)
+dirty_inode:
 write_inode:
 drop_inode:                             !!!inode->i_lock!!!
 evict_inode:
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 21a7dc467bba..88b9f5519af9 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -211,7 +211,7 @@ struct super_operations {
         struct inode *(*alloc_inode)(struct super_block *sb);
         void (*destroy_inode)(struct inode *);
 
-        void (*dirty_inode) (struct inode *);
+        void (*dirty_inode) (struct inode *, int flags);
         int (*write_inode) (struct inode *, int);
         void (*drop_inode) (struct inode *);
         void (*delete_inode) (struct inode *);
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 5438a2d7907f..d9a203b058f1 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -999,7 +999,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
                         With this option on every unmap_single operation will
                         result in a hardware IOTLB flush operation as opposed
                         to batching them for performance.
-
+                sp_off [Default Off]
+                        By default, super page will be supported if Intel IOMMU
+                        has the capability. With this option, super page will
+                        not be supported.
         intremap=       [X86-64, Intel-IOMMU]
                         Format: { on (default) | off | nosid }
                         on      enable Interrupt Remapping (default)
diff --git a/Documentation/laptops/acer-wmi.txt b/Documentation/laptops/acer-wmi.txt
deleted file mode 100644
index 4beafa663dd6..000000000000
--- a/Documentation/laptops/acer-wmi.txt
+++ /dev/null
@@ -1,184 +0,0 @@
-Acer Laptop WMI Extras Driver
-http://code.google.com/p/aceracpi
-Version 0.3
-4th April 2009
-
-Copyright 2007-2009 Carlos Corbacho <carlos@strangeworlds.co.uk>
-
-acer-wmi is a driver to allow you to control various parts of your Acer laptop
-hardware under Linux which are exposed via ACPI-WMI.
-
-This driver completely replaces the old out-of-tree acer_acpi, which I am
-currently maintaining for bug fixes only on pre-2.6.25 kernels. All development
-work is now focused solely on acer-wmi.
-
-Disclaimer
-**********
-
-Acer and Wistron have provided nothing towards the development acer_acpi or
-acer-wmi. All information we have has been through the efforts of the developers
-and the users to discover as much as possible about the hardware.
-
-As such, I do warn that this could break your hardware - this is extremely
-unlikely of course, but please bear this in mind.
-
-Background
-**********
-
-acer-wmi is derived from acer_acpi, originally developed by Mark
-Smith in 2005, then taken over by Carlos Corbacho in 2007, in order to activate
-the wireless LAN card under a 64-bit version of Linux, as acerhk[1] (the
-previous solution to the problem) relied on making 32 bit BIOS calls which are
-not possible in kernel space from a 64 bit OS.
-
-[1] acerhk: http://www.cakey.de/acerhk/
-
-Supported Hardware
-******************
-
-NOTE: The Acer Aspire One is not supported hardware. It cannot work with
-acer-wmi until Acer fix their ACPI-WMI implementation on them, so has been
-blacklisted until that happens.
-
-Please see the website for the current list of known working hardware:
-
-http://code.google.com/p/aceracpi/wiki/SupportedHardware
-
-If your laptop is not listed, or listed as unknown, and works with acer-wmi,
-please contact me with a copy of the DSDT.
-
-If your Acer laptop doesn't work with acer-wmi, I would also like to see the
-DSDT.
-
-To send me the DSDT, as root/sudo:
-
-cat /sys/firmware/acpi/tables/DSDT > dsdt
-
-And send me the resulting 'dsdt' file.
-
-Usage
-*****
-
-On Acer laptops, acer-wmi should already be autoloaded based on DMI matching.
-For non-Acer laptops, until WMI based autoloading support is added, you will
-need to manually load acer-wmi.
-
-acer-wmi creates /sys/devices/platform/acer-wmi, and fills it with various
-files whose usage is detailed below, which enables you to control some of the
-following (varies between models):
-
-* the wireless LAN card radio
-* inbuilt Bluetooth adapter
-* inbuilt 3G card
-* mail LED of your laptop
-* brightness of the LCD panel
-
-Wireless
-********
-
-With regards to wireless, all acer-wmi does is enable the radio on the card. It
-is not responsible for the wireless LED - once the radio is enabled, this is
-down to the wireless driver for your card. So the behaviour of the wireless LED,
-once you enable the radio, will depend on your hardware and driver combination.
-
-e.g. With the BCM4318 on the Acer Aspire 5020 series:
-
-ndiswrapper: Light blinks on when transmitting
-b43: Solid light, blinks off when transmitting
-
-Wireless radio control is unconditionally enabled - all Acer laptops that support
-acer-wmi come with built-in wireless. However, should you feel so inclined to
-ever wish to remove the card, or swap it out at some point, please get in touch
-with me, as we may well be able to gain some data on wireless card detection.
-
-The wireless radio is exposed through rfkill.
-
-Bluetooth
-*********
-
-For bluetooth, this is an internal USB dongle, so once enabled, you will get
-a USB device connection event, and a new USB device appears. When you disable
-bluetooth, you get the reverse - a USB device disconnect event, followed by the
-device disappearing again.
-
-Bluetooth is autodetected by acer-wmi, so if you do not have a bluetooth module
-installed in your laptop, this file won't exist (please be aware that it is
-quite common for Acer not to fit bluetooth to their laptops - so just because
-you have a bluetooth button on the laptop, doesn't mean that bluetooth is
-installed).
-
-For the adventurously minded - if you want to buy an internal bluetooth
-module off the internet that is compatible with your laptop and fit it, then
-it will work just fine with acer-wmi.
-
-Bluetooth is exposed through rfkill.
-
-3G
-**
-
-3G is currently not autodetected, so the 'threeg' file is always created under
-sysfs. So far, no-one in possession of an Acer laptop with 3G built-in appears to
-have tried Linux, or reported back, so we don't have any information on this.
-
-If you have an Acer laptop that does have a 3G card in, please contact me so we
-can properly detect these, and find out a bit more about them.
-
-To read the status of the 3G card (0=off, 1=on):
-cat /sys/devices/platform/acer-wmi/threeg
-
-To enable the 3G card:
-echo 1 > /sys/devices/platform/acer-wmi/threeg
-
-To disable the 3G card:
-echo 0 > /sys/devices/platform/acer-wmi/threeg
-
-To set the state of the 3G card when loading acer-wmi, pass:
-threeg=X (where X is 0 or 1)
-
-Mail LED
-********
-
-This can be found in most older Acer laptops supported by acer-wmi, and many
-newer ones - it is built into the 'mail' button, and blinks when active.
-
-On newer (WMID) laptops though, we have no way of detecting the mail LED. If
-your laptop identifies itself in dmesg as a WMID model, then please try loading
-acer_acpi with:
-
-force_series=2490
-
-This will use a known alternative method of reading/ writing the mail LED. If
-it works, please report back to me with the DMI data from your laptop so this
-can be added to acer-wmi.
-
-The LED is exposed through the LED subsystem, and can be found in:
-
-/sys/devices/platform/acer-wmi/leds/acer-wmi::mail/
-
-The mail LED is autodetected, so if you don't have one, the LED device won't
-be registered.
-
-Backlight
-*********
-
-The backlight brightness control is available on all acer-wmi supported
-hardware. The maximum brightness level is usually 15, but on some newer laptops
-it's 10 (this is again autodetected).
-
-The backlight is exposed through the backlight subsystem, and can be found in:
-
-/sys/devices/platform/acer-wmi/backlight/acer-wmi/
-
-Credits
-*******
-
-Olaf Tauber, who did the real hard work when he developed acerhk
-http://www.cakey.de/acerhk/
-All the authors of laptop ACPI modules in the kernel, whose work
-was an inspiration in the early days of acer_acpi
-Mathieu Segaud, who solved the problem with having to modprobe the driver
-twice in acer_acpi 0.2.
-Jim Ramsay, who added support for the WMID interface
-Mark Smith, who started the original acer_acpi
-
-And the many people who have used both acer_acpi and acer-wmi.
diff --git a/Documentation/lockstat.txt b/Documentation/lockstat.txt
index 9c0a80d17a23..cef00d42ed5b 100644
--- a/Documentation/lockstat.txt
+++ b/Documentation/lockstat.txt
@@ -12,8 +12,9 @@ Because things like lock contention can severely impact performance.
 - HOW
 
 Lockdep already has hooks in the lock functions and maps lock instances to
-lock classes. We build on that. The graph below shows the relation between
-the lock functions and the various hooks therein.
+lock classes. We build on that (see Documentation/lockdep-design.txt).
+The graph below shows the relation between the lock functions and the various
+hooks therein.
 
         __acquire
             |
@@ -128,6 +129,37 @@ points are the points we're contending with.
 
 The integer part of the time values is in us.
 
+Dealing with nested locks, subclasses may appear:
+
+32...............................................................................................................................................................................................
+33
+34                               &rq->lock:         13128          13128           0.43         190.53      103881.26          97454        3453404           0.00         401.11    13224683.11
+35                               ---------
+36                               &rq->lock            645          [<ffffffff8103bfc4>] task_rq_lock+0x43/0x75
+37                               &rq->lock            297          [<ffffffff8104ba65>] try_to_wake_up+0x127/0x25a
+38                               &rq->lock            360          [<ffffffff8103c4c5>] select_task_rq_fair+0x1f0/0x74a
+39                               &rq->lock            428          [<ffffffff81045f98>] scheduler_tick+0x46/0x1fb
+40                               ---------
+41                               &rq->lock             77          [<ffffffff8103bfc4>] task_rq_lock+0x43/0x75
+42                               &rq->lock            174          [<ffffffff8104ba65>] try_to_wake_up+0x127/0x25a
+43                               &rq->lock           4715          [<ffffffff8103ed4b>] double_rq_lock+0x42/0x54
+44                               &rq->lock            893          [<ffffffff81340524>] schedule+0x157/0x7b8
+45
+46...............................................................................................................................................................................................
+47
+48                             &rq->lock/1:         11526          11488           0.33         388.73      136294.31          21461          38404           0.00          37.93      109388.53
+49                             -----------
+50                             &rq->lock/1          11526          [<ffffffff8103ed58>] double_rq_lock+0x4f/0x54
+51                             -----------
+52                             &rq->lock/1           5645          [<ffffffff8103ed4b>] double_rq_lock+0x42/0x54
+53                             &rq->lock/1           1224          [<ffffffff81340524>] schedule+0x157/0x7b8
+54                             &rq->lock/1           4336          [<ffffffff8103ed58>] double_rq_lock+0x4f/0x54
+55                             &rq->lock/1            181          [<ffffffff8104ba65>] try_to_wake_up+0x127/0x25a
+
+Line 48 shows statistics for the second subclass (/1) of &rq->lock class
+(subclass starts from 0), since in this case, as line 50 suggests,
+double_rq_lock actually acquires a nested lock of two spinlocks.
+
 View the top contending locks:
 
 # grep : /proc/lock_stat | head
diff --git a/Documentation/virtual/lguest/Makefile b/Documentation/virtual/lguest/Makefile
index bebac6b4f332..0ac34206f7a7 100644
--- a/Documentation/virtual/lguest/Makefile
+++ b/Documentation/virtual/lguest/Makefile
@@ -1,5 +1,5 @@
 # This creates the demonstration utility "lguest" which runs a Linux guest.
-# Missing headers?  Add "-I../../include -I../../arch/x86/include"
+# Missing headers?  Add "-I../../../include -I../../../arch/x86/include"
 CFLAGS:=-m32 -Wall -Wmissing-declarations -Wmissing-prototypes -O3 -U_FORTIFY_SOURCE
 
 all: lguest
diff --git a/Documentation/virtual/lguest/lguest.c b/Documentation/virtual/lguest/lguest.c
index d9da7e148538..cd9d6af61d07 100644
--- a/Documentation/virtual/lguest/lguest.c
+++ b/Documentation/virtual/lguest/lguest.c
@@ -49,7 +49,7 @@
 #include <linux/virtio_rng.h>
 #include <linux/virtio_ring.h>
 #include <asm/bootparam.h>
-#include "../../include/linux/lguest_launcher.h"
+#include "../../../include/linux/lguest_launcher.h"
 /*L:110
  * We can ignore the 42 include files we need for this program, but I do want
  * to draw attention to the use of kernel-style types.
@@ -135,9 +135,6 @@ struct device {
         /* Is it operational */
         bool running;
 
-        /* Does Guest want an intrrupt on empty? */
-        bool irq_on_empty;
-
         /* Device-specific data. */
         void *priv;
 };
@@ -637,10 +634,7 @@ static void trigger_irq(struct virtqueue *vq)
 
         /* If they don't want an interrupt, don't send one... */
         if (vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT) {
-                /* ... unless they've asked us to force one on empty. */
-                if (!vq->dev->irq_on_empty
-                    || lg_last_avail(vq) != vq->vring.avail->idx)
-                        return;
+                return;
         }
 
         /* Send the Guest an interrupt tell them we used something up. */
@@ -1057,15 +1051,6 @@ static void create_thread(struct virtqueue *vq)
         close(vq->eventfd);
 }
 
-static bool accepted_feature(struct device *dev, unsigned int bit)
-{
-        const u8 *features = get_feature_bits(dev) + dev->feature_len;
-
-        if (dev->feature_len < bit / CHAR_BIT)
-                return false;
-        return features[bit / CHAR_BIT] & (1 << (bit % CHAR_BIT));
-}
-
 static void start_device(struct device *dev)
 {
         unsigned int i;
@@ -1079,8 +1064,6 @@ static void start_device(struct device *dev)
                 verbose(" %02x", get_feature_bits(dev)
                         [dev->feature_len+i]);
 
-        dev->irq_on_empty = accepted_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY);
-
         for (vq = dev->vq; vq; vq = vq->next) {
                 if (vq->service)
                         create_thread(vq);
@@ -1564,7 +1547,6 @@ static void setup_tun_net(char *arg)
         /* Set up the tun device. */
         configure_device(ipfd, tapif, ip);
 
-        add_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY);
         /* Expect Guest to handle everything except UFO */
         add_feature(dev, VIRTIO_NET_F_CSUM);
         add_feature(dev, VIRTIO_NET_F_GUEST_CSUM);
diff --git a/MAINTAINERS b/MAINTAINERS
index b9f5aee36375..29801f760b6f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -223,10 +223,8 @@ S:	Maintained
 F:      drivers/platform/x86/acerhdf.c
 
 ACER WMI LAPTOP EXTRAS
-M:      Carlos Corbacho <carlos@strangeworlds.co.uk>
-L:      aceracpi@googlegroups.com (subscribers-only)
+M:      Joey Lee <jlee@novell.com>
 L:      platform-driver-x86@vger.kernel.org
-W:      http://code.google.com/p/aceracpi
 S:      Maintained
 F:      drivers/platform/x86/acer-wmi.c
 
@@ -271,10 +269,8 @@ S:	Supported
 F:      drivers/acpi/video.c
 
 ACPI WMI DRIVER
-M:      Carlos Corbacho <carlos@strangeworlds.co.uk>
 L:      platform-driver-x86@vger.kernel.org
-W:      http://www.lesswatts.org/projects/acpi/
-S:      Maintained
+S:      Orphan
 F:      drivers/platform/x86/wmi.c
 
 AD1889 ALSA SOUND DRIVER
@@ -2178,6 +2174,8 @@ M:	Dan Williams <dan.j.williams@intel.com>
 S:      Supported
 F:      drivers/dma/
 F:      include/linux/dma*
+T:      git git://git.kernel.org/pub/scm/linux/kernel/git/djbw/async_tx.git
+T:      git git://git.infradead.org/users/vkoul/slave-dma.git (slave-dma)
 
 DME1737 HARDWARE MONITOR DRIVER
 M:      Juerg Haefliger <juergh@gmail.com>
@@ -3031,9 +3029,8 @@ S:	Maintained
 F:      drivers/net/wireless/hostap/
 
 HP COMPAQ TC1100 TABLET WMI EXTRAS DRIVER
-M:      Carlos Corbacho <carlos@strangeworlds.co.uk>
 L:      platform-driver-x86@vger.kernel.org
-S:      Odd Fixes
+S:      Orphan
 F:      drivers/platform/x86/tc1100-wmi.c
 
 HP100:  Driver for HP 10/100 Mbit/s Voice Grade Network Adapter Series
@@ -5451,6 +5448,13 @@ L:	linux-serial@vger.kernel.org
 S:      Maintained
 F:      drivers/tty/serial
 
+SYNOPSYS DESIGNWARE DMAC DRIVER
+M:      Viresh Kumar <viresh.kumar@st.com>
+S:      Maintained
+F:      include/linux/dw_dmac.h
+F:      drivers/dma/dw_dmac_regs.h
+F:      drivers/dma/dw_dmac.c
+
 TIMEKEEPING, NTP
 M:      John Stultz <johnstul@us.ibm.com>
 M:      Thomas Gleixner <tglx@linutronix.de>
diff --git a/Makefile b/Makefile
index 529d93fa2430..0f1db8d90741 100644
--- a/Makefile
+++ b/Makefile
@@ -1,8 +1,8 @@
-VERSION = 2
-PATCHLEVEL = 6
-SUBLEVEL = 39
-EXTRAVERSION =
-NAME = Flesh-Eating Bats with Fangs
+VERSION = 3
+PATCHLEVEL = 0
+SUBLEVEL = 0
+EXTRAVERSION = -rc2
+NAME = Sneaky Weasel
 
 # *DOCUMENTATION*
 # To see a list of typical targets execute "make help"
diff --git a/arch/arm/mach-omap2/pm-debug.c b/arch/arm/mach-omap2/pm-debug.c
index a5a83b358ddd..e01da45c0537 100644
--- a/arch/arm/mach-omap2/pm-debug.c
+++ b/arch/arm/mach-omap2/pm-debug.c
@@ -189,7 +189,7 @@ static struct dentry *pm_dbg_dir;
 
 static int pm_dbg_init_done;
 
-static int __init pm_dbg_init(void);
+static int pm_dbg_init(void);
 
 enum {
         DEBUG_FILE_COUNTERS = 0,
@@ -595,7 +595,7 @@ static int option_set(void *data, u64 val)
 
 DEFINE_SIMPLE_ATTRIBUTE(pm_dbg_option_fops, option_get, option_set, "%llu\n");
 
-static int __init pm_dbg_init(void)
+static int pm_dbg_init(void)
 {
         int i;
         struct dentry *d;
diff --git a/arch/arm/mach-shmobile/board-ap4evb.c b/arch/arm/mach-shmobile/board-ap4evb.c
index 08acb6ec8139..f6b687f61c28 100644
--- a/arch/arm/mach-shmobile/board-ap4evb.c
+++ b/arch/arm/mach-shmobile/board-ap4evb.c
@@ -249,6 +249,29 @@ static int slot_cn7_get_cd(struct platform_device *pdev)
 {
         return !gpio_get_value(GPIO_PORT41);
 }
+/* MERAM */
+static struct sh_mobile_meram_info meram_info = {
+        .addr_mode      = SH_MOBILE_MERAM_MODE1,
+};
+
+static struct resource meram_resources[] = {
+        [0] = {
+                .name   = "MERAM",
+                .start  = 0xe8000000,
+                .end    = 0xe81fffff,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+
+static struct platform_device meram_device = {
+        .name           = "sh_mobile_meram",
+        .id             = 0,
+        .num_resources  = ARRAY_SIZE(meram_resources),
+        .resource       = meram_resources,
+        .dev            = {
+                .platform_data = &meram_info,
+        },
+};
 
 /* SH_MMCIF */
 static struct resource sh_mmcif_resources[] = {
@@ -447,13 +470,29 @@ const static struct fb_videomode ap4evb_lcdc_modes[] = {
 #endif
         },
 };
+static struct sh_mobile_meram_cfg lcd_meram_cfg = {
+        .icb[0] = {
+                .marker_icb     = 28,
+                .cache_icb      = 24,
+                .meram_offset   = 0x0,
+                .meram_size     = 0x40,
+        },
+        .icb[1] = {
+                .marker_icb     = 29,
+                .cache_icb      = 25,
+                .meram_offset   = 0x40,
+                .meram_size     = 0x40,
+        },
+};
 
 static struct sh_mobile_lcdc_info lcdc_info = {
+        .meram_dev = &meram_info,
         .ch[0] = {
                 .chan = LCDC_CHAN_MAINLCD,
                 .bpp = 16,
                 .lcd_cfg = ap4evb_lcdc_modes,
                 .num_cfg = ARRAY_SIZE(ap4evb_lcdc_modes),
+                .meram_cfg = &lcd_meram_cfg,
         }
 };
 
@@ -724,15 +763,31 @@ static struct platform_device fsi_device = {
 static struct platform_device fsi_ak4643_device = {
         .name           = "sh_fsi2_a_ak4643",
 };
+static struct sh_mobile_meram_cfg hdmi_meram_cfg = {
+        .icb[0] = {
+                .marker_icb     = 30,
+                .cache_icb      = 26,
+                .meram_offset   = 0x80,
+                .meram_size     = 0x100,
+        },
+        .icb[1] = {
+                .marker_icb     = 31,
+                .cache_icb      = 27,
+                .meram_offset   = 0x180,
+                .meram_size     = 0x100,
+        },
+};
 
 static struct sh_mobile_lcdc_info sh_mobile_lcdc1_info = {
         .clock_source = LCDC_CLK_EXTERNAL,
+        .meram_dev = &meram_info,
         .ch[0] = {
                 .chan = LCDC_CHAN_MAINLCD,
                 .bpp = 16,
                 .interface_type = RGB24,
                 .clock_divider = 1,
                 .flags = LCDC_FLAGS_DWPOL,
+                .meram_cfg = &hdmi_meram_cfg,
         }
 };
 
@@ -961,6 +1016,7 @@ static struct platform_device *ap4evb_devices[] __initdata = {
         &csi2_device,
         &ceu_device,
         &ap4evb_camera,
+        &meram_device,
 };
 
 static void __init hdmi_init_pm_clock(void)
diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c
index 448ddbe43335..776f20560e72 100644
--- a/arch/arm/mach-shmobile/board-mackerel.c
+++ b/arch/arm/mach-shmobile/board-mackerel.c
@@ -39,6 +39,7 @@
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/physmap.h>
+#include <linux/pm_runtime.h>
 #include <linux/smsc911x.h>
 #include <linux/sh_intc.h>
 #include <linux/tca6416_keypad.h>
@@ -314,6 +315,30 @@ static struct platform_device smc911x_device = {
         },
 };
 
+/* MERAM */
+static struct sh_mobile_meram_info mackerel_meram_info = {
+        .addr_mode      = SH_MOBILE_MERAM_MODE1,
+};
+
+static struct resource meram_resources[] = {
+        [0] = {
+                .name   = "MERAM",
+                .start  = 0xe8000000,
+                .end    = 0xe81fffff,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+
+static struct platform_device meram_device = {
+        .name           = "sh_mobile_meram",
+        .id             = 0,
+        .num_resources  = ARRAY_SIZE(meram_resources),
+        .resource       = meram_resources,
+        .dev            = {
+                .platform_data = &mackerel_meram_info,
+        },
+};
+
 /* LCDC */
 static struct fb_videomode mackerel_lcdc_modes[] = {
         {
@@ -342,7 +367,23 @@ static int mackerel_get_brightness(void *board_data)
         return gpio_get_value(GPIO_PORT31);
 }
 
+static struct sh_mobile_meram_cfg lcd_meram_cfg = {
+        .icb[0] = {
+                .marker_icb     = 28,
+                .cache_icb      = 24,
+                .meram_offset   = 0x0,
+                .meram_size     = 0x40,
+        },
+        .icb[1] = {
+                .marker_icb     = 29,
+                .cache_icb      = 25,
+                .meram_offset   = 0x40,
+                .meram_size     = 0x40,
+        },
+};
+
 static struct sh_mobile_lcdc_info lcdc_info = {
+        .meram_dev = &mackerel_meram_info,
         .clock_source = LCDC_CLK_BUS,
         .ch[0] = {
                 .chan = LCDC_CHAN_MAINLCD,
@@ -362,6 +403,7 @@ static struct sh_mobile_lcdc_info lcdc_info = {
                         .name = "sh_mobile_lcdc_bl",
                         .max_brightness = 1,
                 },
+                .meram_cfg = &lcd_meram_cfg,
         }
 };
 
@@ -388,8 +430,23 @@ static struct platform_device lcdc_device = {
         },
 };
 
+static struct sh_mobile_meram_cfg hdmi_meram_cfg = {
+        .icb[0] = {
+                .marker_icb     = 30,
+                .cache_icb      = 26,
+                .meram_offset   = 0x80,
+                .meram_size     = 0x100,
+        },
+        .icb[1] = {
+                .marker_icb     = 31,
+                .cache_icb      = 27,
+                .meram_offset   = 0x180,
+                .meram_size     = 0x100,
+        },
+};
 /* HDMI */
 static struct sh_mobile_lcdc_info hdmi_lcdc_info = {
+        .meram_dev = &mackerel_meram_info,
         .clock_source = LCDC_CLK_EXTERNAL,
         .ch[0] = {
                 .chan = LCDC_CHAN_MAINLCD,
@@ -397,6 +454,7 @@ static struct sh_mobile_lcdc_info hdmi_lcdc_info = {
                 .interface_type = RGB24,
                 .clock_divider = 1,
                 .flags = LCDC_FLAGS_DWPOL,
+                .meram_cfg = &hdmi_meram_cfg,
         }
 };
 
@@ -856,6 +914,17 @@ static int slot_cn7_get_cd(struct platform_device *pdev)
 }
 
 /* SDHI0 */
+static irqreturn_t mackerel_sdhi0_gpio_cd(int irq, void *arg)
+{
+        struct device *dev = arg;
+        struct sh_mobile_sdhi_info *info = dev->platform_data;
+        struct tmio_mmc_data *pdata = info->pdata;
+
+        tmio_mmc_cd_wakeup(pdata);
+
+        return IRQ_HANDLED;
+}
+
 static struct sh_mobile_sdhi_info sdhi0_info = {
         .dma_slave_tx   = SHDMA_SLAVE_SDHI0_TX,
         .dma_slave_rx   = SHDMA_SLAVE_SDHI0_RX,
@@ -1150,6 +1219,7 @@ static struct platform_device *mackerel_devices[] __initdata = {
         &mackerel_camera,
         &hdmi_lcdc_device,
         &hdmi_device,
+        &meram_device,
 };
 
 /* Keypad Initialization */
@@ -1238,6 +1308,7 @@ static void __init mackerel_init(void)
 {
         u32 srcr4;
         struct clk *clk;
+        int ret;
 
         sh7372_pinmux_init();
 
@@ -1343,6 +1414,13 @@ static void __init mackerel_init(void)
         gpio_request(GPIO_FN_SDHID0_1, NULL);
         gpio_request(GPIO_FN_SDHID0_0, NULL);
 
+        ret = request_irq(evt2irq(0x3340), mackerel_sdhi0_gpio_cd,
+                          IRQF_TRIGGER_FALLING, "sdhi0 cd", &sdhi0_device.dev);
+        if (!ret)
+                sdhi0_info.tmio_flags |= TMIO_MMC_HAS_COLD_CD;
+        else
+                pr_err("Cannot get IRQ #%d: %d\n", evt2irq(0x3340), ret);
+
 #if !defined(CONFIG_MMC_SH_MMCIF) && !defined(CONFIG_MMC_SH_MMCIF_MODULE)
         /* enable SDHI1 */
         gpio_request(GPIO_FN_SDHICMD1, NULL);
diff --git a/arch/arm/mach-shmobile/clock-sh7372.c b/arch/arm/mach-shmobile/clock-sh7372.c
index d17eb66f4ac2..c0800d83971e 100644
--- a/arch/arm/mach-shmobile/clock-sh7372.c
+++ b/arch/arm/mach-shmobile/clock-sh7372.c
@@ -509,6 +509,7 @@ enum { MSTP001,
        MSTP118, MSTP117, MSTP116, MSTP113,
        MSTP106, MSTP101, MSTP100,
        MSTP223,
+       MSTP218, MSTP217, MSTP216,
        MSTP207, MSTP206, MSTP204, MSTP203, MSTP202, MSTP201, MSTP200,
        MSTP329, MSTP328, MSTP323, MSTP322, MSTP314, MSTP313, MSTP312,
        MSTP423, MSTP415, MSTP413, MSTP411, MSTP410, MSTP406, MSTP403,
@@ -534,6 +535,9 @@ static struct clk mstp_clks[MSTP_NR] = {
         [MSTP101] = MSTP(&div4_clks[DIV4_M1], SMSTPCR1, 1, 0), /* VPU */
         [MSTP100] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 0, 0), /* LCDC0 */
         [MSTP223] = MSTP(&div6_clks[DIV6_SPU], SMSTPCR2, 23, 0), /* SPU2 */
+        [MSTP218] = MSTP(&div4_clks[DIV4_HP], SMSTPCR2, 18, 0), /* DMAC1 */
+        [MSTP217] = MSTP(&div4_clks[DIV4_HP], SMSTPCR2, 17, 0), /* DMAC2 */
+        [MSTP216] = MSTP(&div4_clks[DIV4_HP], SMSTPCR2, 16, 0), /* DMAC3 */
         [MSTP207] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 7, 0), /* SCIFA5 */
         [MSTP206] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 6, 0), /* SCIFB */
         [MSTP204] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 4, 0), /* SCIFA0 */
@@ -626,6 +630,9 @@ static struct clk_lookup lookups[] = {
         CLKDEV_DEV_ID("sh_mobile_lcdc_fb.0", &mstp_clks[MSTP100]), /* LCDC0 */
         CLKDEV_DEV_ID("uio_pdrv_genirq.6", &mstp_clks[MSTP223]), /* SPU2DSP0 */
         CLKDEV_DEV_ID("uio_pdrv_genirq.7", &mstp_clks[MSTP223]), /* SPU2DSP1 */
+        CLKDEV_DEV_ID("sh-dma-engine.0", &mstp_clks[MSTP218]), /* DMAC1 */
+        CLKDEV_DEV_ID("sh-dma-engine.1", &mstp_clks[MSTP217]), /* DMAC2 */
+        CLKDEV_DEV_ID("sh-dma-engine.2", &mstp_clks[MSTP216]), /* DMAC3 */
         CLKDEV_DEV_ID("sh-sci.5", &mstp_clks[MSTP207]), /* SCIFA5 */
         CLKDEV_DEV_ID("sh-sci.6", &mstp_clks[MSTP206]), /* SCIFB */
         CLKDEV_DEV_ID("sh-sci.0", &mstp_clks[MSTP204]), /* SCIFA0 */
diff --git a/arch/arm/mach-tegra/board-harmony-power.c b/arch/arm/mach-tegra/board-harmony-power.c
index c84442cabe07..5ad8b2f94f8d 100644
--- a/arch/arm/mach-tegra/board-harmony-power.c
+++ b/arch/arm/mach-tegra/board-harmony-power.c
@@ -24,6 +24,8 @@
 
 #include <mach/irqs.h>
 
+#include "board-harmony.h"
+
 #define PMC_CTRL                0x0
 #define PMC_CTRL_INTR_LOW       (1 << 17)
 
@@ -98,7 +100,7 @@ static struct tps6586x_platform_data tps_platform = {
         .irq_base       = TEGRA_NR_IRQS,
         .num_subdevs    = ARRAY_SIZE(tps_devs),
         .subdevs        = tps_devs,
-        .gpio_base      = TEGRA_NR_GPIOS,
+        .gpio_base      = HARMONY_GPIO_TPS6586X(0),
 };
 
 static struct i2c_board_info __initdata harmony_regulators[] = {
diff --git a/arch/arm/mach-tegra/board-harmony.h b/arch/arm/mach-tegra/board-harmony.h
index 1e57b071f52d..d85142edaf6b 100644
--- a/arch/arm/mach-tegra/board-harmony.h
+++ b/arch/arm/mach-tegra/board-harmony.h
@@ -17,7 +17,8 @@
 #ifndef _MACH_TEGRA_BOARD_HARMONY_H
 #define _MACH_TEGRA_BOARD_HARMONY_H
 
-#define HARMONY_GPIO_WM8903(_x_)        (TEGRA_NR_GPIOS + (_x_))
+#define HARMONY_GPIO_TPS6586X(_x_)      (TEGRA_NR_GPIOS + (_x_))
+#define HARMONY_GPIO_WM8903(_x_)        (HARMONY_GPIO_TPS6586X(4) + (_x_))
 
 #define TEGRA_GPIO_SD2_CD               TEGRA_GPIO_PI5
 #define TEGRA_GPIO_SD2_WP               TEGRA_GPIO_PH1
diff --git a/arch/arm/plat-omap/omap_device.c b/arch/arm/plat-omap/omap_device.c
index a37b8eb65b76..49fc0df0c21f 100644
--- a/arch/arm/plat-omap/omap_device.c
+++ b/arch/arm/plat-omap/omap_device.c
@@ -84,6 +84,7 @@
 #include <linux/io.h>
 #include <linux/clk.h>
 #include <linux/clkdev.h>
+#include <linux/pm_runtime.h>
 
 #include <plat/omap_device.h>
 #include <plat/omap_hwmod.h>
@@ -539,20 +540,34 @@ int omap_early_device_register(struct omap_device *od)
 static int _od_runtime_suspend(struct device *dev)
 {
         struct platform_device *pdev = to_platform_device(dev);
+        int ret;
+
+        ret = pm_generic_runtime_suspend(dev);
+
+        if (!ret)
+                omap_device_idle(pdev);
+
+        return ret;
+}
 
-        return omap_device_idle(pdev);
+static int _od_runtime_idle(struct device *dev)
+{
+        return pm_generic_runtime_idle(dev);
 }
 
 static int _od_runtime_resume(struct device *dev)
 {
         struct platform_device *pdev = to_platform_device(dev);
 
-        return omap_device_enable(pdev);
+        omap_device_enable(pdev);
+
+        return pm_generic_runtime_resume(dev);
 }
 
 static struct dev_power_domain omap_device_power_domain = {
         .ops = {
                 .runtime_suspend = _od_runtime_suspend,
+                .runtime_idle = _od_runtime_idle,
                 .runtime_resume = _od_runtime_resume,
                 USE_PLATFORM_PM_SLEEP_OPS
         }
diff --git a/arch/blackfin/include/asm/bfin_serial.h b/arch/blackfin/include/asm/bfin_serial.h
index 7dbc664eab1e..7fd0ec7b5b0f 100644
--- a/arch/blackfin/include/asm/bfin_serial.h
+++ b/arch/blackfin/include/asm/bfin_serial.h
@@ -184,7 +184,7 @@ struct bfin_uart_regs {
 #undef __BFP
 
 #ifndef port_membase
-# define port_membase(p) (((struct bfin_serial_port *)(p))->port.membase)
+# define port_membase(p) 0
 #endif
 
 #define UART_GET_CHAR(p)      bfin_read16(port_membase(p) + OFFSET_RBR)
@@ -235,10 +235,10 @@ struct bfin_uart_regs {
 #define UART_SET_DLAB(p)      do { UART_PUT_LCR(p, UART_GET_LCR(p) | DLAB); SSYNC(); } while (0)
 
 #ifndef put_lsr_cache
-# define put_lsr_cache(p, v) (((struct bfin_serial_port *)(p))->lsr = (v))
+# define put_lsr_cache(p, v)
 #endif
 #ifndef get_lsr_cache
-# define get_lsr_cache(p)    (((struct bfin_serial_port *)(p))->lsr)
+# define get_lsr_cache(p) 0
 #endif
 
 /* The hardware clears the LSR bits upon read, so we need to cache
diff --git a/arch/blackfin/include/asm/gptimers.h b/arch/blackfin/include/asm/gptimers.h
index c722acdda0d3..38657dac1235 100644
--- a/arch/blackfin/include/asm/gptimers.h
+++ b/arch/blackfin/include/asm/gptimers.h
@@ -193,4 +193,22 @@ uint16_t get_enabled_gptimers(void);
 uint32_t get_gptimer_status(unsigned int group);
 void     set_gptimer_status(unsigned int group, uint32_t value);
 
+/*
+ * All Blackfin system MMRs are padded to 32bits even if the register
+ * itself is only 16bits.  So use a helper macro to streamline this.
+ */
+#define __BFP(m) u16 m; u16 __pad_##m
+
+/*
+ * bfin timer registers layout
+ */
+struct bfin_gptimer_regs {
+        __BFP(config);
+        u32 counter;
+        u32 period;
+        u32 width;
+};
+
+#undef __BFP
+
 #endif
diff --git a/arch/blackfin/include/asm/unistd.h b/arch/blackfin/include/asm/unistd.h
index 6ff9c411b145..0ccba60b9ccf 100644
--- a/arch/blackfin/include/asm/unistd.h
+++ b/arch/blackfin/include/asm/unistd.h
@@ -398,8 +398,9 @@
 #define __NR_clock_adjtime      377
 #define __NR_syncfs             378
 #define __NR_setns              379
+#define __NR_sendmmsg           380
 
-#define __NR_syscall            380
+#define __NR_syscall            381
 #define NR_syscalls             __NR_syscall
 
 /* Old optional stuff no one actually uses */
diff --git a/arch/blackfin/kernel/debug-mmrs.c b/arch/blackfin/kernel/debug-mmrs.c
index 94b1d8a0256a..fce4807ceef9 100644
--- a/arch/blackfin/kernel/debug-mmrs.c
+++ b/arch/blackfin/kernel/debug-mmrs.c
@@ -13,6 +13,7 @@
 
 #include <asm/blackfin.h>
 #include <asm/gpio.h>
+#include <asm/gptimers.h>
 #include <asm/bfin_can.h>
 #include <asm/bfin_dma.h>
 #include <asm/bfin_ppi.h>
@@ -230,8 +231,8 @@ bfin_debug_mmrs_dma(struct dentry *parent, unsigned long base, int num, char mdm
 #define DMA(num)  _DMA(num, DMA##num##_NEXT_DESC_PTR, 0, "")
 #define _MDMA(num, x) \
         do { \
-                _DMA(num, x##DMA_D##num##_CONFIG, 'D', #x); \
-                _DMA(num, x##DMA_S##num##_CONFIG, 'S', #x); \
+                _DMA(num, x##DMA_D##num##_NEXT_DESC_PTR, 'D', #x); \
+                _DMA(num, x##DMA_S##num##_NEXT_DESC_PTR, 'S', #x); \
         } while (0)
 #define MDMA(num) _MDMA(num, M)
 #define IMDMA(num) _MDMA(num, IM)
@@ -264,20 +265,15 @@ bfin_debug_mmrs_eppi(struct dentry *parent, unsigned long base, int num)
 /*
  * General Purpose Timers
  */
-#define GPTIMER_OFF(mmr) (TIMER0_##mmr - TIMER0_CONFIG)
-#define __GPTIMER(name) \
-        do { \
-                strcpy(_buf, #name); \
-                debugfs_create_x16(buf, S_IRUSR|S_IWUSR, parent, (u16 *)(base + GPTIMER_OFF(name))); \
-        } while (0)
+#define __GPTIMER(uname, lname) __REGS(gptimer, #uname, lname)
 static void __init __maybe_unused
 bfin_debug_mmrs_gptimer(struct dentry *parent, unsigned long base, int num)
 {
         char buf[32], *_buf = REGS_STR_PFX(buf, TIMER, num);
-        __GPTIMER(CONFIG);
-        __GPTIMER(COUNTER);
-        __GPTIMER(PERIOD);
-        __GPTIMER(WIDTH);
+        __GPTIMER(CONFIG, config);
+        __GPTIMER(COUNTER, counter);
+        __GPTIMER(PERIOD, period);
+        __GPTIMER(WIDTH, width);
 }
 #define GPTIMER(num) bfin_debug_mmrs_gptimer(parent, TIMER##num##_CONFIG, num)
 
@@ -355,7 +351,7 @@ bfin_debug_mmrs_ppi(struct dentry *parent, unsigned long base, int num)
         __PPI(DELAY, delay);
         __PPI(FRAME, frame);
 }
-#define PPI(num) bfin_debug_mmrs_ppi(parent, PPI##num##_STATUS, num)
+#define PPI(num) bfin_debug_mmrs_ppi(parent, PPI##num##_CONTROL, num)
 
 /*
  * SPI
@@ -1288,15 +1284,15 @@ static int __init bfin_debug_mmrs_init(void)
         D16(VR_CTL);
         D32(CHIPID);    /* it's part of this hardware block */
 
-#if defined(PPI_STATUS) || defined(PPI0_STATUS) || defined(PPI1_STATUS)
+#if defined(PPI_CONTROL) || defined(PPI0_CONTROL) || defined(PPI1_CONTROL)
         parent = debugfs_create_dir("ppi", top);
-# ifdef PPI_STATUS
-        bfin_debug_mmrs_ppi(parent, PPI_STATUS, -1);
+# ifdef PPI_CONTROL
+        bfin_debug_mmrs_ppi(parent, PPI_CONTROL, -1);
 # endif
-# ifdef PPI0_STATUS
+# ifdef PPI0_CONTROL
         PPI(0);
 # endif
-# ifdef PPI1_STATUS
+# ifdef PPI1_CONTROL
         PPI(1);
 # endif
 #endif
@@ -1341,6 +1337,10 @@ static int __init bfin_debug_mmrs_init(void)
         D16(RSI_PID1);
         D16(RSI_PID2);
         D16(RSI_PID3);
+        D16(RSI_PID4);
+        D16(RSI_PID5);
+        D16(RSI_PID6);
+        D16(RSI_PID7);
         D16(RSI_PWR_CONTROL);
         D16(RSI_RD_WAIT_EN);
         D32(RSI_RESPONSE0);
diff --git a/arch/blackfin/lib/strncpy.S b/arch/blackfin/lib/strncpy.S
index f3931d50b4a7..2c07dddac995 100644
--- a/arch/blackfin/lib/strncpy.S
+++ b/arch/blackfin/lib/strncpy.S
@@ -25,7 +25,7 @@
 
 ENTRY(_strncpy)
         CC = R2 == 0;
-        if CC JUMP 4f;
+        if CC JUMP 6f;
 
         P2 = R2 ;       /* size */
         P0 = R0 ;       /* dst*/
diff --git a/arch/blackfin/mach-bf518/include/mach/bfin_serial_5xx.h b/arch/blackfin/mach-bf518/include/mach/bfin_serial_5xx.h
deleted file mode 100644
index f6d924ac0c44..000000000000
--- a/arch/blackfin/mach-bf518/include/mach/bfin_serial_5xx.h
+++ /dev/null
@@ -1,79 +0,0 @@
-/*
- * Copyright 2008-2009 Analog Devices Inc.
- *
- * Licensed under the GPL-2 or later
- */
-
-#include <asm/dma.h>
-#include <asm/portmux.h>
-
-#if defined(CONFIG_BFIN_UART0_CTSRTS) || defined(CONFIG_BFIN_UART1_CTSRTS)
-# define CONFIG_SERIAL_BFIN_CTSRTS
-
-# ifndef CONFIG_UART0_CTS_PIN
-#  define CONFIG_UART0_CTS_PIN -1
-# endif
-
-# ifndef CONFIG_UART0_RTS_PIN
-#  define CONFIG_UART0_RTS_PIN -1
-# endif
-
-# ifndef CONFIG_UART1_CTS_PIN
-#  define CONFIG_UART1_CTS_PIN -1
-# endif
-
-# ifndef CONFIG_UART1_RTS_PIN
-#  define CONFIG_UART1_RTS_PIN -1
-# endif
-#endif
-
-struct bfin_serial_res {
-        unsigned long uart_base_addr;
-        int uart_irq;
-        int uart_status_irq;
-#ifdef CONFIG_SERIAL_BFIN_DMA
-        unsigned int uart_tx_dma_channel;
-        unsigned int uart_rx_dma_channel;
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-        int uart_cts_pin;
-        int uart_rts_pin;
-#endif
-};
-
-struct bfin_serial_res bfin_serial_resource[] = {
-#ifdef CONFIG_SERIAL_BFIN_UART0
-        {
-         0xFFC00400,
-         IRQ_UART0_RX,
-         IRQ_UART0_ERROR,
-#ifdef CONFIG_SERIAL_BFIN_DMA
-         CH_UART0_TX,
-         CH_UART0_RX,
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-         CONFIG_UART0_CTS_PIN,
-         CONFIG_UART0_RTS_PIN,
-#endif
-         },
-#endif
-#ifdef CONFIG_SERIAL_BFIN_UART1
-        {
-         0xFFC02000,
-         IRQ_UART1_RX,
-         IRQ_UART1_ERROR,
-#ifdef CONFIG_SERIAL_BFIN_DMA
-         CH_UART1_TX,
-         CH_UART1_RX,
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-         CONFIG_UART1_CTS_PIN,
-         CONFIG_UART1_RTS_PIN,
-#endif
-         },
-#endif
-};
-
-#define DRIVER_NAME "bfin-uart"
-
-#include <asm/bfin_serial.h>
diff --git a/arch/blackfin/mach-bf518/include/mach/defBF514.h b/arch/blackfin/mach-bf518/include/mach/defBF514.h
index 98a51c479290..cfab428e577c 100644
--- a/arch/blackfin/mach-bf518/include/mach/defBF514.h
+++ b/arch/blackfin/mach-bf518/include/mach/defBF514.h
@@ -36,13 +36,13 @@
 #define RSI_EMASK                      0xFFC038C4 /* RSI Exception Mask Register */
 #define RSI_CONFIG                     0xFFC038C8 /* RSI Configuration Register */
 #define RSI_RD_WAIT_EN                 0xFFC038CC /* RSI Read Wait Enable Register */
-#define RSI_PID0                       0xFFC03FE0 /* RSI Peripheral ID Register 0 */
-#define RSI_PID1                       0xFFC03FE4 /* RSI Peripheral ID Register 1 */
-#define RSI_PID2                       0xFFC03FE8 /* RSI Peripheral ID Register 2 */
-#define RSI_PID3                       0xFFC03FEC /* RSI Peripheral ID Register 3 */
-#define RSI_PID4                       0xFFC03FF0 /* RSI Peripheral ID Register 4 */
-#define RSI_PID5                       0xFFC03FF4 /* RSI Peripheral ID Register 5 */
-#define RSI_PID6                       0xFFC03FF8 /* RSI Peripheral ID Register 6 */
-#define RSI_PID7                       0xFFC03FFC /* RSI Peripheral ID Register 7 */
+#define RSI_PID0                       0xFFC038D0 /* RSI Peripheral ID Register 0 */
+#define RSI_PID1                       0xFFC038D4 /* RSI Peripheral ID Register 1 */
+#define RSI_PID2                       0xFFC038D8 /* RSI Peripheral ID Register 2 */
+#define RSI_PID3                       0xFFC038DC /* RSI Peripheral ID Register 3 */
+#define RSI_PID4                       0xFFC038E0 /* RSI Peripheral ID Register 0 */
+#define RSI_PID5                       0xFFC038E4 /* RSI Peripheral ID Register 1 */
+#define RSI_PID6                       0xFFC038E8 /* RSI Peripheral ID Register 2 */
+#define RSI_PID7                       0xFFC038EC /* RSI Peripheral ID Register 3 */
 
 #endif /* _DEF_BF514_H */
diff --git a/arch/blackfin/mach-bf527/include/mach/bfin_serial_5xx.h b/arch/blackfin/mach-bf527/include/mach/bfin_serial_5xx.h
deleted file mode 100644
index 960e08919def..000000000000
--- a/arch/blackfin/mach-bf527/include/mach/bfin_serial_5xx.h
+++ /dev/null
@@ -1,79 +0,0 @@
-/*
- * Copyright 2007-2009 Analog Devices Inc.
- *
- * Licensed under the GPL-2 or later
- */
-
-#include <asm/dma.h>
-#include <asm/portmux.h>
-
-#if defined(CONFIG_BFIN_UART0_CTSRTS) || defined(CONFIG_BFIN_UART1_CTSRTS)
-# define CONFIG_SERIAL_BFIN_CTSRTS
-
-# ifndef CONFIG_UART0_CTS_PIN
-#  define CONFIG_UART0_CTS_PIN -1
-# endif
-
-# ifndef CONFIG_UART0_RTS_PIN
-#  define CONFIG_UART0_RTS_PIN -1
-# endif
-
-# ifndef CONFIG_UART1_CTS_PIN
-#  define CONFIG_UART1_CTS_PIN -1
-# endif
-
-# ifndef CONFIG_UART1_RTS_PIN
-#  define CONFIG_UART1_RTS_PIN -1
-# endif
-#endif
-
-struct bfin_serial_res {
-        unsigned long uart_base_addr;
-        int uart_irq;
-        int uart_status_irq;
-#ifdef CONFIG_SERIAL_BFIN_DMA
-        unsigned int uart_tx_dma_channel;
-        unsigned int uart_rx_dma_channel;
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-        int uart_cts_pin;
-        int uart_rts_pin;
-#endif
-};
-
-struct bfin_serial_res bfin_serial_resource[] = {
-#ifdef CONFIG_SERIAL_BFIN_UART0
-        {
-         0xFFC00400,
-         IRQ_UART0_RX,
-         IRQ_UART0_ERROR,
-#ifdef CONFIG_SERIAL_BFIN_DMA
-         CH_UART0_TX,
-         CH_UART0_RX,
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-         CONFIG_UART0_CTS_PIN,
-         CONFIG_UART0_RTS_PIN,
-#endif
-         },
-#endif
-#ifdef CONFIG_SERIAL_BFIN_UART1
-        {
-         0xFFC02000,
-         IRQ_UART1_RX,
-         IRQ_UART1_ERROR,
-#ifdef CONFIG_SERIAL_BFIN_DMA
-         CH_UART1_TX,
-         CH_UART1_RX,
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-         CONFIG_UART1_CTS_PIN,
-         CONFIG_UART1_RTS_PIN,
-#endif
-         },
-#endif
-};
-
-#define DRIVER_NAME "bfin-uart"
-
-#include <asm/bfin_serial.h>
diff --git a/arch/blackfin/mach-bf527/include/mach/defBF525.h b/arch/blackfin/mach-bf527/include/mach/defBF525.h
index cc383adfdffa..aab80bb1a683 100644
--- a/arch/blackfin/mach-bf527/include/mach/defBF525.h
+++ b/arch/blackfin/mach-bf527/include/mach/defBF525.h
@@ -185,8 +185,8 @@
 #define                USB_EP_NI7_TXTYPE  0xffc03bd4   /* Sets the transaction protocol and peripheral endpoint number for the Host Tx endpoint7 */
 #define            USB_EP_NI7_TXINTERVAL  0xffc03bd8   /* Sets the NAK response timeout on Endpoint7 */
 #define                USB_EP_NI7_RXTYPE  0xffc03bdc   /* Sets the transaction protocol and peripheral endpoint number for the Host Rx endpoint7 */
-#define            USB_EP_NI7_RXINTERVAL  0xffc03bf0   /* Sets the polling interval for Interrupt/Isochronous transfers or the NAK response timeout on Bulk transfers for Host Rx endpoint7 */
-#define               USB_EP_NI7_TXCOUNT  0xffc03bf8   /* Number of bytes to be written to the endpoint7 Tx FIFO */
+#define            USB_EP_NI7_RXINTERVAL  0xffc03be0   /* Sets the polling interval for Interrupt/Isochronous transfers or the NAK response timeout on Bulk transfers for Host Rx endpoint7 */
+#define               USB_EP_NI7_TXCOUNT  0xffc03be8   /* Number of bytes to be written to the endpoint7 Tx FIFO */
 
 #define                USB_DMA_INTERRUPT  0xffc03c00   /* Indicates pending interrupts for the DMA channels */
 
diff --git a/arch/blackfin/mach-bf533/include/mach/bfin_serial_5xx.h b/arch/blackfin/mach-bf533/include/mach/bfin_serial_5xx.h
deleted file mode 100644
index 45dcaa4f3e41..000000000000
--- a/arch/blackfin/mach-bf533/include/mach/bfin_serial_5xx.h
+++ /dev/null
@@ -1,52 +0,0 @@
-/*
- * Copyright 2006-2009 Analog Devices Inc.
- *
- * Licensed under the GPL-2 or later
- */
-
-#include <asm/dma.h>
-#include <asm/portmux.h>
-
-#ifdef CONFIG_BFIN_UART0_CTSRTS
-# define CONFIG_SERIAL_BFIN_CTSRTS
-# ifndef CONFIG_UART0_CTS_PIN
-#  define CONFIG_UART0_CTS_PIN -1
-# endif
-# ifndef CONFIG_UART0_RTS_PIN
-#  define CONFIG_UART0_RTS_PIN -1
-# endif
-#endif
-
-struct bfin_serial_res {
-        unsigned long   uart_base_addr;
-        int             uart_irq;
-        int             uart_status_irq;
-#ifdef CONFIG_SERIAL_BFIN_DMA
-        unsigned int    uart_tx_dma_channel;
-        unsigned int    uart_rx_dma_channel;
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-        int             uart_cts_pin;
-        int             uart_rts_pin;
-#endif
-};
-
-struct bfin_serial_res bfin_serial_resource[] = {
-        {
-        0xFFC00400,
-        IRQ_UART0_RX,
-        IRQ_UART0_ERROR,
-#ifdef CONFIG_SERIAL_BFIN_DMA
-        CH_UART0_TX,
-        CH_UART0_RX,
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-        CONFIG_UART0_CTS_PIN,
-        CONFIG_UART0_RTS_PIN,
-#endif
-        }
-};
-
-#define DRIVER_NAME "bfin-uart"
-
-#include <asm/bfin_serial.h>
diff --git a/arch/blackfin/mach-bf537/include/mach/bfin_serial_5xx.h b/arch/blackfin/mach-bf537/include/mach/bfin_serial_5xx.h
deleted file mode 100644
index 3e955dba8951..000000000000
--- a/arch/blackfin/mach-bf537/include/mach/bfin_serial_5xx.h
+++ /dev/null
@@ -1,79 +0,0 @@
-/*
- * Copyright 2006-2009 Analog Devices Inc.
- *
- * Licensed under the GPL-2 or later
- */
-
-#include <asm/dma.h>
-#include <asm/portmux.h>
-
-#if defined(CONFIG_BFIN_UART0_CTSRTS) || defined(CONFIG_BFIN_UART1_CTSRTS)
-# define CONFIG_SERIAL_BFIN_CTSRTS
-
-# ifndef CONFIG_UART0_CTS_PIN
-#  define CONFIG_UART0_CTS_PIN -1
-# endif
-
-# ifndef CONFIG_UART0_RTS_PIN
-#  define CONFIG_UART0_RTS_PIN -1
-# endif
-
-# ifndef CONFIG_UART1_CTS_PIN
-#  define CONFIG_UART1_CTS_PIN -1
-# endif
-
-# ifndef CONFIG_UART1_RTS_PIN
-#  define CONFIG_UART1_RTS_PIN -1
-# endif
-#endif
-
-struct bfin_serial_res {
-        unsigned long   uart_base_addr;
-        int             uart_irq;
-        int             uart_status_irq;
-#ifdef CONFIG_SERIAL_BFIN_DMA
-        unsigned int    uart_tx_dma_channel;
-        unsigned int    uart_rx_dma_channel;
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-        int     uart_cts_pin;
-        int     uart_rts_pin;
-#endif
-};
-
-struct bfin_serial_res bfin_serial_resource[] = {
-#ifdef CONFIG_SERIAL_BFIN_UART0
-        {
-        0xFFC00400,
-        IRQ_UART0_RX,
-        IRQ_UART0_ERROR,
-#ifdef CONFIG_SERIAL_BFIN_DMA
-        CH_UART0_TX,
-        CH_UART0_RX,
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-        CONFIG_UART0_CTS_PIN,
-        CONFIG_UART0_RTS_PIN,
-#endif
-        },
-#endif
-#ifdef CONFIG_SERIAL_BFIN_UART1
-        {
-        0xFFC02000,
-        IRQ_UART1_RX,
-        IRQ_UART1_ERROR,
-#ifdef CONFIG_SERIAL_BFIN_DMA
-        CH_UART1_TX,
-        CH_UART1_RX,
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-        CONFIG_UART1_CTS_PIN,
-        CONFIG_UART1_RTS_PIN,
-#endif
-        },
-#endif
-};
-
-#define DRIVER_NAME "bfin-uart"
-
-#include <asm/bfin_serial.h>
diff --git a/arch/blackfin/mach-bf538/include/mach/bfin_serial_5xx.h b/arch/blackfin/mach-bf538/include/mach/bfin_serial_5xx.h
deleted file mode 100644
index beb502e9cb33..000000000000
--- a/arch/blackfin/mach-bf538/include/mach/bfin_serial_5xx.h
+++ /dev/null
@@ -1,93 +0,0 @@
-/*
- * Copyright 2008-2009 Analog Devices Inc.
- *
- * Licensed under the GPL-2 or later.
- */
-
-#include <asm/dma.h>
-#include <asm/portmux.h>
-
-#if defined(CONFIG_BFIN_UART0_CTSRTS) || defined(CONFIG_BFIN_UART1_CTSRTS)
-# define CONFIG_SERIAL_BFIN_CTSRTS
-
-# ifndef CONFIG_UART0_CTS_PIN
-#  define CONFIG_UART0_CTS_PIN -1
-# endif
-
-# ifndef CONFIG_UART0_RTS_PIN
-#  define CONFIG_UART0_RTS_PIN -1
-# endif
-
-# ifndef CONFIG_UART1_CTS_PIN
-#  define CONFIG_UART1_CTS_PIN -1
-# endif
-
-# ifndef CONFIG_UART1_RTS_PIN
-#  define CONFIG_UART1_RTS_PIN -1
-# endif
-#endif
-
-struct bfin_serial_res {
-        unsigned long   uart_base_addr;
-        int             uart_irq;
-        int             uart_status_irq;
-#ifdef CONFIG_SERIAL_BFIN_DMA
-        unsigned int    uart_tx_dma_channel;
-        unsigned int    uart_rx_dma_channel;
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-        int     uart_cts_pin;
-        int     uart_rts_pin;
-#endif
-};
-
-struct bfin_serial_res bfin_serial_resource[] = {
-#ifdef CONFIG_SERIAL_BFIN_UART0
-        {
-        0xFFC00400,
-        IRQ_UART0_RX,
-        IRQ_UART0_ERROR,
-#ifdef CONFIG_SERIAL_BFIN_DMA
-        CH_UART0_TX,
-        CH_UART0_RX,
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-        CONFIG_UART0_CTS_PIN,
-        CONFIG_UART0_RTS_PIN,
-#endif
-        },
-#endif
-#ifdef CONFIG_SERIAL_BFIN_UART1
-        {
-        0xFFC02000,
-        IRQ_UART1_RX,
-        IRQ_UART1_ERROR,
-#ifdef CONFIG_SERIAL_BFIN_DMA
-        CH_UART1_TX,
-        CH_UART1_RX,
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-        CONFIG_UART1_CTS_PIN,
-        CONFIG_UART1_RTS_PIN,
-#endif
-        },
-#endif
-#ifdef CONFIG_SERIAL_BFIN_UART2
-        {
-        0xFFC02100,
-        IRQ_UART2_RX,
-#ifdef CONFIG_SERIAL_BFIN_DMA
-        CH_UART2_TX,
-        CH_UART2_RX,
-#endif
-#ifdef CONFIG_BFIN_UART2_CTSRTS
-        CONFIG_UART2_CTS_PIN,
-        CONFIG_UART2_RTS_PIN,
-#endif
-        },
-#endif
-};
-
-#define DRIVER_NAME "bfin-uart"
-
-#include <asm/bfin_serial.h>
diff --git a/arch/blackfin/mach-bf548/include/mach/bfin_serial_5xx.h b/arch/blackfin/mach-bf548/include/mach/bfin_serial_5xx.h
deleted file mode 100644
index 0d94edaaaa2e..000000000000
--- a/arch/blackfin/mach-bf548/include/mach/bfin_serial_5xx.h
+++ /dev/null
@@ -1,94 +0,0 @@
-/*
- * Copyright 2007-2009 Analog Devices Inc.
- *
- * Licensed under the GPL-2 or later.
- */
-
-#include <asm/dma.h>
-#include <asm/portmux.h>
-
-#if defined(CONFIG_BFIN_UART0_CTSRTS) || defined(CONFIG_BFIN_UART1_CTSRTS) || \
-        defined(CONFIG_BFIN_UART2_CTSRTS) || defined(CONFIG_BFIN_UART3_CTSRTS)
-# define CONFIG_SERIAL_BFIN_HARD_CTSRTS
-#endif
-
-struct bfin_serial_res {
-        unsigned long   uart_base_addr;
-        int             uart_irq;
-        int             uart_status_irq;
-#ifdef CONFIG_SERIAL_BFIN_DMA
-        unsigned int    uart_tx_dma_channel;
-        unsigned int    uart_rx_dma_channel;
-#endif
-#ifdef CONFIG_SERIAL_BFIN_HARD_CTSRTS
-        int             uart_cts_pin;
-        int             uart_rts_pin;
-#endif
-};
-
-struct bfin_serial_res bfin_serial_resource[] = {
-#ifdef CONFIG_SERIAL_BFIN_UART0
-        {
-        0xFFC00400,
-        IRQ_UART0_RX,
-        IRQ_UART0_ERROR,
-#ifdef CONFIG_SERIAL_BFIN_DMA
-        CH_UART0_TX,
-        CH_UART0_RX,
-#endif
-#ifdef CONFIG_SERIAL_BFIN_HARD_CTSRTS
-        0,
-        0,
-#endif
-        },
-#endif
-#ifdef CONFIG_SERIAL_BFIN_UART1
-        {
-        0xFFC02000,
-        IRQ_UART1_RX,
-        IRQ_UART1_ERROR,
-#ifdef CONFIG_SERIAL_BFIN_DMA
-        CH_UART1_TX,
-        CH_UART1_RX,
-#endif
-#ifdef CONFIG_SERIAL_BFIN_HARD_CTSRTS
-        GPIO_PE10,
-        GPIO_PE9,
-#endif
-        },
-#endif
-#ifdef CONFIG_SERIAL_BFIN_UART2
-        {
-        0xFFC02100,
-        IRQ_UART2_RX,
-        IRQ_UART2_ERROR,
-#ifdef CONFIG_SERIAL_BFIN_DMA
-        CH_UART2_TX,
-        CH_UART2_RX,
-#endif
-#ifdef CONFIG_SERIAL_BFIN_HARD_CTSRTS
-        0,
-        0,
-#endif
-        },
-#endif
-#ifdef CONFIG_SERIAL_BFIN_UART3
-        {
-        0xFFC03100,
-        IRQ_UART3_RX,
-        IRQ_UART3_ERROR,
-#ifdef CONFIG_SERIAL_BFIN_DMA
-        CH_UART3_TX,
-        CH_UART3_RX,
-#endif
-#ifdef CONFIG_SERIAL_BFIN_HARD_CTSRTS
-        GPIO_PB3,
-        GPIO_PB2,
-#endif
-        },
-#endif
-};
-
-#define DRIVER_NAME "bfin-uart"
-
-#include <asm/bfin_serial.h>
diff --git a/arch/blackfin/mach-bf548/include/mach/defBF547.h b/arch/blackfin/mach-bf548/include/mach/defBF547.h
index 1cbba115f96f..1fa41ec03f31 100644
--- a/arch/blackfin/mach-bf548/include/mach/defBF547.h
+++ b/arch/blackfin/mach-bf548/include/mach/defBF547.h
@@ -271,10 +271,10 @@
 #define            USB_EP_NI0_TXINTERVAL  0xffc03e18   /* Sets the NAK response timeout on Endpoint 0 */
 #define                USB_EP_NI0_RXTYPE  0xffc03e1c   /* Sets the transaction protocol and peripheral endpoint number for the Host Rx endpoint0 */
 #define            USB_EP_NI0_RXINTERVAL  0xffc03e20   /* Sets the polling interval for Interrupt/Isochronous transfers or the NAK response timeout on Bulk transfers for Host Rx endpoint0 */
+#define               USB_EP_NI0_TXCOUNT  0xffc03e28   /* Number of bytes to be written to the endpoint0 Tx FIFO */
 
 /* USB Endpoint 1 Control Registers */
 
-#define               USB_EP_NI0_TXCOUNT  0xffc03e28   /* Number of bytes to be written to the endpoint0 Tx FIFO */
 #define                USB_EP_NI1_TXMAXP  0xffc03e40   /* Maximum packet size for Host Tx endpoint1 */
 #define                 USB_EP_NI1_TXCSR  0xffc03e44   /* Control Status register for endpoint1 */
 #define                USB_EP_NI1_RXMAXP  0xffc03e48   /* Maximum packet size for Host Rx endpoint1 */
@@ -284,10 +284,10 @@
 #define            USB_EP_NI1_TXINTERVAL  0xffc03e58   /* Sets the NAK response timeout on Endpoint1 */
 #define                USB_EP_NI1_RXTYPE  0xffc03e5c   /* Sets the transaction protocol and peripheral endpoint number for the Host Rx endpoint1 */
 #define            USB_EP_NI1_RXINTERVAL  0xffc03e60   /* Sets the polling interval for Interrupt/Isochronous transfers or the NAK response timeout on Bulk transfers for Host Rx endpoint1 */
+#define               USB_EP_NI1_TXCOUNT  0xffc03e68   /* Number of bytes to be written to the+H102 endpoint1 Tx FIFO */
 
 /* USB Endpoint 2 Control Registers */
 
-#define               USB_EP_NI1_TXCOUNT  0xffc03e68   /* Number of bytes to be written to the+H102 endpoint1 Tx FIFO */
 #define                USB_EP_NI2_TXMAXP  0xffc03e80   /* Maximum packet size for Host Tx endpoint2 */
 #define                 USB_EP_NI2_TXCSR  0xffc03e84   /* Control Status register for endpoint2 */
 #define                USB_EP_NI2_RXMAXP  0xffc03e88   /* Maximum packet size for Host Rx endpoint2 */
@@ -297,10 +297,10 @@
 #define            USB_EP_NI2_TXINTERVAL  0xffc03e98   /* Sets the NAK response timeout on Endpoint2 */
 #define                USB_EP_NI2_RXTYPE  0xffc03e9c   /* Sets the transaction protocol and peripheral endpoint number for the Host Rx endpoint2 */
 #define            USB_EP_NI2_RXINTERVAL  0xffc03ea0   /* Sets the polling interval for Interrupt/Isochronous transfers or the NAK response timeout on Bulk transfers for Host Rx endpoint2 */
+#define               USB_EP_NI2_TXCOUNT  0xffc03ea8   /* Number of bytes to be written to the endpoint2 Tx FIFO */
 
 /* USB Endpoint 3 Control Registers */
 
-#define               USB_EP_NI2_TXCOUNT  0xffc03ea8   /* Number of bytes to be written to the endpoint2 Tx FIFO */
 #define                USB_EP_NI3_TXMAXP  0xffc03ec0   /* Maximum packet size for Host Tx endpoint3 */
 #define                 USB_EP_NI3_TXCSR  0xffc03ec4   /* Control Status register for endpoint3 */
 #define                USB_EP_NI3_RXMAXP  0xffc03ec8   /* Maximum packet size for Host Rx endpoint3 */
@@ -310,10 +310,10 @@
 #define            USB_EP_NI3_TXINTERVAL  0xffc03ed8   /* Sets the NAK response timeout on Endpoint3 */
 #define                USB_EP_NI3_RXTYPE  0xffc03edc   /* Sets the transaction protocol and peripheral endpoint number for the Host Rx endpoint3 */
 #define            USB_EP_NI3_RXINTERVAL  0xffc03ee0   /* Sets the polling interval for Interrupt/Isochronous transfers or the NAK response timeout on Bulk transfers for Host Rx endpoint3 */
+#define               USB_EP_NI3_TXCOUNT  0xffc03ee8   /* Number of bytes to be written to the H124endpoint3 Tx FIFO */
 
 /* USB Endpoint 4 Control Registers */
 
-#define               USB_EP_NI3_TXCOUNT  0xffc03ee8   /* Number of bytes to be written to the H124endpoint3 Tx FIFO */
 #define                USB_EP_NI4_TXMAXP  0xffc03f00   /* Maximum packet size for Host Tx endpoint4 */
 #define                 USB_EP_NI4_TXCSR  0xffc03f04   /* Control Status register for endpoint4 */
 #define                USB_EP_NI4_RXMAXP  0xffc03f08   /* Maximum packet size for Host Rx endpoint4 */
@@ -323,10 +323,10 @@
 #define            USB_EP_NI4_TXINTERVAL  0xffc03f18   /* Sets the NAK response timeout on Endpoint4 */
 #define                USB_EP_NI4_RXTYPE  0xffc03f1c   /* Sets the transaction protocol and peripheral endpoint number for the Host Rx endpoint4 */
 #define            USB_EP_NI4_RXINTERVAL  0xffc03f20   /* Sets the polling interval for Interrupt/Isochronous transfers or the NAK response timeout on Bulk transfers for Host Rx endpoint4 */
+#define               USB_EP_NI4_TXCOUNT  0xffc03f28   /* Number of bytes to be written to the endpoint4 Tx FIFO */
 
 /* USB Endpoint 5 Control Registers */
 
-#define               USB_EP_NI4_TXCOUNT  0xffc03f28   /* Number of bytes to be written to the endpoint4 Tx FIFO */
 #define                USB_EP_NI5_TXMAXP  0xffc03f40   /* Maximum packet size for Host Tx endpoint5 */
 #define                 USB_EP_NI5_TXCSR  0xffc03f44   /* Control Status register for endpoint5 */
 #define                USB_EP_NI5_RXMAXP  0xffc03f48   /* Maximum packet size for Host Rx endpoint5 */
@@ -336,10 +336,10 @@
 #define            USB_EP_NI5_TXINTERVAL  0xffc03f58   /* Sets the NAK response timeout on Endpoint5 */
 #define                USB_EP_NI5_RXTYPE  0xffc03f5c   /* Sets the transaction protocol and peripheral endpoint number for the Host Rx endpoint5 */
 #define            USB_EP_NI5_RXINTERVAL  0xffc03f60   /* Sets the polling interval for Interrupt/Isochronous transfers or the NAK response timeout on Bulk transfers for Host Rx endpoint5 */
+#define               USB_EP_NI5_TXCOUNT  0xffc03f68   /* Number of bytes to be written to the H145endpoint5 Tx FIFO */
 
 /* USB Endpoint 6 Control Registers */
 
-#define               USB_EP_NI5_TXCOUNT  0xffc03f68   /* Number of bytes to be written to the H145endpoint5 Tx FIFO */
 #define                USB_EP_NI6_TXMAXP  0xffc03f80   /* Maximum packet size for Host Tx endpoint6 */
 #define                 USB_EP_NI6_TXCSR  0xffc03f84   /* Control Status register for endpoint6 */
 #define                USB_EP_NI6_RXMAXP  0xffc03f88   /* Maximum packet size for Host Rx endpoint6 */
@@ -349,10 +349,10 @@
 #define            USB_EP_NI6_TXINTERVAL  0xffc03f98   /* Sets the NAK response timeout on Endpoint6 */
 #define                USB_EP_NI6_RXTYPE  0xffc03f9c   /* Sets the transaction protocol and peripheral endpoint number for the Host Rx endpoint6 */
 #define            USB_EP_NI6_RXINTERVAL  0xffc03fa0   /* Sets the polling interval for Interrupt/Isochronous transfers or the NAK response timeout on Bulk transfers for Host Rx endpoint6 */
+#define               USB_EP_NI6_TXCOUNT  0xffc03fa8   /* Number of bytes to be written to the endpoint6 Tx FIFO */
 
 /* USB Endpoint 7 Control Registers */
 
-#define               USB_EP_NI6_TXCOUNT  0xffc03fa8   /* Number of bytes to be written to the endpoint6 Tx FIFO */
 #define                USB_EP_NI7_TXMAXP  0xffc03fc0   /* Maximum packet size for Host Tx endpoint7 */
 #define                 USB_EP_NI7_TXCSR  0xffc03fc4   /* Control Status register for endpoint7 */
 #define                USB_EP_NI7_RXMAXP  0xffc03fc8   /* Maximum packet size for Host Rx endpoint7 */
@@ -361,8 +361,9 @@
 #define                USB_EP_NI7_TXTYPE  0xffc03fd4   /* Sets the transaction protocol and peripheral endpoint number for the Host Tx endpoint7 */
 #define            USB_EP_NI7_TXINTERVAL  0xffc03fd8   /* Sets the NAK response timeout on Endpoint7 */
 #define                USB_EP_NI7_RXTYPE  0xffc03fdc   /* Sets the transaction protocol and peripheral endpoint number for the Host Rx endpoint7 */
-#define            USB_EP_NI7_RXINTERVAL  0xffc03ff0   /* Sets the polling interval for Interrupt/Isochronous transfers or the NAK response timeout on Bulk transfers for Host Rx endpoint7 */
-#define               USB_EP_NI7_TXCOUNT  0xffc03ff8   /* Number of bytes to be written to the endpoint7 Tx FIFO */
+#define            USB_EP_NI7_RXINTERVAL  0xffc03fe0   /* Sets the polling interval for Interrupt/Isochronous transfers or the NAK response timeout on Bulk transfers for Host Rx endpoint7 */
+#define               USB_EP_NI7_TXCOUNT  0xffc03fe8   /* Number of bytes to be written to the endpoint7 Tx FIFO */
+
 #define                USB_DMA_INTERRUPT  0xffc04000   /* Indicates pending interrupts for the DMA channels */
 
 /* USB Channel 0 Config Registers */
diff --git a/arch/blackfin/mach-bf561/include/mach/bfin_serial_5xx.h b/arch/blackfin/mach-bf561/include/mach/bfin_serial_5xx.h
deleted file mode 100644
index 3a6947456cf1..000000000000
--- a/arch/blackfin/mach-bf561/include/mach/bfin_serial_5xx.h
+++ /dev/null
@@ -1,52 +0,0 @@
-/*
- * Copyright 2006-2009 Analog Devices Inc.
- *
- * Licensed under the GPL-2 or later.
- */
-
-#include <asm/dma.h>
-#include <asm/portmux.h>
-
-#ifdef CONFIG_BFIN_UART0_CTSRTS
-# define CONFIG_SERIAL_BFIN_CTSRTS
-# ifndef CONFIG_UART0_CTS_PIN
-#  define CONFIG_UART0_CTS_PIN -1
-# endif
-# ifndef CONFIG_UART0_RTS_PIN
-#  define CONFIG_UART0_RTS_PIN -1
-# endif
-#endif
-
-struct bfin_serial_res {
-        unsigned long   uart_base_addr;
-        int             uart_irq;
-        int             uart_status_irq;
-#ifdef CONFIG_SERIAL_BFIN_DMA
-        unsigned int    uart_tx_dma_channel;
-        unsigned int    uart_rx_dma_channel;
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-        int             uart_cts_pin;
-        int             uart_rts_pin;
-#endif
-};
-
-struct bfin_serial_res bfin_serial_resource[] = {
-        {
-        0xFFC00400,
-        IRQ_UART_RX,
-        IRQ_UART_ERROR,
-#ifdef CONFIG_SERIAL_BFIN_DMA
-        CH_UART_TX,
-        CH_UART_RX,
-#endif
-#ifdef CONFIG_SERIAL_BFIN_CTSRTS
-        CONFIG_UART0_CTS_PIN,
-        CONFIG_UART0_RTS_PIN,
-#endif
-        }
-};
-
-#define DRIVER_NAME "bfin-uart"
-
-#include <asm/bfin_serial.h>
diff --git a/arch/blackfin/mach-common/entry.S b/arch/blackfin/mach-common/entry.S
index dda11ef06be5..225d311c9701 100644
--- a/arch/blackfin/mach-common/entry.S
+++ b/arch/blackfin/mach-common/entry.S
@@ -1754,6 +1754,7 @@ ENTRY(_sys_call_table)
         .long _sys_clock_adjtime
         .long _sys_syncfs
         .long _sys_setns
+        .long _sys_sendmmsg             /* 380 */
 
         .rept NR_syscalls-(.-_sys_call_table)/4
         .long _sys_ni_syscall
diff --git a/arch/blackfin/mm/maccess.c b/arch/blackfin/mm/maccess.c
index b71cebc1f8a3..e2532114c5fd 100644
--- a/arch/blackfin/mm/maccess.c
+++ b/arch/blackfin/mm/maccess.c
@@ -16,7 +16,7 @@ static int validate_memory_access_address(unsigned long addr, int size)
         return bfin_mem_access_type(addr, size);
 }
 
-long probe_kernel_read(void *dst, void *src, size_t size)
+long probe_kernel_read(void *dst, const void *src, size_t size)
 {
         unsigned long lsrc = (unsigned long)src;
         int mem_type;
@@ -55,7 +55,7 @@ long probe_kernel_read(void *dst, void *src, size_t size)
         return -EFAULT;
 }
 
-long probe_kernel_write(void *dst, void *src, size_t size)
+long probe_kernel_write(void *dst, const void *src, size_t size)
 {
         unsigned long ldst = (unsigned long)dst;
         int mem_type;
diff --git a/arch/ia64/include/asm/unistd.h b/arch/ia64/include/asm/unistd.h
index 1cf0f496f744..7c928da35b17 100644
--- a/arch/ia64/include/asm/unistd.h
+++ b/arch/ia64/include/asm/unistd.h
@@ -320,11 +320,12 @@
 #define __NR_clock_adjtime              1328
 #define __NR_syncfs                     1329
 #define __NR_setns                      1330
+#define __NR_sendmmsg                   1331
 
 #ifdef __KERNEL__
 
 
-#define NR_syscalls                     307 /* length of syscall table */
+#define NR_syscalls                     308 /* length of syscall table */
 
 /*
  * The following defines stop scripts/checksyscalls.sh from complaining about
diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index 9ca80193cd4e..97dd2abdeb1a 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -1776,6 +1776,7 @@ sys_call_table:
         data8 sys_clock_adjtime
         data8 sys_syncfs
         data8 sys_setns                         // 1330
+        data8 sys_sendmmsg
 
         .org sys_call_table + 8*NR_syscalls     // guard against failures to increase NR_syscalls
 #endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */
diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c
index 9089b0421191..7667db448aa7 100644
--- a/arch/powerpc/platforms/powermac/pic.c
+++ b/arch/powerpc/platforms/powermac/pic.c
@@ -715,7 +715,8 @@ static struct syscore_ops pmacpic_syscore_ops = {
 
 static int __init init_pmacpic_syscore(void)
 {
-        register_syscore_ops(&pmacpic_syscore_ops);
+        if (pmac_irq_hw[0])
+                register_syscore_ops(&pmacpic_syscore_ops);
         return 0;
 }
 
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index c4773a2ef3d3..e4efacfe1b63 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -577,16 +577,16 @@ static inline void pgste_set_unlock(pte_t *ptep, pgste_t pgste)
 static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste)
 {
 #ifdef CONFIG_PGSTE
-        unsigned long pfn, bits;
+        unsigned long address, bits;
         unsigned char skey;
 
-        pfn = pte_val(*ptep) >> PAGE_SHIFT;
-        skey = page_get_storage_key(pfn);
+        address = pte_val(*ptep) & PAGE_MASK;
+        skey = page_get_storage_key(address);
         bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED);
         /* Clear page changed & referenced bit in the storage key */
         if (bits) {
                 skey ^= bits;
-                page_set_storage_key(pfn, skey, 1);
+                page_set_storage_key(address, skey, 1);
         }
         /* Transfer page changed & referenced bit to guest bits in pgste */
         pgste_val(pgste) |= bits << 48;         /* RCP_GR_BIT & RCP_GC_BIT */
@@ -628,16 +628,16 @@ static inline pgste_t pgste_update_young(pte_t *ptep, pgste_t pgste)
 static inline void pgste_set_pte(pte_t *ptep, pgste_t pgste)
 {
 #ifdef CONFIG_PGSTE
-        unsigned long pfn;
+        unsigned long address;
         unsigned long okey, nkey;
 
-        pfn = pte_val(*ptep) >> PAGE_SHIFT;
-        okey = nkey = page_get_storage_key(pfn);
+        address = pte_val(*ptep) & PAGE_MASK;
+        okey = nkey = page_get_storage_key(address);
         nkey &= ~(_PAGE_ACC_BITS | _PAGE_FP_BIT);
         /* Set page access key and fetch protection bit from pgste */
         nkey |= (pgste_val(pgste) & (RCP_ACC_BITS | RCP_FP_BIT)) >> 56;
         if (okey != nkey)
-                page_set_storage_key(pfn, nkey, 1);
+                page_set_storage_key(address, nkey, 1);
 #endif
 }
 
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index 71a4b0d34be0..51e5cd9b906a 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -19,7 +19,7 @@
  * using the stura instruction.
  * Returns the number of bytes copied or -EFAULT.
  */
-static long probe_kernel_write_odd(void *dst, void *src, size_t size)
+static long probe_kernel_write_odd(void *dst, const void *src, size_t size)
 {
         unsigned long count, aligned;
         int offset, mask;
@@ -45,7 +45,7 @@ static long probe_kernel_write_odd(void *dst, void *src, size_t size)
         return rc ? rc : count;
 }
 
-long probe_kernel_write(void *dst, void *src, size_t size)
+long probe_kernel_write(void *dst, const void *src, size_t size)
 {
         long copied = 0;
 
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 14c6fae6fe6b..b09763fe5da1 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -71,12 +71,15 @@ static void rcu_table_freelist_callback(struct rcu_head *head)
 
 void rcu_table_freelist_finish(void)
 {
-        struct rcu_table_freelist *batch = __get_cpu_var(rcu_table_freelist);
+        struct rcu_table_freelist **batchp = &get_cpu_var(rcu_table_freelist);
+        struct rcu_table_freelist *batch = *batchp;
 
         if (!batch)
-                return;
+                goto out;
         call_rcu(&batch->rcu, rcu_table_freelist_callback);
-        __get_cpu_var(rcu_table_freelist) = NULL;
+        *batchp = NULL;
+out:
+        put_cpu_var(rcu_table_freelist);
 }
 
 static void smp_sync(void *arg)
@@ -141,20 +144,23 @@ void crst_table_free_rcu(struct mm_struct *mm, unsigned long *table)
 {
         struct rcu_table_freelist *batch;
 
+        preempt_disable();
         if (atomic_read(&mm->mm_users) < 2 &&
             cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) {
                 crst_table_free(mm, table);
-                return;
+                goto out;
         }
         batch = rcu_table_freelist_get(mm);
         if (!batch) {
                 smp_call_function(smp_sync, NULL, 1);
                 crst_table_free(mm, table);
-                return;
+                goto out;
         }
         batch->table[--batch->crst_index] = table;
         if (batch->pgt_index >= batch->crst_index)
                 rcu_table_freelist_finish();
+out:
+        preempt_enable();
 }
 
 #ifdef CONFIG_64BIT
@@ -323,16 +329,17 @@ void page_table_free_rcu(struct mm_struct *mm, unsigned long *table)
         struct page *page;
         unsigned long bits;
 
+        preempt_disable();
         if (atomic_read(&mm->mm_users) < 2 &&
             cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) {
                 page_table_free(mm, table);
-                return;
+                goto out;
         }
         batch = rcu_table_freelist_get(mm);
         if (!batch) {
                 smp_call_function(smp_sync, NULL, 1);
                 page_table_free(mm, table);
-                return;
+                goto out;
         }
         bits = (mm->context.has_pgste) ? 3UL : 1UL;
         bits <<= (__pa(table) & (PAGE_SIZE - 1)) / 256 / sizeof(unsigned long);
@@ -345,6 +352,8 @@ void page_table_free_rcu(struct mm_struct *mm, unsigned long *table)
         batch->table[batch->pgt_index++] = table;
         if (batch->pgt_index >= batch->crst_index)
                 rcu_table_freelist_finish();
+out:
+        preempt_enable();
 }
 
 /*
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 74495a5ea027..f03338c2f088 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -161,7 +161,7 @@ config ARCH_HAS_CPU_IDLE_WAIT
 
 config NO_IOPORT
         def_bool !PCI
-        depends on !SH_CAYMAN && !SH_SH4202_MICRODEV
+        depends on !SH_CAYMAN && !SH_SH4202_MICRODEV && !SH_SHMIN
 
 config IO_TRAPPED
         bool
diff --git a/arch/sh/boards/mach-ap325rxa/setup.c b/arch/sh/boards/mach-ap325rxa/setup.c
index 618bd566cf53..969421f64a15 100644
--- a/arch/sh/boards/mach-ap325rxa/setup.c
+++ b/arch/sh/boards/mach-ap325rxa/setup.c
@@ -359,37 +359,31 @@ static struct soc_camera_link camera_link = {
         .priv           = &camera_info,
 };
 
-static void dummy_release(struct device *dev)
+static struct platform_device *camera_device;
+
+static void ap325rxa_camera_release(struct device *dev)
 {
+        soc_camera_platform_release(&camera_device);
 }
 
-static struct platform_device camera_device = {
-        .name           = "soc_camera_platform",
-        .dev            = {
-                .platform_data  = &camera_info,
-                .release        = dummy_release,
-        },
-};
-
 static int ap325rxa_camera_add(struct soc_camera_link *icl,
                                struct device *dev)
 {
-        if (icl != &camera_link || camera_probe() <= 0)
-                return -ENODEV;
+        int ret = soc_camera_platform_add(icl, dev, &camera_device, &camera_link,
+                                          ap325rxa_camera_release, 0);
+        if (ret < 0)
+                return ret;
 
-        camera_info.dev = dev;
+        ret = camera_probe();
+        if (ret < 0)
+                soc_camera_platform_del(icl, camera_device, &camera_link);
 
-        return platform_device_register(&camera_device);
+        return ret;
 }
 
 static void ap325rxa_camera_del(struct soc_camera_link *icl)
 {
-        if (icl != &camera_link)
-                return;
-
-        platform_device_unregister(&camera_device);
-        memset(&camera_device.dev.kobj, 0,
-               sizeof(camera_device.dev.kobj));
+        soc_camera_platform_del(icl, camera_device, &camera_link);
 }
 #endif /* CONFIG_I2C */
 
diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c
index bb13d0e1b964..3a32741cc0ac 100644
--- a/arch/sh/boards/mach-ecovec24/setup.c
+++ b/arch/sh/boards/mach-ecovec24/setup.c
@@ -885,6 +885,9 @@ static struct platform_device sh_mmcif_device = {
         },
         .num_resources  = ARRAY_SIZE(sh_mmcif_resources),
         .resource       = sh_mmcif_resources,
+        .archdata = {
+                .hwblk_id = HWBLK_MMC,
+        },
 };
 #endif
 
diff --git a/arch/sh/include/asm/pgtable.h b/arch/sh/include/asm/pgtable.h
index db85916b9e95..9210e93a92c3 100644
--- a/arch/sh/include/asm/pgtable.h
+++ b/arch/sh/include/asm/pgtable.h
@@ -18,6 +18,7 @@
 #include <asm/pgtable-2level.h>
 #endif
 #include <asm/page.h>
+#include <asm/mmu.h>
 
 #ifndef __ASSEMBLY__
 #include <asm/addrspace.h>
diff --git a/arch/sh/include/asm/ptrace.h b/arch/sh/include/asm/ptrace.h
index 40725b4a8018..88bd6be168a9 100644
--- a/arch/sh/include/asm/ptrace.h
+++ b/arch/sh/include/asm/ptrace.h
@@ -41,7 +41,9 @@
 
 #define user_mode(regs)                 (((regs)->sr & 0x40000000)==0)
 #define kernel_stack_pointer(_regs)     ((unsigned long)(_regs)->regs[15])
-#define GET_USP(regs) ((regs)->regs[15])
+
+#define GET_FP(regs)    ((regs)->regs[14])
+#define GET_USP(regs)   ((regs)->regs[15])
 
 extern void show_regs(struct pt_regs *);
 
@@ -131,7 +133,7 @@ extern void ptrace_triggered(struct perf_event *bp, int nmi,
 
 static inline unsigned long profile_pc(struct pt_regs *regs)
 {
-        unsigned long pc = instruction_pointer(regs);
+        unsigned long pc = regs->pc;
 
         if (virt_addr_uncached(pc))
                 return CAC_ADDR(pc);
diff --git a/arch/sh/include/asm/tlb.h b/arch/sh/include/asm/tlb.h
index 6c308d8b9a50..ec88bfcdf7ce 100644
--- a/arch/sh/include/asm/tlb.h
+++ b/arch/sh/include/asm/tlb.h
@@ -9,6 +9,7 @@
 #include <linux/pagemap.h>
 
 #ifdef CONFIG_MMU
+#include <linux/swap.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
diff --git a/arch/sh/include/cpu-sh4/cpu/sh7722.h b/arch/sh/include/cpu-sh4/cpu/sh7722.h
index 7a5b8a331b4a..bd0622788d64 100644
--- a/arch/sh/include/cpu-sh4/cpu/sh7722.h
+++ b/arch/sh/include/cpu-sh4/cpu/sh7722.h
@@ -236,6 +236,7 @@ enum {
 };
 
 enum {
+        SHDMA_SLAVE_INVALID,
         SHDMA_SLAVE_SCIF0_TX,
         SHDMA_SLAVE_SCIF0_RX,
         SHDMA_SLAVE_SCIF1_TX,
diff --git a/arch/sh/include/cpu-sh4/cpu/sh7724.h b/arch/sh/include/cpu-sh4/cpu/sh7724.h
index 7eb435999426..3daef8ecbc63 100644
--- a/arch/sh/include/cpu-sh4/cpu/sh7724.h
+++ b/arch/sh/include/cpu-sh4/cpu/sh7724.h
@@ -285,6 +285,7 @@ enum {
 };
 
 enum {
+        SHDMA_SLAVE_INVALID,
         SHDMA_SLAVE_SCIF0_TX,
         SHDMA_SLAVE_SCIF0_RX,
         SHDMA_SLAVE_SCIF1_TX,
diff --git a/arch/sh/include/cpu-sh4/cpu/sh7757.h b/arch/sh/include/cpu-sh4/cpu/sh7757.h
index 05b8196c7753..41f9f8b9db73 100644
--- a/arch/sh/include/cpu-sh4/cpu/sh7757.h
+++ b/arch/sh/include/cpu-sh4/cpu/sh7757.h
@@ -252,6 +252,7 @@ enum {
 };
 
 enum {
+        SHDMA_SLAVE_INVALID,
         SHDMA_SLAVE_SDHI_TX,
         SHDMA_SLAVE_SDHI_RX,
         SHDMA_SLAVE_MMCIF_TX,
diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c
index 762a13984bbd..b473f0c06fbc 100644
--- a/arch/sh/kernel/process_32.c
+++ b/arch/sh/kernel/process_32.c
@@ -21,6 +21,7 @@
 #include <linux/fs.h>
 #include <linux/ftrace.h>
 #include <linux/hw_breakpoint.h>
+#include <linux/prefetch.h>
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
 #include <asm/system.h>
diff --git a/arch/sh/mm/consistent.c b/arch/sh/mm/consistent.c
index 40733a952402..f251b5f27652 100644
--- a/arch/sh/mm/consistent.c
+++ b/arch/sh/mm/consistent.c
@@ -82,7 +82,7 @@ void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
         void *addr;
 
         addr = __in_29bit_mode() ?
-               (void *)P1SEGADDR((unsigned long)vaddr) : vaddr;
+               (void *)CAC_ADDR((unsigned long)vaddr) : vaddr;
 
         switch (direction) {
         case DMA_FROM_DEVICE:           /* invalidate only */
diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig
index e1e50101b3bb..0249b8b4db54 100644
--- a/arch/tile/Kconfig
+++ b/arch/tile/Kconfig
@@ -11,6 +11,7 @@ config TILE
         select GENERIC_IRQ_PROBE
         select GENERIC_PENDING_IRQ if SMP
         select GENERIC_IRQ_SHOW
+        select SYS_HYPERVISOR
 
 # FIXME: investigate whether we need/want these options.
 #       select HAVE_IOREMAP_PROT
diff --git a/arch/tile/include/asm/hardwall.h b/arch/tile/include/asm/hardwall.h
index 0bed3ec7b42c..2ac422848c7d 100644
--- a/arch/tile/include/asm/hardwall.h
+++ b/arch/tile/include/asm/hardwall.h
@@ -40,6 +40,10 @@
 #define HARDWALL_DEACTIVATE \
  _IO(HARDWALL_IOCTL_BASE, _HARDWALL_DEACTIVATE)
 
+#define _HARDWALL_GET_ID 4
+#define HARDWALL_GET_ID \
+ _IO(HARDWALL_IOCTL_BASE, _HARDWALL_GET_ID)
+
 #ifndef __KERNEL__
 
 /* This is the canonical name expected by userspace. */
@@ -47,9 +51,14 @@
 
 #else
 
-/* Hook for /proc/tile/hardwall. */
-struct seq_file;
-int proc_tile_hardwall_show(struct seq_file *sf, void *v);
+/* /proc hooks for hardwall. */
+struct proc_dir_entry;
+#ifdef CONFIG_HARDWALL
+void proc_tile_hardwall_init(struct proc_dir_entry *root);
+int proc_pid_hardwall(struct task_struct *task, char *buffer);
+#else
+static inline void proc_tile_hardwall_init(struct proc_dir_entry *root) {}
+#endif
 
 #endif
 
diff --git a/arch/tile/kernel/Makefile b/arch/tile/kernel/Makefile
index b4c8e8ec45dc..b4dbc057baad 100644
--- a/arch/tile/kernel/Makefile
+++ b/arch/tile/kernel/Makefile
@@ -5,7 +5,7 @@
 extra-y := vmlinux.lds head_$(BITS).o
 obj-y := backtrace.o entry.o init_task.o irq.o messaging.o \
         pci-dma.o proc.o process.o ptrace.o reboot.o \
-        setup.o signal.o single_step.o stack.o sys.o time.o traps.o \
+        setup.o signal.o single_step.o stack.o sys.o sysfs.o time.o traps.o \
         intvec_$(BITS).o regs_$(BITS).o tile-desc_$(BITS).o
 
 obj-$(CONFIG_HARDWALL)          += hardwall.o
diff --git a/arch/tile/kernel/hardwall.c b/arch/tile/kernel/hardwall.c
index 3bddef710de4..8c41891aab34 100644
--- a/arch/tile/kernel/hardwall.c
+++ b/arch/tile/kernel/hardwall.c
@@ -40,16 +40,25 @@
 struct hardwall_info {
         struct list_head list;             /* "rectangles" list */
         struct list_head task_head;        /* head of tasks in this hardwall */
+        struct cpumask cpumask;            /* cpus in the rectangle */
         int ulhc_x;                        /* upper left hand corner x coord */
         int ulhc_y;                        /* upper left hand corner y coord */
         int width;                         /* rectangle width */
         int height;                        /* rectangle height */
+        int id;                            /* integer id for this hardwall */
         int teardown_in_progress;          /* are we tearing this one down? */
 };
 
 /* Currently allocated hardwall rectangles */
 static LIST_HEAD(rectangles);
 
+/* /proc/tile/hardwall */
+static struct proc_dir_entry *hardwall_proc_dir;
+
+/* Functions to manage files in /proc/tile/hardwall. */
+static void hardwall_add_proc(struct hardwall_info *rect);
+static void hardwall_remove_proc(struct hardwall_info *rect);
+
 /*
  * Guard changes to the hardwall data structures.
  * This could be finer grained (e.g. one lock for the list of hardwall
@@ -105,6 +114,8 @@ static int setup_rectangle(struct hardwall_info *r, struct cpumask *mask)
         r->ulhc_y = cpu_y(ulhc);
         r->width = cpu_x(lrhc) - r->ulhc_x + 1;
         r->height = cpu_y(lrhc) - r->ulhc_y + 1;
+        cpumask_copy(&r->cpumask, mask);
+        r->id = ulhc;   /* The ulhc cpu id can be the hardwall id. */
 
         /* Width and height must be positive */
         if (r->width <= 0 || r->height <= 0)
@@ -388,6 +399,9 @@ static struct hardwall_info *hardwall_create(
         /* Set up appropriate hardwalling on all affected cpus. */
         hardwall_setup(rect);
 
+        /* Create a /proc/tile/hardwall entry. */
+        hardwall_add_proc(rect);
+
         return rect;
 }
 
@@ -645,6 +659,9 @@ static void hardwall_destroy(struct hardwall_info *rect)
         /* Restart switch and disable firewall. */
         on_each_cpu_mask(&mask, restart_udn_switch, NULL, 1);
 
+        /* Remove the /proc/tile/hardwall entry. */
+        hardwall_remove_proc(rect);
+
         /* Now free the rectangle from the list. */
         spin_lock_irqsave(&hardwall_lock, flags);
         BUG_ON(!list_empty(&rect->task_head));
@@ -654,35 +671,57 @@ static void hardwall_destroy(struct hardwall_info *rect)
 }
 
 
-/*
- * Dump hardwall state via /proc; initialized in arch/tile/sys/proc.c.
- */
-int proc_tile_hardwall_show(struct seq_file *sf, void *v)
+static int hardwall_proc_show(struct seq_file *sf, void *v)
 {
-        struct hardwall_info *r;
+        struct hardwall_info *rect = sf->private;
+        char buf[256];
 
-        if (udn_disabled) {
-                seq_printf(sf, "%dx%d 0,0 pids:\n", smp_width, smp_height);
-                return 0;
-        }
-
-        spin_lock_irq(&hardwall_lock);
-        list_for_each_entry(r, &rectangles, list) {
-                struct task_struct *p;
-                seq_printf(sf, "%dx%d %d,%d pids:",
-                           r->width, r->height, r->ulhc_x, r->ulhc_y);
-                list_for_each_entry(p, &r->task_head, thread.hardwall_list) {
-                        unsigned int cpu = cpumask_first(&p->cpus_allowed);
-                        unsigned int x = cpu % smp_width;
-                        unsigned int y = cpu / smp_width;
-                        seq_printf(sf, " %d@%d,%d", p->pid, x, y);
-                }
-                seq_printf(sf, "\n");
-        }
-        spin_unlock_irq(&hardwall_lock);
+        int rc = cpulist_scnprintf(buf, sizeof(buf), &rect->cpumask);
+        buf[rc++] = '\n';
+        seq_write(sf, buf, rc);
         return 0;
 }
 
+static int hardwall_proc_open(struct inode *inode,
+                              struct file *file)
+{
+        return single_open(file, hardwall_proc_show, PDE(inode)->data);
+}
+
+static const struct file_operations hardwall_proc_fops = {
+        .open           = hardwall_proc_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = single_release,
+};
+
+static void hardwall_add_proc(struct hardwall_info *rect)
+{
+        char buf[64];
+        snprintf(buf, sizeof(buf), "%d", rect->id);
+        proc_create_data(buf, 0444, hardwall_proc_dir,
+                         &hardwall_proc_fops, rect);
+}
+
+static void hardwall_remove_proc(struct hardwall_info *rect)
+{
+        char buf[64];
+        snprintf(buf, sizeof(buf), "%d", rect->id);
+        remove_proc_entry(buf, hardwall_proc_dir);
+}
+
+int proc_pid_hardwall(struct task_struct *task, char *buffer)
+{
+        struct hardwall_info *rect = task->thread.hardwall;
+        return rect ? sprintf(buffer, "%d\n", rect->id) : 0;
+}
+
+void proc_tile_hardwall_init(struct proc_dir_entry *root)
+{
+        if (!udn_disabled)
+                hardwall_proc_dir = proc_mkdir("hardwall", root);
+}
+
 
 /*
  * Character device support via ioctl/close.
@@ -716,6 +755,9 @@ static long hardwall_ioctl(struct file *file, unsigned int a, unsigned long b)
                         return -EINVAL;
                 return hardwall_deactivate(current);
 
+        case _HARDWALL_GET_ID:
+                return rect ? rect->id : -EINVAL;
+
         default:
                 return -EINVAL;
         }
diff --git a/arch/tile/kernel/proc.c b/arch/tile/kernel/proc.c
index 2e02c41ddf3b..62d820833c68 100644
--- a/arch/tile/kernel/proc.c
+++ b/arch/tile/kernel/proc.c
@@ -27,6 +27,7 @@
 #include <asm/processor.h>
 #include <asm/sections.h>
 #include <asm/homecache.h>
+#include <asm/hardwall.h>
 #include <arch/chip.h>
 
 
@@ -88,3 +89,75 @@ const struct seq_operations cpuinfo_op = {
         .stop   = c_stop,
         .show   = show_cpuinfo,
 };
+
+/*
+ * Support /proc/tile directory
+ */
+
+static int __init proc_tile_init(void)
+{
+        struct proc_dir_entry *root = proc_mkdir("tile", NULL);
+        if (root == NULL)
+                return 0;
+
+        proc_tile_hardwall_init(root);
+
+        return 0;
+}
+
+arch_initcall(proc_tile_init);
+
+/*
+ * Support /proc/sys/tile directory
+ */
+
+#ifndef __tilegx__  /* FIXME: GX: no support for unaligned access yet */
+static ctl_table unaligned_subtable[] = {
+        {
+                .procname       = "enabled",
+                .data           = &unaligned_fixup,
+                .maxlen         = sizeof(int),
+                .mode           = 0644,
+                .proc_handler   = &proc_dointvec
+        },
+        {
+                .procname       = "printk",
+                .data           = &unaligned_printk,
+                .maxlen         = sizeof(int),
+                .mode           = 0644,
+                .proc_handler   = &proc_dointvec
+        },
+        {
+                .procname       = "count",
+                .data           = &unaligned_fixup_count,
+                .maxlen         = sizeof(int),
+                .mode           = 0644,
+                .proc_handler   = &proc_dointvec
+        },
+        {}
+};
+
+static ctl_table unaligned_table[] = {
+        {
+                .procname       = "unaligned_fixup",
+                .mode           = 0555,
+                .child          = unaligned_subtable
+        },
+        {}
+};
+#endif
+
+static struct ctl_path tile_path[] = {
+        { .procname = "tile" },
+        { }
+};
+
+static int __init proc_sys_tile_init(void)
+{
+#ifndef __tilegx__  /* FIXME: GX: no support for unaligned access yet */
+        register_sysctl_paths(tile_path, unaligned_table);
+#endif
+        return 0;
+}
+
+arch_initcall(proc_sys_tile_init);
diff --git a/arch/tile/kernel/sysfs.c b/arch/tile/kernel/sysfs.c
new file mode 100644
index 000000000000..b671a86f4515
--- /dev/null
+++ b/arch/tile/kernel/sysfs.c
@@ -0,0 +1,185 @@
+/*
+ * Copyright 2011 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ *
+ * /sys entry support.
+ */
+
+#include <linux/sysdev.h>
+#include <linux/cpu.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+#include <hv/hypervisor.h>
+
+/* Return a string queried from the hypervisor, truncated to page size. */
+static ssize_t get_hv_confstr(char *page, int query)
+{
+        ssize_t n = hv_confstr(query, (unsigned long)page, PAGE_SIZE - 1);
+        n = n < 0 ? 0 : min(n, (ssize_t)PAGE_SIZE - 1) - 1;
+        if (n)
+                page[n++] = '\n';
+        page[n] = '\0';
+        return n;
+}
+
+static ssize_t chip_width_show(struct sysdev_class *dev,
+                               struct sysdev_class_attribute *attr,
+                               char *page)
+{
+        return sprintf(page, "%u\n", smp_width);
+}
+static SYSDEV_CLASS_ATTR(chip_width, 0444, chip_width_show, NULL);
+
+static ssize_t chip_height_show(struct sysdev_class *dev,
+                                struct sysdev_class_attribute *attr,
+                                char *page)
+{
+        return sprintf(page, "%u\n", smp_height);
+}
+static SYSDEV_CLASS_ATTR(chip_height, 0444, chip_height_show, NULL);
+
+static ssize_t chip_serial_show(struct sysdev_class *dev,
+                                struct sysdev_class_attribute *attr,
+                                char *page)
+{
+        return get_hv_confstr(page, HV_CONFSTR_CHIP_SERIAL_NUM);
+}
+static SYSDEV_CLASS_ATTR(chip_serial, 0444, chip_serial_show, NULL);
+
+static ssize_t chip_revision_show(struct sysdev_class *dev,
+                                  struct sysdev_class_attribute *attr,
+                                  char *page)
+{
+        return get_hv_confstr(page, HV_CONFSTR_CHIP_REV);
+}
+static SYSDEV_CLASS_ATTR(chip_revision, 0444, chip_revision_show, NULL);
+
+
+static ssize_t type_show(struct sysdev_class *dev,
+                            struct sysdev_class_attribute *attr,
+                            char *page)
+{
+        return sprintf(page, "tilera\n");
+}
+static SYSDEV_CLASS_ATTR(type, 0444, type_show, NULL);
+
+#define HV_CONF_ATTR(name, conf)                                        \
+        static ssize_t name ## _show(struct sysdev_class *dev,          \
+                                     struct sysdev_class_attribute *attr, \
+                                     char *page)                        \
+        {                                                               \
+                return get_hv_confstr(page, conf);                      \
+        }                                                               \
+        static SYSDEV_CLASS_ATTR(name, 0444, name ## _show, NULL);
+
+HV_CONF_ATTR(version,           HV_CONFSTR_HV_SW_VER)
+HV_CONF_ATTR(config_version,    HV_CONFSTR_HV_CONFIG_VER)
+
+HV_CONF_ATTR(board_part,        HV_CONFSTR_BOARD_PART_NUM)
+HV_CONF_ATTR(board_serial,      HV_CONFSTR_BOARD_SERIAL_NUM)
+HV_CONF_ATTR(board_revision,    HV_CONFSTR_BOARD_REV)
+HV_CONF_ATTR(board_description, HV_CONFSTR_BOARD_DESC)
+HV_CONF_ATTR(mezz_part,         HV_CONFSTR_MEZZ_PART_NUM)
+HV_CONF_ATTR(mezz_serial,       HV_CONFSTR_MEZZ_SERIAL_NUM)
+HV_CONF_ATTR(mezz_revision,     HV_CONFSTR_MEZZ_REV)
+HV_CONF_ATTR(mezz_description,  HV_CONFSTR_MEZZ_DESC)
+HV_CONF_ATTR(switch_control,    HV_CONFSTR_SWITCH_CONTROL)
+
+static struct attribute *board_attrs[] = {
+        &attr_board_part.attr,
+        &attr_board_serial.attr,
+        &attr_board_revision.attr,
+        &attr_board_description.attr,
+        &attr_mezz_part.attr,
+        &attr_mezz_serial.attr,
+        &attr_mezz_revision.attr,
+        &attr_mezz_description.attr,
+        &attr_switch_control.attr,
+        NULL
+};
+
+static struct attribute_group board_attr_group = {
+        .name   = "board",
+        .attrs  = board_attrs,
+};
+
+
+static struct bin_attribute hvconfig_bin;
+
+static ssize_t
+hvconfig_bin_read(struct file *filp, struct kobject *kobj,
+                  struct bin_attribute *bin_attr,
+                  char *buf, loff_t off, size_t count)
+{
+        static size_t size;
+
+        /* Lazily learn the true size (minus the trailing NUL). */
+        if (size == 0)
+                size = hv_confstr(HV_CONFSTR_HV_CONFIG, 0, 0) - 1;
+
+        /* Check and adjust input parameters. */
+        if (off > size)
+                return -EINVAL;
+        if (count > size - off)
+                count = size - off;
+
+        if (count) {
+                /* Get a copy of the hvc and copy out the relevant portion. */
+                char *hvc;
+
+                size = off + count;
+                hvc = kmalloc(size, GFP_KERNEL);
+                if (hvc == NULL)
+                        return -ENOMEM;
+                hv_confstr(HV_CONFSTR_HV_CONFIG, (unsigned long)hvc, size);
+                memcpy(buf, hvc + off, count);
+                kfree(hvc);
+        }
+
+        return count;
+}
+
+static int __init create_sysfs_entries(void)
+{
+        struct sysdev_class *cls = &cpu_sysdev_class;
+        int err = 0;
+
+#define create_cpu_attr(name)                                           \
+        if (!err)                                                       \
+                err = sysfs_create_file(&cls->kset.kobj, &attr_##name.attr);
+        create_cpu_attr(chip_width);
+        create_cpu_attr(chip_height);
+        create_cpu_attr(chip_serial);
+        create_cpu_attr(chip_revision);
+
+#define create_hv_attr(name)                                            \
+        if (!err)                                                       \
+                err = sysfs_create_file(hypervisor_kobj, &attr_##name.attr);
+        create_hv_attr(type);
+        create_hv_attr(version);
+        create_hv_attr(config_version);
+
+        if (!err)
+                err = sysfs_create_group(hypervisor_kobj, &board_attr_group);
+
+        if (!err) {
+                sysfs_bin_attr_init(&hvconfig_bin);
+                hvconfig_bin.attr.name = "hvconfig";
+                hvconfig_bin.attr.mode = S_IRUGO;
+                hvconfig_bin.read = hvconfig_bin_read;
+                hvconfig_bin.size = PAGE_SIZE;
+                err = sysfs_create_bin_file(hypervisor_kobj, &hvconfig_bin);
+        }
+
+        return err;
+}
+subsys_initcall(create_sysfs_entries);
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 416d865eae39..610001d385dd 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -139,7 +139,7 @@ static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate)
             boot_cpu_data.x86_model <= 0x05 &&
             boot_cpu_data.x86_mask < 0x0A)
                 return 1;
-        else if (c1e_detected)
+        else if (amd_e400_c1e_detected)
                 return 1;
         else
                 return max_cstate;
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 5dc6acc98dbd..71cc3800712c 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -125,7 +125,7 @@
 #define X86_FEATURE_OSXSAVE     (4*32+27) /* "" XSAVE enabled in the OS */
 #define X86_FEATURE_AVX         (4*32+28) /* Advanced Vector Extensions */
 #define X86_FEATURE_F16C        (4*32+29) /* 16-bit fp conversions */
-#define X86_FEATURE_RDRND       (4*32+30) /* The RDRAND instruction */
+#define X86_FEATURE_RDRAND      (4*32+30) /* The RDRAND instruction */
 #define X86_FEATURE_HYPERVISOR  (4*32+31) /* Running on a hypervisor */
 
 /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 617bd56b3070..7b439d9aea2a 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -4,30 +4,33 @@
 #include <asm/desc_defs.h>
 #include <asm/ldt.h>
 #include <asm/mmu.h>
+
 #include <linux/smp.h>
 
-static inline void fill_ldt(struct desc_struct *desc,
-                            const struct user_desc *info)
-{
-        desc->limit0 = info->limit & 0x0ffff;
-        desc->base0 = info->base_addr & 0x0000ffff;
-
-        desc->base1 = (info->base_addr & 0x00ff0000) >> 16;
-        desc->type = (info->read_exec_only ^ 1) << 1;
-        desc->type |= info->contents << 2;
-        desc->s = 1;
-        desc->dpl = 0x3;
-        desc->p = info->seg_not_present ^ 1;
-        desc->limit = (info->limit & 0xf0000) >> 16;
-        desc->avl = info->useable;
-        desc->d = info->seg_32bit;
-        desc->g = info->limit_in_pages;
-        desc->base2 = (info->base_addr & 0xff000000) >> 24;
+static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *info)
+{
+        desc->limit0            = info->limit & 0x0ffff;
+
+        desc->base0             = (info->base_addr & 0x0000ffff);
+        desc->base1             = (info->base_addr & 0x00ff0000) >> 16;
+
+        desc->type              = (info->read_exec_only ^ 1) << 1;
+        desc->type             |= info->contents << 2;
+
+        desc->s                 = 1;
+        desc->dpl               = 0x3;
+        desc->p                 = info->seg_not_present ^ 1;
+        desc->limit             = (info->limit & 0xf0000) >> 16;
+        desc->avl               = info->useable;
+        desc->d                 = info->seg_32bit;
+        desc->g                 = info->limit_in_pages;
+
+        desc->base2             = (info->base_addr & 0xff000000) >> 24;
         /*
          * Don't allow setting of the lm bit. It is useless anyway
          * because 64bit system calls require __USER_CS:
          */
-        desc->l = 0;
+        desc->l                 = 0;
 }
 
 extern struct desc_ptr idt_descr;
@@ -36,6 +39,7 @@ extern gate_desc idt_table[];
 struct gdt_page {
         struct desc_struct gdt[GDT_ENTRIES];
 } __attribute__((aligned(PAGE_SIZE)));
+
 DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page);
 
 static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu)
@@ -48,16 +52,16 @@ static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu)
 static inline void pack_gate(gate_desc *gate, unsigned type, unsigned long func,
                              unsigned dpl, unsigned ist, unsigned seg)
 {
-        gate->offset_low = PTR_LOW(func);
-        gate->segment = __KERNEL_CS;
-        gate->ist = ist;
-        gate->p = 1;
-        gate->dpl = dpl;
-        gate->zero0 = 0;
-        gate->zero1 = 0;
-        gate->type = type;
-        gate->offset_middle = PTR_MIDDLE(func);
-        gate->offset_high = PTR_HIGH(func);
+        gate->offset_low        = PTR_LOW(func);
+        gate->segment           = __KERNEL_CS;
+        gate->ist               = ist;
+        gate->p                 = 1;
+        gate->dpl               = dpl;
+        gate->zero0             = 0;
+        gate->zero1             = 0;
+        gate->type              = type;
+        gate->offset_middle     = PTR_MIDDLE(func);
+        gate->offset_high       = PTR_HIGH(func);
 }
 
 #else
@@ -66,8 +70,7 @@ static inline void pack_gate(gate_desc *gate, unsigned char type,
                              unsigned short seg)
 {
         gate->a = (seg << 16) | (base & 0xffff);
-        gate->b = (base & 0xffff0000) |
-                  (((0x80 | type | (dpl << 5)) & 0xff) << 8);
+        gate->b = (base & 0xffff0000) | (((0x80 | type | (dpl << 5)) & 0xff) << 8);
 }
 
 #endif
@@ -75,31 +78,29 @@ static inline void pack_gate(gate_desc *gate, unsigned char type,
 static inline int desc_empty(const void *ptr)
 {
         const u32 *desc = ptr;
+
         return !(desc[0] | desc[1]);
 }
 
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #else
-#define load_TR_desc() native_load_tr_desc()
-#define load_gdt(dtr) native_load_gdt(dtr)
-#define load_idt(dtr) native_load_idt(dtr)
-#define load_tr(tr) asm volatile("ltr %0"::"m" (tr))
-#define load_ldt(ldt) asm volatile("lldt %0"::"m" (ldt))
-
-#define store_gdt(dtr) native_store_gdt(dtr)
-#define store_idt(dtr) native_store_idt(dtr)
-#define store_tr(tr) (tr = native_store_tr())
-
-#define load_TLS(t, cpu) native_load_tls(t, cpu)
-#define set_ldt native_set_ldt
-
-#define write_ldt_entry(dt, entry, desc)        \
-        native_write_ldt_entry(dt, entry, desc)
-#define write_gdt_entry(dt, entry, desc, type)          \
-        native_write_gdt_entry(dt, entry, desc, type)
-#define write_idt_entry(dt, entry, g)           \
-        native_write_idt_entry(dt, entry, g)
+#define load_TR_desc()                          native_load_tr_desc()
+#define load_gdt(dtr)                           native_load_gdt(dtr)
+#define load_idt(dtr)                           native_load_idt(dtr)
+#define load_tr(tr)                             asm volatile("ltr %0"::"m" (tr))
+#define load_ldt(ldt)                           asm volatile("lldt %0"::"m" (ldt))
+
+#define store_gdt(dtr)                          native_store_gdt(dtr)
+#define store_idt(dtr)                          native_store_idt(dtr)
+#define store_tr(tr)                            (tr = native_store_tr())
+
+#define load_TLS(t, cpu)                        native_load_tls(t, cpu)
+#define set_ldt                                 native_set_ldt
+
+#define write_ldt_entry(dt, entry, desc)        native_write_ldt_entry(dt, entry, desc)
+#define write_gdt_entry(dt, entry, desc, type)  native_write_gdt_entry(dt, entry, desc, type)
+#define write_idt_entry(dt, entry, g)           native_write_idt_entry(dt, entry, g)
 
 static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries)
 {
@@ -112,33 +113,27 @@ static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries)
 
 #define store_ldt(ldt) asm("sldt %0" : "=m"(ldt))
 
-static inline void native_write_idt_entry(gate_desc *idt, int entry,
-                                          const gate_desc *gate)
+static inline void native_write_idt_entry(gate_desc *idt, int entry, const gate_desc *gate)
 {
         memcpy(&idt[entry], gate, sizeof(*gate));
 }
 
-static inline void native_write_ldt_entry(struct desc_struct *ldt, int entry,
-                                          const void *desc)
+static inline void native_write_ldt_entry(struct desc_struct *ldt, int entry, const void *desc)
 {
         memcpy(&ldt[entry], desc, 8);
 }
 
-static inline void native_write_gdt_entry(struct desc_struct *gdt, int entry,
-                                          const void *desc, int type)
+static inline void
+native_write_gdt_entry(struct desc_struct *gdt, int entry, const void *desc, int type)
 {
         unsigned int size;
+
         switch (type) {
-        case DESC_TSS:
-                size = sizeof(tss_desc);
-                break;
-        case DESC_LDT:
-                size = sizeof(ldt_desc);
-                break;
-        default:
-                size = sizeof(struct desc_struct);
-                break;
+        case DESC_TSS:  size = sizeof(tss_desc);        break;
+        case DESC_LDT:  size = sizeof(ldt_desc);        break;
+        default:        size = sizeof(*gdt);            break;
         }
+
         memcpy(&gdt[entry], desc, size);
 }
 
@@ -154,20 +149,21 @@ static inline void pack_descriptor(struct desc_struct *desc, unsigned long base,
 }
 
 
-static inline void set_tssldt_descriptor(void *d, unsigned long addr,
-                                         unsigned type, unsigned size)
+static inline void set_tssldt_descriptor(void *d, unsigned long addr, unsigned type, unsigned size)
 {
 #ifdef CONFIG_X86_64
         struct ldttss_desc64 *desc = d;
+
         memset(desc, 0, sizeof(*desc));
-        desc->limit0 = size & 0xFFFF;
-        desc->base0 = PTR_LOW(addr);
-        desc->base1 = PTR_MIDDLE(addr) & 0xFF;
-        desc->type = type;
-        desc->p = 1;
-        desc->limit1 = (size >> 16) & 0xF;
-        desc->base2 = (PTR_MIDDLE(addr) >> 8) & 0xFF;
-        desc->base3 = PTR_HIGH(addr);
+
+        desc->limit0            = size & 0xFFFF;
+        desc->base0             = PTR_LOW(addr);
+        desc->base1             = PTR_MIDDLE(addr) & 0xFF;
+        desc->type              = type;
+        desc->p                 = 1;
+        desc->limit1            = (size >> 16) & 0xF;
+        desc->base2             = (PTR_MIDDLE(addr) >> 8) & 0xFF;
+        desc->base3             = PTR_HIGH(addr);
 #else
         pack_descriptor((struct desc_struct *)d, addr, size, 0x80 | type, 0);
 #endif
@@ -237,14 +233,16 @@ static inline void native_store_idt(struct desc_ptr *dtr)
 static inline unsigned long native_store_tr(void)
 {
         unsigned long tr;
+
         asm volatile("str %0":"=r" (tr));
+
         return tr;
 }
 
 static inline void native_load_tls(struct thread_struct *t, unsigned int cpu)
 {
-        unsigned int i;
         struct desc_struct *gdt = get_cpu_gdt_table(cpu);
+        unsigned int i;
 
         for (i = 0; i < GDT_ENTRY_TLS_ENTRIES; i++)
                 gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i];
@@ -313,6 +311,7 @@ static inline void _set_gate(int gate, unsigned type, void *addr,
                              unsigned dpl, unsigned ist, unsigned seg)
 {
         gate_desc s;
+
         pack_gate(&s, type, (unsigned long)addr, dpl, ist, seg);
         /*
          * does not need to be atomic because it is only done once at
@@ -343,8 +342,9 @@ static inline void alloc_system_vector(int vector)
                 set_bit(vector, used_vectors);
                 if (first_system_vector > vector)
                         first_system_vector = vector;
-        } else
+        } else {
                 BUG();
+        }
 }
 
 static inline void alloc_intr_gate(unsigned int n, void *addr)
diff --git a/arch/x86/include/asm/idle.h b/arch/x86/include/asm/idle.h
index 38d87379e270..f49253d75710 100644
--- a/arch/x86/include/asm/idle.h
+++ b/arch/x86/include/asm/idle.h
@@ -16,6 +16,6 @@ static inline void enter_idle(void) { }
 static inline void exit_idle(void) { }
 #endif /* CONFIG_X86_64 */
 
-void c1e_remove_cpu(int cpu);
+void amd_e400_remove_cpu(int cpu);
 
 #endif /* _ASM_X86_IDLE_H */
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index aeff3e89b222..5f55e6962769 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -11,14 +11,14 @@
 typedef struct {
         void *ldt;
         int size;
-        struct mutex lock;
-        void *vdso;
 
 #ifdef CONFIG_X86_64
         /* True if mm supports a task running in 32 bit compatibility mode. */
         unsigned short ia32_compat;
 #endif
 
+        struct mutex lock;
+        void *vdso;
 } mm_context_t;
 
 #ifdef CONFIG_SMP
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 4c25ab48257b..219371546afd 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -754,10 +754,10 @@ static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
 extern void mwait_idle_with_hints(unsigned long eax, unsigned long ecx);
 
 extern void select_idle_routine(const struct cpuinfo_x86 *c);
-extern void init_c1e_mask(void);
+extern void init_amd_e400_c1e_mask(void);
 
 extern unsigned long            boot_option_idle_override;
-extern bool                     c1e_detected;
+extern bool                     amd_e400_c1e_detected;
 
 enum idle_boot_override {IDLE_NO_OVERRIDE=0, IDLE_HALT, IDLE_NOMWAIT,
                          IDLE_POLL, IDLE_FORCE_MWAIT};
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 130f1eeee5fe..a291c40efd43 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -5,7 +5,7 @@
  *
  * SGI UV Broadcast Assist Unit definitions
  *
- * Copyright (C) 2008 Silicon Graphics, Inc. All rights reserved.
+ * Copyright (C) 2008-2011 Silicon Graphics, Inc. All rights reserved.
  */
 
 #ifndef _ASM_X86_UV_UV_BAU_H
@@ -35,17 +35,20 @@
 
 #define MAX_CPUS_PER_UVHUB              64
 #define MAX_CPUS_PER_SOCKET             32
-#define UV_ADP_SIZE                     64 /* hardware-provided max. */
-#define UV_CPUS_PER_ACT_STATUS          32 /* hardware-provided max. */
-#define UV_ITEMS_PER_DESCRIPTOR         8
+#define ADP_SZ                          64 /* hardware-provided max. */
+#define UV_CPUS_PER_AS                  32 /* hardware-provided max. */
+#define ITEMS_PER_DESC                  8
 /* the 'throttle' to prevent the hardware stay-busy bug */
 #define MAX_BAU_CONCURRENT              3
 #define UV_ACT_STATUS_MASK              0x3
 #define UV_ACT_STATUS_SIZE              2
 #define UV_DISTRIBUTION_SIZE            256
 #define UV_SW_ACK_NPENDING              8
-#define UV_NET_ENDPOINT_INTD            0x38
-#define UV_DESC_BASE_PNODE_SHIFT        49
+#define UV1_NET_ENDPOINT_INTD           0x38
+#define UV2_NET_ENDPOINT_INTD           0x28
+#define UV_NET_ENDPOINT_INTD            (is_uv1_hub() ?                 \
+                        UV1_NET_ENDPOINT_INTD : UV2_NET_ENDPOINT_INTD)
+#define UV_DESC_PSHIFT                  49
 #define UV_PAYLOADQ_PNODE_SHIFT         49
 #define UV_PTC_BASENAME                 "sgi_uv/ptc_statistics"
 #define UV_BAU_BASENAME                 "sgi_uv/bau_tunables"
@@ -53,29 +56,64 @@
 #define UV_BAU_TUNABLES_FILE            "bau_tunables"
 #define WHITESPACE                      " \t\n"
 #define uv_physnodeaddr(x)              ((__pa((unsigned long)(x)) & uv_mmask))
-#define UV_ENABLE_INTD_SOFT_ACK_MODE_SHIFT 15
-#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHIFT 16
-#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD 0x0000000009UL
+#define cpubit_isset(cpu, bau_local_cpumask) \
+        test_bit((cpu), (bau_local_cpumask).bits)
+
 /* [19:16] SOFT_ACK timeout period  19: 1 is urgency 7  17:16 1 is multiplier */
-#define BAU_MISC_CONTROL_MULT_MASK 3
+/*
+ * UV2: Bit 19 selects between
+ *  (0): 10 microsecond timebase and
+ *  (1): 80 microseconds
+ *  we're using 655us, similar to UV1: 65 units of 10us
+ */
+#define UV1_INTD_SOFT_ACK_TIMEOUT_PERIOD (9UL)
+#define UV2_INTD_SOFT_ACK_TIMEOUT_PERIOD (65*10UL)
+
+#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD (is_uv1_hub() ?                 \
+                UV1_INTD_SOFT_ACK_TIMEOUT_PERIOD :                      \
+                UV2_INTD_SOFT_ACK_TIMEOUT_PERIOD)
 
-#define UVH_AGING_PRESCALE_SEL 0x000000b000UL
+#define BAU_MISC_CONTROL_MULT_MASK      3
+
+#define UVH_AGING_PRESCALE_SEL          0x000000b000UL
 /* [30:28] URGENCY_7  an index into a table of times */
-#define BAU_URGENCY_7_SHIFT 28
-#define BAU_URGENCY_7_MASK 7
+#define BAU_URGENCY_7_SHIFT             28
+#define BAU_URGENCY_7_MASK              7
 
-#define UVH_TRANSACTION_TIMEOUT 0x000000b200UL
+#define UVH_TRANSACTION_TIMEOUT         0x000000b200UL
 /* [45:40] BAU - BAU transaction timeout select - a multiplier */
-#define BAU_TRANS_SHIFT 40
-#define BAU_TRANS_MASK 0x3f
+#define BAU_TRANS_SHIFT                 40
+#define BAU_TRANS_MASK                  0x3f
+
+/*
+ * shorten some awkward names
+ */
+#define AS_PUSH_SHIFT UVH_LB_BAU_SB_ACTIVATION_CONTROL_PUSH_SHFT
+#define SOFTACK_MSHIFT UVH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT
+#define SOFTACK_PSHIFT UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT
+#define SOFTACK_TIMEOUT_PERIOD UV_INTD_SOFT_ACK_TIMEOUT_PERIOD
+#define write_gmmr      uv_write_global_mmr64
+#define write_lmmr      uv_write_local_mmr
+#define read_lmmr       uv_read_local_mmr
+#define read_gmmr       uv_read_global_mmr64
 
 /*
  * bits in UVH_LB_BAU_SB_ACTIVATION_STATUS_0/1
  */
-#define DESC_STATUS_IDLE                0
-#define DESC_STATUS_ACTIVE              1
-#define DESC_STATUS_DESTINATION_TIMEOUT 2
-#define DESC_STATUS_SOURCE_TIMEOUT      3
+#define DS_IDLE                         0
+#define DS_ACTIVE                       1
+#define DS_DESTINATION_TIMEOUT          2
+#define DS_SOURCE_TIMEOUT               3
+/*
+ * bits put together from HRP_LB_BAU_SB_ACTIVATION_STATUS_0/1/2
+ * values 1 and 5 will not occur
+ */
+#define UV2H_DESC_IDLE                  0
+#define UV2H_DESC_DEST_TIMEOUT          2
+#define UV2H_DESC_DEST_STRONG_NACK      3
+#define UV2H_DESC_BUSY                  4
+#define UV2H_DESC_SOURCE_TIMEOUT        6
+#define UV2H_DESC_DEST_PUT_ERR          7
 
 /*
  * delay for 'plugged' timeout retries, in microseconds
@@ -86,15 +124,24 @@
  * threshholds at which to use IPI to free resources
  */
 /* after this # consecutive 'plugged' timeouts, use IPI to release resources */
-#define PLUGSB4RESET 100
+#define PLUGSB4RESET                    100
 /* after this many consecutive timeouts, use IPI to release resources */
-#define TIMEOUTSB4RESET 1
+#define TIMEOUTSB4RESET                 1
 /* at this number uses of IPI to release resources, giveup the request */
-#define IPI_RESET_LIMIT 1
+#define IPI_RESET_LIMIT                 1
 /* after this # consecutive successes, bump up the throttle if it was lowered */
-#define COMPLETE_THRESHOLD 5
+#define COMPLETE_THRESHOLD              5
+
+#define UV_LB_SUBNODEID                 0x10
 
-#define UV_LB_SUBNODEID 0x10
+/* these two are the same for UV1 and UV2: */
+#define UV_SA_SHFT UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT
+#define UV_SA_MASK UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_MASK
+/* 4 bits of software ack period */
+#define UV2_ACK_MASK                    0x7UL
+#define UV2_ACK_UNITS_SHFT              3
+#define UV2_LEG_SHFT UV2H_LB_BAU_MISC_CONTROL_USE_LEGACY_DESCRIPTOR_FORMATS_SHFT
+#define UV2_EXT_SHFT UV2H_LB_BAU_MISC_CONTROL_ENABLE_EXTENDED_SB_STATUS_SHFT
 
 /*
  * number of entries in the destination side payload queue
@@ -115,9 +162,16 @@
 /*
  * tuning the action when the numalink network is extremely delayed
  */
-#define CONGESTED_RESPONSE_US 1000 /* 'long' response time, in microseconds */
-#define CONGESTED_REPS 10 /* long delays averaged over this many broadcasts */
-#define CONGESTED_PERIOD 30 /* time for the bau to be disabled, in seconds */
+#define CONGESTED_RESPONSE_US           1000    /* 'long' response time, in
+                                                   microseconds */
+#define CONGESTED_REPS                  10      /* long delays averaged over
+                                                   this many broadcasts */
+#define CONGESTED_PERIOD                30      /* time for the bau to be
+                                                   disabled, in seconds */
+/* see msg_type: */
+#define MSG_NOOP                        0
+#define MSG_REGULAR                     1
+#define MSG_RETRY                       2
 
 /*
  * Distribution: 32 bytes (256 bits) (bytes 0-0x1f of descriptor)
@@ -129,8 +183,8 @@
  * 'base_dest_nasid' field of the header corresponds to the
  * destination nodeID associated with that specified bit.
  */
-struct bau_target_uvhubmask {
-        unsigned long bits[BITS_TO_LONGS(UV_DISTRIBUTION_SIZE)];
+struct bau_targ_hubmask {
+        unsigned long           bits[BITS_TO_LONGS(UV_DISTRIBUTION_SIZE)];
 };
 
 /*
@@ -139,7 +193,7 @@ struct bau_target_uvhubmask {
  *  enough bits for max. cpu's per uvhub)
  */
 struct bau_local_cpumask {
-        unsigned long bits;
+        unsigned long           bits;
 };
 
 /*
@@ -160,14 +214,14 @@ struct bau_local_cpumask {
  * The payload is software-defined for INTD transactions
  */
 struct bau_msg_payload {
-        unsigned long address;          /* signifies a page or all TLB's
-                                                of the cpu */
+        unsigned long   address;                /* signifies a page or all
+                                                   TLB's of the cpu */
         /* 64 bits */
-        unsigned short sending_cpu;     /* filled in by sender */
+        unsigned short  sending_cpu;            /* filled in by sender */
         /* 16 bits */
-        unsigned short acknowledge_count;/* filled in by destination */
+        unsigned short  acknowledge_count;      /* filled in by destination */
         /* 16 bits */
-        unsigned int reserved1:32;      /* not usable */
+        unsigned int    reserved1:32;           /* not usable */
 };
 
 
@@ -176,93 +230,96 @@ struct bau_msg_payload {
  * see table 4.2.3.0.1 in broacast_assist spec.
  */
 struct bau_msg_header {
-        unsigned int dest_subnodeid:6;  /* must be 0x10, for the LB */
+        unsigned int    dest_subnodeid:6;       /* must be 0x10, for the LB */
         /* bits 5:0 */
-        unsigned int base_dest_nasid:15; /* nasid of the */
-        /* bits 20:6 */                   /* first bit in uvhub map */
-        unsigned int command:8; /* message type */
+        unsigned int    base_dest_nasid:15;     /* nasid of the first bit */
+        /* bits 20:6 */                         /* in uvhub map */
+        unsigned int    command:8;              /* message type */
         /* bits 28:21 */
-                                /* 0x38: SN3net EndPoint Message */
-        unsigned int rsvd_1:3;  /* must be zero */
+        /* 0x38: SN3net EndPoint Message */
+        unsigned int    rsvd_1:3;               /* must be zero */
         /* bits 31:29 */
-                                /* int will align on 32 bits */
-        unsigned int rsvd_2:9;  /* must be zero */
+        /* int will align on 32 bits */
+        unsigned int    rsvd_2:9;               /* must be zero */
         /* bits 40:32 */
-                                /* Suppl_A is 56-41 */
-        unsigned int sequence:16;/* message sequence number */
-        /* bits 56:41 */        /* becomes bytes 16-17 of msg */
-                                /* Address field (96:57) is never used as an
-                                   address (these are address bits 42:3) */
-
-        unsigned int rsvd_3:1;  /* must be zero */
+        /* Suppl_A is 56-41 */
+        unsigned int    sequence:16;            /* message sequence number */
+        /* bits 56:41 */                        /* becomes bytes 16-17 of msg */
+                                                /* Address field (96:57) is
+                                                   never used as an address
+                                                   (these are address bits
+                                                   42:3) */
+
+        unsigned int    rsvd_3:1;               /* must be zero */
         /* bit 57 */
-                                /* address bits 27:4 are payload */
+        /* address bits 27:4 are payload */
         /* these next 24  (58-81) bits become bytes 12-14 of msg */
-
         /* bits 65:58 land in byte 12 */
-        unsigned int replied_to:1;/* sent as 0 by the source to byte 12 */
+        unsigned int    replied_to:1;           /* sent as 0 by the source to
+                                                   byte 12 */
         /* bit 58 */
-        unsigned int msg_type:3; /* software type of the message*/
+        unsigned int    msg_type:3;             /* software type of the
+                                                   message */
         /* bits 61:59 */
-        unsigned int canceled:1; /* message canceled, resource to be freed*/
+        unsigned int    canceled:1;             /* message canceled, resource
+                                                   is to be freed*/
         /* bit 62 */
-        unsigned int payload_1a:1;/* not currently used */
+        unsigned int    payload_1a:1;           /* not currently used */
         /* bit 63 */
-        unsigned int payload_1b:2;/* not currently used */
+        unsigned int    payload_1b:2;           /* not currently used */
         /* bits 65:64 */
 
         /* bits 73:66 land in byte 13 */
-        unsigned int payload_1ca:6;/* not currently used */
+        unsigned int    payload_1ca:6;          /* not currently used */
         /* bits 71:66 */
-        unsigned int payload_1c:2;/* not currently used */
+        unsigned int    payload_1c:2;           /* not currently used */
         /* bits 73:72 */
 
         /* bits 81:74 land in byte 14 */
-        unsigned int payload_1d:6;/* not currently used */
+        unsigned int    payload_1d:6;           /* not currently used */
         /* bits 79:74 */
-        unsigned int payload_1e:2;/* not currently used */
+        unsigned int    payload_1e:2;           /* not currently used */
         /* bits 81:80 */
 
-        unsigned int rsvd_4:7;  /* must be zero */
+        unsigned int    rsvd_4:7;               /* must be zero */
         /* bits 88:82 */
-        unsigned int sw_ack_flag:1;/* software acknowledge flag */
+        unsigned int    swack_flag:1;           /* software acknowledge flag */
         /* bit 89 */
-                                /* INTD trasactions at destination are to
-                                   wait for software acknowledge */
-        unsigned int rsvd_5:6;  /* must be zero */
+                                                /* INTD trasactions at
+                                                   destination are to wait for
+                                                   software acknowledge */
+        unsigned int    rsvd_5:6;               /* must be zero */
         /* bits 95:90 */
-        unsigned int rsvd_6:5;  /* must be zero */
+        unsigned int    rsvd_6:5;               /* must be zero */
         /* bits 100:96 */
-        unsigned int int_both:1;/* if 1, interrupt both sockets on the uvhub */
+        unsigned int    int_both:1;             /* if 1, interrupt both sockets
+                                                   on the uvhub */
         /* bit 101*/
-        unsigned int fairness:3;/* usually zero */
+        unsigned int    fairness:3;             /* usually zero */
         /* bits 104:102 */
-        unsigned int multilevel:1;      /* multi-level multicast format */
+        unsigned int    multilevel:1;           /* multi-level multicast
+                                                   format */
         /* bit 105 */
-                                /* 0 for TLB: endpoint multi-unicast messages */
-        unsigned int chaining:1;/* next descriptor is part of this activation*/
+        /* 0 for TLB: endpoint multi-unicast messages */
+        unsigned int    chaining:1;             /* next descriptor is part of
+                                                   this activation*/
         /* bit 106 */
-        unsigned int rsvd_7:21; /* must be zero */
+        unsigned int    rsvd_7:21;              /* must be zero */
         /* bits 127:107 */
 };
 
-/* see msg_type: */
-#define MSG_NOOP 0
-#define MSG_REGULAR 1
-#define MSG_RETRY 2
-
 /*
  * The activation descriptor:
  * The format of the message to send, plus all accompanying control
  * Should be 64 bytes
  */
 struct bau_desc {
-        struct bau_target_uvhubmask distribution;
+        struct bau_targ_hubmask distribution;
         /*
          * message template, consisting of header and payload:
          */
-        struct bau_msg_header header;
-        struct bau_msg_payload payload;
+        struct bau_msg_header           header;
+        struct bau_msg_payload          payload;
 };
 /*
  *   -payload--    ---------header------
@@ -281,59 +338,51 @@ struct bau_desc {
  * are 32 bytes (2 micropackets) (256 bits) in length, but contain only 17
  * bytes of usable data, including the sw ack vector in byte 15 (bits 127:120)
  * (12 bytes come from bau_msg_payload, 3 from payload_1, 2 from
- *  sw_ack_vector and payload_2)
+ *  swack_vec and payload_2)
  * "Enabling Software Acknowledgment mode (see Section 4.3.3 Software
  *  Acknowledge Processing) also selects 32 byte (17 bytes usable) payload
  *  operation."
  */
-struct bau_payload_queue_entry {
-        unsigned long address;          /* signifies a page or all TLB's
-                                                of the cpu */
+struct bau_pq_entry {
+        unsigned long   address;        /* signifies a page or all TLB's
+                                           of the cpu */
         /* 64 bits, bytes 0-7 */
-
-        unsigned short sending_cpu;     /* cpu that sent the message */
+        unsigned short  sending_cpu;    /* cpu that sent the message */
         /* 16 bits, bytes 8-9 */
-
-        unsigned short acknowledge_count; /* filled in by destination */
+        unsigned short  acknowledge_count; /* filled in by destination */
         /* 16 bits, bytes 10-11 */
-
         /* these next 3 bytes come from bits 58-81 of the message header */
-        unsigned short replied_to:1;    /* sent as 0 by the source */
-        unsigned short msg_type:3;      /* software message type */
-        unsigned short canceled:1;      /* sent as 0 by the source */
-        unsigned short unused1:3;       /* not currently using */
+        unsigned short  replied_to:1;   /* sent as 0 by the source */
+        unsigned short  msg_type:3;     /* software message type */
+        unsigned short  canceled:1;     /* sent as 0 by the source */
+        unsigned short  unused1:3;      /* not currently using */
         /* byte 12 */
-
-        unsigned char unused2a;         /* not currently using */
+        unsigned char   unused2a;       /* not currently using */
         /* byte 13 */
-        unsigned char unused2;          /* not currently using */
+        unsigned char   unused2;        /* not currently using */
         /* byte 14 */
-
-        unsigned char sw_ack_vector;    /* filled in by the hardware */
+        unsigned char   swack_vec;      /* filled in by the hardware */
         /* byte 15 (bits 127:120) */
-
-        unsigned short sequence;        /* message sequence number */
+        unsigned short  sequence;       /* message sequence number */
         /* bytes 16-17 */
-        unsigned char unused4[2];       /* not currently using bytes 18-19 */
+        unsigned char   unused4[2];     /* not currently using bytes 18-19 */
         /* bytes 18-19 */
-
-        int number_of_cpus;             /* filled in at destination */
+        int             number_of_cpus; /* filled in at destination */
         /* 32 bits, bytes 20-23 (aligned) */
-
-        unsigned char unused5[8];       /* not using */
+        unsigned char   unused5[8];     /* not using */
         /* bytes 24-31 */
 };
 
 struct msg_desc {
-        struct bau_payload_queue_entry *msg;
-        int msg_slot;
-        int sw_ack_slot;
-        struct bau_payload_queue_entry *va_queue_first;
-        struct bau_payload_queue_entry *va_queue_last;
+        struct bau_pq_entry     *msg;
+        int                     msg_slot;
+        int                     swack_slot;
+        struct bau_pq_entry     *queue_first;
+        struct bau_pq_entry     *queue_last;
 };
 
 struct reset_args {
-        int sender;
+        int                     sender;
 };
 
 /*
@@ -341,112 +390,226 @@ struct reset_args {
  */
 struct ptc_stats {
         /* sender statistics */
-        unsigned long s_giveup; /* number of fall backs to IPI-style flushes */
-        unsigned long s_requestor; /* number of shootdown requests */
-        unsigned long s_stimeout; /* source side timeouts */
-        unsigned long s_dtimeout; /* destination side timeouts */
-        unsigned long s_time; /* time spent in sending side */
-        unsigned long s_retriesok; /* successful retries */
-        unsigned long s_ntargcpu; /* total number of cpu's targeted */
-        unsigned long s_ntargself; /* times the sending cpu was targeted */
-        unsigned long s_ntarglocals; /* targets of cpus on the local blade */
-        unsigned long s_ntargremotes; /* targets of cpus on remote blades */
-        unsigned long s_ntarglocaluvhub; /* targets of the local hub */
-        unsigned long s_ntargremoteuvhub; /* remotes hubs targeted */
-        unsigned long s_ntarguvhub; /* total number of uvhubs targeted */
-        unsigned long s_ntarguvhub16; /* number of times target hubs >= 16*/
-        unsigned long s_ntarguvhub8; /* number of times target hubs >= 8 */
-        unsigned long s_ntarguvhub4; /* number of times target hubs >= 4 */
-        unsigned long s_ntarguvhub2; /* number of times target hubs >= 2 */
-        unsigned long s_ntarguvhub1; /* number of times target hubs == 1 */
-        unsigned long s_resets_plug; /* ipi-style resets from plug state */
-        unsigned long s_resets_timeout; /* ipi-style resets from timeouts */
-        unsigned long s_busy; /* status stayed busy past s/w timer */
-        unsigned long s_throttles; /* waits in throttle */
-        unsigned long s_retry_messages; /* retry broadcasts */
-        unsigned long s_bau_reenabled; /* for bau enable/disable */
-        unsigned long s_bau_disabled; /* for bau enable/disable */
+        unsigned long   s_giveup;               /* number of fall backs to
+                                                   IPI-style flushes */
+        unsigned long   s_requestor;            /* number of shootdown
+                                                   requests */
+        unsigned long   s_stimeout;             /* source side timeouts */
+        unsigned long   s_dtimeout;             /* destination side timeouts */
+        unsigned long   s_time;                 /* time spent in sending side */
+        unsigned long   s_retriesok;            /* successful retries */
+        unsigned long   s_ntargcpu;             /* total number of cpu's
+                                                   targeted */
+        unsigned long   s_ntargself;            /* times the sending cpu was
+                                                   targeted */
+        unsigned long   s_ntarglocals;          /* targets of cpus on the local
+                                                   blade */
+        unsigned long   s_ntargremotes;         /* targets of cpus on remote
+                                                   blades */
+        unsigned long   s_ntarglocaluvhub;      /* targets of the local hub */
+        unsigned long   s_ntargremoteuvhub;     /* remotes hubs targeted */
+        unsigned long   s_ntarguvhub;           /* total number of uvhubs
+                                                   targeted */
+        unsigned long   s_ntarguvhub16;         /* number of times target
+                                                   hubs >= 16*/
+        unsigned long   s_ntarguvhub8;          /* number of times target
+                                                   hubs >= 8 */
+        unsigned long   s_ntarguvhub4;          /* number of times target
+                                                   hubs >= 4 */
+        unsigned long   s_ntarguvhub2;          /* number of times target
+                                                   hubs >= 2 */
+        unsigned long   s_ntarguvhub1;          /* number of times target
+                                                   hubs == 1 */
+        unsigned long   s_resets_plug;          /* ipi-style resets from plug
+                                                   state */
+        unsigned long   s_resets_timeout;       /* ipi-style resets from
+                                                   timeouts */
+        unsigned long   s_busy;                 /* status stayed busy past
+                                                   s/w timer */
+        unsigned long   s_throttles;            /* waits in throttle */
+        unsigned long   s_retry_messages;       /* retry broadcasts */
+        unsigned long   s_bau_reenabled;        /* for bau enable/disable */
+        unsigned long   s_bau_disabled;         /* for bau enable/disable */
         /* destination statistics */
-        unsigned long d_alltlb; /* times all tlb's on this cpu were flushed */
-        unsigned long d_onetlb; /* times just one tlb on this cpu was flushed */
-        unsigned long d_multmsg; /* interrupts with multiple messages */
-        unsigned long d_nomsg; /* interrupts with no message */
-        unsigned long d_time; /* time spent on destination side */
-        unsigned long d_requestee; /* number of messages processed */
-        unsigned long d_retries; /* number of retry messages processed */
-        unsigned long d_canceled; /* number of messages canceled by retries */
-        unsigned long d_nocanceled; /* retries that found nothing to cancel */
-        unsigned long d_resets; /* number of ipi-style requests processed */
-        unsigned long d_rcanceled; /* number of messages canceled by resets */
+        unsigned long   d_alltlb;               /* times all tlb's on this
+                                                   cpu were flushed */
+        unsigned long   d_onetlb;               /* times just one tlb on this
+                                                   cpu was flushed */
+        unsigned long   d_multmsg;              /* interrupts with multiple
+                                                   messages */
+        unsigned long   d_nomsg;                /* interrupts with no message */
+        unsigned long   d_time;                 /* time spent on destination
+                                                   side */
+        unsigned long   d_requestee;            /* number of messages
+                                                   processed */
+        unsigned long   d_retries;              /* number of retry messages
+                                                   processed */
+        unsigned long   d_canceled;             /* number of messages canceled
+                                                   by retries */
+        unsigned long   d_nocanceled;           /* retries that found nothing
+                                                   to cancel */
+        unsigned long   d_resets;               /* number of ipi-style requests
+                                                   processed */
+        unsigned long   d_rcanceled;            /* number of messages canceled
+                                                   by resets */
+};
+
+struct tunables {
+        int                     *tunp;
+        int                     deflt;
 };
 
 struct hub_and_pnode {
-        short uvhub;
-        short pnode;
+        short                   uvhub;
+        short                   pnode;
 };
+
+struct socket_desc {
+        short                   num_cpus;
+        short                   cpu_number[MAX_CPUS_PER_SOCKET];
+};
+
+struct uvhub_desc {
+        unsigned short          socket_mask;
+        short                   num_cpus;
+        short                   uvhub;
+        short                   pnode;
+        struct socket_desc      socket[2];
+};
+
 /*
  * one per-cpu; to locate the software tables
  */
 struct bau_control {
-        struct bau_desc *descriptor_base;
-        struct bau_payload_queue_entry *va_queue_first;
-        struct bau_payload_queue_entry *va_queue_last;
-        struct bau_payload_queue_entry *bau_msg_head;
-        struct bau_control *uvhub_master;
-        struct bau_control *socket_master;
-        struct ptc_stats *statp;
-        unsigned long timeout_interval;
-        unsigned long set_bau_on_time;
-        atomic_t active_descriptor_count;
-        int plugged_tries;
-        int timeout_tries;
-        int ipi_attempts;
-        int conseccompletes;
-        int baudisabled;
-        int set_bau_off;
-        short cpu;
-        short osnode;
-        short uvhub_cpu;
-        short uvhub;
-        short cpus_in_socket;
-        short cpus_in_uvhub;
-        short partition_base_pnode;
-        unsigned short message_number;
-        unsigned short uvhub_quiesce;
-        short socket_acknowledge_count[DEST_Q_SIZE];
-        cycles_t send_message;
-        spinlock_t uvhub_lock;
-        spinlock_t queue_lock;
+        struct bau_desc         *descriptor_base;
+        struct bau_pq_entry     *queue_first;
+        struct bau_pq_entry     *queue_last;
+        struct bau_pq_entry     *bau_msg_head;
+        struct bau_control      *uvhub_master;
+        struct bau_control      *socket_master;
+        struct ptc_stats        *statp;
+        unsigned long           timeout_interval;
+        unsigned long           set_bau_on_time;
+        atomic_t                active_descriptor_count;
+        int                     plugged_tries;
+        int                     timeout_tries;
+        int                     ipi_attempts;
+        int                     conseccompletes;
+        int                     baudisabled;
+        int                     set_bau_off;
+        short                   cpu;
+        short                   osnode;
+        short                   uvhub_cpu;
+        short                   uvhub;
+        short                   cpus_in_socket;
+        short                   cpus_in_uvhub;
+        short                   partition_base_pnode;
+        unsigned short          message_number;
+        unsigned short          uvhub_quiesce;
+        short                   socket_acknowledge_count[DEST_Q_SIZE];
+        cycles_t                send_message;
+        spinlock_t              uvhub_lock;
+        spinlock_t              queue_lock;
         /* tunables */
-        int max_bau_concurrent;
-        int max_bau_concurrent_constant;
-        int plugged_delay;
-        int plugsb4reset;
-        int timeoutsb4reset;
-        int ipi_reset_limit;
-        int complete_threshold;
-        int congested_response_us;
-        int congested_reps;
-        int congested_period;
-        cycles_t period_time;
-        long period_requests;
-        struct hub_and_pnode *target_hub_and_pnode;
+        int                     max_concurr;
+        int                     max_concurr_const;
+        int                     plugged_delay;
+        int                     plugsb4reset;
+        int                     timeoutsb4reset;
+        int                     ipi_reset_limit;
+        int                     complete_threshold;
+        int                     cong_response_us;
+        int                     cong_reps;
+        int                     cong_period;
+        cycles_t                period_time;
+        long                    period_requests;
+        struct hub_and_pnode    *thp;
 };
 
-static inline int bau_uvhub_isset(int uvhub, struct bau_target_uvhubmask *dstp)
+static unsigned long read_mmr_uv2_status(void)
+{
+        return read_lmmr(UV2H_LB_BAU_SB_ACTIVATION_STATUS_2);
+}
+
+static void write_mmr_data_broadcast(int pnode, unsigned long mmr_image)
+{
+        write_gmmr(pnode, UVH_BAU_DATA_BROADCAST, mmr_image);
+}
+
+static void write_mmr_descriptor_base(int pnode, unsigned long mmr_image)
+{
+        write_gmmr(pnode, UVH_LB_BAU_SB_DESCRIPTOR_BASE, mmr_image);
+}
+
+static void write_mmr_activation(unsigned long index)
+{
+        write_lmmr(UVH_LB_BAU_SB_ACTIVATION_CONTROL, index);
+}
+
+static void write_gmmr_activation(int pnode, unsigned long mmr_image)
+{
+        write_gmmr(pnode, UVH_LB_BAU_SB_ACTIVATION_CONTROL, mmr_image);
+}
+
+static void write_mmr_payload_first(int pnode, unsigned long mmr_image)
+{
+        write_gmmr(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST, mmr_image);
+}
+
+static void write_mmr_payload_tail(int pnode, unsigned long mmr_image)
+{
+        write_gmmr(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL, mmr_image);
+}
+
+static void write_mmr_payload_last(int pnode, unsigned long mmr_image)
+{
+        write_gmmr(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST, mmr_image);
+}
+
+static void write_mmr_misc_control(int pnode, unsigned long mmr_image)
+{
+        write_gmmr(pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image);
+}
+
+static unsigned long read_mmr_misc_control(int pnode)
+{
+        return read_gmmr(pnode, UVH_LB_BAU_MISC_CONTROL);
+}
+
+static void write_mmr_sw_ack(unsigned long mr)
+{
+        uv_write_local_mmr(UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS, mr);
+}
+
+static unsigned long read_mmr_sw_ack(void)
+{
+        return read_lmmr(UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE);
+}
+
+static unsigned long read_gmmr_sw_ack(int pnode)
+{
+        return read_gmmr(pnode, UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE);
+}
+
+static void write_mmr_data_config(int pnode, unsigned long mr)
+{
+        uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG, mr);
+}
+
+static inline int bau_uvhub_isset(int uvhub, struct bau_targ_hubmask *dstp)
 {
         return constant_test_bit(uvhub, &dstp->bits[0]);
 }
-static inline void bau_uvhub_set(int pnode, struct bau_target_uvhubmask *dstp)
+static inline void bau_uvhub_set(int pnode, struct bau_targ_hubmask *dstp)
 {
         __set_bit(pnode, &dstp->bits[0]);
 }
-static inline void bau_uvhubs_clear(struct bau_target_uvhubmask *dstp,
+static inline void bau_uvhubs_clear(struct bau_targ_hubmask *dstp,
                                     int nbits)
 {
         bitmap_zero(&dstp->bits[0], nbits);
 }
-static inline int bau_uvhub_weight(struct bau_target_uvhubmask *dstp)
+static inline int bau_uvhub_weight(struct bau_targ_hubmask *dstp)
 {
         return bitmap_weight((unsigned long *)&dstp->bits[0],
                                 UV_DISTRIBUTION_SIZE);
@@ -457,9 +620,6 @@ static inline void bau_cpubits_clear(struct bau_local_cpumask *dstp, int nbits)
         bitmap_zero(&dstp->bits, nbits);
 }
 
-#define cpubit_isset(cpu, bau_local_cpumask) \
-        test_bit((cpu), (bau_local_cpumask).bits)
-
 extern void uv_bau_message_intr1(void);
 extern void uv_bau_timeout_intr1(void);
 
@@ -467,7 +627,7 @@ struct atomic_short {
         short counter;
 };
 
-/**
+/*
  * atomic_read_short - read a short atomic variable
  * @v: pointer of type atomic_short
  *
@@ -478,14 +638,14 @@ static inline int atomic_read_short(const struct atomic_short *v)
         return v->counter;
 }
 
-/**
- * atomic_add_short_return - add and return a short int
+/*
+ * atom_asr - add and return a short int
  * @i: short value to add
  * @v: pointer of type atomic_short
  *
  * Atomically adds @i to @v and returns @i + @v
  */
-static inline int atomic_add_short_return(short i, struct atomic_short *v)
+static inline int atom_asr(short i, struct atomic_short *v)
 {
         short __i = i;
         asm volatile(LOCK_PREFIX "xaddw %0, %1"
@@ -494,4 +654,26 @@ static inline int atomic_add_short_return(short i, struct atomic_short *v)
         return i + __i;
 }
 
+/*
+ * conditionally add 1 to *v, unless *v is >= u
+ * return 0 if we cannot add 1 to *v because it is >= u
+ * return 1 if we can add 1 to *v because it is < u
+ * the add is atomic
+ *
+ * This is close to atomic_add_unless(), but this allows the 'u' value
+ * to be lowered below the current 'v'.  atomic_add_unless can only stop
+ * on equal.
+ */
+static inline int atomic_inc_unless_ge(spinlock_t *lock, atomic_t *v, int u)
+{
+        spin_lock(lock);
+        if (atomic_read(v) >= u) {
+                spin_unlock(lock);
+                return 0;
+        }
+        atomic_inc(v);
+        spin_unlock(lock);
+        return 1;
+}
+
 #endif /* _ASM_X86_UV_UV_BAU_H */
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 4298002d0c83..f26544a15214 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -77,8 +77,9 @@
  *
  *              1111110000000000
  *              5432109876543210
- *              pppppppppplc0cch        Nehalem-EX
- *              ppppppppplcc0cch        Westmere-EX
+ *              pppppppppplc0cch        Nehalem-EX (12 bits in hdw reg)
+ *              ppppppppplcc0cch        Westmere-EX (12 bits in hdw reg)
+ *              pppppppppppcccch        SandyBridge (15 bits in hdw reg)
  *              sssssssssss
  *
  *                      p  = pnode bits
@@ -87,7 +88,7 @@
  *                      h  = hyperthread
  *                      s  = bits that are in the SOCKET_ID CSR
  *
- *      Note: Processor only supports 12 bits in the APICID register. The ACPI
+ *      Note: Processor may support fewer bits in the APICID register. The ACPI
  *            tables hold all 16 bits. Software needs to be aware of this.
  *
  *            Unless otherwise specified, all references to APICID refer to
@@ -138,6 +139,8 @@ struct uv_hub_info_s {
         unsigned long           global_mmr_base;
         unsigned long           gpa_mask;
         unsigned int            gnode_extra;
+        unsigned char           hub_revision;
+        unsigned char           apic_pnode_shift;
         unsigned long           gnode_upper;
         unsigned long           lowmem_remap_top;
         unsigned long           lowmem_remap_base;
@@ -149,13 +152,31 @@ struct uv_hub_info_s {
         unsigned char           m_val;
         unsigned char           n_val;
         struct uv_scir_s        scir;
-        unsigned char           apic_pnode_shift;
 };
 
 DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
 #define uv_hub_info             (&__get_cpu_var(__uv_hub_info))
 #define uv_cpu_hub_info(cpu)    (&per_cpu(__uv_hub_info, cpu))
 
+/*
+ * Hub revisions less than UV2_HUB_REVISION_BASE are UV1 hubs. All UV2
+ * hubs have revision numbers greater than or equal to UV2_HUB_REVISION_BASE.
+ * This is a software convention - NOT the hardware revision numbers in
+ * the hub chip.
+ */
+#define UV1_HUB_REVISION_BASE           1
+#define UV2_HUB_REVISION_BASE           3
+
+static inline int is_uv1_hub(void)
+{
+        return uv_hub_info->hub_revision < UV2_HUB_REVISION_BASE;
+}
+
+static inline int is_uv2_hub(void)
+{
+        return uv_hub_info->hub_revision >= UV2_HUB_REVISION_BASE;
+}
+
 union uvh_apicid {
     unsigned long       v;
     struct uvh_apicid_s {
@@ -180,11 +201,25 @@ union uvh_apicid {
 #define UV_PNODE_TO_GNODE(p)            ((p) |uv_hub_info->gnode_extra)
 #define UV_PNODE_TO_NASID(p)            (UV_PNODE_TO_GNODE(p) << 1)
 
-#define UV_LOCAL_MMR_BASE               0xf4000000UL
-#define UV_GLOBAL_MMR32_BASE            0xf8000000UL
+#define UV1_LOCAL_MMR_BASE              0xf4000000UL
+#define UV1_GLOBAL_MMR32_BASE           0xf8000000UL
+#define UV1_LOCAL_MMR_SIZE              (64UL * 1024 * 1024)
+#define UV1_GLOBAL_MMR32_SIZE           (64UL * 1024 * 1024)
+
+#define UV2_LOCAL_MMR_BASE              0xfa000000UL
+#define UV2_GLOBAL_MMR32_BASE           0xfc000000UL
+#define UV2_LOCAL_MMR_SIZE              (32UL * 1024 * 1024)
+#define UV2_GLOBAL_MMR32_SIZE           (32UL * 1024 * 1024)
+
+#define UV_LOCAL_MMR_BASE               (is_uv1_hub() ? UV1_LOCAL_MMR_BASE     \
+                                                : UV2_LOCAL_MMR_BASE)
+#define UV_GLOBAL_MMR32_BASE            (is_uv1_hub() ? UV1_GLOBAL_MMR32_BASE  \
+                                                : UV2_GLOBAL_MMR32_BASE)
+#define UV_LOCAL_MMR_SIZE               (is_uv1_hub() ? UV1_LOCAL_MMR_SIZE :   \
+                                                UV2_LOCAL_MMR_SIZE)
+#define UV_GLOBAL_MMR32_SIZE            (is_uv1_hub() ? UV1_GLOBAL_MMR32_SIZE :\
+                                                UV2_GLOBAL_MMR32_SIZE)
 #define UV_GLOBAL_MMR64_BASE            (uv_hub_info->global_mmr_base)
-#define UV_LOCAL_MMR_SIZE               (64UL * 1024 * 1024)
-#define UV_GLOBAL_MMR32_SIZE            (64UL * 1024 * 1024)
 
 #define UV_GLOBAL_GRU_MMR_BASE          0x4000000
 
@@ -301,6 +336,17 @@ static inline int uv_apicid_to_pnode(int apicid)
 }
 
 /*
+ * Convert an apicid to the socket number on the blade
+ */
+static inline int uv_apicid_to_socket(int apicid)
+{
+        if (is_uv1_hub())
+                return (apicid >> (uv_hub_info->apic_pnode_shift - 1)) & 1;
+        else
+                return 0;
+}
+
+/*
  * Access global MMRs using the low memory MMR32 space. This region supports
  * faster MMR access but not all MMRs are accessible in this space.
  */
@@ -519,14 +565,13 @@ static inline void uv_hub_send_ipi(int pnode, int apicid, int vector)
 
 /*
  * Get the minimum revision number of the hub chips within the partition.
- *     1 - initial rev 1.0 silicon
- *     2 - rev 2.0 production silicon
+ *     1 - UV1 rev 1.0 initial silicon
+ *     2 - UV1 rev 2.0 production silicon
+ *     3 - UV2 rev 1.0 initial silicon
  */
 static inline int uv_get_min_hub_revision_id(void)
 {
-        extern int uv_min_hub_revision_id;
-
-        return uv_min_hub_revision_id;
+        return uv_hub_info->hub_revision;
 }
 
 #endif /* CONFIG_X86_64 */
diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h
index f5bb64a823d7..4be52c863448 100644
--- a/arch/x86/include/asm/uv/uv_mmrs.h
+++ b/arch/x86/include/asm/uv/uv_mmrs.h
@@ -11,13 +11,64 @@
 #ifndef _ASM_X86_UV_UV_MMRS_H
 #define _ASM_X86_UV_UV_MMRS_H
 
+/*
+ * This file contains MMR definitions for both UV1 & UV2 hubs.
+ *
+ * In general, MMR addresses and structures are identical on both hubs.
+ * These MMRs are identified as:
+ *      #define UVH_xxx         <address>
+ *      union uvh_xxx {
+ *              unsigned long       v;
+ *              struct uvh_int_cmpd_s {
+ *              } s;
+ *      };
+ *
+ * If the MMR exists on both hub type but has different addresses or
+ * contents, the MMR definition is similar to:
+ *      #define UV1H_xxx        <uv1 address>
+ *      #define UV2H_xxx        <uv2address>
+ *      #define UVH_xxx         (is_uv1_hub() ? UV1H_xxx : UV2H_xxx)
+ *      union uvh_xxx {
+ *              unsigned long       v;
+ *              struct uv1h_int_cmpd_s {         (Common fields only)
+ *              } s;
+ *              struct uv1h_int_cmpd_s {         (Full UV1 definition)
+ *              } s1;
+ *              struct uv2h_int_cmpd_s {         (Full UV2 definition)
+ *              } s2;
+ *      };
+ *
+ * Only essential difference are enumerated. For example, if the address is
+ * the same for both UV1 & UV2, only a single #define is generated. Likewise,
+ * if the contents is the same for both hubs, only the "s" structure is
+ * generated.
+ *
+ * If the MMR exists on ONLY 1 type of hub, no generic definition is
+ * generated:
+ *      #define UVnH_xxx        <uvn address>
+ *      union uvnh_xxx {
+ *              unsigned long       v;
+ *              struct uvh_int_cmpd_s {
+ *              } sn;
+ *      };
+ */
+
 #define UV_MMR_ENABLE           (1UL << 63)
 
+#define UV1_HUB_PART_NUMBER     0x88a5
+#define UV2_HUB_PART_NUMBER     0x8eb8
+
+/* Compat: if this #define is present, UV headers support UV2 */
+#define UV2_HUB_IS_SUPPORTED    1
+
+/* KABI compat: if this #define is present, KABI hacks are present */
+#define UV2_HUB_KABI_HACKS      1
+
 /* ========================================================================= */
 /*                          UVH_BAU_DATA_BROADCAST                           */
 /* ========================================================================= */
 #define UVH_BAU_DATA_BROADCAST 0x61688UL
-#define UVH_BAU_DATA_BROADCAST_32 0x0440
+#define UVH_BAU_DATA_BROADCAST_32 0x440
 
 #define UVH_BAU_DATA_BROADCAST_ENABLE_SHFT 0
 #define UVH_BAU_DATA_BROADCAST_ENABLE_MASK 0x0000000000000001UL
@@ -34,7 +85,7 @@ union uvh_bau_data_broadcast_u {
 /*                           UVH_BAU_DATA_CONFIG                             */
 /* ========================================================================= */
 #define UVH_BAU_DATA_CONFIG 0x61680UL
-#define UVH_BAU_DATA_CONFIG_32 0x0438
+#define UVH_BAU_DATA_CONFIG_32 0x438
 
 #define UVH_BAU_DATA_CONFIG_VECTOR_SHFT 0
 #define UVH_BAU_DATA_CONFIG_VECTOR_MASK 0x00000000000000ffUL
@@ -73,125 +124,245 @@ union uvh_bau_data_config_u {
 /*                           UVH_EVENT_OCCURRED0                             */
 /* ========================================================================= */
 #define UVH_EVENT_OCCURRED0 0x70000UL
-#define UVH_EVENT_OCCURRED0_32 0x005e8
-
-#define UVH_EVENT_OCCURRED0_LB_HCERR_SHFT 0
-#define UVH_EVENT_OCCURRED0_LB_HCERR_MASK 0x0000000000000001UL
-#define UVH_EVENT_OCCURRED0_GR0_HCERR_SHFT 1
-#define UVH_EVENT_OCCURRED0_GR0_HCERR_MASK 0x0000000000000002UL
-#define UVH_EVENT_OCCURRED0_GR1_HCERR_SHFT 2
-#define UVH_EVENT_OCCURRED0_GR1_HCERR_MASK 0x0000000000000004UL
-#define UVH_EVENT_OCCURRED0_LH_HCERR_SHFT 3
-#define UVH_EVENT_OCCURRED0_LH_HCERR_MASK 0x0000000000000008UL
-#define UVH_EVENT_OCCURRED0_RH_HCERR_SHFT 4
-#define UVH_EVENT_OCCURRED0_RH_HCERR_MASK 0x0000000000000010UL
-#define UVH_EVENT_OCCURRED0_XN_HCERR_SHFT 5
-#define UVH_EVENT_OCCURRED0_XN_HCERR_MASK 0x0000000000000020UL
-#define UVH_EVENT_OCCURRED0_SI_HCERR_SHFT 6
-#define UVH_EVENT_OCCURRED0_SI_HCERR_MASK 0x0000000000000040UL
-#define UVH_EVENT_OCCURRED0_LB_AOERR0_SHFT 7
-#define UVH_EVENT_OCCURRED0_LB_AOERR0_MASK 0x0000000000000080UL
-#define UVH_EVENT_OCCURRED0_GR0_AOERR0_SHFT 8
-#define UVH_EVENT_OCCURRED0_GR0_AOERR0_MASK 0x0000000000000100UL
-#define UVH_EVENT_OCCURRED0_GR1_AOERR0_SHFT 9
-#define UVH_EVENT_OCCURRED0_GR1_AOERR0_MASK 0x0000000000000200UL
-#define UVH_EVENT_OCCURRED0_LH_AOERR0_SHFT 10
-#define UVH_EVENT_OCCURRED0_LH_AOERR0_MASK 0x0000000000000400UL
-#define UVH_EVENT_OCCURRED0_RH_AOERR0_SHFT 11
-#define UVH_EVENT_OCCURRED0_RH_AOERR0_MASK 0x0000000000000800UL
-#define UVH_EVENT_OCCURRED0_XN_AOERR0_SHFT 12
-#define UVH_EVENT_OCCURRED0_XN_AOERR0_MASK 0x0000000000001000UL
-#define UVH_EVENT_OCCURRED0_SI_AOERR0_SHFT 13
-#define UVH_EVENT_OCCURRED0_SI_AOERR0_MASK 0x0000000000002000UL
-#define UVH_EVENT_OCCURRED0_LB_AOERR1_SHFT 14
-#define UVH_EVENT_OCCURRED0_LB_AOERR1_MASK 0x0000000000004000UL
-#define UVH_EVENT_OCCURRED0_GR0_AOERR1_SHFT 15
-#define UVH_EVENT_OCCURRED0_GR0_AOERR1_MASK 0x0000000000008000UL
-#define UVH_EVENT_OCCURRED0_GR1_AOERR1_SHFT 16
-#define UVH_EVENT_OCCURRED0_GR1_AOERR1_MASK 0x0000000000010000UL
-#define UVH_EVENT_OCCURRED0_LH_AOERR1_SHFT 17
-#define UVH_EVENT_OCCURRED0_LH_AOERR1_MASK 0x0000000000020000UL
-#define UVH_EVENT_OCCURRED0_RH_AOERR1_SHFT 18
-#define UVH_EVENT_OCCURRED0_RH_AOERR1_MASK 0x0000000000040000UL
-#define UVH_EVENT_OCCURRED0_XN_AOERR1_SHFT 19
-#define UVH_EVENT_OCCURRED0_XN_AOERR1_MASK 0x0000000000080000UL
-#define UVH_EVENT_OCCURRED0_SI_AOERR1_SHFT 20
-#define UVH_EVENT_OCCURRED0_SI_AOERR1_MASK 0x0000000000100000UL
-#define UVH_EVENT_OCCURRED0_RH_VPI_INT_SHFT 21
-#define UVH_EVENT_OCCURRED0_RH_VPI_INT_MASK 0x0000000000200000UL
-#define UVH_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_SHFT 22
-#define UVH_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_MASK 0x0000000000400000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_0_SHFT 23
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_0_MASK 0x0000000000800000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_1_SHFT 24
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_1_MASK 0x0000000001000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_2_SHFT 25
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_2_MASK 0x0000000002000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_3_SHFT 26
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_3_MASK 0x0000000004000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_4_SHFT 27
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_4_MASK 0x0000000008000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_5_SHFT 28
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_5_MASK 0x0000000010000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_6_SHFT 29
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_6_MASK 0x0000000020000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_7_SHFT 30
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_7_MASK 0x0000000040000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_8_SHFT 31
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_8_MASK 0x0000000080000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_9_SHFT 32
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_9_MASK 0x0000000100000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_10_SHFT 33
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_10_MASK 0x0000000200000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_11_SHFT 34
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_11_MASK 0x0000000400000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_12_SHFT 35
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_12_MASK 0x0000000800000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_13_SHFT 36
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_13_MASK 0x0000001000000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_14_SHFT 37
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_14_MASK 0x0000002000000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_15_SHFT 38
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_15_MASK 0x0000004000000000UL
-#define UVH_EVENT_OCCURRED0_L1_NMI_INT_SHFT 39
-#define UVH_EVENT_OCCURRED0_L1_NMI_INT_MASK 0x0000008000000000UL
-#define UVH_EVENT_OCCURRED0_STOP_CLOCK_SHFT 40
-#define UVH_EVENT_OCCURRED0_STOP_CLOCK_MASK 0x0000010000000000UL
-#define UVH_EVENT_OCCURRED0_ASIC_TO_L1_SHFT 41
-#define UVH_EVENT_OCCURRED0_ASIC_TO_L1_MASK 0x0000020000000000UL
-#define UVH_EVENT_OCCURRED0_L1_TO_ASIC_SHFT 42
-#define UVH_EVENT_OCCURRED0_L1_TO_ASIC_MASK 0x0000040000000000UL
-#define UVH_EVENT_OCCURRED0_LTC_INT_SHFT 43
-#define UVH_EVENT_OCCURRED0_LTC_INT_MASK 0x0000080000000000UL
-#define UVH_EVENT_OCCURRED0_LA_SEQ_TRIGGER_SHFT 44
-#define UVH_EVENT_OCCURRED0_LA_SEQ_TRIGGER_MASK 0x0000100000000000UL
-#define UVH_EVENT_OCCURRED0_IPI_INT_SHFT 45
-#define UVH_EVENT_OCCURRED0_IPI_INT_MASK 0x0000200000000000UL
-#define UVH_EVENT_OCCURRED0_EXTIO_INT0_SHFT 46
-#define UVH_EVENT_OCCURRED0_EXTIO_INT0_MASK 0x0000400000000000UL
-#define UVH_EVENT_OCCURRED0_EXTIO_INT1_SHFT 47
-#define UVH_EVENT_OCCURRED0_EXTIO_INT1_MASK 0x0000800000000000UL
-#define UVH_EVENT_OCCURRED0_EXTIO_INT2_SHFT 48
-#define UVH_EVENT_OCCURRED0_EXTIO_INT2_MASK 0x0001000000000000UL
-#define UVH_EVENT_OCCURRED0_EXTIO_INT3_SHFT 49
-#define UVH_EVENT_OCCURRED0_EXTIO_INT3_MASK 0x0002000000000000UL
-#define UVH_EVENT_OCCURRED0_PROFILE_INT_SHFT 50
-#define UVH_EVENT_OCCURRED0_PROFILE_INT_MASK 0x0004000000000000UL
-#define UVH_EVENT_OCCURRED0_RTC0_SHFT 51
-#define UVH_EVENT_OCCURRED0_RTC0_MASK 0x0008000000000000UL
-#define UVH_EVENT_OCCURRED0_RTC1_SHFT 52
-#define UVH_EVENT_OCCURRED0_RTC1_MASK 0x0010000000000000UL
-#define UVH_EVENT_OCCURRED0_RTC2_SHFT 53
-#define UVH_EVENT_OCCURRED0_RTC2_MASK 0x0020000000000000UL
-#define UVH_EVENT_OCCURRED0_RTC3_SHFT 54
-#define UVH_EVENT_OCCURRED0_RTC3_MASK 0x0040000000000000UL
-#define UVH_EVENT_OCCURRED0_BAU_DATA_SHFT 55
-#define UVH_EVENT_OCCURRED0_BAU_DATA_MASK 0x0080000000000000UL
-#define UVH_EVENT_OCCURRED0_POWER_MANAGEMENT_REQ_SHFT 56
-#define UVH_EVENT_OCCURRED0_POWER_MANAGEMENT_REQ_MASK 0x0100000000000000UL
+#define UVH_EVENT_OCCURRED0_32 0x5e8
+
+#define UV1H_EVENT_OCCURRED0_LB_HCERR_SHFT 0
+#define UV1H_EVENT_OCCURRED0_LB_HCERR_MASK 0x0000000000000001UL
+#define UV1H_EVENT_OCCURRED0_GR0_HCERR_SHFT 1
+#define UV1H_EVENT_OCCURRED0_GR0_HCERR_MASK 0x0000000000000002UL
+#define UV1H_EVENT_OCCURRED0_GR1_HCERR_SHFT 2
+#define UV1H_EVENT_OCCURRED0_GR1_HCERR_MASK 0x0000000000000004UL
+#define UV1H_EVENT_OCCURRED0_LH_HCERR_SHFT 3
+#define UV1H_EVENT_OCCURRED0_LH_HCERR_MASK 0x0000000000000008UL
+#define UV1H_EVENT_OCCURRED0_RH_HCERR_SHFT 4
+#define UV1H_EVENT_OCCURRED0_RH_HCERR_MASK 0x0000000000000010UL
+#define UV1H_EVENT_OCCURRED0_XN_HCERR_SHFT 5
+#define UV1H_EVENT_OCCURRED0_XN_HCERR_MASK 0x0000000000000020UL
+#define UV1H_EVENT_OCCURRED0_SI_HCERR_SHFT 6
+#define UV1H_EVENT_OCCURRED0_SI_HCERR_MASK 0x0000000000000040UL
+#define UV1H_EVENT_OCCURRED0_LB_AOERR0_SHFT 7
+#define UV1H_EVENT_OCCURRED0_LB_AOERR0_MASK 0x0000000000000080UL
+#define UV1H_EVENT_OCCURRED0_GR0_AOERR0_SHFT 8
+#define UV1H_EVENT_OCCURRED0_GR0_AOERR0_MASK 0x0000000000000100UL
+#define UV1H_EVENT_OCCURRED0_GR1_AOERR0_SHFT 9
+#define UV1H_EVENT_OCCURRED0_GR1_AOERR0_MASK 0x0000000000000200UL
+#define UV1H_EVENT_OCCURRED0_LH_AOERR0_SHFT 10
+#define UV1H_EVENT_OCCURRED0_LH_AOERR0_MASK 0x0000000000000400UL
+#define UV1H_EVENT_OCCURRED0_RH_AOERR0_SHFT 11
+#define UV1H_EVENT_OCCURRED0_RH_AOERR0_MASK 0x0000000000000800UL
+#define UV1H_EVENT_OCCURRED0_XN_AOERR0_SHFT 12
+#define UV1H_EVENT_OCCURRED0_XN_AOERR0_MASK 0x0000000000001000UL
+#define UV1H_EVENT_OCCURRED0_SI_AOERR0_SHFT 13
+#define UV1H_EVENT_OCCURRED0_SI_AOERR0_MASK 0x0000000000002000UL
+#define UV1H_EVENT_OCCURRED0_LB_AOERR1_SHFT 14
+#define UV1H_EVENT_OCCURRED0_LB_AOERR1_MASK 0x0000000000004000UL
+#define UV1H_EVENT_OCCURRED0_GR0_AOERR1_SHFT 15
+#define UV1H_EVENT_OCCURRED0_GR0_AOERR1_MASK 0x0000000000008000UL
+#define UV1H_EVENT_OCCURRED0_GR1_AOERR1_SHFT 16
+#define UV1H_EVENT_OCCURRED0_GR1_AOERR1_MASK 0x0000000000010000UL
+#define UV1H_EVENT_OCCURRED0_LH_AOERR1_SHFT 17
+#define UV1H_EVENT_OCCURRED0_LH_AOERR1_MASK 0x0000000000020000UL
+#define UV1H_EVENT_OCCURRED0_RH_AOERR1_SHFT 18
+#define UV1H_EVENT_OCCURRED0_RH_AOERR1_MASK 0x0000000000040000UL
+#define UV1H_EVENT_OCCURRED0_XN_AOERR1_SHFT 19
+#define UV1H_EVENT_OCCURRED0_XN_AOERR1_MASK 0x0000000000080000UL
+#define UV1H_EVENT_OCCURRED0_SI_AOERR1_SHFT 20
+#define UV1H_EVENT_OCCURRED0_SI_AOERR1_MASK 0x0000000000100000UL
+#define UV1H_EVENT_OCCURRED0_RH_VPI_INT_SHFT 21
+#define UV1H_EVENT_OCCURRED0_RH_VPI_INT_MASK 0x0000000000200000UL
+#define UV1H_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_SHFT 22
+#define UV1H_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_MASK 0x0000000000400000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_0_SHFT 23
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_0_MASK 0x0000000000800000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_1_SHFT 24
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_1_MASK 0x0000000001000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_2_SHFT 25
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_2_MASK 0x0000000002000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_3_SHFT 26
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_3_MASK 0x0000000004000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_4_SHFT 27
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_4_MASK 0x0000000008000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_5_SHFT 28
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_5_MASK 0x0000000010000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_6_SHFT 29
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_6_MASK 0x0000000020000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_7_SHFT 30
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_7_MASK 0x0000000040000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_8_SHFT 31
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_8_MASK 0x0000000080000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_9_SHFT 32
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_9_MASK 0x0000000100000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_10_SHFT 33
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_10_MASK 0x0000000200000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_11_SHFT 34
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_11_MASK 0x0000000400000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_12_SHFT 35
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_12_MASK 0x0000000800000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_13_SHFT 36
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_13_MASK 0x0000001000000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_14_SHFT 37
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_14_MASK 0x0000002000000000UL
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_15_SHFT 38
+#define UV1H_EVENT_OCCURRED0_LB_IRQ_INT_15_MASK 0x0000004000000000UL
+#define UV1H_EVENT_OCCURRED0_L1_NMI_INT_SHFT 39
+#define UV1H_EVENT_OCCURRED0_L1_NMI_INT_MASK 0x0000008000000000UL
+#define UV1H_EVENT_OCCURRED0_STOP_CLOCK_SHFT 40
+#define UV1H_EVENT_OCCURRED0_STOP_CLOCK_MASK 0x0000010000000000UL
+#define UV1H_EVENT_OCCURRED0_ASIC_TO_L1_SHFT 41
+#define UV1H_EVENT_OCCURRED0_ASIC_TO_L1_MASK 0x0000020000000000UL
+#define UV1H_EVENT_OCCURRED0_L1_TO_ASIC_SHFT 42
+#define UV1H_EVENT_OCCURRED0_L1_TO_ASIC_MASK 0x0000040000000000UL
+#define UV1H_EVENT_OCCURRED0_LTC_INT_SHFT 43
+#define UV1H_EVENT_OCCURRED0_LTC_INT_MASK 0x0000080000000000UL
+#define UV1H_EVENT_OCCURRED0_LA_SEQ_TRIGGER_SHFT 44
+#define UV1H_EVENT_OCCURRED0_LA_SEQ_TRIGGER_MASK 0x0000100000000000UL
+#define UV1H_EVENT_OCCURRED0_IPI_INT_SHFT 45
+#define UV1H_EVENT_OCCURRED0_IPI_INT_MASK 0x0000200000000000UL
+#define UV1H_EVENT_OCCURRED0_EXTIO_INT0_SHFT 46
+#define UV1H_EVENT_OCCURRED0_EXTIO_INT0_MASK 0x0000400000000000UL
+#define UV1H_EVENT_OCCURRED0_EXTIO_INT1_SHFT 47
+#define UV1H_EVENT_OCCURRED0_EXTIO_INT1_MASK 0x0000800000000000UL
+#define UV1H_EVENT_OCCURRED0_EXTIO_INT2_SHFT 48
+#define UV1H_EVENT_OCCURRED0_EXTIO_INT2_MASK 0x0001000000000000UL
+#define UV1H_EVENT_OCCURRED0_EXTIO_INT3_SHFT 49
+#define UV1H_EVENT_OCCURRED0_EXTIO_INT3_MASK 0x0002000000000000UL
+#define UV1H_EVENT_OCCURRED0_PROFILE_INT_SHFT 50
+#define UV1H_EVENT_OCCURRED0_PROFILE_INT_MASK 0x0004000000000000UL
+#define UV1H_EVENT_OCCURRED0_RTC0_SHFT 51
+#define UV1H_EVENT_OCCURRED0_RTC0_MASK 0x0008000000000000UL
+#define UV1H_EVENT_OCCURRED0_RTC1_SHFT 52
+#define UV1H_EVENT_OCCURRED0_RTC1_MASK 0x0010000000000000UL
+#define UV1H_EVENT_OCCURRED0_RTC2_SHFT 53
+#define UV1H_EVENT_OCCURRED0_RTC2_MASK 0x0020000000000000UL
+#define UV1H_EVENT_OCCURRED0_RTC3_SHFT 54
+#define UV1H_EVENT_OCCURRED0_RTC3_MASK 0x0040000000000000UL
+#define UV1H_EVENT_OCCURRED0_BAU_DATA_SHFT 55
+#define UV1H_EVENT_OCCURRED0_BAU_DATA_MASK 0x0080000000000000UL
+#define UV1H_EVENT_OCCURRED0_POWER_MANAGEMENT_REQ_SHFT 56
+#define UV1H_EVENT_OCCURRED0_POWER_MANAGEMENT_REQ_MASK 0x0100000000000000UL
+
+#define UV2H_EVENT_OCCURRED0_LB_HCERR_SHFT 0
+#define UV2H_EVENT_OCCURRED0_LB_HCERR_MASK 0x0000000000000001UL
+#define UV2H_EVENT_OCCURRED0_QP_HCERR_SHFT 1
+#define UV2H_EVENT_OCCURRED0_QP_HCERR_MASK 0x0000000000000002UL
+#define UV2H_EVENT_OCCURRED0_RH_HCERR_SHFT 2
+#define UV2H_EVENT_OCCURRED0_RH_HCERR_MASK 0x0000000000000004UL
+#define UV2H_EVENT_OCCURRED0_LH0_HCERR_SHFT 3
+#define UV2H_EVENT_OCCURRED0_LH0_HCERR_MASK 0x0000000000000008UL
+#define UV2H_EVENT_OCCURRED0_LH1_HCERR_SHFT 4
+#define UV2H_EVENT_OCCURRED0_LH1_HCERR_MASK 0x0000000000000010UL
+#define UV2H_EVENT_OCCURRED0_GR0_HCERR_SHFT 5
+#define UV2H_EVENT_OCCURRED0_GR0_HCERR_MASK 0x0000000000000020UL
+#define UV2H_EVENT_OCCURRED0_GR1_HCERR_SHFT 6
+#define UV2H_EVENT_OCCURRED0_GR1_HCERR_MASK 0x0000000000000040UL
+#define UV2H_EVENT_OCCURRED0_NI0_HCERR_SHFT 7
+#define UV2H_EVENT_OCCURRED0_NI0_HCERR_MASK 0x0000000000000080UL
+#define UV2H_EVENT_OCCURRED0_NI1_HCERR_SHFT 8
+#define UV2H_EVENT_OCCURRED0_NI1_HCERR_MASK 0x0000000000000100UL
+#define UV2H_EVENT_OCCURRED0_LB_AOERR0_SHFT 9
+#define UV2H_EVENT_OCCURRED0_LB_AOERR0_MASK 0x0000000000000200UL
+#define UV2H_EVENT_OCCURRED0_QP_AOERR0_SHFT 10
+#define UV2H_EVENT_OCCURRED0_QP_AOERR0_MASK 0x0000000000000400UL
+#define UV2H_EVENT_OCCURRED0_RH_AOERR0_SHFT 11
+#define UV2H_EVENT_OCCURRED0_RH_AOERR0_MASK 0x0000000000000800UL
+#define UV2H_EVENT_OCCURRED0_LH0_AOERR0_SHFT 12
+#define UV2H_EVENT_OCCURRED0_LH0_AOERR0_MASK 0x0000000000001000UL
+#define UV2H_EVENT_OCCURRED0_LH1_AOERR0_SHFT 13
+#define UV2H_EVENT_OCCURRED0_LH1_AOERR0_MASK 0x0000000000002000UL
+#define UV2H_EVENT_OCCURRED0_GR0_AOERR0_SHFT 14
+#define UV2H_EVENT_OCCURRED0_GR0_AOERR0_MASK 0x0000000000004000UL
+#define UV2H_EVENT_OCCURRED0_GR1_AOERR0_SHFT 15
+#define UV2H_EVENT_OCCURRED0_GR1_AOERR0_MASK 0x0000000000008000UL
+#define UV2H_EVENT_OCCURRED0_XB_AOERR0_SHFT 16
+#define UV2H_EVENT_OCCURRED0_XB_AOERR0_MASK 0x0000000000010000UL
+#define UV2H_EVENT_OCCURRED0_RT_AOERR0_SHFT 17
+#define UV2H_EVENT_OCCURRED0_RT_AOERR0_MASK 0x0000000000020000UL
+#define UV2H_EVENT_OCCURRED0_NI0_AOERR0_SHFT 18
+#define UV2H_EVENT_OCCURRED0_NI0_AOERR0_MASK 0x0000000000040000UL
+#define UV2H_EVENT_OCCURRED0_NI1_AOERR0_SHFT 19
+#define UV2H_EVENT_OCCURRED0_NI1_AOERR0_MASK 0x0000000000080000UL
+#define UV2H_EVENT_OCCURRED0_LB_AOERR1_SHFT 20
+#define UV2H_EVENT_OCCURRED0_LB_AOERR1_MASK 0x0000000000100000UL
+#define UV2H_EVENT_OCCURRED0_QP_AOERR1_SHFT 21
+#define UV2H_EVENT_OCCURRED0_QP_AOERR1_MASK 0x0000000000200000UL
+#define UV2H_EVENT_OCCURRED0_RH_AOERR1_SHFT 22
+#define UV2H_EVENT_OCCURRED0_RH_AOERR1_MASK 0x0000000000400000UL
+#define UV2H_EVENT_OCCURRED0_LH0_AOERR1_SHFT 23
+#define UV2H_EVENT_OCCURRED0_LH0_AOERR1_MASK 0x0000000000800000UL
+#define UV2H_EVENT_OCCURRED0_LH1_AOERR1_SHFT 24
+#define UV2H_EVENT_OCCURRED0_LH1_AOERR1_MASK 0x0000000001000000UL
+#define UV2H_EVENT_OCCURRED0_GR0_AOERR1_SHFT 25
+#define UV2H_EVENT_OCCURRED0_GR0_AOERR1_MASK 0x0000000002000000UL
+#define UV2H_EVENT_OCCURRED0_GR1_AOERR1_SHFT 26
+#define UV2H_EVENT_OCCURRED0_GR1_AOERR1_MASK 0x0000000004000000UL
+#define UV2H_EVENT_OCCURRED0_XB_AOERR1_SHFT 27
+#define UV2H_EVENT_OCCURRED0_XB_AOERR1_MASK 0x0000000008000000UL
+#define UV2H_EVENT_OCCURRED0_RT_AOERR1_SHFT 28
+#define UV2H_EVENT_OCCURRED0_RT_AOERR1_MASK 0x0000000010000000UL
+#define UV2H_EVENT_OCCURRED0_NI0_AOERR1_SHFT 29
+#define UV2H_EVENT_OCCURRED0_NI0_AOERR1_MASK 0x0000000020000000UL
+#define UV2H_EVENT_OCCURRED0_NI1_AOERR1_SHFT 30
+#define UV2H_EVENT_OCCURRED0_NI1_AOERR1_MASK 0x0000000040000000UL
+#define UV2H_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_SHFT 31
+#define UV2H_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_MASK 0x0000000080000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_0_SHFT 32
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_0_MASK 0x0000000100000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_1_SHFT 33
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_1_MASK 0x0000000200000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_2_SHFT 34
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_2_MASK 0x0000000400000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_3_SHFT 35
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_3_MASK 0x0000000800000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_4_SHFT 36
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_4_MASK 0x0000001000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_5_SHFT 37
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_5_MASK 0x0000002000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_6_SHFT 38
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_6_MASK 0x0000004000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_7_SHFT 39
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_7_MASK 0x0000008000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_8_SHFT 40
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_8_MASK 0x0000010000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_9_SHFT 41
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_9_MASK 0x0000020000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_10_SHFT 42
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_10_MASK 0x0000040000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_11_SHFT 43
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_11_MASK 0x0000080000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_12_SHFT 44
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_12_MASK 0x0000100000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_13_SHFT 45
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_13_MASK 0x0000200000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_14_SHFT 46
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_14_MASK 0x0000400000000000UL
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_15_SHFT 47
+#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_15_MASK 0x0000800000000000UL
+#define UV2H_EVENT_OCCURRED0_L1_NMI_INT_SHFT 48
+#define UV2H_EVENT_OCCURRED0_L1_NMI_INT_MASK 0x0001000000000000UL
+#define UV2H_EVENT_OCCURRED0_STOP_CLOCK_SHFT 49
+#define UV2H_EVENT_OCCURRED0_STOP_CLOCK_MASK 0x0002000000000000UL
+#define UV2H_EVENT_OCCURRED0_ASIC_TO_L1_SHFT 50
+#define UV2H_EVENT_OCCURRED0_ASIC_TO_L1_MASK 0x0004000000000000UL
+#define UV2H_EVENT_OCCURRED0_L1_TO_ASIC_SHFT 51
+#define UV2H_EVENT_OCCURRED0_L1_TO_ASIC_MASK 0x0008000000000000UL
+#define UV2H_EVENT_OCCURRED0_LA_SEQ_TRIGGER_SHFT 52
+#define UV2H_EVENT_OCCURRED0_LA_SEQ_TRIGGER_MASK 0x0010000000000000UL
+#define UV2H_EVENT_OCCURRED0_IPI_INT_SHFT 53
+#define UV2H_EVENT_OCCURRED0_IPI_INT_MASK 0x0020000000000000UL
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT0_SHFT 54
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT0_MASK 0x0040000000000000UL
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT1_SHFT 55
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT1_MASK 0x0080000000000000UL
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT2_SHFT 56
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT2_MASK 0x0100000000000000UL
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT3_SHFT 57
+#define UV2H_EVENT_OCCURRED0_EXTIO_INT3_MASK 0x0200000000000000UL
+#define UV2H_EVENT_OCCURRED0_PROFILE_INT_SHFT 58
+#define UV2H_EVENT_OCCURRED0_PROFILE_INT_MASK 0x0400000000000000UL
+
 union uvh_event_occurred0_u {
     unsigned long       v;
-    struct uvh_event_occurred0_s {
+    struct uv1h_event_occurred0_s {
         unsigned long   lb_hcerr             :  1;  /* RW, W1C */
         unsigned long   gr0_hcerr            :  1;  /* RW, W1C */
         unsigned long   gr1_hcerr            :  1;  /* RW, W1C */
@@ -250,14 +421,76 @@ union uvh_event_occurred0_u {
         unsigned long   bau_data             :  1;  /* RW, W1C */
         unsigned long   power_management_req :  1;  /* RW, W1C */
         unsigned long   rsvd_57_63           :  7;  /*    */
-    } s;
+    } s1;
+    struct uv2h_event_occurred0_s {
+        unsigned long   lb_hcerr            :  1;  /* RW */
+        unsigned long   qp_hcerr            :  1;  /* RW */
+        unsigned long   rh_hcerr            :  1;  /* RW */
+        unsigned long   lh0_hcerr           :  1;  /* RW */
+        unsigned long   lh1_hcerr           :  1;  /* RW */
+        unsigned long   gr0_hcerr           :  1;  /* RW */
+        unsigned long   gr1_hcerr           :  1;  /* RW */
+        unsigned long   ni0_hcerr           :  1;  /* RW */
+        unsigned long   ni1_hcerr           :  1;  /* RW */
+        unsigned long   lb_aoerr0           :  1;  /* RW */
+        unsigned long   qp_aoerr0           :  1;  /* RW */
+        unsigned long   rh_aoerr0           :  1;  /* RW */
+        unsigned long   lh0_aoerr0          :  1;  /* RW */
+        unsigned long   lh1_aoerr0          :  1;  /* RW */
+        unsigned long   gr0_aoerr0          :  1;  /* RW */
+        unsigned long   gr1_aoerr0          :  1;  /* RW */
+        unsigned long   xb_aoerr0           :  1;  /* RW */
+        unsigned long   rt_aoerr0           :  1;  /* RW */
+        unsigned long   ni0_aoerr0          :  1;  /* RW */
+        unsigned long   ni1_aoerr0          :  1;  /* RW */
+        unsigned long   lb_aoerr1           :  1;  /* RW */
+        unsigned long   qp_aoerr1           :  1;  /* RW */
+        unsigned long   rh_aoerr1           :  1;  /* RW */
+        unsigned long   lh0_aoerr1          :  1;  /* RW */
+        unsigned long   lh1_aoerr1          :  1;  /* RW */
+        unsigned long   gr0_aoerr1          :  1;  /* RW */
+        unsigned long   gr1_aoerr1          :  1;  /* RW */
+        unsigned long   xb_aoerr1           :  1;  /* RW */
+        unsigned long   rt_aoerr1           :  1;  /* RW */
+        unsigned long   ni0_aoerr1          :  1;  /* RW */
+        unsigned long   ni1_aoerr1          :  1;  /* RW */
+        unsigned long   system_shutdown_int :  1;  /* RW */
+        unsigned long   lb_irq_int_0        :  1;  /* RW */
+        unsigned long   lb_irq_int_1        :  1;  /* RW */
+        unsigned long   lb_irq_int_2        :  1;  /* RW */
+        unsigned long   lb_irq_int_3        :  1;  /* RW */
+        unsigned long   lb_irq_int_4        :  1;  /* RW */
+        unsigned long   lb_irq_int_5        :  1;  /* RW */
+        unsigned long   lb_irq_int_6        :  1;  /* RW */
+        unsigned long   lb_irq_int_7        :  1;  /* RW */
+        unsigned long   lb_irq_int_8        :  1;  /* RW */
+        unsigned long   lb_irq_int_9        :  1;  /* RW */
+        unsigned long   lb_irq_int_10       :  1;  /* RW */
+        unsigned long   lb_irq_int_11       :  1;  /* RW */
+        unsigned long   lb_irq_int_12       :  1;  /* RW */
+        unsigned long   lb_irq_int_13       :  1;  /* RW */
+        unsigned long   lb_irq_int_14       :  1;  /* RW */
+        unsigned long   lb_irq_int_15       :  1;  /* RW */
+        unsigned long   l1_nmi_int          :  1;  /* RW */
+        unsigned long   stop_clock          :  1;  /* RW */
+        unsigned long   asic_to_l1          :  1;  /* RW */
+        unsigned long   l1_to_asic          :  1;  /* RW */
+        unsigned long   la_seq_trigger      :  1;  /* RW */
+        unsigned long   ipi_int             :  1;  /* RW */
+        unsigned long   extio_int0          :  1;  /* RW */
+        unsigned long   extio_int1          :  1;  /* RW */
+        unsigned long   extio_int2          :  1;  /* RW */
+        unsigned long   extio_int3          :  1;  /* RW */
+        unsigned long   profile_int         :  1;  /* RW */
+        unsigned long   rsvd_59_63          :  5;  /*    */
+    } s2;
 };
 
 /* ========================================================================= */
 /*                        UVH_EVENT_OCCURRED0_ALIAS                          */
 /* ========================================================================= */
 #define UVH_EVENT_OCCURRED0_ALIAS 0x0000000000070008UL
-#define UVH_EVENT_OCCURRED0_ALIAS_32 0x005f0
+#define UVH_EVENT_OCCURRED0_ALIAS_32 0x5f0
 
 /* ========================================================================= */
 /*                         UVH_GR0_TLB_INT0_CONFIG                           */
@@ -432,8 +665,16 @@ union uvh_int_cmpb_u {
 /* ========================================================================= */
 #define UVH_INT_CMPC 0x22100UL
 
-#define UVH_INT_CMPC_REAL_TIME_CMPC_SHFT 0
-#define UVH_INT_CMPC_REAL_TIME_CMPC_MASK 0x00ffffffffffffffUL
+#define UV1H_INT_CMPC_REAL_TIME_CMPC_SHFT       0
+#define UV2H_INT_CMPC_REAL_TIME_CMPC_SHFT       0
+#define UVH_INT_CMPC_REAL_TIME_CMPC_SHFT        (is_uv1_hub() ?         \
+                        UV1H_INT_CMPC_REAL_TIME_CMPC_SHFT :     \
+                        UV2H_INT_CMPC_REAL_TIME_CMPC_SHFT)
+#define UV1H_INT_CMPC_REAL_TIME_CMPC_MASK       0xffffffffffffffUL
+#define UV2H_INT_CMPC_REAL_TIME_CMPC_MASK       0xffffffffffffffUL
+#define UVH_INT_CMPC_REAL_TIME_CMPC_MASK        (is_uv1_hub() ?         \
+                        UV1H_INT_CMPC_REAL_TIME_CMPC_MASK :     \
+                        UV2H_INT_CMPC_REAL_TIME_CMPC_MASK)
 
 union uvh_int_cmpc_u {
     unsigned long       v;
@@ -448,8 +689,16 @@ union uvh_int_cmpc_u {
 /* ========================================================================= */
 #define UVH_INT_CMPD 0x22180UL
 
-#define UVH_INT_CMPD_REAL_TIME_CMPD_SHFT 0
-#define UVH_INT_CMPD_REAL_TIME_CMPD_MASK 0x00ffffffffffffffUL
+#define UV1H_INT_CMPD_REAL_TIME_CMPD_SHFT       0
+#define UV2H_INT_CMPD_REAL_TIME_CMPD_SHFT       0
+#define UVH_INT_CMPD_REAL_TIME_CMPD_SHFT        (is_uv1_hub() ?         \
+                        UV1H_INT_CMPD_REAL_TIME_CMPD_SHFT :     \
+                        UV2H_INT_CMPD_REAL_TIME_CMPD_SHFT)
+#define UV1H_INT_CMPD_REAL_TIME_CMPD_MASK       0xffffffffffffffUL
+#define UV2H_INT_CMPD_REAL_TIME_CMPD_MASK       0xffffffffffffffUL
+#define UVH_INT_CMPD_REAL_TIME_CMPD_MASK        (is_uv1_hub() ?         \
+                        UV1H_INT_CMPD_REAL_TIME_CMPD_MASK :     \
+                        UV2H_INT_CMPD_REAL_TIME_CMPD_MASK)
 
 union uvh_int_cmpd_u {
     unsigned long       v;
@@ -463,7 +712,7 @@ union uvh_int_cmpd_u {
 /*                               UVH_IPI_INT                                 */
 /* ========================================================================= */
 #define UVH_IPI_INT 0x60500UL
-#define UVH_IPI_INT_32 0x0348
+#define UVH_IPI_INT_32 0x348
 
 #define UVH_IPI_INT_VECTOR_SHFT 0
 #define UVH_IPI_INT_VECTOR_MASK 0x00000000000000ffUL
@@ -493,7 +742,7 @@ union uvh_ipi_int_u {
 /*                   UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST                     */
 /* ========================================================================= */
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST 0x320050UL
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_32 0x009c0
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_32 0x9c0
 
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_ADDRESS_SHFT 4
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_ADDRESS_MASK 0x000007fffffffff0UL
@@ -515,7 +764,7 @@ union uvh_lb_bau_intd_payload_queue_first_u {
 /*                    UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST                     */
 /* ========================================================================= */
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST 0x320060UL
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_32 0x009c8
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_32 0x9c8
 
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_ADDRESS_SHFT 4
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_ADDRESS_MASK 0x000007fffffffff0UL
@@ -533,7 +782,7 @@ union uvh_lb_bau_intd_payload_queue_last_u {
 /*                    UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL                     */
 /* ========================================================================= */
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL 0x320070UL
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_32 0x009d0
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_32 0x9d0
 
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_ADDRESS_SHFT 4
 #define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_ADDRESS_MASK 0x000007fffffffff0UL
@@ -551,7 +800,7 @@ union uvh_lb_bau_intd_payload_queue_tail_u {
 /*                   UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE                    */
 /* ========================================================================= */
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE 0x320080UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_32 0x0a68
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_32 0xa68
 
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_0_SHFT 0
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_0_MASK 0x0000000000000001UL
@@ -585,6 +834,7 @@ union uvh_lb_bau_intd_payload_queue_tail_u {
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_6_MASK 0x0000000000004000UL
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_7_SHFT 15
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_7_MASK 0x0000000000008000UL
+
 union uvh_lb_bau_intd_software_acknowledge_u {
     unsigned long       v;
     struct uvh_lb_bau_intd_software_acknowledge_s {
@@ -612,13 +862,13 @@ union uvh_lb_bau_intd_software_acknowledge_u {
 /*                UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS                 */
 /* ========================================================================= */
 #define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS 0x0000000000320088UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS_32 0x0a70
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS_32 0xa70
 
 /* ========================================================================= */
 /*                         UVH_LB_BAU_MISC_CONTROL                           */
 /* ========================================================================= */
 #define UVH_LB_BAU_MISC_CONTROL 0x320170UL
-#define UVH_LB_BAU_MISC_CONTROL_32 0x00a10
+#define UVH_LB_BAU_MISC_CONTROL_32 0xa10
 
 #define UVH_LB_BAU_MISC_CONTROL_REJECTION_DELAY_SHFT 0
 #define UVH_LB_BAU_MISC_CONTROL_REJECTION_DELAY_MASK 0x00000000000000ffUL
@@ -628,8 +878,8 @@ union uvh_lb_bau_intd_software_acknowledge_u {
 #define UVH_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_MASK 0x0000000000000200UL
 #define UVH_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_SHFT 10
 #define UVH_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_MASK 0x0000000000000400UL
-#define UVH_LB_BAU_MISC_CONTROL_CSI_AGENT_PRESENCE_VECTOR_SHFT 11
-#define UVH_LB_BAU_MISC_CONTROL_CSI_AGENT_PRESENCE_VECTOR_MASK 0x0000000000003800UL
+#define UVH_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_SHFT 11
+#define UVH_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_MASK 0x0000000000003800UL
 #define UVH_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_SHFT 14
 #define UVH_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_MASK 0x0000000000004000UL
 #define UVH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT 15
@@ -650,8 +900,86 @@ union uvh_lb_bau_intd_software_acknowledge_u {
 #define UVH_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_MASK 0x0000000008000000UL
 #define UVH_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_SHFT 28
 #define UVH_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000010000000UL
-#define UVH_LB_BAU_MISC_CONTROL_FUN_SHFT 48
-#define UVH_LB_BAU_MISC_CONTROL_FUN_MASK 0xffff000000000000UL
+
+#define UV1H_LB_BAU_MISC_CONTROL_REJECTION_DELAY_SHFT 0
+#define UV1H_LB_BAU_MISC_CONTROL_REJECTION_DELAY_MASK 0x00000000000000ffUL
+#define UV1H_LB_BAU_MISC_CONTROL_APIC_MODE_SHFT 8
+#define UV1H_LB_BAU_MISC_CONTROL_APIC_MODE_MASK 0x0000000000000100UL
+#define UV1H_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_SHFT 9
+#define UV1H_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_MASK 0x0000000000000200UL
+#define UV1H_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_SHFT 10
+#define UV1H_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_MASK 0x0000000000000400UL
+#define UV1H_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_SHFT 11
+#define UV1H_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_MASK 0x0000000000003800UL
+#define UV1H_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_SHFT 14
+#define UV1H_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_MASK 0x0000000000004000UL
+#define UV1H_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT 15
+#define UV1H_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_MASK 0x0000000000008000UL
+#define UV1H_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT 16
+#define UV1H_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_MASK 0x00000000000f0000UL
+#define UV1H_LB_BAU_MISC_CONTROL_ENABLE_DUAL_MAPPING_MODE_SHFT 20
+#define UV1H_LB_BAU_MISC_CONTROL_ENABLE_DUAL_MAPPING_MODE_MASK 0x0000000000100000UL
+#define UV1H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_DECODE_ENABLE_SHFT 21
+#define UV1H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_DECODE_ENABLE_MASK 0x0000000000200000UL
+#define UV1H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_16_BIT_DECODE_SHFT 22
+#define UV1H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_16_BIT_DECODE_MASK 0x0000000000400000UL
+#define UV1H_LB_BAU_MISC_CONTROL_SUPPRESS_DEST_REGISTRATION_SHFT 23
+#define UV1H_LB_BAU_MISC_CONTROL_SUPPRESS_DEST_REGISTRATION_MASK 0x0000000000800000UL
+#define UV1H_LB_BAU_MISC_CONTROL_PROGRAMMED_INITIAL_PRIORITY_SHFT 24
+#define UV1H_LB_BAU_MISC_CONTROL_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000007000000UL
+#define UV1H_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_SHFT 27
+#define UV1H_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_MASK 0x0000000008000000UL
+#define UV1H_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_SHFT 28
+#define UV1H_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000010000000UL
+#define UV1H_LB_BAU_MISC_CONTROL_FUN_SHFT 48
+#define UV1H_LB_BAU_MISC_CONTROL_FUN_MASK 0xffff000000000000UL
+
+#define UV2H_LB_BAU_MISC_CONTROL_REJECTION_DELAY_SHFT 0
+#define UV2H_LB_BAU_MISC_CONTROL_REJECTION_DELAY_MASK 0x00000000000000ffUL
+#define UV2H_LB_BAU_MISC_CONTROL_APIC_MODE_SHFT 8
+#define UV2H_LB_BAU_MISC_CONTROL_APIC_MODE_MASK 0x0000000000000100UL
+#define UV2H_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_SHFT 9
+#define UV2H_LB_BAU_MISC_CONTROL_FORCE_BROADCAST_MASK 0x0000000000000200UL
+#define UV2H_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_SHFT 10
+#define UV2H_LB_BAU_MISC_CONTROL_FORCE_LOCK_NOP_MASK 0x0000000000000400UL
+#define UV2H_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_SHFT 11
+#define UV2H_LB_BAU_MISC_CONTROL_QPI_AGENT_PRESENCE_VECTOR_MASK 0x0000000000003800UL
+#define UV2H_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_SHFT 14
+#define UV2H_LB_BAU_MISC_CONTROL_DESCRIPTOR_FETCH_MODE_MASK 0x0000000000004000UL
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT 15
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_MASK 0x0000000000008000UL
+#define UV2H_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT 16
+#define UV2H_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_MASK 0x00000000000f0000UL
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_DUAL_MAPPING_MODE_SHFT 20
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_DUAL_MAPPING_MODE_MASK 0x0000000000100000UL
+#define UV2H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_DECODE_ENABLE_SHFT 21
+#define UV2H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_DECODE_ENABLE_MASK 0x0000000000200000UL
+#define UV2H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_16_BIT_DECODE_SHFT 22
+#define UV2H_LB_BAU_MISC_CONTROL_VGA_IO_PORT_16_BIT_DECODE_MASK 0x0000000000400000UL
+#define UV2H_LB_BAU_MISC_CONTROL_SUPPRESS_DEST_REGISTRATION_SHFT 23
+#define UV2H_LB_BAU_MISC_CONTROL_SUPPRESS_DEST_REGISTRATION_MASK 0x0000000000800000UL
+#define UV2H_LB_BAU_MISC_CONTROL_PROGRAMMED_INITIAL_PRIORITY_SHFT 24
+#define UV2H_LB_BAU_MISC_CONTROL_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000007000000UL
+#define UV2H_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_SHFT 27
+#define UV2H_LB_BAU_MISC_CONTROL_USE_INCOMING_PRIORITY_MASK 0x0000000008000000UL
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_SHFT 28
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_PROGRAMMED_INITIAL_PRIORITY_MASK 0x0000000010000000UL
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_AUTOMATIC_APIC_MODE_SELECTION_SHFT 29
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_AUTOMATIC_APIC_MODE_SELECTION_MASK 0x0000000020000000UL
+#define UV2H_LB_BAU_MISC_CONTROL_APIC_MODE_STATUS_SHFT 30
+#define UV2H_LB_BAU_MISC_CONTROL_APIC_MODE_STATUS_MASK 0x0000000040000000UL
+#define UV2H_LB_BAU_MISC_CONTROL_SUPPRESS_INTERRUPTS_TO_SELF_SHFT 31
+#define UV2H_LB_BAU_MISC_CONTROL_SUPPRESS_INTERRUPTS_TO_SELF_MASK 0x0000000080000000UL
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_LOCK_BASED_SYSTEM_FLUSH_SHFT 32
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_LOCK_BASED_SYSTEM_FLUSH_MASK 0x0000000100000000UL
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_EXTENDED_SB_STATUS_SHFT 33
+#define UV2H_LB_BAU_MISC_CONTROL_ENABLE_EXTENDED_SB_STATUS_MASK 0x0000000200000000UL
+#define UV2H_LB_BAU_MISC_CONTROL_SUPPRESS_INT_PRIO_UDT_TO_SELF_SHFT 34
+#define UV2H_LB_BAU_MISC_CONTROL_SUPPRESS_INT_PRIO_UDT_TO_SELF_MASK 0x0000000400000000UL
+#define UV2H_LB_BAU_MISC_CONTROL_USE_LEGACY_DESCRIPTOR_FORMATS_SHFT 35
+#define UV2H_LB_BAU_MISC_CONTROL_USE_LEGACY_DESCRIPTOR_FORMATS_MASK 0x0000000800000000UL
+#define UV2H_LB_BAU_MISC_CONTROL_FUN_SHFT 48
+#define UV2H_LB_BAU_MISC_CONTROL_FUN_MASK 0xffff000000000000UL
 
 union uvh_lb_bau_misc_control_u {
     unsigned long       v;
@@ -660,7 +988,25 @@ union uvh_lb_bau_misc_control_u {
         unsigned long   apic_mode                          :  1;  /* RW */
         unsigned long   force_broadcast                    :  1;  /* RW */
         unsigned long   force_lock_nop                     :  1;  /* RW */
-        unsigned long   csi_agent_presence_vector          :  3;  /* RW */
+        unsigned long   qpi_agent_presence_vector          :  3;  /* RW */
+        unsigned long   descriptor_fetch_mode              :  1;  /* RW */
+        unsigned long   enable_intd_soft_ack_mode          :  1;  /* RW */
+        unsigned long   intd_soft_ack_timeout_period       :  4;  /* RW */
+        unsigned long   enable_dual_mapping_mode           :  1;  /* RW */
+        unsigned long   vga_io_port_decode_enable          :  1;  /* RW */
+        unsigned long   vga_io_port_16_bit_decode          :  1;  /* RW */
+        unsigned long   suppress_dest_registration         :  1;  /* RW */
+        unsigned long   programmed_initial_priority        :  3;  /* RW */
+        unsigned long   use_incoming_priority              :  1;  /* RW */
+        unsigned long   enable_programmed_initial_priority :  1;  /* RW */
+        unsigned long   rsvd_29_63    : 35;
+    } s;
+    struct uv1h_lb_bau_misc_control_s {
+        unsigned long   rejection_delay                    :  8;  /* RW */
+        unsigned long   apic_mode                          :  1;  /* RW */
+        unsigned long   force_broadcast                    :  1;  /* RW */
+        unsigned long   force_lock_nop                     :  1;  /* RW */
+        unsigned long   qpi_agent_presence_vector          :  3;  /* RW */
         unsigned long   descriptor_fetch_mode              :  1;  /* RW */
         unsigned long   enable_intd_soft_ack_mode          :  1;  /* RW */
         unsigned long   intd_soft_ack_timeout_period       :  4;  /* RW */
@@ -673,14 +1019,40 @@ union uvh_lb_bau_misc_control_u {
         unsigned long   enable_programmed_initial_priority :  1;  /* RW */
         unsigned long   rsvd_29_47                         : 19;  /*    */
         unsigned long   fun                                : 16;  /* RW */
-    } s;
+    } s1;
+    struct uv2h_lb_bau_misc_control_s {
+        unsigned long   rejection_delay                      :  8;  /* RW */
+        unsigned long   apic_mode                            :  1;  /* RW */
+        unsigned long   force_broadcast                      :  1;  /* RW */
+        unsigned long   force_lock_nop                       :  1;  /* RW */
+        unsigned long   qpi_agent_presence_vector            :  3;  /* RW */
+        unsigned long   descriptor_fetch_mode                :  1;  /* RW */
+        unsigned long   enable_intd_soft_ack_mode            :  1;  /* RW */
+        unsigned long   intd_soft_ack_timeout_period         :  4;  /* RW */
+        unsigned long   enable_dual_mapping_mode             :  1;  /* RW */
+        unsigned long   vga_io_port_decode_enable            :  1;  /* RW */
+        unsigned long   vga_io_port_16_bit_decode            :  1;  /* RW */
+        unsigned long   suppress_dest_registration           :  1;  /* RW */
+        unsigned long   programmed_initial_priority          :  3;  /* RW */
+        unsigned long   use_incoming_priority                :  1;  /* RW */
+        unsigned long   enable_programmed_initial_priority   :  1;  /* RW */
+        unsigned long   enable_automatic_apic_mode_selection :  1;  /* RW */
+        unsigned long   apic_mode_status                     :  1;  /* RO */
+        unsigned long   suppress_interrupts_to_self          :  1;  /* RW */
+        unsigned long   enable_lock_based_system_flush       :  1;  /* RW */
+        unsigned long   enable_extended_sb_status            :  1;  /* RW */
+        unsigned long   suppress_int_prio_udt_to_self        :  1;  /* RW */
+        unsigned long   use_legacy_descriptor_formats        :  1;  /* RW */
+        unsigned long   rsvd_36_47                           : 12;  /*    */
+        unsigned long   fun                                  : 16;  /* RW */
+    } s2;
 };
 
 /* ========================================================================= */
 /*                     UVH_LB_BAU_SB_ACTIVATION_CONTROL                      */
 /* ========================================================================= */
 #define UVH_LB_BAU_SB_ACTIVATION_CONTROL 0x320020UL
-#define UVH_LB_BAU_SB_ACTIVATION_CONTROL_32 0x009a8
+#define UVH_LB_BAU_SB_ACTIVATION_CONTROL_32 0x9a8
 
 #define UVH_LB_BAU_SB_ACTIVATION_CONTROL_INDEX_SHFT 0
 #define UVH_LB_BAU_SB_ACTIVATION_CONTROL_INDEX_MASK 0x000000000000003fUL
@@ -703,7 +1075,7 @@ union uvh_lb_bau_sb_activation_control_u {
 /*                    UVH_LB_BAU_SB_ACTIVATION_STATUS_0                      */
 /* ========================================================================= */
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_0 0x320030UL
-#define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_32 0x009b0
+#define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_32 0x9b0
 
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_STATUS_SHFT 0
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_STATUS_MASK 0xffffffffffffffffUL
@@ -719,7 +1091,7 @@ union uvh_lb_bau_sb_activation_status_0_u {
 /*                    UVH_LB_BAU_SB_ACTIVATION_STATUS_1                      */
 /* ========================================================================= */
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_1 0x320040UL
-#define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_32 0x009b8
+#define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_32 0x9b8
 
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_STATUS_SHFT 0
 #define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_STATUS_MASK 0xffffffffffffffffUL
@@ -735,7 +1107,7 @@ union uvh_lb_bau_sb_activation_status_1_u {
 /*                      UVH_LB_BAU_SB_DESCRIPTOR_BASE                        */
 /* ========================================================================= */
 #define UVH_LB_BAU_SB_DESCRIPTOR_BASE 0x320010UL
-#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_32 0x009a0
+#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_32 0x9a0
 
 #define UVH_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_SHFT 12
 #define UVH_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_MASK 0x000007fffffff000UL
@@ -754,23 +1126,6 @@ union uvh_lb_bau_sb_descriptor_base_u {
 };
 
 /* ========================================================================= */
-/*                   UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK                     */
-/* ========================================================================= */
-#define UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK 0x320130UL
-#define UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK_32 0x009f0
-
-#define UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK_BIT_ENABLES_SHFT 0
-#define UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK_BIT_ENABLES_MASK 0x00000000ffffffffUL
-
-union uvh_lb_target_physical_apic_id_mask_u {
-        unsigned long v;
-        struct uvh_lb_target_physical_apic_id_mask_s {
-                unsigned long bit_enables : 32;  /* RW */
-                unsigned long rsvd_32_63  : 32;  /*    */
-        } s;
-};
-
-/* ========================================================================= */
 /*                               UVH_NODE_ID                                 */
 /* ========================================================================= */
 #define UVH_NODE_ID 0x0UL
@@ -785,10 +1140,36 @@ union uvh_lb_target_physical_apic_id_mask_u {
 #define UVH_NODE_ID_REVISION_MASK 0x00000000f0000000UL
 #define UVH_NODE_ID_NODE_ID_SHFT 32
 #define UVH_NODE_ID_NODE_ID_MASK 0x00007fff00000000UL
-#define UVH_NODE_ID_NODES_PER_BIT_SHFT 48
-#define UVH_NODE_ID_NODES_PER_BIT_MASK 0x007f000000000000UL
-#define UVH_NODE_ID_NI_PORT_SHFT 56
-#define UVH_NODE_ID_NI_PORT_MASK 0x0f00000000000000UL
+
+#define UV1H_NODE_ID_FORCE1_SHFT 0
+#define UV1H_NODE_ID_FORCE1_MASK 0x0000000000000001UL
+#define UV1H_NODE_ID_MANUFACTURER_SHFT 1
+#define UV1H_NODE_ID_MANUFACTURER_MASK 0x0000000000000ffeUL
+#define UV1H_NODE_ID_PART_NUMBER_SHFT 12
+#define UV1H_NODE_ID_PART_NUMBER_MASK 0x000000000ffff000UL
+#define UV1H_NODE_ID_REVISION_SHFT 28
+#define UV1H_NODE_ID_REVISION_MASK 0x00000000f0000000UL
+#define UV1H_NODE_ID_NODE_ID_SHFT 32
+#define UV1H_NODE_ID_NODE_ID_MASK 0x00007fff00000000UL
+#define UV1H_NODE_ID_NODES_PER_BIT_SHFT 48
+#define UV1H_NODE_ID_NODES_PER_BIT_MASK 0x007f000000000000UL
+#define UV1H_NODE_ID_NI_PORT_SHFT 56
+#define UV1H_NODE_ID_NI_PORT_MASK 0x0f00000000000000UL
+
+#define UV2H_NODE_ID_FORCE1_SHFT 0
+#define UV2H_NODE_ID_FORCE1_MASK 0x0000000000000001UL
+#define UV2H_NODE_ID_MANUFACTURER_SHFT 1
+#define UV2H_NODE_ID_MANUFACTURER_MASK 0x0000000000000ffeUL
+#define UV2H_NODE_ID_PART_NUMBER_SHFT 12
+#define UV2H_NODE_ID_PART_NUMBER_MASK 0x000000000ffff000UL
+#define UV2H_NODE_ID_REVISION_SHFT 28
+#define UV2H_NODE_ID_REVISION_MASK 0x00000000f0000000UL
+#define UV2H_NODE_ID_NODE_ID_SHFT 32
+#define UV2H_NODE_ID_NODE_ID_MASK 0x00007fff00000000UL
+#define UV2H_NODE_ID_NODES_PER_BIT_SHFT 50
+#define UV2H_NODE_ID_NODES_PER_BIT_MASK 0x01fc000000000000UL
+#define UV2H_NODE_ID_NI_PORT_SHFT 57
+#define UV2H_NODE_ID_NI_PORT_MASK 0x3e00000000000000UL
 
 union uvh_node_id_u {
     unsigned long       v;
@@ -798,12 +1179,31 @@ union uvh_node_id_u {
         unsigned long   part_number   : 16;  /* RO */
         unsigned long   revision      :  4;  /* RO */
         unsigned long   node_id       : 15;  /* RW */
+        unsigned long   rsvd_47_63    : 17;
+    } s;
+    struct uv1h_node_id_s {
+        unsigned long   force1        :  1;  /* RO */
+        unsigned long   manufacturer  : 11;  /* RO */
+        unsigned long   part_number   : 16;  /* RO */
+        unsigned long   revision      :  4;  /* RO */
+        unsigned long   node_id       : 15;  /* RW */
         unsigned long   rsvd_47       :  1;  /*    */
         unsigned long   nodes_per_bit :  7;  /* RW */
         unsigned long   rsvd_55       :  1;  /*    */
         unsigned long   ni_port       :  4;  /* RO */
         unsigned long   rsvd_60_63    :  4;  /*    */
-    } s;
+    } s1;
+    struct uv2h_node_id_s {
+        unsigned long   force1        :  1;  /* RO */
+        unsigned long   manufacturer  : 11;  /* RO */
+        unsigned long   part_number   : 16;  /* RO */
+        unsigned long   revision      :  4;  /* RO */
+        unsigned long   node_id       : 15;  /* RW */
+        unsigned long   rsvd_47_49    :  3;  /*    */
+        unsigned long   nodes_per_bit :  7;  /* RO */
+        unsigned long   ni_port       :  5;  /* RO */
+        unsigned long   rsvd_62_63    :  2;  /*    */
+    } s2;
 };
 
 /* ========================================================================= */
@@ -954,18 +1354,38 @@ union uvh_rh_gam_alias210_redirect_config_2_mmr_u {
 #define UVH_RH_GAM_CONFIG_MMR_M_SKT_MASK 0x000000000000003fUL
 #define UVH_RH_GAM_CONFIG_MMR_N_SKT_SHFT 6
 #define UVH_RH_GAM_CONFIG_MMR_N_SKT_MASK 0x00000000000003c0UL
-#define UVH_RH_GAM_CONFIG_MMR_MMIOL_CFG_SHFT 12
-#define UVH_RH_GAM_CONFIG_MMR_MMIOL_CFG_MASK 0x0000000000001000UL
+
+#define UV1H_RH_GAM_CONFIG_MMR_M_SKT_SHFT 0
+#define UV1H_RH_GAM_CONFIG_MMR_M_SKT_MASK 0x000000000000003fUL
+#define UV1H_RH_GAM_CONFIG_MMR_N_SKT_SHFT 6
+#define UV1H_RH_GAM_CONFIG_MMR_N_SKT_MASK 0x00000000000003c0UL
+#define UV1H_RH_GAM_CONFIG_MMR_MMIOL_CFG_SHFT 12
+#define UV1H_RH_GAM_CONFIG_MMR_MMIOL_CFG_MASK 0x0000000000001000UL
+
+#define UV2H_RH_GAM_CONFIG_MMR_M_SKT_SHFT 0
+#define UV2H_RH_GAM_CONFIG_MMR_M_SKT_MASK 0x000000000000003fUL
+#define UV2H_RH_GAM_CONFIG_MMR_N_SKT_SHFT 6
+#define UV2H_RH_GAM_CONFIG_MMR_N_SKT_MASK 0x00000000000003c0UL
 
 union uvh_rh_gam_config_mmr_u {
     unsigned long       v;
     struct uvh_rh_gam_config_mmr_s {
         unsigned long   m_skt     :  6;  /* RW */
         unsigned long   n_skt     :  4;  /* RW */
+        unsigned long   rsvd_10_63    : 54;
+    } s;
+    struct uv1h_rh_gam_config_mmr_s {
+        unsigned long   m_skt     :  6;  /* RW */
+        unsigned long   n_skt     :  4;  /* RW */
         unsigned long   rsvd_10_11:  2;  /*    */
         unsigned long   mmiol_cfg :  1;  /* RW */
         unsigned long   rsvd_13_63: 51;  /*    */
-    } s;
+    } s1;
+    struct uv2h_rh_gam_config_mmr_s {
+        unsigned long   m_skt :  6;  /* RW */
+        unsigned long   n_skt :  4;  /* RW */
+        unsigned long   rsvd_10_63: 54;  /*    */
+    } s2;
 };
 
 /* ========================================================================= */
@@ -975,25 +1395,49 @@ union uvh_rh_gam_config_mmr_u {
 
 #define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT 28
 #define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffff0000000UL
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_GR4_SHFT 48
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_GR4_MASK 0x0001000000000000UL
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_SHFT 52
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_MASK 0x00f0000000000000UL
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT 28
+#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffff0000000UL
+#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_GR4_SHFT 48
+#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_GR4_MASK 0x0001000000000000UL
+#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_SHFT 52
+#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_MASK 0x00f0000000000000UL
+#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
+#define UV1H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT 28
+#define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffff0000000UL
+#define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_SHFT 52
+#define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_MASK 0x00f0000000000000UL
+#define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
+#define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
 
 union uvh_rh_gam_gru_overlay_config_mmr_u {
     unsigned long       v;
     struct uvh_rh_gam_gru_overlay_config_mmr_s {
         unsigned long   rsvd_0_27: 28;  /*    */
         unsigned long   base   : 18;  /* RW */
+        unsigned long   rsvd_46_62    : 17;
+        unsigned long   enable :  1;  /* RW */
+    } s;
+    struct uv1h_rh_gam_gru_overlay_config_mmr_s {
+        unsigned long   rsvd_0_27: 28;  /*    */
+        unsigned long   base   : 18;  /* RW */
         unsigned long   rsvd_46_47:  2;  /*    */
         unsigned long   gr4    :  1;  /* RW */
         unsigned long   rsvd_49_51:  3;  /*    */
         unsigned long   n_gru  :  4;  /* RW */
         unsigned long   rsvd_56_62:  7;  /*    */
         unsigned long   enable :  1;  /* RW */
-    } s;
+    } s1;
+    struct uv2h_rh_gam_gru_overlay_config_mmr_s {
+        unsigned long   rsvd_0_27: 28;  /*    */
+        unsigned long   base   : 18;  /* RW */
+        unsigned long   rsvd_46_51:  6;  /*    */
+        unsigned long   n_gru  :  4;  /* RW */
+        unsigned long   rsvd_56_62:  7;  /*    */
+        unsigned long   enable :  1;  /* RW */
+    } s2;
 };
 
 /* ========================================================================= */
@@ -1001,25 +1445,42 @@ union uvh_rh_gam_gru_overlay_config_mmr_u {
 /* ========================================================================= */
 #define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR 0x1600030UL
 
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT 30
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003fffc0000000UL
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_SHFT 46
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_MASK 0x000fc00000000000UL
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_SHFT 52
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_MASK 0x00f0000000000000UL
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
+#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT 30
+#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003fffc0000000UL
+#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_SHFT 46
+#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_MASK 0x000fc00000000000UL
+#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_SHFT 52
+#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_MASK 0x00f0000000000000UL
+#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
+#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT 27
+#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffff8000000UL
+#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_SHFT 46
+#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_MASK 0x000fc00000000000UL
+#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_SHFT 52
+#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_MASK 0x00f0000000000000UL
+#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
+#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
 
 union uvh_rh_gam_mmioh_overlay_config_mmr_u {
     unsigned long       v;
-    struct uvh_rh_gam_mmioh_overlay_config_mmr_s {
+    struct uv1h_rh_gam_mmioh_overlay_config_mmr_s {
         unsigned long   rsvd_0_29: 30;  /*    */
         unsigned long   base   : 16;  /* RW */
         unsigned long   m_io   :  6;  /* RW */
         unsigned long   n_io   :  4;  /* RW */
         unsigned long   rsvd_56_62:  7;  /*    */
         unsigned long   enable :  1;  /* RW */
-    } s;
+    } s1;
+    struct uv2h_rh_gam_mmioh_overlay_config_mmr_s {
+        unsigned long   rsvd_0_26: 27;  /*    */
+        unsigned long   base   : 19;  /* RW */
+        unsigned long   m_io   :  6;  /* RW */
+        unsigned long   n_io   :  4;  /* RW */
+        unsigned long   rsvd_56_62:  7;  /*    */
+        unsigned long   enable :  1;  /* RW */
+    } s2;
 };
 
 /* ========================================================================= */
@@ -1029,20 +1490,40 @@ union uvh_rh_gam_mmioh_overlay_config_mmr_u {
 
 #define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_SHFT 26
 #define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffffc000000UL
-#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_DUAL_HUB_SHFT 46
-#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_DUAL_HUB_MASK 0x0000400000000000UL
-#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
-#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_SHFT 26
+#define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffffc000000UL
+#define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_DUAL_HUB_SHFT 46
+#define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_DUAL_HUB_MASK 0x0000400000000000UL
+#define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
+#define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV2H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_SHFT 26
+#define UV2H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffffc000000UL
+#define UV2H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
+#define UV2H_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
 
 union uvh_rh_gam_mmr_overlay_config_mmr_u {
     unsigned long       v;
     struct uvh_rh_gam_mmr_overlay_config_mmr_s {
         unsigned long   rsvd_0_25: 26;  /*    */
         unsigned long   base     : 20;  /* RW */
+        unsigned long   rsvd_46_62    : 17;
+        unsigned long   enable   :  1;  /* RW */
+    } s;
+    struct uv1h_rh_gam_mmr_overlay_config_mmr_s {
+        unsigned long   rsvd_0_25: 26;  /*    */
+        unsigned long   base     : 20;  /* RW */
         unsigned long   dual_hub :  1;  /* RW */
         unsigned long   rsvd_47_62: 16;  /*    */
         unsigned long   enable   :  1;  /* RW */
-    } s;
+    } s1;
+    struct uv2h_rh_gam_mmr_overlay_config_mmr_s {
+        unsigned long   rsvd_0_25: 26;  /*    */
+        unsigned long   base   : 20;  /* RW */
+        unsigned long   rsvd_46_62: 17;  /*    */
+        unsigned long   enable :  1;  /* RW */
+    } s2;
 };
 
 /* ========================================================================= */
@@ -1103,10 +1584,11 @@ union uvh_rtc1_int_config_u {
 /*                               UVH_SCRATCH5                                */
 /* ========================================================================= */
 #define UVH_SCRATCH5 0x2d0200UL
-#define UVH_SCRATCH5_32 0x00778
+#define UVH_SCRATCH5_32 0x778
 
 #define UVH_SCRATCH5_SCRATCH5_SHFT 0
 #define UVH_SCRATCH5_SCRATCH5_MASK 0xffffffffffffffffUL
+
 union uvh_scratch5_u {
     unsigned long       v;
     struct uvh_scratch5_s {
@@ -1114,4 +1596,154 @@ union uvh_scratch5_u {
     } s;
 };
 
+/* ========================================================================= */
+/*                           UV2H_EVENT_OCCURRED2                            */
+/* ========================================================================= */
+#define UV2H_EVENT_OCCURRED2 0x70100UL
+#define UV2H_EVENT_OCCURRED2_32 0xb68
+
+#define UV2H_EVENT_OCCURRED2_RTC_0_SHFT 0
+#define UV2H_EVENT_OCCURRED2_RTC_0_MASK 0x0000000000000001UL
+#define UV2H_EVENT_OCCURRED2_RTC_1_SHFT 1
+#define UV2H_EVENT_OCCURRED2_RTC_1_MASK 0x0000000000000002UL
+#define UV2H_EVENT_OCCURRED2_RTC_2_SHFT 2
+#define UV2H_EVENT_OCCURRED2_RTC_2_MASK 0x0000000000000004UL
+#define UV2H_EVENT_OCCURRED2_RTC_3_SHFT 3
+#define UV2H_EVENT_OCCURRED2_RTC_3_MASK 0x0000000000000008UL
+#define UV2H_EVENT_OCCURRED2_RTC_4_SHFT 4
+#define UV2H_EVENT_OCCURRED2_RTC_4_MASK 0x0000000000000010UL
+#define UV2H_EVENT_OCCURRED2_RTC_5_SHFT 5
+#define UV2H_EVENT_OCCURRED2_RTC_5_MASK 0x0000000000000020UL
+#define UV2H_EVENT_OCCURRED2_RTC_6_SHFT 6
+#define UV2H_EVENT_OCCURRED2_RTC_6_MASK 0x0000000000000040UL
+#define UV2H_EVENT_OCCURRED2_RTC_7_SHFT 7
+#define UV2H_EVENT_OCCURRED2_RTC_7_MASK 0x0000000000000080UL
+#define UV2H_EVENT_OCCURRED2_RTC_8_SHFT 8
+#define UV2H_EVENT_OCCURRED2_RTC_8_MASK 0x0000000000000100UL
+#define UV2H_EVENT_OCCURRED2_RTC_9_SHFT 9
+#define UV2H_EVENT_OCCURRED2_RTC_9_MASK 0x0000000000000200UL
+#define UV2H_EVENT_OCCURRED2_RTC_10_SHFT 10
+#define UV2H_EVENT_OCCURRED2_RTC_10_MASK 0x0000000000000400UL
+#define UV2H_EVENT_OCCURRED2_RTC_11_SHFT 11
+#define UV2H_EVENT_OCCURRED2_RTC_11_MASK 0x0000000000000800UL
+#define UV2H_EVENT_OCCURRED2_RTC_12_SHFT 12
+#define UV2H_EVENT_OCCURRED2_RTC_12_MASK 0x0000000000001000UL
+#define UV2H_EVENT_OCCURRED2_RTC_13_SHFT 13
+#define UV2H_EVENT_OCCURRED2_RTC_13_MASK 0x0000000000002000UL
+#define UV2H_EVENT_OCCURRED2_RTC_14_SHFT 14
+#define UV2H_EVENT_OCCURRED2_RTC_14_MASK 0x0000000000004000UL
+#define UV2H_EVENT_OCCURRED2_RTC_15_SHFT 15
+#define UV2H_EVENT_OCCURRED2_RTC_15_MASK 0x0000000000008000UL
+#define UV2H_EVENT_OCCURRED2_RTC_16_SHFT 16
+#define UV2H_EVENT_OCCURRED2_RTC_16_MASK 0x0000000000010000UL
+#define UV2H_EVENT_OCCURRED2_RTC_17_SHFT 17
+#define UV2H_EVENT_OCCURRED2_RTC_17_MASK 0x0000000000020000UL
+#define UV2H_EVENT_OCCURRED2_RTC_18_SHFT 18
+#define UV2H_EVENT_OCCURRED2_RTC_18_MASK 0x0000000000040000UL
+#define UV2H_EVENT_OCCURRED2_RTC_19_SHFT 19
+#define UV2H_EVENT_OCCURRED2_RTC_19_MASK 0x0000000000080000UL
+#define UV2H_EVENT_OCCURRED2_RTC_20_SHFT 20
+#define UV2H_EVENT_OCCURRED2_RTC_20_MASK 0x0000000000100000UL
+#define UV2H_EVENT_OCCURRED2_RTC_21_SHFT 21
+#define UV2H_EVENT_OCCURRED2_RTC_21_MASK 0x0000000000200000UL
+#define UV2H_EVENT_OCCURRED2_RTC_22_SHFT 22
+#define UV2H_EVENT_OCCURRED2_RTC_22_MASK 0x0000000000400000UL
+#define UV2H_EVENT_OCCURRED2_RTC_23_SHFT 23
+#define UV2H_EVENT_OCCURRED2_RTC_23_MASK 0x0000000000800000UL
+#define UV2H_EVENT_OCCURRED2_RTC_24_SHFT 24
+#define UV2H_EVENT_OCCURRED2_RTC_24_MASK 0x0000000001000000UL
+#define UV2H_EVENT_OCCURRED2_RTC_25_SHFT 25
+#define UV2H_EVENT_OCCURRED2_RTC_25_MASK 0x0000000002000000UL
+#define UV2H_EVENT_OCCURRED2_RTC_26_SHFT 26
+#define UV2H_EVENT_OCCURRED2_RTC_26_MASK 0x0000000004000000UL
+#define UV2H_EVENT_OCCURRED2_RTC_27_SHFT 27
+#define UV2H_EVENT_OCCURRED2_RTC_27_MASK 0x0000000008000000UL
+#define UV2H_EVENT_OCCURRED2_RTC_28_SHFT 28
+#define UV2H_EVENT_OCCURRED2_RTC_28_MASK 0x0000000010000000UL
+#define UV2H_EVENT_OCCURRED2_RTC_29_SHFT 29
+#define UV2H_EVENT_OCCURRED2_RTC_29_MASK 0x0000000020000000UL
+#define UV2H_EVENT_OCCURRED2_RTC_30_SHFT 30
+#define UV2H_EVENT_OCCURRED2_RTC_30_MASK 0x0000000040000000UL
+#define UV2H_EVENT_OCCURRED2_RTC_31_SHFT 31
+#define UV2H_EVENT_OCCURRED2_RTC_31_MASK 0x0000000080000000UL
+
+union uv2h_event_occurred2_u {
+    unsigned long       v;
+    struct uv2h_event_occurred2_s {
+        unsigned long   rtc_0  :  1;  /* RW */
+        unsigned long   rtc_1  :  1;  /* RW */
+        unsigned long   rtc_2  :  1;  /* RW */
+        unsigned long   rtc_3  :  1;  /* RW */
+        unsigned long   rtc_4  :  1;  /* RW */
+        unsigned long   rtc_5  :  1;  /* RW */
+        unsigned long   rtc_6  :  1;  /* RW */
+        unsigned long   rtc_7  :  1;  /* RW */
+        unsigned long   rtc_8  :  1;  /* RW */
+        unsigned long   rtc_9  :  1;  /* RW */
+        unsigned long   rtc_10 :  1;  /* RW */
+        unsigned long   rtc_11 :  1;  /* RW */
+        unsigned long   rtc_12 :  1;  /* RW */
+        unsigned long   rtc_13 :  1;  /* RW */
+        unsigned long   rtc_14 :  1;  /* RW */
+        unsigned long   rtc_15 :  1;  /* RW */
+        unsigned long   rtc_16 :  1;  /* RW */
+        unsigned long   rtc_17 :  1;  /* RW */
+        unsigned long   rtc_18 :  1;  /* RW */
+        unsigned long   rtc_19 :  1;  /* RW */
+        unsigned long   rtc_20 :  1;  /* RW */
+        unsigned long   rtc_21 :  1;  /* RW */
+        unsigned long   rtc_22 :  1;  /* RW */
+        unsigned long   rtc_23 :  1;  /* RW */
+        unsigned long   rtc_24 :  1;  /* RW */
+        unsigned long   rtc_25 :  1;  /* RW */
+        unsigned long   rtc_26 :  1;  /* RW */
+        unsigned long   rtc_27 :  1;  /* RW */
+        unsigned long   rtc_28 :  1;  /* RW */
+        unsigned long   rtc_29 :  1;  /* RW */
+        unsigned long   rtc_30 :  1;  /* RW */
+        unsigned long   rtc_31 :  1;  /* RW */
+        unsigned long   rsvd_32_63: 32;  /*    */
+    } s1;
+};
+
+/* ========================================================================= */
+/*                        UV2H_EVENT_OCCURRED2_ALIAS                         */
+/* ========================================================================= */
+#define UV2H_EVENT_OCCURRED2_ALIAS 0x70108UL
+#define UV2H_EVENT_OCCURRED2_ALIAS_32 0xb70
+
+/* ========================================================================= */
+/*                    UV2H_LB_BAU_SB_ACTIVATION_STATUS_2                     */
+/* ========================================================================= */
+#define UV2H_LB_BAU_SB_ACTIVATION_STATUS_2 0x320130UL
+#define UV2H_LB_BAU_SB_ACTIVATION_STATUS_2_32 0x9f0
+
+#define UV2H_LB_BAU_SB_ACTIVATION_STATUS_2_AUX_ERROR_SHFT 0
+#define UV2H_LB_BAU_SB_ACTIVATION_STATUS_2_AUX_ERROR_MASK 0xffffffffffffffffUL
+
+union uv2h_lb_bau_sb_activation_status_2_u {
+    unsigned long       v;
+    struct uv2h_lb_bau_sb_activation_status_2_s {
+        unsigned long   aux_error : 64;  /* RW */
+    } s1;
+};
+
+/* ========================================================================= */
+/*                   UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK                    */
+/* ========================================================================= */
+#define UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK 0x320130UL
+#define UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK_32 0x9f0
+
+#define UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK_BIT_ENABLES_SHFT 0
+#define UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK_BIT_ENABLES_MASK 0x00000000ffffffffUL
+
+union uv1h_lb_target_physical_apic_id_mask_u {
+    unsigned long       v;
+    struct uv1h_lb_target_physical_apic_id_mask_s {
+        unsigned long   bit_enables : 32;  /* RW */
+        unsigned long   rsvd_32_63  : 32;  /*    */
+    } s1;
+};
+
+
 #endif /* __ASM_UV_MMRS_X86_H__ */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index f5abe3a245b8..90b06d4daee2 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -8,6 +8,7 @@ CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE)
 
 ifdef CONFIG_FUNCTION_TRACER
 # Do not profile debug and lowlevel utilities
+CFLAGS_REMOVE_tsc.o = -pg
 CFLAGS_REMOVE_rtc.o = -pg
 CFLAGS_REMOVE_paravirt-spinlocks.o = -pg
 CFLAGS_REMOVE_pvclock.o = -pg
@@ -28,6 +29,7 @@ CFLAGS_paravirt.o	:= $(nostackp)
 GCOV_PROFILE_vsyscall_64.o      := n
 GCOV_PROFILE_hpet.o             := n
 GCOV_PROFILE_tsc.o              := n
+GCOV_PROFILE_vread_tsc_64.o     := n
 GCOV_PROFILE_paravirt.o         := n
 
 # vread_tsc_64 is hot and should be fully optimized:
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index f450b683dfcf..b511a011b7d0 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -91,6 +91,10 @@ static int __init early_get_pnodeid(void)
         m_n_config.v = uv_early_read_mmr(UVH_RH_GAM_CONFIG_MMR);
         uv_min_hub_revision_id = node_id.s.revision;
 
+        if (node_id.s.part_number == UV2_HUB_PART_NUMBER)
+                uv_min_hub_revision_id += UV2_HUB_REVISION_BASE - 1;
+
+        uv_hub_info->hub_revision = uv_min_hub_revision_id;
         pnode = (node_id.s.node_id >> 1) & ((1 << m_n_config.s.n_skt) - 1);
         return pnode;
 }
@@ -112,17 +116,25 @@ static void __init early_get_apic_pnode_shift(void)
  */
 static void __init uv_set_apicid_hibit(void)
 {
-        union uvh_lb_target_physical_apic_id_mask_u apicid_mask;
+        union uv1h_lb_target_physical_apic_id_mask_u apicid_mask;
 
-        apicid_mask.v = uv_early_read_mmr(UVH_LB_TARGET_PHYSICAL_APIC_ID_MASK);
-        uv_apicid_hibits = apicid_mask.s.bit_enables & UV_APICID_HIBIT_MASK;
+        if (is_uv1_hub()) {
+                apicid_mask.v =
+                        uv_early_read_mmr(UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK);
+                uv_apicid_hibits =
+                        apicid_mask.s1.bit_enables & UV_APICID_HIBIT_MASK;
+        }
 }
 
 static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 {
-        int pnodeid;
+        int pnodeid, is_uv1, is_uv2;
 
-        if (!strcmp(oem_id, "SGI")) {
+        is_uv1 = !strcmp(oem_id, "SGI");
+        is_uv2 = !strcmp(oem_id, "SGI2");
+        if (is_uv1 || is_uv2) {
+                uv_hub_info->hub_revision =
+                        is_uv1 ? UV1_HUB_REVISION_BASE : UV2_HUB_REVISION_BASE;
                 pnodeid = early_get_pnodeid();
                 early_get_apic_pnode_shift();
                 x86_platform.is_untracked_pat_range =  uv_is_untracked_pat_range;
@@ -484,12 +496,19 @@ static __init void map_mmr_high(int max_pnode)
 static __init void map_mmioh_high(int max_pnode)
 {
         union uvh_rh_gam_mmioh_overlay_config_mmr_u mmioh;
-        int shift = UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT;
+        int shift;
 
         mmioh.v = uv_read_local_mmr(UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR);
-        if (mmioh.s.enable)
-                map_high("MMIOH", mmioh.s.base, shift, mmioh.s.m_io,
+        if (is_uv1_hub() && mmioh.s1.enable) {
+                shift = UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT;
+                map_high("MMIOH", mmioh.s1.base, shift, mmioh.s1.m_io,
+                        max_pnode, map_uc);
+        }
+        if (is_uv2_hub() && mmioh.s2.enable) {
+                shift = UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT;
+                map_high("MMIOH", mmioh.s2.base, shift, mmioh.s2.m_io,
                         max_pnode, map_uc);
+        }
 }
 
 static __init void map_low_mmrs(void)
@@ -736,13 +755,14 @@ void __init uv_system_init(void)
         unsigned long mmr_base, present, paddr;
         unsigned short pnode_mask, pnode_io_mask;
 
+        printk(KERN_INFO "UV: Found %s hub\n", is_uv1_hub() ? "UV1" : "UV2");
         map_low_mmrs();
 
         m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR );
         m_val = m_n_config.s.m_skt;
         n_val = m_n_config.s.n_skt;
         mmioh.v = uv_read_local_mmr(UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR);
-        n_io = mmioh.s.n_io;
+        n_io = is_uv1_hub() ? mmioh.s1.n_io : mmioh.s2.n_io;
         mmr_base =
             uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) &
             ~UV_MMR_ENABLE;
@@ -811,6 +831,8 @@ void __init uv_system_init(void)
                  */
                 uv_cpu_hub_info(cpu)->pnode_mask = pnode_mask;
                 uv_cpu_hub_info(cpu)->apic_pnode_shift = uvh_apicid.s.pnode_shift;
+                uv_cpu_hub_info(cpu)->hub_revision = uv_hub_info->hub_revision;
+
                 pnode = uv_apicid_to_pnode(apicid);
                 blade = boot_pnode_to_blade(pnode);
                 lcpu = uv_blade_info[blade].nr_possible_cpus;
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 3bfa02235965..965a7666c283 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -361,6 +361,7 @@ struct apm_user {
  * idle percentage above which bios idle calls are done
  */
 #ifdef CONFIG_APM_CPU_IDLE
+#warning deprecated CONFIG_APM_CPU_IDLE will be deleted in 2012
 #define DEFAULT_IDLE_THRESHOLD  95
 #else
 #define DEFAULT_IDLE_THRESHOLD  100
@@ -904,6 +905,7 @@ static void apm_cpu_idle(void)
         unsigned int jiffies_since_last_check = jiffies - last_jiffies;
         unsigned int bucket;
 
+        WARN_ONCE(1, "deprecated apm_cpu_idle will be deleted in 2012");
 recalc:
         if (jiffies_since_last_check > IDLE_CALC_LIMIT) {
                 use_apm_idle = 0;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 8f5cabb3c5b0..b13ed393dfce 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -612,8 +612,11 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
         }
 #endif
 
-        /* As a rule processors have APIC timer running in deep C states */
-        if (c->x86 > 0xf && !cpu_has_amd_erratum(amd_erratum_400))
+        /*
+         * Family 0x12 and above processors have APIC timer
+         * running in deep C states.
+         */
+        if (c->x86 > 0x11)
                 set_cpu_cap(c, X86_FEATURE_ARAT);
 
         /*
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index c39576cb3018..525514cf33c3 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -19,6 +19,7 @@
 
 static int __init no_halt(char *s)
 {
+        WARN_ONCE(1, "\"no-hlt\" is deprecated, please use \"idle=poll\"\n");
         boot_cpu_data.hlt_works_ok = 0;
         return 1;
 }
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c8b41623377f..22a073d7fbff 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -477,13 +477,6 @@ void __cpuinit detect_ht(struct cpuinfo_x86 *c)
         if (smp_num_siblings <= 1)
                 goto out;
 
-        if (smp_num_siblings > nr_cpu_ids) {
-                pr_warning("CPU: Unsupported number of siblings %d",
-                           smp_num_siblings);
-                smp_num_siblings = 1;
-                return;
-        }
-
         index_msb = get_count_order(smp_num_siblings);
         c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, index_msb);
 
@@ -909,7 +902,7 @@ static void vgetcpu_set_mode(void)
 void __init identify_boot_cpu(void)
 {
         identify_cpu(&boot_cpu_data);
-        init_c1e_mask();
+        init_amd_e400_c1e_mask();
 #ifdef CONFIG_X86_32
         sysenter_setup();
         enable_sep_cpu();
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 0ba15a6cc57e..c9a281f272fd 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -123,7 +123,7 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 static atomic_t nmi_running = ATOMIC_INIT(0);
 static int mod_code_status;             /* holds return value of text write */
 static void *mod_code_ip;               /* holds the IP to write to */
-static void *mod_code_newcode;          /* holds the text to write to the IP */
+static const void *mod_code_newcode;    /* holds the text to write to the IP */
 
 static unsigned nmi_wait_count;
 static atomic_t nmi_update_count = ATOMIC_INIT(0);
@@ -225,7 +225,7 @@ within(unsigned long addr, unsigned long start, unsigned long end)
 }
 
 static int
-do_ftrace_mod_code(unsigned long ip, void *new_code)
+do_ftrace_mod_code(unsigned long ip, const void *new_code)
 {
         /*
          * On x86_64, kernel text mappings are mapped read-only with
@@ -266,8 +266,8 @@ static const unsigned char *ftrace_nop_replace(void)
 }
 
 static int
-ftrace_modify_code(unsigned long ip, unsigned char *old_code,
-                   unsigned char *new_code)
+ftrace_modify_code(unsigned long ip, unsigned const char *old_code,
+                   unsigned const char *new_code)
 {
         unsigned char replaced[MCOUNT_INSN_SIZE];
 
@@ -301,7 +301,7 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 int ftrace_make_nop(struct module *mod,
                     struct dyn_ftrace *rec, unsigned long addr)
 {
-        unsigned char *new, *old;
+        unsigned const char *new, *old;
         unsigned long ip = rec->ip;
 
         old = ftrace_call_replace(ip, addr);
@@ -312,7 +312,7 @@ int ftrace_make_nop(struct module *mod,
 
 int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 {
-        unsigned char *new, *old;
+        unsigned const char *new, *old;
         unsigned long ip = rec->ip;
 
         old = ftrace_nop_replace();
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 88a90a977f8e..2e4928d45a2d 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -337,7 +337,9 @@ EXPORT_SYMBOL(boot_option_idle_override);
  * Powermanagement idle function, if any..
  */
 void (*pm_idle)(void);
+#if defined(CONFIG_APM_MODULE) && defined(CONFIG_APM_CPU_IDLE)
 EXPORT_SYMBOL(pm_idle);
+#endif
 
 #ifdef CONFIG_X86_32
 /*
@@ -397,7 +399,7 @@ void default_idle(void)
                 cpu_relax();
         }
 }
-#ifdef CONFIG_APM_MODULE
+#if defined(CONFIG_APM_MODULE) && defined(CONFIG_APM_CPU_IDLE)
 EXPORT_SYMBOL(default_idle);
 #endif
 
@@ -535,45 +537,45 @@ int mwait_usable(const struct cpuinfo_x86 *c)
         return (edx & MWAIT_EDX_C1);
 }
 
-bool c1e_detected;
-EXPORT_SYMBOL(c1e_detected);
+bool amd_e400_c1e_detected;
+EXPORT_SYMBOL(amd_e400_c1e_detected);
 
-static cpumask_var_t c1e_mask;
+static cpumask_var_t amd_e400_c1e_mask;
 
-void c1e_remove_cpu(int cpu)
+void amd_e400_remove_cpu(int cpu)
 {
-        if (c1e_mask != NULL)
-                cpumask_clear_cpu(cpu, c1e_mask);
+        if (amd_e400_c1e_mask != NULL)
+                cpumask_clear_cpu(cpu, amd_e400_c1e_mask);
 }
 
 /*
- * C1E aware idle routine. We check for C1E active in the interrupt
+ * AMD Erratum 400 aware idle routine. We check for C1E active in the interrupt
  * pending message MSR. If we detect C1E, then we handle it the same
  * way as C3 power states (local apic timer and TSC stop)
  */
-static void c1e_idle(void)
+static void amd_e400_idle(void)
 {
         if (need_resched())
                 return;
 
-        if (!c1e_detected) {
+        if (!amd_e400_c1e_detected) {
                 u32 lo, hi;
 
                 rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
 
                 if (lo & K8_INTP_C1E_ACTIVE_MASK) {
-                        c1e_detected = true;
+                        amd_e400_c1e_detected = true;
                         if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
                                 mark_tsc_unstable("TSC halt in AMD C1E");
                         printk(KERN_INFO "System has AMD C1E enabled\n");
                 }
         }
 
-        if (c1e_detected) {
+        if (amd_e400_c1e_detected) {
                 int cpu = smp_processor_id();
 
-                if (!cpumask_test_cpu(cpu, c1e_mask)) {
-                        cpumask_set_cpu(cpu, c1e_mask);
+                if (!cpumask_test_cpu(cpu, amd_e400_c1e_mask)) {
+                        cpumask_set_cpu(cpu, amd_e400_c1e_mask);
                         /*
                          * Force broadcast so ACPI can not interfere.
                          */
@@ -616,17 +618,17 @@ void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
                 pm_idle = mwait_idle;
         } else if (cpu_has_amd_erratum(amd_erratum_400)) {
                 /* E400: APIC timer interrupt does not wake up CPU from C1e */
-                printk(KERN_INFO "using C1E aware idle routine\n");
-                pm_idle = c1e_idle;
+                printk(KERN_INFO "using AMD E400 aware idle routine\n");
+                pm_idle = amd_e400_idle;
         } else
                 pm_idle = default_idle;
 }
 
-void __init init_c1e_mask(void)
+void __init init_amd_e400_c1e_mask(void)
 {
-        /* If we're using c1e_idle, we need to allocate c1e_mask. */
-        if (pm_idle == c1e_idle)
-                zalloc_cpumask_var(&c1e_mask, GFP_KERNEL);
+        /* If we're using amd_e400_idle, we need to allocate amd_e400_c1e_mask. */
+        if (pm_idle == amd_e400_idle)
+                zalloc_cpumask_var(&amd_e400_c1e_mask, GFP_KERNEL);
 }
 
 static int __init idle_setup(char *str)
@@ -640,6 +642,7 @@ static int __init idle_setup(char *str)
                 boot_option_idle_override = IDLE_POLL;
         } else if (!strcmp(str, "mwait")) {
                 boot_option_idle_override = IDLE_FORCE_MWAIT;
+                WARN_ONCE(1, "\"idle=mwait\" will be removed in 2012\n");
         } else if (!strcmp(str, "halt")) {
                 /*
                  * When the boot option of idle=halt is added, halt is
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index a3e5948670c2..afaf38447ef5 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -910,6 +910,13 @@ void __init setup_arch(char **cmdline_p)
         memblock.current_limit = get_max_mapped();
         memblock_x86_fill();
 
+        /*
+         * The EFI specification says that boot service code won't be called
+         * after ExitBootServices(). This is, in fact, a lie.
+         */
+        if (efi_enabled)
+                efi_reserve_boot_services();
+
         /* preallocate 4k for mptable mpc */
         early_reserve_e820_mpc_new();
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index a3c430bdfb60..33a0c11797de 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1307,7 +1307,7 @@ void play_dead_common(void)
 {
         idle_task_exit();
         reset_lazy_tlbstate();
-        c1e_remove_cpu(raw_smp_processor_id());
+        amd_e400_remove_cpu(raw_smp_processor_id());
 
         mb();
         /* Ack it */
@@ -1332,7 +1332,7 @@ static inline void mwait_play_dead(void)
         void *mwait_ptr;
         struct cpuinfo_x86 *c = __this_cpu_ptr(&cpu_info);
 
-        if (!this_cpu_has(X86_FEATURE_MWAIT) && mwait_usable(c))
+        if (!(this_cpu_has(X86_FEATURE_MWAIT) && mwait_usable(c)))
                 return;
         if (!this_cpu_has(X86_FEATURE_CLFLSH))
                 return;
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index e191c096ab90..db832fd65ecb 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -993,6 +993,7 @@ static void lguest_time_irq(unsigned int irq, struct irq_desc *desc)
 static void lguest_time_init(void)
 {
         /* Set up the timer interrupt (0) to go to our simple timer routine */
+        lguest_setup_irq(0);
         irq_set_handler(0, lguest_time_irq);
 
         clocksource_register_hz(&lguest_clock, NSEC_PER_SEC);
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index f7a2a054a3c0..2dbf6bf4c7e5 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -823,16 +823,30 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
         force_sig_info_fault(SIGBUS, code, address, tsk, fault);
 }
 
-static noinline void
+static noinline int
 mm_fault_error(struct pt_regs *regs, unsigned long error_code,
                unsigned long address, unsigned int fault)
 {
+        /*
+         * Pagefault was interrupted by SIGKILL. We have no reason to
+         * continue pagefault.
+         */
+        if (fatal_signal_pending(current)) {
+                if (!(fault & VM_FAULT_RETRY))
+                        up_read(&current->mm->mmap_sem);
+                if (!(error_code & PF_USER))
+                        no_context(regs, error_code, address);
+                return 1;
+        }
+        if (!(fault & VM_FAULT_ERROR))
+                return 0;
+
         if (fault & VM_FAULT_OOM) {
                 /* Kernel mode? Handle exceptions or die: */
                 if (!(error_code & PF_USER)) {
                         up_read(&current->mm->mmap_sem);
                         no_context(regs, error_code, address);
-                        return;
+                        return 1;
                 }
 
                 out_of_memory(regs, error_code, address);
@@ -843,6 +857,7 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
                 else
                         BUG();
         }
+        return 1;
 }
 
 static int spurious_fault_check(unsigned long error_code, pte_t *pte)
@@ -1133,19 +1148,9 @@ good_area:
          */
         fault = handle_mm_fault(mm, vma, address, flags);
 
-        if (unlikely(fault & VM_FAULT_ERROR)) {
-                mm_fault_error(regs, error_code, address, fault);
-                return;
-        }
-
-        /*
-         * Pagefault was interrupted by SIGKILL. We have no reason to
-         * continue pagefault.
-         */
-        if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
-                if (!(error_code & PF_USER))
-                        no_context(regs, error_code, address);
-                return;
+        if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) {
+                if (mm_fault_error(regs, error_code, address, fault))
+                        return;
         }
 
         /*
diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c
index c3b8e24f2b16..9fd8a567fe1e 100644
--- a/arch/x86/oprofile/op_model_amd.c
+++ b/arch/x86/oprofile/op_model_amd.c
@@ -316,16 +316,23 @@ static void op_amd_stop_ibs(void)
                 wrmsrl(MSR_AMD64_IBSOPCTL, 0);
 }
 
-static inline int eilvt_is_available(int offset)
+static inline int get_eilvt(int offset)
 {
-        /* check if we may assign a vector */
         return !setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_NMI, 1);
 }
 
+static inline int put_eilvt(int offset)
+{
+        return !setup_APIC_eilvt(offset, 0, 0, 1);
+}
+
 static inline int ibs_eilvt_valid(void)
 {
         int offset;
         u64 val;
+        int valid = 0;
+
+        preempt_disable();
 
         rdmsrl(MSR_AMD64_IBSCTL, val);
         offset = val & IBSCTL_LVT_OFFSET_MASK;
@@ -333,16 +340,20 @@ static inline int ibs_eilvt_valid(void)
         if (!(val & IBSCTL_LVT_OFFSET_VALID)) {
                 pr_err(FW_BUG "cpu %d, invalid IBS interrupt offset %d (MSR%08X=0x%016llx)\n",
                        smp_processor_id(), offset, MSR_AMD64_IBSCTL, val);
-                return 0;
+                goto out;
         }
 
-        if (!eilvt_is_available(offset)) {
+        if (!get_eilvt(offset)) {
                 pr_err(FW_BUG "cpu %d, IBS interrupt offset %d not available (MSR%08X=0x%016llx)\n",
                        smp_processor_id(), offset, MSR_AMD64_IBSCTL, val);
-                return 0;
+                goto out;
         }
 
-        return 1;
+        valid = 1;
+out:
+        preempt_enable();
+
+        return valid;
 }
 
 static inline int get_ibs_offset(void)
@@ -600,67 +611,69 @@ static int setup_ibs_ctl(int ibs_eilvt_off)
 
 static int force_ibs_eilvt_setup(void)
 {
-        int i;
+        int offset;
         int ret;
 
-        /* find the next free available EILVT entry */
-        for (i = 1; i < 4; i++) {
-                if (!eilvt_is_available(i))
-                        continue;
-                ret = setup_ibs_ctl(i);
-                if (ret)
-                        return ret;
-                pr_err(FW_BUG "using offset %d for IBS interrupts\n", i);
-                return 0;
+        /*
+         * find the next free available EILVT entry, skip offset 0,
+         * pin search to this cpu
+         */
+        preempt_disable();
+        for (offset = 1; offset < APIC_EILVT_NR_MAX; offset++) {
+                if (get_eilvt(offset))
+                        break;
         }
+        preempt_enable();
 
-        printk(KERN_DEBUG "No EILVT entry available\n");
-
-        return -EBUSY;
-}
-
-static int __init_ibs_nmi(void)
-{
-        int ret;
-
-        if (ibs_eilvt_valid())
-                return 0;
+        if (offset == APIC_EILVT_NR_MAX) {
+                printk(KERN_DEBUG "No EILVT entry available\n");
+                return -EBUSY;
+        }
 
-        ret = force_ibs_eilvt_setup();
+        ret = setup_ibs_ctl(offset);
         if (ret)
-                return ret;
+                goto out;
 
-        if (!ibs_eilvt_valid())
-                return -EFAULT;
+        if (!ibs_eilvt_valid()) {
+                ret = -EFAULT;
+                goto out;
+        }
 
+        pr_err(FW_BUG "using offset %d for IBS interrupts\n", offset);
         pr_err(FW_BUG "workaround enabled for IBS LVT offset\n");
 
         return 0;
+out:
+        preempt_disable();
+        put_eilvt(offset);
+        preempt_enable();
+        return ret;
 }
 
 /*
  * check and reserve APIC extended interrupt LVT offset for IBS if
  * available
- *
- * init_ibs() preforms implicitly cpu-local operations, so pin this
- * thread to its current CPU
  */
 
 static void init_ibs(void)
 {
-        preempt_disable();
-
         ibs_caps = get_ibs_caps();
+
         if (!ibs_caps)
+                return;
+
+        if (ibs_eilvt_valid())
                 goto out;
 
-        if (__init_ibs_nmi() < 0)
-                ibs_caps = 0;
-        else
-                printk(KERN_INFO "oprofile: AMD IBS detected (0x%08x)\n", ibs_caps);
+        if (!force_ibs_eilvt_setup())
+                goto out;
+
+        /* Failed to setup ibs */
+        ibs_caps = 0;
+        return;
 
 out:
-        preempt_enable();
+        printk(KERN_INFO "oprofile: AMD IBS detected (0x%08x)\n", ibs_caps);
 }
 
 static int (*create_arch_files)(struct super_block *sb, struct dentry *root);
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index b30aa26a8df2..0d3a4fa34560 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -304,6 +304,40 @@ static void __init print_efi_memmap(void)
 }
 #endif  /*  EFI_DEBUG  */
 
+void __init efi_reserve_boot_services(void)
+{
+        void *p;
+
+        for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+                efi_memory_desc_t *md = p;
+                unsigned long long start = md->phys_addr;
+                unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
+
+                if (md->type != EFI_BOOT_SERVICES_CODE &&
+                    md->type != EFI_BOOT_SERVICES_DATA)
+                        continue;
+
+                memblock_x86_reserve_range(start, start + size, "EFI Boot");
+        }
+}
+
+static void __init efi_free_boot_services(void)
+{
+        void *p;
+
+        for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+                efi_memory_desc_t *md = p;
+                unsigned long long start = md->phys_addr;
+                unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
+
+                if (md->type != EFI_BOOT_SERVICES_CODE &&
+                    md->type != EFI_BOOT_SERVICES_DATA)
+                        continue;
+
+                free_bootmem_late(start, size);
+        }
+}
+
 void __init efi_init(void)
 {
         efi_config_table_t *config_tables;
@@ -536,7 +570,9 @@ void __init efi_enter_virtual_mode(void)
 
         for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
                 md = p;
-                if (!(md->attribute & EFI_MEMORY_RUNTIME))
+                if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
+                    md->type != EFI_BOOT_SERVICES_CODE &&
+                    md->type != EFI_BOOT_SERVICES_DATA)
                         continue;
 
                 size = md->num_pages << EFI_PAGE_SHIFT;
@@ -593,6 +629,13 @@ void __init efi_enter_virtual_mode(void)
         }
 
         /*
+         * Thankfully, it does seem that no runtime services other than
+         * SetVirtualAddressMap() will touch boot services code, so we can
+         * get rid of it all at this point
+         */
+        efi_free_boot_services();
+
+        /*
          * Now that EFI is in virtual mode, update the function
          * pointers in the runtime service table to the new virtual addresses.
          *
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 2649426a7905..ac3aa54e2654 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -49,10 +49,11 @@ static void __init early_code_mapping_set_exec(int executable)
         if (!(__supported_pte_mask & _PAGE_NX))
                 return;
 
-        /* Make EFI runtime service code area executable */
+        /* Make EFI service code area executable */
         for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
                 md = p;
-                if (md->type == EFI_RUNTIME_SERVICES_CODE)
+                if (md->type == EFI_RUNTIME_SERVICES_CODE ||
+                    md->type == EFI_BOOT_SERVICES_CODE)
                         efi_set_executable(md, executable);
         }
 }
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index c58e0ea39ef5..68e467f69fec 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -1,7 +1,7 @@
 /*
  *      SGI UltraViolet TLB flush routines.
  *
- *      (c) 2008-2010 Cliff Wickman <cpw@sgi.com>, SGI.
+ *      (c) 2008-2011 Cliff Wickman <cpw@sgi.com>, SGI.
  *
  *      This code is released under the GNU General Public License version 2 or
  *      later.
@@ -35,6 +35,7 @@ static int timeout_base_ns[] = {
                 5242880,
                 167772160
 };
+
 static int timeout_us;
 static int nobau;
 static int baudisabled;
@@ -42,20 +43,70 @@ static spinlock_t disable_lock;
 static cycles_t congested_cycles;
 
 /* tunables: */
-static int max_bau_concurrent = MAX_BAU_CONCURRENT;
-static int max_bau_concurrent_constant = MAX_BAU_CONCURRENT;
-static int plugged_delay = PLUGGED_DELAY;
-static int plugsb4reset = PLUGSB4RESET;
-static int timeoutsb4reset = TIMEOUTSB4RESET;
-static int ipi_reset_limit = IPI_RESET_LIMIT;
-static int complete_threshold = COMPLETE_THRESHOLD;
-static int congested_response_us = CONGESTED_RESPONSE_US;
-static int congested_reps = CONGESTED_REPS;
-static int congested_period = CONGESTED_PERIOD;
+static int max_concurr          = MAX_BAU_CONCURRENT;
+static int max_concurr_const    = MAX_BAU_CONCURRENT;
+static int plugged_delay        = PLUGGED_DELAY;
+static int plugsb4reset         = PLUGSB4RESET;
+static int timeoutsb4reset      = TIMEOUTSB4RESET;
+static int ipi_reset_limit      = IPI_RESET_LIMIT;
+static int complete_threshold   = COMPLETE_THRESHOLD;
+static int congested_respns_us  = CONGESTED_RESPONSE_US;
+static int congested_reps       = CONGESTED_REPS;
+static int congested_period     = CONGESTED_PERIOD;
+
+static struct tunables tunables[] = {
+        {&max_concurr, MAX_BAU_CONCURRENT}, /* must be [0] */
+        {&plugged_delay, PLUGGED_DELAY},
+        {&plugsb4reset, PLUGSB4RESET},
+        {&timeoutsb4reset, TIMEOUTSB4RESET},
+        {&ipi_reset_limit, IPI_RESET_LIMIT},
+        {&complete_threshold, COMPLETE_THRESHOLD},
+        {&congested_respns_us, CONGESTED_RESPONSE_US},
+        {&congested_reps, CONGESTED_REPS},
+        {&congested_period, CONGESTED_PERIOD}
+};
+
 static struct dentry *tunables_dir;
 static struct dentry *tunables_file;
 
-static int __init setup_nobau(char *arg)
+/* these correspond to the statistics printed by ptc_seq_show() */
+static char *stat_description[] = {
+        "sent:     number of shootdown messages sent",
+        "stime:    time spent sending messages",
+        "numuvhubs: number of hubs targeted with shootdown",
+        "numuvhubs16: number times 16 or more hubs targeted",
+        "numuvhubs8: number times 8 or more hubs targeted",
+        "numuvhubs4: number times 4 or more hubs targeted",
+        "numuvhubs2: number times 2 or more hubs targeted",
+        "numuvhubs1: number times 1 hub targeted",
+        "numcpus:  number of cpus targeted with shootdown",
+        "dto:      number of destination timeouts",
+        "retries:  destination timeout retries sent",
+        "rok:   :  destination timeouts successfully retried",
+        "resetp:   ipi-style resource resets for plugs",
+        "resett:   ipi-style resource resets for timeouts",
+        "giveup:   fall-backs to ipi-style shootdowns",
+        "sto:      number of source timeouts",
+        "bz:       number of stay-busy's",
+        "throt:    number times spun in throttle",
+        "swack:   image of UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE",
+        "recv:     shootdown messages received",
+        "rtime:    time spent processing messages",
+        "all:      shootdown all-tlb messages",
+        "one:      shootdown one-tlb messages",
+        "mult:     interrupts that found multiple messages",
+        "none:     interrupts that found no messages",
+        "retry:    number of retry messages processed",
+        "canc:     number messages canceled by retries",
+        "nocan:    number retries that found nothing to cancel",
+        "reset:    number of ipi-style reset requests processed",
+        "rcan:     number messages canceled by reset requests",
+        "disable:  number times use of the BAU was disabled",
+        "enable:   number times use of the BAU was re-enabled"
+};
+
+static int __init
+setup_nobau(char *arg)
 {
         nobau = 1;
         return 0;
@@ -63,7 +114,7 @@ static int __init setup_nobau(char *arg)
 early_param("nobau", setup_nobau);
 
 /* base pnode in this partition */
-static int uv_partition_base_pnode __read_mostly;
+static int uv_base_pnode __read_mostly;
 /* position of pnode (which is nasid>>1): */
 static int uv_nshift __read_mostly;
 static unsigned long uv_mmask __read_mostly;
@@ -109,60 +160,52 @@ static int __init uvhub_to_first_apicid(int uvhub)
  * clear of the Timeout bit (as well) will free the resource. No reply will
  * be sent (the hardware will only do one reply per message).
  */
-static inline void uv_reply_to_message(struct msg_desc *mdp,
-                                       struct bau_control *bcp)
+static void reply_to_message(struct msg_desc *mdp, struct bau_control *bcp)
 {
         unsigned long dw;
-        struct bau_payload_queue_entry *msg;
+        struct bau_pq_entry *msg;
 
         msg = mdp->msg;
         if (!msg->canceled) {
-                dw = (msg->sw_ack_vector << UV_SW_ACK_NPENDING) |
-                                                msg->sw_ack_vector;
-                uv_write_local_mmr(
-                                UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS, dw);
+                dw = (msg->swack_vec << UV_SW_ACK_NPENDING) | msg->swack_vec;
+                write_mmr_sw_ack(dw);
         }
         msg->replied_to = 1;
-        msg->sw_ack_vector = 0;
+        msg->swack_vec = 0;
 }
 
 /*
  * Process the receipt of a RETRY message
  */
-static inline void uv_bau_process_retry_msg(struct msg_desc *mdp,
-                                            struct bau_control *bcp)
+static void bau_process_retry_msg(struct msg_desc *mdp,
+                                        struct bau_control *bcp)
 {
         int i;
         int cancel_count = 0;
-        int slot2;
         unsigned long msg_res;
         unsigned long mmr = 0;
-        struct bau_payload_queue_entry *msg;
-        struct bau_payload_queue_entry *msg2;
-        struct ptc_stats *stat;
+        struct bau_pq_entry *msg = mdp->msg;
+        struct bau_pq_entry *msg2;
+        struct ptc_stats *stat = bcp->statp;
 
-        msg = mdp->msg;
-        stat = bcp->statp;
         stat->d_retries++;
         /*
          * cancel any message from msg+1 to the retry itself
          */
         for (msg2 = msg+1, i = 0; i < DEST_Q_SIZE; msg2++, i++) {
-                if (msg2 > mdp->va_queue_last)
-                        msg2 = mdp->va_queue_first;
+                if (msg2 > mdp->queue_last)
+                        msg2 = mdp->queue_first;
                 if (msg2 == msg)
                         break;
 
-                /* same conditions for cancellation as uv_do_reset */
+                /* same conditions for cancellation as do_reset */
                 if ((msg2->replied_to == 0) && (msg2->canceled == 0) &&
-                    (msg2->sw_ack_vector) && ((msg2->sw_ack_vector &
-                        msg->sw_ack_vector) == 0) &&
+                    (msg2->swack_vec) && ((msg2->swack_vec &
+                        msg->swack_vec) == 0) &&
                     (msg2->sending_cpu == msg->sending_cpu) &&
                     (msg2->msg_type != MSG_NOOP)) {
-                        slot2 = msg2 - mdp->va_queue_first;
-                        mmr = uv_read_local_mmr
-                                (UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE);
-                        msg_res = msg2->sw_ack_vector;
+                        mmr = read_mmr_sw_ack();
+                        msg_res = msg2->swack_vec;
                         /*
                          * This is a message retry; clear the resources held
                          * by the previous message only if they timed out.
@@ -170,6 +213,7 @@ static inline void uv_bau_process_retry_msg(struct msg_desc *mdp,
                          * situation to report.
                          */
                         if (mmr & (msg_res << UV_SW_ACK_NPENDING)) {
+                                unsigned long mr;
                                 /*
                                  * is the resource timed out?
                                  * make everyone ignore the cancelled message.
@@ -177,10 +221,8 @@ static inline void uv_bau_process_retry_msg(struct msg_desc *mdp,
                                 msg2->canceled = 1;
                                 stat->d_canceled++;
                                 cancel_count++;
-                                uv_write_local_mmr(
-                                    UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS,
-                                        (msg_res << UV_SW_ACK_NPENDING) |
-                                         msg_res);
+                                mr = (msg_res << UV_SW_ACK_NPENDING) | msg_res;
+                                write_mmr_sw_ack(mr);
                         }
                 }
         }
@@ -192,20 +234,19 @@ static inline void uv_bau_process_retry_msg(struct msg_desc *mdp,
  * Do all the things a cpu should do for a TLB shootdown message.
  * Other cpu's may come here at the same time for this message.
  */
-static void uv_bau_process_message(struct msg_desc *mdp,
-                                   struct bau_control *bcp)
+static void bau_process_message(struct msg_desc *mdp,
+                                        struct bau_control *bcp)
 {
-        int msg_ack_count;
         short socket_ack_count = 0;
-        struct ptc_stats *stat;
-        struct bau_payload_queue_entry *msg;
+        short *sp;
+        struct atomic_short *asp;
+        struct ptc_stats *stat = bcp->statp;
+        struct bau_pq_entry *msg = mdp->msg;
         struct bau_control *smaster = bcp->socket_master;
 
         /*
          * This must be a normal message, or retry of a normal message
          */
-        msg = mdp->msg;
-        stat = bcp->statp;
         if (msg->address == TLB_FLUSH_ALL) {
                 local_flush_tlb();
                 stat->d_alltlb++;
@@ -222,30 +263,32 @@ static void uv_bau_process_message(struct msg_desc *mdp,
          * cpu number.
          */
         if (msg->msg_type == MSG_RETRY && bcp == bcp->uvhub_master)
-                uv_bau_process_retry_msg(mdp, bcp);
+                bau_process_retry_msg(mdp, bcp);
 
         /*
-         * This is a sw_ack message, so we have to reply to it.
+         * This is a swack message, so we have to reply to it.
          * Count each responding cpu on the socket. This avoids
          * pinging the count's cache line back and forth between
          * the sockets.
          */
-        socket_ack_count = atomic_add_short_return(1, (struct atomic_short *)
-                        &smaster->socket_acknowledge_count[mdp->msg_slot]);
+        sp = &smaster->socket_acknowledge_count[mdp->msg_slot];
+        asp = (struct atomic_short *)sp;
+        socket_ack_count = atom_asr(1, asp);
         if (socket_ack_count == bcp->cpus_in_socket) {
+                int msg_ack_count;
                 /*
                  * Both sockets dump their completed count total into
                  * the message's count.
                  */
                 smaster->socket_acknowledge_count[mdp->msg_slot] = 0;
-                msg_ack_count = atomic_add_short_return(socket_ack_count,
-                                (struct atomic_short *)&msg->acknowledge_count);
+                asp = (struct atomic_short *)&msg->acknowledge_count;
+                msg_ack_count = atom_asr(socket_ack_count, asp);
 
                 if (msg_ack_count == bcp->cpus_in_uvhub) {
                         /*
                          * All cpus in uvhub saw it; reply
                          */
-                        uv_reply_to_message(mdp, bcp);
+                        reply_to_message(mdp, bcp);
                 }
         }
 
@@ -268,62 +311,51 @@ static int uvhub_to_first_cpu(int uvhub)
  * Last resort when we get a large number of destination timeouts is
  * to clear resources held by a given cpu.
  * Do this with IPI so that all messages in the BAU message queue
- * can be identified by their nonzero sw_ack_vector field.
+ * can be identified by their nonzero swack_vec field.
  *
  * This is entered for a single cpu on the uvhub.
  * The sender want's this uvhub to free a specific message's
- * sw_ack resources.
+ * swack resources.
  */
-static void
-uv_do_reset(void *ptr)
+static void do_reset(void *ptr)
 {
         int i;
-        int slot;
-        int count = 0;
-        unsigned long mmr;
-        unsigned long msg_res;
-        struct bau_control *bcp;
-        struct reset_args *rap;
-        struct bau_payload_queue_entry *msg;
-        struct ptc_stats *stat;
+        struct bau_control *bcp = &per_cpu(bau_control, smp_processor_id());
+        struct reset_args *rap = (struct reset_args *)ptr;
+        struct bau_pq_entry *msg;
+        struct ptc_stats *stat = bcp->statp;
 
-        bcp = &per_cpu(bau_control, smp_processor_id());
-        rap = (struct reset_args *)ptr;
-        stat = bcp->statp;
         stat->d_resets++;
-
         /*
          * We're looking for the given sender, and
-         * will free its sw_ack resource.
+         * will free its swack resource.
          * If all cpu's finally responded after the timeout, its
          * message 'replied_to' was set.
          */
-        for (msg = bcp->va_queue_first, i = 0; i < DEST_Q_SIZE; msg++, i++) {
-                /* uv_do_reset: same conditions for cancellation as
-                   uv_bau_process_retry_msg() */
+        for (msg = bcp->queue_first, i = 0; i < DEST_Q_SIZE; msg++, i++) {
+                unsigned long msg_res;
+                /* do_reset: same conditions for cancellation as
+                   bau_process_retry_msg() */
                 if ((msg->replied_to == 0) &&
                     (msg->canceled == 0) &&
                     (msg->sending_cpu == rap->sender) &&
-                    (msg->sw_ack_vector) &&
+                    (msg->swack_vec) &&
                     (msg->msg_type != MSG_NOOP)) {
+                        unsigned long mmr;
+                        unsigned long mr;
                         /*
                          * make everyone else ignore this message
                          */
                         msg->canceled = 1;
-                        slot = msg - bcp->va_queue_first;
-                        count++;
                         /*
                          * only reset the resource if it is still pending
                          */
-                        mmr = uv_read_local_mmr
-                                        (UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE);
-                        msg_res = msg->sw_ack_vector;
+                        mmr = read_mmr_sw_ack();
+                        msg_res = msg->swack_vec;
+                        mr = (msg_res << UV_SW_ACK_NPENDING) | msg_res;
                         if (mmr & msg_res) {
                                 stat->d_rcanceled++;
-                                uv_write_local_mmr(
-                                    UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS,
-                                        (msg_res << UV_SW_ACK_NPENDING) |
-                                         msg_res);
+                                write_mmr_sw_ack(mr);
                         }
                 }
         }
@@ -334,39 +366,38 @@ uv_do_reset(void *ptr)
  * Use IPI to get all target uvhubs to release resources held by
  * a given sending cpu number.
  */
-static void uv_reset_with_ipi(struct bau_target_uvhubmask *distribution,
-                              int sender)
+static void reset_with_ipi(struct bau_targ_hubmask *distribution, int sender)
 {
         int uvhub;
-        int cpu;
+        int maskbits;
         cpumask_t mask;
         struct reset_args reset_args;
 
         reset_args.sender = sender;
-
         cpus_clear(mask);
         /* find a single cpu for each uvhub in this distribution mask */
-        for (uvhub = 0;
-                    uvhub < sizeof(struct bau_target_uvhubmask) * BITSPERBYTE;
-                    uvhub++) {
+        maskbits = sizeof(struct bau_targ_hubmask) * BITSPERBYTE;
+        for (uvhub = 0; uvhub < maskbits; uvhub++) {
+                int cpu;
                 if (!bau_uvhub_isset(uvhub, distribution))
                         continue;
                 /* find a cpu for this uvhub */
                 cpu = uvhub_to_first_cpu(uvhub);
                 cpu_set(cpu, mask);
         }
-        /* IPI all cpus; Preemption is already disabled */
-        smp_call_function_many(&mask, uv_do_reset, (void *)&reset_args, 1);
+
+        /* IPI all cpus; preemption is already disabled */
+        smp_call_function_many(&mask, do_reset, (void *)&reset_args, 1);
         return;
 }
 
-static inline unsigned long
-cycles_2_us(unsigned long long cyc)
+static inline unsigned long cycles_2_us(unsigned long long cyc)
 {
         unsigned long long ns;
         unsigned long us;
-        ns =  (cyc * per_cpu(cyc2ns, smp_processor_id()))
-                                                >> CYC2NS_SCALE_FACTOR;
+        int cpu = smp_processor_id();
+
+        ns =  (cyc * per_cpu(cyc2ns, cpu)) >> CYC2NS_SCALE_FACTOR;
         us = ns / 1000;
         return us;
 }
@@ -376,56 +407,56 @@ cycles_2_us(unsigned long long cyc)
  * leaves uvhub_quiesce set so that no new broadcasts are started by
  * bau_flush_send_and_wait()
  */
-static inline void
-quiesce_local_uvhub(struct bau_control *hmaster)
+static inline void quiesce_local_uvhub(struct bau_control *hmaster)
 {
-        atomic_add_short_return(1, (struct atomic_short *)
-                 &hmaster->uvhub_quiesce);
+        atom_asr(1, (struct atomic_short *)&hmaster->uvhub_quiesce);
 }
 
 /*
  * mark this quiet-requestor as done
  */
-static inline void
-end_uvhub_quiesce(struct bau_control *hmaster)
+static inline void end_uvhub_quiesce(struct bau_control *hmaster)
 {
-        atomic_add_short_return(-1, (struct atomic_short *)
-                &hmaster->uvhub_quiesce);
+        atom_asr(-1, (struct atomic_short *)&hmaster->uvhub_quiesce);
+}
+
+static unsigned long uv1_read_status(unsigned long mmr_offset, int right_shift)
+{
+        unsigned long descriptor_status;
+
+        descriptor_status = uv_read_local_mmr(mmr_offset);
+        descriptor_status >>= right_shift;
+        descriptor_status &= UV_ACT_STATUS_MASK;
+        return descriptor_status;
 }
 
 /*
  * Wait for completion of a broadcast software ack message
  * return COMPLETE, RETRY(PLUGGED or TIMEOUT) or GIVEUP
  */
-static int uv_wait_completion(struct bau_desc *bau_desc,
-        unsigned long mmr_offset, int right_shift, int this_cpu,
-        struct bau_control *bcp, struct bau_control *smaster, long try)
+static int uv1_wait_completion(struct bau_desc *bau_desc,
+                                unsigned long mmr_offset, int right_shift,
+                                struct bau_control *bcp, long try)
 {
         unsigned long descriptor_status;
-        cycles_t ttime;
+        cycles_t ttm;
         struct ptc_stats *stat = bcp->statp;
-        struct bau_control *hmaster;
-
-        hmaster = bcp->uvhub_master;
 
+        descriptor_status = uv1_read_status(mmr_offset, right_shift);
         /* spin on the status MMR, waiting for it to go idle */
-        while ((descriptor_status = (((unsigned long)
-                uv_read_local_mmr(mmr_offset) >>
-                        right_shift) & UV_ACT_STATUS_MASK)) !=
-                        DESC_STATUS_IDLE) {
+        while ((descriptor_status != DS_IDLE)) {
                 /*
-                 * Our software ack messages may be blocked because there are
-                 * no swack resources available.  As long as none of them
-                 * has timed out hardware will NACK our message and its
-                 * state will stay IDLE.
+                 * Our software ack messages may be blocked because
+                 * there are no swack resources available.  As long
+                 * as none of them has timed out hardware will NACK
+                 * our message and its state will stay IDLE.
                  */
-                if (descriptor_status == DESC_STATUS_SOURCE_TIMEOUT) {
+                if (descriptor_status == DS_SOURCE_TIMEOUT) {
                         stat->s_stimeout++;
                         return FLUSH_GIVEUP;
-                } else if (descriptor_status ==
-                                        DESC_STATUS_DESTINATION_TIMEOUT) {
+                } else if (descriptor_status == DS_DESTINATION_TIMEOUT) {
                         stat->s_dtimeout++;
-                        ttime = get_cycles();
+                        ttm = get_cycles();
 
                         /*
                          * Our retries may be blocked by all destination
@@ -433,8 +464,7 @@ static int uv_wait_completion(struct bau_desc *bau_desc,
                          * pending.  In that case hardware returns the
                          * ERROR that looks like a destination timeout.
                          */
-                        if (cycles_2_us(ttime - bcp->send_message) <
-                                                        timeout_us) {
+                        if (cycles_2_us(ttm - bcp->send_message) < timeout_us) {
                                 bcp->conseccompletes = 0;
                                 return FLUSH_RETRY_PLUGGED;
                         }
@@ -447,80 +477,160 @@ static int uv_wait_completion(struct bau_desc *bau_desc,
                          */
                         cpu_relax();
                 }
+                descriptor_status = uv1_read_status(mmr_offset, right_shift);
         }
         bcp->conseccompletes++;
         return FLUSH_COMPLETE;
 }
 
-static inline cycles_t
-sec_2_cycles(unsigned long sec)
+/*
+ * UV2 has an extra bit of status in the ACTIVATION_STATUS_2 register.
+ */
+static unsigned long uv2_read_status(unsigned long offset, int rshft, int cpu)
 {
-        unsigned long ns;
-        cycles_t cyc;
+        unsigned long descriptor_status;
+        unsigned long descriptor_status2;
 
-        ns = sec * 1000000000;
-        cyc = (ns << CYC2NS_SCALE_FACTOR)/(per_cpu(cyc2ns, smp_processor_id()));
-        return cyc;
+        descriptor_status = ((read_lmmr(offset) >> rshft) & UV_ACT_STATUS_MASK);
+        descriptor_status2 = (read_mmr_uv2_status() >> cpu) & 0x1UL;
+        descriptor_status = (descriptor_status << 1) | descriptor_status2;
+        return descriptor_status;
+}
+
+static int uv2_wait_completion(struct bau_desc *bau_desc,
+                                unsigned long mmr_offset, int right_shift,
+                                struct bau_control *bcp, long try)
+{
+        unsigned long descriptor_stat;
+        cycles_t ttm;
+        int cpu = bcp->uvhub_cpu;
+        struct ptc_stats *stat = bcp->statp;
+
+        descriptor_stat = uv2_read_status(mmr_offset, right_shift, cpu);
+
+        /* spin on the status MMR, waiting for it to go idle */
+        while (descriptor_stat != UV2H_DESC_IDLE) {
+                /*
+                 * Our software ack messages may be blocked because
+                 * there are no swack resources available.  As long
+                 * as none of them has timed out hardware will NACK
+                 * our message and its state will stay IDLE.
+                 */
+                if ((descriptor_stat == UV2H_DESC_SOURCE_TIMEOUT) ||
+                    (descriptor_stat == UV2H_DESC_DEST_STRONG_NACK) ||
+                    (descriptor_stat == UV2H_DESC_DEST_PUT_ERR)) {
+                        stat->s_stimeout++;
+                        return FLUSH_GIVEUP;
+                } else if (descriptor_stat == UV2H_DESC_DEST_TIMEOUT) {
+                        stat->s_dtimeout++;
+                        ttm = get_cycles();
+                        /*
+                         * Our retries may be blocked by all destination
+                         * swack resources being consumed, and a timeout
+                         * pending.  In that case hardware returns the
+                         * ERROR that looks like a destination timeout.
+                         */
+                        if (cycles_2_us(ttm - bcp->send_message) < timeout_us) {
+                                bcp->conseccompletes = 0;
+                                return FLUSH_RETRY_PLUGGED;
+                        }
+                        bcp->conseccompletes = 0;
+                        return FLUSH_RETRY_TIMEOUT;
+                } else {
+                        /*
+                         * descriptor_stat is still BUSY
+                         */
+                        cpu_relax();
+                }
+                descriptor_stat = uv2_read_status(mmr_offset, right_shift, cpu);
+        }
+        bcp->conseccompletes++;
+        return FLUSH_COMPLETE;
 }
 
 /*
- * conditionally add 1 to *v, unless *v is >= u
- * return 0 if we cannot add 1 to *v because it is >= u
- * return 1 if we can add 1 to *v because it is < u
- * the add is atomic
- *
- * This is close to atomic_add_unless(), but this allows the 'u' value
- * to be lowered below the current 'v'.  atomic_add_unless can only stop
- * on equal.
+ * There are 2 status registers; each and array[32] of 2 bits. Set up for
+ * which register to read and position in that register based on cpu in
+ * current hub.
  */
-static inline int atomic_inc_unless_ge(spinlock_t *lock, atomic_t *v, int u)
+static int wait_completion(struct bau_desc *bau_desc,
+                                struct bau_control *bcp, long try)
 {
-        spin_lock(lock);
-        if (atomic_read(v) >= u) {
-                spin_unlock(lock);
-                return 0;
+        int right_shift;
+        unsigned long mmr_offset;
+        int cpu = bcp->uvhub_cpu;
+
+        if (cpu < UV_CPUS_PER_AS) {
+                mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_0;
+                right_shift = cpu * UV_ACT_STATUS_SIZE;
+        } else {
+                mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_1;
+                right_shift = ((cpu - UV_CPUS_PER_AS) * UV_ACT_STATUS_SIZE);
         }
-        atomic_inc(v);
-        spin_unlock(lock);
-        return 1;
+
+        if (is_uv1_hub())
+                return uv1_wait_completion(bau_desc, mmr_offset, right_shift,
+                                                                bcp, try);
+        else
+                return uv2_wait_completion(bau_desc, mmr_offset, right_shift,
+                                                                bcp, try);
+}
+
+static inline cycles_t sec_2_cycles(unsigned long sec)
+{
+        unsigned long ns;
+        cycles_t cyc;
+
+        ns = sec * 1000000000;
+        cyc = (ns << CYC2NS_SCALE_FACTOR)/(per_cpu(cyc2ns, smp_processor_id()));
+        return cyc;
 }
 
 /*
- * Our retries are blocked by all destination swack resources being
+ * Our retries are blocked by all destination sw ack resources being
  * in use, and a timeout is pending. In that case hardware immediately
  * returns the ERROR that looks like a destination timeout.
  */
-static void
-destination_plugged(struct bau_desc *bau_desc, struct bau_control *bcp,
+static void destination_plugged(struct bau_desc *bau_desc,
+                        struct bau_control *bcp,
                         struct bau_control *hmaster, struct ptc_stats *stat)
 {
         udelay(bcp->plugged_delay);
         bcp->plugged_tries++;
+
         if (bcp->plugged_tries >= bcp->plugsb4reset) {
                 bcp->plugged_tries = 0;
+
                 quiesce_local_uvhub(hmaster);
+
                 spin_lock(&hmaster->queue_lock);
-                uv_reset_with_ipi(&bau_desc->distribution, bcp->cpu);
+                reset_with_ipi(&bau_desc->distribution, bcp->cpu);
                 spin_unlock(&hmaster->queue_lock);
+
                 end_uvhub_quiesce(hmaster);
+
                 bcp->ipi_attempts++;
                 stat->s_resets_plug++;
         }
 }
 
-static void
-destination_timeout(struct bau_desc *bau_desc, struct bau_control *bcp,
-                        struct bau_control *hmaster, struct ptc_stats *stat)
+static void destination_timeout(struct bau_desc *bau_desc,
+                        struct bau_control *bcp, struct bau_control *hmaster,
+                        struct ptc_stats *stat)
 {
-        hmaster->max_bau_concurrent = 1;
+        hmaster->max_concurr = 1;
         bcp->timeout_tries++;
         if (bcp->timeout_tries >= bcp->timeoutsb4reset) {
                 bcp->timeout_tries = 0;
+
                 quiesce_local_uvhub(hmaster);
+
                 spin_lock(&hmaster->queue_lock);
-                uv_reset_with_ipi(&bau_desc->distribution, bcp->cpu);
+                reset_with_ipi(&bau_desc->distribution, bcp->cpu);
                 spin_unlock(&hmaster->queue_lock);
+
                 end_uvhub_quiesce(hmaster);
+
                 bcp->ipi_attempts++;
                 stat->s_resets_timeout++;
         }
@@ -530,34 +640,104 @@ destination_timeout(struct bau_desc *bau_desc, struct bau_control *bcp,
  * Completions are taking a very long time due to a congested numalink
  * network.
  */
-static void
-disable_for_congestion(struct bau_control *bcp, struct ptc_stats *stat)
+static void disable_for_congestion(struct bau_control *bcp,
+                                        struct ptc_stats *stat)
 {
-        int tcpu;
-        struct bau_control *tbcp;
-
         /* let only one cpu do this disabling */
         spin_lock(&disable_lock);
+
         if (!baudisabled && bcp->period_requests &&
             ((bcp->period_time / bcp->period_requests) > congested_cycles)) {
+                int tcpu;
+                struct bau_control *tbcp;
                 /* it becomes this cpu's job to turn on the use of the
                    BAU again */
                 baudisabled = 1;
                 bcp->set_bau_off = 1;
-                bcp->set_bau_on_time = get_cycles() +
-                        sec_2_cycles(bcp->congested_period);
+                bcp->set_bau_on_time = get_cycles();
+                bcp->set_bau_on_time += sec_2_cycles(bcp->cong_period);
                 stat->s_bau_disabled++;
                 for_each_present_cpu(tcpu) {
                         tbcp = &per_cpu(bau_control, tcpu);
-                                tbcp->baudisabled = 1;
+                        tbcp->baudisabled = 1;
                 }
         }
+
         spin_unlock(&disable_lock);
 }
 
-/**
- * uv_flush_send_and_wait
- *
+static void count_max_concurr(int stat, struct bau_control *bcp,
+                                struct bau_control *hmaster)
+{
+        bcp->plugged_tries = 0;
+        bcp->timeout_tries = 0;
+        if (stat != FLUSH_COMPLETE)
+                return;
+        if (bcp->conseccompletes <= bcp->complete_threshold)
+                return;
+        if (hmaster->max_concurr >= hmaster->max_concurr_const)
+                return;
+        hmaster->max_concurr++;
+}
+
+static void record_send_stats(cycles_t time1, cycles_t time2,
+                struct bau_control *bcp, struct ptc_stats *stat,
+                int completion_status, int try)
+{
+        cycles_t elapsed;
+
+        if (time2 > time1) {
+                elapsed = time2 - time1;
+                stat->s_time += elapsed;
+
+                if ((completion_status == FLUSH_COMPLETE) && (try == 1)) {
+                        bcp->period_requests++;
+                        bcp->period_time += elapsed;
+                        if ((elapsed > congested_cycles) &&
+                            (bcp->period_requests > bcp->cong_reps))
+                                disable_for_congestion(bcp, stat);
+                }
+        } else
+                stat->s_requestor--;
+
+        if (completion_status == FLUSH_COMPLETE && try > 1)
+                stat->s_retriesok++;
+        else if (completion_status == FLUSH_GIVEUP)
+                stat->s_giveup++;
+}
+
+/*
+ * Because of a uv1 hardware bug only a limited number of concurrent
+ * requests can be made.
+ */
+static void uv1_throttle(struct bau_control *hmaster, struct ptc_stats *stat)
+{
+        spinlock_t *lock = &hmaster->uvhub_lock;
+        atomic_t *v;
+
+        v = &hmaster->active_descriptor_count;
+        if (!atomic_inc_unless_ge(lock, v, hmaster->max_concurr)) {
+                stat->s_throttles++;
+                do {
+                        cpu_relax();
+                } while (!atomic_inc_unless_ge(lock, v, hmaster->max_concurr));
+        }
+}
+
+/*
+ * Handle the completion status of a message send.
+ */
+static void handle_cmplt(int completion_status, struct bau_desc *bau_desc,
+                        struct bau_control *bcp, struct bau_control *hmaster,
+                        struct ptc_stats *stat)
+{
+        if (completion_status == FLUSH_RETRY_PLUGGED)
+                destination_plugged(bau_desc, bcp, hmaster, stat);
+        else if (completion_status == FLUSH_RETRY_TIMEOUT)
+                destination_timeout(bau_desc, bcp, hmaster, stat);
+}
+
+/*
  * Send a broadcast and wait for it to complete.
  *
  * The flush_mask contains the cpus the broadcast is to be sent to including
@@ -568,44 +748,23 @@ disable_for_congestion(struct bau_control *bcp, struct ptc_stats *stat)
  * returned to the kernel.
  */
 int uv_flush_send_and_wait(struct bau_desc *bau_desc,
-                           struct cpumask *flush_mask, struct bau_control *bcp)
+                        struct cpumask *flush_mask, struct bau_control *bcp)
 {
-        int right_shift;
-        int completion_status = 0;
         int seq_number = 0;
+        int completion_stat = 0;
         long try = 0;
-        int cpu = bcp->uvhub_cpu;
-        int this_cpu = bcp->cpu;
-        unsigned long mmr_offset;
         unsigned long index;
         cycles_t time1;
         cycles_t time2;
-        cycles_t elapsed;
         struct ptc_stats *stat = bcp->statp;
-        struct bau_control *smaster = bcp->socket_master;
         struct bau_control *hmaster = bcp->uvhub_master;
 
-        if (!atomic_inc_unless_ge(&hmaster->uvhub_lock,
-                        &hmaster->active_descriptor_count,
-                        hmaster->max_bau_concurrent)) {
-                stat->s_throttles++;
-                do {
-                        cpu_relax();
-                } while (!atomic_inc_unless_ge(&hmaster->uvhub_lock,
-                        &hmaster->active_descriptor_count,
-                        hmaster->max_bau_concurrent));
-        }
+        if (is_uv1_hub())
+                uv1_throttle(hmaster, stat);
+
         while (hmaster->uvhub_quiesce)
                 cpu_relax();
 
-        if (cpu < UV_CPUS_PER_ACT_STATUS) {
-                mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_0;
-                right_shift = cpu * UV_ACT_STATUS_SIZE;
-        } else {
-                mmr_offset = UVH_LB_BAU_SB_ACTIVATION_STATUS_1;
-                right_shift =
-                    ((cpu - UV_CPUS_PER_ACT_STATUS) * UV_ACT_STATUS_SIZE);
-        }
         time1 = get_cycles();
         do {
                 if (try == 0) {
@@ -615,64 +774,134 @@ int uv_flush_send_and_wait(struct bau_desc *bau_desc,
                         bau_desc->header.msg_type = MSG_RETRY;
                         stat->s_retry_messages++;
                 }
+
                 bau_desc->header.sequence = seq_number;
-                index = (1UL << UVH_LB_BAU_SB_ACTIVATION_CONTROL_PUSH_SHFT) |
-                        bcp->uvhub_cpu;
+                index = (1UL << AS_PUSH_SHIFT) | bcp->uvhub_cpu;
                 bcp->send_message = get_cycles();
-                uv_write_local_mmr(UVH_LB_BAU_SB_ACTIVATION_CONTROL, index);
+
+                write_mmr_activation(index);
+
                 try++;
-                completion_status = uv_wait_completion(bau_desc, mmr_offset,
-                        right_shift, this_cpu, bcp, smaster, try);
+                completion_stat = wait_completion(bau_desc, bcp, try);
+
+                handle_cmplt(completion_stat, bau_desc, bcp, hmaster, stat);
 
-                if (completion_status == FLUSH_RETRY_PLUGGED) {
-                        destination_plugged(bau_desc, bcp, hmaster, stat);
-                } else if (completion_status == FLUSH_RETRY_TIMEOUT) {
-                        destination_timeout(bau_desc, bcp, hmaster, stat);
-                }
                 if (bcp->ipi_attempts >= bcp->ipi_reset_limit) {
                         bcp->ipi_attempts = 0;
-                        completion_status = FLUSH_GIVEUP;
+                        completion_stat = FLUSH_GIVEUP;
                         break;
                 }
                 cpu_relax();
-        } while ((completion_status == FLUSH_RETRY_PLUGGED) ||
-                 (completion_status == FLUSH_RETRY_TIMEOUT));
+        } while ((completion_stat == FLUSH_RETRY_PLUGGED) ||
+                 (completion_stat == FLUSH_RETRY_TIMEOUT));
+
         time2 = get_cycles();
-        bcp->plugged_tries = 0;
-        bcp->timeout_tries = 0;
-        if ((completion_status == FLUSH_COMPLETE) &&
-            (bcp->conseccompletes > bcp->complete_threshold) &&
-            (hmaster->max_bau_concurrent <
-                                        hmaster->max_bau_concurrent_constant))
-                        hmaster->max_bau_concurrent++;
+
+        count_max_concurr(completion_stat, bcp, hmaster);
+
         while (hmaster->uvhub_quiesce)
                 cpu_relax();
+
         atomic_dec(&hmaster->active_descriptor_count);
-        if (time2 > time1) {
-                elapsed = time2 - time1;
-                stat->s_time += elapsed;
-                if ((completion_status == FLUSH_COMPLETE) && (try == 1)) {
-                        bcp->period_requests++;
-                        bcp->period_time += elapsed;
-                        if ((elapsed > congested_cycles) &&
-                            (bcp->period_requests > bcp->congested_reps)) {
-                                disable_for_congestion(bcp, stat);
+
+        record_send_stats(time1, time2, bcp, stat, completion_stat, try);
+
+        if (completion_stat == FLUSH_GIVEUP)
+                return 1;
+        return 0;
+}
+
+/*
+ * The BAU is disabled. When the disabled time period has expired, the cpu
+ * that disabled it must re-enable it.
+ * Return 0 if it is re-enabled for all cpus.
+ */
+static int check_enable(struct bau_control *bcp, struct ptc_stats *stat)
+{
+        int tcpu;
+        struct bau_control *tbcp;
+
+        if (bcp->set_bau_off) {
+                if (get_cycles() >= bcp->set_bau_on_time) {
+                        stat->s_bau_reenabled++;
+                        baudisabled = 0;
+                        for_each_present_cpu(tcpu) {
+                                tbcp = &per_cpu(bau_control, tcpu);
+                                tbcp->baudisabled = 0;
+                                tbcp->period_requests = 0;
+                                tbcp->period_time = 0;
                         }
+                        return 0;
                 }
+        }
+        return -1;
+}
+
+static void record_send_statistics(struct ptc_stats *stat, int locals, int hubs,
+                                int remotes, struct bau_desc *bau_desc)
+{
+        stat->s_requestor++;
+        stat->s_ntargcpu += remotes + locals;
+        stat->s_ntargremotes += remotes;
+        stat->s_ntarglocals += locals;
+
+        /* uvhub statistics */
+        hubs = bau_uvhub_weight(&bau_desc->distribution);
+        if (locals) {
+                stat->s_ntarglocaluvhub++;
+                stat->s_ntargremoteuvhub += (hubs - 1);
         } else
-                stat->s_requestor--;
-        if (completion_status == FLUSH_COMPLETE && try > 1)
-                stat->s_retriesok++;
-        else if (completion_status == FLUSH_GIVEUP) {
-                stat->s_giveup++;
-                return 1;
+                stat->s_ntargremoteuvhub += hubs;
+
+        stat->s_ntarguvhub += hubs;
+
+        if (hubs >= 16)
+                stat->s_ntarguvhub16++;
+        else if (hubs >= 8)
+                stat->s_ntarguvhub8++;
+        else if (hubs >= 4)
+                stat->s_ntarguvhub4++;
+        else if (hubs >= 2)
+                stat->s_ntarguvhub2++;
+        else
+                stat->s_ntarguvhub1++;
+}
+
+/*
+ * Translate a cpu mask to the uvhub distribution mask in the BAU
+ * activation descriptor.
+ */
+static int set_distrib_bits(struct cpumask *flush_mask, struct bau_control *bcp,
+                        struct bau_desc *bau_desc, int *localsp, int *remotesp)
+{
+        int cpu;
+        int pnode;
+        int cnt = 0;
+        struct hub_and_pnode *hpp;
+
+        for_each_cpu(cpu, flush_mask) {
+                /*
+                 * The distribution vector is a bit map of pnodes, relative
+                 * to the partition base pnode (and the partition base nasid
+                 * in the header).
+                 * Translate cpu to pnode and hub using a local memory array.
+                 */
+                hpp = &bcp->socket_master->thp[cpu];
+                pnode = hpp->pnode - bcp->partition_base_pnode;
+                bau_uvhub_set(pnode, &bau_desc->distribution);
+                cnt++;
+                if (hpp->uvhub == bcp->uvhub)
+                        (*localsp)++;
+                else
+                        (*remotesp)++;
         }
+        if (!cnt)
+                return 1;
         return 0;
 }
 
-/**
- * uv_flush_tlb_others - globally purge translation cache of a virtual
- * address or all TLB's
+/*
+ * globally purge translation cache of a virtual address or all TLB's
  * @cpumask: mask of all cpu's in which the address is to be removed
  * @mm: mm_struct containing virtual address range
  * @va: virtual address to be removed (or TLB_FLUSH_ALL for all TLB's on cpu)
@@ -696,20 +925,16 @@ int uv_flush_send_and_wait(struct bau_desc *bau_desc,
  * done.  The returned pointer is valid till preemption is re-enabled.
  */
 const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
-                                          struct mm_struct *mm,
-                                          unsigned long va, unsigned int cpu)
+                                struct mm_struct *mm, unsigned long va,
+                                unsigned int cpu)
 {
         int locals = 0;
         int remotes = 0;
         int hubs = 0;
-        int tcpu;
-        int tpnode;
         struct bau_desc *bau_desc;
         struct cpumask *flush_mask;
         struct ptc_stats *stat;
         struct bau_control *bcp;
-        struct bau_control *tbcp;
-        struct hub_and_pnode *hpp;
 
         /* kernel was booted 'nobau' */
         if (nobau)
@@ -720,20 +945,8 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 
         /* bau was disabled due to slow response */
         if (bcp->baudisabled) {
-                /* the cpu that disabled it must re-enable it */
-                if (bcp->set_bau_off) {
-                        if (get_cycles() >= bcp->set_bau_on_time) {
-                                stat->s_bau_reenabled++;
-                                baudisabled = 0;
-                                for_each_present_cpu(tcpu) {
-                                        tbcp = &per_cpu(bau_control, tcpu);
-                                        tbcp->baudisabled = 0;
-                                        tbcp->period_requests = 0;
-                                        tbcp->period_time = 0;
-                                }
-                        }
-                }
-                return cpumask;
+                if (check_enable(bcp, stat))
+                        return cpumask;
         }
 
         /*
@@ -744,59 +957,20 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
         flush_mask = (struct cpumask *)per_cpu(uv_flush_tlb_mask, cpu);
         /* don't actually do a shootdown of the local cpu */
         cpumask_andnot(flush_mask, cpumask, cpumask_of(cpu));
+
         if (cpu_isset(cpu, *cpumask))
                 stat->s_ntargself++;
 
         bau_desc = bcp->descriptor_base;
-        bau_desc += UV_ITEMS_PER_DESCRIPTOR * bcp->uvhub_cpu;
+        bau_desc += ITEMS_PER_DESC * bcp->uvhub_cpu;
         bau_uvhubs_clear(&bau_desc->distribution, UV_DISTRIBUTION_SIZE);
-
-        for_each_cpu(tcpu, flush_mask) {
-                /*
-                 * The distribution vector is a bit map of pnodes, relative
-                 * to the partition base pnode (and the partition base nasid
-                 * in the header).
-                 * Translate cpu to pnode and hub using an array stored
-                 * in local memory.
-                 */
-                hpp = &bcp->socket_master->target_hub_and_pnode[tcpu];
-                tpnode = hpp->pnode - bcp->partition_base_pnode;
-                bau_uvhub_set(tpnode, &bau_desc->distribution);
-                if (hpp->uvhub == bcp->uvhub)
-                        locals++;
-                else
-                        remotes++;
-        }
-        if ((locals + remotes) == 0)
+        if (set_distrib_bits(flush_mask, bcp, bau_desc, &locals, &remotes))
                 return NULL;
-        stat->s_requestor++;
-        stat->s_ntargcpu += remotes + locals;
-        stat->s_ntargremotes += remotes;
-        stat->s_ntarglocals += locals;
-        remotes = bau_uvhub_weight(&bau_desc->distribution);
 
-        /* uvhub statistics */
-        hubs = bau_uvhub_weight(&bau_desc->distribution);
-        if (locals) {
-                stat->s_ntarglocaluvhub++;
-                stat->s_ntargremoteuvhub += (hubs - 1);
-        } else
-                stat->s_ntargremoteuvhub += hubs;
-        stat->s_ntarguvhub += hubs;
-        if (hubs >= 16)
-                stat->s_ntarguvhub16++;
-        else if (hubs >= 8)
-                stat->s_ntarguvhub8++;
-        else if (hubs >= 4)
-                stat->s_ntarguvhub4++;
-        else if (hubs >= 2)
-                stat->s_ntarguvhub2++;
-        else
-                stat->s_ntarguvhub1++;
+        record_send_statistics(stat, locals, hubs, remotes, bau_desc);
 
         bau_desc->payload.address = va;
         bau_desc->payload.sending_cpu = cpu;
-
         /*
          * uv_flush_send_and_wait returns 0 if all cpu's were messaged,
          * or 1 if it gave up and the original cpumask should be returned.
@@ -825,26 +999,31 @@ void uv_bau_message_interrupt(struct pt_regs *regs)
 {
         int count = 0;
         cycles_t time_start;
-        struct bau_payload_queue_entry *msg;
+        struct bau_pq_entry *msg;
         struct bau_control *bcp;
         struct ptc_stats *stat;
         struct msg_desc msgdesc;
 
         time_start = get_cycles();
+
         bcp = &per_cpu(bau_control, smp_processor_id());
         stat = bcp->statp;
-        msgdesc.va_queue_first = bcp->va_queue_first;
-        msgdesc.va_queue_last = bcp->va_queue_last;
+
+        msgdesc.queue_first = bcp->queue_first;
+        msgdesc.queue_last = bcp->queue_last;
+
         msg = bcp->bau_msg_head;
-        while (msg->sw_ack_vector) {
+        while (msg->swack_vec) {
                 count++;
-                msgdesc.msg_slot = msg - msgdesc.va_queue_first;
-                msgdesc.sw_ack_slot = ffs(msg->sw_ack_vector) - 1;
+
+                msgdesc.msg_slot = msg - msgdesc.queue_first;
+                msgdesc.swack_slot = ffs(msg->swack_vec) - 1;
                 msgdesc.msg = msg;
-                uv_bau_process_message(&msgdesc, bcp);
+                bau_process_message(&msgdesc, bcp);
+
                 msg++;
-                if (msg > msgdesc.va_queue_last)
-                        msg = msgdesc.va_queue_first;
+                if (msg > msgdesc.queue_last)
+                        msg = msgdesc.queue_first;
                 bcp->bau_msg_head = msg;
         }
         stat->d_time += (get_cycles() - time_start);
@@ -852,18 +1031,17 @@ void uv_bau_message_interrupt(struct pt_regs *regs)
                 stat->d_nomsg++;
         else if (count > 1)
                 stat->d_multmsg++;
+
         ack_APIC_irq();
 }
 
 /*
- * uv_enable_timeouts
- *
- * Each target uvhub (i.e. a uvhub that has no cpu's) needs to have
+ * Each target uvhub (i.e. a uvhub that has cpu's) needs to have
  * shootdown message timeouts enabled.  The timeout does not cause
  * an interrupt, but causes an error message to be returned to
  * the sender.
  */
-static void __init uv_enable_timeouts(void)
+static void __init enable_timeouts(void)
 {
         int uvhub;
         int nuvhubs;
@@ -877,47 +1055,44 @@ static void __init uv_enable_timeouts(void)
                         continue;
 
                 pnode = uv_blade_to_pnode(uvhub);
-                mmr_image =
-                    uv_read_global_mmr64(pnode, UVH_LB_BAU_MISC_CONTROL);
+                mmr_image = read_mmr_misc_control(pnode);
                 /*
                  * Set the timeout period and then lock it in, in three
                  * steps; captures and locks in the period.
                  *
                  * To program the period, the SOFT_ACK_MODE must be off.
                  */
-                mmr_image &= ~((unsigned long)1 <<
-                    UVH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT);
-                uv_write_global_mmr64
-                    (pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image);
+                mmr_image &= ~(1L << SOFTACK_MSHIFT);
+                write_mmr_misc_control(pnode, mmr_image);
                 /*
                  * Set the 4-bit period.
                  */
-                mmr_image &= ~((unsigned long)0xf <<
-                     UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT);
-                mmr_image |= (UV_INTD_SOFT_ACK_TIMEOUT_PERIOD <<
-                     UVH_LB_BAU_MISC_CONTROL_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHFT);
-                uv_write_global_mmr64
-                    (pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image);
+                mmr_image &= ~((unsigned long)0xf << SOFTACK_PSHIFT);
+                mmr_image |= (SOFTACK_TIMEOUT_PERIOD << SOFTACK_PSHIFT);
+                write_mmr_misc_control(pnode, mmr_image);
                 /*
+                 * UV1:
                  * Subsequent reversals of the timebase bit (3) cause an
                  * immediate timeout of one or all INTD resources as
                  * indicated in bits 2:0 (7 causes all of them to timeout).
                  */
-                mmr_image |= ((unsigned long)1 <<
-                    UVH_LB_BAU_MISC_CONTROL_ENABLE_INTD_SOFT_ACK_MODE_SHFT);
-                uv_write_global_mmr64
-                    (pnode, UVH_LB_BAU_MISC_CONTROL, mmr_image);
+                mmr_image |= (1L << SOFTACK_MSHIFT);
+                if (is_uv2_hub()) {
+                        mmr_image |= (1L << UV2_LEG_SHFT);
+                        mmr_image |= (1L << UV2_EXT_SHFT);
+                }
+                write_mmr_misc_control(pnode, mmr_image);
         }
 }
 
-static void *uv_ptc_seq_start(struct seq_file *file, loff_t *offset)
+static void *ptc_seq_start(struct seq_file *file, loff_t *offset)
 {
         if (*offset < num_possible_cpus())
                 return offset;
         return NULL;
 }
 
-static void *uv_ptc_seq_next(struct seq_file *file, void *data, loff_t *offset)
+static void *ptc_seq_next(struct seq_file *file, void *data, loff_t *offset)
 {
         (*offset)++;
         if (*offset < num_possible_cpus())
@@ -925,12 +1100,11 @@ static void *uv_ptc_seq_next(struct seq_file *file, void *data, loff_t *offset)
         return NULL;
 }
 
-static void uv_ptc_seq_stop(struct seq_file *file, void *data)
+static void ptc_seq_stop(struct seq_file *file, void *data)
 {
 }
 
-static inline unsigned long long
-microsec_2_cycles(unsigned long microsec)
+static inline unsigned long long usec_2_cycles(unsigned long microsec)
 {
         unsigned long ns;
         unsigned long long cyc;
@@ -941,29 +1115,27 @@ microsec_2_cycles(unsigned long microsec)
 }
 
 /*
- * Display the statistics thru /proc.
+ * Display the statistics thru /proc/sgi_uv/ptc_statistics
  * 'data' points to the cpu number
+ * Note: see the descriptions in stat_description[].
  */
-static int uv_ptc_seq_show(struct seq_file *file, void *data)
+static int ptc_seq_show(struct seq_file *file, void *data)
 {
         struct ptc_stats *stat;
         int cpu;
 
         cpu = *(loff_t *)data;
-
         if (!cpu) {
                 seq_printf(file,
                         "# cpu sent stime self locals remotes ncpus localhub ");
                 seq_printf(file,
                         "remotehub numuvhubs numuvhubs16 numuvhubs8 ");
                 seq_printf(file,
-                        "numuvhubs4 numuvhubs2 numuvhubs1 dto ");
-                seq_printf(file,
-                        "retries rok resetp resett giveup sto bz throt ");
+                        "numuvhubs4 numuvhubs2 numuvhubs1 dto retries rok ");
                 seq_printf(file,
-                        "sw_ack recv rtime all ");
+                        "resetp resett giveup sto bz throt swack recv rtime ");
                 seq_printf(file,
-                        "one mult none retry canc nocan reset rcan ");
+                        "all one mult none retry canc nocan reset rcan ");
                 seq_printf(file,
                         "disable enable\n");
         }
@@ -990,8 +1162,7 @@ static int uv_ptc_seq_show(struct seq_file *file, void *data)
                 /* destination side statistics */
                 seq_printf(file,
                            "%lx %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld ",
-                           uv_read_global_mmr64(uv_cpu_to_pnode(cpu),
-                                        UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE),
+                           read_gmmr_sw_ack(uv_cpu_to_pnode(cpu)),
                            stat->d_requestee, cycles_2_us(stat->d_time),
                            stat->d_alltlb, stat->d_onetlb, stat->d_multmsg,
                            stat->d_nomsg, stat->d_retries, stat->d_canceled,
@@ -1000,7 +1171,6 @@ static int uv_ptc_seq_show(struct seq_file *file, void *data)
                 seq_printf(file, "%ld %ld\n",
                         stat->s_bau_disabled, stat->s_bau_reenabled);
         }
-
         return 0;
 }
 
@@ -1008,18 +1178,18 @@ static int uv_ptc_seq_show(struct seq_file *file, void *data)
  * Display the tunables thru debugfs
  */
 static ssize_t tunables_read(struct file *file, char __user *userbuf,
-                                                size_t count, loff_t *ppos)
+                                size_t count, loff_t *ppos)
 {
         char *buf;
         int ret;
 
         buf = kasprintf(GFP_KERNEL, "%s %s %s\n%d %d %d %d %d %d %d %d %d\n",
-                "max_bau_concurrent plugged_delay plugsb4reset",
+                "max_concur plugged_delay plugsb4reset",
                 "timeoutsb4reset ipi_reset_limit complete_threshold",
                 "congested_response_us congested_reps congested_period",
-                max_bau_concurrent, plugged_delay, plugsb4reset,
+                max_concurr, plugged_delay, plugsb4reset,
                 timeoutsb4reset, ipi_reset_limit, complete_threshold,
-                congested_response_us, congested_reps, congested_period);
+                congested_respns_us, congested_reps, congested_period);
 
         if (!buf)
                 return -ENOMEM;
@@ -1030,13 +1200,16 @@ static ssize_t tunables_read(struct file *file, char __user *userbuf,
 }
 
 /*
- * -1: resetf the statistics
+ * handle a write to /proc/sgi_uv/ptc_statistics
+ * -1: reset the statistics
  *  0: display meaning of the statistics
  */
-static ssize_t uv_ptc_proc_write(struct file *file, const char __user *user,
-                                 size_t count, loff_t *data)
+static ssize_t ptc_proc_write(struct file *file, const char __user *user,
+                                size_t count, loff_t *data)
 {
         int cpu;
+        int i;
+        int elements;
         long input_arg;
         char optstr[64];
         struct ptc_stats *stat;
@@ -1046,79 +1219,18 @@ static ssize_t uv_ptc_proc_write(struct file *file, const char __user *user,
         if (copy_from_user(optstr, user, count))
                 return -EFAULT;
         optstr[count - 1] = '\0';
+
         if (strict_strtol(optstr, 10, &input_arg) < 0) {
                 printk(KERN_DEBUG "%s is invalid\n", optstr);
                 return -EINVAL;
         }
 
         if (input_arg == 0) {
+                elements = sizeof(stat_description)/sizeof(*stat_description);
                 printk(KERN_DEBUG "# cpu:      cpu number\n");
                 printk(KERN_DEBUG "Sender statistics:\n");
-                printk(KERN_DEBUG
-                "sent:     number of shootdown messages sent\n");
-                printk(KERN_DEBUG
-                "stime:    time spent sending messages\n");
-                printk(KERN_DEBUG
-                "numuvhubs: number of hubs targeted with shootdown\n");
-                printk(KERN_DEBUG
-                "numuvhubs16: number times 16 or more hubs targeted\n");
-                printk(KERN_DEBUG
-                "numuvhubs8: number times 8 or more hubs targeted\n");
-                printk(KERN_DEBUG
-                "numuvhubs4: number times 4 or more hubs targeted\n");
-                printk(KERN_DEBUG
-                "numuvhubs2: number times 2 or more hubs targeted\n");
-                printk(KERN_DEBUG
-                "numuvhubs1: number times 1 hub targeted\n");
-                printk(KERN_DEBUG
-                "numcpus:  number of cpus targeted with shootdown\n");
-                printk(KERN_DEBUG
-                "dto:      number of destination timeouts\n");
-                printk(KERN_DEBUG
-                "retries:  destination timeout retries sent\n");
-                printk(KERN_DEBUG
-                "rok:   :  destination timeouts successfully retried\n");
-                printk(KERN_DEBUG
-                "resetp:   ipi-style resource resets for plugs\n");
-                printk(KERN_DEBUG
-                "resett:   ipi-style resource resets for timeouts\n");
-                printk(KERN_DEBUG
-                "giveup:   fall-backs to ipi-style shootdowns\n");
-                printk(KERN_DEBUG
-                "sto:      number of source timeouts\n");
-                printk(KERN_DEBUG
-                "bz:       number of stay-busy's\n");
-                printk(KERN_DEBUG
-                "throt:    number times spun in throttle\n");
-                printk(KERN_DEBUG "Destination side statistics:\n");
-                printk(KERN_DEBUG
-                "sw_ack:   image of UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE\n");
-                printk(KERN_DEBUG
-                "recv:     shootdown messages received\n");
-                printk(KERN_DEBUG
-                "rtime:    time spent processing messages\n");
-                printk(KERN_DEBUG
-                "all:      shootdown all-tlb messages\n");
-                printk(KERN_DEBUG
-                "one:      shootdown one-tlb messages\n");
-                printk(KERN_DEBUG
-                "mult:     interrupts that found multiple messages\n");
-                printk(KERN_DEBUG
-                "none:     interrupts that found no messages\n");
-                printk(KERN_DEBUG
-                "retry:    number of retry messages processed\n");
-                printk(KERN_DEBUG
-                "canc:     number messages canceled by retries\n");
-                printk(KERN_DEBUG
-                "nocan:    number retries that found nothing to cancel\n");
-                printk(KERN_DEBUG
-                "reset:    number of ipi-style reset requests processed\n");
-                printk(KERN_DEBUG
-                "rcan:     number messages canceled by reset requests\n");
-                printk(KERN_DEBUG
-                "disable:  number times use of the BAU was disabled\n");
-                printk(KERN_DEBUG
-                "enable:   number times use of the BAU was re-enabled\n");
+                for (i = 0; i < elements; i++)
+                        printk(KERN_DEBUG "%s\n", stat_description[i]);
         } else if (input_arg == -1) {
                 for_each_present_cpu(cpu) {
                         stat = &per_cpu(ptcstats, cpu);
@@ -1145,27 +1257,18 @@ static int local_atoi(const char *name)
 }
 
 /*
- * set the tunables
- * 0 values reset them to defaults
+ * Parse the values written to /sys/kernel/debug/sgi_uv/bau_tunables.
+ * Zero values reset them to defaults.
  */
-static ssize_t tunables_write(struct file *file, const char __user *user,
-                                 size_t count, loff_t *data)
+static int parse_tunables_write(struct bau_control *bcp, char *instr,
+                                int count)
 {
-        int cpu;
-        int cnt = 0;
-        int val;
         char *p;
         char *q;
-        char instr[64];
-        struct bau_control *bcp;
-
-        if (count == 0 || count > sizeof(instr)-1)
-                return -EINVAL;
-        if (copy_from_user(instr, user, count))
-                return -EFAULT;
+        int cnt = 0;
+        int val;
+        int e = sizeof(tunables) / sizeof(*tunables);
 
-        instr[count] = '\0';
-        /* count the fields */
         p = instr + strspn(instr, WHITESPACE);
         q = p;
         for (; *p; p = q + strspn(q, WHITESPACE)) {
@@ -1174,8 +1277,8 @@ static ssize_t tunables_write(struct file *file, const char __user *user,
                 if (q == p)
                         break;
         }
-        if (cnt != 9) {
-                printk(KERN_INFO "bau tunable error: should be 9 numbers\n");
+        if (cnt != e) {
+                printk(KERN_INFO "bau tunable error: should be %d values\n", e);
                 return -EINVAL;
         }
 
@@ -1187,97 +1290,80 @@ static ssize_t tunables_write(struct file *file, const char __user *user,
                 switch (cnt) {
                 case 0:
                         if (val == 0) {
-                                max_bau_concurrent = MAX_BAU_CONCURRENT;
-                                max_bau_concurrent_constant =
-                                                        MAX_BAU_CONCURRENT;
+                                max_concurr = MAX_BAU_CONCURRENT;
+                                max_concurr_const = MAX_BAU_CONCURRENT;
                                 continue;
                         }
-                        bcp = &per_cpu(bau_control, smp_processor_id());
                         if (val < 1 || val > bcp->cpus_in_uvhub) {
                                 printk(KERN_DEBUG
                                 "Error: BAU max concurrent %d is invalid\n",
                                 val);
                                 return -EINVAL;
                         }
-                        max_bau_concurrent = val;
-                        max_bau_concurrent_constant = val;
-                        continue;
-                case 1:
-                        if (val == 0)
-                                plugged_delay = PLUGGED_DELAY;
-                        else
-                                plugged_delay = val;
-                        continue;
-                case 2:
-                        if (val == 0)
-                                plugsb4reset = PLUGSB4RESET;
-                        else
-                                plugsb4reset = val;
-                        continue;
-                case 3:
-                        if (val == 0)
-                                timeoutsb4reset = TIMEOUTSB4RESET;
-                        else
-                                timeoutsb4reset = val;
-                        continue;
-                case 4:
-                        if (val == 0)
-                                ipi_reset_limit = IPI_RESET_LIMIT;
-                        else
-                                ipi_reset_limit = val;
-                        continue;
-                case 5:
-                        if (val == 0)
-                                complete_threshold = COMPLETE_THRESHOLD;
-                        else
-                                complete_threshold = val;
-                        continue;
-                case 6:
-                        if (val == 0)
-                                congested_response_us = CONGESTED_RESPONSE_US;
-                        else
-                                congested_response_us = val;
-                        continue;
-                case 7:
-                        if (val == 0)
-                                congested_reps = CONGESTED_REPS;
-                        else
-                                congested_reps = val;
+                        max_concurr = val;
+                        max_concurr_const = val;
                         continue;
-                case 8:
+                default:
                         if (val == 0)
-                                congested_period = CONGESTED_PERIOD;
+                                *tunables[cnt].tunp = tunables[cnt].deflt;
                         else
-                                congested_period = val;
+                                *tunables[cnt].tunp = val;
                         continue;
                 }
                 if (q == p)
                         break;
         }
+        return 0;
+}
+
+/*
+ * Handle a write to debugfs. (/sys/kernel/debug/sgi_uv/bau_tunables)
+ */
+static ssize_t tunables_write(struct file *file, const char __user *user,
+                                size_t count, loff_t *data)
+{
+        int cpu;
+        int ret;
+        char instr[100];
+        struct bau_control *bcp;
+
+        if (count == 0 || count > sizeof(instr)-1)
+                return -EINVAL;
+        if (copy_from_user(instr, user, count))
+                return -EFAULT;
+
+        instr[count] = '\0';
+
+        bcp = &per_cpu(bau_control, smp_processor_id());
+
+        ret = parse_tunables_write(bcp, instr, count);
+        if (ret)
+                return ret;
+
         for_each_present_cpu(cpu) {
                 bcp = &per_cpu(bau_control, cpu);
-                bcp->max_bau_concurrent = max_bau_concurrent;
-                bcp->max_bau_concurrent_constant = max_bau_concurrent;
-                bcp->plugged_delay = plugged_delay;
-                bcp->plugsb4reset = plugsb4reset;
-                bcp->timeoutsb4reset = timeoutsb4reset;
-                bcp->ipi_reset_limit = ipi_reset_limit;
-                bcp->complete_threshold = complete_threshold;
-                bcp->congested_response_us = congested_response_us;
-                bcp->congested_reps = congested_reps;
-                bcp->congested_period = congested_period;
+                bcp->max_concurr =              max_concurr;
+                bcp->max_concurr_const =        max_concurr;
+                bcp->plugged_delay =            plugged_delay;
+                bcp->plugsb4reset =             plugsb4reset;
+                bcp->timeoutsb4reset =          timeoutsb4reset;
+                bcp->ipi_reset_limit =          ipi_reset_limit;
+                bcp->complete_threshold =       complete_threshold;
+                bcp->cong_response_us =         congested_respns_us;
+                bcp->cong_reps =                congested_reps;
+                bcp->cong_period =              congested_period;
         }
         return count;
 }
 
 static const struct seq_operations uv_ptc_seq_ops = {
-        .start          = uv_ptc_seq_start,
-        .next           = uv_ptc_seq_next,
-        .stop           = uv_ptc_seq_stop,
-        .show           = uv_ptc_seq_show
+        .start          = ptc_seq_start,
+        .next           = ptc_seq_next,
+        .stop           = ptc_seq_stop,
+        .show           = ptc_seq_show
 };
 
-static int uv_ptc_proc_open(struct inode *inode, struct file *file)
+static int ptc_proc_open(struct inode *inode, struct file *file)
 {
         return seq_open(file, &uv_ptc_seq_ops);
 }
@@ -1288,9 +1374,9 @@ static int tunables_open(struct inode *inode, struct file *file)
 }
 
 static const struct file_operations proc_uv_ptc_operations = {
-        .open           = uv_ptc_proc_open,
+        .open           = ptc_proc_open,
         .read           = seq_read,
-        .write          = uv_ptc_proc_write,
+        .write          = ptc_proc_write,
         .llseek         = seq_lseek,
         .release        = seq_release,
 };
@@ -1324,7 +1410,7 @@ static int __init uv_ptc_init(void)
                 return -EINVAL;
         }
         tunables_file = debugfs_create_file(UV_BAU_TUNABLES_FILE, 0600,
-                        tunables_dir, NULL, &tunables_fops);
+                                        tunables_dir, NULL, &tunables_fops);
         if (!tunables_file) {
                 printk(KERN_ERR "unable to create debugfs file %s\n",
                        UV_BAU_TUNABLES_FILE);
@@ -1336,24 +1422,24 @@ static int __init uv_ptc_init(void)
 /*
  * Initialize the sending side's sending buffers.
  */
-static void
-uv_activation_descriptor_init(int node, int pnode, int base_pnode)
+static void activation_descriptor_init(int node, int pnode, int base_pnode)
 {
         int i;
         int cpu;
         unsigned long pa;
         unsigned long m;
         unsigned long n;
+        size_t dsize;
         struct bau_desc *bau_desc;
         struct bau_desc *bd2;
         struct bau_control *bcp;
 
         /*
-         * each bau_desc is 64 bytes; there are 8 (UV_ITEMS_PER_DESCRIPTOR)
-         * per cpu; and one per cpu on the uvhub (UV_ADP_SIZE)
+         * each bau_desc is 64 bytes; there are 8 (ITEMS_PER_DESC)
+         * per cpu; and one per cpu on the uvhub (ADP_SZ)
          */
-        bau_desc = kmalloc_node(sizeof(struct bau_desc) * UV_ADP_SIZE
-                                * UV_ITEMS_PER_DESCRIPTOR, GFP_KERNEL, node);
+        dsize = sizeof(struct bau_desc) * ADP_SZ * ITEMS_PER_DESC;
+        bau_desc = kmalloc_node(dsize, GFP_KERNEL, node);
         BUG_ON(!bau_desc);
 
         pa = uv_gpa(bau_desc); /* need the real nasid*/
@@ -1361,27 +1447,25 @@ uv_activation_descriptor_init(int node, int pnode, int base_pnode)
         m = pa & uv_mmask;
 
         /* the 14-bit pnode */
-        uv_write_global_mmr64(pnode, UVH_LB_BAU_SB_DESCRIPTOR_BASE,
-                              (n << UV_DESC_BASE_PNODE_SHIFT | m));
+        write_mmr_descriptor_base(pnode, (n << UV_DESC_PSHIFT | m));
         /*
-         * Initializing all 8 (UV_ITEMS_PER_DESCRIPTOR) descriptors for each
+         * Initializing all 8 (ITEMS_PER_DESC) descriptors for each
          * cpu even though we only use the first one; one descriptor can
          * describe a broadcast to 256 uv hubs.
          */
-        for (i = 0, bd2 = bau_desc; i < (UV_ADP_SIZE*UV_ITEMS_PER_DESCRIPTOR);
-                i++, bd2++) {
+        for (i = 0, bd2 = bau_desc; i < (ADP_SZ * ITEMS_PER_DESC); i++, bd2++) {
                 memset(bd2, 0, sizeof(struct bau_desc));
-                bd2->header.sw_ack_flag = 1;
+                bd2->header.swack_flag =        1;
                 /*
                  * The base_dest_nasid set in the message header is the nasid
                  * of the first uvhub in the partition. The bit map will
                  * indicate destination pnode numbers relative to that base.
                  * They may not be consecutive if nasid striding is being used.
                  */
-                bd2->header.base_dest_nasid = UV_PNODE_TO_NASID(base_pnode);
-                bd2->header.dest_subnodeid = UV_LB_SUBNODEID;
-                bd2->header.command = UV_NET_ENDPOINT_INTD;
-                bd2->header.int_both = 1;
+                bd2->header.base_dest_nasid =   UV_PNODE_TO_NASID(base_pnode);
+                bd2->header.dest_subnodeid =    UV_LB_SUBNODEID;
+                bd2->header.command =           UV_NET_ENDPOINT_INTD;
+                bd2->header.int_both =          1;
                 /*
                  * all others need to be set to zero:
                  *   fairness chaining multilevel count replied_to
@@ -1401,57 +1485,55 @@ uv_activation_descriptor_init(int node, int pnode, int base_pnode)
  * - node is first node (kernel memory notion) on the uvhub
  * - pnode is the uvhub's physical identifier
  */
-static void
-uv_payload_queue_init(int node, int pnode)
+static void pq_init(int node, int pnode)
 {
-        int pn;
         int cpu;
+        size_t plsize;
         char *cp;
-        unsigned long pa;
-        struct bau_payload_queue_entry *pqp;
-        struct bau_payload_queue_entry *pqp_malloc;
+        void *vp;
+        unsigned long pn;
+        unsigned long first;
+        unsigned long pn_first;
+        unsigned long last;
+        struct bau_pq_entry *pqp;
         struct bau_control *bcp;
 
-        pqp = kmalloc_node((DEST_Q_SIZE + 1)
-                           * sizeof(struct bau_payload_queue_entry),
-                           GFP_KERNEL, node);
+        plsize = (DEST_Q_SIZE + 1) * sizeof(struct bau_pq_entry);
+        vp = kmalloc_node(plsize, GFP_KERNEL, node);
+        pqp = (struct bau_pq_entry *)vp;
         BUG_ON(!pqp);
-        pqp_malloc = pqp;
 
         cp = (char *)pqp + 31;
-        pqp = (struct bau_payload_queue_entry *)(((unsigned long)cp >> 5) << 5);
+        pqp = (struct bau_pq_entry *)(((unsigned long)cp >> 5) << 5);
 
         for_each_present_cpu(cpu) {
                 if (pnode != uv_cpu_to_pnode(cpu))
                         continue;
                 /* for every cpu on this pnode: */
                 bcp = &per_cpu(bau_control, cpu);
-                bcp->va_queue_first = pqp;
-                bcp->bau_msg_head = pqp;
-                bcp->va_queue_last = pqp + (DEST_Q_SIZE - 1);
+                bcp->queue_first        = pqp;
+                bcp->bau_msg_head       = pqp;
+                bcp->queue_last         = pqp + (DEST_Q_SIZE - 1);
         }
         /*
          * need the pnode of where the memory was really allocated
          */
-        pa = uv_gpa(pqp);
-        pn = pa >> uv_nshift;
-        uv_write_global_mmr64(pnode,
-                              UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST,
-                              ((unsigned long)pn << UV_PAYLOADQ_PNODE_SHIFT) |
-                              uv_physnodeaddr(pqp));
-        uv_write_global_mmr64(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL,
-                              uv_physnodeaddr(pqp));
-        uv_write_global_mmr64(pnode, UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST,
-                              (unsigned long)
-                              uv_physnodeaddr(pqp + (DEST_Q_SIZE - 1)));
+        pn = uv_gpa(pqp) >> uv_nshift;
+        first = uv_physnodeaddr(pqp);
+        pn_first = ((unsigned long)pn << UV_PAYLOADQ_PNODE_SHIFT) | first;
+        last = uv_physnodeaddr(pqp + (DEST_Q_SIZE - 1));
+        write_mmr_payload_first(pnode, pn_first);
+        write_mmr_payload_tail(pnode, first);
+        write_mmr_payload_last(pnode, last);
+
         /* in effect, all msg_type's are set to MSG_NOOP */
-        memset(pqp, 0, sizeof(struct bau_payload_queue_entry) * DEST_Q_SIZE);
+        memset(pqp, 0, sizeof(struct bau_pq_entry) * DEST_Q_SIZE);
 }
 
 /*
  * Initialization of each UV hub's structures
  */
-static void __init uv_init_uvhub(int uvhub, int vector, int base_pnode)
+static void __init init_uvhub(int uvhub, int vector, int base_pnode)
 {
         int node;
         int pnode;
@@ -1459,24 +1541,24 @@ static void __init uv_init_uvhub(int uvhub, int vector, int base_pnode)
 
         node = uvhub_to_first_node(uvhub);
         pnode = uv_blade_to_pnode(uvhub);
-        uv_activation_descriptor_init(node, pnode, base_pnode);
-        uv_payload_queue_init(node, pnode);
+
+        activation_descriptor_init(node, pnode, base_pnode);
+
+        pq_init(node, pnode);
         /*
          * The below initialization can't be in firmware because the
          * messaging IRQ will be determined by the OS.
          */
         apicid = uvhub_to_first_apicid(uvhub) | uv_apicid_hibits;
-        uv_write_global_mmr64(pnode, UVH_BAU_DATA_CONFIG,
-                                      ((apicid << 32) | vector));
+        write_mmr_data_config(pnode, ((apicid << 32) | vector));
 }
 
 /*
  * We will set BAU_MISC_CONTROL with a timeout period.
  * But the BIOS has set UVH_AGING_PRESCALE_SEL and UVH_TRANSACTION_TIMEOUT.
- * So the destination timeout period has be be calculated from them.
+ * So the destination timeout period has to be calculated from them.
  */
-static int
-calculate_destination_timeout(void)
+static int calculate_destination_timeout(void)
 {
         unsigned long mmr_image;
         int mult1;
@@ -1486,73 +1568,92 @@ calculate_destination_timeout(void)
         int ret;
         unsigned long ts_ns;
 
-        mult1 = UV_INTD_SOFT_ACK_TIMEOUT_PERIOD & BAU_MISC_CONTROL_MULT_MASK;
-        mmr_image = uv_read_local_mmr(UVH_AGING_PRESCALE_SEL);
-        index = (mmr_image >> BAU_URGENCY_7_SHIFT) & BAU_URGENCY_7_MASK;
-        mmr_image = uv_read_local_mmr(UVH_TRANSACTION_TIMEOUT);
-        mult2 = (mmr_image >> BAU_TRANS_SHIFT) & BAU_TRANS_MASK;
-        base = timeout_base_ns[index];
-        ts_ns = base * mult1 * mult2;
-        ret = ts_ns / 1000;
+        if (is_uv1_hub()) {
+                mult1 = SOFTACK_TIMEOUT_PERIOD & BAU_MISC_CONTROL_MULT_MASK;
+                mmr_image = uv_read_local_mmr(UVH_AGING_PRESCALE_SEL);
+                index = (mmr_image >> BAU_URGENCY_7_SHIFT) & BAU_URGENCY_7_MASK;
+                mmr_image = uv_read_local_mmr(UVH_TRANSACTION_TIMEOUT);
+                mult2 = (mmr_image >> BAU_TRANS_SHIFT) & BAU_TRANS_MASK;
+                base = timeout_base_ns[index];
+                ts_ns = base * mult1 * mult2;
+                ret = ts_ns / 1000;
+        } else {
+                /* 4 bits  0/1 for 10/80us, 3 bits of multiplier */
+                mmr_image = uv_read_local_mmr(UVH_AGING_PRESCALE_SEL);
+                mmr_image = (mmr_image & UV_SA_MASK) >> UV_SA_SHFT;
+                if (mmr_image & (1L << UV2_ACK_UNITS_SHFT))
+                        mult1 = 80;
+                else
+                        mult1 = 10;
+                base = mmr_image & UV2_ACK_MASK;
+                ret = mult1 * base;
+        }
         return ret;
 }
 
+static void __init init_per_cpu_tunables(void)
+{
+        int cpu;
+        struct bau_control *bcp;
+
+        for_each_present_cpu(cpu) {
+                bcp = &per_cpu(bau_control, cpu);
+                bcp->baudisabled                = 0;
+                bcp->statp                      = &per_cpu(ptcstats, cpu);
+                /* time interval to catch a hardware stay-busy bug */
+                bcp->timeout_interval           = usec_2_cycles(2*timeout_us);
+                bcp->max_concurr                = max_concurr;
+                bcp->max_concurr_const          = max_concurr;
+                bcp->plugged_delay              = plugged_delay;
+                bcp->plugsb4reset               = plugsb4reset;
+                bcp->timeoutsb4reset            = timeoutsb4reset;
+                bcp->ipi_reset_limit            = ipi_reset_limit;
+                bcp->complete_threshold         = complete_threshold;
+                bcp->cong_response_us           = congested_respns_us;
+                bcp->cong_reps                  = congested_reps;
+                bcp->cong_period                = congested_period;
+        }
+}
+
 /*
- * initialize the bau_control structure for each cpu
+ * Scan all cpus to collect blade and socket summaries.
  */
-static int __init uv_init_per_cpu(int nuvhubs, int base_part_pnode)
+static int __init get_cpu_topology(int base_pnode,
+                                        struct uvhub_desc *uvhub_descs,
+                                        unsigned char *uvhub_mask)
 {
-        int i;
         int cpu;
-        int tcpu;
         int pnode;
         int uvhub;
-        int have_hmaster;
-        short socket = 0;
-        unsigned short socket_mask;
-        unsigned char *uvhub_mask;
+        int socket;
         struct bau_control *bcp;
         struct uvhub_desc *bdp;
         struct socket_desc *sdp;
-        struct bau_control *hmaster = NULL;
-        struct bau_control *smaster = NULL;
-        struct socket_desc {
-                short num_cpus;
-                short cpu_number[MAX_CPUS_PER_SOCKET];
-        };
-        struct uvhub_desc {
-                unsigned short socket_mask;
-                short num_cpus;
-                short uvhub;
-                short pnode;
-                struct socket_desc socket[2];
-        };
-        struct uvhub_desc *uvhub_descs;
-
-        timeout_us = calculate_destination_timeout();
 
-        uvhub_descs = kmalloc(nuvhubs * sizeof(struct uvhub_desc), GFP_KERNEL);
-        memset(uvhub_descs, 0, nuvhubs * sizeof(struct uvhub_desc));
-        uvhub_mask = kzalloc((nuvhubs+7)/8, GFP_KERNEL);
         for_each_present_cpu(cpu) {
                 bcp = &per_cpu(bau_control, cpu);
+
                 memset(bcp, 0, sizeof(struct bau_control));
+
                 pnode = uv_cpu_hub_info(cpu)->pnode;
-                if ((pnode - base_part_pnode) >= UV_DISTRIBUTION_SIZE) {
+                if ((pnode - base_pnode) >= UV_DISTRIBUTION_SIZE) {
                         printk(KERN_EMERG
                                 "cpu %d pnode %d-%d beyond %d; BAU disabled\n",
-                                cpu, pnode, base_part_pnode,
-                                UV_DISTRIBUTION_SIZE);
+                                cpu, pnode, base_pnode, UV_DISTRIBUTION_SIZE);
                         return 1;
                 }
+
                 bcp->osnode = cpu_to_node(cpu);
-                bcp->partition_base_pnode = uv_partition_base_pnode;
+                bcp->partition_base_pnode = base_pnode;
+
                 uvhub = uv_cpu_hub_info(cpu)->numa_blade_id;
                 *(uvhub_mask + (uvhub/8)) |= (1 << (uvhub%8));
                 bdp = &uvhub_descs[uvhub];
+
                 bdp->num_cpus++;
                 bdp->uvhub = uvhub;
                 bdp->pnode = pnode;
+
                 /* kludge: 'assuming' one node per socket, and assuming that
                    disabling a socket just leaves a gap in node numbers */
                 socket = bcp->osnode & 1;
@@ -1561,84 +1662,129 @@ static int __init uv_init_per_cpu(int nuvhubs, int base_part_pnode)
                 sdp->cpu_number[sdp->num_cpus] = cpu;
                 sdp->num_cpus++;
                 if (sdp->num_cpus > MAX_CPUS_PER_SOCKET) {
-                        printk(KERN_EMERG "%d cpus per socket invalid\n", sdp->num_cpus);
+                        printk(KERN_EMERG "%d cpus per socket invalid\n",
+                                sdp->num_cpus);
                         return 1;
                 }
         }
+        return 0;
+}
+
+/*
+ * Each socket is to get a local array of pnodes/hubs.
+ */
+static void make_per_cpu_thp(struct bau_control *smaster)
+{
+        int cpu;
+        size_t hpsz = sizeof(struct hub_and_pnode) * num_possible_cpus();
+
+        smaster->thp = kmalloc_node(hpsz, GFP_KERNEL, smaster->osnode);
+        memset(smaster->thp, 0, hpsz);
+        for_each_present_cpu(cpu) {
+                smaster->thp[cpu].pnode = uv_cpu_hub_info(cpu)->pnode;
+                smaster->thp[cpu].uvhub = uv_cpu_hub_info(cpu)->numa_blade_id;
+        }
+}
+
+/*
+ * Initialize all the per_cpu information for the cpu's on a given socket,
+ * given what has been gathered into the socket_desc struct.
+ * And reports the chosen hub and socket masters back to the caller.
+ */
+static int scan_sock(struct socket_desc *sdp, struct uvhub_desc *bdp,
+                        struct bau_control **smasterp,
+                        struct bau_control **hmasterp)
+{
+        int i;
+        int cpu;
+        struct bau_control *bcp;
+
+        for (i = 0; i < sdp->num_cpus; i++) {
+                cpu = sdp->cpu_number[i];
+                bcp = &per_cpu(bau_control, cpu);
+                bcp->cpu = cpu;
+                if (i == 0) {
+                        *smasterp = bcp;
+                        if (!(*hmasterp))
+                                *hmasterp = bcp;
+                }
+                bcp->cpus_in_uvhub = bdp->num_cpus;
+                bcp->cpus_in_socket = sdp->num_cpus;
+                bcp->socket_master = *smasterp;
+                bcp->uvhub = bdp->uvhub;
+                bcp->uvhub_master = *hmasterp;
+                bcp->uvhub_cpu = uv_cpu_hub_info(cpu)->blade_processor_id;
+                if (bcp->uvhub_cpu >= MAX_CPUS_PER_UVHUB) {
+                        printk(KERN_EMERG "%d cpus per uvhub invalid\n",
+                                bcp->uvhub_cpu);
+                        return 1;
+                }
+        }
+        return 0;
+}
+
+/*
+ * Summarize the blade and socket topology into the per_cpu structures.
+ */
+static int __init summarize_uvhub_sockets(int nuvhubs,
+                        struct uvhub_desc *uvhub_descs,
+                        unsigned char *uvhub_mask)
+{
+        int socket;
+        int uvhub;
+        unsigned short socket_mask;
+
         for (uvhub = 0; uvhub < nuvhubs; uvhub++) {
+                struct uvhub_desc *bdp;
+                struct bau_control *smaster = NULL;
+                struct bau_control *hmaster = NULL;
+
                 if (!(*(uvhub_mask + (uvhub/8)) & (1 << (uvhub%8))))
                         continue;
-                have_hmaster = 0;
+
                 bdp = &uvhub_descs[uvhub];
                 socket_mask = bdp->socket_mask;
                 socket = 0;
                 while (socket_mask) {
-                        if (!(socket_mask & 1))
-                                goto nextsocket;
-                        sdp = &bdp->socket[socket];
-                        for (i = 0; i < sdp->num_cpus; i++) {
-                                cpu = sdp->cpu_number[i];
-                                bcp = &per_cpu(bau_control, cpu);
-                                bcp->cpu = cpu;
-                                if (i == 0) {
-                                        smaster = bcp;
-                                        if (!have_hmaster) {
-                                                have_hmaster++;
-                                                hmaster = bcp;
-                                        }
-                                }
-                                bcp->cpus_in_uvhub = bdp->num_cpus;
-                                bcp->cpus_in_socket = sdp->num_cpus;
-                                bcp->socket_master = smaster;
-                                bcp->uvhub = bdp->uvhub;
-                                bcp->uvhub_master = hmaster;
-                                bcp->uvhub_cpu = uv_cpu_hub_info(cpu)->
-                                                blade_processor_id;
-                                if (bcp->uvhub_cpu >= MAX_CPUS_PER_UVHUB) {
-                                        printk(KERN_EMERG
-                                                "%d cpus per uvhub invalid\n",
-                                                bcp->uvhub_cpu);
+                        struct socket_desc *sdp;
+                        if ((socket_mask & 1)) {
+                                sdp = &bdp->socket[socket];
+                                if (scan_sock(sdp, bdp, &smaster, &hmaster))
                                         return 1;
-                                }
                         }
-nextsocket:
                         socket++;
                         socket_mask = (socket_mask >> 1);
-                        /* each socket gets a local array of pnodes/hubs */
-                        bcp = smaster;
-                        bcp->target_hub_and_pnode = kmalloc_node(
-                                sizeof(struct hub_and_pnode) *
-                                num_possible_cpus(), GFP_KERNEL, bcp->osnode);
-                        memset(bcp->target_hub_and_pnode, 0,
-                                sizeof(struct hub_and_pnode) *
-                                num_possible_cpus());
-                        for_each_present_cpu(tcpu) {
-                                bcp->target_hub_and_pnode[tcpu].pnode =
-                                        uv_cpu_hub_info(tcpu)->pnode;
-                                bcp->target_hub_and_pnode[tcpu].uvhub =
-                                        uv_cpu_hub_info(tcpu)->numa_blade_id;
-                        }
+                        make_per_cpu_thp(smaster);
                 }
         }
+        return 0;
+}
+
+/*
+ * initialize the bau_control structure for each cpu
+ */
+static int __init init_per_cpu(int nuvhubs, int base_part_pnode)
+{
+        unsigned char *uvhub_mask;
+        void *vp;
+        struct uvhub_desc *uvhub_descs;
+
+        timeout_us = calculate_destination_timeout();
+
+        vp = kmalloc(nuvhubs * sizeof(struct uvhub_desc), GFP_KERNEL);
+        uvhub_descs = (struct uvhub_desc *)vp;
+        memset(uvhub_descs, 0, nuvhubs * sizeof(struct uvhub_desc));
+        uvhub_mask = kzalloc((nuvhubs+7)/8, GFP_KERNEL);
+
+        if (get_cpu_topology(base_part_pnode, uvhub_descs, uvhub_mask))
+                return 1;
+
+        if (summarize_uvhub_sockets(nuvhubs, uvhub_descs, uvhub_mask))
+                return 1;
+
         kfree(uvhub_descs);
         kfree(uvhub_mask);
-        for_each_present_cpu(cpu) {
-                bcp = &per_cpu(bau_control, cpu);
-                bcp->baudisabled = 0;
-                bcp->statp = &per_cpu(ptcstats, cpu);
-                /* time interval to catch a hardware stay-busy bug */
-                bcp->timeout_interval = microsec_2_cycles(2*timeout_us);
-                bcp->max_bau_concurrent = max_bau_concurrent;
-                bcp->max_bau_concurrent_constant = max_bau_concurrent;
-                bcp->plugged_delay = plugged_delay;
-                bcp->plugsb4reset = plugsb4reset;
-                bcp->timeoutsb4reset = timeoutsb4reset;
-                bcp->ipi_reset_limit = ipi_reset_limit;
-                bcp->complete_threshold = complete_threshold;
-                bcp->congested_response_us = congested_response_us;
-                bcp->congested_reps = congested_reps;
-                bcp->congested_period = congested_period;
-        }
+        init_per_cpu_tunables();
         return 0;
 }
 
@@ -1651,8 +1797,9 @@ static int __init uv_bau_init(void)
         int pnode;
         int nuvhubs;
         int cur_cpu;
+        int cpus;
         int vector;
-        unsigned long mmr;
+        cpumask_var_t *mask;
 
         if (!is_uv_system())
                 return 0;
@@ -1660,24 +1807,25 @@ static int __init uv_bau_init(void)
         if (nobau)
                 return 0;
 
-        for_each_possible_cpu(cur_cpu)
-                zalloc_cpumask_var_node(&per_cpu(uv_flush_tlb_mask, cur_cpu),
-                                       GFP_KERNEL, cpu_to_node(cur_cpu));
+        for_each_possible_cpu(cur_cpu) {
+                mask = &per_cpu(uv_flush_tlb_mask, cur_cpu);
+                zalloc_cpumask_var_node(mask, GFP_KERNEL, cpu_to_node(cur_cpu));
+        }
 
         uv_nshift = uv_hub_info->m_val;
         uv_mmask = (1UL << uv_hub_info->m_val) - 1;
         nuvhubs = uv_num_possible_blades();
         spin_lock_init(&disable_lock);
-        congested_cycles = microsec_2_cycles(congested_response_us);
+        congested_cycles = usec_2_cycles(congested_respns_us);
 
-        uv_partition_base_pnode = 0x7fffffff;
+        uv_base_pnode = 0x7fffffff;
         for (uvhub = 0; uvhub < nuvhubs; uvhub++) {
-                if (uv_blade_nr_possible_cpus(uvhub) &&
-                        (uv_blade_to_pnode(uvhub) < uv_partition_base_pnode))
-                        uv_partition_base_pnode = uv_blade_to_pnode(uvhub);
+                cpus = uv_blade_nr_possible_cpus(uvhub);
+                if (cpus && (uv_blade_to_pnode(uvhub) < uv_base_pnode))
+                        uv_base_pnode = uv_blade_to_pnode(uvhub);
         }
 
-        if (uv_init_per_cpu(nuvhubs, uv_partition_base_pnode)) {
+        if (init_per_cpu(nuvhubs, uv_base_pnode)) {
                 nobau = 1;
                 return 0;
         }
@@ -1685,21 +1833,21 @@ static int __init uv_bau_init(void)
         vector = UV_BAU_MESSAGE;
         for_each_possible_blade(uvhub)
                 if (uv_blade_nr_possible_cpus(uvhub))
-                        uv_init_uvhub(uvhub, vector, uv_partition_base_pnode);
+                        init_uvhub(uvhub, vector, uv_base_pnode);
 
-        uv_enable_timeouts();
+        enable_timeouts();
         alloc_intr_gate(vector, uv_bau_message_intr1);
 
         for_each_possible_blade(uvhub) {
                 if (uv_blade_nr_possible_cpus(uvhub)) {
+                        unsigned long val;
+                        unsigned long mmr;
                         pnode = uv_blade_to_pnode(uvhub);
                         /* INIT the bau */
-                        uv_write_global_mmr64(pnode,
-                                        UVH_LB_BAU_SB_ACTIVATION_CONTROL,
-                                        ((unsigned long)1 << 63));
+                        val = 1L << 63;
+                        write_gmmr_activation(pnode, val);
                         mmr = 1; /* should be 1 to broadcast to both sockets */
-                        uv_write_global_mmr64(pnode, UVH_BAU_DATA_BROADCAST,
-                                                mmr);
+                        write_mmr_data_broadcast(pnode, mmr);
                 }
         }
 
diff --git a/arch/x86/platform/uv/uv_time.c b/arch/x86/platform/uv/uv_time.c
index 0eb90184515f..9f29a01ee1b3 100644
--- a/arch/x86/platform/uv/uv_time.c
+++ b/arch/x86/platform/uv/uv_time.c
@@ -99,8 +99,12 @@ static void uv_rtc_send_IPI(int cpu)
 /* Check for an RTC interrupt pending */
 static int uv_intr_pending(int pnode)
 {
-        return uv_read_global_mmr64(pnode, UVH_EVENT_OCCURRED0) &
-                UVH_EVENT_OCCURRED0_RTC1_MASK;
+        if (is_uv1_hub())
+                return uv_read_global_mmr64(pnode, UVH_EVENT_OCCURRED0) &
+                        UV1H_EVENT_OCCURRED0_RTC1_MASK;
+        else
+                return uv_read_global_mmr64(pnode, UV2H_EVENT_OCCURRED2) &
+                        UV2H_EVENT_OCCURRED2_RTC_1_MASK;
 }
 
 /* Setup interrupt and return non-zero if early expiration occurred. */
@@ -114,8 +118,12 @@ static int uv_setup_intr(int cpu, u64 expires)
                 UVH_RTC1_INT_CONFIG_M_MASK);
         uv_write_global_mmr64(pnode, UVH_INT_CMPB, -1L);
 
-        uv_write_global_mmr64(pnode, UVH_EVENT_OCCURRED0_ALIAS,
-                UVH_EVENT_OCCURRED0_RTC1_MASK);
+        if (is_uv1_hub())
+                uv_write_global_mmr64(pnode, UVH_EVENT_OCCURRED0_ALIAS,
+                                UV1H_EVENT_OCCURRED0_RTC1_MASK);
+        else
+                uv_write_global_mmr64(pnode, UV2H_EVENT_OCCURRED2_ALIAS,
+                                UV2H_EVENT_OCCURRED2_RTC_1_MASK);
 
         val = (X86_PLATFORM_IPI_VECTOR << UVH_RTC1_INT_CONFIG_VECTOR_SHFT) |
                 ((u64)apicid << UVH_RTC1_INT_CONFIG_APIC_ID_SHFT);
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index c898049dafd5..342eae9b0d3c 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -21,7 +21,7 @@ static void cfq_dtor(struct io_context *ioc)
         if (!hlist_empty(&ioc->cic_list)) {
                 struct cfq_io_context *cic;
 
-                cic = list_entry(ioc->cic_list.first, struct cfq_io_context,
+                cic = hlist_entry(ioc->cic_list.first, struct cfq_io_context,
                                                                 cic_list);
                 cic->dtor(ioc);
         }
@@ -57,7 +57,7 @@ static void cfq_exit(struct io_context *ioc)
         if (!hlist_empty(&ioc->cic_list)) {
                 struct cfq_io_context *cic;
 
-                cic = list_entry(ioc->cic_list.first, struct cfq_io_context,
+                cic = hlist_entry(ioc->cic_list.first, struct cfq_io_context,
                                                                 cic_list);
                 cic->exit(ioc);
         }
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 7c52d6888924..3c7b537bf908 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -185,7 +185,7 @@ struct cfq_group {
         int nr_cfqq;
 
         /*
-         * Per group busy queus average. Useful for workload slice calc. We
+         * Per group busy queues average. Useful for workload slice calc. We
          * create the array for each prio class but at run time it is used
          * only for RT and BE class and slot for IDLE class remains unused.
          * This is primarily done to avoid confusion and a gcc warning.
@@ -369,16 +369,16 @@ CFQ_CFQQ_FNS(wait_busy);
 #define cfq_log_cfqq(cfqd, cfqq, fmt, args...)  \
         blk_add_trace_msg((cfqd)->queue, "cfq%d%c %s " fmt, (cfqq)->pid, \
                         cfq_cfqq_sync((cfqq)) ? 'S' : 'A', \
-                        blkg_path(&(cfqq)->cfqg->blkg), ##args);
+                        blkg_path(&(cfqq)->cfqg->blkg), ##args)
 
 #define cfq_log_cfqg(cfqd, cfqg, fmt, args...)                          \
         blk_add_trace_msg((cfqd)->queue, "%s " fmt,                     \
-                                blkg_path(&(cfqg)->blkg), ##args);      \
+                                blkg_path(&(cfqg)->blkg), ##args)       \
 
 #else
 #define cfq_log_cfqq(cfqd, cfqq, fmt, args...)  \
         blk_add_trace_msg((cfqd)->queue, "cfq%d " fmt, (cfqq)->pid, ##args)
-#define cfq_log_cfqg(cfqd, cfqg, fmt, args...)          do {} while (0);
+#define cfq_log_cfqg(cfqd, cfqg, fmt, args...)          do {} while (0)
 #endif
 #define cfq_log(cfqd, fmt, args...)     \
         blk_add_trace_msg((cfqd)->queue, "cfq " fmt, ##args)
@@ -3786,9 +3786,6 @@ new_queue:
         return 0;
 
 queue_fail:
-        if (cic)
-                put_io_context(cic->ioc);
-
         cfq_schedule_dispatch(cfqd);
         spin_unlock_irqrestore(q->queue_lock, flags);
         cfq_log(cfqd, "set_request fail");
diff --git a/drivers/Makefile b/drivers/Makefile
index 6b17f5864340..09f3232bcdcd 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -17,6 +17,9 @@ obj-$(CONFIG_SFI)		+= sfi/
 # was used and do nothing if so
 obj-$(CONFIG_PNP)               += pnp/
 obj-$(CONFIG_ARM_AMBA)          += amba/
+# Many drivers will want to use DMA so this has to be made available
+# really early.
+obj-$(CONFIG_DMA_ENGINE)        += dma/
 
 obj-$(CONFIG_VIRTIO)            += virtio/
 obj-$(CONFIG_XEN)               += xen/
@@ -92,7 +95,6 @@ obj-$(CONFIG_EISA)		+= eisa/
 obj-y                           += lguest/
 obj-$(CONFIG_CPU_FREQ)          += cpufreq/
 obj-$(CONFIG_CPU_IDLE)          += cpuidle/
-obj-$(CONFIG_DMA_ENGINE)        += dma/
 obj-$(CONFIG_MMC)               += mmc/
 obj-$(CONFIG_MEMSTICK)          += memstick/
 obj-y                           += leds/
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index bc2218db5ba9..de0e3df76776 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -369,6 +369,21 @@ config ACPI_HED
           which is used to report some hardware errors notified via
           SCI, mainly the corrected errors.
 
+config ACPI_CUSTOM_METHOD
+        tristate "Allow ACPI methods to be inserted/replaced at run time"
+        depends on DEBUG_FS
+        default n
+        help
+          This debug facility allows ACPI AML methods to me inserted and/or
+          replaced without rebooting the system. For details refer to:
+          Documentation/acpi/method-customizing.txt.
+
+          NOTE: This option is security sensitive, because it allows arbitrary
+          kernel memory to be written to by root (uid=0) users, allowing them
+          to bypass certain security measures (e.g. if root is not allowed to
+          load additional kernel modules after boot, this feature may be used
+          to override that restriction).
+
 source "drivers/acpi/apei/Kconfig"
 
 endif   # ACPI
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index b66fbb2fc85f..ecb26b4f29a0 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -61,6 +61,7 @@ obj-$(CONFIG_ACPI_SBS)		+= sbshc.o
 obj-$(CONFIG_ACPI_SBS)          += sbs.o
 obj-$(CONFIG_ACPI_HED)          += hed.o
 obj-$(CONFIG_ACPI_EC_DEBUGFS)   += ec_sys.o
+obj-$(CONFIG_ACPI_CUSTOM_METHOD)+= custom_method.o
 
 # processor has its own "processor." module_param namespace
 processor-y                     := processor_driver.o processor_throttling.o
diff --git a/drivers/acpi/acpica/Makefile b/drivers/acpi/acpica/Makefile
index a1224712fd0c..301bd2d388ad 100644
--- a/drivers/acpi/acpica/Makefile
+++ b/drivers/acpi/acpica/Makefile
@@ -14,7 +14,7 @@ acpi-y := dsfield.o   dsmthdat.o  dsopcode.o  dswexec.o  dswscope.o \
 
 acpi-y += evevent.o  evregion.o  evsci.o    evxfevnt.o \
          evmisc.o   evrgnini.o  evxface.o  evxfregn.o \
-         evgpe.o    evgpeblk.o evgpeinit.o  evgpeutil.o evxfgpe.o
+         evgpe.o    evgpeblk.o evgpeinit.o  evgpeutil.o evxfgpe.o evglock.o
 
 acpi-y += exconfig.o  exfield.o  exnames.o   exoparg6.o  exresolv.o  exstorob.o\
          exconvrt.o  exfldio.o  exoparg1.o  exprep.o    exresop.o   exsystem.o\
diff --git a/drivers/acpi/acpica/acconfig.h b/drivers/acpi/acpica/acconfig.h
index ab87396c2c07..bc533dde16c4 100644
--- a/drivers/acpi/acpica/acconfig.h
+++ b/drivers/acpi/acpica/acconfig.h
@@ -187,7 +187,6 @@
 
 /* Operation regions */
 
-#define ACPI_NUM_PREDEFINED_REGIONS     9
 #define ACPI_USER_REGION_BEGIN          0x80
 
 /* Maximum space_ids for Operation Regions */
diff --git a/drivers/acpi/acpica/acevents.h b/drivers/acpi/acpica/acevents.h
index 41d247daf461..bea3b4899183 100644
--- a/drivers/acpi/acpica/acevents.h
+++ b/drivers/acpi/acpica/acevents.h
@@ -58,12 +58,6 @@ u32 acpi_ev_fixed_event_detect(void);
  */
 u8 acpi_ev_is_notify_object(struct acpi_namespace_node *node);
 
-acpi_status acpi_ev_acquire_global_lock(u16 timeout);
-
-acpi_status acpi_ev_release_global_lock(void);
-
-acpi_status acpi_ev_init_global_lock_handler(void);
-
 u32 acpi_ev_get_gpe_number_index(u32 gpe_number);
 
 acpi_status
@@ -71,6 +65,17 @@ acpi_ev_queue_notify_request(struct acpi_namespace_node *node,
                              u32 notify_value);
 
 /*
+ * evglock - Global Lock support
+ */
+acpi_status acpi_ev_init_global_lock_handler(void);
+
+acpi_status acpi_ev_acquire_global_lock(u16 timeout);
+
+acpi_status acpi_ev_release_global_lock(void);
+
+acpi_status acpi_ev_remove_global_lock_handler(void);
+
+/*
  * evgpe - Low-level GPE support
  */
 u32 acpi_ev_gpe_detect(struct acpi_gpe_xrupt_info *gpe_xrupt_list);
diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h
index d69750b83b36..73863d86f022 100644
--- a/drivers/acpi/acpica/acglobal.h
+++ b/drivers/acpi/acpica/acglobal.h
@@ -214,24 +214,23 @@ ACPI_EXTERN struct acpi_mutex_info acpi_gbl_mutex_info[ACPI_NUM_MUTEX];
 
 /*
  * Global lock mutex is an actual AML mutex object
- * Global lock semaphore works in conjunction with the HW global lock
+ * Global lock semaphore works in conjunction with the actual global lock
+ * Global lock spinlock is used for "pending" handshake
  */
 ACPI_EXTERN union acpi_operand_object *acpi_gbl_global_lock_mutex;
 ACPI_EXTERN acpi_semaphore acpi_gbl_global_lock_semaphore;
+ACPI_EXTERN acpi_spinlock acpi_gbl_global_lock_pending_lock;
 ACPI_EXTERN u16 acpi_gbl_global_lock_handle;
 ACPI_EXTERN u8 acpi_gbl_global_lock_acquired;
 ACPI_EXTERN u8 acpi_gbl_global_lock_present;
+ACPI_EXTERN u8 acpi_gbl_global_lock_pending;
 
 /*
  * Spinlocks are used for interfaces that can be possibly called at
  * interrupt level
  */
-ACPI_EXTERN spinlock_t _acpi_gbl_gpe_lock;      /* For GPE data structs and registers */
-ACPI_EXTERN spinlock_t _acpi_gbl_hardware_lock; /* For ACPI H/W except GPE registers */
-ACPI_EXTERN spinlock_t _acpi_ev_global_lock_pending_lock; /* For global lock */
-#define acpi_gbl_gpe_lock       &_acpi_gbl_gpe_lock
-#define acpi_gbl_hardware_lock  &_acpi_gbl_hardware_lock
-#define acpi_ev_global_lock_pending_lock &_acpi_ev_global_lock_pending_lock
+ACPI_EXTERN acpi_spinlock acpi_gbl_gpe_lock;    /* For GPE data structs and registers */
+ACPI_EXTERN acpi_spinlock acpi_gbl_hardware_lock;       /* For ACPI H/W except GPE registers */
 
 /*****************************************************************************
  *
diff --git a/drivers/acpi/acpica/amlcode.h b/drivers/acpi/acpica/amlcode.h
index f4f0998d3967..1077f17859ed 100644
--- a/drivers/acpi/acpica/amlcode.h
+++ b/drivers/acpi/acpica/amlcode.h
@@ -394,21 +394,6 @@
 #define AML_CLASS_METHOD_CALL       0x09
 #define AML_CLASS_UNKNOWN           0x0A
 
-/* Predefined Operation Region space_iDs */
-
-typedef enum {
-        REGION_MEMORY = 0,
-        REGION_IO,
-        REGION_PCI_CONFIG,
-        REGION_EC,
-        REGION_SMBUS,
-        REGION_CMOS,
-        REGION_PCI_BAR,
-        REGION_IPMI,
-        REGION_DATA_TABLE,      /* Internal use only */
-        REGION_FIXED_HW = 0x7F
-} AML_REGION_TYPES;
-
 /* Comparison operation codes for match_op operator */
 
 typedef enum {
diff --git a/drivers/acpi/acpica/dswload.c b/drivers/acpi/acpica/dswload.c
index 23a3b1ab20c1..324acec1179a 100644
--- a/drivers/acpi/acpica/dswload.c
+++ b/drivers/acpi/acpica/dswload.c
@@ -450,7 +450,7 @@ acpi_status acpi_ds_load1_end_op(struct acpi_walk_state *walk_state)
                         status =
                             acpi_ex_create_region(op->named.data,
                                                   op->named.length,
-                                                  REGION_DATA_TABLE,
+                                                  ACPI_ADR_SPACE_DATA_TABLE,
                                                   walk_state);
                         if (ACPI_FAILURE(status)) {
                                 return_ACPI_STATUS(status);
diff --git a/drivers/acpi/acpica/dswload2.c b/drivers/acpi/acpica/dswload2.c
index 4be4e921dfe1..976318138c56 100644
--- a/drivers/acpi/acpica/dswload2.c
+++ b/drivers/acpi/acpica/dswload2.c
@@ -562,7 +562,7 @@ acpi_status acpi_ds_load2_end_op(struct acpi_walk_state *walk_state)
                                     ((op->common.value.arg)->common.value.
                                      integer);
                         } else {
-                                region_space = REGION_DATA_TABLE;
+                                region_space = ACPI_ADR_SPACE_DATA_TABLE;
                         }
 
                         /*
diff --git a/drivers/acpi/acpica/evglock.c b/drivers/acpi/acpica/evglock.c
new file mode 100644
index 000000000000..56a562a1e5d7
--- /dev/null
+++ b/drivers/acpi/acpica/evglock.c
@@ -0,0 +1,335 @@
+/******************************************************************************
+ *
+ * Module Name: evglock - Global Lock support
+ *
+ *****************************************************************************/
+
+/*
+ * Copyright (C) 2000 - 2011, Intel Corp.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions, and the following disclaimer,
+ *    without modification.
+ * 2. Redistributions in binary form must reproduce at minimum a disclaimer
+ *    substantially similar to the "NO WARRANTY" disclaimer below
+ *    ("Disclaimer") and any redistribution must be conditioned upon
+ *    including a substantially similar Disclaimer requirement for further
+ *    binary redistribution.
+ * 3. Neither the names of the above-listed copyright holders nor the names
+ *    of any contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * NO WARRANTY
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTIBILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * HOLDERS OR CONTRIBUTORS BE LIABLE FOR SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
+ * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING
+ * IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGES.
+ */
+
+#include <acpi/acpi.h>
+#include "accommon.h"
+#include "acevents.h"
+#include "acinterp.h"
+
+#define _COMPONENT          ACPI_EVENTS
+ACPI_MODULE_NAME("evglock")
+
+/* Local prototypes */
+static u32 acpi_ev_global_lock_handler(void *context);
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ev_init_global_lock_handler
+ *
+ * PARAMETERS:  None
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Install a handler for the global lock release event
+ *
+ ******************************************************************************/
+
+acpi_status acpi_ev_init_global_lock_handler(void)
+{
+        acpi_status status;
+
+        ACPI_FUNCTION_TRACE(ev_init_global_lock_handler);
+
+        /* Attempt installation of the global lock handler */
+
+        status = acpi_install_fixed_event_handler(ACPI_EVENT_GLOBAL,
+                                                  acpi_ev_global_lock_handler,
+                                                  NULL);
+
+        /*
+         * If the global lock does not exist on this platform, the attempt to
+         * enable GBL_STATUS will fail (the GBL_ENABLE bit will not stick).
+         * Map to AE_OK, but mark global lock as not present. Any attempt to
+         * actually use the global lock will be flagged with an error.
+         */
+        acpi_gbl_global_lock_present = FALSE;
+        if (status == AE_NO_HARDWARE_RESPONSE) {
+                ACPI_ERROR((AE_INFO,
+                            "No response from Global Lock hardware, disabling lock"));
+
+                return_ACPI_STATUS(AE_OK);
+        }
+
+        status = acpi_os_create_lock(&acpi_gbl_global_lock_pending_lock);
+        if (ACPI_FAILURE(status)) {
+                return_ACPI_STATUS(status);
+        }
+
+        acpi_gbl_global_lock_pending = FALSE;
+        acpi_gbl_global_lock_present = TRUE;
+        return_ACPI_STATUS(status);
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ev_remove_global_lock_handler
+ *
+ * PARAMETERS:  None
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Remove the handler for the Global Lock
+ *
+ ******************************************************************************/
+
+acpi_status acpi_ev_remove_global_lock_handler(void)
+{
+        acpi_status status;
+
+        ACPI_FUNCTION_TRACE(ev_remove_global_lock_handler);
+
+        acpi_gbl_global_lock_present = FALSE;
+        status = acpi_remove_fixed_event_handler(ACPI_EVENT_GLOBAL,
+                                                 acpi_ev_global_lock_handler);
+
+        return_ACPI_STATUS(status);
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ev_global_lock_handler
+ *
+ * PARAMETERS:  Context         - From thread interface, not used
+ *
+ * RETURN:      ACPI_INTERRUPT_HANDLED
+ *
+ * DESCRIPTION: Invoked directly from the SCI handler when a global lock
+ *              release interrupt occurs. If there is actually a pending
+ *              request for the lock, signal the waiting thread.
+ *
+ ******************************************************************************/
+
+static u32 acpi_ev_global_lock_handler(void *context)
+{
+        acpi_status status;
+        acpi_cpu_flags flags;
+
+        flags = acpi_os_acquire_lock(acpi_gbl_global_lock_pending_lock);
+
+        /*
+         * If a request for the global lock is not actually pending,
+         * we are done. This handles "spurious" global lock interrupts
+         * which are possible (and have been seen) with bad BIOSs.
+         */
+        if (!acpi_gbl_global_lock_pending) {
+                goto cleanup_and_exit;
+        }
+
+        /*
+         * Send a unit to the global lock semaphore. The actual acquisition
+         * of the global lock will be performed by the waiting thread.
+         */
+        status = acpi_os_signal_semaphore(acpi_gbl_global_lock_semaphore, 1);
+        if (ACPI_FAILURE(status)) {
+                ACPI_ERROR((AE_INFO, "Could not signal Global Lock semaphore"));
+        }
+
+        acpi_gbl_global_lock_pending = FALSE;
+
+      cleanup_and_exit:
+
+        acpi_os_release_lock(acpi_gbl_global_lock_pending_lock, flags);
+        return (ACPI_INTERRUPT_HANDLED);
+}
+
+/******************************************************************************
+ *
+ * FUNCTION:    acpi_ev_acquire_global_lock
+ *
+ * PARAMETERS:  Timeout         - Max time to wait for the lock, in millisec.
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Attempt to gain ownership of the Global Lock.
+ *
+ * MUTEX:       Interpreter must be locked
+ *
+ * Note: The original implementation allowed multiple threads to "acquire" the
+ * Global Lock, and the OS would hold the lock until the last thread had
+ * released it. However, this could potentially starve the BIOS out of the
+ * lock, especially in the case where there is a tight handshake between the
+ * Embedded Controller driver and the BIOS. Therefore, this implementation
+ * allows only one thread to acquire the HW Global Lock at a time, and makes
+ * the global lock appear as a standard mutex on the OS side.
+ *
+ *****************************************************************************/
+
+acpi_status acpi_ev_acquire_global_lock(u16 timeout)
+{
+        acpi_cpu_flags flags;
+        acpi_status status;
+        u8 acquired = FALSE;
+
+        ACPI_FUNCTION_TRACE(ev_acquire_global_lock);
+
+        /*
+         * Only one thread can acquire the GL at a time, the global_lock_mutex
+         * enforces this. This interface releases the interpreter if we must wait.
+         */
+        status =
+            acpi_ex_system_wait_mutex(acpi_gbl_global_lock_mutex->mutex.
+                                      os_mutex, timeout);
+        if (ACPI_FAILURE(status)) {
+                return_ACPI_STATUS(status);
+        }
+
+        /*
+         * Update the global lock handle and check for wraparound. The handle is
+         * only used for the external global lock interfaces, but it is updated
+         * here to properly handle the case where a single thread may acquire the
+         * lock via both the AML and the acpi_acquire_global_lock interfaces. The
+         * handle is therefore updated on the first acquire from a given thread
+         * regardless of where the acquisition request originated.
+         */
+        acpi_gbl_global_lock_handle++;
+        if (acpi_gbl_global_lock_handle == 0) {
+                acpi_gbl_global_lock_handle = 1;
+        }
+
+        /*
+         * Make sure that a global lock actually exists. If not, just
+         * treat the lock as a standard mutex.
+         */
+        if (!acpi_gbl_global_lock_present) {
+                acpi_gbl_global_lock_acquired = TRUE;
+                return_ACPI_STATUS(AE_OK);
+        }
+
+        flags = acpi_os_acquire_lock(acpi_gbl_global_lock_pending_lock);
+
+        do {
+
+                /* Attempt to acquire the actual hardware lock */
+
+                ACPI_ACQUIRE_GLOBAL_LOCK(acpi_gbl_FACS, acquired);
+                if (acquired) {
+                        acpi_gbl_global_lock_acquired = TRUE;
+                        ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
+                                          "Acquired hardware Global Lock\n"));
+                        break;
+                }
+
+                /*
+                 * Did not get the lock. The pending bit was set above, and
+                 * we must now wait until we receive the global lock
+                 * released interrupt.
+                 */
+                acpi_gbl_global_lock_pending = TRUE;
+                acpi_os_release_lock(acpi_gbl_global_lock_pending_lock, flags);
+
+                ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
+                                  "Waiting for hardware Global Lock\n"));
+
+                /*
+                 * Wait for handshake with the global lock interrupt handler.
+                 * This interface releases the interpreter if we must wait.
+                 */
+                status =
+                    acpi_ex_system_wait_semaphore
+                    (acpi_gbl_global_lock_semaphore, ACPI_WAIT_FOREVER);
+
+                flags = acpi_os_acquire_lock(acpi_gbl_global_lock_pending_lock);
+
+        } while (ACPI_SUCCESS(status));
+
+        acpi_gbl_global_lock_pending = FALSE;
+        acpi_os_release_lock(acpi_gbl_global_lock_pending_lock, flags);
+
+        return_ACPI_STATUS(status);
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ev_release_global_lock
+ *
+ * PARAMETERS:  None
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Releases ownership of the Global Lock.
+ *
+ ******************************************************************************/
+
+acpi_status acpi_ev_release_global_lock(void)
+{
+        u8 pending = FALSE;
+        acpi_status status = AE_OK;
+
+        ACPI_FUNCTION_TRACE(ev_release_global_lock);
+
+        /* Lock must be already acquired */
+
+        if (!acpi_gbl_global_lock_acquired) {
+                ACPI_WARNING((AE_INFO,
+                              "Cannot release the ACPI Global Lock, it has not been acquired"));
+                return_ACPI_STATUS(AE_NOT_ACQUIRED);
+        }
+
+        if (acpi_gbl_global_lock_present) {
+
+                /* Allow any thread to release the lock */
+
+                ACPI_RELEASE_GLOBAL_LOCK(acpi_gbl_FACS, pending);
+
+                /*
+                 * If the pending bit was set, we must write GBL_RLS to the control
+                 * register
+                 */
+                if (pending) {
+                        status =
+                            acpi_write_bit_register
+                            (ACPI_BITREG_GLOBAL_LOCK_RELEASE,
+                             ACPI_ENABLE_EVENT);
+                }
+
+                ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
+                                  "Released hardware Global Lock\n"));
+        }
+
+        acpi_gbl_global_lock_acquired = FALSE;
+
+        /* Release the local GL mutex */
+
+        acpi_os_release_mutex(acpi_gbl_global_lock_mutex->mutex.os_mutex);
+        return_ACPI_STATUS(status);
+}
diff --git a/drivers/acpi/acpica/evmisc.c b/drivers/acpi/acpica/evmisc.c
index 7dc80946f7bd..d0b331844427 100644
--- a/drivers/acpi/acpica/evmisc.c
+++ b/drivers/acpi/acpica/evmisc.c
@@ -45,7 +45,6 @@
 #include "accommon.h"
 #include "acevents.h"
 #include "acnamesp.h"
-#include "acinterp.h"
 
 #define _COMPONENT          ACPI_EVENTS
 ACPI_MODULE_NAME("evmisc")
@@ -53,10 +52,6 @@ ACPI_MODULE_NAME("evmisc")
 /* Local prototypes */
 static void ACPI_SYSTEM_XFACE acpi_ev_notify_dispatch(void *context);
 
-static u32 acpi_ev_global_lock_handler(void *context);
-
-static acpi_status acpi_ev_remove_global_lock_handler(void);
-
 /*******************************************************************************
  *
  * FUNCTION:    acpi_ev_is_notify_object
@@ -275,304 +270,6 @@ static void ACPI_SYSTEM_XFACE acpi_ev_notify_dispatch(void *context)
         acpi_ut_delete_generic_state(notify_info);
 }
 
-/*******************************************************************************
- *
- * FUNCTION:    acpi_ev_global_lock_handler
- *
- * PARAMETERS:  Context         - From thread interface, not used
- *
- * RETURN:      ACPI_INTERRUPT_HANDLED
- *
- * DESCRIPTION: Invoked directly from the SCI handler when a global lock
- *              release interrupt occurs.  If there's a thread waiting for
- *              the global lock, signal it.
- *
- * NOTE: Assumes that the semaphore can be signaled from interrupt level. If
- * this is not possible for some reason, a separate thread will have to be
- * scheduled to do this.
- *
- ******************************************************************************/
-static u8 acpi_ev_global_lock_pending;
-
-static u32 acpi_ev_global_lock_handler(void *context)
-{
-        acpi_status status;
-        acpi_cpu_flags flags;
-
-        flags = acpi_os_acquire_lock(acpi_ev_global_lock_pending_lock);
-
-        if (!acpi_ev_global_lock_pending) {
-                goto out;
-        }
-
-        /* Send a unit to the semaphore */
-
-        status = acpi_os_signal_semaphore(acpi_gbl_global_lock_semaphore, 1);
-        if (ACPI_FAILURE(status)) {
-                ACPI_ERROR((AE_INFO, "Could not signal Global Lock semaphore"));
-        }
-
-        acpi_ev_global_lock_pending = FALSE;
-
- out:
-        acpi_os_release_lock(acpi_ev_global_lock_pending_lock, flags);
-
-        return (ACPI_INTERRUPT_HANDLED);
-}
-
-/*******************************************************************************
- *
- * FUNCTION:    acpi_ev_init_global_lock_handler
- *
- * PARAMETERS:  None
- *
- * RETURN:      Status
- *
- * DESCRIPTION: Install a handler for the global lock release event
- *
- ******************************************************************************/
-
-acpi_status acpi_ev_init_global_lock_handler(void)
-{
-        acpi_status status;
-
-        ACPI_FUNCTION_TRACE(ev_init_global_lock_handler);
-
-        /* Attempt installation of the global lock handler */
-
-        status = acpi_install_fixed_event_handler(ACPI_EVENT_GLOBAL,
-                                                  acpi_ev_global_lock_handler,
-                                                  NULL);
-
-        /*
-         * If the global lock does not exist on this platform, the attempt to
-         * enable GBL_STATUS will fail (the GBL_ENABLE bit will not stick).
-         * Map to AE_OK, but mark global lock as not present. Any attempt to
-         * actually use the global lock will be flagged with an error.
-         */
-        if (status == AE_NO_HARDWARE_RESPONSE) {
-                ACPI_ERROR((AE_INFO,
-                            "No response from Global Lock hardware, disabling lock"));
-
-                acpi_gbl_global_lock_present = FALSE;
-                return_ACPI_STATUS(AE_OK);
-        }
-
-        acpi_gbl_global_lock_present = TRUE;
-        return_ACPI_STATUS(status);
-}
-
-/*******************************************************************************
- *
- * FUNCTION:    acpi_ev_remove_global_lock_handler
- *
- * PARAMETERS:  None
- *
- * RETURN:      Status
- *
- * DESCRIPTION: Remove the handler for the Global Lock
- *
- ******************************************************************************/
-
-static acpi_status acpi_ev_remove_global_lock_handler(void)
-{
-        acpi_status status;
-
-        ACPI_FUNCTION_TRACE(ev_remove_global_lock_handler);
-
-        acpi_gbl_global_lock_present = FALSE;
-        status = acpi_remove_fixed_event_handler(ACPI_EVENT_GLOBAL,
-                                                 acpi_ev_global_lock_handler);
-
-        return_ACPI_STATUS(status);
-}
-
-/******************************************************************************
- *
- * FUNCTION:    acpi_ev_acquire_global_lock
- *
- * PARAMETERS:  Timeout         - Max time to wait for the lock, in millisec.
- *
- * RETURN:      Status
- *
- * DESCRIPTION: Attempt to gain ownership of the Global Lock.
- *
- * MUTEX:       Interpreter must be locked
- *
- * Note: The original implementation allowed multiple threads to "acquire" the
- * Global Lock, and the OS would hold the lock until the last thread had
- * released it. However, this could potentially starve the BIOS out of the
- * lock, especially in the case where there is a tight handshake between the
- * Embedded Controller driver and the BIOS. Therefore, this implementation
- * allows only one thread to acquire the HW Global Lock at a time, and makes
- * the global lock appear as a standard mutex on the OS side.
- *
- *****************************************************************************/
-static acpi_thread_id acpi_ev_global_lock_thread_id;
-static int acpi_ev_global_lock_acquired;
-
-acpi_status acpi_ev_acquire_global_lock(u16 timeout)
-{
-        acpi_cpu_flags flags;
-        acpi_status status = AE_OK;
-        u8 acquired = FALSE;
-
-        ACPI_FUNCTION_TRACE(ev_acquire_global_lock);
-
-        /*
-         * Only one thread can acquire the GL at a time, the global_lock_mutex
-         * enforces this. This interface releases the interpreter if we must wait.
-         */
-        status = acpi_ex_system_wait_mutex(
-                        acpi_gbl_global_lock_mutex->mutex.os_mutex, 0);
-        if (status == AE_TIME) {
-                if (acpi_ev_global_lock_thread_id == acpi_os_get_thread_id()) {
-                        acpi_ev_global_lock_acquired++;
-                        return AE_OK;
-                }
-        }
-
-        if (ACPI_FAILURE(status)) {
-                status = acpi_ex_system_wait_mutex(
-                                acpi_gbl_global_lock_mutex->mutex.os_mutex,
-                                timeout);
-        }
-        if (ACPI_FAILURE(status)) {
-                return_ACPI_STATUS(status);
-        }
-
-        acpi_ev_global_lock_thread_id = acpi_os_get_thread_id();
-        acpi_ev_global_lock_acquired++;
-
-        /*
-         * Update the global lock handle and check for wraparound. The handle is
-         * only used for the external global lock interfaces, but it is updated
-         * here to properly handle the case where a single thread may acquire the
-         * lock via both the AML and the acpi_acquire_global_lock interfaces. The
-         * handle is therefore updated on the first acquire from a given thread
-         * regardless of where the acquisition request originated.
-         */
-        acpi_gbl_global_lock_handle++;
-        if (acpi_gbl_global_lock_handle == 0) {
-                acpi_gbl_global_lock_handle = 1;
-        }
-
-        /*
-         * Make sure that a global lock actually exists. If not, just treat the
-         * lock as a standard mutex.
-         */
-        if (!acpi_gbl_global_lock_present) {
-                acpi_gbl_global_lock_acquired = TRUE;
-                return_ACPI_STATUS(AE_OK);
-        }
-
-        flags = acpi_os_acquire_lock(acpi_ev_global_lock_pending_lock);
-
-        do {
-
-                /* Attempt to acquire the actual hardware lock */
-
-                ACPI_ACQUIRE_GLOBAL_LOCK(acpi_gbl_FACS, acquired);
-                if (acquired) {
-                        acpi_gbl_global_lock_acquired = TRUE;
-
-                        ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
-                                          "Acquired hardware Global Lock\n"));
-                        break;
-                }
-
-                acpi_ev_global_lock_pending = TRUE;
-
-                acpi_os_release_lock(acpi_ev_global_lock_pending_lock, flags);
-
-                /*
-                 * Did not get the lock. The pending bit was set above, and we
-                 * must wait until we get the global lock released interrupt.
-                 */
-                ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
-                                  "Waiting for hardware Global Lock\n"));
-
-                /*
-                 * Wait for handshake with the global lock interrupt handler.
-                 * This interface releases the interpreter if we must wait.
-                 */
-                status = acpi_ex_system_wait_semaphore(
-                                                acpi_gbl_global_lock_semaphore,
-                                                ACPI_WAIT_FOREVER);
-
-                flags = acpi_os_acquire_lock(acpi_ev_global_lock_pending_lock);
-
-        } while (ACPI_SUCCESS(status));
-
-        acpi_ev_global_lock_pending = FALSE;
-
-        acpi_os_release_lock(acpi_ev_global_lock_pending_lock, flags);
-
-        return_ACPI_STATUS(status);
-}
-
-/*******************************************************************************
- *
- * FUNCTION:    acpi_ev_release_global_lock
- *
- * PARAMETERS:  None
- *
- * RETURN:      Status
- *
- * DESCRIPTION: Releases ownership of the Global Lock.
- *
- ******************************************************************************/
-
-acpi_status acpi_ev_release_global_lock(void)
-{
-        u8 pending = FALSE;
-        acpi_status status = AE_OK;
-
-        ACPI_FUNCTION_TRACE(ev_release_global_lock);
-
-        /* Lock must be already acquired */
-
-        if (!acpi_gbl_global_lock_acquired) {
-                ACPI_WARNING((AE_INFO,
-                              "Cannot release the ACPI Global Lock, it has not been acquired"));
-                return_ACPI_STATUS(AE_NOT_ACQUIRED);
-        }
-
-        acpi_ev_global_lock_acquired--;
-        if (acpi_ev_global_lock_acquired > 0) {
-                return AE_OK;
-        }
-
-        if (acpi_gbl_global_lock_present) {
-
-                /* Allow any thread to release the lock */
-
-                ACPI_RELEASE_GLOBAL_LOCK(acpi_gbl_FACS, pending);
-
-                /*
-                 * If the pending bit was set, we must write GBL_RLS to the control
-                 * register
-                 */
-                if (pending) {
-                        status =
-                            acpi_write_bit_register
-                            (ACPI_BITREG_GLOBAL_LOCK_RELEASE,
-                             ACPI_ENABLE_EVENT);
-                }
-
-                ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
-                                  "Released hardware Global Lock\n"));
-        }
-
-        acpi_gbl_global_lock_acquired = FALSE;
-
-        /* Release the local GL mutex */
-        acpi_ev_global_lock_thread_id = 0;
-        acpi_ev_global_lock_acquired = 0;
-        acpi_os_release_mutex(acpi_gbl_global_lock_mutex->mutex.os_mutex);
-        return_ACPI_STATUS(status);
-}
-
 /******************************************************************************
  *
  * FUNCTION:    acpi_ev_terminate
diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c
index bea7223d7a71..f0edf5c43c03 100644
--- a/drivers/acpi/acpica/evregion.c
+++ b/drivers/acpi/acpica/evregion.c
@@ -55,6 +55,8 @@ static u8
 acpi_ev_has_default_handler(struct acpi_namespace_node *node,
                             acpi_adr_space_type space_id);
 
+static void acpi_ev_orphan_ec_reg_method(void);
+
 static acpi_status
 acpi_ev_reg_run(acpi_handle obj_handle,
                 u32 level, void *context, void **return_value);
@@ -561,7 +563,9 @@ acpi_ev_detach_region(union acpi_operand_object *region_obj,
 
                         /* Now stop region accesses by executing the _REG method */
 
-                        status = acpi_ev_execute_reg_method(region_obj, 0);
+                        status =
+                            acpi_ev_execute_reg_method(region_obj,
+                                                       ACPI_REG_DISCONNECT);
                         if (ACPI_FAILURE(status)) {
                                 ACPI_EXCEPTION((AE_INFO, status,
                                                 "from region _REG, [%s]",
@@ -1062,6 +1066,12 @@ acpi_ev_execute_reg_methods(struct acpi_namespace_node *node,
                                         ACPI_NS_WALK_UNLOCK, acpi_ev_reg_run,
                                         NULL, &space_id, NULL);
 
+        /* Special case for EC: handle "orphan" _REG methods with no region */
+
+        if (space_id == ACPI_ADR_SPACE_EC) {
+                acpi_ev_orphan_ec_reg_method();
+        }
+
         return_ACPI_STATUS(status);
 }
 
@@ -1120,6 +1130,113 @@ acpi_ev_reg_run(acpi_handle obj_handle,
                 return (AE_OK);
         }
 
-        status = acpi_ev_execute_reg_method(obj_desc, 1);
+        status = acpi_ev_execute_reg_method(obj_desc, ACPI_REG_CONNECT);
         return (status);
 }
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ev_orphan_ec_reg_method
+ *
+ * PARAMETERS:  None
+ *
+ * RETURN:      None
+ *
+ * DESCRIPTION: Execute an "orphan" _REG method that appears under the EC
+ *              device. This is a _REG method that has no corresponding region
+ *              within the EC device scope. The orphan _REG method appears to
+ *              have been enabled by the description of the ECDT in the ACPI
+ *              specification: "The availability of the region space can be
+ *              detected by providing a _REG method object underneath the
+ *              Embedded Controller device."
+ *
+ *              To quickly access the EC device, we use the EC_ID that appears
+ *              within the ECDT. Otherwise, we would need to perform a time-
+ *              consuming namespace walk, executing _HID methods to find the
+ *              EC device.
+ *
+ ******************************************************************************/
+
+static void acpi_ev_orphan_ec_reg_method(void)
+{
+        struct acpi_table_ecdt *table;
+        acpi_status status;
+        struct acpi_object_list args;
+        union acpi_object objects[2];
+        struct acpi_namespace_node *ec_device_node;
+        struct acpi_namespace_node *reg_method;
+        struct acpi_namespace_node *next_node;
+
+        ACPI_FUNCTION_TRACE(ev_orphan_ec_reg_method);
+
+        /* Get the ECDT (if present in system) */
+
+        status = acpi_get_table(ACPI_SIG_ECDT, 0,
+                                ACPI_CAST_INDIRECT_PTR(struct acpi_table_header,
+                                                       &table));
+        if (ACPI_FAILURE(status)) {
+                return_VOID;
+        }
+
+        /* We need a valid EC_ID string */
+
+        if (!(*table->id)) {
+                return_VOID;
+        }
+
+        /* Namespace is currently locked, must release */
+
+        (void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE);
+
+        /* Get a handle to the EC device referenced in the ECDT */
+
+        status = acpi_get_handle(NULL,
+                                 ACPI_CAST_PTR(char, table->id),
+                                 ACPI_CAST_PTR(acpi_handle, &ec_device_node));
+        if (ACPI_FAILURE(status)) {
+                goto exit;
+        }
+
+        /* Get a handle to a _REG method immediately under the EC device */
+
+        status = acpi_get_handle(ec_device_node,
+                                 METHOD_NAME__REG, ACPI_CAST_PTR(acpi_handle,
+                                                                 &reg_method));
+        if (ACPI_FAILURE(status)) {
+                goto exit;
+        }
+
+        /*
+         * Execute the _REG method only if there is no Operation Region in
+         * this scope with the Embedded Controller space ID. Otherwise, it
+         * will already have been executed. Note, this allows for Regions
+         * with other space IDs to be present; but the code below will then
+         * execute the _REG method with the EC space ID argument.
+         */
+        next_node = acpi_ns_get_next_node(ec_device_node, NULL);
+        while (next_node) {
+                if ((next_node->type == ACPI_TYPE_REGION) &&
+                    (next_node->object) &&
+                    (next_node->object->region.space_id == ACPI_ADR_SPACE_EC)) {
+                        goto exit;      /* Do not execute _REG */
+                }
+                next_node = acpi_ns_get_next_node(ec_device_node, next_node);
+        }
+
+        /* Evaluate the _REG(EC,Connect) method */
+
+        args.count = 2;
+        args.pointer = objects;
+        objects[0].type = ACPI_TYPE_INTEGER;
+        objects[0].integer.value = ACPI_ADR_SPACE_EC;
+        objects[1].type = ACPI_TYPE_INTEGER;
+        objects[1].integer.value = ACPI_REG_CONNECT;
+
+        status = acpi_evaluate_object(reg_method, NULL, &args, NULL);
+
+      exit:
+        /* We ignore all errors from above, don't care */
+
+        status = acpi_ut_acquire_mutex(ACPI_MTX_NAMESPACE);
+        return_VOID;
+}
diff --git a/drivers/acpi/acpica/evrgnini.c b/drivers/acpi/acpica/evrgnini.c
index 9659cee6093e..55a5d35ef34a 100644
--- a/drivers/acpi/acpica/evrgnini.c
+++ b/drivers/acpi/acpica/evrgnini.c
@@ -637,7 +637,7 @@ acpi_ev_initialize_region(union acpi_operand_object *region_obj,
 
                                         status =
                                             acpi_ev_execute_reg_method
-                                            (region_obj, 1);
+                                            (region_obj, ACPI_REG_CONNECT);
 
                                         if (acpi_ns_locked) {
                                                 status =
diff --git a/drivers/acpi/acpica/evxfregn.c b/drivers/acpi/acpica/evxfregn.c
index c85c8c45599d..00cd95692a91 100644
--- a/drivers/acpi/acpica/evxfregn.c
+++ b/drivers/acpi/acpica/evxfregn.c
@@ -130,20 +130,21 @@ acpi_install_address_space_handler(acpi_handle device,
         case ACPI_ADR_SPACE_PCI_CONFIG:
         case ACPI_ADR_SPACE_DATA_TABLE:
 
-                if (acpi_gbl_reg_methods_executed) {
+                if (!acpi_gbl_reg_methods_executed) {
 
-                        /* Run all _REG methods for this address space */
-
-                        status = acpi_ev_execute_reg_methods(node, space_id);
+                        /* We will defer execution of the _REG methods for this space */
+                        goto unlock_and_exit;
                 }
                 break;
 
         default:
-
-                status = acpi_ev_execute_reg_methods(node, space_id);
                 break;
         }
 
+        /* Run all _REG methods for this address space */
+
+        status = acpi_ev_execute_reg_methods(node, space_id);
+
       unlock_and_exit:
         (void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE);
         return_ACPI_STATUS(status);
diff --git a/drivers/acpi/acpica/excreate.c b/drivers/acpi/acpica/excreate.c
index e7b372d17667..110711afada8 100644
--- a/drivers/acpi/acpica/excreate.c
+++ b/drivers/acpi/acpica/excreate.c
@@ -305,7 +305,8 @@ acpi_ex_create_region(u8 * aml_start,
          * range
          */
         if ((region_space >= ACPI_NUM_PREDEFINED_REGIONS) &&
-            (region_space < ACPI_USER_REGION_BEGIN)) {
+            (region_space < ACPI_USER_REGION_BEGIN) &&
+            (region_space != ACPI_ADR_SPACE_DATA_TABLE)) {
                 ACPI_ERROR((AE_INFO, "Invalid AddressSpace type 0x%X",
                             region_space));
                 return_ACPI_STATUS(AE_AML_INVALID_SPACE_ID);
diff --git a/drivers/acpi/acpica/nsrepair.c b/drivers/acpi/acpica/nsrepair.c
index 1d76ac85b5e7..ac7b854b0bd7 100644
--- a/drivers/acpi/acpica/nsrepair.c
+++ b/drivers/acpi/acpica/nsrepair.c
@@ -74,7 +74,6 @@ ACPI_MODULE_NAME("nsrepair")
  *
  * Additional possible repairs:
  *
- * Optional/unnecessary NULL package elements removed
  * Required package elements that are NULL replaced by Integer/String/Buffer
  * Incorrect standalone package wrapped with required outer package
  *
@@ -623,16 +622,12 @@ acpi_ns_remove_null_elements(struct acpi_predefined_data *data,
         ACPI_FUNCTION_NAME(ns_remove_null_elements);
 
         /*
-         * PTYPE1 packages contain no subpackages.
-         * PTYPE2 packages contain a variable number of sub-packages. We can
-         * safely remove all NULL elements from the PTYPE2 packages.
+         * We can safely remove all NULL elements from these package types:
+         * PTYPE1_VAR packages contain a variable number of simple data types.
+         * PTYPE2 packages contain a variable number of sub-packages.
          */
         switch (package_type) {
-        case ACPI_PTYPE1_FIXED:
         case ACPI_PTYPE1_VAR:
-        case ACPI_PTYPE1_OPTION:
-                return;
-
         case ACPI_PTYPE2:
         case ACPI_PTYPE2_COUNT:
         case ACPI_PTYPE2_PKG_COUNT:
@@ -642,6 +637,8 @@ acpi_ns_remove_null_elements(struct acpi_predefined_data *data,
                 break;
 
         default:
+        case ACPI_PTYPE1_FIXED:
+        case ACPI_PTYPE1_OPTION:
                 return;
         }
 
diff --git a/drivers/acpi/acpica/utdecode.c b/drivers/acpi/acpica/utdecode.c
index 136a814cec69..97cb36f85ce9 100644
--- a/drivers/acpi/acpica/utdecode.c
+++ b/drivers/acpi/acpica/utdecode.c
@@ -170,8 +170,7 @@ const char *acpi_gbl_region_types[ACPI_NUM_PREDEFINED_REGIONS] = {
         "SMBus",
         "SystemCMOS",
         "PCIBARTarget",
-        "IPMI",
-        "DataTable"
+        "IPMI"
 };
 
 char *acpi_ut_get_region_name(u8 space_id)
@@ -179,6 +178,8 @@ char *acpi_ut_get_region_name(u8 space_id)
 
         if (space_id >= ACPI_USER_REGION_BEGIN) {
                 return ("UserDefinedRegion");
+        } else if (space_id == ACPI_ADR_SPACE_DATA_TABLE) {
+                return ("DataTable");
         } else if (space_id == ACPI_ADR_SPACE_FIXED_HARDWARE) {
                 return ("FunctionalFixedHW");
         } else if (space_id >= ACPI_NUM_PREDEFINED_REGIONS) {
diff --git a/drivers/acpi/acpica/utmutex.c b/drivers/acpi/acpica/utmutex.c
index a946c689f03b..7d797e2baecd 100644
--- a/drivers/acpi/acpica/utmutex.c
+++ b/drivers/acpi/acpica/utmutex.c
@@ -83,9 +83,15 @@ acpi_status acpi_ut_mutex_initialize(void)
 
         /* Create the spinlocks for use at interrupt level */
 
-        spin_lock_init(acpi_gbl_gpe_lock);
-        spin_lock_init(acpi_gbl_hardware_lock);
-        spin_lock_init(acpi_ev_global_lock_pending_lock);
+        status = acpi_os_create_lock (&acpi_gbl_gpe_lock);
+        if (ACPI_FAILURE (status)) {
+                return_ACPI_STATUS (status);
+        }
+
+        status = acpi_os_create_lock (&acpi_gbl_hardware_lock);
+        if (ACPI_FAILURE (status)) {
+                return_ACPI_STATUS (status);
+        }
 
         /* Mutex for _OSI support */
         status = acpi_os_create_mutex(&acpi_gbl_osi_mutex);
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 9749980ca6ca..d1e06c182cdb 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -227,7 +227,7 @@ static int __acpi_bus_set_power(struct acpi_device *device, int state)
         acpi_status status = AE_OK;
         char object_name[5] = { '_', 'P', 'S', '0' + state, '\0' };
 
-        if (!device || (state < ACPI_STATE_D0) || (state > ACPI_STATE_D3))
+        if (!device || (state < ACPI_STATE_D0) || (state > ACPI_STATE_D3_COLD))
                 return -EINVAL;
 
         /* Make sure this is a valid target state */
diff --git a/drivers/acpi/custom_method.c b/drivers/acpi/custom_method.c
new file mode 100644
index 000000000000..5d42c2414ae5
--- /dev/null
+++ b/drivers/acpi/custom_method.c
@@ -0,0 +1,100 @@
+/*
+ * debugfs.c - ACPI debugfs interface to userspace.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/uaccess.h>
+#include <linux/debugfs.h>
+#include <acpi/acpi_drivers.h>
+
+#include "internal.h"
+
+#define _COMPONENT              ACPI_SYSTEM_COMPONENT
+ACPI_MODULE_NAME("custom_method");
+MODULE_LICENSE("GPL");
+
+static struct dentry *cm_dentry;
+
+/* /sys/kernel/debug/acpi/custom_method */
+
+static ssize_t cm_write(struct file *file, const char __user * user_buf,
+                        size_t count, loff_t *ppos)
+{
+        static char *buf;
+        static u32 max_size;
+        static u32 uncopied_bytes;
+
+        struct acpi_table_header table;
+        acpi_status status;
+
+        if (!(*ppos)) {
+                /* parse the table header to get the table length */
+                if (count <= sizeof(struct acpi_table_header))
+                        return -EINVAL;
+                if (copy_from_user(&table, user_buf,
+                                   sizeof(struct acpi_table_header)))
+                        return -EFAULT;
+                uncopied_bytes = max_size = table.length;
+                buf = kzalloc(max_size, GFP_KERNEL);
+                if (!buf)
+                        return -ENOMEM;
+        }
+
+        if (buf == NULL)
+                return -EINVAL;
+
+        if ((*ppos > max_size) ||
+            (*ppos + count > max_size) ||
+            (*ppos + count < count) ||
+            (count > uncopied_bytes))
+                return -EINVAL;
+
+        if (copy_from_user(buf + (*ppos), user_buf, count)) {
+                kfree(buf);
+                buf = NULL;
+                return -EFAULT;
+        }
+
+        uncopied_bytes -= count;
+        *ppos += count;
+
+        if (!uncopied_bytes) {
+                status = acpi_install_method(buf);
+                kfree(buf);
+                buf = NULL;
+                if (ACPI_FAILURE(status))
+                        return -EINVAL;
+                add_taint(TAINT_OVERRIDDEN_ACPI_TABLE);
+        }
+
+        return count;
+}
+
+static const struct file_operations cm_fops = {
+        .write = cm_write,
+        .llseek = default_llseek,
+};
+
+static int __init acpi_custom_method_init(void)
+{
+        if (acpi_debugfs_dir == NULL)
+                return -ENOENT;
+
+        cm_dentry = debugfs_create_file("custom_method", S_IWUSR,
+                                        acpi_debugfs_dir, NULL, &cm_fops);
+        if (cm_dentry == NULL)
+                return -ENODEV;
+
+        return 0;
+}
+
+static void __exit acpi_custom_method_exit(void)
+{
+        if (cm_dentry)
+                debugfs_remove(cm_dentry);
+ }
+
+module_init(acpi_custom_method_init);
+module_exit(acpi_custom_method_exit);
diff --git a/drivers/acpi/debugfs.c b/drivers/acpi/debugfs.c
index 384f7abcff77..182a9fc36355 100644
--- a/drivers/acpi/debugfs.c
+++ b/drivers/acpi/debugfs.c
@@ -3,100 +3,16 @@
  */
 
 #include <linux/init.h>
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/uaccess.h>
 #include <linux/debugfs.h>
 #include <acpi/acpi_drivers.h>
 
 #define _COMPONENT              ACPI_SYSTEM_COMPONENT
 ACPI_MODULE_NAME("debugfs");
 
+struct dentry *acpi_debugfs_dir;
+EXPORT_SYMBOL_GPL(acpi_debugfs_dir);
 
-/* /sys/modules/acpi/parameters/aml_debug_output */
-
-module_param_named(aml_debug_output, acpi_gbl_enable_aml_debug_object,
-                   bool, 0644);
-MODULE_PARM_DESC(aml_debug_output,
-                 "To enable/disable the ACPI Debug Object output.");
-
-/* /sys/kernel/debug/acpi/custom_method */
-
-static ssize_t cm_write(struct file *file, const char __user * user_buf,
-                        size_t count, loff_t *ppos)
+void __init acpi_debugfs_init(void)
 {
-        static char *buf;
-        static u32 max_size;
-        static u32 uncopied_bytes;
-
-        struct acpi_table_header table;
-        acpi_status status;
-
-        if (!(*ppos)) {
-                /* parse the table header to get the table length */
-                if (count <= sizeof(struct acpi_table_header))
-                        return -EINVAL;
-                if (copy_from_user(&table, user_buf,
-                                   sizeof(struct acpi_table_header)))
-                        return -EFAULT;
-                uncopied_bytes = max_size = table.length;
-                buf = kzalloc(max_size, GFP_KERNEL);
-                if (!buf)
-                        return -ENOMEM;
-        }
-
-        if (buf == NULL)
-                return -EINVAL;
-
-        if ((*ppos > max_size) ||
-            (*ppos + count > max_size) ||
-            (*ppos + count < count) ||
-            (count > uncopied_bytes))
-                return -EINVAL;
-
-        if (copy_from_user(buf + (*ppos), user_buf, count)) {
-                kfree(buf);
-                buf = NULL;
-                return -EFAULT;
-        }
-
-        uncopied_bytes -= count;
-        *ppos += count;
-
-        if (!uncopied_bytes) {
-                status = acpi_install_method(buf);
-                kfree(buf);
-                buf = NULL;
-                if (ACPI_FAILURE(status))
-                        return -EINVAL;
-                add_taint(TAINT_OVERRIDDEN_ACPI_TABLE);
-        }
-
-        return count;
-}
-
-static const struct file_operations cm_fops = {
-        .write = cm_write,
-        .llseek = default_llseek,
-};
-
-int __init acpi_debugfs_init(void)
-{
-        struct dentry *acpi_dir, *cm_dentry;
-
-        acpi_dir = debugfs_create_dir("acpi", NULL);
-        if (!acpi_dir)
-                goto err;
-
-        cm_dentry = debugfs_create_file("custom_method", S_IWUSR,
-                                        acpi_dir, NULL, &cm_fops);
-        if (!cm_dentry)
-                goto err;
-
-        return 0;
-
-err:
-        if (acpi_dir)
-                debugfs_remove(acpi_dir);
-        return -EINVAL;
+        acpi_debugfs_dir = debugfs_create_dir("acpi", NULL);
 }
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index fa848c4116a8..b19a18dd994f 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -69,7 +69,6 @@ enum ec_command {
 
 #define ACPI_EC_DELAY           500     /* Wait 500ms max. during EC ops */
 #define ACPI_EC_UDELAY_GLK      1000    /* Wait 1ms max. to get global lock */
-#define ACPI_EC_CDELAY          10      /* Wait 10us before polling EC */
 #define ACPI_EC_MSI_UDELAY      550     /* Wait 550us for MSI EC */
 
 #define ACPI_EC_STORM_THRESHOLD 8       /* number of false interrupts
@@ -433,8 +432,7 @@ EXPORT_SYMBOL(ec_write);
 
 int ec_transaction(u8 command,
                    const u8 * wdata, unsigned wdata_len,
-                   u8 * rdata, unsigned rdata_len,
-                   int force_poll)
+                   u8 * rdata, unsigned rdata_len)
 {
         struct transaction t = {.command = command,
                                 .wdata = wdata, .rdata = rdata,
@@ -592,8 +590,6 @@ static void acpi_ec_gpe_query(void *ec_cxt)
         mutex_unlock(&ec->lock);
 }
 
-static void acpi_ec_gpe_query(void *ec_cxt);
-
 static int ec_check_sci(struct acpi_ec *ec, u8 state)
 {
         if (state & ACPI_EC_FLAG_SCI) {
@@ -808,8 +804,6 @@ static int acpi_ec_add(struct acpi_device *device)
                         return -EINVAL;
         }
 
-        ec->handle = device->handle;
-
         /* Find and register all query methods */
         acpi_walk_namespace(ACPI_TYPE_METHOD, ec->handle, 1,
                             acpi_ec_register_query_methods, NULL, ec, NULL);
@@ -938,8 +932,19 @@ static struct dmi_system_id __initdata ec_dmi_table[] = {
         ec_flag_msi, "MSI hardware", {
         DMI_MATCH(DMI_CHASSIS_VENDOR, "MICRO-STAR")}, NULL},
         {
+        ec_flag_msi, "Quanta hardware", {
+        DMI_MATCH(DMI_SYS_VENDOR, "Quanta"),
+        DMI_MATCH(DMI_PRODUCT_NAME, "TW8/SW8/DW8"),}, NULL},
+        {
+        ec_flag_msi, "Quanta hardware", {
+        DMI_MATCH(DMI_SYS_VENDOR, "Quanta"),
+        DMI_MATCH(DMI_PRODUCT_NAME, "TW9/SW9"),}, NULL},
+        {
         ec_validate_ecdt, "ASUS hardware", {
         DMI_MATCH(DMI_BIOS_VENDOR, "ASUS") }, NULL},
+        {
+        ec_validate_ecdt, "ASUS hardware", {
+        DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer Inc.") }, NULL},
         {},
 };
 
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 4bfb759deb10..ca75b9ce0489 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -28,9 +28,10 @@ int acpi_scan_init(void);
 int acpi_sysfs_init(void);
 
 #ifdef CONFIG_DEBUG_FS
+extern struct dentry *acpi_debugfs_dir;
 int acpi_debugfs_init(void);
 #else
-static inline int acpi_debugfs_init(void) { return 0; }
+static inline void acpi_debugfs_init(void) { return; }
 #endif
 
 /* --------------------------------------------------------------------------
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 45ad4ffef533..52ca9649d769 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -902,14 +902,6 @@ void acpi_os_wait_events_complete(void *context)
 
 EXPORT_SYMBOL(acpi_os_wait_events_complete);
 
-/*
- * Deallocate the memory for a spinlock.
- */
-void acpi_os_delete_lock(acpi_spinlock handle)
-{
-        return;
-}
-
 acpi_status
 acpi_os_create_semaphore(u32 max_units, u32 initial_units, acpi_handle * handle)
 {
@@ -1341,6 +1333,31 @@ int acpi_resources_are_enforced(void)
 EXPORT_SYMBOL(acpi_resources_are_enforced);
 
 /*
+ * Create and initialize a spinlock.
+ */
+acpi_status
+acpi_os_create_lock(acpi_spinlock *out_handle)
+{
+        spinlock_t *lock;
+
+        lock = ACPI_ALLOCATE(sizeof(spinlock_t));
+        if (!lock)
+                return AE_NO_MEMORY;
+        spin_lock_init(lock);
+        *out_handle = lock;
+
+        return AE_OK;
+}
+
+/*
+ * Deallocate the memory for a spinlock.
+ */
+void acpi_os_delete_lock(acpi_spinlock handle)
+{
+        ACPI_FREE(handle);
+}
+
+/*
  * Acquire a spinlock.
  *
  * handle is a pointer to the spinlock_t.
diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c
index 25bf17da69fd..02d2a4c9084d 100644
--- a/drivers/acpi/processor_core.c
+++ b/drivers/acpi/processor_core.c
@@ -37,7 +37,6 @@ static struct dmi_system_id __initdata processor_idle_dmi_table[] = {
         {},
 };
 
-#ifdef CONFIG_SMP
 static int map_lapic_id(struct acpi_subtable_header *entry,
                  u32 acpi_id, int *apic_id)
 {
@@ -165,7 +164,9 @@ exit:
 
 int acpi_get_cpuid(acpi_handle handle, int type, u32 acpi_id)
 {
+#ifdef CONFIG_SMP
         int i;
+#endif
         int apic_id = -1;
 
         apic_id = map_mat_entry(handle, type, acpi_id);
@@ -174,14 +175,19 @@ int acpi_get_cpuid(acpi_handle handle, int type, u32 acpi_id)
         if (apic_id == -1)
                 return apic_id;
 
+#ifdef CONFIG_SMP
         for_each_possible_cpu(i) {
                 if (cpu_physical_id(i) == apic_id)
                         return i;
         }
+#else
+        /* In UP kernel, only processor 0 is valid */
+        if (apic_id == 0)
+                return apic_id;
+#endif
         return -1;
 }
 EXPORT_SYMBOL_GPL(acpi_get_cpuid);
-#endif
 
 static bool __init processor_physically_present(acpi_handle handle)
 {
@@ -217,7 +223,7 @@ static bool __init processor_physically_present(acpi_handle handle)
         type = (acpi_type == ACPI_TYPE_DEVICE) ? 1 : 0;
         cpuid = acpi_get_cpuid(handle, type, acpi_id);
 
-        if ((cpuid == -1) && (num_possible_cpus() > 1))
+        if (cpuid == -1)
                 return false;
 
         return true;
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index d615b7d69bca..431ab11c8c1b 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -161,7 +161,7 @@ static void lapic_timer_check_state(int state, struct acpi_processor *pr,
         if (cpu_has(&cpu_data(pr->id), X86_FEATURE_ARAT))
                 return;
 
-        if (c1e_detected)
+        if (amd_e400_c1e_detected)
                 type = ACPI_STATE_C1;
 
         /*
diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c
index 61891e75583d..77255f250dbb 100644
--- a/drivers/acpi/sysfs.c
+++ b/drivers/acpi/sysfs.c
@@ -220,6 +220,14 @@ module_param_call(trace_state, param_set_trace_state, param_get_trace_state,
                   NULL, 0644);
 #endif /* CONFIG_ACPI_DEBUG */
 
+
+/* /sys/modules/acpi/parameters/aml_debug_output */
+
+module_param_named(aml_debug_output, acpi_gbl_enable_aml_debug_object,
+                   bool, 0644);
+MODULE_PARM_DESC(aml_debug_output,
+                 "To enable/disable the ACPI Debug Object output.");
+
 /* /sys/module/acpi/parameters/acpica_version */
 static int param_get_acpica_version(char *buffer, struct kernel_param *kp)
 {
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index db8f88586c8d..98de8f418676 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -1038,6 +1038,7 @@ static void floppy_disable_hlt(void)
 {
         unsigned long flags;
 
+        WARN_ONCE(1, "floppy_disable_hlt() scheduled for removal in 2012");
         spin_lock_irqsave(&floppy_hlt_lock, flags);
         if (!hlt_disabled) {
                 hlt_disabled = 1;
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index e6fc716aca45..f533f3375e24 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -192,7 +192,8 @@ static int sock_xmit(struct nbd_device *lo, int send, void *buf, int size,
                         if (lo->xmit_timeout)
                                 del_timer_sync(&ti);
                 } else
-                        result = kernel_recvmsg(sock, &msg, &iov, 1, size, 0);
+                        result = kernel_recvmsg(sock, &msg, &iov, 1, size,
+                                                msg.msg_flags);
 
                 if (signal_pending(current)) {
                         siginfo_t info;
@@ -753,9 +754,26 @@ static int __init nbd_init(void)
                 return -ENOMEM;
 
         part_shift = 0;
-        if (max_part > 0)
+        if (max_part > 0) {
                 part_shift = fls(max_part);
 
+                /*
+                 * Adjust max_part according to part_shift as it is exported
+                 * to user space so that user can know the max number of
+                 * partition kernel should be able to manage.
+                 *
+                 * Note that -1 is required because partition 0 is reserved
+                 * for the whole disk.
+                 */
+                max_part = (1UL << part_shift) - 1;
+        }
+
+        if ((1UL << part_shift) > DISK_MAX_PARTS)
+                return -EINVAL;
+
+        if (nbds_max > 1UL << (MINORBITS - part_shift))
+                return -EINVAL;
+
         for (i = 0; i < nbds_max; i++) {
                 struct gendisk *disk = alloc_disk(1 << part_shift);
                 if (!disk)
diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c
index a0aabd904a51..46b8136c31bb 100644
--- a/drivers/block/paride/pcd.c
+++ b/drivers/block/paride/pcd.c
@@ -321,7 +321,6 @@ static void pcd_init_units(void)
                 strcpy(disk->disk_name, cd->name);      /* umm... */
                 disk->fops = &pcd_bdops;
                 disk->flags = GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
-                disk->events = DISK_EVENT_MEDIA_CHANGE;
         }
 }
 
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 6ecf89cdf006..079c08808d8a 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -6,10 +6,13 @@
 #include <linux/virtio.h>
 #include <linux/virtio_blk.h>
 #include <linux/scatterlist.h>
+#include <linux/string_helpers.h>
+#include <scsi/scsi_cmnd.h>
 
 #define PART_BITS 4
 
 static int major, index;
+struct workqueue_struct *virtblk_wq;
 
 struct virtio_blk
 {
@@ -26,6 +29,9 @@ struct virtio_blk
 
         mempool_t *pool;
 
+        /* Process context for config space updates */
+        struct work_struct config_work;
+
         /* What host tells us, plus 2 for header & tailer. */
         unsigned int sg_elems;
 
@@ -141,7 +147,7 @@ static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
         num = blk_rq_map_sg(q, vbr->req, vblk->sg + out);
 
         if (vbr->req->cmd_type == REQ_TYPE_BLOCK_PC) {
-                sg_set_buf(&vblk->sg[num + out + in++], vbr->req->sense, 96);
+                sg_set_buf(&vblk->sg[num + out + in++], vbr->req->sense, SCSI_SENSE_BUFFERSIZE);
                 sg_set_buf(&vblk->sg[num + out + in++], &vbr->in_hdr,
                            sizeof(vbr->in_hdr));
         }
@@ -291,6 +297,46 @@ static ssize_t virtblk_serial_show(struct device *dev,
 }
 DEVICE_ATTR(serial, S_IRUGO, virtblk_serial_show, NULL);
 
+static void virtblk_config_changed_work(struct work_struct *work)
+{
+        struct virtio_blk *vblk =
+                container_of(work, struct virtio_blk, config_work);
+        struct virtio_device *vdev = vblk->vdev;
+        struct request_queue *q = vblk->disk->queue;
+        char cap_str_2[10], cap_str_10[10];
+        u64 capacity, size;
+
+        /* Host must always specify the capacity. */
+        vdev->config->get(vdev, offsetof(struct virtio_blk_config, capacity),
+                          &capacity, sizeof(capacity));
+
+        /* If capacity is too big, truncate with warning. */
+        if ((sector_t)capacity != capacity) {
+                dev_warn(&vdev->dev, "Capacity %llu too large: truncating\n",
+                         (unsigned long long)capacity);
+                capacity = (sector_t)-1;
+        }
+
+        size = capacity * queue_logical_block_size(q);
+        string_get_size(size, STRING_UNITS_2, cap_str_2, sizeof(cap_str_2));
+        string_get_size(size, STRING_UNITS_10, cap_str_10, sizeof(cap_str_10));
+
+        dev_notice(&vdev->dev,
+                  "new size: %llu %d-byte logical blocks (%s/%s)\n",
+                  (unsigned long long)capacity,
+                  queue_logical_block_size(q),
+                  cap_str_10, cap_str_2);
+
+        set_capacity(vblk->disk, capacity);
+}
+
+static void virtblk_config_changed(struct virtio_device *vdev)
+{
+        struct virtio_blk *vblk = vdev->priv;
+
+        queue_work(virtblk_wq, &vblk->config_work);
+}
+
 static int __devinit virtblk_probe(struct virtio_device *vdev)
 {
         struct virtio_blk *vblk;
@@ -327,6 +373,7 @@ static int __devinit virtblk_probe(struct virtio_device *vdev)
         vblk->vdev = vdev;
         vblk->sg_elems = sg_elems;
         sg_init_table(vblk->sg, vblk->sg_elems);
+        INIT_WORK(&vblk->config_work, virtblk_config_changed_work);
 
         /* We expect one virtqueue, for output. */
         vblk->vq = virtio_find_single_vq(vdev, blk_done, "requests");
@@ -477,6 +524,8 @@ static void __devexit virtblk_remove(struct virtio_device *vdev)
 {
         struct virtio_blk *vblk = vdev->priv;
 
+        flush_work(&vblk->config_work);
+
         /* Nothing should be pending. */
         BUG_ON(!list_empty(&vblk->reqs));
 
@@ -508,27 +557,47 @@ static unsigned int features[] = {
  * Use __refdata to avoid this warning.
  */
 static struct virtio_driver __refdata virtio_blk = {
-        .feature_table = features,
-        .feature_table_size = ARRAY_SIZE(features),
-        .driver.name =  KBUILD_MODNAME,
-        .driver.owner = THIS_MODULE,
-        .id_table =     id_table,
-        .probe =        virtblk_probe,
-        .remove =       __devexit_p(virtblk_remove),
+        .feature_table          = features,
+        .feature_table_size     = ARRAY_SIZE(features),
+        .driver.name            = KBUILD_MODNAME,
+        .driver.owner           = THIS_MODULE,
+        .id_table               = id_table,
+        .probe                  = virtblk_probe,
+        .remove                 = __devexit_p(virtblk_remove),
+        .config_changed         = virtblk_config_changed,
 };
 
 static int __init init(void)
 {
+        int error;
+
+        virtblk_wq = alloc_workqueue("virtio-blk", 0, 0);
+        if (!virtblk_wq)
+                return -ENOMEM;
+
         major = register_blkdev(0, "virtblk");
-        if (major < 0)
-                return major;
-        return register_virtio_driver(&virtio_blk);
+        if (major < 0) {
+                error = major;
+                goto out_destroy_workqueue;
+        }
+
+        error = register_virtio_driver(&virtio_blk);
+        if (error)
+                goto out_unregister_blkdev;
+        return 0;
+
+out_unregister_blkdev:
+        unregister_blkdev(major, "virtblk");
+out_destroy_workqueue:
+        destroy_workqueue(virtblk_wq);
+        return error;
 }
 
 static void __exit fini(void)
 {
         unregister_blkdev(major, "virtblk");
         unregister_virtio_driver(&virtio_blk);
+        destroy_workqueue(virtblk_wq);
 }
 module_init(init);
 module_exit(fini);
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index c73910cc28c9..5cf2993a8338 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -809,11 +809,13 @@ static int __init xen_blkif_init(void)
  failed_init:
         kfree(blkbk->pending_reqs);
         kfree(blkbk->pending_grant_handles);
-        for (i = 0; i < mmap_pages; i++) {
-                if (blkbk->pending_pages[i])
-                        __free_page(blkbk->pending_pages[i]);
+        if (blkbk->pending_pages) {
+                for (i = 0; i < mmap_pages; i++) {
+                        if (blkbk->pending_pages[i])
+                                __free_page(blkbk->pending_pages[i]);
+                }
+                kfree(blkbk->pending_pages);
         }
-        kfree(blkbk->pending_pages);
         kfree(blkbk);
         blkbk = NULL;
         return rc;
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index 34570823355b..6cc0db1bf522 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -357,14 +357,13 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
         }
 
         vbd->bdev = bdev;
-        vbd->size = vbd_sz(vbd);
-
         if (vbd->bdev->bd_disk == NULL) {
                 DPRINTK("xen_vbd_create: device %08x doesn't exist.\n",
                         vbd->pdevice);
                 xen_vbd_free(vbd);
                 return -ENOENT;
         }
+        vbd->size = vbd_sz(vbd);
 
         if (vbd->bdev->bd_disk->flags & GENHD_FL_CD || cdrom)
                 vbd->type |= VDISK_CDROM;
diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c
index b3f01996318f..48ad2a7ab080 100644
--- a/drivers/bluetooth/hci_ldisc.c
+++ b/drivers/bluetooth/hci_ldisc.c
@@ -355,29 +355,24 @@ static void hci_uart_tty_wakeup(struct tty_struct *tty)
  *             flags        pointer to flags for data
  *             count        count of received data in bytes
  *     
- * Return Value:    Number of bytes received
+ * Return Value:    None
  */
-static unsigned int hci_uart_tty_receive(struct tty_struct *tty,
-                const u8 *data, char *flags, int count)
+static void hci_uart_tty_receive(struct tty_struct *tty, const u8 *data, char *flags, int count)
 {
         struct hci_uart *hu = (void *)tty->disc_data;
-        int received;
 
         if (!hu || tty != hu->tty)
-                return -ENODEV;
+                return;
 
         if (!test_bit(HCI_UART_PROTO_SET, &hu->flags))
-                return -EINVAL;
+                return;
 
         spin_lock(&hu->rx_lock);
-        received = hu->proto->recv(hu, (void *) data, count);
-        if (received > 0)
-                hu->hdev->stat.byte_rx += received;
+        hu->proto->recv(hu, (void *) data, count);
+        hu->hdev->stat.byte_rx += count;
         spin_unlock(&hu->rx_lock);
 
         tty_unthrottle(tty);
-
-        return received;
 }
 
 static int hci_uart_register_dev(struct hci_uart *hu)
diff --git a/drivers/cdrom/viocd.c b/drivers/cdrom/viocd.c
index ae15a4ddaa9b..7878da89d29e 100644
--- a/drivers/cdrom/viocd.c
+++ b/drivers/cdrom/viocd.c
@@ -627,7 +627,6 @@ static int viocd_probe(struct vio_dev *vdev, const struct vio_device_id *id)
         gendisk->fops = &viocd_fops;
         gendisk->flags = GENHD_FL_CD | GENHD_FL_REMOVABLE |
                          GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
-        gendisk->events = DISK_EVENT_MEDIA_CHANGE;
         set_capacity(gendisk, 0);
         gendisk->private_data = d;
         d->viocd_disk = gendisk;
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 838568a7dbf5..fb68b1295373 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -1677,17 +1677,12 @@ static int __devinit virtcons_probe(struct virtio_device *vdev)
         portdev->config.max_nr_ports = 1;
         if (virtio_has_feature(vdev, VIRTIO_CONSOLE_F_MULTIPORT)) {
                 multiport = true;
-                vdev->features[0] |= 1 << VIRTIO_CONSOLE_F_MULTIPORT;
-
                 vdev->config->get(vdev, offsetof(struct virtio_console_config,
                                                  max_nr_ports),
                                   &portdev->config.max_nr_ports,
                                   sizeof(portdev->config.max_nr_ports));
         }
 
-        /* Let the Host know we support multiple ports.*/
-        vdev->config->finalize_features(vdev);
-
         err = init_vqs(portdev);
         if (err < 0) {
                 dev_err(&vdev->dev, "Error %d initializing vqs\n", err);
diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c
index 036e5865eb40..dc7c033ef587 100644
--- a/drivers/clocksource/sh_cmt.c
+++ b/drivers/clocksource/sh_cmt.c
@@ -24,7 +24,6 @@
 #include <linux/ioport.h>
 #include <linux/io.h>
 #include <linux/clk.h>
-#include <linux/pm_runtime.h>
 #include <linux/irq.h>
 #include <linux/err.h>
 #include <linux/clocksource.h>
@@ -153,12 +152,10 @@ static int sh_cmt_enable(struct sh_cmt_priv *p, unsigned long *rate)
 {
         int ret;
 
-        /* wake up device and enable clock */
-        pm_runtime_get_sync(&p->pdev->dev);
+        /* enable clock */
         ret = clk_enable(p->clk);
         if (ret) {
                 dev_err(&p->pdev->dev, "cannot enable clock\n");
-                pm_runtime_put_sync(&p->pdev->dev);
                 return ret;
         }
 
@@ -190,9 +187,8 @@ static void sh_cmt_disable(struct sh_cmt_priv *p)
         /* disable interrupts in CMT block */
         sh_cmt_write(p, CMCSR, 0);
 
-        /* stop clock and mark device as idle */
+        /* stop clock */
         clk_disable(p->clk);
-        pm_runtime_put_sync(&p->pdev->dev);
 }
 
 /* private flags */
@@ -664,7 +660,6 @@ static int __devinit sh_cmt_probe(struct platform_device *pdev)
 
         if (p) {
                 dev_info(&pdev->dev, "kept as earlytimer\n");
-                pm_runtime_enable(&pdev->dev);
                 return 0;
         }
 
@@ -679,9 +674,6 @@ static int __devinit sh_cmt_probe(struct platform_device *pdev)
                 kfree(p);
                 platform_set_drvdata(pdev, NULL);
         }
-
-        if (!is_early_platform_device(pdev))
-                pm_runtime_enable(&pdev->dev);
         return ret;
 }
 
diff --git a/drivers/clocksource/sh_tmu.c b/drivers/clocksource/sh_tmu.c
index 17296288a205..808135768617 100644
--- a/drivers/clocksource/sh_tmu.c
+++ b/drivers/clocksource/sh_tmu.c
@@ -25,7 +25,6 @@
 #include <linux/delay.h>
 #include <linux/io.h>
 #include <linux/clk.h>
-#include <linux/pm_runtime.h>
 #include <linux/irq.h>
 #include <linux/err.h>
 #include <linux/clocksource.h>
@@ -110,12 +109,10 @@ static int sh_tmu_enable(struct sh_tmu_priv *p)
 {
         int ret;
 
-        /* wake up device and enable clock */
-        pm_runtime_get_sync(&p->pdev->dev);
+        /* enable clock */
         ret = clk_enable(p->clk);
         if (ret) {
                 dev_err(&p->pdev->dev, "cannot enable clock\n");
-                pm_runtime_put_sync(&p->pdev->dev);
                 return ret;
         }
 
@@ -144,9 +141,8 @@ static void sh_tmu_disable(struct sh_tmu_priv *p)
         /* disable interrupts in TMU block */
         sh_tmu_write(p, TCR, 0x0000);
 
-        /* stop clock and mark device as idle */
+        /* stop clock */
         clk_disable(p->clk);
-        pm_runtime_put_sync(&p->pdev->dev);
 }
 
 static void sh_tmu_set_next(struct sh_tmu_priv *p, unsigned long delta,
@@ -415,7 +411,6 @@ static int __devinit sh_tmu_probe(struct platform_device *pdev)
 
         if (p) {
                 dev_info(&pdev->dev, "kept as earlytimer\n");
-                pm_runtime_enable(&pdev->dev);
                 return 0;
         }
 
@@ -430,9 +425,6 @@ static int __devinit sh_tmu_probe(struct platform_device *pdev)
                 kfree(p);
                 platform_set_drvdata(pdev, NULL);
         }
-
-        if (!is_early_platform_device(pdev))
-                pm_runtime_enable(&pdev->dev);
         return ret;
 }
 
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index f508690eb958..c47f3d09c1ee 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -237,6 +237,7 @@ static int menu_select(struct cpuidle_device *dev)
         unsigned int power_usage = -1;
         int i;
         int multiplier;
+        struct timespec t;
 
         if (data->needs_update) {
                 menu_update(dev);
@@ -251,8 +252,9 @@ static int menu_select(struct cpuidle_device *dev)
                 return 0;
 
         /* determine the expected residency time, round up */
+        t = ktime_to_timespec(tick_nohz_get_sleep_length());
         data->expected_us =
-            DIV_ROUND_UP((u32)ktime_to_ns(tick_nohz_get_sleep_length()), 1000);
+                t.tv_sec * USEC_PER_SEC + t.tv_nsec / NSEC_PER_USEC;
 
 
         data->bucket = which_bucket(data->expected_us);
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index a572600e44eb..25cf327cd1cb 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -200,16 +200,18 @@ config PL330_DMA
           platform_data for a dma-pl330 device.
 
 config PCH_DMA
-        tristate "Intel EG20T PCH / OKI SEMICONDUCTOR ML7213 IOH DMA support"
+        tristate "Intel EG20T PCH / OKI Semi IOH(ML7213/ML7223) DMA support"
         depends on PCI && X86
         select DMA_ENGINE
         help
           Enable support for Intel EG20T PCH DMA engine.
 
-          This driver also can be used for OKI SEMICONDUCTOR ML7213 IOH(Input/
-          Output Hub) which is for IVI(In-Vehicle Infotainment) use.
-          ML7213 is companion chip for Intel Atom E6xx series.
-          ML7213 is completely compatible for Intel EG20T PCH.
+          This driver also can be used for OKI SEMICONDUCTOR IOH(Input/
+          Output Hub), ML7213 and ML7223.
+          ML7213 IOH is for IVI(In-Vehicle Infotainment) use and ML7223 IOH is
+          for MP(Media Phone) use.
+          ML7213/ML7223 is companion chip for Intel Atom E6xx series.
+          ML7213/ML7223 is completely compatible for Intel EG20T PCH.
 
 config IMX_SDMA
         tristate "i.MX SDMA support"
diff --git a/drivers/dma/TODO b/drivers/dma/TODO
new file mode 100644
index 000000000000..a4af8589330c
--- /dev/null
+++ b/drivers/dma/TODO
@@ -0,0 +1,14 @@
+TODO for slave dma
+
+1. Move remaining drivers to use new slave interface
+2. Remove old slave pointer machansim
+3. Make issue_pending to start the transaction in below drivers
+        - mpc512x_dma
+        - imx-dma
+        - imx-sdma
+        - mxs-dma.c
+        - dw_dmac
+        - intel_mid_dma
+        - ste_dma40
+4. Check other subsystems for dma drivers and merge/move to dmaengine
+5. Remove dma_slave_config's dma direction.
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index 235f53bf494e..36144f88d718 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -37,8 +37,8 @@
 
 #define ATC_DEFAULT_CFG         (ATC_FIFOCFG_HALFFIFO)
 #define ATC_DEFAULT_CTRLA       (0)
-#define ATC_DEFAULT_CTRLB       (ATC_SIF(0)     \
-                                |ATC_DIF(1))
+#define ATC_DEFAULT_CTRLB       (ATC_SIF(AT_DMA_MEM_IF) \
+                                |ATC_DIF(AT_DMA_MEM_IF))
 
 /*
  * Initial number of descriptors to allocate for each channel. This could
@@ -165,6 +165,29 @@ static void atc_desc_put(struct at_dma_chan *atchan, struct at_desc *desc)
 }
 
 /**
+ * atc_desc_chain - build chain adding a descripor
+ * @first: address of first descripor of the chain
+ * @prev: address of previous descripor of the chain
+ * @desc: descriptor to queue
+ *
+ * Called from prep_* functions
+ */
+static void atc_desc_chain(struct at_desc **first, struct at_desc **prev,
+                           struct at_desc *desc)
+{
+        if (!(*first)) {
+                *first = desc;
+        } else {
+                /* inform the HW lli about chaining */
+                (*prev)->lli.dscr = desc->txd.phys;
+                /* insert the link descriptor to the LD ring */
+                list_add_tail(&desc->desc_node,
+                                &(*first)->tx_list);
+        }
+        *prev = desc;
+}
+
+/**
  * atc_assign_cookie - compute and assign new cookie
  * @atchan: channel we work on
  * @desc: descriptor to assign cookie for
@@ -237,16 +260,12 @@ static void atc_dostart(struct at_dma_chan *atchan, struct at_desc *first)
 static void
 atc_chain_complete(struct at_dma_chan *atchan, struct at_desc *desc)
 {
-        dma_async_tx_callback           callback;
-        void                            *param;
         struct dma_async_tx_descriptor  *txd = &desc->txd;
 
         dev_vdbg(chan2dev(&atchan->chan_common),
                 "descriptor %u complete\n", txd->cookie);
 
         atchan->completed_cookie = txd->cookie;
-        callback = txd->callback;
-        param = txd->callback_param;
 
         /* move children to free_list */
         list_splice_init(&desc->tx_list, &atchan->free_list);
@@ -278,12 +297,19 @@ atc_chain_complete(struct at_dma_chan *atchan, struct at_desc *desc)
                 }
         }
 
-        /*
-         * The API requires that no submissions are done from a
-         * callback, so we don't need to drop the lock here
-         */
-        if (callback)
-                callback(param);
+        /* for cyclic transfers,
+         * no need to replay callback function while stopping */
+        if (!test_bit(ATC_IS_CYCLIC, &atchan->status)) {
+                dma_async_tx_callback   callback = txd->callback;
+                void                    *param = txd->callback_param;
+
+                /*
+                 * The API requires that no submissions are done from a
+                 * callback, so we don't need to drop the lock here
+                 */
+                if (callback)
+                        callback(param);
+        }
 
         dma_run_dependencies(txd);
 }
@@ -419,6 +445,26 @@ static void atc_handle_error(struct at_dma_chan *atchan)
         atc_chain_complete(atchan, bad_desc);
 }
 
+/**
+ * atc_handle_cyclic - at the end of a period, run callback function
+ * @atchan: channel used for cyclic operations
+ *
+ * Called with atchan->lock held and bh disabled
+ */
+static void atc_handle_cyclic(struct at_dma_chan *atchan)
+{
+        struct at_desc                  *first = atc_first_active(atchan);
+        struct dma_async_tx_descriptor  *txd = &first->txd;
+        dma_async_tx_callback           callback = txd->callback;
+        void                            *param = txd->callback_param;
+
+        dev_vdbg(chan2dev(&atchan->chan_common),
+                        "new cyclic period llp 0x%08x\n",
+                        channel_readl(atchan, DSCR));
+
+        if (callback)
+                callback(param);
+}
 
 /*--  IRQ & Tasklet  ---------------------------------------------------*/
 
@@ -426,16 +472,11 @@ static void atc_tasklet(unsigned long data)
 {
         struct at_dma_chan *atchan = (struct at_dma_chan *)data;
 
-        /* Channel cannot be enabled here */
-        if (atc_chan_is_enabled(atchan)) {
-                dev_err(chan2dev(&atchan->chan_common),
-                        "BUG: channel enabled in tasklet\n");
-                return;
-        }
-
         spin_lock(&atchan->lock);
-        if (test_and_clear_bit(0, &atchan->error_status))
+        if (test_and_clear_bit(ATC_IS_ERROR, &atchan->status))
                 atc_handle_error(atchan);
+        else if (test_bit(ATC_IS_CYCLIC, &atchan->status))
+                atc_handle_cyclic(atchan);
         else
                 atc_advance_work(atchan);
 
@@ -464,12 +505,13 @@ static irqreturn_t at_dma_interrupt(int irq, void *dev_id)
 
                 for (i = 0; i < atdma->dma_common.chancnt; i++) {
                         atchan = &atdma->chan[i];
-                        if (pending & (AT_DMA_CBTC(i) | AT_DMA_ERR(i))) {
+                        if (pending & (AT_DMA_BTC(i) | AT_DMA_ERR(i))) {
                                 if (pending & AT_DMA_ERR(i)) {
                                         /* Disable channel on AHB error */
-                                        dma_writel(atdma, CHDR, atchan->mask);
+                                        dma_writel(atdma, CHDR,
+                                                AT_DMA_RES(i) | atchan->mask);
                                         /* Give information to tasklet */
-                                        set_bit(0, &atchan->error_status);
+                                        set_bit(ATC_IS_ERROR, &atchan->status);
                                 }
                                 tasklet_schedule(&atchan->tasklet);
                                 ret = IRQ_HANDLED;
@@ -549,7 +591,7 @@ atc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
         }
 
         ctrla =   ATC_DEFAULT_CTRLA;
-        ctrlb =   ATC_DEFAULT_CTRLB
+        ctrlb =   ATC_DEFAULT_CTRLB | ATC_IEN
                 | ATC_SRC_ADDR_MODE_INCR
                 | ATC_DST_ADDR_MODE_INCR
                 | ATC_FC_MEM2MEM;
@@ -584,16 +626,7 @@ atc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 
                 desc->txd.cookie = 0;
 
-                if (!first) {
-                        first = desc;
-                } else {
-                        /* inform the HW lli about chaining */
-                        prev->lli.dscr = desc->txd.phys;
-                        /* insert the link descriptor to the LD ring */
-                        list_add_tail(&desc->desc_node,
-                                        &first->tx_list);
-                }
-                prev = desc;
+                atc_desc_chain(&first, &prev, desc);
         }
 
         /* First descriptor of the chain embedds additional information */
@@ -639,7 +672,8 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
         struct scatterlist      *sg;
         size_t                  total_len = 0;
 
-        dev_vdbg(chan2dev(chan), "prep_slave_sg: %s f0x%lx\n",
+        dev_vdbg(chan2dev(chan), "prep_slave_sg (%d): %s f0x%lx\n",
+                        sg_len,
                         direction == DMA_TO_DEVICE ? "TO DEVICE" : "FROM DEVICE",
                         flags);
 
@@ -651,14 +685,15 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
         reg_width = atslave->reg_width;
 
         ctrla = ATC_DEFAULT_CTRLA | atslave->ctrla;
-        ctrlb = ATC_DEFAULT_CTRLB | ATC_IEN;
+        ctrlb = ATC_IEN;
 
         switch (direction) {
         case DMA_TO_DEVICE:
                 ctrla |=  ATC_DST_WIDTH(reg_width);
                 ctrlb |=  ATC_DST_ADDR_MODE_FIXED
                         | ATC_SRC_ADDR_MODE_INCR
-                        | ATC_FC_MEM2PER;
+                        | ATC_FC_MEM2PER
+                        | ATC_SIF(AT_DMA_MEM_IF) | ATC_DIF(AT_DMA_PER_IF);
                 reg = atslave->tx_reg;
                 for_each_sg(sgl, sg, sg_len, i) {
                         struct at_desc  *desc;
@@ -682,16 +717,7 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
                                         | len >> mem_width;
                         desc->lli.ctrlb = ctrlb;
 
-                        if (!first) {
-                                first = desc;
-                        } else {
-                                /* inform the HW lli about chaining */
-                                prev->lli.dscr = desc->txd.phys;
-                                /* insert the link descriptor to the LD ring */
-                                list_add_tail(&desc->desc_node,
-                                                &first->tx_list);
-                        }
-                        prev = desc;
+                        atc_desc_chain(&first, &prev, desc);
                         total_len += len;
                 }
                 break;
@@ -699,7 +725,8 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
                 ctrla |=  ATC_SRC_WIDTH(reg_width);
                 ctrlb |=  ATC_DST_ADDR_MODE_INCR
                         | ATC_SRC_ADDR_MODE_FIXED
-                        | ATC_FC_PER2MEM;
+                        | ATC_FC_PER2MEM
+                        | ATC_SIF(AT_DMA_PER_IF) | ATC_DIF(AT_DMA_MEM_IF);
 
                 reg = atslave->rx_reg;
                 for_each_sg(sgl, sg, sg_len, i) {
@@ -724,16 +751,7 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
                                         | len >> reg_width;
                         desc->lli.ctrlb = ctrlb;
 
-                        if (!first) {
-                                first = desc;
-                        } else {
-                                /* inform the HW lli about chaining */
-                                prev->lli.dscr = desc->txd.phys;
-                                /* insert the link descriptor to the LD ring */
-                                list_add_tail(&desc->desc_node,
-                                                &first->tx_list);
-                        }
-                        prev = desc;
+                        atc_desc_chain(&first, &prev, desc);
                         total_len += len;
                 }
                 break;
@@ -759,41 +777,211 @@ err_desc_get:
         return NULL;
 }
 
+/**
+ * atc_dma_cyclic_check_values
+ * Check for too big/unaligned periods and unaligned DMA buffer
+ */
+static int
+atc_dma_cyclic_check_values(unsigned int reg_width, dma_addr_t buf_addr,
+                size_t period_len, enum dma_data_direction direction)
+{
+        if (period_len > (ATC_BTSIZE_MAX << reg_width))
+                goto err_out;
+        if (unlikely(period_len & ((1 << reg_width) - 1)))
+                goto err_out;
+        if (unlikely(buf_addr & ((1 << reg_width) - 1)))
+                goto err_out;
+        if (unlikely(!(direction & (DMA_TO_DEVICE | DMA_FROM_DEVICE))))
+                goto err_out;
+
+        return 0;
+
+err_out:
+        return -EINVAL;
+}
+
+/**
+ * atc_dma_cyclic_fill_desc - Fill one period decriptor
+ */
+static int
+atc_dma_cyclic_fill_desc(struct at_dma_slave *atslave, struct at_desc *desc,
+                unsigned int period_index, dma_addr_t buf_addr,
+                size_t period_len, enum dma_data_direction direction)
+{
+        u32             ctrla;
+        unsigned int    reg_width = atslave->reg_width;
+
+        /* prepare common CRTLA value */
+        ctrla =   ATC_DEFAULT_CTRLA | atslave->ctrla
+                | ATC_DST_WIDTH(reg_width)
+                | ATC_SRC_WIDTH(reg_width)
+                | period_len >> reg_width;
+
+        switch (direction) {
+        case DMA_TO_DEVICE:
+                desc->lli.saddr = buf_addr + (period_len * period_index);
+                desc->lli.daddr = atslave->tx_reg;
+                desc->lli.ctrla = ctrla;
+                desc->lli.ctrlb = ATC_DST_ADDR_MODE_FIXED
+                                | ATC_SRC_ADDR_MODE_INCR
+                                | ATC_FC_MEM2PER
+                                | ATC_SIF(AT_DMA_MEM_IF)
+                                | ATC_DIF(AT_DMA_PER_IF);
+                break;
+
+        case DMA_FROM_DEVICE:
+                desc->lli.saddr = atslave->rx_reg;
+                desc->lli.daddr = buf_addr + (period_len * period_index);
+                desc->lli.ctrla = ctrla;
+                desc->lli.ctrlb = ATC_DST_ADDR_MODE_INCR
+                                | ATC_SRC_ADDR_MODE_FIXED
+                                | ATC_FC_PER2MEM
+                                | ATC_SIF(AT_DMA_PER_IF)
+                                | ATC_DIF(AT_DMA_MEM_IF);
+                break;
+
+        default:
+                return -EINVAL;
+        }
+
+        return 0;
+}
+
+/**
+ * atc_prep_dma_cyclic - prepare the cyclic DMA transfer
+ * @chan: the DMA channel to prepare
+ * @buf_addr: physical DMA address where the buffer starts
+ * @buf_len: total number of bytes for the entire buffer
+ * @period_len: number of bytes for each period
+ * @direction: transfer direction, to or from device
+ */
+static struct dma_async_tx_descriptor *
+atc_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
+                size_t period_len, enum dma_data_direction direction)
+{
+        struct at_dma_chan      *atchan = to_at_dma_chan(chan);
+        struct at_dma_slave     *atslave = chan->private;
+        struct at_desc          *first = NULL;
+        struct at_desc          *prev = NULL;
+        unsigned long           was_cyclic;
+        unsigned int            periods = buf_len / period_len;
+        unsigned int            i;
+
+        dev_vdbg(chan2dev(chan), "prep_dma_cyclic: %s buf@0x%08x - %d (%d/%d)\n",
+                        direction == DMA_TO_DEVICE ? "TO DEVICE" : "FROM DEVICE",
+                        buf_addr,
+                        periods, buf_len, period_len);
+
+        if (unlikely(!atslave || !buf_len || !period_len)) {
+                dev_dbg(chan2dev(chan), "prep_dma_cyclic: length is zero!\n");
+                return NULL;
+        }
+
+        was_cyclic = test_and_set_bit(ATC_IS_CYCLIC, &atchan->status);
+        if (was_cyclic) {
+                dev_dbg(chan2dev(chan), "prep_dma_cyclic: channel in use!\n");
+                return NULL;
+        }
+
+        /* Check for too big/unaligned periods and unaligned DMA buffer */
+        if (atc_dma_cyclic_check_values(atslave->reg_width, buf_addr,
+                                        period_len, direction))
+                goto err_out;
+
+        /* build cyclic linked list */
+        for (i = 0; i < periods; i++) {
+                struct at_desc  *desc;
+
+                desc = atc_desc_get(atchan);
+                if (!desc)
+                        goto err_desc_get;
+
+                if (atc_dma_cyclic_fill_desc(atslave, desc, i, buf_addr,
+                                                period_len, direction))
+                        goto err_desc_get;
+
+                atc_desc_chain(&first, &prev, desc);
+        }
+
+        /* lets make a cyclic list */
+        prev->lli.dscr = first->txd.phys;
+
+        /* First descriptor of the chain embedds additional information */
+        first->txd.cookie = -EBUSY;
+        first->len = buf_len;
+
+        return &first->txd;
+
+err_desc_get:
+        dev_err(chan2dev(chan), "not enough descriptors available\n");
+        atc_desc_put(atchan, first);
+err_out:
+        clear_bit(ATC_IS_CYCLIC, &atchan->status);
+        return NULL;
+}
+
+
 static int atc_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
                        unsigned long arg)
 {
         struct at_dma_chan      *atchan = to_at_dma_chan(chan);
         struct at_dma           *atdma = to_at_dma(chan->device);
-        struct at_desc          *desc, *_desc;
+        int                     chan_id = atchan->chan_common.chan_id;
+
         LIST_HEAD(list);
 
-        /* Only supports DMA_TERMINATE_ALL */
-        if (cmd != DMA_TERMINATE_ALL)
-                return -ENXIO;
+        dev_vdbg(chan2dev(chan), "atc_control (%d)\n", cmd);
 
-        /*
-         * This is only called when something went wrong elsewhere, so
-         * we don't really care about the data. Just disable the
-         * channel. We still have to poll the channel enable bit due
-         * to AHB/HSB limitations.
-         */
-        spin_lock_bh(&atchan->lock);
+        if (cmd == DMA_PAUSE) {
+                spin_lock_bh(&atchan->lock);
 
-        dma_writel(atdma, CHDR, atchan->mask);
+                dma_writel(atdma, CHER, AT_DMA_SUSP(chan_id));
+                set_bit(ATC_IS_PAUSED, &atchan->status);
 
-        /* confirm that this channel is disabled */
-        while (dma_readl(atdma, CHSR) & atchan->mask)
-                cpu_relax();
+                spin_unlock_bh(&atchan->lock);
+        } else if (cmd == DMA_RESUME) {
+                if (!test_bit(ATC_IS_PAUSED, &atchan->status))
+                        return 0;
 
-        /* active_list entries will end up before queued entries */
-        list_splice_init(&atchan->queue, &list);
-        list_splice_init(&atchan->active_list, &list);
+                spin_lock_bh(&atchan->lock);
 
-        /* Flush all pending and queued descriptors */
-        list_for_each_entry_safe(desc, _desc, &list, desc_node)
-                atc_chain_complete(atchan, desc);
+                dma_writel(atdma, CHDR, AT_DMA_RES(chan_id));
+                clear_bit(ATC_IS_PAUSED, &atchan->status);
 
-        spin_unlock_bh(&atchan->lock);
+                spin_unlock_bh(&atchan->lock);
+        } else if (cmd == DMA_TERMINATE_ALL) {
+                struct at_desc  *desc, *_desc;
+                /*
+                 * This is only called when something went wrong elsewhere, so
+                 * we don't really care about the data. Just disable the
+                 * channel. We still have to poll the channel enable bit due
+                 * to AHB/HSB limitations.
+                 */
+                spin_lock_bh(&atchan->lock);
+
+                /* disabling channel: must also remove suspend state */
+                dma_writel(atdma, CHDR, AT_DMA_RES(chan_id) | atchan->mask);
+
+                /* confirm that this channel is disabled */
+                while (dma_readl(atdma, CHSR) & atchan->mask)
+                        cpu_relax();
+
+                /* active_list entries will end up before queued entries */
+                list_splice_init(&atchan->queue, &list);
+                list_splice_init(&atchan->active_list, &list);
+
+                /* Flush all pending and queued descriptors */
+                list_for_each_entry_safe(desc, _desc, &list, desc_node)
+                        atc_chain_complete(atchan, desc);
+
+                clear_bit(ATC_IS_PAUSED, &atchan->status);
+                /* if channel dedicated to cyclic operations, free it */
+                clear_bit(ATC_IS_CYCLIC, &atchan->status);
+
+                spin_unlock_bh(&atchan->lock);
+        } else {
+                return -ENXIO;
+        }
 
         return 0;
 }
@@ -835,9 +1023,17 @@ atc_tx_status(struct dma_chan *chan,
 
         spin_unlock_bh(&atchan->lock);
 
-        dma_set_tx_state(txstate, last_complete, last_used, 0);
-        dev_vdbg(chan2dev(chan), "tx_status: %d (d%d, u%d)\n",
-                 cookie, last_complete ? last_complete : 0,
+        if (ret != DMA_SUCCESS)
+                dma_set_tx_state(txstate, last_complete, last_used,
+                        atc_first_active(atchan)->len);
+        else
+                dma_set_tx_state(txstate, last_complete, last_used, 0);
+
+        if (test_bit(ATC_IS_PAUSED, &atchan->status))
+                ret = DMA_PAUSED;
+
+        dev_vdbg(chan2dev(chan), "tx_status %d: cookie = %d (d%d, u%d)\n",
+                 ret, cookie, last_complete ? last_complete : 0,
                  last_used ? last_used : 0);
 
         return ret;
@@ -853,6 +1049,10 @@ static void atc_issue_pending(struct dma_chan *chan)
 
         dev_vdbg(chan2dev(chan), "issue_pending\n");
 
+        /* Not needed for cyclic transfers */
+        if (test_bit(ATC_IS_CYCLIC, &atchan->status))
+                return;
+
         spin_lock_bh(&atchan->lock);
         if (!atc_chan_is_enabled(atchan)) {
                 atc_advance_work(atchan);
@@ -959,6 +1159,7 @@ static void atc_free_chan_resources(struct dma_chan *chan)
         }
         list_splice_init(&atchan->free_list, &list);
         atchan->descs_allocated = 0;
+        atchan->status = 0;
 
         dev_vdbg(chan2dev(chan), "free_chan_resources: done\n");
 }
@@ -1092,10 +1293,15 @@ static int __init at_dma_probe(struct platform_device *pdev)
         if (dma_has_cap(DMA_MEMCPY, atdma->dma_common.cap_mask))
                 atdma->dma_common.device_prep_dma_memcpy = atc_prep_dma_memcpy;
 
-        if (dma_has_cap(DMA_SLAVE, atdma->dma_common.cap_mask)) {
+        if (dma_has_cap(DMA_SLAVE, atdma->dma_common.cap_mask))
                 atdma->dma_common.device_prep_slave_sg = atc_prep_slave_sg;
+
+        if (dma_has_cap(DMA_CYCLIC, atdma->dma_common.cap_mask))
+                atdma->dma_common.device_prep_dma_cyclic = atc_prep_dma_cyclic;
+
+        if (dma_has_cap(DMA_SLAVE, atdma->dma_common.cap_mask) ||
+            dma_has_cap(DMA_CYCLIC, atdma->dma_common.cap_mask))
                 atdma->dma_common.device_control = atc_control;
-        }
 
         dma_writel(atdma, EN, AT_DMA_ENABLE);
 
diff --git a/drivers/dma/at_hdmac_regs.h b/drivers/dma/at_hdmac_regs.h
index 495457e3dc4b..087dbf1dd39c 100644
--- a/drivers/dma/at_hdmac_regs.h
+++ b/drivers/dma/at_hdmac_regs.h
@@ -103,6 +103,10 @@
 /* Bitfields in CTRLB */
 #define ATC_SIF(i)              (0x3 & (i))     /* Src tx done via AHB-Lite Interface i */
 #define ATC_DIF(i)              ((0x3 & (i)) <<  4)     /* Dst tx done via AHB-Lite Interface i */
+                                  /* Specify AHB interfaces */
+#define AT_DMA_MEM_IF           0 /* interface 0 as memory interface */
+#define AT_DMA_PER_IF           1 /* interface 1 as peripheral interface */
+
 #define ATC_SRC_PIP             (0x1 <<  8)     /* Source Picture-in-Picture enabled */
 #define ATC_DST_PIP             (0x1 << 12)     /* Destination Picture-in-Picture enabled */
 #define ATC_SRC_DSCR_DIS        (0x1 << 16)     /* Src Descriptor fetch disable */
@@ -181,12 +185,23 @@ txd_to_at_desc(struct dma_async_tx_descriptor *txd)
 /*--  Channels  --------------------------------------------------------*/
 
 /**
+ * atc_status - information bits stored in channel status flag
+ *
+ * Manipulated with atomic operations.
+ */
+enum atc_status {
+        ATC_IS_ERROR = 0,
+        ATC_IS_PAUSED = 1,
+        ATC_IS_CYCLIC = 24,
+};
+
+/**
  * struct at_dma_chan - internal representation of an Atmel HDMAC channel
  * @chan_common: common dmaengine channel object members
  * @device: parent device
  * @ch_regs: memory mapped register base
  * @mask: channel index in a mask
- * @error_status: transmit error status information from irq handler
+ * @status: transmit status information from irq/prep* functions
  *                to tasklet (use atomic operations)
  * @tasklet: bottom half to finish transaction work
  * @lock: serializes enqueue/dequeue operations to descriptors lists
@@ -201,7 +216,7 @@ struct at_dma_chan {
         struct at_dma           *device;
         void __iomem            *ch_regs;
         u8                      mask;
-        unsigned long           error_status;
+        unsigned long           status;
         struct tasklet_struct   tasklet;
 
         spinlock_t              lock;
@@ -309,8 +324,8 @@ static void atc_setup_irq(struct at_dma_chan *atchan, int on)
         struct at_dma   *atdma = to_at_dma(atchan->chan_common.device);
         u32             ebci;
 
-        /* enable interrupts on buffer chain completion & error */
-        ebci =    AT_DMA_CBTC(atchan->chan_common.chan_id)
+        /* enable interrupts on buffer transfer completion & error */
+        ebci =    AT_DMA_BTC(atchan->chan_common.chan_id)
                 | AT_DMA_ERR(atchan->chan_common.chan_id);
         if (on)
                 dma_writel(atdma, EBCIER, ebci);
@@ -347,7 +362,12 @@ static inline int atc_chan_is_enabled(struct at_dma_chan *atchan)
  */
 static void set_desc_eol(struct at_desc *desc)
 {
-        desc->lli.ctrlb |= ATC_SRC_DSCR_DIS | ATC_DST_DSCR_DIS;
+        u32 ctrlb = desc->lli.ctrlb;
+
+        ctrlb &= ~ATC_IEN;
+        ctrlb |= ATC_SRC_DSCR_DIS | ATC_DST_DSCR_DIS;
+
+        desc->lli.ctrlb = ctrlb;
         desc->lli.dscr = 0;
 }
 
diff --git a/drivers/dma/coh901318.c b/drivers/dma/coh901318.c
index f48e54006518..af8c0b5ed70f 100644
--- a/drivers/dma/coh901318.c
+++ b/drivers/dma/coh901318.c
@@ -1610,7 +1610,7 @@ int __init coh901318_init(void)
 {
         return platform_driver_probe(&coh901318_driver, coh901318_probe);
 }
-arch_initcall(coh901318_init);
+subsys_initcall(coh901318_init);
 
 void __exit coh901318_exit(void)
 {
diff --git a/drivers/dma/dw_dmac.c b/drivers/dma/dw_dmac.c
index 2a2e2fa00e91..4d180ca9a1d8 100644
--- a/drivers/dma/dw_dmac.c
+++ b/drivers/dma/dw_dmac.c
@@ -3,6 +3,7 @@
  * AVR32 systems.)
  *
  * Copyright (C) 2007-2008 Atmel Corporation
+ * Copyright (C) 2010-2011 ST Microelectronics
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -93,8 +94,9 @@ static struct dw_desc *dwc_desc_get(struct dw_dma_chan *dwc)
         struct dw_desc *desc, *_desc;
         struct dw_desc *ret = NULL;
         unsigned int i = 0;
+        unsigned long flags;
 
-        spin_lock_bh(&dwc->lock);
+        spin_lock_irqsave(&dwc->lock, flags);
         list_for_each_entry_safe(desc, _desc, &dwc->free_list, desc_node) {
                 if (async_tx_test_ack(&desc->txd)) {
                         list_del(&desc->desc_node);
@@ -104,7 +106,7 @@ static struct dw_desc *dwc_desc_get(struct dw_dma_chan *dwc)
                 dev_dbg(chan2dev(&dwc->chan), "desc %p not ACKed\n", desc);
                 i++;
         }
-        spin_unlock_bh(&dwc->lock);
+        spin_unlock_irqrestore(&dwc->lock, flags);
 
         dev_vdbg(chan2dev(&dwc->chan), "scanned %u descriptors on freelist\n", i);
 
@@ -130,12 +132,14 @@ static void dwc_sync_desc_for_cpu(struct dw_dma_chan *dwc, struct dw_desc *desc)
  */
 static void dwc_desc_put(struct dw_dma_chan *dwc, struct dw_desc *desc)
 {
+        unsigned long flags;
+
         if (desc) {
                 struct dw_desc *child;
 
                 dwc_sync_desc_for_cpu(dwc, desc);
 
-                spin_lock_bh(&dwc->lock);
+                spin_lock_irqsave(&dwc->lock, flags);
                 list_for_each_entry(child, &desc->tx_list, desc_node)
                         dev_vdbg(chan2dev(&dwc->chan),
                                         "moving child desc %p to freelist\n",
@@ -143,7 +147,7 @@ static void dwc_desc_put(struct dw_dma_chan *dwc, struct dw_desc *desc)
                 list_splice_init(&desc->tx_list, &dwc->free_list);
                 dev_vdbg(chan2dev(&dwc->chan), "moving desc %p to freelist\n", desc);
                 list_add(&desc->desc_node, &dwc->free_list);
-                spin_unlock_bh(&dwc->lock);
+                spin_unlock_irqrestore(&dwc->lock, flags);
         }
 }
 
@@ -195,18 +199,23 @@ static void dwc_dostart(struct dw_dma_chan *dwc, struct dw_desc *first)
 /*----------------------------------------------------------------------*/
 
 static void
-dwc_descriptor_complete(struct dw_dma_chan *dwc, struct dw_desc *desc)
+dwc_descriptor_complete(struct dw_dma_chan *dwc, struct dw_desc *desc,
+                bool callback_required)
 {
-        dma_async_tx_callback           callback;
-        void                            *param;
+        dma_async_tx_callback           callback = NULL;
+        void                            *param = NULL;
         struct dma_async_tx_descriptor  *txd = &desc->txd;
         struct dw_desc                  *child;
+        unsigned long                   flags;
 
         dev_vdbg(chan2dev(&dwc->chan), "descriptor %u complete\n", txd->cookie);
 
+        spin_lock_irqsave(&dwc->lock, flags);
         dwc->completed = txd->cookie;
-        callback = txd->callback;
-        param = txd->callback_param;
+        if (callback_required) {
+                callback = txd->callback;
+                param = txd->callback_param;
+        }
 
         dwc_sync_desc_for_cpu(dwc, desc);
 
@@ -238,11 +247,9 @@ dwc_descriptor_complete(struct dw_dma_chan *dwc, struct dw_desc *desc)
                 }
         }
 
-        /*
-         * The API requires that no submissions are done from a
-         * callback, so we don't need to drop the lock here
-         */
-        if (callback)
+        spin_unlock_irqrestore(&dwc->lock, flags);
+
+        if (callback_required && callback)
                 callback(param);
 }
 
@@ -250,7 +257,9 @@ static void dwc_complete_all(struct dw_dma *dw, struct dw_dma_chan *dwc)
 {
         struct dw_desc *desc, *_desc;
         LIST_HEAD(list);
+        unsigned long flags;
 
+        spin_lock_irqsave(&dwc->lock, flags);
         if (dma_readl(dw, CH_EN) & dwc->mask) {
                 dev_err(chan2dev(&dwc->chan),
                         "BUG: XFER bit set, but channel not idle!\n");
@@ -271,8 +280,10 @@ static void dwc_complete_all(struct dw_dma *dw, struct dw_dma_chan *dwc)
                 dwc_dostart(dwc, dwc_first_active(dwc));
         }
 
+        spin_unlock_irqrestore(&dwc->lock, flags);
+
         list_for_each_entry_safe(desc, _desc, &list, desc_node)
-                dwc_descriptor_complete(dwc, desc);
+                dwc_descriptor_complete(dwc, desc, true);
 }
 
 static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
@@ -281,7 +292,9 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
         struct dw_desc *desc, *_desc;
         struct dw_desc *child;
         u32 status_xfer;
+        unsigned long flags;
 
+        spin_lock_irqsave(&dwc->lock, flags);
         /*
          * Clear block interrupt flag before scanning so that we don't
          * miss any, and read LLP before RAW_XFER to ensure it is
@@ -294,30 +307,47 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
         if (status_xfer & dwc->mask) {
                 /* Everything we've submitted is done */
                 dma_writel(dw, CLEAR.XFER, dwc->mask);
+                spin_unlock_irqrestore(&dwc->lock, flags);
+
                 dwc_complete_all(dw, dwc);
                 return;
         }
 
-        if (list_empty(&dwc->active_list))
+        if (list_empty(&dwc->active_list)) {
+                spin_unlock_irqrestore(&dwc->lock, flags);
                 return;
+        }
 
         dev_vdbg(chan2dev(&dwc->chan), "scan_descriptors: llp=0x%x\n", llp);
 
         list_for_each_entry_safe(desc, _desc, &dwc->active_list, desc_node) {
-                if (desc->lli.llp == llp)
+                /* check first descriptors addr */
+                if (desc->txd.phys == llp) {
+                        spin_unlock_irqrestore(&dwc->lock, flags);
+                        return;
+                }
+
+                /* check first descriptors llp */
+                if (desc->lli.llp == llp) {
                         /* This one is currently in progress */
+                        spin_unlock_irqrestore(&dwc->lock, flags);
                         return;
+                }
 
                 list_for_each_entry(child, &desc->tx_list, desc_node)
-                        if (child->lli.llp == llp)
+                        if (child->lli.llp == llp) {
                                 /* Currently in progress */
+                                spin_unlock_irqrestore(&dwc->lock, flags);
                                 return;
+                        }
 
                 /*
                  * No descriptors so far seem to be in progress, i.e.
                  * this one must be done.
                  */
-                dwc_descriptor_complete(dwc, desc);
+                spin_unlock_irqrestore(&dwc->lock, flags);
+                dwc_descriptor_complete(dwc, desc, true);
+                spin_lock_irqsave(&dwc->lock, flags);
         }
 
         dev_err(chan2dev(&dwc->chan),
@@ -332,6 +362,7 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
                 list_move(dwc->queue.next, &dwc->active_list);
                 dwc_dostart(dwc, dwc_first_active(dwc));
         }
+        spin_unlock_irqrestore(&dwc->lock, flags);
 }
 
 static void dwc_dump_lli(struct dw_dma_chan *dwc, struct dw_lli *lli)
@@ -346,9 +377,12 @@ static void dwc_handle_error(struct dw_dma *dw, struct dw_dma_chan *dwc)
 {
         struct dw_desc *bad_desc;
         struct dw_desc *child;
+        unsigned long flags;
 
         dwc_scan_descriptors(dw, dwc);
 
+        spin_lock_irqsave(&dwc->lock, flags);
+
         /*
          * The descriptor currently at the head of the active list is
          * borked. Since we don't have any way to report errors, we'll
@@ -378,8 +412,10 @@ static void dwc_handle_error(struct dw_dma *dw, struct dw_dma_chan *dwc)
         list_for_each_entry(child, &bad_desc->tx_list, desc_node)
                 dwc_dump_lli(dwc, &child->lli);
 
+        spin_unlock_irqrestore(&dwc->lock, flags);
+
         /* Pretend the descriptor completed successfully */
-        dwc_descriptor_complete(dwc, bad_desc);
+        dwc_descriptor_complete(dwc, bad_desc, true);
 }
 
 /* --------------------- Cyclic DMA API extensions -------------------- */
@@ -402,6 +438,8 @@ EXPORT_SYMBOL(dw_dma_get_dst_addr);
 static void dwc_handle_cyclic(struct dw_dma *dw, struct dw_dma_chan *dwc,
                 u32 status_block, u32 status_err, u32 status_xfer)
 {
+        unsigned long flags;
+
         if (status_block & dwc->mask) {
                 void (*callback)(void *param);
                 void *callback_param;
@@ -412,11 +450,9 @@ static void dwc_handle_cyclic(struct dw_dma *dw, struct dw_dma_chan *dwc,
 
                 callback = dwc->cdesc->period_callback;
                 callback_param = dwc->cdesc->period_callback_param;
-                if (callback) {
-                        spin_unlock(&dwc->lock);
+
+                if (callback)
                         callback(callback_param);
-                        spin_lock(&dwc->lock);
-                }
         }
 
         /*
@@ -430,6 +466,9 @@ static void dwc_handle_cyclic(struct dw_dma *dw, struct dw_dma_chan *dwc,
                 dev_err(chan2dev(&dwc->chan), "cyclic DMA unexpected %s "
                                 "interrupt, stopping DMA transfer\n",
                                 status_xfer ? "xfer" : "error");
+
+                spin_lock_irqsave(&dwc->lock, flags);
+
                 dev_err(chan2dev(&dwc->chan),
                         "  SAR: 0x%x DAR: 0x%x LLP: 0x%x CTL: 0x%x:%08x\n",
                         channel_readl(dwc, SAR),
@@ -453,6 +492,8 @@ static void dwc_handle_cyclic(struct dw_dma *dw, struct dw_dma_chan *dwc,
 
                 for (i = 0; i < dwc->cdesc->periods; i++)
                         dwc_dump_lli(dwc, &dwc->cdesc->desc[i]->lli);
+
+                spin_unlock_irqrestore(&dwc->lock, flags);
         }
 }
 
@@ -476,7 +517,6 @@ static void dw_dma_tasklet(unsigned long data)
 
         for (i = 0; i < dw->dma.chancnt; i++) {
                 dwc = &dw->chan[i];
-                spin_lock(&dwc->lock);
                 if (test_bit(DW_DMA_IS_CYCLIC, &dwc->flags))
                         dwc_handle_cyclic(dw, dwc, status_block, status_err,
                                         status_xfer);
@@ -484,7 +524,6 @@ static void dw_dma_tasklet(unsigned long data)
                         dwc_handle_error(dw, dwc);
                 else if ((status_block | status_xfer) & (1 << i))
                         dwc_scan_descriptors(dw, dwc);
-                spin_unlock(&dwc->lock);
         }
 
         /*
@@ -539,8 +578,9 @@ static dma_cookie_t dwc_tx_submit(struct dma_async_tx_descriptor *tx)
         struct dw_desc          *desc = txd_to_dw_desc(tx);
         struct dw_dma_chan      *dwc = to_dw_dma_chan(tx->chan);
         dma_cookie_t            cookie;
+        unsigned long           flags;
 
-        spin_lock_bh(&dwc->lock);
+        spin_lock_irqsave(&dwc->lock, flags);
         cookie = dwc_assign_cookie(dwc, desc);
 
         /*
@@ -560,7 +600,7 @@ static dma_cookie_t dwc_tx_submit(struct dma_async_tx_descriptor *tx)
                 list_add_tail(&desc->desc_node, &dwc->queue);
         }
 
-        spin_unlock_bh(&dwc->lock);
+        spin_unlock_irqrestore(&dwc->lock, flags);
 
         return cookie;
 }
@@ -689,9 +729,15 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
                 reg = dws->tx_reg;
                 for_each_sg(sgl, sg, sg_len, i) {
                         struct dw_desc  *desc;
-                        u32             len;
-                        u32             mem;
+                        u32             len, dlen, mem;
+
+                        mem = sg_phys(sg);
+                        len = sg_dma_len(sg);
+                        mem_width = 2;
+                        if (unlikely(mem & 3 || len & 3))
+                                mem_width = 0;
 
+slave_sg_todev_fill_desc:
                         desc = dwc_desc_get(dwc);
                         if (!desc) {
                                 dev_err(chan2dev(chan),
@@ -699,16 +745,19 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
                                 goto err_desc_get;
                         }
 
-                        mem = sg_phys(sg);
-                        len = sg_dma_len(sg);
-                        mem_width = 2;
-                        if (unlikely(mem & 3 || len & 3))
-                                mem_width = 0;
-
                         desc->lli.sar = mem;
                         desc->lli.dar = reg;
                         desc->lli.ctllo = ctllo | DWC_CTLL_SRC_WIDTH(mem_width);
-                        desc->lli.ctlhi = len >> mem_width;
+                        if ((len >> mem_width) > DWC_MAX_COUNT) {
+                                dlen = DWC_MAX_COUNT << mem_width;
+                                mem += dlen;
+                                len -= dlen;
+                        } else {
+                                dlen = len;
+                                len = 0;
+                        }
+
+                        desc->lli.ctlhi = dlen >> mem_width;
 
                         if (!first) {
                                 first = desc;
@@ -722,7 +771,10 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
                                                 &first->tx_list);
                         }
                         prev = desc;
-                        total_len += len;
+                        total_len += dlen;
+
+                        if (len)
+                                goto slave_sg_todev_fill_desc;
                 }
                 break;
         case DMA_FROM_DEVICE:
@@ -735,15 +787,7 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
                 reg = dws->rx_reg;
                 for_each_sg(sgl, sg, sg_len, i) {
                         struct dw_desc  *desc;
-                        u32             len;
-                        u32             mem;
-
-                        desc = dwc_desc_get(dwc);
-                        if (!desc) {
-                                dev_err(chan2dev(chan),
-                                        "not enough descriptors available\n");
-                                goto err_desc_get;
-                        }
+                        u32             len, dlen, mem;
 
                         mem = sg_phys(sg);
                         len = sg_dma_len(sg);
@@ -751,10 +795,26 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
                         if (unlikely(mem & 3 || len & 3))
                                 mem_width = 0;
 
+slave_sg_fromdev_fill_desc:
+                        desc = dwc_desc_get(dwc);
+                        if (!desc) {
+                                dev_err(chan2dev(chan),
+                                                "not enough descriptors available\n");
+                                goto err_desc_get;
+                        }
+
                         desc->lli.sar = reg;
                         desc->lli.dar = mem;
                         desc->lli.ctllo = ctllo | DWC_CTLL_DST_WIDTH(mem_width);
-                        desc->lli.ctlhi = len >> reg_width;
+                        if ((len >> reg_width) > DWC_MAX_COUNT) {
+                                dlen = DWC_MAX_COUNT << reg_width;
+                                mem += dlen;
+                                len -= dlen;
+                        } else {
+                                dlen = len;
+                                len = 0;
+                        }
+                        desc->lli.ctlhi = dlen >> reg_width;
 
                         if (!first) {
                                 first = desc;
@@ -768,7 +828,10 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
                                                 &first->tx_list);
                         }
                         prev = desc;
-                        total_len += len;
+                        total_len += dlen;
+
+                        if (len)
+                                goto slave_sg_fromdev_fill_desc;
                 }
                 break;
         default:
@@ -799,34 +862,51 @@ static int dwc_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
         struct dw_dma_chan      *dwc = to_dw_dma_chan(chan);
         struct dw_dma           *dw = to_dw_dma(chan->device);
         struct dw_desc          *desc, *_desc;
+        unsigned long           flags;
+        u32                     cfglo;
         LIST_HEAD(list);
 
-        /* Only supports DMA_TERMINATE_ALL */
-        if (cmd != DMA_TERMINATE_ALL)
-                return -ENXIO;
+        if (cmd == DMA_PAUSE) {
+                spin_lock_irqsave(&dwc->lock, flags);
 
-        /*
-         * This is only called when something went wrong elsewhere, so
-         * we don't really care about the data. Just disable the
-         * channel. We still have to poll the channel enable bit due
-         * to AHB/HSB limitations.
-         */
-        spin_lock_bh(&dwc->lock);
+                cfglo = channel_readl(dwc, CFG_LO);
+                channel_writel(dwc, CFG_LO, cfglo | DWC_CFGL_CH_SUSP);
+                while (!(channel_readl(dwc, CFG_LO) & DWC_CFGL_FIFO_EMPTY))
+                        cpu_relax();
 
-        channel_clear_bit(dw, CH_EN, dwc->mask);
+                dwc->paused = true;
+                spin_unlock_irqrestore(&dwc->lock, flags);
+        } else if (cmd == DMA_RESUME) {
+                if (!dwc->paused)
+                        return 0;
 
-        while (dma_readl(dw, CH_EN) & dwc->mask)
-                cpu_relax();
+                spin_lock_irqsave(&dwc->lock, flags);
 
-        /* active_list entries will end up before queued entries */
-        list_splice_init(&dwc->queue, &list);
-        list_splice_init(&dwc->active_list, &list);
+                cfglo = channel_readl(dwc, CFG_LO);
+                channel_writel(dwc, CFG_LO, cfglo & ~DWC_CFGL_CH_SUSP);
+                dwc->paused = false;
 
-        spin_unlock_bh(&dwc->lock);
+                spin_unlock_irqrestore(&dwc->lock, flags);
+        } else if (cmd == DMA_TERMINATE_ALL) {
+                spin_lock_irqsave(&dwc->lock, flags);
 
-        /* Flush all pending and queued descriptors */
-        list_for_each_entry_safe(desc, _desc, &list, desc_node)
-                dwc_descriptor_complete(dwc, desc);
+                channel_clear_bit(dw, CH_EN, dwc->mask);
+                while (dma_readl(dw, CH_EN) & dwc->mask)
+                        cpu_relax();
+
+                dwc->paused = false;
+
+                /* active_list entries will end up before queued entries */
+                list_splice_init(&dwc->queue, &list);
+                list_splice_init(&dwc->active_list, &list);
+
+                spin_unlock_irqrestore(&dwc->lock, flags);
+
+                /* Flush all pending and queued descriptors */
+                list_for_each_entry_safe(desc, _desc, &list, desc_node)
+                        dwc_descriptor_complete(dwc, desc, false);
+        } else
+                return -ENXIO;
 
         return 0;
 }
@@ -846,9 +926,7 @@ dwc_tx_status(struct dma_chan *chan,
 
         ret = dma_async_is_complete(cookie, last_complete, last_used);
         if (ret != DMA_SUCCESS) {
-                spin_lock_bh(&dwc->lock);
                 dwc_scan_descriptors(to_dw_dma(chan->device), dwc);
-                spin_unlock_bh(&dwc->lock);
 
                 last_complete = dwc->completed;
                 last_used = chan->cookie;
@@ -856,7 +934,14 @@ dwc_tx_status(struct dma_chan *chan,
                 ret = dma_async_is_complete(cookie, last_complete, last_used);
         }
 
-        dma_set_tx_state(txstate, last_complete, last_used, 0);
+        if (ret != DMA_SUCCESS)
+                dma_set_tx_state(txstate, last_complete, last_used,
+                                dwc_first_active(dwc)->len);
+        else
+                dma_set_tx_state(txstate, last_complete, last_used, 0);
+
+        if (dwc->paused)
+                return DMA_PAUSED;
 
         return ret;
 }
@@ -865,10 +950,8 @@ static void dwc_issue_pending(struct dma_chan *chan)
 {
         struct dw_dma_chan      *dwc = to_dw_dma_chan(chan);
 
-        spin_lock_bh(&dwc->lock);
         if (!list_empty(&dwc->queue))
                 dwc_scan_descriptors(to_dw_dma(chan->device), dwc);
-        spin_unlock_bh(&dwc->lock);
 }
 
 static int dwc_alloc_chan_resources(struct dma_chan *chan)
@@ -880,6 +963,7 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan)
         int                     i;
         u32                     cfghi;
         u32                     cfglo;
+        unsigned long           flags;
 
         dev_vdbg(chan2dev(chan), "alloc_chan_resources\n");
 
@@ -917,16 +1001,16 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan)
          * doesn't mean what you think it means), and status writeback.
          */
 
-        spin_lock_bh(&dwc->lock);
+        spin_lock_irqsave(&dwc->lock, flags);
         i = dwc->descs_allocated;
         while (dwc->descs_allocated < NR_DESCS_PER_CHANNEL) {
-                spin_unlock_bh(&dwc->lock);
+                spin_unlock_irqrestore(&dwc->lock, flags);
 
                 desc = kzalloc(sizeof(struct dw_desc), GFP_KERNEL);
                 if (!desc) {
                         dev_info(chan2dev(chan),
                                 "only allocated %d descriptors\n", i);
-                        spin_lock_bh(&dwc->lock);
+                        spin_lock_irqsave(&dwc->lock, flags);
                         break;
                 }
 
@@ -938,7 +1022,7 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan)
                                 sizeof(desc->lli), DMA_TO_DEVICE);
                 dwc_desc_put(dwc, desc);
 
-                spin_lock_bh(&dwc->lock);
+                spin_lock_irqsave(&dwc->lock, flags);
                 i = ++dwc->descs_allocated;
         }
 
@@ -947,7 +1031,7 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan)
         channel_set_bit(dw, MASK.BLOCK, dwc->mask);
         channel_set_bit(dw, MASK.ERROR, dwc->mask);
 
-        spin_unlock_bh(&dwc->lock);
+        spin_unlock_irqrestore(&dwc->lock, flags);
 
         dev_dbg(chan2dev(chan),
                 "alloc_chan_resources allocated %d descriptors\n", i);
@@ -960,6 +1044,7 @@ static void dwc_free_chan_resources(struct dma_chan *chan)
         struct dw_dma_chan      *dwc = to_dw_dma_chan(chan);
         struct dw_dma           *dw = to_dw_dma(chan->device);
         struct dw_desc          *desc, *_desc;
+        unsigned long           flags;
         LIST_HEAD(list);
 
         dev_dbg(chan2dev(chan), "free_chan_resources (descs allocated=%u)\n",
@@ -970,7 +1055,7 @@ static void dwc_free_chan_resources(struct dma_chan *chan)
         BUG_ON(!list_empty(&dwc->queue));
         BUG_ON(dma_readl(to_dw_dma(chan->device), CH_EN) & dwc->mask);
 
-        spin_lock_bh(&dwc->lock);
+        spin_lock_irqsave(&dwc->lock, flags);
         list_splice_init(&dwc->free_list, &list);
         dwc->descs_allocated = 0;
 
@@ -979,7 +1064,7 @@ static void dwc_free_chan_resources(struct dma_chan *chan)
         channel_clear_bit(dw, MASK.BLOCK, dwc->mask);
         channel_clear_bit(dw, MASK.ERROR, dwc->mask);
 
-        spin_unlock_bh(&dwc->lock);
+        spin_unlock_irqrestore(&dwc->lock, flags);
 
         list_for_each_entry_safe(desc, _desc, &list, desc_node) {
                 dev_vdbg(chan2dev(chan), "  freeing descriptor %p\n", desc);
@@ -1004,13 +1089,14 @@ int dw_dma_cyclic_start(struct dma_chan *chan)
 {
         struct dw_dma_chan      *dwc = to_dw_dma_chan(chan);
         struct dw_dma           *dw = to_dw_dma(dwc->chan.device);
+        unsigned long           flags;
 
         if (!test_bit(DW_DMA_IS_CYCLIC, &dwc->flags)) {
                 dev_err(chan2dev(&dwc->chan), "missing prep for cyclic DMA\n");
                 return -ENODEV;
         }
 
-        spin_lock(&dwc->lock);
+        spin_lock_irqsave(&dwc->lock, flags);
 
         /* assert channel is idle */
         if (dma_readl(dw, CH_EN) & dwc->mask) {
@@ -1023,7 +1109,7 @@ int dw_dma_cyclic_start(struct dma_chan *chan)
                         channel_readl(dwc, LLP),
                         channel_readl(dwc, CTL_HI),
                         channel_readl(dwc, CTL_LO));
-                spin_unlock(&dwc->lock);
+                spin_unlock_irqrestore(&dwc->lock, flags);
                 return -EBUSY;
         }
 
@@ -1038,7 +1124,7 @@ int dw_dma_cyclic_start(struct dma_chan *chan)
 
         channel_set_bit(dw, CH_EN, dwc->mask);
 
-        spin_unlock(&dwc->lock);
+        spin_unlock_irqrestore(&dwc->lock, flags);
 
         return 0;
 }
@@ -1054,14 +1140,15 @@ void dw_dma_cyclic_stop(struct dma_chan *chan)
 {
         struct dw_dma_chan      *dwc = to_dw_dma_chan(chan);
         struct dw_dma           *dw = to_dw_dma(dwc->chan.device);
+        unsigned long           flags;
 
-        spin_lock(&dwc->lock);
+        spin_lock_irqsave(&dwc->lock, flags);
 
         channel_clear_bit(dw, CH_EN, dwc->mask);
         while (dma_readl(dw, CH_EN) & dwc->mask)
                 cpu_relax();
 
-        spin_unlock(&dwc->lock);
+        spin_unlock_irqrestore(&dwc->lock, flags);
 }
 EXPORT_SYMBOL(dw_dma_cyclic_stop);
 
@@ -1090,17 +1177,18 @@ struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan,
         unsigned int                    reg_width;
         unsigned int                    periods;
         unsigned int                    i;
+        unsigned long                   flags;
 
-        spin_lock_bh(&dwc->lock);
+        spin_lock_irqsave(&dwc->lock, flags);
         if (!list_empty(&dwc->queue) || !list_empty(&dwc->active_list)) {
-                spin_unlock_bh(&dwc->lock);
+                spin_unlock_irqrestore(&dwc->lock, flags);
                 dev_dbg(chan2dev(&dwc->chan),
                                 "queue and/or active list are not empty\n");
                 return ERR_PTR(-EBUSY);
         }
 
         was_cyclic = test_and_set_bit(DW_DMA_IS_CYCLIC, &dwc->flags);
-        spin_unlock_bh(&dwc->lock);
+        spin_unlock_irqrestore(&dwc->lock, flags);
         if (was_cyclic) {
                 dev_dbg(chan2dev(&dwc->chan),
                                 "channel already prepared for cyclic DMA\n");
@@ -1214,13 +1302,14 @@ void dw_dma_cyclic_free(struct dma_chan *chan)
         struct dw_dma           *dw = to_dw_dma(dwc->chan.device);
         struct dw_cyclic_desc   *cdesc = dwc->cdesc;
         int                     i;
+        unsigned long           flags;
 
         dev_dbg(chan2dev(&dwc->chan), "cyclic free\n");
 
         if (!cdesc)
                 return;
 
-        spin_lock_bh(&dwc->lock);
+        spin_lock_irqsave(&dwc->lock, flags);
 
         channel_clear_bit(dw, CH_EN, dwc->mask);
         while (dma_readl(dw, CH_EN) & dwc->mask)
@@ -1230,7 +1319,7 @@ void dw_dma_cyclic_free(struct dma_chan *chan)
         dma_writel(dw, CLEAR.ERROR, dwc->mask);
         dma_writel(dw, CLEAR.XFER, dwc->mask);
 
-        spin_unlock_bh(&dwc->lock);
+        spin_unlock_irqrestore(&dwc->lock, flags);
 
         for (i = 0; i < cdesc->periods; i++)
                 dwc_desc_put(dwc, cdesc->desc[i]);
@@ -1487,3 +1576,4 @@ module_exit(dw_exit);
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("Synopsys DesignWare DMA Controller driver");
 MODULE_AUTHOR("Haavard Skinnemoen (Atmel)");
+MODULE_AUTHOR("Viresh Kumar <viresh.kumar@st.com>");
diff --git a/drivers/dma/dw_dmac_regs.h b/drivers/dma/dw_dmac_regs.h
index 720f821527f8..c3419518d701 100644
--- a/drivers/dma/dw_dmac_regs.h
+++ b/drivers/dma/dw_dmac_regs.h
@@ -2,6 +2,7 @@
  * Driver for the Synopsys DesignWare AHB DMA Controller
  *
  * Copyright (C) 2005-2007 Atmel Corporation
+ * Copyright (C) 2010-2011 ST Microelectronics
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -138,6 +139,7 @@ struct dw_dma_chan {
         void __iomem            *ch_regs;
         u8                      mask;
         u8                      priority;
+        bool                    paused;
 
         spinlock_t              lock;
 
diff --git a/drivers/dma/intel_mid_dma.c b/drivers/dma/intel_mid_dma.c
index 3d4ec38b9b62..f653517ef744 100644
--- a/drivers/dma/intel_mid_dma.c
+++ b/drivers/dma/intel_mid_dma.c
@@ -1292,8 +1292,7 @@ static int __devinit intel_mid_dma_probe(struct pci_dev *pdev,
         if (err)
                 goto err_dma;
 
-        pm_runtime_set_active(&pdev->dev);
-        pm_runtime_enable(&pdev->dev);
+        pm_runtime_put_noidle(&pdev->dev);
         pm_runtime_allow(&pdev->dev);
         return 0;
 
@@ -1322,6 +1321,9 @@ err_enable_device:
 static void __devexit intel_mid_dma_remove(struct pci_dev *pdev)
 {
         struct middma_device *device = pci_get_drvdata(pdev);
+
+        pm_runtime_get_noresume(&pdev->dev);
+        pm_runtime_forbid(&pdev->dev);
         middma_shutdown(pdev);
         pci_dev_put(pdev);
         kfree(device);
@@ -1385,13 +1387,20 @@ int dma_resume(struct pci_dev *pci)
 static int dma_runtime_suspend(struct device *dev)
 {
         struct pci_dev *pci_dev = to_pci_dev(dev);
-        return dma_suspend(pci_dev, PMSG_SUSPEND);
+        struct middma_device *device = pci_get_drvdata(pci_dev);
+
+        device->state = SUSPENDED;
+        return 0;
 }
 
 static int dma_runtime_resume(struct device *dev)
 {
         struct pci_dev *pci_dev = to_pci_dev(dev);
-        return dma_resume(pci_dev);
+        struct middma_device *device = pci_get_drvdata(pci_dev);
+
+        device->state = RUNNING;
+        iowrite32(REG_BIT0, device->dma_base + DMA_CFG);
+        return 0;
 }
 
 static int dma_runtime_idle(struct device *dev)
diff --git a/drivers/dma/ioat/dma_v2.c b/drivers/dma/ioat/dma_v2.c
index f4a51d4d0349..5d65f8377971 100644
--- a/drivers/dma/ioat/dma_v2.c
+++ b/drivers/dma/ioat/dma_v2.c
@@ -508,6 +508,7 @@ int ioat2_alloc_chan_resources(struct dma_chan *c)
         struct ioat_ring_ent **ring;
         u64 status;
         int order;
+        int i = 0;
 
         /* have we already been set up? */
         if (ioat->ring)
@@ -548,8 +549,11 @@ int ioat2_alloc_chan_resources(struct dma_chan *c)
         ioat2_start_null_desc(ioat);
 
         /* check that we got off the ground */
-        udelay(5);
-        status = ioat_chansts(chan);
+        do {
+                udelay(1);
+                status = ioat_chansts(chan);
+        } while (i++ < 20 && !is_ioat_active(status) && !is_ioat_idle(status));
+
         if (is_ioat_active(status) || is_ioat_idle(status)) {
                 set_bit(IOAT_RUN, &chan->state);
                 return 1 << ioat->alloc_order;
diff --git a/drivers/dma/iop-adma.c b/drivers/dma/iop-adma.c
index c6b01f535b29..e03f811a83dd 100644
--- a/drivers/dma/iop-adma.c
+++ b/drivers/dma/iop-adma.c
@@ -619,7 +619,7 @@ iop_adma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dma_dest,
 
         if (unlikely(!len))
                 return NULL;
-        BUG_ON(unlikely(len > IOP_ADMA_MAX_BYTE_COUNT));
+        BUG_ON(len > IOP_ADMA_MAX_BYTE_COUNT);
 
         dev_dbg(iop_chan->device->common.dev, "%s len: %u\n",
                 __func__, len);
@@ -652,7 +652,7 @@ iop_adma_prep_dma_memset(struct dma_chan *chan, dma_addr_t dma_dest,
 
         if (unlikely(!len))
                 return NULL;
-        BUG_ON(unlikely(len > IOP_ADMA_MAX_BYTE_COUNT));
+        BUG_ON(len > IOP_ADMA_MAX_BYTE_COUNT);
 
         dev_dbg(iop_chan->device->common.dev, "%s len: %u\n",
                 __func__, len);
@@ -686,7 +686,7 @@ iop_adma_prep_dma_xor(struct dma_chan *chan, dma_addr_t dma_dest,
 
         if (unlikely(!len))
                 return NULL;
-        BUG_ON(unlikely(len > IOP_ADMA_XOR_MAX_BYTE_COUNT));
+        BUG_ON(len > IOP_ADMA_XOR_MAX_BYTE_COUNT);
 
         dev_dbg(iop_chan->device->common.dev,
                 "%s src_cnt: %d len: %u flags: %lx\n",
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index a25f5f61e0e0..954e334e01bb 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -671,7 +671,7 @@ mv_xor_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
         if (unlikely(len < MV_XOR_MIN_BYTE_COUNT))
                 return NULL;
 
-        BUG_ON(unlikely(len > MV_XOR_MAX_BYTE_COUNT));
+        BUG_ON(len > MV_XOR_MAX_BYTE_COUNT);
 
         spin_lock_bh(&mv_chan->lock);
         slot_cnt = mv_chan_memcpy_slot_count(len);
@@ -710,7 +710,7 @@ mv_xor_prep_dma_memset(struct dma_chan *chan, dma_addr_t dest, int value,
         if (unlikely(len < MV_XOR_MIN_BYTE_COUNT))
                 return NULL;
 
-        BUG_ON(unlikely(len > MV_XOR_MAX_BYTE_COUNT));
+        BUG_ON(len > MV_XOR_MAX_BYTE_COUNT);
 
         spin_lock_bh(&mv_chan->lock);
         slot_cnt = mv_chan_memset_slot_count(len);
@@ -744,7 +744,7 @@ mv_xor_prep_dma_xor(struct dma_chan *chan, dma_addr_t dest, dma_addr_t *src,
         if (unlikely(len < MV_XOR_MIN_BYTE_COUNT))
                 return NULL;
 
-        BUG_ON(unlikely(len > MV_XOR_MAX_BYTE_COUNT));
+        BUG_ON(len > MV_XOR_MAX_BYTE_COUNT);
 
         dev_dbg(mv_chan->device->common.dev,
                 "%s src_cnt: %d len: dest %x %u flags: %ld\n",
diff --git a/drivers/dma/pch_dma.c b/drivers/dma/pch_dma.c
index 8d8fef1480a9..ff5b38f9d45b 100644
--- a/drivers/dma/pch_dma.c
+++ b/drivers/dma/pch_dma.c
@@ -77,10 +77,10 @@ struct pch_dma_regs {
         u32     dma_ctl0;
         u32     dma_ctl1;
         u32     dma_ctl2;
-        u32     reserved1;
+        u32     dma_ctl3;
         u32     dma_sts0;
         u32     dma_sts1;
-        u32     reserved2;
+        u32     dma_sts2;
         u32     reserved3;
         struct pch_dma_desc_regs desc[MAX_CHAN_NR];
 };
@@ -130,6 +130,7 @@ struct pch_dma {
 #define PCH_DMA_CTL0    0x00
 #define PCH_DMA_CTL1    0x04
 #define PCH_DMA_CTL2    0x08
+#define PCH_DMA_CTL3    0x0C
 #define PCH_DMA_STS0    0x10
 #define PCH_DMA_STS1    0x14
 
@@ -138,7 +139,8 @@ struct pch_dma {
 #define dma_writel(pd, name, val) \
         writel((val), (pd)->membase + PCH_DMA_##name)
 
-static inline struct pch_dma_desc *to_pd_desc(struct dma_async_tx_descriptor *txd)
+static inline
+struct pch_dma_desc *to_pd_desc(struct dma_async_tx_descriptor *txd)
 {
         return container_of(txd, struct pch_dma_desc, txd);
 }
@@ -163,13 +165,15 @@ static inline struct device *chan2parent(struct dma_chan *chan)
         return chan->dev->device.parent;
 }
 
-static inline struct pch_dma_desc *pdc_first_active(struct pch_dma_chan *pd_chan)
+static inline
+struct pch_dma_desc *pdc_first_active(struct pch_dma_chan *pd_chan)
 {
         return list_first_entry(&pd_chan->active_list,
                                 struct pch_dma_desc, desc_node);
 }
 
-static inline struct pch_dma_desc *pdc_first_queued(struct pch_dma_chan *pd_chan)
+static inline
+struct pch_dma_desc *pdc_first_queued(struct pch_dma_chan *pd_chan)
 {
         return list_first_entry(&pd_chan->queue,
                                 struct pch_dma_desc, desc_node);
@@ -199,16 +203,30 @@ static void pdc_set_dir(struct dma_chan *chan)
         struct pch_dma *pd = to_pd(chan->device);
         u32 val;
 
-        val = dma_readl(pd, CTL0);
+        if (chan->chan_id < 8) {
+                val = dma_readl(pd, CTL0);
 
-        if (pd_chan->dir == DMA_TO_DEVICE)
-                val |= 0x1 << (DMA_CTL0_BITS_PER_CH * chan->chan_id +
-                               DMA_CTL0_DIR_SHIFT_BITS);
-        else
-                val &= ~(0x1 << (DMA_CTL0_BITS_PER_CH * chan->chan_id +
-                                 DMA_CTL0_DIR_SHIFT_BITS));
+                if (pd_chan->dir == DMA_TO_DEVICE)
+                        val |= 0x1 << (DMA_CTL0_BITS_PER_CH * chan->chan_id +
+                                       DMA_CTL0_DIR_SHIFT_BITS);
+                else
+                        val &= ~(0x1 << (DMA_CTL0_BITS_PER_CH * chan->chan_id +
+                                         DMA_CTL0_DIR_SHIFT_BITS));
+
+                dma_writel(pd, CTL0, val);
+        } else {
+                int ch = chan->chan_id - 8; /* ch8-->0 ch9-->1 ... ch11->3 */
+                val = dma_readl(pd, CTL3);
 
-        dma_writel(pd, CTL0, val);
+                if (pd_chan->dir == DMA_TO_DEVICE)
+                        val |= 0x1 << (DMA_CTL0_BITS_PER_CH * ch +
+                                       DMA_CTL0_DIR_SHIFT_BITS);
+                else
+                        val &= ~(0x1 << (DMA_CTL0_BITS_PER_CH * ch +
+                                         DMA_CTL0_DIR_SHIFT_BITS));
+
+                dma_writel(pd, CTL3, val);
+        }
 
         dev_dbg(chan2dev(chan), "pdc_set_dir: chan %d -> %x\n",
                 chan->chan_id, val);
@@ -219,13 +237,26 @@ static void pdc_set_mode(struct dma_chan *chan, u32 mode)
         struct pch_dma *pd = to_pd(chan->device);
         u32 val;
 
-        val = dma_readl(pd, CTL0);
+        if (chan->chan_id < 8) {
+                val = dma_readl(pd, CTL0);
+
+                val &= ~(DMA_CTL0_MODE_MASK_BITS <<
+                        (DMA_CTL0_BITS_PER_CH * chan->chan_id));
+                val |= mode << (DMA_CTL0_BITS_PER_CH * chan->chan_id);
 
-        val &= ~(DMA_CTL0_MODE_MASK_BITS <<
-                (DMA_CTL0_BITS_PER_CH * chan->chan_id));
-        val |= mode << (DMA_CTL0_BITS_PER_CH * chan->chan_id);
+                dma_writel(pd, CTL0, val);
+        } else {
+                int ch = chan->chan_id - 8; /* ch8-->0 ch9-->1 ... ch11->3 */
+
+                val = dma_readl(pd, CTL3);
+
+                val &= ~(DMA_CTL0_MODE_MASK_BITS <<
+                        (DMA_CTL0_BITS_PER_CH * ch));
+                val |= mode << (DMA_CTL0_BITS_PER_CH * ch);
 
-        dma_writel(pd, CTL0, val);
+                dma_writel(pd, CTL3, val);
+
+        }
 
         dev_dbg(chan2dev(chan), "pdc_set_mode: chan %d -> %x\n",
                 chan->chan_id, val);
@@ -251,9 +282,6 @@ static bool pdc_is_idle(struct pch_dma_chan *pd_chan)
 
 static void pdc_dostart(struct pch_dma_chan *pd_chan, struct pch_dma_desc* desc)
 {
-        struct pch_dma *pd = to_pd(pd_chan->chan.device);
-        u32 val;
-
         if (!pdc_is_idle(pd_chan)) {
                 dev_err(chan2dev(&pd_chan->chan),
                         "BUG: Attempt to start non-idle channel\n");
@@ -279,10 +307,6 @@ static void pdc_dostart(struct pch_dma_chan *pd_chan, struct pch_dma_desc* desc)
                 channel_writel(pd_chan, NEXT, desc->txd.phys);
                 pdc_set_mode(&pd_chan->chan, DMA_CTL0_SG);
         }
-
-        val = dma_readl(pd, CTL2);
-        val |= 1 << (DMA_CTL2_START_SHIFT_BITS + pd_chan->chan.chan_id);
-        dma_writel(pd, CTL2, val);
 }
 
 static void pdc_chain_complete(struct pch_dma_chan *pd_chan,
@@ -403,7 +427,7 @@ static struct pch_dma_desc *pdc_desc_get(struct pch_dma_chan *pd_chan)
 {
         struct pch_dma_desc *desc, *_d;
         struct pch_dma_desc *ret = NULL;
-        int i;
+        int i = 0;
 
         spin_lock(&pd_chan->lock);
         list_for_each_entry_safe(desc, _d, &pd_chan->free_list, desc_node) {
@@ -478,7 +502,6 @@ static int pd_alloc_chan_resources(struct dma_chan *chan)
         spin_unlock_bh(&pd_chan->lock);
 
         pdc_enable_irq(chan, 1);
-        pdc_set_dir(chan);
 
         return pd_chan->descs_allocated;
 }
@@ -561,6 +584,9 @@ static struct dma_async_tx_descriptor *pd_prep_slave_sg(struct dma_chan *chan,
         else
                 return NULL;
 
+        pd_chan->dir = direction;
+        pdc_set_dir(chan);
+
         for_each_sg(sgl, sg, sg_len, i) {
                 desc = pdc_desc_get(pd_chan);
 
@@ -703,6 +729,7 @@ static void pch_dma_save_regs(struct pch_dma *pd)
         pd->regs.dma_ctl0 = dma_readl(pd, CTL0);
         pd->regs.dma_ctl1 = dma_readl(pd, CTL1);
         pd->regs.dma_ctl2 = dma_readl(pd, CTL2);
+        pd->regs.dma_ctl3 = dma_readl(pd, CTL3);
 
         list_for_each_entry_safe(chan, _c, &pd->dma.channels, device_node) {
                 pd_chan = to_pd_chan(chan);
@@ -725,6 +752,7 @@ static void pch_dma_restore_regs(struct pch_dma *pd)
         dma_writel(pd, CTL0, pd->regs.dma_ctl0);
         dma_writel(pd, CTL1, pd->regs.dma_ctl1);
         dma_writel(pd, CTL2, pd->regs.dma_ctl2);
+        dma_writel(pd, CTL3, pd->regs.dma_ctl3);
 
         list_for_each_entry_safe(chan, _c, &pd->dma.channels, device_node) {
                 pd_chan = to_pd_chan(chan);
@@ -850,8 +878,6 @@ static int __devinit pch_dma_probe(struct pci_dev *pdev,
 
                 pd_chan->membase = &regs->desc[i];
 
-                pd_chan->dir = (i % 2) ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
-
                 spin_lock_init(&pd_chan->lock);
 
                 INIT_LIST_HEAD(&pd_chan->active_list);
@@ -929,13 +955,23 @@ static void __devexit pch_dma_remove(struct pci_dev *pdev)
 #define PCI_DEVICE_ID_ML7213_DMA1_8CH   0x8026
 #define PCI_DEVICE_ID_ML7213_DMA2_8CH   0x802B
 #define PCI_DEVICE_ID_ML7213_DMA3_4CH   0x8034
+#define PCI_DEVICE_ID_ML7213_DMA4_12CH  0x8032
+#define PCI_DEVICE_ID_ML7223_DMA1_4CH   0x800B
+#define PCI_DEVICE_ID_ML7223_DMA2_4CH   0x800E
+#define PCI_DEVICE_ID_ML7223_DMA3_4CH   0x8017
+#define PCI_DEVICE_ID_ML7223_DMA4_4CH   0x803B
 
-static const struct pci_device_id pch_dma_id_table[] = {
+DEFINE_PCI_DEVICE_TABLE(pch_dma_id_table) = {
         { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_EG20T_PCH_DMA_8CH), 8 },
         { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_EG20T_PCH_DMA_4CH), 4 },
         { PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ML7213_DMA1_8CH), 8}, /* UART Video */
         { PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ML7213_DMA2_8CH), 8}, /* PCMIF SPI */
         { PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ML7213_DMA3_4CH), 4}, /* FPGA */
+        { PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ML7213_DMA4_12CH), 12}, /* I2S */
+        { PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ML7223_DMA1_4CH), 4}, /* UART */
+        { PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ML7223_DMA2_4CH), 4}, /* Video SPI */
+        { PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ML7223_DMA3_4CH), 4}, /* Security */
+        { PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ML7223_DMA4_4CH), 4}, /* FPGA */
         { 0, },
 };
 
diff --git a/drivers/dma/ppc4xx/adma.c b/drivers/dma/ppc4xx/adma.c
index 3b0247e74cc4..fc457a7e8832 100644
--- a/drivers/dma/ppc4xx/adma.c
+++ b/drivers/dma/ppc4xx/adma.c
@@ -2313,7 +2313,7 @@ static struct dma_async_tx_descriptor *ppc440spe_adma_prep_dma_memcpy(
         if (unlikely(!len))
                 return NULL;
 
-        BUG_ON(unlikely(len > PPC440SPE_ADMA_DMA_MAX_BYTE_COUNT));
+        BUG_ON(len > PPC440SPE_ADMA_DMA_MAX_BYTE_COUNT);
 
         spin_lock_bh(&ppc440spe_chan->lock);
 
@@ -2354,7 +2354,7 @@ static struct dma_async_tx_descriptor *ppc440spe_adma_prep_dma_memset(
         if (unlikely(!len))
                 return NULL;
 
-        BUG_ON(unlikely(len > PPC440SPE_ADMA_DMA_MAX_BYTE_COUNT));
+        BUG_ON(len > PPC440SPE_ADMA_DMA_MAX_BYTE_COUNT);
 
         spin_lock_bh(&ppc440spe_chan->lock);
 
@@ -2397,7 +2397,7 @@ static struct dma_async_tx_descriptor *ppc440spe_adma_prep_dma_xor(
                                      dma_dest, dma_src, src_cnt));
         if (unlikely(!len))
                 return NULL;
-        BUG_ON(unlikely(len > PPC440SPE_ADMA_XOR_MAX_BYTE_COUNT));
+        BUG_ON(len > PPC440SPE_ADMA_XOR_MAX_BYTE_COUNT);
 
         dev_dbg(ppc440spe_chan->device->common.dev,
                 "ppc440spe adma%d: %s src_cnt: %d len: %u int_en: %d\n",
@@ -2887,7 +2887,7 @@ static struct dma_async_tx_descriptor *ppc440spe_adma_prep_dma_pq(
         ADMA_LL_DBG(prep_dma_pq_dbg(ppc440spe_chan->device->id,
                                     dst, src, src_cnt));
         BUG_ON(!len);
-        BUG_ON(unlikely(len > PPC440SPE_ADMA_XOR_MAX_BYTE_COUNT));
+        BUG_ON(len > PPC440SPE_ADMA_XOR_MAX_BYTE_COUNT);
         BUG_ON(!src_cnt);
 
         if (src_cnt == 1 && dst[1] == src[0]) {
diff --git a/drivers/dma/shdma.c b/drivers/dma/shdma.c
index 636e40925b16..2a638f9f09a2 100644
--- a/drivers/dma/shdma.c
+++ b/drivers/dma/shdma.c
@@ -343,7 +343,7 @@ static int sh_dmae_alloc_chan_resources(struct dma_chan *chan)
 
                 dmae_set_dmars(sh_chan, cfg->mid_rid);
                 dmae_set_chcr(sh_chan, cfg->chcr);
-        } else if ((sh_dmae_readl(sh_chan, CHCR) & 0xf00) != 0x400) {
+        } else {
                 dmae_init(sh_chan);
         }
 
@@ -1144,6 +1144,8 @@ static int __init sh_dmae_probe(struct platform_device *pdev)
         /* platform data */
         shdev->pdata = pdata;
 
+        platform_set_drvdata(pdev, shdev);
+
         pm_runtime_enable(&pdev->dev);
         pm_runtime_get_sync(&pdev->dev);
 
@@ -1256,7 +1258,6 @@ static int __init sh_dmae_probe(struct platform_device *pdev)
 
         pm_runtime_put(&pdev->dev);
 
-        platform_set_drvdata(pdev, shdev);
         dma_async_device_register(&shdev->common);
 
         return err;
@@ -1278,6 +1279,8 @@ rst_err:
 
         if (dmars)
                 iounmap(shdev->dmars);
+
+        platform_set_drvdata(pdev, NULL);
 emapdmars:
         iounmap(shdev->chan_reg);
         synchronize_rcu();
@@ -1316,6 +1319,8 @@ static int __exit sh_dmae_remove(struct platform_device *pdev)
                 iounmap(shdev->dmars);
         iounmap(shdev->chan_reg);
 
+        platform_set_drvdata(pdev, NULL);
+
         synchronize_rcu();
         kfree(shdev);
 
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index 94ee15dd3aed..8f222d4db7de 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -1829,7 +1829,7 @@ d40_get_dev_addr(struct d40_chan *chan, enum dma_data_direction direction)
 {
         struct stedma40_platform_data *plat = chan->base->plat_data;
         struct stedma40_chan_cfg *cfg = &chan->dma_cfg;
-        dma_addr_t addr;
+        dma_addr_t addr = 0;
 
         if (chan->runtime_addr)
                 return chan->runtime_addr;
@@ -2962,4 +2962,4 @@ static int __init stedma40_init(void)
 {
         return platform_driver_probe(&d40_driver, d40_probe);
 }
-arch_initcall(stedma40_init);
+subsys_initcall(stedma40_init);
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 592397629ddc..4a7f63143455 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -89,24 +89,28 @@ config GPIO_IT8761E
 config GPIO_EXYNOS4
         bool "Samsung Exynos4 GPIO library support"
         default y if CPU_EXYNOS4210
+        depends on ARM
         help
           Say yes here to support Samsung Exynos4 series SoCs GPIO library
 
 config GPIO_PLAT_SAMSUNG
         bool "Samsung SoCs GPIO library support"
         default y if SAMSUNG_GPIOLIB_4BIT
+        depends on ARM
         help
           Say yes here to support Samsung SoCs GPIO library
 
 config GPIO_S5PC100
         bool "Samsung S5PC100 GPIO library support"
         default y if CPU_S5PC100
+        depends on ARM
         help
           Say yes here to support Samsung S5PC100 SoCs GPIO library
 
 config GPIO_S5PV210
         bool "Samsung S5PV210/S5PC110 GPIO library support"
         default y if CPU_S5PV210
+        depends on ARM
         help
           Say yes here to support Samsung S5PV210/S5PC110 SoCs GPIO library
 
diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index de3d2465fe24..85e937984ff7 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -296,7 +296,7 @@ static int get_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev)
                  * If the TjMax is not plausible, an assumption
                  * will be used
                  */
-                if (val > 80 && val < 120) {
+                if (val) {
                         dev_info(dev, "TjMax is %d C.\n", val);
                         return val * 1000;
                 }
@@ -304,24 +304,9 @@ static int get_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev)
 
         /*
          * An assumption is made for early CPUs and unreadable MSR.
-         * NOTE: the given value may not be correct.
+         * NOTE: the calculated value may not be correct.
          */
-
-        switch (c->x86_model) {
-        case 0xe:
-        case 0xf:
-        case 0x16:
-        case 0x1a:
-                dev_warn(dev, "TjMax is assumed as 100 C!\n");
-                return 100000;
-        case 0x17:
-        case 0x1c:              /* Atom CPUs */
-                return adjust_tjmax(c, id, dev);
-        default:
-                dev_warn(dev, "CPU (model=0x%x) is not supported yet,"
-                        " using default TjMax of 100C.\n", c->x86_model);
-                return 100000;
-        }
+        return adjust_tjmax(c, id, dev);
 }
 
 static void __devinit get_ucode_rev_on_cpu(void *edx)
@@ -341,7 +326,7 @@ static int get_pkg_tjmax(unsigned int cpu, struct device *dev)
         err = rdmsr_safe_on_cpu(cpu, MSR_IA32_TEMPERATURE_TARGET, &eax, &edx);
         if (!err) {
                 val = (eax >> 16) & 0xff;
-                if (val > 80 && val < 120)
+                if (val)
                         return val * 1000;
         }
         dev_warn(dev, "Unable to read Pkg-TjMax from CPU:%u\n", cpu);
diff --git a/drivers/hwmon/max6642.c b/drivers/hwmon/max6642.c
index 0f9fc40379cd..e855d3b0bd1f 100644
--- a/drivers/hwmon/max6642.c
+++ b/drivers/hwmon/max6642.c
@@ -136,15 +136,29 @@ static int max6642_detect(struct i2c_client *client,
         if (man_id != 0x4D)
                 return -ENODEV;
 
+        /* sanity check */
+        if (i2c_smbus_read_byte_data(client, 0x04) != 0x4D
+            || i2c_smbus_read_byte_data(client, 0x06) != 0x4D
+            || i2c_smbus_read_byte_data(client, 0xff) != 0x4D)
+                return -ENODEV;
+
         /*
          * We read the config and status register, the 4 lower bits in the
          * config register should be zero and bit 5, 3, 1 and 0 should be
          * zero in the status register.
          */
         reg_config = i2c_smbus_read_byte_data(client, MAX6642_REG_R_CONFIG);
+        if ((reg_config & 0x0f) != 0x00)
+                return -ENODEV;
+
+        /* in between, another round of sanity checks */
+        if (i2c_smbus_read_byte_data(client, 0x04) != reg_config
+            || i2c_smbus_read_byte_data(client, 0x06) != reg_config
+            || i2c_smbus_read_byte_data(client, 0xff) != reg_config)
+                return -ENODEV;
+
         reg_status = i2c_smbus_read_byte_data(client, MAX6642_REG_R_STATUS);
-        if (((reg_config & 0x0f) != 0x00) ||
-            ((reg_status & 0x2b) != 0x00))
+        if ((reg_status & 0x2b) != 0x00)
                 return -ENODEV;
 
         strlcpy(info->type, "max6642", I2C_NAME_SIZE);
@@ -246,7 +260,7 @@ static SENSOR_DEVICE_ATTR_2(temp1_max, S_IWUSR | S_IRUGO, show_temp_max,
                             set_temp_max, 0, MAX6642_REG_W_LOCAL_HIGH);
 static SENSOR_DEVICE_ATTR_2(temp2_max, S_IWUSR | S_IRUGO, show_temp_max,
                             set_temp_max, 1, MAX6642_REG_W_REMOTE_HIGH);
-static SENSOR_DEVICE_ATTR(temp_fault, S_IRUGO, show_alarm, NULL, 2);
+static SENSOR_DEVICE_ATTR(temp2_fault, S_IRUGO, show_alarm, NULL, 2);
 static SENSOR_DEVICE_ATTR(temp1_max_alarm, S_IRUGO, show_alarm, NULL, 6);
 static SENSOR_DEVICE_ATTR(temp2_max_alarm, S_IRUGO, show_alarm, NULL, 4);
 
@@ -256,7 +270,7 @@ static struct attribute *max6642_attributes[] = {
         &sensor_dev_attr_temp1_max.dev_attr.attr,
         &sensor_dev_attr_temp2_max.dev_attr.attr,
 
-        &sensor_dev_attr_temp_fault.dev_attr.attr,
+        &sensor_dev_attr_temp2_fault.dev_attr.attr,
         &sensor_dev_attr_temp1_max_alarm.dev_attr.attr,
         &sensor_dev_attr_temp2_max_alarm.dev_attr.attr,
         NULL
diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index 6e5123b1d341..144d27261e43 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -1782,7 +1782,6 @@ static int ide_cd_probe(ide_drive_t *drive)
         ide_cd_read_toc(drive, &sense);
         g->fops = &idecd_ops;
         g->flags |= GENHD_FL_REMOVABLE | GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
-        g->events = DISK_EVENT_MEDIA_CHANGE;
         add_disk(g);
         return 0;
 
diff --git a/drivers/input/serio/serport.c b/drivers/input/serio/serport.c
index f3698967edf6..8755f5f3ad37 100644
--- a/drivers/input/serio/serport.c
+++ b/drivers/input/serio/serport.c
@@ -120,21 +120,17 @@ static void serport_ldisc_close(struct tty_struct *tty)
  * 'interrupt' routine.
  */
 
-static unsigned int serport_ldisc_receive(struct tty_struct *tty,
-                const unsigned char *cp, char *fp, int count)
+static void serport_ldisc_receive(struct tty_struct *tty, const unsigned char *cp, char *fp, int count)
 {
         struct serport *serport = (struct serport*) tty->disc_data;
         unsigned long flags;
         unsigned int ch_flags;
-        int ret = 0;
         int i;
 
         spin_lock_irqsave(&serport->lock, flags);
 
-        if (!test_bit(SERPORT_ACTIVE, &serport->flags)) {
-                ret = -EINVAL;
+        if (!test_bit(SERPORT_ACTIVE, &serport->flags))
                 goto out;
-        }
 
         for (i = 0; i < count; i++) {
                 switch (fp[i]) {
@@ -156,8 +152,6 @@ static unsigned int serport_ldisc_receive(struct tty_struct *tty,
 
 out:
         spin_unlock_irqrestore(&serport->lock, flags);
-
-        return ret == 0 ? count : ret;
 }
 
 /*
diff --git a/drivers/isdn/gigaset/ser-gigaset.c b/drivers/isdn/gigaset/ser-gigaset.c
index 1d44d470897c..86a5c4f7775e 100644
--- a/drivers/isdn/gigaset/ser-gigaset.c
+++ b/drivers/isdn/gigaset/ser-gigaset.c
@@ -674,7 +674,7 @@ gigaset_tty_ioctl(struct tty_struct *tty, struct file *file,
  *      cflags  buffer containing error flags for received characters (ignored)
  *      count   number of received characters
  */
-static unsigned int
+static void
 gigaset_tty_receive(struct tty_struct *tty, const unsigned char *buf,
                     char *cflags, int count)
 {
@@ -683,12 +683,12 @@ gigaset_tty_receive(struct tty_struct *tty, const unsigned char *buf,
         struct inbuf_t *inbuf;
 
         if (!cs)
-                return -ENODEV;
+                return;
         inbuf = cs->inbuf;
         if (!inbuf) {
                 dev_err(cs->dev, "%s: no inbuf\n", __func__);
                 cs_put(cs);
-                return -EINVAL;
+                return;
         }
 
         tail = inbuf->tail;
@@ -725,8 +725,6 @@ gigaset_tty_receive(struct tty_struct *tty, const unsigned char *buf,
         gig_dbg(DEBUG_INTR, "%s-->BH", __func__);
         gigaset_schedule_event(cs);
         cs_put(cs);
-
-        return count;
 }
 
 /*
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index 76a5af00a26b..2067288f61f9 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -19,6 +19,8 @@
 #define DM_MSG_PREFIX "io"
 
 #define DM_IO_MAX_REGIONS       BITS_PER_LONG
+#define MIN_IOS         16
+#define MIN_BIOS        16
 
 struct dm_io_client {
         mempool_t *pool;
@@ -41,33 +43,21 @@ struct io {
 static struct kmem_cache *_dm_io_cache;
 
 /*
- * io contexts are only dynamically allocated for asynchronous
- * io.  Since async io is likely to be the majority of io we'll
- * have the same number of io contexts as bios! (FIXME: must reduce this).
- */
-
-static unsigned int pages_to_ios(unsigned int pages)
-{
-        return 4 * pages;       /* too many ? */
-}
-
-/*
  * Create a client with mempool and bioset.
  */
-struct dm_io_client *dm_io_client_create(unsigned num_pages)
+struct dm_io_client *dm_io_client_create(void)
 {
-        unsigned ios = pages_to_ios(num_pages);
         struct dm_io_client *client;
 
         client = kmalloc(sizeof(*client), GFP_KERNEL);
         if (!client)
                 return ERR_PTR(-ENOMEM);
 
-        client->pool = mempool_create_slab_pool(ios, _dm_io_cache);
+        client->pool = mempool_create_slab_pool(MIN_IOS, _dm_io_cache);
         if (!client->pool)
                 goto bad;
 
-        client->bios = bioset_create(16, 0);
+        client->bios = bioset_create(MIN_BIOS, 0);
         if (!client->bios)
                 goto bad;
 
@@ -81,13 +71,6 @@ struct dm_io_client *dm_io_client_create(unsigned num_pages)
 }
 EXPORT_SYMBOL(dm_io_client_create);
 
-int dm_io_client_resize(unsigned num_pages, struct dm_io_client *client)
-{
-        return mempool_resize(client->pool, pages_to_ios(num_pages),
-                              GFP_KERNEL);
-}
-EXPORT_SYMBOL(dm_io_client_resize);
-
 void dm_io_client_destroy(struct dm_io_client *client)
 {
         mempool_destroy(client->pool);
diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c
index 1bb73a13ca40..819e37eaaeba 100644
--- a/drivers/md/dm-kcopyd.c
+++ b/drivers/md/dm-kcopyd.c
@@ -27,15 +27,19 @@
 
 #include "dm.h"
 
+#define SUB_JOB_SIZE    128
+#define SPLIT_COUNT     8
+#define MIN_JOBS        8
+#define RESERVE_PAGES   (DIV_ROUND_UP(SUB_JOB_SIZE << SECTOR_SHIFT, PAGE_SIZE))
+
 /*-----------------------------------------------------------------
  * Each kcopyd client has its own little pool of preallocated
  * pages for kcopyd io.
  *---------------------------------------------------------------*/
 struct dm_kcopyd_client {
-        spinlock_t lock;
         struct page_list *pages;
-        unsigned int nr_pages;
-        unsigned int nr_free_pages;
+        unsigned nr_reserved_pages;
+        unsigned nr_free_pages;
 
         struct dm_io_client *io_client;
 
@@ -67,15 +71,18 @@ static void wake(struct dm_kcopyd_client *kc)
         queue_work(kc->kcopyd_wq, &kc->kcopyd_work);
 }
 
-static struct page_list *alloc_pl(void)
+/*
+ * Obtain one page for the use of kcopyd.
+ */
+static struct page_list *alloc_pl(gfp_t gfp)
 {
         struct page_list *pl;
 
-        pl = kmalloc(sizeof(*pl), GFP_KERNEL);
+        pl = kmalloc(sizeof(*pl), gfp);
         if (!pl)
                 return NULL;
 
-        pl->page = alloc_page(GFP_KERNEL);
+        pl->page = alloc_page(gfp);
         if (!pl->page) {
                 kfree(pl);
                 return NULL;
@@ -90,41 +97,56 @@ static void free_pl(struct page_list *pl)
         kfree(pl);
 }
 
-static int kcopyd_get_pages(struct dm_kcopyd_client *kc,
-                            unsigned int nr, struct page_list **pages)
+/*
+ * Add the provided pages to a client's free page list, releasing
+ * back to the system any beyond the reserved_pages limit.
+ */
+static void kcopyd_put_pages(struct dm_kcopyd_client *kc, struct page_list *pl)
 {
-        struct page_list *pl;
-
-        spin_lock(&kc->lock);
-        if (kc->nr_free_pages < nr) {
-                spin_unlock(&kc->lock);
-                return -ENOMEM;
-        }
-
-        kc->nr_free_pages -= nr;
-        for (*pages = pl = kc->pages; --nr; pl = pl->next)
-                ;
+        struct page_list *next;
 
-        kc->pages = pl->next;
-        pl->next = NULL;
+        do {
+                next = pl->next;
 
-        spin_unlock(&kc->lock);
+                if (kc->nr_free_pages >= kc->nr_reserved_pages)
+                        free_pl(pl);
+                else {
+                        pl->next = kc->pages;
+                        kc->pages = pl;
+                        kc->nr_free_pages++;
+                }
 
-        return 0;
+                pl = next;
+        } while (pl);
 }
 
-static void kcopyd_put_pages(struct dm_kcopyd_client *kc, struct page_list *pl)
+static int kcopyd_get_pages(struct dm_kcopyd_client *kc,
+                            unsigned int nr, struct page_list **pages)
 {
-        struct page_list *cursor;
+        struct page_list *pl;
+
+        *pages = NULL;
+
+        do {
+                pl = alloc_pl(__GFP_NOWARN | __GFP_NORETRY);
+                if (unlikely(!pl)) {
+                        /* Use reserved pages */
+                        pl = kc->pages;
+                        if (unlikely(!pl))
+                                goto out_of_memory;
+                        kc->pages = pl->next;
+                        kc->nr_free_pages--;
+                }
+                pl->next = *pages;
+                *pages = pl;
+        } while (--nr);
 
-        spin_lock(&kc->lock);
-        for (cursor = pl; cursor->next; cursor = cursor->next)
-                kc->nr_free_pages++;
+        return 0;
 
-        kc->nr_free_pages++;
-        cursor->next = kc->pages;
-        kc->pages = pl;
-        spin_unlock(&kc->lock);
+out_of_memory:
+        if (*pages)
+                kcopyd_put_pages(kc, *pages);
+        return -ENOMEM;
 }
 
 /*
@@ -141,13 +163,16 @@ static void drop_pages(struct page_list *pl)
         }
 }
 
-static int client_alloc_pages(struct dm_kcopyd_client *kc, unsigned int nr)
+/*
+ * Allocate and reserve nr_pages for the use of a specific client.
+ */
+static int client_reserve_pages(struct dm_kcopyd_client *kc, unsigned nr_pages)
 {
-        unsigned int i;
+        unsigned i;
         struct page_list *pl = NULL, *next;
 
-        for (i = 0; i < nr; i++) {
-                next = alloc_pl();
+        for (i = 0; i < nr_pages; i++) {
+                next = alloc_pl(GFP_KERNEL);
                 if (!next) {
                         if (pl)
                                 drop_pages(pl);
@@ -157,17 +182,18 @@ static int client_alloc_pages(struct dm_kcopyd_client *kc, unsigned int nr)
                 pl = next;
         }
 
+        kc->nr_reserved_pages += nr_pages;
         kcopyd_put_pages(kc, pl);
-        kc->nr_pages += nr;
+
         return 0;
 }
 
 static void client_free_pages(struct dm_kcopyd_client *kc)
 {
-        BUG_ON(kc->nr_free_pages != kc->nr_pages);
+        BUG_ON(kc->nr_free_pages != kc->nr_reserved_pages);
         drop_pages(kc->pages);
         kc->pages = NULL;
-        kc->nr_free_pages = kc->nr_pages = 0;
+        kc->nr_free_pages = kc->nr_reserved_pages = 0;
 }
 
 /*-----------------------------------------------------------------
@@ -216,16 +242,17 @@ struct kcopyd_job {
         struct mutex lock;
         atomic_t sub_jobs;
         sector_t progress;
-};
 
-/* FIXME: this should scale with the number of pages */
-#define MIN_JOBS 512
+        struct kcopyd_job *master_job;
+};
 
 static struct kmem_cache *_job_cache;
 
 int __init dm_kcopyd_init(void)
 {
-        _job_cache = KMEM_CACHE(kcopyd_job, 0);
+        _job_cache = kmem_cache_create("kcopyd_job",
+                                sizeof(struct kcopyd_job) * (SPLIT_COUNT + 1),
+                                __alignof__(struct kcopyd_job), 0, NULL);
         if (!_job_cache)
                 return -ENOMEM;
 
@@ -299,7 +326,12 @@ static int run_complete_job(struct kcopyd_job *job)
 
         if (job->pages)
                 kcopyd_put_pages(kc, job->pages);
-        mempool_free(job, kc->job_pool);
+        /*
+         * If this is the master job, the sub jobs have already
+         * completed so we can free everything.
+         */
+        if (job->master_job == job)
+                mempool_free(job, kc->job_pool);
         fn(read_err, write_err, context);
 
         if (atomic_dec_and_test(&kc->nr_jobs))
@@ -460,14 +492,14 @@ static void dispatch_job(struct kcopyd_job *job)
         wake(kc);
 }
 
-#define SUB_JOB_SIZE 128
 static void segment_complete(int read_err, unsigned long write_err,
                              void *context)
 {
         /* FIXME: tidy this function */
         sector_t progress = 0;
         sector_t count = 0;
-        struct kcopyd_job *job = (struct kcopyd_job *) context;
+        struct kcopyd_job *sub_job = (struct kcopyd_job *) context;
+        struct kcopyd_job *job = sub_job->master_job;
         struct dm_kcopyd_client *kc = job->kc;
 
         mutex_lock(&job->lock);
@@ -498,8 +530,6 @@ static void segment_complete(int read_err, unsigned long write_err,
 
         if (count) {
                 int i;
-                struct kcopyd_job *sub_job = mempool_alloc(kc->job_pool,
-                                                           GFP_NOIO);
 
                 *sub_job = *job;
                 sub_job->source.sector += progress;
@@ -511,7 +541,7 @@ static void segment_complete(int read_err, unsigned long write_err,
                 }
 
                 sub_job->fn = segment_complete;
-                sub_job->context = job;
+                sub_job->context = sub_job;
                 dispatch_job(sub_job);
 
         } else if (atomic_dec_and_test(&job->sub_jobs)) {
@@ -531,19 +561,19 @@ static void segment_complete(int read_err, unsigned long write_err,
 }
 
 /*
- * Create some little jobs that will do the move between
- * them.
+ * Create some sub jobs to share the work between them.
  */
-#define SPLIT_COUNT 8
-static void split_job(struct kcopyd_job *job)
+static void split_job(struct kcopyd_job *master_job)
 {
         int i;
 
-        atomic_inc(&job->kc->nr_jobs);
+        atomic_inc(&master_job->kc->nr_jobs);
 
-        atomic_set(&job->sub_jobs, SPLIT_COUNT);
-        for (i = 0; i < SPLIT_COUNT; i++)
-                segment_complete(0, 0u, job);
+        atomic_set(&master_job->sub_jobs, SPLIT_COUNT);
+        for (i = 0; i < SPLIT_COUNT; i++) {
+                master_job[i + 1].master_job = master_job;
+                segment_complete(0, 0u, &master_job[i + 1]);
+        }
 }
 
 int dm_kcopyd_copy(struct dm_kcopyd_client *kc, struct dm_io_region *from,
@@ -553,7 +583,8 @@ int dm_kcopyd_copy(struct dm_kcopyd_client *kc, struct dm_io_region *from,
         struct kcopyd_job *job;
 
         /*
-         * Allocate a new job.
+         * Allocate an array of jobs consisting of one master job
+         * followed by SPLIT_COUNT sub jobs.
          */
         job = mempool_alloc(kc->job_pool, GFP_NOIO);
 
@@ -577,10 +608,10 @@ int dm_kcopyd_copy(struct dm_kcopyd_client *kc, struct dm_io_region *from,
 
         job->fn = fn;
         job->context = context;
+        job->master_job = job;
 
-        if (job->source.count < SUB_JOB_SIZE)
+        if (job->source.count <= SUB_JOB_SIZE)
                 dispatch_job(job);
-
         else {
                 mutex_init(&job->lock);
                 job->progress = 0;
@@ -606,17 +637,15 @@ int kcopyd_cancel(struct kcopyd_job *job, int block)
 /*-----------------------------------------------------------------
  * Client setup
  *---------------------------------------------------------------*/
-int dm_kcopyd_client_create(unsigned int nr_pages,
-                            struct dm_kcopyd_client **result)
+struct dm_kcopyd_client *dm_kcopyd_client_create(void)
 {
         int r = -ENOMEM;
         struct dm_kcopyd_client *kc;
 
         kc = kmalloc(sizeof(*kc), GFP_KERNEL);
         if (!kc)
-                return -ENOMEM;
+                return ERR_PTR(-ENOMEM);
 
-        spin_lock_init(&kc->lock);
         spin_lock_init(&kc->job_lock);
         INIT_LIST_HEAD(&kc->complete_jobs);
         INIT_LIST_HEAD(&kc->io_jobs);
@@ -633,12 +662,12 @@ int dm_kcopyd_client_create(unsigned int nr_pages,
                 goto bad_workqueue;
 
         kc->pages = NULL;
-        kc->nr_pages = kc->nr_free_pages = 0;
-        r = client_alloc_pages(kc, nr_pages);
+        kc->nr_reserved_pages = kc->nr_free_pages = 0;
+        r = client_reserve_pages(kc, RESERVE_PAGES);
         if (r)
                 goto bad_client_pages;
 
-        kc->io_client = dm_io_client_create(nr_pages);
+        kc->io_client = dm_io_client_create();
         if (IS_ERR(kc->io_client)) {
                 r = PTR_ERR(kc->io_client);
                 goto bad_io_client;
@@ -647,8 +676,7 @@ int dm_kcopyd_client_create(unsigned int nr_pages,
         init_waitqueue_head(&kc->destroyq);
         atomic_set(&kc->nr_jobs, 0);
 
-        *result = kc;
-        return 0;
+        return kc;
 
 bad_io_client:
         client_free_pages(kc);
@@ -659,7 +687,7 @@ bad_workqueue:
 bad_slab:
         kfree(kc);
 
-        return r;
+        return ERR_PTR(r);
 }
 EXPORT_SYMBOL(dm_kcopyd_client_create);
 
diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c
index a1f321889676..948e3f4925bf 100644
--- a/drivers/md/dm-log.c
+++ b/drivers/md/dm-log.c
@@ -449,8 +449,7 @@ static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti,
 
                 lc->io_req.mem.type = DM_IO_VMA;
                 lc->io_req.notify.fn = NULL;
-                lc->io_req.client = dm_io_client_create(dm_div_up(buf_size,
-                                                                   PAGE_SIZE));
+                lc->io_req.client = dm_io_client_create();
                 if (IS_ERR(lc->io_req.client)) {
                         r = PTR_ERR(lc->io_req.client);
                         DMWARN("couldn't allocate disk io client");
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index a550a057d991..aa4e570c2cb5 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -1290,7 +1290,7 @@ static int do_end_io(struct multipath *m, struct request *clone,
         if (!error && !clone->errors)
                 return 0;       /* I/O complete */
 
-        if (error == -EOPNOTSUPP || error == -EREMOTEIO)
+        if (error == -EOPNOTSUPP || error == -EREMOTEIO || error == -EILSEQ)
                 return error;
 
         if (mpio->pgpath)
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 976ad4688afc..9bfd057be686 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -22,8 +22,6 @@
 #define DM_MSG_PREFIX "raid1"
 
 #define MAX_RECOVERY 1  /* Maximum number of regions recovered in parallel. */
-#define DM_IO_PAGES 64
-#define DM_KCOPYD_PAGES 64
 
 #define DM_RAID1_HANDLE_ERRORS 0x01
 #define errors_handled(p)       ((p)->features & DM_RAID1_HANDLE_ERRORS)
@@ -887,7 +885,7 @@ static struct mirror_set *alloc_context(unsigned int nr_mirrors,
                 return NULL;
         }
 
-        ms->io_client = dm_io_client_create(DM_IO_PAGES);
+        ms->io_client = dm_io_client_create();
         if (IS_ERR(ms->io_client)) {
                 ti->error = "Error creating dm_io client";
                 mempool_destroy(ms->read_record_pool);
@@ -1117,9 +1115,11 @@ static int mirror_ctr(struct dm_target *ti, unsigned int argc, char **argv)
                 goto err_destroy_wq;
         }
 
-        r = dm_kcopyd_client_create(DM_KCOPYD_PAGES, &ms->kcopyd_client);
-        if (r)
+        ms->kcopyd_client = dm_kcopyd_client_create();
+        if (IS_ERR(ms->kcopyd_client)) {
+                r = PTR_ERR(ms->kcopyd_client);
                 goto err_destroy_wq;
+        }
 
         wakeup_mirrord(ms);
         return 0;
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index 95891dfcbca0..135c2f1fdbfc 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -154,11 +154,6 @@ struct pstore {
         struct workqueue_struct *metadata_wq;
 };
 
-static unsigned sectors_to_pages(unsigned sectors)
-{
-        return DIV_ROUND_UP(sectors, PAGE_SIZE >> 9);
-}
-
 static int alloc_area(struct pstore *ps)
 {
         int r = -ENOMEM;
@@ -318,8 +313,7 @@ static int read_header(struct pstore *ps, int *new_snapshot)
                 chunk_size_supplied = 0;
         }
 
-        ps->io_client = dm_io_client_create(sectors_to_pages(ps->store->
-                                                             chunk_size));
+        ps->io_client = dm_io_client_create();
         if (IS_ERR(ps->io_client))
                 return PTR_ERR(ps->io_client);
 
@@ -368,11 +362,6 @@ static int read_header(struct pstore *ps, int *new_snapshot)
                 return r;
         }
 
-        r = dm_io_client_resize(sectors_to_pages(ps->store->chunk_size),
-                                ps->io_client);
-        if (r)
-                return r;
-
         r = alloc_area(ps);
         return r;
 
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index a2d330942cb2..9ecff5f3023a 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -40,11 +40,6 @@ static const char dm_snapshot_merge_target_name[] = "snapshot-merge";
 #define SNAPSHOT_COPY_PRIORITY 2
 
 /*
- * Reserve 1MB for each snapshot initially (with minimum of 1 page).
- */
-#define SNAPSHOT_PAGES (((1UL << 20) >> PAGE_SHIFT) ? : 1)
-
-/*
  * The size of the mempool used to track chunks in use.
  */
 #define MIN_IOS 256
@@ -1116,8 +1111,9 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
                 goto bad_hash_tables;
         }
 
-        r = dm_kcopyd_client_create(SNAPSHOT_PAGES, &s->kcopyd_client);
-        if (r) {
+        s->kcopyd_client = dm_kcopyd_client_create();
+        if (IS_ERR(s->kcopyd_client)) {
+                r = PTR_ERR(s->kcopyd_client);
                 ti->error = "Could not create kcopyd client";
                 goto bad_kcopyd;
         }
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index cb8380c9767f..451c3bb176d2 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -362,6 +362,7 @@ static void close_dev(struct dm_dev_internal *d, struct mapped_device *md)
 static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev,
                                   sector_t start, sector_t len, void *data)
 {
+        struct request_queue *q;
         struct queue_limits *limits = data;
         struct block_device *bdev = dev->bdev;
         sector_t dev_size =
@@ -370,6 +371,22 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev,
                 limits->logical_block_size >> SECTOR_SHIFT;
         char b[BDEVNAME_SIZE];
 
+        /*
+         * Some devices exist without request functions,
+         * such as loop devices not yet bound to backing files.
+         * Forbid the use of such devices.
+         */
+        q = bdev_get_queue(bdev);
+        if (!q || !q->make_request_fn) {
+                DMWARN("%s: %s is not yet initialised: "
+                       "start=%llu, len=%llu, dev_size=%llu",
+                       dm_device_name(ti->table->md), bdevname(bdev, b),
+                       (unsigned long long)start,
+                       (unsigned long long)len,
+                       (unsigned long long)dev_size);
+                return 1;
+        }
+
         if (!dev_size)
                 return 0;
 
@@ -1346,7 +1363,8 @@ bool dm_table_supports_discards(struct dm_table *t)
                 return 0;
 
         /*
-         * Ensure that at least one underlying device supports discards.
+         * Unless any target used by the table set discards_supported,
+         * require at least one underlying device to support discards.
          * t->devices includes internal dm devices such as mirror logs
          * so we need to use iterate_devices here, which targets
          * supporting discard must provide.
@@ -1354,6 +1372,9 @@ bool dm_table_supports_discards(struct dm_table *t)
         while (i < dm_table_get_num_targets(t)) {
                 ti = dm_table_get_target(t, i++);
 
+                if (ti->discards_supported)
+                        return 1;
+
                 if (ti->type->iterate_devices &&
                     ti->type->iterate_devices(ti, device_discard_capable, NULL))
                         return 1;
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index b6c267724e14..0f09c057e796 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -721,7 +721,7 @@ config MFD_PM8XXX_IRQ
 
 config MFD_TPS65910
         bool "TPS65910 Power Management chip"
-        depends on I2C=y
+        depends on I2C=y && GPIOLIB
         select MFD_CORE
         select GPIO_TPS65910
         help
diff --git a/drivers/mfd/db8500-prcmu.c b/drivers/mfd/db8500-prcmu.c
index e63782107e2f..02a15d7cb3b0 100644
--- a/drivers/mfd/db8500-prcmu.c
+++ b/drivers/mfd/db8500-prcmu.c
@@ -2005,7 +2005,8 @@ static struct regulator_init_data db8500_regulators[DB8500_NUM_REGULATORS] = {
 static struct mfd_cell db8500_prcmu_devs[] = {
         {
                 .name = "db8500-prcmu-regulators",
-                .mfd_data = &db8500_regulators,
+                .platform_data = &db8500_regulators,
+                .pdata_size = sizeof(db8500_regulators),
         },
         {
                 .name = "cpufreq-u8500",
diff --git a/drivers/misc/kgdbts.c b/drivers/misc/kgdbts.c
index b0c56313dbbb..8cebec5e85ee 100644
--- a/drivers/misc/kgdbts.c
+++ b/drivers/misc/kgdbts.c
@@ -304,7 +304,10 @@ static int check_and_rewind_pc(char *put_str, char *arg)
                 return 1;
         }
         /* Readjust the instruction pointer if needed */
-        instruction_pointer_set(&kgdbts_regs, ip + offset);
+        ip += offset;
+#ifdef GDB_ADJUSTS_BREAK_OFFSET
+        instruction_pointer_set(&kgdbts_regs, ip);
+#endif
         return 0;
 }
 
diff --git a/drivers/misc/ti-st/st_core.c b/drivers/misc/ti-st/st_core.c
index 1a05fe08e2cb..f91f82eabda7 100644
--- a/drivers/misc/ti-st/st_core.c
+++ b/drivers/misc/ti-st/st_core.c
@@ -747,8 +747,8 @@ static void st_tty_close(struct tty_struct *tty)
         pr_debug("%s: done ", __func__);
 }
 
-static unsigned int st_tty_receive(struct tty_struct *tty,
-                const unsigned char *data, char *tty_flags, int count)
+static void st_tty_receive(struct tty_struct *tty, const unsigned char *data,
+                           char *tty_flags, int count)
 {
 #ifdef VERBOSE
         print_hex_dump(KERN_DEBUG, ">in>", DUMP_PREFIX_NONE,
@@ -761,8 +761,6 @@ static unsigned int st_tty_receive(struct tty_struct *tty,
          */
         st_recv(tty->disc_data, data, count);
         pr_debug("done %s", __func__);
-
-        return count;
 }
 
 /* wake-up function called in from the TTY layer
diff --git a/drivers/net/3c509.c b/drivers/net/3c509.c
index 5f25889e27ef..44b28b2d7003 100644
--- a/drivers/net/3c509.c
+++ b/drivers/net/3c509.c
@@ -185,7 +185,7 @@ static int max_interrupt_work = 10;
 static int nopnp;
 #endif
 
-static int el3_common_init(struct net_device *dev);
+static int __devinit el3_common_init(struct net_device *dev);
 static void el3_common_remove(struct net_device *dev);
 static ushort id_read_eeprom(int index);
 static ushort read_eeprom(int ioaddr, int index);
@@ -395,7 +395,7 @@ static struct isa_driver el3_isa_driver = {
 static int isa_registered;
 
 #ifdef CONFIG_PNP
-static const struct pnp_device_id el3_pnp_ids[] __devinitconst = {
+static struct pnp_device_id el3_pnp_ids[] = {
         { .id = "TCM5090" }, /* 3Com Etherlink III (TP) */
         { .id = "TCM5091" }, /* 3Com Etherlink III */
         { .id = "TCM5094" }, /* 3Com Etherlink III (combo) */
@@ -478,7 +478,7 @@ static int pnp_registered;
 #endif /* CONFIG_PNP */
 
 #ifdef CONFIG_EISA
-static const struct eisa_device_id el3_eisa_ids[] __devinitconst = {
+static struct eisa_device_id el3_eisa_ids[] = {
                 { "TCM5090" },
                 { "TCM5091" },
                 { "TCM5092" },
@@ -508,7 +508,7 @@ static int eisa_registered;
 #ifdef CONFIG_MCA
 static int el3_mca_probe(struct device *dev);
 
-static const short el3_mca_adapter_ids[] __devinitconst = {
+static short el3_mca_adapter_ids[] __initdata = {
                 0x627c,
                 0x627d,
                 0x62db,
@@ -517,7 +517,7 @@ static const short el3_mca_adapter_ids[] __devinitconst = {
                 0x0000
 };
 
-static const char *const el3_mca_adapter_names[] __devinitconst = {
+static char *el3_mca_adapter_names[] __initdata = {
                 "3Com 3c529 EtherLink III (10base2)",
                 "3Com 3c529 EtherLink III (10baseT)",
                 "3Com 3c529 EtherLink III (test mode)",
@@ -601,7 +601,7 @@ static void el3_common_remove (struct net_device *dev)
 }
 
 #ifdef CONFIG_MCA
-static int __devinit el3_mca_probe(struct device *device)
+static int __init el3_mca_probe(struct device *device)
 {
         /* Based on Erik Nygren's (nygren@mit.edu) 3c529 patch,
          * heavily modified by Chris Beauregard
@@ -671,7 +671,7 @@ static int __devinit el3_mca_probe(struct device *device)
 #endif /* CONFIG_MCA */
 
 #ifdef CONFIG_EISA
-static int __devinit el3_eisa_probe (struct device *device)
+static int __init el3_eisa_probe (struct device *device)
 {
         short i;
         int ioaddr, irq, if_port;
diff --git a/drivers/net/3c59x.c b/drivers/net/3c59x.c
index 99f43d275442..8cc22568ebd3 100644
--- a/drivers/net/3c59x.c
+++ b/drivers/net/3c59x.c
@@ -901,14 +901,14 @@ static const struct dev_pm_ops vortex_pm_ops = {
 #endif /* !CONFIG_PM */
 
 #ifdef CONFIG_EISA
-static const struct eisa_device_id vortex_eisa_ids[] __devinitconst = {
+static struct eisa_device_id vortex_eisa_ids[] = {
         { "TCM5920", CH_3C592 },
         { "TCM5970", CH_3C597 },
         { "" }
 };
 MODULE_DEVICE_TABLE(eisa, vortex_eisa_ids);
 
-static int __devinit vortex_eisa_probe(struct device *device)
+static int __init vortex_eisa_probe(struct device *device)
 {
         void __iomem *ioaddr;
         struct eisa_device *edev;
diff --git a/drivers/net/caif/caif_serial.c b/drivers/net/caif/caif_serial.c
index 73c7e03617ec..3df0c0f8b8bf 100644
--- a/drivers/net/caif/caif_serial.c
+++ b/drivers/net/caif/caif_serial.c
@@ -167,8 +167,8 @@ static inline void debugfs_tx(struct ser_device *ser, const u8 *data, int size)
 
 #endif
 
-static unsigned int ldisc_receive(struct tty_struct *tty,
-                const u8 *data, char *flags, int count)
+static void ldisc_receive(struct tty_struct *tty, const u8 *data,
+                        char *flags, int count)
 {
         struct sk_buff *skb = NULL;
         struct ser_device *ser;
@@ -215,8 +215,6 @@ static unsigned int ldisc_receive(struct tty_struct *tty,
         } else
                 ++ser->dev->stats.rx_dropped;
         update_tty_status(ser);
-
-        return count;
 }
 
 static int handle_tx(struct ser_device *ser)
diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index d4990568baee..17678117ed69 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -923,7 +923,7 @@ static int __devinit flexcan_probe(struct platform_device *pdev)
         mem_size = resource_size(mem);
         if (!request_mem_region(mem->start, mem_size, pdev->name)) {
                 err = -EBUSY;
-                goto failed_req;
+                goto failed_get;
         }
 
         base = ioremap(mem->start, mem_size);
@@ -977,9 +977,8 @@ static int __devinit flexcan_probe(struct platform_device *pdev)
         iounmap(base);
  failed_map:
         release_mem_region(mem->start, mem_size);
- failed_req:
-        clk_put(clk);
  failed_get:
+        clk_put(clk);
  failed_clock:
         return err;
 }
diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c
index 75622d54581f..1b49df6b2470 100644
--- a/drivers/net/can/slcan.c
+++ b/drivers/net/can/slcan.c
@@ -425,17 +425,16 @@ static void slc_setup(struct net_device *dev)
  * in parallel
  */
 
-static unsigned int slcan_receive_buf(struct tty_struct *tty,
+static void slcan_receive_buf(struct tty_struct *tty,
                               const unsigned char *cp, char *fp, int count)
 {
         struct slcan *sl = (struct slcan *) tty->disc_data;
-        int bytes = count;
 
         if (!sl || sl->magic != SLCAN_MAGIC || !netif_running(sl->dev))
-                return -ENODEV;
+                return;
 
         /* Read the characters out of the buffer */
-        while (bytes--) {
+        while (count--) {
                 if (fp && *fp++) {
                         if (!test_and_set_bit(SLF_ERROR, &sl->flags))
                                 sl->dev->stats.rx_errors++;
@@ -444,8 +443,6 @@ static unsigned int slcan_receive_buf(struct tty_struct *tty,
                 }
                 slcan_unesc(sl, *cp++);
         }
-
-        return count;
 }
 
 /************************************
diff --git a/drivers/net/davinci_emac.c b/drivers/net/davinci_emac.c
index 29a4f06fbfcf..dcc4a170b0f3 100644
--- a/drivers/net/davinci_emac.c
+++ b/drivers/net/davinci_emac.c
@@ -1781,8 +1781,8 @@ static int __devinit davinci_emac_probe(struct platform_device *pdev)
         ndev = alloc_etherdev(sizeof(struct emac_priv));
         if (!ndev) {
                 dev_err(&pdev->dev, "error allocating net_device\n");
-                clk_put(emac_clk);
-                return -ENOMEM;
+                rc = -ENOMEM;
+                goto free_clk;
         }
 
         platform_set_drvdata(pdev, ndev);
@@ -1796,7 +1796,8 @@ static int __devinit davinci_emac_probe(struct platform_device *pdev)
         pdata = pdev->dev.platform_data;
         if (!pdata) {
                 dev_err(&pdev->dev, "no platform data\n");
-                return -ENODEV;
+                rc = -ENODEV;
+                goto probe_quit;
         }
 
         /* MAC addr and PHY mask , RMII enable info from platform_data */
@@ -1929,8 +1930,9 @@ no_dma:
         iounmap(priv->remap_addr);
 
 probe_quit:
-        clk_put(emac_clk);
         free_netdev(ndev);
+free_clk:
+        clk_put(emac_clk);
         return rc;
 }
 
diff --git a/drivers/net/depca.c b/drivers/net/depca.c
index 17654059922d..8b0084d17c8c 100644
--- a/drivers/net/depca.c
+++ b/drivers/net/depca.c
@@ -331,18 +331,18 @@ static struct {
                          "DE422",\
                          ""}
 
-static const char* const depca_signature[] __devinitconst = DEPCA_SIGNATURE;
+static char* __initdata depca_signature[] = DEPCA_SIGNATURE;
 
 enum depca_type {
         DEPCA, de100, de101, de200, de201, de202, de210, de212, de422, unknown
 };
 
-static const char depca_string[] = "depca";
+static char depca_string[] = "depca";
 
 static int depca_device_remove (struct device *device);
 
 #ifdef CONFIG_EISA
-static const struct eisa_device_id depca_eisa_ids[] __devinitconst = {
+static struct eisa_device_id depca_eisa_ids[] = {
         { "DEC4220", de422 },
         { "" }
 };
@@ -367,19 +367,19 @@ static struct eisa_driver depca_eisa_driver = {
 #define DE210_ID 0x628d
 #define DE212_ID 0x6def
 
-static const short depca_mca_adapter_ids[] __devinitconst = {
+static short depca_mca_adapter_ids[] = {
         DE210_ID,
         DE212_ID,
         0x0000
 };
 
-static const char *depca_mca_adapter_name[] = {
+static char *depca_mca_adapter_name[] = {
         "DEC EtherWORKS MC Adapter (DE210)",
         "DEC EtherWORKS MC Adapter (DE212)",
         NULL
 };
 
-static const enum depca_type depca_mca_adapter_type[] = {
+static enum depca_type depca_mca_adapter_type[] = {
         de210,
         de212,
         0
@@ -541,9 +541,10 @@ static void SetMulticastFilter(struct net_device *dev);
 static int load_packet(struct net_device *dev, struct sk_buff *skb);
 static void depca_dbg_open(struct net_device *dev);
 
-static const u_char de1xx_irq[] __devinitconst = { 2, 3, 4, 5, 7, 9, 0 };
-static const u_char de2xx_irq[] __devinitconst = { 5, 9, 10, 11, 15, 0 };
-static const u_char de422_irq[] __devinitconst = { 5, 9, 10, 11, 0 };
+static u_char de1xx_irq[] __initdata = { 2, 3, 4, 5, 7, 9, 0 };
+static u_char de2xx_irq[] __initdata = { 5, 9, 10, 11, 15, 0 };
+static u_char de422_irq[] __initdata = { 5, 9, 10, 11, 0 };
+static u_char *depca_irq;
 
 static int irq;
 static int io;
@@ -579,7 +580,7 @@ static const struct net_device_ops depca_netdev_ops = {
         .ndo_validate_addr      = eth_validate_addr,
 };
 
-static int __devinit depca_hw_init (struct net_device *dev, struct device *device)
+static int __init depca_hw_init (struct net_device *dev, struct device *device)
 {
         struct depca_private *lp;
         int i, j, offset, netRAM, mem_len, status = 0;
@@ -747,7 +748,6 @@ static int __devinit depca_hw_init (struct net_device *dev, struct device *devic
         if (dev->irq < 2) {
                 unsigned char irqnum;
                 unsigned long irq_mask, delay;
-                const u_char *depca_irq;
 
                 irq_mask = probe_irq_on();
 
@@ -770,7 +770,6 @@ static int __devinit depca_hw_init (struct net_device *dev, struct device *devic
                         break;
 
                 default:
-                        depca_irq = NULL;
                         break;  /* Not reached */
                 }
 
@@ -1303,7 +1302,7 @@ static void SetMulticastFilter(struct net_device *dev)
         }
 }
 
-static int __devinit depca_common_init (u_long ioaddr, struct net_device **devp)
+static int __init depca_common_init (u_long ioaddr, struct net_device **devp)
 {
         int status = 0;
 
@@ -1334,7 +1333,7 @@ static int __devinit depca_common_init (u_long ioaddr, struct net_device **devp)
 /*
 ** Microchannel bus I/O device probe
 */
-static int __devinit depca_mca_probe(struct device *device)
+static int __init depca_mca_probe(struct device *device)
 {
         unsigned char pos[2];
         unsigned char where;
@@ -1458,7 +1457,7 @@ static int __devinit depca_mca_probe(struct device *device)
 ** ISA bus I/O device probe
 */
 
-static void __devinit depca_platform_probe (void)
+static void __init depca_platform_probe (void)
 {
         int i;
         struct platform_device *pldev;
@@ -1498,7 +1497,7 @@ static void __devinit depca_platform_probe (void)
         }
 }
 
-static enum depca_type __devinit depca_shmem_probe (ulong *mem_start)
+static enum depca_type __init depca_shmem_probe (ulong *mem_start)
 {
         u_long mem_base[] = DEPCA_RAM_BASE_ADDRESSES;
         enum depca_type adapter = unknown;
@@ -1559,7 +1558,7 @@ static int __devinit depca_isa_probe (struct platform_device *device)
 */
 
 #ifdef CONFIG_EISA
-static int __devinit depca_eisa_probe (struct device *device)
+static int __init depca_eisa_probe (struct device *device)
 {
         enum depca_type adapter = unknown;
         struct eisa_device *edev;
@@ -1630,7 +1629,7 @@ static int __devexit depca_device_remove (struct device *device)
 ** and Boot (readb) ROM. This will also give us a clue to the network RAM
 ** base address.
 */
-static int __devinit DepcaSignature(char *name, u_long base_addr)
+static int __init DepcaSignature(char *name, u_long base_addr)
 {
         u_int i, j, k;
         void __iomem *ptr;
diff --git a/drivers/net/dm9000.c b/drivers/net/dm9000.c
index fbaff3584bd4..ee597e676ee5 100644
--- a/drivers/net/dm9000.c
+++ b/drivers/net/dm9000.c
@@ -1157,9 +1157,6 @@ dm9000_open(struct net_device *dev)
 
         irqflags |= IRQF_SHARED;
 
-        if (request_irq(dev->irq, dm9000_interrupt, irqflags, dev->name, dev))
-                return -EAGAIN;
-
         /* GPIO0 on pre-activate PHY, Reg 1F is not set by reset */
         iow(db, DM9000_GPR, 0); /* REG_1F bit0 activate phyxcer */
         mdelay(1); /* delay needs by DM9000B */
@@ -1168,6 +1165,9 @@ dm9000_open(struct net_device *dev)
         dm9000_reset(db);
         dm9000_init_dm9000(dev);
 
+        if (request_irq(dev->irq, dm9000_interrupt, irqflags, dev->name, dev))
+                return -EAGAIN;
+
         /* Init driver variable */
         db->dbug_cnt = 0;
 
diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c
index 992089639ea4..3e5d0b6b6516 100644
--- a/drivers/net/hamradio/6pack.c
+++ b/drivers/net/hamradio/6pack.c
@@ -456,7 +456,7 @@ out:
  * a block of 6pack data has been received, which can now be decapsulated
  * and sent on to some IP layer for further processing.
  */
-static unsigned int sixpack_receive_buf(struct tty_struct *tty,
+static void sixpack_receive_buf(struct tty_struct *tty,
         const unsigned char *cp, char *fp, int count)
 {
         struct sixpack *sp;
@@ -464,11 +464,11 @@ static unsigned int sixpack_receive_buf(struct tty_struct *tty,
         int count1;
 
         if (!count)
-                return 0;
+                return;
 
         sp = sp_get(tty);
         if (!sp)
-                return -ENODEV;
+                return;
 
         memcpy(buf, cp, count < sizeof(buf) ? count : sizeof(buf));
 
@@ -487,8 +487,6 @@ static unsigned int sixpack_receive_buf(struct tty_struct *tty,
 
         sp_put(sp);
         tty_unthrottle(tty);
-
-        return count1;
 }
 
 /*
diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c
index 0e4f23531140..4c628393c8b1 100644
--- a/drivers/net/hamradio/mkiss.c
+++ b/drivers/net/hamradio/mkiss.c
@@ -923,14 +923,13 @@ static long mkiss_compat_ioctl(struct tty_struct *tty, struct file *file,
  * a block of data has been received, which can now be decapsulated
  * and sent on to the AX.25 layer for further processing.
  */
-static unsigned int mkiss_receive_buf(struct tty_struct *tty,
-                const unsigned char *cp, char *fp, int count)
+static void mkiss_receive_buf(struct tty_struct *tty, const unsigned char *cp,
+        char *fp, int count)
 {
         struct mkiss *ax = mkiss_get(tty);
-        int bytes = count;
 
         if (!ax)
-                return -ENODEV;
+                return;
 
         /*
          * Argh! mtu change time! - costs us the packet part received
@@ -940,7 +939,7 @@ static unsigned int mkiss_receive_buf(struct tty_struct *tty,
                 ax_changedmtu(ax);
 
         /* Read the characters out of the buffer */
-        while (bytes--) {
+        while (count--) {
                 if (fp != NULL && *fp++) {
                         if (!test_and_set_bit(AXF_ERROR, &ax->flags))
                                 ax->dev->stats.rx_errors++;
@@ -953,8 +952,6 @@ static unsigned int mkiss_receive_buf(struct tty_struct *tty,
 
         mkiss_put(ax);
         tty_unthrottle(tty);
-
-        return count;
 }
 
 /*
diff --git a/drivers/net/hp100.c b/drivers/net/hp100.c
index c52a1df5d922..8e10d2f6a5ad 100644
--- a/drivers/net/hp100.c
+++ b/drivers/net/hp100.c
@@ -188,14 +188,14 @@ struct hp100_private {
  *  variables
  */
 #ifdef CONFIG_ISA
-static const char *const hp100_isa_tbl[] __devinitconst = {
+static const char *hp100_isa_tbl[] = {
         "HWPF150", /* HP J2573 rev A */
         "HWP1950", /* HP J2573 */
 };
 #endif
 
 #ifdef CONFIG_EISA
-static const struct eisa_device_id hp100_eisa_tbl[] __devinitconst = {
+static struct eisa_device_id hp100_eisa_tbl[] = {
         { "HWPF180" }, /* HP J2577 rev A */
         { "HWP1920" }, /* HP 27248B */
         { "HWP1940" }, /* HP J2577 */
@@ -336,7 +336,7 @@ static __devinit const char *hp100_read_id(int ioaddr)
 }
 
 #ifdef CONFIG_ISA
-static __devinit int hp100_isa_probe1(struct net_device *dev, int ioaddr)
+static __init int hp100_isa_probe1(struct net_device *dev, int ioaddr)
 {
         const char *sig;
         int i;
@@ -372,7 +372,7 @@ static __devinit int hp100_isa_probe1(struct net_device *dev, int ioaddr)
  * EISA and PCI are handled by device infrastructure.
  */
 
-static int  __devinit hp100_isa_probe(struct net_device *dev, int addr)
+static int  __init hp100_isa_probe(struct net_device *dev, int addr)
 {
         int err = -ENODEV;
 
@@ -396,7 +396,7 @@ static int  __devinit hp100_isa_probe(struct net_device *dev, int addr)
 #endif /* CONFIG_ISA */
 
 #if !defined(MODULE) && defined(CONFIG_ISA)
-struct net_device * __devinit hp100_probe(int unit)
+struct net_device * __init hp100_probe(int unit)
 {
         struct net_device *dev = alloc_etherdev(sizeof(struct hp100_private));
         int err;
@@ -2843,7 +2843,7 @@ static void cleanup_dev(struct net_device *d)
 }
 
 #ifdef CONFIG_EISA
-static int __devinit hp100_eisa_probe (struct device *gendev)
+static int __init hp100_eisa_probe (struct device *gendev)
 {
         struct net_device *dev = alloc_etherdev(sizeof(struct hp100_private));
         struct eisa_device *edev = to_eisa_device(gendev);
diff --git a/drivers/net/ibmlana.c b/drivers/net/ibmlana.c
index 136d7544cc33..a7d6cad32953 100644
--- a/drivers/net/ibmlana.c
+++ b/drivers/net/ibmlana.c
@@ -895,12 +895,12 @@ static int ibmlana_irq;
 static int ibmlana_io;
 static int startslot;           /* counts through slots when probing multiple devices */
 
-static const short ibmlana_adapter_ids[] __devinitconst = {
+static short ibmlana_adapter_ids[] __initdata = {
         IBM_LANA_ID,
         0x0000
 };
 
-static const char *const ibmlana_adapter_names[] __devinitconst = {
+static char *ibmlana_adapter_names[] __devinitdata = {
         "IBM LAN Adapter/A",
         NULL
 };
diff --git a/drivers/net/irda/irtty-sir.c b/drivers/net/irda/irtty-sir.c
index 035861d8acb1..3352b2443e58 100644
--- a/drivers/net/irda/irtty-sir.c
+++ b/drivers/net/irda/irtty-sir.c
@@ -216,23 +216,23 @@ static int irtty_do_write(struct sir_dev *dev, const unsigned char *ptr, size_t
  * usbserial:   urb-complete-interrupt / softint
  */
 
-static unsigned int irtty_receive_buf(struct tty_struct *tty,
-                const unsigned char *cp, char *fp, int count)
+static void irtty_receive_buf(struct tty_struct *tty, const unsigned char *cp,
+                              char *fp, int count) 
 {
         struct sir_dev *dev;
         struct sirtty_cb *priv = tty->disc_data;
         int     i;
 
-        IRDA_ASSERT(priv != NULL, return -ENODEV;);
-        IRDA_ASSERT(priv->magic == IRTTY_MAGIC, return -EINVAL;);
+        IRDA_ASSERT(priv != NULL, return;);
+        IRDA_ASSERT(priv->magic == IRTTY_MAGIC, return;);
 
         if (unlikely(count==0))         /* yes, this happens */
-                return 0;
+                return;
 
         dev = priv->dev;
         if (!dev) {
                 IRDA_WARNING("%s(), not ready yet!\n", __func__);
-                return -ENODEV;
+                return;
         }
 
         for (i = 0; i < count; i++) {
@@ -242,13 +242,11 @@ static unsigned int irtty_receive_buf(struct tty_struct *tty,
                 if (fp && *fp++) { 
                         IRDA_DEBUG(0, "Framing or parity error!\n");
                         sirdev_receive(dev, NULL, 0);   /* notify sir_dev (updating stats) */
-                        return -EINVAL;
+                        return;
                 }
         }
 
         sirdev_receive(dev, cp, count);
-
-        return count;
 }
 
 /*
diff --git a/drivers/net/irda/smsc-ircc2.c b/drivers/net/irda/smsc-ircc2.c
index 69b5707db369..8800e1fe4129 100644
--- a/drivers/net/irda/smsc-ircc2.c
+++ b/drivers/net/irda/smsc-ircc2.c
@@ -222,19 +222,19 @@ static void smsc_ircc_set_transceiver_for_speed(struct smsc_ircc_cb *self, u32 s
 static void smsc_ircc_sir_wait_hw_transmitter_finish(struct smsc_ircc_cb *self);
 
 /* Probing */
-static int smsc_ircc_look_for_chips(void);
-static const struct smsc_chip * smsc_ircc_probe(unsigned short cfg_base, u8 reg, const struct smsc_chip *chip, char *type);
-static int smsc_superio_flat(const struct smsc_chip *chips, unsigned short cfg_base, char *type);
-static int smsc_superio_paged(const struct smsc_chip *chips, unsigned short cfg_base, char *type);
-static int smsc_superio_fdc(unsigned short cfg_base);
-static int smsc_superio_lpc(unsigned short cfg_base);
+static int __init smsc_ircc_look_for_chips(void);
+static const struct smsc_chip * __init smsc_ircc_probe(unsigned short cfg_base, u8 reg, const struct smsc_chip *chip, char *type);
+static int __init smsc_superio_flat(const struct smsc_chip *chips, unsigned short cfg_base, char *type);
+static int __init smsc_superio_paged(const struct smsc_chip *chips, unsigned short cfg_base, char *type);
+static int __init smsc_superio_fdc(unsigned short cfg_base);
+static int __init smsc_superio_lpc(unsigned short cfg_base);
 #ifdef CONFIG_PCI
-static int preconfigure_smsc_chip(struct smsc_ircc_subsystem_configuration *conf);
-static int preconfigure_through_82801(struct pci_dev *dev, struct smsc_ircc_subsystem_configuration *conf);
-static void preconfigure_ali_port(struct pci_dev *dev,
+static int __init preconfigure_smsc_chip(struct smsc_ircc_subsystem_configuration *conf);
+static int __init preconfigure_through_82801(struct pci_dev *dev, struct smsc_ircc_subsystem_configuration *conf);
+static void __init preconfigure_ali_port(struct pci_dev *dev,
                                          unsigned short port);
-static int preconfigure_through_ali(struct pci_dev *dev, struct smsc_ircc_subsystem_configuration *conf);
-static int smsc_ircc_preconfigure_subsystems(unsigned short ircc_cfg,
+static int __init preconfigure_through_ali(struct pci_dev *dev, struct smsc_ircc_subsystem_configuration *conf);
+static int __init smsc_ircc_preconfigure_subsystems(unsigned short ircc_cfg,
                                                     unsigned short ircc_fir,
                                                     unsigned short ircc_sir,
                                                     unsigned char ircc_dma,
@@ -366,7 +366,7 @@ static inline void register_bank(int iobase, int bank)
 }
 
 /* PNP hotplug support */
-static const struct pnp_device_id smsc_ircc_pnp_table[] __devinitconst = {
+static const struct pnp_device_id smsc_ircc_pnp_table[] = {
         { .id = "SMCf010", .driver_data = 0 },
         /* and presumably others */
         { }
@@ -515,7 +515,7 @@ static const struct net_device_ops smsc_ircc_netdev_ops = {
  *    Try to open driver instance
  *
  */
-static int __devinit smsc_ircc_open(unsigned int fir_base, unsigned int sir_base, u8 dma, u8 irq)
+static int __init smsc_ircc_open(unsigned int fir_base, unsigned int sir_base, u8 dma, u8 irq)
 {
         struct smsc_ircc_cb *self;
         struct net_device *dev;
@@ -2273,7 +2273,7 @@ static int __init smsc_superio_paged(const struct smsc_chip *chips, unsigned sho
 }
 
 
-static int __devinit smsc_access(unsigned short cfg_base, unsigned char reg)
+static int __init smsc_access(unsigned short cfg_base, unsigned char reg)
 {
         IRDA_DEBUG(1, "%s\n", __func__);
 
@@ -2281,7 +2281,7 @@ static int __devinit smsc_access(unsigned short cfg_base, unsigned char reg)
         return inb(cfg_base) != reg ? -1 : 0;
 }
 
-static const struct smsc_chip * __devinit smsc_ircc_probe(unsigned short cfg_base, u8 reg, const struct smsc_chip *chip, char *type)
+static const struct smsc_chip * __init smsc_ircc_probe(unsigned short cfg_base, u8 reg, const struct smsc_chip *chip, char *type)
 {
         u8 devid, xdevid, rev;
 
@@ -2406,7 +2406,7 @@ static int __init smsc_superio_lpc(unsigned short cfg_base)
 #ifdef CONFIG_PCI
 #define PCIID_VENDOR_INTEL 0x8086
 #define PCIID_VENDOR_ALI 0x10b9
-static const struct smsc_ircc_subsystem_configuration subsystem_configurations[] __devinitconst = {
+static struct smsc_ircc_subsystem_configuration subsystem_configurations[] __initdata = {
         /*
          * Subsystems needing entries:
          * 0x10b9:0x1533 0x103c:0x0850 HP nx9010 family
@@ -2532,7 +2532,7 @@ static const struct smsc_ircc_subsystem_configuration subsystem_configurations[]
  * (FIR port, SIR port, FIR DMA, FIR IRQ)
  * through the chip configuration port.
  */
-static int __devinit preconfigure_smsc_chip(struct
+static int __init preconfigure_smsc_chip(struct
                                          smsc_ircc_subsystem_configuration
                                          *conf)
 {
@@ -2633,7 +2633,7 @@ static int __devinit preconfigure_smsc_chip(struct
  * or Intel 82801DB/DBL (ICH4/ICH4-L) LPC Interface Bridge.
  * They all work the same way!
  */
-static int __devinit preconfigure_through_82801(struct pci_dev *dev,
+static int __init preconfigure_through_82801(struct pci_dev *dev,
                                              struct
                                              smsc_ircc_subsystem_configuration
                                              *conf)
@@ -2786,7 +2786,7 @@ static int __devinit preconfigure_through_82801(struct pci_dev *dev,
  * This is based on reverse-engineering since ALi does not
  * provide any data sheet for the 1533 chip.
  */
-static void __devinit preconfigure_ali_port(struct pci_dev *dev,
+static void __init preconfigure_ali_port(struct pci_dev *dev,
                                          unsigned short port)
 {
         unsigned char reg;
@@ -2824,7 +2824,7 @@ static void __devinit preconfigure_ali_port(struct pci_dev *dev,
         IRDA_MESSAGE("Activated ALi 1533 ISA bridge port 0x%04x.\n", port);
 }
 
-static int __devinit preconfigure_through_ali(struct pci_dev *dev,
+static int __init preconfigure_through_ali(struct pci_dev *dev,
                                            struct
                                            smsc_ircc_subsystem_configuration
                                            *conf)
@@ -2837,7 +2837,7 @@ static int __devinit preconfigure_through_ali(struct pci_dev *dev,
         return preconfigure_smsc_chip(conf);
 }
 
-static int __devinit smsc_ircc_preconfigure_subsystems(unsigned short ircc_cfg,
+static int __init smsc_ircc_preconfigure_subsystems(unsigned short ircc_cfg,
                                                     unsigned short ircc_fir,
                                                     unsigned short ircc_sir,
                                                     unsigned char ircc_dma,
@@ -2849,7 +2849,7 @@ static int __devinit smsc_ircc_preconfigure_subsystems(unsigned short ircc_cfg,
         int ret = 0;
 
         for_each_pci_dev(dev) {
-                const struct smsc_ircc_subsystem_configuration *conf;
+                struct smsc_ircc_subsystem_configuration *conf;
 
                 /*
                  * Cache the subsystem vendor/device:
diff --git a/drivers/net/ks8842.c b/drivers/net/ks8842.c
index 4d40626b3bfa..fc12ac0d9f2e 100644
--- a/drivers/net/ks8842.c
+++ b/drivers/net/ks8842.c
@@ -661,7 +661,7 @@ static void ks8842_rx_frame(struct net_device *netdev,
 
         /* check the status */
         if ((status & RXSR_VALID) && !(status & RXSR_ERROR)) {
-                struct sk_buff *skb = netdev_alloc_skb_ip_align(netdev, len);
+                struct sk_buff *skb = netdev_alloc_skb_ip_align(netdev, len + 3);
 
                 if (skb) {
 
diff --git a/drivers/net/ne3210.c b/drivers/net/ne3210.c
index e8984b0ca521..243ed2aee88e 100644
--- a/drivers/net/ne3210.c
+++ b/drivers/net/ne3210.c
@@ -80,20 +80,17 @@ static void ne3210_block_output(struct net_device *dev, int count, const unsigne
 
 #define NE3210_DEBUG    0x0
 
-static const unsigned char irq_map[] __devinitconst =
-        { 15, 12, 11, 10, 9, 7, 5, 3 };
-static const unsigned int shmem_map[] __devinitconst =
-        { 0xff0, 0xfe0, 0xfff0, 0xd8, 0xffe0, 0xffc0, 0xd0, 0x0 };
-static const char *const ifmap[] __devinitconst =
-        { "UTP", "?", "BNC", "AUI" };
-static const int ifmap_val[] __devinitconst = {
+static unsigned char irq_map[] __initdata = {15, 12, 11, 10, 9, 7, 5, 3};
+static unsigned int shmem_map[] __initdata = {0xff0, 0xfe0, 0xfff0, 0xd8, 0xffe0, 0xffc0, 0xd0, 0x0};
+static const char *ifmap[] __initdata = {"UTP", "?", "BNC", "AUI"};
+static int ifmap_val[] __initdata = {
                 IF_PORT_10BASET,
                 IF_PORT_UNKNOWN,
                 IF_PORT_10BASE2,
                 IF_PORT_AUI,
 };
 
-static int __devinit ne3210_eisa_probe (struct device *device)
+static int __init ne3210_eisa_probe (struct device *device)
 {
         unsigned long ioaddr, phys_mem;
         int i, retval, port_index;
@@ -316,7 +313,7 @@ static void ne3210_block_output(struct net_device *dev, int count,
         memcpy_toio(shmem, buf, count);
 }
 
-static const struct eisa_device_id ne3210_ids[] __devinitconst = {
+static struct eisa_device_id ne3210_ids[] = {
         { "EGL0101" },
         { "NVL1801" },
         { "" },
diff --git a/drivers/net/ppp_async.c b/drivers/net/ppp_async.c
index 53872d7d7382..a1b82c9c67d2 100644
--- a/drivers/net/ppp_async.c
+++ b/drivers/net/ppp_async.c
@@ -340,7 +340,7 @@ ppp_asynctty_poll(struct tty_struct *tty, struct file *file, poll_table *wait)
 }
 
 /* May sleep, don't call from interrupt level or with interrupts disabled */
-static unsigned int
+static void
 ppp_asynctty_receive(struct tty_struct *tty, const unsigned char *buf,
                   char *cflags, int count)
 {
@@ -348,7 +348,7 @@ ppp_asynctty_receive(struct tty_struct *tty, const unsigned char *buf,
         unsigned long flags;
 
         if (!ap)
-                return -ENODEV;
+                return;
         spin_lock_irqsave(&ap->recv_lock, flags);
         ppp_async_input(ap, buf, cflags, count);
         spin_unlock_irqrestore(&ap->recv_lock, flags);
@@ -356,8 +356,6 @@ ppp_asynctty_receive(struct tty_struct *tty, const unsigned char *buf,
                 tasklet_schedule(&ap->tsk);
         ap_put(ap);
         tty_unthrottle(tty);
-
-        return count;
 }
 
 static void
diff --git a/drivers/net/ppp_synctty.c b/drivers/net/ppp_synctty.c
index 0815790a5cf9..2573f525f11c 100644
--- a/drivers/net/ppp_synctty.c
+++ b/drivers/net/ppp_synctty.c
@@ -381,7 +381,7 @@ ppp_sync_poll(struct tty_struct *tty, struct file *file, poll_table *wait)
 }
 
 /* May sleep, don't call from interrupt level or with interrupts disabled */
-static unsigned int
+static void
 ppp_sync_receive(struct tty_struct *tty, const unsigned char *buf,
                   char *cflags, int count)
 {
@@ -389,7 +389,7 @@ ppp_sync_receive(struct tty_struct *tty, const unsigned char *buf,
         unsigned long flags;
 
         if (!ap)
-                return -ENODEV;
+                return;
         spin_lock_irqsave(&ap->recv_lock, flags);
         ppp_sync_input(ap, buf, cflags, count);
         spin_unlock_irqrestore(&ap->recv_lock, flags);
@@ -397,8 +397,6 @@ ppp_sync_receive(struct tty_struct *tty, const unsigned char *buf,
                 tasklet_schedule(&ap->tsk);
         sp_put(ap);
         tty_unthrottle(tty);
-
-        return count;
 }
 
 static void
diff --git a/drivers/net/slip.c b/drivers/net/slip.c
index 584809c656d5..8ec1a9a0bb9a 100644
--- a/drivers/net/slip.c
+++ b/drivers/net/slip.c
@@ -670,17 +670,16 @@ static void sl_setup(struct net_device *dev)
  * in parallel
  */
 
-static unsigned int slip_receive_buf(struct tty_struct *tty,
-                const unsigned char *cp, char *fp, int count)
+static void slip_receive_buf(struct tty_struct *tty, const unsigned char *cp,
+                                                        char *fp, int count)
 {
         struct slip *sl = tty->disc_data;
-        int bytes = count;
 
         if (!sl || sl->magic != SLIP_MAGIC || !netif_running(sl->dev))
-                return -ENODEV;
+                return;
 
         /* Read the characters out of the buffer */
-        while (bytes--) {
+        while (count--) {
                 if (fp && *fp++) {
                         if (!test_and_set_bit(SLF_ERROR, &sl->flags))
                                 sl->dev->stats.rx_errors++;
@@ -694,8 +693,6 @@ static unsigned int slip_receive_buf(struct tty_struct *tty,
 #endif
                         slip_unesc(sl, *cp++);
         }
-
-        return count;
 }
 
 /************************************
diff --git a/drivers/net/smc-mca.c b/drivers/net/smc-mca.c
index 0f29f261fcfe..d07c39cb4daf 100644
--- a/drivers/net/smc-mca.c
+++ b/drivers/net/smc-mca.c
@@ -156,7 +156,7 @@ static const struct {
    { 14, 15 }
 };
 
-static const short smc_mca_adapter_ids[] __devinitconst = {
+static short smc_mca_adapter_ids[] __initdata = {
         0x61c8,
         0x61c9,
         0x6fc0,
@@ -168,7 +168,7 @@ static const short smc_mca_adapter_ids[] __devinitconst = {
         0x0000
 };
 
-static const char *const smc_mca_adapter_names[] __devinitconst = {
+static char *smc_mca_adapter_names[] __initdata = {
         "SMC Ethercard PLUS Elite/A BNC/AUI (WD8013EP/A)",
         "SMC Ethercard PLUS Elite/A UTP/AUI (WD8013WP/A)",
         "WD Ethercard PLUS/A (WD8003E/A or WD8003ET/A)",
@@ -199,7 +199,7 @@ static const struct net_device_ops ultramca_netdev_ops = {
 #endif
 };
 
-static int __devinit ultramca_probe(struct device *gen_dev)
+static int __init ultramca_probe(struct device *gen_dev)
 {
         unsigned short ioaddr;
         struct net_device *dev;
diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c
index f4b01c638a33..a1f9f9eef37d 100644
--- a/drivers/net/tg3.c
+++ b/drivers/net/tg3.c
@@ -5774,7 +5774,7 @@ static void tg3_skb_error_unmap(struct tg3_napi *tnapi,
                          dma_unmap_addr(txb, mapping),
                          skb_headlen(skb),
                          PCI_DMA_TODEVICE);
-        for (i = 0; i <= last; i++) {
+        for (i = 0; i < last; i++) {
                 skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 
                 entry = NEXT_TX(entry);
diff --git a/drivers/net/tokenring/madgemc.c b/drivers/net/tokenring/madgemc.c
index 1313aa1315f0..2bedc0ace812 100644
--- a/drivers/net/tokenring/madgemc.c
+++ b/drivers/net/tokenring/madgemc.c
@@ -727,7 +727,7 @@ static int __devexit madgemc_remove(struct device *device)
         return 0;
 }
 
-static const short madgemc_adapter_ids[] __devinitconst = {
+static short madgemc_adapter_ids[] __initdata = {
         0x002d,
         0x0000
 };
diff --git a/drivers/net/tulip/de4x5.c b/drivers/net/tulip/de4x5.c
index 45144d5bd11b..efaa1d69b720 100644
--- a/drivers/net/tulip/de4x5.c
+++ b/drivers/net/tulip/de4x5.c
@@ -1995,7 +1995,7 @@ SetMulticastFilter(struct net_device *dev)
 
 static u_char de4x5_irq[] = EISA_ALLOWED_IRQ_LIST;
 
-static int __devinit de4x5_eisa_probe (struct device *gendev)
+static int __init de4x5_eisa_probe (struct device *gendev)
 {
         struct eisa_device *edev;
         u_long iobase;
@@ -2097,7 +2097,7 @@ static int __devexit de4x5_eisa_remove (struct device *device)
         return 0;
 }
 
-static const struct eisa_device_id de4x5_eisa_ids[] __devinitconst = {
+static struct eisa_device_id de4x5_eisa_ids[] = {
         { "DEC4250", 0 },       /* 0 is the board name index... */
         { "" }
 };
diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c
index d7221c4a5dcf..8056f8a27c6a 100644
--- a/drivers/net/usb/catc.c
+++ b/drivers/net/usb/catc.c
@@ -495,7 +495,7 @@ static void catc_ctrl_run(struct catc *catc)
         if (!q->dir && q->buf && q->len)
                 memcpy(catc->ctrl_buf, q->buf, q->len);
 
-        if ((status = usb_submit_urb(catc->ctrl_urb, GFP_KERNEL)))
+        if ((status = usb_submit_urb(catc->ctrl_urb, GFP_ATOMIC)))
                 err("submit(ctrl_urb) status %d", status);
 }
 
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index cdd3ae486109..f33ca6aa29e9 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -54,7 +54,7 @@
 #include <linux/usb/usbnet.h>
 #include <linux/usb/cdc.h>
 
-#define DRIVER_VERSION                          "24-May-2011"
+#define DRIVER_VERSION                          "01-June-2011"
 
 /* CDC NCM subclass 3.2.1 */
 #define USB_CDC_NCM_NDP16_LENGTH_MIN            0x10
@@ -1234,6 +1234,7 @@ static struct usb_driver cdc_ncm_driver = {
         .disconnect = cdc_ncm_disconnect,
         .suspend = usbnet_suspend,
         .resume = usbnet_resume,
+        .reset_resume = usbnet_resume,
         .supports_autosuspend = 1,
 };
 
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 0cb0b0632672..f6853247a620 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -609,7 +609,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
          * before it gets out of hand.  Naturally, this wastes entries. */
         if (capacity < 2+MAX_SKB_FRAGS) {
                 netif_stop_queue(dev);
-                if (unlikely(!virtqueue_enable_cb(vi->svq))) {
+                if (unlikely(!virtqueue_enable_cb_delayed(vi->svq))) {
                         /* More just got used, free them then recheck. */
                         capacity += free_old_xmit_skbs(vi);
                         if (capacity >= 2+MAX_SKB_FRAGS) {
diff --git a/drivers/net/wan/x25_asy.c b/drivers/net/wan/x25_asy.c
index 40398bf7d036..24297b274cd4 100644
--- a/drivers/net/wan/x25_asy.c
+++ b/drivers/net/wan/x25_asy.c
@@ -517,18 +517,17 @@ static int x25_asy_close(struct net_device *dev)
  * and sent on to some IP layer for further processing.
  */
 
-static unsigned int x25_asy_receive_buf(struct tty_struct *tty,
+static void x25_asy_receive_buf(struct tty_struct *tty,
                                 const unsigned char *cp, char *fp, int count)
 {
         struct x25_asy *sl = tty->disc_data;
-        int bytes = count;
 
         if (!sl || sl->magic != X25_ASY_MAGIC || !netif_running(sl->dev))
                 return;
 
 
         /* Read the characters out of the buffer */
-        while (bytes--) {
+        while (count--) {
                 if (fp && *fp++) {
                         if (!test_and_set_bit(SLF_ERROR, &sl->flags))
                                 sl->dev->stats.rx_errors++;
@@ -537,8 +536,6 @@ static unsigned int x25_asy_receive_buf(struct tty_struct *tty,
                 }
                 x25_asy_unesc(sl, *cp++);
         }
-
-        return count;
 }
 
 /*
diff --git a/drivers/net/wireless/ath/ath9k/Kconfig b/drivers/net/wireless/ath/ath9k/Kconfig
index d9ff8413ab9a..d9c08c619a3a 100644
--- a/drivers/net/wireless/ath/ath9k/Kconfig
+++ b/drivers/net/wireless/ath/ath9k/Kconfig
@@ -26,7 +26,6 @@ config ATH9K
 config ATH9K_PCI
         bool "Atheros ath9k PCI/PCIe bus support"
         depends on ATH9K && PCI
-        default PCI
         ---help---
           This option enables the PCI bus support in ath9k.
 
diff --git a/drivers/net/wireless/ath/ath9k/ar9002_calib.c b/drivers/net/wireless/ath/ath9k/ar9002_calib.c
index 015d97439935..2d4c0910295b 100644
--- a/drivers/net/wireless/ath/ath9k/ar9002_calib.c
+++ b/drivers/net/wireless/ath/ath9k/ar9002_calib.c
@@ -829,7 +829,7 @@ static bool ar9002_hw_init_cal(struct ath_hw *ah, struct ath9k_channel *chan)
         if (AR_SREV_9271(ah)) {
                 if (!ar9285_hw_cl_cal(ah, chan))
                         return false;
-        } else if (AR_SREV_9285_12_OR_LATER(ah)) {
+        } else if (AR_SREV_9285(ah) && AR_SREV_9285_12_OR_LATER(ah)) {
                 if (!ar9285_hw_clc(ah, chan))
                         return false;
         } else {
diff --git a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
index 0ca7635d0669..ff8150e46f0e 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
+++ b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
@@ -4645,10 +4645,16 @@ static void ar9003_hw_set_power_per_rate_table(struct ath_hw *ah,
         case 1:
                 break;
         case 2:
-                scaledPower -= REDUCE_SCALED_POWER_BY_TWO_CHAIN;
+                if (scaledPower > REDUCE_SCALED_POWER_BY_TWO_CHAIN)
+                        scaledPower -= REDUCE_SCALED_POWER_BY_TWO_CHAIN;
+                else
+                        scaledPower = 0;
                 break;
         case 3:
-                scaledPower -= REDUCE_SCALED_POWER_BY_THREE_CHAIN;
+                if (scaledPower > REDUCE_SCALED_POWER_BY_THREE_CHAIN)
+                        scaledPower -= REDUCE_SCALED_POWER_BY_THREE_CHAIN;
+                else
+                        scaledPower = 0;
                 break;
         }
 
diff --git a/drivers/net/wireless/ath/ath9k/ar9003_phy.c b/drivers/net/wireless/ath/ath9k/ar9003_phy.c
index eee23ecd118a..892c48b15434 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_phy.c
+++ b/drivers/net/wireless/ath/ath9k/ar9003_phy.c
@@ -1381,3 +1381,25 @@ void ar9003_hw_bb_watchdog_dbg_info(struct ath_hw *ah)
                 "==== BB update: done ====\n\n");
 }
 EXPORT_SYMBOL(ar9003_hw_bb_watchdog_dbg_info);
+
+void ar9003_hw_disable_phy_restart(struct ath_hw *ah)
+{
+        u32 val;
+
+        /* While receiving unsupported rate frame rx state machine
+         * gets into a state 0xb and if phy_restart happens in that
+         * state, BB would go hang. If RXSM is in 0xb state after
+         * first bb panic, ensure to disable the phy_restart.
+         */
+        if (!((MS(ah->bb_watchdog_last_status,
+                  AR_PHY_WATCHDOG_RX_OFDM_SM) == 0xb) ||
+            ah->bb_hang_rx_ofdm))
+                return;
+
+        ah->bb_hang_rx_ofdm = true;
+        val = REG_READ(ah, AR_PHY_RESTART);
+        val &= ~AR_PHY_RESTART_ENA;
+
+        REG_WRITE(ah, AR_PHY_RESTART, val);
+}
+EXPORT_SYMBOL(ar9003_hw_disable_phy_restart);
diff --git a/drivers/net/wireless/ath/ath9k/eeprom_9287.c b/drivers/net/wireless/ath/ath9k/eeprom_9287.c
index 7856f0d4512d..343fc9f946db 100644
--- a/drivers/net/wireless/ath/ath9k/eeprom_9287.c
+++ b/drivers/net/wireless/ath/ath9k/eeprom_9287.c
@@ -524,10 +524,16 @@ static void ath9k_hw_set_ar9287_power_per_rate_table(struct ath_hw *ah,
         case 1:
                 break;
         case 2:
-                scaledPower -= REDUCE_SCALED_POWER_BY_TWO_CHAIN;
+                if (scaledPower > REDUCE_SCALED_POWER_BY_TWO_CHAIN)
+                        scaledPower -= REDUCE_SCALED_POWER_BY_TWO_CHAIN;
+                else
+                        scaledPower = 0;
                 break;
         case 3:
-                scaledPower -= REDUCE_SCALED_POWER_BY_THREE_CHAIN;
+                if (scaledPower > REDUCE_SCALED_POWER_BY_THREE_CHAIN)
+                        scaledPower -= REDUCE_SCALED_POWER_BY_THREE_CHAIN;
+                else
+                        scaledPower = 0;
                 break;
         }
         scaledPower = max((u16)0, scaledPower);
diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c
index 72543ce8f616..1be7c8bbef84 100644
--- a/drivers/net/wireless/ath/ath9k/hw.c
+++ b/drivers/net/wireless/ath/ath9k/hw.c
@@ -1555,9 +1555,12 @@ int ath9k_hw_reset(struct ath_hw *ah, struct ath9k_channel *chan,
         if (ah->btcoex_hw.enabled)
                 ath9k_hw_btcoex_enable(ah);
 
-        if (AR_SREV_9300_20_OR_LATER(ah))
+        if (AR_SREV_9300_20_OR_LATER(ah)) {
                 ar9003_hw_bb_watchdog_config(ah);
 
+                ar9003_hw_disable_phy_restart(ah);
+        }
+
         ath9k_hw_apply_gpio_override(ah);
 
         return 0;
diff --git a/drivers/net/wireless/ath/ath9k/hw.h b/drivers/net/wireless/ath/ath9k/hw.h
index 57435ce62792..4b157c53d1a8 100644
--- a/drivers/net/wireless/ath/ath9k/hw.h
+++ b/drivers/net/wireless/ath/ath9k/hw.h
@@ -842,6 +842,7 @@ struct ath_hw {
 
         u32 bb_watchdog_last_status;
         u32 bb_watchdog_timeout_ms; /* in ms, 0 to disable */
+        u8 bb_hang_rx_ofdm; /* true if bb hang due to rx_ofdm */
 
         unsigned int paprd_target_power;
         unsigned int paprd_training_power;
@@ -990,6 +991,7 @@ void ar9002_hw_enable_wep_aggregation(struct ath_hw *ah);
 void ar9003_hw_bb_watchdog_config(struct ath_hw *ah);
 void ar9003_hw_bb_watchdog_read(struct ath_hw *ah);
 void ar9003_hw_bb_watchdog_dbg_info(struct ath_hw *ah);
+void ar9003_hw_disable_phy_restart(struct ath_hw *ah);
 void ar9003_paprd_enable(struct ath_hw *ah, bool val);
 void ar9003_paprd_populate_single_table(struct ath_hw *ah,
                                         struct ath9k_hw_cal_data *caldata,
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index a198ee374b05..2ca351fe6d3c 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -670,7 +670,8 @@ void ath9k_tasklet(unsigned long data)
         u32 status = sc->intrstatus;
         u32 rxmask;
 
-        if (status & ATH9K_INT_FATAL) {
+        if ((status & ATH9K_INT_FATAL) ||
+            (status & ATH9K_INT_BB_WATCHDOG)) {
                 ath_reset(sc, true);
                 return;
         }
@@ -737,6 +738,7 @@ irqreturn_t ath_isr(int irq, void *dev)
 {
 #define SCHED_INTR (                            \
                 ATH9K_INT_FATAL |               \
+                ATH9K_INT_BB_WATCHDOG |         \
                 ATH9K_INT_RXORN |               \
                 ATH9K_INT_RXEOL |               \
                 ATH9K_INT_RX |                  \
diff --git a/drivers/net/wireless/ath/ath9k/rc.c b/drivers/net/wireless/ath/ath9k/rc.c
index 17542214c93f..ba7f36ab0a74 100644
--- a/drivers/net/wireless/ath/ath9k/rc.c
+++ b/drivers/net/wireless/ath/ath9k/rc.c
@@ -689,7 +689,8 @@ static void ath_rc_rate_set_series(const struct ath_rate_table *rate_table,
 
         if (WLAN_RC_PHY_HT(rate_table->info[rix].phy)) {
                 rate->flags |= IEEE80211_TX_RC_MCS;
-                if (WLAN_RC_PHY_40(rate_table->info[rix].phy))
+                if (WLAN_RC_PHY_40(rate_table->info[rix].phy) &&
+                    conf_is_ht40(&txrc->hw->conf))
                         rate->flags |= IEEE80211_TX_RC_40_MHZ_WIDTH;
                 if (WLAN_RC_PHY_SGI(rate_table->info[rix].phy))
                         rate->flags |= IEEE80211_TX_RC_SHORT_GI;
diff --git a/drivers/net/wireless/b43/phy_n.c b/drivers/net/wireless/b43/phy_n.c
index 9ed65157bef5..05960ddde24e 100644
--- a/drivers/net/wireless/b43/phy_n.c
+++ b/drivers/net/wireless/b43/phy_n.c
@@ -3093,7 +3093,7 @@ static int b43_nphy_cal_tx_iq_lo(struct b43_wldev *dev,
         int freq;
         bool avoid = false;
         u8 length;
-        u16 tmp, core, type, count, max, numb, last, cmd;
+        u16 tmp, core, type, count, max, numb, last = 0, cmd;
         const u16 *table;
         bool phy6or5x;
 
diff --git a/drivers/net/wireless/iwlegacy/iwl-4965-lib.c b/drivers/net/wireless/iwlegacy/iwl-4965-lib.c
index 7e5e85a017b5..a7a4739880dc 100644
--- a/drivers/net/wireless/iwlegacy/iwl-4965-lib.c
+++ b/drivers/net/wireless/iwlegacy/iwl-4965-lib.c
@@ -628,11 +628,11 @@ void iwl4965_rx_reply_rx(struct iwl_priv *priv,
 
         /* rx_status carries information about the packet to mac80211 */
         rx_status.mactime = le64_to_cpu(phy_res->timestamp);
+        rx_status.band = (phy_res->phy_flags & RX_RES_PHY_FLAGS_BAND_24_MSK) ?
+                                IEEE80211_BAND_2GHZ : IEEE80211_BAND_5GHZ;
         rx_status.freq =
                 ieee80211_channel_to_frequency(le16_to_cpu(phy_res->channel),
                                                         rx_status.band);
-        rx_status.band = (phy_res->phy_flags & RX_RES_PHY_FLAGS_BAND_24_MSK) ?
-                                IEEE80211_BAND_2GHZ : IEEE80211_BAND_5GHZ;
         rx_status.rate_idx =
                 iwl4965_hwrate_to_mac80211_idx(rate_n_flags, rx_status.band);
         rx_status.flag = 0;
diff --git a/drivers/net/wireless/iwlegacy/iwl-4965.c b/drivers/net/wireless/iwlegacy/iwl-4965.c
index f5433c74b845..f9db25bb35c3 100644
--- a/drivers/net/wireless/iwlegacy/iwl-4965.c
+++ b/drivers/net/wireless/iwlegacy/iwl-4965.c
@@ -1543,7 +1543,7 @@ static void iwl4965_temperature_calib(struct iwl_priv *priv)
         s32 temp;
 
         temp = iwl4965_hw_get_temperature(priv);
-        if (temp < 0)
+        if (IWL_TX_POWER_TEMPERATURE_OUT_OF_RANGE(temp))
                 return;
 
         if (priv->temperature != temp) {
diff --git a/drivers/net/wireless/iwlwifi/iwl-6000.c b/drivers/net/wireless/iwlwifi/iwl-6000.c
index f8c710db6e6f..fda6fe08cf91 100644
--- a/drivers/net/wireless/iwlwifi/iwl-6000.c
+++ b/drivers/net/wireless/iwlwifi/iwl-6000.c
@@ -603,19 +603,27 @@ struct iwl_cfg iwl6050_2abg_cfg = {
         IWL_DEVICE_6050,
 };
 
+#define IWL_DEVICE_6150                                         \
+        .fw_name_pre = IWL6050_FW_PRE,                          \
+        .ucode_api_max = IWL6050_UCODE_API_MAX,                 \
+        .ucode_api_min = IWL6050_UCODE_API_MIN,                 \
+        .ops = &iwl6150_ops,                                    \
+        .eeprom_ver = EEPROM_6150_EEPROM_VERSION,               \
+        .eeprom_calib_ver = EEPROM_6150_TX_POWER_VERSION,       \
+        .base_params = &iwl6050_base_params,                    \
+        .need_dc_calib = true,                                  \
+        .led_mode = IWL_LED_BLINK,                              \
+        .internal_wimax_coex = true
+
 struct iwl_cfg iwl6150_bgn_cfg = {
         .name = "Intel(R) Centrino(R) Wireless-N + WiMAX 6150 BGN",
-        .fw_name_pre = IWL6050_FW_PRE,
-        .ucode_api_max = IWL6050_UCODE_API_MAX,
-        .ucode_api_min = IWL6050_UCODE_API_MIN,
-        .eeprom_ver = EEPROM_6150_EEPROM_VERSION,
-        .eeprom_calib_ver = EEPROM_6150_TX_POWER_VERSION,
-        .ops = &iwl6150_ops,
-        .base_params = &iwl6050_base_params,
+        IWL_DEVICE_6150,
         .ht_params = &iwl6000_ht_params,
-        .need_dc_calib = true,
-        .led_mode = IWL_LED_RF_STATE,
-        .internal_wimax_coex = true,
+};
+
+struct iwl_cfg iwl6150_bg_cfg = {
+        .name = "Intel(R) Centrino(R) Wireless-N + WiMAX 6150 BG",
+        IWL_DEVICE_6150,
 };
 
 struct iwl_cfg iwl6000_3agn_cfg = {
diff --git a/drivers/net/wireless/iwlwifi/iwl-agn.c b/drivers/net/wireless/iwlwifi/iwl-agn.c
index 11c6c1169e78..a662adcb2adb 100644
--- a/drivers/net/wireless/iwlwifi/iwl-agn.c
+++ b/drivers/net/wireless/iwlwifi/iwl-agn.c
@@ -3831,11 +3831,11 @@ static DEFINE_PCI_DEVICE_TABLE(iwl_hw_card_ids) = {
 
 /* 6150 WiFi/WiMax Series */
         {IWL_PCI_DEVICE(0x0885, 0x1305, iwl6150_bgn_cfg)},
-        {IWL_PCI_DEVICE(0x0885, 0x1306, iwl6150_bgn_cfg)},
+        {IWL_PCI_DEVICE(0x0885, 0x1307, iwl6150_bg_cfg)},
         {IWL_PCI_DEVICE(0x0885, 0x1325, iwl6150_bgn_cfg)},
-        {IWL_PCI_DEVICE(0x0885, 0x1326, iwl6150_bgn_cfg)},
+        {IWL_PCI_DEVICE(0x0885, 0x1327, iwl6150_bg_cfg)},
         {IWL_PCI_DEVICE(0x0886, 0x1315, iwl6150_bgn_cfg)},
-        {IWL_PCI_DEVICE(0x0886, 0x1316, iwl6150_bgn_cfg)},
+        {IWL_PCI_DEVICE(0x0886, 0x1317, iwl6150_bg_cfg)},
 
 /* 1000 Series WiFi */
         {IWL_PCI_DEVICE(0x0083, 0x1205, iwl1000_bgn_cfg)},
diff --git a/drivers/net/wireless/iwlwifi/iwl-agn.h b/drivers/net/wireless/iwlwifi/iwl-agn.h
index 2495fe7a58cb..d1716844002e 100644
--- a/drivers/net/wireless/iwlwifi/iwl-agn.h
+++ b/drivers/net/wireless/iwlwifi/iwl-agn.h
@@ -89,6 +89,7 @@ extern struct iwl_cfg iwl6000_3agn_cfg;
 extern struct iwl_cfg iwl6050_2agn_cfg;
 extern struct iwl_cfg iwl6050_2abg_cfg;
 extern struct iwl_cfg iwl6150_bgn_cfg;
+extern struct iwl_cfg iwl6150_bg_cfg;
 extern struct iwl_cfg iwl1000_bgn_cfg;
 extern struct iwl_cfg iwl1000_bg_cfg;
 extern struct iwl_cfg iwl100_bgn_cfg;
diff --git a/drivers/net/wireless/libertas/cmd.c b/drivers/net/wireless/libertas/cmd.c
index 84566db486d2..71c8f3fccfa1 100644
--- a/drivers/net/wireless/libertas/cmd.c
+++ b/drivers/net/wireless/libertas/cmd.c
@@ -994,6 +994,8 @@ static void lbs_submit_command(struct lbs_private *priv,
         cmd = cmdnode->cmdbuf;
 
         spin_lock_irqsave(&priv->driver_lock, flags);
+        priv->seqnum++;
+        cmd->seqnum = cpu_to_le16(priv->seqnum);
         priv->cur_cmd = cmdnode;
         spin_unlock_irqrestore(&priv->driver_lock, flags);
 
@@ -1621,11 +1623,9 @@ struct cmd_ctrl_node *__lbs_cmd_async(struct lbs_private *priv,
         /* Copy the incoming command to the buffer */
         memcpy(cmdnode->cmdbuf, in_cmd, in_cmd_size);
 
-        /* Set sequence number, clean result, move to buffer */
-        priv->seqnum++;
+        /* Set command, clean result, move to buffer */
         cmdnode->cmdbuf->command = cpu_to_le16(command);
         cmdnode->cmdbuf->size    = cpu_to_le16(in_cmd_size);
-        cmdnode->cmdbuf->seqnum  = cpu_to_le16(priv->seqnum);
         cmdnode->cmdbuf->result  = 0;
 
         lbs_deb_host("PREP_CMD: command 0x%04x\n", command);
diff --git a/drivers/net/wireless/mwifiex/sdio.h b/drivers/net/wireless/mwifiex/sdio.h
index a0e9bc5253e0..4e97e90aa399 100644
--- a/drivers/net/wireless/mwifiex/sdio.h
+++ b/drivers/net/wireless/mwifiex/sdio.h
@@ -167,8 +167,8 @@
 /* Rx unit register */
 #define CARD_RX_UNIT_REG                0x63
 
-/* Event header Len*/
-#define MWIFIEX_EVENT_HEADER_LEN           8
+/* Event header len w/o 4 bytes of interface header */
+#define MWIFIEX_EVENT_HEADER_LEN           4
 
 /* Max retry number of CMD53 write */
 #define MAX_WRITE_IOMEM_RETRY           2
diff --git a/drivers/net/wireless/rt2x00/Kconfig b/drivers/net/wireless/rt2x00/Kconfig
index 9def1e5369a1..b2f8b8fd4d2d 100644
--- a/drivers/net/wireless/rt2x00/Kconfig
+++ b/drivers/net/wireless/rt2x00/Kconfig
@@ -166,7 +166,6 @@ config RT2800USB_RT35XX
 config RT2800USB_RT53XX
        bool "rt2800usb - Include support for rt53xx devices (EXPERIMENTAL)"
        depends on EXPERIMENTAL
-       default y
        ---help---
          This adds support for rt53xx wireless chipset family to the
          rt2800pci driver.
diff --git a/drivers/net/wireless/rtlwifi/pci.c b/drivers/net/wireless/rtlwifi/pci.c
index a40952845436..89100e7c553b 100644
--- a/drivers/net/wireless/rtlwifi/pci.c
+++ b/drivers/net/wireless/rtlwifi/pci.c
@@ -669,11 +669,6 @@ static void _rtl_pci_rx_interrupt(struct ieee80211_hw *hw)
                                                          &rx_status,
                                                          (u8 *) pdesc, skb);
 
-                        pci_unmap_single(rtlpci->pdev,
-                                         *((dma_addr_t *) skb->cb),
-                                         rtlpci->rxbuffersize,
-                                         PCI_DMA_FROMDEVICE);
-
                         skb_put(skb, rtlpriv->cfg->ops->get_desc((u8 *) pdesc,
                                                          false,
                                                          HW_DESC_RXPKT_LEN));
@@ -690,6 +685,21 @@ static void _rtl_pci_rx_interrupt(struct ieee80211_hw *hw)
                         hdr = rtl_get_hdr(skb);
                         fc = rtl_get_fc(skb);
 
+                        /* try for new buffer - if allocation fails, drop
+                         * frame and reuse old buffer
+                         */
+                        new_skb = dev_alloc_skb(rtlpci->rxbuffersize);
+                        if (unlikely(!new_skb)) {
+                                RT_TRACE(rtlpriv, (COMP_INTR | COMP_RECV),
+                                         DBG_DMESG,
+                                         ("can't alloc skb for rx\n"));
+                                goto done;
+                        }
+                        pci_unmap_single(rtlpci->pdev,
+                                         *((dma_addr_t *) skb->cb),
+                                         rtlpci->rxbuffersize,
+                                         PCI_DMA_FROMDEVICE);
+
                         if (!stats.crc || !stats.hwerror) {
                                 memcpy(IEEE80211_SKB_RXCB(skb), &rx_status,
                                        sizeof(rx_status));
@@ -758,15 +768,7 @@ static void _rtl_pci_rx_interrupt(struct ieee80211_hw *hw)
                                 rtl_lps_leave(hw);
                         }
 
-                        new_skb = dev_alloc_skb(rtlpci->rxbuffersize);
-                        if (unlikely(!new_skb)) {
-                                RT_TRACE(rtlpriv, (COMP_INTR | COMP_RECV),
-                                         DBG_DMESG,
-                                         ("can't alloc skb for rx\n"));
-                                goto done;
-                        }
                         skb = new_skb;
-                        /*skb->dev = dev; */
 
                         rtlpci->rx_ring[rx_queue_idx].rx_buf[rtlpci->
                                                              rx_ring
@@ -1113,6 +1115,13 @@ static int _rtl_pci_init_rx_ring(struct ieee80211_hw *hw)
 
                 rtlpci->rx_ring[rx_queue_idx].idx = 0;
 
+                /* If amsdu_8k is disabled, set buffersize to 4096. This
+                 * change will reduce memory fragmentation.
+                 */
+                if (rtlpci->rxbuffersize > 4096 &&
+                    rtlpriv->rtlhal.disable_amsdu_8k)
+                        rtlpci->rxbuffersize = 4096;
+
                 for (i = 0; i < rtlpci->rxringcount; i++) {
                         struct sk_buff *skb =
                             dev_alloc_skb(rtlpci->rxbuffersize);
diff --git a/drivers/net/wireless/wl12xx/conf.h b/drivers/net/wireless/wl12xx/conf.h
index 1ab6c86aac40..c83fefb6662f 100644
--- a/drivers/net/wireless/wl12xx/conf.h
+++ b/drivers/net/wireless/wl12xx/conf.h
@@ -1157,6 +1157,9 @@ struct conf_sched_scan_settings {
         /* time to wait on the channel for passive scans (in TUs) */
         u32 dwell_time_passive;
 
+        /* time to wait on the channel for DFS scans (in TUs) */
+        u32 dwell_time_dfs;
+
         /* number of probe requests to send on each channel in active scans */
         u8 num_probe_reqs;
 
diff --git a/drivers/net/wireless/wl12xx/main.c b/drivers/net/wireless/wl12xx/main.c
index bc00e52f6445..e6497dc669df 100644
--- a/drivers/net/wireless/wl12xx/main.c
+++ b/drivers/net/wireless/wl12xx/main.c
@@ -311,6 +311,7 @@ static struct conf_drv_settings default_conf = {
                 .min_dwell_time_active = 8,
                 .max_dwell_time_active = 30,
                 .dwell_time_passive    = 100,
+                .dwell_time_dfs        = 150,
                 .num_probe_reqs        = 2,
                 .rssi_threshold        = -90,
                 .snr_threshold         = 0,
diff --git a/drivers/net/wireless/wl12xx/scan.c b/drivers/net/wireless/wl12xx/scan.c
index f37e5a391976..56f76abc754d 100644
--- a/drivers/net/wireless/wl12xx/scan.c
+++ b/drivers/net/wireless/wl12xx/scan.c
@@ -331,16 +331,22 @@ wl1271_scan_get_sched_scan_channels(struct wl1271 *wl,
         struct conf_sched_scan_settings *c = &wl->conf.sched_scan;
         int i, j;
         u32 flags;
+        bool force_passive = !req->n_ssids;
 
         for (i = 0, j = start;
              i < req->n_channels && j < MAX_CHANNELS_ALL_BANDS;
              i++) {
                 flags = req->channels[i]->flags;
 
-                if (!(flags & IEEE80211_CHAN_DISABLED) &&
-                    ((flags & IEEE80211_CHAN_PASSIVE_SCAN) == passive) &&
-                    ((flags & IEEE80211_CHAN_RADAR) == radar) &&
-                    (req->channels[i]->band == band)) {
+                if (force_passive)
+                        flags |= IEEE80211_CHAN_PASSIVE_SCAN;
+
+                if ((req->channels[i]->band == band) &&
+                    !(flags & IEEE80211_CHAN_DISABLED) &&
+                    (!!(flags & IEEE80211_CHAN_RADAR) == radar) &&
+                    /* if radar is set, we ignore the passive flag */
+                    (radar ||
+                     !!(flags & IEEE80211_CHAN_PASSIVE_SCAN) == passive)) {
                         wl1271_debug(DEBUG_SCAN, "band %d, center_freq %d ",
                                      req->channels[i]->band,
                                      req->channels[i]->center_freq);
@@ -350,7 +356,12 @@ wl1271_scan_get_sched_scan_channels(struct wl1271 *wl,
                         wl1271_debug(DEBUG_SCAN, "max_power %d",
                                      req->channels[i]->max_power);
 
-                        if (flags & IEEE80211_CHAN_PASSIVE_SCAN) {
+                        if (flags & IEEE80211_CHAN_RADAR) {
+                                channels[j].flags |= SCAN_CHANNEL_FLAGS_DFS;
+                                channels[j].passive_duration =
+                                        cpu_to_le16(c->dwell_time_dfs);
+                        }
+                        else if (flags & IEEE80211_CHAN_PASSIVE_SCAN) {
                                 channels[j].passive_duration =
                                         cpu_to_le16(c->dwell_time_passive);
                         } else {
@@ -359,7 +370,7 @@ wl1271_scan_get_sched_scan_channels(struct wl1271 *wl,
                                 channels[j].max_duration =
                                         cpu_to_le16(c->max_dwell_time_active);
                         }
-                        channels[j].tx_power_att = req->channels[j]->max_power;
+                        channels[j].tx_power_att = req->channels[i]->max_power;
                         channels[j].channel = req->channels[i]->hw_value;
 
                         j++;
@@ -386,7 +397,11 @@ wl1271_scan_sched_scan_channels(struct wl1271 *wl,
                 wl1271_scan_get_sched_scan_channels(wl, req, cfg->channels,
                                                     IEEE80211_BAND_2GHZ,
                                                     false, false, idx);
-        idx += cfg->active[0];
+        /*
+         * 5GHz channels always start at position 14, not immediately
+         * after the last 2.4GHz channel
+         */
+        idx = 14;
 
         cfg->passive[1] =
                 wl1271_scan_get_sched_scan_channels(wl, req, cfg->channels,
@@ -394,22 +409,23 @@ wl1271_scan_sched_scan_channels(struct wl1271 *wl,
                                                     false, true, idx);
         idx += cfg->passive[1];
 
-        cfg->active[1] =
+        cfg->dfs =
                 wl1271_scan_get_sched_scan_channels(wl, req, cfg->channels,
                                                     IEEE80211_BAND_5GHZ,
-                                                    false, false, 14);
-        idx += cfg->active[1];
+                                                    true, true, idx);
+        idx += cfg->dfs;
 
-        cfg->dfs =
+        cfg->active[1] =
                 wl1271_scan_get_sched_scan_channels(wl, req, cfg->channels,
                                                     IEEE80211_BAND_5GHZ,
-                                                    true, false, idx);
-        idx += cfg->dfs;
+                                                    false, false, idx);
+        idx += cfg->active[1];
 
         wl1271_debug(DEBUG_SCAN, "    2.4GHz: active %d passive %d",
                      cfg->active[0], cfg->passive[0]);
         wl1271_debug(DEBUG_SCAN, "    5GHz: active %d passive %d",
                      cfg->active[1], cfg->passive[1]);
+        wl1271_debug(DEBUG_SCAN, "    DFS: %d", cfg->dfs);
 
         return idx;
 }
@@ -421,6 +437,7 @@ int wl1271_scan_sched_scan_config(struct wl1271 *wl,
         struct wl1271_cmd_sched_scan_config *cfg = NULL;
         struct conf_sched_scan_settings *c = &wl->conf.sched_scan;
         int i, total_channels, ret;
+        bool force_passive = !req->n_ssids;
 
         wl1271_debug(DEBUG_CMD, "cmd sched_scan scan config");
 
@@ -444,7 +461,7 @@ int wl1271_scan_sched_scan_config(struct wl1271 *wl,
         for (i = 0; i < SCAN_MAX_CYCLE_INTERVALS; i++)
                 cfg->intervals[i] = cpu_to_le32(req->interval);
 
-        if (req->ssids[0].ssid_len && req->ssids[0].ssid) {
+        if (!force_passive && req->ssids[0].ssid_len && req->ssids[0].ssid) {
                 cfg->filter_type = SCAN_SSID_FILTER_SPECIFIC;
                 cfg->ssid_len = req->ssids[0].ssid_len;
                 memcpy(cfg->ssid, req->ssids[0].ssid,
@@ -461,7 +478,7 @@ int wl1271_scan_sched_scan_config(struct wl1271 *wl,
                 goto out;
         }
 
-        if (cfg->active[0]) {
+        if (!force_passive && cfg->active[0]) {
                 ret = wl1271_cmd_build_probe_req(wl, req->ssids[0].ssid,
                                                  req->ssids[0].ssid_len,
                                                  ies->ie[IEEE80211_BAND_2GHZ],
@@ -473,7 +490,7 @@ int wl1271_scan_sched_scan_config(struct wl1271 *wl,
                 }
         }
 
-        if (cfg->active[1]) {
+        if (!force_passive && cfg->active[1]) {
                 ret = wl1271_cmd_build_probe_req(wl,  req->ssids[0].ssid,
                                                  req->ssids[0].ssid_len,
                                                  ies->ie[IEEE80211_BAND_5GHZ],
diff --git a/drivers/net/wireless/wl12xx/scan.h b/drivers/net/wireless/wl12xx/scan.h
index c83319579ca3..a0b6c5d67b07 100644
--- a/drivers/net/wireless/wl12xx/scan.h
+++ b/drivers/net/wireless/wl12xx/scan.h
@@ -137,6 +137,9 @@ enum {
         SCAN_BSS_TYPE_ANY,
 };
 
+#define SCAN_CHANNEL_FLAGS_DFS          BIT(0)
+#define SCAN_CHANNEL_FLAGS_DFS_ENABLED  BIT(1)
+
 struct conn_scan_ch_params {
         __le16 min_duration;
         __le16 max_duration;
diff --git a/drivers/net/wireless/zd1211rw/zd_usb.c b/drivers/net/wireless/zd1211rw/zd_usb.c
index 0e819943b9e4..631194d49828 100644
--- a/drivers/net/wireless/zd1211rw/zd_usb.c
+++ b/drivers/net/wireless/zd1211rw/zd_usb.c
@@ -1533,6 +1533,31 @@ static void __exit usb_exit(void)
 module_init(usb_init);
 module_exit(usb_exit);
 
+static int zd_ep_regs_out_msg(struct usb_device *udev, void *data, int len,
+                              int *actual_length, int timeout)
+{
+        /* In USB 2.0 mode EP_REGS_OUT endpoint is interrupt type. However in
+         * USB 1.1 mode endpoint is bulk. Select correct type URB by endpoint
+         * descriptor.
+         */
+        struct usb_host_endpoint *ep;
+        unsigned int pipe;
+
+        pipe = usb_sndintpipe(udev, EP_REGS_OUT);
+        ep = usb_pipe_endpoint(udev, pipe);
+        if (!ep)
+                return -EINVAL;
+
+        if (usb_endpoint_xfer_int(&ep->desc)) {
+                return usb_interrupt_msg(udev, pipe, data, len,
+                                         actual_length, timeout);
+        } else {
+                pipe = usb_sndbulkpipe(udev, EP_REGS_OUT);
+                return usb_bulk_msg(udev, pipe, data, len, actual_length,
+                                    timeout);
+        }
+}
+
 static int usb_int_regs_length(unsigned int count)
 {
         return sizeof(struct usb_int_regs) + count * sizeof(struct reg_data);
@@ -1648,15 +1673,14 @@ int zd_usb_ioread16v(struct zd_usb *usb, u16 *values,
 
         udev = zd_usb_to_usbdev(usb);
         prepare_read_regs_int(usb);
-        r = usb_interrupt_msg(udev, usb_sndintpipe(udev, EP_REGS_OUT),
-                              req, req_len, &actual_req_len, 50 /* ms */);
+        r = zd_ep_regs_out_msg(udev, req, req_len, &actual_req_len, 50 /*ms*/);
         if (r) {
                 dev_dbg_f(zd_usb_dev(usb),
-                        "error in usb_interrupt_msg(). Error number %d\n", r);
+                        "error in zd_ep_regs_out_msg(). Error number %d\n", r);
                 goto error;
         }
         if (req_len != actual_req_len) {
-                dev_dbg_f(zd_usb_dev(usb), "error in usb_interrupt_msg()\n"
+                dev_dbg_f(zd_usb_dev(usb), "error in zd_ep_regs_out_msg()\n"
                         " req_len %d != actual_req_len %d\n",
                         req_len, actual_req_len);
                 r = -EIO;
@@ -1818,9 +1842,17 @@ int zd_usb_iowrite16v_async(struct zd_usb *usb, const struct zd_ioreq16 *ioreqs,
                 rw->value = cpu_to_le16(ioreqs[i].value);
         }
 
-        usb_fill_int_urb(urb, udev, usb_sndintpipe(udev, EP_REGS_OUT),
-                         req, req_len, iowrite16v_urb_complete, usb,
-                         ep->desc.bInterval);
+        /* In USB 2.0 mode endpoint is interrupt type. However in USB 1.1 mode
+         * endpoint is bulk. Select correct type URB by endpoint descriptor.
+         */
+        if (usb_endpoint_xfer_int(&ep->desc))
+                usb_fill_int_urb(urb, udev, usb_sndintpipe(udev, EP_REGS_OUT),
+                                 req, req_len, iowrite16v_urb_complete, usb,
+                                 ep->desc.bInterval);
+        else
+                usb_fill_bulk_urb(urb, udev, usb_sndbulkpipe(udev, EP_REGS_OUT),
+                                  req, req_len, iowrite16v_urb_complete, usb);
+
         urb->transfer_flags |= URB_FREE_BUFFER;
 
         /* Submit previous URB */
@@ -1924,15 +1956,14 @@ int zd_usb_rfwrite(struct zd_usb *usb, u32 value, u8 bits)
         }
 
         udev = zd_usb_to_usbdev(usb);
-        r = usb_interrupt_msg(udev, usb_sndintpipe(udev, EP_REGS_OUT),
-                              req, req_len, &actual_req_len, 50 /* ms */);
+        r = zd_ep_regs_out_msg(udev, req, req_len, &actual_req_len, 50 /*ms*/);
         if (r) {
                 dev_dbg_f(zd_usb_dev(usb),
-                        "error in usb_interrupt_msg(). Error number %d\n", r);
+                        "error in zd_ep_regs_out_msg(). Error number %d\n", r);
                 goto out;
         }
         if (req_len != actual_req_len) {
-                dev_dbg_f(zd_usb_dev(usb), "error in usb_interrupt_msg()"
+                dev_dbg_f(zd_usb_dev(usb), "error in zd_ep_regs_out_msg()"
                         " req_len %d != actual_req_len %d\n",
                         req_len, actual_req_len);
                 r = -EIO;
diff --git a/drivers/oprofile/event_buffer.h b/drivers/oprofile/event_buffer.h
index 4e70749f8d16..a8d5bb3cba89 100644
--- a/drivers/oprofile/event_buffer.h
+++ b/drivers/oprofile/event_buffer.h
@@ -11,7 +11,7 @@
 #define EVENT_BUFFER_H
 
 #include <linux/types.h>
-#include <asm/mutex.h>
+#include <linux/mutex.h>
 
 int alloc_event_buffer(void);
 
diff --git a/drivers/oprofile/oprof.c b/drivers/oprofile/oprof.c
index f9bda64fcd1b..dccd8636095c 100644
--- a/drivers/oprofile/oprof.c
+++ b/drivers/oprofile/oprof.c
@@ -14,7 +14,7 @@
 #include <linux/moduleparam.h>
 #include <linux/workqueue.h>
 #include <linux/time.h>
-#include <asm/mutex.h>
+#include <linux/mutex.h>
 
 #include "oprof.h"
 #include "event_buffer.h"
diff --git a/drivers/pci/dmar.c b/drivers/pci/dmar.c
index 12e02bf92c4a..3dc9befa5aec 100644
--- a/drivers/pci/dmar.c
+++ b/drivers/pci/dmar.c
@@ -698,12 +698,7 @@ int __init detect_intel_iommu(void)
         {
 #ifdef CONFIG_INTR_REMAP
                 struct acpi_table_dmar *dmar;
-                /*
-                 * for now we will disable dma-remapping when interrupt
-                 * remapping is enabled.
-                 * When support for queued invalidation for IOTLB invalidation
-                 * is added, we will not need this any more.
-                 */
+
                 dmar = (struct acpi_table_dmar *) dmar_tbl;
                 if (ret && cpu_has_x2apic && dmar->flags & 0x1)
                         printk(KERN_INFO
diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c
index 6af6b628175b..59f17acf7f68 100644
--- a/drivers/pci/intel-iommu.c
+++ b/drivers/pci/intel-iommu.c
@@ -47,6 +47,8 @@
 #define ROOT_SIZE               VTD_PAGE_SIZE
 #define CONTEXT_SIZE            VTD_PAGE_SIZE
 
+#define IS_BRIDGE_HOST_DEVICE(pdev) \
+                            ((pdev->class >> 8) == PCI_CLASS_BRIDGE_HOST)
 #define IS_GFX_DEVICE(pdev) ((pdev->class >> 16) == PCI_BASE_CLASS_DISPLAY)
 #define IS_ISA_DEVICE(pdev) ((pdev->class >> 8) == PCI_CLASS_BRIDGE_ISA)
 #define IS_AZALIA(pdev) ((pdev)->vendor == 0x8086 && (pdev)->device == 0x3a3e)
@@ -116,6 +118,11 @@ static inline unsigned long align_to_level(unsigned long pfn, int level)
         return (pfn + level_size(level) - 1) & level_mask(level);
 }
 
+static inline unsigned long lvl_to_nr_pages(unsigned int lvl)
+{
+        return  1 << ((lvl - 1) * LEVEL_STRIDE);
+}
+
 /* VT-d pages must always be _smaller_ than MM pages. Otherwise things
    are never going to work. */
 static inline unsigned long dma_to_mm_pfn(unsigned long dma_pfn)
@@ -143,6 +150,12 @@ static void __init check_tylersburg_isoch(void);
 static int rwbf_quirk;
 
 /*
+ * set to 1 to panic kernel if can't successfully enable VT-d
+ * (used when kernel is launched w/ TXT)
+ */
+static int force_on = 0;
+
+/*
  * 0: Present
  * 1-11: Reserved
  * 12-63: Context Ptr (12 - (haw-1))
@@ -338,6 +351,9 @@ struct dmar_domain {
         int             iommu_coherency;/* indicate coherency of iommu access */
         int             iommu_snooping; /* indicate snooping control feature*/
         int             iommu_count;    /* reference count of iommu */
+        int             iommu_superpage;/* Level of superpages supported:
+                                           0 == 4KiB (no superpages), 1 == 2MiB,
+                                           2 == 1GiB, 3 == 512GiB, 4 == 1TiB */
         spinlock_t      iommu_lock;     /* protect iommu set in domain */
         u64             max_addr;       /* maximum mapped address */
 };
@@ -387,6 +403,7 @@ int dmar_disabled = 1;
 static int dmar_map_gfx = 1;
 static int dmar_forcedac;
 static int intel_iommu_strict;
+static int intel_iommu_superpage = 1;
 
 #define DUMMY_DEVICE_DOMAIN_INFO ((struct device_domain_info *)(-1))
 static DEFINE_SPINLOCK(device_domain_lock);
@@ -417,6 +434,10 @@ static int __init intel_iommu_setup(char *str)
                         printk(KERN_INFO
                                 "Intel-IOMMU: disable batched IOTLB flush\n");
                         intel_iommu_strict = 1;
+                } else if (!strncmp(str, "sp_off", 6)) {
+                        printk(KERN_INFO
+                                "Intel-IOMMU: disable supported super page\n");
+                        intel_iommu_superpage = 0;
                 }
 
                 str += strcspn(str, ",");
@@ -555,11 +576,32 @@ static void domain_update_iommu_snooping(struct dmar_domain *domain)
         }
 }
 
+static void domain_update_iommu_superpage(struct dmar_domain *domain)
+{
+        int i, mask = 0xf;
+
+        if (!intel_iommu_superpage) {
+                domain->iommu_superpage = 0;
+                return;
+        }
+
+        domain->iommu_superpage = 4; /* 1TiB */
+
+        for_each_set_bit(i, &domain->iommu_bmp, g_num_of_iommus) {
+                mask |= cap_super_page_val(g_iommus[i]->cap);
+                if (!mask) {
+                        break;
+                }
+        }
+        domain->iommu_superpage = fls(mask);
+}
+
 /* Some capabilities may be different across iommus */
 static void domain_update_iommu_cap(struct dmar_domain *domain)
 {
         domain_update_iommu_coherency(domain);
         domain_update_iommu_snooping(domain);
+        domain_update_iommu_superpage(domain);
 }
 
 static struct intel_iommu *device_to_iommu(int segment, u8 bus, u8 devfn)
@@ -689,23 +731,31 @@ out:
 }
 
 static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
-                                      unsigned long pfn)
+                                      unsigned long pfn, int large_level)
 {
         int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;
         struct dma_pte *parent, *pte = NULL;
         int level = agaw_to_level(domain->agaw);
-        int offset;
+        int offset, target_level;
 
         BUG_ON(!domain->pgd);
         BUG_ON(addr_width < BITS_PER_LONG && pfn >> addr_width);
         parent = domain->pgd;
 
+        /* Search pte */
+        if (!large_level)
+                target_level = 1;
+        else
+                target_level = large_level;
+
         while (level > 0) {
                 void *tmp_page;
 
                 offset = pfn_level_offset(pfn, level);
                 pte = &parent[offset];
-                if (level == 1)
+                if (!large_level && (pte->val & DMA_PTE_LARGE_PAGE))
+                        break;
+                if (level == target_level)
                         break;
 
                 if (!dma_pte_present(pte)) {
@@ -733,10 +783,11 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
         return pte;
 }
 
+
 /* return address's pte at specific level */
 static struct dma_pte *dma_pfn_level_pte(struct dmar_domain *domain,
                                          unsigned long pfn,
-                                         int level)
+                                         int level, int *large_page)
 {
         struct dma_pte *parent, *pte = NULL;
         int total = agaw_to_level(domain->agaw);
@@ -749,8 +800,16 @@ static struct dma_pte *dma_pfn_level_pte(struct dmar_domain *domain,
                 if (level == total)
                         return pte;
 
-                if (!dma_pte_present(pte))
+                if (!dma_pte_present(pte)) {
+                        *large_page = total;
                         break;
+                }
+
+                if (pte->val & DMA_PTE_LARGE_PAGE) {
+                        *large_page = total;
+                        return pte;
+                }
+
                 parent = phys_to_virt(dma_pte_addr(pte));
                 total--;
         }
@@ -763,6 +822,7 @@ static void dma_pte_clear_range(struct dmar_domain *domain,
                                 unsigned long last_pfn)
 {
         int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;
+        unsigned int large_page = 1;
         struct dma_pte *first_pte, *pte;
 
         BUG_ON(addr_width < BITS_PER_LONG && start_pfn >> addr_width);
@@ -771,14 +831,15 @@ static void dma_pte_clear_range(struct dmar_domain *domain,
 
         /* we don't need lock here; nobody else touches the iova range */
         do {
-                first_pte = pte = dma_pfn_level_pte(domain, start_pfn, 1);
+                large_page = 1;
+                first_pte = pte = dma_pfn_level_pte(domain, start_pfn, 1, &large_page);
                 if (!pte) {
-                        start_pfn = align_to_level(start_pfn + 1, 2);
+                        start_pfn = align_to_level(start_pfn + 1, large_page + 1);
                         continue;
                 }
-                do { 
+                do {
                         dma_clear_pte(pte);
-                        start_pfn++;
+                        start_pfn += lvl_to_nr_pages(large_page);
                         pte++;
                 } while (start_pfn <= last_pfn && !first_pte_in_page(pte));
 
@@ -798,6 +859,7 @@ static void dma_pte_free_pagetable(struct dmar_domain *domain,
         int total = agaw_to_level(domain->agaw);
         int level;
         unsigned long tmp;
+        int large_page = 2;
 
         BUG_ON(addr_width < BITS_PER_LONG && start_pfn >> addr_width);
         BUG_ON(addr_width < BITS_PER_LONG && last_pfn >> addr_width);
@@ -813,7 +875,10 @@ static void dma_pte_free_pagetable(struct dmar_domain *domain,
                         return;
 
                 do {
-                        first_pte = pte = dma_pfn_level_pte(domain, tmp, level);
+                        large_page = level;
+                        first_pte = pte = dma_pfn_level_pte(domain, tmp, level, &large_page);
+                        if (large_page > level)
+                                level = large_page + 1;
                         if (!pte) {
                                 tmp = align_to_level(tmp + 1, level + 1);
                                 continue;
@@ -1397,6 +1462,7 @@ static int domain_init(struct dmar_domain *domain, int guest_width)
         else
                 domain->iommu_snooping = 0;
 
+        domain->iommu_superpage = fls(cap_super_page_val(iommu->cap));
         domain->iommu_count = 1;
         domain->nid = iommu->node;
 
@@ -1417,6 +1483,10 @@ static void domain_exit(struct dmar_domain *domain)
         if (!domain)
                 return;
 
+        /* Flush any lazy unmaps that may reference this domain */
+        if (!intel_iommu_strict)
+                flush_unmaps_timeout(0);
+
         domain_remove_dev_info(domain);
         /* destroy iovas */
         put_iova_domain(&domain->iovad);
@@ -1648,6 +1718,34 @@ static inline unsigned long aligned_nrpages(unsigned long host_addr,
         return PAGE_ALIGN(host_addr + size) >> VTD_PAGE_SHIFT;
 }
 
+/* Return largest possible superpage level for a given mapping */
+static inline int hardware_largepage_caps(struct dmar_domain *domain,
+                                          unsigned long iov_pfn,
+                                          unsigned long phy_pfn,
+                                          unsigned long pages)
+{
+        int support, level = 1;
+        unsigned long pfnmerge;
+
+        support = domain->iommu_superpage;
+
+        /* To use a large page, the virtual *and* physical addresses
+           must be aligned to 2MiB/1GiB/etc. Lower bits set in either
+           of them will mean we have to use smaller pages. So just
+           merge them and check both at once. */
+        pfnmerge = iov_pfn | phy_pfn;
+
+        while (support && !(pfnmerge & ~VTD_STRIDE_MASK)) {
+                pages >>= VTD_STRIDE_SHIFT;
+                if (!pages)
+                        break;
+                pfnmerge >>= VTD_STRIDE_SHIFT;
+                level++;
+                support--;
+        }
+        return level;
+}
+
 static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
                             struct scatterlist *sg, unsigned long phys_pfn,
                             unsigned long nr_pages, int prot)
@@ -1656,6 +1754,8 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
         phys_addr_t uninitialized_var(pteval);
         int addr_width = agaw_to_width(domain->agaw) - VTD_PAGE_SHIFT;
         unsigned long sg_res;
+        unsigned int largepage_lvl = 0;
+        unsigned long lvl_pages = 0;
 
         BUG_ON(addr_width < BITS_PER_LONG && (iov_pfn + nr_pages - 1) >> addr_width);
 
@@ -1671,7 +1771,7 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
                 pteval = ((phys_addr_t)phys_pfn << VTD_PAGE_SHIFT) | prot;
         }
 
-        while (nr_pages--) {
+        while (nr_pages > 0) {
                 uint64_t tmp;
 
                 if (!sg_res) {
@@ -1679,11 +1779,21 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
                         sg->dma_address = ((dma_addr_t)iov_pfn << VTD_PAGE_SHIFT) + sg->offset;
                         sg->dma_length = sg->length;
                         pteval = page_to_phys(sg_page(sg)) | prot;
+                        phys_pfn = pteval >> VTD_PAGE_SHIFT;
                 }
+
                 if (!pte) {
-                        first_pte = pte = pfn_to_dma_pte(domain, iov_pfn);
+                        largepage_lvl = hardware_largepage_caps(domain, iov_pfn, phys_pfn, sg_res);
+
+                        first_pte = pte = pfn_to_dma_pte(domain, iov_pfn, largepage_lvl);
                         if (!pte)
                                 return -ENOMEM;
+                        /* It is large page*/
+                        if (largepage_lvl > 1)
+                                pteval |= DMA_PTE_LARGE_PAGE;
+                        else
+                                pteval &= ~(uint64_t)DMA_PTE_LARGE_PAGE;
+
                 }
                 /* We don't need lock here, nobody else
                  * touches the iova range
@@ -1699,16 +1809,38 @@ static int __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
                         }
                         WARN_ON(1);
                 }
+
+                lvl_pages = lvl_to_nr_pages(largepage_lvl);
+
+                BUG_ON(nr_pages < lvl_pages);
+                BUG_ON(sg_res < lvl_pages);
+
+                nr_pages -= lvl_pages;
+                iov_pfn += lvl_pages;
+                phys_pfn += lvl_pages;
+                pteval += lvl_pages * VTD_PAGE_SIZE;
+                sg_res -= lvl_pages;
+
+                /* If the next PTE would be the first in a new page, then we
+                   need to flush the cache on the entries we've just written.
+                   And then we'll need to recalculate 'pte', so clear it and
+                   let it get set again in the if (!pte) block above.
+
+                   If we're done (!nr_pages) we need to flush the cache too.
+
+                   Also if we've been setting superpages, we may need to
+                   recalculate 'pte' and switch back to smaller pages for the
+                   end of the mapping, if the trailing size is not enough to
+                   use another superpage (i.e. sg_res < lvl_pages). */
                 pte++;
-                if (!nr_pages || first_pte_in_page(pte)) {
+                if (!nr_pages || first_pte_in_page(pte) ||
+                    (largepage_lvl > 1 && sg_res < lvl_pages)) {
                         domain_flush_cache(domain, first_pte,
                                            (void *)pte - (void *)first_pte);
                         pte = NULL;
                 }
-                iov_pfn++;
-                pteval += VTD_PAGE_SIZE;
-                sg_res--;
-                if (!sg_res)
+
+                if (!sg_res && nr_pages)
                         sg = sg_next(sg);
         }
         return 0;
@@ -2016,7 +2148,7 @@ static inline int iommu_prepare_rmrr_dev(struct dmar_rmrr_unit *rmrr,
         if (pdev->dev.archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO)
                 return 0;
         return iommu_prepare_identity_map(pdev, rmrr->base_address,
-                rmrr->end_address + 1);
+                rmrr->end_address);
 }
 
 #ifdef CONFIG_DMAR_FLOPPY_WA
@@ -2030,7 +2162,7 @@ static inline void iommu_prepare_isa(void)
                 return;
 
         printk(KERN_INFO "IOMMU: Prepare 0-16MiB unity mapping for LPC\n");
-        ret = iommu_prepare_identity_map(pdev, 0, 16*1024*1024);
+        ret = iommu_prepare_identity_map(pdev, 0, 16*1024*1024 - 1);
 
         if (ret)
                 printk(KERN_ERR "IOMMU: Failed to create 0-16MiB identity map; "
@@ -2106,10 +2238,10 @@ static int identity_mapping(struct pci_dev *pdev)
         if (likely(!iommu_identity_mapping))
                 return 0;
 
+        info = pdev->dev.archdata.iommu;
+        if (info && info != DUMMY_DEVICE_DOMAIN_INFO)
+                return (info->domain == si_domain);
 
-        list_for_each_entry(info, &si_domain->devices, link)
-                if (info->dev == pdev)
-                        return 1;
         return 0;
 }
 
@@ -2187,8 +2319,19 @@ static int iommu_should_identity_map(struct pci_dev *pdev, int startup)
          * Assume that they will -- if they turn out not to be, then we can 
          * take them out of the 1:1 domain later.
          */
-        if (!startup)
-                return pdev->dma_mask > DMA_BIT_MASK(32);
+        if (!startup) {
+                /*
+                 * If the device's dma_mask is less than the system's memory
+                 * size then this is not a candidate for identity mapping.
+                 */
+                u64 dma_mask = pdev->dma_mask;
+
+                if (pdev->dev.coherent_dma_mask &&
+                    pdev->dev.coherent_dma_mask < dma_mask)
+                        dma_mask = pdev->dev.coherent_dma_mask;
+
+                return dma_mask >= dma_get_required_mask(&pdev->dev);
+        }
 
         return 1;
 }
@@ -2203,6 +2346,9 @@ static int __init iommu_prepare_static_identity_mapping(int hw)
                 return -EFAULT;
 
         for_each_pci_dev(pdev) {
+                /* Skip Host/PCI Bridge devices */
+                if (IS_BRIDGE_HOST_DEVICE(pdev))
+                        continue;
                 if (iommu_should_identity_map(pdev, 1)) {
                         printk(KERN_INFO "IOMMU: %s identity mapping for device %s\n",
                                hw ? "hardware" : "software", pci_name(pdev));
@@ -2218,7 +2364,7 @@ static int __init iommu_prepare_static_identity_mapping(int hw)
         return 0;
 }
 
-static int __init init_dmars(int force_on)
+static int __init init_dmars(void)
 {
         struct dmar_drhd_unit *drhd;
         struct dmar_rmrr_unit *rmrr;
@@ -2592,8 +2738,7 @@ static dma_addr_t __intel_map_single(struct device *hwdev, phys_addr_t paddr,
         iommu = domain_get_iommu(domain);
         size = aligned_nrpages(paddr, size);
 
-        iova = intel_alloc_iova(hwdev, domain, dma_to_mm_pfn(size),
-                                pdev->dma_mask);
+        iova = intel_alloc_iova(hwdev, domain, dma_to_mm_pfn(size), dma_mask);
         if (!iova)
                 goto error;
 
@@ -3118,7 +3263,17 @@ static int init_iommu_hw(void)
                 if (iommu->qi)
                         dmar_reenable_qi(iommu);
 
-        for_each_active_iommu(iommu, drhd) {
+        for_each_iommu(iommu, drhd) {
+                if (drhd->ignored) {
+                        /*
+                         * we always have to disable PMRs or DMA may fail on
+                         * this device
+                         */
+                        if (force_on)
+                                iommu_disable_protect_mem_regions(iommu);
+                        continue;
+                }
+        
                 iommu_flush_write_buffer(iommu);
 
                 iommu_set_root_entry(iommu);
@@ -3127,7 +3282,8 @@ static int init_iommu_hw(void)
                                            DMA_CCMD_GLOBAL_INVL);
                 iommu->flush.flush_iotlb(iommu, 0, 0, 0,
                                          DMA_TLB_GLOBAL_FLUSH);
-                iommu_enable_translation(iommu);
+                if (iommu_enable_translation(iommu))
+                        return 1;
                 iommu_disable_protect_mem_regions(iommu);
         }
 
@@ -3194,7 +3350,10 @@ static void iommu_resume(void)
         unsigned long flag;
 
         if (init_iommu_hw()) {
-                WARN(1, "IOMMU setup failed, DMAR can not resume!\n");
+                if (force_on)
+                        panic("tboot: IOMMU setup failed, DMAR can not resume!\n");
+                else
+                        WARN(1, "IOMMU setup failed, DMAR can not resume!\n");
                 return;
         }
 
@@ -3271,7 +3430,6 @@ static struct notifier_block device_nb = {
 int __init intel_iommu_init(void)
 {
         int ret = 0;
-        int force_on = 0;
 
         /* VT-d is required for a TXT/tboot launch, so enforce that */
         force_on = tboot_force_iommu();
@@ -3309,7 +3467,7 @@ int __init intel_iommu_init(void)
 
         init_no_remapping_devices();
 
-        ret = init_dmars(force_on);
+        ret = init_dmars();
         if (ret) {
                 if (force_on)
                         panic("tboot: Failed to initialize DMARs\n");
@@ -3380,8 +3538,8 @@ static void domain_remove_one_dev_info(struct dmar_domain *domain,
         spin_lock_irqsave(&device_domain_lock, flags);
         list_for_each_safe(entry, tmp, &domain->devices) {
                 info = list_entry(entry, struct device_domain_info, link);
-                /* No need to compare PCI domain; it has to be the same */
-                if (info->bus == pdev->bus->number &&
+                if (info->segment == pci_domain_nr(pdev->bus) &&
+                    info->bus == pdev->bus->number &&
                     info->devfn == pdev->devfn) {
                         list_del(&info->link);
                         list_del(&info->global);
@@ -3419,10 +3577,13 @@ static void domain_remove_one_dev_info(struct dmar_domain *domain,
                 domain_update_iommu_cap(domain);
                 spin_unlock_irqrestore(&domain->iommu_lock, tmp_flags);
 
-                spin_lock_irqsave(&iommu->lock, tmp_flags);
-                clear_bit(domain->id, iommu->domain_ids);
-                iommu->domains[domain->id] = NULL;
-                spin_unlock_irqrestore(&iommu->lock, tmp_flags);
+                if (!(domain->flags & DOMAIN_FLAG_VIRTUAL_MACHINE) &&
+                    !(domain->flags & DOMAIN_FLAG_STATIC_IDENTITY)) {
+                        spin_lock_irqsave(&iommu->lock, tmp_flags);
+                        clear_bit(domain->id, iommu->domain_ids);
+                        iommu->domains[domain->id] = NULL;
+                        spin_unlock_irqrestore(&iommu->lock, tmp_flags);
+                }
         }
 
         spin_unlock_irqrestore(&device_domain_lock, flags);
@@ -3505,6 +3666,7 @@ static int md_domain_init(struct dmar_domain *domain, int guest_width)
         domain->iommu_count = 0;
         domain->iommu_coherency = 0;
         domain->iommu_snooping = 0;
+        domain->iommu_superpage = 0;
         domain->max_addr = 0;
         domain->nid = -1;
 
@@ -3720,7 +3882,7 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
         struct dma_pte *pte;
         u64 phys = 0;
 
-        pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT);
+        pte = pfn_to_dma_pte(dmar_domain, iova >> VTD_PAGE_SHIFT, 0);
         if (pte)
                 phys = dma_pte_addr(pte);
 
diff --git a/drivers/pci/iova.c b/drivers/pci/iova.c
index 9606e599a475..c5c274ab5c5a 100644
--- a/drivers/pci/iova.c
+++ b/drivers/pci/iova.c
@@ -63,8 +63,16 @@ __cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free)
         curr = iovad->cached32_node;
         cached_iova = container_of(curr, struct iova, node);
 
-        if (free->pfn_lo >= cached_iova->pfn_lo)
-                iovad->cached32_node = rb_next(&free->node);
+        if (free->pfn_lo >= cached_iova->pfn_lo) {
+                struct rb_node *node = rb_next(&free->node);
+                struct iova *iova = container_of(node, struct iova, node);
+
+                /* only cache if it's below 32bit pfn */
+                if (node && iova->pfn_lo < iovad->dma_32bit_pfn)
+                        iovad->cached32_node = node;
+                else
+                        iovad->cached32_node = NULL;
+        }
 }
 
 /* Computes the padding size required, to make the
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index 7c3b18e78cee..d36f41ea8cbf 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -195,6 +195,8 @@ static pci_power_t acpi_pci_choose_state(struct pci_dev *pdev)
                 return PCI_D2;
         case ACPI_STATE_D3:
                 return PCI_D3hot;
+        case ACPI_STATE_D3_COLD:
+                return PCI_D3cold;
         }
         return PCI_POWER_ERROR;
 }
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index 5cb999b50f95..45e0191c35dd 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -39,7 +39,7 @@ config ACER_WMI
 
 config ACERHDF
         tristate "Acer Aspire One temperature and fan driver"
-        depends on THERMAL && THERMAL_HWMON && ACPI
+        depends on THERMAL && ACPI
         ---help---
           This is a driver for Acer Aspire One netbooks. It allows to access
           the temperature sensor and to control the fan.
@@ -760,4 +760,13 @@ config MXM_WMI
           MXM is a standard for laptop graphics cards, the WMI interface
           is required for switchable nvidia graphics machines
 
+config INTEL_OAKTRAIL
+        tristate "Intel Oaktrail Platform Extras"
+        depends on ACPI
+        depends on RFKILL && BACKLIGHT_CLASS_DEVICE && ACPI
+        ---help---
+          Intel Oaktrail platform need this driver to provide interfaces to
+          enable/disable the Camera, WiFi, BT etc. devices. If in doubt, say Y
+          here; it will only load on supported platforms.
+
 endif # X86_PLATFORM_DEVICES
diff --git a/drivers/platform/x86/Makefile b/drivers/platform/x86/Makefile
index a7ab3bc7b3a1..afc1f832aa67 100644
--- a/drivers/platform/x86/Makefile
+++ b/drivers/platform/x86/Makefile
@@ -41,5 +41,6 @@ obj-$(CONFIG_XO1_RFKILL)	+= xo1-rfkill.o
 obj-$(CONFIG_XO15_EBOOK)        += xo15-ebook.o
 obj-$(CONFIG_IBM_RTL)           += ibm_rtl.o
 obj-$(CONFIG_SAMSUNG_LAPTOP)    += samsung-laptop.o
-obj-$(CONFIG_INTEL_MFLD_THERMAL)        += intel_mid_thermal.o
 obj-$(CONFIG_MXM_WMI)           += mxm-wmi.o
+obj-$(CONFIG_INTEL_MID_POWER_BUTTON)    += intel_mid_powerbtn.o
+obj-$(CONFIG_INTEL_OAKTRAIL)    += intel_oaktrail.o
diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c
index ac4e7f83ce6c..005417bd429e 100644
--- a/drivers/platform/x86/acer-wmi.c
+++ b/drivers/platform/x86/acer-wmi.c
@@ -98,13 +98,26 @@ enum acer_wmi_event_ids {
 
 static const struct key_entry acer_wmi_keymap[] = {
         {KE_KEY, 0x01, {KEY_WLAN} },     /* WiFi */
+        {KE_KEY, 0x03, {KEY_WLAN} },     /* WiFi */
         {KE_KEY, 0x12, {KEY_BLUETOOTH} },       /* BT */
         {KE_KEY, 0x21, {KEY_PROG1} },    /* Backup */
         {KE_KEY, 0x22, {KEY_PROG2} },    /* Arcade */
         {KE_KEY, 0x23, {KEY_PROG3} },    /* P_Key */
         {KE_KEY, 0x24, {KEY_PROG4} },    /* Social networking_Key */
+        {KE_IGNORE, 0x41, {KEY_MUTE} },
+        {KE_IGNORE, 0x42, {KEY_PREVIOUSSONG} },
+        {KE_IGNORE, 0x43, {KEY_NEXTSONG} },
+        {KE_IGNORE, 0x44, {KEY_PLAYPAUSE} },
+        {KE_IGNORE, 0x45, {KEY_STOP} },
+        {KE_IGNORE, 0x48, {KEY_VOLUMEUP} },
+        {KE_IGNORE, 0x49, {KEY_VOLUMEDOWN} },
+        {KE_IGNORE, 0x61, {KEY_SWITCHVIDEOMODE} },
+        {KE_IGNORE, 0x62, {KEY_BRIGHTNESSUP} },
+        {KE_IGNORE, 0x63, {KEY_BRIGHTNESSDOWN} },
         {KE_KEY, 0x64, {KEY_SWITCHVIDEOMODE} }, /* Display Switch */
+        {KE_IGNORE, 0x81, {KEY_SLEEP} },
         {KE_KEY, 0x82, {KEY_TOUCHPAD_TOGGLE} }, /* Touch Pad On/Off */
+        {KE_IGNORE, 0x83, {KEY_TOUCHPAD_TOGGLE} },
         {KE_END, 0}
 };
 
@@ -122,6 +135,7 @@ struct event_return_value {
  */
 #define ACER_WMID3_GDS_WIRELESS         (1<<0)  /* WiFi */
 #define ACER_WMID3_GDS_THREEG           (1<<6)  /* 3G */
+#define ACER_WMID3_GDS_WIMAX            (1<<7)  /* WiMAX */
 #define ACER_WMID3_GDS_BLUETOOTH        (1<<11) /* BT */
 
 struct lm_input_params {
@@ -737,8 +751,11 @@ WMI_execute_u32(u32 method_id, u32 in, u32 *out)
 
         obj = (union acpi_object *) result.pointer;
         if (obj && obj->type == ACPI_TYPE_BUFFER &&
-                obj->buffer.length == sizeof(u32)) {
+                (obj->buffer.length == sizeof(u32) ||
+                obj->buffer.length == sizeof(u64))) {
                 tmp = *((u32 *) obj->buffer.pointer);
+        } else if (obj->type == ACPI_TYPE_INTEGER) {
+                tmp = (u32) obj->integer.value;
         } else {
                 tmp = 0;
         }
@@ -866,8 +883,11 @@ static acpi_status WMID_set_capabilities(void)
 
         obj = (union acpi_object *) out.pointer;
         if (obj && obj->type == ACPI_TYPE_BUFFER &&
-                obj->buffer.length == sizeof(u32)) {
+                (obj->buffer.length == sizeof(u32) ||
+                obj->buffer.length == sizeof(u64))) {
                 devices = *((u32 *) obj->buffer.pointer);
+        } else if (obj->type == ACPI_TYPE_INTEGER) {
+                devices = (u32) obj->integer.value;
         } else {
                 kfree(out.pointer);
                 return AE_ERROR;
@@ -876,7 +896,8 @@ static acpi_status WMID_set_capabilities(void)
         dmi_walk(type_aa_dmi_decode, NULL);
         if (!has_type_aa) {
                 interface->capability |= ACER_CAP_WIRELESS;
-                interface->capability |= ACER_CAP_THREEG;
+                if (devices & 0x40)
+                        interface->capability |= ACER_CAP_THREEG;
                 if (devices & 0x10)
                         interface->capability |= ACER_CAP_BLUETOOTH;
         }
@@ -961,10 +982,12 @@ static void __init acer_commandline_init(void)
          * These will all fail silently if the value given is invalid, or the
          * capability isn't available on the given interface
          */
-        set_u32(mailled, ACER_CAP_MAILLED);
-        if (!has_type_aa)
+        if (mailled >= 0)
+                set_u32(mailled, ACER_CAP_MAILLED);
+        if (!has_type_aa && threeg >= 0)
                 set_u32(threeg, ACER_CAP_THREEG);
-        set_u32(brightness, ACER_CAP_BRIGHTNESS);
+        if (brightness >= 0)
+                set_u32(brightness, ACER_CAP_BRIGHTNESS);
 }
 
 /*
@@ -1081,7 +1104,7 @@ static acpi_status wmid3_get_device_status(u32 *value, u16 device)
                 return AE_ERROR;
         }
         if (obj->buffer.length != 8) {
-                pr_warning("Unknown buffer length %d\n", obj->buffer.length);
+                pr_warn("Unknown buffer length %d\n", obj->buffer.length);
                 kfree(obj);
                 return AE_ERROR;
         }
@@ -1090,8 +1113,8 @@ static acpi_status wmid3_get_device_status(u32 *value, u16 device)
         kfree(obj);
 
         if (return_value.error_code || return_value.ec_return_value)
-                pr_warning("Get Device Status failed: "
-                        "0x%x - 0x%x\n", return_value.error_code,
+                pr_warn("Get Device Status failed: 0x%x - 0x%x\n",
+                        return_value.error_code,
                         return_value.ec_return_value);
         else
                 *value = !!(return_value.devices & device);
@@ -1124,6 +1147,114 @@ static acpi_status get_device_status(u32 *value, u32 cap)
         }
 }
 
+static acpi_status wmid3_set_device_status(u32 value, u16 device)
+{
+        struct wmid3_gds_return_value return_value;
+        acpi_status status;
+        union acpi_object *obj;
+        u16 devices;
+        struct wmid3_gds_input_param params = {
+                .function_num = 0x1,
+                .hotkey_number = 0x01,
+                .devices = ACER_WMID3_GDS_WIRELESS &
+                                ACER_WMID3_GDS_THREEG &
+                                ACER_WMID3_GDS_WIMAX &
+                                ACER_WMID3_GDS_BLUETOOTH,
+        };
+        struct acpi_buffer input = {
+                sizeof(struct wmid3_gds_input_param),
+                &params
+        };
+        struct acpi_buffer output = { ACPI_ALLOCATE_BUFFER, NULL };
+        struct acpi_buffer output2 = { ACPI_ALLOCATE_BUFFER, NULL };
+
+        status = wmi_evaluate_method(WMID_GUID3, 0, 0x2, &input, &output);
+        if (ACPI_FAILURE(status))
+                return status;
+
+        obj = output.pointer;
+
+        if (!obj)
+                return AE_ERROR;
+        else if (obj->type != ACPI_TYPE_BUFFER) {
+                kfree(obj);
+                return AE_ERROR;
+        }
+        if (obj->buffer.length != 8) {
+                pr_warning("Unknown buffer length %d\n", obj->buffer.length);
+                kfree(obj);
+                return AE_ERROR;
+        }
+
+        return_value = *((struct wmid3_gds_return_value *)obj->buffer.pointer);
+        kfree(obj);
+
+        if (return_value.error_code || return_value.ec_return_value) {
+                pr_warning("Get Current Device Status failed: "
+                        "0x%x - 0x%x\n", return_value.error_code,
+                        return_value.ec_return_value);
+                return status;
+        }
+
+        devices = return_value.devices;
+        params.function_num = 0x2;
+        params.hotkey_number = 0x01;
+        params.devices = (value) ? (devices | device) : (devices & ~device);
+
+        status = wmi_evaluate_method(WMID_GUID3, 0, 0x1, &input, &output2);
+        if (ACPI_FAILURE(status))
+                return status;
+
+        obj = output2.pointer;
+
+        if (!obj)
+                return AE_ERROR;
+        else if (obj->type != ACPI_TYPE_BUFFER) {
+                kfree(obj);
+                return AE_ERROR;
+        }
+        if (obj->buffer.length != 4) {
+                pr_warning("Unknown buffer length %d\n", obj->buffer.length);
+                kfree(obj);
+                return AE_ERROR;
+        }
+
+        return_value = *((struct wmid3_gds_return_value *)obj->buffer.pointer);
+        kfree(obj);
+
+        if (return_value.error_code || return_value.ec_return_value)
+                pr_warning("Set Device Status failed: "
+                        "0x%x - 0x%x\n", return_value.error_code,
+                        return_value.ec_return_value);
+
+        return status;
+}
+
+static acpi_status set_device_status(u32 value, u32 cap)
+{
+        if (wmi_has_guid(WMID_GUID3)) {
+                u16 device;
+
+                switch (cap) {
+                case ACER_CAP_WIRELESS:
+                        device = ACER_WMID3_GDS_WIRELESS;
+                        break;
+                case ACER_CAP_BLUETOOTH:
+                        device = ACER_WMID3_GDS_BLUETOOTH;
+                        break;
+                case ACER_CAP_THREEG:
+                        device = ACER_WMID3_GDS_THREEG;
+                        break;
+                default:
+                        return AE_ERROR;
+                }
+                return wmid3_set_device_status(value, device);
+
+        } else {
+                return set_u32(value, cap);
+        }
+}
+
 /*
  * Rfkill devices
  */
@@ -1160,7 +1291,7 @@ static int acer_rfkill_set(void *data, bool blocked)
         u32 cap = (unsigned long)data;
 
         if (rfkill_inited) {
-                status = set_u32(!blocked, cap);
+                status = set_device_status(!blocked, cap);
                 if (ACPI_FAILURE(status))
                         return -ENODEV;
         }
@@ -1317,7 +1448,7 @@ static void acer_wmi_notify(u32 value, void *context)
 
         status = wmi_get_event_data(value, &response);
         if (status != AE_OK) {
-                pr_warning("bad event status 0x%x\n", status);
+                pr_warn("bad event status 0x%x\n", status);
                 return;
         }
 
@@ -1326,12 +1457,12 @@ static void acer_wmi_notify(u32 value, void *context)
         if (!obj)
                 return;
         if (obj->type != ACPI_TYPE_BUFFER) {
-                pr_warning("Unknown response received %d\n", obj->type);
+                pr_warn("Unknown response received %d\n", obj->type);
                 kfree(obj);
                 return;
         }
         if (obj->buffer.length != 8) {
-                pr_warning("Unknown buffer length %d\n", obj->buffer.length);
+                pr_warn("Unknown buffer length %d\n", obj->buffer.length);
                 kfree(obj);
                 return;
         }
@@ -1343,7 +1474,7 @@ static void acer_wmi_notify(u32 value, void *context)
         case WMID_HOTKEY_EVENT:
                 if (return_value.device_state) {
                         u16 device_state = return_value.device_state;
-                        pr_debug("deivces states: 0x%x\n", device_state);
+                        pr_debug("device state: 0x%x\n", device_state);
                         if (has_cap(ACER_CAP_WIRELESS))
                                 rfkill_set_sw_state(wireless_rfkill,
                                 !(device_state & ACER_WMID3_GDS_WIRELESS));
@@ -1356,11 +1487,11 @@ static void acer_wmi_notify(u32 value, void *context)
                 }
                 if (!sparse_keymap_report_event(acer_wmi_input_dev,
                                 return_value.key_num, 1, true))
-                        pr_warning("Unknown key number - 0x%x\n",
+                        pr_warn("Unknown key number - 0x%x\n",
                                 return_value.key_num);
                 break;
         default:
-                pr_warning("Unknown function number - %d - %d\n",
+                pr_warn("Unknown function number - %d - %d\n",
                         return_value.function, return_value.key_num);
                 break;
         }
@@ -1389,7 +1520,7 @@ wmid3_set_lm_mode(struct lm_input_params *params,
                 return AE_ERROR;
         }
         if (obj->buffer.length != 4) {
-                pr_warning("Unknown buffer length %d\n", obj->buffer.length);
+                pr_warn("Unknown buffer length %d\n", obj->buffer.length);
                 kfree(obj);
                 return AE_ERROR;
         }
@@ -1414,11 +1545,11 @@ static int acer_wmi_enable_ec_raw(void)
         status = wmid3_set_lm_mode(&params, &return_value);
 
         if (return_value.error_code || return_value.ec_return_value)
-                pr_warning("Enabling EC raw mode failed: "
-                       "0x%x - 0x%x\n", return_value.error_code,
-                       return_value.ec_return_value);
+                pr_warn("Enabling EC raw mode failed: 0x%x - 0x%x\n",
+                        return_value.error_code,
+                        return_value.ec_return_value);
         else
-                pr_info("Enabled EC raw mode");
+                pr_info("Enabled EC raw mode\n");
 
         return status;
 }
@@ -1437,9 +1568,9 @@ static int acer_wmi_enable_lm(void)
         status = wmid3_set_lm_mode(&params, &return_value);
 
         if (return_value.error_code || return_value.ec_return_value)
-                pr_warning("Enabling Launch Manager failed: "
-                       "0x%x - 0x%x\n", return_value.error_code,
-                       return_value.ec_return_value);
+                pr_warn("Enabling Launch Manager failed: 0x%x - 0x%x\n",
+                        return_value.error_code,
+                        return_value.ec_return_value);
 
         return status;
 }
@@ -1506,8 +1637,11 @@ static u32 get_wmid_devices(void)
 
         obj = (union acpi_object *) out.pointer;
         if (obj && obj->type == ACPI_TYPE_BUFFER &&
-                obj->buffer.length == sizeof(u32)) {
+                (obj->buffer.length == sizeof(u32) ||
+                obj->buffer.length == sizeof(u64))) {
                 devices = *((u32 *) obj->buffer.pointer);
+        } else if (obj->type == ACPI_TYPE_INTEGER) {
+                devices = (u32) obj->integer.value;
         }
 
         kfree(out.pointer);
diff --git a/drivers/platform/x86/acerhdf.c b/drivers/platform/x86/acerhdf.c
index 60f9cfcac93f..fca3489218b7 100644
--- a/drivers/platform/x86/acerhdf.c
+++ b/drivers/platform/x86/acerhdf.c
@@ -35,10 +35,8 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/fs.h>
 #include <linux/dmi.h>
-#include <acpi/acpi_drivers.h>
-#include <linux/sched.h>
+#include <linux/acpi.h>
 #include <linux/thermal.h>
 #include <linux/platform_device.h>
 
diff --git a/drivers/platform/x86/asus-laptop.c b/drivers/platform/x86/asus-laptop.c
index c53b3ff7978a..d65df92e2acc 100644
--- a/drivers/platform/x86/asus-laptop.c
+++ b/drivers/platform/x86/asus-laptop.c
@@ -318,7 +318,7 @@ static int acpi_check_handle(acpi_handle handle, const char *method,
 
         if (status != AE_OK) {
                 if (ret)
-                        pr_warning("Error finding %s\n", method);
+                        pr_warn("Error finding %s\n", method);
                 return -ENODEV;
         }
         return 0;
@@ -383,7 +383,7 @@ static int asus_kled_lvl(struct asus_laptop *asus)
         rv = acpi_evaluate_integer(asus->handle, METHOD_KBD_LIGHT_GET,
                                    &params, &kblv);
         if (ACPI_FAILURE(rv)) {
-                pr_warning("Error reading kled level\n");
+                pr_warn("Error reading kled level\n");
                 return -ENODEV;
         }
         return kblv;
@@ -397,7 +397,7 @@ static int asus_kled_set(struct asus_laptop *asus, int kblv)
                 kblv = 0;
 
         if (write_acpi_int(asus->handle, METHOD_KBD_LIGHT_SET, kblv)) {
-                pr_warning("Keyboard LED display write failed\n");
+                pr_warn("Keyboard LED display write failed\n");
                 return -EINVAL;
         }
         return 0;
@@ -531,7 +531,7 @@ static int asus_read_brightness(struct backlight_device *bd)
         rv = acpi_evaluate_integer(asus->handle, METHOD_BRIGHTNESS_GET,
                                    NULL, &value);
         if (ACPI_FAILURE(rv))
-                pr_warning("Error reading brightness\n");
+                pr_warn("Error reading brightness\n");
 
         return value;
 }
@@ -541,7 +541,7 @@ static int asus_set_brightness(struct backlight_device *bd, int value)
         struct asus_laptop *asus = bl_get_data(bd);
 
         if (write_acpi_int(asus->handle, METHOD_BRIGHTNESS_SET, value)) {
-                pr_warning("Error changing brightness\n");
+                pr_warn("Error changing brightness\n");
                 return -EIO;
         }
         return 0;
@@ -730,7 +730,7 @@ static ssize_t store_ledd(struct device *dev, struct device_attribute *attr,
         rv = parse_arg(buf, count, &value);
         if (rv > 0) {
                 if (write_acpi_int(asus->handle, METHOD_LEDD, value)) {
-                        pr_warning("LED display write failed\n");
+                        pr_warn("LED display write failed\n");
                         return -ENODEV;
                 }
                 asus->ledd_status = (u32) value;
@@ -752,7 +752,7 @@ static int asus_wireless_status(struct asus_laptop *asus, int mask)
         rv = acpi_evaluate_integer(asus->handle, METHOD_WL_STATUS,
                                    NULL, &status);
         if (ACPI_FAILURE(rv)) {
-                pr_warning("Error reading Wireless status\n");
+                pr_warn("Error reading Wireless status\n");
                 return -EINVAL;
         }
         return !!(status & mask);
@@ -764,7 +764,7 @@ static int asus_wireless_status(struct asus_laptop *asus, int mask)
 static int asus_wlan_set(struct asus_laptop *asus, int status)
 {
         if (write_acpi_int(asus->handle, METHOD_WLAN, !!status)) {
-                pr_warning("Error setting wlan status to %d", status);
+                pr_warn("Error setting wlan status to %d\n", status);
                 return -EIO;
         }
         return 0;
@@ -792,7 +792,7 @@ static ssize_t store_wlan(struct device *dev, struct device_attribute *attr,
 static int asus_bluetooth_set(struct asus_laptop *asus, int status)
 {
         if (write_acpi_int(asus->handle, METHOD_BLUETOOTH, !!status)) {
-                pr_warning("Error setting bluetooth status to %d", status);
+                pr_warn("Error setting bluetooth status to %d\n", status);
                 return -EIO;
         }
         return 0;
@@ -821,7 +821,7 @@ static ssize_t store_bluetooth(struct device *dev,
 static int asus_wimax_set(struct asus_laptop *asus, int status)
 {
         if (write_acpi_int(asus->handle, METHOD_WIMAX, !!status)) {
-                pr_warning("Error setting wimax status to %d", status);
+                pr_warn("Error setting wimax status to %d\n", status);
                 return -EIO;
         }
         return 0;
@@ -850,7 +850,7 @@ static ssize_t store_wimax(struct device *dev,
 static int asus_wwan_set(struct asus_laptop *asus, int status)
 {
         if (write_acpi_int(asus->handle, METHOD_WWAN, !!status)) {
-                pr_warning("Error setting wwan status to %d", status);
+                pr_warn("Error setting wwan status to %d\n", status);
                 return -EIO;
         }
         return 0;
@@ -880,7 +880,7 @@ static void asus_set_display(struct asus_laptop *asus, int value)
 {
         /* no sanity check needed for now */
         if (write_acpi_int(asus->handle, METHOD_SWITCH_DISPLAY, value))
-                pr_warning("Error setting display\n");
+                pr_warn("Error setting display\n");
         return;
 }
 
@@ -909,7 +909,7 @@ static ssize_t store_disp(struct device *dev, struct device_attribute *attr,
 static void asus_als_switch(struct asus_laptop *asus, int value)
 {
         if (write_acpi_int(asus->handle, METHOD_ALS_CONTROL, value))
-                pr_warning("Error setting light sensor switch\n");
+                pr_warn("Error setting light sensor switch\n");
         asus->light_switch = value;
 }
 
@@ -937,7 +937,7 @@ static ssize_t store_lssw(struct device *dev, struct device_attribute *attr,
 static void asus_als_level(struct asus_laptop *asus, int value)
 {
         if (write_acpi_int(asus->handle, METHOD_ALS_LEVEL, value))
-                pr_warning("Error setting light sensor level\n");
+                pr_warn("Error setting light sensor level\n");
         asus->light_level = value;
 }
 
@@ -976,7 +976,7 @@ static int asus_gps_status(struct asus_laptop *asus)
         rv = acpi_evaluate_integer(asus->handle, METHOD_GPS_STATUS,
                                    NULL, &status);
         if (ACPI_FAILURE(rv)) {
-                pr_warning("Error reading GPS status\n");
+                pr_warn("Error reading GPS status\n");
                 return -ENODEV;
         }
         return !!status;
@@ -1284,7 +1284,7 @@ static int asus_laptop_get_info(struct asus_laptop *asus)
          */
         status = acpi_get_table(ACPI_SIG_DSDT, 1, &asus->dsdt_info);
         if (ACPI_FAILURE(status))
-                pr_warning("Couldn't get the DSDT table header\n");
+                pr_warn("Couldn't get the DSDT table header\n");
 
         /* We have to write 0 on init this far for all ASUS models */
         if (write_acpi_int_ret(asus->handle, "INIT", 0, &buffer)) {
@@ -1296,7 +1296,7 @@ static int asus_laptop_get_info(struct asus_laptop *asus)
         status =
             acpi_evaluate_integer(asus->handle, "BSTS", NULL, &bsts_result);
         if (ACPI_FAILURE(status))
-                pr_warning("Error calling BSTS\n");
+                pr_warn("Error calling BSTS\n");
         else if (bsts_result)
                 pr_notice("BSTS called, 0x%02x returned\n",
                        (uint) bsts_result);
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index 832a3fd7c1c8..00460cb9587b 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -425,7 +425,7 @@ static void asus_rfkill_hotplug(struct asus_wmi *asus)
         if (asus->hotplug_slot) {
                 bus = pci_find_bus(0, 1);
                 if (!bus) {
-                        pr_warning("Unable to find PCI bus 1?\n");
+                        pr_warn("Unable to find PCI bus 1?\n");
                         goto out_unlock;
                 }
 
@@ -436,12 +436,12 @@ static void asus_rfkill_hotplug(struct asus_wmi *asus)
                 absent = (l == 0xffffffff);
 
                 if (blocked != absent) {
-                        pr_warning("BIOS says wireless lan is %s, "
-                                   "but the pci device is %s\n",
-                                   blocked ? "blocked" : "unblocked",
-                                   absent ? "absent" : "present");
-                        pr_warning("skipped wireless hotplug as probably "
-                                   "inappropriate for this model\n");
+                        pr_warn("BIOS says wireless lan is %s, "
+                                "but the pci device is %s\n",
+                                blocked ? "blocked" : "unblocked",
+                                absent ? "absent" : "present");
+                        pr_warn("skipped wireless hotplug as probably "
+                                "inappropriate for this model\n");
                         goto out_unlock;
                 }
 
@@ -500,7 +500,7 @@ static int asus_register_rfkill_notifier(struct asus_wmi *asus, char *node)
                                                      ACPI_SYSTEM_NOTIFY,
                                                      asus_rfkill_notify, asus);
                 if (ACPI_FAILURE(status))
-                        pr_warning("Failed to register notify on %s\n", node);
+                        pr_warn("Failed to register notify on %s\n", node);
         } else
                 return -ENODEV;
 
@@ -1223,7 +1223,7 @@ static int asus_wmi_sysfs_init(struct platform_device *device)
 /*
  * Platform device
  */
-static int __init asus_wmi_platform_init(struct asus_wmi *asus)
+static int asus_wmi_platform_init(struct asus_wmi *asus)
 {
         int rv;
 
@@ -1583,12 +1583,12 @@ static int asus_wmi_probe(struct platform_device *pdev)
         int ret;
 
         if (!wmi_has_guid(ASUS_WMI_MGMT_GUID)) {
-                pr_warning("Management GUID not found\n");
+                pr_warn("Management GUID not found\n");
                 return -ENODEV;
         }
 
         if (wdrv->event_guid && !wmi_has_guid(wdrv->event_guid)) {
-                pr_warning("Event GUID not found\n");
+                pr_warn("Event GUID not found\n");
                 return -ENODEV;
         }
 
diff --git a/drivers/platform/x86/asus_acpi.c b/drivers/platform/x86/asus_acpi.c
index f503607c0645..d9312b3073e5 100644
--- a/drivers/platform/x86/asus_acpi.c
+++ b/drivers/platform/x86/asus_acpi.c
@@ -30,6 +30,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/slab.h>
@@ -581,8 +583,7 @@ static int read_led(const char *ledname, int ledmask)
                 if (read_acpi_int(NULL, ledname, &led_status))
                         return led_status;
                 else
-                        printk(KERN_WARNING "Asus ACPI: Error reading LED "
-                               "status\n");
+                        pr_warn("Error reading LED status\n");
         }
         return (hotk->status & ledmask) ? 1 : 0;
 }
@@ -621,8 +622,7 @@ write_led(const char __user *buffer, unsigned long count,
                 led_out = !led_out;
 
         if (!write_acpi_int(hotk->handle, ledname, led_out, NULL))
-                printk(KERN_WARNING "Asus ACPI: LED (%s) write failed\n",
-                       ledname);
+                pr_warn("LED (%s) write failed\n", ledname);
 
         return rv;
 }
@@ -679,8 +679,7 @@ static ssize_t ledd_proc_write(struct file *file, const char __user *buffer,
         if (rv > 0) {
                 if (!write_acpi_int
                     (hotk->handle, hotk->methods->mt_ledd, value, NULL))
-                        printk(KERN_WARNING
-                               "Asus ACPI: LED display write failed\n");
+                        pr_warn("LED display write failed\n");
                 else
                         hotk->ledd_status = (u32) value;
         }
@@ -838,8 +837,7 @@ static int get_lcd_state(void)
         } else {
                 /* We don't have to check anything if we are here */
                 if (!read_acpi_int(NULL, hotk->methods->lcd_status, &lcd))
-                        printk(KERN_WARNING
-                               "Asus ACPI: Error reading LCD status\n");
+                        pr_warn("Error reading LCD status\n");
 
                 if (hotk->model == L2D)
                         lcd = ~lcd;
@@ -871,7 +869,7 @@ static int set_lcd_state(int value)
                            the exact behaviour is simulated here */
                 }
                 if (ACPI_FAILURE(status))
-                        printk(KERN_WARNING "Asus ACPI: Error switching LCD\n");
+                        pr_warn("Error switching LCD\n");
         }
         return 0;
 
@@ -915,13 +913,11 @@ static int read_brightness(struct backlight_device *bd)
         if (hotk->methods->brightness_get) {    /* SPLV/GPLV laptop */
                 if (!read_acpi_int(hotk->handle, hotk->methods->brightness_get,
                                    &value))
-                        printk(KERN_WARNING
-                               "Asus ACPI: Error reading brightness\n");
+                        pr_warn("Error reading brightness\n");
         } else if (hotk->methods->brightness_status) {  /* For D1 for example */
                 if (!read_acpi_int(NULL, hotk->methods->brightness_status,
                                    &value))
-                        printk(KERN_WARNING
-                               "Asus ACPI: Error reading brightness\n");
+                        pr_warn("Error reading brightness\n");
         } else                  /* No GPLV method */
                 value = hotk->brightness;
         return value;
@@ -939,8 +935,7 @@ static int set_brightness(int value)
         if (hotk->methods->brightness_set) {
                 if (!write_acpi_int(hotk->handle, hotk->methods->brightness_set,
                                     value, NULL)) {
-                        printk(KERN_WARNING
-                               "Asus ACPI: Error changing brightness\n");
+                        pr_warn("Error changing brightness\n");
                         ret = -EIO;
                 }
                 goto out;
@@ -955,8 +950,7 @@ static int set_brightness(int value)
                                               NULL, NULL);
                 (value > 0) ? value-- : value++;
                 if (ACPI_FAILURE(status)) {
-                        printk(KERN_WARNING
-                               "Asus ACPI: Error changing brightness\n");
+                        pr_warn("Error changing brightness\n");
                         ret = -EIO;
                 }
         }
@@ -1008,7 +1002,7 @@ static void set_display(int value)
         /* no sanity check needed for now */
         if (!write_acpi_int(hotk->handle, hotk->methods->display_set,
                             value, NULL))
-                printk(KERN_WARNING "Asus ACPI: Error setting display\n");
+                pr_warn("Error setting display\n");
         return;
 }
 
@@ -1021,8 +1015,7 @@ static int disp_proc_show(struct seq_file *m, void *v)
         int value = 0;
 
         if (!read_acpi_int(hotk->handle, hotk->methods->display_get, &value))
-                printk(KERN_WARNING
-                       "Asus ACPI: Error reading display status\n");
+                pr_warn("Error reading display status\n");
         value &= 0x07;  /* needed for some models, shouldn't hurt others */
         seq_printf(m, "%d\n", value);
         return 0;
@@ -1068,7 +1061,7 @@ asus_proc_add(char *name, const struct file_operations *proc_fops, mode_t mode,
         proc = proc_create_data(name, mode, acpi_device_dir(device),
                                 proc_fops, acpi_driver_data(device));
         if (!proc) {
-                printk(KERN_WARNING "  Unable to create %s fs entry\n", name);
+                pr_warn("  Unable to create %s fs entry\n", name);
                 return -1;
         }
         proc->uid = asus_uid;
@@ -1085,8 +1078,8 @@ static int asus_hotk_add_fs(struct acpi_device *device)
                 mode = S_IFREG | S_IRUGO | S_IWUSR | S_IWGRP;
         } else {
                 mode = S_IFREG | S_IRUSR | S_IRGRP | S_IWUSR | S_IWGRP;
-                printk(KERN_WARNING "  asus_uid and asus_gid parameters are "
-                       "deprecated, use chown and chmod instead!\n");
+                pr_warn("  asus_uid and asus_gid parameters are "
+                        "deprecated, use chown and chmod instead!\n");
         }
 
         acpi_device_dir(device) = asus_proc_dir;
@@ -1099,8 +1092,7 @@ static int asus_hotk_add_fs(struct acpi_device *device)
                 proc->uid = asus_uid;
                 proc->gid = asus_gid;
         } else {
-                printk(KERN_WARNING "  Unable to create " PROC_INFO
-                       " fs entry\n");
+                pr_warn("  Unable to create " PROC_INFO " fs entry\n");
         }
 
         if (hotk->methods->mt_wled) {
@@ -1283,20 +1275,19 @@ static int asus_hotk_get_info(void)
          */
         status = acpi_get_table(ACPI_SIG_DSDT, 1, &asus_info);
         if (ACPI_FAILURE(status))
-                printk(KERN_WARNING "  Couldn't get the DSDT table header\n");
+                pr_warn("  Couldn't get the DSDT table header\n");
 
         /* We have to write 0 on init this far for all ASUS models */
         if (!write_acpi_int(hotk->handle, "INIT", 0, &buffer)) {
-                printk(KERN_ERR "  Hotkey initialization failed\n");
+                pr_err("  Hotkey initialization failed\n");
                 return -ENODEV;
         }
 
         /* This needs to be called for some laptops to init properly */
         if (!read_acpi_int(hotk->handle, "BSTS", &bsts_result))
-                printk(KERN_WARNING "  Error calling BSTS\n");
+                pr_warn("  Error calling BSTS\n");
         else if (bsts_result)
-                printk(KERN_NOTICE "  BSTS called, 0x%02x returned\n",
-                       bsts_result);
+                pr_notice("  BSTS called, 0x%02x returned\n", bsts_result);
 
         /*
          * Try to match the object returned by INIT to the specific model.
@@ -1324,23 +1315,21 @@ static int asus_hotk_get_info(void)
                 if (asus_info &&
                     strncmp(asus_info->oem_table_id, "ODEM", 4) == 0) {
                         hotk->model = P30;
-                        printk(KERN_NOTICE
-                               "  Samsung P30 detected, supported\n");
+                        pr_notice("  Samsung P30 detected, supported\n");
                         hotk->methods = &model_conf[hotk->model];
                         kfree(model);
                         return 0;
                 } else {
                         hotk->model = M2E;
-                        printk(KERN_NOTICE "  unsupported model %s, trying "
-                               "default values\n", string);
-                        printk(KERN_NOTICE
-                               "  send /proc/acpi/dsdt to the developers\n");
+                        pr_notice("  unsupported model %s, trying default values\n",
+                                  string);
+                        pr_notice("  send /proc/acpi/dsdt to the developers\n");
                         kfree(model);
                         return -ENODEV;
                 }
         }
         hotk->methods = &model_conf[hotk->model];
-        printk(KERN_NOTICE "  %s model detected, supported\n", string);
+        pr_notice("  %s model detected, supported\n", string);
 
         /* Sort of per-model blacklist */
         if (strncmp(string, "L2B", 3) == 0)
@@ -1385,7 +1374,7 @@ static int asus_hotk_check(void)
         if (hotk->device->status.present) {
                 result = asus_hotk_get_info();
         } else {
-                printk(KERN_ERR "  Hotkey device not present, aborting\n");
+                pr_err("  Hotkey device not present, aborting\n");
                 return -EINVAL;
         }
 
@@ -1399,8 +1388,7 @@ static int asus_hotk_add(struct acpi_device *device)
         acpi_status status = AE_OK;
         int result;
 
-        printk(KERN_NOTICE "Asus Laptop ACPI Extras version %s\n",
-               ASUS_ACPI_VERSION);
+        pr_notice("Asus Laptop ACPI Extras version %s\n", ASUS_ACPI_VERSION);
 
         hotk = kzalloc(sizeof(struct asus_hotk), GFP_KERNEL);
         if (!hotk)
@@ -1428,15 +1416,14 @@ static int asus_hotk_add(struct acpi_device *device)
                     acpi_evaluate_object(NULL, hotk->methods->brightness_down,
                                          NULL, NULL);
                 if (ACPI_FAILURE(status))
-                        printk(KERN_WARNING "  Error changing brightness\n");
+                        pr_warn("  Error changing brightness\n");
                 else {
                         status =
                             acpi_evaluate_object(NULL,
                                                  hotk->methods->brightness_up,
                                                  NULL, NULL);
                         if (ACPI_FAILURE(status))
-                                printk(KERN_WARNING "  Strange, error changing"
-                                       " brightness\n");
+                                pr_warn("  Strange, error changing brightness\n");
                 }
         }
 
@@ -1488,7 +1475,7 @@ static int __init asus_acpi_init(void)
 
         asus_proc_dir = proc_mkdir(PROC_ASUS, acpi_root_dir);
         if (!asus_proc_dir) {
-                printk(KERN_ERR "Asus ACPI: Unable to create /proc entry\n");
+                pr_err("Unable to create /proc entry\n");
                 acpi_bus_unregister_driver(&asus_hotk_driver);
                 return -ENODEV;
         }
@@ -1513,7 +1500,7 @@ static int __init asus_acpi_init(void)
                                                           &asus_backlight_data,
                                                           &props);
         if (IS_ERR(asus_backlight_device)) {
-                printk(KERN_ERR "Could not register asus backlight device\n");
+                pr_err("Could not register asus backlight device\n");
                 asus_backlight_device = NULL;
                 asus_acpi_exit();
                 return -ENODEV;
diff --git a/drivers/platform/x86/compal-laptop.c b/drivers/platform/x86/compal-laptop.c
index c16a27641ced..3f204fde1b02 100644
--- a/drivers/platform/x86/compal-laptop.c
+++ b/drivers/platform/x86/compal-laptop.c
@@ -68,6 +68,8 @@
  * only enabled on a JHL90 board until it is verified that they work on the
  * other boards too.  See the extra_features variable. */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -200,8 +202,8 @@ static bool extra_features;
  * watching the output of address 0x4F (do an ec_transaction writing 0x33
  * into 0x4F and read a few bytes from the output, like so:
  *      u8 writeData = 0x33;
- *      ec_transaction(0x4F, &writeData, 1, buffer, 32, 0);
- * That address is labelled "fan1 table information" in the service manual.
+ *      ec_transaction(0x4F, &writeData, 1, buffer, 32);
+ * That address is labeled "fan1 table information" in the service manual.
  * It should be clear which value in 'buffer' changes). This seems to be
  * related to fan speed. It isn't a proper 'realtime' fan speed value
  * though, because physically stopping or speeding up the fan doesn't
@@ -286,7 +288,7 @@ static int get_backlight_level(void)
 static void set_backlight_state(bool on)
 {
         u8 data = on ? BACKLIGHT_STATE_ON_DATA : BACKLIGHT_STATE_OFF_DATA;
-        ec_transaction(BACKLIGHT_STATE_ADDR, &data, 1, NULL, 0, 0);
+        ec_transaction(BACKLIGHT_STATE_ADDR, &data, 1, NULL, 0);
 }
 
 
@@ -294,24 +296,24 @@ static void set_backlight_state(bool on)
 static void pwm_enable_control(void)
 {
         unsigned char writeData = PWM_ENABLE_DATA;
-        ec_transaction(PWM_ENABLE_ADDR, &writeData, 1, NULL, 0, 0);
+        ec_transaction(PWM_ENABLE_ADDR, &writeData, 1, NULL, 0);
 }
 
 static void pwm_disable_control(void)
 {
         unsigned char writeData = PWM_DISABLE_DATA;
-        ec_transaction(PWM_DISABLE_ADDR, &writeData, 1, NULL, 0, 0);
+        ec_transaction(PWM_DISABLE_ADDR, &writeData, 1, NULL, 0);
 }
 
 static void set_pwm(int pwm)
 {
-        ec_transaction(PWM_ADDRESS, &pwm_lookup_table[pwm], 1, NULL, 0, 0);
+        ec_transaction(PWM_ADDRESS, &pwm_lookup_table[pwm], 1, NULL, 0);
 }
 
 static int get_fan_rpm(void)
 {
         u8 value, data = FAN_DATA;
-        ec_transaction(FAN_ADDRESS, &data, 1, &value, 1, 0);
+        ec_transaction(FAN_ADDRESS, &data, 1, &value, 1);
         return 100 * (int)value;
 }
 
@@ -760,16 +762,14 @@ static struct rfkill *bt_rfkill;
 
 static int dmi_check_cb(const struct dmi_system_id *id)
 {
-        printk(KERN_INFO DRIVER_NAME": Identified laptop model '%s'\n",
-                id->ident);
+        pr_info("Identified laptop model '%s'\n", id->ident);
         extra_features = false;
         return 1;
 }
 
 static int dmi_check_cb_extra(const struct dmi_system_id *id)
 {
-        printk(KERN_INFO DRIVER_NAME": Identified laptop model '%s', "
-                "enabling extra features\n",
+        pr_info("Identified laptop model '%s', enabling extra features\n",
                 id->ident);
         extra_features = true;
         return 1;
@@ -956,14 +956,12 @@ static int __init compal_init(void)
         int ret;
 
         if (acpi_disabled) {
-                printk(KERN_ERR DRIVER_NAME": ACPI needs to be enabled for "
-                                                "this driver to work!\n");
+                pr_err("ACPI needs to be enabled for this driver to work!\n");
                 return -ENODEV;
         }
 
         if (!force && !dmi_check_system(compal_dmi_table)) {
-                printk(KERN_ERR DRIVER_NAME": Motherboard not recognized (You "
-                                "could try the module's force-parameter)");
+                pr_err("Motherboard not recognized (You could try the module's force-parameter)\n");
                 return -ENODEV;
         }
 
@@ -998,8 +996,7 @@ static int __init compal_init(void)
         if (ret)
                 goto err_rfkill;
 
-        printk(KERN_INFO DRIVER_NAME": Driver "DRIVER_VERSION
-                                                " successfully loaded\n");
+        pr_info("Driver " DRIVER_VERSION " successfully loaded\n");
         return 0;
 
 err_rfkill:
@@ -1064,7 +1061,7 @@ static void __exit compal_cleanup(void)
         rfkill_destroy(wifi_rfkill);
         rfkill_destroy(bt_rfkill);
 
-        printk(KERN_INFO DRIVER_NAME": Driver unloaded\n");
+        pr_info("Driver unloaded\n");
 }
 
 static int __devexit compal_remove(struct platform_device *pdev)
@@ -1074,8 +1071,7 @@ static int __devexit compal_remove(struct platform_device *pdev)
         if (!extra_features)
                 return 0;
 
-        printk(KERN_INFO DRIVER_NAME": Unloading: resetting fan control "
-                                                        "to motherboard\n");
+        pr_info("Unloading: resetting fan control to motherboard\n");
         pwm_disable_control();
 
         data = platform_get_drvdata(pdev);
diff --git a/drivers/platform/x86/dell-laptop.c b/drivers/platform/x86/dell-laptop.c
index de301aa8e5c3..d3841de6a8cf 100644
--- a/drivers/platform/x86/dell-laptop.c
+++ b/drivers/platform/x86/dell-laptop.c
@@ -11,6 +11,8 @@
  *  published by the Free Software Foundation.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -434,8 +436,7 @@ static int __init dell_setup_rfkill(void)
         int ret;
 
         if (dmi_check_system(dell_blacklist)) {
-                printk(KERN_INFO "dell-laptop: Blacklisted hardware detected - "
-                                "not enabling rfkill\n");
+                pr_info("Blacklisted hardware detected - not enabling rfkill\n");
                 return 0;
         }
 
@@ -606,7 +607,7 @@ static int __init dell_init(void)
         dmi_walk(find_tokens, NULL);
 
         if (!da_tokens)  {
-                printk(KERN_INFO "dell-laptop: Unable to find dmi tokens\n");
+                pr_info("Unable to find dmi tokens\n");
                 return -ENODEV;
         }
 
@@ -636,14 +637,13 @@ static int __init dell_init(void)
         ret = dell_setup_rfkill();
 
         if (ret) {
-                printk(KERN_WARNING "dell-laptop: Unable to setup rfkill\n");
+                pr_warn("Unable to setup rfkill\n");
                 goto fail_rfkill;
         }
 
         ret = i8042_install_filter(dell_laptop_i8042_filter);
         if (ret) {
-                printk(KERN_WARNING
-                       "dell-laptop: Unable to install key filter\n");
+                pr_warn("Unable to install key filter\n");
                 goto fail_filter;
         }
 
diff --git a/drivers/platform/x86/dell-wmi-aio.c b/drivers/platform/x86/dell-wmi-aio.c
index 0ed84573ae1f..3f945457f71c 100644
--- a/drivers/platform/x86/dell-wmi-aio.c
+++ b/drivers/platform/x86/dell-wmi-aio.c
@@ -15,6 +15,7 @@
  *  along with this program; if not, write to the Free Software
  *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
+
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/kernel.h>
@@ -138,7 +139,7 @@ static int __init dell_wmi_aio_init(void)
 
         guid = dell_wmi_aio_find();
         if (!guid) {
-                pr_warning("No known WMI GUID found\n");
+                pr_warn("No known WMI GUID found\n");
                 return -ENXIO;
         }
 
diff --git a/drivers/platform/x86/dell-wmi.c b/drivers/platform/x86/dell-wmi.c
index 77f1d55414c6..ce790827e199 100644
--- a/drivers/platform/x86/dell-wmi.c
+++ b/drivers/platform/x86/dell-wmi.c
@@ -23,6 +23,8 @@
  *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -141,7 +143,7 @@ static void dell_wmi_notify(u32 value, void *context)
 
         status = wmi_get_event_data(value, &response);
         if (status != AE_OK) {
-                printk(KERN_INFO "dell-wmi: bad event status 0x%x\n", status);
+                pr_info("bad event status 0x%x\n", status);
                 return;
         }
 
@@ -153,8 +155,8 @@ static void dell_wmi_notify(u32 value, void *context)
                 u16 *buffer_entry = (u16 *)obj->buffer.pointer;
 
                 if (dell_new_hk_type && (buffer_entry[1] != 0x10)) {
-                        printk(KERN_INFO "dell-wmi: Received unknown WMI event"
-                                         " (0x%x)\n", buffer_entry[1]);
+                        pr_info("Received unknown WMI event (0x%x)\n",
+                                buffer_entry[1]);
                         kfree(obj);
                         return;
                 }
@@ -167,8 +169,7 @@ static void dell_wmi_notify(u32 value, void *context)
                 key = sparse_keymap_entry_from_scancode(dell_wmi_input_dev,
                                                         reported_key);
                 if (!key) {
-                        printk(KERN_INFO "dell-wmi: Unknown key %x pressed\n",
-                                reported_key);
+                        pr_info("Unknown key %x pressed\n", reported_key);
                 } else if ((key->keycode == KEY_BRIGHTNESSUP ||
                             key->keycode == KEY_BRIGHTNESSDOWN) && acpi_video) {
                         /* Don't report brightness notifications that will also
@@ -275,7 +276,7 @@ static int __init dell_wmi_init(void)
         acpi_status status;
 
         if (!wmi_has_guid(DELL_EVENT_GUID)) {
-                printk(KERN_WARNING "dell-wmi: No known WMI GUID found\n");
+                pr_warn("No known WMI GUID found\n");
                 return -ENODEV;
         }
 
@@ -290,9 +291,7 @@ static int __init dell_wmi_init(void)
                                          dell_wmi_notify, NULL);
         if (ACPI_FAILURE(status)) {
                 dell_wmi_input_destroy();
-                printk(KERN_ERR
-                        "dell-wmi: Unable to register notify handler - %d\n",
-                        status);
+                pr_err("Unable to register notify handler - %d\n", status);
                 return -ENODEV;
         }
 
diff --git a/drivers/platform/x86/eeepc-laptop.c b/drivers/platform/x86/eeepc-laptop.c
index 2c1abf63957f..1c45d92e2163 100644
--- a/drivers/platform/x86/eeepc-laptop.c
+++ b/drivers/platform/x86/eeepc-laptop.c
@@ -228,7 +228,7 @@ static int set_acpi(struct eeepc_laptop *eeepc, int cm, int value)
                 return -ENODEV;
 
         if (write_acpi_int(eeepc->handle, method, value))
-                pr_warning("Error writing %s\n", method);
+                pr_warn("Error writing %s\n", method);
         return 0;
 }
 
@@ -243,7 +243,7 @@ static int get_acpi(struct eeepc_laptop *eeepc, int cm)
                 return -ENODEV;
 
         if (read_acpi_int(eeepc->handle, method, &value))
-                pr_warning("Error reading %s\n", method);
+                pr_warn("Error reading %s\n", method);
         return value;
 }
 
@@ -261,7 +261,7 @@ static int acpi_setter_handle(struct eeepc_laptop *eeepc, int cm,
         status = acpi_get_handle(eeepc->handle, (char *)method,
                                  handle);
         if (status != AE_OK) {
-                pr_warning("Error finding %s\n", method);
+                pr_warn("Error finding %s\n", method);
                 return -ENODEV;
         }
         return 0;
@@ -417,7 +417,7 @@ static ssize_t store_cpufv_disabled(struct device *dev,
         switch (value) {
         case 0:
                 if (eeepc->cpufv_disabled)
-                        pr_warning("cpufv enabled (not officially supported "
+                        pr_warn("cpufv enabled (not officially supported "
                                 "on this model)\n");
                 eeepc->cpufv_disabled = false;
                 return rv;
@@ -609,7 +609,7 @@ static void eeepc_rfkill_hotplug(struct eeepc_laptop *eeepc, acpi_handle handle)
                 bus = port->subordinate;
 
                 if (!bus) {
-                        pr_warning("Unable to find PCI bus?\n");
+                        pr_warn("Unable to find PCI bus 1?\n");
                         goto out_unlock;
                 }
 
@@ -621,12 +621,12 @@ static void eeepc_rfkill_hotplug(struct eeepc_laptop *eeepc, acpi_handle handle)
                 absent = (l == 0xffffffff);
 
                 if (blocked != absent) {
-                        pr_warning("BIOS says wireless lan is %s, "
-                                        "but the pci device is %s\n",
+                        pr_warn("BIOS says wireless lan is %s, "
+                                "but the pci device is %s\n",
                                 blocked ? "blocked" : "unblocked",
                                 absent ? "absent" : "present");
-                        pr_warning("skipped wireless hotplug as probably "
-                                        "inappropriate for this model\n");
+                        pr_warn("skipped wireless hotplug as probably "
+                                "inappropriate for this model\n");
                         goto out_unlock;
                 }
 
@@ -691,7 +691,8 @@ static int eeepc_register_rfkill_notifier(struct eeepc_laptop *eeepc,
                                                      eeepc_rfkill_notify,
                                                      eeepc);
                 if (ACPI_FAILURE(status))
-                        pr_warning("Failed to register notify on %s\n", node);
+                        pr_warn("Failed to register notify on %s\n", node);
+
                 /*
                  * Refresh pci hotplug in case the rfkill state was
                  * changed during setup.
diff --git a/drivers/platform/x86/eeepc-wmi.c b/drivers/platform/x86/eeepc-wmi.c
index 649dcadd8ea3..4aa867a9b88b 100644
--- a/drivers/platform/x86/eeepc-wmi.c
+++ b/drivers/platform/x86/eeepc-wmi.c
@@ -84,7 +84,7 @@ static const struct key_entry eeepc_wmi_keymap[] = {
 static acpi_status eeepc_wmi_parse_device(acpi_handle handle, u32 level,
                                                  void *context, void **retval)
 {
-        pr_warning("Found legacy ATKD device (%s)", EEEPC_ACPI_HID);
+        pr_warn("Found legacy ATKD device (%s)\n", EEEPC_ACPI_HID);
         *(bool *)context = true;
         return AE_CTRL_TERMINATE;
 }
@@ -105,12 +105,12 @@ static int eeepc_wmi_check_atkd(void)
 static int eeepc_wmi_probe(struct platform_device *pdev)
 {
         if (eeepc_wmi_check_atkd()) {
-                pr_warning("WMI device present, but legacy ATKD device is also "
-                           "present and enabled.");
-                pr_warning("You probably booted with acpi_osi=\"Linux\" or "
-                           "acpi_osi=\"!Windows 2009\"");
-                pr_warning("Can't load eeepc-wmi, use default acpi_osi "
-                           "(preferred) or eeepc-laptop");
+                pr_warn("WMI device present, but legacy ATKD device is also "
+                        "present and enabled\n");
+                pr_warn("You probably booted with acpi_osi=\"Linux\" or "
+                        "acpi_osi=\"!Windows 2009\"\n");
+                pr_warn("Can't load eeepc-wmi, use default acpi_osi "
+                        "(preferred) or eeepc-laptop\n");
                 return -EBUSY;
         }
         return 0;
diff --git a/drivers/platform/x86/fujitsu-laptop.c b/drivers/platform/x86/fujitsu-laptop.c
index 493054c2dbe1..6b26666b37f2 100644
--- a/drivers/platform/x86/fujitsu-laptop.c
+++ b/drivers/platform/x86/fujitsu-laptop.c
@@ -56,6 +56,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -585,8 +587,7 @@ static struct platform_driver fujitsupf_driver = {
 static void dmi_check_cb_common(const struct dmi_system_id *id)
 {
         acpi_handle handle;
-        printk(KERN_INFO "fujitsu-laptop: Identified laptop model '%s'.\n",
-               id->ident);
+        pr_info("Identified laptop model '%s'\n", id->ident);
         if (use_alt_lcd_levels == -1) {
                 if (ACPI_SUCCESS(acpi_get_handle(NULL,
                                 "\\_SB.PCI0.LPCB.FJEX.SBL2", &handle)))
@@ -691,11 +692,11 @@ static int acpi_fujitsu_add(struct acpi_device *device)
 
         result = acpi_bus_update_power(fujitsu->acpi_handle, &state);
         if (result) {
-                printk(KERN_ERR "Error reading power state\n");
+                pr_err("Error reading power state\n");
                 goto err_unregister_input_dev;
         }
 
-        printk(KERN_INFO "ACPI: %s [%s] (%s)\n",
+        pr_info("ACPI: %s [%s] (%s)\n",
                acpi_device_name(device), acpi_device_bid(device),
                !device->power.state ? "on" : "off");
 
@@ -707,7 +708,7 @@ static int acpi_fujitsu_add(struct acpi_device *device)
                 if (ACPI_FAILURE
                     (acpi_evaluate_object
                      (device->handle, METHOD_NAME__INI, NULL, NULL)))
-                        printk(KERN_ERR "_INI Method failed\n");
+                        pr_err("_INI Method failed\n");
         }
 
         /* do config (detect defaults) */
@@ -827,7 +828,7 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
         error = kfifo_alloc(&fujitsu_hotkey->fifo, RINGBUFFERSIZE * sizeof(int),
                         GFP_KERNEL);
         if (error) {
-                printk(KERN_ERR "kfifo_alloc failed\n");
+                pr_err("kfifo_alloc failed\n");
                 goto err_stop;
         }
 
@@ -859,13 +860,13 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
 
         result = acpi_bus_update_power(fujitsu_hotkey->acpi_handle, &state);
         if (result) {
-                printk(KERN_ERR "Error reading power state\n");
+                pr_err("Error reading power state\n");
                 goto err_unregister_input_dev;
         }
 
-        printk(KERN_INFO "ACPI: %s [%s] (%s)\n",
-               acpi_device_name(device), acpi_device_bid(device),
-               !device->power.state ? "on" : "off");
+        pr_info("ACPI: %s [%s] (%s)\n",
+                acpi_device_name(device), acpi_device_bid(device),
+                !device->power.state ? "on" : "off");
 
         fujitsu_hotkey->dev = device;
 
@@ -875,7 +876,7 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
                 if (ACPI_FAILURE
                     (acpi_evaluate_object
                      (device->handle, METHOD_NAME__INI, NULL, NULL)))
-                        printk(KERN_ERR "_INI Method failed\n");
+                        pr_err("_INI Method failed\n");
         }
 
         i = 0;
@@ -897,8 +898,7 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
                         call_fext_func(FUNC_RFKILL, 0x4, 0x0, 0x0);
 
         /* Suspect this is a keymap of the application panel, print it */
-        printk(KERN_INFO "fujitsu-laptop: BTNI: [0x%x]\n",
-                call_fext_func(FUNC_BUTTONS, 0x0, 0x0, 0x0));
+        pr_info("BTNI: [0x%x]\n", call_fext_func(FUNC_BUTTONS, 0x0, 0x0, 0x0));
 
 #if defined(CONFIG_LEDS_CLASS) || defined(CONFIG_LEDS_CLASS_MODULE)
         if (call_fext_func(FUNC_LEDS, 0x0, 0x0, 0x0) & LOGOLAMP_POWERON) {
@@ -907,8 +907,8 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
                 if (result == 0) {
                         fujitsu_hotkey->logolamp_registered = 1;
                 } else {
-                        printk(KERN_ERR "fujitsu-laptop: Could not register "
-                        "LED handler for logo lamp, error %i\n", result);
+                        pr_err("Could not register LED handler for logo lamp, error %i\n",
+                               result);
                 }
         }
 
@@ -919,8 +919,8 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
                 if (result == 0) {
                         fujitsu_hotkey->kblamps_registered = 1;
                 } else {
-                        printk(KERN_ERR "fujitsu-laptop: Could not register "
-                        "LED handler for keyboard lamps, error %i\n", result);
+                        pr_err("Could not register LED handler for keyboard lamps, error %i\n",
+                               result);
                 }
         }
 #endif
@@ -1169,8 +1169,7 @@ static int __init fujitsu_init(void)
                         fujitsu->bl_device->props.power = 0;
         }
 
-        printk(KERN_INFO "fujitsu-laptop: driver " FUJITSU_DRIVER_VERSION
-               " successfully loaded.\n");
+        pr_info("driver " FUJITSU_DRIVER_VERSION " successfully loaded\n");
 
         return 0;
 
@@ -1216,7 +1215,7 @@ static void __exit fujitsu_cleanup(void)
 
         kfree(fujitsu);
 
-        printk(KERN_INFO "fujitsu-laptop: driver unloaded.\n");
+        pr_info("driver unloaded\n");
 }
 
 module_init(fujitsu_init);
diff --git a/drivers/platform/x86/hdaps.c b/drivers/platform/x86/hdaps.c
index 067bf36d32f3..5a34973dc164 100644
--- a/drivers/platform/x86/hdaps.c
+++ b/drivers/platform/x86/hdaps.c
@@ -26,6 +26,8 @@
  * 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/delay.h>
 #include <linux/platform_device.h>
 #include <linux/input-polldev.h>
@@ -238,7 +240,7 @@ static int hdaps_device_init(void)
                      __check_latch(0x1611, 0x01))
                 goto out;
 
-        printk(KERN_DEBUG "hdaps: initial latch check good (0x%02x).\n",
+        printk(KERN_DEBUG "hdaps: initial latch check good (0x%02x)\n",
                __get_latch(0x1611));
 
         outb(0x17, 0x1610);
@@ -299,7 +301,7 @@ static int hdaps_probe(struct platform_device *dev)
         if (ret)
                 return ret;
 
-        printk(KERN_INFO "hdaps: device successfully initialized.\n");
+        pr_info("device successfully initialized\n");
         return 0;
 }
 
@@ -480,7 +482,7 @@ static struct attribute_group hdaps_attribute_group = {
 /* hdaps_dmi_match - found a match.  return one, short-circuiting the hunt. */
 static int __init hdaps_dmi_match(const struct dmi_system_id *id)
 {
-        printk(KERN_INFO "hdaps: %s detected.\n", id->ident);
+        pr_info("%s detected\n", id->ident);
         return 1;
 }
 
@@ -488,8 +490,7 @@ static int __init hdaps_dmi_match(const struct dmi_system_id *id)
 static int __init hdaps_dmi_match_invert(const struct dmi_system_id *id)
 {
         hdaps_invert = (unsigned long)id->driver_data;
-        printk(KERN_INFO "hdaps: inverting axis (%u) readings.\n",
-               hdaps_invert);
+        pr_info("inverting axis (%u) readings\n", hdaps_invert);
         return hdaps_dmi_match(id);
 }
 
@@ -543,7 +544,7 @@ static int __init hdaps_init(void)
         int ret;
 
         if (!dmi_check_system(hdaps_whitelist)) {
-                printk(KERN_WARNING "hdaps: supported laptop not found!\n");
+                pr_warn("supported laptop not found!\n");
                 ret = -ENODEV;
                 goto out;
         }
@@ -595,7 +596,7 @@ static int __init hdaps_init(void)
         if (ret)
                 goto out_idev;
 
-        printk(KERN_INFO "hdaps: driver successfully loaded.\n");
+        pr_info("driver successfully loaded\n");
         return 0;
 
 out_idev:
@@ -609,7 +610,7 @@ out_driver:
 out_region:
         release_region(HDAPS_LOW_PORT, HDAPS_NR_PORTS);
 out:
-        printk(KERN_WARNING "hdaps: driver init failed (ret=%d)!\n", ret);
+        pr_warn("driver init failed (ret=%d)!\n", ret);
         return ret;
 }
 
@@ -622,7 +623,7 @@ static void __exit hdaps_exit(void)
         platform_driver_unregister(&hdaps_driver);
         release_region(HDAPS_LOW_PORT, HDAPS_NR_PORTS);
 
-        printk(KERN_INFO "hdaps: driver unloaded.\n");
+        pr_info("driver unloaded\n");
 }
 
 module_init(hdaps_init);
diff --git a/drivers/platform/x86/hp-wmi.c b/drivers/platform/x86/hp-wmi.c
index 1bc4a7539ba9..f94017bcdd6e 100644
--- a/drivers/platform/x86/hp-wmi.c
+++ b/drivers/platform/x86/hp-wmi.c
@@ -24,6 +24,8 @@
  *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -54,9 +56,6 @@ MODULE_ALIAS("wmi:5FB7F034-2C63-45e9-BE91-3D44E2C707E4");
 #define HPWMI_HOTKEY_QUERY 0xc
 #define HPWMI_WIRELESS2_QUERY 0x1b
 
-#define PREFIX "HP WMI: "
-#define UNIMP "Unimplemented "
-
 enum hp_wmi_radio {
         HPWMI_WIFI = 0,
         HPWMI_BLUETOOTH = 1,
@@ -228,9 +227,8 @@ static int hp_wmi_perform_query(int query, int write, void *buffer,
 
         if (bios_return->return_code) {
                 if (bios_return->return_code != HPWMI_RET_UNKNOWN_CMDTYPE)
-                        printk(KERN_WARNING PREFIX "query 0x%x returned "
-                                                   "error 0x%x\n",
-                               query, bios_return->return_code);
+                        pr_warn("query 0x%x returned error 0x%x\n",
+                                query, bios_return->return_code);
                 kfree(obj);
                 return bios_return->return_code;
         }
@@ -384,8 +382,7 @@ static int hp_wmi_rfkill2_refresh(void)
 
                 if (num >= state.count ||
                     devstate->rfkill_id != rfkill2[i].id) {
-                        printk(KERN_WARNING PREFIX "power configuration of "
-                               "the wireless devices unexpectedly changed\n");
+                        pr_warn("power configuration of the wireless devices unexpectedly changed\n");
                         continue;
                 }
 
@@ -471,7 +468,7 @@ static void hp_wmi_notify(u32 value, void *context)
 
         status = wmi_get_event_data(value, &response);
         if (status != AE_OK) {
-                printk(KERN_INFO PREFIX "bad event status 0x%x\n", status);
+                pr_info("bad event status 0x%x\n", status);
                 return;
         }
 
@@ -480,8 +477,7 @@ static void hp_wmi_notify(u32 value, void *context)
         if (!obj)
                 return;
         if (obj->type != ACPI_TYPE_BUFFER) {
-                printk(KERN_INFO "hp-wmi: Unknown response received %d\n",
-                       obj->type);
+                pr_info("Unknown response received %d\n", obj->type);
                 kfree(obj);
                 return;
         }
@@ -498,8 +494,7 @@ static void hp_wmi_notify(u32 value, void *context)
                 event_id = *location;
                 event_data = *(location + 2);
         } else {
-                printk(KERN_INFO "hp-wmi: Unknown buffer length %d\n",
-                       obj->buffer.length);
+                pr_info("Unknown buffer length %d\n", obj->buffer.length);
                 kfree(obj);
                 return;
         }
@@ -527,8 +522,7 @@ static void hp_wmi_notify(u32 value, void *context)
 
                 if (!sparse_keymap_report_event(hp_wmi_input_dev,
                                                 key_code, 1, true))
-                        printk(KERN_INFO PREFIX "Unknown key code - 0x%x\n",
-                               key_code);
+                        pr_info("Unknown key code - 0x%x\n", key_code);
                 break;
         case HPWMI_WIRELESS:
                 if (rfkill2_count) {
@@ -550,14 +544,12 @@ static void hp_wmi_notify(u32 value, void *context)
                                           hp_wmi_get_hw_state(HPWMI_WWAN));
                 break;
         case HPWMI_CPU_BATTERY_THROTTLE:
-                printk(KERN_INFO PREFIX UNIMP "CPU throttle because of 3 Cell"
-                       " battery event detected\n");
+                pr_info("Unimplemented CPU throttle because of 3 Cell battery event detected\n");
                 break;
         case HPWMI_LOCK_SWITCH:
                 break;
         default:
-                printk(KERN_INFO PREFIX "Unknown event_id - %d - 0x%x\n",
-                       event_id, event_data);
+                pr_info("Unknown event_id - %d - 0x%x\n", event_id, event_data);
                 break;
         }
 }
@@ -705,7 +697,7 @@ static int __devinit hp_wmi_rfkill2_setup(struct platform_device *device)
                 return err;
 
         if (state.count > HPWMI_MAX_RFKILL2_DEVICES) {
-                printk(KERN_WARNING PREFIX "unable to parse 0x1b query output\n");
+                pr_warn("unable to parse 0x1b query output\n");
                 return -EINVAL;
         }
 
@@ -727,14 +719,14 @@ static int __devinit hp_wmi_rfkill2_setup(struct platform_device *device)
                         name = "hp-wwan";
                         break;
                 default:
-                        printk(KERN_WARNING PREFIX "unknown device type 0x%x\n",
-                                 state.device[i].radio_type);
+                        pr_warn("unknown device type 0x%x\n",
+                                state.device[i].radio_type);
                         continue;
                 }
 
                 if (!state.device[i].vendor_id) {
-                        printk(KERN_WARNING PREFIX "zero device %d while %d "
-                               "reported\n", i, state.count);
+                        pr_warn("zero device %d while %d reported\n",
+                                i, state.count);
                         continue;
                 }
 
@@ -755,8 +747,7 @@ static int __devinit hp_wmi_rfkill2_setup(struct platform_device *device)
                                     IS_HWBLOCKED(state.device[i].power));
 
                 if (!(state.device[i].power & HPWMI_POWER_BIOS))
-                        printk(KERN_INFO PREFIX "device %s blocked by BIOS\n",
-                               name);
+                        pr_info("device %s blocked by BIOS\n", name);
 
                 err = rfkill_register(rfkill);
                 if (err) {
diff --git a/drivers/platform/x86/ibm_rtl.c b/drivers/platform/x86/ibm_rtl.c
index b1396e5b2953..811d436cd677 100644
--- a/drivers/platform/x86/ibm_rtl.c
+++ b/drivers/platform/x86/ibm_rtl.c
@@ -22,6 +22,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/delay.h>
 #include <linux/module.h>
@@ -69,9 +71,10 @@ struct ibm_rtl_table {
 #define RTL_SIGNATURE 0x0000005f4c54525fULL
 #define RTL_MASK      0x000000ffffffffffULL
 
-#define RTL_DEBUG(A, ...) do { \
-        if (debug) \
-                pr_info("ibm-rtl: " A, ##__VA_ARGS__ ); \
+#define RTL_DEBUG(fmt, ...)                             \
+do {                                                    \
+        if (debug)                                      \
+                pr_info(fmt, ##__VA_ARGS__);            \
 } while (0)
 
 static DEFINE_MUTEX(rtl_lock);
@@ -114,7 +117,7 @@ static int ibm_rtl_write(u8 value)
         int ret = 0, count = 0;
         static u32 cmd_port_val;
 
-        RTL_DEBUG("%s(%d)\n", __FUNCTION__, value);
+        RTL_DEBUG("%s(%d)\n", __func__, value);
 
         value = value == 1 ? RTL_CMD_ENTER_PRTM : RTL_CMD_EXIT_PRTM;
 
@@ -144,8 +147,8 @@ static int ibm_rtl_write(u8 value)
                 while (ioread8(&rtl_table->command)) {
                         msleep(10);
                         if (count++ > 500) {
-                                pr_err("ibm-rtl: Hardware not responding to "
-                                        "mode switch request\n");
+                                pr_err("Hardware not responding to "
+                                       "mode switch request\n");
                                 ret = -EIO;
                                 break;
                         }
@@ -250,7 +253,7 @@ static int __init ibm_rtl_init(void) {
         int ret = -ENODEV, i;
 
         if (force)
-                pr_warning("ibm-rtl: module loaded by force\n");
+                pr_warn("module loaded by force\n");
         /* first ensure that we are running on IBM HW */
         else if (efi_enabled || !dmi_check_system(ibm_rtl_dmi_table))
                 return -ENODEV;
@@ -288,19 +291,19 @@ static int __init ibm_rtl_init(void) {
                 if ((readq(&tmp->signature) & RTL_MASK) == RTL_SIGNATURE) {
                         phys_addr_t addr;
                         unsigned int plen;
-                        RTL_DEBUG("found RTL_SIGNATURE at %#llx\n", (u64)tmp);
+                        RTL_DEBUG("found RTL_SIGNATURE at %p\n", tmp);
                         rtl_table = tmp;
                         /* The address, value, width and offset are platform
                          * dependent and found in the ibm_rtl_table */
                         rtl_cmd_width = ioread8(&rtl_table->cmd_granularity);
                         rtl_cmd_type = ioread8(&rtl_table->cmd_address_type);
                         RTL_DEBUG("rtl_cmd_width = %u, rtl_cmd_type = %u\n",
-                              rtl_cmd_width, rtl_cmd_type);
+                                  rtl_cmd_width, rtl_cmd_type);
                         addr = ioread32(&rtl_table->cmd_port_address);
                         RTL_DEBUG("addr = %#llx\n", (unsigned long long)addr);
                         plen = rtl_cmd_width/sizeof(char);
                         rtl_cmd_addr = rtl_port_map(addr, plen);
-                        RTL_DEBUG("rtl_cmd_addr = %#llx\n", (u64)rtl_cmd_addr);
+                        RTL_DEBUG("rtl_cmd_addr = %p\n", rtl_cmd_addr);
                         if (!rtl_cmd_addr) {
                                 ret = -ENOMEM;
                                 break;
diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c
index 21b101899bae..bfdda33feb26 100644
--- a/drivers/platform/x86/ideapad-laptop.c
+++ b/drivers/platform/x86/ideapad-laptop.c
@@ -20,6 +20,8 @@
  *  02110-1301, USA.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
diff --git a/drivers/platform/x86/intel_menlow.c b/drivers/platform/x86/intel_menlow.c
index eacd5da7dd24..809adea4965f 100644
--- a/drivers/platform/x86/intel_menlow.c
+++ b/drivers/platform/x86/intel_menlow.c
@@ -27,6 +27,8 @@
  *  to get/set bandwidth.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -135,8 +137,7 @@ static int memory_set_cur_bandwidth(struct thermal_cooling_device *cdev,
             acpi_evaluate_integer(handle, MEMORY_SET_BANDWIDTH, &arg_list,
                                   &temp);
 
-        printk(KERN_INFO
-               "Bandwidth value was %ld: status is %d\n", state, status);
+        pr_info("Bandwidth value was %ld: status is %d\n", state, status);
         if (ACPI_FAILURE(status))
                 return -EFAULT;
 
diff --git a/drivers/platform/x86/intel_mid_powerbtn.c b/drivers/platform/x86/intel_mid_powerbtn.c
index 213e79ba68d5..f1ae5078b7ec 100644
--- a/drivers/platform/x86/intel_mid_powerbtn.c
+++ b/drivers/platform/x86/intel_mid_powerbtn.c
@@ -23,58 +23,48 @@
 #include <linux/slab.h>
 #include <linux/platform_device.h>
 #include <linux/input.h>
+
 #include <asm/intel_scu_ipc.h>
 
 #define DRIVER_NAME "msic_power_btn"
 
-#define MSIC_IRQ_STAT   0x02
-  #define MSIC_IRQ_PB   (1 << 0)
-#define MSIC_PB_CONFIG  0x3e
 #define MSIC_PB_STATUS  0x3f
-  #define MSIC_PB_LEVEL (1 << 3) /* 1 - release, 0 - press */
-
-struct mfld_pb_priv {
-        struct input_dev *input;
-        unsigned int irq;
-};
+#define MSIC_PB_LEVEL   (1 << 3) /* 1 - release, 0 - press */
 
 static irqreturn_t mfld_pb_isr(int irq, void *dev_id)
 {
-        struct mfld_pb_priv *priv = dev_id;
+        struct input_dev *input = dev_id;
         int ret;
         u8 pbstat;
 
         ret = intel_scu_ipc_ioread8(MSIC_PB_STATUS, &pbstat);
-        if (ret < 0)
-                return IRQ_HANDLED;
-
-        input_event(priv->input, EV_KEY, KEY_POWER, !(pbstat & MSIC_PB_LEVEL));
-        input_sync(priv->input);
+        if (ret < 0) {
+                dev_err(input->dev.parent, "Read error %d while reading"
+                               " MSIC_PB_STATUS\n", ret);
+        } else {
+                input_event(input, EV_KEY, KEY_POWER,
+                               !(pbstat & MSIC_PB_LEVEL));
+                input_sync(input);
+        }
 
         return IRQ_HANDLED;
 }
 
 static int __devinit mfld_pb_probe(struct platform_device *pdev)
 {
-        struct mfld_pb_priv *priv;
         struct input_dev *input;
-        int irq;
+        int irq = platform_get_irq(pdev, 0);
         int error;
 
-        irq = platform_get_irq(pdev, 0);
         if (irq < 0)
                 return -EINVAL;
 
-        priv = kzalloc(sizeof(struct mfld_pb_priv), GFP_KERNEL);
         input = input_allocate_device();
-        if (!priv || !input) {
-                error = -ENOMEM;
-                goto err_free_mem;
+        if (!input) {
+                dev_err(&pdev->dev, "Input device allocation error\n");
+                return -ENOMEM;
         }
 
-        priv->input = input;
-        priv->irq = irq;
-
         input->name = pdev->name;
         input->phys = "power-button/input0";
         input->id.bustype = BUS_HOST;
@@ -82,42 +72,40 @@ static int __devinit mfld_pb_probe(struct platform_device *pdev)
 
         input_set_capability(input, EV_KEY, KEY_POWER);
 
-        error = request_threaded_irq(priv->irq, NULL, mfld_pb_isr,
-                                     0, DRIVER_NAME, priv);
+        error = request_threaded_irq(irq, NULL, mfld_pb_isr, 0,
+                        DRIVER_NAME, input);
         if (error) {
-                dev_err(&pdev->dev,
-                        "unable to request irq %d for mfld power button\n",
-                        irq);
-                goto err_free_mem;
+                dev_err(&pdev->dev, "Unable to request irq %d for mfld power"
+                                "button\n", irq);
+                goto err_free_input;
         }
 
         error = input_register_device(input);
         if (error) {
-                dev_err(&pdev->dev,
-                        "unable to register input dev, error %d\n", error);
+                dev_err(&pdev->dev, "Unable to register input dev, error "
+                                "%d\n", error);
                 goto err_free_irq;
         }
 
-        platform_set_drvdata(pdev, priv);
+        platform_set_drvdata(pdev, input);
         return 0;
 
 err_free_irq:
-        free_irq(priv->irq, priv);
-err_free_mem:
+        free_irq(irq, input);
+err_free_input:
         input_free_device(input);
-        kfree(priv);
         return error;
 }
 
 static int __devexit mfld_pb_remove(struct platform_device *pdev)
 {
-        struct mfld_pb_priv *priv = platform_get_drvdata(pdev);
-
-        free_irq(priv->irq, priv);
-        input_unregister_device(priv->input);
-        kfree(priv);
+        struct input_dev *input = platform_get_drvdata(pdev);
+        int irq = platform_get_irq(pdev, 0);
 
+        free_irq(irq, input);
+        input_unregister_device(input);
         platform_set_drvdata(pdev, NULL);
+
         return 0;
 }
 
diff --git a/drivers/platform/x86/intel_mid_thermal.c b/drivers/platform/x86/intel_mid_thermal.c
index c2f4bd8013b5..3a578323122b 100644
--- a/drivers/platform/x86/intel_mid_thermal.c
+++ b/drivers/platform/x86/intel_mid_thermal.c
@@ -37,49 +37,50 @@
 #include <asm/intel_scu_ipc.h>
 
 /* Number of thermal sensors */
-#define MSIC_THERMAL_SENSORS   4
+#define MSIC_THERMAL_SENSORS    4
 
 /* ADC1 - thermal registers */
-#define MSIC_THERM_ADC1CNTL1   0x1C0
-#define MSIC_ADC_ENBL          0x10
-#define MSIC_ADC_START         0x08
+#define MSIC_THERM_ADC1CNTL1    0x1C0
+#define MSIC_ADC_ENBL           0x10
+#define MSIC_ADC_START          0x08
 
-#define MSIC_THERM_ADC1CNTL3   0x1C2
-#define MSIC_ADCTHERM_ENBL     0x04
-#define MSIC_ADCRRDATA_ENBL    0x05
-#define MSIC_CHANL_MASK_VAL    0x0F
+#define MSIC_THERM_ADC1CNTL3    0x1C2
+#define MSIC_ADCTHERM_ENBL      0x04
+#define MSIC_ADCRRDATA_ENBL     0x05
+#define MSIC_CHANL_MASK_VAL     0x0F
 
-#define MSIC_STOPBIT_MASK      16
-#define MSIC_ADCTHERM_MASK     4
-#define ADC_CHANLS_MAX         15 /* Number of ADC channels */
-#define ADC_LOOP_MAX           (ADC_CHANLS_MAX - MSIC_THERMAL_SENSORS)
+#define MSIC_STOPBIT_MASK       16
+#define MSIC_ADCTHERM_MASK      4
+/* Number of ADC channels */
+#define ADC_CHANLS_MAX          15
+#define ADC_LOOP_MAX            (ADC_CHANLS_MAX - MSIC_THERMAL_SENSORS)
 
 /* ADC channel code values */
-#define SKIN_SENSOR0_CODE      0x08
-#define SKIN_SENSOR1_CODE      0x09
-#define SYS_SENSOR_CODE                0x0A
-#define MSIC_DIE_SENSOR_CODE   0x03
+#define SKIN_SENSOR0_CODE       0x08
+#define SKIN_SENSOR1_CODE       0x09
+#define SYS_SENSOR_CODE         0x0A
+#define MSIC_DIE_SENSOR_CODE    0x03
 
-#define SKIN_THERM_SENSOR0     0
-#define SKIN_THERM_SENSOR1     1
-#define SYS_THERM_SENSOR2      2
-#define MSIC_DIE_THERM_SENSOR3 3
+#define SKIN_THERM_SENSOR0      0
+#define SKIN_THERM_SENSOR1      1
+#define SYS_THERM_SENSOR2       2
+#define MSIC_DIE_THERM_SENSOR3  3
 
 /* ADC code range */
-#define ADC_MAX                        977
-#define ADC_MIN                        162
-#define ADC_VAL0C              887
-#define ADC_VAL20C             720
-#define ADC_VAL40C             508
-#define ADC_VAL60C             315
+#define ADC_MAX                 977
+#define ADC_MIN                 162
+#define ADC_VAL0C               887
+#define ADC_VAL20C              720
+#define ADC_VAL40C              508
+#define ADC_VAL60C              315
 
 /* ADC base addresses */
-#define ADC_CHNL_START_ADDR    0x1C5   /* increments by 1 */
-#define ADC_DATA_START_ADDR     0x1D4   /* increments by 2 */
+#define ADC_CHNL_START_ADDR     0x1C5   /* increments by 1 */
+#define ADC_DATA_START_ADDR     0x1D4   /* increments by 2 */
 
 /* MSIC die attributes */
-#define MSIC_DIE_ADC_MIN       488
-#define MSIC_DIE_ADC_MAX       1004
+#define MSIC_DIE_ADC_MIN        488
+#define MSIC_DIE_ADC_MAX        1004
 
 /* This holds the address of the first free ADC channel,
  * among the 15 channels
@@ -87,15 +88,15 @@
 static int channel_index;
 
 struct platform_info {
-       struct platform_device *pdev;
-       struct thermal_zone_device *tzd[MSIC_THERMAL_SENSORS];
+        struct platform_device *pdev;
+        struct thermal_zone_device *tzd[MSIC_THERMAL_SENSORS];
 };
 
 struct thermal_device_info {
-       unsigned int chnl_addr;
-       int direct;
-       /* This holds the current temperature in millidegree celsius */
-       long curr_temp;
+        unsigned int chnl_addr;
+        int direct;
+        /* This holds the current temperature in millidegree celsius */
+        long curr_temp;
 };
 
 /**
@@ -106,7 +107,7 @@ struct thermal_device_info {
  */
 static int to_msic_die_temp(uint16_t adc_val)
 {
-       return (368 * (adc_val) / 1000) - 220;
+        return (368 * (adc_val) / 1000) - 220;
 }
 
 /**
@@ -118,7 +119,7 @@ static int to_msic_die_temp(uint16_t adc_val)
  */
 static int is_valid_adc(uint16_t adc_val, uint16_t min, uint16_t max)
 {
-       return (adc_val >= min) && (adc_val <= max);
+        return (adc_val >= min) && (adc_val <= max);
 }
 
 /**
@@ -136,35 +137,35 @@ static int is_valid_adc(uint16_t adc_val, uint16_t min, uint16_t max)
  */
 static int adc_to_temp(int direct, uint16_t adc_val, unsigned long *tp)
 {
-       int temp;
-
-       /* Direct conversion for die temperature */
-       if (direct) {
-               if (is_valid_adc(adc_val, MSIC_DIE_ADC_MIN, MSIC_DIE_ADC_MAX)) {
-                       *tp = to_msic_die_temp(adc_val) * 1000;
-                       return 0;
-               }
-               return -ERANGE;
-       }
-
-       if (!is_valid_adc(adc_val, ADC_MIN, ADC_MAX))
-               return -ERANGE;
-
-       /* Linear approximation for skin temperature */
-       if (adc_val > ADC_VAL0C)
-               temp = 177 - (adc_val/5);
-       else if ((adc_val <= ADC_VAL0C) && (adc_val > ADC_VAL20C))
-               temp = 111 - (adc_val/8);
-       else if ((adc_val <= ADC_VAL20C) && (adc_val > ADC_VAL40C))
-               temp = 92 - (adc_val/10);
-       else if ((adc_val <= ADC_VAL40C) && (adc_val > ADC_VAL60C))
-               temp = 91 - (adc_val/10);
-       else
-               temp = 112 - (adc_val/6);
-
-       /* Convert temperature in celsius to milli degree celsius */
-       *tp = temp * 1000;
-       return 0;
+        int temp;
+
+        /* Direct conversion for die temperature */
+        if (direct) {
+                if (is_valid_adc(adc_val, MSIC_DIE_ADC_MIN, MSIC_DIE_ADC_MAX)) {
+                        *tp = to_msic_die_temp(adc_val) * 1000;
+                        return 0;
+                }
+                return -ERANGE;
+        }
+
+        if (!is_valid_adc(adc_val, ADC_MIN, ADC_MAX))
+                return -ERANGE;
+
+        /* Linear approximation for skin temperature */
+        if (adc_val > ADC_VAL0C)
+                temp = 177 - (adc_val/5);
+        else if ((adc_val <= ADC_VAL0C) && (adc_val > ADC_VAL20C))
+                temp = 111 - (adc_val/8);
+        else if ((adc_val <= ADC_VAL20C) && (adc_val > ADC_VAL40C))
+                temp = 92 - (adc_val/10);
+        else if ((adc_val <= ADC_VAL40C) && (adc_val > ADC_VAL60C))
+                temp = 91 - (adc_val/10);
+        else
+                temp = 112 - (adc_val/6);
+
+        /* Convert temperature in celsius to milli degree celsius */
+        *tp = temp * 1000;
+        return 0;
 }
 
 /**
@@ -178,47 +179,47 @@ static int adc_to_temp(int direct, uint16_t adc_val, unsigned long *tp)
  */
 static int mid_read_temp(struct thermal_zone_device *tzd, unsigned long *temp)
 {
-       struct thermal_device_info *td_info = tzd->devdata;
-       uint16_t adc_val, addr;
-       uint8_t data = 0;
-       int ret;
-       unsigned long curr_temp;
-
-
-       addr = td_info->chnl_addr;
-
-       /* Enable the msic for conversion before reading */
-       ret = intel_scu_ipc_iowrite8(MSIC_THERM_ADC1CNTL3, MSIC_ADCRRDATA_ENBL);
-       if (ret)
-               return ret;
-
-       /* Re-toggle the RRDATARD bit (temporary workaround) */
-       ret = intel_scu_ipc_iowrite8(MSIC_THERM_ADC1CNTL3, MSIC_ADCTHERM_ENBL);
-       if (ret)
-               return ret;
-
-       /* Read the higher bits of data */
-       ret = intel_scu_ipc_ioread8(addr, &data);
-       if (ret)
-               return ret;
-
-       /* Shift bits to accommodate the lower two data bits */
-       adc_val = (data << 2);
-       addr++;
-
-       ret = intel_scu_ipc_ioread8(addr, &data);/* Read lower bits */
-       if (ret)
-               return ret;
-
-       /* Adding lower two bits to the higher bits */
-       data &= 03;
-       adc_val += data;
-
-       /* Convert ADC value to temperature */
-       ret = adc_to_temp(td_info->direct, adc_val, &curr_temp);
-       if (ret == 0)
-               *temp = td_info->curr_temp = curr_temp;
-       return ret;
+        struct thermal_device_info *td_info = tzd->devdata;
+        uint16_t adc_val, addr;
+        uint8_t data = 0;
+        int ret;
+        unsigned long curr_temp;
+
+
+        addr = td_info->chnl_addr;
+
+        /* Enable the msic for conversion before reading */
+        ret = intel_scu_ipc_iowrite8(MSIC_THERM_ADC1CNTL3, MSIC_ADCRRDATA_ENBL);
+        if (ret)
+                return ret;
+
+        /* Re-toggle the RRDATARD bit (temporary workaround) */
+        ret = intel_scu_ipc_iowrite8(MSIC_THERM_ADC1CNTL3, MSIC_ADCTHERM_ENBL);
+        if (ret)
+                return ret;
+
+        /* Read the higher bits of data */
+        ret = intel_scu_ipc_ioread8(addr, &data);
+        if (ret)
+                return ret;
+
+        /* Shift bits to accommodate the lower two data bits */
+        adc_val = (data << 2);
+        addr++;
+
+        ret = intel_scu_ipc_ioread8(addr, &data);/* Read lower bits */
+        if (ret)
+                return ret;
+
+        /* Adding lower two bits to the higher bits */
+        data &= 03;
+        adc_val += data;
+
+        /* Convert ADC value to temperature */
+        ret = adc_to_temp(td_info->direct, adc_val, &curr_temp);
+        if (ret == 0)
+                *temp = td_info->curr_temp = curr_temp;
+        return ret;
 }
 
 /**
@@ -231,22 +232,21 @@ static int mid_read_temp(struct thermal_zone_device *tzd, unsigned long *temp)
  */
 static int configure_adc(int val)
 {
-       int ret;
-       uint8_t data;
-
-       ret = intel_scu_ipc_ioread8(MSIC_THERM_ADC1CNTL1, &data);
-       if (ret)
-               return ret;
-
-       if (val) {
-               /* Enable and start the ADC */
-               data |= (MSIC_ADC_ENBL | MSIC_ADC_START);
-       } else {
-               /* Just stop the ADC */
-               data &= (~MSIC_ADC_START);
-       }
-
-       return intel_scu_ipc_iowrite8(MSIC_THERM_ADC1CNTL1, data);
+        int ret;
+        uint8_t data;
+
+        ret = intel_scu_ipc_ioread8(MSIC_THERM_ADC1CNTL1, &data);
+        if (ret)
+                return ret;
+
+        if (val) {
+                /* Enable and start the ADC */
+                data |= (MSIC_ADC_ENBL | MSIC_ADC_START);
+        } else {
+                /* Just stop the ADC */
+                data &= (~MSIC_ADC_START);
+        }
+        return intel_scu_ipc_iowrite8(MSIC_THERM_ADC1CNTL1, data);
 }
 
 /**
@@ -259,30 +259,30 @@ static int configure_adc(int val)
  */
 static int set_up_therm_channel(u16 base_addr)
 {
-       int ret;
-
-       /* Enable all the sensor channels */
-       ret = intel_scu_ipc_iowrite8(base_addr, SKIN_SENSOR0_CODE);
-       if (ret)
-               return ret;
-
-       ret = intel_scu_ipc_iowrite8(base_addr + 1, SKIN_SENSOR1_CODE);
-       if (ret)
-               return ret;
-
-       ret = intel_scu_ipc_iowrite8(base_addr + 2, SYS_SENSOR_CODE);
-       if (ret)
-               return ret;
-
-       /* Since this is the last channel, set the stop bit
-          to 1 by ORing the DIE_SENSOR_CODE with 0x10 */
-       ret = intel_scu_ipc_iowrite8(base_addr + 3,
-                                       (MSIC_DIE_SENSOR_CODE | 0x10));
-       if (ret)
-               return ret;
-
-       /* Enable ADC and start it */
-       return configure_adc(1);
+        int ret;
+
+        /* Enable all the sensor channels */
+        ret = intel_scu_ipc_iowrite8(base_addr, SKIN_SENSOR0_CODE);
+        if (ret)
+                return ret;
+
+        ret = intel_scu_ipc_iowrite8(base_addr + 1, SKIN_SENSOR1_CODE);
+        if (ret)
+                return ret;
+
+        ret = intel_scu_ipc_iowrite8(base_addr + 2, SYS_SENSOR_CODE);
+        if (ret)
+                return ret;
+
+        /* Since this is the last channel, set the stop bit
+         * to 1 by ORing the DIE_SENSOR_CODE with 0x10 */
+        ret = intel_scu_ipc_iowrite8(base_addr + 3,
+                        (MSIC_DIE_SENSOR_CODE | 0x10));
+        if (ret)
+                return ret;
+
+        /* Enable ADC and start it */
+        return configure_adc(1);
 }
 
 /**
@@ -293,13 +293,13 @@ static int set_up_therm_channel(u16 base_addr)
  */
 static int reset_stopbit(uint16_t addr)
 {
-       int ret;
-       uint8_t data;
-       ret = intel_scu_ipc_ioread8(addr, &data);
-       if (ret)
-               return ret;
-       /* Set the stop bit to zero */
-       return intel_scu_ipc_iowrite8(addr, (data & 0xEF));
+        int ret;
+        uint8_t data;
+        ret = intel_scu_ipc_ioread8(addr, &data);
+        if (ret)
+                return ret;
+        /* Set the stop bit to zero */
+        return intel_scu_ipc_iowrite8(addr, (data & 0xEF));
 }
 
 /**
@@ -317,30 +317,30 @@ static int reset_stopbit(uint16_t addr)
  */
 static int find_free_channel(void)
 {
-       int ret;
-       int i;
-       uint8_t data;
-
-       /* check whether ADC is enabled */
-       ret = intel_scu_ipc_ioread8(MSIC_THERM_ADC1CNTL1, &data);
-       if (ret)
-               return ret;
-
-       if ((data & MSIC_ADC_ENBL) == 0)
-               return 0;
-
-       /* ADC is already enabled; Looking for an empty channel */
-       for (i = 0; i < ADC_CHANLS_MAX; i++) {
-               ret = intel_scu_ipc_ioread8(ADC_CHNL_START_ADDR + i, &data);
-               if (ret)
-                       return ret;
-
-               if (data & MSIC_STOPBIT_MASK) {
-                       ret = i;
-                       break;
-               }
-       }
-       return (ret > ADC_LOOP_MAX) ? (-EINVAL) : ret;
+        int ret;
+        int i;
+        uint8_t data;
+
+        /* check whether ADC is enabled */
+        ret = intel_scu_ipc_ioread8(MSIC_THERM_ADC1CNTL1, &data);
+        if (ret)
+                return ret;
+
+        if ((data & MSIC_ADC_ENBL) == 0)
+                return 0;
+
+        /* ADC is already enabled; Looking for an empty channel */
+        for (i = 0; i < ADC_CHANLS_MAX; i++) {
+                ret = intel_scu_ipc_ioread8(ADC_CHNL_START_ADDR + i, &data);
+                if (ret)
+                        return ret;
+
+                if (data & MSIC_STOPBIT_MASK) {
+                        ret = i;
+                        break;
+                }
+        }
+        return (ret > ADC_LOOP_MAX) ? (-EINVAL) : ret;
 }
 
 /**
@@ -351,48 +351,48 @@ static int find_free_channel(void)
  */
 static int mid_initialize_adc(struct device *dev)
 {
-       u8  data;
-       u16 base_addr;
-       int ret;
-
-       /*
-        * Ensure that adctherm is disabled before we
-        * initialize the ADC
-        */
-       ret = intel_scu_ipc_ioread8(MSIC_THERM_ADC1CNTL3, &data);
-       if (ret)
-               return ret;
-
-       if (data & MSIC_ADCTHERM_MASK)
-               dev_warn(dev, "ADCTHERM already set");
-
-       /* Index of the first channel in which the stop bit is set */
-       channel_index = find_free_channel();
-       if (channel_index < 0) {
-               dev_err(dev, "No free ADC channels");
-               return channel_index;
-       }
-
-       base_addr = ADC_CHNL_START_ADDR + channel_index;
-
-       if (!(channel_index == 0 || channel_index == ADC_LOOP_MAX)) {
-               /* Reset stop bit for channels other than 0 and 12 */
-               ret = reset_stopbit(base_addr);
-               if (ret)
-                       return ret;
-
-               /* Index of the first free channel */
-               base_addr++;
-               channel_index++;
-       }
-
-       ret = set_up_therm_channel(base_addr);
-       if (ret) {
-               dev_err(dev, "unable to enable ADC");
-               return ret;
-       }
-       dev_dbg(dev, "ADC initialization successful");
-       return ret;
+        u8  data;
+        u16 base_addr;
+        int ret;
+
+        /*
+         * Ensure that adctherm is disabled before we
+         * initialize the ADC
+         */
+        ret = intel_scu_ipc_ioread8(MSIC_THERM_ADC1CNTL3, &data);
+        if (ret)
+                return ret;
+
+        if (data & MSIC_ADCTHERM_MASK)
+                dev_warn(dev, "ADCTHERM already set");
+
+        /* Index of the first channel in which the stop bit is set */
+        channel_index = find_free_channel();
+        if (channel_index < 0) {
+                dev_err(dev, "No free ADC channels");
+                return channel_index;
+        }
+
+        base_addr = ADC_CHNL_START_ADDR + channel_index;
+
+        if (!(channel_index == 0 || channel_index == ADC_LOOP_MAX)) {
+                /* Reset stop bit for channels other than 0 and 12 */
+                ret = reset_stopbit(base_addr);
+                if (ret)
+                        return ret;
+
+                /* Index of the first free channel */
+                base_addr++;
+                channel_index++;
+        }
+
+        ret = set_up_therm_channel(base_addr);
+        if (ret) {
+                dev_err(dev, "unable to enable ADC");
+                return ret;
+        }
+        dev_dbg(dev, "ADC initialization successful");
+        return ret;
 }
 
 /**
@@ -403,18 +403,18 @@ static int mid_initialize_adc(struct device *dev)
  */
 static struct thermal_device_info *initialize_sensor(int index)
 {
-       struct thermal_device_info *td_info =
-               kzalloc(sizeof(struct thermal_device_info), GFP_KERNEL);
-
-       if (!td_info)
-               return NULL;
-
-       /* Set the base addr of the channel for this sensor */
-       td_info->chnl_addr = ADC_DATA_START_ADDR + 2 * (channel_index + index);
-       /* Sensor 3 is direct conversion */
-       if (index == 3)
-               td_info->direct = 1;
-       return td_info;
+        struct thermal_device_info *td_info =
+                kzalloc(sizeof(struct thermal_device_info), GFP_KERNEL);
+
+        if (!td_info)
+                return NULL;
+
+        /* Set the base addr of the channel for this sensor */
+        td_info->chnl_addr = ADC_DATA_START_ADDR + 2 * (channel_index + index);
+        /* Sensor 3 is direct conversion */
+        if (index == 3)
+                td_info->direct = 1;
+        return td_info;
 }
 
 /**
@@ -425,7 +425,7 @@ static struct thermal_device_info *initialize_sensor(int index)
  */
 static int mid_thermal_resume(struct platform_device *pdev)
 {
-       return mid_initialize_adc(&pdev->dev);
+        return mid_initialize_adc(&pdev->dev);
 }
 
 /**
@@ -437,12 +437,12 @@ static int mid_thermal_resume(struct platform_device *pdev)
  */
 static int mid_thermal_suspend(struct platform_device *pdev, pm_message_t mesg)
 {
-       /*
-        * This just stops the ADC and does not disable it.
-        * temporary workaround until we have a generic ADC driver.
-        * If 0 is passed, it disables the ADC.
-        */
-       return configure_adc(0);
+        /*
+         * This just stops the ADC and does not disable it.
+         * temporary workaround until we have a generic ADC driver.
+         * If 0 is passed, it disables the ADC.
+         */
+        return configure_adc(0);
 }
 
 /**
@@ -453,16 +453,15 @@ static int mid_thermal_suspend(struct platform_device *pdev, pm_message_t mesg)
  */
 static int read_curr_temp(struct thermal_zone_device *tzd, unsigned long *temp)
 {
-       WARN_ON(tzd == NULL);
-       return mid_read_temp(tzd, temp);
+        WARN_ON(tzd == NULL);
+        return mid_read_temp(tzd, temp);
 }
 
 /* Can't be const */
 static struct thermal_zone_device_ops tzd_ops = {
-       .get_temp = read_curr_temp,
+        .get_temp = read_curr_temp,
 };
 
-
 /**
  * mid_thermal_probe - mfld thermal initialize
  * @pdev: platform device structure
@@ -472,46 +471,45 @@ static struct thermal_zone_device_ops tzd_ops = {
  */
 static int mid_thermal_probe(struct platform_device *pdev)
 {
-       static char *name[MSIC_THERMAL_SENSORS] = {
-               "skin0", "skin1", "sys", "msicdie"
-       };
-
-       int ret;
-       int i;
-       struct platform_info *pinfo;
-
-       pinfo = kzalloc(sizeof(struct platform_info), GFP_KERNEL);
-       if (!pinfo)
-               return -ENOMEM;
-
-       /* Initializing the hardware */
-       ret = mid_initialize_adc(&pdev->dev);
-       if (ret) {
-               dev_err(&pdev->dev, "ADC init failed");
-               kfree(pinfo);
-               return ret;
-       }
-
-       /* Register each sensor with the generic thermal framework*/
-       for (i = 0; i < MSIC_THERMAL_SENSORS; i++) {
-               pinfo->tzd[i] = thermal_zone_device_register(name[i],
-                                       0, initialize_sensor(i),
-                                       &tzd_ops, 0, 0, 0, 0);
-               if (IS_ERR(pinfo->tzd[i]))
-                       goto reg_fail;
-       }
-
-       pinfo->pdev = pdev;
-       platform_set_drvdata(pdev, pinfo);
-       return 0;
+        static char *name[MSIC_THERMAL_SENSORS] = {
+                "skin0", "skin1", "sys", "msicdie"
+        };
+
+        int ret;
+        int i;
+        struct platform_info *pinfo;
+
+        pinfo = kzalloc(sizeof(struct platform_info), GFP_KERNEL);
+        if (!pinfo)
+                return -ENOMEM;
+
+        /* Initializing the hardware */
+        ret = mid_initialize_adc(&pdev->dev);
+        if (ret) {
+                dev_err(&pdev->dev, "ADC init failed");
+                kfree(pinfo);
+                return ret;
+        }
+
+        /* Register each sensor with the generic thermal framework*/
+        for (i = 0; i < MSIC_THERMAL_SENSORS; i++) {
+                pinfo->tzd[i] = thermal_zone_device_register(name[i],
+                                0, initialize_sensor(i), &tzd_ops, 0, 0, 0, 0);
+                if (IS_ERR(pinfo->tzd[i]))
+                        goto reg_fail;
+        }
+
+        pinfo->pdev = pdev;
+        platform_set_drvdata(pdev, pinfo);
+        return 0;
 
 reg_fail:
-       ret = PTR_ERR(pinfo->tzd[i]);
-       while (--i >= 0)
-               thermal_zone_device_unregister(pinfo->tzd[i]);
-       configure_adc(0);
-       kfree(pinfo);
-       return ret;
+        ret = PTR_ERR(pinfo->tzd[i]);
+        while (--i >= 0)
+                thermal_zone_device_unregister(pinfo->tzd[i]);
+        configure_adc(0);
+        kfree(pinfo);
+        return ret;
 }
 
 /**
@@ -523,49 +521,46 @@ reg_fail:
  */
 static int mid_thermal_remove(struct platform_device *pdev)
 {
-       int i;
-       struct platform_info *pinfo = platform_get_drvdata(pdev);
+        int i;
+        struct platform_info *pinfo = platform_get_drvdata(pdev);
 
-       for (i = 0; i < MSIC_THERMAL_SENSORS; i++)
-               thermal_zone_device_unregister(pinfo->tzd[i]);
+        for (i = 0; i < MSIC_THERMAL_SENSORS; i++)
+                thermal_zone_device_unregister(pinfo->tzd[i]);
 
-       platform_set_drvdata(pdev, NULL);
+        kfree(pinfo);
+        platform_set_drvdata(pdev, NULL);
 
-       /* Stop the ADC */
-       return configure_adc(0);
+        /* Stop the ADC */
+        return configure_adc(0);
 }
 
-/*********************************************************************
- *             Driver initialisation and finalization
- *********************************************************************/
-
 #define DRIVER_NAME "msic_sensor"
 
 static const struct platform_device_id therm_id_table[] = {
-       { DRIVER_NAME, 1 },
-       { }
+        { DRIVER_NAME, 1 },
+        { }
 };
 
 static struct platform_driver mid_thermal_driver = {
-       .driver = {
-               .name = DRIVER_NAME,
-               .owner = THIS_MODULE,
-       },
-       .probe = mid_thermal_probe,
-       .suspend = mid_thermal_suspend,
-       .resume = mid_thermal_resume,
-       .remove = __devexit_p(mid_thermal_remove),
-       .id_table = therm_id_table,
+        .driver = {
+                .name = DRIVER_NAME,
+                .owner = THIS_MODULE,
+        },
+        .probe = mid_thermal_probe,
+        .suspend = mid_thermal_suspend,
+        .resume = mid_thermal_resume,
+        .remove = __devexit_p(mid_thermal_remove),
+        .id_table = therm_id_table,
 };
 
 static int __init mid_thermal_module_init(void)
 {
-       return platform_driver_register(&mid_thermal_driver);
+        return platform_driver_register(&mid_thermal_driver);
 }
 
 static void __exit mid_thermal_module_exit(void)
 {
-       platform_driver_unregister(&mid_thermal_driver);
+        platform_driver_unregister(&mid_thermal_driver);
 }
 
 module_init(mid_thermal_module_init);
diff --git a/drivers/platform/x86/intel_oaktrail.c b/drivers/platform/x86/intel_oaktrail.c
new file mode 100644
index 000000000000..e936364a609d
--- /dev/null
+++ b/drivers/platform/x86/intel_oaktrail.c
@@ -0,0 +1,396 @@
+/*
+ * intel_oaktrail.c - Intel OakTrail Platform support.
+ *
+ * Copyright (C) 2010-2011 Intel Corporation
+ * Author: Yin Kangkai (kangkai.yin@intel.com)
+ *
+ * based on Compal driver, Copyright (C) 2008 Cezary Jackiewicz
+ * <cezary.jackiewicz (at) gmail.com>, based on MSI driver
+ * Copyright (C) 2006 Lennart Poettering <mzxreary (at) 0pointer (dot) de>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ *  General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ *  02110-1301, USA.
+ *
+ * This driver does below things:
+ * 1. registers itself in the Linux backlight control in
+ *    /sys/class/backlight/intel_oaktrail/
+ *
+ * 2. registers in the rfkill subsystem here: /sys/class/rfkill/rfkillX/
+ *    for these components: wifi, bluetooth, wwan (3g), gps
+ *
+ * This driver might work on other products based on Oaktrail. If you
+ * want to try it you can pass force=1 as argument to the module which
+ * will force it to load even when the DMI data doesn't identify the
+ * product as compatible.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/acpi.h>
+#include <linux/fb.h>
+#include <linux/mutex.h>
+#include <linux/err.h>
+#include <linux/i2c.h>
+#include <linux/backlight.h>
+#include <linux/platform_device.h>
+#include <linux/dmi.h>
+#include <linux/rfkill.h>
+#include <acpi/acpi_bus.h>
+#include <acpi/acpi_drivers.h>
+
+
+#define DRIVER_NAME     "intel_oaktrail"
+#define DRIVER_VERSION  "0.4ac1"
+
+/*
+ * This is the devices status address in EC space, and the control bits
+ * definition:
+ *
+ * (1 << 0):    Camera enable/disable, RW.
+ * (1 << 1):    Bluetooth enable/disable, RW.
+ * (1 << 2):    GPS enable/disable, RW.
+ * (1 << 3):    WiFi enable/disable, RW.
+ * (1 << 4):    WWAN (3G) enable/disalbe, RW.
+ * (1 << 5):    Touchscreen enable/disable, Read Only.
+ */
+#define OT_EC_DEVICE_STATE_ADDRESS      0xD6
+
+#define OT_EC_CAMERA_MASK       (1 << 0)
+#define OT_EC_BT_MASK           (1 << 1)
+#define OT_EC_GPS_MASK          (1 << 2)
+#define OT_EC_WIFI_MASK         (1 << 3)
+#define OT_EC_WWAN_MASK         (1 << 4)
+#define OT_EC_TS_MASK           (1 << 5)
+
+/*
+ * This is the address in EC space and commands used to control LCD backlight:
+ *
+ * Two steps needed to change the LCD backlight:
+ *   1. write the backlight percentage into OT_EC_BL_BRIGHTNESS_ADDRESS;
+ *   2. write OT_EC_BL_CONTROL_ON_DATA into OT_EC_BL_CONTROL_ADDRESS.
+ *
+ * To read the LCD back light, just read out the value from
+ * OT_EC_BL_BRIGHTNESS_ADDRESS.
+ *
+ * LCD backlight brightness range: 0 - 100 (OT_EC_BL_BRIGHTNESS_MAX)
+ */
+#define OT_EC_BL_BRIGHTNESS_ADDRESS     0x44
+#define OT_EC_BL_BRIGHTNESS_MAX         100
+#define OT_EC_BL_CONTROL_ADDRESS        0x3A
+#define OT_EC_BL_CONTROL_ON_DATA        0x1A
+
+
+static int force;
+module_param(force, bool, 0);
+MODULE_PARM_DESC(force, "Force driver load, ignore DMI data");
+
+static struct platform_device *oaktrail_device;
+static struct backlight_device *oaktrail_bl_device;
+static struct rfkill *bt_rfkill;
+static struct rfkill *gps_rfkill;
+static struct rfkill *wifi_rfkill;
+static struct rfkill *wwan_rfkill;
+
+
+/* rfkill */
+static int oaktrail_rfkill_set(void *data, bool blocked)
+{
+        u8 value;
+        u8 result;
+        unsigned long radio = (unsigned long) data;
+
+        ec_read(OT_EC_DEVICE_STATE_ADDRESS, &result);
+
+        if (!blocked)
+                value = (u8) (result | radio);
+        else
+                value = (u8) (result & ~radio);
+
+        ec_write(OT_EC_DEVICE_STATE_ADDRESS, value);
+
+        return 0;
+}
+
+static const struct rfkill_ops oaktrail_rfkill_ops = {
+        .set_block = oaktrail_rfkill_set,
+};
+
+static struct rfkill *oaktrail_rfkill_new(char *name, enum rfkill_type type,
+                                          unsigned long mask)
+{
+        struct rfkill *rfkill_dev;
+        u8 value;
+        int err;
+
+        rfkill_dev = rfkill_alloc(name, &oaktrail_device->dev, type,
+                                  &oaktrail_rfkill_ops, (void *)mask);
+        if (!rfkill_dev)
+                return ERR_PTR(-ENOMEM);
+
+        ec_read(OT_EC_DEVICE_STATE_ADDRESS, &value);
+        rfkill_init_sw_state(rfkill_dev, (value & mask) != 1);
+
+        err = rfkill_register(rfkill_dev);
+        if (err) {
+                rfkill_destroy(rfkill_dev);
+                return ERR_PTR(err);
+        }
+
+        return rfkill_dev;
+}
+
+static inline void __oaktrail_rfkill_cleanup(struct rfkill *rf)
+{
+        if (rf) {
+                rfkill_unregister(rf);
+                rfkill_destroy(rf);
+        }
+}
+
+static void oaktrail_rfkill_cleanup(void)
+{
+        __oaktrail_rfkill_cleanup(wifi_rfkill);
+        __oaktrail_rfkill_cleanup(bt_rfkill);
+        __oaktrail_rfkill_cleanup(gps_rfkill);
+        __oaktrail_rfkill_cleanup(wwan_rfkill);
+}
+
+static int oaktrail_rfkill_init(void)
+{
+        int ret;
+
+        wifi_rfkill = oaktrail_rfkill_new("oaktrail-wifi",
+                                          RFKILL_TYPE_WLAN,
+                                          OT_EC_WIFI_MASK);
+        if (IS_ERR(wifi_rfkill)) {
+                ret = PTR_ERR(wifi_rfkill);
+                wifi_rfkill = NULL;
+                goto cleanup;
+        }
+
+        bt_rfkill = oaktrail_rfkill_new("oaktrail-bluetooth",
+                                        RFKILL_TYPE_BLUETOOTH,
+                                        OT_EC_BT_MASK);
+        if (IS_ERR(bt_rfkill)) {
+                ret = PTR_ERR(bt_rfkill);
+                bt_rfkill = NULL;
+                goto cleanup;
+        }
+
+        gps_rfkill = oaktrail_rfkill_new("oaktrail-gps",
+                                         RFKILL_TYPE_GPS,
+                                         OT_EC_GPS_MASK);
+        if (IS_ERR(gps_rfkill)) {
+                ret = PTR_ERR(gps_rfkill);
+                gps_rfkill = NULL;
+                goto cleanup;
+        }
+
+        wwan_rfkill = oaktrail_rfkill_new("oaktrail-wwan",
+                                          RFKILL_TYPE_WWAN,
+                                          OT_EC_WWAN_MASK);
+        if (IS_ERR(wwan_rfkill)) {
+                ret = PTR_ERR(wwan_rfkill);
+                wwan_rfkill = NULL;
+                goto cleanup;
+        }
+
+        return 0;
+
+cleanup:
+        oaktrail_rfkill_cleanup();
+        return ret;
+}
+
+
+/* backlight */
+static int get_backlight_brightness(struct backlight_device *b)
+{
+        u8 value;
+        ec_read(OT_EC_BL_BRIGHTNESS_ADDRESS, &value);
+
+        return value;
+}
+
+static int set_backlight_brightness(struct backlight_device *b)
+{
+        u8 percent = (u8) b->props.brightness;
+        if (percent < 0 || percent > OT_EC_BL_BRIGHTNESS_MAX)
+                return -EINVAL;
+
+        ec_write(OT_EC_BL_BRIGHTNESS_ADDRESS, percent);
+        ec_write(OT_EC_BL_CONTROL_ADDRESS, OT_EC_BL_CONTROL_ON_DATA);
+
+        return 0;
+}
+
+static const struct backlight_ops oaktrail_bl_ops = {
+        .get_brightness = get_backlight_brightness,
+        .update_status  = set_backlight_brightness,
+};
+
+static int oaktrail_backlight_init(void)
+{
+        struct backlight_device *bd;
+        struct backlight_properties props;
+
+        memset(&props, 0, sizeof(struct backlight_properties));
+        props.max_brightness = OT_EC_BL_BRIGHTNESS_MAX;
+        bd = backlight_device_register(DRIVER_NAME,
+                                       &oaktrail_device->dev, NULL,
+                                       &oaktrail_bl_ops,
+                                       &props);
+
+        if (IS_ERR(bd)) {
+                oaktrail_bl_device = NULL;
+                pr_warning("Unable to register backlight device\n");
+                return PTR_ERR(bd);
+        }
+
+        oaktrail_bl_device = bd;
+
+        bd->props.brightness = get_backlight_brightness(bd);
+        bd->props.power = FB_BLANK_UNBLANK;
+        backlight_update_status(bd);
+
+        return 0;
+}
+
+static void oaktrail_backlight_exit(void)
+{
+        if (oaktrail_bl_device)
+                backlight_device_unregister(oaktrail_bl_device);
+}
+
+static int __devinit oaktrail_probe(struct platform_device *pdev)
+{
+        return 0;
+}
+
+static int __devexit oaktrail_remove(struct platform_device *pdev)
+{
+        return 0;
+}
+
+static struct platform_driver oaktrail_driver = {
+        .driver = {
+                .name = DRIVER_NAME,
+                .owner = THIS_MODULE,
+        },
+        .probe  = oaktrail_probe,
+        .remove = __devexit_p(oaktrail_remove)
+};
+
+static int dmi_check_cb(const struct dmi_system_id *id)
+{
+        pr_info("Identified model '%s'\n", id->ident);
+        return 0;
+}
+
+static struct dmi_system_id __initdata oaktrail_dmi_table[] = {
+        {
+                .ident = "OakTrail platform",
+                .matches = {
+                        DMI_MATCH(DMI_PRODUCT_NAME, "OakTrail platform"),
+                },
+                .callback = dmi_check_cb
+        },
+        { }
+};
+
+static int __init oaktrail_init(void)
+{
+        int ret;
+
+        if (acpi_disabled) {
+                pr_err("ACPI needs to be enabled for this driver to work!\n");
+                return -ENODEV;
+        }
+
+        if (!force && !dmi_check_system(oaktrail_dmi_table)) {
+                pr_err("Platform not recognized (You could try the module's force-parameter)");
+                return -ENODEV;
+        }
+
+        ret = platform_driver_register(&oaktrail_driver);
+        if (ret) {
+                pr_warning("Unable to register platform driver\n");
+                goto err_driver_reg;
+        }
+
+        oaktrail_device = platform_device_alloc(DRIVER_NAME, -1);
+        if (!oaktrail_device) {
+                pr_warning("Unable to allocate platform device\n");
+                ret = -ENOMEM;
+                goto err_device_alloc;
+        }
+
+        ret = platform_device_add(oaktrail_device);
+        if (ret) {
+                pr_warning("Unable to add platform device\n");
+                goto err_device_add;
+        }
+
+        if (!acpi_video_backlight_support()) {
+                ret = oaktrail_backlight_init();
+                if (ret)
+                        goto err_backlight;
+
+        } else
+                pr_info("Backlight controlled by ACPI video driver\n");
+
+        ret = oaktrail_rfkill_init();
+        if (ret) {
+                pr_warning("Setup rfkill failed\n");
+                goto err_rfkill;
+        }
+
+        pr_info("Driver "DRIVER_VERSION" successfully loaded\n");
+        return 0;
+
+err_rfkill:
+        oaktrail_backlight_exit();
+err_backlight:
+        platform_device_del(oaktrail_device);
+err_device_add:
+        platform_device_put(oaktrail_device);
+err_device_alloc:
+        platform_driver_unregister(&oaktrail_driver);
+err_driver_reg:
+
+        return ret;
+}
+
+static void __exit oaktrail_cleanup(void)
+{
+        oaktrail_backlight_exit();
+        oaktrail_rfkill_cleanup();
+        platform_device_unregister(oaktrail_device);
+        platform_driver_unregister(&oaktrail_driver);
+
+        pr_info("Driver unloaded\n");
+}
+
+module_init(oaktrail_init);
+module_exit(oaktrail_cleanup);
+
+MODULE_AUTHOR("Yin Kangkai (kangkai.yin@intel.com)");
+MODULE_DESCRIPTION("Intel Oaktrail Platform ACPI Extras");
+MODULE_VERSION(DRIVER_VERSION);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("dmi:*:svnIntelCorporation:pnOakTrailplatform:*");
diff --git a/drivers/platform/x86/intel_pmic_gpio.c b/drivers/platform/x86/intel_pmic_gpio.c
index 464bb3fc4d88..1686c1e07d5d 100644
--- a/drivers/platform/x86/intel_pmic_gpio.c
+++ b/drivers/platform/x86/intel_pmic_gpio.c
@@ -19,6 +19,8 @@
  * Moorestown platform PMIC chip
  */
 
+#define pr_fmt(fmt) "%s: " fmt, __func__
+
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/interrupt.h>
@@ -90,8 +92,7 @@ static void pmic_program_irqtype(int gpio, int type)
 static int pmic_gpio_direction_input(struct gpio_chip *chip, unsigned offset)
 {
         if (offset > 8) {
-                printk(KERN_ERR
-                        "%s: only pin 0-7 support input\n", __func__);
+                pr_err("only pin 0-7 support input\n");
                 return -1;/* we only have 8 GPIO can use as input */
         }
         return intel_scu_ipc_update_register(GPIO0 + offset,
@@ -116,8 +117,7 @@ static int pmic_gpio_direction_output(struct gpio_chip *chip,
                                 value ? 1 << (offset - 16) : 0,
                                 1 << (offset - 16));
         else {
-                printk(KERN_ERR
-                        "%s: invalid PMIC GPIO pin %d!\n", __func__, offset);
+                pr_err("invalid PMIC GPIO pin %d!\n", offset);
                 WARN_ON(1);
         }
 
@@ -260,7 +260,7 @@ static int __devinit platform_pmic_gpio_probe(struct platform_device *pdev)
         /* setting up SRAM mapping for GPIOINT register */
         pg->gpiointr = ioremap_nocache(pdata->gpiointr, 8);
         if (!pg->gpiointr) {
-                printk(KERN_ERR "%s: Can not map GPIOINT.\n", __func__);
+                pr_err("Can not map GPIOINT\n");
                 retval = -EINVAL;
                 goto err2;
         }
@@ -281,13 +281,13 @@ static int __devinit platform_pmic_gpio_probe(struct platform_device *pdev)
         pg->chip.dev = dev;
         retval = gpiochip_add(&pg->chip);
         if (retval) {
-                printk(KERN_ERR "%s: Can not add pmic gpio chip.\n", __func__);
+                pr_err("Can not add pmic gpio chip\n");
                 goto err;
         }
 
         retval = request_irq(pg->irq, pmic_irq_handler, 0, "pmic", pg);
         if (retval) {
-                printk(KERN_WARNING "pmic: Interrupt request failed\n");
+                pr_warn("Interrupt request failed\n");
                 goto err;
         }
 
diff --git a/drivers/platform/x86/msi-laptop.c b/drivers/platform/x86/msi-laptop.c
index 23fb2afda00b..3ff629df9f01 100644
--- a/drivers/platform/x86/msi-laptop.c
+++ b/drivers/platform/x86/msi-laptop.c
@@ -135,7 +135,7 @@ static int set_lcd_level(int level)
         buf[1] = (u8) (level*31);
 
         return ec_transaction(MSI_EC_COMMAND_LCD_LEVEL, buf, sizeof(buf),
-                              NULL, 0, 1);
+                              NULL, 0);
 }
 
 static int get_lcd_level(void)
@@ -144,7 +144,7 @@ static int get_lcd_level(void)
         int result;
 
         result = ec_transaction(MSI_EC_COMMAND_LCD_LEVEL, &wdata, 1,
-                                &rdata, 1, 1);
+                                &rdata, 1);
         if (result < 0)
                 return result;
 
@@ -157,7 +157,7 @@ static int get_auto_brightness(void)
         int result;
 
         result = ec_transaction(MSI_EC_COMMAND_LCD_LEVEL, &wdata, 1,
-                                &rdata, 1, 1);
+                                &rdata, 1);
         if (result < 0)
                 return result;
 
@@ -172,7 +172,7 @@ static int set_auto_brightness(int enable)
         wdata[0] = 4;
 
         result = ec_transaction(MSI_EC_COMMAND_LCD_LEVEL, wdata, 1,
-                                &rdata, 1, 1);
+                                &rdata, 1);
         if (result < 0)
                 return result;
 
@@ -180,7 +180,7 @@ static int set_auto_brightness(int enable)
         wdata[1] = (rdata & 0xF7) | (enable ? 8 : 0);
 
         return ec_transaction(MSI_EC_COMMAND_LCD_LEVEL, wdata, 2,
-                              NULL, 0, 1);
+                              NULL, 0);
 }
 
 static ssize_t set_device_state(const char *buf, size_t count, u8 mask)
@@ -217,7 +217,7 @@ static int get_wireless_state(int *wlan, int *bluetooth)
         u8 wdata = 0, rdata;
         int result;
 
-        result = ec_transaction(MSI_EC_COMMAND_WIRELESS, &wdata, 1, &rdata, 1, 1);
+        result = ec_transaction(MSI_EC_COMMAND_WIRELESS, &wdata, 1, &rdata, 1);
         if (result < 0)
                 return -1;
 
@@ -447,7 +447,7 @@ static struct platform_device *msipf_device;
 
 static int dmi_check_cb(const struct dmi_system_id *id)
 {
-        pr_info("Identified laptop model '%s'.\n", id->ident);
+        pr_info("Identified laptop model '%s'\n", id->ident);
         return 1;
 }
 
@@ -800,7 +800,7 @@ static void msi_laptop_input_destroy(void)
         input_unregister_device(msi_laptop_input_dev);
 }
 
-static int load_scm_model_init(struct platform_device *sdev)
+static int __init load_scm_model_init(struct platform_device *sdev)
 {
         u8 data;
         int result;
@@ -875,8 +875,7 @@ static int __init msi_init(void)
         /* Register backlight stuff */
 
         if (acpi_video_backlight_support()) {
-                pr_info("Brightness ignored, must be controlled "
-                       "by ACPI video driver\n");
+                pr_info("Brightness ignored, must be controlled by ACPI video driver\n");
         } else {
                 struct backlight_properties props;
                 memset(&props, 0, sizeof(struct backlight_properties));
@@ -930,7 +929,7 @@ static int __init msi_init(void)
         if (auto_brightness != 2)
                 set_auto_brightness(auto_brightness);
 
-        pr_info("driver "MSI_DRIVER_VERSION" successfully loaded.\n");
+        pr_info("driver " MSI_DRIVER_VERSION " successfully loaded\n");
 
         return 0;
 
@@ -978,7 +977,7 @@ static void __exit msi_cleanup(void)
         if (auto_brightness != 2)
                 set_auto_brightness(1);
 
-        pr_info("driver unloaded.\n");
+        pr_info("driver unloaded\n");
 }
 
 module_init(msi_init);
diff --git a/drivers/platform/x86/msi-wmi.c b/drivers/platform/x86/msi-wmi.c
index d5419c9ec07a..c832e3356cd6 100644
--- a/drivers/platform/x86/msi-wmi.c
+++ b/drivers/platform/x86/msi-wmi.c
@@ -20,6 +20,7 @@
  *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/kernel.h>
 #include <linux/input.h>
@@ -36,13 +37,10 @@ MODULE_ALIAS("wmi:551A1F84-FBDD-4125-91DB-3EA8F44F1D45");
 MODULE_ALIAS("wmi:B6F3EEF2-3D2F-49DC-9DE3-85BCE18C62F2");
 
 #define DRV_NAME "msi-wmi"
-#define DRV_PFX DRV_NAME ": "
 
 #define MSIWMI_BIOS_GUID "551A1F84-FBDD-4125-91DB-3EA8F44F1D45"
 #define MSIWMI_EVENT_GUID "B6F3EEF2-3D2F-49DC-9DE3-85BCE18C62F2"
 
-#define dprintk(msg...) pr_debug(DRV_PFX msg)
-
 #define SCANCODE_BASE 0xD0
 #define MSI_WMI_BRIGHTNESSUP   SCANCODE_BASE
 #define MSI_WMI_BRIGHTNESSDOWN (SCANCODE_BASE + 1)
@@ -78,7 +76,7 @@ static int msi_wmi_query_block(int instance, int *ret)
 
         if (!obj || obj->type != ACPI_TYPE_INTEGER) {
                 if (obj) {
-                        printk(KERN_ERR DRV_PFX "query block returned object "
+                        pr_err("query block returned object "
                                "type: %d - buffer length:%d\n", obj->type,
                                obj->type == ACPI_TYPE_BUFFER ?
                                obj->buffer.length : 0);
@@ -97,8 +95,8 @@ static int msi_wmi_set_block(int instance, int value)
 
         struct acpi_buffer input = { sizeof(int), &value };
 
-        dprintk("Going to set block of instance: %d - value: %d\n",
-                instance, value);
+        pr_debug("Going to set block of instance: %d - value: %d\n",
+                 instance, value);
 
         status = wmi_set_block(MSIWMI_BIOS_GUID, instance, &input);
 
@@ -112,20 +110,19 @@ static int bl_get(struct backlight_device *bd)
         /* Instance 1 is "get backlight", cmp with DSDT */
         err = msi_wmi_query_block(1, &ret);
         if (err) {
-                printk(KERN_ERR DRV_PFX "Could not query backlight: %d\n", err);
+                pr_err("Could not query backlight: %d\n", err);
                 return -EINVAL;
         }
-        dprintk("Get: Query block returned: %d\n", ret);
+        pr_debug("Get: Query block returned: %d\n", ret);
         for (level = 0; level < ARRAY_SIZE(backlight_map); level++) {
                 if (backlight_map[level] == ret) {
-                        dprintk("Current backlight level: 0x%X - index: %d\n",
-                                backlight_map[level], level);
+                        pr_debug("Current backlight level: 0x%X - index: %d\n",
+                                 backlight_map[level], level);
                         break;
                 }
         }
         if (level == ARRAY_SIZE(backlight_map)) {
-                printk(KERN_ERR DRV_PFX "get: Invalid brightness value: 0x%X\n",
-                       ret);
+                pr_err("get: Invalid brightness value: 0x%X\n", ret);
                 return -EINVAL;
         }
         return level;
@@ -156,7 +153,7 @@ static void msi_wmi_notify(u32 value, void *context)
 
         status = wmi_get_event_data(value, &response);
         if (status != AE_OK) {
-                printk(KERN_INFO DRV_PFX "bad event status 0x%x\n", status);
+                pr_info("bad event status 0x%x\n", status);
                 return;
         }
 
@@ -164,7 +161,7 @@ static void msi_wmi_notify(u32 value, void *context)
 
         if (obj && obj->type == ACPI_TYPE_INTEGER) {
                 int eventcode = obj->integer.value;
-                dprintk("Eventcode: 0x%x\n", eventcode);
+                pr_debug("Eventcode: 0x%x\n", eventcode);
                 key = sparse_keymap_entry_from_scancode(msi_wmi_input_dev,
                                 eventcode);
                 if (key) {
@@ -175,8 +172,8 @@ static void msi_wmi_notify(u32 value, void *context)
                         /* Ignore event if the same event happened in a 50 ms
                            timeframe -> Key press may result in 10-20 GPEs */
                         if (ktime_to_us(diff) < 1000 * 50) {
-                                dprintk("Suppressed key event 0x%X - "
-                                        "Last press was %lld us ago\n",
+                                pr_debug("Suppressed key event 0x%X - "
+                                         "Last press was %lld us ago\n",
                                          key->code, ktime_to_us(diff));
                                 return;
                         }
@@ -187,17 +184,16 @@ static void msi_wmi_notify(u32 value, void *context)
                         (!acpi_video_backlight_support() ||
                         (key->code != MSI_WMI_BRIGHTNESSUP &&
                         key->code != MSI_WMI_BRIGHTNESSDOWN))) {
-                                dprintk("Send key: 0x%X - "
-                                        "Input layer keycode: %d\n", key->code,
-                                         key->keycode);
+                                pr_debug("Send key: 0x%X - "
+                                         "Input layer keycode: %d\n",
+                                         key->code, key->keycode);
                                 sparse_keymap_report_entry(msi_wmi_input_dev,
                                                 key, 1, true);
                         }
                 } else
-                        printk(KERN_INFO "Unknown key pressed - %x\n",
-                               eventcode);
+                        pr_info("Unknown key pressed - %x\n", eventcode);
         } else
-                printk(KERN_INFO DRV_PFX "Unknown event received\n");
+                pr_info("Unknown event received\n");
         kfree(response.pointer);
 }
 
@@ -238,8 +234,7 @@ static int __init msi_wmi_init(void)
         int err;
 
         if (!wmi_has_guid(MSIWMI_EVENT_GUID)) {
-                printk(KERN_ERR
-                       "This machine doesn't have MSI-hotkeys through WMI\n");
+                pr_err("This machine doesn't have MSI-hotkeys through WMI\n");
                 return -ENODEV;
         }
         err = wmi_install_notify_handler(MSIWMI_EVENT_GUID,
@@ -270,7 +265,7 @@ static int __init msi_wmi_init(void)
 
                 backlight->props.brightness = err;
         }
-        dprintk("Event handler installed\n");
+        pr_debug("Event handler installed\n");
 
         return 0;
 
diff --git a/drivers/platform/x86/sony-laptop.c b/drivers/platform/x86/sony-laptop.c
index 6fe8cd6e23b5..bbd182e178cb 100644
--- a/drivers/platform/x86/sony-laptop.c
+++ b/drivers/platform/x86/sony-laptop.c
@@ -42,6 +42,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
@@ -70,10 +72,10 @@
 #include <linux/miscdevice.h>
 #endif
 
-#define DRV_PFX                 "sony-laptop: "
-#define dprintk(msg...)         do {    \
-        if (debug)                      \
-                pr_warn(DRV_PFX msg);   \
+#define dprintk(fmt, ...)                       \
+do {                                            \
+        if (debug)                              \
+                pr_warn(fmt, ##__VA_ARGS__);    \
 } while (0)
 
 #define SONY_LAPTOP_DRIVER_VERSION      "0.6"
@@ -418,7 +420,7 @@ static int sony_laptop_setup_input(struct acpi_device *acpi_device)
         error = kfifo_alloc(&sony_laptop_input.fifo,
                             SONY_LAPTOP_BUF_SIZE, GFP_KERNEL);
         if (error) {
-                pr_err(DRV_PFX "kfifo_alloc failed\n");
+                pr_err("kfifo_alloc failed\n");
                 goto err_dec_users;
         }
 
@@ -702,7 +704,7 @@ static int acpi_callgetfunc(acpi_handle handle, char *name, int *result)
                 return 0;
         }
 
-        pr_warn(DRV_PFX "acpi_callreadfunc failed\n");
+        pr_warn("acpi_callreadfunc failed\n");
 
         return -1;
 }
@@ -728,8 +730,7 @@ static int acpi_callsetfunc(acpi_handle handle, char *name, int value,
         if (status == AE_OK) {
                 if (result != NULL) {
                         if (out_obj.type != ACPI_TYPE_INTEGER) {
-                                pr_warn(DRV_PFX "acpi_evaluate_object bad "
-                                       "return type\n");
+                                pr_warn("acpi_evaluate_object bad return type\n");
                                 return -1;
                         }
                         *result = out_obj.integer.value;
@@ -737,7 +738,7 @@ static int acpi_callsetfunc(acpi_handle handle, char *name, int value,
                 return 0;
         }
 
-        pr_warn(DRV_PFX "acpi_evaluate_object failed\n");
+        pr_warn("acpi_evaluate_object failed\n");
 
         return -1;
 }
@@ -961,7 +962,6 @@ static int sony_backlight_get_brightness(struct backlight_device *bd)
 static int sony_nc_get_brightness_ng(struct backlight_device *bd)
 {
         int result;
-        int *handle = (int *)bl_get_data(bd);
         struct sony_backlight_props *sdev =
                 (struct sony_backlight_props *)bl_get_data(bd);
 
@@ -973,7 +973,6 @@ static int sony_nc_get_brightness_ng(struct backlight_device *bd)
 static int sony_nc_update_status_ng(struct backlight_device *bd)
 {
         int value, result;
-        int *handle = (int *)bl_get_data(bd);
         struct sony_backlight_props *sdev =
                 (struct sony_backlight_props *)bl_get_data(bd);
 
@@ -1104,10 +1103,8 @@ static void sony_nc_notify(struct acpi_device *device, u32 event)
                                 }
 
                                 if (!key_event->data)
-                                        pr_info(DRV_PFX
-                                                        "Unknown event: 0x%x 0x%x\n",
-                                                        key_handle,
-                                                        ev);
+                                        pr_info("Unknown event: 0x%x 0x%x\n",
+                                                key_handle, ev);
                                 else
                                         sony_laptop_report_input_event(ev);
                         }
@@ -1128,7 +1125,7 @@ static acpi_status sony_walk_callback(acpi_handle handle, u32 level,
         struct acpi_device_info *info;
 
         if (ACPI_SUCCESS(acpi_get_object_info(handle, &info))) {
-                pr_warn(DRV_PFX "method: name: %4.4s, args %X\n",
+                pr_warn("method: name: %4.4s, args %X\n",
                         (char *)&info->name, info->param_count);
 
                 kfree(info);
@@ -1169,7 +1166,7 @@ static int sony_nc_resume(struct acpi_device *device)
                 ret = acpi_callsetfunc(sony_nc_acpi_handle, *item->acpiset,
                                        item->value, NULL);
                 if (ret < 0) {
-                        pr_err(DRV_PFX "%s: %d\n", __func__, ret);
+                        pr_err("%s: %d\n", __func__, ret);
                         break;
                 }
         }
@@ -1336,12 +1333,12 @@ static void sony_nc_rfkill_setup(struct acpi_device *device)
 
         device_enum = (union acpi_object *) buffer.pointer;
         if (!device_enum) {
-                pr_err(DRV_PFX "No SN06 return object.");
+                pr_err("No SN06 return object\n");
                 goto out_no_enum;
         }
         if (device_enum->type != ACPI_TYPE_BUFFER) {
-                pr_err(DRV_PFX "Invalid SN06 return object 0x%.2x\n",
-                                device_enum->type);
+                pr_err("Invalid SN06 return object 0x%.2x\n",
+                       device_enum->type);
                 goto out_no_enum;
         }
 
@@ -1662,7 +1659,7 @@ static void sony_nc_backlight_setup(void)
                                                       ops, &props);
 
         if (IS_ERR(sony_bl_props.dev)) {
-                pr_warn(DRV_PFX "unable to register backlight device\n");
+                pr_warn("unable to register backlight device\n");
                 sony_bl_props.dev = NULL;
         } else
                 sony_bl_props.dev->props.brightness =
@@ -1682,8 +1679,7 @@ static int sony_nc_add(struct acpi_device *device)
         acpi_handle handle;
         struct sony_nc_value *item;
 
-        pr_info(DRV_PFX "%s v%s.\n", SONY_NC_DRIVER_NAME,
-                        SONY_LAPTOP_DRIVER_VERSION);
+        pr_info("%s v%s\n", SONY_NC_DRIVER_NAME, SONY_LAPTOP_DRIVER_VERSION);
 
         sony_nc_acpi_device = device;
         strcpy(acpi_device_class(device), "sony/hotkey");
@@ -1708,7 +1704,7 @@ static int sony_nc_add(struct acpi_device *device)
                                 sony_nc_acpi_handle, 1, sony_walk_callback,
                                 NULL, NULL, NULL);
                 if (ACPI_FAILURE(status)) {
-                        pr_warn(DRV_PFX "unable to walk acpi resources\n");
+                        pr_warn("unable to walk acpi resources\n");
                         result = -ENODEV;
                         goto outpresent;
                 }
@@ -1736,13 +1732,12 @@ static int sony_nc_add(struct acpi_device *device)
         /* setup input devices and helper fifo */
         result = sony_laptop_setup_input(device);
         if (result) {
-                pr_err(DRV_PFX "Unable to create input devices.\n");
+                pr_err("Unable to create input devices\n");
                 goto outkbdbacklight;
         }
 
         if (acpi_video_backlight_support()) {
-                pr_info(DRV_PFX "brightness ignored, must be "
-                       "controlled by ACPI video driver\n");
+                pr_info("brightness ignored, must be controlled by ACPI video driver\n");
         } else {
                 sony_nc_backlight_setup();
         }
@@ -2265,9 +2260,9 @@ out:
         if (pcidev)
                 pci_dev_put(pcidev);
 
-        pr_info(DRV_PFX "detected Type%d model\n",
-                        dev->model == SONYPI_DEVICE_TYPE1 ? 1 :
-                        dev->model == SONYPI_DEVICE_TYPE2 ? 2 : 3);
+        pr_info("detected Type%d model\n",
+                dev->model == SONYPI_DEVICE_TYPE1 ? 1 :
+                dev->model == SONYPI_DEVICE_TYPE2 ? 2 : 3);
 }
 
 /* camera tests and poweron/poweroff */
@@ -2313,7 +2308,7 @@ static int __sony_pic_camera_ready(void)
 static int __sony_pic_camera_off(void)
 {
         if (!camera) {
-                pr_warn(DRV_PFX "camera control not enabled\n");
+                pr_warn("camera control not enabled\n");
                 return -ENODEV;
         }
 
@@ -2333,7 +2328,7 @@ static int __sony_pic_camera_on(void)
         int i, j, x;
 
         if (!camera) {
-                pr_warn(DRV_PFX "camera control not enabled\n");
+                pr_warn("camera control not enabled\n");
                 return -ENODEV;
         }
 
@@ -2356,7 +2351,7 @@ static int __sony_pic_camera_on(void)
         }
 
         if (j == 0) {
-                pr_warn(DRV_PFX "failed to power on camera\n");
+                pr_warn("failed to power on camera\n");
                 return -ENODEV;
         }
 
@@ -2412,8 +2407,7 @@ int sony_pic_camera_command(int command, u8 value)
                                 ITERATIONS_SHORT);
                 break;
         default:
-                pr_err(DRV_PFX "sony_pic_camera_command invalid: %d\n",
-                       command);
+                pr_err("sony_pic_camera_command invalid: %d\n", command);
                 break;
         }
         mutex_unlock(&spic_dev.lock);
@@ -2819,7 +2813,7 @@ static int sonypi_compat_init(void)
         error =
          kfifo_alloc(&sonypi_compat.fifo, SONY_LAPTOP_BUF_SIZE, GFP_KERNEL);
         if (error) {
-                pr_err(DRV_PFX "kfifo_alloc failed\n");
+                pr_err("kfifo_alloc failed\n");
                 return error;
         }
 
@@ -2829,12 +2823,12 @@ static int sonypi_compat_init(void)
                 sonypi_misc_device.minor = minor;
         error = misc_register(&sonypi_misc_device);
         if (error) {
-                pr_err(DRV_PFX "misc_register failed\n");
+                pr_err("misc_register failed\n");
                 goto err_free_kfifo;
         }
         if (minor == -1)
-                pr_info(DRV_PFX "device allocated minor is %d\n",
-                       sonypi_misc_device.minor);
+                pr_info("device allocated minor is %d\n",
+                        sonypi_misc_device.minor);
 
         return 0;
 
@@ -2893,8 +2887,8 @@ sony_pic_read_possible_resource(struct acpi_resource *resource, void *context)
                         }
                         for (i = 0; i < p->interrupt_count; i++) {
                                 if (!p->interrupts[i]) {
-                                        pr_warn(DRV_PFX "Invalid IRQ %d\n",
-                                                        p->interrupts[i]);
+                                        pr_warn("Invalid IRQ %d\n",
+                                                p->interrupts[i]);
                                         continue;
                                 }
                                 interrupt = kzalloc(sizeof(*interrupt),
@@ -2932,14 +2926,14 @@ sony_pic_read_possible_resource(struct acpi_resource *resource, void *context)
                                                 ioport->io2.address_length);
                         }
                         else {
-                                pr_err(DRV_PFX "Unknown SPIC Type, more than 2 IO Ports\n");
+                                pr_err("Unknown SPIC Type, more than 2 IO Ports\n");
                                 return AE_ERROR;
                         }
                         return AE_OK;
                 }
         default:
                 dprintk("Resource %d isn't an IRQ nor an IO port\n",
-                                resource->type);
+                        resource->type);
 
         case ACPI_RESOURCE_TYPE_END_TAG:
                 return AE_OK;
@@ -2960,7 +2954,7 @@ static int sony_pic_possible_resources(struct acpi_device *device)
         dprintk("Evaluating _STA\n");
         result = acpi_bus_get_status(device);
         if (result) {
-                pr_warn(DRV_PFX "Unable to read status\n");
+                pr_warn("Unable to read status\n");
                 goto end;
         }
 
@@ -2976,8 +2970,7 @@ static int sony_pic_possible_resources(struct acpi_device *device)
         status = acpi_walk_resources(device->handle, METHOD_NAME__PRS,
                         sony_pic_read_possible_resource, &spic_dev);
         if (ACPI_FAILURE(status)) {
-                pr_warn(DRV_PFX "Failure evaluating %s\n",
-                                METHOD_NAME__PRS);
+                pr_warn("Failure evaluating %s\n", METHOD_NAME__PRS);
                 result = -ENODEV;
         }
 end:
@@ -3090,7 +3083,7 @@ static int sony_pic_enable(struct acpi_device *device,
 
         /* check for total failure */
         if (ACPI_FAILURE(status)) {
-                pr_err(DRV_PFX "Error evaluating _SRS\n");
+                pr_err("Error evaluating _SRS\n");
                 result = -ENODEV;
                 goto end;
         }
@@ -3182,7 +3175,7 @@ static int sony_pic_remove(struct acpi_device *device, int type)
         struct sony_pic_irq *irq, *tmp_irq;
 
         if (sony_pic_disable(device)) {
-                pr_err(DRV_PFX "Couldn't disable device.\n");
+                pr_err("Couldn't disable device\n");
                 return -ENXIO;
         }
 
@@ -3222,8 +3215,7 @@ static int sony_pic_add(struct acpi_device *device)
         struct sony_pic_ioport *io, *tmp_io;
         struct sony_pic_irq *irq, *tmp_irq;
 
-        pr_info(DRV_PFX "%s v%s.\n", SONY_PIC_DRIVER_NAME,
-                        SONY_LAPTOP_DRIVER_VERSION);
+        pr_info("%s v%s\n", SONY_PIC_DRIVER_NAME, SONY_LAPTOP_DRIVER_VERSION);
 
         spic_dev.acpi_dev = device;
         strcpy(acpi_device_class(device), "sony/hotkey");
@@ -3233,14 +3225,14 @@ static int sony_pic_add(struct acpi_device *device)
         /* read _PRS resources */
         result = sony_pic_possible_resources(device);
         if (result) {
-                pr_err(DRV_PFX "Unable to read possible resources.\n");
+                pr_err("Unable to read possible resources\n");
                 goto err_free_resources;
         }
 
         /* setup input devices and helper fifo */
         result = sony_laptop_setup_input(device);
         if (result) {
-                pr_err(DRV_PFX "Unable to create input devices.\n");
+                pr_err("Unable to create input devices\n");
                 goto err_free_resources;
         }
 
@@ -3281,7 +3273,7 @@ static int sony_pic_add(struct acpi_device *device)
                 }
         }
         if (!spic_dev.cur_ioport) {
-                pr_err(DRV_PFX "Failed to request_region.\n");
+                pr_err("Failed to request_region\n");
                 result = -ENODEV;
                 goto err_remove_compat;
         }
@@ -3301,7 +3293,7 @@ static int sony_pic_add(struct acpi_device *device)
                 }
         }
         if (!spic_dev.cur_irq) {
-                pr_err(DRV_PFX "Failed to request_irq.\n");
+                pr_err("Failed to request_irq\n");
                 result = -ENODEV;
                 goto err_release_region;
         }
@@ -3309,7 +3301,7 @@ static int sony_pic_add(struct acpi_device *device)
         /* set resource status _SRS */
         result = sony_pic_enable(device, spic_dev.cur_ioport, spic_dev.cur_irq);
         if (result) {
-                pr_err(DRV_PFX "Couldn't enable device.\n");
+                pr_err("Couldn't enable device\n");
                 goto err_free_irq;
         }
 
@@ -3418,7 +3410,7 @@ static int __init sony_laptop_init(void)
         if (!no_spic && dmi_check_system(sonypi_dmi_table)) {
                 result = acpi_bus_register_driver(&sony_pic_driver);
                 if (result) {
-                        pr_err(DRV_PFX "Unable to register SPIC driver.");
+                        pr_err("Unable to register SPIC driver\n");
                         goto out;
                 }
                 spic_drv_registered = 1;
@@ -3426,7 +3418,7 @@ static int __init sony_laptop_init(void)
 
         result = acpi_bus_register_driver(&sony_nc_driver);
         if (result) {
-                pr_err(DRV_PFX "Unable to register SNC driver.");
+                pr_err("Unable to register SNC driver\n");
                 goto out_unregister_pic;
         }
 
diff --git a/drivers/platform/x86/tc1100-wmi.c b/drivers/platform/x86/tc1100-wmi.c
index 865ef78d6f1a..e24f5ae475af 100644
--- a/drivers/platform/x86/tc1100-wmi.c
+++ b/drivers/platform/x86/tc1100-wmi.c
@@ -25,6 +25,8 @@
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/slab.h>
@@ -40,9 +42,6 @@
 #define TC1100_INSTANCE_WIRELESS                1
 #define TC1100_INSTANCE_JOGDIAL         2
 
-#define TC1100_LOGPREFIX "tc1100-wmi: "
-#define TC1100_INFO KERN_INFO TC1100_LOGPREFIX
-
 MODULE_AUTHOR("Jamey Hicks, Carlos Corbacho");
 MODULE_DESCRIPTION("HP Compaq TC1100 Tablet WMI Extras");
 MODULE_LICENSE("GPL");
@@ -264,7 +263,7 @@ static int __init tc1100_init(void)
         if (error)
                 goto err_device_del;
 
-        printk(TC1100_INFO "HP Compaq TC1100 Tablet WMI Extras loaded\n");
+        pr_info("HP Compaq TC1100 Tablet WMI Extras loaded\n");
         return 0;
 
  err_device_del:
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index 562fcf0dd2b5..77f6e707a2a9 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -21,6 +21,8 @@
  *  02110-1301, USA.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #define TPACPI_VERSION "0.24"
 #define TPACPI_SYSFS_VERSION 0x020700
 
@@ -224,17 +226,6 @@ enum tpacpi_hkey_event_t {
 
 #define TPACPI_MAX_ACPI_ARGS 3
 
-/* printk headers */
-#define TPACPI_LOG TPACPI_FILE ": "
-#define TPACPI_EMERG    KERN_EMERG      TPACPI_LOG
-#define TPACPI_ALERT    KERN_ALERT      TPACPI_LOG
-#define TPACPI_CRIT     KERN_CRIT       TPACPI_LOG
-#define TPACPI_ERR      KERN_ERR        TPACPI_LOG
-#define TPACPI_WARN     KERN_WARNING    TPACPI_LOG
-#define TPACPI_NOTICE   KERN_NOTICE     TPACPI_LOG
-#define TPACPI_INFO     KERN_INFO       TPACPI_LOG
-#define TPACPI_DEBUG    KERN_DEBUG      TPACPI_LOG
-
 /* Debugging printk groups */
 #define TPACPI_DBG_ALL          0xffff
 #define TPACPI_DBG_DISCLOSETASK 0x8000
@@ -389,34 +380,36 @@ static int tpacpi_uwb_emulstate;
  *  Debugging helpers
  */
 
-#define dbg_printk(a_dbg_level, format, arg...) \
-        do { if (dbg_level & (a_dbg_level)) \
-                printk(TPACPI_DEBUG "%s: " format, __func__ , ## arg); \
-        } while (0)
+#define dbg_printk(a_dbg_level, format, arg...)                         \
+do {                                                                    \
+        if (dbg_level & (a_dbg_level))                                  \
+                printk(KERN_DEBUG pr_fmt("%s: " format),                \
+                       __func__, ##arg);                                \
+} while (0)
 
 #ifdef CONFIG_THINKPAD_ACPI_DEBUG
 #define vdbg_printk dbg_printk
 static const char *str_supported(int is_supported);
 #else
-#define vdbg_printk(a_dbg_level, format, arg...) \
-        do { } while (0)
+static inline const char *str_supported(int is_supported) { return ""; }
+#define vdbg_printk(a_dbg_level, format, arg...)        \
+        no_printk(format, ##arg)
 #endif
 
 static void tpacpi_log_usertask(const char * const what)
 {
-        printk(TPACPI_DEBUG "%s: access by process with PID %d\n",
-                what, task_tgid_vnr(current));
+        printk(KERN_DEBUG pr_fmt("%s: access by process with PID %d\n"),
+               what, task_tgid_vnr(current));
 }
 
-#define tpacpi_disclose_usertask(what, format, arg...) \
-        do { \
-                if (unlikely( \
-                    (dbg_level & TPACPI_DBG_DISCLOSETASK) && \
-                    (tpacpi_lifecycle == TPACPI_LIFE_RUNNING))) { \
-                        printk(TPACPI_DEBUG "%s: PID %d: " format, \
-                                what, task_tgid_vnr(current), ## arg); \
-                } \
-        } while (0)
+#define tpacpi_disclose_usertask(what, format, arg...)                  \
+do {                                                                    \
+        if (unlikely((dbg_level & TPACPI_DBG_DISCLOSETASK) &&           \
+                     (tpacpi_lifecycle == TPACPI_LIFE_RUNNING))) {      \
+                printk(KERN_DEBUG pr_fmt("%s: PID %d: " format),        \
+                       what, task_tgid_vnr(current), ## arg);           \
+        }                                                               \
+} while (0)
 
 /*
  * Quirk handling helpers
@@ -535,15 +528,6 @@ TPACPI_HANDLE(hkey, ec, "\\_SB.HKEY",	/* 600e/x, 770e, 770x */
            "HKEY",              /* all others */
            );                   /* 570 */
 
-TPACPI_HANDLE(vid, root, "\\_SB.PCI.AGP.VGA",   /* 570 */
-           "\\_SB.PCI0.AGP0.VID0",      /* 600e/x, 770x */
-           "\\_SB.PCI0.VID0",   /* 770e */
-           "\\_SB.PCI0.VID",    /* A21e, G4x, R50e, X30, X40 */
-           "\\_SB.PCI0.AGP.VGA",        /* X100e and a few others */
-           "\\_SB.PCI0.AGP.VID",        /* all others */
-           );                           /* R30, R31 */
-
-
 /*************************************************************************
  * ACPI helpers
  */
@@ -563,7 +547,7 @@ static int acpi_evalf(acpi_handle handle,
         int quiet;
 
         if (!*fmt) {
-                printk(TPACPI_ERR "acpi_evalf() called with empty format\n");
+                pr_err("acpi_evalf() called with empty format\n");
                 return 0;
         }
 
@@ -588,7 +572,7 @@ static int acpi_evalf(acpi_handle handle,
                         break;
                         /* add more types as needed */
                 default:
-                        printk(TPACPI_ERR "acpi_evalf() called "
+                        pr_err("acpi_evalf() called "
                                "with invalid format character '%c'\n", c);
                         va_end(ap);
                         return 0;
@@ -617,13 +601,13 @@ static int acpi_evalf(acpi_handle handle,
                 break;
                 /* add more types as needed */
         default:
-                printk(TPACPI_ERR "acpi_evalf() called "
+                pr_err("acpi_evalf() called "
                        "with invalid format character '%c'\n", res_type);
                 return 0;
         }
 
         if (!success && !quiet)
-                printk(TPACPI_ERR "acpi_evalf(%s, %s, ...) failed: %s\n",
+                pr_err("acpi_evalf(%s, %s, ...) failed: %s\n",
                        method, fmt0, acpi_format_exception(status));
 
         return success;
@@ -767,8 +751,7 @@ static int __init setup_acpi_notify(struct ibm_struct *ibm)
 
         rc = acpi_bus_get_device(*ibm->acpi->handle, &ibm->acpi->device);
         if (rc < 0) {
-                printk(TPACPI_ERR "acpi_bus_get_device(%s) failed: %d\n",
-                        ibm->name, rc);
+                pr_err("acpi_bus_get_device(%s) failed: %d\n", ibm->name, rc);
                 return -ENODEV;
         }
 
@@ -781,12 +764,10 @@ static int __init setup_acpi_notify(struct ibm_struct *ibm)
                         ibm->acpi->type, dispatch_acpi_notify, ibm);
         if (ACPI_FAILURE(status)) {
                 if (status == AE_ALREADY_EXISTS) {
-                        printk(TPACPI_NOTICE
-                               "another device driver is already "
-                               "handling %s events\n", ibm->name);
+                        pr_notice("another device driver is already "
+                                  "handling %s events\n", ibm->name);
                 } else {
-                        printk(TPACPI_ERR
-                               "acpi_install_notify_handler(%s) failed: %s\n",
+                        pr_err("acpi_install_notify_handler(%s) failed: %s\n",
                                ibm->name, acpi_format_exception(status));
                 }
                 return -ENODEV;
@@ -811,8 +792,7 @@ static int __init register_tpacpi_subdriver(struct ibm_struct *ibm)
 
         ibm->acpi->driver = kzalloc(sizeof(struct acpi_driver), GFP_KERNEL);
         if (!ibm->acpi->driver) {
-                printk(TPACPI_ERR
-                       "failed to allocate memory for ibm->acpi->driver\n");
+                pr_err("failed to allocate memory for ibm->acpi->driver\n");
                 return -ENOMEM;
         }
 
@@ -823,7 +803,7 @@ static int __init register_tpacpi_subdriver(struct ibm_struct *ibm)
 
         rc = acpi_bus_register_driver(ibm->acpi->driver);
         if (rc < 0) {
-                printk(TPACPI_ERR "acpi_bus_register_driver(%s) failed: %d\n",
+                pr_err("acpi_bus_register_driver(%s) failed: %d\n",
                        ibm->name, rc);
                 kfree(ibm->acpi->driver);
                 ibm->acpi->driver = NULL;
@@ -1081,15 +1061,14 @@ static int parse_strtoul(const char *buf,
 static void tpacpi_disable_brightness_delay(void)
 {
         if (acpi_evalf(hkey_handle, NULL, "PWMS", "qvd", 0))
-                printk(TPACPI_NOTICE
-                        "ACPI backlight control delay disabled\n");
+                pr_notice("ACPI backlight control delay disabled\n");
 }
 
 static void printk_deprecated_attribute(const char * const what,
                                         const char * const details)
 {
         tpacpi_log_usertask("deprecated sysfs attribute");
-        printk(TPACPI_WARN "WARNING: sysfs attribute %s is deprecated and "
+        pr_warn("WARNING: sysfs attribute %s is deprecated and "
                 "will be removed. %s\n",
                 what, details);
 }
@@ -1264,8 +1243,7 @@ static int __init tpacpi_new_rfkill(const enum tpacpi_rfk_id id,
                                                 &tpacpi_rfk_rfkill_ops,
                                                 atp_rfk);
         if (!atp_rfk || !atp_rfk->rfkill) {
-                printk(TPACPI_ERR
-                        "failed to allocate memory for rfkill class\n");
+                pr_err("failed to allocate memory for rfkill class\n");
                 kfree(atp_rfk);
                 return -ENOMEM;
         }
@@ -1275,9 +1253,8 @@ static int __init tpacpi_new_rfkill(const enum tpacpi_rfk_id id,
 
         sw_status = (tp_rfkops->get_status)();
         if (sw_status < 0) {
-                printk(TPACPI_ERR
-                        "failed to read initial state for %s, error %d\n",
-                        name, sw_status);
+                pr_err("failed to read initial state for %s, error %d\n",
+                       name, sw_status);
         } else {
                 sw_state = (sw_status == TPACPI_RFK_RADIO_OFF);
                 if (set_default) {
@@ -1291,9 +1268,7 @@ static int __init tpacpi_new_rfkill(const enum tpacpi_rfk_id id,
 
         res = rfkill_register(atp_rfk->rfkill);
         if (res < 0) {
-                printk(TPACPI_ERR
-                        "failed to register %s rfkill switch: %d\n",
-                        name, res);
+                pr_err("failed to register %s rfkill switch: %d\n", name, res);
                 rfkill_destroy(atp_rfk->rfkill);
                 kfree(atp_rfk);
                 return res;
@@ -1301,7 +1276,7 @@ static int __init tpacpi_new_rfkill(const enum tpacpi_rfk_id id,
 
         tpacpi_rfkill_switches[id] = atp_rfk;
 
-        printk(TPACPI_INFO "rfkill switch %s: radio is %sblocked\n",
+        pr_info("rfkill switch %s: radio is %sblocked\n",
                 name, (sw_state || hw_state) ? "" : "un");
         return 0;
 }
@@ -1825,10 +1800,8 @@ static void __init tpacpi_check_outdated_fw(void)
                  * broken, or really stable to begin with, so it is
                  * best if the user upgrades the firmware anyway.
                  */
-                printk(TPACPI_WARN
-                        "WARNING: Outdated ThinkPad BIOS/EC firmware\n");
-                printk(TPACPI_WARN
-                        "WARNING: This firmware may be missing critical bug "
+                pr_warn("WARNING: Outdated ThinkPad BIOS/EC firmware\n");
+                pr_warn("WARNING: This firmware may be missing critical bug "
                         "fixes and/or important features\n");
         }
 }
@@ -2117,9 +2090,7 @@ void static hotkey_mask_warn_incomplete_mask(void)
                 (hotkey_all_mask | TPACPI_HKEY_NVRAM_KNOWN_MASK);
 
         if (wantedmask)
-                printk(TPACPI_NOTICE
-                        "required events 0x%08x not enabled!\n",
-                        wantedmask);
+                pr_notice("required events 0x%08x not enabled!\n", wantedmask);
 }
 
 /*
@@ -2157,10 +2128,9 @@ static int hotkey_mask_set(u32 mask)
          * a given event.
          */
         if (!hotkey_mask_get() && !rc && (fwmask & ~hotkey_acpi_mask)) {
-                printk(TPACPI_NOTICE
-                       "asked for hotkey mask 0x%08x, but "
-                       "firmware forced it to 0x%08x\n",
-                       fwmask, hotkey_acpi_mask);
+                pr_notice("asked for hotkey mask 0x%08x, but "
+                          "firmware forced it to 0x%08x\n",
+                          fwmask, hotkey_acpi_mask);
         }
 
         if (tpacpi_lifecycle != TPACPI_LIFE_EXITING)
@@ -2184,13 +2154,11 @@ static int hotkey_user_mask_set(const u32 mask)
             (mask == 0xffff || mask == 0xffffff ||
              mask == 0xffffffff)) {
                 tp_warned.hotkey_mask_ff = 1;
-                printk(TPACPI_NOTICE
-                       "setting the hotkey mask to 0x%08x is likely "
-                       "not the best way to go about it\n", mask);
-                printk(TPACPI_NOTICE
-                       "please consider using the driver defaults, "
-                       "and refer to up-to-date thinkpad-acpi "
-                       "documentation\n");
+                pr_notice("setting the hotkey mask to 0x%08x is likely "
+                          "not the best way to go about it\n", mask);
+                pr_notice("please consider using the driver defaults, "
+                          "and refer to up-to-date thinkpad-acpi "
+                          "documentation\n");
         }
 
         /* Try to enable what the user asked for, plus whatever we need.
@@ -2574,8 +2542,7 @@ static void hotkey_poll_setup(const bool may_warn)
                                         NULL, TPACPI_NVRAM_KTHREAD_NAME);
                         if (IS_ERR(tpacpi_hotkey_task)) {
                                 tpacpi_hotkey_task = NULL;
-                                printk(TPACPI_ERR
-                                       "could not create kernel thread "
+                                pr_err("could not create kernel thread "
                                        "for hotkey polling\n");
                         }
                 }
@@ -2583,11 +2550,10 @@ static void hotkey_poll_setup(const bool may_warn)
                 hotkey_poll_stop_sync();
                 if (may_warn && (poll_driver_mask || poll_user_mask) &&
                     hotkey_poll_freq == 0) {
-                        printk(TPACPI_NOTICE
-                                "hot keys 0x%08x and/or events 0x%08x "
-                                "require polling, which is currently "
-                                "disabled\n",
-                                poll_user_mask, poll_driver_mask);
+                        pr_notice("hot keys 0x%08x and/or events 0x%08x "
+                                  "require polling, which is currently "
+                                  "disabled\n",
+                                  poll_user_mask, poll_driver_mask);
                 }
         }
 }
@@ -2811,13 +2777,13 @@ static ssize_t hotkey_source_mask_store(struct device *dev,
         mutex_unlock(&hotkey_mutex);
 
         if (rc < 0)
-                printk(TPACPI_ERR "hotkey_source_mask: failed to update the"
-                        "firmware event mask!\n");
+                pr_err("hotkey_source_mask: "
+                       "failed to update the firmware event mask!\n");
 
         if (r_ev)
-                printk(TPACPI_NOTICE "hotkey_source_mask: "
-                        "some important events were disabled: "
-                        "0x%04x\n", r_ev);
+                pr_notice("hotkey_source_mask: "
+                          "some important events were disabled: 0x%04x\n",
+                          r_ev);
 
         tpacpi_disclose_usertask("hotkey_source_mask", "set to 0x%08lx\n", t);
 
@@ -3048,8 +3014,7 @@ static void hotkey_exit(void)
         if (((tp_features.hotkey_mask &&
               hotkey_mask_set(hotkey_orig_mask)) |
              hotkey_status_set(false)) != 0)
-                printk(TPACPI_ERR
-                       "failed to restore hot key mask "
+                pr_err("failed to restore hot key mask "
                        "to BIOS defaults\n");
 }
 
@@ -3288,10 +3253,9 @@ static int __init hotkey_init(struct ibm_init_struct *iibm)
            for HKEY interface version 0x100 */
         if (acpi_evalf(hkey_handle, &hkeyv, "MHKV", "qd")) {
                 if ((hkeyv >> 8) != 1) {
-                        printk(TPACPI_ERR "unknown version of the "
-                               "HKEY interface: 0x%x\n", hkeyv);
-                        printk(TPACPI_ERR "please report this to %s\n",
-                               TPACPI_MAIL);
+                        pr_err("unknown version of the HKEY interface: 0x%x\n",
+                               hkeyv);
+                        pr_err("please report this to %s\n", TPACPI_MAIL);
                 } else {
                         /*
                          * MHKV 0x100 in A31, R40, R40e,
@@ -3304,8 +3268,7 @@ static int __init hotkey_init(struct ibm_init_struct *iibm)
                         /* Paranoia check AND init hotkey_all_mask */
                         if (!acpi_evalf(hkey_handle, &hotkey_all_mask,
                                         "MHKA", "qd")) {
-                                printk(TPACPI_ERR
-                                       "missing MHKA handler, "
+                                pr_err("missing MHKA handler, "
                                        "please report this to %s\n",
                                        TPACPI_MAIL);
                                 /* Fallback: pre-init for FN+F3,F4,F12 */
@@ -3343,16 +3306,14 @@ static int __init hotkey_init(struct ibm_init_struct *iibm)
         if (dbg_wlswemul) {
                 tp_features.hotkey_wlsw = 1;
                 radiosw_state = !!tpacpi_wlsw_emulstate;
-                printk(TPACPI_INFO
-                        "radio switch emulation enabled\n");
+                pr_info("radio switch emulation enabled\n");
         } else
 #endif
         /* Not all thinkpads have a hardware radio switch */
         if (acpi_evalf(hkey_handle, &status, "WLSW", "qd")) {
                 tp_features.hotkey_wlsw = 1;
                 radiosw_state = !!status;
-                printk(TPACPI_INFO
-                        "radio switch found; radios are %s\n",
+                pr_info("radio switch found; radios are %s\n",
                         enabled(status, 0));
         }
         if (tp_features.hotkey_wlsw)
@@ -3363,8 +3324,7 @@ static int __init hotkey_init(struct ibm_init_struct *iibm)
         if (!res && acpi_evalf(hkey_handle, &status, "MHKG", "qd")) {
                 tp_features.hotkey_tablet = 1;
                 tabletsw_state = !!(status & TP_HOTKEY_TABLET_MASK);
-                printk(TPACPI_INFO
-                        "possible tablet mode switch found; "
+                pr_info("possible tablet mode switch found; "
                         "ThinkPad in %s mode\n",
                         (tabletsw_state) ? "tablet" : "laptop");
                 res = add_to_attr_set(hotkey_dev_attributes,
@@ -3382,8 +3342,7 @@ static int __init hotkey_init(struct ibm_init_struct *iibm)
         hotkey_keycode_map = kmalloc(TPACPI_HOTKEY_MAP_SIZE,
                                         GFP_KERNEL);
         if (!hotkey_keycode_map) {
-                printk(TPACPI_ERR
-                        "failed to allocate memory for key map\n");
+                pr_err("failed to allocate memory for key map\n");
                 res = -ENOMEM;
                 goto err_exit;
         }
@@ -3426,13 +3385,11 @@ static int __init hotkey_init(struct ibm_init_struct *iibm)
          * userspace. tpacpi_detect_brightness_capabilities() must have
          * been called before this point  */
         if (tp_features.bright_acpimode && acpi_video_backlight_support()) {
-                printk(TPACPI_INFO
-                       "This ThinkPad has standard ACPI backlight "
-                       "brightness control, supported by the ACPI "
-                       "video driver\n");
-                printk(TPACPI_NOTICE
-                       "Disabling thinkpad-acpi brightness events "
-                       "by default...\n");
+                pr_info("This ThinkPad has standard ACPI backlight "
+                        "brightness control, supported by the ACPI "
+                        "video driver\n");
+                pr_notice("Disabling thinkpad-acpi brightness events "
+                          "by default...\n");
 
                 /* Disable brightness up/down on Lenovo thinkpads when
                  * ACPI is handling them, otherwise it is plain impossible
@@ -3539,8 +3496,7 @@ static bool hotkey_notify_wakeup(const u32 hkey,
 
         case TP_HKEY_EV_WKUP_S3_BATLOW: /* Battery on critical low level/S3 */
         case TP_HKEY_EV_WKUP_S4_BATLOW: /* Battery on critical low level/S4 */
-                printk(TPACPI_ALERT
-                        "EMERGENCY WAKEUP: battery almost empty\n");
+                pr_alert("EMERGENCY WAKEUP: battery almost empty\n");
                 /* how to auto-heal: */
                 /* 2313: woke up from S3, go to S4/S5 */
                 /* 2413: woke up from S4, go to S5 */
@@ -3551,9 +3507,7 @@ static bool hotkey_notify_wakeup(const u32 hkey,
         }
 
         if (hotkey_wakeup_reason != TP_ACPI_WAKEUP_NONE) {
-                printk(TPACPI_INFO
-                       "woke up due to a hot-unplug "
-                       "request...\n");
+                pr_info("woke up due to a hot-unplug request...\n");
                 hotkey_wakeup_reason_notify_change();
         }
         return true;
@@ -3605,37 +3559,31 @@ static bool hotkey_notify_thermal(const u32 hkey,
 
         switch (hkey) {
         case TP_HKEY_EV_THM_TABLE_CHANGED:
-                printk(TPACPI_INFO
-                        "EC reports that Thermal Table has changed\n");
+                pr_info("EC reports that Thermal Table has changed\n");
                 /* recommended action: do nothing, we don't have
                  * Lenovo ATM information */
                 return true;
         case TP_HKEY_EV_ALARM_BAT_HOT:
-                printk(TPACPI_CRIT
-                        "THERMAL ALARM: battery is too hot!\n");
+                pr_crit("THERMAL ALARM: battery is too hot!\n");
                 /* recommended action: warn user through gui */
                 break;
         case TP_HKEY_EV_ALARM_BAT_XHOT:
-                printk(TPACPI_ALERT
-                        "THERMAL EMERGENCY: battery is extremely hot!\n");
+                pr_alert("THERMAL EMERGENCY: battery is extremely hot!\n");
                 /* recommended action: immediate sleep/hibernate */
                 break;
         case TP_HKEY_EV_ALARM_SENSOR_HOT:
-                printk(TPACPI_CRIT
-                        "THERMAL ALARM: "
+                pr_crit("THERMAL ALARM: "
                         "a sensor reports something is too hot!\n");
                 /* recommended action: warn user through gui, that */
                 /* some internal component is too hot */
                 break;
         case TP_HKEY_EV_ALARM_SENSOR_XHOT:
-                printk(TPACPI_ALERT
-                        "THERMAL EMERGENCY: "
-                        "a sensor reports something is extremely hot!\n");
+                pr_alert("THERMAL EMERGENCY: "
+                         "a sensor reports something is extremely hot!\n");
                 /* recommended action: immediate sleep/hibernate */
                 break;
         default:
-                printk(TPACPI_ALERT
-                         "THERMAL ALERT: unknown thermal alarm received\n");
+                pr_alert("THERMAL ALERT: unknown thermal alarm received\n");
                 known = false;
         }
 
@@ -3652,8 +3600,7 @@ static void hotkey_notify(struct ibm_struct *ibm, u32 event)
         bool known_ev;
 
         if (event != 0x80) {
-                printk(TPACPI_ERR
-                       "unknown HKEY notification event %d\n", event);
+                pr_err("unknown HKEY notification event %d\n", event);
                 /* forward it to userspace, maybe it knows how to handle it */
                 acpi_bus_generate_netlink_event(
                                         ibm->acpi->device->pnp.device_class,
@@ -3664,7 +3611,7 @@ static void hotkey_notify(struct ibm_struct *ibm, u32 event)
 
         while (1) {
                 if (!acpi_evalf(hkey_handle, &hkey, "MHKP", "d")) {
-                        printk(TPACPI_ERR "failed to retrieve HKEY event\n");
+                        pr_err("failed to retrieve HKEY event\n");
                         return;
                 }
 
@@ -3692,8 +3639,7 @@ static void hotkey_notify(struct ibm_struct *ibm, u32 event)
                         switch (hkey) {
                         case TP_HKEY_EV_BAYEJ_ACK:
                                 hotkey_autosleep_ack = 1;
-                                printk(TPACPI_INFO
-                                       "bay ejected\n");
+                                pr_info("bay ejected\n");
                                 hotkey_wakeup_hotunplug_complete_notify_change();
                                 known_ev = true;
                                 break;
@@ -3709,8 +3655,7 @@ static void hotkey_notify(struct ibm_struct *ibm, u32 event)
                         /* 0x4000-0x4FFF: dock-related wakeups */
                         if (hkey == TP_HKEY_EV_UNDOCK_ACK) {
                                 hotkey_autosleep_ack = 1;
-                                printk(TPACPI_INFO
-                                       "undocked\n");
+                                pr_info("undocked\n");
                                 hotkey_wakeup_hotunplug_complete_notify_change();
                                 known_ev = true;
                         } else {
@@ -3741,11 +3686,9 @@ static void hotkey_notify(struct ibm_struct *ibm, u32 event)
                         known_ev = false;
                 }
                 if (!known_ev) {
-                        printk(TPACPI_NOTICE
-                               "unhandled HKEY event 0x%04x\n", hkey);
-                        printk(TPACPI_NOTICE
-                               "please report the conditions when this "
-                               "event happened to %s\n", TPACPI_MAIL);
+                        pr_notice("unhandled HKEY event 0x%04x\n", hkey);
+                        pr_notice("please report the conditions when this "
+                                  "event happened to %s\n", TPACPI_MAIL);
                 }
 
                 /* Legacy events */
@@ -3778,8 +3721,7 @@ static void hotkey_resume(void)
 
         if (hotkey_status_set(true) < 0 ||
             hotkey_mask_set(hotkey_acpi_mask) < 0)
-                printk(TPACPI_ERR
-                       "error while attempting to reset the event "
+                pr_err("error while attempting to reset the event "
                        "firmware interface\n");
 
         tpacpi_send_radiosw_update();
@@ -3824,14 +3766,12 @@ static void hotkey_enabledisable_warn(bool enable)
 {
         tpacpi_log_usertask("procfs hotkey enable/disable");
         if (!WARN((tpacpi_lifecycle == TPACPI_LIFE_RUNNING || !enable),
-                        TPACPI_WARN
-                        "hotkey enable/disable functionality has been "
-                        "removed from the driver.  Hotkeys are always "
-                        "enabled\n"))
-                printk(TPACPI_ERR
-                        "Please remove the hotkey=enable module "
-                        "parameter, it is deprecated.  Hotkeys are always "
-                        "enabled\n");
+                  pr_fmt("hotkey enable/disable functionality has been "
+                         "removed from the driver.  "
+                         "Hotkeys are always enabled.\n")))
+                pr_err("Please remove the hotkey=enable module "
+                       "parameter, it is deprecated.  "
+                       "Hotkeys are always enabled.\n");
 }
 
 static int hotkey_write(char *buf)
@@ -4011,8 +3951,7 @@ static void bluetooth_shutdown(void)
         /* Order firmware to save current state to NVRAM */
         if (!acpi_evalf(NULL, NULL, "\\BLTH", "vd",
                         TP_ACPI_BLTH_SAVE_STATE))
-                printk(TPACPI_NOTICE
-                        "failed to save bluetooth state to NVRAM\n");
+                pr_notice("failed to save bluetooth state to NVRAM\n");
         else
                 vdbg_printk(TPACPI_DBG_RFKILL,
                         "bluestooth state saved to NVRAM\n");
@@ -4051,8 +3990,7 @@ static int __init bluetooth_init(struct ibm_init_struct *iibm)
 #ifdef CONFIG_THINKPAD_ACPI_DEBUGFACILITIES
         if (dbg_bluetoothemul) {
                 tp_features.bluetooth = 1;
-                printk(TPACPI_INFO
-                        "bluetooth switch emulation enabled\n");
+                pr_info("bluetooth switch emulation enabled\n");
         } else
 #endif
         if (tp_features.bluetooth &&
@@ -4203,8 +4141,7 @@ static void wan_shutdown(void)
         /* Order firmware to save current state to NVRAM */
         if (!acpi_evalf(NULL, NULL, "\\WGSV", "vd",
                         TP_ACPI_WGSV_SAVE_STATE))
-                printk(TPACPI_NOTICE
-                        "failed to save WWAN state to NVRAM\n");
+                pr_notice("failed to save WWAN state to NVRAM\n");
         else
                 vdbg_printk(TPACPI_DBG_RFKILL,
                         "WWAN state saved to NVRAM\n");
@@ -4241,8 +4178,7 @@ static int __init wan_init(struct ibm_init_struct *iibm)
 #ifdef CONFIG_THINKPAD_ACPI_DEBUGFACILITIES
         if (dbg_wwanemul) {
                 tp_features.wan = 1;
-                printk(TPACPI_INFO
-                        "wwan switch emulation enabled\n");
+                pr_info("wwan switch emulation enabled\n");
         } else
 #endif
         if (tp_features.wan &&
@@ -4382,8 +4318,7 @@ static int __init uwb_init(struct ibm_init_struct *iibm)
 #ifdef CONFIG_THINKPAD_ACPI_DEBUGFACILITIES
         if (dbg_uwbemul) {
                 tp_features.uwb = 1;
-                printk(TPACPI_INFO
-                        "uwb switch emulation enabled\n");
+                pr_info("uwb switch emulation enabled\n");
         } else
 #endif
         if (tp_features.uwb &&
@@ -4444,6 +4379,15 @@ static int video_orig_autosw;
 static int video_autosw_get(void);
 static int video_autosw_set(int enable);
 
+TPACPI_HANDLE(vid, root,
+              "\\_SB.PCI.AGP.VGA",      /* 570 */
+              "\\_SB.PCI0.AGP0.VID0",   /* 600e/x, 770x */
+              "\\_SB.PCI0.VID0",        /* 770e */
+              "\\_SB.PCI0.VID",         /* A21e, G4x, R50e, X30, X40 */
+              "\\_SB.PCI0.AGP.VGA",     /* X100e and a few others */
+              "\\_SB.PCI0.AGP.VID",     /* all others */
+        );                              /* R30, R31 */
+
 TPACPI_HANDLE(vid2, root, "\\_SB.PCI0.AGPB.VID");       /* G41 */
 
 static int __init video_init(struct ibm_init_struct *iibm)
@@ -4487,7 +4431,7 @@ static void video_exit(void)
         dbg_printk(TPACPI_DBG_EXIT,
                    "restoring original video autoswitch mode\n");
         if (video_autosw_set(video_orig_autosw))
-                printk(TPACPI_ERR "error while trying to restore original "
+                pr_err("error while trying to restore original "
                         "video autoswitch mode\n");
 }
 
@@ -4560,8 +4504,7 @@ static int video_outputsw_set(int status)
                 res = acpi_evalf(vid_handle, NULL,
                                  "ASWT", "vdd", status * 0x100, 0);
                 if (!autosw && video_autosw_set(autosw)) {
-                        printk(TPACPI_ERR
-                               "video auto-switch left enabled due to error\n");
+                        pr_err("video auto-switch left enabled due to error\n");
                         return -EIO;
                 }
                 break;
@@ -4630,8 +4573,7 @@ static int video_outputsw_cycle(void)
                 return -ENOSYS;
         }
         if (!autosw && video_autosw_set(autosw)) {
-                printk(TPACPI_ERR
-                       "video auto-switch left enabled due to error\n");
+                pr_err("video auto-switch left enabled due to error\n");
                 return -EIO;
         }
 
@@ -5348,7 +5290,7 @@ static int __init led_init(struct ibm_init_struct *iibm)
         tpacpi_leds = kzalloc(sizeof(*tpacpi_leds) * TPACPI_LED_NUMLEDS,
                               GFP_KERNEL);
         if (!tpacpi_leds) {
-                printk(TPACPI_ERR "Out of memory for LED data\n");
+                pr_err("Out of memory for LED data\n");
                 return -ENOMEM;
         }
 
@@ -5367,9 +5309,8 @@ static int __init led_init(struct ibm_init_struct *iibm)
         }
 
 #ifdef CONFIG_THINKPAD_ACPI_UNSAFE_LEDS
-        printk(TPACPI_NOTICE
-                "warning: userspace override of important "
-                "firmware LEDs is enabled\n");
+        pr_notice("warning: userspace override of important "
+                  "firmware LEDs is enabled\n");
 #endif
         return 0;
 }
@@ -5639,17 +5580,16 @@ static void thermal_dump_all_sensors(void)
         if (n <= 0)
                 return;
 
-        printk(TPACPI_NOTICE
-                "temperatures (Celsius):");
+        pr_notice("temperatures (Celsius):");
 
         for (i = 0; i < n; i++) {
                 if (t.temp[i] != TPACPI_THERMAL_SENSOR_NA)
-                        printk(KERN_CONT " %d", (int)(t.temp[i] / 1000));
+                        pr_cont(" %d", (int)(t.temp[i] / 1000));
                 else
-                        printk(KERN_CONT " N/A");
+                        pr_cont(" N/A");
         }
 
-        printk(KERN_CONT "\n");
+        pr_cont("\n");
 }
 
 /* sysfs temp##_input -------------------------------------------------- */
@@ -5769,14 +5709,12 @@ static int __init thermal_init(struct ibm_init_struct *iibm)
                 if (ta1 == 0) {
                         /* This is sheer paranoia, but we handle it anyway */
                         if (acpi_tmp7) {
-                                printk(TPACPI_ERR
-                                       "ThinkPad ACPI EC access misbehaving, "
+                                pr_err("ThinkPad ACPI EC access misbehaving, "
                                        "falling back to ACPI TMPx access "
                                        "mode\n");
                                 thermal_read_mode = TPACPI_THERMAL_ACPI_TMP07;
                         } else {
-                                printk(TPACPI_ERR
-                                       "ThinkPad ACPI EC access misbehaving, "
+                                pr_err("ThinkPad ACPI EC access misbehaving, "
                                        "disabling thermal sensors access\n");
                                 thermal_read_mode = TPACPI_THERMAL_NONE;
                         }
@@ -6129,8 +6067,8 @@ static int __init tpacpi_query_bcl_levels(acpi_handle handle)
         if (ACPI_SUCCESS(acpi_evaluate_object(handle, "_BCL", NULL, &buffer))) {
                 obj = (union acpi_object *)buffer.pointer;
                 if (!obj || (obj->type != ACPI_TYPE_PACKAGE)) {
-                        printk(TPACPI_ERR "Unknown _BCL data, "
-                               "please report this to %s\n", TPACPI_MAIL);
+                        pr_err("Unknown _BCL data, please report this to %s\n",
+                               TPACPI_MAIL);
                         rc = 0;
                 } else {
                         rc = obj->package.count;
@@ -6214,18 +6152,15 @@ static void __init tpacpi_detect_brightness_capabilities(void)
         switch (b) {
         case 16:
                 bright_maxlvl = 15;
-                printk(TPACPI_INFO
-                       "detected a 16-level brightness capable ThinkPad\n");
+                pr_info("detected a 16-level brightness capable ThinkPad\n");
                 break;
         case 8:
         case 0:
                 bright_maxlvl = 7;
-                printk(TPACPI_INFO
-                       "detected a 8-level brightness capable ThinkPad\n");
+                pr_info("detected a 8-level brightness capable ThinkPad\n");
                 break;
         default:
-                printk(TPACPI_ERR
-                       "Unsupported brightness interface, "
+                pr_err("Unsupported brightness interface, "
                        "please contact %s\n", TPACPI_MAIL);
                 tp_features.bright_unkfw = 1;
                 bright_maxlvl = b - 1;
@@ -6260,22 +6195,19 @@ static int __init brightness_init(struct ibm_init_struct *iibm)
 
         if (acpi_video_backlight_support()) {
                 if (brightness_enable > 1) {
-                        printk(TPACPI_INFO
-                               "Standard ACPI backlight interface "
-                               "available, not loading native one.\n");
+                        pr_info("Standard ACPI backlight interface "
+                                "available, not loading native one\n");
                         return 1;
                 } else if (brightness_enable == 1) {
-                        printk(TPACPI_WARN
-                                "Cannot enable backlight brightness support, "
+                        pr_warn("Cannot enable backlight brightness support, "
                                 "ACPI is already handling it.  Refer to the "
-                                "acpi_backlight kernel parameter\n");
+                                "acpi_backlight kernel parameter.\n");
                         return 1;
                 }
         } else if (tp_features.bright_acpimode && brightness_enable > 1) {
-                printk(TPACPI_NOTICE
-                        "Standard ACPI backlight interface not "
-                        "available, thinkpad_acpi native "
-                        "brightness control enabled\n");
+                pr_notice("Standard ACPI backlight interface not "
+                          "available, thinkpad_acpi native "
+                          "brightness control enabled\n");
         }
 
         /*
@@ -6319,19 +6251,17 @@ static int __init brightness_init(struct ibm_init_struct *iibm)
         if (IS_ERR(ibm_backlight_device)) {
                 int rc = PTR_ERR(ibm_backlight_device);
                 ibm_backlight_device = NULL;
-                printk(TPACPI_ERR "Could not register backlight device\n");
+                pr_err("Could not register backlight device\n");
                 return rc;
         }
         vdbg_printk(TPACPI_DBG_INIT | TPACPI_DBG_BRGHT,
                         "brightness is supported\n");
 
         if (quirks & TPACPI_BRGHT_Q_ASK) {
-                printk(TPACPI_NOTICE
-                        "brightness: will use unverified default: "
-                        "brightness_mode=%d\n", brightness_mode);
-                printk(TPACPI_NOTICE
-                        "brightness: please report to %s whether it works well "
-                        "or not on your ThinkPad\n", TPACPI_MAIL);
+                pr_notice("brightness: will use unverified default: "
+                          "brightness_mode=%d\n", brightness_mode);
+                pr_notice("brightness: please report to %s whether it works well "
+                          "or not on your ThinkPad\n", TPACPI_MAIL);
         }
 
         /* Added by mistake in early 2007.  Probably useless, but it could
@@ -6804,8 +6734,7 @@ static int __init volume_create_alsa_mixer(void)
         rc = snd_card_create(alsa_index, alsa_id, THIS_MODULE,
                             sizeof(struct tpacpi_alsa_data), &card);
         if (rc < 0 || !card) {
-                printk(TPACPI_ERR
-                        "Failed to create ALSA card structures: %d\n", rc);
+                pr_err("Failed to create ALSA card structures: %d\n", rc);
                 return 1;
         }
 
@@ -6839,9 +6768,8 @@ static int __init volume_create_alsa_mixer(void)
                 ctl_vol = snd_ctl_new1(&volume_alsa_control_vol, NULL);
                 rc = snd_ctl_add(card, ctl_vol);
                 if (rc < 0) {
-                        printk(TPACPI_ERR
-                                "Failed to create ALSA volume control: %d\n",
-                                rc);
+                        pr_err("Failed to create ALSA volume control: %d\n",
+                               rc);
                         goto err_exit;
                 }
                 data->ctl_vol_id = &ctl_vol->id;
@@ -6850,8 +6778,7 @@ static int __init volume_create_alsa_mixer(void)
         ctl_mute = snd_ctl_new1(&volume_alsa_control_mute, NULL);
         rc = snd_ctl_add(card, ctl_mute);
         if (rc < 0) {
-                printk(TPACPI_ERR "Failed to create ALSA mute control: %d\n",
-                        rc);
+                pr_err("Failed to create ALSA mute control: %d\n", rc);
                 goto err_exit;
         }
         data->ctl_mute_id = &ctl_mute->id;
@@ -6859,7 +6786,7 @@ static int __init volume_create_alsa_mixer(void)
         snd_card_set_dev(card, &tpacpi_pdev->dev);
         rc = snd_card_register(card);
         if (rc < 0) {
-                printk(TPACPI_ERR "Failed to register ALSA card: %d\n", rc);
+                pr_err("Failed to register ALSA card: %d\n", rc);
                 goto err_exit;
         }
 
@@ -6915,9 +6842,8 @@ static int __init volume_init(struct ibm_init_struct *iibm)
                 return -EINVAL;
 
         if (volume_mode == TPACPI_VOL_MODE_UCMS_STEP) {
-                printk(TPACPI_ERR
-                        "UCMS step volume mode not implemented, "
-                        "please contact %s\n", TPACPI_MAIL);
+                pr_err("UCMS step volume mode not implemented, "
+                       "please contact %s\n", TPACPI_MAIL);
                 return 1;
         }
 
@@ -6981,13 +6907,11 @@ static int __init volume_init(struct ibm_init_struct *iibm)
 
         rc = volume_create_alsa_mixer();
         if (rc) {
-                printk(TPACPI_ERR
-                        "Could not create the ALSA mixer interface\n");
+                pr_err("Could not create the ALSA mixer interface\n");
                 return rc;
         }
 
-        printk(TPACPI_INFO
-                "Console audio control enabled, mode: %s\n",
+        pr_info("Console audio control enabled, mode: %s\n",
                 (volume_control_allowed) ?
                         "override (read/write)" :
                         "monitor (read only)");
@@ -7049,12 +6973,10 @@ static int volume_write(char *buf)
         if (!volume_control_allowed && tpacpi_lifecycle != TPACPI_LIFE_INIT) {
                 if (unlikely(!tp_warned.volume_ctrl_forbidden)) {
                         tp_warned.volume_ctrl_forbidden = 1;
-                        printk(TPACPI_NOTICE
-                                "Console audio control in monitor mode, "
-                                "changes are not allowed.\n");
-                        printk(TPACPI_NOTICE
-                                "Use the volume_control=1 module parameter "
-                                "to enable volume control\n");
+                        pr_notice("Console audio control in monitor mode, "
+                                  "changes are not allowed\n");
+                        pr_notice("Use the volume_control=1 module parameter "
+                                  "to enable volume control\n");
                 }
                 return -EPERM;
         }
@@ -7129,8 +7051,7 @@ static void inline volume_alsa_notify_change(void)
 
 static int __init volume_init(struct ibm_init_struct *iibm)
 {
-        printk(TPACPI_INFO
-                "volume: disabled as there is no ALSA support in this kernel\n");
+        pr_info("volume: disabled as there is no ALSA support in this kernel\n");
 
         return 1;
 }
@@ -7337,9 +7258,8 @@ TPACPI_HANDLE(sfan, ec, "SFAN",	/* 570 */
 static void fan_quirk1_setup(void)
 {
         if (fan_control_initial_status == 0x07) {
-                printk(TPACPI_NOTICE
-                       "fan_init: initial fan status is unknown, "
-                       "assuming it is in auto mode\n");
+                pr_notice("fan_init: initial fan status is unknown, "
+                          "assuming it is in auto mode\n");
                 tp_features.fan_ctrl_status_undef = 1;
         }
 }
@@ -7726,8 +7646,7 @@ static void fan_watchdog_reset(void)
                 if (!queue_delayed_work(tpacpi_wq, &fan_watchdog_task,
                                 msecs_to_jiffies(fan_watchdog_maxinterval
                                                  * 1000))) {
-                        printk(TPACPI_ERR
-                               "failed to queue the fan watchdog, "
+                        pr_err("failed to queue the fan watchdog, "
                                "watchdog will not trigger\n");
                 }
         } else
@@ -7741,11 +7660,11 @@ static void fan_watchdog_fire(struct work_struct *ignored)
         if (tpacpi_lifecycle != TPACPI_LIFE_RUNNING)
                 return;
 
-        printk(TPACPI_NOTICE "fan watchdog: enabling fan\n");
+        pr_notice("fan watchdog: enabling fan\n");
         rc = fan_set_enable();
         if (rc < 0) {
-                printk(TPACPI_ERR "fan watchdog: error %d while enabling fan, "
-                        "will try again later...\n", -rc);
+                pr_err("fan watchdog: error %d while enabling fan, "
+                       "will try again later...\n", -rc);
                 /* reschedule for later */
                 fan_watchdog_reset();
         }
@@ -8049,8 +7968,7 @@ static int __init fan_init(struct ibm_init_struct *iibm)
                                         "secondary fan support enabled\n");
                         }
                 } else {
-                        printk(TPACPI_ERR
-                               "ThinkPad ACPI EC access misbehaving, "
+                        pr_err("ThinkPad ACPI EC access misbehaving, "
                                "fan status and control unavailable\n");
                         return 1;
                 }
@@ -8150,9 +8068,8 @@ static void fan_suspend(pm_message_t state)
         fan_control_resume_level = 0;
         rc = fan_get_status_safe(&fan_control_resume_level);
         if (rc < 0)
-                printk(TPACPI_NOTICE
-                        "failed to read fan level for later "
-                        "restore during resume: %d\n", rc);
+                pr_notice("failed to read fan level for later "
+                          "restore during resume: %d\n", rc);
 
         /* if it is undefined, don't attempt to restore it.
          * KEEP THIS LAST */
@@ -8207,13 +8124,11 @@ static void fan_resume(void)
                 return;
         }
         if (do_set) {
-                printk(TPACPI_NOTICE
-                        "restoring fan level to 0x%02x\n",
-                        fan_control_resume_level);
+                pr_notice("restoring fan level to 0x%02x\n",
+                          fan_control_resume_level);
                 rc = fan_set_level_safe(fan_control_resume_level);
                 if (rc < 0)
-                        printk(TPACPI_NOTICE
-                                "failed to restore fan level: %d\n", rc);
+                        pr_notice("failed to restore fan level: %d\n", rc);
         }
 }
 
@@ -8305,8 +8220,8 @@ static int fan_write_cmd_level(const char *cmd, int *rc)
 
         *rc = fan_set_level_safe(level);
         if (*rc == -ENXIO)
-                printk(TPACPI_ERR "level command accepted for unsupported "
-                       "access mode %d", fan_control_access_mode);
+                pr_err("level command accepted for unsupported access mode %d\n",
+                       fan_control_access_mode);
         else if (!*rc)
                 tpacpi_disclose_usertask("procfs fan",
                         "set level to %d\n", level);
@@ -8321,8 +8236,8 @@ static int fan_write_cmd_enable(const char *cmd, int *rc)
 
         *rc = fan_set_enable();
         if (*rc == -ENXIO)
-                printk(TPACPI_ERR "enable command accepted for unsupported "
-                       "access mode %d", fan_control_access_mode);
+                pr_err("enable command accepted for unsupported access mode %d\n",
+                       fan_control_access_mode);
         else if (!*rc)
                 tpacpi_disclose_usertask("procfs fan", "enable\n");
 
@@ -8336,8 +8251,8 @@ static int fan_write_cmd_disable(const char *cmd, int *rc)
 
         *rc = fan_set_disable();
         if (*rc == -ENXIO)
-                printk(TPACPI_ERR "disable command accepted for unsupported "
-                       "access mode %d", fan_control_access_mode);
+                pr_err("disable command accepted for unsupported access mode %d\n",
+                       fan_control_access_mode);
         else if (!*rc)
                 tpacpi_disclose_usertask("procfs fan", "disable\n");
 
@@ -8356,8 +8271,8 @@ static int fan_write_cmd_speed(const char *cmd, int *rc)
 
         *rc = fan_set_speed(speed);
         if (*rc == -ENXIO)
-                printk(TPACPI_ERR "speed command accepted for unsupported "
-                       "access mode %d", fan_control_access_mode);
+                pr_err("speed command accepted for unsupported access mode %d\n",
+                       fan_control_access_mode);
         else if (!*rc)
                 tpacpi_disclose_usertask("procfs fan",
                         "set speed to %d\n", speed);
@@ -8560,8 +8475,8 @@ static int __init ibm_init(struct ibm_init_struct *iibm)
                 if (ibm->acpi->notify) {
                         ret = setup_acpi_notify(ibm);
                         if (ret == -ENODEV) {
-                                printk(TPACPI_NOTICE "disabling subdriver %s\n",
-                                        ibm->name);
+                                pr_notice("disabling subdriver %s\n",
+                                          ibm->name);
                                 ret = 0;
                                 goto err_out;
                         }
@@ -8583,8 +8498,7 @@ static int __init ibm_init(struct ibm_init_struct *iibm)
                 entry = proc_create_data(ibm->name, mode, proc_dir,
                                          &dispatch_proc_fops, ibm);
                 if (!entry) {
-                        printk(TPACPI_ERR "unable to create proc entry %s\n",
-                               ibm->name);
+                        pr_err("unable to create proc entry %s\n", ibm->name);
                         ret = -ENODEV;
                         goto err_out;
                 }
@@ -8683,13 +8597,11 @@ static int __must_check __init get_thinkpad_model_data(
                                 tp->ec_release = (ec_fw_string[4] << 8)
                                                 | ec_fw_string[5];
                         } else {
-                                printk(TPACPI_NOTICE
-                                        "ThinkPad firmware release %s "
-                                        "doesn't match the known patterns\n",
-                                        ec_fw_string);
-                                printk(TPACPI_NOTICE
-                                        "please report this to %s\n",
-                                        TPACPI_MAIL);
+                                pr_notice("ThinkPad firmware release %s "
+                                          "doesn't match the known patterns\n",
+                                          ec_fw_string);
+                                pr_notice("please report this to %s\n",
+                                          TPACPI_MAIL);
                         }
                         break;
                 }
@@ -8733,8 +8645,7 @@ static int __init probe_for_thinkpad(void)
         tpacpi_acpi_handle_locate("ec", TPACPI_ACPI_EC_HID, &ec_handle);
         if (!ec_handle) {
                 if (is_thinkpad)
-                        printk(TPACPI_ERR
-                                "Not yet supported ThinkPad detected!\n");
+                        pr_err("Not yet supported ThinkPad detected!\n");
                 return -ENODEV;
         }
 
@@ -8746,10 +8657,10 @@ static int __init probe_for_thinkpad(void)
 
 static void __init thinkpad_acpi_init_banner(void)
 {
-        printk(TPACPI_INFO "%s v%s\n", TPACPI_DESC, TPACPI_VERSION);
-        printk(TPACPI_INFO "%s\n", TPACPI_URL);
+        pr_info("%s v%s\n", TPACPI_DESC, TPACPI_VERSION);
+        pr_info("%s\n", TPACPI_URL);
 
-        printk(TPACPI_INFO "ThinkPad BIOS %s, EC %s\n",
+        pr_info("ThinkPad BIOS %s, EC %s\n",
                 (thinkpad_id.bios_version_str) ?
                         thinkpad_id.bios_version_str : "unknown",
                 (thinkpad_id.ec_version_str) ?
@@ -8758,7 +8669,7 @@ static void __init thinkpad_acpi_init_banner(void)
         BUG_ON(!thinkpad_id.vendor);
 
         if (thinkpad_id.model_str)
-                printk(TPACPI_INFO "%s %s, model %s\n",
+                pr_info("%s %s, model %s\n",
                         (thinkpad_id.vendor == PCI_VENDOR_ID_IBM) ?
                                 "IBM" : ((thinkpad_id.vendor ==
                                                 PCI_VENDOR_ID_LENOVO) ?
@@ -9024,8 +8935,7 @@ static int __init thinkpad_acpi_module_init(void)
 
         ret = get_thinkpad_model_data(&thinkpad_id);
         if (ret) {
-                printk(TPACPI_ERR
-                        "unable to get DMI data: %d\n", ret);
+                pr_err("unable to get DMI data: %d\n", ret);
                 thinkpad_acpi_module_exit();
                 return ret;
         }
@@ -9051,16 +8961,14 @@ static int __init thinkpad_acpi_module_init(void)
 
         proc_dir = proc_mkdir(TPACPI_PROC_DIR, acpi_root_dir);
         if (!proc_dir) {
-                printk(TPACPI_ERR
-                       "unable to create proc dir " TPACPI_PROC_DIR);
+                pr_err("unable to create proc dir " TPACPI_PROC_DIR "\n");
                 thinkpad_acpi_module_exit();
                 return -ENODEV;
         }
 
         ret = platform_driver_register(&tpacpi_pdriver);
         if (ret) {
-                printk(TPACPI_ERR
-                       "unable to register main platform driver\n");
+                pr_err("unable to register main platform driver\n");
                 thinkpad_acpi_module_exit();
                 return ret;
         }
@@ -9068,8 +8976,7 @@ static int __init thinkpad_acpi_module_init(void)
 
         ret = platform_driver_register(&tpacpi_hwmon_pdriver);
         if (ret) {
-                printk(TPACPI_ERR
-                       "unable to register hwmon platform driver\n");
+                pr_err("unable to register hwmon platform driver\n");
                 thinkpad_acpi_module_exit();
                 return ret;
         }
@@ -9082,8 +8989,7 @@ static int __init thinkpad_acpi_module_init(void)
                                         &tpacpi_hwmon_pdriver.driver);
         }
         if (ret) {
-                printk(TPACPI_ERR
-                       "unable to create sysfs driver attributes\n");
+                pr_err("unable to create sysfs driver attributes\n");
                 thinkpad_acpi_module_exit();
                 return ret;
         }
@@ -9096,7 +9002,7 @@ static int __init thinkpad_acpi_module_init(void)
         if (IS_ERR(tpacpi_pdev)) {
                 ret = PTR_ERR(tpacpi_pdev);
                 tpacpi_pdev = NULL;
-                printk(TPACPI_ERR "unable to register platform device\n");
+                pr_err("unable to register platform device\n");
                 thinkpad_acpi_module_exit();
                 return ret;
         }
@@ -9106,16 +9012,14 @@ static int __init thinkpad_acpi_module_init(void)
         if (IS_ERR(tpacpi_sensors_pdev)) {
                 ret = PTR_ERR(tpacpi_sensors_pdev);
                 tpacpi_sensors_pdev = NULL;
-                printk(TPACPI_ERR
-                       "unable to register hwmon platform device\n");
+                pr_err("unable to register hwmon platform device\n");
                 thinkpad_acpi_module_exit();
                 return ret;
         }
         ret = device_create_file(&tpacpi_sensors_pdev->dev,
                                  &dev_attr_thinkpad_acpi_pdev_name);
         if (ret) {
-                printk(TPACPI_ERR
-                       "unable to create sysfs hwmon device attributes\n");
+                pr_err("unable to create sysfs hwmon device attributes\n");
                 thinkpad_acpi_module_exit();
                 return ret;
         }
@@ -9124,14 +9028,14 @@ static int __init thinkpad_acpi_module_init(void)
         if (IS_ERR(tpacpi_hwmon)) {
                 ret = PTR_ERR(tpacpi_hwmon);
                 tpacpi_hwmon = NULL;
-                printk(TPACPI_ERR "unable to register hwmon device\n");
+                pr_err("unable to register hwmon device\n");
                 thinkpad_acpi_module_exit();
                 return ret;
         }
         mutex_init(&tpacpi_inputdev_send_mutex);
         tpacpi_inputdev = input_allocate_device();
         if (!tpacpi_inputdev) {
-                printk(TPACPI_ERR "unable to allocate input device\n");
+                pr_err("unable to allocate input device\n");
                 thinkpad_acpi_module_exit();
                 return -ENOMEM;
         } else {
@@ -9163,7 +9067,7 @@ static int __init thinkpad_acpi_module_init(void)
 
         ret = input_register_device(tpacpi_inputdev);
         if (ret < 0) {
-                printk(TPACPI_ERR "unable to register input device\n");
+                pr_err("unable to register input device\n");
                 thinkpad_acpi_module_exit();
                 return ret;
         } else {
diff --git a/drivers/platform/x86/topstar-laptop.c b/drivers/platform/x86/topstar-laptop.c
index 1d07d6d09f27..4c20447ddbb7 100644
--- a/drivers/platform/x86/topstar-laptop.c
+++ b/drivers/platform/x86/topstar-laptop.c
@@ -194,7 +194,7 @@ static int __init topstar_laptop_init(void)
         if (ret < 0)
                 return ret;
 
-        printk(KERN_INFO "Topstar Laptop ACPI extras driver loaded\n");
+        pr_info("ACPI extras driver loaded\n");
 
         return 0;
 }
diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c
index 63f42a22e102..cb009b2629ee 100644
--- a/drivers/platform/x86/toshiba_acpi.c
+++ b/drivers/platform/x86/toshiba_acpi.c
@@ -35,6 +35,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #define TOSHIBA_ACPI_VERSION    "0.19"
 #define PROC_INTERFACE_VERSION  1
 
@@ -60,11 +62,6 @@ MODULE_AUTHOR("John Belmonte");
 MODULE_DESCRIPTION("Toshiba Laptop ACPI Extras Driver");
 MODULE_LICENSE("GPL");
 
-#define MY_LOGPREFIX "toshiba_acpi: "
-#define MY_ERR KERN_ERR MY_LOGPREFIX
-#define MY_NOTICE KERN_NOTICE MY_LOGPREFIX
-#define MY_INFO KERN_INFO MY_LOGPREFIX
-
 /* Toshiba ACPI method paths */
 #define METHOD_LCD_BRIGHTNESS   "\\_SB_.PCI0.VGA_.LCD_._BCM"
 #define TOSH_INTERFACE_1        "\\_SB_.VALD"
@@ -301,7 +298,7 @@ static int toshiba_illumination_available(void)
         in[0] = 0xf100;
         status = hci_raw(in, out);
         if (ACPI_FAILURE(status)) {
-                printk(MY_INFO "Illumination device not available\n");
+                pr_info("Illumination device not available\n");
                 return 0;
         }
         in[0] = 0xf400;
@@ -320,7 +317,7 @@ static void toshiba_illumination_set(struct led_classdev *cdev,
         in[0] = 0xf100;
         status = hci_raw(in, out);
         if (ACPI_FAILURE(status)) {
-                printk(MY_INFO "Illumination device not available\n");
+                pr_info("Illumination device not available\n");
                 return;
         }
 
@@ -331,7 +328,7 @@ static void toshiba_illumination_set(struct led_classdev *cdev,
                 in[2] = 1;
                 status = hci_raw(in, out);
                 if (ACPI_FAILURE(status)) {
-                        printk(MY_INFO "ACPI call for illumination failed.\n");
+                        pr_info("ACPI call for illumination failed\n");
                         return;
                 }
         } else {
@@ -341,7 +338,7 @@ static void toshiba_illumination_set(struct led_classdev *cdev,
                 in[2] = 0;
                 status = hci_raw(in, out);
                 if (ACPI_FAILURE(status)) {
-                        printk(MY_INFO "ACPI call for illumination failed.\n");
+                        pr_info("ACPI call for illumination failed.\n");
                         return;
                 }
         }
@@ -364,7 +361,7 @@ static enum led_brightness toshiba_illumination_get(struct led_classdev *cdev)
         in[0] = 0xf100;
         status = hci_raw(in, out);
         if (ACPI_FAILURE(status)) {
-                printk(MY_INFO "Illumination device not available\n");
+                pr_info("Illumination device not available\n");
                 return LED_OFF;
         }
 
@@ -373,7 +370,7 @@ static enum led_brightness toshiba_illumination_get(struct led_classdev *cdev)
         in[1] = 0x14e;
         status = hci_raw(in, out);
         if (ACPI_FAILURE(status)) {
-                printk(MY_INFO "ACPI call for illumination failed.\n");
+                pr_info("ACPI call for illumination failed.\n");
                 return LED_OFF;
         }
 
@@ -517,7 +514,7 @@ static int lcd_proc_show(struct seq_file *m, void *v)
                 seq_printf(m, "brightness_levels:       %d\n",
                              HCI_LCD_BRIGHTNESS_LEVELS);
         } else {
-                printk(MY_ERR "Error reading LCD brightness\n");
+                pr_err("Error reading LCD brightness\n");
         }
 
         return 0;
@@ -592,7 +589,7 @@ static int video_proc_show(struct seq_file *m, void *v)
                 seq_printf(m, "crt_out:                 %d\n", is_crt);
                 seq_printf(m, "tv_out:                  %d\n", is_tv);
         } else {
-                printk(MY_ERR "Error reading video out status\n");
+                pr_err("Error reading video out status\n");
         }
 
         return 0;
@@ -686,7 +683,7 @@ static int fan_proc_show(struct seq_file *m, void *v)
                 seq_printf(m, "running:                 %d\n", (value > 0));
                 seq_printf(m, "force_on:                %d\n", force_fan);
         } else {
-                printk(MY_ERR "Error reading fan status\n");
+                pr_err("Error reading fan status\n");
         }
 
         return 0;
@@ -750,9 +747,9 @@ static int keys_proc_show(struct seq_file *m, void *v)
                          * some machines where system events sporadically
                          * become disabled. */
                         hci_write1(HCI_SYSTEM_EVENT, 1, &hci_result);
-                        printk(MY_NOTICE "Re-enabled hotkeys\n");
+                        pr_notice("Re-enabled hotkeys\n");
                 } else {
-                        printk(MY_ERR "Error reading hotkey status\n");
+                        pr_err("Error reading hotkey status\n");
                         goto end;
                 }
         }
@@ -863,7 +860,7 @@ static void toshiba_acpi_notify(acpi_handle handle, u32 event, void *context)
 
                         if (!sparse_keymap_report_event(toshiba_acpi.hotkey_dev,
                                                         value, 1, true)) {
-                                printk(MY_INFO "Unknown key %x\n",
+                                pr_info("Unknown key %x\n",
                                        value);
                         }
                 } else if (hci_result == HCI_NOT_SUPPORTED) {
@@ -871,7 +868,7 @@ static void toshiba_acpi_notify(acpi_handle handle, u32 event, void *context)
                          * some machines where system events sporadically
                          * become disabled. */
                         hci_write1(HCI_SYSTEM_EVENT, 1, &hci_result);
-                        printk(MY_NOTICE "Re-enabled hotkeys\n");
+                        pr_notice("Re-enabled hotkeys\n");
                 }
         } while (hci_result != HCI_EMPTY);
 }
@@ -883,13 +880,13 @@ static int __init toshiba_acpi_setup_keyboard(char *device)
 
         status = acpi_get_handle(NULL, device, &toshiba_acpi.handle);
         if (ACPI_FAILURE(status)) {
-                printk(MY_INFO "Unable to get notification device\n");
+                pr_info("Unable to get notification device\n");
                 return -ENODEV;
         }
 
         toshiba_acpi.hotkey_dev = input_allocate_device();
         if (!toshiba_acpi.hotkey_dev) {
-                printk(MY_INFO "Unable to register input device\n");
+                pr_info("Unable to register input device\n");
                 return -ENOMEM;
         }
 
@@ -905,21 +902,21 @@ static int __init toshiba_acpi_setup_keyboard(char *device)
         status = acpi_install_notify_handler(toshiba_acpi.handle,
                                 ACPI_DEVICE_NOTIFY, toshiba_acpi_notify, NULL);
         if (ACPI_FAILURE(status)) {
-                printk(MY_INFO "Unable to install hotkey notification\n");
+                pr_info("Unable to install hotkey notification\n");
                 error = -ENODEV;
                 goto err_free_keymap;
         }
 
         status = acpi_evaluate_object(toshiba_acpi.handle, "ENAB", NULL, NULL);
         if (ACPI_FAILURE(status)) {
-                printk(MY_INFO "Unable to enable hotkeys\n");
+                pr_info("Unable to enable hotkeys\n");
                 error = -ENODEV;
                 goto err_remove_notify;
         }
 
         error = input_register_device(toshiba_acpi.hotkey_dev);
         if (error) {
-                printk(MY_INFO "Unable to register input device\n");
+                pr_info("Unable to register input device\n");
                 goto err_remove_notify;
         }
 
@@ -980,17 +977,17 @@ static int __init toshiba_acpi_init(void)
         if (is_valid_acpi_path(TOSH_INTERFACE_1 GHCI_METHOD)) {
                 method_hci = TOSH_INTERFACE_1 GHCI_METHOD;
                 if (toshiba_acpi_setup_keyboard(TOSH_INTERFACE_1))
-                        printk(MY_INFO "Unable to activate hotkeys\n");
+                        pr_info("Unable to activate hotkeys\n");
         } else if (is_valid_acpi_path(TOSH_INTERFACE_2 GHCI_METHOD)) {
                 method_hci = TOSH_INTERFACE_2 GHCI_METHOD;
                 if (toshiba_acpi_setup_keyboard(TOSH_INTERFACE_2))
-                        printk(MY_INFO "Unable to activate hotkeys\n");
+                        pr_info("Unable to activate hotkeys\n");
         } else
                 return -ENODEV;
 
-        printk(MY_INFO "Toshiba Laptop ACPI Extras version %s\n",
+        pr_info("Toshiba Laptop ACPI Extras version %s\n",
                TOSHIBA_ACPI_VERSION);
-        printk(MY_INFO "    HCI method: %s\n", method_hci);
+        pr_info("    HCI method: %s\n", method_hci);
 
         mutex_init(&toshiba_acpi.mutex);
 
@@ -998,7 +995,7 @@ static int __init toshiba_acpi_init(void)
                                                               -1, NULL, 0);
         if (IS_ERR(toshiba_acpi.p_dev)) {
                 ret = PTR_ERR(toshiba_acpi.p_dev);
-                printk(MY_ERR "unable to register platform device\n");
+                pr_err("unable to register platform device\n");
                 toshiba_acpi.p_dev = NULL;
                 toshiba_acpi_exit();
                 return ret;
@@ -1028,7 +1025,7 @@ static int __init toshiba_acpi_init(void)
         if (IS_ERR(toshiba_backlight_device)) {
                 ret = PTR_ERR(toshiba_backlight_device);
 
-                printk(KERN_ERR "Could not register toshiba backlight device\n");
+                pr_err("Could not register toshiba backlight device\n");
                 toshiba_backlight_device = NULL;
                 toshiba_acpi_exit();
                 return ret;
@@ -1042,14 +1039,14 @@ static int __init toshiba_acpi_init(void)
                                                    &toshiba_rfk_ops,
                                                    &toshiba_acpi);
                 if (!toshiba_acpi.bt_rfk) {
-                        printk(MY_ERR "unable to allocate rfkill device\n");
+                        pr_err("unable to allocate rfkill device\n");
                         toshiba_acpi_exit();
                         return -ENOMEM;
                 }
 
                 ret = rfkill_register(toshiba_acpi.bt_rfk);
                 if (ret) {
-                        printk(MY_ERR "unable to register rfkill device\n");
+                        pr_err("unable to register rfkill device\n");
                         rfkill_destroy(toshiba_acpi.bt_rfk);
                         toshiba_acpi_exit();
                         return ret;
diff --git a/drivers/platform/x86/toshiba_bluetooth.c b/drivers/platform/x86/toshiba_bluetooth.c
index 944068611919..5fb7186694df 100644
--- a/drivers/platform/x86/toshiba_bluetooth.c
+++ b/drivers/platform/x86/toshiba_bluetooth.c
@@ -17,6 +17,8 @@
  * delivered.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -70,14 +72,13 @@ static int toshiba_bluetooth_enable(acpi_handle handle)
         if (!(result & 0x01))
                 return 0;
 
-        printk(KERN_INFO "toshiba_bluetooth: Re-enabling Toshiba Bluetooth\n");
+        pr_info("Re-enabling Toshiba Bluetooth\n");
         res1 = acpi_evaluate_object(handle, "AUSB", NULL, NULL);
         res2 = acpi_evaluate_object(handle, "BTPO", NULL, NULL);
         if (!ACPI_FAILURE(res1) || !ACPI_FAILURE(res2))
                 return 0;
 
-        printk(KERN_WARNING "toshiba_bluetooth: Failed to re-enable "
-               "Toshiba Bluetooth\n");
+        pr_warn("Failed to re-enable Toshiba Bluetooth\n");
 
         return -ENODEV;
 }
@@ -107,8 +108,8 @@ static int toshiba_bt_rfkill_add(struct acpi_device *device)
                                        &bt_present);
 
         if (!ACPI_FAILURE(status) && bt_present) {
-                printk(KERN_INFO "Detected Toshiba ACPI Bluetooth device - "
-                      "installing RFKill handler\n");
+                pr_info("Detected Toshiba ACPI Bluetooth device - "
+                        "installing RFKill handler\n");
                 result = toshiba_bluetooth_enable(device->handle);
         }
 
diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c
index 05cc79672a8b..f23d5a84e7b1 100644
--- a/drivers/platform/x86/wmi.c
+++ b/drivers/platform/x86/wmi.c
@@ -486,16 +486,16 @@ static void wmi_dump_wdg(const struct guid_block *g)
         pr_info("\tnotify_id: %02X\n", g->notify_id);
         pr_info("\treserved: %02X\n", g->reserved);
         pr_info("\tinstance_count: %d\n", g->instance_count);
-        pr_info("\tflags: %#x ", g->flags);
+        pr_info("\tflags: %#x", g->flags);
         if (g->flags) {
                 if (g->flags & ACPI_WMI_EXPENSIVE)
-                        pr_cont("ACPI_WMI_EXPENSIVE ");
+                        pr_cont(" ACPI_WMI_EXPENSIVE");
                 if (g->flags & ACPI_WMI_METHOD)
-                        pr_cont("ACPI_WMI_METHOD ");
+                        pr_cont(" ACPI_WMI_METHOD");
                 if (g->flags & ACPI_WMI_STRING)
-                        pr_cont("ACPI_WMI_STRING ");
+                        pr_cont(" ACPI_WMI_STRING");
                 if (g->flags & ACPI_WMI_EVENT)
-                        pr_cont("ACPI_WMI_EVENT ");
+                        pr_cont(" ACPI_WMI_EVENT");
         }
         pr_cont("\n");
 
diff --git a/drivers/platform/x86/xo15-ebook.c b/drivers/platform/x86/xo15-ebook.c
index c1372ed9d2e9..fad153dc0355 100644
--- a/drivers/platform/x86/xo15-ebook.c
+++ b/drivers/platform/x86/xo15-ebook.c
@@ -11,6 +11,8 @@
  *  your option) any later version.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -20,7 +22,6 @@
 #include <acpi/acpi_drivers.h>
 
 #define MODULE_NAME "xo15-ebook"
-#define PREFIX MODULE_NAME ": "
 
 #define XO15_EBOOK_CLASS                MODULE_NAME
 #define XO15_EBOOK_TYPE_UNKNOWN 0x00
@@ -105,7 +106,7 @@ static int ebook_switch_add(struct acpi_device *device)
         class = acpi_device_class(device);
 
         if (strcmp(hid, XO15_EBOOK_HID)) {
-                printk(KERN_ERR PREFIX "Unsupported hid [%s]\n", hid);
+                pr_err("Unsupported hid [%s]\n", hid);
                 error = -ENODEV;
                 goto err_free_input;
         }
diff --git a/drivers/scsi/scsi_proc.c b/drivers/scsi/scsi_proc.c
index f46855cd853d..ad747dc337da 100644
--- a/drivers/scsi/scsi_proc.c
+++ b/drivers/scsi/scsi_proc.c
@@ -381,11 +381,6 @@ static ssize_t proc_scsi_write(struct file *file, const char __user *buf,
         return err;
 }
 
-/**
- * proc_scsi_show - show contents of /proc/scsi/scsi (attached devices)
- * @s: output goes here
- * @p: not used
- */
 static int always_match(struct device *dev, void *data)
 {
         return 1;
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 58584dc0724a..44e8ca398efa 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -297,7 +297,7 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget,
                 kfree(sdev);
                 goto out;
         }
-
+        blk_get_queue(sdev->request_queue);
         sdev->request_queue->queuedata = sdev;
         scsi_adjust_queue_depth(sdev, 0, sdev->host->cmd_per_lun);
 
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index e63912510fb9..e0bd3f790fca 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -322,6 +322,7 @@ static void scsi_device_dev_release_usercontext(struct work_struct *work)
                 kfree(evt);
         }
 
+        blk_put_queue(sdev->request_queue);
         /* NULL queue means the device can't be used */
         sdev->request_queue = NULL;
 
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index fbd96b29530d..de35c3ad8a69 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -80,6 +80,15 @@ config SPI_BFIN
         help
           This is the SPI controller master driver for Blackfin 5xx processor.
 
+config SPI_BFIN_SPORT
+        tristate "SPI bus via Blackfin SPORT"
+        depends on BLACKFIN
+        help
+          Enable support for a SPI bus via the Blackfin SPORT peripheral.
+
+          This driver can also be built as a module.  If so, the module
+          will be called spi_bfin_sport.
+
 config SPI_AU1550
         tristate "Au1550/Au12x0 SPI Controller"
         depends on (SOC_AU1550 || SOC_AU1200) && EXPERIMENTAL
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index fd2fc5f6505f..0f8c69b6b19e 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -13,6 +13,7 @@ obj-$(CONFIG_SPI_ALTERA)		+= spi_altera.o
 obj-$(CONFIG_SPI_ATMEL)                 += atmel_spi.o
 obj-$(CONFIG_SPI_ATH79)                 += ath79_spi.o
 obj-$(CONFIG_SPI_BFIN)                  += spi_bfin5xx.o
+obj-$(CONFIG_SPI_BFIN_SPORT)            += spi_bfin_sport.o
 obj-$(CONFIG_SPI_BITBANG)               += spi_bitbang.o
 obj-$(CONFIG_SPI_AU1550)                += au1550_spi.o
 obj-$(CONFIG_SPI_BUTTERFLY)             += spi_butterfly.o
diff --git a/drivers/spi/spi_bfin_sport.c b/drivers/spi/spi_bfin_sport.c
new file mode 100644
index 000000000000..e557ff617b11
--- /dev/null
+++ b/drivers/spi/spi_bfin_sport.c
@@ -0,0 +1,952 @@
+/*
+ * SPI bus via the Blackfin SPORT peripheral
+ *
+ * Enter bugs at http://blackfin.uclinux.org/
+ *
+ * Copyright 2009-2011 Analog Devices Inc.
+ *
+ * Licensed under the GPL-2 or later.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/gpio.h>
+#include <linux/io.h>
+#include <linux/ioport.h>
+#include <linux/irq.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/platform_device.h>
+#include <linux/spi/spi.h>
+#include <linux/workqueue.h>
+
+#include <asm/portmux.h>
+#include <asm/bfin5xx_spi.h>
+#include <asm/blackfin.h>
+#include <asm/bfin_sport.h>
+#include <asm/cacheflush.h>
+
+#define DRV_NAME        "bfin-sport-spi"
+#define DRV_DESC        "SPI bus via the Blackfin SPORT"
+
+MODULE_AUTHOR("Cliff Cai");
+MODULE_DESCRIPTION(DRV_DESC);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:bfin-sport-spi");
+
+enum bfin_sport_spi_state {
+        START_STATE,
+        RUNNING_STATE,
+        DONE_STATE,
+        ERROR_STATE,
+};
+
+struct bfin_sport_spi_master_data;
+
+struct bfin_sport_transfer_ops {
+        void (*write) (struct bfin_sport_spi_master_data *);
+        void (*read) (struct bfin_sport_spi_master_data *);
+        void (*duplex) (struct bfin_sport_spi_master_data *);
+};
+
+struct bfin_sport_spi_master_data {
+        /* Driver model hookup */
+        struct device *dev;
+
+        /* SPI framework hookup */
+        struct spi_master *master;
+
+        /* Regs base of SPI controller */
+        struct sport_register __iomem *regs;
+        int err_irq;
+
+        /* Pin request list */
+        u16 *pin_req;
+
+        /* Driver message queue */
+        struct workqueue_struct *workqueue;
+        struct work_struct pump_messages;
+        spinlock_t lock;
+        struct list_head queue;
+        int busy;
+        bool run;
+
+        /* Message Transfer pump */
+        struct tasklet_struct pump_transfers;
+
+        /* Current message transfer state info */
+        enum bfin_sport_spi_state state;
+        struct spi_message *cur_msg;
+        struct spi_transfer *cur_transfer;
+        struct bfin_sport_spi_slave_data *cur_chip;
+        union {
+                void *tx;
+                u8 *tx8;
+                u16 *tx16;
+        };
+        void *tx_end;
+        union {
+                void *rx;
+                u8 *rx8;
+                u16 *rx16;
+        };
+        void *rx_end;
+
+        int cs_change;
+        struct bfin_sport_transfer_ops *ops;
+};
+
+struct bfin_sport_spi_slave_data {
+        u16 ctl_reg;
+        u16 baud;
+        u16 cs_chg_udelay;      /* Some devices require > 255usec delay */
+        u32 cs_gpio;
+        u16 idle_tx_val;
+        struct bfin_sport_transfer_ops *ops;
+};
+
+static void
+bfin_sport_spi_enable(struct bfin_sport_spi_master_data *drv_data)
+{
+        bfin_write_or(&drv_data->regs->tcr1, TSPEN);
+        bfin_write_or(&drv_data->regs->rcr1, TSPEN);
+        SSYNC();
+}
+
+static void
+bfin_sport_spi_disable(struct bfin_sport_spi_master_data *drv_data)
+{
+        bfin_write_and(&drv_data->regs->tcr1, ~TSPEN);
+        bfin_write_and(&drv_data->regs->rcr1, ~TSPEN);
+        SSYNC();
+}
+
+/* Caculate the SPI_BAUD register value based on input HZ */
+static u16
+bfin_sport_hz_to_spi_baud(u32 speed_hz)
+{
+        u_long clk, sclk = get_sclk();
+        int div = (sclk / (2 * speed_hz)) - 1;
+
+        if (div < 0)
+                div = 0;
+
+        clk = sclk / (2 * (div + 1));
+
+        if (clk > speed_hz)
+                div++;
+
+        return div;
+}
+
+/* Chip select operation functions for cs_change flag */
+static void
+bfin_sport_spi_cs_active(struct bfin_sport_spi_slave_data *chip)
+{
+        gpio_direction_output(chip->cs_gpio, 0);
+}
+
+static void
+bfin_sport_spi_cs_deactive(struct bfin_sport_spi_slave_data *chip)
+{
+        gpio_direction_output(chip->cs_gpio, 1);
+        /* Move delay here for consistency */
+        if (chip->cs_chg_udelay)
+                udelay(chip->cs_chg_udelay);
+}
+
+static void
+bfin_sport_spi_stat_poll_complete(struct bfin_sport_spi_master_data *drv_data)
+{
+        unsigned long timeout = jiffies + HZ;
+        while (!(bfin_read(&drv_data->regs->stat) & RXNE)) {
+                if (!time_before(jiffies, timeout))
+                        break;
+        }
+}
+
+static void
+bfin_sport_spi_u8_writer(struct bfin_sport_spi_master_data *drv_data)
+{
+        u16 dummy;
+
+        while (drv_data->tx < drv_data->tx_end) {
+                bfin_write(&drv_data->regs->tx16, *drv_data->tx8++);
+                bfin_sport_spi_stat_poll_complete(drv_data);
+                dummy = bfin_read(&drv_data->regs->rx16);
+        }
+}
+
+static void
+bfin_sport_spi_u8_reader(struct bfin_sport_spi_master_data *drv_data)
+{
+        u16 tx_val = drv_data->cur_chip->idle_tx_val;
+
+        while (drv_data->rx < drv_data->rx_end) {
+                bfin_write(&drv_data->regs->tx16, tx_val);
+                bfin_sport_spi_stat_poll_complete(drv_data);
+                *drv_data->rx8++ = bfin_read(&drv_data->regs->rx16);
+        }
+}
+
+static void
+bfin_sport_spi_u8_duplex(struct bfin_sport_spi_master_data *drv_data)
+{
+        while (drv_data->rx < drv_data->rx_end) {
+                bfin_write(&drv_data->regs->tx16, *drv_data->tx8++);
+                bfin_sport_spi_stat_poll_complete(drv_data);
+                *drv_data->rx8++ = bfin_read(&drv_data->regs->rx16);
+        }
+}
+
+static struct bfin_sport_transfer_ops bfin_sport_transfer_ops_u8 = {
+        .write  = bfin_sport_spi_u8_writer,
+        .read   = bfin_sport_spi_u8_reader,
+        .duplex = bfin_sport_spi_u8_duplex,
+};
+
+static void
+bfin_sport_spi_u16_writer(struct bfin_sport_spi_master_data *drv_data)
+{
+        u16 dummy;
+
+        while (drv_data->tx < drv_data->tx_end) {
+                bfin_write(&drv_data->regs->tx16, *drv_data->tx16++);
+                bfin_sport_spi_stat_poll_complete(drv_data);
+                dummy = bfin_read(&drv_data->regs->rx16);
+        }
+}
+
+static void
+bfin_sport_spi_u16_reader(struct bfin_sport_spi_master_data *drv_data)
+{
+        u16 tx_val = drv_data->cur_chip->idle_tx_val;
+
+        while (drv_data->rx < drv_data->rx_end) {
+                bfin_write(&drv_data->regs->tx16, tx_val);
+                bfin_sport_spi_stat_poll_complete(drv_data);
+                *drv_data->rx16++ = bfin_read(&drv_data->regs->rx16);
+        }
+}
+
+static void
+bfin_sport_spi_u16_duplex(struct bfin_sport_spi_master_data *drv_data)
+{
+        while (drv_data->rx < drv_data->rx_end) {
+                bfin_write(&drv_data->regs->tx16, *drv_data->tx16++);
+                bfin_sport_spi_stat_poll_complete(drv_data);
+                *drv_data->rx16++ = bfin_read(&drv_data->regs->rx16);
+        }
+}
+
+static struct bfin_sport_transfer_ops bfin_sport_transfer_ops_u16 = {
+        .write  = bfin_sport_spi_u16_writer,
+        .read   = bfin_sport_spi_u16_reader,
+        .duplex = bfin_sport_spi_u16_duplex,
+};
+
+/* stop controller and re-config current chip */
+static void
+bfin_sport_spi_restore_state(struct bfin_sport_spi_master_data *drv_data)
+{
+        struct bfin_sport_spi_slave_data *chip = drv_data->cur_chip;
+        unsigned int bits = (drv_data->ops == &bfin_sport_transfer_ops_u8 ? 7 : 15);
+
+        bfin_sport_spi_disable(drv_data);
+        dev_dbg(drv_data->dev, "restoring spi ctl state\n");
+
+        bfin_write(&drv_data->regs->tcr1, chip->ctl_reg);
+        bfin_write(&drv_data->regs->tcr2, bits);
+        bfin_write(&drv_data->regs->tclkdiv, chip->baud);
+        bfin_write(&drv_data->regs->tfsdiv, bits);
+        SSYNC();
+
+        bfin_write(&drv_data->regs->rcr1, chip->ctl_reg & ~(ITCLK | ITFS));
+        bfin_write(&drv_data->regs->rcr2, bits);
+        SSYNC();
+
+        bfin_sport_spi_cs_active(chip);
+}
+
+/* test if there is more transfer to be done */
+static enum bfin_sport_spi_state
+bfin_sport_spi_next_transfer(struct bfin_sport_spi_master_data *drv_data)
+{
+        struct spi_message *msg = drv_data->cur_msg;
+        struct spi_transfer *trans = drv_data->cur_transfer;
+
+        /* Move to next transfer */
+        if (trans->transfer_list.next != &msg->transfers) {
+                drv_data->cur_transfer =
+                    list_entry(trans->transfer_list.next,
+                               struct spi_transfer, transfer_list);
+                return RUNNING_STATE;
+        }
+
+        return DONE_STATE;
+}
+
+/*
+ * caller already set message->status;
+ * dma and pio irqs are blocked give finished message back
+ */
+static void
+bfin_sport_spi_giveback(struct bfin_sport_spi_master_data *drv_data)
+{
+        struct bfin_sport_spi_slave_data *chip = drv_data->cur_chip;
+        unsigned long flags;
+        struct spi_message *msg;
+
+        spin_lock_irqsave(&drv_data->lock, flags);
+        msg = drv_data->cur_msg;
+        drv_data->state = START_STATE;
+        drv_data->cur_msg = NULL;
+        drv_data->cur_transfer = NULL;
+        drv_data->cur_chip = NULL;
+        queue_work(drv_data->workqueue, &drv_data->pump_messages);
+        spin_unlock_irqrestore(&drv_data->lock, flags);
+
+        if (!drv_data->cs_change)
+                bfin_sport_spi_cs_deactive(chip);
+
+        if (msg->complete)
+                msg->complete(msg->context);
+}
+
+static irqreturn_t
+sport_err_handler(int irq, void *dev_id)
+{
+        struct bfin_sport_spi_master_data *drv_data = dev_id;
+        u16 status;
+
+        dev_dbg(drv_data->dev, "%s enter\n", __func__);
+        status = bfin_read(&drv_data->regs->stat) & (TOVF | TUVF | ROVF | RUVF);
+
+        if (status) {
+                bfin_write(&drv_data->regs->stat, status);
+                SSYNC();
+
+                bfin_sport_spi_disable(drv_data);
+                dev_err(drv_data->dev, "status error:%s%s%s%s\n",
+                        status & TOVF ? " TOVF" : "",
+                        status & TUVF ? " TUVF" : "",
+                        status & ROVF ? " ROVF" : "",
+                        status & RUVF ? " RUVF" : "");
+        }
+
+        return IRQ_HANDLED;
+}
+
+static void
+bfin_sport_spi_pump_transfers(unsigned long data)
+{
+        struct bfin_sport_spi_master_data *drv_data = (void *)data;
+        struct spi_message *message = NULL;
+        struct spi_transfer *transfer = NULL;
+        struct spi_transfer *previous = NULL;
+        struct bfin_sport_spi_slave_data *chip = NULL;
+        unsigned int bits_per_word;
+        u32 tranf_success = 1;
+        u32 transfer_speed;
+        u8 full_duplex = 0;
+
+        /* Get current state information */
+        message = drv_data->cur_msg;
+        transfer = drv_data->cur_transfer;
+        chip = drv_data->cur_chip;
+
+        if (transfer->speed_hz)
+                transfer_speed = bfin_sport_hz_to_spi_baud(transfer->speed_hz);
+        else
+                transfer_speed = chip->baud;
+        bfin_write(&drv_data->regs->tclkdiv, transfer_speed);
+        SSYNC();
+
+        /*
+         * if msg is error or done, report it back using complete() callback
+         */
+
+         /* Handle for abort */
+        if (drv_data->state == ERROR_STATE) {
+                dev_dbg(drv_data->dev, "transfer: we've hit an error\n");
+                message->status = -EIO;
+                bfin_sport_spi_giveback(drv_data);
+                return;
+        }
+
+        /* Handle end of message */
+        if (drv_data->state == DONE_STATE) {
+                dev_dbg(drv_data->dev, "transfer: all done!\n");
+                message->status = 0;
+                bfin_sport_spi_giveback(drv_data);
+                return;
+        }
+
+        /* Delay if requested at end of transfer */
+        if (drv_data->state == RUNNING_STATE) {
+                dev_dbg(drv_data->dev, "transfer: still running ...\n");
+                previous = list_entry(transfer->transfer_list.prev,
+                                      struct spi_transfer, transfer_list);
+                if (previous->delay_usecs)
+                        udelay(previous->delay_usecs);
+        }
+
+        if (transfer->len == 0) {
+                /* Move to next transfer of this msg */
+                drv_data->state = bfin_sport_spi_next_transfer(drv_data);
+                /* Schedule next transfer tasklet */
+                tasklet_schedule(&drv_data->pump_transfers);
+        }
+
+        if (transfer->tx_buf != NULL) {
+                drv_data->tx = (void *)transfer->tx_buf;
+                drv_data->tx_end = drv_data->tx + transfer->len;
+                dev_dbg(drv_data->dev, "tx_buf is %p, tx_end is %p\n",
+                        transfer->tx_buf, drv_data->tx_end);
+        } else
+                drv_data->tx = NULL;
+
+        if (transfer->rx_buf != NULL) {
+                full_duplex = transfer->tx_buf != NULL;
+                drv_data->rx = transfer->rx_buf;
+                drv_data->rx_end = drv_data->rx + transfer->len;
+                dev_dbg(drv_data->dev, "rx_buf is %p, rx_end is %p\n",
+                        transfer->rx_buf, drv_data->rx_end);
+        } else
+                drv_data->rx = NULL;
+
+        drv_data->cs_change = transfer->cs_change;
+
+        /* Bits per word setup */
+        bits_per_word = transfer->bits_per_word ? : message->spi->bits_per_word;
+        if (bits_per_word == 8)
+                drv_data->ops = &bfin_sport_transfer_ops_u8;
+        else
+                drv_data->ops = &bfin_sport_transfer_ops_u16;
+
+        drv_data->state = RUNNING_STATE;
+
+        if (drv_data->cs_change)
+                bfin_sport_spi_cs_active(chip);
+
+        dev_dbg(drv_data->dev,
+                "now pumping a transfer: width is %d, len is %d\n",
+                bits_per_word, transfer->len);
+
+        /* PIO mode write then read */
+        dev_dbg(drv_data->dev, "doing IO transfer\n");
+
+        bfin_sport_spi_enable(drv_data);
+        if (full_duplex) {
+                /* full duplex mode */
+                BUG_ON((drv_data->tx_end - drv_data->tx) !=
+                       (drv_data->rx_end - drv_data->rx));
+                drv_data->ops->duplex(drv_data);
+
+                if (drv_data->tx != drv_data->tx_end)
+                        tranf_success = 0;
+        } else if (drv_data->tx != NULL) {
+                /* write only half duplex */
+
+                drv_data->ops->write(drv_data);
+
+                if (drv_data->tx != drv_data->tx_end)
+                        tranf_success = 0;
+        } else if (drv_data->rx != NULL) {
+                /* read only half duplex */
+
+                drv_data->ops->read(drv_data);
+                if (drv_data->rx != drv_data->rx_end)
+                        tranf_success = 0;
+        }
+        bfin_sport_spi_disable(drv_data);
+
+        if (!tranf_success) {
+                dev_dbg(drv_data->dev, "IO write error!\n");
+                drv_data->state = ERROR_STATE;
+        } else {
+                /* Update total byte transfered */
+                message->actual_length += transfer->len;
+                /* Move to next transfer of this msg */
+                drv_data->state = bfin_sport_spi_next_transfer(drv_data);
+                if (drv_data->cs_change)
+                        bfin_sport_spi_cs_deactive(chip);
+        }
+
+        /* Schedule next transfer tasklet */
+        tasklet_schedule(&drv_data->pump_transfers);
+}
+
+/* pop a msg from queue and kick off real transfer */
+static void
+bfin_sport_spi_pump_messages(struct work_struct *work)
+{
+        struct bfin_sport_spi_master_data *drv_data;
+        unsigned long flags;
+        struct spi_message *next_msg;
+
+        drv_data = container_of(work, struct bfin_sport_spi_master_data, pump_messages);
+
+        /* Lock queue and check for queue work */
+        spin_lock_irqsave(&drv_data->lock, flags);
+        if (list_empty(&drv_data->queue) || !drv_data->run) {
+                /* pumper kicked off but no work to do */
+                drv_data->busy = 0;
+                spin_unlock_irqrestore(&drv_data->lock, flags);
+                return;
+        }
+
+        /* Make sure we are not already running a message */
+        if (drv_data->cur_msg) {
+                spin_unlock_irqrestore(&drv_data->lock, flags);
+                return;
+        }
+
+        /* Extract head of queue */
+        next_msg = list_entry(drv_data->queue.next,
+                struct spi_message, queue);
+
+        drv_data->cur_msg = next_msg;
+
+        /* Setup the SSP using the per chip configuration */
+        drv_data->cur_chip = spi_get_ctldata(drv_data->cur_msg->spi);
+
+        list_del_init(&drv_data->cur_msg->queue);
+
+        /* Initialize message state */
+        drv_data->cur_msg->state = START_STATE;
+        drv_data->cur_transfer = list_entry(drv_data->cur_msg->transfers.next,
+                                            struct spi_transfer, transfer_list);
+        bfin_sport_spi_restore_state(drv_data);
+        dev_dbg(drv_data->dev, "got a message to pump, "
+                "state is set to: baud %d, cs_gpio %i, ctl 0x%x\n",
+                drv_data->cur_chip->baud, drv_data->cur_chip->cs_gpio,
+                drv_data->cur_chip->ctl_reg);
+
+        dev_dbg(drv_data->dev,
+                "the first transfer len is %d\n",
+                drv_data->cur_transfer->len);
+
+        /* Mark as busy and launch transfers */
+        tasklet_schedule(&drv_data->pump_transfers);
+
+        drv_data->busy = 1;
+        spin_unlock_irqrestore(&drv_data->lock, flags);
+}
+
+/*
+ * got a msg to transfer, queue it in drv_data->queue.
+ * And kick off message pumper
+ */
+static int
+bfin_sport_spi_transfer(struct spi_device *spi, struct spi_message *msg)
+{
+        struct bfin_sport_spi_master_data *drv_data = spi_master_get_devdata(spi->master);
+        unsigned long flags;
+
+        spin_lock_irqsave(&drv_data->lock, flags);
+
+        if (!drv_data->run) {
+                spin_unlock_irqrestore(&drv_data->lock, flags);
+                return -ESHUTDOWN;
+        }
+
+        msg->actual_length = 0;
+        msg->status = -EINPROGRESS;
+        msg->state = START_STATE;
+
+        dev_dbg(&spi->dev, "adding an msg in transfer()\n");
+        list_add_tail(&msg->queue, &drv_data->queue);
+
+        if (drv_data->run && !drv_data->busy)
+                queue_work(drv_data->workqueue, &drv_data->pump_messages);
+
+        spin_unlock_irqrestore(&drv_data->lock, flags);
+
+        return 0;
+}
+
+/* Called every time common spi devices change state */
+static int
+bfin_sport_spi_setup(struct spi_device *spi)
+{
+        struct bfin_sport_spi_slave_data *chip, *first = NULL;
+        int ret;
+
+        /* Only alloc (or use chip_info) on first setup */
+        chip = spi_get_ctldata(spi);
+        if (chip == NULL) {
+                struct bfin5xx_spi_chip *chip_info;
+
+                chip = first = kzalloc(sizeof(*chip), GFP_KERNEL);
+                if (!chip)
+                        return -ENOMEM;
+
+                /* platform chip_info isn't required */
+                chip_info = spi->controller_data;
+                if (chip_info) {
+                        /*
+                         * DITFS and TDTYPE are only thing we don't set, but
+                         * they probably shouldn't be changed by people.
+                         */
+                        if (chip_info->ctl_reg || chip_info->enable_dma) {
+                                ret = -EINVAL;
+                                dev_err(&spi->dev, "don't set ctl_reg/enable_dma fields");
+                                goto error;
+                        }
+                        chip->cs_chg_udelay = chip_info->cs_chg_udelay;
+                        chip->idle_tx_val = chip_info->idle_tx_val;
+                        spi->bits_per_word = chip_info->bits_per_word;
+                }
+        }
+
+        if (spi->bits_per_word != 8 && spi->bits_per_word != 16) {
+                ret = -EINVAL;
+                goto error;
+        }
+
+        /* translate common spi framework into our register
+         * following configure contents are same for tx and rx.
+         */
+
+        if (spi->mode & SPI_CPHA)
+                chip->ctl_reg &= ~TCKFE;
+        else
+                chip->ctl_reg |= TCKFE;
+
+        if (spi->mode & SPI_LSB_FIRST)
+                chip->ctl_reg |= TLSBIT;
+        else
+                chip->ctl_reg &= ~TLSBIT;
+
+        /* Sport in master mode */
+        chip->ctl_reg |= ITCLK | ITFS | TFSR | LATFS | LTFS;
+
+        chip->baud = bfin_sport_hz_to_spi_baud(spi->max_speed_hz);
+
+        chip->cs_gpio = spi->chip_select;
+        ret = gpio_request(chip->cs_gpio, spi->modalias);
+        if (ret)
+                goto error;
+
+        dev_dbg(&spi->dev, "setup spi chip %s, width is %d\n",
+                        spi->modalias, spi->bits_per_word);
+        dev_dbg(&spi->dev, "ctl_reg is 0x%x, GPIO is %i\n",
+                        chip->ctl_reg, spi->chip_select);
+
+        spi_set_ctldata(spi, chip);
+
+        bfin_sport_spi_cs_deactive(chip);
+
+        return ret;
+
+ error:
+        kfree(first);
+        return ret;
+}
+
+/*
+ * callback for spi framework.
+ * clean driver specific data
+ */
+static void
+bfin_sport_spi_cleanup(struct spi_device *spi)
+{
+        struct bfin_sport_spi_slave_data *chip = spi_get_ctldata(spi);
+
+        if (!chip)
+                return;
+
+        gpio_free(chip->cs_gpio);
+
+        kfree(chip);
+}
+
+static int
+bfin_sport_spi_init_queue(struct bfin_sport_spi_master_data *drv_data)
+{
+        INIT_LIST_HEAD(&drv_data->queue);
+        spin_lock_init(&drv_data->lock);
+
+        drv_data->run = false;
+        drv_data->busy = 0;
+
+        /* init transfer tasklet */
+        tasklet_init(&drv_data->pump_transfers,
+                     bfin_sport_spi_pump_transfers, (unsigned long)drv_data);
+
+        /* init messages workqueue */
+        INIT_WORK(&drv_data->pump_messages, bfin_sport_spi_pump_messages);
+        drv_data->workqueue =
+            create_singlethread_workqueue(dev_name(drv_data->master->dev.parent));
+        if (drv_data->workqueue == NULL)
+                return -EBUSY;
+
+        return 0;
+}
+
+static int
+bfin_sport_spi_start_queue(struct bfin_sport_spi_master_data *drv_data)
+{
+        unsigned long flags;
+
+        spin_lock_irqsave(&drv_data->lock, flags);
+
+        if (drv_data->run || drv_data->busy) {
+                spin_unlock_irqrestore(&drv_data->lock, flags);
+                return -EBUSY;
+        }
+
+        drv_data->run = true;
+        drv_data->cur_msg = NULL;
+        drv_data->cur_transfer = NULL;
+        drv_data->cur_chip = NULL;
+        spin_unlock_irqrestore(&drv_data->lock, flags);
+
+        queue_work(drv_data->workqueue, &drv_data->pump_messages);
+
+        return 0;
+}
+
+static inline int
+bfin_sport_spi_stop_queue(struct bfin_sport_spi_master_data *drv_data)
+{
+        unsigned long flags;
+        unsigned limit = 500;
+        int status = 0;
+
+        spin_lock_irqsave(&drv_data->lock, flags);
+
+        /*
+         * This is a bit lame, but is optimized for the common execution path.
+         * A wait_queue on the drv_data->busy could be used, but then the common
+         * execution path (pump_messages) would be required to call wake_up or
+         * friends on every SPI message. Do this instead
+         */
+        drv_data->run = false;
+        while (!list_empty(&drv_data->queue) && drv_data->busy && limit--) {
+                spin_unlock_irqrestore(&drv_data->lock, flags);
+                msleep(10);
+                spin_lock_irqsave(&drv_data->lock, flags);
+        }
+
+        if (!list_empty(&drv_data->queue) || drv_data->busy)
+                status = -EBUSY;
+
+        spin_unlock_irqrestore(&drv_data->lock, flags);
+
+        return status;
+}
+
+static inline int
+bfin_sport_spi_destroy_queue(struct bfin_sport_spi_master_data *drv_data)
+{
+        int status;
+
+        status = bfin_sport_spi_stop_queue(drv_data);
+        if (status)
+                return status;
+
+        destroy_workqueue(drv_data->workqueue);
+
+        return 0;
+}
+
+static int __devinit
+bfin_sport_spi_probe(struct platform_device *pdev)
+{
+        struct device *dev = &pdev->dev;
+        struct bfin5xx_spi_master *platform_info;
+        struct spi_master *master;
+        struct resource *res, *ires;
+        struct bfin_sport_spi_master_data *drv_data;
+        int status;
+
+        platform_info = dev->platform_data;
+
+        /* Allocate master with space for drv_data */
+        master = spi_alloc_master(dev, sizeof(*master) + 16);
+        if (!master) {
+                dev_err(dev, "cannot alloc spi_master\n");
+                return -ENOMEM;
+        }
+
+        drv_data = spi_master_get_devdata(master);
+        drv_data->master = master;
+        drv_data->dev = dev;
+        drv_data->pin_req = platform_info->pin_req;
+
+        master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_LSB_FIRST;
+        master->bus_num = pdev->id;
+        master->num_chipselect = platform_info->num_chipselect;
+        master->cleanup = bfin_sport_spi_cleanup;
+        master->setup = bfin_sport_spi_setup;
+        master->transfer = bfin_sport_spi_transfer;
+
+        /* Find and map our resources */
+        res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+        if (res == NULL) {
+                dev_err(dev, "cannot get IORESOURCE_MEM\n");
+                status = -ENOENT;
+                goto out_error_get_res;
+        }
+
+        drv_data->regs = ioremap(res->start, resource_size(res));
+        if (drv_data->regs == NULL) {
+                dev_err(dev, "cannot map registers\n");
+                status = -ENXIO;
+                goto out_error_ioremap;
+        }
+
+        ires = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
+        if (!ires) {
+                dev_err(dev, "cannot get IORESOURCE_IRQ\n");
+                status = -ENODEV;
+                goto out_error_get_ires;
+        }
+        drv_data->err_irq = ires->start;
+
+        /* Initial and start queue */
+        status = bfin_sport_spi_init_queue(drv_data);
+        if (status) {
+                dev_err(dev, "problem initializing queue\n");
+                goto out_error_queue_alloc;
+        }
+
+        status = bfin_sport_spi_start_queue(drv_data);
+        if (status) {
+                dev_err(dev, "problem starting queue\n");
+                goto out_error_queue_alloc;
+        }
+
+        status = request_irq(drv_data->err_irq, sport_err_handler,
+                0, "sport_spi_err", drv_data);
+        if (status) {
+                dev_err(dev, "unable to request sport err irq\n");
+                goto out_error_irq;
+        }
+
+        status = peripheral_request_list(drv_data->pin_req, DRV_NAME);
+        if (status) {
+                dev_err(dev, "requesting peripherals failed\n");
+                goto out_error_peripheral;
+        }
+
+        /* Register with the SPI framework */
+        platform_set_drvdata(pdev, drv_data);
+        status = spi_register_master(master);
+        if (status) {
+                dev_err(dev, "problem registering spi master\n");
+                goto out_error_master;
+        }
+
+        dev_info(dev, "%s, regs_base@%p\n", DRV_DESC, drv_data->regs);
+        return 0;
+
+ out_error_master:
+        peripheral_free_list(drv_data->pin_req);
+ out_error_peripheral:
+        free_irq(drv_data->err_irq, drv_data);
+ out_error_irq:
+ out_error_queue_alloc:
+        bfin_sport_spi_destroy_queue(drv_data);
+ out_error_get_ires:
+        iounmap(drv_data->regs);
+ out_error_ioremap:
+ out_error_get_res:
+        spi_master_put(master);
+
+        return status;
+}
+
+/* stop hardware and remove the driver */
+static int __devexit
+bfin_sport_spi_remove(struct platform_device *pdev)
+{
+        struct bfin_sport_spi_master_data *drv_data = platform_get_drvdata(pdev);
+        int status = 0;
+
+        if (!drv_data)
+                return 0;
+
+        /* Remove the queue */
+        status = bfin_sport_spi_destroy_queue(drv_data);
+        if (status)
+                return status;
+
+        /* Disable the SSP at the peripheral and SOC level */
+        bfin_sport_spi_disable(drv_data);
+
+        /* Disconnect from the SPI framework */
+        spi_unregister_master(drv_data->master);
+
+        peripheral_free_list(drv_data->pin_req);
+
+        /* Prevent double remove */
+        platform_set_drvdata(pdev, NULL);
+
+        return 0;
+}
+
+#ifdef CONFIG_PM
+static int
+bfin_sport_spi_suspend(struct platform_device *pdev, pm_message_t state)
+{
+        struct bfin_sport_spi_master_data *drv_data = platform_get_drvdata(pdev);
+        int status;
+
+        status = bfin_sport_spi_stop_queue(drv_data);
+        if (status)
+                return status;
+
+        /* stop hardware */
+        bfin_sport_spi_disable(drv_data);
+
+        return status;
+}
+
+static int
+bfin_sport_spi_resume(struct platform_device *pdev)
+{
+        struct bfin_sport_spi_master_data *drv_data = platform_get_drvdata(pdev);
+        int status;
+
+        /* Enable the SPI interface */
+        bfin_sport_spi_enable(drv_data);
+
+        /* Start the queue running */
+        status = bfin_sport_spi_start_queue(drv_data);
+        if (status)
+                dev_err(drv_data->dev, "problem resuming queue\n");
+
+        return status;
+}
+#else
+# define bfin_sport_spi_suspend NULL
+# define bfin_sport_spi_resume  NULL
+#endif
+
+static struct platform_driver bfin_sport_spi_driver = {
+        .driver = {
+                .name = DRV_NAME,
+                .owner = THIS_MODULE,
+        },
+        .probe   = bfin_sport_spi_probe,
+        .remove  = __devexit_p(bfin_sport_spi_remove),
+        .suspend = bfin_sport_spi_suspend,
+        .resume  = bfin_sport_spi_resume,
+};
+
+static int __init bfin_sport_spi_init(void)
+{
+        return platform_driver_register(&bfin_sport_spi_driver);
+}
+module_init(bfin_sport_spi_init);
+
+static void __exit bfin_sport_spi_exit(void)
+{
+        platform_driver_unregister(&bfin_sport_spi_driver);
+}
+module_exit(bfin_sport_spi_exit);
diff --git a/drivers/spi/tle62x0.c b/drivers/spi/tle62x0.c
index a3938958147c..32a40876532f 100644
--- a/drivers/spi/tle62x0.c
+++ b/drivers/spi/tle62x0.c
@@ -283,7 +283,7 @@ static int __devinit tle62x0_probe(struct spi_device *spi)
         return 0;
 
  err_gpios:
-        for (; ptr > 0; ptr--)
+        while (--ptr >= 0)
                 device_remove_file(&spi->dev, gpio_attrs[ptr]);
 
         device_remove_file(&spi->dev, &dev_attr_status_show);
@@ -301,6 +301,7 @@ static int __devexit tle62x0_remove(struct spi_device *spi)
         for (ptr = 0; ptr < st->nr_gpio; ptr++)
                 device_remove_file(&spi->dev, gpio_attrs[ptr]);
 
+        device_remove_file(&spi->dev, &dev_attr_status_show);
         kfree(st);
         return 0;
 }
diff --git a/drivers/thermal/thermal_sys.c b/drivers/thermal/thermal_sys.c
index fc6f2a5bde01..0b1c82ad6805 100644
--- a/drivers/thermal/thermal_sys.c
+++ b/drivers/thermal/thermal_sys.c
@@ -499,7 +499,7 @@ thermal_add_hwmon_sysfs(struct thermal_zone_device *tz)
         dev_set_drvdata(hwmon->device, hwmon);
         result = device_create_file(hwmon->device, &dev_attr_name);
         if (result)
-                goto unregister_hwmon_device;
+                goto free_mem;
 
  register_sys_interface:
         tz->hwmon = hwmon;
@@ -513,7 +513,7 @@ thermal_add_hwmon_sysfs(struct thermal_zone_device *tz)
         sysfs_attr_init(&tz->temp_input.attr.attr);
         result = device_create_file(hwmon->device, &tz->temp_input.attr);
         if (result)
-                goto unregister_hwmon_device;
+                goto unregister_name;
 
         if (tz->ops->get_crit_temp) {
                 unsigned long temperature;
@@ -527,7 +527,7 @@ thermal_add_hwmon_sysfs(struct thermal_zone_device *tz)
                         result = device_create_file(hwmon->device,
                                                     &tz->temp_crit.attr);
                         if (result)
-                                goto unregister_hwmon_device;
+                                goto unregister_input;
                 }
         }
 
@@ -539,9 +539,9 @@ thermal_add_hwmon_sysfs(struct thermal_zone_device *tz)
 
         return 0;
 
- unregister_hwmon_device:
-        device_remove_file(hwmon->device, &tz->temp_crit.attr);
+ unregister_input:
         device_remove_file(hwmon->device, &tz->temp_input.attr);
+ unregister_name:
         if (new_hwmon_device) {
                 device_remove_file(hwmon->device, &dev_attr_name);
                 hwmon_device_unregister(hwmon->device);
diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c
index a4c42a75a3bf..09e8c7d53af3 100644
--- a/drivers/tty/n_gsm.c
+++ b/drivers/tty/n_gsm.c
@@ -2128,8 +2128,8 @@ static void gsmld_detach_gsm(struct tty_struct *tty, struct gsm_mux *gsm)
         gsm->tty = NULL;
 }
 
-static unsigned int gsmld_receive_buf(struct tty_struct *tty,
-                const unsigned char *cp, char *fp, int count)
+static void gsmld_receive_buf(struct tty_struct *tty, const unsigned char *cp,
+                              char *fp, int count)
 {
         struct gsm_mux *gsm = tty->disc_data;
         const unsigned char *dp;
@@ -2162,8 +2162,6 @@ static unsigned int gsmld_receive_buf(struct tty_struct *tty,
         }
         /* FASYNC if needed ? */
         /* If clogged call tty_throttle(tty); */
-
-        return count;
 }
 
 /**
diff --git a/drivers/tty/n_hdlc.c b/drivers/tty/n_hdlc.c
index cac666314aef..cea56033b34c 100644
--- a/drivers/tty/n_hdlc.c
+++ b/drivers/tty/n_hdlc.c
@@ -188,8 +188,8 @@ static unsigned int n_hdlc_tty_poll(struct tty_struct *tty, struct file *filp,
                                     poll_table *wait);
 static int n_hdlc_tty_open(struct tty_struct *tty);
 static void n_hdlc_tty_close(struct tty_struct *tty);
-static unsigned int n_hdlc_tty_receive(struct tty_struct *tty,
-                const __u8 *cp, char *fp, int count);
+static void n_hdlc_tty_receive(struct tty_struct *tty, const __u8 *cp,
+                               char *fp, int count);
 static void n_hdlc_tty_wakeup(struct tty_struct *tty);
 
 #define bset(p,b)       ((p)[(b) >> 5] |= (1 << ((b) & 0x1f)))
@@ -509,8 +509,8 @@ static void n_hdlc_tty_wakeup(struct tty_struct *tty)
  * Called by tty low level driver when receive data is available. Data is
  * interpreted as one HDLC frame.
  */
-static unsigned int n_hdlc_tty_receive(struct tty_struct *tty,
-                const __u8 *data, char *flags, int count)
+static void n_hdlc_tty_receive(struct tty_struct *tty, const __u8 *data,
+                               char *flags, int count)
 {
         register struct n_hdlc *n_hdlc = tty2n_hdlc (tty);
         register struct n_hdlc_buf *buf;
@@ -521,20 +521,20 @@ static unsigned int n_hdlc_tty_receive(struct tty_struct *tty,
                 
         /* This can happen if stuff comes in on the backup tty */
         if (!n_hdlc || tty != n_hdlc->tty)
-                return -ENODEV;
+                return;
                 
         /* verify line is using HDLC discipline */
         if (n_hdlc->magic != HDLC_MAGIC) {
                 printk("%s(%d) line not using HDLC discipline\n",
                         __FILE__,__LINE__);
-                return -EINVAL;
+                return;
         }
         
         if ( count>maxframe ) {
                 if (debuglevel >= DEBUG_LEVEL_INFO)     
                         printk("%s(%d) rx count>maxframesize, data discarded\n",
                                __FILE__,__LINE__);
-                return -EINVAL;
+                return;
         }
 
         /* get a free HDLC buffer */    
@@ -550,7 +550,7 @@ static unsigned int n_hdlc_tty_receive(struct tty_struct *tty,
                 if (debuglevel >= DEBUG_LEVEL_INFO)     
                         printk("%s(%d) no more rx buffers, data discarded\n",
                                __FILE__,__LINE__);
-                return -EINVAL;
+                return;
         }
                 
         /* copy received data to HDLC buffer */
@@ -565,8 +565,6 @@ static unsigned int n_hdlc_tty_receive(struct tty_struct *tty,
         if (n_hdlc->tty->fasync != NULL)
                 kill_fasync (&n_hdlc->tty->fasync, SIGIO, POLL_IN);
 
-        return count;
-
 }       /* end of n_hdlc_tty_receive() */
 
 /**
diff --git a/drivers/tty/n_r3964.c b/drivers/tty/n_r3964.c
index a4bc39c21a43..5c6c31459a2f 100644
--- a/drivers/tty/n_r3964.c
+++ b/drivers/tty/n_r3964.c
@@ -139,8 +139,8 @@ static int r3964_ioctl(struct tty_struct *tty, struct file *file,
 static void r3964_set_termios(struct tty_struct *tty, struct ktermios *old);
 static unsigned int r3964_poll(struct tty_struct *tty, struct file *file,
                 struct poll_table_struct *wait);
-static unsigned int r3964_receive_buf(struct tty_struct *tty,
-                const unsigned char *cp, char *fp, int count);
+static void r3964_receive_buf(struct tty_struct *tty, const unsigned char *cp,
+                char *fp, int count);
 
 static struct tty_ldisc_ops tty_ldisc_N_R3964 = {
         .owner = THIS_MODULE,
@@ -1239,8 +1239,8 @@ static unsigned int r3964_poll(struct tty_struct *tty, struct file *file,
         return result;
 }
 
-static unsigned int r3964_receive_buf(struct tty_struct *tty,
-                const unsigned char *cp, char *fp, int count)
+static void r3964_receive_buf(struct tty_struct *tty, const unsigned char *cp,
+                        char *fp, int count)
 {
         struct r3964_info *pInfo = tty->disc_data;
         const unsigned char *p;
@@ -1257,8 +1257,6 @@ static unsigned int r3964_receive_buf(struct tty_struct *tty,
                 }
 
         }
-
-        return count;
 }
 
 MODULE_LICENSE("GPL");
diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index 95d0a9c2dd13..0ad32888091c 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -81,6 +81,38 @@ static inline int tty_put_user(struct tty_struct *tty, unsigned char x,
         return put_user(x, ptr);
 }
 
+/**
+ *      n_tty_set__room -       receive space
+ *      @tty: terminal
+ *
+ *      Called by the driver to find out how much data it is
+ *      permitted to feed to the line discipline without any being lost
+ *      and thus to manage flow control. Not serialized. Answers for the
+ *      "instant".
+ */
+
+static void n_tty_set_room(struct tty_struct *tty)
+{
+        /* tty->read_cnt is not read locked ? */
+        int     left = N_TTY_BUF_SIZE - tty->read_cnt - 1;
+        int old_left;
+
+        /*
+         * If we are doing input canonicalization, and there are no
+         * pending newlines, let characters through without limit, so
+         * that erase characters will be handled.  Other excess
+         * characters will be beeped.
+         */
+        if (left <= 0)
+                left = tty->icanon && !tty->canon_data;
+        old_left = tty->receive_room;
+        tty->receive_room = left;
+
+        /* Did this open up the receive buffer? We may need to flip */
+        if (left && !old_left)
+                schedule_work(&tty->buf.work);
+}
+
 static void put_tty_queue_nolock(unsigned char c, struct tty_struct *tty)
 {
         if (tty->read_cnt < N_TTY_BUF_SIZE) {
@@ -152,6 +184,7 @@ static void reset_buffer_flags(struct tty_struct *tty)
 
         tty->canon_head = tty->canon_data = tty->erasing = 0;
         memset(&tty->read_flags, 0, sizeof tty->read_flags);
+        n_tty_set_room(tty);
         check_unthrottle(tty);
 }
 
@@ -1327,19 +1360,17 @@ static void n_tty_write_wakeup(struct tty_struct *tty)
  *      calls one at a time and in order (or using flush_to_ldisc)
  */
 
-static unsigned int n_tty_receive_buf(struct tty_struct *tty,
-                const unsigned char *cp, char *fp, int count)
+static void n_tty_receive_buf(struct tty_struct *tty, const unsigned char *cp,
+                              char *fp, int count)
 {
         const unsigned char *p;
         char *f, flags = TTY_NORMAL;
         int     i;
         char    buf[64];
         unsigned long cpuflags;
-        int left;
-        int ret = 0;
 
         if (!tty->read_buf)
-                return 0;
+                return;
 
         if (tty->real_raw) {
                 spin_lock_irqsave(&tty->read_lock, cpuflags);
@@ -1349,7 +1380,6 @@ static unsigned int n_tty_receive_buf(struct tty_struct *tty,
                 memcpy(tty->read_buf + tty->read_head, cp, i);
                 tty->read_head = (tty->read_head + i) & (N_TTY_BUF_SIZE-1);
                 tty->read_cnt += i;
-                ret += i;
                 cp += i;
                 count -= i;
 
@@ -1359,10 +1389,8 @@ static unsigned int n_tty_receive_buf(struct tty_struct *tty,
                 memcpy(tty->read_buf + tty->read_head, cp, i);
                 tty->read_head = (tty->read_head + i) & (N_TTY_BUF_SIZE-1);
                 tty->read_cnt += i;
-                ret += i;
                 spin_unlock_irqrestore(&tty->read_lock, cpuflags);
         } else {
-                ret = count;
                 for (i = count, p = cp, f = fp; i; i--, p++) {
                         if (f)
                                 flags = *f++;
@@ -1390,6 +1418,8 @@ static unsigned int n_tty_receive_buf(struct tty_struct *tty,
                         tty->ops->flush_chars(tty);
         }
 
+        n_tty_set_room(tty);
+
         if ((!tty->icanon && (tty->read_cnt >= tty->minimum_to_wake)) ||
                 L_EXTPROC(tty)) {
                 kill_fasync(&tty->fasync, SIGIO, POLL_IN);
@@ -1402,12 +1432,8 @@ static unsigned int n_tty_receive_buf(struct tty_struct *tty,
          * mode.  We don't want to throttle the driver if we're in
          * canonical mode and don't have a newline yet!
          */
-        left = N_TTY_BUF_SIZE - tty->read_cnt - 1;
-
-        if (left < TTY_THRESHOLD_THROTTLE)
+        if (tty->receive_room < TTY_THRESHOLD_THROTTLE)
                 tty_throttle(tty);
-
-        return ret;
 }
 
 int is_ignored(int sig)
@@ -1451,6 +1477,7 @@ static void n_tty_set_termios(struct tty_struct *tty, struct ktermios *old)
         if (test_bit(TTY_HW_COOK_IN, &tty->flags)) {
                 tty->raw = 1;
                 tty->real_raw = 1;
+                n_tty_set_room(tty);
                 return;
         }
         if (I_ISTRIP(tty) || I_IUCLC(tty) || I_IGNCR(tty) ||
@@ -1503,6 +1530,7 @@ static void n_tty_set_termios(struct tty_struct *tty, struct ktermios *old)
                 else
                         tty->real_raw = 0;
         }
+        n_tty_set_room(tty);
         /* The termios change make the tty ready for I/O */
         wake_up_interruptible(&tty->write_wait);
         wake_up_interruptible(&tty->read_wait);
@@ -1784,6 +1812,8 @@ do_it_again:
                                 retval = -ERESTARTSYS;
                                 break;
                         }
+                        /* FIXME: does n_tty_set_room need locking ? */
+                        n_tty_set_room(tty);
                         timeout = schedule_timeout(timeout);
                         continue;
                 }
@@ -1855,8 +1885,10 @@ do_it_again:
                  * longer than TTY_THRESHOLD_UNTHROTTLE in canonical mode,
                  * we won't get any more characters.
                  */
-                if (n_tty_chars_in_buffer(tty) <= TTY_THRESHOLD_UNTHROTTLE)
+                if (n_tty_chars_in_buffer(tty) <= TTY_THRESHOLD_UNTHROTTLE) {
+                        n_tty_set_room(tty);
                         check_unthrottle(tty);
+                }
 
                 if (b - buf >= minimum)
                         break;
@@ -1878,6 +1910,7 @@ do_it_again:
         } else if (test_and_clear_bit(TTY_PUSH, &tty->flags))
                  goto do_it_again;
 
+        n_tty_set_room(tty);
         return retval;
 }
 
diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c
index 46de2e075dac..f1a7918d71aa 100644
--- a/drivers/tty/tty_buffer.c
+++ b/drivers/tty/tty_buffer.c
@@ -416,7 +416,6 @@ static void flush_to_ldisc(struct work_struct *work)
                 struct tty_buffer *head, *tail = tty->buf.tail;
                 int seen_tail = 0;
                 while ((head = tty->buf.head) != NULL) {
-                        int copied;
                         int count;
                         char *char_buf;
                         unsigned char *flag_buf;
@@ -443,19 +442,17 @@ static void flush_to_ldisc(struct work_struct *work)
                            line discipline as we want to empty the queue */
                         if (test_bit(TTY_FLUSHPENDING, &tty->flags))
                                 break;
+                        if (!tty->receive_room || seen_tail)
+                                break;
+                        if (count > tty->receive_room)
+                                count = tty->receive_room;
                         char_buf = head->char_buf_ptr + head->read;
                         flag_buf = head->flag_buf_ptr + head->read;
+                        head->read += count;
                         spin_unlock_irqrestore(&tty->buf.lock, flags);
-                        copied = disc->ops->receive_buf(tty, char_buf,
+                        disc->ops->receive_buf(tty, char_buf,
                                                         flag_buf, count);
                         spin_lock_irqsave(&tty->buf.lock, flags);
-
-                        head->read += copied;
-
-                        if (copied == 0 || seen_tail) {
-                                schedule_work(&tty->buf.work);
-                                break;
-                        }
                 }
                 clear_bit(TTY_FLUSHING, &tty->flags);
         }
diff --git a/drivers/tty/vt/selection.c b/drivers/tty/vt/selection.c
index 67b1d0d7c8ac..fb864e7fcd13 100644
--- a/drivers/tty/vt/selection.c
+++ b/drivers/tty/vt/selection.c
@@ -332,7 +332,8 @@ int paste_selection(struct tty_struct *tty)
                         continue;
                 }
                 count = sel_buffer_lth - pasted;
-                count = tty->ldisc->ops->receive_buf(tty, sel_buffer + pasted,
+                count = min(count, tty->receive_room);
+                tty->ldisc->ops->receive_buf(tty, sel_buffer + pasted,
                                                                 NULL, count);
                 pasted += count;
         }
diff --git a/drivers/usb/host/ehci-pci.c b/drivers/usb/host/ehci-pci.c
index 660b80a75cac..1102ce65a3a9 100644
--- a/drivers/usb/host/ehci-pci.c
+++ b/drivers/usb/host/ehci-pci.c
@@ -348,11 +348,50 @@ static int ehci_pci_suspend(struct usb_hcd *hcd, bool do_wakeup)
         return rc;
 }
 
+static bool usb_is_intel_switchable_ehci(struct pci_dev *pdev)
+{
+        return pdev->class == PCI_CLASS_SERIAL_USB_EHCI &&
+                pdev->vendor == PCI_VENDOR_ID_INTEL &&
+                pdev->device == 0x1E26;
+}
+
+static void ehci_enable_xhci_companion(void)
+{
+        struct pci_dev          *companion = NULL;
+
+        /* The xHCI and EHCI controllers are not on the same PCI slot */
+        for_each_pci_dev(companion) {
+                if (!usb_is_intel_switchable_xhci(companion))
+                        continue;
+                usb_enable_xhci_ports(companion);
+                return;
+        }
+}
+
 static int ehci_pci_resume(struct usb_hcd *hcd, bool hibernated)
 {
         struct ehci_hcd         *ehci = hcd_to_ehci(hcd);
         struct pci_dev          *pdev = to_pci_dev(hcd->self.controller);
 
+        /* The BIOS on systems with the Intel Panther Point chipset may or may
+         * not support xHCI natively.  That means that during system resume, it
+         * may switch the ports back to EHCI so that users can use their
+         * keyboard to select a kernel from GRUB after resume from hibernate.
+         *
+         * The BIOS is supposed to remember whether the OS had xHCI ports
+         * enabled before resume, and switch the ports back to xHCI when the
+         * BIOS/OS semaphore is written, but we all know we can't trust BIOS
+         * writers.
+         *
+         * Unconditionally switch the ports back to xHCI after a system resume.
+         * We can't tell whether the EHCI or xHCI controller will be resumed
+         * first, so we have to do the port switchover in both drivers.  Writing
+         * a '1' to the port switchover registers should have no effect if the
+         * port was already switched over.
+         */
+        if (usb_is_intel_switchable_ehci(pdev))
+                ehci_enable_xhci_companion();
+
         // maybe restore FLADJ
 
         if (time_before(jiffies, ehci->next_statechange))
diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c
index f16c59d5f487..fd930618c28f 100644
--- a/drivers/usb/host/pci-quirks.c
+++ b/drivers/usb/host/pci-quirks.c
@@ -69,6 +69,9 @@
 #define NB_PIF0_PWRDOWN_0       0x01100012
 #define NB_PIF0_PWRDOWN_1       0x01100013
 
+#define USB_INTEL_XUSB2PR      0xD0
+#define USB_INTEL_USB3_PSSEN   0xD8
+
 static struct amd_chipset_info {
         struct pci_dev  *nb_dev;
         struct pci_dev  *smbus_dev;
@@ -673,6 +676,64 @@ static int handshake(void __iomem *ptr, u32 mask, u32 done,
         return -ETIMEDOUT;
 }
 
+bool usb_is_intel_switchable_xhci(struct pci_dev *pdev)
+{
+        return pdev->class == PCI_CLASS_SERIAL_USB_XHCI &&
+                pdev->vendor == PCI_VENDOR_ID_INTEL &&
+                pdev->device == PCI_DEVICE_ID_INTEL_PANTHERPOINT_XHCI;
+}
+EXPORT_SYMBOL_GPL(usb_is_intel_switchable_xhci);
+
+/*
+ * Intel's Panther Point chipset has two host controllers (EHCI and xHCI) that
+ * share some number of ports.  These ports can be switched between either
+ * controller.  Not all of the ports under the EHCI host controller may be
+ * switchable.
+ *
+ * The ports should be switched over to xHCI before PCI probes for any device
+ * start.  This avoids active devices under EHCI being disconnected during the
+ * port switchover, which could cause loss of data on USB storage devices, or
+ * failed boot when the root file system is on a USB mass storage device and is
+ * enumerated under EHCI first.
+ *
+ * We write into the xHC's PCI configuration space in some Intel-specific
+ * registers to switch the ports over.  The USB 3.0 terminations and the USB
+ * 2.0 data wires are switched separately.  We want to enable the SuperSpeed
+ * terminations before switching the USB 2.0 wires over, so that USB 3.0
+ * devices connect at SuperSpeed, rather than at USB 2.0 speeds.
+ */
+void usb_enable_xhci_ports(struct pci_dev *xhci_pdev)
+{
+        u32             ports_available;
+
+        ports_available = 0xffffffff;
+        /* Write USB3_PSSEN, the USB 3.0 Port SuperSpeed Enable
+         * Register, to turn on SuperSpeed terminations for all
+         * available ports.
+         */
+        pci_write_config_dword(xhci_pdev, USB_INTEL_USB3_PSSEN,
+                        cpu_to_le32(ports_available));
+
+        pci_read_config_dword(xhci_pdev, USB_INTEL_USB3_PSSEN,
+                        &ports_available);
+        dev_dbg(&xhci_pdev->dev, "USB 3.0 ports that are now enabled "
+                        "under xHCI: 0x%x\n", ports_available);
+
+        ports_available = 0xffffffff;
+        /* Write XUSB2PR, the xHC USB 2.0 Port Routing Register, to
+         * switch the USB 2.0 power and data lines over to the xHCI
+         * host.
+         */
+        pci_write_config_dword(xhci_pdev, USB_INTEL_XUSB2PR,
+                        cpu_to_le32(ports_available));
+
+        pci_read_config_dword(xhci_pdev, USB_INTEL_XUSB2PR,
+                        &ports_available);
+        dev_dbg(&xhci_pdev->dev, "USB 2.0 ports that are now switched over "
+                        "to xHCI: 0x%x\n", ports_available);
+}
+EXPORT_SYMBOL_GPL(usb_enable_xhci_ports);
+
 /**
  * PCI Quirks for xHCI.
  *
@@ -732,6 +793,8 @@ static void __devinit quirk_usb_handoff_xhci(struct pci_dev *pdev)
         writel(XHCI_LEGACY_DISABLE_SMI,
                         base + ext_cap_offset + XHCI_LEGACY_CONTROL_OFFSET);
 
+        if (usb_is_intel_switchable_xhci(pdev))
+                usb_enable_xhci_ports(pdev);
 hc_init:
         op_reg_base = base + XHCI_HC_LENGTH(readl(base));
 
diff --git a/drivers/usb/host/pci-quirks.h b/drivers/usb/host/pci-quirks.h
index 6ae9f78e9938..b1002a8ef96f 100644
--- a/drivers/usb/host/pci-quirks.h
+++ b/drivers/usb/host/pci-quirks.h
@@ -8,6 +8,8 @@ int usb_amd_find_chipset_info(void);
 void usb_amd_dev_put(void);
 void usb_amd_quirk_pll_disable(void);
 void usb_amd_quirk_pll_enable(void);
+bool usb_is_intel_switchable_xhci(struct pci_dev *pdev);
+void usb_enable_xhci_ports(struct pci_dev *xhci_pdev);
 #else
 static inline void usb_amd_quirk_pll_disable(void) {}
 static inline void usb_amd_quirk_pll_enable(void) {}
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index cbc4d491e626..c408e9f6a707 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -118,6 +118,12 @@ static int xhci_pci_setup(struct usb_hcd *hcd)
         /* AMD PLL quirk */
         if (pdev->vendor == PCI_VENDOR_ID_AMD && usb_amd_find_chipset_info())
                 xhci->quirks |= XHCI_AMD_PLL_FIX;
+        if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
+                        pdev->device == PCI_DEVICE_ID_INTEL_PANTHERPOINT_XHCI) {
+                xhci->quirks |= XHCI_SPURIOUS_SUCCESS;
+                xhci->quirks |= XHCI_EP_LIMIT_QUIRK;
+                xhci->limit_active_eps = 64;
+        }
 
         /* Make sure the HC is halted. */
         retval = xhci_halt(xhci);
@@ -242,8 +248,28 @@ static int xhci_pci_suspend(struct usb_hcd *hcd, bool do_wakeup)
 static int xhci_pci_resume(struct usb_hcd *hcd, bool hibernated)
 {
         struct xhci_hcd         *xhci = hcd_to_xhci(hcd);
+        struct pci_dev          *pdev = to_pci_dev(hcd->self.controller);
         int                     retval = 0;
 
+        /* The BIOS on systems with the Intel Panther Point chipset may or may
+         * not support xHCI natively.  That means that during system resume, it
+         * may switch the ports back to EHCI so that users can use their
+         * keyboard to select a kernel from GRUB after resume from hibernate.
+         *
+         * The BIOS is supposed to remember whether the OS had xHCI ports
+         * enabled before resume, and switch the ports back to xHCI when the
+         * BIOS/OS semaphore is written, but we all know we can't trust BIOS
+         * writers.
+         *
+         * Unconditionally switch the ports back to xHCI after a system resume.
+         * We can't tell whether the EHCI or xHCI controller will be resumed
+         * first, so we have to do the port switchover in both drivers.  Writing
+         * a '1' to the port switchover registers should have no effect if the
+         * port was already switched over.
+         */
+        if (usb_is_intel_switchable_xhci(pdev))
+                usb_enable_xhci_ports(pdev);
+
         retval = xhci_resume(xhci, hibernated);
         return retval;
 }
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 237a765f8d18..cc1485bfed38 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -167,12 +167,6 @@ static void inc_deq(struct xhci_hcd *xhci, struct xhci_ring *ring, bool consumer
                 next = ring->dequeue;
         }
         addr = (unsigned long long) xhci_trb_virt_to_dma(ring->deq_seg, ring->dequeue);
-        if (ring == xhci->event_ring)
-                xhci_dbg(xhci, "Event ring deq = 0x%llx (DMA)\n", addr);
-        else if (ring == xhci->cmd_ring)
-                xhci_dbg(xhci, "Command ring deq = 0x%llx (DMA)\n", addr);
-        else
-                xhci_dbg(xhci, "Ring deq = 0x%llx (DMA)\n", addr);
 }
 
 /*
@@ -248,12 +242,6 @@ static void inc_enq(struct xhci_hcd *xhci, struct xhci_ring *ring,
                 next = ring->enqueue;
         }
         addr = (unsigned long long) xhci_trb_virt_to_dma(ring->enq_seg, ring->enqueue);
-        if (ring == xhci->event_ring)
-                xhci_dbg(xhci, "Event ring enq = 0x%llx (DMA)\n", addr);
-        else if (ring == xhci->cmd_ring)
-                xhci_dbg(xhci, "Command ring enq = 0x%llx (DMA)\n", addr);
-        else
-                xhci_dbg(xhci, "Ring enq = 0x%llx (DMA)\n", addr);
 }
 
 /*
@@ -636,13 +624,11 @@ static void xhci_giveback_urb_in_irq(struct xhci_hcd *xhci,
                         }
                 }
                 usb_hcd_unlink_urb_from_ep(hcd, urb);
-                xhci_dbg(xhci, "Giveback %s URB %p\n", adjective, urb);
 
                 spin_unlock(&xhci->lock);
                 usb_hcd_giveback_urb(hcd, urb, status);
                 xhci_urb_free_priv(xhci, urb_priv);
                 spin_lock(&xhci->lock);
-                xhci_dbg(xhci, "%s URB given back\n", adjective);
         }
 }
 
@@ -692,6 +678,8 @@ static void handle_stopped_endpoint(struct xhci_hcd *xhci,
 
         if (list_empty(&ep->cancelled_td_list)) {
                 xhci_stop_watchdog_timer_in_irq(xhci, ep);
+                ep->stopped_td = NULL;
+                ep->stopped_trb = NULL;
                 ring_doorbell_for_active_rings(xhci, slot_id, ep_index);
                 return;
         }
@@ -1093,8 +1081,13 @@ static void handle_cmd_completion(struct xhci_hcd *xhci,
                 complete(&xhci->addr_dev);
                 break;
         case TRB_TYPE(TRB_DISABLE_SLOT):
-                if (xhci->devs[slot_id])
+                if (xhci->devs[slot_id]) {
+                        if (xhci->quirks & XHCI_EP_LIMIT_QUIRK)
+                                /* Delete default control endpoint resources */
+                                xhci_free_device_endpoint_resources(xhci,
+                                                xhci->devs[slot_id], true);
                         xhci_free_virt_device(xhci, slot_id);
+                }
                 break;
         case TRB_TYPE(TRB_CONFIG_EP):
                 virt_dev = xhci->devs[slot_id];
@@ -1630,7 +1623,6 @@ static int process_ctrl_td(struct xhci_hcd *xhci, struct xhci_td *td,
                                         "without IOC set??\n");
                         *status = -ESHUTDOWN;
                 } else {
-                        xhci_dbg(xhci, "Successful control transfer!\n");
                         *status = 0;
                 }
                 break;
@@ -1727,7 +1719,6 @@ static int process_isoc_td(struct xhci_hcd *xhci, struct xhci_td *td,
         switch (trb_comp_code) {
         case COMP_SUCCESS:
                 frame->status = 0;
-                xhci_dbg(xhci, "Successful isoc transfer!\n");
                 break;
         case COMP_SHORT_TX:
                 frame->status = td->urb->transfer_flags & URB_SHORT_NOT_OK ?
@@ -1837,12 +1828,6 @@ static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_td *td,
                         else
                                 *status = 0;
                 } else {
-                        if (usb_endpoint_xfer_bulk(&td->urb->ep->desc))
-                                xhci_dbg(xhci, "Successful bulk "
-                                                "transfer!\n");
-                        else
-                                xhci_dbg(xhci, "Successful interrupt "
-                                                "transfer!\n");
                         *status = 0;
                 }
                 break;
@@ -1856,11 +1841,12 @@ static int process_bulk_intr_td(struct xhci_hcd *xhci, struct xhci_td *td,
                 /* Others already handled above */
                 break;
         }
-        xhci_dbg(xhci, "ep %#x - asked for %d bytes, "
-                        "%d bytes untransferred\n",
-                        td->urb->ep->desc.bEndpointAddress,
-                        td->urb->transfer_buffer_length,
-                 TRB_LEN(le32_to_cpu(event->transfer_len)));
+        if (trb_comp_code == COMP_SHORT_TX)
+                xhci_dbg(xhci, "ep %#x - asked for %d bytes, "
+                                "%d bytes untransferred\n",
+                                td->urb->ep->desc.bEndpointAddress,
+                                td->urb->transfer_buffer_length,
+                                TRB_LEN(le32_to_cpu(event->transfer_len)));
         /* Fast path - was this the last TRB in the TD for this URB? */
         if (event_trb == td->last_trb) {
                 if (TRB_LEN(le32_to_cpu(event->transfer_len)) != 0) {
@@ -1954,7 +1940,6 @@ static int handle_tx_event(struct xhci_hcd *xhci,
 
         /* Endpoint ID is 1 based, our index is zero based */
         ep_index = TRB_TO_EP_ID(le32_to_cpu(event->flags)) - 1;
-        xhci_dbg(xhci, "%s - ep index = %d\n", __func__, ep_index);
         ep = &xdev->eps[ep_index];
         ep_ring = xhci_dma_to_transfer_ring(ep, le64_to_cpu(event->buffer));
         ep_ctx = xhci_get_ep_ctx(xhci, xdev->out_ctx, ep_index);
@@ -2081,6 +2066,16 @@ static int handle_tx_event(struct xhci_hcd *xhci,
                 if (!event_seg) {
                         if (!ep->skip ||
                             !usb_endpoint_xfer_isoc(&td->urb->ep->desc)) {
+                                /* Some host controllers give a spurious
+                                 * successful event after a short transfer.
+                                 * Ignore it.
+                                 */
+                                if ((xhci->quirks & XHCI_SPURIOUS_SUCCESS) && 
+                                                ep_ring->last_td_was_short) {
+                                        ep_ring->last_td_was_short = false;
+                                        ret = 0;
+                                        goto cleanup;
+                                }
                                 /* HC is busted, give up! */
                                 xhci_err(xhci,
                                         "ERROR Transfer event TRB DMA ptr not "
@@ -2091,6 +2086,10 @@ static int handle_tx_event(struct xhci_hcd *xhci,
                         ret = skip_isoc_td(xhci, td, event, ep, &status);
                         goto cleanup;
                 }
+                if (trb_comp_code == COMP_SHORT_TX)
+                        ep_ring->last_td_was_short = true;
+                else
+                        ep_ring->last_td_was_short = false;
 
                 if (ep->skip) {
                         xhci_dbg(xhci, "Found td. Clear skip flag.\n");
@@ -2149,9 +2148,15 @@ cleanup:
                                 xhci_urb_free_priv(xhci, urb_priv);
 
                         usb_hcd_unlink_urb_from_ep(bus_to_hcd(urb->dev->bus), urb);
-                        xhci_dbg(xhci, "Giveback URB %p, len = %d, "
-                                        "status = %d\n",
-                                        urb, urb->actual_length, status);
+                        if ((urb->actual_length != urb->transfer_buffer_length &&
+                                                (urb->transfer_flags &
+                                                 URB_SHORT_NOT_OK)) ||
+                                        status != 0)
+                                xhci_dbg(xhci, "Giveback URB %p, len = %d, "
+                                                "expected = %x, status = %d\n",
+                                                urb, urb->actual_length,
+                                                urb->transfer_buffer_length,
+                                                status);
                         spin_unlock(&xhci->lock);
                         usb_hcd_giveback_urb(bus_to_hcd(urb->dev->bus), urb, status);
                         spin_lock(&xhci->lock);
@@ -2180,7 +2185,6 @@ static int xhci_handle_event(struct xhci_hcd *xhci)
         int update_ptrs = 1;
         int ret;
 
-        xhci_dbg(xhci, "In %s\n", __func__);
         if (!xhci->event_ring || !xhci->event_ring->dequeue) {
                 xhci->error_bitmask |= 1 << 1;
                 return 0;
@@ -2193,7 +2197,6 @@ static int xhci_handle_event(struct xhci_hcd *xhci)
                 xhci->error_bitmask |= 1 << 2;
                 return 0;
         }
-        xhci_dbg(xhci, "%s - OS owns TRB\n", __func__);
 
         /*
          * Barrier between reading the TRB_CYCLE (valid) flag above and any
@@ -2203,20 +2206,14 @@ static int xhci_handle_event(struct xhci_hcd *xhci)
         /* FIXME: Handle more event types. */
         switch ((le32_to_cpu(event->event_cmd.flags) & TRB_TYPE_BITMASK)) {
         case TRB_TYPE(TRB_COMPLETION):
-                xhci_dbg(xhci, "%s - calling handle_cmd_completion\n", __func__);
                 handle_cmd_completion(xhci, &event->event_cmd);
-                xhci_dbg(xhci, "%s - returned from handle_cmd_completion\n", __func__);
                 break;
         case TRB_TYPE(TRB_PORT_STATUS):
-                xhci_dbg(xhci, "%s - calling handle_port_status\n", __func__);
                 handle_port_status(xhci, event);
-                xhci_dbg(xhci, "%s - returned from handle_port_status\n", __func__);
                 update_ptrs = 0;
                 break;
         case TRB_TYPE(TRB_TRANSFER):
-                xhci_dbg(xhci, "%s - calling handle_tx_event\n", __func__);
                 ret = handle_tx_event(xhci, &event->trans_event);
-                xhci_dbg(xhci, "%s - returned from handle_tx_event\n", __func__);
                 if (ret < 0)
                         xhci->error_bitmask |= 1 << 9;
                 else
@@ -2273,16 +2270,6 @@ irqreturn_t xhci_irq(struct usb_hcd *hcd)
                 spin_unlock(&xhci->lock);
                 return IRQ_NONE;
         }
-        xhci_dbg(xhci, "op reg status = %08x\n", status);
-        xhci_dbg(xhci, "Event ring dequeue ptr:\n");
-        xhci_dbg(xhci, "@%llx %08x %08x %08x %08x\n",
-                 (unsigned long long)
-                 xhci_trb_virt_to_dma(xhci->event_ring->deq_seg, trb),
-                 lower_32_bits(le64_to_cpu(trb->link.segment_ptr)),
-                 upper_32_bits(le64_to_cpu(trb->link.segment_ptr)),
-                 (unsigned int) le32_to_cpu(trb->link.intr_target),
-                 (unsigned int) le32_to_cpu(trb->link.control));
-
         if (status & STS_FATAL) {
                 xhci_warn(xhci, "WARNING: Host System Error\n");
                 xhci_halt(xhci);
@@ -2397,7 +2384,6 @@ static int prepare_ring(struct xhci_hcd *xhci, struct xhci_ring *ep_ring,
                 u32 ep_state, unsigned int num_trbs, gfp_t mem_flags)
 {
         /* Make sure the endpoint has been added to xHC schedule */
-        xhci_dbg(xhci, "Endpoint state = 0x%x\n", ep_state);
         switch (ep_state) {
         case EP_STATE_DISABLED:
                 /*
@@ -2434,7 +2420,6 @@ static int prepare_ring(struct xhci_hcd *xhci, struct xhci_ring *ep_ring,
                 struct xhci_ring *ring = ep_ring;
                 union xhci_trb *next;
 
-                xhci_dbg(xhci, "prepare_ring: pointing to link trb\n");
                 next = ring->enqueue;
 
                 while (last_trb(xhci, ring, ring->enq_seg, next)) {
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 8f2a56ece44f..d9660eb97eb9 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -1314,8 +1314,10 @@ int xhci_drop_endpoint(struct usb_hcd *hcd, struct usb_device *udev,
         if (ret <= 0)
                 return ret;
         xhci = hcd_to_xhci(hcd);
-        xhci_dbg(xhci, "%s called for udev %p\n", __func__, udev);
+        if (xhci->xhc_state & XHCI_STATE_DYING)
+                return -ENODEV;
 
+        xhci_dbg(xhci, "%s called for udev %p\n", __func__, udev);
         drop_flag = xhci_get_endpoint_flag(&ep->desc);
         if (drop_flag == SLOT_FLAG || drop_flag == EP0_FLAG) {
                 xhci_dbg(xhci, "xHCI %s - can't drop slot or ep 0 %#x\n",
@@ -1401,6 +1403,8 @@ int xhci_add_endpoint(struct usb_hcd *hcd, struct usb_device *udev,
                 return ret;
         }
         xhci = hcd_to_xhci(hcd);
+        if (xhci->xhc_state & XHCI_STATE_DYING)
+                return -ENODEV;
 
         added_ctxs = xhci_get_endpoint_flag(&ep->desc);
         last_ctx = xhci_last_valid_endpoint(added_ctxs);
@@ -1578,6 +1582,113 @@ static int xhci_evaluate_context_result(struct xhci_hcd *xhci,
         return ret;
 }
 
+static u32 xhci_count_num_new_endpoints(struct xhci_hcd *xhci,
+                struct xhci_container_ctx *in_ctx)
+{
+        struct xhci_input_control_ctx *ctrl_ctx;
+        u32 valid_add_flags;
+        u32 valid_drop_flags;
+
+        ctrl_ctx = xhci_get_input_control_ctx(xhci, in_ctx);
+        /* Ignore the slot flag (bit 0), and the default control endpoint flag
+         * (bit 1).  The default control endpoint is added during the Address
+         * Device command and is never removed until the slot is disabled.
+         */
+        valid_add_flags = ctrl_ctx->add_flags >> 2;
+        valid_drop_flags = ctrl_ctx->drop_flags >> 2;
+
+        /* Use hweight32 to count the number of ones in the add flags, or
+         * number of endpoints added.  Don't count endpoints that are changed
+         * (both added and dropped).
+         */
+        return hweight32(valid_add_flags) -
+                hweight32(valid_add_flags & valid_drop_flags);
+}
+
+static unsigned int xhci_count_num_dropped_endpoints(struct xhci_hcd *xhci,
+                struct xhci_container_ctx *in_ctx)
+{
+        struct xhci_input_control_ctx *ctrl_ctx;
+        u32 valid_add_flags;
+        u32 valid_drop_flags;
+
+        ctrl_ctx = xhci_get_input_control_ctx(xhci, in_ctx);
+        valid_add_flags = ctrl_ctx->add_flags >> 2;
+        valid_drop_flags = ctrl_ctx->drop_flags >> 2;
+
+        return hweight32(valid_drop_flags) -
+                hweight32(valid_add_flags & valid_drop_flags);
+}
+
+/*
+ * We need to reserve the new number of endpoints before the configure endpoint
+ * command completes.  We can't subtract the dropped endpoints from the number
+ * of active endpoints until the command completes because we can oversubscribe
+ * the host in this case:
+ *
+ *  - the first configure endpoint command drops more endpoints than it adds
+ *  - a second configure endpoint command that adds more endpoints is queued
+ *  - the first configure endpoint command fails, so the config is unchanged
+ *  - the second command may succeed, even though there isn't enough resources
+ *
+ * Must be called with xhci->lock held.
+ */
+static int xhci_reserve_host_resources(struct xhci_hcd *xhci,
+                struct xhci_container_ctx *in_ctx)
+{
+        u32 added_eps;
+
+        added_eps = xhci_count_num_new_endpoints(xhci, in_ctx);
+        if (xhci->num_active_eps + added_eps > xhci->limit_active_eps) {
+                xhci_dbg(xhci, "Not enough ep ctxs: "
+                                "%u active, need to add %u, limit is %u.\n",
+                                xhci->num_active_eps, added_eps,
+                                xhci->limit_active_eps);
+                return -ENOMEM;
+        }
+        xhci->num_active_eps += added_eps;
+        xhci_dbg(xhci, "Adding %u ep ctxs, %u now active.\n", added_eps,
+                        xhci->num_active_eps);
+        return 0;
+}
+
+/*
+ * The configure endpoint was failed by the xHC for some other reason, so we
+ * need to revert the resources that failed configuration would have used.
+ *
+ * Must be called with xhci->lock held.
+ */
+static void xhci_free_host_resources(struct xhci_hcd *xhci,
+                struct xhci_container_ctx *in_ctx)
+{
+        u32 num_failed_eps;
+
+        num_failed_eps = xhci_count_num_new_endpoints(xhci, in_ctx);
+        xhci->num_active_eps -= num_failed_eps;
+        xhci_dbg(xhci, "Removing %u failed ep ctxs, %u now active.\n",
+                        num_failed_eps,
+                        xhci->num_active_eps);
+}
+
+/*
+ * Now that the command has completed, clean up the active endpoint count by
+ * subtracting out the endpoints that were dropped (but not changed).
+ *
+ * Must be called with xhci->lock held.
+ */
+static void xhci_finish_resource_reservation(struct xhci_hcd *xhci,
+                struct xhci_container_ctx *in_ctx)
+{
+        u32 num_dropped_eps;
+
+        num_dropped_eps = xhci_count_num_dropped_endpoints(xhci, in_ctx);
+        xhci->num_active_eps -= num_dropped_eps;
+        if (num_dropped_eps)
+                xhci_dbg(xhci, "Removing %u dropped ep ctxs, %u now active.\n",
+                                num_dropped_eps,
+                                xhci->num_active_eps);
+}
+
 /* Issue a configure endpoint command or evaluate context command
  * and wait for it to finish.
  */
@@ -1598,6 +1709,15 @@ static int xhci_configure_endpoint(struct xhci_hcd *xhci,
         virt_dev = xhci->devs[udev->slot_id];
         if (command) {
                 in_ctx = command->in_ctx;
+                if ((xhci->quirks & XHCI_EP_LIMIT_QUIRK) &&
+                                xhci_reserve_host_resources(xhci, in_ctx)) {
+                        spin_unlock_irqrestore(&xhci->lock, flags);
+                        xhci_warn(xhci, "Not enough host resources, "
+                                        "active endpoint contexts = %u\n",
+                                        xhci->num_active_eps);
+                        return -ENOMEM;
+                }
+
                 cmd_completion = command->completion;
                 cmd_status = &command->status;
                 command->command_trb = xhci->cmd_ring->enqueue;
@@ -1613,6 +1733,14 @@ static int xhci_configure_endpoint(struct xhci_hcd *xhci,
                 list_add_tail(&command->cmd_list, &virt_dev->cmd_list);
         } else {
                 in_ctx = virt_dev->in_ctx;
+                if ((xhci->quirks & XHCI_EP_LIMIT_QUIRK) &&
+                                xhci_reserve_host_resources(xhci, in_ctx)) {
+                        spin_unlock_irqrestore(&xhci->lock, flags);
+                        xhci_warn(xhci, "Not enough host resources, "
+                                        "active endpoint contexts = %u\n",
+                                        xhci->num_active_eps);
+                        return -ENOMEM;
+                }
                 cmd_completion = &virt_dev->cmd_completion;
                 cmd_status = &virt_dev->cmd_status;
         }
@@ -1627,6 +1755,8 @@ static int xhci_configure_endpoint(struct xhci_hcd *xhci,
         if (ret < 0) {
                 if (command)
                         list_del(&command->cmd_list);
+                if ((xhci->quirks & XHCI_EP_LIMIT_QUIRK))
+                        xhci_free_host_resources(xhci, in_ctx);
                 spin_unlock_irqrestore(&xhci->lock, flags);
                 xhci_dbg(xhci, "FIXME allocate a new ring segment\n");
                 return -ENOMEM;
@@ -1649,8 +1779,22 @@ static int xhci_configure_endpoint(struct xhci_hcd *xhci,
         }
 
         if (!ctx_change)
-                return xhci_configure_endpoint_result(xhci, udev, cmd_status);
-        return xhci_evaluate_context_result(xhci, udev, cmd_status);
+                ret = xhci_configure_endpoint_result(xhci, udev, cmd_status);
+        else
+                ret = xhci_evaluate_context_result(xhci, udev, cmd_status);
+
+        if ((xhci->quirks & XHCI_EP_LIMIT_QUIRK)) {
+                spin_lock_irqsave(&xhci->lock, flags);
+                /* If the command failed, remove the reserved resources.
+                 * Otherwise, clean up the estimate to include dropped eps.
+                 */
+                if (ret)
+                        xhci_free_host_resources(xhci, in_ctx);
+                else
+                        xhci_finish_resource_reservation(xhci, in_ctx);
+                spin_unlock_irqrestore(&xhci->lock, flags);
+        }
+        return ret;
 }
 
 /* Called after one or more calls to xhci_add_endpoint() or
@@ -1676,6 +1820,8 @@ int xhci_check_bandwidth(struct usb_hcd *hcd, struct usb_device *udev)
         if (ret <= 0)
                 return ret;
         xhci = hcd_to_xhci(hcd);
+        if (xhci->xhc_state & XHCI_STATE_DYING)
+                return -ENODEV;
 
         xhci_dbg(xhci, "%s called for udev %p\n", __func__, udev);
         virt_dev = xhci->devs[udev->slot_id];
@@ -2266,6 +2412,34 @@ int xhci_free_streams(struct usb_hcd *hcd, struct usb_device *udev,
 }
 
 /*
+ * Deletes endpoint resources for endpoints that were active before a Reset
+ * Device command, or a Disable Slot command.  The Reset Device command leaves
+ * the control endpoint intact, whereas the Disable Slot command deletes it.
+ *
+ * Must be called with xhci->lock held.
+ */
+void xhci_free_device_endpoint_resources(struct xhci_hcd *xhci,
+        struct xhci_virt_device *virt_dev, bool drop_control_ep)
+{
+        int i;
+        unsigned int num_dropped_eps = 0;
+        unsigned int drop_flags = 0;
+
+        for (i = (drop_control_ep ? 0 : 1); i < 31; i++) {
+                if (virt_dev->eps[i].ring) {
+                        drop_flags |= 1 << i;
+                        num_dropped_eps++;
+                }
+        }
+        xhci->num_active_eps -= num_dropped_eps;
+        if (num_dropped_eps)
+                xhci_dbg(xhci, "Dropped %u ep ctxs, flags = 0x%x, "
+                                "%u now active.\n",
+                                num_dropped_eps, drop_flags,
+                                xhci->num_active_eps);
+}
+
+/*
  * This submits a Reset Device Command, which will set the device state to 0,
  * set the device address to 0, and disable all the endpoints except the default
  * control endpoint.  The USB core should come back and call
@@ -2406,6 +2580,14 @@ int xhci_discover_or_reset_device(struct usb_hcd *hcd, struct usb_device *udev)
                 goto command_cleanup;
         }
 
+        /* Free up host controller endpoint resources */
+        if ((xhci->quirks & XHCI_EP_LIMIT_QUIRK)) {
+                spin_lock_irqsave(&xhci->lock, flags);
+                /* Don't delete the default control endpoint resources */
+                xhci_free_device_endpoint_resources(xhci, virt_dev, false);
+                spin_unlock_irqrestore(&xhci->lock, flags);
+        }
+
         /* Everything but endpoint 0 is disabled, so free or cache the rings. */
         last_freed_endpoint = 1;
         for (i = 1; i < 31; ++i) {
@@ -2479,6 +2661,27 @@ void xhci_free_dev(struct usb_hcd *hcd, struct usb_device *udev)
 }
 
 /*
+ * Checks if we have enough host controller resources for the default control
+ * endpoint.
+ *
+ * Must be called with xhci->lock held.
+ */
+static int xhci_reserve_host_control_ep_resources(struct xhci_hcd *xhci)
+{
+        if (xhci->num_active_eps + 1 > xhci->limit_active_eps) {
+                xhci_dbg(xhci, "Not enough ep ctxs: "
+                                "%u active, need to add 1, limit is %u.\n",
+                                xhci->num_active_eps, xhci->limit_active_eps);
+                return -ENOMEM;
+        }
+        xhci->num_active_eps += 1;
+        xhci_dbg(xhci, "Adding 1 ep ctx, %u now active.\n",
+                        xhci->num_active_eps);
+        return 0;
+}
+
+
+/*
  * Returns 0 if the xHC ran out of device slots, the Enable Slot command
  * timed out, or allocating memory failed.  Returns 1 on success.
  */
@@ -2513,24 +2716,39 @@ int xhci_alloc_dev(struct usb_hcd *hcd, struct usb_device *udev)
                 xhci_err(xhci, "Error while assigning device slot ID\n");
                 return 0;
         }
-        /* xhci_alloc_virt_device() does not touch rings; no need to lock.
-         * Use GFP_NOIO, since this function can be called from
+
+        if ((xhci->quirks & XHCI_EP_LIMIT_QUIRK)) {
+                spin_lock_irqsave(&xhci->lock, flags);
+                ret = xhci_reserve_host_control_ep_resources(xhci);
+                if (ret) {
+                        spin_unlock_irqrestore(&xhci->lock, flags);
+                        xhci_warn(xhci, "Not enough host resources, "
+                                        "active endpoint contexts = %u\n",
+                                        xhci->num_active_eps);
+                        goto disable_slot;
+                }
+                spin_unlock_irqrestore(&xhci->lock, flags);
+        }
+        /* Use GFP_NOIO, since this function can be called from
          * xhci_discover_or_reset_device(), which may be called as part of
          * mass storage driver error handling.
          */
         if (!xhci_alloc_virt_device(xhci, xhci->slot_id, udev, GFP_NOIO)) {
-                /* Disable slot, if we can do it without mem alloc */
                 xhci_warn(xhci, "Could not allocate xHCI USB device data structures\n");
-                spin_lock_irqsave(&xhci->lock, flags);
-                if (!xhci_queue_slot_control(xhci, TRB_DISABLE_SLOT, udev->slot_id))
-                        xhci_ring_cmd_db(xhci);
-                spin_unlock_irqrestore(&xhci->lock, flags);
-                return 0;
+                goto disable_slot;
         }
         udev->slot_id = xhci->slot_id;
         /* Is this a LS or FS device under a HS hub? */
         /* Hub or peripherial? */
         return 1;
+
+disable_slot:
+        /* Disable slot, if we can do it without mem alloc */
+        spin_lock_irqsave(&xhci->lock, flags);
+        if (!xhci_queue_slot_control(xhci, TRB_DISABLE_SLOT, udev->slot_id))
+                xhci_ring_cmd_db(xhci);
+        spin_unlock_irqrestore(&xhci->lock, flags);
+        return 0;
 }
 
 /*
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index e12db7cfb9bb..ac0196e7fcf1 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1123,6 +1123,7 @@ struct xhci_ring {
          */
         u32                     cycle_state;
         unsigned int            stream_id;
+        bool                    last_td_was_short;
 };
 
 struct xhci_erst_entry {
@@ -1290,6 +1291,19 @@ struct xhci_hcd {
 #define XHCI_RESET_EP_QUIRK     (1 << 1)
 #define XHCI_NEC_HOST           (1 << 2)
 #define XHCI_AMD_PLL_FIX        (1 << 3)
+#define XHCI_SPURIOUS_SUCCESS   (1 << 4)
+/*
+ * Certain Intel host controllers have a limit to the number of endpoint
+ * contexts they can handle.  Ideally, they would signal that they can't handle
+ * anymore endpoint contexts by returning a Resource Error for the Configure
+ * Endpoint command, but they don't.  Instead they expect software to keep track
+ * of the number of active endpoints for them, across configure endpoint
+ * commands, reset device commands, disable slot commands, and address device
+ * commands.
+ */
+#define XHCI_EP_LIMIT_QUIRK     (1 << 5)
+        unsigned int            num_active_eps;
+        unsigned int            limit_active_eps;
         /* There are two roothubs to keep track of bus suspend info for */
         struct xhci_bus_state   bus_state[2];
         /* Is each xHCI roothub port a USB 3.0, USB 2.0, or USB 1.1 port? */
@@ -1338,9 +1352,6 @@ static inline unsigned int xhci_readl(const struct xhci_hcd *xhci,
 static inline void xhci_writel(struct xhci_hcd *xhci,
                 const unsigned int val, __le32 __iomem *regs)
 {
-        xhci_dbg(xhci,
-                        "`MEM_WRITE_DWORD(3'b000, 32'h%p, 32'h%0x, 4'hf);\n",
-                        regs, val);
         writel(val, regs);
 }
 
@@ -1368,9 +1379,6 @@ static inline void xhci_write_64(struct xhci_hcd *xhci,
         u32 val_lo = lower_32_bits(val);
         u32 val_hi = upper_32_bits(val);
 
-        xhci_dbg(xhci,
-                        "`MEM_WRITE_DWORD(3'b000, 64'h%p, 64'h%0lx, 4'hf);\n",
-                        regs, (long unsigned int) val);
         writel(val_lo, ptr);
         writel(val_hi, ptr + 1);
 }
@@ -1439,6 +1447,8 @@ void xhci_setup_streams_ep_input_ctx(struct xhci_hcd *xhci,
 void xhci_setup_no_streams_ep_input_ctx(struct xhci_hcd *xhci,
                 struct xhci_ep_ctx *ep_ctx,
                 struct xhci_virt_ep *ep);
+void xhci_free_device_endpoint_resources(struct xhci_hcd *xhci,
+        struct xhci_virt_device *virt_dev, bool drop_control_ep);
 struct xhci_ring *xhci_dma_to_transfer_ring(
                 struct xhci_virt_ep *ep,
                 u64 address);
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 2f7c76a85e53..e224a92baa16 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -144,7 +144,7 @@ static void handle_tx(struct vhost_net *net)
         }
 
         mutex_lock(&vq->mutex);
-        vhost_disable_notify(vq);
+        vhost_disable_notify(&net->dev, vq);
 
         if (wmem < sock->sk->sk_sndbuf / 2)
                 tx_poll_stop(net);
@@ -166,8 +166,8 @@ static void handle_tx(struct vhost_net *net)
                                 set_bit(SOCK_ASYNC_NOSPACE, &sock->flags);
                                 break;
                         }
-                        if (unlikely(vhost_enable_notify(vq))) {
-                                vhost_disable_notify(vq);
+                        if (unlikely(vhost_enable_notify(&net->dev, vq))) {
+                                vhost_disable_notify(&net->dev, vq);
                                 continue;
                         }
                         break;
@@ -315,7 +315,7 @@ static void handle_rx(struct vhost_net *net)
                 return;
 
         mutex_lock(&vq->mutex);
-        vhost_disable_notify(vq);
+        vhost_disable_notify(&net->dev, vq);
         vhost_hlen = vq->vhost_hlen;
         sock_hlen = vq->sock_hlen;
 
@@ -334,10 +334,10 @@ static void handle_rx(struct vhost_net *net)
                         break;
                 /* OK, now we need to know about added descriptors. */
                 if (!headcount) {
-                        if (unlikely(vhost_enable_notify(vq))) {
+                        if (unlikely(vhost_enable_notify(&net->dev, vq))) {
                                 /* They have slipped one in as we were
                                  * doing that: check again. */
-                                vhost_disable_notify(vq);
+                                vhost_disable_notify(&net->dev, vq);
                                 continue;
                         }
                         /* Nothing new?  Wait for eventfd to tell us
diff --git a/drivers/vhost/test.c b/drivers/vhost/test.c
index 099f30230d06..734e1d74ad80 100644
--- a/drivers/vhost/test.c
+++ b/drivers/vhost/test.c
@@ -49,7 +49,7 @@ static void handle_vq(struct vhost_test *n)
                 return;
 
         mutex_lock(&vq->mutex);
-        vhost_disable_notify(vq);
+        vhost_disable_notify(&n->dev, vq);
 
         for (;;) {
                 head = vhost_get_vq_desc(&n->dev, vq, vq->iov,
@@ -61,8 +61,8 @@ static void handle_vq(struct vhost_test *n)
                         break;
                 /* Nothing new?  Wait for eventfd to tell us they refilled. */
                 if (head == vq->num) {
-                        if (unlikely(vhost_enable_notify(vq))) {
-                                vhost_disable_notify(vq);
+                        if (unlikely(vhost_enable_notify(&n->dev, vq))) {
+                                vhost_disable_notify(&n->dev, vq);
                                 continue;
                         }
                         break;
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 7aa4eea930f1..ea966b356352 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -37,6 +37,9 @@ enum {
         VHOST_MEMORY_F_LOG = 0x1,
 };
 
+#define vhost_used_event(vq) ((u16 __user *)&vq->avail->ring[vq->num])
+#define vhost_avail_event(vq) ((u16 __user *)&vq->used->ring[vq->num])
+
 static void vhost_poll_func(struct file *file, wait_queue_head_t *wqh,
                             poll_table *pt)
 {
@@ -161,6 +164,8 @@ static void vhost_vq_reset(struct vhost_dev *dev,
         vq->last_avail_idx = 0;
         vq->avail_idx = 0;
         vq->last_used_idx = 0;
+        vq->signalled_used = 0;
+        vq->signalled_used_valid = false;
         vq->used_flags = 0;
         vq->log_used = false;
         vq->log_addr = -1ull;
@@ -489,16 +494,17 @@ static int memory_access_ok(struct vhost_dev *d, struct vhost_memory *mem,
         return 1;
 }
 
-static int vq_access_ok(unsigned int num,
+static int vq_access_ok(struct vhost_dev *d, unsigned int num,
                         struct vring_desc __user *desc,
                         struct vring_avail __user *avail,
                         struct vring_used __user *used)
 {
+        size_t s = vhost_has_feature(d, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
         return access_ok(VERIFY_READ, desc, num * sizeof *desc) &&
                access_ok(VERIFY_READ, avail,
-                         sizeof *avail + num * sizeof *avail->ring) &&
+                         sizeof *avail + num * sizeof *avail->ring + s) &&
                access_ok(VERIFY_WRITE, used,
-                        sizeof *used + num * sizeof *used->ring);
+                        sizeof *used + num * sizeof *used->ring + s);
 }
 
 /* Can we log writes? */
@@ -514,9 +520,11 @@ int vhost_log_access_ok(struct vhost_dev *dev)
 
 /* Verify access for write logging. */
 /* Caller should have vq mutex and device mutex */
-static int vq_log_access_ok(struct vhost_virtqueue *vq, void __user *log_base)
+static int vq_log_access_ok(struct vhost_dev *d, struct vhost_virtqueue *vq,
+                            void __user *log_base)
 {
         struct vhost_memory *mp;
+        size_t s = vhost_has_feature(d, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0;
 
         mp = rcu_dereference_protected(vq->dev->memory,
                                        lockdep_is_held(&vq->mutex));
@@ -524,15 +532,15 @@ static int vq_log_access_ok(struct vhost_virtqueue *vq, void __user *log_base)
                             vhost_has_feature(vq->dev, VHOST_F_LOG_ALL)) &&
                 (!vq->log_used || log_access_ok(log_base, vq->log_addr,
                                         sizeof *vq->used +
-                                        vq->num * sizeof *vq->used->ring));
+                                        vq->num * sizeof *vq->used->ring + s));
 }
 
 /* Can we start vq? */
 /* Caller should have vq mutex and device mutex */
 int vhost_vq_access_ok(struct vhost_virtqueue *vq)
 {
-        return vq_access_ok(vq->num, vq->desc, vq->avail, vq->used) &&
-                vq_log_access_ok(vq, vq->log_base);
+        return vq_access_ok(vq->dev, vq->num, vq->desc, vq->avail, vq->used) &&
+                vq_log_access_ok(vq->dev, vq, vq->log_base);
 }
 
 static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
@@ -577,6 +585,7 @@ static int init_used(struct vhost_virtqueue *vq,
 
         if (r)
                 return r;
+        vq->signalled_used_valid = false;
         return get_user(vq->last_used_idx, &used->idx);
 }
 
@@ -674,7 +683,7 @@ static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp)
                  * If it is not, we don't as size might not have been setup.
                  * We will verify when backend is configured. */
                 if (vq->private_data) {
-                        if (!vq_access_ok(vq->num,
+                        if (!vq_access_ok(d, vq->num,
                                 (void __user *)(unsigned long)a.desc_user_addr,
                                 (void __user *)(unsigned long)a.avail_user_addr,
                                 (void __user *)(unsigned long)a.used_user_addr)) {
@@ -818,7 +827,7 @@ long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, unsigned long arg)
                         vq = d->vqs + i;
                         mutex_lock(&vq->mutex);
                         /* If ring is inactive, will check when it's enabled. */
-                        if (vq->private_data && !vq_log_access_ok(vq, base))
+                        if (vq->private_data && !vq_log_access_ok(d, vq, base))
                                 r = -EFAULT;
                         else
                                 vq->log_base = base;
@@ -1219,6 +1228,10 @@ int vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq,
 
         /* On success, increment avail index. */
         vq->last_avail_idx++;
+
+        /* Assume notifications from guest are disabled at this point,
+         * if they aren't we would need to update avail_event index. */
+        BUG_ON(!(vq->used_flags & VRING_USED_F_NO_NOTIFY));
         return head;
 }
 
@@ -1267,6 +1280,12 @@ int vhost_add_used(struct vhost_virtqueue *vq, unsigned int head, int len)
                         eventfd_signal(vq->log_ctx, 1);
         }
         vq->last_used_idx++;
+        /* If the driver never bothers to signal in a very long while,
+         * used index might wrap around. If that happens, invalidate
+         * signalled_used index we stored. TODO: make sure driver
+         * signals at least once in 2^16 and remove this. */
+        if (unlikely(vq->last_used_idx == vq->signalled_used))
+                vq->signalled_used_valid = false;
         return 0;
 }
 
@@ -1275,6 +1294,7 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq,
                             unsigned count)
 {
         struct vring_used_elem __user *used;
+        u16 old, new;
         int start;
 
         start = vq->last_used_idx % vq->num;
@@ -1292,7 +1312,14 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq,
                            ((void __user *)used - (void __user *)vq->used),
                           count * sizeof *used);
         }
-        vq->last_used_idx += count;
+        old = vq->last_used_idx;
+        new = (vq->last_used_idx += count);
+        /* If the driver never bothers to signal in a very long while,
+         * used index might wrap around. If that happens, invalidate
+         * signalled_used index we stored. TODO: make sure driver
+         * signals at least once in 2^16 and remove this. */
+        if (unlikely((u16)(new - vq->signalled_used) < (u16)(new - old)))
+                vq->signalled_used_valid = false;
         return 0;
 }
 
@@ -1331,29 +1358,47 @@ int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads,
         return r;
 }
 
-/* This actually signals the guest, using eventfd. */
-void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq)
+static bool vhost_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 {
-        __u16 flags;
-
+        __u16 old, new, event;
+        bool v;
         /* Flush out used index updates. This is paired
          * with the barrier that the Guest executes when enabling
          * interrupts. */
         smp_mb();
 
-        if (__get_user(flags, &vq->avail->flags)) {
-                vq_err(vq, "Failed to get flags");
-                return;
+        if (vhost_has_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY) &&
+            unlikely(vq->avail_idx == vq->last_avail_idx))
+                return true;
+
+        if (!vhost_has_feature(dev, VIRTIO_RING_F_EVENT_IDX)) {
+                __u16 flags;
+                if (__get_user(flags, &vq->avail->flags)) {
+                        vq_err(vq, "Failed to get flags");
+                        return true;
+                }
+                return !(flags & VRING_AVAIL_F_NO_INTERRUPT);
         }
+        old = vq->signalled_used;
+        v = vq->signalled_used_valid;
+        new = vq->signalled_used = vq->last_used_idx;
+        vq->signalled_used_valid = true;
 
-        /* If they don't want an interrupt, don't signal, unless empty. */
-        if ((flags & VRING_AVAIL_F_NO_INTERRUPT) &&
-            (vq->avail_idx != vq->last_avail_idx ||
-             !vhost_has_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY)))
-                return;
+        if (unlikely(!v))
+                return true;
 
+        if (get_user(event, vhost_used_event(vq))) {
+                vq_err(vq, "Failed to get used event idx");
+                return true;
+        }
+        return vring_need_event(event, new, old);
+}
+
+/* This actually signals the guest, using eventfd. */
+void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq)
+{
         /* Signal the Guest tell them we used something up. */
-        if (vq->call_ctx)
+        if (vq->call_ctx && vhost_notify(dev, vq))
                 eventfd_signal(vq->call_ctx, 1);
 }
 
@@ -1376,7 +1421,7 @@ void vhost_add_used_and_signal_n(struct vhost_dev *dev,
 }
 
 /* OK, now we need to know about added descriptors. */
-bool vhost_enable_notify(struct vhost_virtqueue *vq)
+bool vhost_enable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 {
         u16 avail_idx;
         int r;
@@ -1384,11 +1429,34 @@ bool vhost_enable_notify(struct vhost_virtqueue *vq)
         if (!(vq->used_flags & VRING_USED_F_NO_NOTIFY))
                 return false;
         vq->used_flags &= ~VRING_USED_F_NO_NOTIFY;
-        r = put_user(vq->used_flags, &vq->used->flags);
-        if (r) {
-                vq_err(vq, "Failed to enable notification at %p: %d\n",
-                       &vq->used->flags, r);
-                return false;
+        if (!vhost_has_feature(dev, VIRTIO_RING_F_EVENT_IDX)) {
+                r = put_user(vq->used_flags, &vq->used->flags);
+                if (r) {
+                        vq_err(vq, "Failed to enable notification at %p: %d\n",
+                               &vq->used->flags, r);
+                        return false;
+                }
+        } else {
+                r = put_user(vq->avail_idx, vhost_avail_event(vq));
+                if (r) {
+                        vq_err(vq, "Failed to update avail event index at %p: %d\n",
+                               vhost_avail_event(vq), r);
+                        return false;
+                }
+        }
+        if (unlikely(vq->log_used)) {
+                void __user *used;
+                /* Make sure data is seen before log. */
+                smp_wmb();
+                used = vhost_has_feature(dev, VIRTIO_RING_F_EVENT_IDX) ?
+                        &vq->used->flags : vhost_avail_event(vq);
+                /* Log used flags or event index entry write. Both are 16 bit
+                 * fields. */
+                log_write(vq->log_base, vq->log_addr +
+                           (used - (void __user *)vq->used),
+                          sizeof(u16));
+                if (vq->log_ctx)
+                        eventfd_signal(vq->log_ctx, 1);
         }
         /* They could have slipped one in as we were doing that: make
          * sure it's written, then check again. */
@@ -1404,15 +1472,17 @@ bool vhost_enable_notify(struct vhost_virtqueue *vq)
 }
 
 /* We don't need to be notified again. */
-void vhost_disable_notify(struct vhost_virtqueue *vq)
+void vhost_disable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
 {
         int r;
 
         if (vq->used_flags & VRING_USED_F_NO_NOTIFY)
                 return;
         vq->used_flags |= VRING_USED_F_NO_NOTIFY;
-        r = put_user(vq->used_flags, &vq->used->flags);
-        if (r)
-                vq_err(vq, "Failed to enable notification at %p: %d\n",
-                       &vq->used->flags, r);
+        if (!vhost_has_feature(dev, VIRTIO_RING_F_EVENT_IDX)) {
+                r = put_user(vq->used_flags, &vq->used->flags);
+                if (r)
+                        vq_err(vq, "Failed to enable notification at %p: %d\n",
+                               &vq->used->flags, r);
+        }
 }
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index b3363ae38518..8e03379dd30f 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -84,6 +84,12 @@ struct vhost_virtqueue {
         /* Used flags */
         u16 used_flags;
 
+        /* Last used index value we have signalled on */
+        u16 signalled_used;
+
+        /* Last used index value we have signalled on */
+        bool signalled_used_valid;
+
         /* Log writes to used structure. */
         bool log_used;
         u64 log_addr;
@@ -149,8 +155,8 @@ void vhost_add_used_and_signal(struct vhost_dev *, struct vhost_virtqueue *,
 void vhost_add_used_and_signal_n(struct vhost_dev *, struct vhost_virtqueue *,
                                struct vring_used_elem *heads, unsigned count);
 void vhost_signal(struct vhost_dev *, struct vhost_virtqueue *);
-void vhost_disable_notify(struct vhost_virtqueue *);
-bool vhost_enable_notify(struct vhost_virtqueue *);
+void vhost_disable_notify(struct vhost_dev *, struct vhost_virtqueue *);
+bool vhost_enable_notify(struct vhost_dev *, struct vhost_virtqueue *);
 
 int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
                     unsigned int log_num, u64 len);
@@ -162,11 +168,12 @@ int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
         } while (0)
 
 enum {
-        VHOST_FEATURES = (1 << VIRTIO_F_NOTIFY_ON_EMPTY) |
-                         (1 << VIRTIO_RING_F_INDIRECT_DESC) |
-                         (1 << VHOST_F_LOG_ALL) |
-                         (1 << VHOST_NET_F_VIRTIO_NET_HDR) |
-                         (1 << VIRTIO_NET_F_MRG_RXBUF),
+        VHOST_FEATURES = (1ULL << VIRTIO_F_NOTIFY_ON_EMPTY) |
+                         (1ULL << VIRTIO_RING_F_INDIRECT_DESC) |
+                         (1ULL << VIRTIO_RING_F_EVENT_IDX) |
+                         (1ULL << VHOST_F_LOG_ALL) |
+                         (1ULL << VHOST_NET_F_VIRTIO_NET_HDR) |
+                         (1ULL << VIRTIO_NET_F_MRG_RXBUF),
 };
 
 static inline int vhost_has_feature(struct vhost_dev *dev, int bit)
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 0f1da45ba47d..e058ace2a4ad 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -40,9 +40,6 @@ struct virtio_balloon
         /* Waiting for host to ack the pages we released. */
         struct completion acked;
 
-        /* Do we have to tell Host *before* we reuse pages? */
-        bool tell_host_first;
-
         /* The pages we've told the Host we're not using. */
         unsigned int num_pages;
         struct list_head pages;
@@ -151,13 +148,14 @@ static void leak_balloon(struct virtio_balloon *vb, size_t num)
                 vb->num_pages--;
         }
 
-        if (vb->tell_host_first) {
-                tell_host(vb, vb->deflate_vq);
-                release_pages_by_pfn(vb->pfns, vb->num_pfns);
-        } else {
-                release_pages_by_pfn(vb->pfns, vb->num_pfns);
-                tell_host(vb, vb->deflate_vq);
-        }
+
+        /*
+         * Note that if
+         * virtio_has_feature(vdev, VIRTIO_BALLOON_F_MUST_TELL_HOST);
+         * is true, we *have* to do it in this order
+         */
+        tell_host(vb, vb->deflate_vq);
+        release_pages_by_pfn(vb->pfns, vb->num_pfns);
 }
 
 static inline void update_stat(struct virtio_balloon *vb, int idx,
@@ -325,9 +323,6 @@ static int virtballoon_probe(struct virtio_device *vdev)
                 goto out_del_vqs;
         }
 
-        vb->tell_host_first
-                = virtio_has_feature(vdev, VIRTIO_BALLOON_F_MUST_TELL_HOST);
-
         return 0;
 
 out_del_vqs:
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index b0043fb26a4d..68b9136847af 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -82,6 +82,9 @@ struct vring_virtqueue
         /* Host supports indirect buffers */
         bool indirect;
 
+        /* Host publishes avail event idx */
+        bool event;
+
         /* Number of free buffers */
         unsigned int num_free;
         /* Head of free buffer list. */
@@ -237,18 +240,22 @@ EXPORT_SYMBOL_GPL(virtqueue_add_buf_gfp);
 void virtqueue_kick(struct virtqueue *_vq)
 {
         struct vring_virtqueue *vq = to_vvq(_vq);
+        u16 new, old;
         START_USE(vq);
         /* Descriptors and available array need to be set before we expose the
          * new available array entries. */
         virtio_wmb();
 
-        vq->vring.avail->idx += vq->num_added;
+        old = vq->vring.avail->idx;
+        new = vq->vring.avail->idx = old + vq->num_added;
         vq->num_added = 0;
 
         /* Need to update avail index before checking if we should notify */
         virtio_mb();
 
-        if (!(vq->vring.used->flags & VRING_USED_F_NO_NOTIFY))
+        if (vq->event ?
+            vring_need_event(vring_avail_event(&vq->vring), new, old) :
+            !(vq->vring.used->flags & VRING_USED_F_NO_NOTIFY))
                 /* Prod other side to tell it about changes. */
                 vq->notify(&vq->vq);
 
@@ -324,6 +331,14 @@ void *virtqueue_get_buf(struct virtqueue *_vq, unsigned int *len)
         ret = vq->data[i];
         detach_buf(vq, i);
         vq->last_used_idx++;
+        /* If we expect an interrupt for the next entry, tell host
+         * by writing event index and flush out the write before
+         * the read in the next get_buf call. */
+        if (!(vq->vring.avail->flags & VRING_AVAIL_F_NO_INTERRUPT)) {
+                vring_used_event(&vq->vring) = vq->last_used_idx;
+                virtio_mb();
+        }
+
         END_USE(vq);
         return ret;
 }
@@ -345,7 +360,11 @@ bool virtqueue_enable_cb(struct virtqueue *_vq)
 
         /* We optimistically turn back on interrupts, then check if there was
          * more to do. */
+        /* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to
+         * either clear the flags bit or point the event index at the next
+         * entry. Always do both to keep code simple. */
         vq->vring.avail->flags &= ~VRING_AVAIL_F_NO_INTERRUPT;
+        vring_used_event(&vq->vring) = vq->last_used_idx;
         virtio_mb();
         if (unlikely(more_used(vq))) {
                 END_USE(vq);
@@ -357,6 +376,33 @@ bool virtqueue_enable_cb(struct virtqueue *_vq)
 }
 EXPORT_SYMBOL_GPL(virtqueue_enable_cb);
 
+bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
+{
+        struct vring_virtqueue *vq = to_vvq(_vq);
+        u16 bufs;
+
+        START_USE(vq);
+
+        /* We optimistically turn back on interrupts, then check if there was
+         * more to do. */
+        /* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to
+         * either clear the flags bit or point the event index at the next
+         * entry. Always do both to keep code simple. */
+        vq->vring.avail->flags &= ~VRING_AVAIL_F_NO_INTERRUPT;
+        /* TODO: tune this threshold */
+        bufs = (u16)(vq->vring.avail->idx - vq->last_used_idx) * 3 / 4;
+        vring_used_event(&vq->vring) = vq->last_used_idx + bufs;
+        virtio_mb();
+        if (unlikely((u16)(vq->vring.used->idx - vq->last_used_idx) > bufs)) {
+                END_USE(vq);
+                return false;
+        }
+
+        END_USE(vq);
+        return true;
+}
+EXPORT_SYMBOL_GPL(virtqueue_enable_cb_delayed);
+
 void *virtqueue_detach_unused_buf(struct virtqueue *_vq)
 {
         struct vring_virtqueue *vq = to_vvq(_vq);
@@ -438,6 +484,7 @@ struct virtqueue *vring_new_virtqueue(unsigned int num,
 #endif
 
         vq->indirect = virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC);
+        vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX);
 
         /* No callback?  Tell other side not to bother us. */
         if (!callback)
@@ -472,6 +519,8 @@ void vring_transport_features(struct virtio_device *vdev)
                 switch (i) {
                 case VIRTIO_RING_F_INDIRECT_DESC:
                         break;
+                case VIRTIO_RING_F_EVENT_IDX:
+                        break;
                 default:
                         /* We don't understand this bit. */
                         clear_bit(i, vdev->features);
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 8d7f3e69ae29..7f6c67703195 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -814,7 +814,6 @@ int v9fs_vfs_unlink(struct inode *i, struct dentry *d)
 
 int v9fs_vfs_rmdir(struct inode *i, struct dentry *d)
 {
-        dentry_unhash(d);
         return v9fs_remove(i, d, 1);
 }
 
@@ -840,9 +839,6 @@ v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
         struct p9_fid *newdirfid;
         struct p9_wstat wstat;
 
-        if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
-                dentry_unhash(new_dentry);
-
         P9_DPRINTK(P9_DEBUG_VFS, "\n");
         retval = 0;
         old_inode = old_dentry->d_inode;
diff --git a/fs/affs/namei.c b/fs/affs/namei.c
index 03330e2e390c..e3e9efc1fdd8 100644
--- a/fs/affs/namei.c
+++ b/fs/affs/namei.c
@@ -320,8 +320,6 @@ affs_rmdir(struct inode *dir, struct dentry *dentry)
                  dentry->d_inode->i_ino,
                  (int)dentry->d_name.len, dentry->d_name.name);
 
-        dentry_unhash(dentry);
-
         return affs_remove_header(dentry);
 }
 
@@ -419,9 +417,6 @@ affs_rename(struct inode *old_dir, struct dentry *old_dentry,
         struct buffer_head *bh = NULL;
         int retval;
 
-        if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
-                dentry_unhash(new_dentry);
-
         pr_debug("AFFS: rename(old=%u,\"%*s\" to new=%u,\"%*s\")\n",
                  (u32)old_dir->i_ino, (int)old_dentry->d_name.len, old_dentry->d_name.name,
                  (u32)new_dir->i_ino, (int)new_dentry->d_name.len, new_dentry->d_name.name);
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 2c4e05160042..20c106f24927 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -845,8 +845,6 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry)
         _enter("{%x:%u},{%s}",
                dvnode->fid.vid, dvnode->fid.vnode, dentry->d_name.name);
 
-        dentry_unhash(dentry);
-
         ret = -ENAMETOOLONG;
         if (dentry->d_name.len >= AFSNAMEMAX)
                 goto error;
@@ -1148,9 +1146,6 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry,
         struct key *key;
         int ret;
 
-        if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
-                dentry_unhash(new_dentry);
-
         vnode = AFS_FS_I(old_dentry->d_inode);
         orig_dvnode = AFS_FS_I(old_dir);
         new_dvnode = AFS_FS_I(new_dir);
diff --git a/fs/attr.c b/fs/attr.c
index 91dbe2a107f2..caf2aa521e2b 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -175,6 +175,13 @@ int notify_change(struct dentry * dentry, struct iattr * attr)
                         return -EPERM;
         }
 
+        if ((ia_valid & ATTR_MODE)) {
+                mode_t amode = attr->ia_mode;
+                /* Flag setting protected by i_mutex */
+                if (is_sxid(amode))
+                        inode->i_flags &= ~S_NOSEC;
+        }
+
         now = current_fs_time(inode->i_sb);
 
         attr->ia_ctime = now;
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index 87d95a8cddbc..f55ae23b137e 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -583,8 +583,6 @@ static int autofs4_dir_unlink(struct inode *dir, struct dentry *dentry)
         if (!autofs4_oz_mode(sbi) && !capable(CAP_SYS_ADMIN))
                 return -EACCES;
 
-        dentry_unhash(dentry);
-
         if (atomic_dec_and_test(&ino->count)) {
                 p_ino = autofs4_dentry_ino(dentry->d_parent);
                 if (p_ino && dentry->d_parent != dentry)
diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c
index c7d1d06b0483..b14cebfd9047 100644
--- a/fs/bfs/dir.c
+++ b/fs/bfs/dir.c
@@ -224,9 +224,6 @@ static int bfs_rename(struct inode *old_dir, struct dentry *old_dentry,
         struct bfs_sb_info *info;
         int error = -ENOENT;
 
-        if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
-                dentry_unhash(new_dentry);
-
         old_bh = new_bh = NULL;
         old_inode = old_dentry->d_inode;
         if (S_ISDIR(old_inode->i_mode))
diff --git a/fs/bio.c b/fs/bio.c
index 840a0d755248..9bfade8a609b 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -638,10 +638,11 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
  *      @offset: vec entry offset
  *
  *      Attempt to add a page to the bio_vec maplist. This can fail for a
- *      number of reasons, such as the bio being full or target block
- *      device limitations. The target block device must allow bio's
- *      smaller than PAGE_SIZE, so it is always possible to add a single
- *      page to an empty bio. This should only be used by REQ_PC bios.
+ *      number of reasons, such as the bio being full or target block device
+ *      limitations. The target block device must allow bio's up to PAGE_SIZE,
+ *      so it is always possible to add a single page to an empty bio.
+ *
+ *      This should only be used by REQ_PC bios.
  */
 int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page *page,
                     unsigned int len, unsigned int offset)
@@ -659,10 +660,9 @@ EXPORT_SYMBOL(bio_add_pc_page);
  *      @offset: vec entry offset
  *
  *      Attempt to add a page to the bio_vec maplist. This can fail for a
- *      number of reasons, such as the bio being full or target block
- *      device limitations. The target block device must allow bio's
- *      smaller than PAGE_SIZE, so it is always possible to add a single
- *      page to an empty bio.
+ *      number of reasons, such as the bio being full or target block device
+ *      limitations. The target block device must allow bio's up to PAGE_SIZE,
+ *      so it is always possible to add a single page to an empty bio.
  */
 int bio_add_page(struct bio *bio, struct page *page, unsigned int len,
                  unsigned int offset)
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 1f2b19978333..1a2421f908f0 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1272,8 +1272,8 @@ int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder)
                  * individual writeable reference is too fragile given the
                  * way @mode is used in blkdev_get/put().
                  */
-                if ((disk->flags & GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE) &&
-                    !res && (mode & FMODE_WRITE) && !bdev->bd_write_holder) {
+                if (!res && (mode & FMODE_WRITE) && !bdev->bd_write_holder &&
+                    (disk->flags & GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE)) {
                         bdev->bd_write_holder = true;
                         disk_block_events(disk);
                 }
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 93b1aa932014..52d7eca8c7bf 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -121,9 +121,6 @@ struct btrfs_inode {
          */
         u64 index_cnt;
 
-        /* the start of block group preferred for allocations. */
-        u64 block_group;
-
         /* the fsync log has some corner cases that mean we have to check
          * directories to see if any unlinks have been done before
          * the directory was logged.  See tree-log.c for all the
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index b0e18d986e0a..d84089349c82 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -43,8 +43,6 @@ struct btrfs_path *btrfs_alloc_path(void)
 {
         struct btrfs_path *path;
         path = kmem_cache_zalloc(btrfs_path_cachep, GFP_NOFS);
-        if (path)
-                path->reada = 1;
         return path;
 }
 
@@ -1224,6 +1222,7 @@ static void reada_for_search(struct btrfs_root *root,
         u64 search;
         u64 target;
         u64 nread = 0;
+        u64 gen;
         int direction = path->reada;
         struct extent_buffer *eb;
         u32 nr;
@@ -1251,6 +1250,15 @@ static void reada_for_search(struct btrfs_root *root,
         nritems = btrfs_header_nritems(node);
         nr = slot;
         while (1) {
+                if (!node->map_token) {
+                        unsigned long offset = btrfs_node_key_ptr_offset(nr);
+                        map_private_extent_buffer(node, offset,
+                                                  sizeof(struct btrfs_key_ptr),
+                                                  &node->map_token,
+                                                  &node->kaddr,
+                                                  &node->map_start,
+                                                  &node->map_len, KM_USER1);
+                }
                 if (direction < 0) {
                         if (nr == 0)
                                 break;
@@ -1268,14 +1276,23 @@ static void reada_for_search(struct btrfs_root *root,
                 search = btrfs_node_blockptr(node, nr);
                 if ((search <= target && target - search <= 65536) ||
                     (search > target && search - target <= 65536)) {
-                        readahead_tree_block(root, search, blocksize,
-                                     btrfs_node_ptr_generation(node, nr));
+                        gen = btrfs_node_ptr_generation(node, nr);
+                        if (node->map_token) {
+                                unmap_extent_buffer(node, node->map_token,
+                                                    KM_USER1);
+                                node->map_token = NULL;
+                        }
+                        readahead_tree_block(root, search, blocksize, gen);
                         nread += blocksize;
                 }
                 nscan++;
                 if ((nread > 65536 || nscan > 32))
                         break;
         }
+        if (node->map_token) {
+                unmap_extent_buffer(node, node->map_token, KM_USER1);
+                node->map_token = NULL;
+        }
 }
 
 /*
@@ -1648,9 +1665,6 @@ again:
                 }
 cow_done:
                 BUG_ON(!cow && ins_len);
-                if (level != btrfs_header_level(b))
-                        WARN_ON(1);
-                level = btrfs_header_level(b);
 
                 p->nodes[level] = b;
                 if (!p->skip_locking)
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 332323e19dd1..378b5b4443f3 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -930,7 +930,6 @@ struct btrfs_fs_info {
          * is required instead of the faster short fsync log commits
          */
         u64 last_trans_log_full_commit;
-        u64 open_ioctl_trans;
         unsigned long mount_opt:20;
         unsigned long compress_type:4;
         u64 max_inline;
@@ -947,7 +946,6 @@ struct btrfs_fs_info {
         struct super_block *sb;
         struct inode *btree_inode;
         struct backing_dev_info bdi;
-        struct mutex trans_mutex;
         struct mutex tree_log_mutex;
         struct mutex transaction_kthread_mutex;
         struct mutex cleaner_mutex;
@@ -968,6 +966,7 @@ struct btrfs_fs_info {
         struct rw_semaphore subvol_sem;
         struct srcu_struct subvol_srcu;
 
+        spinlock_t trans_lock;
         struct list_head trans_list;
         struct list_head hashers;
         struct list_head dead_roots;
@@ -980,6 +979,7 @@ struct btrfs_fs_info {
         atomic_t async_submit_draining;
         atomic_t nr_async_bios;
         atomic_t async_delalloc_pages;
+        atomic_t open_ioctl_trans;
 
         /*
          * this is used by the balancing code to wait for all the pending
@@ -1044,6 +1044,7 @@ struct btrfs_fs_info {
         int closing;
         int log_root_recovering;
         int enospc_unlink;
+        int trans_no_join;
 
         u64 total_pinned;
 
@@ -1065,7 +1066,6 @@ struct btrfs_fs_info {
         struct reloc_control *reloc_ctl;
 
         spinlock_t delalloc_lock;
-        spinlock_t new_trans_lock;
         u64 delalloc_bytes;
 
         /* data_alloc_cluster is only used in ssd mode */
@@ -1340,6 +1340,7 @@ struct btrfs_ioctl_defrag_range_args {
 #define BTRFS_MOUNT_USER_SUBVOL_RM_ALLOWED (1 << 14)
 #define BTRFS_MOUNT_ENOSPC_DEBUG         (1 << 15)
 #define BTRFS_MOUNT_AUTO_DEFRAG         (1 << 16)
+#define BTRFS_MOUNT_INODE_MAP_CACHE     (1 << 17)
 
 #define btrfs_clear_opt(o, opt)         ((o) &= ~BTRFS_MOUNT_##opt)
 #define btrfs_set_opt(o, opt)           ((o) |= BTRFS_MOUNT_##opt)
@@ -2238,6 +2239,9 @@ int btrfs_block_rsv_migrate(struct btrfs_block_rsv *src_rsv,
 void btrfs_block_rsv_release(struct btrfs_root *root,
                              struct btrfs_block_rsv *block_rsv,
                              u64 num_bytes);
+int btrfs_truncate_reserve_metadata(struct btrfs_trans_handle *trans,
+                                    struct btrfs_root *root,
+                                    struct btrfs_block_rsv *rsv);
 int btrfs_set_block_group_ro(struct btrfs_root *root,
                              struct btrfs_block_group_cache *cache);
 int btrfs_set_block_group_rw(struct btrfs_root *root,
@@ -2350,6 +2354,15 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
                         struct btrfs_root *root,
                         struct extent_buffer *node,
                         struct extent_buffer *parent);
+static inline int btrfs_fs_closing(struct btrfs_fs_info *fs_info)
+{
+        /*
+         * Get synced with close_ctree()
+         */
+        smp_mb();
+        return fs_info->closing;
+}
+
 /* root-item.c */
 int btrfs_find_root_ref(struct btrfs_root *tree_root,
                         struct btrfs_path *path,
@@ -2512,8 +2525,7 @@ int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
 int btrfs_writepages(struct address_space *mapping,
                      struct writeback_control *wbc);
 int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
-                             struct btrfs_root *new_root,
-                             u64 new_dirid, u64 alloc_hint);
+                             struct btrfs_root *new_root, u64 new_dirid);
 int btrfs_merge_bio_hook(struct page *page, unsigned long offset,
                          size_t size, struct bio *bio, unsigned long bio_flags);
 
@@ -2524,7 +2536,7 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
 int btrfs_readpage(struct file *file, struct page *page);
 void btrfs_evict_inode(struct inode *inode);
 int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc);
-void btrfs_dirty_inode(struct inode *inode);
+void btrfs_dirty_inode(struct inode *inode, int flags);
 struct inode *btrfs_alloc_inode(struct super_block *sb);
 void btrfs_destroy_inode(struct inode *inode);
 int btrfs_drop_inode(struct inode *inode);
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 01e29503a54b..6462c29d2d37 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -678,6 +678,7 @@ static int btrfs_batch_insert_items(struct btrfs_trans_handle *trans,
         INIT_LIST_HEAD(&head);
 
         next = item;
+        nitems = 0;
 
         /*
          * count the number of the continuous items that we can insert in batch
@@ -1129,7 +1130,7 @@ static void btrfs_async_run_delayed_node_done(struct btrfs_work *work)
         delayed_node = async_node->delayed_node;
         root = delayed_node->root;
 
-        trans = btrfs_join_transaction(root, 0);
+        trans = btrfs_join_transaction(root);
         if (IS_ERR(trans))
                 goto free_path;
 
@@ -1572,8 +1573,7 @@ static void fill_stack_inode_item(struct btrfs_trans_handle *trans,
         btrfs_set_stack_inode_transid(inode_item, trans->transid);
         btrfs_set_stack_inode_rdev(inode_item, inode->i_rdev);
         btrfs_set_stack_inode_flags(inode_item, BTRFS_I(inode)->flags);
-        btrfs_set_stack_inode_block_group(inode_item,
-                                          BTRFS_I(inode)->block_group);
+        btrfs_set_stack_inode_block_group(inode_item, 0);
 
         btrfs_set_stack_timespec_sec(btrfs_inode_atime(inode_item),
                                      inode->i_atime.tv_sec);
@@ -1595,7 +1595,7 @@ int btrfs_delayed_update_inode(struct btrfs_trans_handle *trans,
                                struct btrfs_root *root, struct inode *inode)
 {
         struct btrfs_delayed_node *delayed_node;
-        int ret;
+        int ret = 0;
 
         delayed_node = btrfs_get_or_create_delayed_node(inode);
         if (IS_ERR(delayed_node))
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 98b6a71decba..a203d363184d 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1505,24 +1505,24 @@ static int transaction_kthread(void *arg)
                 vfs_check_frozen(root->fs_info->sb, SB_FREEZE_WRITE);
                 mutex_lock(&root->fs_info->transaction_kthread_mutex);
 
-                spin_lock(&root->fs_info->new_trans_lock);
+                spin_lock(&root->fs_info->trans_lock);
                 cur = root->fs_info->running_transaction;
                 if (!cur) {
-                        spin_unlock(&root->fs_info->new_trans_lock);
+                        spin_unlock(&root->fs_info->trans_lock);
                         goto sleep;
                 }
 
                 now = get_seconds();
                 if (!cur->blocked &&
                     (now < cur->start_time || now - cur->start_time < 30)) {
-                        spin_unlock(&root->fs_info->new_trans_lock);
+                        spin_unlock(&root->fs_info->trans_lock);
                         delay = HZ * 5;
                         goto sleep;
                 }
                 transid = cur->transid;
-                spin_unlock(&root->fs_info->new_trans_lock);
+                spin_unlock(&root->fs_info->trans_lock);
 
-                trans = btrfs_join_transaction(root, 1);
+                trans = btrfs_join_transaction(root);
                 BUG_ON(IS_ERR(trans));
                 if (transid == trans->transid) {
                         ret = btrfs_commit_transaction(trans, root);
@@ -1613,7 +1613,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
         INIT_LIST_HEAD(&fs_info->ordered_operations);
         INIT_LIST_HEAD(&fs_info->caching_block_groups);
         spin_lock_init(&fs_info->delalloc_lock);
-        spin_lock_init(&fs_info->new_trans_lock);
+        spin_lock_init(&fs_info->trans_lock);
         spin_lock_init(&fs_info->ref_cache_lock);
         spin_lock_init(&fs_info->fs_roots_radix_lock);
         spin_lock_init(&fs_info->delayed_iput_lock);
@@ -1645,6 +1645,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
         fs_info->max_inline = 8192 * 1024;
         fs_info->metadata_ratio = 0;
         fs_info->defrag_inodes = RB_ROOT;
+        fs_info->trans_no_join = 0;
 
         fs_info->thread_pool_size = min_t(unsigned long,
                                           num_online_cpus() + 2, 8);
@@ -1709,7 +1710,6 @@ struct btrfs_root *open_ctree(struct super_block *sb,
         fs_info->do_barriers = 1;
 
 
-        mutex_init(&fs_info->trans_mutex);
         mutex_init(&fs_info->ordered_operations_mutex);
         mutex_init(&fs_info->tree_log_mutex);
         mutex_init(&fs_info->chunk_mutex);
@@ -2479,13 +2479,13 @@ int btrfs_commit_super(struct btrfs_root *root)
         down_write(&root->fs_info->cleanup_work_sem);
         up_write(&root->fs_info->cleanup_work_sem);
 
-        trans = btrfs_join_transaction(root, 1);
+        trans = btrfs_join_transaction(root);
         if (IS_ERR(trans))
                 return PTR_ERR(trans);
         ret = btrfs_commit_transaction(trans, root);
         BUG_ON(ret);
         /* run commit again to drop the original snapshot */
-        trans = btrfs_join_transaction(root, 1);
+        trans = btrfs_join_transaction(root);
         if (IS_ERR(trans))
                 return PTR_ERR(trans);
         btrfs_commit_transaction(trans, root);
@@ -3024,10 +3024,13 @@ static int btrfs_cleanup_transaction(struct btrfs_root *root)
 
         WARN_ON(1);
 
-        mutex_lock(&root->fs_info->trans_mutex);
         mutex_lock(&root->fs_info->transaction_kthread_mutex);
 
+        spin_lock(&root->fs_info->trans_lock);
         list_splice_init(&root->fs_info->trans_list, &list);
+        root->fs_info->trans_no_join = 1;
+        spin_unlock(&root->fs_info->trans_lock);
+
         while (!list_empty(&list)) {
                 t = list_entry(list.next, struct btrfs_transaction, list);
                 if (!t)
@@ -3052,23 +3055,18 @@ static int btrfs_cleanup_transaction(struct btrfs_root *root)
                 t->blocked = 0;
                 if (waitqueue_active(&root->fs_info->transaction_wait))
                         wake_up(&root->fs_info->transaction_wait);
-                mutex_unlock(&root->fs_info->trans_mutex);
 
-                mutex_lock(&root->fs_info->trans_mutex);
                 t->commit_done = 1;
                 if (waitqueue_active(&t->commit_wait))
                         wake_up(&t->commit_wait);
-                mutex_unlock(&root->fs_info->trans_mutex);
-
-                mutex_lock(&root->fs_info->trans_mutex);
 
                 btrfs_destroy_pending_snapshots(t);
 
                 btrfs_destroy_delalloc_inodes(root);
 
-                spin_lock(&root->fs_info->new_trans_lock);
+                spin_lock(&root->fs_info->trans_lock);
                 root->fs_info->running_transaction = NULL;
-                spin_unlock(&root->fs_info->new_trans_lock);
+                spin_unlock(&root->fs_info->trans_lock);
 
                 btrfs_destroy_marked_extents(root, &t->dirty_pages,
                                              EXTENT_DIRTY);
@@ -3082,8 +3080,10 @@ static int btrfs_cleanup_transaction(struct btrfs_root *root)
                 kmem_cache_free(btrfs_transaction_cachep, t);
         }
 
+        spin_lock(&root->fs_info->trans_lock);
+        root->fs_info->trans_no_join = 0;
+        spin_unlock(&root->fs_info->trans_lock);
         mutex_unlock(&root->fs_info->transaction_kthread_mutex);
-        mutex_unlock(&root->fs_info->trans_mutex);
 
         return 0;
 }
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 169bd62ce776..5b9b6b6df242 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -348,7 +348,7 @@ static int caching_kthread(void *data)
          */
         path->skip_locking = 1;
         path->search_commit_root = 1;
-        path->reada = 2;
+        path->reada = 1;
 
         key.objectid = last;
         key.offset = 0;
@@ -366,8 +366,7 @@ again:
         nritems = btrfs_header_nritems(leaf);
 
         while (1) {
-                smp_mb();
-                if (fs_info->closing > 1) {
+                if (btrfs_fs_closing(fs_info) > 1) {
                         last = (u64)-1;
                         break;
                 }
@@ -379,15 +378,18 @@ again:
                         if (ret)
                                 break;
 
-                        caching_ctl->progress = last;
-                        btrfs_release_path(path);
-                        up_read(&fs_info->extent_commit_sem);
-                        mutex_unlock(&caching_ctl->mutex);
-                        if (btrfs_transaction_in_commit(fs_info))
-                                schedule_timeout(1);
-                        else
+                        if (need_resched() ||
+                            btrfs_next_leaf(extent_root, path)) {
+                                caching_ctl->progress = last;
+                                btrfs_release_path(path);
+                                up_read(&fs_info->extent_commit_sem);
+                                mutex_unlock(&caching_ctl->mutex);
                                 cond_resched();
-                        goto again;
+                                goto again;
+                        }
+                        leaf = path->nodes[0];
+                        nritems = btrfs_header_nritems(leaf);
+                        continue;
                 }
 
                 if (key.objectid < block_group->key.objectid) {
@@ -3065,7 +3067,7 @@ again:
                         spin_unlock(&data_sinfo->lock);
 alloc:
                         alloc_target = btrfs_get_alloc_profile(root, 1);
-                        trans = btrfs_join_transaction(root, 1);
+                        trans = btrfs_join_transaction(root);
                         if (IS_ERR(trans))
                                 return PTR_ERR(trans);
 
@@ -3091,9 +3093,10 @@ alloc:
 
                 /* commit the current transaction and try again */
 commit_trans:
-                if (!committed && !root->fs_info->open_ioctl_trans) {
+                if (!committed &&
+                    !atomic_read(&root->fs_info->open_ioctl_trans)) {
                         committed = 1;
-                        trans = btrfs_join_transaction(root, 1);
+                        trans = btrfs_join_transaction(root);
                         if (IS_ERR(trans))
                                 return PTR_ERR(trans);
                         ret = btrfs_commit_transaction(trans, root);
@@ -3472,7 +3475,7 @@ again:
                 goto out;
 
         ret = -ENOSPC;
-        trans = btrfs_join_transaction(root, 1);
+        trans = btrfs_join_transaction(root);
         if (IS_ERR(trans))
                 goto out;
         ret = btrfs_commit_transaction(trans, root);
@@ -3699,7 +3702,7 @@ int btrfs_block_rsv_check(struct btrfs_trans_handle *trans,
                 if (trans)
                         return -EAGAIN;
 
-                trans = btrfs_join_transaction(root, 1);
+                trans = btrfs_join_transaction(root);
                 BUG_ON(IS_ERR(trans));
                 ret = btrfs_commit_transaction(trans, root);
                 return 0;
@@ -3837,6 +3840,37 @@ static void release_global_block_rsv(struct btrfs_fs_info *fs_info)
         WARN_ON(fs_info->chunk_block_rsv.reserved > 0);
 }
 
+int btrfs_truncate_reserve_metadata(struct btrfs_trans_handle *trans,
+                                    struct btrfs_root *root,
+                                    struct btrfs_block_rsv *rsv)
+{
+        struct btrfs_block_rsv *trans_rsv = &root->fs_info->trans_block_rsv;
+        u64 num_bytes;
+        int ret;
+
+        /*
+         * Truncate should be freeing data, but give us 2 items just in case it
+         * needs to use some space.  We may want to be smarter about this in the
+         * future.
+         */
+        num_bytes = btrfs_calc_trans_metadata_size(root, 2);
+
+        /* We already have enough bytes, just return */
+        if (rsv->reserved >= num_bytes)
+                return 0;
+
+        num_bytes -= rsv->reserved;
+
+        /*
+         * You should have reserved enough space before hand to do this, so this
+         * should not fail.
+         */
+        ret = block_rsv_migrate_bytes(trans_rsv, rsv, num_bytes);
+        BUG_ON(ret);
+
+        return 0;
+}
+
 int btrfs_trans_reserve_metadata(struct btrfs_trans_handle *trans,
                                  struct btrfs_root *root,
                                  int num_items)
@@ -3877,23 +3911,18 @@ int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans,
         struct btrfs_block_rsv *dst_rsv = root->orphan_block_rsv;
 
         /*
-         * one for deleting orphan item, one for updating inode and
-         * two for calling btrfs_truncate_inode_items.
-         *
-         * btrfs_truncate_inode_items is a delete operation, it frees
-         * more space than it uses in most cases. So two units of
-         * metadata space should be enough for calling it many times.
-         * If all of the metadata space is used, we can commit
-         * transaction and use space it freed.
+         * We need to hold space in order to delete our orphan item once we've
+         * added it, so this takes the reservation so we can release it later
+         * when we are truly done with the orphan item.
          */
-        u64 num_bytes = btrfs_calc_trans_metadata_size(root, 4);
+        u64 num_bytes = btrfs_calc_trans_metadata_size(root, 1);
         return block_rsv_migrate_bytes(src_rsv, dst_rsv, num_bytes);
 }
 
 void btrfs_orphan_release_metadata(struct inode *inode)
 {
         struct btrfs_root *root = BTRFS_I(inode)->root;
-        u64 num_bytes = btrfs_calc_trans_metadata_size(root, 4);
+        u64 num_bytes = btrfs_calc_trans_metadata_size(root, 1);
         btrfs_block_rsv_release(root, root->orphan_block_rsv, num_bytes);
 }
 
@@ -4987,6 +5016,15 @@ have_block_group:
                 if (unlikely(block_group->ro))
                         goto loop;
 
+                spin_lock(&block_group->free_space_ctl->tree_lock);
+                if (cached &&
+                    block_group->free_space_ctl->free_space <
+                    num_bytes + empty_size) {
+                        spin_unlock(&block_group->free_space_ctl->tree_lock);
+                        goto loop;
+                }
+                spin_unlock(&block_group->free_space_ctl->tree_lock);
+
                 /*
                  * Ok we want to try and use the cluster allocator, so lets look
                  * there, unless we are on LOOP_NO_EMPTY_SIZE, since we will
@@ -5150,6 +5188,7 @@ checks:
                         btrfs_add_free_space(block_group, offset,
                                              search_start - offset);
                 BUG_ON(offset > search_start);
+                btrfs_put_block_group(block_group);
                 break;
 loop:
                 failed_cluster_refill = false;
@@ -5242,14 +5281,7 @@ loop:
                 ret = -ENOSPC;
         } else if (!ins->objectid) {
                 ret = -ENOSPC;
-        }
-
-        /* we found what we needed */
-        if (ins->objectid) {
-                if (!(data & BTRFS_BLOCK_GROUP_DATA))
-                        trans->block_group = block_group->key.objectid;
-
-                btrfs_put_block_group(block_group);
+        } else if (ins->objectid) {
                 ret = 0;
         }
 
@@ -6526,7 +6558,7 @@ int btrfs_set_block_group_ro(struct btrfs_root *root,
 
         BUG_ON(cache->ro);
 
-        trans = btrfs_join_transaction(root, 1);
+        trans = btrfs_join_transaction(root);
         BUG_ON(IS_ERR(trans));
 
         alloc_flags = update_block_group_flags(root, cache->flags);
@@ -6882,6 +6914,7 @@ int btrfs_read_block_groups(struct btrfs_root *root)
         path = btrfs_alloc_path();
         if (!path)
                 return -ENOMEM;
+        path->reada = 1;
 
         cache_gen = btrfs_super_cache_generation(&root->fs_info->super_copy);
         if (cache_gen != 0 &&
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index c5d9fbb92bc3..7055d11c1efd 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1476,7 +1476,7 @@ u64 count_range_bits(struct extent_io_tree *tree,
                         if (total_bytes >= max_bytes)
                                 break;
                         if (!found) {
-                                *start = state->start;
+                                *start = max(cur_start, state->start);
                                 found = 1;
                         }
                         last = state->end;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index c6a22d783c35..fa4ef18b66b1 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -129,7 +129,7 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
         if (!btrfs_test_opt(root, AUTO_DEFRAG))
                 return 0;
 
-        if (root->fs_info->closing)
+        if (btrfs_fs_closing(root->fs_info))
                 return 0;
 
         if (BTRFS_I(inode)->in_defrag)
@@ -144,7 +144,7 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
         if (!defrag)
                 return -ENOMEM;
 
-        defrag->ino = inode->i_ino;
+        defrag->ino = btrfs_ino(inode);
         defrag->transid = transid;
         defrag->root = root->root_key.objectid;
 
@@ -229,7 +229,7 @@ int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info)
                 first_ino = defrag->ino + 1;
                 rb_erase(&defrag->rb_node, &fs_info->defrag_inodes);
 
-                if (fs_info->closing)
+                if (btrfs_fs_closing(fs_info))
                         goto next_free;
 
                 spin_unlock(&fs_info->defrag_inodes_lock);
@@ -1480,14 +1480,12 @@ int btrfs_sync_file(struct file *file, int datasync)
          * the current transaction, we can bail out now without any
          * syncing
          */
-        mutex_lock(&root->fs_info->trans_mutex);
+        smp_mb();
         if (BTRFS_I(inode)->last_trans <=
             root->fs_info->last_trans_committed) {
                 BTRFS_I(inode)->last_trans = 0;
-                mutex_unlock(&root->fs_info->trans_mutex);
                 goto out;
         }
-        mutex_unlock(&root->fs_info->trans_mutex);
 
         /*
          * ok we haven't committed the transaction yet, lets do a commit
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 70d45795d758..ad144736a5fd 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -98,7 +98,7 @@ struct inode *lookup_free_space_inode(struct btrfs_root *root,
                 return inode;
 
         spin_lock(&block_group->lock);
-        if (!root->fs_info->closing) {
+        if (!btrfs_fs_closing(root->fs_info)) {
                 block_group->inode = igrab(inode);
                 block_group->iref = 1;
         }
@@ -402,7 +402,14 @@ int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
                                 spin_lock(&ctl->tree_lock);
                                 ret = link_free_space(ctl, e);
                                 spin_unlock(&ctl->tree_lock);
-                                BUG_ON(ret);
+                                if (ret) {
+                                        printk(KERN_ERR "Duplicate entries in "
+                                               "free space cache, dumping\n");
+                                        kunmap(page);
+                                        unlock_page(page);
+                                        page_cache_release(page);
+                                        goto free_cache;
+                                }
                         } else {
                                 e->bitmap = kzalloc(PAGE_CACHE_SIZE, GFP_NOFS);
                                 if (!e->bitmap) {
@@ -419,6 +426,14 @@ int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
                                 ctl->op->recalc_thresholds(ctl);
                                 spin_unlock(&ctl->tree_lock);
                                 list_add_tail(&e->list, &bitmaps);
+                                if (ret) {
+                                        printk(KERN_ERR "Duplicate entries in "
+                                               "free space cache, dumping\n");
+                                        kunmap(page);
+                                        unlock_page(page);
+                                        page_cache_release(page);
+                                        goto free_cache;
+                                }
                         }
 
                         num_entries--;
@@ -478,8 +493,7 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info,
          * If we're unmounting then just return, since this does a search on the
          * normal root and not the commit root and we could deadlock.
          */
-        smp_mb();
-        if (fs_info->closing)
+        if (btrfs_fs_closing(fs_info))
                 return 0;
 
         /*
@@ -575,10 +589,25 @@ int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
 
         num_pages = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >>
                 PAGE_CACHE_SHIFT;
+
+        /* Since the first page has all of our checksums and our generation we
+         * need to calculate the offset into the page that we can start writing
+         * our entries.
+         */
+        first_page_offset = (sizeof(u32) * num_pages) + sizeof(u64);
+
         filemap_write_and_wait(inode->i_mapping);
         btrfs_wait_ordered_range(inode, inode->i_size &
                                  ~(root->sectorsize - 1), (u64)-1);
 
+        /* make sure we don't overflow that first page */
+        if (first_page_offset + sizeof(struct btrfs_free_space_entry) >= PAGE_CACHE_SIZE) {
+                /* this is really the same as running out of space, where we also return 0 */
+                printk(KERN_CRIT "Btrfs: free space cache was too big for the crc page\n");
+                ret = 0;
+                goto out_update;
+        }
+
         /* We need a checksum per page. */
         crc = checksums = kzalloc(sizeof(u32) * num_pages, GFP_NOFS);
         if (!crc)
@@ -590,12 +619,6 @@ int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
                 return -1;
         }
 
-        /* Since the first page has all of our checksums and our generation we
-         * need to calculate the offset into the page that we can start writing
-         * our entries.
-         */
-        first_page_offset = (sizeof(u32) * num_pages) + sizeof(u64);
-
         /* Get the cluster for this block_group if it exists */
         if (block_group && !list_empty(&block_group->cluster_list))
                 cluster = list_entry(block_group->cluster_list.next,
@@ -857,12 +880,14 @@ int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
         ret = 1;
 
 out_free:
+        kfree(checksums);
+        kfree(pages);
+
+out_update:
         if (ret != 1) {
                 invalidate_inode_pages2_range(inode->i_mapping, 0, index);
                 BTRFS_I(inode)->generation = 0;
         }
-        kfree(checksums);
-        kfree(pages);
         btrfs_update_inode(trans, root, inode);
         return ret;
 }
@@ -963,10 +988,16 @@ static int tree_insert_offset(struct rb_root *root, u64 offset,
                          * logically.
                          */
                         if (bitmap) {
-                                WARN_ON(info->bitmap);
+                                if (info->bitmap) {
+                                        WARN_ON_ONCE(1);
+                                        return -EEXIST;
+                                }
                                 p = &(*p)->rb_right;
                         } else {
-                                WARN_ON(!info->bitmap);
+                                if (!info->bitmap) {
+                                        WARN_ON_ONCE(1);
+                                        return -EEXIST;
+                                }
                                 p = &(*p)->rb_left;
                         }
                 }
@@ -2481,7 +2512,7 @@ struct inode *lookup_free_ino_inode(struct btrfs_root *root,
                 return inode;
 
         spin_lock(&root->cache_lock);
-        if (!root->fs_info->closing)
+        if (!btrfs_fs_closing(root->fs_info))
                 root->cache_inode = igrab(inode);
         spin_unlock(&root->cache_lock);
 
@@ -2504,12 +2535,14 @@ int load_free_ino_cache(struct btrfs_fs_info *fs_info, struct btrfs_root *root)
         int ret = 0;
         u64 root_gen = btrfs_root_generation(&root->root_item);
 
+        if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+                return 0;
+
         /*
          * If we're unmounting then just return, since this does a search on the
          * normal root and not the commit root and we could deadlock.
          */
-        smp_mb();
-        if (fs_info->closing)
+        if (btrfs_fs_closing(fs_info))
                 return 0;
 
         path = btrfs_alloc_path();
@@ -2543,6 +2576,9 @@ int btrfs_write_out_ino_cache(struct btrfs_root *root,
         struct inode *inode;
         int ret;
 
+        if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+                return 0;
+
         inode = lookup_free_ino_inode(root, path);
         if (IS_ERR(inode))
                 return 0;
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index 3262cd17a12f..b4087e0fa871 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -38,6 +38,9 @@ static int caching_kthread(void *data)
         int slot;
         int ret;
 
+        if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+                return 0;
+
         path = btrfs_alloc_path();
         if (!path)
                 return -ENOMEM;
@@ -59,8 +62,7 @@ again:
                 goto out;
 
         while (1) {
-                smp_mb();
-                if (fs_info->closing)
+                if (btrfs_fs_closing(fs_info))
                         goto out;
 
                 leaf = path->nodes[0];
@@ -141,6 +143,9 @@ static void start_caching(struct btrfs_root *root)
         int ret;
         u64 objectid;
 
+        if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+                return;
+
         spin_lock(&root->cache_lock);
         if (root->cached != BTRFS_CACHE_NO) {
                 spin_unlock(&root->cache_lock);
@@ -178,6 +183,9 @@ static void start_caching(struct btrfs_root *root)
 
 int btrfs_find_free_ino(struct btrfs_root *root, u64 *objectid)
 {
+        if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+                return btrfs_find_free_objectid(root, objectid);
+
 again:
         *objectid = btrfs_find_ino_for_alloc(root);
 
@@ -201,6 +209,10 @@ void btrfs_return_ino(struct btrfs_root *root, u64 objectid)
 {
         struct btrfs_free_space_ctl *ctl = root->free_ino_ctl;
         struct btrfs_free_space_ctl *pinned = root->free_ino_pinned;
+
+        if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+                return;
+
 again:
         if (root->cached == BTRFS_CACHE_FINISHED) {
                 __btrfs_add_free_space(ctl, objectid, 1);
@@ -250,6 +262,9 @@ void btrfs_unpin_free_ino(struct btrfs_root *root)
         struct rb_node *n;
         u64 count;
 
+        if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+                return;
+
         while (1) {
                 n = rb_first(rbroot);
                 if (!n)
@@ -388,9 +403,24 @@ int btrfs_save_ino_cache(struct btrfs_root *root,
         int prealloc;
         bool retry = false;
 
+        /* only fs tree and subvol/snap needs ino cache */
+        if (root->root_key.objectid != BTRFS_FS_TREE_OBJECTID &&
+            (root->root_key.objectid < BTRFS_FIRST_FREE_OBJECTID ||
+             root->root_key.objectid > BTRFS_LAST_FREE_OBJECTID))
+                return 0;
+
+        /* Don't save inode cache if we are deleting this root */
+        if (btrfs_root_refs(&root->root_item) == 0 &&
+            root != root->fs_info->tree_root)
+                return 0;
+
+        if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+                return 0;
+
         path = btrfs_alloc_path();
         if (!path)
                 return -ENOMEM;
+
 again:
         inode = lookup_free_ino_inode(root, path);
         if (IS_ERR(inode) && PTR_ERR(inode) != -ENOENT) {
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index bb51bb1fa44f..ebf95f7a44d6 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -138,7 +138,6 @@ static noinline int insert_inline_extent(struct btrfs_trans_handle *trans,
                 return -ENOMEM;
 
         path->leave_spinning = 1;
-        btrfs_set_trans_block_group(trans, inode);
 
         key.objectid = btrfs_ino(inode);
         key.offset = start;
@@ -426,9 +425,8 @@ again:
                 }
         }
         if (start == 0) {
-                trans = btrfs_join_transaction(root, 1);
+                trans = btrfs_join_transaction(root);
                 BUG_ON(IS_ERR(trans));
-                btrfs_set_trans_block_group(trans, inode);
                 trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 
                 /* lets try to make an inline extent */
@@ -623,8 +621,9 @@ retry:
                             async_extent->start + async_extent->ram_size - 1,
                             GFP_NOFS);
 
-                trans = btrfs_join_transaction(root, 1);
+                trans = btrfs_join_transaction(root);
                 BUG_ON(IS_ERR(trans));
+                trans->block_rsv = &root->fs_info->delalloc_block_rsv;
                 ret = btrfs_reserve_extent(trans, root,
                                            async_extent->compressed_size,
                                            async_extent->compressed_size,
@@ -793,9 +792,8 @@ static noinline int cow_file_range(struct inode *inode,
         int ret = 0;
 
         BUG_ON(is_free_space_inode(root, inode));
-        trans = btrfs_join_transaction(root, 1);
+        trans = btrfs_join_transaction(root);
         BUG_ON(IS_ERR(trans));
-        btrfs_set_trans_block_group(trans, inode);
         trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 
         num_bytes = (end - start + blocksize) & ~(blocksize - 1);
@@ -1077,10 +1075,12 @@ static noinline int run_delalloc_nocow(struct inode *inode,
         nolock = is_free_space_inode(root, inode);
 
         if (nolock)
-                trans = btrfs_join_transaction_nolock(root, 1);
+                trans = btrfs_join_transaction_nolock(root);
         else
-                trans = btrfs_join_transaction(root, 1);
+                trans = btrfs_join_transaction(root);
+
         BUG_ON(IS_ERR(trans));
+        trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 
         cow_start = (u64)-1;
         cur_offset = start;
@@ -1519,8 +1519,6 @@ static noinline int add_pending_csums(struct btrfs_trans_handle *trans,
 {
         struct btrfs_ordered_sum *sum;
 
-        btrfs_set_trans_block_group(trans, inode);
-
         list_for_each_entry(sum, list, list) {
                 btrfs_csum_file_blocks(trans,
                        BTRFS_I(inode)->root->fs_info->csum_root, sum);
@@ -1735,11 +1733,10 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
                 ret = btrfs_ordered_update_i_size(inode, 0, ordered_extent);
                 if (!ret) {
                         if (nolock)
-                                trans = btrfs_join_transaction_nolock(root, 1);
+                                trans = btrfs_join_transaction_nolock(root);
                         else
-                                trans = btrfs_join_transaction(root, 1);
+                                trans = btrfs_join_transaction(root);
                         BUG_ON(IS_ERR(trans));
-                        btrfs_set_trans_block_group(trans, inode);
                         trans->block_rsv = &root->fs_info->delalloc_block_rsv;
                         ret = btrfs_update_inode(trans, root, inode);
                         BUG_ON(ret);
@@ -1752,11 +1749,10 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
                          0, &cached_state, GFP_NOFS);
 
         if (nolock)
-                trans = btrfs_join_transaction_nolock(root, 1);
+                trans = btrfs_join_transaction_nolock(root);
         else
-                trans = btrfs_join_transaction(root, 1);
+                trans = btrfs_join_transaction(root);
         BUG_ON(IS_ERR(trans));
-        btrfs_set_trans_block_group(trans, inode);
         trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 
         if (test_bit(BTRFS_ORDERED_COMPRESSED, &ordered_extent->flags))
@@ -2431,7 +2427,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
                                         (u64)-1);
 
         if (root->orphan_block_rsv || root->orphan_item_inserted) {
-                trans = btrfs_join_transaction(root, 1);
+                trans = btrfs_join_transaction(root);
                 if (!IS_ERR(trans))
                         btrfs_end_transaction(trans, root);
         }
@@ -2511,12 +2507,12 @@ static void btrfs_read_locked_inode(struct inode *inode)
         struct btrfs_root *root = BTRFS_I(inode)->root;
         struct btrfs_key location;
         int maybe_acls;
-        u64 alloc_group_block;
         u32 rdev;
         int ret;
 
         path = btrfs_alloc_path();
         BUG_ON(!path);
+        path->leave_spinning = 1;
         memcpy(&location, &BTRFS_I(inode)->location, sizeof(location));
 
         ret = btrfs_lookup_inode(NULL, root, path, &location, 0);
@@ -2526,6 +2522,12 @@ static void btrfs_read_locked_inode(struct inode *inode)
         leaf = path->nodes[0];
         inode_item = btrfs_item_ptr(leaf, path->slots[0],
                                     struct btrfs_inode_item);
+        if (!leaf->map_token)
+                map_private_extent_buffer(leaf, (unsigned long)inode_item,
+                                          sizeof(struct btrfs_inode_item),
+                                          &leaf->map_token, &leaf->kaddr,
+                                          &leaf->map_start, &leaf->map_len,
+                                          KM_USER1);
 
         inode->i_mode = btrfs_inode_mode(leaf, inode_item);
         inode->i_nlink = btrfs_inode_nlink(leaf, inode_item);
@@ -2555,8 +2557,6 @@ static void btrfs_read_locked_inode(struct inode *inode)
         BTRFS_I(inode)->index_cnt = (u64)-1;
         BTRFS_I(inode)->flags = btrfs_inode_flags(leaf, inode_item);
 
-        alloc_group_block = btrfs_inode_block_group(leaf, inode_item);
-
         /*
          * try to precache a NULL acl entry for files that don't have
          * any xattrs or acls
@@ -2566,8 +2566,11 @@ static void btrfs_read_locked_inode(struct inode *inode)
         if (!maybe_acls)
                 cache_no_acl(inode);
 
-        BTRFS_I(inode)->block_group = btrfs_find_block_group(root, 0,
-                                                alloc_group_block, 0);
+        if (leaf->map_token) {
+                unmap_extent_buffer(leaf, leaf->map_token, KM_USER1);
+                leaf->map_token = NULL;
+        }
+
         btrfs_free_path(path);
         inode_item = NULL;
 
@@ -2647,7 +2650,7 @@ static void fill_inode_item(struct btrfs_trans_handle *trans,
         btrfs_set_inode_transid(leaf, item, trans->transid);
         btrfs_set_inode_rdev(leaf, item, inode->i_rdev);
         btrfs_set_inode_flags(leaf, item, BTRFS_I(inode)->flags);
-        btrfs_set_inode_block_group(leaf, item, BTRFS_I(inode)->block_group);
+        btrfs_set_inode_block_group(leaf, item, 0);
 
         if (leaf->map_token) {
                 unmap_extent_buffer(leaf, leaf->map_token, KM_USER1);
@@ -3004,8 +3007,6 @@ static int btrfs_unlink(struct inode *dir, struct dentry *dentry)
         if (IS_ERR(trans))
                 return PTR_ERR(trans);
 
-        btrfs_set_trans_block_group(trans, dir);
-
         btrfs_record_unlink_dir(trans, dir, dentry->d_inode, 0);
 
         ret = btrfs_unlink_inode(trans, root, dir, dentry->d_inode,
@@ -3094,8 +3095,6 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
         if (IS_ERR(trans))
                 return PTR_ERR(trans);
 
-        btrfs_set_trans_block_group(trans, dir);
-
         if (unlikely(btrfs_ino(inode) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) {
                 err = btrfs_unlink_subvol(trans, root, dir,
                                           BTRFS_I(inode)->location.objectid,
@@ -3514,7 +3513,6 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
                                 err = PTR_ERR(trans);
                                 break;
                         }
-                        btrfs_set_trans_block_group(trans, inode);
 
                         err = btrfs_drop_extents(trans, inode, cur_offset,
                                                  cur_offset + hole_size,
@@ -3650,7 +3648,6 @@ void btrfs_evict_inode(struct inode *inode)
         while (1) {
                 trans = btrfs_start_transaction(root, 0);
                 BUG_ON(IS_ERR(trans));
-                btrfs_set_trans_block_group(trans, inode);
                 trans->block_rsv = root->orphan_block_rsv;
 
                 ret = btrfs_block_rsv_check(trans, root,
@@ -4133,7 +4130,8 @@ static int btrfs_real_readdir(struct file *filp, void *dirent,
         path = btrfs_alloc_path();
         if (!path)
                 return -ENOMEM;
-        path->reada = 2;
+
+        path->reada = 1;
 
         if (key_type == BTRFS_DIR_INDEX_KEY) {
                 INIT_LIST_HEAD(&ins_list);
@@ -4268,18 +4266,16 @@ int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc)
         if (BTRFS_I(inode)->dummy_inode)
                 return 0;
 
-        smp_mb();
-        if (root->fs_info->closing && is_free_space_inode(root, inode))
+        if (btrfs_fs_closing(root->fs_info) && is_free_space_inode(root, inode))
                 nolock = true;
 
         if (wbc->sync_mode == WB_SYNC_ALL) {
                 if (nolock)
-                        trans = btrfs_join_transaction_nolock(root, 1);
+                        trans = btrfs_join_transaction_nolock(root);
                 else
-                        trans = btrfs_join_transaction(root, 1);
+                        trans = btrfs_join_transaction(root);
                 if (IS_ERR(trans))
                         return PTR_ERR(trans);
-                btrfs_set_trans_block_group(trans, inode);
                 if (nolock)
                         ret = btrfs_end_transaction_nolock(trans, root);
                 else
@@ -4294,7 +4290,7 @@ int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc)
  * FIXME, needs more benchmarking...there are no reasons other than performance
  * to keep or drop this code.
  */
-void btrfs_dirty_inode(struct inode *inode)
+void btrfs_dirty_inode(struct inode *inode, int flags)
 {
         struct btrfs_root *root = BTRFS_I(inode)->root;
         struct btrfs_trans_handle *trans;
@@ -4303,9 +4299,8 @@ void btrfs_dirty_inode(struct inode *inode)
         if (BTRFS_I(inode)->dummy_inode)
                 return;
 
-        trans = btrfs_join_transaction(root, 1);
+        trans = btrfs_join_transaction(root);
         BUG_ON(IS_ERR(trans));
-        btrfs_set_trans_block_group(trans, inode);
 
         ret = btrfs_update_inode(trans, root, inode);
         if (ret && ret == -ENOSPC) {
@@ -4319,7 +4314,6 @@ void btrfs_dirty_inode(struct inode *inode)
                                        PTR_ERR(trans));
                         return;
                 }
-                btrfs_set_trans_block_group(trans, inode);
 
                 ret = btrfs_update_inode(trans, root, inode);
                 if (ret) {
@@ -4418,8 +4412,8 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
                                      struct btrfs_root *root,
                                      struct inode *dir,
                                      const char *name, int name_len,
-                                     u64 ref_objectid, u64 objectid,
-                                     u64 alloc_hint, int mode, u64 *index)
+                                     u64 ref_objectid, u64 objectid, int mode,
+                                     u64 *index)
 {
         struct inode *inode;
         struct btrfs_inode_item *inode_item;
@@ -4472,8 +4466,6 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
                 owner = 0;
         else
                 owner = 1;
-        BTRFS_I(inode)->block_group =
-                        btrfs_find_block_group(root, 0, alloc_hint, owner);
 
         key[0].objectid = objectid;
         btrfs_set_key_type(&key[0], BTRFS_INODE_ITEM_KEY);
@@ -4629,15 +4621,13 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
         if (IS_ERR(trans))
                 return PTR_ERR(trans);
 
-        btrfs_set_trans_block_group(trans, dir);
-
         err = btrfs_find_free_ino(root, &objectid);
         if (err)
                 goto out_unlock;
 
         inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name,
                                 dentry->d_name.len, btrfs_ino(dir), objectid,
-                                BTRFS_I(dir)->block_group, mode, &index);
+                                mode, &index);
         if (IS_ERR(inode)) {
                 err = PTR_ERR(inode);
                 goto out_unlock;
@@ -4649,7 +4639,6 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
                 goto out_unlock;
         }
 
-        btrfs_set_trans_block_group(trans, inode);
         err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
         if (err)
                 drop_inode = 1;
@@ -4658,8 +4647,6 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
                 init_special_inode(inode, inode->i_mode, rdev);
                 btrfs_update_inode(trans, root, inode);
         }
-        btrfs_update_inode_block_group(trans, inode);
-        btrfs_update_inode_block_group(trans, dir);
 out_unlock:
         nr = trans->blocks_used;
         btrfs_end_transaction_throttle(trans, root);
@@ -4692,15 +4679,13 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
         if (IS_ERR(trans))
                 return PTR_ERR(trans);
 
-        btrfs_set_trans_block_group(trans, dir);
-
         err = btrfs_find_free_ino(root, &objectid);
         if (err)
                 goto out_unlock;
 
         inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name,
                                 dentry->d_name.len, btrfs_ino(dir), objectid,
-                                BTRFS_I(dir)->block_group, mode, &index);
+                                mode, &index);
         if (IS_ERR(inode)) {
                 err = PTR_ERR(inode);
                 goto out_unlock;
@@ -4712,7 +4697,6 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
                 goto out_unlock;
         }
 
-        btrfs_set_trans_block_group(trans, inode);
         err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
         if (err)
                 drop_inode = 1;
@@ -4723,8 +4707,6 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
                 inode->i_op = &btrfs_file_inode_operations;
                 BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
         }
-        btrfs_update_inode_block_group(trans, inode);
-        btrfs_update_inode_block_group(trans, dir);
 out_unlock:
         nr = trans->blocks_used;
         btrfs_end_transaction_throttle(trans, root);
@@ -4771,8 +4753,6 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 
         btrfs_inc_nlink(inode);
         inode->i_ctime = CURRENT_TIME;
-
-        btrfs_set_trans_block_group(trans, dir);
         ihold(inode);
 
         err = btrfs_add_nondir(trans, dir, dentry, inode, 1, index);
@@ -4781,7 +4761,6 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
                 drop_inode = 1;
         } else {
                 struct dentry *parent = dget_parent(dentry);
-                btrfs_update_inode_block_group(trans, dir);
                 err = btrfs_update_inode(trans, root, inode);
                 BUG_ON(err);
                 btrfs_log_new_name(trans, inode, NULL, parent);
@@ -4818,7 +4797,6 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
         trans = btrfs_start_transaction(root, 5);
         if (IS_ERR(trans))
                 return PTR_ERR(trans);
-        btrfs_set_trans_block_group(trans, dir);
 
         err = btrfs_find_free_ino(root, &objectid);
         if (err)
@@ -4826,8 +4804,7 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 
         inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name,
                                 dentry->d_name.len, btrfs_ino(dir), objectid,
-                                BTRFS_I(dir)->block_group, S_IFDIR | mode,
-                                &index);
+                                S_IFDIR | mode, &index);
         if (IS_ERR(inode)) {
                 err = PTR_ERR(inode);
                 goto out_fail;
@@ -4841,7 +4818,6 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 
         inode->i_op = &btrfs_dir_inode_operations;
         inode->i_fop = &btrfs_dir_file_operations;
-        btrfs_set_trans_block_group(trans, inode);
 
         btrfs_i_size_write(inode, 0);
         err = btrfs_update_inode(trans, root, inode);
@@ -4855,8 +4831,6 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 
         d_instantiate(dentry, inode);
         drop_on_err = 0;
-        btrfs_update_inode_block_group(trans, inode);
-        btrfs_update_inode_block_group(trans, dir);
 
 out_fail:
         nr = trans->blocks_used;
@@ -4989,7 +4963,15 @@ again:
 
         if (!path) {
                 path = btrfs_alloc_path();
-                BUG_ON(!path);
+                if (!path) {
+                        err = -ENOMEM;
+                        goto out;
+                }
+                /*
+                 * Chances are we'll be called again, so go ahead and do
+                 * readahead
+                 */
+                path->reada = 1;
         }
 
         ret = btrfs_lookup_file_extent(trans, root, path,
@@ -5130,8 +5112,10 @@ again:
                                 kunmap(page);
                                 free_extent_map(em);
                                 em = NULL;
+
                                 btrfs_release_path(path);
-                                trans = btrfs_join_transaction(root, 1);
+                                trans = btrfs_join_transaction(root);
+
                                 if (IS_ERR(trans))
                                         return ERR_CAST(trans);
                                 goto again;
@@ -5375,7 +5359,7 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
                 btrfs_drop_extent_cache(inode, start, start + len - 1, 0);
         }
 
-        trans = btrfs_join_transaction(root, 0);
+        trans = btrfs_join_transaction(root);
         if (IS_ERR(trans))
                 return ERR_CAST(trans);
 
@@ -5611,7 +5595,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
                  * to make sure the current transaction stays open
                  * while we look for nocow cross refs
                  */
-                trans = btrfs_join_transaction(root, 0);
+                trans = btrfs_join_transaction(root);
                 if (IS_ERR(trans))
                         goto must_cow;
 
@@ -5750,7 +5734,7 @@ again:
 
         BUG_ON(!ordered);
 
-        trans = btrfs_join_transaction(root, 1);
+        trans = btrfs_join_transaction(root);
         if (IS_ERR(trans)) {
                 err = -ENOMEM;
                 goto out;
@@ -6500,6 +6484,7 @@ out:
 static int btrfs_truncate(struct inode *inode)
 {
         struct btrfs_root *root = BTRFS_I(inode)->root;
+        struct btrfs_block_rsv *rsv;
         int ret;
         int err = 0;
         struct btrfs_trans_handle *trans;
@@ -6513,28 +6498,80 @@ static int btrfs_truncate(struct inode *inode)
         btrfs_wait_ordered_range(inode, inode->i_size & (~mask), (u64)-1);
         btrfs_ordered_update_i_size(inode, inode->i_size, NULL);
 
-        trans = btrfs_start_transaction(root, 5);
-        if (IS_ERR(trans))
-                return PTR_ERR(trans);
+        /*
+         * Yes ladies and gentelment, this is indeed ugly.  The fact is we have
+         * 3 things going on here
+         *
+         * 1) We need to reserve space for our orphan item and the space to
+         * delete our orphan item.  Lord knows we don't want to have a dangling
+         * orphan item because we didn't reserve space to remove it.
+         *
+         * 2) We need to reserve space to update our inode.
+         *
+         * 3) We need to have something to cache all the space that is going to
+         * be free'd up by the truncate operation, but also have some slack
+         * space reserved in case it uses space during the truncate (thank you
+         * very much snapshotting).
+         *
+         * And we need these to all be seperate.  The fact is we can use alot of
+         * space doing the truncate, and we have no earthly idea how much space
+         * we will use, so we need the truncate reservation to be seperate so it
+         * doesn't end up using space reserved for updating the inode or
+         * removing the orphan item.  We also need to be able to stop the
+         * transaction and start a new one, which means we need to be able to
+         * update the inode several times, and we have no idea of knowing how
+         * many times that will be, so we can't just reserve 1 item for the
+         * entirety of the opration, so that has to be done seperately as well.
+         * Then there is the orphan item, which does indeed need to be held on
+         * to for the whole operation, and we need nobody to touch this reserved
+         * space except the orphan code.
+         *
+         * So that leaves us with
+         *
+         * 1) root->orphan_block_rsv - for the orphan deletion.
+         * 2) rsv - for the truncate reservation, which we will steal from the
+         * transaction reservation.
+         * 3) fs_info->trans_block_rsv - this will have 1 items worth left for
+         * updating the inode.
+         */
+        rsv = btrfs_alloc_block_rsv(root);
+        if (!rsv)
+                return -ENOMEM;
+        btrfs_add_durable_block_rsv(root->fs_info, rsv);
+
+        trans = btrfs_start_transaction(root, 4);
+        if (IS_ERR(trans)) {
+                err = PTR_ERR(trans);
+                goto out;
+        }
 
-        btrfs_set_trans_block_group(trans, inode);
+        /*
+         * Reserve space for the truncate process.  Truncate should be adding
+         * space, but if there are snapshots it may end up using space.
+         */
+        ret = btrfs_truncate_reserve_metadata(trans, root, rsv);
+        BUG_ON(ret);
 
         ret = btrfs_orphan_add(trans, inode);
         if (ret) {
                 btrfs_end_transaction(trans, root);
-                return ret;
+                goto out;
         }
 
         nr = trans->blocks_used;
         btrfs_end_transaction(trans, root);
         btrfs_btree_balance_dirty(root, nr);
 
-        /* Now start a transaction for the truncate */
-        trans = btrfs_start_transaction(root, 0);
-        if (IS_ERR(trans))
-                return PTR_ERR(trans);
-        btrfs_set_trans_block_group(trans, inode);
-        trans->block_rsv = root->orphan_block_rsv;
+        /*
+         * Ok so we've already migrated our bytes over for the truncate, so here
+         * just reserve the one slot we need for updating the inode.
+         */
+        trans = btrfs_start_transaction(root, 1);
+        if (IS_ERR(trans)) {
+                err = PTR_ERR(trans);
+                goto out;
+        }
+        trans->block_rsv = rsv;
 
         /*
          * setattr is responsible for setting the ordered_data_close flag,
@@ -6558,24 +6595,17 @@ static int btrfs_truncate(struct inode *inode)
 
         while (1) {
                 if (!trans) {
-                        trans = btrfs_start_transaction(root, 0);
-                        if (IS_ERR(trans))
-                                return PTR_ERR(trans);
-                        btrfs_set_trans_block_group(trans, inode);
-                        trans->block_rsv = root->orphan_block_rsv;
-                }
+                        trans = btrfs_start_transaction(root, 3);
+                        if (IS_ERR(trans)) {
+                                err = PTR_ERR(trans);
+                                goto out;
+                        }
 
-                ret = btrfs_block_rsv_check(trans, root,
-                                            root->orphan_block_rsv, 0, 5);
-                if (ret == -EAGAIN) {
-                        ret = btrfs_commit_transaction(trans, root);
-                        if (ret)
-                                return ret;
-                        trans = NULL;
-                        continue;
-                } else if (ret) {
-                        err = ret;
-                        break;
+                        ret = btrfs_truncate_reserve_metadata(trans, root,
+                                                              rsv);
+                        BUG_ON(ret);
+
+                        trans->block_rsv = rsv;
                 }
 
                 ret = btrfs_truncate_inode_items(trans, root, inode,
@@ -6586,6 +6616,7 @@ static int btrfs_truncate(struct inode *inode)
                         break;
                 }
 
+                trans->block_rsv = &root->fs_info->trans_block_rsv;
                 ret = btrfs_update_inode(trans, root, inode);
                 if (ret) {
                         err = ret;
@@ -6599,6 +6630,7 @@ static int btrfs_truncate(struct inode *inode)
         }
 
         if (ret == 0 && inode->i_nlink > 0) {
+                trans->block_rsv = root->orphan_block_rsv;
                 ret = btrfs_orphan_del(trans, inode);
                 if (ret)
                         err = ret;
@@ -6610,15 +6642,20 @@ static int btrfs_truncate(struct inode *inode)
                 ret = btrfs_orphan_del(NULL, inode);
         }
 
+        trans->block_rsv = &root->fs_info->trans_block_rsv;
         ret = btrfs_update_inode(trans, root, inode);
         if (ret && !err)
                 err = ret;
 
         nr = trans->blocks_used;
         ret = btrfs_end_transaction_throttle(trans, root);
+        btrfs_btree_balance_dirty(root, nr);
+
+out:
+        btrfs_free_block_rsv(root, rsv);
+
         if (ret && !err)
                 err = ret;
-        btrfs_btree_balance_dirty(root, nr);
 
         return err;
 }
@@ -6627,15 +6664,14 @@ static int btrfs_truncate(struct inode *inode)
  * create a new subvolume directory/inode (helper for the ioctl).
  */
 int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
-                             struct btrfs_root *new_root,
-                             u64 new_dirid, u64 alloc_hint)
+                             struct btrfs_root *new_root, u64 new_dirid)
 {
         struct inode *inode;
         int err;
         u64 index = 0;
 
         inode = btrfs_new_inode(trans, new_root, NULL, "..", 2, new_dirid,
-                                new_dirid, alloc_hint, S_IFDIR | 0700, &index);
+                                new_dirid, S_IFDIR | 0700, &index);
         if (IS_ERR(inode))
                 return PTR_ERR(inode);
         inode->i_op = &btrfs_dir_inode_operations;
@@ -6748,21 +6784,6 @@ void btrfs_destroy_inode(struct inode *inode)
                 spin_unlock(&root->fs_info->ordered_extent_lock);
         }
 
-        if (root == root->fs_info->tree_root) {
-                struct btrfs_block_group_cache *block_group;
-
-                block_group = btrfs_lookup_block_group(root->fs_info,
-                                                BTRFS_I(inode)->block_group);
-                if (block_group && block_group->inode == inode) {
-                        spin_lock(&block_group->lock);
-                        block_group->inode = NULL;
-                        spin_unlock(&block_group->lock);
-                        btrfs_put_block_group(block_group);
-                } else if (block_group) {
-                        btrfs_put_block_group(block_group);
-                }
-        }
-
         spin_lock(&root->orphan_lock);
         if (!list_empty(&BTRFS_I(inode)->i_orphan)) {
                 printk(KERN_INFO "BTRFS: inode %llu still on the orphan list\n",
@@ -6948,8 +6969,6 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
                 goto out_notrans;
         }
 
-        btrfs_set_trans_block_group(trans, new_dir);
-
         if (dest != root)
                 btrfs_record_root_in_trans(trans, dest);
 
@@ -7131,16 +7150,13 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
         if (IS_ERR(trans))
                 return PTR_ERR(trans);
 
-        btrfs_set_trans_block_group(trans, dir);
-
         err = btrfs_find_free_ino(root, &objectid);
         if (err)
                 goto out_unlock;
 
         inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name,
                                 dentry->d_name.len, btrfs_ino(dir), objectid,
-                                BTRFS_I(dir)->block_group, S_IFLNK|S_IRWXUGO,
-                                &index);
+                                S_IFLNK|S_IRWXUGO, &index);
         if (IS_ERR(inode)) {
                 err = PTR_ERR(inode);
                 goto out_unlock;
@@ -7152,7 +7168,6 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
                 goto out_unlock;
         }
 
-        btrfs_set_trans_block_group(trans, inode);
         err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
         if (err)
                 drop_inode = 1;
@@ -7163,8 +7178,6 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
                 inode->i_op = &btrfs_file_inode_operations;
                 BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
         }
-        btrfs_update_inode_block_group(trans, inode);
-        btrfs_update_inode_block_group(trans, dir);
         if (drop_inode)
                 goto out_unlock;
 
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 85e818ce00c5..ac37040e426a 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -243,7 +243,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
                 ip->flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS);
         }
 
-        trans = btrfs_join_transaction(root, 1);
+        trans = btrfs_join_transaction(root);
         BUG_ON(IS_ERR(trans));
 
         ret = btrfs_update_inode(trans, root, inode);
@@ -414,8 +414,7 @@ static noinline int create_subvol(struct btrfs_root *root,
 
         btrfs_record_root_in_trans(trans, new_root);
 
-        ret = btrfs_create_subvol_root(trans, new_root, new_dirid,
-                                       BTRFS_I(dir)->block_group);
+        ret = btrfs_create_subvol_root(trans, new_root, new_dirid);
         /*
          * insert the directory item
          */
@@ -707,16 +706,17 @@ static int find_new_extents(struct btrfs_root *root,
         struct btrfs_file_extent_item *extent;
         int type;
         int ret;
+        u64 ino = btrfs_ino(inode);
 
         path = btrfs_alloc_path();
         if (!path)
                 return -ENOMEM;
 
-        min_key.objectid = inode->i_ino;
+        min_key.objectid = ino;
         min_key.type = BTRFS_EXTENT_DATA_KEY;
         min_key.offset = *off;
 
-        max_key.objectid = inode->i_ino;
+        max_key.objectid = ino;
         max_key.type = (u8)-1;
         max_key.offset = (u64)-1;
 
@@ -727,7 +727,7 @@ static int find_new_extents(struct btrfs_root *root,
                                            path, 0, newer_than);
                 if (ret != 0)
                         goto none;
-                if (min_key.objectid != inode->i_ino)
+                if (min_key.objectid != ino)
                         goto none;
                 if (min_key.type != BTRFS_EXTENT_DATA_KEY)
                         goto none;
@@ -2489,12 +2489,10 @@ static long btrfs_ioctl_trans_start(struct file *file)
         if (ret)
                 goto out;
 
-        mutex_lock(&root->fs_info->trans_mutex);
-        root->fs_info->open_ioctl_trans++;
-        mutex_unlock(&root->fs_info->trans_mutex);
+        atomic_inc(&root->fs_info->open_ioctl_trans);
 
         ret = -ENOMEM;
-        trans = btrfs_start_ioctl_transaction(root, 0);
+        trans = btrfs_start_ioctl_transaction(root);
         if (IS_ERR(trans))
                 goto out_drop;
 
@@ -2502,9 +2500,7 @@ static long btrfs_ioctl_trans_start(struct file *file)
         return 0;
 
 out_drop:
-        mutex_lock(&root->fs_info->trans_mutex);
-        root->fs_info->open_ioctl_trans--;
-        mutex_unlock(&root->fs_info->trans_mutex);
+        atomic_dec(&root->fs_info->open_ioctl_trans);
         mnt_drop_write(file->f_path.mnt);
 out:
         return ret;
@@ -2738,9 +2734,7 @@ long btrfs_ioctl_trans_end(struct file *file)
 
         btrfs_end_transaction(trans, root);
 
-        mutex_lock(&root->fs_info->trans_mutex);
-        root->fs_info->open_ioctl_trans--;
-        mutex_unlock(&root->fs_info->trans_mutex);
+        atomic_dec(&root->fs_info->open_ioctl_trans);
 
         mnt_drop_write(file->f_path.mnt);
         return 0;
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index ca38eca70af0..b1ef27cc673b 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -677,6 +677,8 @@ struct backref_node *build_backref_tree(struct reloc_control *rc,
                 err = -ENOMEM;
                 goto out;
         }
+        path1->reada = 1;
+        path2->reada = 2;
 
         node = alloc_backref_node(cache);
         if (!node) {
@@ -1999,6 +2001,7 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc,
         path = btrfs_alloc_path();
         if (!path)
                 return -ENOMEM;
+        path->reada = 1;
 
         reloc_root = root->reloc_root;
         root_item = &reloc_root->root_item;
@@ -2139,10 +2142,10 @@ int prepare_to_merge(struct reloc_control *rc, int err)
         u64 num_bytes = 0;
         int ret;
 
-        mutex_lock(&root->fs_info->trans_mutex);
+        spin_lock(&root->fs_info->trans_lock);
         rc->merging_rsv_size += root->nodesize * (BTRFS_MAX_LEVEL - 1) * 2;
         rc->merging_rsv_size += rc->nodes_relocated * 2;
-        mutex_unlock(&root->fs_info->trans_mutex);
+        spin_unlock(&root->fs_info->trans_lock);
 again:
         if (!err) {
                 num_bytes = rc->merging_rsv_size;
@@ -2152,7 +2155,7 @@ again:
                         err = ret;
         }
 
-        trans = btrfs_join_transaction(rc->extent_root, 1);
+        trans = btrfs_join_transaction(rc->extent_root);
         if (IS_ERR(trans)) {
                 if (!err)
                         btrfs_block_rsv_release(rc->extent_root,
@@ -2211,9 +2214,9 @@ int merge_reloc_roots(struct reloc_control *rc)
         int ret;
 again:
         root = rc->extent_root;
-        mutex_lock(&root->fs_info->trans_mutex);
+        spin_lock(&root->fs_info->trans_lock);
         list_splice_init(&rc->reloc_roots, &reloc_roots);
-        mutex_unlock(&root->fs_info->trans_mutex);
+        spin_unlock(&root->fs_info->trans_lock);
 
         while (!list_empty(&reloc_roots)) {
                 found = 1;
@@ -3236,7 +3239,7 @@ truncate:
                 goto out;
         }
 
-        trans = btrfs_join_transaction(root, 0);
+        trans = btrfs_join_transaction(root);
         if (IS_ERR(trans)) {
                 btrfs_free_path(path);
                 ret = PTR_ERR(trans);
@@ -3300,6 +3303,7 @@ static int find_data_references(struct reloc_control *rc,
         path = btrfs_alloc_path();
         if (!path)
                 return -ENOMEM;
+        path->reada = 1;
 
         root = read_fs_root(rc->extent_root->fs_info, ref_root);
         if (IS_ERR(root)) {
@@ -3586,17 +3590,17 @@ next:
 static void set_reloc_control(struct reloc_control *rc)
 {
         struct btrfs_fs_info *fs_info = rc->extent_root->fs_info;
-        mutex_lock(&fs_info->trans_mutex);
+        spin_lock(&fs_info->trans_lock);
         fs_info->reloc_ctl = rc;
-        mutex_unlock(&fs_info->trans_mutex);
+        spin_unlock(&fs_info->trans_lock);
 }
 
 static void unset_reloc_control(struct reloc_control *rc)
 {
         struct btrfs_fs_info *fs_info = rc->extent_root->fs_info;
-        mutex_lock(&fs_info->trans_mutex);
+        spin_lock(&fs_info->trans_lock);
         fs_info->reloc_ctl = NULL;
-        mutex_unlock(&fs_info->trans_mutex);
+        spin_unlock(&fs_info->trans_lock);
 }
 
 static int check_extent_flags(u64 flags)
@@ -3645,7 +3649,7 @@ int prepare_to_relocate(struct reloc_control *rc)
         rc->create_reloc_tree = 1;
         set_reloc_control(rc);
 
-        trans = btrfs_join_transaction(rc->extent_root, 1);
+        trans = btrfs_join_transaction(rc->extent_root);
         BUG_ON(IS_ERR(trans));
         btrfs_commit_transaction(trans, rc->extent_root);
         return 0;
@@ -3668,6 +3672,7 @@ static noinline_for_stack int relocate_block_group(struct reloc_control *rc)
         path = btrfs_alloc_path();
         if (!path)
                 return -ENOMEM;
+        path->reada = 1;
 
         ret = prepare_to_relocate(rc);
         if (ret) {
@@ -3834,7 +3839,7 @@ restart:
         btrfs_block_rsv_release(rc->extent_root, rc->block_rsv, (u64)-1);
 
         /* get rid of pinned extents */
-        trans = btrfs_join_transaction(rc->extent_root, 1);
+        trans = btrfs_join_transaction(rc->extent_root);
         if (IS_ERR(trans))
                 err = PTR_ERR(trans);
         else
@@ -4093,6 +4098,7 @@ int btrfs_recover_relocation(struct btrfs_root *root)
         path = btrfs_alloc_path();
         if (!path)
                 return -ENOMEM;
+        path->reada = -1;
 
         key.objectid = BTRFS_TREE_RELOC_OBJECTID;
         key.type = BTRFS_ROOT_ITEM_KEY;
@@ -4159,7 +4165,7 @@ int btrfs_recover_relocation(struct btrfs_root *root)
 
         set_reloc_control(rc);
 
-        trans = btrfs_join_transaction(rc->extent_root, 1);
+        trans = btrfs_join_transaction(rc->extent_root);
         if (IS_ERR(trans)) {
                 unset_reloc_control(rc);
                 err = PTR_ERR(trans);
@@ -4193,7 +4199,7 @@ int btrfs_recover_relocation(struct btrfs_root *root)
 
         unset_reloc_control(rc);
 
-        trans = btrfs_join_transaction(rc->extent_root, 1);
+        trans = btrfs_join_transaction(rc->extent_root);
         if (IS_ERR(trans))
                 err = PTR_ERR(trans);
         else
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 6dfed0c27ac3..df50fd1eca8f 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -117,33 +117,37 @@ static void scrub_free_csums(struct scrub_dev *sdev)
         }
 }
 
+static void scrub_free_bio(struct bio *bio)
+{
+        int i;
+        struct page *last_page = NULL;
+
+        if (!bio)
+                return;
+
+        for (i = 0; i < bio->bi_vcnt; ++i) {
+                if (bio->bi_io_vec[i].bv_page == last_page)
+                        continue;
+                last_page = bio->bi_io_vec[i].bv_page;
+                __free_page(last_page);
+        }
+        bio_put(bio);
+}
+
 static noinline_for_stack void scrub_free_dev(struct scrub_dev *sdev)
 {
         int i;
-        int j;
-        struct page *last_page;
 
         if (!sdev)
                 return;
 
         for (i = 0; i < SCRUB_BIOS_PER_DEV; ++i) {
                 struct scrub_bio *sbio = sdev->bios[i];
-                struct bio *bio;
 
                 if (!sbio)
                         break;
 
-                bio = sbio->bio;
-                if (bio) {
-                        last_page = NULL;
-                        for (j = 0; j < bio->bi_vcnt; ++j) {
-                                if (bio->bi_io_vec[j].bv_page == last_page)
-                                        continue;
-                                last_page = bio->bi_io_vec[j].bv_page;
-                                __free_page(last_page);
-                        }
-                        bio_put(bio);
-                }
+                scrub_free_bio(sbio->bio);
                 kfree(sbio);
         }
 
@@ -156,8 +160,6 @@ struct scrub_dev *scrub_setup_dev(struct btrfs_device *dev)
 {
         struct scrub_dev *sdev;
         int             i;
-        int             j;
-        int             ret;
         struct btrfs_fs_info *fs_info = dev->dev_root->fs_info;
 
         sdev = kzalloc(sizeof(*sdev), GFP_NOFS);
@@ -165,7 +167,6 @@ struct scrub_dev *scrub_setup_dev(struct btrfs_device *dev)
                 goto nomem;
         sdev->dev = dev;
         for (i = 0; i < SCRUB_BIOS_PER_DEV; ++i) {
-                struct bio *bio;
                 struct scrub_bio *sbio;
 
                 sbio = kzalloc(sizeof(*sbio), GFP_NOFS);
@@ -173,32 +174,10 @@ struct scrub_dev *scrub_setup_dev(struct btrfs_device *dev)
                         goto nomem;
                 sdev->bios[i] = sbio;
 
-                bio = bio_kmalloc(GFP_NOFS, SCRUB_PAGES_PER_BIO);
-                if (!bio)
-                        goto nomem;
-
                 sbio->index = i;
                 sbio->sdev = sdev;
-                sbio->bio = bio;
                 sbio->count = 0;
                 sbio->work.func = scrub_checksum;
-                bio->bi_private = sdev->bios[i];
-                bio->bi_end_io = scrub_bio_end_io;
-                bio->bi_sector = 0;
-                bio->bi_bdev = dev->bdev;
-                bio->bi_size = 0;
-
-                for (j = 0; j < SCRUB_PAGES_PER_BIO; ++j) {
-                        struct page *page;
-                        page = alloc_page(GFP_NOFS);
-                        if (!page)
-                                goto nomem;
-
-                        ret = bio_add_page(bio, page, PAGE_SIZE, 0);
-                        if (!ret)
-                                goto nomem;
-                }
-                WARN_ON(bio->bi_vcnt != SCRUB_PAGES_PER_BIO);
 
                 if (i != SCRUB_BIOS_PER_DEV-1)
                         sdev->bios[i]->next_free = i + 1;
@@ -369,9 +348,6 @@ static int scrub_fixup_io(int rw, struct block_device *bdev, sector_t sector,
         int ret;
         DECLARE_COMPLETION_ONSTACK(complete);
 
-        /* we are going to wait on this IO */
-        rw |= REQ_SYNC;
-
         bio = bio_alloc(GFP_NOFS, 1);
         bio->bi_bdev = bdev;
         bio->bi_sector = sector;
@@ -380,6 +356,7 @@ static int scrub_fixup_io(int rw, struct block_device *bdev, sector_t sector,
         bio->bi_private = &complete;
         submit_bio(rw, bio);
 
+        /* this will also unplug the queue */
         wait_for_completion(&complete);
 
         ret = !test_bit(BIO_UPTODATE, &bio->bi_flags);
@@ -394,6 +371,7 @@ static void scrub_bio_end_io(struct bio *bio, int err)
         struct btrfs_fs_info *fs_info = sdev->dev->dev_root->fs_info;
 
         sbio->err = err;
+        sbio->bio = bio;
 
         btrfs_queue_worker(&fs_info->scrub_workers, &sbio->work);
 }
@@ -453,6 +431,8 @@ static void scrub_checksum(struct btrfs_work *work)
         }
 
 out:
+        scrub_free_bio(sbio->bio);
+        sbio->bio = NULL;
         spin_lock(&sdev->list_lock);
         sbio->next_free = sdev->first_free;
         sdev->first_free = sbio->index;
@@ -583,25 +563,50 @@ static int scrub_checksum_super(struct scrub_bio *sbio, void *buffer)
 static int scrub_submit(struct scrub_dev *sdev)
 {
         struct scrub_bio *sbio;
+        struct bio *bio;
+        int i;
 
         if (sdev->curr == -1)
                 return 0;
 
         sbio = sdev->bios[sdev->curr];
 
-        sbio->bio->bi_sector = sbio->physical >> 9;
-        sbio->bio->bi_size = sbio->count * PAGE_SIZE;
-        sbio->bio->bi_next = NULL;
-        sbio->bio->bi_flags |= 1 << BIO_UPTODATE;
-        sbio->bio->bi_comp_cpu = -1;
-        sbio->bio->bi_bdev = sdev->dev->bdev;
+        bio = bio_alloc(GFP_NOFS, sbio->count);
+        if (!bio)
+                goto nomem;
+
+        bio->bi_private = sbio;
+        bio->bi_end_io = scrub_bio_end_io;
+        bio->bi_bdev = sdev->dev->bdev;
+        bio->bi_sector = sbio->physical >> 9;
+
+        for (i = 0; i < sbio->count; ++i) {
+                struct page *page;
+                int ret;
+
+                page = alloc_page(GFP_NOFS);
+                if (!page)
+                        goto nomem;
+
+                ret = bio_add_page(bio, page, PAGE_SIZE, 0);
+                if (!ret) {
+                        __free_page(page);
+                        goto nomem;
+                }
+        }
+
         sbio->err = 0;
         sdev->curr = -1;
         atomic_inc(&sdev->in_flight);
 
-        submit_bio(0, sbio->bio);
+        submit_bio(READ, bio);
 
         return 0;
+
+nomem:
+        scrub_free_bio(bio);
+
+        return -ENOMEM;
 }
 
 static int scrub_page(struct scrub_dev *sdev, u64 logical, u64 len,
@@ -633,7 +638,11 @@ again:
                 sbio->logical = logical;
         } else if (sbio->physical + sbio->count * PAGE_SIZE != physical ||
                    sbio->logical + sbio->count * PAGE_SIZE != logical) {
-                scrub_submit(sdev);
+                int ret;
+
+                ret = scrub_submit(sdev);
+                if (ret)
+                        return ret;
                 goto again;
         }
         sbio->spag[sbio->count].flags = flags;
@@ -645,8 +654,13 @@ again:
                 memcpy(sbio->spag[sbio->count].csum, csum, sdev->csum_size);
         }
         ++sbio->count;
-        if (sbio->count == SCRUB_PAGES_PER_BIO || force)
-                scrub_submit(sdev);
+        if (sbio->count == SCRUB_PAGES_PER_BIO || force) {
+                int ret;
+
+                ret = scrub_submit(sdev);
+                if (ret)
+                        return ret;
+        }
 
         return 0;
 }
@@ -727,6 +741,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_dev *sdev,
         struct btrfs_root *root = fs_info->extent_root;
         struct btrfs_root *csum_root = fs_info->csum_root;
         struct btrfs_extent_item *extent;
+        struct blk_plug plug;
         u64 flags;
         int ret;
         int slot;
@@ -831,6 +846,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_dev *sdev,
          * the scrub. This might currently (crc32) end up to be about 1MB
          */
         start_stripe = 0;
+        blk_start_plug(&plug);
 again:
         logical = base + offset + start_stripe * increment;
         for (i = start_stripe; i < nstripes; ++i) {
@@ -972,6 +988,7 @@ next:
         scrub_submit(sdev);
 
 out:
+        blk_finish_plug(&plug);
         btrfs_free_path(path);
         return ret < 0 ? ret : 0;
 }
@@ -1166,7 +1183,7 @@ int btrfs_scrub_dev(struct btrfs_root *root, u64 devid, u64 start, u64 end,
         int ret;
         struct btrfs_device *dev;
 
-        if (root->fs_info->closing)
+        if (btrfs_fs_closing(root->fs_info))
                 return -EINVAL;
 
         /*
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 9b2e7e5bc3ef..117e74e3604b 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -161,7 +161,8 @@ enum {
         Opt_compress_type, Opt_compress_force, Opt_compress_force_type,
         Opt_notreelog, Opt_ratio, Opt_flushoncommit, Opt_discard,
         Opt_space_cache, Opt_clear_cache, Opt_user_subvol_rm_allowed,
-        Opt_enospc_debug, Opt_subvolrootid, Opt_defrag, Opt_err,
+        Opt_enospc_debug, Opt_subvolrootid, Opt_defrag,
+        Opt_inode_cache, Opt_err,
 };
 
 static match_table_t tokens = {
@@ -193,6 +194,7 @@ static match_table_t tokens = {
         {Opt_enospc_debug, "enospc_debug"},
         {Opt_subvolrootid, "subvolrootid=%d"},
         {Opt_defrag, "autodefrag"},
+        {Opt_inode_cache, "inode_cache"},
         {Opt_err, NULL},
 };
 
@@ -361,6 +363,10 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
                         printk(KERN_INFO "btrfs: enabling disk space caching\n");
                         btrfs_set_opt(info->mount_opt, SPACE_CACHE);
                         break;
+                case Opt_inode_cache:
+                        printk(KERN_INFO "btrfs: enabling inode map caching\n");
+                        btrfs_set_opt(info->mount_opt, INODE_MAP_CACHE);
+                        break;
                 case Opt_clear_cache:
                         printk(KERN_INFO "btrfs: force clearing of disk cache\n");
                         btrfs_set_opt(info->mount_opt, CLEAR_CACHE);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index dc80f7156923..dd719662340e 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -35,6 +35,7 @@ static noinline void put_transaction(struct btrfs_transaction *transaction)
 {
         WARN_ON(atomic_read(&transaction->use_count) == 0);
         if (atomic_dec_and_test(&transaction->use_count)) {
+                BUG_ON(!list_empty(&transaction->list));
                 memset(transaction, 0, sizeof(*transaction));
                 kmem_cache_free(btrfs_transaction_cachep, transaction);
         }
@@ -49,46 +50,72 @@ static noinline void switch_commit_root(struct btrfs_root *root)
 /*
  * either allocate a new transaction or hop into the existing one
  */
-static noinline int join_transaction(struct btrfs_root *root)
+static noinline int join_transaction(struct btrfs_root *root, int nofail)
 {
         struct btrfs_transaction *cur_trans;
+
+        spin_lock(&root->fs_info->trans_lock);
+        if (root->fs_info->trans_no_join) {
+                if (!nofail) {
+                        spin_unlock(&root->fs_info->trans_lock);
+                        return -EBUSY;
+                }
+        }
+
         cur_trans = root->fs_info->running_transaction;
-        if (!cur_trans) {
-                cur_trans = kmem_cache_alloc(btrfs_transaction_cachep,
-                                             GFP_NOFS);
-                if (!cur_trans)
-                        return -ENOMEM;
-                root->fs_info->generation++;
-                atomic_set(&cur_trans->num_writers, 1);
-                cur_trans->num_joined = 0;
-                cur_trans->transid = root->fs_info->generation;
-                init_waitqueue_head(&cur_trans->writer_wait);
-                init_waitqueue_head(&cur_trans->commit_wait);
-                cur_trans->in_commit = 0;
-                cur_trans->blocked = 0;
-                atomic_set(&cur_trans->use_count, 1);
-                cur_trans->commit_done = 0;
-                cur_trans->start_time = get_seconds();
-
-                cur_trans->delayed_refs.root = RB_ROOT;
-                cur_trans->delayed_refs.num_entries = 0;
-                cur_trans->delayed_refs.num_heads_ready = 0;
-                cur_trans->delayed_refs.num_heads = 0;
-                cur_trans->delayed_refs.flushing = 0;
-                cur_trans->delayed_refs.run_delayed_start = 0;
-                spin_lock_init(&cur_trans->delayed_refs.lock);
-
-                INIT_LIST_HEAD(&cur_trans->pending_snapshots);
-                list_add_tail(&cur_trans->list, &root->fs_info->trans_list);
-                extent_io_tree_init(&cur_trans->dirty_pages,
-                                     root->fs_info->btree_inode->i_mapping);
-                spin_lock(&root->fs_info->new_trans_lock);
-                root->fs_info->running_transaction = cur_trans;
-                spin_unlock(&root->fs_info->new_trans_lock);
-        } else {
+        if (cur_trans) {
+                atomic_inc(&cur_trans->use_count);
                 atomic_inc(&cur_trans->num_writers);
                 cur_trans->num_joined++;
+                spin_unlock(&root->fs_info->trans_lock);
+                return 0;
         }
+        spin_unlock(&root->fs_info->trans_lock);
+
+        cur_trans = kmem_cache_alloc(btrfs_transaction_cachep, GFP_NOFS);
+        if (!cur_trans)
+                return -ENOMEM;
+        spin_lock(&root->fs_info->trans_lock);
+        if (root->fs_info->running_transaction) {
+                kmem_cache_free(btrfs_transaction_cachep, cur_trans);
+                cur_trans = root->fs_info->running_transaction;
+                atomic_inc(&cur_trans->use_count);
+                atomic_inc(&cur_trans->num_writers);
+                cur_trans->num_joined++;
+                spin_unlock(&root->fs_info->trans_lock);
+                return 0;
+        }
+        atomic_set(&cur_trans->num_writers, 1);
+        cur_trans->num_joined = 0;
+        init_waitqueue_head(&cur_trans->writer_wait);
+        init_waitqueue_head(&cur_trans->commit_wait);
+        cur_trans->in_commit = 0;
+        cur_trans->blocked = 0;
+        /*
+         * One for this trans handle, one so it will live on until we
+         * commit the transaction.
+         */
+        atomic_set(&cur_trans->use_count, 2);
+        cur_trans->commit_done = 0;
+        cur_trans->start_time = get_seconds();
+
+        cur_trans->delayed_refs.root = RB_ROOT;
+        cur_trans->delayed_refs.num_entries = 0;
+        cur_trans->delayed_refs.num_heads_ready = 0;
+        cur_trans->delayed_refs.num_heads = 0;
+        cur_trans->delayed_refs.flushing = 0;
+        cur_trans->delayed_refs.run_delayed_start = 0;
+        spin_lock_init(&cur_trans->commit_lock);
+        spin_lock_init(&cur_trans->delayed_refs.lock);
+
+        INIT_LIST_HEAD(&cur_trans->pending_snapshots);
+        list_add_tail(&cur_trans->list, &root->fs_info->trans_list);
+        extent_io_tree_init(&cur_trans->dirty_pages,
+                             root->fs_info->btree_inode->i_mapping);
+        root->fs_info->generation++;
+        cur_trans->transid = root->fs_info->generation;
+        root->fs_info->running_transaction = cur_trans;
+        spin_unlock(&root->fs_info->trans_lock);
 
         return 0;
 }
@@ -99,39 +126,28 @@ static noinline int join_transaction(struct btrfs_root *root)
  * to make sure the old root from before we joined the transaction is deleted
  * when the transaction commits
  */
-static noinline int record_root_in_trans(struct btrfs_trans_handle *trans,
-                                         struct btrfs_root *root)
+int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
+                               struct btrfs_root *root)
 {
         if (root->ref_cows && root->last_trans < trans->transid) {
                 WARN_ON(root == root->fs_info->extent_root);
                 WARN_ON(root->commit_root != root->node);
 
+                spin_lock(&root->fs_info->fs_roots_radix_lock);
+                if (root->last_trans == trans->transid) {
+                        spin_unlock(&root->fs_info->fs_roots_radix_lock);
+                        return 0;
+                }
+                root->last_trans = trans->transid;
                 radix_tree_tag_set(&root->fs_info->fs_roots_radix,
                            (unsigned long)root->root_key.objectid,
                            BTRFS_ROOT_TRANS_TAG);
-                root->last_trans = trans->transid;
+                spin_unlock(&root->fs_info->fs_roots_radix_lock);
                 btrfs_init_reloc_root(trans, root);
         }
         return 0;
 }
 
-int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
-                               struct btrfs_root *root)
-{
-        if (!root->ref_cows)
-                return 0;
-
-        mutex_lock(&root->fs_info->trans_mutex);
-        if (root->last_trans == trans->transid) {
-                mutex_unlock(&root->fs_info->trans_mutex);
-                return 0;
-        }
-
-        record_root_in_trans(trans, root);
-        mutex_unlock(&root->fs_info->trans_mutex);
-        return 0;
-}
-
 /* wait for commit against the current transaction to become unblocked
  * when this is done, it is safe to start a new transaction, but the current
  * transaction might not be fully on disk.
@@ -140,21 +156,23 @@ static void wait_current_trans(struct btrfs_root *root)
 {
         struct btrfs_transaction *cur_trans;
 
+        spin_lock(&root->fs_info->trans_lock);
         cur_trans = root->fs_info->running_transaction;
         if (cur_trans && cur_trans->blocked) {
                 DEFINE_WAIT(wait);
                 atomic_inc(&cur_trans->use_count);
+                spin_unlock(&root->fs_info->trans_lock);
                 while (1) {
                         prepare_to_wait(&root->fs_info->transaction_wait, &wait,
                                         TASK_UNINTERRUPTIBLE);
                         if (!cur_trans->blocked)
                                 break;
-                        mutex_unlock(&root->fs_info->trans_mutex);
                         schedule();
-                        mutex_lock(&root->fs_info->trans_mutex);
                 }
                 finish_wait(&root->fs_info->transaction_wait, &wait);
                 put_transaction(cur_trans);
+        } else {
+                spin_unlock(&root->fs_info->trans_lock);
         }
 }
 
@@ -167,10 +185,16 @@ enum btrfs_trans_type {
 
 static int may_wait_transaction(struct btrfs_root *root, int type)
 {
-        if (!root->fs_info->log_root_recovering &&
-            ((type == TRANS_START && !root->fs_info->open_ioctl_trans) ||
-             type == TRANS_USERSPACE))
+        if (root->fs_info->log_root_recovering)
+                return 0;
+
+        if (type == TRANS_USERSPACE)
+                return 1;
+
+        if (type == TRANS_START &&
+            !atomic_read(&root->fs_info->open_ioctl_trans))
                 return 1;
+
         return 0;
 }
 
@@ -184,36 +208,44 @@ static struct btrfs_trans_handle *start_transaction(struct btrfs_root *root,
 
         if (root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR)
                 return ERR_PTR(-EROFS);
+
+        if (current->journal_info) {
+                WARN_ON(type != TRANS_JOIN && type != TRANS_JOIN_NOLOCK);
+                h = current->journal_info;
+                h->use_count++;
+                h->orig_rsv = h->block_rsv;
+                h->block_rsv = NULL;
+                goto got_it;
+        }
 again:
         h = kmem_cache_alloc(btrfs_trans_handle_cachep, GFP_NOFS);
         if (!h)
                 return ERR_PTR(-ENOMEM);
 
-        if (type != TRANS_JOIN_NOLOCK)
-                mutex_lock(&root->fs_info->trans_mutex);
         if (may_wait_transaction(root, type))
                 wait_current_trans(root);
 
-        ret = join_transaction(root);
+        do {
+                ret = join_transaction(root, type == TRANS_JOIN_NOLOCK);
+                if (ret == -EBUSY)
+                        wait_current_trans(root);
+        } while (ret == -EBUSY);
+
         if (ret < 0) {
                 kmem_cache_free(btrfs_trans_handle_cachep, h);
-                if (type != TRANS_JOIN_NOLOCK)
-                        mutex_unlock(&root->fs_info->trans_mutex);
                 return ERR_PTR(ret);
         }
 
         cur_trans = root->fs_info->running_transaction;
-        atomic_inc(&cur_trans->use_count);
-        if (type != TRANS_JOIN_NOLOCK)
-                mutex_unlock(&root->fs_info->trans_mutex);
 
         h->transid = cur_trans->transid;
         h->transaction = cur_trans;
         h->blocks_used = 0;
-        h->block_group = 0;
         h->bytes_reserved = 0;
         h->delayed_ref_updates = 0;
+        h->use_count = 1;
         h->block_rsv = NULL;
+        h->orig_rsv = NULL;
 
         smp_mb();
         if (cur_trans->blocked && may_wait_transaction(root, type)) {
@@ -241,11 +273,8 @@ again:
                 }
         }
 
-        if (type != TRANS_JOIN_NOLOCK)
-                mutex_lock(&root->fs_info->trans_mutex);
-        record_root_in_trans(h, root);
-        if (type != TRANS_JOIN_NOLOCK)
-                mutex_unlock(&root->fs_info->trans_mutex);
+got_it:
+        btrfs_record_root_in_trans(h, root);
 
         if (!current->journal_info && type != TRANS_USERSPACE)
                 current->journal_info = h;
@@ -257,22 +286,19 @@ struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root,
 {
         return start_transaction(root, num_items, TRANS_START);
 }
-struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root,
-                                                   int num_blocks)
+struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root)
 {
         return start_transaction(root, 0, TRANS_JOIN);
 }
 
-struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root,
-                                                          int num_blocks)
+struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root)
 {
         return start_transaction(root, 0, TRANS_JOIN_NOLOCK);
 }
 
-struct btrfs_trans_handle *btrfs_start_ioctl_transaction(struct btrfs_root *r,
-                                                         int num_blocks)
+struct btrfs_trans_handle *btrfs_start_ioctl_transaction(struct btrfs_root *root)
 {
-        return start_transaction(r, 0, TRANS_USERSPACE);
+        return start_transaction(root, 0, TRANS_USERSPACE);
 }
 
 /* wait for a transaction commit to be fully complete */
@@ -280,17 +306,13 @@ static noinline int wait_for_commit(struct btrfs_root *root,
                                     struct btrfs_transaction *commit)
 {
         DEFINE_WAIT(wait);
-        mutex_lock(&root->fs_info->trans_mutex);
         while (!commit->commit_done) {
                 prepare_to_wait(&commit->commit_wait, &wait,
                                 TASK_UNINTERRUPTIBLE);
                 if (commit->commit_done)
                         break;
-                mutex_unlock(&root->fs_info->trans_mutex);
                 schedule();
-                mutex_lock(&root->fs_info->trans_mutex);
         }
-        mutex_unlock(&root->fs_info->trans_mutex);
         finish_wait(&commit->commit_wait, &wait);
         return 0;
 }
@@ -300,59 +322,56 @@ int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid)
         struct btrfs_transaction *cur_trans = NULL, *t;
         int ret;
 
-        mutex_lock(&root->fs_info->trans_mutex);
-
         ret = 0;
         if (transid) {
                 if (transid <= root->fs_info->last_trans_committed)
-                        goto out_unlock;
+                        goto out;
 
                 /* find specified transaction */
+                spin_lock(&root->fs_info->trans_lock);
                 list_for_each_entry(t, &root->fs_info->trans_list, list) {
                         if (t->transid == transid) {
                                 cur_trans = t;
+                                atomic_inc(&cur_trans->use_count);
                                 break;
                         }
                         if (t->transid > transid)
                                 break;
                 }
+                spin_unlock(&root->fs_info->trans_lock);
                 ret = -EINVAL;
                 if (!cur_trans)
-                        goto out_unlock;  /* bad transid */
+                        goto out;  /* bad transid */
         } else {
                 /* find newest transaction that is committing | committed */
+                spin_lock(&root->fs_info->trans_lock);
                 list_for_each_entry_reverse(t, &root->fs_info->trans_list,
                                             list) {
                         if (t->in_commit) {
                                 if (t->commit_done)
-                                        goto out_unlock;
+                                        goto out;
                                 cur_trans = t;
+                                atomic_inc(&cur_trans->use_count);
                                 break;
                         }
                 }
+                spin_unlock(&root->fs_info->trans_lock);
                 if (!cur_trans)
-                        goto out_unlock;  /* nothing committing|committed */
+                        goto out;  /* nothing committing|committed */
         }
 
-        atomic_inc(&cur_trans->use_count);
-        mutex_unlock(&root->fs_info->trans_mutex);
-
         wait_for_commit(root, cur_trans);
 
-        mutex_lock(&root->fs_info->trans_mutex);
         put_transaction(cur_trans);
         ret = 0;
-out_unlock:
-        mutex_unlock(&root->fs_info->trans_mutex);
+out:
         return ret;
 }
 
 void btrfs_throttle(struct btrfs_root *root)
 {
-        mutex_lock(&root->fs_info->trans_mutex);
-        if (!root->fs_info->open_ioctl_trans)
+        if (!atomic_read(&root->fs_info->open_ioctl_trans))
                 wait_current_trans(root);
-        mutex_unlock(&root->fs_info->trans_mutex);
 }
 
 static int should_end_transaction(struct btrfs_trans_handle *trans,
@@ -370,6 +389,7 @@ int btrfs_should_end_transaction(struct btrfs_trans_handle *trans,
         struct btrfs_transaction *cur_trans = trans->transaction;
         int updates;
 
+        smp_mb();
         if (cur_trans->blocked || cur_trans->delayed_refs.flushing)
                 return 1;
 
@@ -388,6 +408,11 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
         struct btrfs_fs_info *info = root->fs_info;
         int count = 0;
 
+        if (--trans->use_count) {
+                trans->block_rsv = trans->orig_rsv;
+                return 0;
+        }
+
         while (count < 4) {
                 unsigned long cur = trans->delayed_ref_updates;
                 trans->delayed_ref_updates = 0;
@@ -410,9 +435,11 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 
         btrfs_trans_release_metadata(trans, root);
 
-        if (lock && !root->fs_info->open_ioctl_trans &&
-            should_end_transaction(trans, root))
+        if (lock && !atomic_read(&root->fs_info->open_ioctl_trans) &&
+            should_end_transaction(trans, root)) {
                 trans->transaction->blocked = 1;
+                smp_wmb();
+        }
 
         if (lock && cur_trans->blocked && !cur_trans->in_commit) {
                 if (throttle)
@@ -703,9 +730,9 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans,
  */
 int btrfs_add_dead_root(struct btrfs_root *root)
 {
-        mutex_lock(&root->fs_info->trans_mutex);
+        spin_lock(&root->fs_info->trans_lock);
         list_add(&root->root_list, &root->fs_info->dead_roots);
-        mutex_unlock(&root->fs_info->trans_mutex);
+        spin_unlock(&root->fs_info->trans_lock);
         return 0;
 }
 
@@ -721,6 +748,7 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans,
         int ret;
         int err = 0;
 
+        spin_lock(&fs_info->fs_roots_radix_lock);
         while (1) {
                 ret = radix_tree_gang_lookup_tag(&fs_info->fs_roots_radix,
                                                  (void **)gang, 0,
@@ -733,6 +761,7 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans,
                         radix_tree_tag_clear(&fs_info->fs_roots_radix,
                                         (unsigned long)root->root_key.objectid,
                                         BTRFS_ROOT_TRANS_TAG);
+                        spin_unlock(&fs_info->fs_roots_radix_lock);
 
                         btrfs_free_log(trans, root);
                         btrfs_update_reloc_root(trans, root);
@@ -753,10 +782,12 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans,
                         err = btrfs_update_root(trans, fs_info->tree_root,
                                                 &root->root_key,
                                                 &root->root_item);
+                        spin_lock(&fs_info->fs_roots_radix_lock);
                         if (err)
                                 break;
                 }
         }
+        spin_unlock(&fs_info->fs_roots_radix_lock);
         return err;
 }
 
@@ -786,7 +817,7 @@ int btrfs_defrag_root(struct btrfs_root *root, int cacheonly)
                 btrfs_btree_balance_dirty(info->tree_root, nr);
                 cond_resched();
 
-                if (root->fs_info->closing || ret != -EAGAIN)
+                if (btrfs_fs_closing(root->fs_info) || ret != -EAGAIN)
                         break;
         }
         root->defrag_running = 0;
@@ -851,7 +882,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
         parent = dget_parent(dentry);
         parent_inode = parent->d_inode;
         parent_root = BTRFS_I(parent_inode)->root;
-        record_root_in_trans(trans, parent_root);
+        btrfs_record_root_in_trans(trans, parent_root);
 
         /*
          * insert the directory item
@@ -869,7 +900,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
         ret = btrfs_update_inode(trans, parent_root, parent_inode);
         BUG_ON(ret);
 
-        record_root_in_trans(trans, root);
+        btrfs_record_root_in_trans(trans, root);
         btrfs_set_root_last_snapshot(&root->root_item, trans->transid);
         memcpy(new_root_item, &root->root_item, sizeof(*new_root_item));
         btrfs_check_and_init_root_item(new_root_item);
@@ -967,20 +998,20 @@ static void update_super_roots(struct btrfs_root *root)
 int btrfs_transaction_in_commit(struct btrfs_fs_info *info)
 {
         int ret = 0;
-        spin_lock(&info->new_trans_lock);
+        spin_lock(&info->trans_lock);
         if (info->running_transaction)
                 ret = info->running_transaction->in_commit;
-        spin_unlock(&info->new_trans_lock);
+        spin_unlock(&info->trans_lock);
         return ret;
 }
 
 int btrfs_transaction_blocked(struct btrfs_fs_info *info)
 {
         int ret = 0;
-        spin_lock(&info->new_trans_lock);
+        spin_lock(&info->trans_lock);
         if (info->running_transaction)
                 ret = info->running_transaction->blocked;
-        spin_unlock(&info->new_trans_lock);
+        spin_unlock(&info->trans_lock);
         return ret;
 }
 
@@ -1004,9 +1035,7 @@ static void wait_current_trans_commit_start(struct btrfs_root *root,
                                     &wait);
                         break;
                 }
-                mutex_unlock(&root->fs_info->trans_mutex);
                 schedule();
-                mutex_lock(&root->fs_info->trans_mutex);
                 finish_wait(&root->fs_info->transaction_blocked_wait, &wait);
         }
 }
@@ -1032,9 +1061,7 @@ static void wait_current_trans_commit_start_and_unblock(struct btrfs_root *root,
                                     &wait);
                         break;
                 }
-                mutex_unlock(&root->fs_info->trans_mutex);
                 schedule();
-                mutex_lock(&root->fs_info->trans_mutex);
                 finish_wait(&root->fs_info->transaction_wait,
                             &wait);
         }
@@ -1072,7 +1099,7 @@ int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans,
 
         INIT_DELAYED_WORK(&ac->work, do_async_commit);
         ac->root = root;
-        ac->newtrans = btrfs_join_transaction(root, 0);
+        ac->newtrans = btrfs_join_transaction(root);
         if (IS_ERR(ac->newtrans)) {
                 int err = PTR_ERR(ac->newtrans);
                 kfree(ac);
@@ -1080,22 +1107,18 @@ int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans,
         }
 
         /* take transaction reference */
-        mutex_lock(&root->fs_info->trans_mutex);
         cur_trans = trans->transaction;
         atomic_inc(&cur_trans->use_count);
-        mutex_unlock(&root->fs_info->trans_mutex);
 
         btrfs_end_transaction(trans, root);
         schedule_delayed_work(&ac->work, 0);
 
         /* wait for transaction to start and unblock */
-        mutex_lock(&root->fs_info->trans_mutex);
         if (wait_for_unblock)
                 wait_current_trans_commit_start_and_unblock(root, cur_trans);
         else
                 wait_current_trans_commit_start(root, cur_trans);
         put_transaction(cur_trans);
-        mutex_unlock(&root->fs_info->trans_mutex);
 
         return 0;
 }
@@ -1139,38 +1162,41 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
         ret = btrfs_run_delayed_refs(trans, root, 0);
         BUG_ON(ret);
 
-        mutex_lock(&root->fs_info->trans_mutex);
+        spin_lock(&cur_trans->commit_lock);
         if (cur_trans->in_commit) {
+                spin_unlock(&cur_trans->commit_lock);
                 atomic_inc(&cur_trans->use_count);
-                mutex_unlock(&root->fs_info->trans_mutex);
                 btrfs_end_transaction(trans, root);
 
                 ret = wait_for_commit(root, cur_trans);
                 BUG_ON(ret);
 
-                mutex_lock(&root->fs_info->trans_mutex);
                 put_transaction(cur_trans);
-                mutex_unlock(&root->fs_info->trans_mutex);
 
                 return 0;
         }
 
         trans->transaction->in_commit = 1;
         trans->transaction->blocked = 1;
+        spin_unlock(&cur_trans->commit_lock);
         wake_up(&root->fs_info->transaction_blocked_wait);
 
+        spin_lock(&root->fs_info->trans_lock);
         if (cur_trans->list.prev != &root->fs_info->trans_list) {
                 prev_trans = list_entry(cur_trans->list.prev,
                                         struct btrfs_transaction, list);
                 if (!prev_trans->commit_done) {
                         atomic_inc(&prev_trans->use_count);
-                        mutex_unlock(&root->fs_info->trans_mutex);
+                        spin_unlock(&root->fs_info->trans_lock);
 
                         wait_for_commit(root, prev_trans);
 
-                        mutex_lock(&root->fs_info->trans_mutex);
                         put_transaction(prev_trans);
+                } else {
+                        spin_unlock(&root->fs_info->trans_lock);
                 }
+        } else {
+                spin_unlock(&root->fs_info->trans_lock);
         }
 
         if (now < cur_trans->start_time || now - cur_trans->start_time < 1)
@@ -1178,12 +1204,12 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 
         do {
                 int snap_pending = 0;
+
                 joined = cur_trans->num_joined;
                 if (!list_empty(&trans->transaction->pending_snapshots))
                         snap_pending = 1;
 
                 WARN_ON(cur_trans != trans->transaction);
-                mutex_unlock(&root->fs_info->trans_mutex);
 
                 if (flush_on_commit || snap_pending) {
                         btrfs_start_delalloc_inodes(root, 1);
@@ -1206,14 +1232,15 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
                 prepare_to_wait(&cur_trans->writer_wait, &wait,
                                 TASK_UNINTERRUPTIBLE);
 
-                smp_mb();
                 if (atomic_read(&cur_trans->num_writers) > 1)
                         schedule_timeout(MAX_SCHEDULE_TIMEOUT);
                 else if (should_grow)
                         schedule_timeout(1);
 
-                mutex_lock(&root->fs_info->trans_mutex);
                 finish_wait(&cur_trans->writer_wait, &wait);
+                spin_lock(&root->fs_info->trans_lock);
+                root->fs_info->trans_no_join = 1;
+                spin_unlock(&root->fs_info->trans_lock);
         } while (atomic_read(&cur_trans->num_writers) > 1 ||
                  (should_grow && cur_trans->num_joined != joined));
 
@@ -1258,9 +1285,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
         btrfs_prepare_extent_commit(trans, root);
 
         cur_trans = root->fs_info->running_transaction;
-        spin_lock(&root->fs_info->new_trans_lock);
-        root->fs_info->running_transaction = NULL;
-        spin_unlock(&root->fs_info->new_trans_lock);
 
         btrfs_set_root_node(&root->fs_info->tree_root->root_item,
                             root->fs_info->tree_root->node);
@@ -1281,10 +1305,13 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
                sizeof(root->fs_info->super_copy));
 
         trans->transaction->blocked = 0;
+        spin_lock(&root->fs_info->trans_lock);
+        root->fs_info->running_transaction = NULL;
+        root->fs_info->trans_no_join = 0;
+        spin_unlock(&root->fs_info->trans_lock);
 
         wake_up(&root->fs_info->transaction_wait);
 
-        mutex_unlock(&root->fs_info->trans_mutex);
         ret = btrfs_write_and_wait_transaction(trans, root);
         BUG_ON(ret);
         write_ctree_super(trans, root, 0);
@@ -1297,22 +1324,21 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 
         btrfs_finish_extent_commit(trans, root);
 
-        mutex_lock(&root->fs_info->trans_mutex);
-
         cur_trans->commit_done = 1;
 
         root->fs_info->last_trans_committed = cur_trans->transid;
 
         wake_up(&cur_trans->commit_wait);
 
+        spin_lock(&root->fs_info->trans_lock);
         list_del_init(&cur_trans->list);
+        spin_unlock(&root->fs_info->trans_lock);
+
         put_transaction(cur_trans);
         put_transaction(cur_trans);
 
         trace_btrfs_transaction_commit(root);
 
-        mutex_unlock(&root->fs_info->trans_mutex);
-
         btrfs_scrub_continue(root);
 
         if (current->journal_info == trans)
@@ -1334,9 +1360,9 @@ int btrfs_clean_old_snapshots(struct btrfs_root *root)
         LIST_HEAD(list);
         struct btrfs_fs_info *fs_info = root->fs_info;
 
-        mutex_lock(&fs_info->trans_mutex);
+        spin_lock(&fs_info->trans_lock);
         list_splice_init(&fs_info->dead_roots, &list);
-        mutex_unlock(&fs_info->trans_mutex);
+        spin_unlock(&fs_info->trans_lock);
 
         while (!list_empty(&list)) {
                 root = list_entry(list.next, struct btrfs_root, root_list);
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 804c88639e5d..02564e6230ac 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -28,10 +28,12 @@ struct btrfs_transaction {
          * transaction can end
          */
         atomic_t num_writers;
+        atomic_t use_count;
 
         unsigned long num_joined;
+
+        spinlock_t commit_lock;
         int in_commit;
-        atomic_t use_count;
         int commit_done;
         int blocked;
         struct list_head list;
@@ -45,13 +47,14 @@ struct btrfs_transaction {
 
 struct btrfs_trans_handle {
         u64 transid;
-        u64 block_group;
         u64 bytes_reserved;
+        unsigned long use_count;
         unsigned long blocks_reserved;
         unsigned long blocks_used;
         unsigned long delayed_ref_updates;
         struct btrfs_transaction *transaction;
         struct btrfs_block_rsv *block_rsv;
+        struct btrfs_block_rsv *orig_rsv;
 };
 
 struct btrfs_pending_snapshot {
@@ -66,19 +69,6 @@ struct btrfs_pending_snapshot {
         struct list_head list;
 };
 
-static inline void btrfs_set_trans_block_group(struct btrfs_trans_handle *trans,
-                                               struct inode *inode)
-{
-        trans->block_group = BTRFS_I(inode)->block_group;
-}
-
-static inline void btrfs_update_inode_block_group(
-                                          struct btrfs_trans_handle *trans,
-                                          struct inode *inode)
-{
-        BTRFS_I(inode)->block_group = trans->block_group;
-}
-
 static inline void btrfs_set_inode_last_trans(struct btrfs_trans_handle *trans,
                                               struct inode *inode)
 {
@@ -92,12 +82,9 @@ int btrfs_end_transaction_nolock(struct btrfs_trans_handle *trans,
                                  struct btrfs_root *root);
 struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root,
                                                    int num_items);
-struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root,
-                                                  int num_blocks);
-struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root,
-                                                          int num_blocks);
-struct btrfs_trans_handle *btrfs_start_ioctl_transaction(struct btrfs_root *r,
-                                                         int num_blocks);
+struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root);
+struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root);
+struct btrfs_trans_handle *btrfs_start_ioctl_transaction(struct btrfs_root *root);
 int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid);
 int btrfs_write_and_wait_transaction(struct btrfs_trans_handle *trans,
                                      struct btrfs_root *root);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index c48214ef5c09..da541dfca2e3 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -504,7 +504,7 @@ static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
                 BUG_ON(!new_device);
                 memcpy(new_device, device, sizeof(*new_device));
                 new_device->name = kstrdup(device->name, GFP_NOFS);
-                BUG_ON(!new_device->name);
+                BUG_ON(device->name && !new_device->name);
                 new_device->bdev = NULL;
                 new_device->writeable = 0;
                 new_device->in_fs_metadata = 0;
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index f3107e4b4d56..5366fe452ab0 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -158,8 +158,6 @@ int __btrfs_setxattr(struct btrfs_trans_handle *trans,
         if (IS_ERR(trans))
                 return PTR_ERR(trans);
 
-        btrfs_set_trans_block_group(trans, inode);
-
         ret = do_setxattr(trans, inode, name, value, size, flags);
         if (ret)
                 goto out;
diff --git a/fs/buffer.c b/fs/buffer.c
index 698c6b2cc462..49c9aada0374 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2382,6 +2382,7 @@ int __block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
                 ret = -EAGAIN;
                 goto out_unlock;
         }
+        wait_on_page_writeback(page);
         return 0;
 out_unlock:
         unlock_page(page);
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 8f1700623b41..21de1d6d5849 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -74,8 +74,9 @@ shrink_idmap_tree(struct rb_root *root, int nr_to_scan, int *nr_rem,
  * Run idmap cache shrinker.
  */
 static int
-cifs_idmap_shrinker(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask)
+cifs_idmap_shrinker(struct shrinker *shrink, struct shrink_control *sc)
 {
+        int nr_to_scan = sc->nr_to_scan;
         int nr_del = 0;
         int nr_rem = 0;
         struct rb_root *root;
diff --git a/fs/coda/dir.c b/fs/coda/dir.c
index a46126fd5735..2b8dae4d121e 100644
--- a/fs/coda/dir.c
+++ b/fs/coda/dir.c
@@ -336,8 +336,6 @@ static int coda_rmdir(struct inode *dir, struct dentry *de)
         int len = de->d_name.len;
         int error;
 
-        dentry_unhash(de);
-
         error = venus_rmdir(dir->i_sb, coda_i2f(dir), name, len);
         if (!error) {
                 /* VFS may delete the child */
@@ -361,9 +359,6 @@ static int coda_rename(struct inode *old_dir, struct dentry *old_dentry,
         int new_length = new_dentry->d_name.len;
         int error;
 
-        if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
-                dentry_unhash(new_dentry);
-
         error = venus_rename(old_dir->i_sb, coda_i2f(old_dir),
                              coda_i2f(new_dir), old_length, new_length,
                              (const char *) old_name, (const char *)new_name);
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index 9d17d350abc5..9a37a9b6de3a 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -1359,8 +1359,6 @@ static int configfs_rmdir(struct inode *dir, struct dentry *dentry)
         struct module *subsys_owner = NULL, *dead_item_owner = NULL;
         int ret;
 
-        dentry_unhash(dentry);
-
         if (dentry->d_parent == configfs_sb->s_root)
                 return -EPERM;
 
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index b8d5c8091024..58609bde3b9f 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -1024,25 +1024,25 @@ out:
 }
 
 /**
- * contains_ecryptfs_marker - check for the ecryptfs marker
+ * ecryptfs_validate_marker - check for the ecryptfs marker
  * @data: The data block in which to check
  *
- * Returns one if marker found; zero if not found
+ * Returns zero if marker found; -EINVAL if not found
  */
-static int contains_ecryptfs_marker(char *data)
+static int ecryptfs_validate_marker(char *data)
 {
         u32 m_1, m_2;
 
         m_1 = get_unaligned_be32(data);
         m_2 = get_unaligned_be32(data + 4);
         if ((m_1 ^ MAGIC_ECRYPTFS_MARKER) == m_2)
-                return 1;
+                return 0;
         ecryptfs_printk(KERN_DEBUG, "m_1 = [0x%.8x]; m_2 = [0x%.8x]; "
                         "MAGIC_ECRYPTFS_MARKER = [0x%.8x]\n", m_1, m_2,
                         MAGIC_ECRYPTFS_MARKER);
         ecryptfs_printk(KERN_DEBUG, "(m_1 ^ MAGIC_ECRYPTFS_MARKER) = "
                         "[0x%.8x]\n", (m_1 ^ MAGIC_ECRYPTFS_MARKER));
-        return 0;
+        return -EINVAL;
 }
 
 struct ecryptfs_flag_map_elem {
@@ -1201,27 +1201,19 @@ int ecryptfs_cipher_code_to_string(char *str, u8 cipher_code)
         return rc;
 }
 
-int ecryptfs_read_and_validate_header_region(char *data,
-                                             struct inode *ecryptfs_inode)
+int ecryptfs_read_and_validate_header_region(struct inode *inode)
 {
-        struct ecryptfs_crypt_stat *crypt_stat =
-                &(ecryptfs_inode_to_private(ecryptfs_inode)->crypt_stat);
+        u8 file_size[ECRYPTFS_SIZE_AND_MARKER_BYTES];
+        u8 *marker = file_size + ECRYPTFS_FILE_SIZE_BYTES;
         int rc;
 
-        if (crypt_stat->extent_size == 0)
-                crypt_stat->extent_size = ECRYPTFS_DEFAULT_EXTENT_SIZE;
-        rc = ecryptfs_read_lower(data, 0, crypt_stat->extent_size,
-                                 ecryptfs_inode);
-        if (rc < 0) {
-                printk(KERN_ERR "%s: Error reading header region; rc = [%d]\n",
-                       __func__, rc);
-                goto out;
-        }
-        if (!contains_ecryptfs_marker(data + ECRYPTFS_FILE_SIZE_BYTES)) {
-                rc = -EINVAL;
-        } else
-                rc = 0;
-out:
+        rc = ecryptfs_read_lower(file_size, 0, ECRYPTFS_SIZE_AND_MARKER_BYTES,
+                                 inode);
+        if (rc < ECRYPTFS_SIZE_AND_MARKER_BYTES)
+                return rc >= 0 ? -EINVAL : rc;
+        rc = ecryptfs_validate_marker(marker);
+        if (!rc)
+                ecryptfs_i_size_init(file_size, inode);
         return rc;
 }
 
@@ -1242,8 +1234,7 @@ ecryptfs_write_header_metadata(char *virt,
         (*written) = 6;
 }
 
-struct kmem_cache *ecryptfs_header_cache_1;
-struct kmem_cache *ecryptfs_header_cache_2;
+struct kmem_cache *ecryptfs_header_cache;
 
 /**
  * ecryptfs_write_headers_virt
@@ -1496,11 +1487,9 @@ static int ecryptfs_read_headers_virt(char *page_virt,
         crypt_stat->mount_crypt_stat = &ecryptfs_superblock_to_private(
                 ecryptfs_dentry->d_sb)->mount_crypt_stat;
         offset = ECRYPTFS_FILE_SIZE_BYTES;
-        rc = contains_ecryptfs_marker(page_virt + offset);
-        if (rc == 0) {
-                rc = -EINVAL;
+        rc = ecryptfs_validate_marker(page_virt + offset);
+        if (rc)
                 goto out;
-        }
         if (!(crypt_stat->flags & ECRYPTFS_I_SIZE_INITIALIZED))
                 ecryptfs_i_size_init(page_virt, ecryptfs_dentry->d_inode);
         offset += MAGIC_ECRYPTFS_MARKER_SIZE_BYTES;
@@ -1567,20 +1556,21 @@ out:
         return rc;
 }
 
-int ecryptfs_read_and_validate_xattr_region(char *page_virt,
-                                            struct dentry *ecryptfs_dentry)
+int ecryptfs_read_and_validate_xattr_region(struct dentry *dentry,
+                                            struct inode *inode)
 {
+        u8 file_size[ECRYPTFS_SIZE_AND_MARKER_BYTES];
+        u8 *marker = file_size + ECRYPTFS_FILE_SIZE_BYTES;
         int rc;
 
-        rc = ecryptfs_read_xattr_region(page_virt, ecryptfs_dentry->d_inode);
-        if (rc)
-                goto out;
-        if (!contains_ecryptfs_marker(page_virt + ECRYPTFS_FILE_SIZE_BYTES)) {
-                printk(KERN_WARNING "Valid data found in [%s] xattr, but "
-                        "the marker is invalid\n", ECRYPTFS_XATTR_NAME);
-                rc = -EINVAL;
-        }
-out:
+        rc = ecryptfs_getxattr_lower(ecryptfs_dentry_to_lower(dentry),
+                                     ECRYPTFS_XATTR_NAME, file_size,
+                                     ECRYPTFS_SIZE_AND_MARKER_BYTES);
+        if (rc < ECRYPTFS_SIZE_AND_MARKER_BYTES)
+                return rc >= 0 ? -EINVAL : rc;
+        rc = ecryptfs_validate_marker(marker);
+        if (!rc)
+                ecryptfs_i_size_init(file_size, inode);
         return rc;
 }
 
@@ -1610,7 +1600,7 @@ int ecryptfs_read_metadata(struct dentry *ecryptfs_dentry)
         ecryptfs_copy_mount_wide_flags_to_inode_flags(crypt_stat,
                                                       mount_crypt_stat);
         /* Read the first page from the underlying file */
-        page_virt = kmem_cache_alloc(ecryptfs_header_cache_1, GFP_USER);
+        page_virt = kmem_cache_alloc(ecryptfs_header_cache, GFP_USER);
         if (!page_virt) {
                 rc = -ENOMEM;
                 printk(KERN_ERR "%s: Unable to allocate page_virt\n",
@@ -1655,7 +1645,7 @@ int ecryptfs_read_metadata(struct dentry *ecryptfs_dentry)
 out:
         if (page_virt) {
                 memset(page_virt, 0, PAGE_CACHE_SIZE);
-                kmem_cache_free(ecryptfs_header_cache_1, page_virt);
+                kmem_cache_free(ecryptfs_header_cache, page_virt);
         }
         return rc;
 }
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index e70282775e2c..43c7c43b06f5 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -200,6 +200,8 @@ ecryptfs_get_key_payload_data(struct key *key)
 #define MAGIC_ECRYPTFS_MARKER 0x3c81b7f5
 #define MAGIC_ECRYPTFS_MARKER_SIZE_BYTES 8      /* 4*2 */
 #define ECRYPTFS_FILE_SIZE_BYTES (sizeof(u64))
+#define ECRYPTFS_SIZE_AND_MARKER_BYTES (ECRYPTFS_FILE_SIZE_BYTES \
+                                        + MAGIC_ECRYPTFS_MARKER_SIZE_BYTES)
 #define ECRYPTFS_DEFAULT_CIPHER "aes"
 #define ECRYPTFS_DEFAULT_KEY_BYTES 16
 #define ECRYPTFS_DEFAULT_HASH "md5"
@@ -603,8 +605,7 @@ extern struct kmem_cache *ecryptfs_file_info_cache;
 extern struct kmem_cache *ecryptfs_dentry_info_cache;
 extern struct kmem_cache *ecryptfs_inode_info_cache;
 extern struct kmem_cache *ecryptfs_sb_info_cache;
-extern struct kmem_cache *ecryptfs_header_cache_1;
-extern struct kmem_cache *ecryptfs_header_cache_2;
+extern struct kmem_cache *ecryptfs_header_cache;
 extern struct kmem_cache *ecryptfs_xattr_cache;
 extern struct kmem_cache *ecryptfs_key_record_cache;
 extern struct kmem_cache *ecryptfs_key_sig_cache;
@@ -625,14 +626,9 @@ struct ecryptfs_open_req {
         struct list_head kthread_ctl_list;
 };
 
-#define ECRYPTFS_INTERPOSE_FLAG_D_ADD                 0x00000001
-int ecryptfs_interpose(struct dentry *hidden_dentry,
-                       struct dentry *this_dentry, struct super_block *sb,
-                       u32 flags);
+struct inode *ecryptfs_get_inode(struct inode *lower_inode,
+                                 struct super_block *sb);
 void ecryptfs_i_size_init(const char *page_virt, struct inode *inode);
-int ecryptfs_lookup_and_interpose_lower(struct dentry *ecryptfs_dentry,
-                                        struct dentry *lower_dentry,
-                                        struct inode *ecryptfs_dir_inode);
 int ecryptfs_decode_and_decrypt_filename(char **decrypted_name,
                                          size_t *decrypted_name_size,
                                          struct dentry *ecryptfs_dentry,
@@ -664,10 +660,9 @@ int ecryptfs_new_file_context(struct dentry *ecryptfs_dentry);
 void ecryptfs_write_crypt_stat_flags(char *page_virt,
                                      struct ecryptfs_crypt_stat *crypt_stat,
                                      size_t *written);
-int ecryptfs_read_and_validate_header_region(char *data,
-                                             struct inode *ecryptfs_inode);
-int ecryptfs_read_and_validate_xattr_region(char *page_virt,
-                                            struct dentry *ecryptfs_dentry);
+int ecryptfs_read_and_validate_header_region(struct inode *inode);
+int ecryptfs_read_and_validate_xattr_region(struct dentry *dentry,
+                                            struct inode *inode);
 u8 ecryptfs_code_for_cipher_string(char *cipher_name, size_t key_bytes);
 int ecryptfs_cipher_code_to_string(char *str, u8 cipher_code);
 void ecryptfs_set_default_sizes(struct ecryptfs_crypt_stat *crypt_stat);
@@ -679,9 +674,6 @@ int
 ecryptfs_parse_packet_set(struct ecryptfs_crypt_stat *crypt_stat,
                           unsigned char *src, struct dentry *ecryptfs_dentry);
 int ecryptfs_truncate(struct dentry *dentry, loff_t new_length);
-int ecryptfs_inode_test(struct inode *inode, void *candidate_lower_inode);
-int ecryptfs_inode_set(struct inode *inode, void *lower_inode);
-void ecryptfs_init_inode(struct inode *inode, struct inode *lower_inode);
 ssize_t
 ecryptfs_getxattr_lower(struct dentry *lower_dentry, const char *name,
                         void *value, size_t size);
@@ -761,7 +753,7 @@ int ecryptfs_privileged_open(struct file **lower_file,
                              struct dentry *lower_dentry,
                              struct vfsmount *lower_mnt,
                              const struct cred *cred);
-int ecryptfs_get_lower_file(struct dentry *ecryptfs_dentry);
+int ecryptfs_get_lower_file(struct dentry *dentry, struct inode *inode);
 void ecryptfs_put_lower_file(struct inode *inode);
 int
 ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index 566e5472f78c..4ec9eb00a241 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -191,7 +191,7 @@ static int ecryptfs_open(struct inode *inode, struct file *file)
                                       | ECRYPTFS_ENCRYPTED);
         }
         mutex_unlock(&crypt_stat->cs_mutex);
-        rc = ecryptfs_get_lower_file(ecryptfs_dentry);
+        rc = ecryptfs_get_lower_file(ecryptfs_dentry, inode);
         if (rc) {
                 printk(KERN_ERR "%s: Error attempting to initialize "
                         "the lower file for the dentry with name "
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index bc116b9ffcf2..7349ade17de6 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -51,6 +51,97 @@ static void unlock_dir(struct dentry *dir)
         dput(dir);
 }
 
+static int ecryptfs_inode_test(struct inode *inode, void *lower_inode)
+{
+        if (ecryptfs_inode_to_lower(inode) == (struct inode *)lower_inode)
+                return 1;
+        return 0;
+}
+
+static int ecryptfs_inode_set(struct inode *inode, void *opaque)
+{
+        struct inode *lower_inode = opaque;
+
+        ecryptfs_set_inode_lower(inode, lower_inode);
+        fsstack_copy_attr_all(inode, lower_inode);
+        /* i_size will be overwritten for encrypted regular files */
+        fsstack_copy_inode_size(inode, lower_inode);
+        inode->i_ino = lower_inode->i_ino;
+        inode->i_version++;
+        inode->i_mapping->a_ops = &ecryptfs_aops;
+
+        if (S_ISLNK(inode->i_mode))
+                inode->i_op = &ecryptfs_symlink_iops;
+        else if (S_ISDIR(inode->i_mode))
+                inode->i_op = &ecryptfs_dir_iops;
+        else
+                inode->i_op = &ecryptfs_main_iops;
+
+        if (S_ISDIR(inode->i_mode))
+                inode->i_fop = &ecryptfs_dir_fops;
+        else if (special_file(inode->i_mode))
+                init_special_inode(inode, inode->i_mode, inode->i_rdev);
+        else
+                inode->i_fop = &ecryptfs_main_fops;
+
+        return 0;
+}
+
+static struct inode *__ecryptfs_get_inode(struct inode *lower_inode,
+                                          struct super_block *sb)
+{
+        struct inode *inode;
+
+        if (lower_inode->i_sb != ecryptfs_superblock_to_lower(sb))
+                return ERR_PTR(-EXDEV);
+        if (!igrab(lower_inode))
+                return ERR_PTR(-ESTALE);
+        inode = iget5_locked(sb, (unsigned long)lower_inode,
+                             ecryptfs_inode_test, ecryptfs_inode_set,
+                             lower_inode);
+        if (!inode) {
+                iput(lower_inode);
+                return ERR_PTR(-EACCES);
+        }
+        if (!(inode->i_state & I_NEW))
+                iput(lower_inode);
+
+        return inode;
+}
+
+struct inode *ecryptfs_get_inode(struct inode *lower_inode,
+                                 struct super_block *sb)
+{
+        struct inode *inode = __ecryptfs_get_inode(lower_inode, sb);
+
+        if (!IS_ERR(inode) && (inode->i_state & I_NEW))
+                unlock_new_inode(inode);
+
+        return inode;
+}
+
+/**
+ * ecryptfs_interpose
+ * @lower_dentry: Existing dentry in the lower filesystem
+ * @dentry: ecryptfs' dentry
+ * @sb: ecryptfs's super_block
+ *
+ * Interposes upper and lower dentries.
+ *
+ * Returns zero on success; non-zero otherwise
+ */
+static int ecryptfs_interpose(struct dentry *lower_dentry,
+                              struct dentry *dentry, struct super_block *sb)
+{
+        struct inode *inode = ecryptfs_get_inode(lower_dentry->d_inode, sb);
+
+        if (IS_ERR(inode))
+                return PTR_ERR(inode);
+        d_instantiate(dentry, inode);
+
+        return 0;
+}
+
 /**
  * ecryptfs_create_underlying_file
  * @lower_dir_inode: inode of the parent in the lower fs of the new file
@@ -129,7 +220,7 @@ ecryptfs_do_create(struct inode *directory_inode,
                 goto out_lock;
         }
         rc = ecryptfs_interpose(lower_dentry, ecryptfs_dentry,
-                                directory_inode->i_sb, 0);
+                                directory_inode->i_sb);
         if (rc) {
                 ecryptfs_printk(KERN_ERR, "Failure in ecryptfs_interpose\n");
                 goto out_lock;
@@ -168,7 +259,8 @@ static int ecryptfs_initialize_file(struct dentry *ecryptfs_dentry)
                                 "context; rc = [%d]\n", rc);
                 goto out;
         }
-        rc = ecryptfs_get_lower_file(ecryptfs_dentry);
+        rc = ecryptfs_get_lower_file(ecryptfs_dentry,
+                                     ecryptfs_dentry->d_inode);
         if (rc) {
                 printk(KERN_ERR "%s: Error attempting to initialize "
                         "the lower file for the dentry with name "
@@ -215,102 +307,90 @@ out:
         return rc;
 }
 
+static int ecryptfs_i_size_read(struct dentry *dentry, struct inode *inode)
+{
+        struct ecryptfs_crypt_stat *crypt_stat;
+        int rc;
+
+        rc = ecryptfs_get_lower_file(dentry, inode);
+        if (rc) {
+                printk(KERN_ERR "%s: Error attempting to initialize "
+                        "the lower file for the dentry with name "
+                        "[%s]; rc = [%d]\n", __func__,
+                        dentry->d_name.name, rc);
+                return rc;
+        }
+
+        crypt_stat = &ecryptfs_inode_to_private(inode)->crypt_stat;
+        /* TODO: lock for crypt_stat comparison */
+        if (!(crypt_stat->flags & ECRYPTFS_POLICY_APPLIED))
+                ecryptfs_set_default_sizes(crypt_stat);
+
+        rc = ecryptfs_read_and_validate_header_region(inode);
+        ecryptfs_put_lower_file(inode);
+        if (rc) {
+                rc = ecryptfs_read_and_validate_xattr_region(dentry, inode);
+                if (!rc)
+                        crypt_stat->flags |= ECRYPTFS_METADATA_IN_XATTR;
+        }
+
+        /* Must return 0 to allow non-eCryptfs files to be looked up, too */
+        return 0;
+}
+
 /**
- * ecryptfs_lookup_and_interpose_lower - Perform a lookup
+ * ecryptfs_lookup_interpose - Dentry interposition for a lookup
  */
-int ecryptfs_lookup_and_interpose_lower(struct dentry *ecryptfs_dentry,
-                                        struct dentry *lower_dentry,
-                                        struct inode *ecryptfs_dir_inode)
+static int ecryptfs_lookup_interpose(struct dentry *dentry,
+                                     struct dentry *lower_dentry,
+                                     struct inode *dir_inode)
 {
-        struct dentry *lower_dir_dentry;
+        struct inode *inode, *lower_inode = lower_dentry->d_inode;
+        struct ecryptfs_dentry_info *dentry_info;
         struct vfsmount *lower_mnt;
-        struct inode *lower_inode;
-        struct ecryptfs_crypt_stat *crypt_stat;
-        char *page_virt = NULL;
-        int put_lower = 0, rc = 0;
-
-        lower_dir_dentry = lower_dentry->d_parent;
-        lower_mnt = mntget(ecryptfs_dentry_to_lower_mnt(
-                                   ecryptfs_dentry->d_parent));
-        lower_inode = lower_dentry->d_inode;
-        fsstack_copy_attr_atime(ecryptfs_dir_inode, lower_dir_dentry->d_inode);
+        int rc = 0;
+
+        lower_mnt = mntget(ecryptfs_dentry_to_lower_mnt(dentry->d_parent));
+        fsstack_copy_attr_atime(dir_inode, lower_dentry->d_parent->d_inode);
         BUG_ON(!lower_dentry->d_count);
-        ecryptfs_set_dentry_private(ecryptfs_dentry,
-                                    kmem_cache_alloc(ecryptfs_dentry_info_cache,
-                                                     GFP_KERNEL));
-        if (!ecryptfs_dentry_to_private(ecryptfs_dentry)) {
-                rc = -ENOMEM;
+
+        dentry_info = kmem_cache_alloc(ecryptfs_dentry_info_cache, GFP_KERNEL);
+        ecryptfs_set_dentry_private(dentry, dentry_info);
+        if (!dentry_info) {
                 printk(KERN_ERR "%s: Out of memory whilst attempting "
                        "to allocate ecryptfs_dentry_info struct\n",
                         __func__);
-                goto out_put;
+                dput(lower_dentry);
+                mntput(lower_mnt);
+                d_drop(dentry);
+                return -ENOMEM;
         }
-        ecryptfs_set_dentry_lower(ecryptfs_dentry, lower_dentry);
-        ecryptfs_set_dentry_lower_mnt(ecryptfs_dentry, lower_mnt);
+        ecryptfs_set_dentry_lower(dentry, lower_dentry);
+        ecryptfs_set_dentry_lower_mnt(dentry, lower_mnt);
+
         if (!lower_dentry->d_inode) {
                 /* We want to add because we couldn't find in lower */
-                d_add(ecryptfs_dentry, NULL);
-                goto out;
-        }
-        rc = ecryptfs_interpose(lower_dentry, ecryptfs_dentry,
-                                ecryptfs_dir_inode->i_sb,
-                                ECRYPTFS_INTERPOSE_FLAG_D_ADD);
-        if (rc) {
-                printk(KERN_ERR "%s: Error interposing; rc = [%d]\n",
-                       __func__, rc);
-                goto out;
-        }
-        if (S_ISDIR(lower_inode->i_mode))
-                goto out;
-        if (S_ISLNK(lower_inode->i_mode))
-                goto out;
-        if (special_file(lower_inode->i_mode))
-                goto out;
-        /* Released in this function */
-        page_virt = kmem_cache_zalloc(ecryptfs_header_cache_2, GFP_USER);
-        if (!page_virt) {
-                printk(KERN_ERR "%s: Cannot kmem_cache_zalloc() a page\n",
-                       __func__);
-                rc = -ENOMEM;
-                goto out;
+                d_add(dentry, NULL);
+                return 0;
         }
-        rc = ecryptfs_get_lower_file(ecryptfs_dentry);
-        if (rc) {
-                printk(KERN_ERR "%s: Error attempting to initialize "
-                        "the lower file for the dentry with name "
-                        "[%s]; rc = [%d]\n", __func__,
-                        ecryptfs_dentry->d_name.name, rc);
-                goto out_free_kmem;
+        inode = __ecryptfs_get_inode(lower_inode, dir_inode->i_sb);
+        if (IS_ERR(inode)) {
+                printk(KERN_ERR "%s: Error interposing; rc = [%ld]\n",
+                       __func__, PTR_ERR(inode));
+                return PTR_ERR(inode);
         }
-        put_lower = 1;
-        crypt_stat = &ecryptfs_inode_to_private(
-                                        ecryptfs_dentry->d_inode)->crypt_stat;
-        /* TODO: lock for crypt_stat comparison */
-        if (!(crypt_stat->flags & ECRYPTFS_POLICY_APPLIED))
-                        ecryptfs_set_default_sizes(crypt_stat);
-        rc = ecryptfs_read_and_validate_header_region(page_virt,
-                                                      ecryptfs_dentry->d_inode);
-        if (rc) {
-                memset(page_virt, 0, PAGE_CACHE_SIZE);
-                rc = ecryptfs_read_and_validate_xattr_region(page_virt,
-                                                             ecryptfs_dentry);
+        if (S_ISREG(inode->i_mode)) {
+                rc = ecryptfs_i_size_read(dentry, inode);
                 if (rc) {
-                        rc = 0;
-                        goto out_free_kmem;
+                        make_bad_inode(inode);
+                        return rc;
                 }
-                crypt_stat->flags |= ECRYPTFS_METADATA_IN_XATTR;
         }
-        ecryptfs_i_size_init(page_virt, ecryptfs_dentry->d_inode);
-out_free_kmem:
-        kmem_cache_free(ecryptfs_header_cache_2, page_virt);
-        goto out;
-out_put:
-        dput(lower_dentry);
-        mntput(lower_mnt);
-        d_drop(ecryptfs_dentry);
-out:
-        if (put_lower)
-                ecryptfs_put_lower_file(ecryptfs_dentry->d_inode);
+
+        if (inode->i_state & I_NEW)
+                unlock_new_inode(inode);
+        d_add(dentry, inode);
+
         return rc;
 }
 
@@ -353,12 +433,12 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
                 goto out_d_drop;
         }
         if (lower_dentry->d_inode)
-                goto lookup_and_interpose;
+                goto interpose;
         mount_crypt_stat = &ecryptfs_superblock_to_private(
                                 ecryptfs_dentry->d_sb)->mount_crypt_stat;
         if (!(mount_crypt_stat
             && (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES)))
-                goto lookup_and_interpose;
+                goto interpose;
         dput(lower_dentry);
         rc = ecryptfs_encrypt_and_encode_filename(
                 &encrypted_and_encoded_name, &encrypted_and_encoded_name_size,
@@ -381,9 +461,9 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
                                 encrypted_and_encoded_name);
                 goto out_d_drop;
         }
-lookup_and_interpose:
-        rc = ecryptfs_lookup_and_interpose_lower(ecryptfs_dentry, lower_dentry,
-                                                 ecryptfs_dir_inode);
+interpose:
+        rc = ecryptfs_lookup_interpose(ecryptfs_dentry, lower_dentry,
+                                       ecryptfs_dir_inode);
         goto out;
 out_d_drop:
         d_drop(ecryptfs_dentry);
@@ -411,7 +491,7 @@ static int ecryptfs_link(struct dentry *old_dentry, struct inode *dir,
                       lower_new_dentry);
         if (rc || !lower_new_dentry->d_inode)
                 goto out_lock;
-        rc = ecryptfs_interpose(lower_new_dentry, new_dentry, dir->i_sb, 0);
+        rc = ecryptfs_interpose(lower_new_dentry, new_dentry, dir->i_sb);
         if (rc)
                 goto out_lock;
         fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode);
@@ -478,7 +558,7 @@ static int ecryptfs_symlink(struct inode *dir, struct dentry *dentry,
         kfree(encoded_symname);
         if (rc || !lower_dentry->d_inode)
                 goto out_lock;
-        rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb, 0);
+        rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb);
         if (rc)
                 goto out_lock;
         fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode);
@@ -502,7 +582,7 @@ static int ecryptfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
         rc = vfs_mkdir(lower_dir_dentry->d_inode, lower_dentry, mode);
         if (rc || !lower_dentry->d_inode)
                 goto out;
-        rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb, 0);
+        rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb);
         if (rc)
                 goto out;
         fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode);
@@ -521,8 +601,6 @@ static int ecryptfs_rmdir(struct inode *dir, struct dentry *dentry)
         struct dentry *lower_dir_dentry;
         int rc;
 
-        dentry_unhash(dentry);
-
         lower_dentry = ecryptfs_dentry_to_lower(dentry);
         dget(dentry);
         lower_dir_dentry = lock_parent(lower_dentry);
@@ -552,7 +630,7 @@ ecryptfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
         rc = vfs_mknod(lower_dir_dentry->d_inode, lower_dentry, mode, dev);
         if (rc || !lower_dentry->d_inode)
                 goto out;
-        rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb, 0);
+        rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb);
         if (rc)
                 goto out;
         fsstack_copy_attr_times(dir, lower_dir_dentry->d_inode);
@@ -575,9 +653,6 @@ ecryptfs_rename(struct inode *old_dir, struct dentry *old_dentry,
         struct dentry *lower_new_dir_dentry;
         struct dentry *trap = NULL;
 
-        if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
-                dentry_unhash(new_dentry);
-
         lower_old_dentry = ecryptfs_dentry_to_lower(old_dentry);
         lower_new_dentry = ecryptfs_dentry_to_lower(new_dentry);
         dget(lower_old_dentry);
@@ -755,7 +830,7 @@ static int truncate_upper(struct dentry *dentry, struct iattr *ia,
                 lower_ia->ia_valid &= ~ATTR_SIZE;
                 return 0;
         }
-        rc = ecryptfs_get_lower_file(dentry);
+        rc = ecryptfs_get_lower_file(dentry, inode);
         if (rc)
                 return rc;
         crypt_stat = &ecryptfs_inode_to_private(dentry->d_inode)->crypt_stat;
@@ -911,7 +986,7 @@ static int ecryptfs_setattr(struct dentry *dentry, struct iattr *ia)
 
                 mount_crypt_stat = &ecryptfs_superblock_to_private(
                         dentry->d_sb)->mount_crypt_stat;
-                rc = ecryptfs_get_lower_file(dentry);
+                rc = ecryptfs_get_lower_file(dentry, inode);
                 if (rc) {
                         mutex_unlock(&crypt_stat->cs_mutex);
                         goto out;
@@ -1084,21 +1159,6 @@ out:
         return rc;
 }
 
-int ecryptfs_inode_test(struct inode *inode, void *candidate_lower_inode)
-{
-        if ((ecryptfs_inode_to_lower(inode)
-             == (struct inode *)candidate_lower_inode))
-                return 1;
-        else
-                return 0;
-}
-
-int ecryptfs_inode_set(struct inode *inode, void *lower_inode)
-{
-        ecryptfs_init_inode(inode, (struct inode *)lower_inode);
-        return 0;
-}
-
 const struct inode_operations ecryptfs_symlink_iops = {
         .readlink = ecryptfs_readlink,
         .follow_link = ecryptfs_follow_link,
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index 89b93389af8e..9f1bb747d77d 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -135,12 +135,12 @@ static int ecryptfs_init_lower_file(struct dentry *dentry,
         return rc;
 }
 
-int ecryptfs_get_lower_file(struct dentry *dentry)
+int ecryptfs_get_lower_file(struct dentry *dentry, struct inode *inode)
 {
-        struct ecryptfs_inode_info *inode_info =
-                ecryptfs_inode_to_private(dentry->d_inode);
+        struct ecryptfs_inode_info *inode_info;
         int count, rc = 0;
 
+        inode_info = ecryptfs_inode_to_private(inode);
         mutex_lock(&inode_info->lower_file_mutex);
         count = atomic_inc_return(&inode_info->lower_file_count);
         if (WARN_ON_ONCE(count < 1))
@@ -168,75 +168,6 @@ void ecryptfs_put_lower_file(struct inode *inode)
         }
 }
 
-static struct inode *ecryptfs_get_inode(struct inode *lower_inode,
-                       struct super_block *sb)
-{
-        struct inode *inode;
-        int rc = 0;
-
-        if (lower_inode->i_sb != ecryptfs_superblock_to_lower(sb)) {
-                rc = -EXDEV;
-                goto out;
-        }
-        if (!igrab(lower_inode)) {
-                rc = -ESTALE;
-                goto out;
-        }
-        inode = iget5_locked(sb, (unsigned long)lower_inode,
-                             ecryptfs_inode_test, ecryptfs_inode_set,
-                             lower_inode);
-        if (!inode) {
-                rc = -EACCES;
-                iput(lower_inode);
-                goto out;
-        }
-        if (inode->i_state & I_NEW)
-                unlock_new_inode(inode);
-        else
-                iput(lower_inode);
-        if (S_ISLNK(lower_inode->i_mode))
-                inode->i_op = &ecryptfs_symlink_iops;
-        else if (S_ISDIR(lower_inode->i_mode))
-                inode->i_op = &ecryptfs_dir_iops;
-        if (S_ISDIR(lower_inode->i_mode))
-                inode->i_fop = &ecryptfs_dir_fops;
-        if (special_file(lower_inode->i_mode))
-                init_special_inode(inode, lower_inode->i_mode,
-                                   lower_inode->i_rdev);
-        fsstack_copy_attr_all(inode, lower_inode);
-        /* This size will be overwritten for real files w/ headers and
-         * other metadata */
-        fsstack_copy_inode_size(inode, lower_inode);
-        return inode;
-out:
-        return ERR_PTR(rc);
-}
-
-/**
- * ecryptfs_interpose
- * @lower_dentry: Existing dentry in the lower filesystem
- * @dentry: ecryptfs' dentry
- * @sb: ecryptfs's super_block
- * @flags: flags to govern behavior of interpose procedure
- *
- * Interposes upper and lower dentries.
- *
- * Returns zero on success; non-zero otherwise
- */
-int ecryptfs_interpose(struct dentry *lower_dentry, struct dentry *dentry,
-                       struct super_block *sb, u32 flags)
-{
-        struct inode *lower_inode = lower_dentry->d_inode;
-        struct inode *inode = ecryptfs_get_inode(lower_inode, sb);
-        if (IS_ERR(inode))
-                return PTR_ERR(inode);
-        if (flags & ECRYPTFS_INTERPOSE_FLAG_D_ADD)
-                d_add(dentry, inode);
-        else
-                d_instantiate(dentry, inode);
-        return 0;
-}
-
 enum { ecryptfs_opt_sig, ecryptfs_opt_ecryptfs_sig,
        ecryptfs_opt_cipher, ecryptfs_opt_ecryptfs_cipher,
        ecryptfs_opt_ecryptfs_key_bytes,
@@ -704,13 +635,8 @@ static struct ecryptfs_cache_info {
                 .size = sizeof(struct ecryptfs_sb_info),
         },
         {
-                .cache = &ecryptfs_header_cache_1,
-                .name = "ecryptfs_headers_1",
-                .size = PAGE_CACHE_SIZE,
-        },
-        {
-                .cache = &ecryptfs_header_cache_2,
-                .name = "ecryptfs_headers_2",
+                .cache = &ecryptfs_header_cache,
+                .name = "ecryptfs_headers",
                 .size = PAGE_CACHE_SIZE,
         },
         {
diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c
index 245b517bf1b6..dbd52d40df4c 100644
--- a/fs/ecryptfs/super.c
+++ b/fs/ecryptfs/super.c
@@ -93,22 +93,6 @@ static void ecryptfs_destroy_inode(struct inode *inode)
 }
 
 /**
- * ecryptfs_init_inode
- * @inode: The ecryptfs inode
- *
- * Set up the ecryptfs inode.
- */
-void ecryptfs_init_inode(struct inode *inode, struct inode *lower_inode)
-{
-        ecryptfs_set_inode_lower(inode, lower_inode);
-        inode->i_ino = lower_inode->i_ino;
-        inode->i_version++;
-        inode->i_op = &ecryptfs_main_iops;
-        inode->i_fop = &ecryptfs_main_fops;
-        inode->i_mapping->a_ops = &ecryptfs_aops;
-}
-
-/**
  * ecryptfs_statfs
  * @sb: The ecryptfs super block
  * @buf: The struct kstatfs to fill in with stats
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 68b2e43d7c35..3451d23c3bae 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -3392,7 +3392,7 @@ int ext3_mark_inode_dirty(handle_t *handle, struct inode *inode)
  * so would cause a commit on atime updates, which we don't bother doing.
  * We handle synchronous inodes at the highest possible level.
  */
-void ext3_dirty_inode(struct inode *inode)
+void ext3_dirty_inode(struct inode *inode, int flags)
 {
         handle_t *current_handle = ext3_journal_current_handle();
         handle_t *handle;
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index a74b89c09f90..1921392cd708 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1813,7 +1813,7 @@ extern int  ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
 extern void ext4_evict_inode(struct inode *);
 extern void ext4_clear_inode(struct inode *);
 extern int  ext4_sync_inode(handle_t *, struct inode *);
-extern void ext4_dirty_inode(struct inode *);
+extern void ext4_dirty_inode(struct inode *, int);
 extern int ext4_change_inode_journal_flag(struct inode *, int);
 extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
 extern int ext4_can_truncate(struct inode *inode);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 50d0e9c64584..a5763e3505ba 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5733,7 +5733,7 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
  * so would cause a commit on atime updates, which we don't bother doing.
  * We handle synchronous inodes at the highest possible level.
  */
-void ext4_dirty_inode(struct inode *inode)
+void ext4_dirty_inode(struct inode *inode, int flags)
 {
         handle_t *handle;
 
diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c
index be15437c272e..3b222dafd15b 100644
--- a/fs/fat/namei_msdos.c
+++ b/fs/fat/namei_msdos.c
@@ -326,8 +326,6 @@ static int msdos_rmdir(struct inode *dir, struct dentry *dentry)
         struct fat_slot_info sinfo;
         int err;
 
-        dentry_unhash(dentry);
-
         lock_super(sb);
         /*
          * Check whether the directory is not in use, then check
@@ -459,9 +457,6 @@ static int do_msdos_rename(struct inode *old_dir, unsigned char *old_name,
         old_inode = old_dentry->d_inode;
         new_inode = new_dentry->d_inode;
 
-        if (new_inode && S_ISDIR(new_inode->i_mode))
-                dentry_unhash(new_dentry);
-
         err = fat_scan(old_dir, old_name, &old_sinfo);
         if (err) {
                 err = -EIO;
diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c
index c61a6789f36c..20b4ea53fdc4 100644
--- a/fs/fat/namei_vfat.c
+++ b/fs/fat/namei_vfat.c
@@ -824,8 +824,6 @@ static int vfat_rmdir(struct inode *dir, struct dentry *dentry)
         struct fat_slot_info sinfo;
         int err;
 
-        dentry_unhash(dentry);
-
         lock_super(sb);
 
         err = fat_dir_empty(inode);
@@ -933,9 +931,6 @@ static int vfat_rename(struct inode *old_dir, struct dentry *old_dentry,
         int err, is_dir, update_dotdot, corrupt = 0;
         struct super_block *sb = old_dir->i_sb;
 
-        if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
-                dentry_unhash(new_dentry);
-
         old_sinfo.bh = sinfo.bh = dotdot_bh = NULL;
         old_inode = old_dentry->d_inode;
         new_inode = new_dentry->d_inode;
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 34591ee804b5..0f015a0468de 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -1007,9 +1007,6 @@ static noinline void block_dump___mark_inode_dirty(struct inode *inode)
  * In short, make sure you hash any inodes _before_ you start marking
  * them dirty.
  *
- * This function *must* be atomic for the I_DIRTY_PAGES case -
- * set_page_dirty() is called under spinlock in several places.
- *
  * Note that for blockdevs, inode->dirtied_when represents the dirtying time of
  * the block-special inode (/dev/hda1) itself.  And the ->dirtied_when field of
  * the kernel-internal blockdev inode represents the dirtying time of the
@@ -1028,7 +1025,7 @@ void __mark_inode_dirty(struct inode *inode, int flags)
          */
         if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
                 if (sb->s_op->dirty_inode)
-                        sb->s_op->dirty_inode(inode);
+                        sb->s_op->dirty_inode(inode, flags);
         }
 
         /*
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 0d0e3faddcfa..d50160714595 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -667,8 +667,6 @@ static int fuse_rmdir(struct inode *dir, struct dentry *entry)
         if (IS_ERR(req))
                 return PTR_ERR(req);
 
-        dentry_unhash(entry);
-
         req->in.h.opcode = FUSE_RMDIR;
         req->in.h.nodeid = get_node_id(dir);
         req->in.numargs = 1;
@@ -694,9 +692,6 @@ static int fuse_rename(struct inode *olddir, struct dentry *oldent,
         struct fuse_conn *fc = get_fuse_conn(olddir);
         struct fuse_req *req = fuse_get_req(fc);
 
-        if (newent->d_inode && S_ISDIR(newent->d_inode->i_mode))
-                dentry_unhash(newent);
-
         if (IS_ERR(req))
                 return PTR_ERR(req);
 
diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c
index 1cb70cdba2c1..b4d70b13be92 100644
--- a/fs/hfs/dir.c
+++ b/fs/hfs/dir.c
@@ -253,9 +253,6 @@ static int hfs_remove(struct inode *dir, struct dentry *dentry)
         struct inode *inode = dentry->d_inode;
         int res;
 
-        if (S_ISDIR(inode->i_mode))
-                dentry_unhash(dentry);
-
         if (S_ISDIR(inode->i_mode) && inode->i_size != 2)
                 return -ENOTEMPTY;
         res = hfs_cat_delete(inode->i_ino, dir, &dentry->d_name);
@@ -286,9 +283,6 @@ static int hfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 
         /* Unlink destination if it already exists */
         if (new_dentry->d_inode) {
-                if (S_ISDIR(new_dentry->d_inode->i_mode))
-                        dentry_unhash(new_dentry);
-
                 res = hfs_remove(new_dir, new_dentry);
                 if (res)
                         return res;
diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c
index b28835091dd0..4df5059c25da 100644
--- a/fs/hfsplus/dir.c
+++ b/fs/hfsplus/dir.c
@@ -370,8 +370,6 @@ static int hfsplus_rmdir(struct inode *dir, struct dentry *dentry)
         struct inode *inode = dentry->d_inode;
         int res;
 
-        dentry_unhash(dentry);
-
         if (inode->i_size != 2)
                 return -ENOTEMPTY;
 
@@ -469,12 +467,10 @@ static int hfsplus_rename(struct inode *old_dir, struct dentry *old_dentry,
 
         /* Unlink destination if it already exists */
         if (new_dentry->d_inode) {
-                if (S_ISDIR(new_dentry->d_inode->i_mode)) {
-                        dentry_unhash(new_dentry);
+                if (S_ISDIR(new_dentry->d_inode->i_mode))
                         res = hfsplus_rmdir(new_dir, new_dentry);
-                } else {
+                else
                         res = hfsplus_unlink(new_dir, new_dentry);
-                }
                 if (res)
                         return res;
         }
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index e6816b9e6903..2638c834ed28 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -683,8 +683,6 @@ int hostfs_rmdir(struct inode *ino, struct dentry *dentry)
         char *file;
         int err;
 
-        dentry_unhash(dentry);
-
         if ((file = dentry_name(dentry)) == NULL)
                 return -ENOMEM;
         err = do_rmdir(file);
@@ -738,9 +736,6 @@ int hostfs_rename(struct inode *from_ino, struct dentry *from,
         char *from_name, *to_name;
         int err;
 
-        if (to->d_inode && S_ISDIR(to->d_inode->i_mode))
-                dentry_unhash(to);
-
         if ((from_name = dentry_name(from)) == NULL)
                 return -ENOMEM;
         if ((to_name = dentry_name(to)) == NULL) {
diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c
index ff0ce21c0867..acf95dab2aac 100644
--- a/fs/hpfs/namei.c
+++ b/fs/hpfs/namei.c
@@ -439,8 +439,6 @@ static int hpfs_rmdir(struct inode *dir, struct dentry *dentry)
         int err;
         int r;
 
-        dentry_unhash(dentry);
-
         hpfs_adjust_length(name, &len);
         hpfs_lock(dir->i_sb);
         err = -ENOENT;
@@ -535,9 +533,6 @@ static int hpfs_rename(struct inode *old_dir, struct dentry *old_dentry,
         struct fnode *fnode;
         int err;
 
-        if (new_inode && S_ISDIR(new_inode->i_mode))
-                dentry_unhash(new_dentry);
-
         if ((err = hpfs_chk_name(new_name, &new_len))) return err;
         err = 0;
         hpfs_adjust_length(old_name, &old_len);
diff --git a/fs/inode.c b/fs/inode.c
index 990d284877a1..0f7e88a7803f 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1,9 +1,7 @@
 /*
- * linux/fs/inode.c
- *
  * (C) 1997 Linus Torvalds
+ * (C) 1999 Andrea Arcangeli <andrea@suse.de> (dynamic inode allocation)
  */
-
 #include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/dcache.h>
@@ -27,10 +25,11 @@
 #include <linux/prefetch.h>
 #include <linux/ima.h>
 #include <linux/cred.h>
+#include <linux/buffer_head.h> /* for inode_has_buffers */
 #include "internal.h"
 
 /*
- * inode locking rules.
+ * Inode locking rules:
  *
  * inode->i_lock protects:
  *   inode->i_state, inode->i_hash, __iget()
@@ -60,54 +59,11 @@
  *   inode_hash_lock
  */
 
-/*
- * This is needed for the following functions:
- *  - inode_has_buffers
- *  - invalidate_bdev
- *
- * FIXME: remove all knowledge of the buffer layer from this file
- */
-#include <linux/buffer_head.h>
-
-/*
- * New inode.c implementation.
- *
- * This implementation has the basic premise of trying
- * to be extremely low-overhead and SMP-safe, yet be
- * simple enough to be "obviously correct".
- *
- * Famous last words.
- */
-
-/* inode dynamic allocation 1999, Andrea Arcangeli <andrea@suse.de> */
-
-/* #define INODE_PARANOIA 1 */
-/* #define INODE_DEBUG 1 */
-
-/*
- * Inode lookup is no longer as critical as it used to be:
- * most of the lookups are going to be through the dcache.
- */
-#define I_HASHBITS      i_hash_shift
-#define I_HASHMASK      i_hash_mask
-
 static unsigned int i_hash_mask __read_mostly;
 static unsigned int i_hash_shift __read_mostly;
 static struct hlist_head *inode_hashtable __read_mostly;
 static __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_hash_lock);
 
-/*
- * Each inode can be on two separate lists. One is
- * the hash list of the inode, used for lookups. The
- * other linked list is the "type" list:
- *  "in_use" - valid inode, i_count > 0, i_nlink > 0
- *  "dirty"  - as "in_use" but also dirty
- *  "unused" - valid inode, i_count = 0
- *
- * A "dirty" list is maintained for each super block,
- * allowing for low-overhead inode sync() operations.
- */
-
 static LIST_HEAD(inode_lru);
 static DEFINE_SPINLOCK(inode_lru_lock);
 
@@ -424,8 +380,8 @@ static unsigned long hash(struct super_block *sb, unsigned long hashval)
 
         tmp = (hashval * (unsigned long)sb) ^ (GOLDEN_RATIO_PRIME + hashval) /
                         L1_CACHE_BYTES;
-        tmp = tmp ^ ((tmp ^ GOLDEN_RATIO_PRIME) >> I_HASHBITS);
-        return tmp & I_HASHMASK;
+        tmp = tmp ^ ((tmp ^ GOLDEN_RATIO_PRIME) >> i_hash_shift);
+        return tmp & i_hash_mask;
 }
 
 /**
diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index 9a1e86fc1362..4bca6a2e5c07 100644
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -605,8 +605,6 @@ static int jffs2_rmdir (struct inode *dir_i, struct dentry *dentry)
         int ret;
         uint32_t now = get_seconds();
 
-        dentry_unhash(dentry);
-
         for (fd = f->dents ; fd; fd = fd->next) {
                 if (fd->ino)
                         return -ENOTEMPTY;
@@ -782,9 +780,6 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry,
         uint8_t type;
         uint32_t now;
 
-        if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
-                dentry_unhash(new_dentry);
-
         /* The VFS will check for us and prevent trying to rename a
          * file over a directory and vice versa, but if it's a directory,
          * the VFS can't check whether the victim is empty. The filesystem
diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c
index e896e67767eb..46ad619b6124 100644
--- a/fs/jffs2/fs.c
+++ b/fs/jffs2/fs.c
@@ -357,7 +357,7 @@ error:
         return ERR_PTR(ret);
 }
 
-void jffs2_dirty_inode(struct inode *inode)
+void jffs2_dirty_inode(struct inode *inode, int flags)
 {
         struct iattr iattr;
 
diff --git a/fs/jffs2/os-linux.h b/fs/jffs2/os-linux.h
index 00bae7cc2e48..65c6c43ca482 100644
--- a/fs/jffs2/os-linux.h
+++ b/fs/jffs2/os-linux.h
@@ -172,7 +172,7 @@ int jffs2_setattr (struct dentry *, struct iattr *);
 int jffs2_do_setattr (struct inode *, struct iattr *);
 struct inode *jffs2_iget(struct super_block *, unsigned long);
 void jffs2_evict_inode (struct inode *);
-void jffs2_dirty_inode(struct inode *inode);
+void jffs2_dirty_inode(struct inode *inode, int flags);
 struct inode *jffs2_new_inode (struct inode *dir_i, int mode,
                                struct jffs2_raw_inode *ri);
 int jffs2_statfs (struct dentry *, struct kstatfs *);
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index eddbb373209e..109655904bbc 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -173,7 +173,7 @@ void jfs_evict_inode(struct inode *inode)
         dquot_drop(inode);
 }
 
-void jfs_dirty_inode(struct inode *inode)
+void jfs_dirty_inode(struct inode *inode, int flags)
 {
         static int noisy = 5;
 
diff --git a/fs/jfs/jfs_inode.h b/fs/jfs/jfs_inode.h
index 155e91eff07d..ec2fb8b945fc 100644
--- a/fs/jfs/jfs_inode.h
+++ b/fs/jfs/jfs_inode.h
@@ -28,7 +28,7 @@ extern struct inode *jfs_iget(struct super_block *, unsigned long);
 extern int jfs_commit_inode(struct inode *, int);
 extern int jfs_write_inode(struct inode *, struct writeback_control *);
 extern void jfs_evict_inode(struct inode *);
-extern void jfs_dirty_inode(struct inode *);
+extern void jfs_dirty_inode(struct inode *, int);
 extern void jfs_truncate(struct inode *);
 extern void jfs_truncate_nolock(struct inode *, loff_t);
 extern void jfs_free_zero_link(struct inode *);
diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c
index 865df16a6cf3..eaaf2b511e89 100644
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -360,8 +360,6 @@ static int jfs_rmdir(struct inode *dip, struct dentry *dentry)
 
         jfs_info("jfs_rmdir: dip:0x%p name:%s", dip, dentry->d_name.name);
 
-        dentry_unhash(dentry);
-
         /* Init inode for quota operations. */
         dquot_initialize(dip);
         dquot_initialize(ip);
@@ -1097,9 +1095,6 @@ static int jfs_rename(struct inode *old_dir, struct dentry *old_dentry,
         jfs_info("jfs_rename: %s %s", old_dentry->d_name.name,
                  new_dentry->d_name.name);
 
-        if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
-                dentry_unhash(new_dentry);
-
         dquot_initialize(old_dir);
         dquot_initialize(new_dir);
 
diff --git a/fs/logfs/dir.c b/fs/logfs/dir.c
index f34c9cde9e94..9ed89d1663f8 100644
--- a/fs/logfs/dir.c
+++ b/fs/logfs/dir.c
@@ -273,8 +273,6 @@ static int logfs_rmdir(struct inode *dir, struct dentry *dentry)
 {
         struct inode *inode = dentry->d_inode;
 
-        dentry_unhash(dentry);
-
         if (!logfs_empty_dir(inode))
                 return -ENOTEMPTY;
 
@@ -624,9 +622,6 @@ static int logfs_rename_cross(struct inode *old_dir, struct dentry *old_dentry,
         loff_t pos;
         int err;
 
-        if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
-                dentry_unhash(new_dentry);
-
         /* 1. locate source dd */
         err = logfs_get_dd(old_dir, old_dentry, &dd, &pos);
         if (err)
diff --git a/fs/minix/namei.c b/fs/minix/namei.c
index f60aed8db9c4..6e6777f1b4b2 100644
--- a/fs/minix/namei.c
+++ b/fs/minix/namei.c
@@ -168,8 +168,6 @@ static int minix_rmdir(struct inode * dir, struct dentry *dentry)
         struct inode * inode = dentry->d_inode;
         int err = -ENOTEMPTY;
 
-        dentry_unhash(dentry);
-
         if (minix_empty_dir(inode)) {
                 err = minix_unlink(dir, dentry);
                 if (!err) {
@@ -192,9 +190,6 @@ static int minix_rename(struct inode * old_dir, struct dentry *old_dentry,
         struct minix_dir_entry * old_de;
         int err = -ENOENT;
 
-        if (new_inode && S_ISDIR(new_inode->i_mode))
-                dentry_unhash(new_dentry);
-
         old_de = minix_find_entry(old_dentry, &old_page);
         if (!old_de)
                 goto out;
diff --git a/fs/namei.c b/fs/namei.c
index 2358b326b221..e2e4e8d032ee 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -919,12 +919,11 @@ static inline bool managed_dentry_might_block(struct dentry *dentry)
 }
 
 /*
- * Skip to top of mountpoint pile in rcuwalk mode.  We abort the rcu-walk if we
- * meet a managed dentry and we're not walking to "..".  True is returned to
- * continue, false to abort.
+ * Try to skip to top of mountpoint pile in rcuwalk mode.  Fail if
+ * we meet a managed dentry that would need blocking.
  */
 static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
-                               struct inode **inode, bool reverse_transit)
+                               struct inode **inode)
 {
         for (;;) {
                 struct vfsmount *mounted;
@@ -933,8 +932,7 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
                  * that wants to block transit.
                  */
                 *inode = path->dentry->d_inode;
-                if (!reverse_transit &&
-                     unlikely(managed_dentry_might_block(path->dentry)))
+                if (unlikely(managed_dentry_might_block(path->dentry)))
                         return false;
 
                 if (!d_mountpoint(path->dentry))
@@ -947,16 +945,24 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
                 path->dentry = mounted->mnt_root;
                 nd->seq = read_seqcount_begin(&path->dentry->d_seq);
         }
-
-        if (unlikely(path->dentry->d_flags & DCACHE_NEED_AUTOMOUNT))
-                return reverse_transit;
         return true;
 }
 
-static int follow_dotdot_rcu(struct nameidata *nd)
+static void follow_mount_rcu(struct nameidata *nd)
 {
-        struct inode *inode = nd->inode;
+        while (d_mountpoint(nd->path.dentry)) {
+                struct vfsmount *mounted;
+                mounted = __lookup_mnt(nd->path.mnt, nd->path.dentry, 1);
+                if (!mounted)
+                        break;
+                nd->path.mnt = mounted;
+                nd->path.dentry = mounted->mnt_root;
+                nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
+        }
+}
 
+static int follow_dotdot_rcu(struct nameidata *nd)
+{
         set_root_rcu(nd);
 
         while (1) {
@@ -972,7 +978,6 @@ static int follow_dotdot_rcu(struct nameidata *nd)
                         seq = read_seqcount_begin(&parent->d_seq);
                         if (read_seqcount_retry(&old->d_seq, nd->seq))
                                 goto failed;
-                        inode = parent->d_inode;
                         nd->path.dentry = parent;
                         nd->seq = seq;
                         break;
@@ -980,10 +985,9 @@ static int follow_dotdot_rcu(struct nameidata *nd)
                 if (!follow_up_rcu(&nd->path))
                         break;
                 nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
-                inode = nd->path.dentry->d_inode;
         }
-        __follow_mount_rcu(nd, &nd->path, &inode, true);
-        nd->inode = inode;
+        follow_mount_rcu(nd);
+        nd->inode = nd->path.dentry->d_inode;
         return 0;
 
 failed:
@@ -1157,8 +1161,11 @@ static int do_lookup(struct nameidata *nd, struct qstr *name,
                 }
                 path->mnt = mnt;
                 path->dentry = dentry;
-                if (likely(__follow_mount_rcu(nd, path, inode, false)))
-                        return 0;
+                if (unlikely(!__follow_mount_rcu(nd, path, inode)))
+                        goto unlazy;
+                if (unlikely(path->dentry->d_flags & DCACHE_NEED_AUTOMOUNT))
+                        goto unlazy;
+                return 0;
 unlazy:
                 if (unlazy_walk(nd, dentry))
                         return -ECHILD;
@@ -2572,6 +2579,7 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry)
         if (error)
                 goto out;
 
+        shrink_dcache_parent(dentry);
         error = dir->i_op->rmdir(dir, dentry);
         if (error)
                 goto out;
@@ -2986,6 +2994,8 @@ static int vfs_rename_dir(struct inode *old_dir, struct dentry *old_dentry,
         if (d_mountpoint(old_dentry) || d_mountpoint(new_dentry))
                 goto out;
 
+        if (target)
+                shrink_dcache_parent(new_dentry);
         error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry);
         if (error)
                 goto out;
diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c
index e3e646b06404..9c51f621e901 100644
--- a/fs/ncpfs/dir.c
+++ b/fs/ncpfs/dir.c
@@ -1033,8 +1033,11 @@ static int ncp_rmdir(struct inode *dir, struct dentry *dentry)
         DPRINTK("ncp_rmdir: removing %s/%s\n",
                 dentry->d_parent->d_name.name, dentry->d_name.name);
 
+        /*
+         * fail with EBUSY if there are still references to this
+         * directory.
+         */
         dentry_unhash(dentry);
-
         error = -EBUSY;
         if (!d_unhashed(dentry))
                 goto out;
@@ -1141,8 +1144,16 @@ static int ncp_rename(struct inode *old_dir, struct dentry *old_dentry,
                 old_dentry->d_parent->d_name.name, old_dentry->d_name.name,
                 new_dentry->d_parent->d_name.name, new_dentry->d_name.name);
 
-        if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
+        if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode)) {
+                /*
+                 * fail with EBUSY if there are still references to this
+                 * directory.
+                 */
                 dentry_unhash(new_dentry);
+                error = -EBUSY;
+                if (!d_unhashed(new_dentry))
+                        goto out;
+        }
 
         ncp_age_dentry(server, old_dentry);
         ncp_age_dentry(server, new_dentry);
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index ba306658a6db..81515545ba75 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -87,6 +87,16 @@ config NFS_V4_1
 config PNFS_FILE_LAYOUT
         tristate
 
+config PNFS_OBJLAYOUT
+        tristate "Provide support for the pNFS Objects Layout Driver for NFSv4.1 pNFS (EXPERIMENTAL)"
+        depends on NFS_FS && NFS_V4_1 && SCSI_OSD_ULD
+        help
+          Say M here if you want your pNFS client to support the Objects Layout Driver.
+          Requires the SCSI osd initiator library (SCSI_OSD_INITIATOR) and
+          upper level driver (SCSI_OSD_ULD).
+
+          If unsure, say N.
+
 config ROOT_NFS
         bool "Root file system on NFS"
         depends on NFS_FS=y && IP_PNP
diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
index 4776ff9e3814..6a34f7dd0e6f 100644
--- a/fs/nfs/Makefile
+++ b/fs/nfs/Makefile
@@ -15,9 +15,11 @@ nfs-$(CONFIG_NFS_V4)	+= nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o \
                            delegation.o idmap.o \
                            callback.o callback_xdr.o callback_proc.o \
                            nfs4namespace.o
-nfs-$(CONFIG_NFS_V4_1)  += pnfs.o
+nfs-$(CONFIG_NFS_V4_1)  += pnfs.o pnfs_dev.o
 nfs-$(CONFIG_SYSCTL) += sysctl.o
 nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o
 
 obj-$(CONFIG_PNFS_FILE_LAYOUT) += nfs_layout_nfsv41_files.o
 nfs_layout_nfsv41_files-y := nfs4filelayout.o nfs4filelayoutdev.o
+
+obj-$(CONFIG_PNFS_OBJLAYOUT) += objlayout/
diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h
index 46d93ce7311b..b257383bb565 100644
--- a/fs/nfs/callback.h
+++ b/fs/nfs/callback.h
@@ -167,6 +167,23 @@ extern unsigned nfs4_callback_layoutrecall(
 
 extern void nfs4_check_drain_bc_complete(struct nfs4_session *ses);
 extern void nfs4_cb_take_slot(struct nfs_client *clp);
+
+struct cb_devicenotifyitem {
+        uint32_t                cbd_notify_type;
+        uint32_t                cbd_layout_type;
+        struct nfs4_deviceid    cbd_dev_id;
+        uint32_t                cbd_immediate;
+};
+
+struct cb_devicenotifyargs {
+        int                              ndevs;
+        struct cb_devicenotifyitem       *devs;
+};
+
+extern __be32 nfs4_callback_devicenotify(
+        struct cb_devicenotifyargs *args,
+        void *dummy, struct cb_process_state *cps);
+
 #endif /* CONFIG_NFS_V4_1 */
 extern int check_gss_callback_principal(struct nfs_client *, struct svc_rqst *);
 extern __be32 nfs4_callback_getattr(struct cb_getattrargs *args,
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 2f41dccea18e..d4d1954e9bb9 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -139,7 +139,7 @@ static u32 initiate_file_draining(struct nfs_client *clp,
         spin_lock(&ino->i_lock);
         if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags) ||
             mark_matching_lsegs_invalid(lo, &free_me_list,
-                                        args->cbl_range.iomode))
+                                        &args->cbl_range))
                 rv = NFS4ERR_DELAY;
         else
                 rv = NFS4ERR_NOMATCHING_LAYOUT;
@@ -184,7 +184,7 @@ static u32 initiate_bulk_draining(struct nfs_client *clp,
                 ino = lo->plh_inode;
                 spin_lock(&ino->i_lock);
                 set_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
-                if (mark_matching_lsegs_invalid(lo, &free_me_list, range.iomode))
+                if (mark_matching_lsegs_invalid(lo, &free_me_list, &range))
                         rv = NFS4ERR_DELAY;
                 list_del_init(&lo->plh_bulk_recall);
                 spin_unlock(&ino->i_lock);
@@ -241,6 +241,53 @@ static void pnfs_recall_all_layouts(struct nfs_client *clp)
         do_callback_layoutrecall(clp, &args);
 }
 
+__be32 nfs4_callback_devicenotify(struct cb_devicenotifyargs *args,
+                                  void *dummy, struct cb_process_state *cps)
+{
+        int i;
+        __be32 res = 0;
+        struct nfs_client *clp = cps->clp;
+        struct nfs_server *server = NULL;
+
+        dprintk("%s: -->\n", __func__);
+
+        if (!clp) {
+                res = cpu_to_be32(NFS4ERR_OP_NOT_IN_SESSION);
+                goto out;
+        }
+
+        for (i = 0; i < args->ndevs; i++) {
+                struct cb_devicenotifyitem *dev = &args->devs[i];
+
+                if (!server ||
+                    server->pnfs_curr_ld->id != dev->cbd_layout_type) {
+                        rcu_read_lock();
+                        list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link)
+                                if (server->pnfs_curr_ld &&
+                                    server->pnfs_curr_ld->id == dev->cbd_layout_type) {
+                                        rcu_read_unlock();
+                                        goto found;
+                                }
+                        rcu_read_unlock();
+                        dprintk("%s: layout type %u not found\n",
+                                __func__, dev->cbd_layout_type);
+                        continue;
+                }
+
+        found:
+                if (dev->cbd_notify_type == NOTIFY_DEVICEID4_CHANGE)
+                        dprintk("%s: NOTIFY_DEVICEID4_CHANGE not supported, "
+                                "deleting instead\n", __func__);
+                nfs4_delete_deviceid(server->pnfs_curr_ld, clp, &dev->cbd_dev_id);
+        }
+
+out:
+        kfree(args->devs);
+        dprintk("%s: exit with status = %u\n",
+                __func__, be32_to_cpu(res));
+        return res;
+}
+
 int nfs41_validate_delegation_stateid(struct nfs_delegation *delegation, const nfs4_stateid *stateid)
 {
         if (delegation == NULL)
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index 00ecf62ce7c1..c6c86a77e043 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -25,6 +25,7 @@
 
 #if defined(CONFIG_NFS_V4_1)
 #define CB_OP_LAYOUTRECALL_RES_MAXSZ    (CB_OP_HDR_RES_MAXSZ)
+#define CB_OP_DEVICENOTIFY_RES_MAXSZ    (CB_OP_HDR_RES_MAXSZ)
 #define CB_OP_SEQUENCE_RES_MAXSZ        (CB_OP_HDR_RES_MAXSZ + \
                                         4 + 1 + 3)
 #define CB_OP_RECALLANY_RES_MAXSZ       (CB_OP_HDR_RES_MAXSZ)
@@ -284,6 +285,93 @@ out:
         return status;
 }
 
+static
+__be32 decode_devicenotify_args(struct svc_rqst *rqstp,
+                                struct xdr_stream *xdr,
+                                struct cb_devicenotifyargs *args)
+{
+        __be32 *p;
+        __be32 status = 0;
+        u32 tmp;
+        int n, i;
+        args->ndevs = 0;
+
+        /* Num of device notifications */
+        p = read_buf(xdr, sizeof(uint32_t));
+        if (unlikely(p == NULL)) {
+                status = htonl(NFS4ERR_BADXDR);
+                goto out;
+        }
+        n = ntohl(*p++);
+        if (n <= 0)
+                goto out;
+
+        args->devs = kmalloc(n * sizeof(*args->devs), GFP_KERNEL);
+        if (!args->devs) {
+                status = htonl(NFS4ERR_DELAY);
+                goto out;
+        }
+
+        /* Decode each dev notification */
+        for (i = 0; i < n; i++) {
+                struct cb_devicenotifyitem *dev = &args->devs[i];
+
+                p = read_buf(xdr, (4 * sizeof(uint32_t)) + NFS4_DEVICEID4_SIZE);
+                if (unlikely(p == NULL)) {
+                        status = htonl(NFS4ERR_BADXDR);
+                        goto err;
+                }
+
+                tmp = ntohl(*p++);      /* bitmap size */
+                if (tmp != 1) {
+                        status = htonl(NFS4ERR_INVAL);
+                        goto err;
+                }
+                dev->cbd_notify_type = ntohl(*p++);
+                if (dev->cbd_notify_type != NOTIFY_DEVICEID4_CHANGE &&
+                    dev->cbd_notify_type != NOTIFY_DEVICEID4_DELETE) {
+                        status = htonl(NFS4ERR_INVAL);
+                        goto err;
+                }
+
+                tmp = ntohl(*p++);      /* opaque size */
+                if (((dev->cbd_notify_type == NOTIFY_DEVICEID4_CHANGE) &&
+                     (tmp != NFS4_DEVICEID4_SIZE + 8)) ||
+                    ((dev->cbd_notify_type == NOTIFY_DEVICEID4_DELETE) &&
+                     (tmp != NFS4_DEVICEID4_SIZE + 4))) {
+                        status = htonl(NFS4ERR_INVAL);
+                        goto err;
+                }
+                dev->cbd_layout_type = ntohl(*p++);
+                memcpy(dev->cbd_dev_id.data, p, NFS4_DEVICEID4_SIZE);
+                p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE);
+
+                if (dev->cbd_layout_type == NOTIFY_DEVICEID4_CHANGE) {
+                        p = read_buf(xdr, sizeof(uint32_t));
+                        if (unlikely(p == NULL)) {
+                                status = htonl(NFS4ERR_BADXDR);
+                                goto err;
+                        }
+                        dev->cbd_immediate = ntohl(*p++);
+                } else {
+                        dev->cbd_immediate = 0;
+                }
+
+                args->ndevs++;
+
+                dprintk("%s: type %d layout 0x%x immediate %d\n",
+                        __func__, dev->cbd_notify_type, dev->cbd_layout_type,
+                        dev->cbd_immediate);
+        }
+out:
+        dprintk("%s: status %d ndevs %d\n",
+                __func__, ntohl(status), args->ndevs);
+        return status;
+err:
+        kfree(args->devs);
+        goto out;
+}
+
 static __be32 decode_sessionid(struct xdr_stream *xdr,
                                  struct nfs4_sessionid *sid)
 {
@@ -639,10 +727,10 @@ preprocess_nfs41_op(int nop, unsigned int op_nr, struct callback_op **op)
         case OP_CB_RECALL_ANY:
         case OP_CB_RECALL_SLOT:
         case OP_CB_LAYOUTRECALL:
+        case OP_CB_NOTIFY_DEVICEID:
                 *op = &callback_ops[op_nr];
                 break;
 
-        case OP_CB_NOTIFY_DEVICEID:
         case OP_CB_NOTIFY:
         case OP_CB_PUSH_DELEG:
         case OP_CB_RECALLABLE_OBJ_AVAIL:
@@ -849,6 +937,12 @@ static struct callback_op callback_ops[] = {
                         (callback_decode_arg_t)decode_layoutrecall_args,
                 .res_maxsize = CB_OP_LAYOUTRECALL_RES_MAXSZ,
         },
+        [OP_CB_NOTIFY_DEVICEID] = {
+                .process_op = (callback_process_op_t)nfs4_callback_devicenotify,
+                .decode_args =
+                        (callback_decode_arg_t)decode_devicenotify_args,
+                .res_maxsize = CB_OP_DEVICENOTIFY_RES_MAXSZ,
+        },
         [OP_CB_SEQUENCE] = {
                 .process_op = (callback_process_op_t)nfs4_callback_sequence,
                 .decode_args = (callback_decode_arg_t)decode_cb_sequence_args,
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 139be9647d80..b3dc2b88b65b 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -290,6 +290,8 @@ static void nfs_free_client(struct nfs_client *clp)
         if (clp->cl_machine_cred != NULL)
                 put_rpccred(clp->cl_machine_cred);
 
+        nfs4_deviceid_purge_client(clp);
+
         kfree(clp->cl_hostname);
         kfree(clp);
 
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index bbbc6bf5cb2e..dd25c2aec375 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -21,25 +21,13 @@
 #include "delegation.h"
 #include "internal.h"
 
-static void nfs_do_free_delegation(struct nfs_delegation *delegation)
-{
-        kfree(delegation);
-}
-
-static void nfs_free_delegation_callback(struct rcu_head *head)
-{
-        struct nfs_delegation *delegation = container_of(head, struct nfs_delegation, rcu);
-
-        nfs_do_free_delegation(delegation);
-}
-
 static void nfs_free_delegation(struct nfs_delegation *delegation)
 {
         if (delegation->cred) {
                 put_rpccred(delegation->cred);
                 delegation->cred = NULL;
         }
-        call_rcu(&delegation->rcu, nfs_free_delegation_callback);
+        kfree_rcu(delegation, rcu);
 }
 
 /**
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 424e47773a84..ededdbd0db38 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -512,12 +512,7 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en
                                 struct page **xdr_pages, struct page *page, unsigned int buflen)
 {
         struct xdr_stream stream;
-        struct xdr_buf buf = {
-                .pages = xdr_pages,
-                .page_len = buflen,
-                .buflen = buflen,
-                .len = buflen,
-        };
+        struct xdr_buf buf;
         struct page *scratch;
         struct nfs_cache_array *array;
         unsigned int count = 0;
@@ -527,7 +522,7 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en
         if (scratch == NULL)
                 return -ENOMEM;
 
-        xdr_init_decode(&stream, &buf, NULL);
+        xdr_init_decode_pages(&stream, &buf, xdr_pages, buflen);
         xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
 
         do {
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 57bb31ad7a5e..144f2a3c7185 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -1298,8 +1298,12 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
                                 i_size_write(inode, new_isize);
                                 invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
                         }
-                        dprintk("NFS: isize change on server for file %s/%ld\n",
-                                        inode->i_sb->s_id, inode->i_ino);
+                        dprintk("NFS: isize change on server for file %s/%ld "
+                                        "(%Ld to %Ld)\n",
+                                        inode->i_sb->s_id,
+                                        inode->i_ino,
+                                        (long long)cur_isize,
+                                        (long long)new_isize);
                 }
         } else
                 invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
@@ -1424,9 +1428,10 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
  */
 void nfs4_evict_inode(struct inode *inode)
 {
-        pnfs_destroy_layout(NFS_I(inode));
         truncate_inode_pages(&inode->i_data, 0);
         end_writeback(inode);
+        pnfs_return_layout(inode);
+        pnfs_destroy_layout(NFS_I(inode));
         /* If we are holding a delegation, return it! */
         nfs_inode_return_delegation_noreclaim(inode);
         /* First call standard NFS clear_inode() code */
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 2df6ca7b5898..b9056cbe68d6 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -310,6 +310,7 @@ extern int nfs_migrate_page(struct address_space *,
 #endif
 
 /* nfs4proc.c */
+extern void __nfs4_read_done_cb(struct nfs_read_data *);
 extern void nfs4_reset_read(struct rpc_task *task, struct nfs_read_data *data);
 extern int nfs4_init_client(struct nfs_client *clp,
                             const struct rpc_timeout *timeparms,
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index be79dc9f386d..426908809c97 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -421,6 +421,7 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo,
                         struct nfs4_deviceid *id,
                         gfp_t gfp_flags)
 {
+        struct nfs4_deviceid_node *d;
         struct nfs4_file_layout_dsaddr *dsaddr;
         int status = -EINVAL;
         struct nfs_server *nfss = NFS_SERVER(lo->plh_inode);
@@ -428,7 +429,7 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo,
         dprintk("--> %s\n", __func__);
 
         if (fl->pattern_offset > lgr->range.offset) {
-                dprintk("%s pattern_offset %lld to large\n",
+                dprintk("%s pattern_offset %lld too large\n",
                                 __func__, fl->pattern_offset);
                 goto out;
         }
@@ -440,12 +441,14 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo,
         }
 
         /* find and reference the deviceid */
-        dsaddr = nfs4_fl_find_get_deviceid(id);
-        if (dsaddr == NULL) {
+        d = nfs4_find_get_deviceid(NFS_SERVER(lo->plh_inode)->pnfs_curr_ld,
+                                   NFS_SERVER(lo->plh_inode)->nfs_client, id);
+        if (d == NULL) {
                 dsaddr = get_device_info(lo->plh_inode, id, gfp_flags);
                 if (dsaddr == NULL)
                         goto out;
-        }
+        } else
+                dsaddr = container_of(d, struct nfs4_file_layout_dsaddr, id_node);
         fl->dsaddr = dsaddr;
 
         if (fl->first_stripe_index < 0 ||
@@ -507,12 +510,7 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
                          gfp_t gfp_flags)
 {
         struct xdr_stream stream;
-        struct xdr_buf buf = {
-                .pages =  lgr->layoutp->pages,
-                .page_len =  lgr->layoutp->len,
-                .buflen =  lgr->layoutp->len,
-                .len = lgr->layoutp->len,
-        };
+        struct xdr_buf buf;
         struct page *scratch;
         __be32 *p;
         uint32_t nfl_util;
@@ -524,7 +522,7 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
         if (!scratch)
                 return -ENOMEM;
 
-        xdr_init_decode(&stream, &buf, NULL);
+        xdr_init_decode_pages(&stream, &buf, lgr->layoutp->pages, lgr->layoutp->len);
         xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
 
         /* 20 = ufl_util (4), first_stripe_index (4), pattern_offset (8),
@@ -535,7 +533,7 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
 
         memcpy(id, p, sizeof(*id));
         p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE);
-        print_deviceid(id);
+        nfs4_print_deviceid(id);
 
         nfl_util = be32_to_cpup(p++);
         if (nfl_util & NFL4_UFLG_COMMIT_THRU_MDS)
@@ -653,16 +651,19 @@ filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid,
 /*
  * filelayout_pg_test(). Called by nfs_can_coalesce_requests()
  *
- * return 1 :  coalesce page
- * return 0 :  don't coalesce page
+ * return true  : coalesce page
+ * return false : don't coalesce page
  */
-int
+bool
 filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
                    struct nfs_page *req)
 {
         u64 p_stripe, r_stripe;
         u32 stripe_unit;
 
+        if (!pnfs_generic_pg_test(pgio, prev, req))
+                return 0;
+
         if (!pgio->pg_lseg)
                 return 1;
         p_stripe = (u64)prev->wb_index << PAGE_CACHE_SHIFT;
@@ -860,6 +861,12 @@ filelayout_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
         return -ENOMEM;
 }
 
+static void
+filelayout_free_deveiceid_node(struct nfs4_deviceid_node *d)
+{
+        nfs4_fl_free_deviceid(container_of(d, struct nfs4_file_layout_dsaddr, id_node));
+}
+
 static struct pnfs_layoutdriver_type filelayout_type = {
         .id                     = LAYOUT_NFSV4_1_FILES,
         .name                   = "LAYOUT_NFSV4_1_FILES",
@@ -872,6 +879,7 @@ static struct pnfs_layoutdriver_type filelayout_type = {
         .commit_pagelist        = filelayout_commit_pagelist,
         .read_pagelist          = filelayout_read_pagelist,
         .write_pagelist         = filelayout_write_pagelist,
+        .free_deviceid_node     = filelayout_free_deveiceid_node,
 };
 
 static int __init nfs4filelayout_init(void)
diff --git a/fs/nfs/nfs4filelayout.h b/fs/nfs/nfs4filelayout.h
index 2b461d77b43a..cebe01e3795e 100644
--- a/fs/nfs/nfs4filelayout.h
+++ b/fs/nfs/nfs4filelayout.h
@@ -59,9 +59,7 @@ struct nfs4_pnfs_ds {
 #define NFS4_DEVICE_ID_NEG_ENTRY        0x00000001
 
 struct nfs4_file_layout_dsaddr {
-        struct hlist_node               node;
-        struct nfs4_deviceid            deviceid;
-        atomic_t                        ref;
+        struct nfs4_deviceid_node       id_node;
         unsigned long                   flags;
         u32                             stripe_count;
         u8                              *stripe_indices;
@@ -95,14 +93,12 @@ extern struct nfs_fh *
 nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j);
 
 extern void print_ds(struct nfs4_pnfs_ds *ds);
-extern void print_deviceid(struct nfs4_deviceid *dev_id);
 u32 nfs4_fl_calc_j_index(struct pnfs_layout_segment *lseg, loff_t offset);
 u32 nfs4_fl_calc_ds_index(struct pnfs_layout_segment *lseg, u32 j);
 struct nfs4_pnfs_ds *nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg,
                                         u32 ds_idx);
-extern struct nfs4_file_layout_dsaddr *
-nfs4_fl_find_get_deviceid(struct nfs4_deviceid *dev_id);
 extern void nfs4_fl_put_deviceid(struct nfs4_file_layout_dsaddr *dsaddr);
+extern void nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr);
 struct nfs4_file_layout_dsaddr *
 get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id, gfp_t gfp_flags);
 
diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c
index db07c7af1395..3b7bf1377264 100644
--- a/fs/nfs/nfs4filelayoutdev.c
+++ b/fs/nfs/nfs4filelayoutdev.c
@@ -37,30 +37,6 @@
 #define NFSDBG_FACILITY         NFSDBG_PNFS_LD
 
 /*
- * Device ID RCU cache. A device ID is unique per client ID and layout type.
- */
-#define NFS4_FL_DEVICE_ID_HASH_BITS     5
-#define NFS4_FL_DEVICE_ID_HASH_SIZE     (1 << NFS4_FL_DEVICE_ID_HASH_BITS)
-#define NFS4_FL_DEVICE_ID_HASH_MASK     (NFS4_FL_DEVICE_ID_HASH_SIZE - 1)
-
-static inline u32
-nfs4_fl_deviceid_hash(struct nfs4_deviceid *id)
-{
-        unsigned char *cptr = (unsigned char *)id->data;
-        unsigned int nbytes = NFS4_DEVICEID4_SIZE;
-        u32 x = 0;
-
-        while (nbytes--) {
-                x *= 37;
-                x += *cptr++;
-        }
-        return x & NFS4_FL_DEVICE_ID_HASH_MASK;
-}
-
-static struct hlist_head filelayout_deviceid_cache[NFS4_FL_DEVICE_ID_HASH_SIZE];
-static DEFINE_SPINLOCK(filelayout_deviceid_lock);
-
-/*
  * Data server cache
  *
  * Data servers can be mapped to different device ids.
@@ -89,27 +65,6 @@ print_ds(struct nfs4_pnfs_ds *ds)
                 ds->ds_clp ? ds->ds_clp->cl_exchange_flags : 0);
 }
 
-void
-print_ds_list(struct nfs4_file_layout_dsaddr *dsaddr)
-{
-        int i;
-
-        ifdebug(FACILITY) {
-                printk("%s dsaddr->ds_num %d\n", __func__,
-                       dsaddr->ds_num);
-                for (i = 0; i < dsaddr->ds_num; i++)
-                        print_ds(dsaddr->ds_list[i]);
-        }
-}
-
-void print_deviceid(struct nfs4_deviceid *id)
-{
-        u32 *p = (u32 *)id;
-
-        dprintk("%s: device id= [%x%x%x%x]\n", __func__,
-                p[0], p[1], p[2], p[3]);
-}
-
 /* nfs4_ds_cache_lock is held */
 static struct nfs4_pnfs_ds *
 _data_server_lookup_locked(u32 ip_addr, u32 port)
@@ -201,13 +156,13 @@ destroy_ds(struct nfs4_pnfs_ds *ds)
         kfree(ds);
 }
 
-static void
+void
 nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
 {
         struct nfs4_pnfs_ds *ds;
         int i;
 
-        print_deviceid(&dsaddr->deviceid);
+        nfs4_print_deviceid(&dsaddr->id_node.deviceid);
 
         for (i = 0; i < dsaddr->ds_num; i++) {
                 ds = dsaddr->ds_list[i];
@@ -353,12 +308,7 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
         u8 max_stripe_index;
         struct nfs4_file_layout_dsaddr *dsaddr = NULL;
         struct xdr_stream stream;
-        struct xdr_buf buf = {
-                .pages = pdev->pages,
-                .page_len = pdev->pglen,
-                .buflen = pdev->pglen,
-                .len = pdev->pglen,
-        };
+        struct xdr_buf buf;
         struct page *scratch;
 
         /* set up xdr stream */
@@ -366,7 +316,7 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
         if (!scratch)
                 goto out_err;
 
-        xdr_init_decode(&stream, &buf, NULL);
+        xdr_init_decode_pages(&stream, &buf, pdev->pages, pdev->pglen);
         xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
 
         /* Get the stripe count (number of stripe index) */
@@ -431,8 +381,10 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
         dsaddr->stripe_indices = stripe_indices;
         stripe_indices = NULL;
         dsaddr->ds_num = num;
-
-        memcpy(&dsaddr->deviceid, &pdev->dev_id, sizeof(pdev->dev_id));
+        nfs4_init_deviceid_node(&dsaddr->id_node,
+                                NFS_SERVER(ino)->pnfs_curr_ld,
+                                NFS_SERVER(ino)->nfs_client,
+                                &pdev->dev_id);
 
         for (i = 0; i < dsaddr->ds_num; i++) {
                 int j;
@@ -505,8 +457,8 @@ out_err:
 static struct nfs4_file_layout_dsaddr *
 decode_and_add_device(struct inode *inode, struct pnfs_device *dev, gfp_t gfp_flags)
 {
-        struct nfs4_file_layout_dsaddr *d, *new;
-        long hash;
+        struct nfs4_deviceid_node *d;
+        struct nfs4_file_layout_dsaddr *n, *new;
 
         new = decode_device(inode, dev, gfp_flags);
         if (!new) {
@@ -515,20 +467,13 @@ decode_and_add_device(struct inode *inode, struct pnfs_device *dev, gfp_t gfp_fl
                 return NULL;
         }
 
-        spin_lock(&filelayout_deviceid_lock);
-        d = nfs4_fl_find_get_deviceid(&new->deviceid);
-        if (d) {
-                spin_unlock(&filelayout_deviceid_lock);
+        d = nfs4_insert_deviceid_node(&new->id_node);
+        n = container_of(d, struct nfs4_file_layout_dsaddr, id_node);
+        if (n != new) {
                 nfs4_fl_free_deviceid(new);
-                return d;
+                return n;
         }
 
-        INIT_HLIST_NODE(&new->node);
-        atomic_set(&new->ref, 1);
-        hash = nfs4_fl_deviceid_hash(&new->deviceid);
-        hlist_add_head_rcu(&new->node, &filelayout_deviceid_cache[hash]);
-        spin_unlock(&filelayout_deviceid_lock);
-
         return new;
 }
 
@@ -600,35 +545,7 @@ out_free:
 void
 nfs4_fl_put_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
 {
-        if (atomic_dec_and_lock(&dsaddr->ref, &filelayout_deviceid_lock)) {
-                hlist_del_rcu(&dsaddr->node);
-                spin_unlock(&filelayout_deviceid_lock);
-
-                synchronize_rcu();
-                nfs4_fl_free_deviceid(dsaddr);
-        }
-}
-
-struct nfs4_file_layout_dsaddr *
-nfs4_fl_find_get_deviceid(struct nfs4_deviceid *id)
-{
-        struct nfs4_file_layout_dsaddr *d;
-        struct hlist_node *n;
-        long hash = nfs4_fl_deviceid_hash(id);
-
-
-        rcu_read_lock();
-        hlist_for_each_entry_rcu(d, n, &filelayout_deviceid_cache[hash], node) {
-                if (!memcmp(&d->deviceid, id, sizeof(*id))) {
-                        if (!atomic_inc_not_zero(&d->ref))
-                                goto fail;
-                        rcu_read_unlock();
-                        return d;
-                }
-        }
-fail:
-        rcu_read_unlock();
-        return NULL;
+        nfs4_put_deviceid_node(&dsaddr->id_node);
 }
 
 /*
@@ -676,15 +593,15 @@ static void
 filelayout_mark_devid_negative(struct nfs4_file_layout_dsaddr *dsaddr,
                                int err, u32 ds_addr)
 {
-        u32 *p = (u32 *)&dsaddr->deviceid;
+        u32 *p = (u32 *)&dsaddr->id_node.deviceid;
 
         printk(KERN_ERR "NFS: data server %x connection error %d."
                 " Deviceid [%x%x%x%x] marked out of use.\n",
                 ds_addr, err, p[0], p[1], p[2], p[3]);
 
-        spin_lock(&filelayout_deviceid_lock);
+        spin_lock(&nfs4_ds_cache_lock);
         dsaddr->flags |= NFS4_DEVICE_ID_NEG_ENTRY;
-        spin_unlock(&filelayout_deviceid_lock);
+        spin_unlock(&nfs4_ds_cache_lock);
 }
 
 struct nfs4_pnfs_ds *
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index cf1b339c3937..d2c4b59c896d 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -267,9 +267,11 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc
                                 break;
                         nfs4_schedule_stateid_recovery(server, state);
                         goto wait_on_recovery;
+                case -NFS4ERR_EXPIRED:
+                        if (state != NULL)
+                                nfs4_schedule_stateid_recovery(server, state);
                 case -NFS4ERR_STALE_STATEID:
                 case -NFS4ERR_STALE_CLIENTID:
-                case -NFS4ERR_EXPIRED:
                         nfs4_schedule_lease_recovery(clp);
                         goto wait_on_recovery;
 #if defined(CONFIG_NFS_V4_1)
@@ -2361,6 +2363,9 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
         struct nfs4_state *state = NULL;
         int status;
 
+        if (pnfs_ld_layoutret_on_setattr(inode))
+                pnfs_return_layout(inode);
+
         nfs_fattr_init(fattr);
         
         /* Search for an existing open(O_WRITE) file */
@@ -3175,6 +3180,11 @@ static int nfs4_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle,
         return err;
 }
 
+void __nfs4_read_done_cb(struct nfs_read_data *data)
+{
+        nfs_invalidate_atime(data->inode);
+}
+
 static int nfs4_read_done_cb(struct rpc_task *task, struct nfs_read_data *data)
 {
         struct nfs_server *server = NFS_SERVER(data->inode);
@@ -3184,7 +3194,7 @@ static int nfs4_read_done_cb(struct rpc_task *task, struct nfs_read_data *data)
                 return -EAGAIN;
         }
 
-        nfs_invalidate_atime(data->inode);
+        __nfs4_read_done_cb(data);
         if (task->tk_status > 0)
                 renew_lease(server, data->timestamp);
         return 0;
@@ -3198,7 +3208,8 @@ static int nfs4_read_done(struct rpc_task *task, struct nfs_read_data *data)
         if (!nfs4_sequence_done(task, &data->res.seq_res))
                 return -EAGAIN;
 
-        return data->read_done_cb(task, data);
+        return data->read_done_cb ? data->read_done_cb(task, data) :
+                                    nfs4_read_done_cb(task, data);
 }
 
 static void nfs4_proc_read_setup(struct nfs_read_data *data, struct rpc_message *msg)
@@ -3243,7 +3254,8 @@ static int nfs4_write_done(struct rpc_task *task, struct nfs_write_data *data)
 {
         if (!nfs4_sequence_done(task, &data->res.seq_res))
                 return -EAGAIN;
-        return data->write_done_cb(task, data);
+        return data->write_done_cb ? data->write_done_cb(task, data) :
+                nfs4_write_done_cb(task, data);
 }
 
 /* Reset the the nfs_write_data to send the write to the MDS. */
@@ -3670,9 +3682,11 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
                                 break;
                         nfs4_schedule_stateid_recovery(server, state);
                         goto wait_on_recovery;
+                case -NFS4ERR_EXPIRED:
+                        if (state != NULL)
+                                nfs4_schedule_stateid_recovery(server, state);
                 case -NFS4ERR_STALE_STATEID:
                 case -NFS4ERR_STALE_CLIENTID:
-                case -NFS4ERR_EXPIRED:
                         nfs4_schedule_lease_recovery(clp);
                         goto wait_on_recovery;
 #if defined(CONFIG_NFS_V4_1)
@@ -4543,6 +4557,7 @@ int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl)
                         case -ESTALE:
                                 goto out;
                         case -NFS4ERR_EXPIRED:
+                                nfs4_schedule_stateid_recovery(server, state);
                         case -NFS4ERR_STALE_CLIENTID:
                         case -NFS4ERR_STALE_STATEID:
                                 nfs4_schedule_lease_recovery(server->nfs_client);
@@ -5666,6 +5681,88 @@ int nfs4_proc_layoutget(struct nfs4_layoutget *lgp)
         return status;
 }
 
+static void
+nfs4_layoutreturn_prepare(struct rpc_task *task, void *calldata)
+{
+        struct nfs4_layoutreturn *lrp = calldata;
+
+        dprintk("--> %s\n", __func__);
+        if (nfs41_setup_sequence(lrp->clp->cl_session, &lrp->args.seq_args,
+                                &lrp->res.seq_res, 0, task))
+                return;
+        rpc_call_start(task);
+}
+
+static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata)
+{
+        struct nfs4_layoutreturn *lrp = calldata;
+        struct nfs_server *server;
+
+        dprintk("--> %s\n", __func__);
+
+        if (!nfs4_sequence_done(task, &lrp->res.seq_res))
+                return;
+
+        server = NFS_SERVER(lrp->args.inode);
+        if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN) {
+                nfs_restart_rpc(task, lrp->clp);
+                return;
+        }
+        if (task->tk_status == 0) {
+                struct pnfs_layout_hdr *lo = NFS_I(lrp->args.inode)->layout;
+
+                if (lrp->res.lrs_present) {
+                        spin_lock(&lo->plh_inode->i_lock);
+                        pnfs_set_layout_stateid(lo, &lrp->res.stateid, true);
+                        spin_unlock(&lo->plh_inode->i_lock);
+                } else
+                        BUG_ON(!list_empty(&lo->plh_segs));
+        }
+        dprintk("<-- %s\n", __func__);
+}
+
+static void nfs4_layoutreturn_release(void *calldata)
+{
+        struct nfs4_layoutreturn *lrp = calldata;
+
+        dprintk("--> %s\n", __func__);
+        put_layout_hdr(NFS_I(lrp->args.inode)->layout);
+        kfree(calldata);
+        dprintk("<-- %s\n", __func__);
+}
+
+static const struct rpc_call_ops nfs4_layoutreturn_call_ops = {
+        .rpc_call_prepare = nfs4_layoutreturn_prepare,
+        .rpc_call_done = nfs4_layoutreturn_done,
+        .rpc_release = nfs4_layoutreturn_release,
+};
+
+int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp)
+{
+        struct rpc_task *task;
+        struct rpc_message msg = {
+                .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LAYOUTRETURN],
+                .rpc_argp = &lrp->args,
+                .rpc_resp = &lrp->res,
+        };
+        struct rpc_task_setup task_setup_data = {
+                .rpc_client = lrp->clp->cl_rpcclient,
+                .rpc_message = &msg,
+                .callback_ops = &nfs4_layoutreturn_call_ops,
+                .callback_data = lrp,
+        };
+        int status;
+
+        dprintk("--> %s\n", __func__);
+        task = rpc_run_task(&task_setup_data);
+        if (IS_ERR(task))
+                return PTR_ERR(task);
+        status = task->tk_status;
+        dprintk("<-- %s status=%d\n", __func__, status);
+        rpc_put_task(task);
+        return status;
+}
+
 static int
 _nfs4_proc_getdeviceinfo(struct nfs_server *server, struct pnfs_device *pdev)
 {
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 036f5adc9e1f..e97dd219f84f 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1466,7 +1466,10 @@ static int nfs4_reclaim_lease(struct nfs_client *clp)
 #ifdef CONFIG_NFS_V4_1
 void nfs4_schedule_session_recovery(struct nfs4_session *session)
 {
-        nfs4_schedule_lease_recovery(session->clp);
+        struct nfs_client *clp = session->clp;
+
+        set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
+        nfs4_schedule_lease_recovery(clp);
 }
 EXPORT_SYMBOL_GPL(nfs4_schedule_session_recovery);
 
@@ -1549,6 +1552,7 @@ static int nfs4_reset_session(struct nfs_client *clp)
                 status = nfs4_recovery_handle_error(clp, status);
                 goto out;
         }
+        clear_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
         /* create_session negotiated new slot table */
         clear_bit(NFS4CLNT_RECALL_SLOT, &clp->cl_state);
 
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index c3ccd2c46834..d869a5e5464b 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -338,7 +338,11 @@ static int nfs4_stat_to_errno(int);
                                 1 /* layoutupdate4 layout type */ + \
                                 1 /* NULL filelayout layoutupdate4 payload */)
 #define decode_layoutcommit_maxsz (op_decode_hdr_maxsz + 3)
-
+#define encode_layoutreturn_maxsz (8 + op_encode_hdr_maxsz + \
+                                encode_stateid_maxsz + \
+                                1 /* FIXME: opaque lrf_body always empty at the moment */)
+#define decode_layoutreturn_maxsz (op_decode_hdr_maxsz + \
+                                1 + decode_stateid_maxsz)
 #else /* CONFIG_NFS_V4_1 */
 #define encode_sequence_maxsz   0
 #define decode_sequence_maxsz   0
@@ -760,7 +764,14 @@ static int nfs4_stat_to_errno(int);
                                 decode_putfh_maxsz + \
                                 decode_layoutcommit_maxsz + \
                                 decode_getattr_maxsz)
-
+#define NFS4_enc_layoutreturn_sz (compound_encode_hdr_maxsz + \
+                                encode_sequence_maxsz + \
+                                encode_putfh_maxsz + \
+                                encode_layoutreturn_maxsz)
+#define NFS4_dec_layoutreturn_sz (compound_decode_hdr_maxsz + \
+                                decode_sequence_maxsz + \
+                                decode_putfh_maxsz + \
+                                decode_layoutreturn_maxsz)
 
 const u32 nfs41_maxwrite_overhead = ((RPC_MAX_HEADER_WITH_AUTH +
                                       compound_encode_hdr_maxsz +
@@ -1864,6 +1875,7 @@ encode_layoutget(struct xdr_stream *xdr,
 
 static int
 encode_layoutcommit(struct xdr_stream *xdr,
+                    struct inode *inode,
                     const struct nfs4_layoutcommit_args *args,
                     struct compound_hdr *hdr)
 {
@@ -1872,7 +1884,7 @@ encode_layoutcommit(struct xdr_stream *xdr,
         dprintk("%s: lbw: %llu type: %d\n", __func__, args->lastbytewritten,
                 NFS_SERVER(args->inode)->pnfs_curr_ld->id);
 
-        p = reserve_space(xdr, 48 + NFS4_STATEID_SIZE);
+        p = reserve_space(xdr, 44 + NFS4_STATEID_SIZE);
         *p++ = cpu_to_be32(OP_LAYOUTCOMMIT);
         /* Only whole file layouts */
         p = xdr_encode_hyper(p, 0); /* offset */
@@ -1883,12 +1895,49 @@ encode_layoutcommit(struct xdr_stream *xdr,
         p = xdr_encode_hyper(p, args->lastbytewritten);
         *p++ = cpu_to_be32(0); /* Never send time_modify_changed */
         *p++ = cpu_to_be32(NFS_SERVER(args->inode)->pnfs_curr_ld->id);/* type */
-        *p++ = cpu_to_be32(0); /* no file layout payload */
+
+        if (NFS_SERVER(inode)->pnfs_curr_ld->encode_layoutcommit)
+                NFS_SERVER(inode)->pnfs_curr_ld->encode_layoutcommit(
+                        NFS_I(inode)->layout, xdr, args);
+        else {
+                p = reserve_space(xdr, 4);
+                *p = cpu_to_be32(0); /* no layout-type payload */
+        }
 
         hdr->nops++;
         hdr->replen += decode_layoutcommit_maxsz;
         return 0;
 }
+
+static void
+encode_layoutreturn(struct xdr_stream *xdr,
+                    const struct nfs4_layoutreturn_args *args,
+                    struct compound_hdr *hdr)
+{
+        __be32 *p;
+
+        p = reserve_space(xdr, 20);
+        *p++ = cpu_to_be32(OP_LAYOUTRETURN);
+        *p++ = cpu_to_be32(0);          /* reclaim. always 0 for now */
+        *p++ = cpu_to_be32(args->layout_type);
+        *p++ = cpu_to_be32(IOMODE_ANY);
+        *p = cpu_to_be32(RETURN_FILE);
+        p = reserve_space(xdr, 16 + NFS4_STATEID_SIZE);
+        p = xdr_encode_hyper(p, 0);
+        p = xdr_encode_hyper(p, NFS4_MAX_UINT64);
+        spin_lock(&args->inode->i_lock);
+        xdr_encode_opaque_fixed(p, &args->stateid.data, NFS4_STATEID_SIZE);
+        spin_unlock(&args->inode->i_lock);
+        if (NFS_SERVER(args->inode)->pnfs_curr_ld->encode_layoutreturn) {
+                NFS_SERVER(args->inode)->pnfs_curr_ld->encode_layoutreturn(
+                        NFS_I(args->inode)->layout, xdr, args);
+        } else {
+                p = reserve_space(xdr, 4);
+                *p = cpu_to_be32(0);
+        }
+        hdr->nops++;
+        hdr->replen += decode_layoutreturn_maxsz;
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 /*
@@ -2706,10 +2755,12 @@ static void nfs4_xdr_enc_layoutget(struct rpc_rqst *req,
 /*
  *  Encode LAYOUTCOMMIT request
  */
-static int nfs4_xdr_enc_layoutcommit(struct rpc_rqst *req,
-                                     struct xdr_stream *xdr,
-                                     struct nfs4_layoutcommit_args *args)
+static void nfs4_xdr_enc_layoutcommit(struct rpc_rqst *req,
+                                      struct xdr_stream *xdr,
+                                      struct nfs4_layoutcommit_args *args)
 {
+        struct nfs4_layoutcommit_data *data =
+                container_of(args, struct nfs4_layoutcommit_data, args);
         struct compound_hdr hdr = {
                 .minorversion = nfs4_xdr_minorversion(&args->seq_args),
         };
@@ -2717,10 +2768,27 @@ static int nfs4_xdr_enc_layoutcommit(struct rpc_rqst *req,
         encode_compound_hdr(xdr, req, &hdr);
         encode_sequence(xdr, &args->seq_args, &hdr);
         encode_putfh(xdr, NFS_FH(args->inode), &hdr);
-        encode_layoutcommit(xdr, args, &hdr);
+        encode_layoutcommit(xdr, data->args.inode, args, &hdr);
         encode_getfattr(xdr, args->bitmask, &hdr);
         encode_nops(&hdr);
-        return 0;
+}
+
+/*
+ * Encode LAYOUTRETURN request
+ */
+static void nfs4_xdr_enc_layoutreturn(struct rpc_rqst *req,
+                                      struct xdr_stream *xdr,
+                                      struct nfs4_layoutreturn_args *args)
+{
+        struct compound_hdr hdr = {
+                .minorversion = nfs4_xdr_minorversion(&args->seq_args),
+        };
+
+        encode_compound_hdr(xdr, req, &hdr);
+        encode_sequence(xdr, &args->seq_args, &hdr);
+        encode_putfh(xdr, NFS_FH(args->inode), &hdr);
+        encode_layoutreturn(xdr, args, &hdr);
+        encode_nops(&hdr);
 }
 #endif /* CONFIG_NFS_V4_1 */
 
@@ -5203,6 +5271,27 @@ out_overflow:
         return -EIO;
 }
 
+static int decode_layoutreturn(struct xdr_stream *xdr,
+                               struct nfs4_layoutreturn_res *res)
+{
+        __be32 *p;
+        int status;
+
+        status = decode_op_hdr(xdr, OP_LAYOUTRETURN);
+        if (status)
+                return status;
+        p = xdr_inline_decode(xdr, 4);
+        if (unlikely(!p))
+                goto out_overflow;
+        res->lrs_present = be32_to_cpup(p);
+        if (res->lrs_present)
+                status = decode_stateid(xdr, &res->stateid);
+        return status;
+out_overflow:
+        print_overflow_msg(__func__, xdr);
+        return -EIO;
+}
+
 static int decode_layoutcommit(struct xdr_stream *xdr,
                                struct rpc_rqst *req,
                                struct nfs4_layoutcommit_res *res)
@@ -6320,6 +6409,30 @@ out:
 }
 
 /*
+ * Decode LAYOUTRETURN response
+ */
+static int nfs4_xdr_dec_layoutreturn(struct rpc_rqst *rqstp,
+                                     struct xdr_stream *xdr,
+                                     struct nfs4_layoutreturn_res *res)
+{
+        struct compound_hdr hdr;
+        int status;
+
+        status = decode_compound_hdr(xdr, &hdr);
+        if (status)
+                goto out;
+        status = decode_sequence(xdr, &res->seq_res, rqstp);
+        if (status)
+                goto out;
+        status = decode_putfh(xdr);
+        if (status)
+                goto out;
+        status = decode_layoutreturn(xdr, res);
+out:
+        return status;
+}
+
+/*
  * Decode LAYOUTCOMMIT response
  */
 static int nfs4_xdr_dec_layoutcommit(struct rpc_rqst *rqstp,
@@ -6547,6 +6660,7 @@ struct rpc_procinfo	nfs4_procedures[] = {
         PROC(GETDEVICEINFO,     enc_getdeviceinfo,      dec_getdeviceinfo),
         PROC(LAYOUTGET,         enc_layoutget,          dec_layoutget),
         PROC(LAYOUTCOMMIT,      enc_layoutcommit,       dec_layoutcommit),
+        PROC(LAYOUTRETURN,      enc_layoutreturn,       dec_layoutreturn),
 #endif /* CONFIG_NFS_V4_1 */
 };
 
diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c
index c541093a5bf2..c4744e1d513c 100644
--- a/fs/nfs/nfsroot.c
+++ b/fs/nfs/nfsroot.c
@@ -87,7 +87,7 @@
 #define NFS_ROOT                "/tftpboot/%s"
 
 /* Default NFSROOT mount options. */
-#define NFS_DEF_OPTIONS         "udp"
+#define NFS_DEF_OPTIONS         "vers=2,udp,rsize=4096,wsize=4096"
 
 /* Parameters passed from the kernel command line */
 static char nfs_root_parms[256] __initdata = "";
diff --git a/fs/nfs/objlayout/Kbuild b/fs/nfs/objlayout/Kbuild
new file mode 100644
index 000000000000..ed30ea072bb8
--- /dev/null
+++ b/fs/nfs/objlayout/Kbuild
@@ -0,0 +1,5 @@
+#
+# Makefile for the pNFS Objects Layout Driver kernel module
+#
+objlayoutdriver-y := objio_osd.o pnfs_osd_xdr_cli.o objlayout.o
+obj-$(CONFIG_PNFS_OBJLAYOUT) += objlayoutdriver.o
diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
new file mode 100644
index 000000000000..9cf208df1f25
--- /dev/null
+++ b/fs/nfs/objlayout/objio_osd.c
@@ -0,0 +1,1057 @@
+/*
+ *  pNFS Objects layout implementation over open-osd initiator library
+ *
+ *  Copyright (C) 2009 Panasas Inc. [year of first publication]
+ *  All rights reserved.
+ *
+ *  Benny Halevy <bhalevy@panasas.com>
+ *  Boaz Harrosh <bharrosh@panasas.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  See the file COPYING included with this distribution for more details.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *  1. Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *  2. Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in the
+ *     documentation and/or other materials provided with the distribution.
+ *  3. Neither the name of the Panasas company nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/module.h>
+#include <scsi/osd_initiator.h>
+
+#include "objlayout.h"
+
+#define NFSDBG_FACILITY         NFSDBG_PNFS_LD
+
+#define _LLU(x) ((unsigned long long)x)
+
+enum { BIO_MAX_PAGES_KMALLOC =
+                (PAGE_SIZE - sizeof(struct bio)) / sizeof(struct bio_vec),
+};
+
+struct objio_dev_ent {
+        struct nfs4_deviceid_node id_node;
+        struct osd_dev *od;
+};
+
+static void
+objio_free_deviceid_node(struct nfs4_deviceid_node *d)
+{
+        struct objio_dev_ent *de = container_of(d, struct objio_dev_ent, id_node);
+
+        dprintk("%s: free od=%p\n", __func__, de->od);
+        osduld_put_device(de->od);
+        kfree(de);
+}
+
+static struct objio_dev_ent *_dev_list_find(const struct nfs_server *nfss,
+        const struct nfs4_deviceid *d_id)
+{
+        struct nfs4_deviceid_node *d;
+        struct objio_dev_ent *de;
+
+        d = nfs4_find_get_deviceid(nfss->pnfs_curr_ld, nfss->nfs_client, d_id);
+        if (!d)
+                return NULL;
+
+        de = container_of(d, struct objio_dev_ent, id_node);
+        return de;
+}
+
+static struct objio_dev_ent *
+_dev_list_add(const struct nfs_server *nfss,
+        const struct nfs4_deviceid *d_id, struct osd_dev *od,
+        gfp_t gfp_flags)
+{
+        struct nfs4_deviceid_node *d;
+        struct objio_dev_ent *de = kzalloc(sizeof(*de), gfp_flags);
+        struct objio_dev_ent *n;
+
+        if (!de) {
+                dprintk("%s: -ENOMEM od=%p\n", __func__, od);
+                return NULL;
+        }
+
+        dprintk("%s: Adding od=%p\n", __func__, od);
+        nfs4_init_deviceid_node(&de->id_node,
+                                nfss->pnfs_curr_ld,
+                                nfss->nfs_client,
+                                d_id);
+        de->od = od;
+
+        d = nfs4_insert_deviceid_node(&de->id_node);
+        n = container_of(d, struct objio_dev_ent, id_node);
+        if (n != de) {
+                dprintk("%s: Race with other n->od=%p\n", __func__, n->od);
+                objio_free_deviceid_node(&de->id_node);
+                de = n;
+        }
+
+        atomic_inc(&de->id_node.ref);
+        return de;
+}
+
+struct caps_buffers {
+        u8 caps_key[OSD_CRYPTO_KEYID_SIZE];
+        u8 creds[OSD_CAP_LEN];
+};
+
+struct objio_segment {
+        struct pnfs_layout_segment lseg;
+
+        struct pnfs_osd_object_cred *comps;
+
+        unsigned mirrors_p1;
+        unsigned stripe_unit;
+        unsigned group_width;   /* Data stripe_units without integrity comps */
+        u64 group_depth;
+        unsigned group_count;
+
+        unsigned max_io_size;
+
+        unsigned comps_index;
+        unsigned num_comps;
+        /* variable length */
+        struct objio_dev_ent *ods[];
+};
+
+static inline struct objio_segment *
+OBJIO_LSEG(struct pnfs_layout_segment *lseg)
+{
+        return container_of(lseg, struct objio_segment, lseg);
+}
+
+struct objio_state;
+typedef ssize_t (*objio_done_fn)(struct objio_state *ios);
+
+struct objio_state {
+        /* Generic layer */
+        struct objlayout_io_state ol_state;
+
+        struct objio_segment *layout;
+
+        struct kref kref;
+        objio_done_fn done;
+        void *private;
+
+        unsigned long length;
+        unsigned numdevs; /* Actually used devs in this IO */
+        /* A per-device variable array of size numdevs */
+        struct _objio_per_comp {
+                struct bio *bio;
+                struct osd_request *or;
+                unsigned long length;
+                u64 offset;
+                unsigned dev;
+        } per_dev[];
+};
+
+/* Send and wait for a get_device_info of devices in the layout,
+   then look them up with the osd_initiator library */
+static struct objio_dev_ent *_device_lookup(struct pnfs_layout_hdr *pnfslay,
+                                struct objio_segment *objio_seg, unsigned comp,
+                                gfp_t gfp_flags)
+{
+        struct pnfs_osd_deviceaddr *deviceaddr;
+        struct nfs4_deviceid *d_id;
+        struct objio_dev_ent *ode;
+        struct osd_dev *od;
+        struct osd_dev_info odi;
+        int err;
+
+        d_id = &objio_seg->comps[comp].oc_object_id.oid_device_id;
+
+        ode = _dev_list_find(NFS_SERVER(pnfslay->plh_inode), d_id);
+        if (ode)
+                return ode;
+
+        err = objlayout_get_deviceinfo(pnfslay, d_id, &deviceaddr, gfp_flags);
+        if (unlikely(err)) {
+                dprintk("%s: objlayout_get_deviceinfo dev(%llx:%llx) =>%d\n",
+                        __func__, _DEVID_LO(d_id), _DEVID_HI(d_id), err);
+                return ERR_PTR(err);
+        }
+
+        odi.systemid_len = deviceaddr->oda_systemid.len;
+        if (odi.systemid_len > sizeof(odi.systemid)) {
+                err = -EINVAL;
+                goto out;
+        } else if (odi.systemid_len)
+                memcpy(odi.systemid, deviceaddr->oda_systemid.data,
+                       odi.systemid_len);
+        odi.osdname_len  = deviceaddr->oda_osdname.len;
+        odi.osdname      = (u8 *)deviceaddr->oda_osdname.data;
+
+        if (!odi.osdname_len && !odi.systemid_len) {
+                dprintk("%s: !odi.osdname_len && !odi.systemid_len\n",
+                        __func__);
+                err = -ENODEV;
+                goto out;
+        }
+
+        od = osduld_info_lookup(&odi);
+        if (unlikely(IS_ERR(od))) {
+                err = PTR_ERR(od);
+                dprintk("%s: osduld_info_lookup => %d\n", __func__, err);
+                goto out;
+        }
+
+        ode = _dev_list_add(NFS_SERVER(pnfslay->plh_inode), d_id, od,
+                            gfp_flags);
+
+out:
+        dprintk("%s: return=%d\n", __func__, err);
+        objlayout_put_deviceinfo(deviceaddr);
+        return err ? ERR_PTR(err) : ode;
+}
+
+static int objio_devices_lookup(struct pnfs_layout_hdr *pnfslay,
+        struct objio_segment *objio_seg,
+        gfp_t gfp_flags)
+{
+        unsigned i;
+        int err;
+
+        /* lookup all devices */
+        for (i = 0; i < objio_seg->num_comps; i++) {
+                struct objio_dev_ent *ode;
+
+                ode = _device_lookup(pnfslay, objio_seg, i, gfp_flags);
+                if (unlikely(IS_ERR(ode))) {
+                        err = PTR_ERR(ode);
+                        goto out;
+                }
+                objio_seg->ods[i] = ode;
+        }
+        err = 0;
+
+out:
+        dprintk("%s: return=%d\n", __func__, err);
+        return err;
+}
+
+static int _verify_data_map(struct pnfs_osd_layout *layout)
+{
+        struct pnfs_osd_data_map *data_map = &layout->olo_map;
+        u64 stripe_length;
+        u32 group_width;
+
+/* FIXME: Only raid0 for now. if not go through MDS */
+        if (data_map->odm_raid_algorithm != PNFS_OSD_RAID_0) {
+                printk(KERN_ERR "Only RAID_0 for now\n");
+                return -ENOTSUPP;
+        }
+        if (0 != (data_map->odm_num_comps % (data_map->odm_mirror_cnt + 1))) {
+                printk(KERN_ERR "Data Map wrong, num_comps=%u mirrors=%u\n",
+                          data_map->odm_num_comps, data_map->odm_mirror_cnt);
+                return -EINVAL;
+        }
+
+        if (data_map->odm_group_width)
+                group_width = data_map->odm_group_width;
+        else
+                group_width = data_map->odm_num_comps /
+                                                (data_map->odm_mirror_cnt + 1);
+
+        stripe_length = (u64)data_map->odm_stripe_unit * group_width;
+        if (stripe_length >= (1ULL << 32)) {
+                printk(KERN_ERR "Total Stripe length(0x%llx)"
+                          " >= 32bit is not supported\n", _LLU(stripe_length));
+                return -ENOTSUPP;
+        }
+
+        if (0 != (data_map->odm_stripe_unit & ~PAGE_MASK)) {
+                printk(KERN_ERR "Stripe Unit(0x%llx)"
+                          " must be Multples of PAGE_SIZE(0x%lx)\n",
+                          _LLU(data_map->odm_stripe_unit), PAGE_SIZE);
+                return -ENOTSUPP;
+        }
+
+        return 0;
+}
+
+static void copy_single_comp(struct pnfs_osd_object_cred *cur_comp,
+                             struct pnfs_osd_object_cred *src_comp,
+                             struct caps_buffers *caps_p)
+{
+        WARN_ON(src_comp->oc_cap_key.cred_len > sizeof(caps_p->caps_key));
+        WARN_ON(src_comp->oc_cap.cred_len > sizeof(caps_p->creds));
+
+        *cur_comp = *src_comp;
+
+        memcpy(caps_p->caps_key, src_comp->oc_cap_key.cred,
+               sizeof(caps_p->caps_key));
+        cur_comp->oc_cap_key.cred = caps_p->caps_key;
+
+        memcpy(caps_p->creds, src_comp->oc_cap.cred,
+               sizeof(caps_p->creds));
+        cur_comp->oc_cap.cred = caps_p->creds;
+}
+
+int objio_alloc_lseg(struct pnfs_layout_segment **outp,
+        struct pnfs_layout_hdr *pnfslay,
+        struct pnfs_layout_range *range,
+        struct xdr_stream *xdr,
+        gfp_t gfp_flags)
+{
+        struct objio_segment *objio_seg;
+        struct pnfs_osd_xdr_decode_layout_iter iter;
+        struct pnfs_osd_layout layout;
+        struct pnfs_osd_object_cred *cur_comp, src_comp;
+        struct caps_buffers *caps_p;
+        int err;
+
+        err = pnfs_osd_xdr_decode_layout_map(&layout, &iter, xdr);
+        if (unlikely(err))
+                return err;
+
+        err = _verify_data_map(&layout);
+        if (unlikely(err))
+                return err;
+
+        objio_seg = kzalloc(sizeof(*objio_seg) +
+                            sizeof(objio_seg->ods[0]) * layout.olo_num_comps +
+                            sizeof(*objio_seg->comps) * layout.olo_num_comps +
+                            sizeof(struct caps_buffers) * layout.olo_num_comps,
+                            gfp_flags);
+        if (!objio_seg)
+                return -ENOMEM;
+
+        objio_seg->comps = (void *)(objio_seg->ods + layout.olo_num_comps);
+        cur_comp = objio_seg->comps;
+        caps_p = (void *)(cur_comp + layout.olo_num_comps);
+        while (pnfs_osd_xdr_decode_layout_comp(&src_comp, &iter, xdr, &err))
+                copy_single_comp(cur_comp++, &src_comp, caps_p++);
+        if (unlikely(err))
+                goto err;
+
+        objio_seg->num_comps = layout.olo_num_comps;
+        objio_seg->comps_index = layout.olo_comps_index;
+        err = objio_devices_lookup(pnfslay, objio_seg, gfp_flags);
+        if (err)
+                goto err;
+
+        objio_seg->mirrors_p1 = layout.olo_map.odm_mirror_cnt + 1;
+        objio_seg->stripe_unit = layout.olo_map.odm_stripe_unit;
+        if (layout.olo_map.odm_group_width) {
+                objio_seg->group_width = layout.olo_map.odm_group_width;
+                objio_seg->group_depth = layout.olo_map.odm_group_depth;
+                objio_seg->group_count = layout.olo_map.odm_num_comps /
+                                                objio_seg->mirrors_p1 /
+                                                objio_seg->group_width;
+        } else {
+                objio_seg->group_width = layout.olo_map.odm_num_comps /
+                                                objio_seg->mirrors_p1;
+                objio_seg->group_depth = -1;
+                objio_seg->group_count = 1;
+        }
+
+        /* Cache this calculation it will hit for every page */
+        objio_seg->max_io_size = (BIO_MAX_PAGES_KMALLOC * PAGE_SIZE -
+                                  objio_seg->stripe_unit) *
+                                 objio_seg->group_width;
+
+        *outp = &objio_seg->lseg;
+        return 0;
+
+err:
+        kfree(objio_seg);
+        dprintk("%s: Error: return %d\n", __func__, err);
+        *outp = NULL;
+        return err;
+}
+
+void objio_free_lseg(struct pnfs_layout_segment *lseg)
+{
+        int i;
+        struct objio_segment *objio_seg = OBJIO_LSEG(lseg);
+
+        for (i = 0; i < objio_seg->num_comps; i++) {
+                if (!objio_seg->ods[i])
+                        break;
+                nfs4_put_deviceid_node(&objio_seg->ods[i]->id_node);
+        }
+        kfree(objio_seg);
+}
+
+int objio_alloc_io_state(struct pnfs_layout_segment *lseg,
+                         struct objlayout_io_state **outp,
+                         gfp_t gfp_flags)
+{
+        struct objio_segment *objio_seg = OBJIO_LSEG(lseg);
+        struct objio_state *ios;
+        const unsigned first_size = sizeof(*ios) +
+                                objio_seg->num_comps * sizeof(ios->per_dev[0]);
+        const unsigned sec_size = objio_seg->num_comps *
+                                                sizeof(ios->ol_state.ioerrs[0]);
+
+        ios = kzalloc(first_size + sec_size, gfp_flags);
+        if (unlikely(!ios))
+                return -ENOMEM;
+
+        ios->layout = objio_seg;
+        ios->ol_state.ioerrs = ((void *)ios) + first_size;
+        ios->ol_state.num_comps = objio_seg->num_comps;
+
+        *outp = &ios->ol_state;
+        return 0;
+}
+
+void objio_free_io_state(struct objlayout_io_state *ol_state)
+{
+        struct objio_state *ios = container_of(ol_state, struct objio_state,
+                                               ol_state);
+
+        kfree(ios);
+}
+
+enum pnfs_osd_errno osd_pri_2_pnfs_err(enum osd_err_priority oep)
+{
+        switch (oep) {
+        case OSD_ERR_PRI_NO_ERROR:
+                return (enum pnfs_osd_errno)0;
+
+        case OSD_ERR_PRI_CLEAR_PAGES:
+                BUG_ON(1);
+                return 0;
+
+        case OSD_ERR_PRI_RESOURCE:
+                return PNFS_OSD_ERR_RESOURCE;
+        case OSD_ERR_PRI_BAD_CRED:
+                return PNFS_OSD_ERR_BAD_CRED;
+        case OSD_ERR_PRI_NO_ACCESS:
+                return PNFS_OSD_ERR_NO_ACCESS;
+        case OSD_ERR_PRI_UNREACHABLE:
+                return PNFS_OSD_ERR_UNREACHABLE;
+        case OSD_ERR_PRI_NOT_FOUND:
+                return PNFS_OSD_ERR_NOT_FOUND;
+        case OSD_ERR_PRI_NO_SPACE:
+                return PNFS_OSD_ERR_NO_SPACE;
+        default:
+                WARN_ON(1);
+                /* fallthrough */
+        case OSD_ERR_PRI_EIO:
+                return PNFS_OSD_ERR_EIO;
+        }
+}
+
+static void _clear_bio(struct bio *bio)
+{
+        struct bio_vec *bv;
+        unsigned i;
+
+        __bio_for_each_segment(bv, bio, i, 0) {
+                unsigned this_count = bv->bv_len;
+
+                if (likely(PAGE_SIZE == this_count))
+                        clear_highpage(bv->bv_page);
+                else
+                        zero_user(bv->bv_page, bv->bv_offset, this_count);
+        }
+}
+
+static int _io_check(struct objio_state *ios, bool is_write)
+{
+        enum osd_err_priority oep = OSD_ERR_PRI_NO_ERROR;
+        int lin_ret = 0;
+        int i;
+
+        for (i = 0; i <  ios->numdevs; i++) {
+                struct osd_sense_info osi;
+                struct osd_request *or = ios->per_dev[i].or;
+                unsigned dev;
+                int ret;
+
+                if (!or)
+                        continue;
+
+                ret = osd_req_decode_sense(or, &osi);
+                if (likely(!ret))
+                        continue;
+
+                if (OSD_ERR_PRI_CLEAR_PAGES == osi.osd_err_pri) {
+                        /* start read offset passed endof file */
+                        BUG_ON(is_write);
+                        _clear_bio(ios->per_dev[i].bio);
+                        dprintk("%s: start read offset passed end of file "
+                                "offset=0x%llx, length=0x%lx\n", __func__,
+                                _LLU(ios->per_dev[i].offset),
+                                ios->per_dev[i].length);
+
+                        continue; /* we recovered */
+                }
+                dev = ios->per_dev[i].dev;
+                objlayout_io_set_result(&ios->ol_state, dev,
+                                        &ios->layout->comps[dev].oc_object_id,
+                                        osd_pri_2_pnfs_err(osi.osd_err_pri),
+                                        ios->per_dev[i].offset,
+                                        ios->per_dev[i].length,
+                                        is_write);
+
+                if (osi.osd_err_pri >= oep) {
+                        oep = osi.osd_err_pri;
+                        lin_ret = ret;
+                }
+        }
+
+        return lin_ret;
+}
+
+/*
+ * Common IO state helpers.
+ */
+static void _io_free(struct objio_state *ios)
+{
+        unsigned i;
+
+        for (i = 0; i < ios->numdevs; i++) {
+                struct _objio_per_comp *per_dev = &ios->per_dev[i];
+
+                if (per_dev->or) {
+                        osd_end_request(per_dev->or);
+                        per_dev->or = NULL;
+                }
+
+                if (per_dev->bio) {
+                        bio_put(per_dev->bio);
+                        per_dev->bio = NULL;
+                }
+        }
+}
+
+struct osd_dev *_io_od(struct objio_state *ios, unsigned dev)
+{
+        unsigned min_dev = ios->layout->comps_index;
+        unsigned max_dev = min_dev + ios->layout->num_comps;
+
+        BUG_ON(dev < min_dev || max_dev <= dev);
+        return ios->layout->ods[dev - min_dev]->od;
+}
+
+struct _striping_info {
+        u64 obj_offset;
+        u64 group_length;
+        unsigned dev;
+        unsigned unit_off;
+};
+
+static void _calc_stripe_info(struct objio_state *ios, u64 file_offset,
+                              struct _striping_info *si)
+{
+        u32     stripe_unit = ios->layout->stripe_unit;
+        u32     group_width = ios->layout->group_width;
+        u64     group_depth = ios->layout->group_depth;
+        u32     U = stripe_unit * group_width;
+
+        u64     T = U * group_depth;
+        u64     S = T * ios->layout->group_count;
+        u64     M = div64_u64(file_offset, S);
+
+        /*
+        G = (L - (M * S)) / T
+        H = (L - (M * S)) % T
+        */
+        u64     LmodU = file_offset - M * S;
+        u32     G = div64_u64(LmodU, T);
+        u64     H = LmodU - G * T;
+
+        u32     N = div_u64(H, U);
+
+        div_u64_rem(file_offset, stripe_unit, &si->unit_off);
+        si->obj_offset = si->unit_off + (N * stripe_unit) +
+                                  (M * group_depth * stripe_unit);
+
+        /* "H - (N * U)" is just "H % U" so it's bound to u32 */
+        si->dev = (u32)(H - (N * U)) / stripe_unit + G * group_width;
+        si->dev *= ios->layout->mirrors_p1;
+
+        si->group_length = T - H;
+}
+
+static int _add_stripe_unit(struct objio_state *ios,  unsigned *cur_pg,
+                unsigned pgbase, struct _objio_per_comp *per_dev, int cur_len,
+                gfp_t gfp_flags)
+{
+        unsigned pg = *cur_pg;
+        struct request_queue *q =
+                        osd_request_queue(_io_od(ios, per_dev->dev));
+
+        per_dev->length += cur_len;
+
+        if (per_dev->bio == NULL) {
+                unsigned stripes = ios->layout->num_comps /
+                                                     ios->layout->mirrors_p1;
+                unsigned pages_in_stripe = stripes *
+                                      (ios->layout->stripe_unit / PAGE_SIZE);
+                unsigned bio_size = (ios->ol_state.nr_pages + pages_in_stripe) /
+                                    stripes;
+
+                if (BIO_MAX_PAGES_KMALLOC < bio_size)
+                        bio_size = BIO_MAX_PAGES_KMALLOC;
+
+                per_dev->bio = bio_kmalloc(gfp_flags, bio_size);
+                if (unlikely(!per_dev->bio)) {
+                        dprintk("Faild to allocate BIO size=%u\n", bio_size);
+                        return -ENOMEM;
+                }
+        }
+
+        while (cur_len > 0) {
+                unsigned pglen = min_t(unsigned, PAGE_SIZE - pgbase, cur_len);
+                unsigned added_len;
+
+                BUG_ON(ios->ol_state.nr_pages <= pg);
+                cur_len -= pglen;
+
+                added_len = bio_add_pc_page(q, per_dev->bio,
+                                        ios->ol_state.pages[pg], pglen, pgbase);
+                if (unlikely(pglen != added_len))
+                        return -ENOMEM;
+                pgbase = 0;
+                ++pg;
+        }
+        BUG_ON(cur_len);
+
+        *cur_pg = pg;
+        return 0;
+}
+
+static int _prepare_one_group(struct objio_state *ios, u64 length,
+                              struct _striping_info *si, unsigned *last_pg,
+                              gfp_t gfp_flags)
+{
+        unsigned stripe_unit = ios->layout->stripe_unit;
+        unsigned mirrors_p1 = ios->layout->mirrors_p1;
+        unsigned devs_in_group = ios->layout->group_width * mirrors_p1;
+        unsigned dev = si->dev;
+        unsigned first_dev = dev - (dev % devs_in_group);
+        unsigned max_comp = ios->numdevs ? ios->numdevs - mirrors_p1 : 0;
+        unsigned cur_pg = *last_pg;
+        int ret = 0;
+
+        while (length) {
+                struct _objio_per_comp *per_dev = &ios->per_dev[dev];
+                unsigned cur_len, page_off = 0;
+
+                if (!per_dev->length) {
+                        per_dev->dev = dev;
+                        if (dev < si->dev) {
+                                per_dev->offset = si->obj_offset + stripe_unit -
+                                                                   si->unit_off;
+                                cur_len = stripe_unit;
+                        } else if (dev == si->dev) {
+                                per_dev->offset = si->obj_offset;
+                                cur_len = stripe_unit - si->unit_off;
+                                page_off = si->unit_off & ~PAGE_MASK;
+                                BUG_ON(page_off &&
+                                      (page_off != ios->ol_state.pgbase));
+                        } else { /* dev > si->dev */
+                                per_dev->offset = si->obj_offset - si->unit_off;
+                                cur_len = stripe_unit;
+                        }
+
+                        if (max_comp < dev)
+                                max_comp = dev;
+                } else {
+                        cur_len = stripe_unit;
+                }
+                if (cur_len >= length)
+                        cur_len = length;
+
+                ret = _add_stripe_unit(ios, &cur_pg, page_off , per_dev,
+                                       cur_len, gfp_flags);
+                if (unlikely(ret))
+                        goto out;
+
+                dev += mirrors_p1;
+                dev = (dev % devs_in_group) + first_dev;
+
+                length -= cur_len;
+                ios->length += cur_len;
+        }
+out:
+        ios->numdevs = max_comp + mirrors_p1;
+        *last_pg = cur_pg;
+        return ret;
+}
+
+static int _io_rw_pagelist(struct objio_state *ios, gfp_t gfp_flags)
+{
+        u64 length = ios->ol_state.count;
+        u64 offset = ios->ol_state.offset;
+        struct _striping_info si;
+        unsigned last_pg = 0;
+        int ret = 0;
+
+        while (length) {
+                _calc_stripe_info(ios, offset, &si);
+
+                if (length < si.group_length)
+                        si.group_length = length;
+
+                ret = _prepare_one_group(ios, si.group_length, &si, &last_pg, gfp_flags);
+                if (unlikely(ret))
+                        goto out;
+
+                offset += si.group_length;
+                length -= si.group_length;
+        }
+
+out:
+        if (!ios->length)
+                return ret;
+
+        return 0;
+}
+
+static ssize_t _sync_done(struct objio_state *ios)
+{
+        struct completion *waiting = ios->private;
+
+        complete(waiting);
+        return 0;
+}
+
+static void _last_io(struct kref *kref)
+{
+        struct objio_state *ios = container_of(kref, struct objio_state, kref);
+
+        ios->done(ios);
+}
+
+static void _done_io(struct osd_request *or, void *p)
+{
+        struct objio_state *ios = p;
+
+        kref_put(&ios->kref, _last_io);
+}
+
+static ssize_t _io_exec(struct objio_state *ios)
+{
+        DECLARE_COMPLETION_ONSTACK(wait);
+        ssize_t status = 0; /* sync status */
+        unsigned i;
+        objio_done_fn saved_done_fn = ios->done;
+        bool sync = ios->ol_state.sync;
+
+        if (sync) {
+                ios->done = _sync_done;
+                ios->private = &wait;
+        }
+
+        kref_init(&ios->kref);
+
+        for (i = 0; i < ios->numdevs; i++) {
+                struct osd_request *or = ios->per_dev[i].or;
+
+                if (!or)
+                        continue;
+
+                kref_get(&ios->kref);
+                osd_execute_request_async(or, _done_io, ios);
+        }
+
+        kref_put(&ios->kref, _last_io);
+
+        if (sync) {
+                wait_for_completion(&wait);
+                status = saved_done_fn(ios);
+        }
+
+        return status;
+}
+
+/*
+ * read
+ */
+static ssize_t _read_done(struct objio_state *ios)
+{
+        ssize_t status;
+        int ret = _io_check(ios, false);
+
+        _io_free(ios);
+
+        if (likely(!ret))
+                status = ios->length;
+        else
+                status = ret;
+
+        objlayout_read_done(&ios->ol_state, status, ios->ol_state.sync);
+        return status;
+}
+
+static int _read_mirrors(struct objio_state *ios, unsigned cur_comp)
+{
+        struct osd_request *or = NULL;
+        struct _objio_per_comp *per_dev = &ios->per_dev[cur_comp];
+        unsigned dev = per_dev->dev;
+        struct pnfs_osd_object_cred *cred =
+                        &ios->layout->comps[dev];
+        struct osd_obj_id obj = {
+                .partition = cred->oc_object_id.oid_partition_id,
+                .id = cred->oc_object_id.oid_object_id,
+        };
+        int ret;
+
+        or = osd_start_request(_io_od(ios, dev), GFP_KERNEL);
+        if (unlikely(!or)) {
+                ret = -ENOMEM;
+                goto err;
+        }
+        per_dev->or = or;
+
+        osd_req_read(or, &obj, per_dev->offset, per_dev->bio, per_dev->length);
+
+        ret = osd_finalize_request(or, 0, cred->oc_cap.cred, NULL);
+        if (ret) {
+                dprintk("%s: Faild to osd_finalize_request() => %d\n",
+                        __func__, ret);
+                goto err;
+        }
+
+        dprintk("%s:[%d] dev=%d obj=0x%llx start=0x%llx length=0x%lx\n",
+                __func__, cur_comp, dev, obj.id, _LLU(per_dev->offset),
+                per_dev->length);
+
+err:
+        return ret;
+}
+
+static ssize_t _read_exec(struct objio_state *ios)
+{
+        unsigned i;
+        int ret;
+
+        for (i = 0; i < ios->numdevs; i += ios->layout->mirrors_p1) {
+                if (!ios->per_dev[i].length)
+                        continue;
+                ret = _read_mirrors(ios, i);
+                if (unlikely(ret))
+                        goto err;
+        }
+
+        ios->done = _read_done;
+        return _io_exec(ios); /* In sync mode exec returns the io status */
+
+err:
+        _io_free(ios);
+        return ret;
+}
+
+ssize_t objio_read_pagelist(struct objlayout_io_state *ol_state)
+{
+        struct objio_state *ios = container_of(ol_state, struct objio_state,
+                                               ol_state);
+        int ret;
+
+        ret = _io_rw_pagelist(ios, GFP_KERNEL);
+        if (unlikely(ret))
+                return ret;
+
+        return _read_exec(ios);
+}
+
+/*
+ * write
+ */
+static ssize_t _write_done(struct objio_state *ios)
+{
+        ssize_t status;
+        int ret = _io_check(ios, true);
+
+        _io_free(ios);
+
+        if (likely(!ret)) {
+                /* FIXME: should be based on the OSD's persistence model
+                 * See OSD2r05 Section 4.13 Data persistence model */
+                ios->ol_state.committed = NFS_FILE_SYNC;
+                status = ios->length;
+        } else {
+                status = ret;
+        }
+
+        objlayout_write_done(&ios->ol_state, status, ios->ol_state.sync);
+        return status;
+}
+
+static int _write_mirrors(struct objio_state *ios, unsigned cur_comp)
+{
+        struct _objio_per_comp *master_dev = &ios->per_dev[cur_comp];
+        unsigned dev = ios->per_dev[cur_comp].dev;
+        unsigned last_comp = cur_comp + ios->layout->mirrors_p1;
+        int ret;
+
+        for (; cur_comp < last_comp; ++cur_comp, ++dev) {
+                struct osd_request *or = NULL;
+                struct pnfs_osd_object_cred *cred =
+                                        &ios->layout->comps[dev];
+                struct osd_obj_id obj = {
+                        .partition = cred->oc_object_id.oid_partition_id,
+                        .id = cred->oc_object_id.oid_object_id,
+                };
+                struct _objio_per_comp *per_dev = &ios->per_dev[cur_comp];
+                struct bio *bio;
+
+                or = osd_start_request(_io_od(ios, dev), GFP_NOFS);
+                if (unlikely(!or)) {
+                        ret = -ENOMEM;
+                        goto err;
+                }
+                per_dev->or = or;
+
+                if (per_dev != master_dev) {
+                        bio = bio_kmalloc(GFP_NOFS,
+                                          master_dev->bio->bi_max_vecs);
+                        if (unlikely(!bio)) {
+                                dprintk("Faild to allocate BIO size=%u\n",
+                                        master_dev->bio->bi_max_vecs);
+                                ret = -ENOMEM;
+                                goto err;
+                        }
+
+                        __bio_clone(bio, master_dev->bio);
+                        bio->bi_bdev = NULL;
+                        bio->bi_next = NULL;
+                        per_dev->bio = bio;
+                        per_dev->dev = dev;
+                        per_dev->length = master_dev->length;
+                        per_dev->offset =  master_dev->offset;
+                } else {
+                        bio = master_dev->bio;
+                        bio->bi_rw |= REQ_WRITE;
+                }
+
+                osd_req_write(or, &obj, per_dev->offset, bio, per_dev->length);
+
+                ret = osd_finalize_request(or, 0, cred->oc_cap.cred, NULL);
+                if (ret) {
+                        dprintk("%s: Faild to osd_finalize_request() => %d\n",
+                                __func__, ret);
+                        goto err;
+                }
+
+                dprintk("%s:[%d] dev=%d obj=0x%llx start=0x%llx length=0x%lx\n",
+                        __func__, cur_comp, dev, obj.id, _LLU(per_dev->offset),
+                        per_dev->length);
+        }
+
+err:
+        return ret;
+}
+
+static ssize_t _write_exec(struct objio_state *ios)
+{
+        unsigned i;
+        int ret;
+
+        for (i = 0; i < ios->numdevs; i += ios->layout->mirrors_p1) {
+                if (!ios->per_dev[i].length)
+                        continue;
+                ret = _write_mirrors(ios, i);
+                if (unlikely(ret))
+                        goto err;
+        }
+
+        ios->done = _write_done;
+        return _io_exec(ios); /* In sync mode exec returns the io->status */
+
+err:
+        _io_free(ios);
+        return ret;
+}
+
+ssize_t objio_write_pagelist(struct objlayout_io_state *ol_state, bool stable)
+{
+        struct objio_state *ios = container_of(ol_state, struct objio_state,
+                                               ol_state);
+        int ret;
+
+        /* TODO: ios->stable = stable; */
+        ret = _io_rw_pagelist(ios, GFP_NOFS);
+        if (unlikely(ret))
+                return ret;
+
+        return _write_exec(ios);
+}
+
+static bool objio_pg_test(struct nfs_pageio_descriptor *pgio,
+                          struct nfs_page *prev, struct nfs_page *req)
+{
+        if (!pnfs_generic_pg_test(pgio, prev, req))
+                return false;
+
+        return pgio->pg_count + req->wb_bytes <=
+                        OBJIO_LSEG(pgio->pg_lseg)->max_io_size;
+}
+
+static struct pnfs_layoutdriver_type objlayout_type = {
+        .id = LAYOUT_OSD2_OBJECTS,
+        .name = "LAYOUT_OSD2_OBJECTS",
+        .flags                   = PNFS_LAYOUTRET_ON_SETATTR,
+
+        .alloc_layout_hdr        = objlayout_alloc_layout_hdr,
+        .free_layout_hdr         = objlayout_free_layout_hdr,
+
+        .alloc_lseg              = objlayout_alloc_lseg,
+        .free_lseg               = objlayout_free_lseg,
+
+        .read_pagelist           = objlayout_read_pagelist,
+        .write_pagelist          = objlayout_write_pagelist,
+        .pg_test                 = objio_pg_test,
+
+        .free_deviceid_node      = objio_free_deviceid_node,
+
+        .encode_layoutcommit     = objlayout_encode_layoutcommit,
+        .encode_layoutreturn     = objlayout_encode_layoutreturn,
+};
+
+MODULE_DESCRIPTION("pNFS Layout Driver for OSD2 objects");
+MODULE_AUTHOR("Benny Halevy <bhalevy@panasas.com>");
+MODULE_LICENSE("GPL");
+
+static int __init
+objlayout_init(void)
+{
+        int ret = pnfs_register_layoutdriver(&objlayout_type);
+
+        if (ret)
+                printk(KERN_INFO
+                        "%s: Registering OSD pNFS Layout Driver failed: error=%d\n",
+                        __func__, ret);
+        else
+                printk(KERN_INFO "%s: Registered OSD pNFS Layout Driver\n",
+                        __func__);
+        return ret;
+}
+
+static void __exit
+objlayout_exit(void)
+{
+        pnfs_unregister_layoutdriver(&objlayout_type);
+        printk(KERN_INFO "%s: Unregistered OSD pNFS Layout Driver\n",
+               __func__);
+}
+
+module_init(objlayout_init);
+module_exit(objlayout_exit);
diff --git a/fs/nfs/objlayout/objlayout.c b/fs/nfs/objlayout/objlayout.c
new file mode 100644
index 000000000000..dc3956c0de80
--- /dev/null
+++ b/fs/nfs/objlayout/objlayout.c
@@ -0,0 +1,712 @@
+/*
+ *  pNFS Objects layout driver high level definitions
+ *
+ *  Copyright (C) 2007 Panasas Inc. [year of first publication]
+ *  All rights reserved.
+ *
+ *  Benny Halevy <bhalevy@panasas.com>
+ *  Boaz Harrosh <bharrosh@panasas.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  See the file COPYING included with this distribution for more details.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *  1. Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *  2. Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in the
+ *     documentation and/or other materials provided with the distribution.
+ *  3. Neither the name of the Panasas company nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <scsi/osd_initiator.h>
+#include "objlayout.h"
+
+#define NFSDBG_FACILITY         NFSDBG_PNFS_LD
+/*
+ * Create a objlayout layout structure for the given inode and return it.
+ */
+struct pnfs_layout_hdr *
+objlayout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags)
+{
+        struct objlayout *objlay;
+
+        objlay = kzalloc(sizeof(struct objlayout), gfp_flags);
+        if (objlay) {
+                spin_lock_init(&objlay->lock);
+                INIT_LIST_HEAD(&objlay->err_list);
+        }
+        dprintk("%s: Return %p\n", __func__, objlay);
+        return &objlay->pnfs_layout;
+}
+
+/*
+ * Free an objlayout layout structure
+ */
+void
+objlayout_free_layout_hdr(struct pnfs_layout_hdr *lo)
+{
+        struct objlayout *objlay = OBJLAYOUT(lo);
+
+        dprintk("%s: objlay %p\n", __func__, objlay);
+
+        WARN_ON(!list_empty(&objlay->err_list));
+        kfree(objlay);
+}
+
+/*
+ * Unmarshall layout and store it in pnfslay.
+ */
+struct pnfs_layout_segment *
+objlayout_alloc_lseg(struct pnfs_layout_hdr *pnfslay,
+                     struct nfs4_layoutget_res *lgr,
+                     gfp_t gfp_flags)
+{
+        int status = -ENOMEM;
+        struct xdr_stream stream;
+        struct xdr_buf buf = {
+                .pages =  lgr->layoutp->pages,
+                .page_len =  lgr->layoutp->len,
+                .buflen =  lgr->layoutp->len,
+                .len = lgr->layoutp->len,
+        };
+        struct page *scratch;
+        struct pnfs_layout_segment *lseg;
+
+        dprintk("%s: Begin pnfslay %p\n", __func__, pnfslay);
+
+        scratch = alloc_page(gfp_flags);
+        if (!scratch)
+                goto err_nofree;
+
+        xdr_init_decode(&stream, &buf, NULL);
+        xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
+
+        status = objio_alloc_lseg(&lseg, pnfslay, &lgr->range, &stream, gfp_flags);
+        if (unlikely(status)) {
+                dprintk("%s: objio_alloc_lseg Return err %d\n", __func__,
+                        status);
+                goto err;
+        }
+
+        __free_page(scratch);
+
+        dprintk("%s: Return %p\n", __func__, lseg);
+        return lseg;
+
+err:
+        __free_page(scratch);
+err_nofree:
+        dprintk("%s: Err Return=>%d\n", __func__, status);
+        return ERR_PTR(status);
+}
+
+/*
+ * Free a layout segement
+ */
+void
+objlayout_free_lseg(struct pnfs_layout_segment *lseg)
+{
+        dprintk("%s: freeing layout segment %p\n", __func__, lseg);
+
+        if (unlikely(!lseg))
+                return;
+
+        objio_free_lseg(lseg);
+}
+
+/*
+ * I/O Operations
+ */
+static inline u64
+end_offset(u64 start, u64 len)
+{
+        u64 end;
+
+        end = start + len;
+        return end >= start ? end : NFS4_MAX_UINT64;
+}
+
+/* last octet in a range */
+static inline u64
+last_byte_offset(u64 start, u64 len)
+{
+        u64 end;
+
+        BUG_ON(!len);
+        end = start + len;
+        return end > start ? end - 1 : NFS4_MAX_UINT64;
+}
+
+static struct objlayout_io_state *
+objlayout_alloc_io_state(struct pnfs_layout_hdr *pnfs_layout_type,
+                        struct page **pages,
+                        unsigned pgbase,
+                        loff_t offset,
+                        size_t count,
+                        struct pnfs_layout_segment *lseg,
+                        void *rpcdata,
+                        gfp_t gfp_flags)
+{
+        struct objlayout_io_state *state;
+        u64 lseg_end_offset;
+
+        dprintk("%s: allocating io_state\n", __func__);
+        if (objio_alloc_io_state(lseg, &state, gfp_flags))
+                return NULL;
+
+        BUG_ON(offset < lseg->pls_range.offset);
+        lseg_end_offset = end_offset(lseg->pls_range.offset,
+                                     lseg->pls_range.length);
+        BUG_ON(offset >= lseg_end_offset);
+        if (offset + count > lseg_end_offset) {
+                count = lseg->pls_range.length -
+                                (offset - lseg->pls_range.offset);
+                dprintk("%s: truncated count %Zd\n", __func__, count);
+        }
+
+        if (pgbase > PAGE_SIZE) {
+                pages += pgbase >> PAGE_SHIFT;
+                pgbase &= ~PAGE_MASK;
+        }
+
+        INIT_LIST_HEAD(&state->err_list);
+        state->lseg = lseg;
+        state->rpcdata = rpcdata;
+        state->pages = pages;
+        state->pgbase = pgbase;
+        state->nr_pages = (pgbase + count + PAGE_SIZE - 1) >> PAGE_SHIFT;
+        state->offset = offset;
+        state->count = count;
+        state->sync = 0;
+
+        return state;
+}
+
+static void
+objlayout_free_io_state(struct objlayout_io_state *state)
+{
+        dprintk("%s: freeing io_state\n", __func__);
+        if (unlikely(!state))
+                return;
+
+        objio_free_io_state(state);
+}
+
+/*
+ * I/O done common code
+ */
+static void
+objlayout_iodone(struct objlayout_io_state *state)
+{
+        dprintk("%s: state %p status\n", __func__, state);
+
+        if (likely(state->status >= 0)) {
+                objlayout_free_io_state(state);
+        } else {
+                struct objlayout *objlay = OBJLAYOUT(state->lseg->pls_layout);
+
+                spin_lock(&objlay->lock);
+                objlay->delta_space_valid = OBJ_DSU_INVALID;
+                list_add(&objlay->err_list, &state->err_list);
+                spin_unlock(&objlay->lock);
+        }
+}
+
+/*
+ * objlayout_io_set_result - Set an osd_error code on a specific osd comp.
+ *
+ * The @index component IO failed (error returned from target). Register
+ * the error for later reporting at layout-return.
+ */
+void
+objlayout_io_set_result(struct objlayout_io_state *state, unsigned index,
+                        struct pnfs_osd_objid *pooid, int osd_error,
+                        u64 offset, u64 length, bool is_write)
+{
+        struct pnfs_osd_ioerr *ioerr = &state->ioerrs[index];
+
+        BUG_ON(index >= state->num_comps);
+        if (osd_error) {
+                ioerr->oer_component = *pooid;
+                ioerr->oer_comp_offset = offset;
+                ioerr->oer_comp_length = length;
+                ioerr->oer_iswrite = is_write;
+                ioerr->oer_errno = osd_error;
+
+                dprintk("%s: err[%d]: errno=%d is_write=%d dev(%llx:%llx) "
+                        "par=0x%llx obj=0x%llx offset=0x%llx length=0x%llx\n",
+                        __func__, index, ioerr->oer_errno,
+                        ioerr->oer_iswrite,
+                        _DEVID_LO(&ioerr->oer_component.oid_device_id),
+                        _DEVID_HI(&ioerr->oer_component.oid_device_id),
+                        ioerr->oer_component.oid_partition_id,
+                        ioerr->oer_component.oid_object_id,
+                        ioerr->oer_comp_offset,
+                        ioerr->oer_comp_length);
+        } else {
+                /* User need not call if no error is reported */
+                ioerr->oer_errno = 0;
+        }
+}
+
+/* Function scheduled on rpc workqueue to call ->nfs_readlist_complete().
+ * This is because the osd completion is called with ints-off from
+ * the block layer
+ */
+static void _rpc_read_complete(struct work_struct *work)
+{
+        struct rpc_task *task;
+        struct nfs_read_data *rdata;
+
+        dprintk("%s enter\n", __func__);
+        task = container_of(work, struct rpc_task, u.tk_work);
+        rdata = container_of(task, struct nfs_read_data, task);
+
+        pnfs_ld_read_done(rdata);
+}
+
+void
+objlayout_read_done(struct objlayout_io_state *state, ssize_t status, bool sync)
+{
+        int eof = state->eof;
+        struct nfs_read_data *rdata;
+
+        state->status = status;
+        dprintk("%s: Begin status=%ld eof=%d\n", __func__, status, eof);
+        rdata = state->rpcdata;
+        rdata->task.tk_status = status;
+        if (status >= 0) {
+                rdata->res.count = status;
+                rdata->res.eof = eof;
+        }
+        objlayout_iodone(state);
+        /* must not use state after this point */
+
+        if (sync)
+                pnfs_ld_read_done(rdata);
+        else {
+                INIT_WORK(&rdata->task.u.tk_work, _rpc_read_complete);
+                schedule_work(&rdata->task.u.tk_work);
+        }
+}
+
+/*
+ * Perform sync or async reads.
+ */
+enum pnfs_try_status
+objlayout_read_pagelist(struct nfs_read_data *rdata)
+{
+        loff_t offset = rdata->args.offset;
+        size_t count = rdata->args.count;
+        struct objlayout_io_state *state;
+        ssize_t status = 0;
+        loff_t eof;
+
+        dprintk("%s: Begin inode %p offset %llu count %d\n",
+                __func__, rdata->inode, offset, (int)count);
+
+        eof = i_size_read(rdata->inode);
+        if (unlikely(offset + count > eof)) {
+                if (offset >= eof) {
+                        status = 0;
+                        rdata->res.count = 0;
+                        rdata->res.eof = 1;
+                        goto out;
+                }
+                count = eof - offset;
+        }
+
+        state = objlayout_alloc_io_state(NFS_I(rdata->inode)->layout,
+                                         rdata->args.pages, rdata->args.pgbase,
+                                         offset, count,
+                                         rdata->lseg, rdata,
+                                         GFP_KERNEL);
+        if (unlikely(!state)) {
+                status = -ENOMEM;
+                goto out;
+        }
+
+        state->eof = state->offset + state->count >= eof;
+
+        status = objio_read_pagelist(state);
+ out:
+        dprintk("%s: Return status %Zd\n", __func__, status);
+        rdata->pnfs_error = status;
+        return PNFS_ATTEMPTED;
+}
+
+/* Function scheduled on rpc workqueue to call ->nfs_writelist_complete().
+ * This is because the osd completion is called with ints-off from
+ * the block layer
+ */
+static void _rpc_write_complete(struct work_struct *work)
+{
+        struct rpc_task *task;
+        struct nfs_write_data *wdata;
+
+        dprintk("%s enter\n", __func__);
+        task = container_of(work, struct rpc_task, u.tk_work);
+        wdata = container_of(task, struct nfs_write_data, task);
+
+        pnfs_ld_write_done(wdata);
+}
+
+void
+objlayout_write_done(struct objlayout_io_state *state, ssize_t status,
+                     bool sync)
+{
+        struct nfs_write_data *wdata;
+
+        dprintk("%s: Begin\n", __func__);
+        wdata = state->rpcdata;
+        state->status = status;
+        wdata->task.tk_status = status;
+        if (status >= 0) {
+                wdata->res.count = status;
+                wdata->verf.committed = state->committed;
+                dprintk("%s: Return status %d committed %d\n",
+                        __func__, wdata->task.tk_status,
+                        wdata->verf.committed);
+        } else
+                dprintk("%s: Return status %d\n",
+                        __func__, wdata->task.tk_status);
+        objlayout_iodone(state);
+        /* must not use state after this point */
+
+        if (sync)
+                pnfs_ld_write_done(wdata);
+        else {
+                INIT_WORK(&wdata->task.u.tk_work, _rpc_write_complete);
+                schedule_work(&wdata->task.u.tk_work);
+        }
+}
+
+/*
+ * Perform sync or async writes.
+ */
+enum pnfs_try_status
+objlayout_write_pagelist(struct nfs_write_data *wdata,
+                         int how)
+{
+        struct objlayout_io_state *state;
+        ssize_t status;
+
+        dprintk("%s: Begin inode %p offset %llu count %u\n",
+                __func__, wdata->inode, wdata->args.offset, wdata->args.count);
+
+        state = objlayout_alloc_io_state(NFS_I(wdata->inode)->layout,
+                                         wdata->args.pages,
+                                         wdata->args.pgbase,
+                                         wdata->args.offset,
+                                         wdata->args.count,
+                                         wdata->lseg, wdata,
+                                         GFP_NOFS);
+        if (unlikely(!state)) {
+                status = -ENOMEM;
+                goto out;
+        }
+
+        state->sync = how & FLUSH_SYNC;
+
+        status = objio_write_pagelist(state, how & FLUSH_STABLE);
+ out:
+        dprintk("%s: Return status %Zd\n", __func__, status);
+        wdata->pnfs_error = status;
+        return PNFS_ATTEMPTED;
+}
+
+void
+objlayout_encode_layoutcommit(struct pnfs_layout_hdr *pnfslay,
+                              struct xdr_stream *xdr,
+                              const struct nfs4_layoutcommit_args *args)
+{
+        struct objlayout *objlay = OBJLAYOUT(pnfslay);
+        struct pnfs_osd_layoutupdate lou;
+        __be32 *start;
+
+        dprintk("%s: Begin\n", __func__);
+
+        spin_lock(&objlay->lock);
+        lou.dsu_valid = (objlay->delta_space_valid == OBJ_DSU_VALID);
+        lou.dsu_delta = objlay->delta_space_used;
+        objlay->delta_space_used = 0;
+        objlay->delta_space_valid = OBJ_DSU_INIT;
+        lou.olu_ioerr_flag = !list_empty(&objlay->err_list);
+        spin_unlock(&objlay->lock);
+
+        start = xdr_reserve_space(xdr, 4);
+
+        BUG_ON(pnfs_osd_xdr_encode_layoutupdate(xdr, &lou));
+
+        *start = cpu_to_be32((xdr->p - start - 1) * 4);
+
+        dprintk("%s: Return delta_space_used %lld err %d\n", __func__,
+                lou.dsu_delta, lou.olu_ioerr_flag);
+}
+
+static int
+err_prio(u32 oer_errno)
+{
+        switch (oer_errno) {
+        case 0:
+                return 0;
+
+        case PNFS_OSD_ERR_RESOURCE:
+                return OSD_ERR_PRI_RESOURCE;
+        case PNFS_OSD_ERR_BAD_CRED:
+                return OSD_ERR_PRI_BAD_CRED;
+        case PNFS_OSD_ERR_NO_ACCESS:
+                return OSD_ERR_PRI_NO_ACCESS;
+        case PNFS_OSD_ERR_UNREACHABLE:
+                return OSD_ERR_PRI_UNREACHABLE;
+        case PNFS_OSD_ERR_NOT_FOUND:
+                return OSD_ERR_PRI_NOT_FOUND;
+        case PNFS_OSD_ERR_NO_SPACE:
+                return OSD_ERR_PRI_NO_SPACE;
+        default:
+                WARN_ON(1);
+                /* fallthrough */
+        case PNFS_OSD_ERR_EIO:
+                return OSD_ERR_PRI_EIO;
+        }
+}
+
+static void
+merge_ioerr(struct pnfs_osd_ioerr *dest_err,
+            const struct pnfs_osd_ioerr *src_err)
+{
+        u64 dest_end, src_end;
+
+        if (!dest_err->oer_errno) {
+                *dest_err = *src_err;
+                /* accumulated device must be blank */
+                memset(&dest_err->oer_component.oid_device_id, 0,
+                        sizeof(dest_err->oer_component.oid_device_id));
+
+                return;
+        }
+
+        if (dest_err->oer_component.oid_partition_id !=
+                                src_err->oer_component.oid_partition_id)
+                dest_err->oer_component.oid_partition_id = 0;
+
+        if (dest_err->oer_component.oid_object_id !=
+                                src_err->oer_component.oid_object_id)
+                dest_err->oer_component.oid_object_id = 0;
+
+        if (dest_err->oer_comp_offset > src_err->oer_comp_offset)
+                dest_err->oer_comp_offset = src_err->oer_comp_offset;
+
+        dest_end = end_offset(dest_err->oer_comp_offset,
+                              dest_err->oer_comp_length);
+        src_end =  end_offset(src_err->oer_comp_offset,
+                              src_err->oer_comp_length);
+        if (dest_end < src_end)
+                dest_end = src_end;
+
+        dest_err->oer_comp_length = dest_end - dest_err->oer_comp_offset;
+
+        if ((src_err->oer_iswrite == dest_err->oer_iswrite) &&
+            (err_prio(src_err->oer_errno) > err_prio(dest_err->oer_errno))) {
+                        dest_err->oer_errno = src_err->oer_errno;
+        } else if (src_err->oer_iswrite) {
+                dest_err->oer_iswrite = true;
+                dest_err->oer_errno = src_err->oer_errno;
+        }
+}
+
+static void
+encode_accumulated_error(struct objlayout *objlay, __be32 *p)
+{
+        struct objlayout_io_state *state, *tmp;
+        struct pnfs_osd_ioerr accumulated_err = {.oer_errno = 0};
+
+        list_for_each_entry_safe(state, tmp, &objlay->err_list, err_list) {
+                unsigned i;
+
+                for (i = 0; i < state->num_comps; i++) {
+                        struct pnfs_osd_ioerr *ioerr = &state->ioerrs[i];
+
+                        if (!ioerr->oer_errno)
+                                continue;
+
+                        printk(KERN_ERR "%s: err[%d]: errno=%d is_write=%d "
+                                "dev(%llx:%llx) par=0x%llx obj=0x%llx "
+                                "offset=0x%llx length=0x%llx\n",
+                                __func__, i, ioerr->oer_errno,
+                                ioerr->oer_iswrite,
+                                _DEVID_LO(&ioerr->oer_component.oid_device_id),
+                                _DEVID_HI(&ioerr->oer_component.oid_device_id),
+                                ioerr->oer_component.oid_partition_id,
+                                ioerr->oer_component.oid_object_id,
+                                ioerr->oer_comp_offset,
+                                ioerr->oer_comp_length);
+
+                        merge_ioerr(&accumulated_err, ioerr);
+                }
+                list_del(&state->err_list);
+                objlayout_free_io_state(state);
+        }
+
+        pnfs_osd_xdr_encode_ioerr(p, &accumulated_err);
+}
+
+void
+objlayout_encode_layoutreturn(struct pnfs_layout_hdr *pnfslay,
+                              struct xdr_stream *xdr,
+                              const struct nfs4_layoutreturn_args *args)
+{
+        struct objlayout *objlay = OBJLAYOUT(pnfslay);
+        struct objlayout_io_state *state, *tmp;
+        __be32 *start;
+
+        dprintk("%s: Begin\n", __func__);
+        start = xdr_reserve_space(xdr, 4);
+        BUG_ON(!start);
+
+        spin_lock(&objlay->lock);
+
+        list_for_each_entry_safe(state, tmp, &objlay->err_list, err_list) {
+                __be32 *last_xdr = NULL, *p;
+                unsigned i;
+                int res = 0;
+
+                for (i = 0; i < state->num_comps; i++) {
+                        struct pnfs_osd_ioerr *ioerr = &state->ioerrs[i];
+
+                        if (!ioerr->oer_errno)
+                                continue;
+
+                        dprintk("%s: err[%d]: errno=%d is_write=%d "
+                                "dev(%llx:%llx) par=0x%llx obj=0x%llx "
+                                "offset=0x%llx length=0x%llx\n",
+                                __func__, i, ioerr->oer_errno,
+                                ioerr->oer_iswrite,
+                                _DEVID_LO(&ioerr->oer_component.oid_device_id),
+                                _DEVID_HI(&ioerr->oer_component.oid_device_id),
+                                ioerr->oer_component.oid_partition_id,
+                                ioerr->oer_component.oid_object_id,
+                                ioerr->oer_comp_offset,
+                                ioerr->oer_comp_length);
+
+                        p = pnfs_osd_xdr_ioerr_reserve_space(xdr);
+                        if (unlikely(!p)) {
+                                res = -E2BIG;
+                                break; /* accumulated_error */
+                        }
+
+                        last_xdr = p;
+                        pnfs_osd_xdr_encode_ioerr(p, &state->ioerrs[i]);
+                }
+
+                /* TODO: use xdr_write_pages */
+                if (unlikely(res)) {
+                        /* no space for even one error descriptor */
+                        BUG_ON(!last_xdr);
+
+                        /* we've encountered a situation with lots and lots of
+                         * errors and no space to encode them all. Use the last
+                         * available slot to report the union of all the
+                         * remaining errors.
+                         */
+                        encode_accumulated_error(objlay, last_xdr);
+                        goto loop_done;
+                }
+                list_del(&state->err_list);
+                objlayout_free_io_state(state);
+        }
+loop_done:
+        spin_unlock(&objlay->lock);
+
+        *start = cpu_to_be32((xdr->p - start - 1) * 4);
+        dprintk("%s: Return\n", __func__);
+}
+
+
+/*
+ * Get Device Info API for io engines
+ */
+struct objlayout_deviceinfo {
+        struct page *page;
+        struct pnfs_osd_deviceaddr da; /* This must be last */
+};
+
+/* Initialize and call nfs_getdeviceinfo, then decode and return a
+ * "struct pnfs_osd_deviceaddr *" Eventually objlayout_put_deviceinfo()
+ * should be called.
+ */
+int objlayout_get_deviceinfo(struct pnfs_layout_hdr *pnfslay,
+        struct nfs4_deviceid *d_id, struct pnfs_osd_deviceaddr **deviceaddr,
+        gfp_t gfp_flags)
+{
+        struct objlayout_deviceinfo *odi;
+        struct pnfs_device pd;
+        struct super_block *sb;
+        struct page *page, **pages;
+        u32 *p;
+        int err;
+
+        page = alloc_page(gfp_flags);
+        if (!page)
+                return -ENOMEM;
+
+        pages = &page;
+        pd.pages = pages;
+
+        memcpy(&pd.dev_id, d_id, sizeof(*d_id));
+        pd.layout_type = LAYOUT_OSD2_OBJECTS;
+        pd.pages = &page;
+        pd.pgbase = 0;
+        pd.pglen = PAGE_SIZE;
+        pd.mincount = 0;
+
+        sb = pnfslay->plh_inode->i_sb;
+        err = nfs4_proc_getdeviceinfo(NFS_SERVER(pnfslay->plh_inode), &pd);
+        dprintk("%s nfs_getdeviceinfo returned %d\n", __func__, err);
+        if (err)
+                goto err_out;
+
+        p = page_address(page);
+        odi = kzalloc(sizeof(*odi), gfp_flags);
+        if (!odi) {
+                err = -ENOMEM;
+                goto err_out;
+        }
+        pnfs_osd_xdr_decode_deviceaddr(&odi->da, p);
+        odi->page = page;
+        *deviceaddr = &odi->da;
+        return 0;
+
+err_out:
+        __free_page(page);
+        return err;
+}
+
+void objlayout_put_deviceinfo(struct pnfs_osd_deviceaddr *deviceaddr)
+{
+        struct objlayout_deviceinfo *odi = container_of(deviceaddr,
+                                                struct objlayout_deviceinfo,
+                                                da);
+
+        __free_page(odi->page);
+        kfree(odi);
+}
diff --git a/fs/nfs/objlayout/objlayout.h b/fs/nfs/objlayout/objlayout.h
new file mode 100644
index 000000000000..a8244c8e042d
--- /dev/null
+++ b/fs/nfs/objlayout/objlayout.h
@@ -0,0 +1,187 @@
+/*
+ *  Data types and function declerations for interfacing with the
+ *  pNFS standard object layout driver.
+ *
+ *  Copyright (C) 2007 Panasas Inc. [year of first publication]
+ *  All rights reserved.
+ *
+ *  Benny Halevy <bhalevy@panasas.com>
+ *  Boaz Harrosh <bharrosh@panasas.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  See the file COPYING included with this distribution for more details.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *  1. Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *  2. Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in the
+ *     documentation and/or other materials provided with the distribution.
+ *  3. Neither the name of the Panasas company nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _OBJLAYOUT_H
+#define _OBJLAYOUT_H
+
+#include <linux/nfs_fs.h>
+#include <linux/pnfs_osd_xdr.h>
+#include "../pnfs.h"
+
+/*
+ * per-inode layout
+ */
+struct objlayout {
+        struct pnfs_layout_hdr pnfs_layout;
+
+         /* for layout_commit */
+        enum osd_delta_space_valid_enum {
+                OBJ_DSU_INIT = 0,
+                OBJ_DSU_VALID,
+                OBJ_DSU_INVALID,
+        } delta_space_valid;
+        s64 delta_space_used;  /* consumed by write ops */
+
+         /* for layout_return */
+        spinlock_t lock;
+        struct list_head err_list;
+};
+
+static inline struct objlayout *
+OBJLAYOUT(struct pnfs_layout_hdr *lo)
+{
+        return container_of(lo, struct objlayout, pnfs_layout);
+}
+
+/*
+ * per-I/O operation state
+ * embedded in objects provider io_state data structure
+ */
+struct objlayout_io_state {
+        struct pnfs_layout_segment *lseg;
+
+        struct page **pages;
+        unsigned pgbase;
+        unsigned nr_pages;
+        unsigned long count;
+        loff_t offset;
+        bool sync;
+
+        void *rpcdata;
+        int status;             /* res */
+        int eof;                /* res */
+        int committed;          /* res */
+
+        /* Error reporting (layout_return) */
+        struct list_head err_list;
+        unsigned num_comps;
+        /* Pointer to array of error descriptors of size num_comps.
+         * It should contain as many entries as devices in the osd_layout
+         * that participate in the I/O. It is up to the io_engine to allocate
+         * needed space and set num_comps.
+         */
+        struct pnfs_osd_ioerr *ioerrs;
+};
+
+/*
+ * Raid engine I/O API
+ */
+extern int objio_alloc_lseg(struct pnfs_layout_segment **outp,
+        struct pnfs_layout_hdr *pnfslay,
+        struct pnfs_layout_range *range,
+        struct xdr_stream *xdr,
+        gfp_t gfp_flags);
+extern void objio_free_lseg(struct pnfs_layout_segment *lseg);
+
+extern int objio_alloc_io_state(
+        struct pnfs_layout_segment *lseg,
+        struct objlayout_io_state **outp,
+        gfp_t gfp_flags);
+extern void objio_free_io_state(struct objlayout_io_state *state);
+
+extern ssize_t objio_read_pagelist(struct objlayout_io_state *ol_state);
+extern ssize_t objio_write_pagelist(struct objlayout_io_state *ol_state,
+                                    bool stable);
+
+/*
+ * callback API
+ */
+extern void objlayout_io_set_result(struct objlayout_io_state *state,
+                        unsigned index, struct pnfs_osd_objid *pooid,
+                        int osd_error, u64 offset, u64 length, bool is_write);
+
+static inline void
+objlayout_add_delta_space_used(struct objlayout_io_state *state, s64 space_used)
+{
+        struct objlayout *objlay = OBJLAYOUT(state->lseg->pls_layout);
+
+        /* If one of the I/Os errored out and the delta_space_used was
+         * invalid we render the complete report as invalid. Protocol mandate
+         * the DSU be accurate or not reported.
+         */
+        spin_lock(&objlay->lock);
+        if (objlay->delta_space_valid != OBJ_DSU_INVALID) {
+                objlay->delta_space_valid = OBJ_DSU_VALID;
+                objlay->delta_space_used += space_used;
+        }
+        spin_unlock(&objlay->lock);
+}
+
+extern void objlayout_read_done(struct objlayout_io_state *state,
+                                ssize_t status, bool sync);
+extern void objlayout_write_done(struct objlayout_io_state *state,
+                                 ssize_t status, bool sync);
+
+extern int objlayout_get_deviceinfo(struct pnfs_layout_hdr *pnfslay,
+        struct nfs4_deviceid *d_id, struct pnfs_osd_deviceaddr **deviceaddr,
+        gfp_t gfp_flags);
+extern void objlayout_put_deviceinfo(struct pnfs_osd_deviceaddr *deviceaddr);
+
+/*
+ * exported generic objects function vectors
+ */
+
+extern struct pnfs_layout_hdr *objlayout_alloc_layout_hdr(struct inode *, gfp_t gfp_flags);
+extern void objlayout_free_layout_hdr(struct pnfs_layout_hdr *);
+
+extern struct pnfs_layout_segment *objlayout_alloc_lseg(
+        struct pnfs_layout_hdr *,
+        struct nfs4_layoutget_res *,
+        gfp_t gfp_flags);
+extern void objlayout_free_lseg(struct pnfs_layout_segment *);
+
+extern enum pnfs_try_status objlayout_read_pagelist(
+        struct nfs_read_data *);
+
+extern enum pnfs_try_status objlayout_write_pagelist(
+        struct nfs_write_data *,
+        int how);
+
+extern void objlayout_encode_layoutcommit(
+        struct pnfs_layout_hdr *,
+        struct xdr_stream *,
+        const struct nfs4_layoutcommit_args *);
+
+extern void objlayout_encode_layoutreturn(
+        struct pnfs_layout_hdr *,
+        struct xdr_stream *,
+        const struct nfs4_layoutreturn_args *);
+
+#endif /* _OBJLAYOUT_H */
diff --git a/fs/nfs/objlayout/pnfs_osd_xdr_cli.c b/fs/nfs/objlayout/pnfs_osd_xdr_cli.c
new file mode 100644
index 000000000000..16fc758e9123
--- /dev/null
+++ b/fs/nfs/objlayout/pnfs_osd_xdr_cli.c
@@ -0,0 +1,412 @@
+/*
+ *  Object-Based pNFS Layout XDR layer
+ *
+ *  Copyright (C) 2007 Panasas Inc. [year of first publication]
+ *  All rights reserved.
+ *
+ *  Benny Halevy <bhalevy@panasas.com>
+ *  Boaz Harrosh <bharrosh@panasas.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  See the file COPYING included with this distribution for more details.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *  1. Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *  2. Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in the
+ *     documentation and/or other materials provided with the distribution.
+ *  3. Neither the name of the Panasas company nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/pnfs_osd_xdr.h>
+
+#define NFSDBG_FACILITY         NFSDBG_PNFS_LD
+
+/*
+ * The following implementation is based on RFC5664
+ */
+
+/*
+ * struct pnfs_osd_objid {
+ *      struct nfs4_deviceid    oid_device_id;
+ *      u64                     oid_partition_id;
+ *      u64                     oid_object_id;
+ * }; // xdr size 32 bytes
+ */
+static __be32 *
+_osd_xdr_decode_objid(__be32 *p, struct pnfs_osd_objid *objid)
+{
+        p = xdr_decode_opaque_fixed(p, objid->oid_device_id.data,
+                                    sizeof(objid->oid_device_id.data));
+
+        p = xdr_decode_hyper(p, &objid->oid_partition_id);
+        p = xdr_decode_hyper(p, &objid->oid_object_id);
+        return p;
+}
+/*
+ * struct pnfs_osd_opaque_cred {
+ *      u32 cred_len;
+ *      void *cred;
+ * }; // xdr size [variable]
+ * The return pointers are from the xdr buffer
+ */
+static int
+_osd_xdr_decode_opaque_cred(struct pnfs_osd_opaque_cred *opaque_cred,
+                            struct xdr_stream *xdr)
+{
+        __be32 *p = xdr_inline_decode(xdr, 1);
+
+        if (!p)
+                return -EINVAL;
+
+        opaque_cred->cred_len = be32_to_cpu(*p++);
+
+        p = xdr_inline_decode(xdr, opaque_cred->cred_len);
+        if (!p)
+                return -EINVAL;
+
+        opaque_cred->cred = p;
+        return 0;
+}
+
+/*
+ * struct pnfs_osd_object_cred {
+ *      struct pnfs_osd_objid           oc_object_id;
+ *      u32                             oc_osd_version;
+ *      u32                             oc_cap_key_sec;
+ *      struct pnfs_osd_opaque_cred     oc_cap_key
+ *      struct pnfs_osd_opaque_cred     oc_cap;
+ * }; // xdr size 32 + 4 + 4 + [variable] + [variable]
+ */
+static int
+_osd_xdr_decode_object_cred(struct pnfs_osd_object_cred *comp,
+                            struct xdr_stream *xdr)
+{
+        __be32 *p = xdr_inline_decode(xdr, 32 + 4 + 4);
+        int ret;
+
+        if (!p)
+                return -EIO;
+
+        p = _osd_xdr_decode_objid(p, &comp->oc_object_id);
+        comp->oc_osd_version = be32_to_cpup(p++);
+        comp->oc_cap_key_sec = be32_to_cpup(p);
+
+        ret = _osd_xdr_decode_opaque_cred(&comp->oc_cap_key, xdr);
+        if (unlikely(ret))
+                return ret;
+
+        ret = _osd_xdr_decode_opaque_cred(&comp->oc_cap, xdr);
+        return ret;
+}
+
+/*
+ * struct pnfs_osd_data_map {
+ *      u32     odm_num_comps;
+ *      u64     odm_stripe_unit;
+ *      u32     odm_group_width;
+ *      u32     odm_group_depth;
+ *      u32     odm_mirror_cnt;
+ *      u32     odm_raid_algorithm;
+ * }; // xdr size 4 + 8 + 4 + 4 + 4 + 4
+ */
+static inline int
+_osd_data_map_xdr_sz(void)
+{
+        return 4 + 8 + 4 + 4 + 4 + 4;
+}
+
+static __be32 *
+_osd_xdr_decode_data_map(__be32 *p, struct pnfs_osd_data_map *data_map)
+{
+        data_map->odm_num_comps = be32_to_cpup(p++);
+        p = xdr_decode_hyper(p, &data_map->odm_stripe_unit);
+        data_map->odm_group_width = be32_to_cpup(p++);
+        data_map->odm_group_depth = be32_to_cpup(p++);
+        data_map->odm_mirror_cnt = be32_to_cpup(p++);
+        data_map->odm_raid_algorithm = be32_to_cpup(p++);
+        dprintk("%s: odm_num_comps=%u odm_stripe_unit=%llu odm_group_width=%u "
+                "odm_group_depth=%u odm_mirror_cnt=%u odm_raid_algorithm=%u\n",
+                __func__,
+                data_map->odm_num_comps,
+                (unsigned long long)data_map->odm_stripe_unit,
+                data_map->odm_group_width,
+                data_map->odm_group_depth,
+                data_map->odm_mirror_cnt,
+                data_map->odm_raid_algorithm);
+        return p;
+}
+
+int pnfs_osd_xdr_decode_layout_map(struct pnfs_osd_layout *layout,
+        struct pnfs_osd_xdr_decode_layout_iter *iter, struct xdr_stream *xdr)
+{
+        __be32 *p;
+
+        memset(iter, 0, sizeof(*iter));
+
+        p = xdr_inline_decode(xdr, _osd_data_map_xdr_sz() + 4 + 4);
+        if (unlikely(!p))
+                return -EINVAL;
+
+        p = _osd_xdr_decode_data_map(p, &layout->olo_map);
+        layout->olo_comps_index = be32_to_cpup(p++);
+        layout->olo_num_comps = be32_to_cpup(p++);
+        iter->total_comps = layout->olo_num_comps;
+        return 0;
+}
+
+bool pnfs_osd_xdr_decode_layout_comp(struct pnfs_osd_object_cred *comp,
+        struct pnfs_osd_xdr_decode_layout_iter *iter, struct xdr_stream *xdr,
+        int *err)
+{
+        BUG_ON(iter->decoded_comps > iter->total_comps);
+        if (iter->decoded_comps == iter->total_comps)
+                return false;
+
+        *err = _osd_xdr_decode_object_cred(comp, xdr);
+        if (unlikely(*err)) {
+                dprintk("%s: _osd_xdr_decode_object_cred=>%d decoded_comps=%d "
+                        "total_comps=%d\n", __func__, *err,
+                        iter->decoded_comps, iter->total_comps);
+                return false; /* stop the loop */
+        }
+        dprintk("%s: dev(%llx:%llx) par=0x%llx obj=0x%llx "
+                "key_len=%u cap_len=%u\n",
+                __func__,
+                _DEVID_LO(&comp->oc_object_id.oid_device_id),
+                _DEVID_HI(&comp->oc_object_id.oid_device_id),
+                comp->oc_object_id.oid_partition_id,
+                comp->oc_object_id.oid_object_id,
+                comp->oc_cap_key.cred_len, comp->oc_cap.cred_len);
+
+        iter->decoded_comps++;
+        return true;
+}
+
+/*
+ * Get Device Information Decoding
+ *
+ * Note: since Device Information is currently done synchronously, all
+ *       variable strings fields are left inside the rpc buffer and are only
+ *       pointed to by the pnfs_osd_deviceaddr members. So the read buffer
+ *       should not be freed while the returned information is in use.
+ */
+/*
+ *struct nfs4_string {
+ *      unsigned int len;
+ *      char *data;
+ *}; // size [variable]
+ * NOTE: Returned string points to inside the XDR buffer
+ */
+static __be32 *
+__read_u8_opaque(__be32 *p, struct nfs4_string *str)
+{
+        str->len = be32_to_cpup(p++);
+        str->data = (char *)p;
+
+        p += XDR_QUADLEN(str->len);
+        return p;
+}
+
+/*
+ * struct pnfs_osd_targetid {
+ *      u32                     oti_type;
+ *      struct nfs4_string      oti_scsi_device_id;
+ * };// size 4 + [variable]
+ */
+static __be32 *
+__read_targetid(__be32 *p, struct pnfs_osd_targetid* targetid)
+{
+        u32 oti_type;
+
+        oti_type = be32_to_cpup(p++);
+        targetid->oti_type = oti_type;
+
+        switch (oti_type) {
+        case OBJ_TARGET_SCSI_NAME:
+        case OBJ_TARGET_SCSI_DEVICE_ID:
+                p = __read_u8_opaque(p, &targetid->oti_scsi_device_id);
+        }
+
+        return p;
+}
+
+/*
+ * struct pnfs_osd_net_addr {
+ *      struct nfs4_string      r_netid;
+ *      struct nfs4_string      r_addr;
+ * };
+ */
+static __be32 *
+__read_net_addr(__be32 *p, struct pnfs_osd_net_addr* netaddr)
+{
+        p = __read_u8_opaque(p, &netaddr->r_netid);
+        p = __read_u8_opaque(p, &netaddr->r_addr);
+
+        return p;
+}
+
+/*
+ * struct pnfs_osd_targetaddr {
+ *      u32                             ota_available;
+ *      struct pnfs_osd_net_addr        ota_netaddr;
+ * };
+ */
+static __be32 *
+__read_targetaddr(__be32 *p, struct pnfs_osd_targetaddr *targetaddr)
+{
+        u32 ota_available;
+
+        ota_available = be32_to_cpup(p++);
+        targetaddr->ota_available = ota_available;
+
+        if (ota_available)
+                p = __read_net_addr(p, &targetaddr->ota_netaddr);
+
+
+        return p;
+}
+
+/*
+ * struct pnfs_osd_deviceaddr {
+ *      struct pnfs_osd_targetid        oda_targetid;
+ *      struct pnfs_osd_targetaddr      oda_targetaddr;
+ *      u8                              oda_lun[8];
+ *      struct nfs4_string              oda_systemid;
+ *      struct pnfs_osd_object_cred     oda_root_obj_cred;
+ *      struct nfs4_string              oda_osdname;
+ * };
+ */
+
+/* We need this version for the pnfs_osd_xdr_decode_deviceaddr which does
+ * not have an xdr_stream
+ */
+static __be32 *
+__read_opaque_cred(__be32 *p,
+                              struct pnfs_osd_opaque_cred *opaque_cred)
+{
+        opaque_cred->cred_len = be32_to_cpu(*p++);
+        opaque_cred->cred = p;
+        return p + XDR_QUADLEN(opaque_cred->cred_len);
+}
+
+static __be32 *
+__read_object_cred(__be32 *p, struct pnfs_osd_object_cred *comp)
+{
+        p = _osd_xdr_decode_objid(p, &comp->oc_object_id);
+        comp->oc_osd_version = be32_to_cpup(p++);
+        comp->oc_cap_key_sec = be32_to_cpup(p++);
+
+        p = __read_opaque_cred(p, &comp->oc_cap_key);
+        p = __read_opaque_cred(p, &comp->oc_cap);
+        return p;
+}
+
+void pnfs_osd_xdr_decode_deviceaddr(
+        struct pnfs_osd_deviceaddr *deviceaddr, __be32 *p)
+{
+        p = __read_targetid(p, &deviceaddr->oda_targetid);
+
+        p = __read_targetaddr(p, &deviceaddr->oda_targetaddr);
+
+        p = xdr_decode_opaque_fixed(p, deviceaddr->oda_lun,
+                                    sizeof(deviceaddr->oda_lun));
+
+        p = __read_u8_opaque(p, &deviceaddr->oda_systemid);
+
+        p = __read_object_cred(p, &deviceaddr->oda_root_obj_cred);
+
+        p = __read_u8_opaque(p, &deviceaddr->oda_osdname);
+
+        /* libosd likes this terminated in dbg. It's last, so no problems */
+        deviceaddr->oda_osdname.data[deviceaddr->oda_osdname.len] = 0;
+}
+
+/*
+ * struct pnfs_osd_layoutupdate {
+ *      u32     dsu_valid;
+ *      s64     dsu_delta;
+ *      u32     olu_ioerr_flag;
+ * }; xdr size 4 + 8 + 4
+ */
+int
+pnfs_osd_xdr_encode_layoutupdate(struct xdr_stream *xdr,
+                                 struct pnfs_osd_layoutupdate *lou)
+{
+        __be32 *p = xdr_reserve_space(xdr,  4 + 8 + 4);
+
+        if (!p)
+                return -E2BIG;
+
+        *p++ = cpu_to_be32(lou->dsu_valid);
+        if (lou->dsu_valid)
+                p = xdr_encode_hyper(p, lou->dsu_delta);
+        *p++ = cpu_to_be32(lou->olu_ioerr_flag);
+        return 0;
+}
+
+/*
+ * struct pnfs_osd_objid {
+ *      struct nfs4_deviceid    oid_device_id;
+ *      u64                     oid_partition_id;
+ *      u64                     oid_object_id;
+ * }; // xdr size 32 bytes
+ */
+static inline __be32 *
+pnfs_osd_xdr_encode_objid(__be32 *p, struct pnfs_osd_objid *object_id)
+{
+        p = xdr_encode_opaque_fixed(p, &object_id->oid_device_id.data,
+                                    sizeof(object_id->oid_device_id.data));
+        p = xdr_encode_hyper(p, object_id->oid_partition_id);
+        p = xdr_encode_hyper(p, object_id->oid_object_id);
+
+        return p;
+}
+
+/*
+ * struct pnfs_osd_ioerr {
+ *      struct pnfs_osd_objid   oer_component;
+ *      u64                     oer_comp_offset;
+ *      u64                     oer_comp_length;
+ *      u32                     oer_iswrite;
+ *      u32                     oer_errno;
+ * }; // xdr size 32 + 24 bytes
+ */
+void pnfs_osd_xdr_encode_ioerr(__be32 *p, struct pnfs_osd_ioerr *ioerr)
+{
+        p = pnfs_osd_xdr_encode_objid(p, &ioerr->oer_component);
+        p = xdr_encode_hyper(p, ioerr->oer_comp_offset);
+        p = xdr_encode_hyper(p, ioerr->oer_comp_length);
+        *p++ = cpu_to_be32(ioerr->oer_iswrite);
+        *p   = cpu_to_be32(ioerr->oer_errno);
+}
+
+__be32 *pnfs_osd_xdr_ioerr_reserve_space(struct xdr_stream *xdr)
+{
+        __be32 *p;
+
+        p = xdr_reserve_space(xdr, 32 + 24);
+        if (unlikely(!p))
+                dprintk("%s: out of xdr space\n", __func__);
+
+        return p;
+}
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index c80add6e2213..7913961aff22 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -204,6 +204,21 @@ nfs_wait_on_request(struct nfs_page *req)
                         TASK_UNINTERRUPTIBLE);
 }
 
+static bool nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, struct nfs_page *prev, struct nfs_page *req)
+{
+        /*
+         * FIXME: ideally we should be able to coalesce all requests
+         * that are not block boundary aligned, but currently this
+         * is problematic for the case of bsize < PAGE_CACHE_SIZE,
+         * since nfs_flush_multi and nfs_pagein_multi assume you
+         * can have only one struct nfs_page.
+         */
+        if (desc->pg_bsize < PAGE_SIZE)
+                return 0;
+
+        return desc->pg_count + req->wb_bytes <= desc->pg_bsize;
+}
+
 /**
  * nfs_pageio_init - initialise a page io descriptor
  * @desc: pointer to descriptor
@@ -229,6 +244,8 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
         desc->pg_ioflags = io_flags;
         desc->pg_error = 0;
         desc->pg_lseg = NULL;
+        desc->pg_test = nfs_generic_pg_test;
+        pnfs_pageio_init(desc, inode);
 }
 
 /**
@@ -242,29 +259,23 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
  *
  * Return 'true' if this is the case, else return 'false'.
  */
-static int nfs_can_coalesce_requests(struct nfs_page *prev,
-                                     struct nfs_page *req,
-                                     struct nfs_pageio_descriptor *pgio)
+static bool nfs_can_coalesce_requests(struct nfs_page *prev,
+                                      struct nfs_page *req,
+                                      struct nfs_pageio_descriptor *pgio)
 {
         if (req->wb_context->cred != prev->wb_context->cred)
-                return 0;
+                return false;
         if (req->wb_lock_context->lockowner != prev->wb_lock_context->lockowner)
-                return 0;
+                return false;
         if (req->wb_context->state != prev->wb_context->state)
-                return 0;
+                return false;
         if (req->wb_index != (prev->wb_index + 1))
-                return 0;
+                return false;
         if (req->wb_pgbase != 0)
-                return 0;
+                return false;
         if (prev->wb_pgbase + prev->wb_bytes != PAGE_CACHE_SIZE)
-                return 0;
-        /*
-         * Non-whole file layouts need to check that req is inside of
-         * pgio->pg_lseg.
-         */
-        if (pgio->pg_test && !pgio->pg_test(pgio, prev, req))
-                return 0;
-        return 1;
+                return false;
+        return pgio->pg_test(pgio, prev, req);
 }
 
 /**
@@ -278,31 +289,18 @@ static int nfs_can_coalesce_requests(struct nfs_page *prev,
 static int nfs_pageio_do_add_request(struct nfs_pageio_descriptor *desc,
                                      struct nfs_page *req)
 {
-        size_t newlen = req->wb_bytes;
-
         if (desc->pg_count != 0) {
                 struct nfs_page *prev;
 
-                /*
-                 * FIXME: ideally we should be able to coalesce all requests
-                 * that are not block boundary aligned, but currently this
-                 * is problematic for the case of bsize < PAGE_CACHE_SIZE,
-                 * since nfs_flush_multi and nfs_pagein_multi assume you
-                 * can have only one struct nfs_page.
-                 */
-                if (desc->pg_bsize < PAGE_SIZE)
-                        return 0;
-                newlen += desc->pg_count;
-                if (newlen > desc->pg_bsize)
-                        return 0;
                 prev = nfs_list_entry(desc->pg_list.prev);
                 if (!nfs_can_coalesce_requests(prev, req, desc))
                         return 0;
-        } else
+        } else {
                 desc->pg_base = req->wb_pgbase;
+        }
         nfs_list_remove_request(req);
         nfs_list_add_request(req, &desc->pg_list);
-        desc->pg_count = newlen;
+        desc->pg_count += req->wb_bytes;
         return 1;
 }
 
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index f57f5281a520..8c1309d852a6 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -177,13 +177,28 @@ get_layout_hdr(struct pnfs_layout_hdr *lo)
         atomic_inc(&lo->plh_refcount);
 }
 
+static struct pnfs_layout_hdr *
+pnfs_alloc_layout_hdr(struct inode *ino, gfp_t gfp_flags)
+{
+        struct pnfs_layoutdriver_type *ld = NFS_SERVER(ino)->pnfs_curr_ld;
+        return ld->alloc_layout_hdr ? ld->alloc_layout_hdr(ino, gfp_flags) :
+                kzalloc(sizeof(struct pnfs_layout_hdr), gfp_flags);
+}
+
+static void
+pnfs_free_layout_hdr(struct pnfs_layout_hdr *lo)
+{
+        struct pnfs_layoutdriver_type *ld = NFS_SERVER(lo->plh_inode)->pnfs_curr_ld;
+        return ld->alloc_layout_hdr ? ld->free_layout_hdr(lo) : kfree(lo);
+}
+
 static void
 destroy_layout_hdr(struct pnfs_layout_hdr *lo)
 {
         dprintk("%s: freeing layout cache %p\n", __func__, lo);
         BUG_ON(!list_empty(&lo->plh_layouts));
         NFS_I(lo->plh_inode)->layout = NULL;
-        kfree(lo);
+        pnfs_free_layout_hdr(lo);
 }
 
 static void
@@ -228,7 +243,7 @@ put_lseg_common(struct pnfs_layout_segment *lseg)
 {
         struct inode *inode = lseg->pls_layout->plh_inode;
 
-        BUG_ON(test_bit(NFS_LSEG_VALID, &lseg->pls_flags));
+        WARN_ON(test_bit(NFS_LSEG_VALID, &lseg->pls_flags));
         list_del_init(&lseg->pls_list);
         if (list_empty(&lseg->pls_layout->plh_segs)) {
                 set_bit(NFS_LAYOUT_DESTROYED, &lseg->pls_layout->plh_flags);
@@ -261,11 +276,72 @@ put_lseg(struct pnfs_layout_segment *lseg)
 }
 EXPORT_SYMBOL_GPL(put_lseg);
 
+static inline u64
+end_offset(u64 start, u64 len)
+{
+        u64 end;
+
+        end = start + len;
+        return end >= start ? end : NFS4_MAX_UINT64;
+}
+
+/* last octet in a range */
+static inline u64
+last_byte_offset(u64 start, u64 len)
+{
+        u64 end;
+
+        BUG_ON(!len);
+        end = start + len;
+        return end > start ? end - 1 : NFS4_MAX_UINT64;
+}
+
+/*
+ * is l2 fully contained in l1?
+ *   start1                             end1
+ *   [----------------------------------)
+ *           start2           end2
+ *           [----------------)
+ */
+static inline int
+lo_seg_contained(struct pnfs_layout_range *l1,
+                 struct pnfs_layout_range *l2)
+{
+        u64 start1 = l1->offset;
+        u64 end1 = end_offset(start1, l1->length);
+        u64 start2 = l2->offset;
+        u64 end2 = end_offset(start2, l2->length);
+
+        return (start1 <= start2) && (end1 >= end2);
+}
+
+/*
+ * is l1 and l2 intersecting?
+ *   start1                             end1
+ *   [----------------------------------)
+ *                              start2           end2
+ *                              [----------------)
+ */
+static inline int
+lo_seg_intersecting(struct pnfs_layout_range *l1,
+                    struct pnfs_layout_range *l2)
+{
+        u64 start1 = l1->offset;
+        u64 end1 = end_offset(start1, l1->length);
+        u64 start2 = l2->offset;
+        u64 end2 = end_offset(start2, l2->length);
+
+        return (end1 == NFS4_MAX_UINT64 || end1 > start2) &&
+               (end2 == NFS4_MAX_UINT64 || end2 > start1);
+}
+
 static bool
-should_free_lseg(u32 lseg_iomode, u32 recall_iomode)
+should_free_lseg(struct pnfs_layout_range *lseg_range,
+                 struct pnfs_layout_range *recall_range)
 {
-        return (recall_iomode == IOMODE_ANY ||
-                lseg_iomode == recall_iomode);
+        return (recall_range->iomode == IOMODE_ANY ||
+                lseg_range->iomode == recall_range->iomode) &&
+               lo_seg_intersecting(lseg_range, recall_range);
 }
 
 /* Returns 1 if lseg is removed from list, 0 otherwise */
@@ -296,7 +372,7 @@ static int mark_lseg_invalid(struct pnfs_layout_segment *lseg,
 int
 mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
                             struct list_head *tmp_list,
-                            u32 iomode)
+                            struct pnfs_layout_range *recall_range)
 {
         struct pnfs_layout_segment *lseg, *next;
         int invalid = 0, removed = 0;
@@ -309,7 +385,8 @@ mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
                 return 0;
         }
         list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list)
-                if (should_free_lseg(lseg->pls_range.iomode, iomode)) {
+                if (!recall_range ||
+                    should_free_lseg(&lseg->pls_range, recall_range)) {
                         dprintk("%s: freeing lseg %p iomode %d "
                                 "offset %llu length %llu\n", __func__,
                                 lseg, lseg->pls_range.iomode, lseg->pls_range.offset,
@@ -358,7 +435,7 @@ pnfs_destroy_layout(struct nfs_inode *nfsi)
         lo = nfsi->layout;
         if (lo) {
                 lo->plh_block_lgets++; /* permanently block new LAYOUTGETs */
-                mark_matching_lsegs_invalid(lo, &tmp_list, IOMODE_ANY);
+                mark_matching_lsegs_invalid(lo, &tmp_list, NULL);
         }
         spin_unlock(&nfsi->vfs_inode.i_lock);
         pnfs_free_lseg_list(&tmp_list);
@@ -467,7 +544,7 @@ pnfs_choose_layoutget_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo,
 static struct pnfs_layout_segment *
 send_layoutget(struct pnfs_layout_hdr *lo,
            struct nfs_open_context *ctx,
-           u32 iomode,
+           struct pnfs_layout_range *range,
            gfp_t gfp_flags)
 {
         struct inode *ino = lo->plh_inode;
@@ -499,11 +576,11 @@ send_layoutget(struct pnfs_layout_hdr *lo,
                         goto out_err_free;
         }
 
-        lgp->args.minlength = NFS4_MAX_UINT64;
+        lgp->args.minlength = PAGE_CACHE_SIZE;
+        if (lgp->args.minlength > range->length)
+                lgp->args.minlength = range->length;
         lgp->args.maxcount = PNFS_LAYOUT_MAXSIZE;
-        lgp->args.range.iomode = iomode;
-        lgp->args.range.offset = 0;
-        lgp->args.range.length = NFS4_MAX_UINT64;
+        lgp->args.range = *range;
         lgp->args.type = server->pnfs_curr_ld->id;
         lgp->args.inode = ino;
         lgp->args.ctx = get_nfs_open_context(ctx);
@@ -518,7 +595,7 @@ send_layoutget(struct pnfs_layout_hdr *lo,
         nfs4_proc_layoutget(lgp);
         if (!lseg) {
                 /* remember that LAYOUTGET failed and suspend trying */
-                set_bit(lo_fail_bit(iomode), &lo->plh_flags);
+                set_bit(lo_fail_bit(range->iomode), &lo->plh_flags);
         }
 
         /* free xdr pages */
@@ -542,6 +619,51 @@ out_err_free:
         return NULL;
 }
 
+/* Initiates a LAYOUTRETURN(FILE) */
+int
+_pnfs_return_layout(struct inode *ino)
+{
+        struct pnfs_layout_hdr *lo = NULL;
+        struct nfs_inode *nfsi = NFS_I(ino);
+        LIST_HEAD(tmp_list);
+        struct nfs4_layoutreturn *lrp;
+        nfs4_stateid stateid;
+        int status = 0;
+
+        dprintk("--> %s\n", __func__);
+
+        spin_lock(&ino->i_lock);
+        lo = nfsi->layout;
+        if (!lo || !mark_matching_lsegs_invalid(lo, &tmp_list, NULL)) {
+                spin_unlock(&ino->i_lock);
+                dprintk("%s: no layout segments to return\n", __func__);
+                goto out;
+        }
+        stateid = nfsi->layout->plh_stateid;
+        /* Reference matched in nfs4_layoutreturn_release */
+        get_layout_hdr(lo);
+        spin_unlock(&ino->i_lock);
+        pnfs_free_lseg_list(&tmp_list);
+
+        WARN_ON(test_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags));
+
+        lrp = kzalloc(sizeof(*lrp), GFP_KERNEL);
+        if (unlikely(lrp == NULL)) {
+                status = -ENOMEM;
+                goto out;
+        }
+
+        lrp->args.stateid = stateid;
+        lrp->args.layout_type = NFS_SERVER(ino)->pnfs_curr_ld->id;
+        lrp->args.inode = ino;
+        lrp->clp = NFS_SERVER(ino)->nfs_client;
+
+        status = nfs4_proc_layoutreturn(lrp);
+out:
+        dprintk("<-- %s status: %d\n", __func__, status);
+        return status;
+}
+
 bool pnfs_roc(struct inode *ino)
 {
         struct pnfs_layout_hdr *lo;
@@ -625,10 +747,23 @@ bool pnfs_roc_drain(struct inode *ino, u32 *barrier)
  * are seen first.
  */
 static s64
-cmp_layout(u32 iomode1, u32 iomode2)
+cmp_layout(struct pnfs_layout_range *l1,
+           struct pnfs_layout_range *l2)
 {
+        s64 d;
+
+        /* high offset > low offset */
+        d = l1->offset - l2->offset;
+        if (d)
+                return d;
+
+        /* short length > long length */
+        d = l2->length - l1->length;
+        if (d)
+                return d;
+
         /* read > read/write */
-        return (int)(iomode2 == IOMODE_READ) - (int)(iomode1 == IOMODE_READ);
+        return (int)(l1->iomode == IOMODE_READ) - (int)(l2->iomode == IOMODE_READ);
 }
 
 static void
@@ -636,13 +771,12 @@ pnfs_insert_layout(struct pnfs_layout_hdr *lo,
                    struct pnfs_layout_segment *lseg)
 {
         struct pnfs_layout_segment *lp;
-        int found = 0;
 
         dprintk("%s:Begin\n", __func__);
 
         assert_spin_locked(&lo->plh_inode->i_lock);
         list_for_each_entry(lp, &lo->plh_segs, pls_list) {
-                if (cmp_layout(lp->pls_range.iomode, lseg->pls_range.iomode) > 0)
+                if (cmp_layout(&lseg->pls_range, &lp->pls_range) > 0)
                         continue;
                 list_add_tail(&lseg->pls_list, &lp->pls_list);
                 dprintk("%s: inserted lseg %p "
@@ -652,16 +786,14 @@ pnfs_insert_layout(struct pnfs_layout_hdr *lo,
                         lseg->pls_range.offset, lseg->pls_range.length,
                         lp, lp->pls_range.iomode, lp->pls_range.offset,
                         lp->pls_range.length);
-                found = 1;
-                break;
-        }
-        if (!found) {
-                list_add_tail(&lseg->pls_list, &lo->plh_segs);
-                dprintk("%s: inserted lseg %p "
-                        "iomode %d offset %llu length %llu at tail\n",
-                        __func__, lseg, lseg->pls_range.iomode,
-                        lseg->pls_range.offset, lseg->pls_range.length);
+                goto out;
         }
+        list_add_tail(&lseg->pls_list, &lo->plh_segs);
+        dprintk("%s: inserted lseg %p "
+                "iomode %d offset %llu length %llu at tail\n",
+                __func__, lseg, lseg->pls_range.iomode,
+                lseg->pls_range.offset, lseg->pls_range.length);
+out:
         get_layout_hdr(lo);
 
         dprintk("%s:Return\n", __func__);
@@ -672,7 +804,7 @@ alloc_init_layout_hdr(struct inode *ino, gfp_t gfp_flags)
 {
         struct pnfs_layout_hdr *lo;
 
-        lo = kzalloc(sizeof(struct pnfs_layout_hdr), gfp_flags);
+        lo = pnfs_alloc_layout_hdr(ino, gfp_flags);
         if (!lo)
                 return NULL;
         atomic_set(&lo->plh_refcount, 1);
@@ -705,7 +837,7 @@ pnfs_find_alloc_layout(struct inode *ino, gfp_t gfp_flags)
         if (likely(nfsi->layout == NULL))       /* Won the race? */
                 nfsi->layout = new;
         else
-                kfree(new);
+                pnfs_free_layout_hdr(new);
         return nfsi->layout;
 }
 
@@ -721,16 +853,28 @@ pnfs_find_alloc_layout(struct inode *ino, gfp_t gfp_flags)
  * READ         RW      true
  */
 static int
-is_matching_lseg(struct pnfs_layout_segment *lseg, u32 iomode)
+is_matching_lseg(struct pnfs_layout_range *ls_range,
+                 struct pnfs_layout_range *range)
 {
-        return (iomode != IOMODE_RW || lseg->pls_range.iomode == IOMODE_RW);
+        struct pnfs_layout_range range1;
+
+        if ((range->iomode == IOMODE_RW &&
+             ls_range->iomode != IOMODE_RW) ||
+            !lo_seg_intersecting(ls_range, range))
+                return 0;
+
+        /* range1 covers only the first byte in the range */
+        range1 = *range;
+        range1.length = 1;
+        return lo_seg_contained(ls_range, &range1);
 }
 
 /*
  * lookup range in layout
  */
 static struct pnfs_layout_segment *
-pnfs_find_lseg(struct pnfs_layout_hdr *lo, u32 iomode)
+pnfs_find_lseg(struct pnfs_layout_hdr *lo,
+                struct pnfs_layout_range *range)
 {
         struct pnfs_layout_segment *lseg, *ret = NULL;
 
@@ -739,11 +883,11 @@ pnfs_find_lseg(struct pnfs_layout_hdr *lo, u32 iomode)
         assert_spin_locked(&lo->plh_inode->i_lock);
         list_for_each_entry(lseg, &lo->plh_segs, pls_list) {
                 if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags) &&
-                    is_matching_lseg(lseg, iomode)) {
+                    is_matching_lseg(&lseg->pls_range, range)) {
                         ret = get_lseg(lseg);
                         break;
                 }
-                if (cmp_layout(iomode, lseg->pls_range.iomode) > 0)
+                if (cmp_layout(range, &lseg->pls_range) > 0)
                         break;
         }
 
@@ -759,9 +903,17 @@ pnfs_find_lseg(struct pnfs_layout_hdr *lo, u32 iomode)
 struct pnfs_layout_segment *
 pnfs_update_layout(struct inode *ino,
                    struct nfs_open_context *ctx,
+                   loff_t pos,
+                   u64 count,
                    enum pnfs_iomode iomode,
                    gfp_t gfp_flags)
 {
+        struct pnfs_layout_range arg = {
+                .iomode = iomode,
+                .offset = pos,
+                .length = count,
+        };
+        unsigned pg_offset;
         struct nfs_inode *nfsi = NFS_I(ino);
         struct nfs_client *clp = NFS_SERVER(ino)->nfs_client;
         struct pnfs_layout_hdr *lo;
@@ -789,7 +941,7 @@ pnfs_update_layout(struct inode *ino,
                 goto out_unlock;
 
         /* Check to see if the layout for the given range already exists */
-        lseg = pnfs_find_lseg(lo, iomode);
+        lseg = pnfs_find_lseg(lo, &arg);
         if (lseg)
                 goto out_unlock;
 
@@ -811,7 +963,14 @@ pnfs_update_layout(struct inode *ino,
                 spin_unlock(&clp->cl_lock);
         }
 
-        lseg = send_layoutget(lo, ctx, iomode, gfp_flags);
+        pg_offset = arg.offset & ~PAGE_CACHE_MASK;
+        if (pg_offset) {
+                arg.offset -= pg_offset;
+                arg.length += pg_offset;
+        }
+        arg.length = PAGE_CACHE_ALIGN(arg.length);
+
+        lseg = send_layoutget(lo, ctx, &arg, gfp_flags);
         if (!lseg && first) {
                 spin_lock(&clp->cl_lock);
                 list_del_init(&lo->plh_layouts);
@@ -838,17 +997,6 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
         struct nfs_client *clp = NFS_SERVER(ino)->nfs_client;
         int status = 0;
 
-        /* Verify we got what we asked for.
-         * Note that because the xdr parsing only accepts a single
-         * element array, this can fail even if the server is behaving
-         * correctly.
-         */
-        if (lgp->args.range.iomode > res->range.iomode ||
-            res->range.offset != 0 ||
-            res->range.length != NFS4_MAX_UINT64) {
-                status = -EINVAL;
-                goto out;
-        }
         /* Inject layout blob into I/O device driver */
         lseg = NFS_SERVER(ino)->pnfs_curr_ld->alloc_lseg(lo, res, lgp->gfp_flags);
         if (!lseg || IS_ERR(lseg)) {
@@ -895,51 +1043,64 @@ out_forget_reply:
         goto out;
 }
 
-static int pnfs_read_pg_test(struct nfs_pageio_descriptor *pgio,
-                             struct nfs_page *prev,
-                             struct nfs_page *req)
+bool
+pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
+                     struct nfs_page *req)
 {
+        enum pnfs_iomode access_type;
+        gfp_t gfp_flags;
+
+        /* We assume that pg_ioflags == 0 iff we're reading a page */
+        if (pgio->pg_ioflags == 0) {
+                access_type = IOMODE_READ;
+                gfp_flags = GFP_KERNEL;
+        } else {
+                access_type = IOMODE_RW;
+                gfp_flags = GFP_NOFS;
+        }
+
         if (pgio->pg_count == prev->wb_bytes) {
                 /* This is first coelesce call for a series of nfs_pages */
                 pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
                                                    prev->wb_context,
-                                                   IOMODE_READ,
-                                                   GFP_KERNEL);
+                                                   req_offset(req),
+                                                   pgio->pg_count,
+                                                   access_type,
+                                                   gfp_flags);
+                return true;
         }
-        return NFS_SERVER(pgio->pg_inode)->pnfs_curr_ld->pg_test(pgio, prev, req);
-}
 
-void
-pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode)
-{
-        struct pnfs_layoutdriver_type *ld;
+        if (pgio->pg_lseg &&
+            req_offset(req) > end_offset(pgio->pg_lseg->pls_range.offset,
+                                         pgio->pg_lseg->pls_range.length))
+                return false;
 
-        ld = NFS_SERVER(inode)->pnfs_curr_ld;
-        pgio->pg_test = (ld && ld->pg_test) ? pnfs_read_pg_test : NULL;
+        return true;
 }
+EXPORT_SYMBOL_GPL(pnfs_generic_pg_test);
 
-static int pnfs_write_pg_test(struct nfs_pageio_descriptor *pgio,
-                              struct nfs_page *prev,
-                              struct nfs_page *req)
+/*
+ * Called by non rpc-based layout drivers
+ */
+int
+pnfs_ld_write_done(struct nfs_write_data *data)
 {
-        if (pgio->pg_count == prev->wb_bytes) {
-                /* This is first coelesce call for a series of nfs_pages */
-                pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
-                                                   prev->wb_context,
-                                                   IOMODE_RW,
-                                                   GFP_NOFS);
-        }
-        return NFS_SERVER(pgio->pg_inode)->pnfs_curr_ld->pg_test(pgio, prev, req);
-}
+        int status;
 
-void
-pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode)
-{
-        struct pnfs_layoutdriver_type *ld;
+        if (!data->pnfs_error) {
+                pnfs_set_layoutcommit(data);
+                data->mds_ops->rpc_call_done(&data->task, data);
+                data->mds_ops->rpc_release(data);
+                return 0;
+        }
 
-        ld = NFS_SERVER(inode)->pnfs_curr_ld;
-        pgio->pg_test = (ld && ld->pg_test) ? pnfs_write_pg_test : NULL;
+        dprintk("%s: pnfs_error=%d, retry via MDS\n", __func__,
+                data->pnfs_error);
+        status = nfs_initiate_write(data, NFS_CLIENT(data->inode),
+                                    data->mds_ops, NFS_FILE_SYNC);
+        return status ? : -EAGAIN;
 }
+EXPORT_SYMBOL_GPL(pnfs_ld_write_done);
 
 enum pnfs_try_status
 pnfs_try_to_write_data(struct nfs_write_data *wdata,
@@ -966,6 +1127,29 @@ pnfs_try_to_write_data(struct nfs_write_data *wdata,
 }
 
 /*
+ * Called by non rpc-based layout drivers
+ */
+int
+pnfs_ld_read_done(struct nfs_read_data *data)
+{
+        int status;
+
+        if (!data->pnfs_error) {
+                __nfs4_read_done_cb(data);
+                data->mds_ops->rpc_call_done(&data->task, data);
+                data->mds_ops->rpc_release(data);
+                return 0;
+        }
+
+        dprintk("%s: pnfs_error=%d, retry via MDS\n", __func__,
+                data->pnfs_error);
+        status = nfs_initiate_read(data, NFS_CLIENT(data->inode),
+                                   data->mds_ops);
+        return status ? : -EAGAIN;
+}
+EXPORT_SYMBOL_GPL(pnfs_ld_read_done);
+
+/*
  * Call the appropriate parallel I/O subsystem read function.
  */
 enum pnfs_try_status
@@ -1009,7 +1193,7 @@ void
 pnfs_set_layoutcommit(struct nfs_write_data *wdata)
 {
         struct nfs_inode *nfsi = NFS_I(wdata->inode);
-        loff_t end_pos = wdata->args.offset + wdata->res.count;
+        loff_t end_pos = wdata->mds_offset + wdata->res.count;
         bool mark_as_dirty = false;
 
         spin_lock(&nfsi->vfs_inode.i_lock);
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 0c015bad9e7a..48d0a8e4d062 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -30,6 +30,7 @@
 #ifndef FS_NFS_PNFS_H
 #define FS_NFS_PNFS_H
 
+#include <linux/nfs_fs.h>
 #include <linux/nfs_page.h>
 
 enum {
@@ -64,17 +65,29 @@ enum {
         NFS_LAYOUT_DESTROYED,           /* no new use of layout allowed */
 };
 
+enum layoutdriver_policy_flags {
+        /* Should the pNFS client commit and return the layout upon a setattr */
+        PNFS_LAYOUTRET_ON_SETATTR       = 1 << 0,
+};
+
+struct nfs4_deviceid_node;
+
 /* Per-layout driver specific registration structure */
 struct pnfs_layoutdriver_type {
         struct list_head pnfs_tblid;
         const u32 id;
         const char *name;
         struct module *owner;
+        unsigned flags;
+
+        struct pnfs_layout_hdr * (*alloc_layout_hdr) (struct inode *inode, gfp_t gfp_flags);
+        void (*free_layout_hdr) (struct pnfs_layout_hdr *);
+
         struct pnfs_layout_segment * (*alloc_lseg) (struct pnfs_layout_hdr *layoutid, struct nfs4_layoutget_res *lgr, gfp_t gfp_flags);
         void (*free_lseg) (struct pnfs_layout_segment *lseg);
 
         /* test for nfs page cache coalescing */
-        int (*pg_test)(struct nfs_pageio_descriptor *, struct nfs_page *, struct nfs_page *);
+        bool (*pg_test)(struct nfs_pageio_descriptor *, struct nfs_page *, struct nfs_page *);
 
         /* Returns true if layoutdriver wants to divert this request to
          * driver's commit routine.
@@ -89,6 +102,16 @@ struct pnfs_layoutdriver_type {
          */
         enum pnfs_try_status (*read_pagelist) (struct nfs_read_data *nfs_data);
         enum pnfs_try_status (*write_pagelist) (struct nfs_write_data *nfs_data, int how);
+
+        void (*free_deviceid_node) (struct nfs4_deviceid_node *);
+
+        void (*encode_layoutreturn) (struct pnfs_layout_hdr *layoutid,
+                                     struct xdr_stream *xdr,
+                                     const struct nfs4_layoutreturn_args *args);
+
+        void (*encode_layoutcommit) (struct pnfs_layout_hdr *layoutid,
+                                     struct xdr_stream *xdr,
+                                     const struct nfs4_layoutcommit_args *args);
 };
 
 struct pnfs_layout_hdr {
@@ -120,21 +143,22 @@ extern void pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *);
 extern int nfs4_proc_getdeviceinfo(struct nfs_server *server,
                                    struct pnfs_device *dev);
 extern int nfs4_proc_layoutget(struct nfs4_layoutget *lgp);
+extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp);
 
 /* pnfs.c */
 void get_layout_hdr(struct pnfs_layout_hdr *lo);
 void put_lseg(struct pnfs_layout_segment *lseg);
 struct pnfs_layout_segment *
 pnfs_update_layout(struct inode *ino, struct nfs_open_context *ctx,
-                   enum pnfs_iomode access_type, gfp_t gfp_flags);
+                   loff_t pos, u64 count, enum pnfs_iomode access_type,
+                   gfp_t gfp_flags);
 void set_pnfs_layoutdriver(struct nfs_server *, u32 id);
 void unset_pnfs_layoutdriver(struct nfs_server *);
 enum pnfs_try_status pnfs_try_to_write_data(struct nfs_write_data *,
                                              const struct rpc_call_ops *, int);
 enum pnfs_try_status pnfs_try_to_read_data(struct nfs_read_data *,
                                             const struct rpc_call_ops *);
-void pnfs_pageio_init_read(struct nfs_pageio_descriptor *, struct inode *);
-void pnfs_pageio_init_write(struct nfs_pageio_descriptor *, struct inode *);
+bool pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, struct nfs_page *req);
 int pnfs_layout_process(struct nfs4_layoutget *lgp);
 void pnfs_free_lseg_list(struct list_head *tmp_list);
 void pnfs_destroy_layout(struct nfs_inode *);
@@ -148,13 +172,37 @@ int pnfs_choose_layoutget_stateid(nfs4_stateid *dst,
                                   struct nfs4_state *open_state);
 int mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
                                 struct list_head *tmp_list,
-                                u32 iomode);
+                                struct pnfs_layout_range *recall_range);
 bool pnfs_roc(struct inode *ino);
 void pnfs_roc_release(struct inode *ino);
 void pnfs_roc_set_barrier(struct inode *ino, u32 barrier);
 bool pnfs_roc_drain(struct inode *ino, u32 *barrier);
 void pnfs_set_layoutcommit(struct nfs_write_data *wdata);
 int pnfs_layoutcommit_inode(struct inode *inode, bool sync);
+int _pnfs_return_layout(struct inode *);
+int pnfs_ld_write_done(struct nfs_write_data *);
+int pnfs_ld_read_done(struct nfs_read_data *);
+
+/* pnfs_dev.c */
+struct nfs4_deviceid_node {
+        struct hlist_node               node;
+        const struct pnfs_layoutdriver_type *ld;
+        const struct nfs_client         *nfs_client;
+        struct nfs4_deviceid            deviceid;
+        atomic_t                        ref;
+};
+
+void nfs4_print_deviceid(const struct nfs4_deviceid *dev_id);
+struct nfs4_deviceid_node *nfs4_find_get_deviceid(const struct pnfs_layoutdriver_type *, const struct nfs_client *, const struct nfs4_deviceid *);
+struct nfs4_deviceid_node *nfs4_unhash_put_deviceid(const struct pnfs_layoutdriver_type *, const struct nfs_client *, const struct nfs4_deviceid *);
+void nfs4_delete_deviceid(const struct pnfs_layoutdriver_type *, const struct nfs_client *, const struct nfs4_deviceid *);
+void nfs4_init_deviceid_node(struct nfs4_deviceid_node *,
+                             const struct pnfs_layoutdriver_type *,
+                             const struct nfs_client *,
+                             const struct nfs4_deviceid *);
+struct nfs4_deviceid_node *nfs4_insert_deviceid_node(struct nfs4_deviceid_node *);
+bool nfs4_put_deviceid_node(struct nfs4_deviceid_node *);
+void nfs4_deviceid_purge_client(const struct nfs_client *);
 
 static inline int lo_fail_bit(u32 iomode)
 {
@@ -223,6 +271,36 @@ static inline void pnfs_clear_request_commit(struct nfs_page *req)
                 put_lseg(req->wb_commit_lseg);
 }
 
+/* Should the pNFS client commit and return the layout upon a setattr */
+static inline bool
+pnfs_ld_layoutret_on_setattr(struct inode *inode)
+{
+        if (!pnfs_enabled_sb(NFS_SERVER(inode)))
+                return false;
+        return NFS_SERVER(inode)->pnfs_curr_ld->flags &
+                PNFS_LAYOUTRET_ON_SETATTR;
+}
+
+static inline int pnfs_return_layout(struct inode *ino)
+{
+        struct nfs_inode *nfsi = NFS_I(ino);
+        struct nfs_server *nfss = NFS_SERVER(ino);
+
+        if (pnfs_enabled_sb(nfss) && nfsi->layout)
+                return _pnfs_return_layout(ino);
+
+        return 0;
+}
+
+static inline void pnfs_pageio_init(struct nfs_pageio_descriptor *pgio,
+                                    struct inode *inode)
+{
+        struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
+
+        if (ld)
+                pgio->pg_test = ld->pg_test;
+}
+
 #else  /* CONFIG_NFS_V4_1 */
 
 static inline void pnfs_destroy_all_layouts(struct nfs_client *clp)
@@ -245,7 +323,8 @@ static inline void put_lseg(struct pnfs_layout_segment *lseg)
 
 static inline struct pnfs_layout_segment *
 pnfs_update_layout(struct inode *ino, struct nfs_open_context *ctx,
-                   enum pnfs_iomode access_type, gfp_t gfp_flags)
+                   loff_t pos, u64 count, enum pnfs_iomode access_type,
+                   gfp_t gfp_flags)
 {
         return NULL;
 }
@@ -264,6 +343,17 @@ pnfs_try_to_write_data(struct nfs_write_data *data,
         return PNFS_NOT_ATTEMPTED;
 }
 
+static inline int pnfs_return_layout(struct inode *ino)
+{
+        return 0;
+}
+
+static inline bool
+pnfs_ld_layoutret_on_setattr(struct inode *inode)
+{
+        return false;
+}
+
 static inline bool
 pnfs_roc(struct inode *ino)
 {
@@ -294,16 +384,9 @@ static inline void unset_pnfs_layoutdriver(struct nfs_server *s)
 {
 }
 
-static inline void
-pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *ino)
-{
-        pgio->pg_test = NULL;
-}
-
-static inline void
-pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *ino)
+static inline void pnfs_pageio_init(struct nfs_pageio_descriptor *pgio,
+                                    struct inode *inode)
 {
-        pgio->pg_test = NULL;
 }
 
 static inline void
@@ -331,6 +414,10 @@ static inline int pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 {
         return 0;
 }
+
+static inline void nfs4_deviceid_purge_client(struct nfs_client *ncl)
+{
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 #endif /* FS_NFS_PNFS_H */
diff --git a/fs/nfs/pnfs_dev.c b/fs/nfs/pnfs_dev.c
new file mode 100644
index 000000000000..c65e133ce9c0
--- /dev/null
+++ b/fs/nfs/pnfs_dev.c
@@ -0,0 +1,270 @@
+/*
+ *  Device operations for the pnfs client.
+ *
+ *  Copyright (c) 2002
+ *  The Regents of the University of Michigan
+ *  All Rights Reserved
+ *
+ *  Dean Hildebrand <dhildebz@umich.edu>
+ *  Garth Goodson   <Garth.Goodson@netapp.com>
+ *
+ *  Permission is granted to use, copy, create derivative works, and
+ *  redistribute this software and such derivative works for any purpose,
+ *  so long as the name of the University of Michigan is not used in
+ *  any advertising or publicity pertaining to the use or distribution
+ *  of this software without specific, written prior authorization. If
+ *  the above copyright notice or any other identification of the
+ *  University of Michigan is included in any copy of any portion of
+ *  this software, then the disclaimer below must also be included.
+ *
+ *  This software is provided as is, without representation or warranty
+ *  of any kind either express or implied, including without limitation
+ *  the implied warranties of merchantability, fitness for a particular
+ *  purpose, or noninfringement.  The Regents of the University of
+ *  Michigan shall not be liable for any damages, including special,
+ *  indirect, incidental, or consequential damages, with respect to any
+ *  claim arising out of or in connection with the use of the software,
+ *  even if it has been or is hereafter advised of the possibility of
+ *  such damages.
+ */
+
+#include "pnfs.h"
+
+#define NFSDBG_FACILITY         NFSDBG_PNFS
+
+/*
+ * Device ID RCU cache. A device ID is unique per server and layout type.
+ */
+#define NFS4_DEVICE_ID_HASH_BITS        5
+#define NFS4_DEVICE_ID_HASH_SIZE        (1 << NFS4_DEVICE_ID_HASH_BITS)
+#define NFS4_DEVICE_ID_HASH_MASK        (NFS4_DEVICE_ID_HASH_SIZE - 1)
+
+static struct hlist_head nfs4_deviceid_cache[NFS4_DEVICE_ID_HASH_SIZE];
+static DEFINE_SPINLOCK(nfs4_deviceid_lock);
+
+void
+nfs4_print_deviceid(const struct nfs4_deviceid *id)
+{
+        u32 *p = (u32 *)id;
+
+        dprintk("%s: device id= [%x%x%x%x]\n", __func__,
+                p[0], p[1], p[2], p[3]);
+}
+EXPORT_SYMBOL_GPL(nfs4_print_deviceid);
+
+static inline u32
+nfs4_deviceid_hash(const struct nfs4_deviceid *id)
+{
+        unsigned char *cptr = (unsigned char *)id->data;
+        unsigned int nbytes = NFS4_DEVICEID4_SIZE;
+        u32 x = 0;
+
+        while (nbytes--) {
+                x *= 37;
+                x += *cptr++;
+        }
+        return x & NFS4_DEVICE_ID_HASH_MASK;
+}
+
+static struct nfs4_deviceid_node *
+_lookup_deviceid(const struct pnfs_layoutdriver_type *ld,
+                 const struct nfs_client *clp, const struct nfs4_deviceid *id,
+                 long hash)
+{
+        struct nfs4_deviceid_node *d;
+        struct hlist_node *n;
+
+        hlist_for_each_entry_rcu(d, n, &nfs4_deviceid_cache[hash], node)
+                if (d->ld == ld && d->nfs_client == clp &&
+                    !memcmp(&d->deviceid, id, sizeof(*id))) {
+                        if (atomic_read(&d->ref))
+                                return d;
+                        else
+                                continue;
+                }
+        return NULL;
+}
+
+/*
+ * Lookup a deviceid in cache and get a reference count on it if found
+ *
+ * @clp nfs_client associated with deviceid
+ * @id deviceid to look up
+ */
+struct nfs4_deviceid_node *
+_find_get_deviceid(const struct pnfs_layoutdriver_type *ld,
+                   const struct nfs_client *clp, const struct nfs4_deviceid *id,
+                   long hash)
+{
+        struct nfs4_deviceid_node *d;
+
+        rcu_read_lock();
+        d = _lookup_deviceid(ld, clp, id, hash);
+        if (d && !atomic_inc_not_zero(&d->ref))
+                d = NULL;
+        rcu_read_unlock();
+        return d;
+}
+
+struct nfs4_deviceid_node *
+nfs4_find_get_deviceid(const struct pnfs_layoutdriver_type *ld,
+                       const struct nfs_client *clp, const struct nfs4_deviceid *id)
+{
+        return _find_get_deviceid(ld, clp, id, nfs4_deviceid_hash(id));
+}
+EXPORT_SYMBOL_GPL(nfs4_find_get_deviceid);
+
+/*
+ * Unhash and put deviceid
+ *
+ * @clp nfs_client associated with deviceid
+ * @id the deviceid to unhash
+ *
+ * @ret the unhashed node, if found and dereferenced to zero, NULL otherwise.
+ */
+struct nfs4_deviceid_node *
+nfs4_unhash_put_deviceid(const struct pnfs_layoutdriver_type *ld,
+                         const struct nfs_client *clp, const struct nfs4_deviceid *id)
+{
+        struct nfs4_deviceid_node *d;
+
+        spin_lock(&nfs4_deviceid_lock);
+        rcu_read_lock();
+        d = _lookup_deviceid(ld, clp, id, nfs4_deviceid_hash(id));
+        rcu_read_unlock();
+        if (!d) {
+                spin_unlock(&nfs4_deviceid_lock);
+                return NULL;
+        }
+        hlist_del_init_rcu(&d->node);
+        spin_unlock(&nfs4_deviceid_lock);
+        synchronize_rcu();
+
+        /* balance the initial ref set in pnfs_insert_deviceid */
+        if (atomic_dec_and_test(&d->ref))
+                return d;
+
+        return NULL;
+}
+EXPORT_SYMBOL_GPL(nfs4_unhash_put_deviceid);
+
+/*
+ * Delete a deviceid from cache
+ *
+ * @clp struct nfs_client qualifying the deviceid
+ * @id deviceid to delete
+ */
+void
+nfs4_delete_deviceid(const struct pnfs_layoutdriver_type *ld,
+                     const struct nfs_client *clp, const struct nfs4_deviceid *id)
+{
+        struct nfs4_deviceid_node *d;
+
+        d = nfs4_unhash_put_deviceid(ld, clp, id);
+        if (!d)
+                return;
+        d->ld->free_deviceid_node(d);
+}
+EXPORT_SYMBOL_GPL(nfs4_delete_deviceid);
+
+void
+nfs4_init_deviceid_node(struct nfs4_deviceid_node *d,
+                        const struct pnfs_layoutdriver_type *ld,
+                        const struct nfs_client *nfs_client,
+                        const struct nfs4_deviceid *id)
+{
+        INIT_HLIST_NODE(&d->node);
+        d->ld = ld;
+        d->nfs_client = nfs_client;
+        d->deviceid = *id;
+        atomic_set(&d->ref, 1);
+}
+EXPORT_SYMBOL_GPL(nfs4_init_deviceid_node);
+
+/*
+ * Uniquely initialize and insert a deviceid node into cache
+ *
+ * @new new deviceid node
+ *      Note that the caller must set up the following members:
+ *        new->ld
+ *        new->nfs_client
+ *        new->deviceid
+ *
+ * @ret the inserted node, if none found, otherwise, the found entry.
+ */
+struct nfs4_deviceid_node *
+nfs4_insert_deviceid_node(struct nfs4_deviceid_node *new)
+{
+        struct nfs4_deviceid_node *d;
+        long hash;
+
+        spin_lock(&nfs4_deviceid_lock);
+        hash = nfs4_deviceid_hash(&new->deviceid);
+        d = _find_get_deviceid(new->ld, new->nfs_client, &new->deviceid, hash);
+        if (d) {
+                spin_unlock(&nfs4_deviceid_lock);
+                return d;
+        }
+
+        hlist_add_head_rcu(&new->node, &nfs4_deviceid_cache[hash]);
+        spin_unlock(&nfs4_deviceid_lock);
+
+        return new;
+}
+EXPORT_SYMBOL_GPL(nfs4_insert_deviceid_node);
+
+/*
+ * Dereference a deviceid node and delete it when its reference count drops
+ * to zero.
+ *
+ * @d deviceid node to put
+ *
+ * @ret true iff the node was deleted
+ */
+bool
+nfs4_put_deviceid_node(struct nfs4_deviceid_node *d)
+{
+        if (!atomic_dec_and_lock(&d->ref, &nfs4_deviceid_lock))
+                return false;
+        hlist_del_init_rcu(&d->node);
+        spin_unlock(&nfs4_deviceid_lock);
+        synchronize_rcu();
+        d->ld->free_deviceid_node(d);
+        return true;
+}
+EXPORT_SYMBOL_GPL(nfs4_put_deviceid_node);
+
+static void
+_deviceid_purge_client(const struct nfs_client *clp, long hash)
+{
+        struct nfs4_deviceid_node *d;
+        struct hlist_node *n, *next;
+        HLIST_HEAD(tmp);
+
+        rcu_read_lock();
+        hlist_for_each_entry_rcu(d, n, &nfs4_deviceid_cache[hash], node)
+                if (d->nfs_client == clp && atomic_read(&d->ref)) {
+                        hlist_del_init_rcu(&d->node);
+                        hlist_add_head(&d->node, &tmp);
+                }
+        rcu_read_unlock();
+
+        if (hlist_empty(&tmp))
+                return;
+
+        synchronize_rcu();
+        hlist_for_each_entry_safe(d, n, next, &tmp, node)
+                if (atomic_dec_and_test(&d->ref))
+                        d->ld->free_deviceid_node(d);
+}
+
+void
+nfs4_deviceid_purge_client(const struct nfs_client *clp)
+{
+        long h;
+
+        spin_lock(&nfs4_deviceid_lock);
+        for (h = 0; h < NFS4_DEVICE_ID_HASH_SIZE; h++)
+                _deviceid_purge_client(clp, h);
+        spin_unlock(&nfs4_deviceid_lock);
+}
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 2bcf0dc306a1..20a7f952e244 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -288,7 +288,9 @@ static int nfs_pagein_multi(struct nfs_pageio_descriptor *desc)
         atomic_set(&req->wb_complete, requests);
 
         BUG_ON(desc->pg_lseg != NULL);
-        lseg = pnfs_update_layout(desc->pg_inode, req->wb_context, IOMODE_READ, GFP_KERNEL);
+        lseg = pnfs_update_layout(desc->pg_inode, req->wb_context,
+                                  req_offset(req), desc->pg_count,
+                                  IOMODE_READ, GFP_KERNEL);
         ClearPageError(page);
         offset = 0;
         nbytes = desc->pg_count;
@@ -351,7 +353,9 @@ static int nfs_pagein_one(struct nfs_pageio_descriptor *desc)
         }
         req = nfs_list_entry(data->pages.next);
         if ((!lseg) && list_is_singular(&data->pages))
-                lseg = pnfs_update_layout(desc->pg_inode, req->wb_context, IOMODE_READ, GFP_KERNEL);
+                lseg = pnfs_update_layout(desc->pg_inode, req->wb_context,
+                                          req_offset(req), desc->pg_count,
+                                          IOMODE_READ, GFP_KERNEL);
 
         ret = nfs_read_rpcsetup(req, data, &nfs_read_full_ops, desc->pg_count,
                                 0, lseg);
@@ -660,7 +664,6 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
         if (ret == 0)
                 goto read_complete; /* all pages were read */
 
-        pnfs_pageio_init_read(&pgio, inode);
         if (rsize < PAGE_CACHE_SIZE)
                 nfs_pageio_init(&pgio, inode, nfs_pagein_multi, rsize, 0);
         else
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index e288f06d3fa7..ce40e5c568ba 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -63,6 +63,7 @@
 #include "iostat.h"
 #include "internal.h"
 #include "fscache.h"
+#include "pnfs.h"
 
 #define NFSDBG_FACILITY         NFSDBG_VFS
 
@@ -732,6 +733,28 @@ static int nfs_show_options(struct seq_file *m, struct vfsmount *mnt)
 
         return 0;
 }
+#ifdef CONFIG_NFS_V4_1
+void show_sessions(struct seq_file *m, struct nfs_server *server)
+{
+        if (nfs4_has_session(server->nfs_client))
+                seq_printf(m, ",sessions");
+}
+#else
+void show_sessions(struct seq_file *m, struct nfs_server *server) {}
+#endif
+
+#ifdef CONFIG_NFS_V4_1
+void show_pnfs(struct seq_file *m, struct nfs_server *server)
+{
+        seq_printf(m, ",pnfs=");
+        if (server->pnfs_curr_ld)
+                seq_printf(m, "%s", server->pnfs_curr_ld->name);
+        else
+                seq_printf(m, "not configured");
+}
+#else  /* CONFIG_NFS_V4_1 */
+void show_pnfs(struct seq_file *m, struct nfs_server *server) {}
+#endif /* CONFIG_NFS_V4_1 */
 
 static int nfs_show_devname(struct seq_file *m, struct vfsmount *mnt)
 {
@@ -792,6 +815,8 @@ static int nfs_show_stats(struct seq_file *m, struct vfsmount *mnt)
                 seq_printf(m, "bm0=0x%x", nfss->attr_bitmask[0]);
                 seq_printf(m, ",bm1=0x%x", nfss->attr_bitmask[1]);
                 seq_printf(m, ",acl=0x%x", nfss->acl_bitmask);
+                show_sessions(m, nfss);
+                show_pnfs(m, nfss);
         }
 #endif
 
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 49c715b4ac92..e268e3b23497 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -939,7 +939,9 @@ static int nfs_flush_multi(struct nfs_pageio_descriptor *desc)
         atomic_set(&req->wb_complete, requests);
 
         BUG_ON(desc->pg_lseg);
-        lseg = pnfs_update_layout(desc->pg_inode, req->wb_context, IOMODE_RW, GFP_NOFS);
+        lseg = pnfs_update_layout(desc->pg_inode, req->wb_context,
+                                  req_offset(req), desc->pg_count,
+                                  IOMODE_RW, GFP_NOFS);
         ClearPageError(page);
         offset = 0;
         nbytes = desc->pg_count;
@@ -1013,7 +1015,9 @@ static int nfs_flush_one(struct nfs_pageio_descriptor *desc)
         }
         req = nfs_list_entry(data->pages.next);
         if ((!lseg) && list_is_singular(&data->pages))
-                lseg = pnfs_update_layout(desc->pg_inode, req->wb_context, IOMODE_RW, GFP_NOFS);
+                lseg = pnfs_update_layout(desc->pg_inode, req->wb_context,
+                                          req_offset(req), desc->pg_count,
+                                          IOMODE_RW, GFP_NOFS);
 
         if ((desc->pg_ioflags & FLUSH_COND_STABLE) &&
             (desc->pg_moreio || NFS_I(desc->pg_inode)->ncommit))
@@ -1032,8 +1036,6 @@ static void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio,
 {
         size_t wsize = NFS_SERVER(inode)->wsize;
 
-        pnfs_pageio_init_write(pgio, inode);
-
         if (wsize < PAGE_CACHE_SIZE)
                 nfs_pageio_init(pgio, inode, nfs_flush_multi, wsize, ioflags);
         else
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index ad000aeb21a2..b9566e46219f 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -1354,12 +1354,6 @@ exp_pseudoroot(struct svc_rqst *rqstp, struct svc_fh *fhp)
         if (IS_ERR(exp))
                 return nfserrno(PTR_ERR(exp));
         rv = fh_compose(fhp, exp, exp->ex_path.dentry, NULL);
-        if (rv)
-                goto out;
-        rv = check_nfsd_access(exp, rqstp);
-        if (rv)
-                fh_put(fhp);
-out:
         exp_put(exp);
         return rv;
 }
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 2247fc91d5e9..9095f3c21df9 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -245,7 +245,7 @@ nfsd3_proc_create(struct svc_rqst *rqstp, struct nfsd3_createargs *argp,
         }
 
         /* Now create the file and set attributes */
-        nfserr = nfsd_create_v3(rqstp, dirfhp, argp->name, argp->len,
+        nfserr = do_nfsd_create(rqstp, dirfhp, argp->name, argp->len,
                                 attr, newfhp,
                                 argp->createmode, argp->verf, NULL, NULL);
 
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index ad48faca20fc..08c6e36ab2eb 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -842,7 +842,7 @@ out:
         return rv;
 }
 
-__be32 *encode_entryplus_baggage(struct nfsd3_readdirres *cd, __be32 *p, const char *name, int namlen)
+static __be32 *encode_entryplus_baggage(struct nfsd3_readdirres *cd, __be32 *p, const char *name, int namlen)
 {
         struct svc_fh   fh;
         int err;
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 5fcb1396a7e3..3a6dbd70b34b 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -196,9 +196,9 @@ do_open_lookup(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_o
 
                 /*
                  * Note: create modes (UNCHECKED,GUARDED...) are the same
-                 * in NFSv4 as in v3.
+                 * in NFSv4 as in v3 except EXCLUSIVE4_1.
                  */
-                status = nfsd_create_v3(rqstp, current_fh, open->op_fname.data,
+                status = do_nfsd_create(rqstp, current_fh, open->op_fname.data,
                                         open->op_fname.len, &open->op_iattr,
                                         &resfh, open->op_createmode,
                                         (u32 *)open->op_verf.data,
@@ -403,7 +403,7 @@ nfsd4_putfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
         cstate->current_fh.fh_handle.fh_size = putfh->pf_fhlen;
         memcpy(&cstate->current_fh.fh_handle.fh_base, putfh->pf_fhval,
                putfh->pf_fhlen);
-        return fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP);
+        return fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_BYPASS_GSS);
 }
 
 static __be32
@@ -762,6 +762,9 @@ nfsd4_secinfo(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
         __be32 err;
 
         fh_init(&resfh, NFS4_FHSIZE);
+        err = fh_verify(rqstp, &cstate->current_fh, S_IFDIR, NFSD_MAY_EXEC);
+        if (err)
+                return err;
         err = nfsd_lookup_dentry(rqstp, &cstate->current_fh,
                                     secinfo->si_name, secinfo->si_namelen,
                                     &exp, &dentry);
@@ -986,6 +989,9 @@ enum nfsd4_op_flags {
         ALLOWED_WITHOUT_FH = 1 << 0,    /* No current filehandle required */
         ALLOWED_ON_ABSENT_FS = 1 << 1,  /* ops processed on absent fs */
         ALLOWED_AS_FIRST_OP = 1 << 2,   /* ops reqired first in compound */
+        /* For rfc 5661 section 2.6.3.1.1: */
+        OP_HANDLES_WRONGSEC = 1 << 3,
+        OP_IS_PUTFH_LIKE = 1 << 4,
 };
 
 struct nfsd4_operation {
@@ -1031,6 +1037,44 @@ static __be32 nfs41_check_op_ordering(struct nfsd4_compoundargs *args)
         return nfs_ok;
 }
 
+static inline struct nfsd4_operation *OPDESC(struct nfsd4_op *op)
+{
+        return &nfsd4_ops[op->opnum];
+}
+
+static bool need_wrongsec_check(struct svc_rqst *rqstp)
+{
+        struct nfsd4_compoundres *resp = rqstp->rq_resp;
+        struct nfsd4_compoundargs *argp = rqstp->rq_argp;
+        struct nfsd4_op *this = &argp->ops[resp->opcnt - 1];
+        struct nfsd4_op *next = &argp->ops[resp->opcnt];
+        struct nfsd4_operation *thisd;
+        struct nfsd4_operation *nextd;
+
+        thisd = OPDESC(this);
+        /*
+         * Most ops check wronsec on our own; only the putfh-like ops
+         * have special rules.
+         */
+        if (!(thisd->op_flags & OP_IS_PUTFH_LIKE))
+                return false;
+        /*
+         * rfc 5661 2.6.3.1.1.6: don't bother erroring out a
+         * put-filehandle operation if we're not going to use the
+         * result:
+         */
+        if (argp->opcnt == resp->opcnt)
+                return false;
+
+        nextd = OPDESC(next);
+        /*
+         * Rest of 2.6.3.1.1: certain operations will return WRONGSEC
+         * errors themselves as necessary; others should check for them
+         * now:
+         */
+        return !(nextd->op_flags & OP_HANDLES_WRONGSEC);
+}
+
 /*
  * COMPOUND call.
  */
@@ -1108,7 +1152,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
                         goto encode_op;
                 }
 
-                opdesc = &nfsd4_ops[op->opnum];
+                opdesc = OPDESC(op);
 
                 if (!cstate->current_fh.fh_dentry) {
                         if (!(opdesc->op_flags & ALLOWED_WITHOUT_FH)) {
@@ -1126,6 +1170,9 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
                 else
                         BUG_ON(op->status == nfs_ok);
 
+                if (!op->status && need_wrongsec_check(rqstp))
+                        op->status = check_nfsd_access(cstate->current_fh.fh_export, rqstp);
+
 encode_op:
                 /* Only from SEQUENCE */
                 if (resp->cstate.status == nfserr_replay_cache) {
@@ -1217,10 +1264,12 @@ static struct nfsd4_operation nfsd4_ops[] = {
         },
         [OP_LOOKUP] = {
                 .op_func = (nfsd4op_func)nfsd4_lookup,
+                .op_flags = OP_HANDLES_WRONGSEC,
                 .op_name = "OP_LOOKUP",
         },
         [OP_LOOKUPP] = {
                 .op_func = (nfsd4op_func)nfsd4_lookupp,
+                .op_flags = OP_HANDLES_WRONGSEC,
                 .op_name = "OP_LOOKUPP",
         },
         [OP_NVERIFY] = {
@@ -1229,6 +1278,7 @@ static struct nfsd4_operation nfsd4_ops[] = {
         },
         [OP_OPEN] = {
                 .op_func = (nfsd4op_func)nfsd4_open,
+                .op_flags = OP_HANDLES_WRONGSEC,
                 .op_name = "OP_OPEN",
         },
         [OP_OPEN_CONFIRM] = {
@@ -1241,17 +1291,20 @@ static struct nfsd4_operation nfsd4_ops[] = {
         },
         [OP_PUTFH] = {
                 .op_func = (nfsd4op_func)nfsd4_putfh,
-                .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
+                .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
+                                | OP_IS_PUTFH_LIKE,
                 .op_name = "OP_PUTFH",
         },
         [OP_PUTPUBFH] = {
                 .op_func = (nfsd4op_func)nfsd4_putrootfh,
-                .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
+                .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
+                                | OP_IS_PUTFH_LIKE,
                 .op_name = "OP_PUTPUBFH",
         },
         [OP_PUTROOTFH] = {
                 .op_func = (nfsd4op_func)nfsd4_putrootfh,
-                .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
+                .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
+                                | OP_IS_PUTFH_LIKE,
                 .op_name = "OP_PUTROOTFH",
         },
         [OP_READ] = {
@@ -1281,15 +1334,18 @@ static struct nfsd4_operation nfsd4_ops[] = {
         },
         [OP_RESTOREFH] = {
                 .op_func = (nfsd4op_func)nfsd4_restorefh,
-                .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS,
+                .op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
+                                | OP_IS_PUTFH_LIKE,
                 .op_name = "OP_RESTOREFH",
         },
         [OP_SAVEFH] = {
                 .op_func = (nfsd4op_func)nfsd4_savefh,
+                .op_flags = OP_HANDLES_WRONGSEC,
                 .op_name = "OP_SAVEFH",
         },
         [OP_SECINFO] = {
                 .op_func = (nfsd4op_func)nfsd4_secinfo,
+                .op_flags = OP_HANDLES_WRONGSEC,
                 .op_name = "OP_SECINFO",
         },
         [OP_SETATTR] = {
@@ -1353,6 +1409,7 @@ static struct nfsd4_operation nfsd4_ops[] = {
         },
         [OP_SECINFO_NO_NAME] = {
                 .op_func = (nfsd4op_func)nfsd4_secinfo_no_name,
+                .op_flags = OP_HANDLES_WRONGSEC,
                 .op_name = "OP_SECINFO_NO_NAME",
         },
 };
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 4cf04e11c66c..e98f3c2e9492 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1519,6 +1519,9 @@ nfsd4_create_session(struct svc_rqst *rqstp,
         bool confirm_me = false;
         int status = 0;
 
+        if (cr_ses->flags & ~SESSION4_FLAG_MASK_A)
+                return nfserr_inval;
+
         nfs4_lock_state();
         unconf = find_unconfirmed_client(&cr_ses->clientid);
         conf = find_confirmed_client(&cr_ses->clientid);
@@ -1637,8 +1640,9 @@ __be32 nfsd4_bind_conn_to_session(struct svc_rqst *rqstp,
                 return nfserr_badsession;
 
         status = nfsd4_map_bcts_dir(&bcts->dir);
-        nfsd4_new_conn(rqstp, cstate->session, bcts->dir);
-        return nfs_ok;
+        if (!status)
+                nfsd4_new_conn(rqstp, cstate->session, bcts->dir);
+        return status;
 }
 
 static bool nfsd4_compound_in_session(struct nfsd4_session *session, struct nfs4_sessionid *sid)
@@ -1725,6 +1729,13 @@ static void nfsd4_sequence_check_conn(struct nfsd4_conn *new, struct nfsd4_sessi
         return;
 }
 
+static bool nfsd4_session_too_many_ops(struct svc_rqst *rqstp, struct nfsd4_session *session)
+{
+        struct nfsd4_compoundargs *args = rqstp->rq_argp;
+
+        return args->opcnt > session->se_fchannel.maxops;
+}
+
 __be32
 nfsd4_sequence(struct svc_rqst *rqstp,
                struct nfsd4_compound_state *cstate,
@@ -1753,6 +1764,10 @@ nfsd4_sequence(struct svc_rqst *rqstp,
         if (!session)
                 goto out;
 
+        status = nfserr_too_many_ops;
+        if (nfsd4_session_too_many_ops(rqstp, session))
+                goto out;
+
         status = nfserr_badslot;
         if (seq->slotid >= session->se_fchannel.maxreqs)
                 goto out;
@@ -1808,6 +1823,8 @@ out:
 __be32
 nfsd4_reclaim_complete(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_reclaim_complete *rc)
 {
+        int status = 0;
+
         if (rc->rca_one_fs) {
                 if (!cstate->current_fh.fh_dentry)
                         return nfserr_nofilehandle;
@@ -1817,9 +1834,14 @@ nfsd4_reclaim_complete(struct svc_rqst *rqstp, struct nfsd4_compound_state *csta
                  */
                  return nfs_ok;
         }
+
         nfs4_lock_state();
-        if (is_client_expired(cstate->session->se_client)) {
-                nfs4_unlock_state();
+        status = nfserr_complete_already;
+        if (cstate->session->se_client->cl_firststate)
+                goto out;
+
+        status = nfserr_stale_clientid;
+        if (is_client_expired(cstate->session->se_client))
                 /*
                  * The following error isn't really legal.
                  * But we only get here if the client just explicitly
@@ -1827,11 +1849,13 @@ nfsd4_reclaim_complete(struct svc_rqst *rqstp, struct nfsd4_compound_state *csta
                  * error it gets back on an operation for the dead
                  * client.
                  */
-                return nfserr_stale_clientid;
-        }
+                goto out;
+
+        status = nfs_ok;
         nfsd4_create_clid_dir(cstate->session->se_client);
+out:
         nfs4_unlock_state();
-        return nfs_ok;
+        return status;
 }
 
 __be32
@@ -2462,7 +2486,7 @@ find_delegation_file(struct nfs4_file *fp, stateid_t *stid)
         return NULL;
 }
 
-int share_access_to_flags(u32 share_access)
+static int share_access_to_flags(u32 share_access)
 {
         share_access &= ~NFS4_SHARE_WANT_MASK;
 
@@ -2882,7 +2906,7 @@ out:
         return status;
 }
 
-struct lock_manager nfsd4_manager = {
+static struct lock_manager nfsd4_manager = {
 };
 
 static void
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index c6766af00d98..990181103214 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -424,15 +424,12 @@ nfsd4_decode_access(struct nfsd4_compoundargs *argp, struct nfsd4_access *access
 static __be32 nfsd4_decode_bind_conn_to_session(struct nfsd4_compoundargs *argp, struct nfsd4_bind_conn_to_session *bcts)
 {
         DECODE_HEAD;
-        u32 dummy;
 
         READ_BUF(NFS4_MAX_SESSIONID_LEN + 8);
         COPYMEM(bcts->sessionid.data, NFS4_MAX_SESSIONID_LEN);
         READ32(bcts->dir);
-        /* XXX: Perhaps Tom Tucker could help us figure out how we
-         * should be using ctsa_use_conn_in_rdma_mode: */
-        READ32(dummy);
-
+        /* XXX: skipping ctsa_use_conn_in_rdma_mode.  Perhaps Tom Tucker
+         * could help us figure out we should be using it. */
         DECODE_TAIL;
 }
 
@@ -588,8 +585,6 @@ nfsd4_decode_lockt(struct nfsd4_compoundargs *argp, struct nfsd4_lockt *lockt)
         READ_BUF(lockt->lt_owner.len);
         READMEM(lockt->lt_owner.data, lockt->lt_owner.len);
 
-        if (argp->minorversion && !zero_clientid(&lockt->lt_clientid))
-                return nfserr_inval;
         DECODE_TAIL;
 }
 
@@ -3120,7 +3115,7 @@ nfsd4_encode_destroy_session(struct nfsd4_compoundres *resp, int nfserr,
         return nfserr;
 }
 
-__be32
+static __be32
 nfsd4_encode_sequence(struct nfsd4_compoundres *resp, int nfserr,
                       struct nfsd4_sequence *seq)
 {
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 55c8e63af0be..90c6aa6d5e0f 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -344,7 +344,7 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access)
          * which clients virtually always use auth_sys for,
          * even while using RPCSEC_GSS for NFS.
          */
-        if (access & NFSD_MAY_LOCK)
+        if (access & NFSD_MAY_LOCK || access & NFSD_MAY_BYPASS_GSS)
                 goto skip_pseudoflavor_check;
         /*
          * Clients may expect to be able to use auth_sys during mount,
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 129f3c9f62d5..d5718273bb32 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -181,16 +181,10 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp,
         struct svc_export       *exp;
         struct dentry           *dparent;
         struct dentry           *dentry;
-        __be32                  err;
         int                     host_err;
 
         dprintk("nfsd: nfsd_lookup(fh %s, %.*s)\n", SVCFH_fmt(fhp), len,name);
 
-        /* Obtain dentry and export. */
-        err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_EXEC);
-        if (err)
-                return err;
-
         dparent = fhp->fh_dentry;
         exp  = fhp->fh_export;
         exp_get(exp);
@@ -254,6 +248,9 @@ nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name,
         struct dentry           *dentry;
         __be32 err;
 
+        err = fh_verify(rqstp, fhp, S_IFDIR, NFSD_MAY_EXEC);
+        if (err)
+                return err;
         err = nfsd_lookup_dentry(rqstp, fhp, name, len, &exp, &dentry);
         if (err)
                 return err;
@@ -877,13 +874,11 @@ static __be32
 nfsd_vfs_read(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
               loff_t offset, struct kvec *vec, int vlen, unsigned long *count)
 {
-        struct inode *inode;
         mm_segment_t    oldfs;
         __be32          err;
         int             host_err;
 
         err = nfserr_perm;
-        inode = file->f_path.dentry->d_inode;
 
         if (file->f_op->splice_read && rqstp->rq_splice_ok) {
                 struct splice_desc sd = {
@@ -1340,11 +1335,18 @@ out_nfserr:
 }
 
 #ifdef CONFIG_NFSD_V3
+
+static inline int nfsd_create_is_exclusive(int createmode)
+{
+        return createmode == NFS3_CREATE_EXCLUSIVE
+               || createmode == NFS4_CREATE_EXCLUSIVE4_1;
+}
+
 /*
- * NFSv3 version of nfsd_create
+ * NFSv3 and NFSv4 version of nfsd_create
  */
 __be32
-nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
+do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
                 char *fname, int flen, struct iattr *iap,
                 struct svc_fh *resfhp, int createmode, u32 *verifier,
                 int *truncp, int *created)
@@ -1396,7 +1398,7 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
         if (err)
                 goto out;
 
-        if (createmode == NFS3_CREATE_EXCLUSIVE) {
+        if (nfsd_create_is_exclusive(createmode)) {
                 /* solaris7 gets confused (bugid 4218508) if these have
                  * the high bit set, so just clear the high bits. If this is
                  * ever changed to use different attrs for storing the
@@ -1437,6 +1439,11 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
                             && dchild->d_inode->i_atime.tv_sec == v_atime
                             && dchild->d_inode->i_size  == 0 )
                                 break;
+                case NFS4_CREATE_EXCLUSIVE4_1:
+                        if (   dchild->d_inode->i_mtime.tv_sec == v_mtime
+                            && dchild->d_inode->i_atime.tv_sec == v_atime
+                            && dchild->d_inode->i_size  == 0 )
+                                goto set_attr;
                          /* fallthru */
                 case NFS3_CREATE_GUARDED:
                         err = nfserr_exist;
@@ -1455,7 +1462,7 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
 
         nfsd_check_ignore_resizing(iap);
 
-        if (createmode == NFS3_CREATE_EXCLUSIVE) {
+        if (nfsd_create_is_exclusive(createmode)) {
                 /* Cram the verifier into atime/mtime */
                 iap->ia_valid = ATTR_MTIME|ATTR_ATIME
                         | ATTR_MTIME_SET|ATTR_ATIME_SET;
@@ -2034,7 +2041,7 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp,
         struct inode    *inode = dentry->d_inode;
         int             err;
 
-        if (acc == NFSD_MAY_NOP)
+        if ((acc & NFSD_MAY_MASK) == NFSD_MAY_NOP)
                 return 0;
 #if 0
         dprintk("nfsd: permission 0x%x%s%s%s%s%s%s%s mode 0%o%s%s%s\n",
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index 9a370a5e36b7..e0bbac04d1dd 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -17,10 +17,14 @@
 #define NFSD_MAY_SATTR          8
 #define NFSD_MAY_TRUNC          16
 #define NFSD_MAY_LOCK           32
+#define NFSD_MAY_MASK           63
+
+/* extra hints to permission and open routines: */
 #define NFSD_MAY_OWNER_OVERRIDE 64
 #define NFSD_MAY_LOCAL_ACCESS   128 /* IRIX doing local access check on device special file*/
 #define NFSD_MAY_BYPASS_GSS_ON_ROOT 256
 #define NFSD_MAY_NOT_BREAK_LEASE 512
+#define NFSD_MAY_BYPASS_GSS     1024
 
 #define NFSD_MAY_CREATE         (NFSD_MAY_EXEC|NFSD_MAY_WRITE)
 #define NFSD_MAY_REMOVE         (NFSD_MAY_EXEC|NFSD_MAY_WRITE|NFSD_MAY_TRUNC)
@@ -54,7 +58,7 @@ __be32		nfsd_create(struct svc_rqst *, struct svc_fh *,
                                 int type, dev_t rdev, struct svc_fh *res);
 #ifdef CONFIG_NFSD_V3
 __be32          nfsd_access(struct svc_rqst *, struct svc_fh *, u32 *, u32 *);
-__be32          nfsd_create_v3(struct svc_rqst *, struct svc_fh *,
+__be32          do_nfsd_create(struct svc_rqst *, struct svc_fh *,
                                 char *name, int len, struct iattr *attrs,
                                 struct svc_fh *res, int createmode,
                                 u32 *verifier, int *truncp, int *created);
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 587f18432832..b954878ad6ce 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -917,7 +917,7 @@ int nilfs_mark_inode_dirty(struct inode *inode)
  * construction. This function can be called both as a single operation
  * and as a part of indivisible file operations.
  */
-void nilfs_dirty_inode(struct inode *inode)
+void nilfs_dirty_inode(struct inode *inode, int flags)
 {
         struct nilfs_transaction_info ti;
         struct nilfs_mdt_info *mdi = NILFS_MDT(inode);
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index 1102a5fbb744..546849b3e88f 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -334,8 +334,6 @@ static int nilfs_rmdir(struct inode *dir, struct dentry *dentry)
         struct nilfs_transaction_info ti;
         int err;
 
-        dentry_unhash(dentry);
-
         err = nilfs_transaction_begin(dir->i_sb, &ti, 0);
         if (err)
                 return err;
@@ -371,9 +369,6 @@ static int nilfs_rename(struct inode *old_dir, struct dentry *old_dentry,
         struct nilfs_transaction_info ti;
         int err;
 
-        if (new_inode && S_ISDIR(new_inode->i_mode))
-                dentry_unhash(new_dentry);
-
         err = nilfs_transaction_begin(old_dir->i_sb, &ti, 1);
         if (unlikely(err))
                 return err;
diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h
index a9c6a531f80c..f02b9ad43a21 100644
--- a/fs/nilfs2/nilfs.h
+++ b/fs/nilfs2/nilfs.h
@@ -269,7 +269,7 @@ int nilfs_load_inode_block(struct inode *inode, struct buffer_head **pbh);
 extern int nilfs_inode_dirty(struct inode *);
 int nilfs_set_file_dirty(struct inode *inode, unsigned nr_dirty);
 extern int nilfs_mark_inode_dirty(struct inode *);
-extern void nilfs_dirty_inode(struct inode *);
+extern void nilfs_dirty_inode(struct inode *, int flags);
 int nilfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
                  __u64 start, __u64 len);
 
diff --git a/fs/omfs/dir.c b/fs/omfs/dir.c
index c368360c35a1..3b8d3979e03b 100644
--- a/fs/omfs/dir.c
+++ b/fs/omfs/dir.c
@@ -241,11 +241,9 @@ static int omfs_remove(struct inode *dir, struct dentry *dentry)
         int ret;
 
 
-        if (S_ISDIR(inode->i_mode)) {
-                dentry_unhash(dentry);
-                if (!omfs_dir_is_empty(inode))
-                        return -ENOTEMPTY;
-        }
+        if (S_ISDIR(inode->i_mode) &&
+            !omfs_dir_is_empty(inode))
+                return -ENOTEMPTY;
 
         ret = omfs_delete_entry(dentry);
         if (ret)
@@ -382,9 +380,6 @@ static int omfs_rename(struct inode *old_dir, struct dentry *old_dentry,
         int err;
 
         if (new_inode) {
-                if (S_ISDIR(new_inode->i_mode))
-                        dentry_unhash(new_dentry);
-
                 /* overwriting existing file/dir */
                 err = omfs_remove(new_dir, new_dentry);
                 if (err)
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index f82e762eeca2..d545e97d99c3 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -255,13 +255,7 @@ ssize_t part_discard_alignment_show(struct device *dev,
                                    struct device_attribute *attr, char *buf)
 {
         struct hd_struct *p = dev_to_part(dev);
-        struct gendisk *disk = dev_to_disk(dev);
-        unsigned int alignment = 0;
-
-        if (disk->queue)
-                alignment = queue_limit_discard_alignment(&disk->queue->limits,
-                                                                p->start_sect);
-        return sprintf(buf, "%u\n", alignment);
+        return sprintf(buf, "%u\n", p->discard_alignment);
 }
 
 ssize_t part_stat_show(struct device *dev,
@@ -455,6 +449,8 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno,
         p->start_sect = start;
         p->alignment_offset =
                 queue_limit_alignment_offset(&disk->queue->limits, start);
+        p->discard_alignment =
+                queue_limit_discard_alignment(&disk->queue->limits, start);
         p->nr_sects = len;
         p->partno = partno;
         p->policy = get_disk_ro(disk);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 4ede550517a6..14def991d9dd 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -83,6 +83,9 @@
 #include <linux/pid_namespace.h>
 #include <linux/fs_struct.h>
 #include <linux/slab.h>
+#ifdef CONFIG_HARDWALL
+#include <asm/hardwall.h>
+#endif
 #include "internal.h"
 
 /* NOTE:
@@ -2842,6 +2845,9 @@ static const struct pid_entry tgid_base_stuff[] = {
 #ifdef CONFIG_TASK_IO_ACCOUNTING
         INF("io",       S_IRUGO, proc_tgid_io_accounting),
 #endif
+#ifdef CONFIG_HARDWALL
+        INF("hardwall",   S_IRUGO, proc_pid_hardwall),
+#endif
 };
 
 static int proc_tgid_base_readdir(struct file * filp,
@@ -3181,6 +3187,9 @@ static const struct pid_entry tid_base_stuff[] = {
 #ifdef CONFIG_TASK_IO_ACCOUNTING
         INF("io",       S_IRUGO, proc_tid_io_accounting),
 #endif
+#ifdef CONFIG_HARDWALL
+        INF("hardwall",   S_IRUGO, proc_pid_hardwall),
+#endif
 };
 
 static int proc_tid_base_readdir(struct file * filp,
diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c
index 76c8164d5651..118662690cdf 100644
--- a/fs/reiserfs/namei.c
+++ b/fs/reiserfs/namei.c
@@ -831,8 +831,6 @@ static int reiserfs_rmdir(struct inode *dir, struct dentry *dentry)
         INITIALIZE_PATH(path);
         struct reiserfs_dir_entry de;
 
-        dentry_unhash(dentry);
-
         /* we will be doing 2 balancings and update 2 stat data, we change quotas
          * of the owner of the directory and of the owner of the parent directory.
          * The quota structure is possibly deleted only on last iput => outside
@@ -1227,9 +1225,6 @@ static int reiserfs_rename(struct inode *old_dir, struct dentry *old_dentry,
         unsigned long savelink = 1;
         struct timespec ctime;
 
-        if (new_dentry->d_inode && S_ISDIR(new_dentry->d_inode->i_mode))
-                dentry_unhash(new_dentry);
-
         /* three balancings: (1) old name removal, (2) new name insertion
            and (3) maybe "save" link insertion
            stat data updates: (1) old directory,
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index b216ff6be1c9..aa91089162cb 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -568,7 +568,7 @@ static void destroy_inodecache(void)
 }
 
 /* we don't mark inodes dirty, we just log them */
-static void reiserfs_dirty_inode(struct inode *inode)
+static void reiserfs_dirty_inode(struct inode *inode, int flags)
 {
         struct reiserfs_transaction_handle th;
 
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index 50f1abccd1cd..e8a62f41b458 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -98,7 +98,6 @@ static int xattr_rmdir(struct inode *dir, struct dentry *dentry)
 
         reiserfs_mutex_lock_nested_safe(&dentry->d_inode->i_mutex,
                                         I_MUTEX_CHILD, dir->i_sb);
-        dentry_unhash(dentry);
         error = dir->i_op->rmdir(dir, dentry);
         if (!error)
                 dentry->d_inode->i_flags |= S_DEAD;
diff --git a/fs/squashfs/export.c b/fs/squashfs/export.c
index 730c56248c9b..5e1101ff276f 100644
--- a/fs/squashfs/export.c
+++ b/fs/squashfs/export.c
@@ -147,7 +147,7 @@ __le64 *squashfs_read_inode_lookup_table(struct super_block *sb,
          * table[0] points to the first inode lookup table metadata block,
          * this should be less than lookup_table_start
          */
-        if (!IS_ERR(table) && table[0] >= lookup_table_start) {
+        if (!IS_ERR(table) && le64_to_cpu(table[0]) >= lookup_table_start) {
                 kfree(table);
                 return ERR_PTR(-EINVAL);
         }
diff --git a/fs/squashfs/fragment.c b/fs/squashfs/fragment.c
index 1516a6490bfb..0ed6edbc5c71 100644
--- a/fs/squashfs/fragment.c
+++ b/fs/squashfs/fragment.c
@@ -90,7 +90,7 @@ __le64 *squashfs_read_fragment_index_table(struct super_block *sb,
          * table[0] points to the first fragment table metadata block, this
          * should be less than fragment_table_start
          */
-        if (!IS_ERR(table) && table[0] >= fragment_table_start) {
+        if (!IS_ERR(table) && le64_to_cpu(table[0]) >= fragment_table_start) {
                 kfree(table);
                 return ERR_PTR(-EINVAL);
         }
diff --git a/fs/squashfs/id.c b/fs/squashfs/id.c
index a70858e0fb44..d38ea3dab951 100644
--- a/fs/squashfs/id.c
+++ b/fs/squashfs/id.c
@@ -93,7 +93,7 @@ __le64 *squashfs_read_id_index_table(struct super_block *sb,
          * table[0] points to the first id lookup table metadata block, this
          * should be less than id_table_start
          */
-        if (!IS_ERR(table) && table[0] >= id_table_start) {
+        if (!IS_ERR(table) && le64_to_cpu(table[0]) >= id_table_start) {
                 kfree(table);
                 return ERR_PTR(-EINVAL);
         }
diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c
index 6f26abee3597..7438850c62d0 100644
--- a/fs/squashfs/super.c
+++ b/fs/squashfs/super.c
@@ -245,7 +245,7 @@ allocate_id_index_table:
                 msblk->id_table = NULL;
                 goto failed_mount;
         }
-        next_table = msblk->id_table[0];
+        next_table = le64_to_cpu(msblk->id_table[0]);
 
         /* Handle inode lookup table */
         lookup_table_start = le64_to_cpu(sblk->lookup_table_start);
@@ -261,7 +261,7 @@ allocate_id_index_table:
                 msblk->inode_lookup_table = NULL;
                 goto failed_mount;
         }
-        next_table = msblk->inode_lookup_table[0];
+        next_table = le64_to_cpu(msblk->inode_lookup_table[0]);
 
         sb->s_export_op = &squashfs_export_ops;
 
@@ -286,7 +286,7 @@ handle_fragments:
                 msblk->fragment_index = NULL;
                 goto failed_mount;
         }
-        next_table = msblk->fragment_index[0];
+        next_table = le64_to_cpu(msblk->fragment_index[0]);
 
 check_directory_table:
         /* Sanity check directory_table */
diff --git a/fs/sysv/namei.c b/fs/sysv/namei.c
index e2cc6756f3b1..e474fbcf8bde 100644
--- a/fs/sysv/namei.c
+++ b/fs/sysv/namei.c
@@ -196,8 +196,6 @@ static int sysv_rmdir(struct inode * dir, struct dentry * dentry)
         struct inode *inode = dentry->d_inode;
         int err = -ENOTEMPTY;
 
-        dentry_unhash(dentry);
-
         if (sysv_empty_dir(inode)) {
                 err = sysv_unlink(dir, dentry);
                 if (!err) {
@@ -224,9 +222,6 @@ static int sysv_rename(struct inode * old_dir, struct dentry * old_dentry,
         struct sysv_dir_entry * old_de;
         int err = -ENOENT;
 
-        if (new_inode && S_ISDIR(new_inode->i_mode))
-                dentry_unhash(new_dentry);
-
         old_de = sysv_find_entry(old_dentry, &old_page);
         if (!old_de)
                 goto out;
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index c2b80943560d..ef5abd38f0bf 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -656,8 +656,6 @@ static int ubifs_rmdir(struct inode *dir, struct dentry *dentry)
         struct ubifs_inode *dir_ui = ubifs_inode(dir);
         struct ubifs_budget_req req = { .mod_dent = 1, .dirtied_ino = 2 };
 
-        dentry_unhash(dentry);
-
         /*
          * Budget request settings: deletion direntry, deletion inode and
          * changing the parent inode. If budgeting fails, go ahead anyway
@@ -978,9 +976,6 @@ static int ubifs_rename(struct inode *old_dir, struct dentry *old_dentry,
                         .dirtied_ino_d = ALIGN(old_inode_ui->data_len, 8) };
         struct timespec time;
 
-        if (new_inode && S_ISDIR(new_inode->i_mode))
-                dentry_unhash(new_dentry);
-
         /*
          * Budget request settings: deletion direntry, new direntry, removing
          * the old inode, and changing old and new parent directory inodes.
diff --git a/fs/ubifs/io.c b/fs/ubifs/io.c
index 166951e0dcd3..3be645e012c9 100644
--- a/fs/ubifs/io.c
+++ b/fs/ubifs/io.c
@@ -581,6 +581,7 @@ int ubifs_wbuf_write_nolock(struct ubifs_wbuf *wbuf, void *buf, int len)
         ubifs_assert(wbuf->size % c->min_io_size == 0);
         ubifs_assert(mutex_is_locked(&wbuf->io_mutex));
         ubifs_assert(!c->ro_media && !c->ro_mount);
+        ubifs_assert(!c->space_fixup);
         if (c->leb_size - wbuf->offs >= c->max_write_size)
                 ubifs_assert(!((wbuf->offs + wbuf->size) % c->max_write_size));
 
@@ -759,6 +760,7 @@ int ubifs_write_node(struct ubifs_info *c, void *buf, int len, int lnum,
         ubifs_assert(lnum >= 0 && lnum < c->leb_cnt && offs >= 0);
         ubifs_assert(offs % c->min_io_size == 0 && offs < c->leb_size);
         ubifs_assert(!c->ro_media && !c->ro_mount);
+        ubifs_assert(!c->space_fixup);
 
         if (c->ro_error)
                 return -EROFS;
diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c
index 34b1679e6e3a..cef0460f4c54 100644
--- a/fs/ubifs/journal.c
+++ b/fs/ubifs/journal.c
@@ -669,6 +669,7 @@ out_free:
 
 out_release:
         release_head(c, BASEHD);
+        kfree(dent);
 out_ro:
         ubifs_ro_mode(c, err);
         if (last_reference)
diff --git a/fs/ubifs/orphan.c b/fs/ubifs/orphan.c
index bd644bf587a8..a5422fffbd69 100644
--- a/fs/ubifs/orphan.c
+++ b/fs/ubifs/orphan.c
@@ -674,7 +674,7 @@ static int kill_orphans(struct ubifs_info *c)
                 if (IS_ERR(sleb)) {
                         if (PTR_ERR(sleb) == -EUCLEAN)
                                 sleb = ubifs_recover_leb(c, lnum, 0,
-                                                         c->sbuf, 0);
+                                                         c->sbuf, -1);
                         if (IS_ERR(sleb)) {
                                 err = PTR_ERR(sleb);
                                 break;
diff --git a/fs/ubifs/recovery.c b/fs/ubifs/recovery.c
index 731d9e2e7b50..783d8e0beb76 100644
--- a/fs/ubifs/recovery.c
+++ b/fs/ubifs/recovery.c
@@ -564,19 +564,15 @@ static int fix_unclean_leb(struct ubifs_info *c, struct ubifs_scan_leb *sleb,
 }
 
 /**
- * drop_last_node - drop the last node or group of nodes.
+ * drop_last_group - drop the last group of nodes.
  * @sleb: scanned LEB information
  * @offs: offset of dropped nodes is returned here
- * @grouped: non-zero if whole group of nodes have to be dropped
  *
  * This is a helper function for 'ubifs_recover_leb()' which drops the last
- * node of the scanned LEB or the last group of nodes if @grouped is not zero.
- * This function returns %1 if a node was dropped and %0 otherwise.
+ * group of nodes of the scanned LEB.
  */
-static int drop_last_node(struct ubifs_scan_leb *sleb, int *offs, int grouped)
+static void drop_last_group(struct ubifs_scan_leb *sleb, int *offs)
 {
-        int dropped = 0;
-
         while (!list_empty(&sleb->nodes)) {
                 struct ubifs_scan_node *snod;
                 struct ubifs_ch *ch;
@@ -585,17 +581,40 @@ static int drop_last_node(struct ubifs_scan_leb *sleb, int *offs, int grouped)
                                   list);
                 ch = snod->node;
                 if (ch->group_type != UBIFS_IN_NODE_GROUP)
-                        return dropped;
-                dbg_rcvry("dropping node at %d:%d", sleb->lnum, snod->offs);
+                        break;
+
+                dbg_rcvry("dropping grouped node at %d:%d",
+                          sleb->lnum, snod->offs);
+                *offs = snod->offs;
+                list_del(&snod->list);
+                kfree(snod);
+                sleb->nodes_cnt -= 1;
+        }
+}
+
+/**
+ * drop_last_node - drop the last node.
+ * @sleb: scanned LEB information
+ * @offs: offset of dropped nodes is returned here
+ * @grouped: non-zero if whole group of nodes have to be dropped
+ *
+ * This is a helper function for 'ubifs_recover_leb()' which drops the last
+ * node of the scanned LEB.
+ */
+static void drop_last_node(struct ubifs_scan_leb *sleb, int *offs)
+{
+        struct ubifs_scan_node *snod;
+
+        if (!list_empty(&sleb->nodes)) {
+                snod = list_entry(sleb->nodes.prev, struct ubifs_scan_node,
+                                  list);
+
+                dbg_rcvry("dropping last node at %d:%d", sleb->lnum, snod->offs);
                 *offs = snod->offs;
                 list_del(&snod->list);
                 kfree(snod);
                 sleb->nodes_cnt -= 1;
-                dropped = 1;
-                if (!grouped)
-                        break;
         }
-        return dropped;
 }
 
 /**
@@ -604,7 +623,8 @@ static int drop_last_node(struct ubifs_scan_leb *sleb, int *offs, int grouped)
  * @lnum: LEB number
  * @offs: offset
  * @sbuf: LEB-sized buffer to use
- * @grouped: nodes may be grouped for recovery
+ * @jhead: journal head number this LEB belongs to (%-1 if the LEB does not
+ *         belong to any journal head)
  *
  * This function does a scan of a LEB, but caters for errors that might have
  * been caused by the unclean unmount from which we are attempting to recover.
@@ -612,13 +632,14 @@ static int drop_last_node(struct ubifs_scan_leb *sleb, int *offs, int grouped)
  * found, and a negative error code in case of failure.
  */
 struct ubifs_scan_leb *ubifs_recover_leb(struct ubifs_info *c, int lnum,
-                                         int offs, void *sbuf, int grouped)
+                                         int offs, void *sbuf, int jhead)
 {
         int ret = 0, err, len = c->leb_size - offs, start = offs, min_io_unit;
+        int grouped = jhead == -1 ? 0 : c->jheads[jhead].grouped;
         struct ubifs_scan_leb *sleb;
         void *buf = sbuf + offs;
 
-        dbg_rcvry("%d:%d", lnum, offs);
+        dbg_rcvry("%d:%d, jhead %d, grouped %d", lnum, offs, jhead, grouped);
 
         sleb = ubifs_start_scan(c, lnum, offs, sbuf);
         if (IS_ERR(sleb))
@@ -635,7 +656,7 @@ struct ubifs_scan_leb *ubifs_recover_leb(struct ubifs_info *c, int lnum,
                  * Scan quietly until there is an error from which we cannot
                  * recover
                  */
-                ret = ubifs_scan_a_node(c, buf, len, lnum, offs, 0);
+                ret = ubifs_scan_a_node(c, buf, len, lnum, offs, 1);
                 if (ret == SCANNED_A_NODE) {
                         /* A valid node, and not a padding node */
                         struct ubifs_ch *ch = buf;
@@ -695,59 +716,62 @@ struct ubifs_scan_leb *ubifs_recover_leb(struct ubifs_info *c, int lnum,
                  * If nodes are grouped, always drop the incomplete group at
                  * the end.
                  */
-                drop_last_node(sleb, &offs, 1);
+                drop_last_group(sleb, &offs);
 
-        /*
-         * While we are in the middle of the same min. I/O unit keep dropping
-         * nodes. So basically, what we want is to make sure that the last min.
-         * I/O unit where we saw the corruption is dropped completely with all
-         * the uncorrupted node which may possibly sit there.
-         *
-         * In other words, let's name the min. I/O unit where the corruption
-         * starts B, and the previous min. I/O unit A. The below code tries to
-         * deal with a situation when half of B contains valid nodes or the end
-         * of a valid node, and the second half of B contains corrupted data or
-         * garbage. This means that UBIFS had been writing to B just before the
-         * power cut happened. I do not know how realistic is this scenario
-         * that half of the min. I/O unit had been written successfully and the
-         * other half not, but this is possible in our 'failure mode emulation'
-         * infrastructure at least.
-         *
-         * So what is the problem, why we need to drop those nodes? Whey can't
-         * we just clean-up the second half of B by putting a padding node
-         * there? We can, and this works fine with one exception which was
-         * reproduced with power cut emulation testing and happens extremely
-         * rarely. The description follows, but it is worth noting that that is
-         * only about the GC head, so we could do this trick only if the bud
-         * belongs to the GC head, but it does not seem to be worth an
-         * additional "if" statement.
-         *
-         * So, imagine the file-system is full, we run GC which is moving valid
-         * nodes from LEB X to LEB Y (obviously, LEB Y is the current GC head
-         * LEB). The @c->gc_lnum is -1, which means that GC will retain LEB X
-         * and will try to continue. Imagine that LEB X is currently the
-         * dirtiest LEB, and the amount of used space in LEB Y is exactly the
-         * same as amount of free space in LEB X.
-         *
-         * And a power cut happens when nodes are moved from LEB X to LEB Y. We
-         * are here trying to recover LEB Y which is the GC head LEB. We find
-         * the min. I/O unit B as described above. Then we clean-up LEB Y by
-         * padding min. I/O unit. And later 'ubifs_rcvry_gc_commit()' function
-         * fails, because it cannot find a dirty LEB which could be GC'd into
-         * LEB Y! Even LEB X does not match because the amount of valid nodes
-         * there does not fit the free space in LEB Y any more! And this is
-         * because of the padding node which we added to LEB Y. The
-         * user-visible effect of this which I once observed and analysed is
-         * that we cannot mount the file-system with -ENOSPC error.
-         *
-         * So obviously, to make sure that situation does not happen we should
-         * free min. I/O unit B in LEB Y completely and the last used min. I/O
-         * unit in LEB Y should be A. This is basically what the below code
-         * tries to do.
-         */
-        while (min_io_unit == round_down(offs, c->min_io_size) &&
-               min_io_unit != offs &&
-               drop_last_node(sleb, &offs, grouped));
+        if (jhead == GCHD) {
+                /*
+                 * If this LEB belongs to the GC head then while we are in the
+                 * middle of the same min. I/O unit keep dropping nodes. So
+                 * basically, what we want is to make sure that the last min.
+                 * I/O unit where we saw the corruption is dropped completely
+                 * with all the uncorrupted nodes which may possibly sit there.
+                 *
+                 * In other words, let's name the min. I/O unit where the
+                 * corruption starts B, and the previous min. I/O unit A. The
+                 * below code tries to deal with a situation when half of B
+                 * contains valid nodes or the end of a valid node, and the
+                 * second half of B contains corrupted data or garbage. This
+                 * means that UBIFS had been writing to B just before the power
+                 * cut happened. I do not know how realistic is this scenario
+                 * that half of the min. I/O unit had been written successfully
+                 * and the other half not, but this is possible in our 'failure
+                 * mode emulation' infrastructure at least.
+                 *
+                 * So what is the problem, why we need to drop those nodes? Why
+                 * can't we just clean-up the second half of B by putting a
+                 * padding node there? We can, and this works fine with one
+                 * exception which was reproduced with power cut emulation
+                 * testing and happens extremely rarely.
+                 *
+                 * Imagine the file-system is full, we run GC which starts
+                 * moving valid nodes from LEB X to LEB Y (obviously, LEB Y is
+                 * the current GC head LEB). The @c->gc_lnum is -1, which means
+                 * that GC will retain LEB X and will try to continue. Imagine
+                 * that LEB X is currently the dirtiest LEB, and the amount of
+                 * used space in LEB Y is exactly the same as amount of free
+                 * space in LEB X.
+                 *
+                 * And a power cut happens when nodes are moved from LEB X to
+                 * LEB Y. We are here trying to recover LEB Y which is the GC
+                 * head LEB. We find the min. I/O unit B as described above.
+                 * Then we clean-up LEB Y by padding min. I/O unit. And later
+                 * 'ubifs_rcvry_gc_commit()' function fails, because it cannot
+                 * find a dirty LEB which could be GC'd into LEB Y! Even LEB X
+                 * does not match because the amount of valid nodes there does
+                 * not fit the free space in LEB Y any more! And this is
+                 * because of the padding node which we added to LEB Y. The
+                 * user-visible effect of this which I once observed and
+                 * analysed is that we cannot mount the file-system with
+                 * -ENOSPC error.
+                 *
+                 * So obviously, to make sure that situation does not happen we
+                 * should free min. I/O unit B in LEB Y completely and the last
+                 * used min. I/O unit in LEB Y should be A. This is basically
+                 * what the below code tries to do.
+                 */
+                while (offs > min_io_unit)
+                        drop_last_node(sleb, &offs);
+        }
 
         buf = sbuf + offs;
         len = c->leb_size - offs;
@@ -881,7 +905,7 @@ struct ubifs_scan_leb *ubifs_recover_log_leb(struct ubifs_info *c, int lnum,
                 }
                 ubifs_scan_destroy(sleb);
         }
-        return ubifs_recover_leb(c, lnum, offs, sbuf, 0);
+        return ubifs_recover_leb(c, lnum, offs, sbuf, -1);
 }
 
 /**
diff --git a/fs/ubifs/replay.c b/fs/ubifs/replay.c
index 6617280d1679..5e97161ce4d3 100644
--- a/fs/ubifs/replay.c
+++ b/fs/ubifs/replay.c
@@ -557,8 +557,7 @@ static int replay_bud(struct ubifs_info *c, struct bud_entry *b)
                  * these LEBs could possibly be written to at the power cut
                  * time.
                  */
-                sleb = ubifs_recover_leb(c, lnum, offs, c->sbuf,
-                                         b->bud->jhead != GCHD);
+                sleb = ubifs_recover_leb(c, lnum, offs, c->sbuf, b->bud->jhead);
         else
                 sleb = ubifs_scan(c, lnum, offs, c->sbuf, 0);
         if (IS_ERR(sleb))
diff --git a/fs/ubifs/shrinker.c b/fs/ubifs/shrinker.c
index 46961c003236..9e1d05666fed 100644
--- a/fs/ubifs/shrinker.c
+++ b/fs/ubifs/shrinker.c
@@ -277,13 +277,18 @@ static int kick_a_thread(void)
         return 0;
 }
 
-int ubifs_shrinker(struct shrinker *shrink, int nr, gfp_t gfp_mask)
+int ubifs_shrinker(struct shrinker *shrink, struct shrink_control *sc)
 {
+        int nr = sc->nr_to_scan;
         int freed, contention = 0;
         long clean_zn_cnt = atomic_long_read(&ubifs_clean_zn_cnt);
 
         if (nr == 0)
-                return clean_zn_cnt;
+                /*
+                 * Due to the way UBIFS updates the clean znode counter it may
+                 * temporarily be negative.
+                 */
+                return clean_zn_cnt >= 0 ? clean_zn_cnt : 1;
 
         if (!clean_zn_cnt) {
                 /*
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 6db0bdaa9f74..b5aeb5a8ebed 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -382,7 +382,7 @@ done:
         end_writeback(inode);
 }
 
-static void ubifs_dirty_inode(struct inode *inode)
+static void ubifs_dirty_inode(struct inode *inode, int flags)
 {
         struct ubifs_inode *ui = ubifs_inode(inode);
 
@@ -811,15 +811,18 @@ static int alloc_wbufs(struct ubifs_info *c)
 
                 c->jheads[i].wbuf.sync_callback = &bud_wbuf_callback;
                 c->jheads[i].wbuf.jhead = i;
+                c->jheads[i].grouped = 1;
         }
 
         c->jheads[BASEHD].wbuf.dtype = UBI_SHORTTERM;
         /*
          * Garbage Collector head likely contains long-term data and
-         * does not need to be synchronized by timer.
+         * does not need to be synchronized by timer. Also GC head nodes are
+         * not grouped.
          */
         c->jheads[GCHD].wbuf.dtype = UBI_LONGTERM;
         c->jheads[GCHD].wbuf.no_timer = 1;
+        c->jheads[GCHD].grouped = 0;
 
         return 0;
 }
@@ -1284,12 +1287,25 @@ static int mount_ubifs(struct ubifs_info *c)
         if ((c->mst_node->flags & cpu_to_le32(UBIFS_MST_DIRTY)) != 0) {
                 ubifs_msg("recovery needed");
                 c->need_recovery = 1;
-                if (!c->ro_mount) {
-                        err = ubifs_recover_inl_heads(c, c->sbuf);
-                        if (err)
-                                goto out_master;
-                }
-        } else if (!c->ro_mount) {
+        }
+
+        if (c->need_recovery && !c->ro_mount) {
+                err = ubifs_recover_inl_heads(c, c->sbuf);
+                if (err)
+                        goto out_master;
+        }
+
+        err = ubifs_lpt_init(c, 1, !c->ro_mount);
+        if (err)
+                goto out_master;
+
+        if (!c->ro_mount && c->space_fixup) {
+                err = ubifs_fixup_free_space(c);
+                if (err)
+                        goto out_master;
+        }
+
+        if (!c->ro_mount) {
                 /*
                  * Set the "dirty" flag so that if we reboot uncleanly we
                  * will notice this immediately on the next mount.
@@ -1297,13 +1313,9 @@ static int mount_ubifs(struct ubifs_info *c)
                 c->mst_node->flags |= cpu_to_le32(UBIFS_MST_DIRTY);
                 err = ubifs_write_master(c);
                 if (err)
-                        goto out_master;
+                        goto out_lpt;
         }
 
-        err = ubifs_lpt_init(c, 1, !c->ro_mount);
-        if (err)
-                goto out_lpt;
-
         err = dbg_check_idx_size(c, c->bi.old_idx_sz);
         if (err)
                 goto out_lpt;
@@ -1396,12 +1408,6 @@ static int mount_ubifs(struct ubifs_info *c)
         } else
                 ubifs_assert(c->lst.taken_empty_lebs > 0);
 
-        if (!c->ro_mount && c->space_fixup) {
-                err = ubifs_fixup_free_space(c);
-                if (err)
-                        goto out_infos;
-        }
-
         err = dbg_check_filesystem(c);
         if (err)
                 goto out_infos;
diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c
index 8119b1fd8d94..91b4213dde84 100644
--- a/fs/ubifs/tnc.c
+++ b/fs/ubifs/tnc.c
@@ -2876,12 +2876,13 @@ static void tnc_destroy_cnext(struct ubifs_info *c)
  */
 void ubifs_tnc_close(struct ubifs_info *c)
 {
-        long clean_freed;
-
         tnc_destroy_cnext(c);
         if (c->zroot.znode) {
-                clean_freed = ubifs_destroy_tnc_subtree(c->zroot.znode);
-                atomic_long_sub(clean_freed, &ubifs_clean_zn_cnt);
+                long n;
+
+                ubifs_destroy_tnc_subtree(c->zroot.znode);
+                n = atomic_long_read(&c->clean_zn_cnt);
+                atomic_long_sub(n, &ubifs_clean_zn_cnt);
         }
         kfree(c->gap_lebs);
         kfree(c->ilebs);
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index 93d1412a06f0..f79983d6f860 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -722,12 +722,14 @@ struct ubifs_bud {
  * struct ubifs_jhead - journal head.
  * @wbuf: head's write-buffer
  * @buds_list: list of bud LEBs belonging to this journal head
+ * @grouped: non-zero if UBIFS groups nodes when writing to this journal head
  *
  * Note, the @buds list is protected by the @c->buds_lock.
  */
 struct ubifs_jhead {
         struct ubifs_wbuf wbuf;
         struct list_head buds_list;
+        unsigned int grouped:1;
 };
 
 /**
@@ -1614,7 +1616,7 @@ int ubifs_tnc_start_commit(struct ubifs_info *c, struct ubifs_zbranch *zroot);
 int ubifs_tnc_end_commit(struct ubifs_info *c);
 
 /* shrinker.c */
-int ubifs_shrinker(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask);
+int ubifs_shrinker(struct shrinker *shrink, struct shrink_control *sc);
 
 /* commit.c */
 int ubifs_bg_thread(void *info);
@@ -1742,7 +1744,7 @@ struct inode *ubifs_iget(struct super_block *sb, unsigned long inum);
 int ubifs_recover_master_node(struct ubifs_info *c);
 int ubifs_write_rcvrd_mst_node(struct ubifs_info *c);
 struct ubifs_scan_leb *ubifs_recover_leb(struct ubifs_info *c, int lnum,
-                                         int offs, void *sbuf, int grouped);
+                                         int offs, void *sbuf, int jhead);
 struct ubifs_scan_leb *ubifs_recover_log_leb(struct ubifs_info *c, int lnum,
                                              int offs, void *sbuf);
 int ubifs_recover_inl_heads(const struct ubifs_info *c, void *sbuf);
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index 4d76594c2a8f..f1dce848ef96 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -783,8 +783,6 @@ static int udf_rmdir(struct inode *dir, struct dentry *dentry)
         struct fileIdentDesc *fi, cfi;
         struct kernel_lb_addr tloc;
 
-        dentry_unhash(dentry);
-
         retval = -ENOENT;
         fi = udf_find_entry(dir, &dentry->d_name, &fibh, &cfi);
         if (!fi)
@@ -1083,9 +1081,6 @@ static int udf_rename(struct inode *old_dir, struct dentry *old_dentry,
         struct kernel_lb_addr tloc;
         struct udf_inode_info *old_iinfo = UDF_I(old_inode);
 
-        if (new_inode && S_ISDIR(new_inode->i_mode))
-                dentry_unhash(new_dentry);
-
         ofi = udf_find_entry(old_dir, &old_dentry->d_name, &ofibh, &ocfi);
         if (ofi) {
                 if (ofibh.sbh != ofibh.ebh)
diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c
index 953ebdfc5bf7..29309e25417f 100644
--- a/fs/ufs/namei.c
+++ b/fs/ufs/namei.c
@@ -258,8 +258,6 @@ static int ufs_rmdir (struct inode * dir, struct dentry *dentry)
         struct inode * inode = dentry->d_inode;
         int err= -ENOTEMPTY;
 
-        dentry_unhash(dentry);
-
         lock_ufs(dir->i_sb);
         if (ufs_empty_dir (inode)) {
                 err = ufs_unlink(dir, dentry);
@@ -284,9 +282,6 @@ static int ufs_rename(struct inode *old_dir, struct dentry *old_dentry,
         struct ufs_dir_entry *old_de;
         int err = -ENOENT;
 
-        if (new_inode && S_ISDIR(new_inode->i_mode))
-                dentry_unhash(new_dentry);
-
         old_de = ufs_find_entry(old_dir, &old_dentry->d_name, &old_page);
         if (!old_de)
                 goto out;
diff --git a/fs/xattr.c b/fs/xattr.c
index f1ef94974dea..f060663ab70c 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -46,18 +46,22 @@ xattr_permission(struct inode *inode, const char *name, int mask)
                 return 0;
 
         /*
-         * The trusted.* namespace can only be accessed by a privileged user.
+         * The trusted.* namespace can only be accessed by privileged users.
          */
-        if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN))
-                return (capable(CAP_SYS_ADMIN) ? 0 : -EPERM);
+        if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN)) {
+                if (!capable(CAP_SYS_ADMIN))
+                        return (mask & MAY_WRITE) ? -EPERM : -ENODATA;
+                return 0;
+        }
 
-        /* In user.* namespace, only regular files and directories can have
+        /*
+         * In the user.* namespace, only regular files and directories can have
          * extended attributes. For sticky directories, only the owner and
-         * privileged user can write attributes.
+         * privileged users can write attributes.
          */
         if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) {
                 if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode))
-                        return -EPERM;
+                        return (mask & MAY_WRITE) ? -EPERM : -ENODATA;
                 if (S_ISDIR(inode->i_mode) && (inode->i_mode & S_ISVTX) &&
                     (mask & MAY_WRITE) && !inode_owner_or_capable(inode))
                         return -EPERM;
@@ -87,7 +91,11 @@ int __vfs_setxattr_noperm(struct dentry *dentry, const char *name,
 {
         struct inode *inode = dentry->d_inode;
         int error = -EOPNOTSUPP;
+        int issec = !strncmp(name, XATTR_SECURITY_PREFIX,
+                                   XATTR_SECURITY_PREFIX_LEN);
 
+        if (issec)
+                inode->i_flags &= ~S_NOSEC;
         if (inode->i_op->setxattr) {
                 error = inode->i_op->setxattr(dentry, name, value, size, flags);
                 if (!error) {
@@ -95,8 +103,7 @@ int __vfs_setxattr_noperm(struct dentry *dentry, const char *name,
                         security_inode_post_setxattr(dentry, name, value,
                                                      size, flags);
                 }
-        } else if (!strncmp(name, XATTR_SECURITY_PREFIX,
-                                XATTR_SECURITY_PREFIX_LEN)) {
+        } else if (issec) {
                 const char *suffix = name + XATTR_SECURITY_PREFIX_LEN;
                 error = security_inode_setsecurity(inode, suffix, value,
                                                    size, flags);
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index 98b9c91fcdf1..1e3a7ce804dc 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -925,7 +925,8 @@ xfs_fs_inode_init_once(
  */
 STATIC void
 xfs_fs_dirty_inode(
-        struct inode    *inode)
+        struct inode    *inode,
+        int             flags)
 {
         barrier();
         XFS_I(inode)->i_update_core = 1;
diff --git a/include/acpi/acpiosxf.h b/include/acpi/acpiosxf.h
index a3252a5ead66..a756bc8d866d 100644
--- a/include/acpi/acpiosxf.h
+++ b/include/acpi/acpiosxf.h
@@ -98,6 +98,9 @@ acpi_os_table_override(struct acpi_table_header *existing_table,
 /*
  * Spinlock primitives
  */
+acpi_status
+acpi_os_create_lock(acpi_spinlock *out_handle);
+
 void acpi_os_delete_lock(acpi_spinlock handle);
 
 acpi_cpu_flags acpi_os_acquire_lock(acpi_spinlock handle);
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index f6ad63d25b73..2ed0a8486c19 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -47,7 +47,7 @@
 
 /* Current ACPICA subsystem version in YYYYMMDD format */
 
-#define ACPI_CA_VERSION                 0x20110316
+#define ACPI_CA_VERSION                 0x20110413
 
 #include "actypes.h"
 #include "actbl.h"
diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index 64f838beaabf..b67231bef632 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -501,8 +501,9 @@ typedef u64 acpi_integer;
 #define ACPI_STATE_D1                   (u8) 1
 #define ACPI_STATE_D2                   (u8) 2
 #define ACPI_STATE_D3                   (u8) 3
-#define ACPI_D_STATES_MAX               ACPI_STATE_D3
-#define ACPI_D_STATE_COUNT              4
+#define ACPI_STATE_D3_COLD              (u8) 4
+#define ACPI_D_STATES_MAX               ACPI_STATE_D3_COLD
+#define ACPI_D_STATE_COUNT              5
 
 #define ACPI_STATE_C0                   (u8) 0
 #define ACPI_STATE_C1                   (u8) 1
@@ -712,8 +713,24 @@ typedef u8 acpi_adr_space_type;
 #define ACPI_ADR_SPACE_CMOS             (acpi_adr_space_type) 5
 #define ACPI_ADR_SPACE_PCI_BAR_TARGET   (acpi_adr_space_type) 6
 #define ACPI_ADR_SPACE_IPMI             (acpi_adr_space_type) 7
-#define ACPI_ADR_SPACE_DATA_TABLE       (acpi_adr_space_type) 8
-#define ACPI_ADR_SPACE_FIXED_HARDWARE   (acpi_adr_space_type) 127
+
+#define ACPI_NUM_PREDEFINED_REGIONS     8
+
+/*
+ * Special Address Spaces
+ *
+ * Note: A Data Table region is a special type of operation region
+ * that has its own AML opcode. However, internally, the AML
+ * interpreter simply creates an operation region with an an address
+ * space type of ACPI_ADR_SPACE_DATA_TABLE.
+ */
+#define ACPI_ADR_SPACE_DATA_TABLE       (acpi_adr_space_type) 0x7E      /* Internal to ACPICA only */
+#define ACPI_ADR_SPACE_FIXED_HARDWARE   (acpi_adr_space_type) 0x7F
+
+/* Values for _REG connection code */
+
+#define ACPI_REG_DISCONNECT             0
+#define ACPI_REG_CONNECT                1
 
 /*
  * bit_register IDs
diff --git a/include/acpi/processor.h b/include/acpi/processor.h
index 55192ac0cede..ba4928cae473 100644
--- a/include/acpi/processor.h
+++ b/include/acpi/processor.h
@@ -310,14 +310,7 @@ static inline int acpi_processor_get_bios_limit(int cpu, unsigned int *limit)
 
 /* in processor_core.c */
 void acpi_processor_set_pdc(acpi_handle handle);
-#ifdef CONFIG_SMP
 int acpi_get_cpuid(acpi_handle, int type, u32 acpi_id);
-#else
-static inline int acpi_get_cpuid(acpi_handle handle, int type, u32 acpi_id)
-{
-        return -1;
-}
-#endif
 
 /* in processor_throttling.c */
 int acpi_processor_tstate_has_changed(struct acpi_processor *pr);
diff --git a/include/asm-generic/unistd.h b/include/asm-generic/unistd.h
index ae90e0f63995..4f76959397fa 100644
--- a/include/asm-generic/unistd.h
+++ b/include/asm-generic/unistd.h
@@ -683,9 +683,11 @@ __SC_COMP(__NR_clock_adjtime, sys_clock_adjtime, compat_sys_clock_adjtime)
 __SYSCALL(__NR_syncfs, sys_syncfs)
 #define __NR_setns 268
 __SYSCALL(__NR_setns, sys_setns)
+#define __NR_sendmmsg 269
+__SC_COMP(__NR_sendmmsg, sys_sendmmsg, compat_sys_sendmmsg)
 
 #undef __NR_syscalls
-#define __NR_syscalls 269
+#define __NR_syscalls 270
 
 /*
  * All syscalls below here should go away really,
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index a2e910e01293..1deb2a73c2da 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -150,8 +150,7 @@ extern int ec_read(u8 addr, u8 *val);
 extern int ec_write(u8 addr, u8 val);
 extern int ec_transaction(u8 command,
                           const u8 *wdata, unsigned wdata_len,
-                          u8 *rdata, unsigned rdata_len,
-                          int force_poll);
+                          u8 *rdata, unsigned rdata_len);
 
 #if defined(CONFIG_ACPI_WMI) || defined(CONFIG_ACPI_WMI_MODULE)
 
diff --git a/include/linux/atomic.h b/include/linux/atomic.h
index 96c038e43d66..ee456c79b0e6 100644
--- a/include/linux/atomic.h
+++ b/include/linux/atomic.h
@@ -34,4 +34,17 @@ static inline int atomic_inc_not_zero_hint(atomic_t *v, int hint)
 }
 #endif
 
+#ifndef CONFIG_ARCH_HAS_ATOMIC_OR
+static inline void atomic_or(int i, atomic_t *v)
+{
+        int old;
+        int new;
+
+        do {
+                old = atomic_read(v);
+                new = old | i;
+        } while (atomic_cmpxchg(v, old, new) != old);
+}
+#endif /* #ifndef CONFIG_ARCH_HAS_ATOMIC_OR */
+
 #endif /* _LINUX_ATOMIC_H */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index ae9091a68480..1a23722e8878 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1282,8 +1282,8 @@ queue_max_integrity_segments(struct request_queue *q)
 #define blk_get_integrity(a)                    (0)
 #define blk_integrity_compare(a, b)             (0)
 #define blk_integrity_register(a, b)            (0)
-#define blk_integrity_unregister(a)             do { } while (0);
-#define blk_queue_max_integrity_segments(a, b)  do { } while (0);
+#define blk_integrity_unregister(a)             do { } while (0)
+#define blk_queue_max_integrity_segments(a, b)  do { } while (0)
 #define queue_max_integrity_segments(a)         (0)
 #define blk_integrity_merge_rq(a, b, c)         (0)
 #define blk_integrity_merge_bio(a, b, c)        (0)
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index f20eb8f16025..e9eaec522655 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -146,7 +146,7 @@ static inline void cpuset_cpus_allowed(struct task_struct *p,
 
 static inline int cpuset_cpus_allowed_fallback(struct task_struct *p)
 {
-        cpumask_copy(&p->cpus_allowed, cpu_possible_mask);
+        do_set_cpus_allowed(p, cpu_possible_mask);
         return cpumask_any(cpu_active_mask);
 }
 
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 32a4423710f5..4427e0454051 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -191,6 +191,12 @@ struct dm_target {
 
         /* Used to provide an error string from the ctr */
         char *error;
+
+        /*
+         * Set if this target needs to receive discards regardless of
+         * whether or not its underlying devices have support.
+         */
+        unsigned discards_supported:1;
 };
 
 /* Each target can link one of these into the table */
diff --git a/include/linux/dm-io.h b/include/linux/dm-io.h
index 5c9186b93fff..f4b0aa3126f5 100644
--- a/include/linux/dm-io.h
+++ b/include/linux/dm-io.h
@@ -69,8 +69,7 @@ struct dm_io_request {
  *
  * Create/destroy may block.
  */
-struct dm_io_client *dm_io_client_create(unsigned num_pages);
-int dm_io_client_resize(unsigned num_pages, struct dm_io_client *client);
+struct dm_io_client *dm_io_client_create(void);
 void dm_io_client_destroy(struct dm_io_client *client);
 
 /*
diff --git a/include/linux/dm-kcopyd.h b/include/linux/dm-kcopyd.h
index 5db216311695..298d587e349b 100644
--- a/include/linux/dm-kcopyd.h
+++ b/include/linux/dm-kcopyd.h
@@ -25,8 +25,7 @@
  * To use kcopyd you must first create a dm_kcopyd_client object.
  */
 struct dm_kcopyd_client;
-int dm_kcopyd_client_create(unsigned num_pages,
-                            struct dm_kcopyd_client **result);
+struct dm_kcopyd_client *dm_kcopyd_client_create(void);
 void dm_kcopyd_client_destroy(struct dm_kcopyd_client *kc);
 
 /*
diff --git a/include/linux/dma_remapping.h b/include/linux/dma_remapping.h
index 5619f8522738..bbd8661b3473 100644
--- a/include/linux/dma_remapping.h
+++ b/include/linux/dma_remapping.h
@@ -9,8 +9,12 @@
 #define VTD_PAGE_MASK           (((u64)-1) << VTD_PAGE_SHIFT)
 #define VTD_PAGE_ALIGN(addr)    (((addr) + VTD_PAGE_SIZE - 1) & VTD_PAGE_MASK)
 
+#define VTD_STRIDE_SHIFT        (9)
+#define VTD_STRIDE_MASK         (((u64)-1) << VTD_STRIDE_SHIFT)
+
 #define DMA_PTE_READ (1)
 #define DMA_PTE_WRITE (2)
+#define DMA_PTE_LARGE_PAGE (1 << 7)
 #define DMA_PTE_SNP (1 << 11)
 
 #define CONTEXT_TT_MULTI_LEVEL  0
diff --git a/include/linux/dw_dmac.h b/include/linux/dw_dmac.h
index 6998d9376ef9..4bfe0a2f7d50 100644
--- a/include/linux/dw_dmac.h
+++ b/include/linux/dw_dmac.h
@@ -3,6 +3,7 @@
  * AVR32 systems.)
  *
  * Copyright (C) 2007 Atmel Corporation
+ * Copyright (C) 2010-2011 ST Microelectronics
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 33fa1203024e..e376270cd26e 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -299,6 +299,7 @@ extern void efi_initialize_iomem_resources(struct resource *code_resource,
                 struct resource *data_resource, struct resource *bss_resource);
 extern unsigned long efi_get_time(void);
 extern int efi_set_rtc_mmss(unsigned long nowtime);
+extern void efi_reserve_boot_services(void);
 extern struct efi_memory_map memmap;
 
 /**
diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h
index 85c1d302c12e..5e06acf95d0f 100644
--- a/include/linux/ext3_fs.h
+++ b/include/linux/ext3_fs.h
@@ -909,7 +909,7 @@ extern int  ext3_setattr (struct dentry *, struct iattr *);
 extern void ext3_evict_inode (struct inode *);
 extern int  ext3_sync_inode (handle_t *, struct inode *);
 extern void ext3_discard_reservation (struct inode *);
-extern void ext3_dirty_inode(struct inode *);
+extern void ext3_dirty_inode(struct inode *, int);
 extern int ext3_change_inode_journal_flag(struct inode *, int);
 extern int ext3_get_inode_loc(struct inode *, struct ext3_iloc *);
 extern int ext3_can_truncate(struct inode *inode);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 241609346dfb..c55d6b7cd5d6 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -237,6 +237,7 @@ struct inodes_stat_t {
 #define S_PRIVATE       512     /* Inode is fs-internal */
 #define S_IMA           1024    /* Inode has an associated IMA struct */
 #define S_AUTOMOUNT     2048    /* Automount/referral quasi-directory */
+#define S_NOSEC         4096    /* no suid or xattr security attributes */
 
 /*
  * Note that nosuid etc flags are inode-specific: setting some file-system
@@ -273,6 +274,7 @@ struct inodes_stat_t {
 #define IS_PRIVATE(inode)       ((inode)->i_flags & S_PRIVATE)
 #define IS_IMA(inode)           ((inode)->i_flags & S_IMA)
 #define IS_AUTOMOUNT(inode)     ((inode)->i_flags & S_AUTOMOUNT)
+#define IS_NOSEC(inode)         ((inode)->i_flags & S_NOSEC)
 
 /* the read-only stuff doesn't really belong here, but any other place is
    probably as bad and I don't want to create yet another include file. */
@@ -1618,7 +1620,7 @@ struct super_operations {
         struct inode *(*alloc_inode)(struct super_block *sb);
         void (*destroy_inode)(struct inode *);
 
-        void (*dirty_inode) (struct inode *);
+        void (*dirty_inode) (struct inode *, int flags);
         int (*write_inode) (struct inode *, struct writeback_control *wbc);
         int (*drop_inode) (struct inode *);
         void (*evict_inode) (struct inode *);
@@ -2582,5 +2584,16 @@ int __init get_filesystem_list(char *buf);
 #define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \
                                             (flag & __FMODE_NONOTIFY)))
 
+static inline int is_sxid(mode_t mode)
+{
+        return (mode & S_ISUID) || ((mode & S_ISGID) && (mode & S_IXGRP));
+}
+
+static inline void inode_has_no_xattr(struct inode *inode)
+{
+        if (!is_sxid(inode->i_mode))
+                inode->i_flags |= S_NOSEC;
+}
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_FS_H */
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index b5a550a39a70..59d3ef100eb9 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -16,6 +16,11 @@ struct trace_print_flags {
         const char              *name;
 };
 
+struct trace_print_flags_u64 {
+        unsigned long long      mask;
+        const char              *name;
+};
+
 const char *ftrace_print_flags_seq(struct trace_seq *p, const char *delim,
                                    unsigned long flags,
                                    const struct trace_print_flags *flag_array);
@@ -23,6 +28,13 @@ const char *ftrace_print_flags_seq(struct trace_seq *p, const char *delim,
 const char *ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val,
                                      const struct trace_print_flags *symbol_array);
 
+#if BITS_PER_LONG == 32
+const char *ftrace_print_symbols_seq_u64(struct trace_seq *p,
+                                         unsigned long long val,
+                                         const struct trace_print_flags_u64
+                                                                 *symbol_array);
+#endif
+
 const char *ftrace_print_hex_seq(struct trace_seq *p,
                                  const unsigned char *buf, int len);
 
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index b78956b3c2e7..300d7582006e 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -100,6 +100,7 @@ struct hd_struct {
         sector_t start_sect;
         sector_t nr_sects;
         sector_t alignment_offset;
+        unsigned int discard_alignment;
         struct device __dev;
         struct kobject *holder_dir;
         int policy, partno;
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index b2eee5879883..bf56b6f78270 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1003,8 +1003,12 @@ struct ieee80211_ht_info {
 #define WLAN_CAPABILITY_ESS             (1<<0)
 #define WLAN_CAPABILITY_IBSS            (1<<1)
 
-/* A mesh STA sets the ESS and IBSS capability bits to zero */
-#define WLAN_CAPABILITY_IS_MBSS(cap)    \
+/*
+ * A mesh STA sets the ESS and IBSS capability bits to zero.
+ * however, this holds true for p2p probe responses (in the p2p_find
+ * phase) as well.
+ */
+#define WLAN_CAPABILITY_IS_STA_BSS(cap) \
         (!((cap) & (WLAN_CAPABILITY_ESS | WLAN_CAPABILITY_IBSS)))
 
 #define WLAN_CAPABILITY_CF_POLLABLE     (1<<2)
diff --git a/include/linux/if_packet.h b/include/linux/if_packet.h
index 72bfa5a034dd..6d66ce1791a9 100644
--- a/include/linux/if_packet.h
+++ b/include/linux/if_packet.h
@@ -70,6 +70,7 @@ struct tpacket_auxdata {
 #define TP_STATUS_COPY          0x2
 #define TP_STATUS_LOSING        0x4
 #define TP_STATUS_CSUMNOTREADY  0x8
+#define TP_STATUS_VLAN_VALID   0x10 /* auxdata has valid tp_vlan_tci */
 
 /* Tx ring - header status */
 #define TP_STATUS_AVAILABLE     0x0
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 2a78aae78c69..027935c86c68 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -264,6 +264,8 @@ struct mm_struct {
 
         struct linux_binfmt *binfmt;
 
+        cpumask_var_t cpu_vm_mask_var;
+
         /* Architecture-specific MM context */
         mm_context_t context;
 
@@ -311,10 +313,18 @@ struct mm_struct {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
         pgtable_t pmd_huge_pte; /* protected by page_table_lock */
 #endif
-
-        cpumask_var_t cpu_vm_mask_var;
+#ifdef CONFIG_CPUMASK_OFFSTACK
+        struct cpumask cpumask_allocation;
+#endif
 };
 
+static inline void mm_init_cpumask(struct mm_struct *mm)
+{
+#ifdef CONFIG_CPUMASK_OFFSTACK
+        mm->cpu_vm_mask_var = &mm->cpumask_allocation;
+#endif
+}
+
 /* Future-safe accessor for struct mm_struct's cpu_vm_mask. */
 static inline cpumask_t *mm_cpumask(struct mm_struct *mm)
 {
diff --git a/include/linux/mtd/physmap.h b/include/linux/mtd/physmap.h
index d40bfa1d9c91..e5f21d293c70 100644
--- a/include/linux/mtd/physmap.h
+++ b/include/linux/mtd/physmap.h
@@ -19,6 +19,7 @@
 #include <linux/mtd/partitions.h>
 
 struct map_info;
+struct platform_device;
 
 struct physmap_flash_data {
         unsigned int            width;
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 178fafe0ff93..504b289ba680 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -562,6 +562,7 @@ enum {
         NFSPROC4_CLNT_LAYOUTGET,
         NFSPROC4_CLNT_GETDEVICEINFO,
         NFSPROC4_CLNT_LAYOUTCOMMIT,
+        NFSPROC4_CLNT_LAYOUTRETURN,
 };
 
 /* nfs41 types */
@@ -570,9 +571,11 @@ struct nfs4_sessionid {
 };
 
 /* Create Session Flags */
-#define SESSION4_PERSIST         0x001
-#define SESSION4_BACK_CHAN       0x002
-#define SESSION4_RDMA            0x004
+#define SESSION4_PERSIST        0x001
+#define SESSION4_BACK_CHAN      0x002
+#define SESSION4_RDMA           0x004
+
+#define SESSION4_FLAG_MASK_A    0x007
 
 enum state_protect_how4 {
         SP4_NONE        = 0,
diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h
index 91af2e49fa3a..3a34e80ae92f 100644
--- a/include/linux/nfs_page.h
+++ b/include/linux/nfs_page.h
@@ -68,7 +68,7 @@ struct nfs_pageio_descriptor {
         int                     pg_ioflags;
         int                     pg_error;
         struct pnfs_layout_segment *pg_lseg;
-        int                     (*pg_test)(struct nfs_pageio_descriptor *, struct nfs_page *, struct nfs_page *);
+        bool                    (*pg_test)(struct nfs_pageio_descriptor *, struct nfs_page *, struct nfs_page *);
 };
 
 #define NFS_WBACK_BUSY(req)     (test_bit(PG_BUSY,&(req)->wb_flags))
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 7e371f7df9c4..5e8444a11adf 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -269,6 +269,27 @@ struct nfs4_layoutcommit_data {
         struct nfs4_layoutcommit_res res;
 };
 
+struct nfs4_layoutreturn_args {
+        __u32   layout_type;
+        struct inode *inode;
+        nfs4_stateid stateid;
+        struct nfs4_sequence_args seq_args;
+};
+
+struct nfs4_layoutreturn_res {
+        struct nfs4_sequence_res seq_res;
+        u32 lrs_present;
+        nfs4_stateid stateid;
+};
+
+struct nfs4_layoutreturn {
+        struct nfs4_layoutreturn_args args;
+        struct nfs4_layoutreturn_res res;
+        struct rpc_cred *cred;
+        struct nfs_client *clp;
+        int rpc_status;
+};
+
 /*
  * Arguments to the open call.
  */
@@ -1087,6 +1108,7 @@ struct nfs_read_data {
         const struct rpc_call_ops *mds_ops;
         int (*read_done_cb) (struct rpc_task *task, struct nfs_read_data *data);
         __u64                   mds_offset;
+        int                     pnfs_error;
         struct page             *page_array[NFS_PAGEVEC_SIZE];
 };
 
@@ -1112,6 +1134,7 @@ struct nfs_write_data {
         unsigned long           timestamp;      /* For lease renewal */
 #endif
         __u64                   mds_offset;     /* Filelayout dense stripe */
+        int                     pnfs_error;
         struct page             *page_array[NFS_PAGEVEC_SIZE];
 };
 
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 79a6700b7162..6081493db68f 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -308,7 +308,7 @@ static inline void SetPageUptodate(struct page *page)
 {
 #ifdef CONFIG_S390
         if (!test_and_set_bit(PG_uptodate, &page->flags))
-                page_set_storage_key(page_to_pfn(page), PAGE_DEFAULT_KEY, 0);
+                page_set_storage_key(page_to_phys(page), PAGE_DEFAULT_KEY, 0);
 #else
         /*
          * Memory barrier must be issued before setting the PG_uptodate bit,
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 24787b751286..a311008af5e1 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2483,6 +2483,7 @@
 #define PCI_DEVICE_ID_INTEL_COUGARPOINT_LPC_MAX 0x1c5f
 #define PCI_DEVICE_ID_INTEL_PATSBURG_LPC_0      0x1d40
 #define PCI_DEVICE_ID_INTEL_PATSBURG_LPC_1      0x1d41
+#define PCI_DEVICE_ID_INTEL_PANTHERPOINT_XHCI   0x1e31
 #define PCI_DEVICE_ID_INTEL_PANTHERPOINT_LPC_MIN        0x1e40
 #define PCI_DEVICE_ID_INTEL_PANTHERPOINT_LPC_MAX        0x1e5f
 #define PCI_DEVICE_ID_INTEL_DH89XXCC_LPC_MIN    0x2310
diff --git a/include/linux/pm_qos_params.h b/include/linux/pm_qos_params.h
index 77cbddb3784c..a7d87f911cab 100644
--- a/include/linux/pm_qos_params.h
+++ b/include/linux/pm_qos_params.h
@@ -16,6 +16,10 @@
 #define PM_QOS_NUM_CLASSES 4
 #define PM_QOS_DEFAULT_VALUE -1
 
+#define PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE        (2000 * USEC_PER_SEC)
+#define PM_QOS_NETWORK_LAT_DEFAULT_VALUE        (2000 * USEC_PER_SEC)
+#define PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE 0
+
 struct pm_qos_request_list {
         struct plist_node list;
         int pm_qos_class;
diff --git a/include/linux/pnfs_osd_xdr.h b/include/linux/pnfs_osd_xdr.h
new file mode 100644
index 000000000000..76efbdd01622
--- /dev/null
+++ b/include/linux/pnfs_osd_xdr.h
@@ -0,0 +1,345 @@
+/*
+ *  pNFS-osd on-the-wire data structures
+ *
+ *  Copyright (C) 2007 Panasas Inc. [year of first publication]
+ *  All rights reserved.
+ *
+ *  Benny Halevy <bhalevy@panasas.com>
+ *  Boaz Harrosh <bharrosh@panasas.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  See the file COPYING included with this distribution for more details.
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *  1. Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *  2. Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in the
+ *     documentation and/or other materials provided with the distribution.
+ *  3. Neither the name of the Panasas company nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+#ifndef __PNFS_OSD_XDR_H__
+#define __PNFS_OSD_XDR_H__
+
+#include <linux/nfs_fs.h>
+#include <linux/nfs_page.h>
+#include <scsi/osd_protocol.h>
+
+#define PNFS_OSD_OSDNAME_MAXSIZE 256
+
+/*
+ * draft-ietf-nfsv4-minorversion-22
+ * draft-ietf-nfsv4-pnfs-obj-12
+ */
+
+/* Layout Structure */
+
+enum pnfs_osd_raid_algorithm4 {
+        PNFS_OSD_RAID_0         = 1,
+        PNFS_OSD_RAID_4         = 2,
+        PNFS_OSD_RAID_5         = 3,
+        PNFS_OSD_RAID_PQ        = 4     /* Reed-Solomon P+Q */
+};
+
+/*   struct pnfs_osd_data_map4 {
+ *       uint32_t                    odm_num_comps;
+ *       length4                     odm_stripe_unit;
+ *       uint32_t                    odm_group_width;
+ *       uint32_t                    odm_group_depth;
+ *       uint32_t                    odm_mirror_cnt;
+ *       pnfs_osd_raid_algorithm4    odm_raid_algorithm;
+ *   };
+ */
+struct pnfs_osd_data_map {
+        u32     odm_num_comps;
+        u64     odm_stripe_unit;
+        u32     odm_group_width;
+        u32     odm_group_depth;
+        u32     odm_mirror_cnt;
+        u32     odm_raid_algorithm;
+};
+
+/*   struct pnfs_osd_objid4 {
+ *       deviceid4       oid_device_id;
+ *       uint64_t        oid_partition_id;
+ *       uint64_t        oid_object_id;
+ *   };
+ */
+struct pnfs_osd_objid {
+        struct nfs4_deviceid    oid_device_id;
+        u64                     oid_partition_id;
+        u64                     oid_object_id;
+};
+
+/* For printout. I use:
+ * kprint("dev(%llx:%llx)", _DEVID_LO(pointer), _DEVID_HI(pointer));
+ * BE style
+ */
+#define _DEVID_LO(oid_device_id) \
+        (unsigned long long)be64_to_cpup((__be64 *)(oid_device_id)->data)
+
+#define _DEVID_HI(oid_device_id) \
+        (unsigned long long)be64_to_cpup(((__be64 *)(oid_device_id)->data) + 1)
+
+static inline int
+pnfs_osd_objid_xdr_sz(void)
+{
+        return (NFS4_DEVICEID4_SIZE / 4) + 2 + 2;
+}
+
+enum pnfs_osd_version {
+        PNFS_OSD_MISSING              = 0,
+        PNFS_OSD_VERSION_1            = 1,
+        PNFS_OSD_VERSION_2            = 2
+};
+
+struct pnfs_osd_opaque_cred {
+        u32 cred_len;
+        void *cred;
+};
+
+enum pnfs_osd_cap_key_sec {
+        PNFS_OSD_CAP_KEY_SEC_NONE     = 0,
+        PNFS_OSD_CAP_KEY_SEC_SSV      = 1,
+};
+
+/*   struct pnfs_osd_object_cred4 {
+ *       pnfs_osd_objid4         oc_object_id;
+ *       pnfs_osd_version4       oc_osd_version;
+ *       pnfs_osd_cap_key_sec4   oc_cap_key_sec;
+ *       opaque                  oc_capability_key<>;
+ *       opaque                  oc_capability<>;
+ *   };
+ */
+struct pnfs_osd_object_cred {
+        struct pnfs_osd_objid           oc_object_id;
+        u32                             oc_osd_version;
+        u32                             oc_cap_key_sec;
+        struct pnfs_osd_opaque_cred     oc_cap_key;
+        struct pnfs_osd_opaque_cred     oc_cap;
+};
+
+/*   struct pnfs_osd_layout4 {
+ *       pnfs_osd_data_map4      olo_map;
+ *       uint32_t                olo_comps_index;
+ *       pnfs_osd_object_cred4   olo_components<>;
+ *   };
+ */
+struct pnfs_osd_layout {
+        struct pnfs_osd_data_map        olo_map;
+        u32                             olo_comps_index;
+        u32                             olo_num_comps;
+        struct pnfs_osd_object_cred     *olo_comps;
+};
+
+/* Device Address */
+enum pnfs_osd_targetid_type {
+        OBJ_TARGET_ANON = 1,
+        OBJ_TARGET_SCSI_NAME = 2,
+        OBJ_TARGET_SCSI_DEVICE_ID = 3,
+};
+
+/*   union pnfs_osd_targetid4 switch (pnfs_osd_targetid_type4 oti_type) {
+ *       case OBJ_TARGET_SCSI_NAME:
+ *           string              oti_scsi_name<>;
+ *
+ *       case OBJ_TARGET_SCSI_DEVICE_ID:
+ *           opaque              oti_scsi_device_id<>;
+ *
+ *       default:
+ *           void;
+ *   };
+ *
+ *   union pnfs_osd_targetaddr4 switch (bool ota_available) {
+ *       case TRUE:
+ *           netaddr4            ota_netaddr;
+ *       case FALSE:
+ *           void;
+ *   };
+ *
+ *   struct pnfs_osd_deviceaddr4 {
+ *       pnfs_osd_targetid4      oda_targetid;
+ *       pnfs_osd_targetaddr4    oda_targetaddr;
+ *       uint64_t                oda_lun;
+ *       opaque                  oda_systemid<>;
+ *       pnfs_osd_object_cred4   oda_root_obj_cred;
+ *       opaque                  oda_osdname<>;
+ *   };
+ */
+struct pnfs_osd_targetid {
+        u32                             oti_type;
+        struct nfs4_string              oti_scsi_device_id;
+};
+
+enum { PNFS_OSD_TARGETID_MAX = 1 + PNFS_OSD_OSDNAME_MAXSIZE / 4 };
+
+/*   struct netaddr4 {
+ *       // see struct rpcb in RFC1833
+ *       string r_netid<>;    // network id
+ *       string r_addr<>;     // universal address
+ *   };
+ */
+struct pnfs_osd_net_addr {
+        struct nfs4_string      r_netid;
+        struct nfs4_string      r_addr;
+};
+
+struct pnfs_osd_targetaddr {
+        u32                             ota_available;
+        struct pnfs_osd_net_addr        ota_netaddr;
+};
+
+enum {
+        NETWORK_ID_MAX = 16 / 4,
+        UNIVERSAL_ADDRESS_MAX = 64 / 4,
+        PNFS_OSD_TARGETADDR_MAX = 3 +  NETWORK_ID_MAX + UNIVERSAL_ADDRESS_MAX,
+};
+
+struct pnfs_osd_deviceaddr {
+        struct pnfs_osd_targetid        oda_targetid;
+        struct pnfs_osd_targetaddr      oda_targetaddr;
+        u8                              oda_lun[8];
+        struct nfs4_string              oda_systemid;
+        struct pnfs_osd_object_cred     oda_root_obj_cred;
+        struct nfs4_string              oda_osdname;
+};
+
+enum {
+        ODA_OSDNAME_MAX = PNFS_OSD_OSDNAME_MAXSIZE / 4,
+        PNFS_OSD_DEVICEADDR_MAX =
+                PNFS_OSD_TARGETID_MAX + PNFS_OSD_TARGETADDR_MAX +
+                2 /*oda_lun*/ +
+                1 + OSD_SYSTEMID_LEN +
+                1 + ODA_OSDNAME_MAX,
+};
+
+/* LAYOUTCOMMIT: layoutupdate */
+
+/*   union pnfs_osd_deltaspaceused4 switch (bool dsu_valid) {
+ *       case TRUE:
+ *           int64_t     dsu_delta;
+ *       case FALSE:
+ *           void;
+ *   };
+ *
+ *   struct pnfs_osd_layoutupdate4 {
+ *       pnfs_osd_deltaspaceused4    olu_delta_space_used;
+ *       bool                        olu_ioerr_flag;
+ *   };
+ */
+struct pnfs_osd_layoutupdate {
+        u32     dsu_valid;
+        s64     dsu_delta;
+        u32     olu_ioerr_flag;
+};
+
+/* LAYOUTRETURN: I/O Rrror Report */
+
+enum pnfs_osd_errno {
+        PNFS_OSD_ERR_EIO                = 1,
+        PNFS_OSD_ERR_NOT_FOUND          = 2,
+        PNFS_OSD_ERR_NO_SPACE           = 3,
+        PNFS_OSD_ERR_BAD_CRED           = 4,
+        PNFS_OSD_ERR_NO_ACCESS          = 5,
+        PNFS_OSD_ERR_UNREACHABLE        = 6,
+        PNFS_OSD_ERR_RESOURCE           = 7
+};
+
+/*   struct pnfs_osd_ioerr4 {
+ *       pnfs_osd_objid4     oer_component;
+ *       length4             oer_comp_offset;
+ *       length4             oer_comp_length;
+ *       bool                oer_iswrite;
+ *       pnfs_osd_errno4     oer_errno;
+ *   };
+ */
+struct pnfs_osd_ioerr {
+        struct pnfs_osd_objid   oer_component;
+        u64                     oer_comp_offset;
+        u64                     oer_comp_length;
+        u32                     oer_iswrite;
+        u32                     oer_errno;
+};
+
+/* OSD XDR API */
+/* Layout helpers */
+/* Layout decoding is done in two parts:
+ * 1. First Call pnfs_osd_xdr_decode_layout_map to read in only the header part
+ *    of the layout. @iter members need not be initialized.
+ *    Returned:
+ *             @layout members are set. (@layout->olo_comps set to NULL).
+ *
+ *             Zero on success, or negative error if passed xdr is broken.
+ *
+ * 2. 2nd Call pnfs_osd_xdr_decode_layout_comp() in a loop until it returns
+ *    false, to decode the next component.
+ *    Returned:
+ *       true if there is more to decode or false if we are done or error.
+ *
+ * Example:
+ *      struct pnfs_osd_xdr_decode_layout_iter iter;
+ *      struct pnfs_osd_layout layout;
+ *      struct pnfs_osd_object_cred comp;
+ *      int status;
+ *
+ *      status = pnfs_osd_xdr_decode_layout_map(&layout, &iter, xdr);
+ *      if (unlikely(status))
+ *              goto err;
+ *      while(pnfs_osd_xdr_decode_layout_comp(&comp, &iter, xdr, &status)) {
+ *              // All of @comp strings point to inside the xdr_buffer
+ *              // or scrach buffer. Copy them out to user memory eg.
+ *              copy_single_comp(dest_comp++, &comp);
+ *      }
+ *      if (unlikely(status))
+ *              goto err;
+ */
+
+struct pnfs_osd_xdr_decode_layout_iter {
+        unsigned total_comps;
+        unsigned decoded_comps;
+};
+
+extern int pnfs_osd_xdr_decode_layout_map(struct pnfs_osd_layout *layout,
+        struct pnfs_osd_xdr_decode_layout_iter *iter, struct xdr_stream *xdr);
+
+extern bool pnfs_osd_xdr_decode_layout_comp(struct pnfs_osd_object_cred *comp,
+        struct pnfs_osd_xdr_decode_layout_iter *iter, struct xdr_stream *xdr,
+        int *err);
+
+/* Device Info helpers */
+
+/* Note: All strings inside @deviceaddr point to space inside @p.
+ * @p should stay valid while @deviceaddr is in use.
+ */
+extern void pnfs_osd_xdr_decode_deviceaddr(
+        struct pnfs_osd_deviceaddr *deviceaddr, __be32 *p);
+
+/* layoutupdate (layout_commit) xdr helpers */
+extern int
+pnfs_osd_xdr_encode_layoutupdate(struct xdr_stream *xdr,
+                                 struct pnfs_osd_layoutupdate *lou);
+
+/* osd_ioerror encoding/decoding (layout_return) */
+/* Client */
+extern __be32 *pnfs_osd_xdr_ioerr_reserve_space(struct xdr_stream *xdr);
+extern void pnfs_osd_xdr_encode_ioerr(__be32 *p, struct pnfs_osd_ioerr *ioerr);
+
+#endif /* __PNFS_OSD_XDR_H__ */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index dc8871295a5a..2a8621c4be1e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1546,7 +1546,7 @@ struct task_struct {
 #ifdef CONFIG_TRACING
         /* state flags for use by tracers */
         unsigned long trace;
-        /* bitmask of trace recursion */
+        /* bitmask and counter of trace recursion */
         unsigned long trace_recursion;
 #endif /* CONFIG_TRACING */
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR /* memcg uses this to do batch job */
@@ -1841,9 +1841,16 @@ static inline void rcu_copy_process(struct task_struct *p)
 #endif
 
 #ifdef CONFIG_SMP
+extern void do_set_cpus_allowed(struct task_struct *p,
+                               const struct cpumask *new_mask);
+
 extern int set_cpus_allowed_ptr(struct task_struct *p,
                                 const struct cpumask *new_mask);
 #else
+static inline void do_set_cpus_allowed(struct task_struct *p,
+                                      const struct cpumask *new_mask)
+{
+}
 static inline int set_cpus_allowed_ptr(struct task_struct *p,
                                        const struct cpumask *new_mask)
 {
@@ -2187,7 +2194,6 @@ static inline void mmdrop(struct mm_struct * mm)
         if (unlikely(atomic_dec_and_test(&mm->mm_count)))
                 __mmdrop(mm);
 }
-extern int mm_init_cpumask(struct mm_struct *mm, struct mm_struct *oldmm);
 
 /* mmput gets rid of the mappings and all user-space */
 extern void mmput(struct mm_struct *);
diff --git a/include/linux/sunrpc/msg_prot.h b/include/linux/sunrpc/msg_prot.h
index 77e624883393..c68a147939a6 100644
--- a/include/linux/sunrpc/msg_prot.h
+++ b/include/linux/sunrpc/msg_prot.h
@@ -145,6 +145,7 @@ typedef __be32	rpc_fraghdr;
 #define RPCBIND_NETID_TCP       "tcp"
 #define RPCBIND_NETID_UDP6      "udp6"
 #define RPCBIND_NETID_TCP6      "tcp6"
+#define RPCBIND_NETID_LOCAL     "local"
 
 /*
  * Note that RFC 1833 does not put any size restrictions on the
diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h
index 04dba23c59f2..85c50b40759d 100644
--- a/include/linux/sunrpc/svcsock.h
+++ b/include/linux/sunrpc/svcsock.h
@@ -28,6 +28,7 @@ struct svc_sock {
         /* private TCP part */
         u32                     sk_reclen;      /* length of record */
         u32                     sk_tcplen;      /* current read length */
+        struct page *           sk_pages[RPCSVC_MAXPAGES];      /* received data */
 };
 
 /*
diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index fc84b7a19ca3..a20970ef9e4e 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -216,6 +216,8 @@ extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes);
 extern void xdr_write_pages(struct xdr_stream *xdr, struct page **pages,
                 unsigned int base, unsigned int len);
 extern void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p);
+extern void xdr_init_decode_pages(struct xdr_stream *xdr, struct xdr_buf *buf,
+                struct page **pages, unsigned int len);
 extern void xdr_set_scratch_buffer(struct xdr_stream *xdr, void *buf, size_t buflen);
 extern __be32 *xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes);
 extern void xdr_read_pages(struct xdr_stream *xdr, unsigned int len);
diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index a0f998c07c65..81cce3b3ee66 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -141,7 +141,8 @@ enum xprt_transports {
         XPRT_TRANSPORT_UDP      = IPPROTO_UDP,
         XPRT_TRANSPORT_TCP      = IPPROTO_TCP,
         XPRT_TRANSPORT_BC_TCP   = IPPROTO_TCP | XPRT_TRANSPORT_BC,
-        XPRT_TRANSPORT_RDMA     = 256
+        XPRT_TRANSPORT_RDMA     = 256,
+        XPRT_TRANSPORT_LOCAL    = 257,
 };
 
 struct rpc_xprt {
diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h
index 5b07792ccb46..ff7dc08696a8 100644
--- a/include/linux/tty_ldisc.h
+++ b/include/linux/tty_ldisc.h
@@ -76,7 +76,7 @@
  *      tty device.  It is solely the responsibility of the line
  *      discipline to handle poll requests.
  *
- * unsigned int (*receive_buf)(struct tty_struct *, const unsigned char *cp,
+ * void (*receive_buf)(struct tty_struct *, const unsigned char *cp,
  *                     char *fp, int count);
  *
  *      This function is called by the low-level tty driver to send
@@ -84,8 +84,7 @@
  *      processing.  <cp> is a pointer to the buffer of input
  *      character received by the device.  <fp> is a pointer to a
  *      pointer of flag bytes which indicate whether a character was
- *      received with a parity error, etc. Returns the amount of bytes
- *      received.
+ *      received with a parity error, etc.
  * 
  * void (*write_wakeup)(struct tty_struct *);
  *
@@ -141,8 +140,8 @@ struct tty_ldisc_ops {
         /*
          * The following routines are called from below.
          */
-        unsigned int (*receive_buf)(struct tty_struct *,
-                        const unsigned char *cp, char *fp, int count);
+        void    (*receive_buf)(struct tty_struct *, const unsigned char *cp,
+                               char *fp, int count);
         void    (*write_wakeup)(struct tty_struct *);
         void    (*dcd_change)(struct tty_struct *, unsigned int,
                                 struct pps_event_time *);
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index d512d98dfb7d..5ca0951e1855 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -93,8 +93,8 @@ static inline unsigned long __copy_from_user_nocache(void *to,
  * Safely read from address @src to the buffer at @dst.  If a kernel fault
  * happens, handle that and return -EFAULT.
  */
-extern long probe_kernel_read(void *dst, void *src, size_t size);
-extern long __probe_kernel_read(void *dst, void *src, size_t size);
+extern long probe_kernel_read(void *dst, const void *src, size_t size);
+extern long __probe_kernel_read(void *dst, const void *src, size_t size);
 
 /*
  * probe_kernel_write(): safely attempt to write to a location
@@ -105,7 +105,7 @@ extern long __probe_kernel_read(void *dst, void *src, size_t size);
  * Safely write to address @dst from the buffer at @src.  If a kernel fault
  * happens, handle that and return -EFAULT.
  */
-extern long notrace probe_kernel_write(void *dst, void *src, size_t size);
-extern long notrace __probe_kernel_write(void *dst, void *src, size_t size);
+extern long notrace probe_kernel_write(void *dst, const void *src, size_t size);
+extern long notrace __probe_kernel_write(void *dst, const void *src, size_t size);
 
 #endif          /* __LINUX_UACCESS_H__ */
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index aff5b4f74041..710885749605 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -51,6 +51,13 @@ struct virtqueue {
  *      This re-enables callbacks; it returns "false" if there are pending
  *      buffers in the queue, to detect a possible race between the driver
  *      checking for more work, and enabling callbacks.
+ * virtqueue_enable_cb_delayed: restart callbacks after disable_cb.
+ *      vq: the struct virtqueue we're talking about.
+ *      This re-enables callbacks but hints to the other side to delay
+ *      interrupts until most of the available buffers have been processed;
+ *      it returns "false" if there are many pending buffers in the queue,
+ *      to detect a possible race between the driver checking for more work,
+ *      and enabling callbacks.
  * virtqueue_detach_unused_buf: detach first unused buffer
  *      vq: the struct virtqueue we're talking about.
  *      Returns NULL or the "data" token handed to add_buf
@@ -86,6 +93,8 @@ void virtqueue_disable_cb(struct virtqueue *vq);
 
 bool virtqueue_enable_cb(struct virtqueue *vq);
 
+bool virtqueue_enable_cb_delayed(struct virtqueue *vq);
+
 void *virtqueue_detach_unused_buf(struct virtqueue *vq);
 
 /**
diff --git a/include/linux/virtio_9p.h b/include/linux/virtio_9p.h
index e68b439b2860..277c4ad44e84 100644
--- a/include/linux/virtio_9p.h
+++ b/include/linux/virtio_9p.h
@@ -1,7 +1,30 @@
 #ifndef _LINUX_VIRTIO_9P_H
 #define _LINUX_VIRTIO_9P_H
 /* This header is BSD licensed so anyone can use the definitions to implement
- * compatible drivers/servers. */
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE. */
 #include <linux/types.h>
 #include <linux/virtio_ids.h>
 #include <linux/virtio_config.h>
diff --git a/include/linux/virtio_balloon.h b/include/linux/virtio_balloon.h
index a50ecd1b81a2..652dc8bea921 100644
--- a/include/linux/virtio_balloon.h
+++ b/include/linux/virtio_balloon.h
@@ -1,7 +1,30 @@
 #ifndef _LINUX_VIRTIO_BALLOON_H
 #define _LINUX_VIRTIO_BALLOON_H
 /* This header is BSD licensed so anyone can use the definitions to implement
- * compatible drivers/servers. */
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE. */
 #include <linux/virtio_ids.h>
 #include <linux/virtio_config.h>
 
diff --git a/include/linux/virtio_blk.h b/include/linux/virtio_blk.h
index 167720d695ed..e0edb40ca7aa 100644
--- a/include/linux/virtio_blk.h
+++ b/include/linux/virtio_blk.h
@@ -1,7 +1,30 @@
 #ifndef _LINUX_VIRTIO_BLK_H
 #define _LINUX_VIRTIO_BLK_H
 /* This header is BSD licensed so anyone can use the definitions to implement
- * compatible drivers/servers. */
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE. */
 #include <linux/types.h>
 #include <linux/virtio_ids.h>
 #include <linux/virtio_config.h>
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 800617b4ddd5..39c88c5ad19d 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -1,7 +1,30 @@
 #ifndef _LINUX_VIRTIO_CONFIG_H
 #define _LINUX_VIRTIO_CONFIG_H
 /* This header, excluding the #ifdef __KERNEL__ part, is BSD licensed so
- * anyone can use the definitions to implement compatible drivers/servers. */
+ * anyone can use the definitions to implement compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE. */
 
 /* Virtio devices use a standardized configuration space to define their
  * features and pass configuration information, but each implementation can
diff --git a/include/linux/virtio_console.h b/include/linux/virtio_console.h
index e4d333543a33..bdf4b0034739 100644
--- a/include/linux/virtio_console.h
+++ b/include/linux/virtio_console.h
@@ -5,7 +5,31 @@
 #include <linux/virtio_config.h>
 /*
  * This header, excluding the #ifdef __KERNEL__ part, is BSD licensed so
- * anyone can use the definitions to implement compatible drivers/servers.
+ * anyone can use the definitions to implement compatible drivers/servers:
+ *
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
  *
  * Copyright (C) Red Hat, Inc., 2009, 2010, 2011
  * Copyright (C) Amit Shah <amit.shah@redhat.com>, 2009, 2010, 2011
diff --git a/include/linux/virtio_ids.h b/include/linux/virtio_ids.h
index 06660c0a78d7..85bb0bb66ffc 100644
--- a/include/linux/virtio_ids.h
+++ b/include/linux/virtio_ids.h
@@ -5,7 +5,29 @@
  *
  * This header is BSD licensed so anyone can use the definitions to implement
  * compatible drivers/servers.
- */
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE. */
 
 #define VIRTIO_ID_NET           1 /* virtio net */
 #define VIRTIO_ID_BLOCK         2 /* virtio block */
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 085e42298ce5..136040bba3e3 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -1,7 +1,30 @@
 #ifndef _LINUX_VIRTIO_NET_H
 #define _LINUX_VIRTIO_NET_H
 /* This header is BSD licensed so anyone can use the definitions to implement
- * compatible drivers/servers. */
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE. */
 #include <linux/types.h>
 #include <linux/virtio_ids.h>
 #include <linux/virtio_config.h>
diff --git a/include/linux/virtio_pci.h b/include/linux/virtio_pci.h
index 9a3d7c48c622..ea66f3f60d63 100644
--- a/include/linux/virtio_pci.h
+++ b/include/linux/virtio_pci.h
@@ -11,6 +11,29 @@
  *
  * This header is BSD licensed so anyone can use the definitions to implement
  * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
  */
 
 #ifndef _LINUX_VIRTIO_PCI_H
diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h
index e4d144b132b5..4a32cb6da425 100644
--- a/include/linux/virtio_ring.h
+++ b/include/linux/virtio_ring.h
@@ -7,6 +7,29 @@
  * This header is BSD licensed so anyone can use the definitions to implement
  * compatible drivers/servers.
  *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ *
  * Copyright Rusty Russell IBM Corporation 2007. */
 #include <linux/types.h>
 
@@ -29,6 +52,12 @@
 /* We support indirect buffer descriptors */
 #define VIRTIO_RING_F_INDIRECT_DESC     28
 
+/* The Guest publishes the used index for which it expects an interrupt
+ * at the end of the avail ring. Host should ignore the avail->flags field. */
+/* The Host publishes the avail index for which it expects a kick
+ * at the end of the used ring. Guest should ignore the used->flags field. */
+#define VIRTIO_RING_F_EVENT_IDX         29
+
 /* Virtio ring descriptors: 16 bytes.  These can chain together via "next". */
 struct vring_desc {
         /* Address (guest-physical). */
@@ -83,6 +112,7 @@ struct vring {
  *      __u16 avail_flags;
  *      __u16 avail_idx;
  *      __u16 available[num];
+ *      __u16 used_event_idx;
  *
  *      // Padding to the next align boundary.
  *      char pad[];
@@ -91,8 +121,14 @@ struct vring {
  *      __u16 used_flags;
  *      __u16 used_idx;
  *      struct vring_used_elem used[num];
+ *      __u16 avail_event_idx;
  * };
  */
+/* We publish the used event index at the end of the available ring, and vice
+ * versa. They are at the end for backwards compatibility. */
+#define vring_used_event(vr) ((vr)->avail->ring[(vr)->num])
+#define vring_avail_event(vr) (*(__u16 *)&(vr)->used->ring[(vr)->num])
+
 static inline void vring_init(struct vring *vr, unsigned int num, void *p,
                               unsigned long align)
 {
@@ -107,7 +143,21 @@ static inline unsigned vring_size(unsigned int num, unsigned long align)
 {
         return ((sizeof(struct vring_desc) * num + sizeof(__u16) * (2 + num)
                  + align - 1) & ~(align - 1))
-                + sizeof(__u16) * 2 + sizeof(struct vring_used_elem) * num;
+                + sizeof(__u16) * 3 + sizeof(struct vring_used_elem) * num;
+}
+
+/* The following is used with USED_EVENT_IDX and AVAIL_EVENT_IDX */
+/* Assuming a given event_idx value from the other size, if
+ * we have just incremented index from old to new_idx,
+ * should we trigger an event? */
+static inline int vring_need_event(__u16 event_idx, __u16 new_idx, __u16 old)
+{
+        /* Note: Xen has similar logic for notification hold-off
+         * in include/xen/interface/io/ring.h with req_event and req_prod
+         * corresponding to event_idx + 1 and new_idx respectively.
+         * Note also that req_event and req_prod in Xen start at 1,
+         * event indexes in virtio start at 0. */
+        return (__u16)(new_idx - event_idx - 1) < (__u16)(new_idx - old);
 }
 
 #ifdef __KERNEL__
diff --git a/include/net/sctp/command.h b/include/net/sctp/command.h
index 2b447646ce4b..dd6847e5d6e4 100644
--- a/include/net/sctp/command.h
+++ b/include/net/sctp/command.h
@@ -107,6 +107,7 @@ typedef enum {
         SCTP_CMD_UPDATE_INITTAG, /* Update peer inittag */
         SCTP_CMD_SEND_MSG,       /* Send the whole use message */
         SCTP_CMD_SEND_NEXT_ASCONF, /* Send the next ASCONF after ACK */
+        SCTP_CMD_PURGE_ASCONF_QUEUE, /* Purge all asconf queues.*/
         SCTP_CMD_LAST
 } sctp_verb_t;
 
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 795f4886e111..7df327a6d564 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1993,7 +1993,7 @@ void sctp_assoc_clean_asconf_ack_cache(const struct sctp_association *asoc);
 struct sctp_chunk *sctp_assoc_lookup_asconf_ack(
                                         const struct sctp_association *asoc,
                                         __be32 serial);
-
+void sctp_asconf_queue_teardown(struct sctp_association *asoc);
 
 int sctp_cmp_addr_exact(const union sctp_addr *ss1,
                         const union sctp_addr *ss2);
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index f445cff66ab7..4114129f0794 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -28,7 +28,7 @@ struct extent_buffer;
                 { BTRFS_SHARED_DATA_REF_KEY,    "SHARED_DATA_REF" })
 
 #define __show_root_type(obj)                                           \
-        __print_symbolic(obj,                                           \
+        __print_symbolic_u64(obj,                                       \
                 { BTRFS_ROOT_TREE_OBJECTID,     "ROOT_TREE"     },      \
                 { BTRFS_EXTENT_TREE_OBJECTID,   "EXTENT_TREE"   },      \
                 { BTRFS_CHUNK_TREE_OBJECTID,    "CHUNK_TREE"    },      \
@@ -125,7 +125,7 @@ DEFINE_EVENT(btrfs__inode, btrfs_inode_evict,
 );
 
 #define __show_map_type(type)                                           \
-        __print_symbolic(type,                                          \
+        __print_symbolic_u64(type,                                      \
                 { EXTENT_MAP_LAST_BYTE, "LAST_BYTE"     },              \
                 { EXTENT_MAP_HOLE,      "HOLE"          },              \
                 { EXTENT_MAP_INLINE,    "INLINE"        },              \
diff --git a/include/trace/events/net.h b/include/trace/events/net.h
index 5f247f5ffc56..f99645d05a8f 100644
--- a/include/trace/events/net.h
+++ b/include/trace/events/net.h
@@ -12,22 +12,24 @@
 TRACE_EVENT(net_dev_xmit,
 
         TP_PROTO(struct sk_buff *skb,
-                 int rc),
+                 int rc,
+                 struct net_device *dev,
+                 unsigned int skb_len),
 
-        TP_ARGS(skb, rc),
+        TP_ARGS(skb, rc, dev, skb_len),
 
         TP_STRUCT__entry(
                 __field(        void *,         skbaddr         )
                 __field(        unsigned int,   len             )
                 __field(        int,            rc              )
-                __string(       name,           skb->dev->name  )
+                __string(       name,           dev->name       )
         ),
 
         TP_fast_assign(
                 __entry->skbaddr = skb;
-                __entry->len = skb->len;
+                __entry->len = skb_len;
                 __entry->rc = rc;
-                __assign_str(name, skb->dev->name);
+                __assign_str(name, dev->name);
         ),
 
         TP_printk("dev=%s skbaddr=%p len=%u rc=%d",
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 3e68366d485a..533c49f48047 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -205,6 +205,19 @@
                 ftrace_print_symbols_seq(p, value, symbols);            \
         })
 
+#undef __print_symbolic_u64
+#if BITS_PER_LONG == 32
+#define __print_symbolic_u64(value, symbol_array...)                    \
+        ({                                                              \
+                static const struct trace_print_flags_u64 symbols[] =   \
+                        { symbol_array, { -1, NULL } };                 \
+                ftrace_print_symbols_seq_u64(p, value, symbols);        \
+        })
+#else
+#define __print_symbolic_u64(value, symbol_array...)                    \
+                        __print_symbolic(value, symbol_array)
+#endif
+
 #undef __print_hex
 #define __print_hex(buf, buf_len) ftrace_print_hex_seq(p, buf, buf_len)
 
diff --git a/init/main.c b/init/main.c
index d2f1e086bf33..cafba67c13bf 100644
--- a/init/main.c
+++ b/init/main.c
@@ -487,6 +487,7 @@ asmlinkage void __init start_kernel(void)
         printk(KERN_NOTICE "%s", linux_banner);
         setup_arch(&command_line);
         mm_init_owner(&init_mm, &init_task);
+        mm_init_cpumask(&init_mm);
         setup_command_line(command_line);
         setup_nr_cpu_ids();
         setup_per_cpu_areas();
@@ -510,7 +511,6 @@ asmlinkage void __init start_kernel(void)
         sort_main_extable();
         trap_init();
         mm_init();
-        BUG_ON(mm_init_cpumask(&init_mm, 0));
 
         /*
          * Set up the scheduler prior starting any interrupts (such as the
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 1ceeb049c827..9c9b7545c810 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -2190,7 +2190,7 @@ int cpuset_cpus_allowed_fallback(struct task_struct *tsk)
         rcu_read_lock();
         cs = task_cs(tsk);
         if (cs)
-                cpumask_copy(&tsk->cpus_allowed, cs->cpus_allowed);
+                do_set_cpus_allowed(tsk, cs->cpus_allowed);
         rcu_read_unlock();
 
         /*
@@ -2217,7 +2217,7 @@ int cpuset_cpus_allowed_fallback(struct task_struct *tsk)
                  * Like above we can temporary set any mask and rely on
                  * set_cpus_allowed_ptr() as synchronization point.
                  */
-                cpumask_copy(&tsk->cpus_allowed, cpu_possible_mask);
+                do_set_cpus_allowed(tsk, cpu_possible_mask);
                 cpu = cpumask_any(cpu_active_mask);
         }
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index c09767f7db3e..d863b3c057bb 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5028,6 +5028,14 @@ static int __perf_event_overflow(struct perf_event *event, int nmi,
         else
                 perf_event_output(event, nmi, data, regs);
 
+        if (event->fasync && event->pending_kill) {
+                if (nmi) {
+                        event->pending_wakeup = 1;
+                        irq_work_queue(&event->pending);
+                } else
+                        perf_event_wakeup(event);
+        }
+
         return ret;
 }
 
diff --git a/kernel/fork.c b/kernel/fork.c
index ca406d916713..0276c30401a0 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -484,20 +484,6 @@ static void mm_init_aio(struct mm_struct *mm)
 #endif
 }
 
-int mm_init_cpumask(struct mm_struct *mm, struct mm_struct *oldmm)
-{
-#ifdef CONFIG_CPUMASK_OFFSTACK
-        if (!alloc_cpumask_var(&mm->cpu_vm_mask_var, GFP_KERNEL))
-                return -ENOMEM;
-
-        if (oldmm)
-                cpumask_copy(mm_cpumask(mm), mm_cpumask(oldmm));
-        else
-                memset(mm_cpumask(mm), 0, cpumask_size());
-#endif
-        return 0;
-}
-
 static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
 {
         atomic_set(&mm->mm_users, 1);
@@ -538,17 +524,8 @@ struct mm_struct * mm_alloc(void)
                 return NULL;
 
         memset(mm, 0, sizeof(*mm));
-        mm = mm_init(mm, current);
-        if (!mm)
-                return NULL;
-
-        if (mm_init_cpumask(mm, NULL)) {
-                mm_free_pgd(mm);
-                free_mm(mm);
-                return NULL;
-        }
-
-        return mm;
+        mm_init_cpumask(mm);
+        return mm_init(mm, current);
 }
 
 /*
@@ -559,7 +536,6 @@ struct mm_struct * mm_alloc(void)
 void __mmdrop(struct mm_struct *mm)
 {
         BUG_ON(mm == &init_mm);
-        free_cpumask_var(mm->cpu_vm_mask_var);
         mm_free_pgd(mm);
         destroy_context(mm);
         mmu_notifier_mm_destroy(mm);
@@ -753,6 +729,7 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
                 goto fail_nomem;
 
         memcpy(mm, oldmm, sizeof(*mm));
+        mm_init_cpumask(mm);
 
         /* Initializing for Swap token stuff */
         mm->token_priority = 0;
@@ -765,9 +742,6 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
         if (!mm_init(mm, tsk))
                 goto fail_nomem;
 
-        if (mm_init_cpumask(mm, oldmm))
-                goto fail_nocpumask;
-
         if (init_new_context(tsk, mm))
                 goto fail_nocontext;
 
@@ -794,9 +768,6 @@ fail_nomem:
         return NULL;
 
 fail_nocontext:
-        free_cpumask_var(mm->cpu_vm_mask_var);
-
-fail_nocpumask:
         /*
          * If init_new_context() failed, we cannot use mmput() to free the mm
          * because it calls destroy_context()
@@ -1591,6 +1562,13 @@ void __init proc_caches_init(void)
         fs_cachep = kmem_cache_create("fs_cache",
                         sizeof(struct fs_struct), 0,
                         SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL);
+        /*
+         * FIXME! The "sizeof(struct mm_struct)" currently includes the
+         * whole struct cpumask for the OFFSTACK case. We could change
+         * this to *only* allocate as much of it as required by the
+         * maximum number of CPU's we can ever have.  The cpumask_allocation
+         * is at the end of the structure, exactly for that reason.
+         */
         mm_cachep = kmem_cache_create("mm_struct",
                         sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN,
                         SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_NOTRACK, NULL);
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 74d1c099fbd1..fa27e750dbc0 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -105,9 +105,12 @@ static int __jump_label_text_reserved(struct jump_entry *iter_start,
 }
 
 static void __jump_label_update(struct jump_label_key *key,
-                struct jump_entry *entry, int enable)
+                                struct jump_entry *entry,
+                                struct jump_entry *stop, int enable)
 {
-        for (; entry->key == (jump_label_t)(unsigned long)key; entry++) {
+        for (; (entry < stop) &&
+              (entry->key == (jump_label_t)(unsigned long)key);
+              entry++) {
                 /*
                  * entry->code set to 0 invalidates module init text sections
                  * kernel_text_address() verifies we are not in core kernel
@@ -181,7 +184,11 @@ static void __jump_label_mod_update(struct jump_label_key *key, int enable)
         struct jump_label_mod *mod = key->next;
 
         while (mod) {
-                __jump_label_update(key, mod->entries, enable);
+                struct module *m = mod->mod;
+
+                __jump_label_update(key, mod->entries,
+                                    m->jump_entries + m->num_jump_entries,
+                                    enable);
                 mod = mod->next;
         }
 }
@@ -245,7 +252,8 @@ static int jump_label_add_module(struct module *mod)
                 key->next = jlm;
 
                 if (jump_label_enabled(key))
-                        __jump_label_update(key, iter, JUMP_LABEL_ENABLE);
+                        __jump_label_update(key, iter, iter_stop,
+                                            JUMP_LABEL_ENABLE);
         }
 
         return 0;
@@ -371,7 +379,7 @@ static void jump_label_update(struct jump_label_key *key, int enable)
 
         /* if there are no users, entry can be NULL */
         if (entry)
-                __jump_label_update(key, entry, enable);
+                __jump_label_update(key, entry, __stop___jump_table, enable);
 
 #ifdef CONFIG_MODULES
         __jump_label_mod_update(key, enable);
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 3b34d2732bce..4ba7cccb4994 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -202,8 +202,8 @@ void kthread_bind(struct task_struct *p, unsigned int cpu)
                 return;
         }
 
-        p->cpus_allowed = cpumask_of_cpu(cpu);
-        p->rt.nr_cpus_allowed = 1;
+        /* It's safe because the task is inactive. */
+        do_set_cpus_allowed(p, cpumask_of(cpu));
         p->flags |= PF_THREAD_BOUND;
 }
 EXPORT_SYMBOL(kthread_bind);
diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c
index fd8d1e035df9..6824ca7d4d0c 100644
--- a/kernel/pm_qos_params.c
+++ b/kernel/pm_qos_params.c
@@ -54,11 +54,17 @@ enum pm_qos_type {
         PM_QOS_MIN              /* return the smallest value */
 };
 
+/*
+ * Note: The lockless read path depends on the CPU accessing
+ * target_value atomically.  Atomic access is only guaranteed on all CPU
+ * types linux supports for 32 bit quantites
+ */
 struct pm_qos_object {
         struct plist_head requests;
         struct blocking_notifier_head *notifiers;
         struct miscdevice pm_qos_power_miscdev;
         char *name;
+        s32 target_value;       /* Do not change to 64 bit */
         s32 default_value;
         enum pm_qos_type type;
 };
@@ -71,7 +77,8 @@ static struct pm_qos_object cpu_dma_pm_qos = {
         .requests = PLIST_HEAD_INIT(cpu_dma_pm_qos.requests, pm_qos_lock),
         .notifiers = &cpu_dma_lat_notifier,
         .name = "cpu_dma_latency",
-        .default_value = 2000 * USEC_PER_SEC,
+        .target_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE,
+        .default_value = PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE,
         .type = PM_QOS_MIN,
 };
 
@@ -80,7 +87,8 @@ static struct pm_qos_object network_lat_pm_qos = {
         .requests = PLIST_HEAD_INIT(network_lat_pm_qos.requests, pm_qos_lock),
         .notifiers = &network_lat_notifier,
         .name = "network_latency",
-        .default_value = 2000 * USEC_PER_SEC,
+        .target_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE,
+        .default_value = PM_QOS_NETWORK_LAT_DEFAULT_VALUE,
         .type = PM_QOS_MIN
 };
 
@@ -90,7 +98,8 @@ static struct pm_qos_object network_throughput_pm_qos = {
         .requests = PLIST_HEAD_INIT(network_throughput_pm_qos.requests, pm_qos_lock),
         .notifiers = &network_throughput_notifier,
         .name = "network_throughput",
-        .default_value = 0,
+        .target_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE,
+        .default_value = PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE,
         .type = PM_QOS_MAX,
 };
 
@@ -136,6 +145,16 @@ static inline int pm_qos_get_value(struct pm_qos_object *o)
         }
 }
 
+static inline s32 pm_qos_read_value(struct pm_qos_object *o)
+{
+        return o->target_value;
+}
+
+static inline void pm_qos_set_value(struct pm_qos_object *o, s32 value)
+{
+        o->target_value = value;
+}
+
 static void update_target(struct pm_qos_object *o, struct plist_node *node,
                           int del, int value)
 {
@@ -160,6 +179,7 @@ static void update_target(struct pm_qos_object *o, struct plist_node *node,
                 plist_add(node, &o->requests);
         }
         curr_value = pm_qos_get_value(o);
+        pm_qos_set_value(o, curr_value);
         spin_unlock_irqrestore(&pm_qos_lock, flags);
 
         if (prev_value != curr_value)
@@ -194,18 +214,11 @@ static int find_pm_qos_object_by_minor(int minor)
  * pm_qos_request - returns current system wide qos expectation
  * @pm_qos_class: identification of which qos value is requested
  *
- * This function returns the current target value in an atomic manner.
+ * This function returns the current target value.
  */
 int pm_qos_request(int pm_qos_class)
 {
-        unsigned long flags;
-        int value;
-
-        spin_lock_irqsave(&pm_qos_lock, flags);
-        value = pm_qos_get_value(pm_qos_array[pm_qos_class]);
-        spin_unlock_irqrestore(&pm_qos_lock, flags);
-
-        return value;
+        return pm_qos_read_value(pm_qos_array[pm_qos_class]);
 }
 EXPORT_SYMBOL_GPL(pm_qos_request);
 
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index f07d2f03181a..89419ff92e99 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -36,7 +36,7 @@
 #include <linux/interrupt.h>
 #include <linux/sched.h>
 #include <linux/nmi.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 #include <linux/bitops.h>
 #include <linux/module.h>
 #include <linux/completion.h>
@@ -95,7 +95,6 @@ static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task);
 DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
 DEFINE_PER_CPU(int, rcu_cpu_kthread_cpu);
 DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops);
-static DEFINE_PER_CPU(wait_queue_head_t, rcu_cpu_wq);
 DEFINE_PER_CPU(char, rcu_cpu_has_work);
 static char rcu_kthreads_spawnable;
 
@@ -163,7 +162,7 @@ EXPORT_SYMBOL_GPL(rcu_note_context_switch);
 #ifdef CONFIG_NO_HZ
 DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
         .dynticks_nesting = 1,
-        .dynticks = 1,
+        .dynticks = ATOMIC_INIT(1),
 };
 #endif /* #ifdef CONFIG_NO_HZ */
 
@@ -322,13 +321,25 @@ void rcu_enter_nohz(void)
         unsigned long flags;
         struct rcu_dynticks *rdtp;
 
-        smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
         local_irq_save(flags);
         rdtp = &__get_cpu_var(rcu_dynticks);
-        rdtp->dynticks++;
-        rdtp->dynticks_nesting--;
-        WARN_ON_ONCE(rdtp->dynticks & 0x1);
+        if (--rdtp->dynticks_nesting) {
+                local_irq_restore(flags);
+                return;
+        }
+        /* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
+        smp_mb__before_atomic_inc();  /* See above. */
+        atomic_inc(&rdtp->dynticks);
+        smp_mb__after_atomic_inc();  /* Force ordering with next sojourn. */
+        WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
         local_irq_restore(flags);
+
+        /* If the interrupt queued a callback, get out of dyntick mode. */
+        if (in_irq() &&
+            (__get_cpu_var(rcu_sched_data).nxtlist ||
+             __get_cpu_var(rcu_bh_data).nxtlist ||
+             rcu_preempt_needs_cpu(smp_processor_id())))
+                set_need_resched();
 }
 
 /*
@@ -344,11 +355,16 @@ void rcu_exit_nohz(void)
 
         local_irq_save(flags);
         rdtp = &__get_cpu_var(rcu_dynticks);
-        rdtp->dynticks++;
-        rdtp->dynticks_nesting++;
-        WARN_ON_ONCE(!(rdtp->dynticks & 0x1));
+        if (rdtp->dynticks_nesting++) {
+                local_irq_restore(flags);
+                return;
+        }
+        smp_mb__before_atomic_inc();  /* Force ordering w/previous sojourn. */
+        atomic_inc(&rdtp->dynticks);
+        /* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
+        smp_mb__after_atomic_inc();  /* See above. */
+        WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
         local_irq_restore(flags);
-        smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
 }
 
 /**
@@ -362,11 +378,15 @@ void rcu_nmi_enter(void)
 {
         struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
 
-        if (rdtp->dynticks & 0x1)
+        if (rdtp->dynticks_nmi_nesting == 0 &&
+            (atomic_read(&rdtp->dynticks) & 0x1))
                 return;
-        rdtp->dynticks_nmi++;
-        WARN_ON_ONCE(!(rdtp->dynticks_nmi & 0x1));
-        smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
+        rdtp->dynticks_nmi_nesting++;
+        smp_mb__before_atomic_inc();  /* Force delay from prior write. */
+        atomic_inc(&rdtp->dynticks);
+        /* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
+        smp_mb__after_atomic_inc();  /* See above. */
+        WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
 }
 
 /**
@@ -380,11 +400,14 @@ void rcu_nmi_exit(void)
 {
         struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
 
-        if (rdtp->dynticks & 0x1)
+        if (rdtp->dynticks_nmi_nesting == 0 ||
+            --rdtp->dynticks_nmi_nesting != 0)
                 return;
-        smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
-        rdtp->dynticks_nmi++;
-        WARN_ON_ONCE(rdtp->dynticks_nmi & 0x1);
+        /* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
+        smp_mb__before_atomic_inc();  /* See above. */
+        atomic_inc(&rdtp->dynticks);
+        smp_mb__after_atomic_inc();  /* Force delay to next write. */
+        WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
 }
 
 /**
@@ -395,13 +418,7 @@ void rcu_nmi_exit(void)
  */
 void rcu_irq_enter(void)
 {
-        struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
-
-        if (rdtp->dynticks_nesting++)
-                return;
-        rdtp->dynticks++;
-        WARN_ON_ONCE(!(rdtp->dynticks & 0x1));
-        smp_mb(); /* CPUs seeing ++ must see later RCU read-side crit sects */
+        rcu_exit_nohz();
 }
 
 /**
@@ -413,18 +430,7 @@ void rcu_irq_enter(void)
  */
 void rcu_irq_exit(void)
 {
-        struct rcu_dynticks *rdtp = &__get_cpu_var(rcu_dynticks);
-
-        if (--rdtp->dynticks_nesting)
-                return;
-        smp_mb(); /* CPUs seeing ++ must see prior RCU read-side crit sects */
-        rdtp->dynticks++;
-        WARN_ON_ONCE(rdtp->dynticks & 0x1);
-
-        /* If the interrupt queued a callback, get out of dyntick mode. */
-        if (__this_cpu_read(rcu_sched_data.nxtlist) ||
-            __this_cpu_read(rcu_bh_data.nxtlist))
-                set_need_resched();
+        rcu_enter_nohz();
 }
 
 #ifdef CONFIG_SMP
@@ -436,19 +442,8 @@ void rcu_irq_exit(void)
  */
 static int dyntick_save_progress_counter(struct rcu_data *rdp)
 {
-        int ret;
-        int snap;
-        int snap_nmi;
-
-        snap = rdp->dynticks->dynticks;
-        snap_nmi = rdp->dynticks->dynticks_nmi;
-        smp_mb();       /* Order sampling of snap with end of grace period. */
-        rdp->dynticks_snap = snap;
-        rdp->dynticks_nmi_snap = snap_nmi;
-        ret = ((snap & 0x1) == 0) && ((snap_nmi & 0x1) == 0);
-        if (ret)
-                rdp->dynticks_fqs++;
-        return ret;
+        rdp->dynticks_snap = atomic_add_return(0, &rdp->dynticks->dynticks);
+        return 0;
 }
 
 /*
@@ -459,16 +454,11 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp)
  */
 static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 {
-        long curr;
-        long curr_nmi;
-        long snap;
-        long snap_nmi;
+        unsigned long curr;
+        unsigned long snap;
 
-        curr = rdp->dynticks->dynticks;
-        snap = rdp->dynticks_snap;
-        curr_nmi = rdp->dynticks->dynticks_nmi;
-        snap_nmi = rdp->dynticks_nmi_snap;
-        smp_mb(); /* force ordering with cpu entering/leaving dynticks. */
+        curr = (unsigned long)atomic_add_return(0, &rdp->dynticks->dynticks);
+        snap = (unsigned long)rdp->dynticks_snap;
 
         /*
          * If the CPU passed through or entered a dynticks idle phase with
@@ -478,8 +468,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
          * read-side critical section that started before the beginning
          * of the current RCU grace period.
          */
-        if ((curr != snap || (curr & 0x1) == 0) &&
-            (curr_nmi != snap_nmi || (curr_nmi & 0x1) == 0)) {
+        if ((curr & 0x1) == 0 || ULONG_CMP_GE(curr, snap + 2)) {
                 rdp->dynticks_fqs++;
                 return 1;
         }
@@ -908,6 +897,12 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
         unsigned long gp_duration;
 
         WARN_ON_ONCE(!rcu_gp_in_progress(rsp));
+
+        /*
+         * Ensure that all grace-period and pre-grace-period activity
+         * is seen before the assignment to rsp->completed.
+         */
+        smp_mb(); /* See above block comment. */
         gp_duration = jiffies - rsp->gp_start;
         if (gp_duration > rsp->gp_max)
                 rsp->gp_max = gp_duration;
@@ -1455,25 +1450,11 @@ __rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
  */
 static void rcu_process_callbacks(void)
 {
-        /*
-         * Memory references from any prior RCU read-side critical sections
-         * executed by the interrupted code must be seen before any RCU
-         * grace-period manipulations below.
-         */
-        smp_mb(); /* See above block comment. */
-
         __rcu_process_callbacks(&rcu_sched_state,
                                 &__get_cpu_var(rcu_sched_data));
         __rcu_process_callbacks(&rcu_bh_state, &__get_cpu_var(rcu_bh_data));
         rcu_preempt_process_callbacks();
 
-        /*
-         * Memory references from any later RCU read-side critical sections
-         * executed by the interrupted code must be seen after any RCU
-         * grace-period manipulations above.
-         */
-        smp_mb(); /* See above block comment. */
-
         /* If we are last CPU on way to dyntick-idle mode, accelerate it. */
         rcu_needs_cpu_flush();
 }
@@ -1494,7 +1475,7 @@ static void invoke_rcu_cpu_kthread(void)
                 local_irq_restore(flags);
                 return;
         }
-        wake_up(&__get_cpu_var(rcu_cpu_wq));
+        wake_up_process(__this_cpu_read(rcu_cpu_kthread_task));
         local_irq_restore(flags);
 }
 
@@ -1544,13 +1525,10 @@ static void rcu_cpu_kthread_setrt(int cpu, int to_rt)
  */
 static void rcu_cpu_kthread_timer(unsigned long arg)
 {
-        unsigned long flags;
         struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, arg);
         struct rcu_node *rnp = rdp->mynode;
 
-        raw_spin_lock_irqsave(&rnp->lock, flags);
-        rnp->wakemask |= rdp->grpmask;
-        raw_spin_unlock_irqrestore(&rnp->lock, flags);
+        atomic_or(rdp->grpmask, &rnp->wakemask);
         invoke_rcu_node_kthread(rnp);
 }
 
@@ -1617,14 +1595,12 @@ static int rcu_cpu_kthread(void *arg)
         unsigned long flags;
         int spincnt = 0;
         unsigned int *statusp = &per_cpu(rcu_cpu_kthread_status, cpu);
-        wait_queue_head_t *wqp = &per_cpu(rcu_cpu_wq, cpu);
         char work;
         char *workp = &per_cpu(rcu_cpu_has_work, cpu);
 
         for (;;) {
                 *statusp = RCU_KTHREAD_WAITING;
-                wait_event_interruptible(*wqp,
-                                         *workp != 0 || kthread_should_stop());
+                rcu_wait(*workp != 0 || kthread_should_stop());
                 local_bh_disable();
                 if (rcu_cpu_kthread_should_stop(cpu)) {
                         local_bh_enable();
@@ -1675,7 +1651,6 @@ static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu)
         per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu;
         WARN_ON_ONCE(per_cpu(rcu_cpu_kthread_task, cpu) != NULL);
         per_cpu(rcu_cpu_kthread_task, cpu) = t;
-        wake_up_process(t);
         sp.sched_priority = RCU_KTHREAD_PRIO;
         sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
         return 0;
@@ -1698,11 +1673,10 @@ static int rcu_node_kthread(void *arg)
 
         for (;;) {
                 rnp->node_kthread_status = RCU_KTHREAD_WAITING;
-                wait_event_interruptible(rnp->node_wq, rnp->wakemask != 0);
+                rcu_wait(atomic_read(&rnp->wakemask) != 0);
                 rnp->node_kthread_status = RCU_KTHREAD_RUNNING;
                 raw_spin_lock_irqsave(&rnp->lock, flags);
-                mask = rnp->wakemask;
-                rnp->wakemask = 0;
+                mask = atomic_xchg(&rnp->wakemask, 0);
                 rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */
                 for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1) {
                         if ((mask & 0x1) == 0)
@@ -1783,13 +1757,14 @@ static int __cpuinit rcu_spawn_one_node_kthread(struct rcu_state *rsp,
                 raw_spin_lock_irqsave(&rnp->lock, flags);
                 rnp->node_kthread_task = t;
                 raw_spin_unlock_irqrestore(&rnp->lock, flags);
-                wake_up_process(t);
                 sp.sched_priority = 99;
                 sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
         }
         return rcu_spawn_one_boost_kthread(rsp, rnp, rnp_index);
 }
 
+static void rcu_wake_one_boost_kthread(struct rcu_node *rnp);
+
 /*
  * Spawn all kthreads -- called as soon as the scheduler is running.
  */
@@ -1797,24 +1772,31 @@ static int __init rcu_spawn_kthreads(void)
 {
         int cpu;
         struct rcu_node *rnp;
+        struct task_struct *t;
 
         rcu_kthreads_spawnable = 1;
         for_each_possible_cpu(cpu) {
-                init_waitqueue_head(&per_cpu(rcu_cpu_wq, cpu));
                 per_cpu(rcu_cpu_has_work, cpu) = 0;
-                if (cpu_online(cpu))
+                if (cpu_online(cpu)) {
                         (void)rcu_spawn_one_cpu_kthread(cpu);
+                        t = per_cpu(rcu_cpu_kthread_task, cpu);
+                        if (t)
+                                wake_up_process(t);
+                }
         }
         rnp = rcu_get_root(rcu_state);
-        init_waitqueue_head(&rnp->node_wq);
-        rcu_init_boost_waitqueue(rnp);
         (void)rcu_spawn_one_node_kthread(rcu_state, rnp);
-        if (NUM_RCU_NODES > 1)
+        if (rnp->node_kthread_task)
+                wake_up_process(rnp->node_kthread_task);
+        if (NUM_RCU_NODES > 1) {
                 rcu_for_each_leaf_node(rcu_state, rnp) {
-                        init_waitqueue_head(&rnp->node_wq);
-                        rcu_init_boost_waitqueue(rnp);
                         (void)rcu_spawn_one_node_kthread(rcu_state, rnp);
+                        t = rnp->node_kthread_task;
+                        if (t)
+                                wake_up_process(t);
+                        rcu_wake_one_boost_kthread(rnp);
                 }
+        }
         return 0;
 }
 early_initcall(rcu_spawn_kthreads);
@@ -2218,14 +2200,14 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible)
         raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
 }
 
-static void __cpuinit rcu_online_cpu(int cpu)
+static void __cpuinit rcu_prepare_cpu(int cpu)
 {
         rcu_init_percpu_data(cpu, &rcu_sched_state, 0);
         rcu_init_percpu_data(cpu, &rcu_bh_state, 0);
         rcu_preempt_init_percpu_data(cpu);
 }
 
-static void __cpuinit rcu_online_kthreads(int cpu)
+static void __cpuinit rcu_prepare_kthreads(int cpu)
 {
         struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu);
         struct rcu_node *rnp = rdp->mynode;
@@ -2239,6 +2221,31 @@ static void __cpuinit rcu_online_kthreads(int cpu)
 }
 
 /*
+ * kthread_create() creates threads in TASK_UNINTERRUPTIBLE state,
+ * but the RCU threads are woken on demand, and if demand is low this
+ * could be a while triggering the hung task watchdog.
+ *
+ * In order to avoid this, poke all tasks once the CPU is fully
+ * up and running.
+ */
+static void __cpuinit rcu_online_kthreads(int cpu)
+{
+        struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, cpu);
+        struct rcu_node *rnp = rdp->mynode;
+        struct task_struct *t;
+
+        t = per_cpu(rcu_cpu_kthread_task, cpu);
+        if (t)
+                wake_up_process(t);
+
+        t = rnp->node_kthread_task;
+        if (t)
+                wake_up_process(t);
+
+        rcu_wake_one_boost_kthread(rnp);
+}
+
+/*
  * Handle CPU online/offline notification events.
  */
 static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
@@ -2251,10 +2258,11 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self,
         switch (action) {
         case CPU_UP_PREPARE:
         case CPU_UP_PREPARE_FROZEN:
-                rcu_online_cpu(cpu);
-                rcu_online_kthreads(cpu);
+                rcu_prepare_cpu(cpu);
+                rcu_prepare_kthreads(cpu);
                 break;
         case CPU_ONLINE:
+                rcu_online_kthreads(cpu);
         case CPU_DOWN_FAILED:
                 rcu_node_kthread_setaffinity(rnp, -1);
                 rcu_cpu_kthread_setrt(cpu, 1);
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 257664815d5d..7b9a08b4aaea 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -84,11 +84,9 @@
  * Dynticks per-CPU state.
  */
 struct rcu_dynticks {
-        int dynticks_nesting;   /* Track nesting level, sort of. */
-        int dynticks;           /* Even value for dynticks-idle, else odd. */
-        int dynticks_nmi;       /* Even value for either dynticks-idle or */
-                                /*  not in nmi handler, else odd.  So this */
-                                /*  remains even for nmi from irq handler. */
+        int dynticks_nesting;   /* Track irq/process nesting level. */
+        int dynticks_nmi_nesting; /* Track NMI nesting level. */
+        atomic_t dynticks;      /* Even value for dynticks-idle, else odd. */
 };
 
 /* RCU's kthread states for tracing. */
@@ -121,7 +119,9 @@ struct rcu_node {
                                 /*  elements that need to drain to allow the */
                                 /*  current expedited grace period to */
                                 /*  complete (only for TREE_PREEMPT_RCU). */
-        unsigned long wakemask; /* CPUs whose kthread needs to be awakened. */
+        atomic_t wakemask;      /* CPUs whose kthread needs to be awakened. */
+                                /*  Since this has meaning only for leaf */
+                                /*  rcu_node structures, 32 bits suffices. */
         unsigned long qsmaskinit;
                                 /* Per-GP initial value for qsmask & expmask. */
         unsigned long grpmask;  /* Mask to apply to parent qsmask. */
@@ -159,9 +159,6 @@ struct rcu_node {
         struct task_struct *boost_kthread_task;
                                 /* kthread that takes care of priority */
                                 /*  boosting for this rcu_node structure. */
-        wait_queue_head_t boost_wq;
-                                /* Wait queue on which to park the boost */
-                                /*  kthread. */
         unsigned int boost_kthread_status;
                                 /* State of boost_kthread_task for tracing. */
         unsigned long n_tasks_boosted;
@@ -188,9 +185,6 @@ struct rcu_node {
                                 /* kthread that takes care of this rcu_node */
                                 /*  structure, for example, awakening the */
                                 /*  per-CPU kthreads as needed. */
-        wait_queue_head_t node_wq;
-                                /* Wait queue on which to park the per-node */
-                                /*  kthread. */
         unsigned int node_kthread_status;
                                 /* State of node_kthread_task for tracing. */
 } ____cacheline_internodealigned_in_smp;
@@ -284,7 +278,6 @@ struct rcu_data {
         /* 3) dynticks interface. */
         struct rcu_dynticks *dynticks;  /* Shared per-CPU dynticks state. */
         int dynticks_snap;              /* Per-GP tracking for dynticks. */
-        int dynticks_nmi_snap;          /* Per-GP tracking for dynticks_nmi. */
 #endif /* #ifdef CONFIG_NO_HZ */
 
         /* 4) reasons this CPU needed to be kicked by force_quiescent_state */
@@ -337,6 +330,16 @@ struct rcu_data {
                                                 /*  scheduling clock irq */
                                                 /*  before ratting on them. */
 
+#define rcu_wait(cond)                                                  \
+do {                                                                    \
+        for (;;) {                                                      \
+                set_current_state(TASK_INTERRUPTIBLE);                  \
+                if (cond)                                               \
+                        break;                                          \
+                schedule();                                             \
+        }                                                               \
+        __set_current_state(TASK_RUNNING);                              \
+} while (0)
 
 /*
  * RCU global state, including node hierarchy.  This hierarchy is
@@ -446,7 +449,6 @@ static void __cpuinit rcu_preempt_init_percpu_data(int cpu);
 static void rcu_preempt_send_cbs_to_online(void);
 static void __init __rcu_init_preempt(void);
 static void rcu_needs_cpu_flush(void);
-static void __init rcu_init_boost_waitqueue(struct rcu_node *rnp);
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
 static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp,
                                           cpumask_var_t cm);
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 3f6559a5f5cd..c8bff3099a89 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -1196,8 +1196,7 @@ static int rcu_boost_kthread(void *arg)
 
         for (;;) {
                 rnp->boost_kthread_status = RCU_KTHREAD_WAITING;
-                wait_event_interruptible(rnp->boost_wq, rnp->boost_tasks ||
-                                                        rnp->exp_tasks);
+                rcu_wait(rnp->boost_tasks || rnp->exp_tasks);
                 rnp->boost_kthread_status = RCU_KTHREAD_RUNNING;
                 more2boost = rcu_boost(rnp);
                 if (more2boost)
@@ -1275,14 +1274,6 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp)
 }
 
 /*
- * Initialize the RCU-boost waitqueue.
- */
-static void __init rcu_init_boost_waitqueue(struct rcu_node *rnp)
-{
-        init_waitqueue_head(&rnp->boost_wq);
-}
-
-/*
  * Create an RCU-boost kthread for the specified node if one does not
  * already exist.  We only create this kthread for preemptible RCU.
  * Returns zero if all is well, a negated errno otherwise.
@@ -1306,12 +1297,17 @@ static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
         raw_spin_lock_irqsave(&rnp->lock, flags);
         rnp->boost_kthread_task = t;
         raw_spin_unlock_irqrestore(&rnp->lock, flags);
-        wake_up_process(t);
         sp.sched_priority = RCU_KTHREAD_PRIO;
         sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
         return 0;
 }
 
+static void __cpuinit rcu_wake_one_boost_kthread(struct rcu_node *rnp)
+{
+        if (rnp->boost_kthread_task)
+                wake_up_process(rnp->boost_kthread_task);
+}
+
 #else /* #ifdef CONFIG_RCU_BOOST */
 
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
@@ -1328,10 +1324,6 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp)
 {
 }
 
-static void __init rcu_init_boost_waitqueue(struct rcu_node *rnp)
-{
-}
-
 static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
                                                  struct rcu_node *rnp,
                                                  int rnp_index)
@@ -1339,6 +1331,10 @@ static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
         return 0;
 }
 
+static void __cpuinit rcu_wake_one_boost_kthread(struct rcu_node *rnp)
+{
+}
+
 #endif /* #else #ifdef CONFIG_RCU_BOOST */
 
 #ifndef CONFIG_SMP
@@ -1520,7 +1516,6 @@ int rcu_needs_cpu(int cpu)
 {
         int c = 0;
         int snap;
-        int snap_nmi;
         int thatcpu;
 
         /* Check for being in the holdoff period. */
@@ -1531,10 +1526,10 @@ int rcu_needs_cpu(int cpu)
         for_each_online_cpu(thatcpu) {
                 if (thatcpu == cpu)
                         continue;
-                snap = per_cpu(rcu_dynticks, thatcpu).dynticks;
-                snap_nmi = per_cpu(rcu_dynticks, thatcpu).dynticks_nmi;
+                snap = atomic_add_return(0, &per_cpu(rcu_dynticks,
+                                                     thatcpu).dynticks);
                 smp_mb(); /* Order sampling of snap with end of grace period. */
-                if (((snap & 0x1) != 0) || ((snap_nmi & 0x1) != 0)) {
+                if ((snap & 0x1) != 0) {
                         per_cpu(rcu_dyntick_drain, cpu) = 0;
                         per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1;
                         return rcu_needs_cpu_quick_check(cpu);
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index aa0fd72b4bc7..9678cc3650f5 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -69,10 +69,10 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
                    rdp->passed_quiesc, rdp->passed_quiesc_completed,
                    rdp->qs_pending);
 #ifdef CONFIG_NO_HZ
-        seq_printf(m, " dt=%d/%d dn=%d df=%lu",
-                   rdp->dynticks->dynticks,
+        seq_printf(m, " dt=%d/%d/%d df=%lu",
+                   atomic_read(&rdp->dynticks->dynticks),
                    rdp->dynticks->dynticks_nesting,
-                   rdp->dynticks->dynticks_nmi,
+                   rdp->dynticks->dynticks_nmi_nesting,
                    rdp->dynticks_fqs);
 #endif /* #ifdef CONFIG_NO_HZ */
         seq_printf(m, " of=%lu ri=%lu", rdp->offline_fqs, rdp->resched_ipi);
@@ -141,9 +141,9 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp)
                    rdp->qs_pending);
 #ifdef CONFIG_NO_HZ
         seq_printf(m, ",%d,%d,%d,%lu",
-                   rdp->dynticks->dynticks,
+                   atomic_read(&rdp->dynticks->dynticks),
                    rdp->dynticks->dynticks_nesting,
-                   rdp->dynticks->dynticks_nmi,
+                   rdp->dynticks->dynticks_nmi_nesting,
                    rdp->dynticks_fqs);
 #endif /* #ifdef CONFIG_NO_HZ */
         seq_printf(m, ",%lu,%lu", rdp->offline_fqs, rdp->resched_ipi);
@@ -167,7 +167,7 @@ static int show_rcudata_csv(struct seq_file *m, void *unused)
 {
         seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pqc\",\"pq\",");
 #ifdef CONFIG_NO_HZ
-        seq_puts(m, "\"dt\",\"dt nesting\",\"dn\",\"df\",");
+        seq_puts(m, "\"dt\",\"dt nesting\",\"dt NMI nesting\",\"df\",");
 #endif /* #ifdef CONFIG_NO_HZ */
         seq_puts(m, "\"of\",\"ri\",\"ql\",\"b\",\"ci\",\"co\",\"ca\"\n");
 #ifdef CONFIG_TREE_PREEMPT_RCU
diff --git a/kernel/sched.c b/kernel/sched.c
index 5e43e9dc65d1..cbb3a0eee58e 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2573,7 +2573,26 @@ static void ttwu_queue_remote(struct task_struct *p, int cpu)
         if (!next)
                 smp_send_reschedule(cpu);
 }
-#endif
+
+#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
+static int ttwu_activate_remote(struct task_struct *p, int wake_flags)
+{
+        struct rq *rq;
+        int ret = 0;
+
+        rq = __task_rq_lock(p);
+        if (p->on_cpu) {
+                ttwu_activate(rq, p, ENQUEUE_WAKEUP);
+                ttwu_do_wakeup(rq, p, wake_flags);
+                ret = 1;
+        }
+        __task_rq_unlock(rq);
+
+        return ret;
+
+}
+#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
+#endif /* CONFIG_SMP */
 
 static void ttwu_queue(struct task_struct *p, int cpu)
 {
@@ -2631,17 +2650,17 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
         while (p->on_cpu) {
 #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
                 /*
-                 * If called from interrupt context we could have landed in the
-                 * middle of schedule(), in this case we should take care not
-                 * to spin on ->on_cpu if p is current, since that would
-                 * deadlock.
+                 * In case the architecture enables interrupts in
+                 * context_switch(), we cannot busy wait, since that
+                 * would lead to deadlocks when an interrupt hits and
+                 * tries to wake up @prev. So bail and do a complete
+                 * remote wakeup.
                  */
-                if (p == current) {
-                        ttwu_queue(p, cpu);
+                if (ttwu_activate_remote(p, wake_flags))
                         goto stat;
-                }
-#endif
+#else
                 cpu_relax();
+#endif
         }
         /*
          * Pairs with the smp_wmb() in finish_lock_switch().
@@ -5841,7 +5860,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
         idle->state = TASK_RUNNING;
         idle->se.exec_start = sched_clock();
 
-        cpumask_copy(&idle->cpus_allowed, cpumask_of(cpu));
+        do_set_cpus_allowed(idle, cpumask_of(cpu));
         /*
          * We're having a chicken and egg problem, even though we are
          * holding rq->lock, the cpu isn't yet set to this cpu so the
@@ -5929,6 +5948,16 @@ static inline void sched_init_granularity(void)
 }
 
 #ifdef CONFIG_SMP
+void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
+{
+        if (p->sched_class && p->sched_class->set_cpus_allowed)
+                p->sched_class->set_cpus_allowed(p, new_mask);
+        else {
+                cpumask_copy(&p->cpus_allowed, new_mask);
+                p->rt.nr_cpus_allowed = cpumask_weight(new_mask);
+        }
+}
+
 /*
  * This is how migration works:
  *
@@ -5974,12 +6003,7 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
                 goto out;
         }
 
-        if (p->sched_class->set_cpus_allowed)
-                p->sched_class->set_cpus_allowed(p, new_mask);
-        else {
-                cpumask_copy(&p->cpus_allowed, new_mask);
-                p->rt.nr_cpus_allowed = cpumask_weight(new_mask);
-        }
+        do_set_cpus_allowed(p, new_mask);
 
         /* Can the task run on the task's current CPU? If so, we're done */
         if (cpumask_test_cpu(task_cpu(p), new_mask))
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index e32a9b70ee9c..433491c2dc8f 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1076,8 +1076,6 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
         se->on_rq = 0;
         update_cfs_load(cfs_rq, 0);
         account_entity_dequeue(cfs_rq, se);
-        update_min_vruntime(cfs_rq);
-        update_cfs_shares(cfs_rq);
 
         /*
          * Normalize the entity after updating the min_vruntime because the
@@ -1086,6 +1084,9 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
          */
         if (!(flags & DEQUEUE_SLEEP))
                 se->vruntime -= cfs_rq->min_vruntime;
+
+        update_min_vruntime(cfs_rq);
+        update_cfs_shares(cfs_rq);
 }
 
 /*
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 64b2a37c07d0..88725c939e0b 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -1263,6 +1263,7 @@ static int find_lowest_rq(struct task_struct *task)
         if (!cpumask_test_cpu(this_cpu, lowest_mask))
                 this_cpu = -1; /* Skip this_cpu opt if not among lowest */
 
+        rcu_read_lock();
         for_each_domain(cpu, sd) {
                 if (sd->flags & SD_WAKE_AFFINE) {
                         int best_cpu;
@@ -1272,15 +1273,20 @@ static int find_lowest_rq(struct task_struct *task)
                          * remote processor.
                          */
                         if (this_cpu != -1 &&
-                            cpumask_test_cpu(this_cpu, sched_domain_span(sd)))
+                            cpumask_test_cpu(this_cpu, sched_domain_span(sd))) {
+                                rcu_read_unlock();
                                 return this_cpu;
+                        }
 
                         best_cpu = cpumask_first_and(lowest_mask,
                                                      sched_domain_span(sd));
-                        if (best_cpu < nr_cpu_ids)
+                        if (best_cpu < nr_cpu_ids) {
+                                rcu_read_unlock();
                                 return best_cpu;
+                        }
                 }
         }
+        rcu_read_unlock();
 
         /*
          * And finally, if there were no matches within the domains
diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h
index 48ddf431db0e..331e01bcd026 100644
--- a/kernel/sched_stats.h
+++ b/kernel/sched_stats.h
@@ -37,7 +37,7 @@ static int show_schedstat(struct seq_file *seq, void *v)
 
 #ifdef CONFIG_SMP
                 /* domain-specific stats */
-                preempt_disable();
+                rcu_read_lock();
                 for_each_domain(cpu, sd) {
                         enum cpu_idle_type itype;
 
@@ -64,7 +64,7 @@ static int show_schedstat(struct seq_file *seq, void *v)
                             sd->ttwu_wake_remote, sd->ttwu_move_affine,
                             sd->ttwu_move_balance);
                 }
-                preempt_enable();
+                rcu_read_unlock();
 #endif
         }
         kfree(mask_str);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index d017c2c82c44..1ee417fcbfa5 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -109,12 +109,18 @@ ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip);
 static void ftrace_global_list_func(unsigned long ip,
                                     unsigned long parent_ip)
 {
-        struct ftrace_ops *op = rcu_dereference_raw(ftrace_global_list); /*see above*/
+        struct ftrace_ops *op;
+
+        if (unlikely(trace_recursion_test(TRACE_GLOBAL_BIT)))
+                return;
 
+        trace_recursion_set(TRACE_GLOBAL_BIT);
+        op = rcu_dereference_raw(ftrace_global_list); /*see above*/
         while (op != &ftrace_list_end) {
                 op->func(ip, parent_ip);
                 op = rcu_dereference_raw(op->next); /*see above*/
         };
+        trace_recursion_clear(TRACE_GLOBAL_BIT);
 }
 
 static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip)
@@ -1638,12 +1644,12 @@ static void ftrace_startup_enable(int command)
         ftrace_run_update_code(command);
 }
 
-static void ftrace_startup(struct ftrace_ops *ops, int command)
+static int ftrace_startup(struct ftrace_ops *ops, int command)
 {
         bool hash_enable = true;
 
         if (unlikely(ftrace_disabled))
-                return;
+                return -ENODEV;
 
         ftrace_start_up++;
         command |= FTRACE_ENABLE_CALLS;
@@ -1662,6 +1668,8 @@ static void ftrace_startup(struct ftrace_ops *ops, int command)
                 ftrace_hash_rec_enable(ops, 1);
 
         ftrace_startup_enable(command);
+
+        return 0;
 }
 
 static void ftrace_shutdown(struct ftrace_ops *ops, int command)
@@ -2501,7 +2509,7 @@ static void __enable_ftrace_function_probe(void)
 
         ret = __register_ftrace_function(&trace_probe_ops);
         if (!ret)
-                ftrace_startup(&trace_probe_ops, 0);
+                ret = ftrace_startup(&trace_probe_ops, 0);
 
         ftrace_probe_registered = 1;
 }
@@ -3466,7 +3474,11 @@ device_initcall(ftrace_nodyn_init);
 static inline int ftrace_init_dyn_debugfs(struct dentry *d_tracer) { return 0; }
 static inline void ftrace_startup_enable(int command) { }
 /* Keep as macros so we do not need to define the commands */
-# define ftrace_startup(ops, command)   do { } while (0)
+# define ftrace_startup(ops, command)                   \
+        ({                                              \
+                (ops)->flags |= FTRACE_OPS_FL_ENABLED;  \
+                0;                                      \
+        })
 # define ftrace_shutdown(ops, command)  do { } while (0)
 # define ftrace_startup_sysctl()        do { } while (0)
 # define ftrace_shutdown_sysctl()       do { } while (0)
@@ -3484,6 +3496,10 @@ ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip)
 {
         struct ftrace_ops *op;
 
+        if (unlikely(trace_recursion_test(TRACE_INTERNAL_BIT)))
+                return;
+
+        trace_recursion_set(TRACE_INTERNAL_BIT);
         /*
          * Some of the ops may be dynamically allocated,
          * they must be freed after a synchronize_sched().
@@ -3496,6 +3512,7 @@ ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip)
                 op = rcu_dereference_raw(op->next);
         };
         preempt_enable_notrace();
+        trace_recursion_clear(TRACE_INTERNAL_BIT);
 }
 
 static void clear_ftrace_swapper(void)
@@ -3799,7 +3816,7 @@ int register_ftrace_function(struct ftrace_ops *ops)
 
         ret = __register_ftrace_function(ops);
         if (!ret)
-                ftrace_startup(ops, 0);
+                ret = ftrace_startup(ops, 0);
 
 
  out_unlock:
@@ -4045,7 +4062,7 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
         ftrace_graph_return = retfunc;
         ftrace_graph_entry = entryfunc;
 
-        ftrace_startup(&global_ops, FTRACE_START_FUNC_RET);
+        ret = ftrace_startup(&global_ops, FTRACE_START_FUNC_RET);
 
 out:
         mutex_unlock(&ftrace_lock);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 0ef7b4b2a1f7..b0c7aa407943 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2216,7 +2216,7 @@ static noinline void trace_recursive_fail(void)
 
         printk_once(KERN_WARNING "Tracing recursion: depth[%ld]:"
                     "HC[%lu]:SC[%lu]:NMI[%lu]\n",
-                    current->trace_recursion,
+                    trace_recursion_buffer(),
                     hardirq_count() >> HARDIRQ_SHIFT,
                     softirq_count() >> SOFTIRQ_SHIFT,
                     in_nmi());
@@ -2226,9 +2226,9 @@ static noinline void trace_recursive_fail(void)
 
 static inline int trace_recursive_lock(void)
 {
-        current->trace_recursion++;
+        trace_recursion_inc();
 
-        if (likely(current->trace_recursion < TRACE_RECURSIVE_DEPTH))
+        if (likely(trace_recursion_buffer() < TRACE_RECURSIVE_DEPTH))
                 return 0;
 
         trace_recursive_fail();
@@ -2238,9 +2238,9 @@ static inline int trace_recursive_lock(void)
 
 static inline void trace_recursive_unlock(void)
 {
-        WARN_ON_ONCE(!current->trace_recursion);
+        WARN_ON_ONCE(!trace_recursion_buffer());
 
-        current->trace_recursion--;
+        trace_recursion_dec();
 }
 
 #else
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 6b69c4bd306f..229f8591f61d 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -784,4 +784,19 @@ extern const char *__stop___trace_bprintk_fmt[];
         FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print))
 #include "trace_entries.h"
 
+/* Only current can touch trace_recursion */
+#define trace_recursion_inc() do { (current)->trace_recursion++; } while (0)
+#define trace_recursion_dec() do { (current)->trace_recursion--; } while (0)
+
+/* Ring buffer has the 10 LSB bits to count */
+#define trace_recursion_buffer() ((current)->trace_recursion & 0x3ff)
+
+/* for function tracing recursion */
+#define TRACE_INTERNAL_BIT              (1<<11)
+#define TRACE_GLOBAL_BIT                (1<<12)
+
+#define trace_recursion_set(bit)        do { (current)->trace_recursion |= (bit); } while (0)
+#define trace_recursion_clear(bit)      do { (current)->trace_recursion &= ~(bit); } while (0)
+#define trace_recursion_test(bit)       ((current)->trace_recursion & (bit))
+
 #endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 2fe110341359..686ec399f2a8 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1657,7 +1657,12 @@ static struct ftrace_ops trace_ops __initdata  =
 
 static __init void event_trace_self_test_with_function(void)
 {
-        register_ftrace_function(&trace_ops);
+        int ret;
+        ret = register_ftrace_function(&trace_ops);
+        if (WARN_ON(ret < 0)) {
+                pr_info("Failed to enable function tracer for event tests\n");
+                return;
+        }
         pr_info("Running tests again, along with the function tracer\n");
         event_trace_self_tests();
         unregister_ftrace_function(&trace_ops);
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index cf535ccedc86..e37de492a9e1 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -353,6 +353,33 @@ ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val,
 }
 EXPORT_SYMBOL(ftrace_print_symbols_seq);
 
+#if BITS_PER_LONG == 32
+const char *
+ftrace_print_symbols_seq_u64(struct trace_seq *p, unsigned long long val,
+                         const struct trace_print_flags_u64 *symbol_array)
+{
+        int i;
+        const char *ret = p->buffer + p->len;
+
+        for (i = 0;  symbol_array[i].name; i++) {
+
+                if (val != symbol_array[i].mask)
+                        continue;
+
+                trace_seq_puts(p, symbol_array[i].name);
+                break;
+        }
+
+        if (!p->len)
+                trace_seq_printf(p, "0x%llx", val);
+
+        trace_seq_putc(p, 0);
+
+        return ret;
+}
+EXPORT_SYMBOL(ftrace_print_symbols_seq_u64);
+#endif
+
 const char *
 ftrace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int buf_len)
 {
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 7daa4b072e9f..3d0c56ad4792 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -415,15 +415,13 @@ static void watchdog_nmi_disable(int cpu) { return; }
 #endif /* CONFIG_HARDLOCKUP_DETECTOR */
 
 /* prepare/enable/disable routines */
-static int watchdog_prepare_cpu(int cpu)
+static void watchdog_prepare_cpu(int cpu)
 {
         struct hrtimer *hrtimer = &per_cpu(watchdog_hrtimer, cpu);
 
         WARN_ON(per_cpu(softlockup_watchdog, cpu));
         hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
         hrtimer->function = watchdog_timer_fn;
-
-        return 0;
 }
 
 static int watchdog_enable(int cpu)
@@ -542,17 +540,16 @@ static int __cpuinit
 cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 {
         int hotcpu = (unsigned long)hcpu;
-        int err = 0;
 
         switch (action) {
         case CPU_UP_PREPARE:
         case CPU_UP_PREPARE_FROZEN:
-                err = watchdog_prepare_cpu(hotcpu);
+                watchdog_prepare_cpu(hotcpu);
                 break;
         case CPU_ONLINE:
         case CPU_ONLINE_FROZEN:
                 if (watchdog_enabled)
-                        err = watchdog_enable(hotcpu);
+                        watchdog_enable(hotcpu);
                 break;
 #ifdef CONFIG_HOTPLUG_CPU
         case CPU_UP_CANCELED:
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 28afa4c5333c..dd373c8ee943 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -697,7 +697,7 @@ config DEBUG_BUGVERBOSE
         bool "Verbose BUG() reporting (adds 70K)" if DEBUG_KERNEL && EXPERT
         depends on BUG
         depends on ARM || AVR32 || M32R || M68K || SPARC32 || SPARC64 || \
-                   FRV || SUPERH || GENERIC_BUG || BLACKFIN || MN10300
+                   FRV || SUPERH || GENERIC_BUG || BLACKFIN || MN10300 || TILE
         default y
         help
           Say Y here to make BUG() panics output the file name and line number
diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c
index 619313ed6c46..507a22fab738 100644
--- a/lib/locking-selftest.c
+++ b/lib/locking-selftest.c
@@ -144,7 +144,7 @@ static void init_shared_classes(void)
 
 #define HARDIRQ_ENTER()                         \
         local_irq_disable();                    \
-        irq_enter();                            \
+        __irq_enter();                          \
         WARN_ON(!in_irq());
 
 #define HARDIRQ_EXIT()                          \
diff --git a/mm/filemap.c b/mm/filemap.c
index bcdc393b6580..d7b10578a64b 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1982,16 +1982,26 @@ static int __remove_suid(struct dentry *dentry, int kill)
 int file_remove_suid(struct file *file)
 {
         struct dentry *dentry = file->f_path.dentry;
-        int killsuid = should_remove_suid(dentry);
-        int killpriv = security_inode_need_killpriv(dentry);
+        struct inode *inode = dentry->d_inode;
+        int killsuid;
+        int killpriv;
         int error = 0;
 
+        /* Fast path for nothing security related */
+        if (IS_NOSEC(inode))
+                return 0;
+
+        killsuid = should_remove_suid(dentry);
+        killpriv = security_inode_need_killpriv(dentry);
+
         if (killpriv < 0)
                 return killpriv;
         if (killpriv)
                 error = security_inode_killpriv(dentry);
         if (!error && killsuid)
                 error = __remove_suid(dentry, killsuid);
+        if (!error)
+                inode->i_flags |= S_NOSEC;
 
         return error;
 }
@@ -2327,7 +2337,7 @@ struct page *grab_cache_page_write_begin(struct address_space *mapping,
 repeat:
         page = find_lock_page(mapping, index);
         if (page)
-                return page;
+                goto found;
 
         page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~gfp_notmask);
         if (!page)
@@ -2340,6 +2350,8 @@ repeat:
                         goto repeat;
                 return NULL;
         }
+found:
+        wait_on_page_writeback(page);
         return page;
 }
 EXPORT_SYMBOL(grab_cache_page_write_begin);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index f33bb319b73f..6402458fee38 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1033,10 +1033,10 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
          */
         chg = vma_needs_reservation(h, vma, addr);
         if (chg < 0)
-                return ERR_PTR(chg);
+                return ERR_PTR(-VM_FAULT_OOM);
         if (chg)
                 if (hugetlb_get_quota(inode->i_mapping, chg))
-                        return ERR_PTR(-ENOSPC);
+                        return ERR_PTR(-VM_FAULT_SIGBUS);
 
         spin_lock(&hugetlb_lock);
         page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve);
diff --git a/mm/maccess.c b/mm/maccess.c
index e2b6f5634e0d..4cee182ab5f3 100644
--- a/mm/maccess.c
+++ b/mm/maccess.c
@@ -15,10 +15,10 @@
  * happens, handle that and return -EFAULT.
  */
 
-long __weak probe_kernel_read(void *dst, void *src, size_t size)
+long __weak probe_kernel_read(void *dst, const void *src, size_t size)
     __attribute__((alias("__probe_kernel_read")));
 
-long __probe_kernel_read(void *dst, void *src, size_t size)
+long __probe_kernel_read(void *dst, const void *src, size_t size)
 {
         long ret;
         mm_segment_t old_fs = get_fs();
@@ -43,10 +43,10 @@ EXPORT_SYMBOL_GPL(probe_kernel_read);
  * Safely write to address @dst from the buffer at @src.  If a kernel fault
  * happens, handle that and return -EFAULT.
  */
-long __weak probe_kernel_write(void *dst, void *src, size_t size)
+long __weak probe_kernel_write(void *dst, const void *src, size_t size)
     __attribute__((alias("__probe_kernel_write")));
 
-long __probe_kernel_write(void *dst, void *src, size_t size)
+long __probe_kernel_write(void *dst, const void *src, size_t size)
 {
         long ret;
         mm_segment_t old_fs = get_fs();
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a4e1db3f1981..4e8985acdab8 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2247,10 +2247,6 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 
         if (should_fail_alloc_page(gfp_mask, order))
                 return NULL;
-#ifndef CONFIG_ZONE_DMA
-        if (WARN_ON_ONCE(gfp_mask & __GFP_DMA))
-                return NULL;
-#endif
 
         /*
          * Check the zones suitable for the gfp_mask contain at least one
diff --git a/mm/rmap.c b/mm/rmap.c
index 3a39b518a653..0eb463ea88dd 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -352,6 +352,11 @@ void __init anon_vma_init(void)
  * The page might have been remapped to a different anon_vma or the anon_vma
  * returned may already be freed (and even reused).
  *
+ * In case it was remapped to a different anon_vma, the new anon_vma will be a
+ * child of the old anon_vma, and the anon_vma lifetime rules will therefore
+ * ensure that any anon_vma obtained from the page will still be valid for as
+ * long as we observe page_mapped() [ hence all those page_mapped() tests ].
+ *
  * All users of this function must be very careful when walking the anon_vma
  * chain and verify that the page in question is indeed mapped in it
  * [ something equivalent to page_mapped_in_vma() ].
@@ -405,6 +410,7 @@ out:
 struct anon_vma *page_lock_anon_vma(struct page *page)
 {
         struct anon_vma *anon_vma = NULL;
+        struct anon_vma *root_anon_vma;
         unsigned long anon_mapping;
 
         rcu_read_lock();
@@ -415,13 +421,15 @@ struct anon_vma *page_lock_anon_vma(struct page *page)
                 goto out;
 
         anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON);
-        if (mutex_trylock(&anon_vma->root->mutex)) {
+        root_anon_vma = ACCESS_ONCE(anon_vma->root);
+        if (mutex_trylock(&root_anon_vma->mutex)) {
                 /*
-                 * If we observe a !0 refcount, then holding the lock ensures
-                 * the anon_vma will not go away, see __put_anon_vma().
+                 * If the page is still mapped, then this anon_vma is still
+                 * its anon_vma, and holding the mutex ensures that it will
+                 * not go away, see anon_vma_free().
                  */
-                if (!atomic_read(&anon_vma->refcount)) {
-                        anon_vma_unlock(anon_vma);
+                if (!page_mapped(page)) {
+                        mutex_unlock(&root_anon_vma->mutex);
                         anon_vma = NULL;
                 }
                 goto out;
@@ -1014,7 +1022,7 @@ void do_page_add_anon_rmap(struct page *page,
                 return;
 
         VM_BUG_ON(!PageLocked(page));
-        VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end);
+        /* address might be in next vma when migration races vma_adjust */
         if (first)
                 __page_set_anon_rmap(page, vma, address, exclusive);
         else
@@ -1709,7 +1717,7 @@ void hugepage_add_anon_rmap(struct page *page,
 
         BUG_ON(!PageLocked(page));
         BUG_ON(!anon_vma);
-        BUG_ON(address < vma->vm_start || address >= vma->vm_end);
+        /* address might be in next vma when migration races vma_adjust */
         first = atomic_inc_and_test(&page->_mapcount);
         if (first)
                 __hugepage_set_anon_rmap(page, vma, address, 0);
diff --git a/mm/shmem.c b/mm/shmem.c
index 1acfb2687bfa..d221a1cfd7b1 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1114,8 +1114,8 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
                 delete_from_page_cache(page);
                 shmem_swp_set(info, entry, swap.val);
                 shmem_swp_unmap(entry);
-                spin_unlock(&info->lock);
                 swap_shmem_alloc(swap);
+                spin_unlock(&info->lock);
                 BUG_ON(page_mapped(page));
                 swap_writepage(page, wbc);
                 return 0;
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index f247f5bff88d..7ea5cf9ea08a 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -165,7 +165,7 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb,
                 u64_stats_update_begin(&stats->syncp);
                 stats->tx_packets++;
                 stats->tx_bytes += len;
-                u64_stats_update_begin(&stats->syncp);
+                u64_stats_update_end(&stats->syncp);
         } else {
                 this_cpu_inc(vlan_dev_info(dev)->vlan_pcpu_stats->tx_dropped);
         }
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index a86f9ba4f05c..e64a1c2df238 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -906,7 +906,7 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm, bdaddr
                 if (c->psm == psm) {
                         /* Exact match. */
                         if (!bacmp(&bt_sk(sk)->src, src)) {
-                                read_unlock_bh(&chan_list_lock);
+                                read_unlock(&chan_list_lock);
                                 return c;
                         }
 
diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c
index 649ebacaf6bc..adbb424403d4 100644
--- a/net/caif/chnl_net.c
+++ b/net/caif/chnl_net.c
@@ -139,17 +139,14 @@ static void close_work(struct work_struct *work)
         struct chnl_net *dev = NULL;
         struct list_head *list_node;
         struct list_head *_tmp;
-        /* May be called with or without RTNL lock held */
-        int islocked = rtnl_is_locked();
-        if (!islocked)
-                rtnl_lock();
+
+        rtnl_lock();
         list_for_each_safe(list_node, _tmp, &chnl_net_list) {
                 dev = list_entry(list_node, struct chnl_net, list_field);
                 if (dev->state == CAIF_SHUTDOWN)
                         dev_close(dev->netdev);
         }
-        if (!islocked)
-                rtnl_unlock();
+        rtnl_unlock();
 }
 static DECLARE_WORK(close_worker, close_work);
 
diff --git a/net/core/dev.c b/net/core/dev.c
index c7e305d13b71..939307891e71 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2096,6 +2096,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 {
         const struct net_device_ops *ops = dev->netdev_ops;
         int rc = NETDEV_TX_OK;
+        unsigned int skb_len;
 
         if (likely(!skb->next)) {
                 u32 features;
@@ -2146,8 +2147,9 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
                         }
                 }
 
+                skb_len = skb->len;
                 rc = ops->ndo_start_xmit(skb, dev);
-                trace_net_dev_xmit(skb, rc);
+                trace_net_dev_xmit(skb, rc, dev, skb_len);
                 if (rc == NETDEV_TX_OK)
                         txq_trans_update(txq);
                 return rc;
@@ -2167,8 +2169,9 @@ gso:
                 if (dev->priv_flags & IFF_XMIT_DST_RELEASE)
                         skb_dst_drop(nskb);
 
+                skb_len = nskb->len;
                 rc = ops->ndo_start_xmit(nskb, dev);
-                trace_net_dev_xmit(nskb, rc);
+                trace_net_dev_xmit(nskb, rc, dev, skb_len);
                 if (unlikely(rc != NETDEV_TX_OK)) {
                         if (rc & ~NETDEV_TX_MASK)
                                 goto out_kfree_gso_skb;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index cc1463156cd0..9c1926027a26 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -465,6 +465,9 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
         if (addr_len < sizeof(struct sockaddr_in))
                 goto out;
 
+        if (addr->sin_family != AF_INET)
+                goto out;
+
         chk_addr_ret = inet_addr_type(sock_net(sk), addr->sin_addr.s_addr);
 
         /* Not specified by any standard per-se, however it breaks too
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index c3118e1cd3bb..ec93335901dd 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <asm/uaccess.h>
+#include <asm/unaligned.h>
 #include <linux/skbuff.h>
 #include <linux/ip.h>
 #include <linux/icmp.h>
@@ -350,7 +351,7 @@ int ip_options_compile(struct net *net,
                                 goto error;
                         }
                         if (optptr[2] <= optlen) {
-                                __be32 *timeptr = NULL;
+                                unsigned char *timeptr = NULL;
                                 if (optptr[2]+3 > optptr[1]) {
                                         pp_ptr = optptr + 2;
                                         goto error;
@@ -359,7 +360,7 @@ int ip_options_compile(struct net *net,
                                       case IPOPT_TS_TSONLY:
                                         opt->ts = optptr - iph;
                                         if (skb)
-                                                timeptr = (__be32*)&optptr[optptr[2]-1];
+                                                timeptr = &optptr[optptr[2]-1];
                                         opt->ts_needtime = 1;
                                         optptr[2] += 4;
                                         break;
@@ -371,7 +372,7 @@ int ip_options_compile(struct net *net,
                                         opt->ts = optptr - iph;
                                         if (rt)  {
                                                 memcpy(&optptr[optptr[2]-1], &rt->rt_spec_dst, 4);
-                                                timeptr = (__be32*)&optptr[optptr[2]+3];
+                                                timeptr = &optptr[optptr[2]+3];
                                         }
                                         opt->ts_needaddr = 1;
                                         opt->ts_needtime = 1;
@@ -389,7 +390,7 @@ int ip_options_compile(struct net *net,
                                                 if (inet_addr_type(net, addr) == RTN_UNICAST)
                                                         break;
                                                 if (skb)
-                                                        timeptr = (__be32*)&optptr[optptr[2]+3];
+                                                        timeptr = &optptr[optptr[2]+3];
                                         }
                                         opt->ts_needtime = 1;
                                         optptr[2] += 8;
@@ -403,10 +404,10 @@ int ip_options_compile(struct net *net,
                                 }
                                 if (timeptr) {
                                         struct timespec tv;
-                                        __be32  midtime;
+                                        u32  midtime;
                                         getnstimeofday(&tv);
-                                        midtime = htonl((tv.tv_sec % 86400) * MSEC_PER_SEC + tv.tv_nsec / NSEC_PER_MSEC);
-                                        memcpy(timeptr, &midtime, sizeof(__be32));
+                                        midtime = (tv.tv_sec % 86400) * MSEC_PER_SEC + tv.tv_nsec / NSEC_PER_MSEC;
+                                        put_unaligned_be32(midtime, timeptr);
                                         opt->is_changed = 1;
                                 }
                         } else {
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 4f6b2675e41d..456cccf26b51 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -232,6 +232,9 @@ static u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata,
                 WARN_ON(!ieee80211_set_channel_type(local, sdata, channel_type));
         }
 
+        ieee80211_stop_queues_by_reason(&sdata->local->hw,
+                                        IEEE80211_QUEUE_STOP_REASON_CSA);
+
         /* channel_type change automatically detected */
         ieee80211_hw_config(local, 0);
 
@@ -245,6 +248,9 @@ static u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata,
                 rcu_read_unlock();
         }
 
+        ieee80211_wake_queues_by_reason(&sdata->local->hw,
+                                        IEEE80211_QUEUE_STOP_REASON_CSA);
+
         ht_opmode = le16_to_cpu(hti->operation_mode);
 
         /* if bss configuration changed store the new one */
@@ -1089,6 +1095,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
                 local->hw.conf.flags &= ~IEEE80211_CONF_PS;
                 config_changed |= IEEE80211_CONF_CHANGE_PS;
         }
+        local->ps_sdata = NULL;
 
         ieee80211_hw_config(local, config_changed);
 
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 27af6723cb5e..58ffa7d069c7 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -15,7 +15,6 @@
 #include <linux/if_arp.h>
 #include <linux/rtnetlink.h>
 #include <linux/pm_qos_params.h>
-#include <linux/slab.h>
 #include <net/sch_generic.h>
 #include <linux/slab.h>
 #include <net/mac80211.h>
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 925f715686a5..ba248d93399a 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -798,7 +798,12 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
                         getnstimeofday(&ts);
                 h.h2->tp_sec = ts.tv_sec;
                 h.h2->tp_nsec = ts.tv_nsec;
-                h.h2->tp_vlan_tci = vlan_tx_tag_get(skb);
+                if (vlan_tx_tag_present(skb)) {
+                        h.h2->tp_vlan_tci = vlan_tx_tag_get(skb);
+                        status |= TP_STATUS_VLAN_VALID;
+                } else {
+                        h.h2->tp_vlan_tci = 0;
+                }
                 hdrlen = sizeof(*h.h2);
                 break;
         default:
@@ -1725,8 +1730,12 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
                 aux.tp_snaplen = skb->len;
                 aux.tp_mac = 0;
                 aux.tp_net = skb_network_offset(skb);
-                aux.tp_vlan_tci = vlan_tx_tag_get(skb);
-
+                if (vlan_tx_tag_present(skb)) {
+                        aux.tp_vlan_tci = vlan_tx_tag_get(skb);
+                        aux.tp_status |= TP_STATUS_VLAN_VALID;
+                } else {
+                        aux.tp_vlan_tci = 0;
+                }
                 put_cmsg(msg, SOL_PACKET, PACKET_AUXDATA, sizeof(aux), &aux);
         }
 
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 525f97c467e9..4a62888f2e43 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -444,15 +444,7 @@ void sctp_association_free(struct sctp_association *asoc)
 
         asoc->peer.transport_count = 0;
 
-        /* Free any cached ASCONF_ACK chunk. */
-        sctp_assoc_free_asconf_acks(asoc);
-
-        /* Free the ASCONF queue. */
-        sctp_assoc_free_asconf_queue(asoc);
-
-        /* Free any cached ASCONF chunk. */
-        if (asoc->addip_last_asconf)
-                sctp_chunk_free(asoc->addip_last_asconf);
+        sctp_asconf_queue_teardown(asoc);
 
         /* AUTH - Free the endpoint shared keys */
         sctp_auth_destroy_keys(&asoc->endpoint_shared_keys);
@@ -1646,3 +1638,16 @@ struct sctp_chunk *sctp_assoc_lookup_asconf_ack(
 
         return NULL;
 }
+
+void sctp_asconf_queue_teardown(struct sctp_association *asoc)
+{
+        /* Free any cached ASCONF_ACK chunk. */
+        sctp_assoc_free_asconf_acks(asoc);
+
+        /* Free the ASCONF queue. */
+        sctp_assoc_free_asconf_queue(asoc);
+
+        /* Free any cached ASCONF chunk. */
+        if (asoc->addip_last_asconf)
+                sctp_chunk_free(asoc->addip_last_asconf);
+}
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index d612ca1ca6c0..534c2e5feb05 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -1670,6 +1670,9 @@ static int sctp_cmd_interpreter(sctp_event_t event_type,
                 case SCTP_CMD_SEND_NEXT_ASCONF:
                         sctp_cmd_send_asconf(asoc);
                         break;
+                case SCTP_CMD_PURGE_ASCONF_QUEUE:
+                        sctp_asconf_queue_teardown(asoc);
+                        break;
                 default:
                         pr_warn("Impossible command: %u, %p\n",
                                 cmd->verb, cmd->obj.ptr);
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 7f4a4f8368ee..a297283154d5 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -1718,11 +1718,21 @@ static sctp_disposition_t sctp_sf_do_dupcook_a(const struct sctp_endpoint *ep,
                 return SCTP_DISPOSITION_CONSUME;
         }
 
-        /* For now, fail any unsent/unacked data.  Consider the optional
-         * choice of resending of this data.
+        /* For now, stop pending T3-rtx and SACK timers, fail any unsent/unacked
+         * data. Consider the optional choice of resending of this data.
          */
+        sctp_add_cmd_sf(commands, SCTP_CMD_T3_RTX_TIMERS_STOP, SCTP_NULL());
+        sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP,
+                        SCTP_TO(SCTP_EVENT_TIMEOUT_SACK));
         sctp_add_cmd_sf(commands, SCTP_CMD_PURGE_OUTQUEUE, SCTP_NULL());
 
+        /* Stop pending T4-rto timer, teardown ASCONF queue, ASCONF-ACK queue
+         * and ASCONF-ACK cache.
+         */
+        sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP,
+                        SCTP_TO(SCTP_EVENT_TIMEOUT_T4_RTO));
+        sctp_add_cmd_sf(commands, SCTP_CMD_PURGE_ASCONF_QUEUE, SCTP_NULL());
+
         repl = sctp_make_cookie_ack(new_asoc, chunk);
         if (!repl)
                 goto nomem;
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 8d83f9d48713..b84d7395535e 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -13,10 +13,6 @@
  *      and need to be refreshed, or when a packet was damaged in transit.
  *      This may be have to be moved to the VFS layer.
  *
- *  NB: BSD uses a more intelligent approach to guessing when a request
- *  or reply has been lost by keeping the RTO estimate for each procedure.
- *  We currently make do with a constant timeout value.
- *
  *  Copyright (C) 1992,1993 Rick Sladkey <jrs@world.std.com>
  *  Copyright (C) 1995,1996 Olaf Kirch <okir@monad.swb.de>
  */
@@ -32,7 +28,9 @@
 #include <linux/slab.h>
 #include <linux/utsname.h>
 #include <linux/workqueue.h>
+#include <linux/in.h>
 #include <linux/in6.h>
+#include <linux/un.h>
 
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/rpc_pipe_fs.h>
@@ -298,22 +296,27 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args)
          * up a string representation of the passed-in address.
          */
         if (args->servername == NULL) {
+                struct sockaddr_un *sun =
+                                (struct sockaddr_un *)args->address;
+                struct sockaddr_in *sin =
+                                (struct sockaddr_in *)args->address;
+                struct sockaddr_in6 *sin6 =
+                                (struct sockaddr_in6 *)args->address;
+
                 servername[0] = '\0';
                 switch (args->address->sa_family) {
-                case AF_INET: {
-                        struct sockaddr_in *sin =
-                                        (struct sockaddr_in *)args->address;
+                case AF_LOCAL:
+                        snprintf(servername, sizeof(servername), "%s",
+                                 sun->sun_path);
+                        break;
+                case AF_INET:
                         snprintf(servername, sizeof(servername), "%pI4",
                                  &sin->sin_addr.s_addr);
                         break;
-                }
-                case AF_INET6: {
-                        struct sockaddr_in6 *sin =
-                                        (struct sockaddr_in6 *)args->address;
+                case AF_INET6:
                         snprintf(servername, sizeof(servername), "%pI6",
-                                 &sin->sin6_addr);
+                                 &sin6->sin6_addr);
                         break;
-                }
                 default:
                         /* caller wants default server name, but
                          * address family isn't recognized. */
diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c
index c652e4cc9fe9..9a80a922c527 100644
--- a/net/sunrpc/rpcb_clnt.c
+++ b/net/sunrpc/rpcb_clnt.c
@@ -16,6 +16,7 @@
 
 #include <linux/types.h>
 #include <linux/socket.h>
+#include <linux/un.h>
 #include <linux/in.h>
 #include <linux/in6.h>
 #include <linux/kernel.h>
@@ -32,6 +33,8 @@
 # define RPCDBG_FACILITY        RPCDBG_BIND
 #endif
 
+#define RPCBIND_SOCK_PATHNAME   "/var/run/rpcbind.sock"
+
 #define RPCBIND_PROGRAM         (100000u)
 #define RPCBIND_PORT            (111u)
 
@@ -158,20 +161,69 @@ static void rpcb_map_release(void *data)
         kfree(map);
 }
 
-static const struct sockaddr_in rpcb_inaddr_loopback = {
-        .sin_family             = AF_INET,
-        .sin_addr.s_addr        = htonl(INADDR_LOOPBACK),
-        .sin_port               = htons(RPCBIND_PORT),
-};
+/*
+ * Returns zero on success, otherwise a negative errno value
+ * is returned.
+ */
+static int rpcb_create_local_unix(void)
+{
+        static const struct sockaddr_un rpcb_localaddr_rpcbind = {
+                .sun_family             = AF_LOCAL,
+                .sun_path               = RPCBIND_SOCK_PATHNAME,
+        };
+        struct rpc_create_args args = {
+                .net            = &init_net,
+                .protocol       = XPRT_TRANSPORT_LOCAL,
+                .address        = (struct sockaddr *)&rpcb_localaddr_rpcbind,
+                .addrsize       = sizeof(rpcb_localaddr_rpcbind),
+                .servername     = "localhost",
+                .program        = &rpcb_program,
+                .version        = RPCBVERS_2,
+                .authflavor     = RPC_AUTH_NULL,
+        };
+        struct rpc_clnt *clnt, *clnt4;
+        int result = 0;
+
+        /*
+         * Because we requested an RPC PING at transport creation time,
+         * this works only if the user space portmapper is rpcbind, and
+         * it's listening on AF_LOCAL on the named socket.
+         */
+        clnt = rpc_create(&args);
+        if (IS_ERR(clnt)) {
+                dprintk("RPC:       failed to create AF_LOCAL rpcbind "
+                                "client (errno %ld).\n", PTR_ERR(clnt));
+                result = -PTR_ERR(clnt);
+                goto out;
+        }
+
+        clnt4 = rpc_bind_new_program(clnt, &rpcb_program, RPCBVERS_4);
+        if (IS_ERR(clnt4)) {
+                dprintk("RPC:       failed to bind second program to "
+                                "rpcbind v4 client (errno %ld).\n",
+                                PTR_ERR(clnt4));
+                clnt4 = NULL;
+        }
+
+        /* Protected by rpcb_create_local_mutex */
+        rpcb_local_clnt = clnt;
+        rpcb_local_clnt4 = clnt4;
 
-static DEFINE_MUTEX(rpcb_create_local_mutex);
+out:
+        return result;
+}
 
 /*
  * Returns zero on success, otherwise a negative errno value
  * is returned.
  */
-static int rpcb_create_local(void)
+static int rpcb_create_local_net(void)
 {
+        static const struct sockaddr_in rpcb_inaddr_loopback = {
+                .sin_family             = AF_INET,
+                .sin_addr.s_addr        = htonl(INADDR_LOOPBACK),
+                .sin_port               = htons(RPCBIND_PORT),
+        };
         struct rpc_create_args args = {
                 .net            = &init_net,
                 .protocol       = XPRT_TRANSPORT_TCP,
@@ -186,13 +238,6 @@ static int rpcb_create_local(void)
         struct rpc_clnt *clnt, *clnt4;
         int result = 0;
 
-        if (rpcb_local_clnt)
-                return result;
-
-        mutex_lock(&rpcb_create_local_mutex);
-        if (rpcb_local_clnt)
-                goto out;
-
         clnt = rpc_create(&args);
         if (IS_ERR(clnt)) {
                 dprintk("RPC:       failed to create local rpcbind "
@@ -214,10 +259,34 @@ static int rpcb_create_local(void)
                 clnt4 = NULL;
         }
 
+        /* Protected by rpcb_create_local_mutex */
         rpcb_local_clnt = clnt;
         rpcb_local_clnt4 = clnt4;
 
 out:
+        return result;
+}
+
+/*
+ * Returns zero on success, otherwise a negative errno value
+ * is returned.
+ */
+static int rpcb_create_local(void)
+{
+        static DEFINE_MUTEX(rpcb_create_local_mutex);
+        int result = 0;
+
+        if (rpcb_local_clnt)
+                return result;
+
+        mutex_lock(&rpcb_create_local_mutex);
+        if (rpcb_local_clnt)
+                goto out;
+
+        if (rpcb_create_local_unix() != 0)
+                result = rpcb_create_local_net();
+
+out:
         mutex_unlock(&rpcb_create_local_mutex);
         return result;
 }
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 08e05a8ce025..2b90292e9505 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -942,6 +942,8 @@ static void svc_unregister(const struct svc_serv *serv)
                         if (progp->pg_vers[i]->vs_hidden)
                                 continue;
 
+                        dprintk("svc: attempting to unregister %sv%u\n",
+                                progp->pg_name, i);
                         __svc_unregister(progp->pg_prog, i, progp->pg_name);
                 }
         }
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index b7d435c3f19e..af04f779ce9f 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -387,6 +387,33 @@ static int svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov, int nr,
         return len;
 }
 
+static int svc_partial_recvfrom(struct svc_rqst *rqstp,
+                                struct kvec *iov, int nr,
+                                int buflen, unsigned int base)
+{
+        size_t save_iovlen;
+        void __user *save_iovbase;
+        unsigned int i;
+        int ret;
+
+        if (base == 0)
+                return svc_recvfrom(rqstp, iov, nr, buflen);
+
+        for (i = 0; i < nr; i++) {
+                if (iov[i].iov_len > base)
+                        break;
+                base -= iov[i].iov_len;
+        }
+        save_iovlen = iov[i].iov_len;
+        save_iovbase = iov[i].iov_base;
+        iov[i].iov_len -= base;
+        iov[i].iov_base += base;
+        ret = svc_recvfrom(rqstp, &iov[i], nr - i, buflen);
+        iov[i].iov_len = save_iovlen;
+        iov[i].iov_base = save_iovbase;
+        return ret;
+}
+
 /*
  * Set socket snd and rcv buffer lengths
  */
@@ -409,7 +436,6 @@ static void svc_sock_setbufsize(struct socket *sock, unsigned int snd,
         lock_sock(sock->sk);
         sock->sk->sk_sndbuf = snd * 2;
         sock->sk->sk_rcvbuf = rcv * 2;
-        sock->sk->sk_userlocks |= SOCK_SNDBUF_LOCK|SOCK_RCVBUF_LOCK;
         sock->sk->sk_write_space(sock->sk);
         release_sock(sock->sk);
 #endif
@@ -884,6 +910,56 @@ failed:
         return NULL;
 }
 
+static unsigned int svc_tcp_restore_pages(struct svc_sock *svsk, struct svc_rqst *rqstp)
+{
+        unsigned int i, len, npages;
+
+        if (svsk->sk_tcplen <= sizeof(rpc_fraghdr))
+                return 0;
+        len = svsk->sk_tcplen - sizeof(rpc_fraghdr);
+        npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+        for (i = 0; i < npages; i++) {
+                if (rqstp->rq_pages[i] != NULL)
+                        put_page(rqstp->rq_pages[i]);
+                BUG_ON(svsk->sk_pages[i] == NULL);
+                rqstp->rq_pages[i] = svsk->sk_pages[i];
+                svsk->sk_pages[i] = NULL;
+        }
+        rqstp->rq_arg.head[0].iov_base = page_address(rqstp->rq_pages[0]);
+        return len;
+}
+
+static void svc_tcp_save_pages(struct svc_sock *svsk, struct svc_rqst *rqstp)
+{
+        unsigned int i, len, npages;
+
+        if (svsk->sk_tcplen <= sizeof(rpc_fraghdr))
+                return;
+        len = svsk->sk_tcplen - sizeof(rpc_fraghdr);
+        npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+        for (i = 0; i < npages; i++) {
+                svsk->sk_pages[i] = rqstp->rq_pages[i];
+                rqstp->rq_pages[i] = NULL;
+        }
+}
+
+static void svc_tcp_clear_pages(struct svc_sock *svsk)
+{
+        unsigned int i, len, npages;
+
+        if (svsk->sk_tcplen <= sizeof(rpc_fraghdr))
+                goto out;
+        len = svsk->sk_tcplen - sizeof(rpc_fraghdr);
+        npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+        for (i = 0; i < npages; i++) {
+                BUG_ON(svsk->sk_pages[i] == NULL);
+                put_page(svsk->sk_pages[i]);
+                svsk->sk_pages[i] = NULL;
+        }
+out:
+        svsk->sk_tcplen = 0;
+}
+
 /*
  * Receive data.
  * If we haven't gotten the record length yet, get the next four bytes.
@@ -893,31 +969,15 @@ failed:
 static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp)
 {
         struct svc_serv *serv = svsk->sk_xprt.xpt_server;
+        unsigned int want;
         int len;
 
-        if (test_and_clear_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags))
-                /* sndbuf needs to have room for one request
-                 * per thread, otherwise we can stall even when the
-                 * network isn't a bottleneck.
-                 *
-                 * We count all threads rather than threads in a
-                 * particular pool, which provides an upper bound
-                 * on the number of threads which will access the socket.
-                 *
-                 * rcvbuf just needs to be able to hold a few requests.
-                 * Normally they will be removed from the queue
-                 * as soon a a complete request arrives.
-                 */
-                svc_sock_setbufsize(svsk->sk_sock,
-                                    (serv->sv_nrthreads+3) * serv->sv_max_mesg,
-                                    3 * serv->sv_max_mesg);
-
         clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
 
         if (svsk->sk_tcplen < sizeof(rpc_fraghdr)) {
-                int             want = sizeof(rpc_fraghdr) - svsk->sk_tcplen;
                 struct kvec     iov;
 
+                want = sizeof(rpc_fraghdr) - svsk->sk_tcplen;
                 iov.iov_base = ((char *) &svsk->sk_reclen) + svsk->sk_tcplen;
                 iov.iov_len  = want;
                 if ((len = svc_recvfrom(rqstp, &iov, 1, want)) < 0)
@@ -927,7 +987,7 @@ static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp)
                 if (len < want) {
                         dprintk("svc: short recvfrom while reading record "
                                 "length (%d of %d)\n", len, want);
-                        goto err_again; /* record header not complete */
+                        return -EAGAIN;
                 }
 
                 svsk->sk_reclen = ntohl(svsk->sk_reclen);
@@ -954,83 +1014,75 @@ static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp)
                 }
         }
 
-        /* Check whether enough data is available */
-        len = svc_recv_available(svsk);
-        if (len < 0)
-                goto error;
+        if (svsk->sk_reclen < 8)
+                goto err_delete; /* client is nuts. */
 
-        if (len < svsk->sk_reclen) {
-                dprintk("svc: incomplete TCP record (%d of %d)\n",
-                        len, svsk->sk_reclen);
-                goto err_again; /* record not complete */
-        }
         len = svsk->sk_reclen;
-        set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
 
         return len;
- error:
-        if (len == -EAGAIN)
-                dprintk("RPC: TCP recv_record got EAGAIN\n");
+error:
+        dprintk("RPC: TCP recv_record got %d\n", len);
         return len;
- err_delete:
+err_delete:
         set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
- err_again:
         return -EAGAIN;
 }
 
-static int svc_process_calldir(struct svc_sock *svsk, struct svc_rqst *rqstp,
-                               struct rpc_rqst **reqpp, struct kvec *vec)
+static int receive_cb_reply(struct svc_sock *svsk, struct svc_rqst *rqstp)
 {
+        struct rpc_xprt *bc_xprt = svsk->sk_xprt.xpt_bc_xprt;
         struct rpc_rqst *req = NULL;
-        u32 *p;
-        u32 xid;
-        u32 calldir;
-        int len;
-
-        len = svc_recvfrom(rqstp, vec, 1, 8);
-        if (len < 0)
-                goto error;
+        struct kvec *src, *dst;
+        __be32 *p = (__be32 *)rqstp->rq_arg.head[0].iov_base;
+        __be32 xid;
+        __be32 calldir;
 
-        p = (u32 *)rqstp->rq_arg.head[0].iov_base;
         xid = *p++;
         calldir = *p;
 
-        if (calldir == 0) {
-                /* REQUEST is the most common case */
-                vec[0] = rqstp->rq_arg.head[0];
-        } else {
-                /* REPLY */
-                struct rpc_xprt *bc_xprt = svsk->sk_xprt.xpt_bc_xprt;
-
-                if (bc_xprt)
-                        req = xprt_lookup_rqst(bc_xprt, xid);
-
-                if (!req) {
-                        printk(KERN_NOTICE
-                                "%s: Got unrecognized reply: "
-                                "calldir 0x%x xpt_bc_xprt %p xid %08x\n",
-                                __func__, ntohl(calldir),
-                                bc_xprt, xid);
-                        vec[0] = rqstp->rq_arg.head[0];
-                        goto out;
-                }
+        if (bc_xprt)
+                req = xprt_lookup_rqst(bc_xprt, xid);
 
-                memcpy(&req->rq_private_buf, &req->rq_rcv_buf,
-                       sizeof(struct xdr_buf));
-                /* copy the xid and call direction */
-                memcpy(req->rq_private_buf.head[0].iov_base,
-                       rqstp->rq_arg.head[0].iov_base, 8);
-                vec[0] = req->rq_private_buf.head[0];
+        if (!req) {
+                printk(KERN_NOTICE
+                        "%s: Got unrecognized reply: "
+                        "calldir 0x%x xpt_bc_xprt %p xid %08x\n",
+                        __func__, ntohl(calldir),
+                        bc_xprt, xid);
+                return -EAGAIN;
         }
- out:
-        vec[0].iov_base += 8;
-        vec[0].iov_len -= 8;
-        len = svsk->sk_reclen - 8;
- error:
-        *reqpp = req;
-        return len;
+
+        memcpy(&req->rq_private_buf, &req->rq_rcv_buf, sizeof(struct xdr_buf));
+        /*
+         * XXX!: cheating for now!  Only copying HEAD.
+         * But we know this is good enough for now (in fact, for any
+         * callback reply in the forseeable future).
+         */
+        dst = &req->rq_private_buf.head[0];
+        src = &rqstp->rq_arg.head[0];
+        if (dst->iov_len < src->iov_len)
+                return -EAGAIN; /* whatever; just giving up. */
+        memcpy(dst->iov_base, src->iov_base, src->iov_len);
+        xprt_complete_rqst(req->rq_task, svsk->sk_reclen);
+        rqstp->rq_arg.len = 0;
+        return 0;
 }
 
+static int copy_pages_to_kvecs(struct kvec *vec, struct page **pages, int len)
+{
+        int i = 0;
+        int t = 0;
+
+        while (t < len) {
+                vec[i].iov_base = page_address(pages[i]);
+                vec[i].iov_len = PAGE_SIZE;
+                i++;
+                t += PAGE_SIZE;
+        }
+        return i;
+}
+
+
 /*
  * Receive data from a TCP socket.
  */
@@ -1041,8 +1093,10 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
         struct svc_serv *serv = svsk->sk_xprt.xpt_server;
         int             len;
         struct kvec *vec;
-        int pnum, vlen;
-        struct rpc_rqst *req = NULL;
+        unsigned int want, base;
+        __be32 *p;
+        __be32 calldir;
+        int pnum;
 
         dprintk("svc: tcp_recv %p data %d conn %d close %d\n",
                 svsk, test_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags),
@@ -1053,87 +1107,73 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
         if (len < 0)
                 goto error;
 
+        base = svc_tcp_restore_pages(svsk, rqstp);
+        want = svsk->sk_reclen - base;
+
         vec = rqstp->rq_vec;
-        vec[0] = rqstp->rq_arg.head[0];
-        vlen = PAGE_SIZE;
 
-        /*
-         * We have enough data for the whole tcp record. Let's try and read the
-         * first 8 bytes to get the xid and the call direction. We can use this
-         * to figure out if this is a call or a reply to a callback. If
-         * sk_reclen is < 8 (xid and calldir), then this is a malformed packet.
-         * In that case, don't bother with the calldir and just read the data.
-         * It will be rejected in svc_process.
-         */
-        if (len >= 8) {
-                len = svc_process_calldir(svsk, rqstp, &req, vec);
-                if (len < 0)
-                        goto err_again;
-                vlen -= 8;
-        }
+        pnum = copy_pages_to_kvecs(&vec[0], &rqstp->rq_pages[0],
+                                                svsk->sk_reclen);
 
-        pnum = 1;
-        while (vlen < len) {
-                vec[pnum].iov_base = (req) ?
-                        page_address(req->rq_private_buf.pages[pnum - 1]) :
-                        page_address(rqstp->rq_pages[pnum]);
-                vec[pnum].iov_len = PAGE_SIZE;
-                pnum++;
-                vlen += PAGE_SIZE;
-        }
         rqstp->rq_respages = &rqstp->rq_pages[pnum];
 
         /* Now receive data */
-        len = svc_recvfrom(rqstp, vec, pnum, len);
-        if (len < 0)
-                goto err_again;
-
-        /*
-         * Account for the 8 bytes we read earlier
-         */
-        len += 8;
-
-        if (req) {
-                xprt_complete_rqst(req->rq_task, len);
-                len = 0;
-                goto out;
+        len = svc_partial_recvfrom(rqstp, vec, pnum, want, base);
+        if (len >= 0)
+                svsk->sk_tcplen += len;
+        if (len != want) {
+                if (len < 0 && len != -EAGAIN)
+                        goto err_other;
+                svc_tcp_save_pages(svsk, rqstp);
+                dprintk("svc: incomplete TCP record (%d of %d)\n",
+                        svsk->sk_tcplen, svsk->sk_reclen);
+                goto err_noclose;
         }
-        dprintk("svc: TCP complete record (%d bytes)\n", len);
-        rqstp->rq_arg.len = len;
+
+        rqstp->rq_arg.len = svsk->sk_reclen;
         rqstp->rq_arg.page_base = 0;
-        if (len <= rqstp->rq_arg.head[0].iov_len) {
-                rqstp->rq_arg.head[0].iov_len = len;
+        if (rqstp->rq_arg.len <= rqstp->rq_arg.head[0].iov_len) {
+                rqstp->rq_arg.head[0].iov_len = rqstp->rq_arg.len;
                 rqstp->rq_arg.page_len = 0;
-        } else {
-                rqstp->rq_arg.page_len = len - rqstp->rq_arg.head[0].iov_len;
-        }
+        } else
+                rqstp->rq_arg.page_len = rqstp->rq_arg.len - rqstp->rq_arg.head[0].iov_len;
 
         rqstp->rq_xprt_ctxt   = NULL;
         rqstp->rq_prot        = IPPROTO_TCP;
 
-out:
+        p = (__be32 *)rqstp->rq_arg.head[0].iov_base;
+        calldir = p[1];
+        if (calldir)
+                len = receive_cb_reply(svsk, rqstp);
+
         /* Reset TCP read info */
         svsk->sk_reclen = 0;
         svsk->sk_tcplen = 0;
+        /* If we have more data, signal svc_xprt_enqueue() to try again */
+        if (svc_recv_available(svsk) > sizeof(rpc_fraghdr))
+                set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
+
+        if (len < 0)
+                goto error;
 
         svc_xprt_copy_addrs(rqstp, &svsk->sk_xprt);
         if (serv->sv_stats)
                 serv->sv_stats->nettcpcnt++;
 
-        return len;
+        dprintk("svc: TCP complete record (%d bytes)\n", rqstp->rq_arg.len);
+        return rqstp->rq_arg.len;
 
-err_again:
-        if (len == -EAGAIN) {
-                dprintk("RPC: TCP recvfrom got EAGAIN\n");
-                return len;
-        }
 error:
-        if (len != -EAGAIN) {
-                printk(KERN_NOTICE "%s: recvfrom returned errno %d\n",
-                       svsk->sk_xprt.xpt_server->sv_name, -len);
-                set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
-        }
+        if (len != -EAGAIN)
+                goto err_other;
+        dprintk("RPC: TCP recvfrom got EAGAIN\n");
         return -EAGAIN;
+err_other:
+        printk(KERN_NOTICE "%s: recvfrom returned errno %d\n",
+               svsk->sk_xprt.xpt_server->sv_name, -len);
+        set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
+err_noclose:
+        return -EAGAIN; /* record not complete */
 }
 
 /*
@@ -1304,18 +1344,10 @@ static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv)
 
                 svsk->sk_reclen = 0;
                 svsk->sk_tcplen = 0;
+                memset(&svsk->sk_pages[0], 0, sizeof(svsk->sk_pages));
 
                 tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF;
 
-                /* initialise setting must have enough space to
-                 * receive and respond to one request.
-                 * svc_tcp_recvfrom will re-adjust if necessary
-                 */
-                svc_sock_setbufsize(svsk->sk_sock,
-                                    3 * svsk->sk_xprt.xpt_server->sv_max_mesg,
-                                    3 * svsk->sk_xprt.xpt_server->sv_max_mesg);
-
-                set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
                 set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
                 if (sk->sk_state != TCP_ESTABLISHED)
                         set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
@@ -1379,8 +1411,14 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
         /* Initialize the socket */
         if (sock->type == SOCK_DGRAM)
                 svc_udp_init(svsk, serv);
-        else
+        else {
+                /* initialise setting must have enough space to
+                 * receive and respond to one request.
+                 */
+                svc_sock_setbufsize(svsk->sk_sock, 4 * serv->sv_max_mesg,
+                                        4 * serv->sv_max_mesg);
                 svc_tcp_init(svsk, serv);
+        }
 
         dprintk("svc: svc_setup_socket created %p (inet %p)\n",
                                 svsk, svsk->sk_sk);
@@ -1562,8 +1600,10 @@ static void svc_tcp_sock_detach(struct svc_xprt *xprt)
 
         svc_sock_detach(xprt);
 
-        if (!test_bit(XPT_LISTENER, &xprt->xpt_flags))
+        if (!test_bit(XPT_LISTENER, &xprt->xpt_flags)) {
+                svc_tcp_clear_pages(svsk);
                 kernel_sock_shutdown(svsk->sk_sock, SHUT_RDWR);
+        }
 }
 
 /*
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 679cd674b81d..f008c14ad34c 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -638,6 +638,25 @@ void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p)
 }
 EXPORT_SYMBOL_GPL(xdr_init_decode);
 
+/**
+ * xdr_init_decode - Initialize an xdr_stream for decoding data.
+ * @xdr: pointer to xdr_stream struct
+ * @buf: pointer to XDR buffer from which to decode data
+ * @pages: list of pages to decode into
+ * @len: length in bytes of buffer in pages
+ */
+void xdr_init_decode_pages(struct xdr_stream *xdr, struct xdr_buf *buf,
+                           struct page **pages, unsigned int len)
+{
+        memset(buf, 0, sizeof(*buf));
+        buf->pages =  pages;
+        buf->page_len =  len;
+        buf->buflen =  len;
+        buf->len = len;
+        xdr_init_decode(xdr, buf, NULL);
+}
+EXPORT_SYMBOL_GPL(xdr_init_decode_pages);
+
 static __be32 * __xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes)
 {
         __be32 *p = xdr->p;
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index bf005d3c65ef..72abb7358933 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -19,6 +19,7 @@
  */
 
 #include <linux/types.h>
+#include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/capability.h>
@@ -28,6 +29,7 @@
 #include <linux/in.h>
 #include <linux/net.h>
 #include <linux/mm.h>
+#include <linux/un.h>
 #include <linux/udp.h>
 #include <linux/tcp.h>
 #include <linux/sunrpc/clnt.h>
@@ -45,6 +47,9 @@
 #include <net/tcp.h>
 
 #include "sunrpc.h"
+
+static void xs_close(struct rpc_xprt *xprt);
+
 /*
  * xprtsock tunables
  */
@@ -261,6 +266,11 @@ static inline struct sockaddr *xs_addr(struct rpc_xprt *xprt)
         return (struct sockaddr *) &xprt->addr;
 }
 
+static inline struct sockaddr_un *xs_addr_un(struct rpc_xprt *xprt)
+{
+        return (struct sockaddr_un *) &xprt->addr;
+}
+
 static inline struct sockaddr_in *xs_addr_in(struct rpc_xprt *xprt)
 {
         return (struct sockaddr_in *) &xprt->addr;
@@ -276,23 +286,34 @@ static void xs_format_common_peer_addresses(struct rpc_xprt *xprt)
         struct sockaddr *sap = xs_addr(xprt);
         struct sockaddr_in6 *sin6;
         struct sockaddr_in *sin;
+        struct sockaddr_un *sun;
         char buf[128];
 
-        (void)rpc_ntop(sap, buf, sizeof(buf));
-        xprt->address_strings[RPC_DISPLAY_ADDR] = kstrdup(buf, GFP_KERNEL);
-
         switch (sap->sa_family) {
+        case AF_LOCAL:
+                sun = xs_addr_un(xprt);
+                strlcpy(buf, sun->sun_path, sizeof(buf));
+                xprt->address_strings[RPC_DISPLAY_ADDR] =
+                                                kstrdup(buf, GFP_KERNEL);
+                break;
         case AF_INET:
+                (void)rpc_ntop(sap, buf, sizeof(buf));
+                xprt->address_strings[RPC_DISPLAY_ADDR] =
+                                                kstrdup(buf, GFP_KERNEL);
                 sin = xs_addr_in(xprt);
                 snprintf(buf, sizeof(buf), "%08x", ntohl(sin->sin_addr.s_addr));
                 break;
         case AF_INET6:
+                (void)rpc_ntop(sap, buf, sizeof(buf));
+                xprt->address_strings[RPC_DISPLAY_ADDR] =
+                                                kstrdup(buf, GFP_KERNEL);
                 sin6 = xs_addr_in6(xprt);
                 snprintf(buf, sizeof(buf), "%pi6", &sin6->sin6_addr);
                 break;
         default:
                 BUG();
         }
+
         xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL);
 }
 
@@ -495,6 +516,70 @@ static int xs_nospace(struct rpc_task *task)
         return ret;
 }
 
+/*
+ * Construct a stream transport record marker in @buf.
+ */
+static inline void xs_encode_stream_record_marker(struct xdr_buf *buf)
+{
+        u32 reclen = buf->len - sizeof(rpc_fraghdr);
+        rpc_fraghdr *base = buf->head[0].iov_base;
+        *base = cpu_to_be32(RPC_LAST_STREAM_FRAGMENT | reclen);
+}
+
+/**
+ * xs_local_send_request - write an RPC request to an AF_LOCAL socket
+ * @task: RPC task that manages the state of an RPC request
+ *
+ * Return values:
+ *        0:    The request has been sent
+ *   EAGAIN:    The socket was blocked, please call again later to
+ *              complete the request
+ * ENOTCONN:    Caller needs to invoke connect logic then call again
+ *    other:    Some other error occured, the request was not sent
+ */
+static int xs_local_send_request(struct rpc_task *task)
+{
+        struct rpc_rqst *req = task->tk_rqstp;
+        struct rpc_xprt *xprt = req->rq_xprt;
+        struct sock_xprt *transport =
+                                container_of(xprt, struct sock_xprt, xprt);
+        struct xdr_buf *xdr = &req->rq_snd_buf;
+        int status;
+
+        xs_encode_stream_record_marker(&req->rq_snd_buf);
+
+        xs_pktdump("packet data:",
+                        req->rq_svec->iov_base, req->rq_svec->iov_len);
+
+        status = xs_sendpages(transport->sock, NULL, 0,
+                                                xdr, req->rq_bytes_sent);
+        dprintk("RPC:       %s(%u) = %d\n",
+                        __func__, xdr->len - req->rq_bytes_sent, status);
+        if (likely(status >= 0)) {
+                req->rq_bytes_sent += status;
+                req->rq_xmit_bytes_sent += status;
+                if (likely(req->rq_bytes_sent >= req->rq_slen)) {
+                        req->rq_bytes_sent = 0;
+                        return 0;
+                }
+                status = -EAGAIN;
+        }
+
+        switch (status) {
+        case -EAGAIN:
+                status = xs_nospace(task);
+                break;
+        default:
+                dprintk("RPC:       sendmsg returned unrecognized error %d\n",
+                        -status);
+        case -EPIPE:
+                xs_close(xprt);
+                status = -ENOTCONN;
+        }
+
+        return status;
+}
+
 /**
  * xs_udp_send_request - write an RPC request to a UDP socket
  * @task: address of RPC task that manages the state of an RPC request
@@ -574,13 +659,6 @@ static void xs_tcp_shutdown(struct rpc_xprt *xprt)
                 kernel_sock_shutdown(sock, SHUT_WR);
 }
 
-static inline void xs_encode_tcp_record_marker(struct xdr_buf *buf)
-{
-        u32 reclen = buf->len - sizeof(rpc_fraghdr);
-        rpc_fraghdr *base = buf->head[0].iov_base;
-        *base = htonl(RPC_LAST_STREAM_FRAGMENT | reclen);
-}
-
 /**
  * xs_tcp_send_request - write an RPC request to a TCP socket
  * @task: address of RPC task that manages the state of an RPC request
@@ -603,7 +681,7 @@ static int xs_tcp_send_request(struct rpc_task *task)
         struct xdr_buf *xdr = &req->rq_snd_buf;
         int status;
 
-        xs_encode_tcp_record_marker(&req->rq_snd_buf);
+        xs_encode_stream_record_marker(&req->rq_snd_buf);
 
         xs_pktdump("packet data:",
                                 req->rq_svec->iov_base,
@@ -785,6 +863,88 @@ static inline struct rpc_xprt *xprt_from_sock(struct sock *sk)
         return (struct rpc_xprt *) sk->sk_user_data;
 }
 
+static int xs_local_copy_to_xdr(struct xdr_buf *xdr, struct sk_buff *skb)
+{
+        struct xdr_skb_reader desc = {
+                .skb            = skb,
+                .offset         = sizeof(rpc_fraghdr),
+                .count          = skb->len - sizeof(rpc_fraghdr),
+        };
+
+        if (xdr_partial_copy_from_skb(xdr, 0, &desc, xdr_skb_read_bits) < 0)
+                return -1;
+        if (desc.count)
+                return -1;
+        return 0;
+}
+
+/**
+ * xs_local_data_ready - "data ready" callback for AF_LOCAL sockets
+ * @sk: socket with data to read
+ * @len: how much data to read
+ *
+ * Currently this assumes we can read the whole reply in a single gulp.
+ */
+static void xs_local_data_ready(struct sock *sk, int len)
+{
+        struct rpc_task *task;
+        struct rpc_xprt *xprt;
+        struct rpc_rqst *rovr;
+        struct sk_buff *skb;
+        int err, repsize, copied;
+        u32 _xid;
+        __be32 *xp;
+
+        read_lock_bh(&sk->sk_callback_lock);
+        dprintk("RPC:       %s...\n", __func__);
+        xprt = xprt_from_sock(sk);
+        if (xprt == NULL)
+                goto out;
+
+        skb = skb_recv_datagram(sk, 0, 1, &err);
+        if (skb == NULL)
+                goto out;
+
+        if (xprt->shutdown)
+                goto dropit;
+
+        repsize = skb->len - sizeof(rpc_fraghdr);
+        if (repsize < 4) {
+                dprintk("RPC:       impossible RPC reply size %d\n", repsize);
+                goto dropit;
+        }
+
+        /* Copy the XID from the skb... */
+        xp = skb_header_pointer(skb, sizeof(rpc_fraghdr), sizeof(_xid), &_xid);
+        if (xp == NULL)
+                goto dropit;
+
+        /* Look up and lock the request corresponding to the given XID */
+        spin_lock(&xprt->transport_lock);
+        rovr = xprt_lookup_rqst(xprt, *xp);
+        if (!rovr)
+                goto out_unlock;
+        task = rovr->rq_task;
+
+        copied = rovr->rq_private_buf.buflen;
+        if (copied > repsize)
+                copied = repsize;
+
+        if (xs_local_copy_to_xdr(&rovr->rq_private_buf, skb)) {
+                dprintk("RPC:       sk_buff copy failed\n");
+                goto out_unlock;
+        }
+
+        xprt_complete_rqst(task, copied);
+
+ out_unlock:
+        spin_unlock(&xprt->transport_lock);
+ dropit:
+        skb_free_datagram(sk, skb);
+ out:
+        read_unlock_bh(&sk->sk_callback_lock);
+}
+
 /**
  * xs_udp_data_ready - "data ready" callback for UDP sockets
  * @sk: socket with data to read
@@ -1344,7 +1504,6 @@ static void xs_tcp_state_change(struct sock *sk)
         case TCP_CLOSE_WAIT:
                 /* The server initiated a shutdown of the socket */
                 xprt_force_disconnect(xprt);
-        case TCP_SYN_SENT:
                 xprt->connect_cookie++;
         case TCP_CLOSING:
                 /*
@@ -1571,11 +1730,31 @@ static int xs_bind(struct sock_xprt *transport, struct socket *sock)
         return err;
 }
 
+/*
+ * We don't support autobind on AF_LOCAL sockets
+ */
+static void xs_local_rpcbind(struct rpc_task *task)
+{
+        xprt_set_bound(task->tk_xprt);
+}
+
+static void xs_local_set_port(struct rpc_xprt *xprt, unsigned short port)
+{
+}
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 static struct lock_class_key xs_key[2];
 static struct lock_class_key xs_slock_key[2];
 
+static inline void xs_reclassify_socketu(struct socket *sock)
+{
+        struct sock *sk = sock->sk;
+
+        BUG_ON(sock_owned_by_user(sk));
+        sock_lock_init_class_and_name(sk, "slock-AF_LOCAL-RPC",
+                &xs_slock_key[1], "sk_lock-AF_LOCAL-RPC", &xs_key[1]);
+}
+
 static inline void xs_reclassify_socket4(struct socket *sock)
 {
         struct sock *sk = sock->sk;
@@ -1597,6 +1776,9 @@ static inline void xs_reclassify_socket6(struct socket *sock)
 static inline void xs_reclassify_socket(int family, struct socket *sock)
 {
         switch (family) {
+        case AF_LOCAL:
+                xs_reclassify_socketu(sock);
+                break;
         case AF_INET:
                 xs_reclassify_socket4(sock);
                 break;
@@ -1606,6 +1788,10 @@ static inline void xs_reclassify_socket(int family, struct socket *sock)
         }
 }
 #else
+static inline void xs_reclassify_socketu(struct socket *sock)
+{
+}
+
 static inline void xs_reclassify_socket4(struct socket *sock)
 {
 }
@@ -1644,6 +1830,94 @@ out:
         return ERR_PTR(err);
 }
 
+static int xs_local_finish_connecting(struct rpc_xprt *xprt,
+                                      struct socket *sock)
+{
+        struct sock_xprt *transport = container_of(xprt, struct sock_xprt,
+                                                                        xprt);
+
+        if (!transport->inet) {
+                struct sock *sk = sock->sk;
+
+                write_lock_bh(&sk->sk_callback_lock);
+
+                xs_save_old_callbacks(transport, sk);
+
+                sk->sk_user_data = xprt;
+                sk->sk_data_ready = xs_local_data_ready;
+                sk->sk_write_space = xs_udp_write_space;
+                sk->sk_error_report = xs_error_report;
+                sk->sk_allocation = GFP_ATOMIC;
+
+                xprt_clear_connected(xprt);
+
+                /* Reset to new socket */
+                transport->sock = sock;
+                transport->inet = sk;
+
+                write_unlock_bh(&sk->sk_callback_lock);
+        }
+
+        /* Tell the socket layer to start connecting... */
+        xprt->stat.connect_count++;
+        xprt->stat.connect_start = jiffies;
+        return kernel_connect(sock, xs_addr(xprt), xprt->addrlen, 0);
+}
+
+/**
+ * xs_local_setup_socket - create AF_LOCAL socket, connect to a local endpoint
+ * @xprt: RPC transport to connect
+ * @transport: socket transport to connect
+ * @create_sock: function to create a socket of the correct type
+ *
+ * Invoked by a work queue tasklet.
+ */
+static void xs_local_setup_socket(struct work_struct *work)
+{
+        struct sock_xprt *transport =
+                container_of(work, struct sock_xprt, connect_worker.work);
+        struct rpc_xprt *xprt = &transport->xprt;
+        struct socket *sock;
+        int status = -EIO;
+
+        if (xprt->shutdown)
+                goto out;
+
+        clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
+        status = __sock_create(xprt->xprt_net, AF_LOCAL,
+                                        SOCK_STREAM, 0, &sock, 1);
+        if (status < 0) {
+                dprintk("RPC:       can't create AF_LOCAL "
+                        "transport socket (%d).\n", -status);
+                goto out;
+        }
+        xs_reclassify_socketu(sock);
+
+        dprintk("RPC:       worker connecting xprt %p via AF_LOCAL to %s\n",
+                        xprt, xprt->address_strings[RPC_DISPLAY_ADDR]);
+
+        status = xs_local_finish_connecting(xprt, sock);
+        switch (status) {
+        case 0:
+                dprintk("RPC:       xprt %p connected to %s\n",
+                                xprt, xprt->address_strings[RPC_DISPLAY_ADDR]);
+                xprt_set_connected(xprt);
+                break;
+        case -ENOENT:
+                dprintk("RPC:       xprt %p: socket %s does not exist\n",
+                                xprt, xprt->address_strings[RPC_DISPLAY_ADDR]);
+                break;
+        default:
+                printk(KERN_ERR "%s: unhandled error (%d) connecting to %s\n",
+                                __func__, -status,
+                                xprt->address_strings[RPC_DISPLAY_ADDR]);
+        }
+
+out:
+        xprt_clear_connecting(xprt);
+        xprt_wake_pending_tasks(xprt, status);
+}
+
 static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 {
         struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
@@ -1758,6 +2032,7 @@ static void xs_tcp_reuse_connection(struct sock_xprt *transport)
 static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
 {
         struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
+        int ret = -ENOTCONN;
 
         if (!transport->inet) {
                 struct sock *sk = sock->sk;
@@ -1789,12 +2064,22 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock)
         }
 
         if (!xprt_bound(xprt))
-                return -ENOTCONN;
+                goto out;
 
         /* Tell the socket layer to start connecting... */
         xprt->stat.connect_count++;
         xprt->stat.connect_start = jiffies;
-        return kernel_connect(sock, xs_addr(xprt), xprt->addrlen, O_NONBLOCK);
+        ret = kernel_connect(sock, xs_addr(xprt), xprt->addrlen, O_NONBLOCK);
+        switch (ret) {
+        case 0:
+        case -EINPROGRESS:
+                /* SYN_SENT! */
+                xprt->connect_cookie++;
+                if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO)
+                        xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO;
+        }
+out:
+        return ret;
 }
 
 /**
@@ -1917,6 +2202,32 @@ static void xs_connect(struct rpc_task *task)
 }
 
 /**
+ * xs_local_print_stats - display AF_LOCAL socket-specifc stats
+ * @xprt: rpc_xprt struct containing statistics
+ * @seq: output file
+ *
+ */
+static void xs_local_print_stats(struct rpc_xprt *xprt, struct seq_file *seq)
+{
+        long idle_time = 0;
+
+        if (xprt_connected(xprt))
+                idle_time = (long)(jiffies - xprt->last_used) / HZ;
+
+        seq_printf(seq, "\txprt:\tlocal %lu %lu %lu %ld %lu %lu %lu "
+                        "%llu %llu\n",
+                        xprt->stat.bind_count,
+                        xprt->stat.connect_count,
+                        xprt->stat.connect_time,
+                        idle_time,
+                        xprt->stat.sends,
+                        xprt->stat.recvs,
+                        xprt->stat.bad_xids,
+                        xprt->stat.req_u,
+                        xprt->stat.bklog_u);
+}
+
+/**
  * xs_udp_print_stats - display UDP socket-specifc stats
  * @xprt: rpc_xprt struct containing statistics
  * @seq: output file
@@ -2014,10 +2325,7 @@ static int bc_sendto(struct rpc_rqst *req)
         unsigned long headoff;
         unsigned long tailoff;
 
-        /*
-         * Set up the rpc header and record marker stuff
-         */
-        xs_encode_tcp_record_marker(xbufp);
+        xs_encode_stream_record_marker(xbufp);
 
         tailoff = (unsigned long)xbufp->tail[0].iov_base & ~PAGE_MASK;
         headoff = (unsigned long)xbufp->head[0].iov_base & ~PAGE_MASK;
@@ -2089,6 +2397,21 @@ static void bc_destroy(struct rpc_xprt *xprt)
 {
 }
 
+static struct rpc_xprt_ops xs_local_ops = {
+        .reserve_xprt           = xprt_reserve_xprt,
+        .release_xprt           = xs_tcp_release_xprt,
+        .rpcbind                = xs_local_rpcbind,
+        .set_port               = xs_local_set_port,
+        .connect                = xs_connect,
+        .buf_alloc              = rpc_malloc,
+        .buf_free               = rpc_free,
+        .send_request           = xs_local_send_request,
+        .set_retrans_timeout    = xprt_set_retrans_timeout_def,
+        .close                  = xs_close,
+        .destroy                = xs_destroy,
+        .print_stats            = xs_local_print_stats,
+};
+
 static struct rpc_xprt_ops xs_udp_ops = {
         .set_buffer_size        = xs_udp_set_buffer_size,
         .reserve_xprt           = xprt_reserve_xprt_cong,
@@ -2150,6 +2473,8 @@ static int xs_init_anyaddr(const int family, struct sockaddr *sap)
         };
 
         switch (family) {
+        case AF_LOCAL:
+                break;
         case AF_INET:
                 memcpy(sap, &sin, sizeof(sin));
                 break;
@@ -2197,6 +2522,70 @@ static struct rpc_xprt *xs_setup_xprt(struct xprt_create *args,
         return xprt;
 }
 
+static const struct rpc_timeout xs_local_default_timeout = {
+        .to_initval = 10 * HZ,
+        .to_maxval = 10 * HZ,
+        .to_retries = 2,
+};
+
+/**
+ * xs_setup_local - Set up transport to use an AF_LOCAL socket
+ * @args: rpc transport creation arguments
+ *
+ * AF_LOCAL is a "tpi_cots_ord" transport, just like TCP
+ */
+static struct rpc_xprt *xs_setup_local(struct xprt_create *args)
+{
+        struct sockaddr_un *sun = (struct sockaddr_un *)args->dstaddr;
+        struct sock_xprt *transport;
+        struct rpc_xprt *xprt;
+        struct rpc_xprt *ret;
+
+        xprt = xs_setup_xprt(args, xprt_tcp_slot_table_entries);
+        if (IS_ERR(xprt))
+                return xprt;
+        transport = container_of(xprt, struct sock_xprt, xprt);
+
+        xprt->prot = 0;
+        xprt->tsh_size = sizeof(rpc_fraghdr) / sizeof(u32);
+        xprt->max_payload = RPC_MAX_FRAGMENT_SIZE;
+
+        xprt->bind_timeout = XS_BIND_TO;
+        xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO;
+        xprt->idle_timeout = XS_IDLE_DISC_TO;
+
+        xprt->ops = &xs_local_ops;
+        xprt->timeout = &xs_local_default_timeout;
+
+        switch (sun->sun_family) {
+        case AF_LOCAL:
+                if (sun->sun_path[0] != '/') {
+                        dprintk("RPC:       bad AF_LOCAL address: %s\n",
+                                        sun->sun_path);
+                        ret = ERR_PTR(-EINVAL);
+                        goto out_err;
+                }
+                xprt_set_bound(xprt);
+                INIT_DELAYED_WORK(&transport->connect_worker,
+                                        xs_local_setup_socket);
+                xs_format_peer_addresses(xprt, "local", RPCBIND_NETID_LOCAL);
+                break;
+        default:
+                ret = ERR_PTR(-EAFNOSUPPORT);
+                goto out_err;
+        }
+
+        dprintk("RPC:       set up xprt to %s via AF_LOCAL\n",
+                        xprt->address_strings[RPC_DISPLAY_ADDR]);
+
+        if (try_module_get(THIS_MODULE))
+                return xprt;
+        ret = ERR_PTR(-EINVAL);
+out_err:
+        xprt_free(xprt);
+        return ret;
+}
+
 static const struct rpc_timeout xs_udp_default_timeout = {
         .to_initval = 5 * HZ,
         .to_maxval = 30 * HZ,
@@ -2438,6 +2827,14 @@ out_err:
         return ret;
 }
 
+static struct xprt_class        xs_local_transport = {
+        .list           = LIST_HEAD_INIT(xs_local_transport.list),
+        .name           = "named UNIX socket",
+        .owner          = THIS_MODULE,
+        .ident          = XPRT_TRANSPORT_LOCAL,
+        .setup          = xs_setup_local,
+};
+
 static struct xprt_class        xs_udp_transport = {
         .list           = LIST_HEAD_INIT(xs_udp_transport.list),
         .name           = "udp",
@@ -2473,6 +2870,7 @@ int init_socket_xprt(void)
                 sunrpc_table_header = register_sysctl_table(sunrpc_table);
 #endif
 
+        xprt_register_transport(&xs_local_transport);
         xprt_register_transport(&xs_udp_transport);
         xprt_register_transport(&xs_tcp_transport);
         xprt_register_transport(&xs_bc_tcp_transport);
@@ -2493,6 +2891,7 @@ void cleanup_socket_xprt(void)
         }
 #endif
 
+        xprt_unregister_transport(&xs_local_transport);
         xprt_unregister_transport(&xs_udp_transport);
         xprt_unregister_transport(&xs_tcp_transport);
         xprt_unregister_transport(&xs_bc_tcp_transport);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index ec83f413a7ed..88a565f130a5 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -3406,12 +3406,12 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info)
         i = 0;
         if (info->attrs[NL80211_ATTR_SCAN_SSIDS]) {
                 nla_for_each_nested(attr, info->attrs[NL80211_ATTR_SCAN_SSIDS], tmp) {
+                        request->ssids[i].ssid_len = nla_len(attr);
                         if (request->ssids[i].ssid_len > IEEE80211_MAX_SSID_LEN) {
                                 err = -EINVAL;
                                 goto out_free;
                         }
                         memcpy(request->ssids[i].ssid, nla_data(attr), nla_len(attr));
-                        request->ssids[i].ssid_len = nla_len(attr);
                         i++;
                 }
         }
@@ -3572,6 +3572,7 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
         if (info->attrs[NL80211_ATTR_SCAN_SSIDS]) {
                 nla_for_each_nested(attr, info->attrs[NL80211_ATTR_SCAN_SSIDS],
                                     tmp) {
+                        request->ssids[i].ssid_len = nla_len(attr);
                         if (request->ssids[i].ssid_len >
                             IEEE80211_MAX_SSID_LEN) {
                                 err = -EINVAL;
@@ -3579,7 +3580,6 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
                         }
                         memcpy(request->ssids[i].ssid, nla_data(attr),
                                nla_len(attr));
-                        request->ssids[i].ssid_len = nla_len(attr);
                         i++;
                 }
         }
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 73a441d237b5..7a6c67667d70 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -267,13 +267,35 @@ static bool is_bss(struct cfg80211_bss *a,
         return memcmp(ssidie + 2, ssid, ssid_len) == 0;
 }
 
+static bool is_mesh_bss(struct cfg80211_bss *a)
+{
+        const u8 *ie;
+
+        if (!WLAN_CAPABILITY_IS_STA_BSS(a->capability))
+                return false;
+
+        ie = cfg80211_find_ie(WLAN_EID_MESH_ID,
+                              a->information_elements,
+                              a->len_information_elements);
+        if (!ie)
+                return false;
+
+        ie = cfg80211_find_ie(WLAN_EID_MESH_CONFIG,
+                              a->information_elements,
+                              a->len_information_elements);
+        if (!ie)
+                return false;
+
+        return true;
+}
+
 static bool is_mesh(struct cfg80211_bss *a,
                     const u8 *meshid, size_t meshidlen,
                     const u8 *meshcfg)
 {
         const u8 *ie;
 
-        if (!WLAN_CAPABILITY_IS_MBSS(a->capability))
+        if (!WLAN_CAPABILITY_IS_STA_BSS(a->capability))
                 return false;
 
         ie = cfg80211_find_ie(WLAN_EID_MESH_ID,
@@ -311,7 +333,7 @@ static int cmp_bss(struct cfg80211_bss *a,
         if (a->channel != b->channel)
                 return b->channel->center_freq - a->channel->center_freq;
 
-        if (WLAN_CAPABILITY_IS_MBSS(a->capability | b->capability)) {
+        if (is_mesh_bss(a) && is_mesh_bss(b)) {
                 r = cmp_ies(WLAN_EID_MESH_ID,
                             a->information_elements,
                             a->len_information_elements,
@@ -457,7 +479,6 @@ cfg80211_bss_update(struct cfg80211_registered_device *dev,
                     struct cfg80211_internal_bss *res)
 {
         struct cfg80211_internal_bss *found = NULL;
-        const u8 *meshid, *meshcfg;
 
         /*
          * The reference to "res" is donated to this function.
@@ -470,22 +491,6 @@ cfg80211_bss_update(struct cfg80211_registered_device *dev,
 
         res->ts = jiffies;
 
-        if (WLAN_CAPABILITY_IS_MBSS(res->pub.capability)) {
-                /* must be mesh, verify */
-                meshid = cfg80211_find_ie(WLAN_EID_MESH_ID,
-                                          res->pub.information_elements,
-                                          res->pub.len_information_elements);
-                meshcfg = cfg80211_find_ie(WLAN_EID_MESH_CONFIG,
-                                           res->pub.information_elements,
-                                           res->pub.len_information_elements);
-                if (!meshid || !meshcfg ||
-                    meshcfg[1] != sizeof(struct ieee80211_meshconf_ie)) {
-                        /* bogus mesh */
-                        kref_put(&res->ref, bss_release);
-                        return NULL;
-                }
-        }
-
         spin_lock_bh(&dev->bss_lock);
 
         found = rb_find_bss(dev, res);
diff --git a/scripts/recordmcount.h b/scripts/recordmcount.h
index 4be60364a405..f40a6af6bf40 100644
--- a/scripts/recordmcount.h
+++ b/scripts/recordmcount.h
@@ -43,6 +43,7 @@
 #undef ELF_R_INFO
 #undef Elf_r_info
 #undef ELF_ST_BIND
+#undef ELF_ST_TYPE
 #undef fn_ELF_R_SYM
 #undef fn_ELF_R_INFO
 #undef uint_t
@@ -76,6 +77,7 @@
 # define ELF_R_INFO             ELF64_R_INFO
 # define Elf_r_info             Elf64_r_info
 # define ELF_ST_BIND            ELF64_ST_BIND
+# define ELF_ST_TYPE            ELF64_ST_TYPE
 # define fn_ELF_R_SYM           fn_ELF64_R_SYM
 # define fn_ELF_R_INFO          fn_ELF64_R_INFO
 # define uint_t                 uint64_t
@@ -108,6 +110,7 @@
 # define ELF_R_INFO             ELF32_R_INFO
 # define Elf_r_info             Elf32_r_info
 # define ELF_ST_BIND            ELF32_ST_BIND
+# define ELF_ST_TYPE            ELF32_ST_TYPE
 # define fn_ELF_R_SYM           fn_ELF32_R_SYM
 # define fn_ELF_R_INFO          fn_ELF32_R_INFO
 # define uint_t                 uint32_t
@@ -427,6 +430,11 @@ static unsigned find_secsym_ndx(unsigned const txtndx,
                 if (txtndx == w2(symp->st_shndx)
                         /* avoid STB_WEAK */
                     && (STB_LOCAL == st_bind || STB_GLOBAL == st_bind)) {
+                        /* function symbols on ARM have quirks, avoid them */
+                        if (w2(ehdr->e_machine) == EM_ARM
+                            && ELF_ST_TYPE(symp->st_info) == STT_FUNC)
+                                continue;
+
                         *recvalp = _w(symp->st_value);
                         return symp - sym0;
                 }
diff --git a/scripts/tags.sh b/scripts/tags.sh
index bd6185d529cf..75c5d24f1993 100755
--- a/scripts/tags.sh
+++ b/scripts/tags.sh
@@ -132,7 +132,7 @@ exuberant()
         --regex-asm='/^ENTRY\(([^)]*)\).*/\1/'                  \
         --regex-c='/^SYSCALL_DEFINE[[:digit:]]?\(([^,)]*).*/sys_\1/' \
         --regex-c++='/^TRACE_EVENT\(([^,)]*).*/trace_\1/'               \
-        --regex-c++='/^DEFINE_EVENT\(([^,)]*).*/trace_\1/'
+        --regex-c++='/^DEFINE_EVENT\([^,)]*, *([^,)]*).*/trace_\1/'
 
         all_kconfigs | xargs $1 -a                              \
         --langdef=kconfig --language-force=kconfig              \
@@ -152,7 +152,9 @@ emacs()
 {
         all_sources | xargs $1 -a                               \
         --regex='/^ENTRY(\([^)]*\)).*/\1/'                      \
-        --regex='/^SYSCALL_DEFINE[0-9]?(\([^,)]*\).*/sys_\1/'
+        --regex='/^SYSCALL_DEFINE[0-9]?(\([^,)]*\).*/sys_\1/'   \
+        --regex='/^TRACE_EVENT(\([^,)]*\).*/trace_\1/'          \
+        --regex='/^DEFINE_EVENT([^,)]*, *\([^,)]*\).*/trace_\1/'
 
         all_kconfigs | xargs $1 -a                              \
         --regex='/^[ \t]*\(\(menu\)*config\)[ \t]+\([a-zA-Z0-9_]+\)/\3/'
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index ae3a698415e6..ec1bcecf2cda 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -593,7 +593,8 @@ static int apparmor_setprocattr(struct task_struct *task, char *name,
                         sa.aad.op = OP_SETPROCATTR;
                         sa.aad.info = name;
                         sa.aad.error = -EINVAL;
-                        return aa_audit(AUDIT_APPARMOR_DENIED, NULL, GFP_KERNEL,
+                        return aa_audit(AUDIT_APPARMOR_DENIED,
+                                        __aa_current_profile(), GFP_KERNEL,
                                         &sa, NULL);
                 }
         } else if (strcmp(name, "exec") == 0) {
diff --git a/sound/pci/asihpi/hpidspcd.c b/sound/pci/asihpi/hpidspcd.c
index fb311d8c05bf..5c6ea113d219 100644
--- a/sound/pci/asihpi/hpidspcd.c
+++ b/sound/pci/asihpi/hpidspcd.c
@@ -60,7 +60,7 @@ struct code_header {
             HPI_VER_MINOR(HPI_VER) * 100 + HPI_VER_RELEASE(HPI_VER)))
 
 /***********************************************************************/
-#include "linux/pci.h"
+#include <linux/pci.h>
 /*-------------------------------------------------------------------*/
 short hpi_dsp_code_open(u32 adapter, struct dsp_code *ps_dsp_code,
         u32 *pos_error_code)
diff --git a/sound/pci/fm801.c b/sound/pci/fm801.c
index eacd4901a308..a7ec7030cf87 100644
--- a/sound/pci/fm801.c
+++ b/sound/pci/fm801.c
@@ -1234,9 +1234,12 @@ static int __devinit snd_fm801_create(struct snd_card *card,
         sprintf(chip->tea.bus_info, "PCI:%s", pci_name(pci));
         if ((tea575x_tuner & TUNER_TYPE_MASK) > 0 &&
             (tea575x_tuner & TUNER_TYPE_MASK) < 4) {
-                if (snd_tea575x_init(&chip->tea))
+                if (snd_tea575x_init(&chip->tea)) {
                         snd_printk(KERN_ERR "TEA575x radio not found\n");
-        } else if ((tea575x_tuner & TUNER_TYPE_MASK) == 0)
+                        snd_fm801_free(chip);
+                        return -ENODEV;
+                }
+        } else if ((tea575x_tuner & TUNER_TYPE_MASK) == 0) {
                 /* autodetect tuner connection */
                 for (tea575x_tuner = 1; tea575x_tuner <= 3; tea575x_tuner++) {
                         chip->tea575x_tuner = tea575x_tuner;
@@ -1246,6 +1249,12 @@ static int __devinit snd_fm801_create(struct snd_card *card,
                                 break;
                         }
                 }
+                if (tea575x_tuner == 4) {
+                        snd_printk(KERN_ERR "TEA575x radio not found\n");
+                        snd_fm801_free(chip);
+                        return -ENODEV;
+                }
+        }
         strlcpy(chip->tea.card, snd_fm801_tea575x_gpios[(tea575x_tuner & TUNER_TYPE_MASK) - 1].name, sizeof(chip->tea.card));
 #endif
 
diff --git a/sound/pci/hda/patch_analog.c b/sound/pci/hda/patch_analog.c
index 696ac2590307..d694e9d4921d 100644
--- a/sound/pci/hda/patch_analog.c
+++ b/sound/pci/hda/patch_analog.c
@@ -506,9 +506,11 @@ static void ad198x_power_eapd_write(struct hda_codec *codec, hda_nid_t front,
                                 hda_nid_t hp)
 {
         struct ad198x_spec *spec = codec->spec;
-        snd_hda_codec_write(codec, front, 0, AC_VERB_SET_EAPD_BTLENABLE,
+        if (snd_hda_query_pin_caps(codec, front) & AC_PINCAP_EAPD)
+                snd_hda_codec_write(codec, front, 0, AC_VERB_SET_EAPD_BTLENABLE,
                             !spec->inv_eapd ? 0x00 : 0x02);
-        snd_hda_codec_write(codec, hp, 0, AC_VERB_SET_EAPD_BTLENABLE,
+        if (snd_hda_query_pin_caps(codec, hp) & AC_PINCAP_EAPD)
+                snd_hda_codec_write(codec, hp, 0, AC_VERB_SET_EAPD_BTLENABLE,
                             !spec->inv_eapd ? 0x00 : 0x02);
 }
 
@@ -524,6 +526,10 @@ static void ad198x_power_eapd(struct hda_codec *codec)
         case 0x11d4184a:
         case 0x11d4194a:
         case 0x11d4194b:
+        case 0x11d41988:
+        case 0x11d4198b:
+        case 0x11d4989a:
+        case 0x11d4989b:
                 ad198x_power_eapd_write(codec, 0x12, 0x11);
                 break;
         case 0x11d41981:
@@ -533,12 +539,6 @@ static void ad198x_power_eapd(struct hda_codec *codec)
         case 0x11d41986:
                 ad198x_power_eapd_write(codec, 0x1b, 0x1a);
                 break;
-        case 0x11d41988:
-        case 0x11d4198b:
-        case 0x11d4989a:
-        case 0x11d4989b:
-                ad198x_power_eapd_write(codec, 0x29, 0x22);
-                break;
         }
 }
 
diff --git a/sound/soc/codecs/cx20442.c b/sound/soc/codecs/cx20442.c
index f8c663dcff02..d68ea532cc7f 100644
--- a/sound/soc/codecs/cx20442.c
+++ b/sound/soc/codecs/cx20442.c
@@ -262,14 +262,14 @@ static int v253_hangup(struct tty_struct *tty)
 }
 
 /* Line discipline .receive_buf() */
-static unsigned int v253_receive(struct tty_struct *tty,
-                                 const unsigned char *cp, char *fp, int count)
+static void v253_receive(struct tty_struct *tty,
+                                const unsigned char *cp, char *fp, int count)
 {
         struct snd_soc_codec *codec = tty->disc_data;
         struct cx20442_priv *cx20442;
 
         if (!codec)
-                return count;
+                return;
 
         cx20442 = snd_soc_codec_get_drvdata(codec);
 
@@ -281,8 +281,6 @@ static unsigned int v253_receive(struct tty_struct *tty,
                 codec->hw_write = (hw_write_t)tty->ops->write;
                 codec->card->pop_time = 1;
         }
-
-        return count;
 }
 
 /* Line discipline .write_wakeup() */
diff --git a/sound/soc/codecs/wm_hubs.c b/sound/soc/codecs/wm_hubs.c
index e55b298c14a0..9e370d14ad88 100644
--- a/sound/soc/codecs/wm_hubs.c
+++ b/sound/soc/codecs/wm_hubs.c
@@ -215,23 +215,23 @@ static const struct snd_kcontrol_new analogue_snd_controls[] = {
 SOC_SINGLE_TLV("IN1L Volume", WM8993_LEFT_LINE_INPUT_1_2_VOLUME, 0, 31, 0,
                inpga_tlv),
 SOC_SINGLE("IN1L Switch", WM8993_LEFT_LINE_INPUT_1_2_VOLUME, 7, 1, 1),
-SOC_SINGLE("IN1L ZC Switch", WM8993_LEFT_LINE_INPUT_1_2_VOLUME, 7, 1, 0),
+SOC_SINGLE("IN1L ZC Switch", WM8993_LEFT_LINE_INPUT_1_2_VOLUME, 6, 1, 0),
 
 SOC_SINGLE_TLV("IN1R Volume", WM8993_RIGHT_LINE_INPUT_1_2_VOLUME, 0, 31, 0,
                inpga_tlv),
 SOC_SINGLE("IN1R Switch", WM8993_RIGHT_LINE_INPUT_1_2_VOLUME, 7, 1, 1),
-SOC_SINGLE("IN1R ZC Switch", WM8993_RIGHT_LINE_INPUT_1_2_VOLUME, 7, 1, 0),
+SOC_SINGLE("IN1R ZC Switch", WM8993_RIGHT_LINE_INPUT_1_2_VOLUME, 6, 1, 0),
 
 
 SOC_SINGLE_TLV("IN2L Volume", WM8993_LEFT_LINE_INPUT_3_4_VOLUME, 0, 31, 0,
                inpga_tlv),
 SOC_SINGLE("IN2L Switch", WM8993_LEFT_LINE_INPUT_3_4_VOLUME, 7, 1, 1),
-SOC_SINGLE("IN2L ZC Switch", WM8993_LEFT_LINE_INPUT_3_4_VOLUME, 7, 1, 0),
+SOC_SINGLE("IN2L ZC Switch", WM8993_LEFT_LINE_INPUT_3_4_VOLUME, 6, 1, 0),
 
 SOC_SINGLE_TLV("IN2R Volume", WM8993_RIGHT_LINE_INPUT_3_4_VOLUME, 0, 31, 0,
                inpga_tlv),
 SOC_SINGLE("IN2R Switch", WM8993_RIGHT_LINE_INPUT_3_4_VOLUME, 7, 1, 1),
-SOC_SINGLE("IN2R ZC Switch", WM8993_RIGHT_LINE_INPUT_3_4_VOLUME, 7, 1, 0),
+SOC_SINGLE("IN2R ZC Switch", WM8993_RIGHT_LINE_INPUT_3_4_VOLUME, 6, 1, 0),
 
 SOC_SINGLE_TLV("MIXINL IN2L Volume", WM8993_INPUT_MIXER3, 7, 1, 0,
                inmix_sw_tlv),
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 999bb08cdfb1..776e6f418306 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -325,6 +325,7 @@ static int dapm_connect_mixer(struct snd_soc_dapm_context *dapm,
 }
 
 static int dapm_is_shared_kcontrol(struct snd_soc_dapm_context *dapm,
+        struct snd_soc_dapm_widget *kcontrolw,
         const struct snd_kcontrol_new *kcontrol_new,
         struct snd_kcontrol **kcontrol)
 {
@@ -334,6 +335,8 @@ static int dapm_is_shared_kcontrol(struct snd_soc_dapm_context *dapm,
         *kcontrol = NULL;
 
         list_for_each_entry(w, &dapm->card->widgets, list) {
+                if (w == kcontrolw || w->dapm != kcontrolw->dapm)
+                        continue;
                 for (i = 0; i < w->num_kcontrols; i++) {
                         if (&w->kcontrol_news[i] == kcontrol_new) {
                                 if (w->kcontrols)
@@ -468,7 +471,7 @@ static int dapm_new_mux(struct snd_soc_dapm_context *dapm,
                 return -EINVAL;
         }
 
-        shared = dapm_is_shared_kcontrol(dapm, &w->kcontrol_news[0],
+        shared = dapm_is_shared_kcontrol(dapm, w, &w->kcontrol_news[0],
                                          &kcontrol);
         if (kcontrol) {
                 wlist = kcontrol->private_data;
diff --git a/sound/usb/6fire/firmware.c b/sound/usb/6fire/firmware.c
index d47beffedb0f..a91719d5918b 100644
--- a/sound/usb/6fire/firmware.c
+++ b/sound/usb/6fire/firmware.c
@@ -227,6 +227,7 @@ static int usb6fire_fw_ezusb_upload(
         ret = usb6fire_fw_ihex_init(fw, rec);
         if (ret < 0) {
                 kfree(rec);
+                release_firmware(fw);
                 snd_printk(KERN_ERR PREFIX "error validating ezusb "
                                 "firmware %s.\n", fwname);
                 return ret;
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 2e969cbb393b..090e1930dfdc 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -403,7 +403,7 @@ static int snd_usb_cm106_boot_quirk(struct usb_device *dev)
 static int snd_usb_cm6206_boot_quirk(struct usb_device *dev)
 {
         int err, reg;
-        int val[] = {0x200c, 0x3000, 0xf800, 0x143f, 0x0000, 0x3000};
+        int val[] = {0x2004, 0x3000, 0xf800, 0x143f, 0x0000, 0x3000};
 
         for (reg = 0; reg < ARRAY_SIZE(val); reg++) {
                 err = snd_usb_cm106_write_int_reg(dev, reg, val[reg]);
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 1455413ec7a7..032ba6398a5c 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -215,11 +215,13 @@ LIB_FILE=$(OUTPUT)libperf.a
 LIB_H += ../../include/linux/perf_event.h
 LIB_H += ../../include/linux/rbtree.h
 LIB_H += ../../include/linux/list.h
+LIB_H += ../../include/linux/const.h
 LIB_H += ../../include/linux/hash.h
 LIB_H += ../../include/linux/stringify.h
 LIB_H += util/include/linux/bitmap.h
 LIB_H += util/include/linux/bitops.h
 LIB_H += util/include/linux/compiler.h
+LIB_H += util/include/linux/const.h
 LIB_H += util/include/linux/ctype.h
 LIB_H += util/include/linux/kernel.h
 LIB_H += util/include/linux/list.h
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index e18eb7ed30ae..7b139e1e7e86 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -8,8 +8,6 @@
 #include "builtin.h"
 
 #include "util/util.h"
-
-#include "util/util.h"
 #include "util/color.h"
 #include <linux/list.h>
 #include "util/cache.h"
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 0974f957b8fa..8e2c85798185 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -823,6 +823,16 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
 
         symbol__init();
 
+        if (symbol_conf.kptr_restrict)
+                pr_warning(
+"WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n"
+"check /proc/sys/kernel/kptr_restrict.\n\n"
+"Samples in kernel functions may not be resolved if a suitable vmlinux\n"
+"file is not found in the buildid cache or in the vmlinux path.\n\n"
+"Samples in kernel modules won't be resolved at all.\n\n"
+"If some relocation was applied (e.g. kexec) symbols may be misresolved\n"
+"even with a suitable vmlinux or kallsyms file.\n\n");
+
         if (no_buildid_cache || no_buildid)
                 disable_buildid_cache();
 
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 498c6f70a747..287a173523a7 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -116,6 +116,9 @@ static int process_sample_event(union perf_event *event,
         if (al.filtered || (hide_unresolved && al.sym == NULL))
                 return 0;
 
+        if (al.map != NULL)
+                al.map->dso->hit = 1;
+
         if (perf_session__add_hist_entry(session, &al, sample, evsel)) {
                 pr_debug("problem incrementing symbol period, skipping event\n");
                 return -1;
@@ -249,6 +252,8 @@ static int __cmd_report(void)
         u64 nr_samples;
         struct perf_session *session;
         struct perf_evsel *pos;
+        struct map *kernel_map;
+        struct kmap *kernel_kmap;
         const char *help = "For a higher level overview, try: perf report --sort comm,dso";
 
         signal(SIGINT, sig_handler);
@@ -268,6 +273,24 @@ static int __cmd_report(void)
         if (ret)
                 goto out_delete;
 
+        kernel_map = session->host_machine.vmlinux_maps[MAP__FUNCTION];
+        kernel_kmap = map__kmap(kernel_map);
+        if (kernel_map == NULL ||
+            (kernel_map->dso->hit &&
+             (kernel_kmap->ref_reloc_sym == NULL ||
+              kernel_kmap->ref_reloc_sym->addr == 0))) {
+                const struct dso *kdso = kernel_map->dso;
+
+                ui__warning(
+"Kernel address maps (/proc/{kallsyms,modules}) were restricted.\n\n"
+"Check /proc/sys/kernel/kptr_restrict before running 'perf record'.\n\n%s\n\n"
+"Samples in kernel modules can't be resolved as well.\n\n",
+                            RB_EMPTY_ROOT(&kdso->symbols[MAP__FUNCTION]) ?
+"As no suitable kallsyms nor vmlinux was found, kernel samples\n"
+"can't be resolved." :
+"If some relocation was applied (e.g. kexec) symbols may be misresolved.");
+        }
+
         if (dump_trace) {
                 perf_session__fprintf_nr_events(session, stdout);
                 goto out_delete;
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 974f6d3f4e53..22747de7234b 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -10,7 +10,6 @@
 #include "util/symbol.h"
 #include "util/thread.h"
 #include "util/trace-event.h"
-#include "util/parse-options.h"
 #include "util/util.h"
 #include "util/evlist.h"
 #include "util/evsel.h"
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 2d7934e9de38..f2f3f4937aa2 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -62,8 +62,6 @@
 #include <linux/unistd.h>
 #include <linux/types.h>
 
-#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
-
 static struct perf_top top = {
         .count_filter           = 5,
         .delay_secs             = 2,
@@ -82,6 +80,8 @@ static bool			use_tui, use_stdio;
 
 static int                      default_interval                =      0;
 
+static bool                     kptr_restrict_warned;
+static bool                     vmlinux_warned;
 static bool                     inherit                         =  false;
 static int                      realtime_prio                   =      0;
 static bool                     group                           =  false;
@@ -740,7 +740,22 @@ static void perf_event__process_sample(const union perf_event *event,
             al.filtered)
                 return;
 
+        if (!kptr_restrict_warned &&
+            symbol_conf.kptr_restrict &&
+            al.cpumode == PERF_RECORD_MISC_KERNEL) {
+                ui__warning(
+"Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n"
+"Check /proc/sys/kernel/kptr_restrict.\n\n"
+"Kernel%s samples will not be resolved.\n",
+                          !RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION]) ?
+                          " modules" : "");
+                if (use_browser <= 0)
+                        sleep(5);
+                kptr_restrict_warned = true;
+        }
+
         if (al.sym == NULL) {
+                const char *msg = "Kernel samples will not be resolved.\n";
                 /*
                  * As we do lazy loading of symtabs we only will know if the
                  * specified vmlinux file is invalid when we actually have a
@@ -752,12 +767,20 @@ static void perf_event__process_sample(const union perf_event *event,
                  * --hide-kernel-symbols, even if the user specifies an
                  * invalid --vmlinux ;-)
                  */
-                if (al.map == machine->vmlinux_maps[MAP__FUNCTION] &&
+                if (!kptr_restrict_warned && !vmlinux_warned &&
+                    al.map == machine->vmlinux_maps[MAP__FUNCTION] &&
                     RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION])) {
-                        ui__warning("The %s file can't be used\n",
-                                    symbol_conf.vmlinux_name);
-                        exit_browser(0);
-                        exit(1);
+                        if (symbol_conf.vmlinux_name) {
+                                ui__warning("The %s file can't be used.\n%s",
+                                            symbol_conf.vmlinux_name, msg);
+                        } else {
+                                ui__warning("A vmlinux file was not found.\n%s",
+                                            msg);
+                        }
+
+                        if (use_browser <= 0)
+                                sleep(5);
+                        vmlinux_warned = true;
                 }
 
                 return;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 6635fcd11ca5..0fe9adf76379 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -553,9 +553,18 @@ static int perf_event__process_kernel_mmap(union perf_event *event,
                         goto out_problem;
 
                 perf_event__set_kernel_mmap_len(event, machine->vmlinux_maps);
-                perf_session__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps,
-                                                         symbol_name,
-                                                         event->mmap.pgoff);
+
+                /*
+                 * Avoid using a zero address (kptr_restrict) for the ref reloc
+                 * symbol. Effectively having zero here means that at record
+                 * time /proc/sys/kernel/kptr_restrict was non zero.
+                 */
+                if (event->mmap.pgoff != 0) {
+                        perf_session__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps,
+                                                                 symbol_name,
+                                                                 event->mmap.pgoff);
+                }
+
                 if (machine__is_default_guest(machine)) {
                         /*
                          * preload dso of guest kernel and modules
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index ee0fe0dffa71..cca29ededb5b 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -35,7 +35,17 @@ struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx)
 
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
+        int cpu, thread;
         evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int));
+
+        if (evsel->fd) {
+                for (cpu = 0; cpu < ncpus; cpu++) {
+                        for (thread = 0; thread < nthreads; thread++) {
+                                FD(evsel, cpu, thread) = -1;
+                        }
+                }
+        }
+
         return evsel->fd != NULL ? 0 : -ENOMEM;
 }
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 0717bebc7649..afb0849fe530 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -193,9 +193,13 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
              *linkname = malloc(size), *targetname;
         int len, err = -1;
 
-        if (is_kallsyms)
+        if (is_kallsyms) {
+                if (symbol_conf.kptr_restrict) {
+                        pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n");
+                        return 0;
+                }
                 realname = (char *)name;
-        else
+        } else
                 realname = realpath(name, NULL);
 
         if (realname == NULL || filename == NULL || linkname == NULL)
diff --git a/tools/perf/util/include/linux/const.h b/tools/perf/util/include/linux/const.h
new file mode 100644
index 000000000000..1b476c9ae649
--- /dev/null
+++ b/tools/perf/util/include/linux/const.h
@@ -0,0 +1 @@
+#include "../../../../include/linux/const.h"
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 516876dfbe52..eec196329fd9 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -676,9 +676,30 @@ discard_symbol:		rb_erase(&pos->rb_node, root);
         return count + moved;
 }
 
+static bool symbol__restricted_filename(const char *filename,
+                                        const char *restricted_filename)
+{
+        bool restricted = false;
+
+        if (symbol_conf.kptr_restrict) {
+                char *r = realpath(filename, NULL);
+
+                if (r != NULL) {
+                        restricted = strcmp(r, restricted_filename) == 0;
+                        free(r);
+                        return restricted;
+                }
+        }
+
+        return restricted;
+}
+
 int dso__load_kallsyms(struct dso *dso, const char *filename,
                        struct map *map, symbol_filter_t filter)
 {
+        if (symbol__restricted_filename(filename, "/proc/kallsyms"))
+                return -1;
+
         if (dso__load_all_kallsyms(dso, filename, map) < 0)
                 return -1;
 
@@ -1790,6 +1811,9 @@ static int machine__create_modules(struct machine *machine)
                 modules = path;
         }
 
+        if (symbol__restricted_filename(path, "/proc/modules"))
+                return -1;
+
         file = fopen(modules, "r");
         if (file == NULL)
                 return -1;
@@ -2239,6 +2263,9 @@ static u64 machine__get_kernel_start_addr(struct machine *machine)
                 }
         }
 
+        if (symbol__restricted_filename(filename, "/proc/kallsyms"))
+                return 0;
+
         if (kallsyms__parse(filename, &args, symbol__in_kernel) <= 0)
                 return 0;
 
@@ -2410,6 +2437,25 @@ static int setup_list(struct strlist **list, const char *list_str,
         return 0;
 }
 
+static bool symbol__read_kptr_restrict(void)
+{
+        bool value = false;
+
+        if (geteuid() != 0) {
+                FILE *fp = fopen("/proc/sys/kernel/kptr_restrict", "r");
+                if (fp != NULL) {
+                        char line[8];
+
+                        if (fgets(line, sizeof(line), fp) != NULL)
+                                value = atoi(line) != 0;
+
+                        fclose(fp);
+                }
+        }
+
+        return value;
+}
+
 int symbol__init(void)
 {
         const char *symfs;
@@ -2456,6 +2502,8 @@ int symbol__init(void)
         if (symfs != symbol_conf.symfs)
                 free((void *)symfs);
 
+        symbol_conf.kptr_restrict = symbol__read_kptr_restrict();
+
         symbol_conf.initialized = true;
         return 0;
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 242de0101a86..325ee36a9d29 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -75,7 +75,8 @@ struct symbol_conf {
                         use_callchain,
                         exclude_other,
                         show_cpu_utilization,
-                        initialized;
+                        initialized,
+                        kptr_restrict;
         const char      *vmlinux_name,
                         *kallsyms_name,
                         *source_prefix,
diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index 1fd29b2daa92..cef28e6632b9 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -788,7 +788,7 @@ sub wait_for_input
 
 sub reboot_to {
     if ($reboot_type eq "grub") {
-        run_ssh "'(echo \"savedefault --default=$grub_number --once\" | grub --batch; reboot)'";
+        run_ssh "'(echo \"savedefault --default=$grub_number --once\" | grub --batch && reboot)'";
         return;
     }
 
@@ -1480,7 +1480,7 @@ sub process_config_ignore {
         or dodie "Failed to read $config";
 
     while (<IN>) {
-        if (/^(.*?(CONFIG\S*)(=.*| is not set))/) {
+        if (/^((CONFIG\S*)=.*)/) {
             $config_ignore{$2} = $1;
         }
     }
@@ -1638,7 +1638,7 @@ sub run_config_bisect {
         if (!$found) {
             # try the other half
             doprint "Top half produced no set configs, trying bottom half\n";
-            @tophalf = @start_list[$half .. $#start_list];
+            @tophalf = @start_list[$half + 1 .. $#start_list];
             create_config @tophalf;
             read_current_config \%current_config;
             foreach my $config (@tophalf) {
@@ -1690,7 +1690,7 @@ sub run_config_bisect {
         # remove half the configs we are looking at and see if
         # they are good.
         $half = int($#start_list / 2);
-    } while ($half > 0);
+    } while ($#start_list > 0);
 
     # we found a single config, try it again unless we are running manually
 
diff --git a/tools/virtio/virtio_test.c b/tools/virtio/virtio_test.c
index df0c6d2c3860..74d3331bdaf9 100644
--- a/tools/virtio/virtio_test.c
+++ b/tools/virtio/virtio_test.c
@@ -198,6 +198,14 @@ const struct option longopts[] = {
                 .val = 'h',
         },
         {
+                .name = "event-idx",
+                .val = 'E',
+        },
+        {
+                .name = "no-event-idx",
+                .val = 'e',
+        },
+        {
                 .name = "indirect",
                 .val = 'I',
         },
@@ -211,13 +219,17 @@ const struct option longopts[] = {
 
 static void help()
 {
-        fprintf(stderr, "Usage: virtio_test [--help] [--no-indirect]\n");
+        fprintf(stderr, "Usage: virtio_test [--help]"
+                " [--no-indirect]"
+                " [--no-event-idx]"
+                "\n");
 }
 
 int main(int argc, char **argv)
 {
         struct vdev_info dev;
-        unsigned long long features = 1ULL << VIRTIO_RING_F_INDIRECT_DESC;
+        unsigned long long features = (1ULL << VIRTIO_RING_F_INDIRECT_DESC) |
+                (1ULL << VIRTIO_RING_F_EVENT_IDX);
         int o;
 
         for (;;) {
@@ -228,6 +240,9 @@ int main(int argc, char **argv)
                 case '?':
                         help();
                         exit(2);
+                case 'e':
+                        features &= ~(1ULL << VIRTIO_RING_F_EVENT_IDX);
+                        break;
                 case 'h':
                         help();
                         goto done;