465 files changed, 16810 insertions, 10045 deletions

diff --git a/Documentation/DocBook/genericirq.tmpl b/Documentation/DocBook/genericirq.tmpl
index 1448b33fd222..fb10fd08c05c 100644
--- a/Documentation/DocBook/genericirq.tmpl
+++ b/Documentation/DocBook/genericirq.tmpl
@@ -28,7 +28,7 @@
   </authorgroup>
 
   <copyright>
-   <year>2005-2006</year>
+   <year>2005-2010</year>
    <holder>Thomas Gleixner</holder>
   </copyright>
   <copyright>
@@ -100,6 +100,10 @@
           <listitem><para>Edge type</para></listitem>
           <listitem><para>Simple type</para></listitem>
         </itemizedlist>
+        During the implementation we identified another type:
+        <itemizedlist>
+          <listitem><para>Fast EOI type</para></listitem>
+        </itemizedlist>
         In the SMP world of the __do_IRQ() super-handler another type
         was identified:
         <itemizedlist>
@@ -153,6 +157,7 @@
         is still available. This leads to a kind of duality for the time
         being. Over time the new model should be used in more and more
         architectures, as it enables smaller and cleaner IRQ subsystems.
+        It's deprecated for three years now and about to be removed.
         </para>
   </chapter>
   <chapter id="bugs">
@@ -217,6 +222,7 @@
           <itemizedlist>
           <listitem><para>handle_level_irq</para></listitem>
           <listitem><para>handle_edge_irq</para></listitem>
+          <listitem><para>handle_fasteoi_irq</para></listitem>
           <listitem><para>handle_simple_irq</para></listitem>
           <listitem><para>handle_percpu_irq</para></listitem>
           </itemizedlist>
@@ -233,33 +239,33 @@
                 are used by the default flow implementations.
                 The following helper functions are implemented (simplified excerpt):
                 <programlisting>
-default_enable(irq)
+default_enable(struct irq_data *data)
 {
-        desc->chip->unmask(irq);
+        desc->chip->irq_unmask(data);
 }
 
-default_disable(irq)
+default_disable(struct irq_data *data)
 {
-        if (!delay_disable(irq))
-                desc->chip->mask(irq);
+        if (!delay_disable(data))
+                desc->chip->irq_mask(data);
 }
 
-default_ack(irq)
+default_ack(struct irq_data *data)
 {
-        chip->ack(irq);
+        chip->irq_ack(data);
 }
 
-default_mask_ack(irq)
+default_mask_ack(struct irq_data *data)
 {
-        if (chip->mask_ack) {
-                chip->mask_ack(irq);
+        if (chip->irq_mask_ack) {
+                chip->irq_mask_ack(data);
         } else {
-                chip->mask(irq);
-                chip->ack(irq);
+                chip->irq_mask(data);
+                chip->irq_ack(data);
         }
 }
 
-noop(irq)
+noop(struct irq_data *data))
 {
 }
 
@@ -278,12 +284,27 @@ noop(irq)
                 <para>
                 The following control flow is implemented (simplified excerpt):
                 <programlisting>
-desc->chip->start();
+desc->chip->irq_mask();
 handle_IRQ_event(desc->action);
-desc->chip->end();
+desc->chip->irq_unmask();
                 </programlisting>
                 </para>
-            </sect3>
+            </sect3>
+            <sect3 id="Default_FASTEOI_IRQ_flow_handler">
+                <title>Default Fast EOI IRQ flow handler</title>
+                <para>
+                handle_fasteoi_irq provides a generic implementation
+                for interrupts, which only need an EOI at the end of
+                the handler
+                </para>
+                <para>
+                The following control flow is implemented (simplified excerpt):
+                <programlisting>
+handle_IRQ_event(desc->action);
+desc->chip->irq_eoi();
+                </programlisting>
+                </para>
+            </sect3>
             <sect3 id="Default_Edge_IRQ_flow_handler">
                 <title>Default Edge IRQ flow handler</title>
                 <para>
@@ -294,20 +315,19 @@ desc->chip->end();
                 The following control flow is implemented (simplified excerpt):
                 <programlisting>
 if (desc->status &amp; running) {
-        desc->chip->hold();
+        desc->chip->irq_mask();
         desc->status |= pending | masked;
         return;
 }
-desc->chip->start();
+desc->chip->irq_ack();
 desc->status |= running;
 do {
         if (desc->status &amp; masked)
-                desc->chip->enable();
+                desc->chip->irq_unmask();
         desc->status &amp;= ~pending;
         handle_IRQ_event(desc->action);
 } while (status &amp; pending);
 desc->status &amp;= ~running;
-desc->chip->end();
                 </programlisting>
                 </para>
             </sect3>
@@ -342,9 +362,9 @@ handle_IRQ_event(desc->action);
                 <para>
                 The following control flow is implemented (simplified excerpt):
                 <programlisting>
-desc->chip->start();
 handle_IRQ_event(desc->action);
-desc->chip->end();
+if (desc->chip->irq_eoi)
+        desc->chip->irq_eoi();
                 </programlisting>
                 </para>
             </sect3>
@@ -375,8 +395,7 @@ desc->chip->end();
         mechanism. (It's necessary to enable CONFIG_HARDIRQS_SW_RESEND when
         you want to use the delayed interrupt disable feature and your
         hardware is not capable of retriggering an interrupt.)
-        The delayed interrupt disable can be runtime enabled, per interrupt,
-        by setting the IRQ_DELAYED_DISABLE flag in the irq_desc status field.
+        The delayed interrupt disable is not configurable.
         </para>
         </sect2>
     </sect1>
@@ -387,13 +406,13 @@ desc->chip->end();
         contains all the direct chip relevant functions, which
         can be utilized by the irq flow implementations.
           <itemizedlist>
-          <listitem><para>ack()</para></listitem>
-          <listitem><para>mask_ack() - Optional, recommended for performance</para></listitem>
-          <listitem><para>mask()</para></listitem>
-          <listitem><para>unmask()</para></listitem>
-          <listitem><para>retrigger() - Optional</para></listitem>
-          <listitem><para>set_type() - Optional</para></listitem>
-          <listitem><para>set_wake() - Optional</para></listitem>
+          <listitem><para>irq_ack()</para></listitem>
+          <listitem><para>irq_mask_ack() - Optional, recommended for performance</para></listitem>
+          <listitem><para>irq_mask()</para></listitem>
+          <listitem><para>irq_unmask()</para></listitem>
+          <listitem><para>irq_retrigger() - Optional</para></listitem>
+          <listitem><para>irq_set_type() - Optional</para></listitem>
+          <listitem><para>irq_set_wake() - Optional</para></listitem>
           </itemizedlist>
         These primitives are strictly intended to mean what they say: ack means
         ACK, masking means masking of an IRQ line, etc. It is up to the flow
@@ -458,6 +477,7 @@ desc->chip->end();
      <para>
      This chapter contains the autogenerated documentation of the internal functions.
      </para>
+!Ikernel/irq/irqdesc.c
 !Ikernel/irq/handle.c
 !Ikernel/irq/chip.c
   </chapter>
diff --git a/Documentation/DocBook/kernel-locking.tmpl b/Documentation/DocBook/kernel-locking.tmpl
index a0d479d1e1dd..f66f4df18690 100644
--- a/Documentation/DocBook/kernel-locking.tmpl
+++ b/Documentation/DocBook/kernel-locking.tmpl
@@ -1645,7 +1645,9 @@ the amount of locking which needs to be done.
       all the readers who were traversing the list when we deleted the
       element are finished.  We use <function>call_rcu()</function> to
       register a callback which will actually destroy the object once
-      the readers are finished.
+      all pre-existing readers are finished.  Alternatively,
+      <function>synchronize_rcu()</function> may be used to block until
+      all pre-existing are finished.
     </para>
     <para>
       But how does Read Copy Update know when the readers are
@@ -1714,7 +1716,7 @@ the amount of locking which needs to be done.
 -        object_put(obj);
 +        list_del_rcu(&amp;obj-&gt;list);
          cache_num--;
-+        call_rcu(&amp;obj-&gt;rcu, cache_delete_rcu, obj);
++        call_rcu(&amp;obj-&gt;rcu, cache_delete_rcu);
  }
 
  /* Must be holding cache_lock */
@@ -1725,14 +1727,6 @@ the amount of locking which needs to be done.
          if (++cache_num > MAX_CACHE_SIZE) {
                  struct object *i, *outcast = NULL;
                  list_for_each_entry(i, &amp;cache, list) {
-@@ -85,6 +94,7 @@
-         obj-&gt;popularity = 0;
-         atomic_set(&amp;obj-&gt;refcnt, 1); /* The cache holds a reference */
-         spin_lock_init(&amp;obj-&gt;lock);
-+        INIT_RCU_HEAD(&amp;obj-&gt;rcu);
-
-         spin_lock_irqsave(&amp;cache_lock, flags);
-         __cache_add(obj);
 @@ -104,12 +114,11 @@
  struct object *cache_find(int id)
  {
diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt
index 790d1a812376..0c134f8afc6f 100644
--- a/Documentation/RCU/checklist.txt
+++ b/Documentation/RCU/checklist.txt
@@ -218,13 +218,22 @@ over a rather long period of time, but improvements are always welcome!
         include:
 
         a.      Keeping a count of the number of data-structure elements
-                used by the RCU-protected data structure, including those
-                waiting for a grace period to elapse.  Enforce a limit
-                on this number, stalling updates as needed to allow
-                previously deferred frees to complete.
-
-                Alternatively, limit only the number awaiting deferred
-                free rather than the total number of elements.
+                used by the RCU-protected data structure, including
+                those waiting for a grace period to elapse.  Enforce a
+                limit on this number, stalling updates as needed to allow
+                previously deferred frees to complete.  Alternatively,
+                limit only the number awaiting deferred free rather than
+                the total number of elements.
+
+                One way to stall the updates is to acquire the update-side
+                mutex.  (Don't try this with a spinlock -- other CPUs
+                spinning on the lock could prevent the grace period
+                from ever ending.)  Another way to stall the updates
+                is for the updates to use a wrapper function around
+                the memory allocator, so that this wrapper function
+                simulates OOM when there is too much memory awaiting an
+                RCU grace period.  There are of course many other
+                variations on this theme.
 
         b.      Limiting update rate.  For example, if updates occur only
                 once per hour, then no explicit rate limiting is required,
@@ -365,3 +374,26 @@ over a rather long period of time, but improvements are always welcome!
         and the compiler to freely reorder code into and out of RCU
         read-side critical sections.  It is the responsibility of the
         RCU update-side primitives to deal with this.
+
+17.     Use CONFIG_PROVE_RCU, CONFIG_DEBUG_OBJECTS_RCU_HEAD, and
+        the __rcu sparse checks to validate your RCU code.  These
+        can help find problems as follows:
+
+        CONFIG_PROVE_RCU: check that accesses to RCU-protected data
+                structures are carried out under the proper RCU
+                read-side critical section, while holding the right
+                combination of locks, or whatever other conditions
+                are appropriate.
+
+        CONFIG_DEBUG_OBJECTS_RCU_HEAD: check that you don't pass the
+                same object to call_rcu() (or friends) before an RCU
+                grace period has elapsed since the last time that you
+                passed that same object to call_rcu() (or friends).
+
+        __rcu sparse checks: tag the pointer to the RCU-protected data
+                structure with __rcu, and sparse will warn you if you
+                access that pointer without the services of one of the
+                variants of rcu_dereference().
+
+        These debugging aids can help you find problems that are
+        otherwise extremely difficult to spot.
diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt
index 44c6dcc93d6d..862c08ef1fde 100644
--- a/Documentation/RCU/stallwarn.txt
+++ b/Documentation/RCU/stallwarn.txt
@@ -80,6 +80,24 @@ o	A CPU looping with bottom halves disabled.  This condition can
 o       For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel
         without invoking schedule().
 
+o       A CPU-bound real-time task in a CONFIG_PREEMPT kernel, which might
+        happen to preempt a low-priority task in the middle of an RCU
+        read-side critical section.   This is especially damaging if
+        that low-priority task is not permitted to run on any other CPU,
+        in which case the next RCU grace period can never complete, which
+        will eventually cause the system to run out of memory and hang.
+        While the system is in the process of running itself out of
+        memory, you might see stall-warning messages.
+
+o       A CPU-bound real-time task in a CONFIG_PREEMPT_RT kernel that
+        is running at a higher priority than the RCU softirq threads.
+        This will prevent RCU callbacks from ever being invoked,
+        and in a CONFIG_TREE_PREEMPT_RCU kernel will further prevent
+        RCU grace periods from ever completing.  Either way, the
+        system will eventually run out of memory and hang.  In the
+        CONFIG_TREE_PREEMPT_RCU case, you might see stall-warning
+        messages.
+
 o       A bug in the RCU implementation.
 
 o       A hardware failure.  This is quite unlikely, but has occurred
diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index efd8cc95c06b..a851118775d8 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -125,6 +125,17 @@ o	"b" is the batch limit for this CPU.  If more than this number
         of RCU callbacks is ready to invoke, then the remainder will
         be deferred.
 
+o       "ci" is the number of RCU callbacks that have been invoked for
+        this CPU.  Note that ci+ql is the number of callbacks that have
+        been registered in absence of CPU-hotplug activity.
+
+o       "co" is the number of RCU callbacks that have been orphaned due to
+        this CPU going offline.
+
+o       "ca" is the number of RCU callbacks that have been adopted due to
+        other CPUs going offline.  Note that ci+co-ca+ql is the number of
+        RCU callbacks registered on this CPU.
+
 There is also an rcu/rcudata.csv file with the same information in
 comma-separated-variable spreadsheet format.
 
@@ -180,7 +191,7 @@ o	"s" is the "signaled" state that drives force_quiescent_state()'s
 
 o       "jfq" is the number of jiffies remaining for this grace period
         before force_quiescent_state() is invoked to help push things
-        along.  Note that CPUs in dyntick-idle mode thoughout the grace
+        along.  Note that CPUs in dyntick-idle mode throughout the grace
         period will not report on their own, but rather must be check by
         some other CPU via force_quiescent_state().
 
diff --git a/Documentation/cputopology.txt b/Documentation/cputopology.txt
index f1c5c4bccd3e..902d3151f527 100644
--- a/Documentation/cputopology.txt
+++ b/Documentation/cputopology.txt
@@ -14,25 +14,39 @@ to /proc/cpuinfo.
         identifier (rather than the kernel's).  The actual value is
         architecture and platform dependent.
 
-3) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
+3) /sys/devices/system/cpu/cpuX/topology/book_id:
+
+        the book ID of cpuX. Typically it is the hardware platform's
+        identifier (rather than the kernel's).  The actual value is
+        architecture and platform dependent.
+
+4) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
 
         internel kernel map of cpuX's hardware threads within the same
         core as cpuX
 
-4) /sys/devices/system/cpu/cpuX/topology/core_siblings:
+5) /sys/devices/system/cpu/cpuX/topology/core_siblings:
 
         internal kernel map of cpuX's hardware threads within the same
         physical_package_id.
 
+6) /sys/devices/system/cpu/cpuX/topology/book_siblings:
+
+        internal kernel map of cpuX's hardware threads within the same
+        book_id.
+
 To implement it in an architecture-neutral way, a new source file,
-drivers/base/topology.c, is to export the 4 attributes.
+drivers/base/topology.c, is to export the 4 or 6 attributes. The two book
+related sysfs files will only be created if CONFIG_SCHED_BOOK is selected.
 
 For an architecture to support this feature, it must define some of
 these macros in include/asm-XXX/topology.h:
 #define topology_physical_package_id(cpu)
 #define topology_core_id(cpu)
+#define topology_book_id(cpu)
 #define topology_thread_cpumask(cpu)
 #define topology_core_cpumask(cpu)
+#define topology_book_cpumask(cpu)
 
 The type of **_id is int.
 The type of siblings is (const) struct cpumask *.
@@ -45,6 +59,9 @@ not defined by include/asm-XXX/topology.h:
 3) thread_siblings: just the given CPU
 4) core_siblings: just the given CPU
 
+For architectures that don't support books (CONFIG_SCHED_BOOK) there are no
+default definitions for topology_book_id() and topology_book_cpumask().
+
 Additionally, CPU topology information is provided under
 /sys/devices/system/cpu and includes these files.  The internal
 source for the output is in brackets ("[]").
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 842aa9de84a6..5e2bc4ab897a 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -386,34 +386,6 @@ Who:	Tejun Heo <tj@kernel.org>
 
 ----------------------------
 
-What:   Support for VMware's guest paravirtuliazation technique [VMI] will be
-        dropped.
-When:   2.6.37 or earlier.
-Why:    With the recent innovations in CPU hardware acceleration technologies
-        from Intel and AMD, VMware ran a few experiments to compare these
-        techniques to guest paravirtualization technique on VMware's platform.
-        These hardware assisted virtualization techniques have outperformed the
-        performance benefits provided by VMI in most of the workloads. VMware
-        expects that these hardware features will be ubiquitous in a couple of
-        years, as a result, VMware has started a phased retirement of this
-        feature from the hypervisor. We will be removing this feature from the
-        Kernel too. Right now we are targeting 2.6.37 but can retire earlier if
-        technical reasons (read opportunity to remove major chunk of pvops)
-        arise.
-
-        Please note that VMI has always been an optimization and non-VMI kernels
-        still work fine on VMware's platform.
-        Latest versions of VMware's product which support VMI are,
-        Workstation 7.0 and VSphere 4.0 on ESX side, future maintainence
-        releases for these products will continue supporting VMI.
-
-        For more details about VMI retirement take a look at this,
-        http://blogs.vmware.com/guestosguide/2009/09/vmi-retirement.html
-
-Who:    Alok N Kataria <akataria@vmware.com>
-
-----------------------------
-
 What:   Support for lcd_switch and display_get in asus-laptop driver
 When:   March 2010
 Why:    These two features use non-standard interfaces. There are the
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 8dd7248508a9..3a0009e03d14 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -455,7 +455,7 @@ and is between 256 and 4096 characters. It is defined in the file
                         [ARM] imx_timer1,OSTS,netx_timer,mpu_timer2,
                                 pxa_timer,timer3,32k_counter,timer0_1
                         [AVR32] avr32
-                        [X86-32] pit,hpet,tsc,vmi-timer;
+                        [X86-32] pit,hpet,tsc;
                                 scx200_hrt on Geode; cyclone on IBM x440
                         [MIPS] MIPS
                         [PARISC] cr16
@@ -2153,6 +2153,11 @@ and is between 256 and 4096 characters. It is defined in the file
                         Reserves a hole at the top of the kernel virtual
                         address space.
 
+        reservelow=     [X86]
+                        Format: nn[K]
+                        Set the amount of memory to reserve for BIOS at
+                        the bottom of the address space.
+
         reset_devices   [KNL] Force drivers to reset the underlying device
                         during initialization.
 
@@ -2435,6 +2440,10 @@ and is between 256 and 4096 characters. It is defined in the file
                         disables clocksource verification at runtime.
                         Used to enable high-resolution timer mode on older
                         hardware, and in virtualized environment.
+                        [x86] noirqtime: Do not use TSC to do irq accounting.
+                        Used to run time disable IRQ_TIME_ACCOUNTING on any
+                        platforms where RDTSC is slow and this accounting
+                        can add overhead.
 
         turbografx.map[2|3]=    [HW,JOY]
                         TurboGraFX parallel port interface
diff --git a/MAINTAINERS b/MAINTAINERS
index f2a2b8e647c5..6f5b5b2b528d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1527,6 +1527,8 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
 S:      Supported
 F:      Documentation/filesystems/ceph.txt
 F:      fs/ceph
+F:      net/ceph
+F:      include/linux/ceph
 
 CERTIFIED WIRELESS USB (WUSB) SUBSYSTEM:
 M:      David Vrabel <david.vrabel@csr.com>
@@ -3239,6 +3241,12 @@ F:	drivers/net/irda/
 F:      include/net/irda/
 F:      net/irda/
 
+IRQ SUBSYSTEM
+M:      Thomas Gleixner <tglx@linutronix.de>
+S:      Maintained
+T:      git git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git irq/core
+F:      kernel/irq/
+
 ISAPNP
 M:      Jaroslav Kysela <perex@perex.cz>
 S:      Maintained
@@ -4805,6 +4813,15 @@ F:	fs/qnx4/
 F:      include/linux/qnx4_fs.h
 F:      include/linux/qnxtypes.h
 
+RADOS BLOCK DEVICE (RBD)
+F:      include/linux/qnxtypes.h
+M:      Yehuda Sadeh <yehuda@hq.newdream.net>
+M:      Sage Weil <sage@newdream.net>
+M:      ceph-devel@vger.kernel.org
+S:      Supported
+F:      drivers/block/rbd.c
+F:      drivers/block/rbd_types.h
+
 RADEON FRAMEBUFFER DISPLAY DRIVER
 M:      Benjamin Herrenschmidt <benh@kernel.crashing.org>
 L:      linux-fbdev@vger.kernel.org
diff --git a/arch/arm/include/asm/hw_irq.h b/arch/arm/include/asm/hw_irq.h
index 90831f6f5f5c..5586b7c8ef6f 100644
--- a/arch/arm/include/asm/hw_irq.h
+++ b/arch/arm/include/asm/hw_irq.h
@@ -24,4 +24,6 @@ void set_irq_flags(unsigned int irq, unsigned int flags);
 #define IRQF_PROBE      (1 << 1)
 #define IRQF_NOAUTOEN   (1 << 2)
 
+#define ARCH_IRQ_INIT_FLAGS     (IRQ_NOREQUEST | IRQ_NOPROBE)
+
 #endif
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index c0d5c3b3a760..36ad3be4692a 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -154,14 +154,6 @@ void set_irq_flags(unsigned int irq, unsigned int iflags)
 
 void __init init_IRQ(void)
 {
-        struct irq_desc *desc;
-        int irq;
-
-        for (irq = 0; irq < nr_irqs; irq++) {
-                desc = irq_to_desc_alloc_node(irq, 0);
-                desc->status |= IRQ_NOREQUEST | IRQ_NOPROBE;
-        }
-
         init_arch_irq();
 }
 
@@ -169,7 +161,7 @@ void __init init_IRQ(void)
 int __init arch_probe_nr_irqs(void)
 {
         nr_irqs = arch_nr_irqs ? arch_nr_irqs : NR_IRQS;
-        return 0;
+        return nr_irqs;
 }
 #endif
 
diff --git a/arch/arm/mach-bcmring/dma.c b/arch/arm/mach-bcmring/dma.c
index 29c0a911df26..77eb35c89cd0 100644
--- a/arch/arm/mach-bcmring/dma.c
+++ b/arch/arm/mach-bcmring/dma.c
@@ -691,7 +691,7 @@ int dma_init(void)
 
         memset(&gDMA, 0, sizeof(gDMA));
 
-        init_MUTEX_LOCKED(&gDMA.lock);
+        sema_init(&gDMA.lock, 0);
         init_waitqueue_head(&gDMA.freeChannelQ);
 
         /* Initialize the Hardware */
@@ -1574,7 +1574,7 @@ int dma_init_mem_map(DMA_MemMap_t *memMap)
 {
         memset(memMap, 0, sizeof(*memMap));
 
-        init_MUTEX(&memMap->lock);
+        sema_init(&memMap->lock, 1);
 
         return 0;
 }
diff --git a/arch/arm/mach-bcmring/irq.c b/arch/arm/mach-bcmring/irq.c
index dc1c4939b0ce..e3152631eb37 100644
--- a/arch/arm/mach-bcmring/irq.c
+++ b/arch/arm/mach-bcmring/irq.c
@@ -67,21 +67,21 @@ static void bcmring_unmask_irq2(unsigned int irq)
 }
 
 static struct irq_chip bcmring_irq0_chip = {
-        .typename = "ARM-INTC0",
+        .name = "ARM-INTC0",
         .ack = bcmring_mask_irq0,
         .mask = bcmring_mask_irq0,      /* mask a specific interrupt, blocking its delivery. */
         .unmask = bcmring_unmask_irq0,  /* unmaks an interrupt */
 };
 
 static struct irq_chip bcmring_irq1_chip = {
-        .typename = "ARM-INTC1",
+        .name = "ARM-INTC1",
         .ack = bcmring_mask_irq1,
         .mask = bcmring_mask_irq1,
         .unmask = bcmring_unmask_irq1,
 };
 
 static struct irq_chip bcmring_irq2_chip = {
-        .typename = "ARM-SINTC",
+        .name = "ARM-SINTC",
         .ack = bcmring_mask_irq2,
         .mask = bcmring_mask_irq2,
         .unmask = bcmring_unmask_irq2,
diff --git a/arch/arm/mach-iop13xx/msi.c b/arch/arm/mach-iop13xx/msi.c
index f34b0ed80630..7149fcc16c8a 100644
--- a/arch/arm/mach-iop13xx/msi.c
+++ b/arch/arm/mach-iop13xx/msi.c
@@ -164,10 +164,10 @@ static void iop13xx_msi_nop(unsigned int irq)
 static struct irq_chip iop13xx_msi_chip = {
         .name = "PCI-MSI",
         .ack = iop13xx_msi_nop,
-        .enable = unmask_msi_irq,
-        .disable = mask_msi_irq,
-        .mask = mask_msi_irq,
-        .unmask = unmask_msi_irq,
+        .irq_enable = unmask_msi_irq,
+        .irq_disable = mask_msi_irq,
+        .irq_mask = mask_msi_irq,
+        .irq_unmask = unmask_msi_irq,
 };
 
 int arch_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *desc)
diff --git a/arch/ia64/include/asm/hardirq.h b/arch/ia64/include/asm/hardirq.h
index d514cd9edb49..8fb7d33a661f 100644
--- a/arch/ia64/include/asm/hardirq.h
+++ b/arch/ia64/include/asm/hardirq.h
@@ -6,12 +6,6 @@
  *      David Mosberger-Tang <davidm@hpl.hp.com>
  */
 
-
-#include <linux/threads.h>
-#include <linux/irq.h>
-
-#include <asm/processor.h>
-
 /*
  * No irq_cpustat_t for IA-64.  The data is held in the per-CPU data structure.
  */
@@ -20,6 +14,11 @@
 
 #define local_softirq_pending()         (local_cpu_data->softirq_pending)
 
+#include <linux/threads.h>
+#include <linux/irq.h>
+
+#include <asm/processor.h>
+
 extern void __iomem *ipi_base_addr;
 
 void ack_bad_irq(unsigned int irq);
diff --git a/arch/ia64/include/asm/system.h b/arch/ia64/include/asm/system.h
index 9f342a574ce8..dd028f2b13b3 100644
--- a/arch/ia64/include/asm/system.h
+++ b/arch/ia64/include/asm/system.h
@@ -272,10 +272,6 @@ void cpu_idle_wait(void);
 
 void default_idle(void);
 
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
-extern void account_system_vtime(struct task_struct *);
-#endif
-
 #endif /* __KERNEL__ */
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/ia64/kernel/msi_ia64.c b/arch/ia64/kernel/msi_ia64.c
index 4a746ea838ff..00b19a416eab 100644
--- a/arch/ia64/kernel/msi_ia64.c
+++ b/arch/ia64/kernel/msi_ia64.c
@@ -104,8 +104,8 @@ static int ia64_msi_retrigger_irq(unsigned int irq)
  */
 static struct irq_chip ia64_msi_chip = {
         .name           = "PCI-MSI",
-        .mask           = mask_msi_irq,
-        .unmask         = unmask_msi_irq,
+        .irq_mask       = mask_msi_irq,
+        .irq_unmask     = unmask_msi_irq,
         .ack            = ia64_ack_msi_irq,
 #ifdef CONFIG_SMP
         .set_affinity   = ia64_set_msi_irq_affinity,
@@ -160,8 +160,8 @@ static int dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 
 static struct irq_chip dmar_msi_type = {
         .name = "DMAR_MSI",
-        .unmask = dmar_msi_unmask,
-        .mask = dmar_msi_mask,
+        .irq_unmask = dmar_msi_unmask,
+        .irq_mask = dmar_msi_mask,
         .ack = ia64_ack_msi_irq,
 #ifdef CONFIG_SMP
         .set_affinity = dmar_msi_set_affinity,
diff --git a/arch/ia64/sn/kernel/msi_sn.c b/arch/ia64/sn/kernel/msi_sn.c
index 0c72dd463831..a5e500f02853 100644
--- a/arch/ia64/sn/kernel/msi_sn.c
+++ b/arch/ia64/sn/kernel/msi_sn.c
@@ -228,8 +228,8 @@ static int sn_msi_retrigger_irq(unsigned int irq)
 
 static struct irq_chip sn_msi_chip = {
         .name           = "PCI-MSI",
-        .mask           = mask_msi_irq,
-        .unmask         = unmask_msi_irq,
+        .irq_mask       = mask_msi_irq,
+        .irq_unmask     = unmask_msi_irq,
         .ack            = sn_ack_msi_irq,
 #ifdef CONFIG_SMP
         .set_affinity   = sn_set_msi_irq_affinity,
diff --git a/arch/m32r/kernel/irq.c b/arch/m32r/kernel/irq.c
index 3c71f776872c..7db26f1f082d 100644
--- a/arch/m32r/kernel/irq.c
+++ b/arch/m32r/kernel/irq.c
@@ -51,7 +51,7 @@ int show_interrupts(struct seq_file *p, void *v)
                 for_each_online_cpu(j)
                         seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #endif
-                seq_printf(p, " %14s", irq_desc[i].chip->typename);
+                seq_printf(p, " %14s", irq_desc[i].chip->name);
                 seq_printf(p, "  %s", action->name);
 
                 for (action=action->next; action; action = action->next)
diff --git a/arch/m32r/platforms/m32104ut/setup.c b/arch/m32r/platforms/m32104ut/setup.c
index 922fdfdadeaa..402a59d7219b 100644
--- a/arch/m32r/platforms/m32104ut/setup.c
+++ b/arch/m32r/platforms/m32104ut/setup.c
@@ -65,7 +65,7 @@ static void shutdown_m32104ut_irq(unsigned int irq)
 
 static struct irq_chip m32104ut_irq_type =
 {
-        .typename = "M32104UT-IRQ",
+        .name = "M32104UT-IRQ",
         .startup = startup_m32104ut_irq,
         .shutdown = shutdown_m32104ut_irq,
         .enable = enable_m32104ut_irq,
diff --git a/arch/m32r/platforms/m32700ut/setup.c b/arch/m32r/platforms/m32700ut/setup.c
index 9c1bc7487c1e..80b1a026795a 100644
--- a/arch/m32r/platforms/m32700ut/setup.c
+++ b/arch/m32r/platforms/m32700ut/setup.c
@@ -71,7 +71,7 @@ static void shutdown_m32700ut_irq(unsigned int irq)
 
 static struct irq_chip m32700ut_irq_type =
 {
-        .typename = "M32700UT-IRQ",
+        .name = "M32700UT-IRQ",
         .startup = startup_m32700ut_irq,
         .shutdown = shutdown_m32700ut_irq,
         .enable = enable_m32700ut_irq,
@@ -148,7 +148,7 @@ static void shutdown_m32700ut_pld_irq(unsigned int irq)
 
 static struct irq_chip m32700ut_pld_irq_type =
 {
-        .typename = "M32700UT-PLD-IRQ",
+        .name = "M32700UT-PLD-IRQ",
         .startup = startup_m32700ut_pld_irq,
         .shutdown = shutdown_m32700ut_pld_irq,
         .enable = enable_m32700ut_pld_irq,
@@ -217,7 +217,7 @@ static void shutdown_m32700ut_lanpld_irq(unsigned int irq)
 
 static struct irq_chip m32700ut_lanpld_irq_type =
 {
-        .typename = "M32700UT-PLD-LAN-IRQ",
+        .name = "M32700UT-PLD-LAN-IRQ",
         .startup = startup_m32700ut_lanpld_irq,
         .shutdown = shutdown_m32700ut_lanpld_irq,
         .enable = enable_m32700ut_lanpld_irq,
@@ -286,7 +286,7 @@ static void shutdown_m32700ut_lcdpld_irq(unsigned int irq)
 
 static struct irq_chip m32700ut_lcdpld_irq_type =
 {
-        .typename = "M32700UT-PLD-LCD-IRQ",
+        .name = "M32700UT-PLD-LCD-IRQ",
         .startup = startup_m32700ut_lcdpld_irq,
         .shutdown = shutdown_m32700ut_lcdpld_irq,
         .enable = enable_m32700ut_lcdpld_irq,
diff --git a/arch/m32r/platforms/mappi/setup.c b/arch/m32r/platforms/mappi/setup.c
index fb4b17799b66..ea00c84d6b1b 100644
--- a/arch/m32r/platforms/mappi/setup.c
+++ b/arch/m32r/platforms/mappi/setup.c
@@ -65,7 +65,7 @@ static void shutdown_mappi_irq(unsigned int irq)
 
 static struct irq_chip mappi_irq_type =
 {
-        .typename = "MAPPI-IRQ",
+        .name = "MAPPI-IRQ",
         .startup = startup_mappi_irq,
         .shutdown = shutdown_mappi_irq,
         .enable = enable_mappi_irq,
diff --git a/arch/m32r/platforms/mappi2/setup.c b/arch/m32r/platforms/mappi2/setup.c
index 6a65eda0a056..c049376d0270 100644
--- a/arch/m32r/platforms/mappi2/setup.c
+++ b/arch/m32r/platforms/mappi2/setup.c
@@ -72,7 +72,7 @@ static void shutdown_mappi2_irq(unsigned int irq)
 
 static struct irq_chip mappi2_irq_type =
 {
-        .typename = "MAPPI2-IRQ",
+        .name = "MAPPI2-IRQ",
         .startup = startup_mappi2_irq,
         .shutdown = shutdown_mappi2_irq,
         .enable = enable_mappi2_irq,
diff --git a/arch/m32r/platforms/mappi3/setup.c b/arch/m32r/platforms/mappi3/setup.c
index 9c337aeac94b..882de25c6e8c 100644
--- a/arch/m32r/platforms/mappi3/setup.c
+++ b/arch/m32r/platforms/mappi3/setup.c
@@ -72,7 +72,7 @@ static void shutdown_mappi3_irq(unsigned int irq)
 
 static struct irq_chip mappi3_irq_type =
 {
-        .typename = "MAPPI3-IRQ",
+        .name = "MAPPI3-IRQ",
         .startup = startup_mappi3_irq,
         .shutdown = shutdown_mappi3_irq,
         .enable = enable_mappi3_irq,
diff --git a/arch/m32r/platforms/oaks32r/setup.c b/arch/m32r/platforms/oaks32r/setup.c
index ed865741c38d..d11d93bf74f5 100644
--- a/arch/m32r/platforms/oaks32r/setup.c
+++ b/arch/m32r/platforms/oaks32r/setup.c
@@ -63,7 +63,7 @@ static void shutdown_oaks32r_irq(unsigned int irq)
 
 static struct irq_chip oaks32r_irq_type =
 {
-        .typename = "OAKS32R-IRQ",
+        .name = "OAKS32R-IRQ",
         .startup = startup_oaks32r_irq,
         .shutdown = shutdown_oaks32r_irq,
         .enable = enable_oaks32r_irq,
diff --git a/arch/m32r/platforms/opsput/setup.c b/arch/m32r/platforms/opsput/setup.c
index 80d680657019..5f3402a2fbaf 100644
--- a/arch/m32r/platforms/opsput/setup.c
+++ b/arch/m32r/platforms/opsput/setup.c
@@ -72,7 +72,7 @@ static void shutdown_opsput_irq(unsigned int irq)
 
 static struct irq_chip opsput_irq_type =
 {
-        .typename = "OPSPUT-IRQ",
+        .name = "OPSPUT-IRQ",
         .startup = startup_opsput_irq,
         .shutdown = shutdown_opsput_irq,
         .enable = enable_opsput_irq,
@@ -149,7 +149,7 @@ static void shutdown_opsput_pld_irq(unsigned int irq)
 
 static struct irq_chip opsput_pld_irq_type =
 {
-        .typename = "OPSPUT-PLD-IRQ",
+        .name = "OPSPUT-PLD-IRQ",
         .startup = startup_opsput_pld_irq,
         .shutdown = shutdown_opsput_pld_irq,
         .enable = enable_opsput_pld_irq,
@@ -218,7 +218,7 @@ static void shutdown_opsput_lanpld_irq(unsigned int irq)
 
 static struct irq_chip opsput_lanpld_irq_type =
 {
-        .typename = "OPSPUT-PLD-LAN-IRQ",
+        .name = "OPSPUT-PLD-LAN-IRQ",
         .startup = startup_opsput_lanpld_irq,
         .shutdown = shutdown_opsput_lanpld_irq,
         .enable = enable_opsput_lanpld_irq,
diff --git a/arch/m32r/platforms/usrv/setup.c b/arch/m32r/platforms/usrv/setup.c
index 757302660af8..1beac7a51ed4 100644
--- a/arch/m32r/platforms/usrv/setup.c
+++ b/arch/m32r/platforms/usrv/setup.c
@@ -63,7 +63,7 @@ static void shutdown_mappi_irq(unsigned int irq)
 
 static struct irq_chip mappi_irq_type =
 {
-        .typename = "M32700-IRQ",
+        .name = "M32700-IRQ",
         .startup = startup_mappi_irq,
         .shutdown = shutdown_mappi_irq,
         .enable = enable_mappi_irq,
@@ -136,7 +136,7 @@ static void shutdown_m32700ut_pld_irq(unsigned int irq)
 
 static struct irq_chip m32700ut_pld_irq_type =
 {
-        .typename = "USRV-PLD-IRQ",
+        .name = "USRV-PLD-IRQ",
         .startup = startup_m32700ut_pld_irq,
         .shutdown = shutdown_m32700ut_pld_irq,
         .enable = enable_m32700ut_pld_irq,
diff --git a/arch/mips/kernel/mips-mt-fpaff.c b/arch/mips/kernel/mips-mt-fpaff.c
index 2340f11dc29c..9a526ba6f257 100644
--- a/arch/mips/kernel/mips-mt-fpaff.c
+++ b/arch/mips/kernel/mips-mt-fpaff.c
@@ -103,7 +103,7 @@ asmlinkage long mipsmt_sys_sched_setaffinity(pid_t pid, unsigned int len,
         if (!check_same_owner(p) && !capable(CAP_SYS_NICE))
                 goto out_unlock;
 
-        retval = security_task_setscheduler(p, 0, NULL);
+        retval = security_task_setscheduler(p)
         if (retval)
                 goto out_unlock;
 
diff --git a/arch/powerpc/include/asm/system.h b/arch/powerpc/include/asm/system.h
index 6c294acac848..9c3d160670b4 100644
--- a/arch/powerpc/include/asm/system.h
+++ b/arch/powerpc/include/asm/system.h
@@ -542,10 +542,6 @@ extern void reloc_got2(unsigned long);
 
 #define PTRRELOC(x)     ((typeof(x)) add_reloc_offset((unsigned long)(x)))
 
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
-extern void account_system_vtime(struct task_struct *);
-#endif
-
 extern struct dentry *powerpc_debugfs_root;
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c
index 97085530aa63..e3e379c6caa7 100644
--- a/arch/powerpc/platforms/cell/axon_msi.c
+++ b/arch/powerpc/platforms/cell/axon_msi.c
@@ -310,9 +310,9 @@ static void axon_msi_teardown_msi_irqs(struct pci_dev *dev)
 }
 
 static struct irq_chip msic_irq_chip = {
-        .mask           = mask_msi_irq,
-        .unmask         = unmask_msi_irq,
-        .shutdown       = unmask_msi_irq,
+        .irq_mask       = mask_msi_irq,
+        .irq_unmask     = unmask_msi_irq,
+        .irq_shutdown   = mask_msi_irq,
         .name           = "AXON-MSI",
 };
 
diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c
index 93834b0d8272..67e2c4bdac8f 100644
--- a/arch/powerpc/platforms/pseries/xics.c
+++ b/arch/powerpc/platforms/pseries/xics.c
@@ -243,7 +243,7 @@ static unsigned int xics_startup(unsigned int virq)
          * at that level, so we do it here by hand.
          */
         if (irq_to_desc(virq)->msi_desc)
-                unmask_msi_irq(virq);
+                unmask_msi_irq(irq_get_irq_data(virq));
 
         /* unmask it */
         xics_unmask_irq(virq);
diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c
index 87991d3abbab..bdbd896c89d8 100644
--- a/arch/powerpc/sysdev/fsl_msi.c
+++ b/arch/powerpc/sysdev/fsl_msi.c
@@ -51,8 +51,8 @@ static void fsl_msi_end_irq(unsigned int virq)
 }
 
 static struct irq_chip fsl_msi_chip = {
-        .mask           = mask_msi_irq,
-        .unmask         = unmask_msi_irq,
+        .irq_mask       = mask_msi_irq,
+        .irq_unmask     = unmask_msi_irq,
         .ack            = fsl_msi_end_irq,
         .name           = "FSL-MSI",
 };
diff --git a/arch/powerpc/sysdev/mpic_pasemi_msi.c b/arch/powerpc/sysdev/mpic_pasemi_msi.c
index 3b6a9a43718f..320ad5a9a25d 100644
--- a/arch/powerpc/sysdev/mpic_pasemi_msi.c
+++ b/arch/powerpc/sysdev/mpic_pasemi_msi.c
@@ -39,24 +39,24 @@
 static struct mpic *msi_mpic;
 
 
-static void mpic_pasemi_msi_mask_irq(unsigned int irq)
+static void mpic_pasemi_msi_mask_irq(struct irq_data *data)
 {
-        pr_debug("mpic_pasemi_msi_mask_irq %d\n", irq);
-        mask_msi_irq(irq);
-        mpic_mask_irq(irq);
+        pr_debug("mpic_pasemi_msi_mask_irq %d\n", data->irq);
+        mask_msi_irq(data);
+        mpic_mask_irq(data->irq);
 }
 
-static void mpic_pasemi_msi_unmask_irq(unsigned int irq)
+static void mpic_pasemi_msi_unmask_irq(struct irq_data *data)
 {
-        pr_debug("mpic_pasemi_msi_unmask_irq %d\n", irq);
-        mpic_unmask_irq(irq);
-        unmask_msi_irq(irq);
+        pr_debug("mpic_pasemi_msi_unmask_irq %d\n", data->irq);
+        mpic_unmask_irq(data->irq);
+        unmask_msi_irq(data);
 }
 
 static struct irq_chip mpic_pasemi_msi_chip = {
-        .shutdown       = mpic_pasemi_msi_mask_irq,
-        .mask           = mpic_pasemi_msi_mask_irq,
-        .unmask         = mpic_pasemi_msi_unmask_irq,
+        .irq_shutdown   = mpic_pasemi_msi_mask_irq,
+        .irq_mask       = mpic_pasemi_msi_mask_irq,
+        .irq_unmask     = mpic_pasemi_msi_unmask_irq,
         .eoi            = mpic_end_irq,
         .set_type       = mpic_set_irq_type,
         .set_affinity   = mpic_set_affinity,
diff --git a/arch/powerpc/sysdev/mpic_u3msi.c b/arch/powerpc/sysdev/mpic_u3msi.c
index bcbfe79c704b..a2b028b4a202 100644
--- a/arch/powerpc/sysdev/mpic_u3msi.c
+++ b/arch/powerpc/sysdev/mpic_u3msi.c
@@ -23,22 +23,22 @@
 /* A bit ugly, can we get this from the pci_dev somehow? */
 static struct mpic *msi_mpic;
 
-static void mpic_u3msi_mask_irq(unsigned int irq)
+static void mpic_u3msi_mask_irq(struct irq_data *data)
 {
-        mask_msi_irq(irq);
-        mpic_mask_irq(irq);
+        mask_msi_irq(data);
+        mpic_mask_irq(data->irq);
 }
 
-static void mpic_u3msi_unmask_irq(unsigned int irq)
+static void mpic_u3msi_unmask_irq(struct irq_data *data)
 {
-        mpic_unmask_irq(irq);
-        unmask_msi_irq(irq);
+        mpic_unmask_irq(data->irq);
+        unmask_msi_irq(data);
 }
 
 static struct irq_chip mpic_u3msi_chip = {
-        .shutdown       = mpic_u3msi_mask_irq,
-        .mask           = mpic_u3msi_mask_irq,
-        .unmask         = mpic_u3msi_unmask_irq,
+        .irq_shutdown   = mpic_u3msi_mask_irq,
+        .irq_mask       = mpic_u3msi_mask_irq,
+        .irq_unmask     = mpic_u3msi_unmask_irq,
         .eoi            = mpic_end_irq,
         .set_type       = mpic_set_irq_type,
         .set_affinity   = mpic_set_affinity,
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 958f0dadeadf..75976a141947 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -199,6 +199,13 @@ config HOTPLUG_CPU
           can be controlled through /sys/devices/system/cpu/cpu#.
           Say N if you want to disable CPU hotplug.
 
+config SCHED_BOOK
+        bool "Book scheduler support"
+        depends on SMP
+        help
+          Book scheduler support improves the CPU scheduler's decision making
+          when dealing with machines that have several books.
+
 config MATHEMU
         bool "IEEE FPU emulation"
         depends on MARCH_G5
diff --git a/arch/s390/include/asm/hardirq.h b/arch/s390/include/asm/hardirq.h
index 498bc3892385..881d94590aeb 100644
--- a/arch/s390/include/asm/hardirq.h
+++ b/arch/s390/include/asm/hardirq.h
@@ -12,10 +12,6 @@
 #ifndef __ASM_HARDIRQ_H
 #define __ASM_HARDIRQ_H
 
-#include <linux/threads.h>
-#include <linux/sched.h>
-#include <linux/cache.h>
-#include <linux/interrupt.h>
 #include <asm/lowcore.h>
 
 #define local_softirq_pending() (S390_lowcore.softirq_pending)
diff --git a/arch/s390/include/asm/system.h b/arch/s390/include/asm/system.h
index cef66210c846..38ddd8a9a9e8 100644
--- a/arch/s390/include/asm/system.h
+++ b/arch/s390/include/asm/system.h
@@ -97,7 +97,6 @@ static inline void restore_access_regs(unsigned int *acrs)
 
 extern void account_vtime(struct task_struct *, struct task_struct *);
 extern void account_tick_vtime(struct task_struct *);
-extern void account_system_vtime(struct task_struct *);
 
 #ifdef CONFIG_PFAULT
 extern void pfault_irq_init(void);
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index 831bd033ea77..051107a2c5e2 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -3,15 +3,32 @@
 
 #include <linux/cpumask.h>
 
-#define mc_capable()    (1)
-
-const struct cpumask *cpu_coregroup_mask(unsigned int cpu);
-
 extern unsigned char cpu_core_id[NR_CPUS];
 extern cpumask_t cpu_core_map[NR_CPUS];
 
+static inline const struct cpumask *cpu_coregroup_mask(unsigned int cpu)
+{
+        return &cpu_core_map[cpu];
+}
+
 #define topology_core_id(cpu)           (cpu_core_id[cpu])
 #define topology_core_cpumask(cpu)      (&cpu_core_map[cpu])
+#define mc_capable()                    (1)
+
+#ifdef CONFIG_SCHED_BOOK
+
+extern unsigned char cpu_book_id[NR_CPUS];
+extern cpumask_t cpu_book_map[NR_CPUS];
+
+static inline const struct cpumask *cpu_book_mask(unsigned int cpu)
+{
+        return &cpu_book_map[cpu];
+}
+
+#define topology_book_id(cpu)           (cpu_book_id[cpu])
+#define topology_book_cpumask(cpu)      (&cpu_book_map[cpu])
+
+#endif /* CONFIG_SCHED_BOOK */
 
 int topology_set_cpu_management(int fc);
 void topology_schedule_update(void);
@@ -30,6 +47,8 @@ static inline void s390_init_cpu_topology(void)
 };
 #endif
 
+#define SD_BOOK_INIT    SD_CPU_INIT
+
 #include <asm-generic/topology.h>
 
 #endif /* _ASM_S390_TOPOLOGY_H */
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index bcef00766a64..13559c993847 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -57,8 +57,8 @@ struct tl_info {
         union tl_entry tle[0];
 };
 
-struct core_info {
-        struct core_info *next;
+struct mask_info {
+        struct mask_info *next;
         unsigned char id;
         cpumask_t mask;
 };
@@ -66,7 +66,6 @@ struct core_info {
 static int topology_enabled;
 static void topology_work_fn(struct work_struct *work);
 static struct tl_info *tl_info;
-static struct core_info core_info;
 static int machine_has_topology;
 static struct timer_list topology_timer;
 static void set_topology_timer(void);
@@ -74,38 +73,37 @@ static DECLARE_WORK(topology_work, topology_work_fn);
 /* topology_lock protects the core linked list */
 static DEFINE_SPINLOCK(topology_lock);
 
+static struct mask_info core_info;
 cpumask_t cpu_core_map[NR_CPUS];
 unsigned char cpu_core_id[NR_CPUS];
 
-static cpumask_t cpu_coregroup_map(unsigned int cpu)
+#ifdef CONFIG_SCHED_BOOK
+static struct mask_info book_info;
+cpumask_t cpu_book_map[NR_CPUS];
+unsigned char cpu_book_id[NR_CPUS];
+#endif
+
+static cpumask_t cpu_group_map(struct mask_info *info, unsigned int cpu)
 {
-        struct core_info *core = &core_info;
-        unsigned long flags;
         cpumask_t mask;
 
         cpus_clear(mask);
         if (!topology_enabled || !machine_has_topology)
                 return cpu_possible_map;
-        spin_lock_irqsave(&topology_lock, flags);
-        while (core) {
-                if (cpu_isset(cpu, core->mask)) {
-                        mask = core->mask;
+        while (info) {
+                if (cpu_isset(cpu, info->mask)) {
+                        mask = info->mask;
                         break;
                 }
-                core = core->next;
+                info = info->next;
         }
-        spin_unlock_irqrestore(&topology_lock, flags);
         if (cpus_empty(mask))
                 mask = cpumask_of_cpu(cpu);
         return mask;
 }
 
-const struct cpumask *cpu_coregroup_mask(unsigned int cpu)
-{
-        return &cpu_core_map[cpu];
-}
-
-static void add_cpus_to_core(struct tl_cpu *tl_cpu, struct core_info *core)
+static void add_cpus_to_mask(struct tl_cpu *tl_cpu, struct mask_info *book,
+                             struct mask_info *core)
 {
         unsigned int cpu;
 
@@ -117,23 +115,35 @@ static void add_cpus_to_core(struct tl_cpu *tl_cpu, struct core_info *core)
 
                 rcpu = CPU_BITS - 1 - cpu + tl_cpu->origin;
                 for_each_present_cpu(lcpu) {
-                        if (cpu_logical_map(lcpu) == rcpu) {
-                                cpu_set(lcpu, core->mask);
-                                cpu_core_id[lcpu] = core->id;
-                                smp_cpu_polarization[lcpu] = tl_cpu->pp;
-                        }
+                        if (cpu_logical_map(lcpu) != rcpu)
+                                continue;
+#ifdef CONFIG_SCHED_BOOK
+                        cpu_set(lcpu, book->mask);
+                        cpu_book_id[lcpu] = book->id;
+#endif
+                        cpu_set(lcpu, core->mask);
+                        cpu_core_id[lcpu] = core->id;
+                        smp_cpu_polarization[lcpu] = tl_cpu->pp;
                 }
         }
 }
 
-static void clear_cores(void)
+static void clear_masks(void)
 {
-        struct core_info *core = &core_info;
+        struct mask_info *info;
 
-        while (core) {
-                cpus_clear(core->mask);
-                core = core->next;
+        info = &core_info;
+        while (info) {
+                cpus_clear(info->mask);
+                info = info->next;
+        }
+#ifdef CONFIG_SCHED_BOOK
+        info = &book_info;
+        while (info) {
+                cpus_clear(info->mask);
+                info = info->next;
         }
+#endif
 }
 
 static union tl_entry *next_tle(union tl_entry *tle)
@@ -146,29 +156,36 @@ static union tl_entry *next_tle(union tl_entry *tle)
 
 static void tl_to_cores(struct tl_info *info)
 {
+#ifdef CONFIG_SCHED_BOOK
+        struct mask_info *book = &book_info;
+#else
+        struct mask_info *book = NULL;
+#endif
+        struct mask_info *core = &core_info;
         union tl_entry *tle, *end;
-        struct core_info *core = &core_info;
+
 
         spin_lock_irq(&topology_lock);
-        clear_cores();
+        clear_masks();
         tle = info->tle;
         end = (union tl_entry *)((unsigned long)info + info->length);
         while (tle < end) {
                 switch (tle->nl) {
-                case 5:
-                case 4:
-                case 3:
+#ifdef CONFIG_SCHED_BOOK
                 case 2:
+                        book = book->next;
+                        book->id = tle->container.id;
                         break;
+#endif
                 case 1:
                         core = core->next;
                         core->id = tle->container.id;
                         break;
                 case 0:
-                        add_cpus_to_core(&tle->cpu, core);
+                        add_cpus_to_mask(&tle->cpu, book, core);
                         break;
                 default:
-                        clear_cores();
+                        clear_masks();
                         machine_has_topology = 0;
                         goto out;
                 }
@@ -221,10 +238,29 @@ int topology_set_cpu_management(int fc)
 
 static void update_cpu_core_map(void)
 {
+        unsigned long flags;
         int cpu;
 
-        for_each_possible_cpu(cpu)
-                cpu_core_map[cpu] = cpu_coregroup_map(cpu);
+        spin_lock_irqsave(&topology_lock, flags);
+        for_each_possible_cpu(cpu) {
+                cpu_core_map[cpu] = cpu_group_map(&core_info, cpu);
+#ifdef CONFIG_SCHED_BOOK
+                cpu_book_map[cpu] = cpu_group_map(&book_info, cpu);
+#endif
+        }
+        spin_unlock_irqrestore(&topology_lock, flags);
+}
+
+static void store_topology(struct tl_info *info)
+{
+#ifdef CONFIG_SCHED_BOOK
+        int rc;
+
+        rc = stsi(info, 15, 1, 3);
+        if (rc != -ENOSYS)
+                return;
+#endif
+        stsi(info, 15, 1, 2);
 }
 
 int arch_update_cpu_topology(void)
@@ -238,7 +274,7 @@ int arch_update_cpu_topology(void)
                 topology_update_polarization_simple();
                 return 0;
         }
-        stsi(info, 15, 1, 2);
+        store_topology(info);
         tl_to_cores(info);
         update_cpu_core_map();
         for_each_online_cpu(cpu) {
@@ -299,12 +335,24 @@ out:
 }
 __initcall(init_topology_update);
 
+static void alloc_masks(struct tl_info *info, struct mask_info *mask, int offset)
+{
+        int i, nr_masks;
+
+        nr_masks = info->mag[NR_MAG - offset];
+        for (i = 0; i < info->mnest - offset; i++)
+                nr_masks *= info->mag[NR_MAG - offset - 1 - i];
+        nr_masks = max(nr_masks, 1);
+        for (i = 0; i < nr_masks; i++) {
+                mask->next = alloc_bootmem(sizeof(struct mask_info));
+                mask = mask->next;
+        }
+}
+
 void __init s390_init_cpu_topology(void)
 {
         unsigned long long facility_bits;
         struct tl_info *info;
-        struct core_info *core;
-        int nr_cores;
         int i;
 
         if (stfle(&facility_bits, 1) <= 0)
@@ -315,25 +363,13 @@ void __init s390_init_cpu_topology(void)
 
         tl_info = alloc_bootmem_pages(PAGE_SIZE);
         info = tl_info;
-        stsi(info, 15, 1, 2);
-
-        nr_cores = info->mag[NR_MAG - 2];
-        for (i = 0; i < info->mnest - 2; i++)
-                nr_cores *= info->mag[NR_MAG - 3 - i];
-
+        store_topology(info);
         pr_info("The CPU configuration topology of the machine is:");
         for (i = 0; i < NR_MAG; i++)
                 printk(" %d", info->mag[i]);
         printk(" / %d\n", info->mnest);
-
-        core = &core_info;
-        for (i = 0; i < nr_cores; i++) {
-                core->next = alloc_bootmem(sizeof(struct core_info));
-                core = core->next;
-                if (!core)
-                        goto error;
-        }
-        return;
-error:
-        machine_has_topology = 0;
+        alloc_masks(info, &core_info, 2);
+#ifdef CONFIG_SCHED_BOOK
+        alloc_masks(info, &book_info, 3);
+#endif
 }
diff --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c
index 257de1f0692b..ae5bac39b896 100644
--- a/arch/sh/kernel/irq.c
+++ b/arch/sh/kernel/irq.c
@@ -290,7 +290,7 @@ void __init init_IRQ(void)
 int __init arch_probe_nr_irqs(void)
 {
         nr_irqs = sh_mv.mv_nr_irqs;
-        return 0;
+        return NR_IRQS_LEGACY;
 }
 #endif
 
diff --git a/arch/sparc/kernel/pci_msi.c b/arch/sparc/kernel/pci_msi.c
index 548b8ca9c210..b210416ace7b 100644
--- a/arch/sparc/kernel/pci_msi.c
+++ b/arch/sparc/kernel/pci_msi.c
@@ -114,10 +114,10 @@ static void free_msi(struct pci_pbm_info *pbm, int msi_num)
 
 static struct irq_chip msi_irq = {
         .name           = "PCI-MSI",
-        .mask           = mask_msi_irq,
-        .unmask         = unmask_msi_irq,
-        .enable         = unmask_msi_irq,
-        .disable        = mask_msi_irq,
+        .irq_mask       = mask_msi_irq,
+        .irq_unmask     = unmask_msi_irq,
+        .irq_enable     = unmask_msi_irq,
+        .irq_disable    = mask_msi_irq,
         /* XXX affinity XXX */
 };
 
diff --git a/arch/tile/kernel/irq.c b/arch/tile/kernel/irq.c
index 596c60086930..9a27d563fc30 100644
--- a/arch/tile/kernel/irq.c
+++ b/arch/tile/kernel/irq.c
@@ -208,7 +208,7 @@ static void tile_irq_chip_eoi(unsigned int irq)
 }
 
 static struct irq_chip tile_irq_chip = {
-        .typename = "tile_irq_chip",
+        .name = "tile_irq_chip",
         .ack = tile_irq_chip_ack,
         .eoi = tile_irq_chip_eoi,
         .mask = tile_irq_chip_mask,
@@ -288,7 +288,7 @@ int show_interrupts(struct seq_file *p, void *v)
                 for_each_online_cpu(j)
                         seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #endif
-                seq_printf(p, " %14s", irq_desc[i].chip->typename);
+                seq_printf(p, " %14s", irq_desc[i].chip->name);
                 seq_printf(p, "  %s", action->name);
 
                 for (action = action->next; action; action = action->next)
diff --git a/arch/um/kernel/irq.c b/arch/um/kernel/irq.c
index a3f0b04d7101..a746e3037a5b 100644
--- a/arch/um/kernel/irq.c
+++ b/arch/um/kernel/irq.c
@@ -46,7 +46,7 @@ int show_interrupts(struct seq_file *p, void *v)
                 for_each_online_cpu(j)
                         seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #endif
-                seq_printf(p, " %14s", irq_desc[i].chip->typename);
+                seq_printf(p, " %14s", irq_desc[i].chip->name);
                 seq_printf(p, "  %s", action->name);
 
                 for (action=action->next; action; action = action->next)
@@ -369,7 +369,7 @@ static void dummy(unsigned int irq)
 
 /* This is used for everything else than the timer. */
 static struct irq_chip normal_irq_type = {
-        .typename = "SIGIO",
+        .name = "SIGIO",
         .release = free_irq_by_irq_and_dev,
         .disable = dummy,
         .enable = dummy,
@@ -378,7 +378,7 @@ static struct irq_chip normal_irq_type = {
 };
 
 static struct irq_chip SIGVTALRM_irq_type = {
-        .typename = "SIGVTALRM",
+        .name = "SIGVTALRM",
         .release = free_irq_by_irq_and_dev,
         .shutdown = dummy, /* never called */
         .disable = dummy,
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index fd227d6b8d9c..7ab9db88ab6a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -63,6 +63,10 @@ config X86
         select HAVE_USER_RETURN_NOTIFIER
         select HAVE_ARCH_JUMP_LABEL
         select HAVE_TEXT_POKE_SMP
+        select HAVE_GENERIC_HARDIRQS
+        select HAVE_SPARSE_IRQ
+        select GENERIC_IRQ_PROBE
+        select GENERIC_PENDING_IRQ if SMP
 
 config INSTRUCTION_DECODER
         def_bool (KPROBES || PERF_EVENTS)
@@ -204,20 +208,6 @@ config HAVE_INTEL_TXT
         def_bool y
         depends on EXPERIMENTAL && DMAR && ACPI
 
-# Use the generic interrupt handling code in kernel/irq/:
-config GENERIC_HARDIRQS
-        def_bool y
-
-config GENERIC_HARDIRQS_NO__DO_IRQ
-       def_bool y
-
-config GENERIC_IRQ_PROBE
-        def_bool y
-
-config GENERIC_PENDING_IRQ
-        def_bool y
-        depends on GENERIC_HARDIRQS && SMP
-
 config USE_GENERIC_SMP_HELPERS
         def_bool y
         depends on SMP
@@ -300,23 +290,6 @@ config X86_X2APIC
 
           If you don't know what to do here, say N.
 
-config SPARSE_IRQ
-        bool "Support sparse irq numbering"
-        depends on PCI_MSI || HT_IRQ
-        ---help---
-          This enables support for sparse irqs. This is useful for distro
-          kernels that want to define a high CONFIG_NR_CPUS value but still
-          want to have low kernel memory footprint on smaller machines.
-
-          ( Sparse IRQs can also be beneficial on NUMA boxes, as they spread
-            out the irq_desc[] array in a more NUMA-friendly way. )
-
-          If you don't know what to do here, say N.
-
-config NUMA_IRQ_DESC
-        def_bool y
-        depends on SPARSE_IRQ && NUMA
-
 config X86_MPPARSE
         bool "Enable MPS table" if ACPI
         default y
@@ -521,25 +494,6 @@ if PARAVIRT_GUEST
 
 source "arch/x86/xen/Kconfig"
 
-config VMI
-        bool "VMI Guest support (DEPRECATED)"
-        select PARAVIRT
-        depends on X86_32
-        ---help---
-          VMI provides a paravirtualized interface to the VMware ESX server
-          (it could be used by other hypervisors in theory too, but is not
-          at the moment), by linking the kernel to a GPL-ed ROM module
-          provided by the hypervisor.
-
-          As of September 2009, VMware has started a phased retirement
-          of this feature from VMware's products. Please see
-          feature-removal-schedule.txt for details.  If you are
-          planning to enable this option, please note that you cannot
-          live migrate a VMI enabled VM to a future VMware product,
-          which doesn't support VMI. So if you expect your kernel to
-          seamlessly migrate to newer VMware products, keep this
-          disabled.
-
 config KVM_CLOCK
         bool "KVM paravirtualized clock"
         select PARAVIRT
@@ -674,7 +628,7 @@ config GART_IOMMU
         bool "GART IOMMU support" if EMBEDDED
         default y
         select SWIOTLB
-        depends on X86_64 && PCI && K8_NB
+        depends on X86_64 && PCI && AMD_NB
         ---help---
           Support for full DMA access of devices with 32bit memory access only
           on systems with more than 3GB. This is usually needed for USB,
@@ -799,6 +753,17 @@ config SCHED_MC
           making when dealing with multi-core CPU chips at a cost of slightly
           increased overhead in some places. If unsure say N here.
 
+config IRQ_TIME_ACCOUNTING
+        bool "Fine granularity task level IRQ time accounting"
+        default n
+        ---help---
+          Select this option to enable fine granularity task irq time
+          accounting. This is done by reading a timestamp on each
+          transitions between softirq and hardirq state, so there can be a
+          small performance impact.
+
+          If in doubt, say N here.
+
 source "kernel/Kconfig.preempt"
 
 config X86_UP_APIC
@@ -1152,6 +1117,9 @@ config X86_PAE
 config ARCH_PHYS_ADDR_T_64BIT
         def_bool X86_64 || X86_PAE
 
+config ARCH_DMA_ADDR_T_64BIT
+        def_bool X86_64 || HIGHMEM64G
+
 config DIRECT_GBPAGES
         bool "Enable 1GB pages for kernel pagetables" if EMBEDDED
         default y
@@ -1330,25 +1298,34 @@ config X86_BOOTPARAM_MEMORY_CORRUPTION_CHECK
           Set whether the default state of memory_corruption_check is
           on or off.
 
-config X86_RESERVE_LOW_64K
-        bool "Reserve low 64K of RAM on AMI/Phoenix BIOSen"
-        default y
+config X86_RESERVE_LOW
+        int "Amount of low memory, in kilobytes, to reserve for the BIOS"
+        default 64
+        range 4 640
         ---help---
-          Reserve the first 64K of physical RAM on BIOSes that are known
-          to potentially corrupt that memory range. A numbers of BIOSes are
-          known to utilize this area during suspend/resume, so it must not
-          be used by the kernel.
+          Specify the amount of low memory to reserve for the BIOS.
+
+          The first page contains BIOS data structures that the kernel
+          must not use, so that page must always be reserved.
 
-          Set this to N if you are absolutely sure that you trust the BIOS
-          to get all its memory reservations and usages right.
+          By default we reserve the first 64K of physical RAM, as a
+          number of BIOSes are known to corrupt that memory range
+          during events such as suspend/resume or monitor cable
+          insertion, so it must not be used by the kernel.
 
-          If you have doubts about the BIOS (e.g. suspend/resume does not
-          work or there's kernel crashes after certain hardware hotplug
-          events) and it's not AMI or Phoenix, then you might want to enable
-          X86_CHECK_BIOS_CORRUPTION=y to allow the kernel to check typical
-          corruption patterns.
+          You can set this to 4 if you are absolutely sure that you
+          trust the BIOS to get all its memory reservations and usages
+          right.  If you know your BIOS have problems beyond the
+          default 64K area, you can set this to 640 to avoid using the
+          entire low memory range.
 
-          Say Y if unsure.
+          If you have doubts about the BIOS (e.g. suspend/resume does
+          not work or there's kernel crashes after certain hardware
+          hotplug events) then you might want to enable
+          X86_CHECK_BIOS_CORRUPTION=y to allow the kernel to check
+          typical corruption patterns.
+
+          Leave this to the default value of 64 if you are unsure.
 
 config MATH_EMULATION
         bool
@@ -1904,7 +1881,7 @@ config PCI_GODIRECT
         bool "Direct"
 
 config PCI_GOOLPC
-        bool "OLPC"
+        bool "OLPC XO-1"
         depends on OLPC
 
 config PCI_GOANY
@@ -2065,14 +2042,21 @@ config SCx200HR_TIMER
 config OLPC
         bool "One Laptop Per Child support"
         select GPIOLIB
+        select OLPC_OPENFIRMWARE
         ---help---
           Add support for detecting the unique features of the OLPC
           XO hardware.
 
+config OLPC_XO1
+        tristate "OLPC XO-1 support"
+        depends on OLPC && PCI
+        ---help---
+          Add support for non-essential features of the OLPC XO-1 laptop.
+
 config OLPC_OPENFIRMWARE
         bool "Support for OLPC's Open Firmware"
         depends on !X86_64 && !X86_PAE
-        default y if OLPC
+        default n
         help
           This option adds support for the implementation of Open Firmware
           that is used on the OLPC XO-1 Children's Machine.
@@ -2080,7 +2064,7 @@ config OLPC_OPENFIRMWARE
 
 endif # X86_32
 
-config K8_NB
+config AMD_NB
         def_bool y
         depends on CPU_SUP_AMD && PCI
 
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 75085080b63e..e5bb96b10f1a 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -43,6 +43,10 @@ config EARLY_PRINTK
           with klogd/syslogd or the X server. You should normally N here,
           unless you want to debug such a crash.
 
+config EARLY_PRINTK_MRST
+        bool "Early printk for MRST platform support"
+        depends on EARLY_PRINTK && X86_MRST
+
 config EARLY_PRINTK_DBGP
         bool "Early printk via EHCI debug port"
         depends on EARLY_PRINTK && PCI
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index e8c8881351b3..b02e509072a7 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -96,8 +96,12 @@ cfi := $(call as-instr,.cfi_startproc\n.cfi_rel_offset $(sp-y)$(comma)0\n.cfi_en
 # is .cfi_signal_frame supported too?
 cfi-sigframe := $(call as-instr,.cfi_startproc\n.cfi_signal_frame\n.cfi_endproc,-DCONFIG_AS_CFI_SIGNAL_FRAME=1)
 cfi-sections := $(call as-instr,.cfi_sections .debug_frame,-DCONFIG_AS_CFI_SECTIONS=1)
-KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections)
-KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections)
+
+# does binutils support specific instructions?
+asinstr := $(call as-instr,fxsaveq (%rax),-DCONFIG_AS_FXSAVEQ=1)
+
+KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr)
+KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr)
 
 LDFLAGS := -m elf_$(UTS_MACHINE)
 
diff --git a/arch/x86/include/asm/amd_iommu.h b/arch/x86/include/asm/amd_iommu.h
index 5af2982133b5..f16a2caca1e0 100644
--- a/arch/x86/include/asm/amd_iommu.h
+++ b/arch/x86/include/asm/amd_iommu.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2007-2009 Advanced Micro Devices, Inc.
+ * Copyright (C) 2007-2010 Advanced Micro Devices, Inc.
  * Author: Joerg Roedel <joerg.roedel@amd.com>
  *         Leo Duran <leo.duran@amd.com>
  *
diff --git a/arch/x86/include/asm/amd_iommu_proto.h b/arch/x86/include/asm/amd_iommu_proto.h
index cb030374b90a..916bc8111a01 100644
--- a/arch/x86/include/asm/amd_iommu_proto.h
+++ b/arch/x86/include/asm/amd_iommu_proto.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2009 Advanced Micro Devices, Inc.
+ * Copyright (C) 2009-2010 Advanced Micro Devices, Inc.
  * Author: Joerg Roedel <joerg.roedel@amd.com>
  *
  * This program is free software; you can redistribute it and/or modify it
diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h
index 08616180deaf..e3509fc303bf 100644
--- a/arch/x86/include/asm/amd_iommu_types.h
+++ b/arch/x86/include/asm/amd_iommu_types.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2007-2009 Advanced Micro Devices, Inc.
+ * Copyright (C) 2007-2010 Advanced Micro Devices, Inc.
  * Author: Joerg Roedel <joerg.roedel@amd.com>
  *         Leo Duran <leo.duran@amd.com>
  *
@@ -416,13 +416,22 @@ struct amd_iommu {
         struct dma_ops_domain *default_dom;
 
         /*
-         * This array is required to work around a potential BIOS bug.
-         * The BIOS may miss to restore parts of the PCI configuration
-         * space when the system resumes from S3. The result is that the
-         * IOMMU does not execute commands anymore which leads to system
-         * failure.
+         * We can't rely on the BIOS to restore all values on reinit, so we
+         * need to stash them
          */
-        u32 cache_cfg[4];
+
+        /* The iommu BAR */
+        u32 stored_addr_lo;
+        u32 stored_addr_hi;
+
+        /*
+         * Each iommu has 6 l1s, each of which is documented as having 0x12
+         * registers
+         */
+        u32 stored_l1[6][0x12];
+
+        /* The l2 indirect registers */
+        u32 stored_l2[0x83];
 };
 
 /*
diff --git a/arch/x86/include/asm/k8.h b/arch/x86/include/asm/amd_nb.h
index af00bd1d2089..c8517f81b21e 100644
--- a/arch/x86/include/asm/k8.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -1,5 +1,5 @@
-#ifndef _ASM_X86_K8_H
-#define _ASM_X86_K8_H
+#ifndef _ASM_X86_AMD_NB_H
+#define _ASM_X86_AMD_NB_H
 
 #include <linux/pci.h>
 
@@ -7,24 +7,27 @@ extern struct pci_device_id k8_nb_ids[];
 struct bootnode;
 
 extern int early_is_k8_nb(u32 value);
-extern struct pci_dev **k8_northbridges;
-extern int num_k8_northbridges;
 extern int cache_k8_northbridges(void);
 extern void k8_flush_garts(void);
 extern int k8_get_nodes(struct bootnode *nodes);
 extern int k8_numa_init(unsigned long start_pfn, unsigned long end_pfn);
 extern int k8_scan_nodes(void);
 
-#ifdef CONFIG_K8_NB
-extern int num_k8_northbridges;
+struct k8_northbridge_info {
+        u16 num;
+        u8 gart_supported;
+        struct pci_dev **nb_misc;
+};
+extern struct k8_northbridge_info k8_northbridges;
+
+#ifdef CONFIG_AMD_NB
 
 static inline struct pci_dev *node_to_k8_nb_misc(int node)
 {
-        return (node < num_k8_northbridges) ? k8_northbridges[node] : NULL;
+        return (node < k8_northbridges.num) ? k8_northbridges.nb_misc[node] : NULL;
 }
 
 #else
-#define num_k8_northbridges 0
 
 static inline struct pci_dev *node_to_k8_nb_misc(int node)
 {
@@ -33,4 +36,4 @@ static inline struct pci_dev *node_to_k8_nb_misc(int node)
 #endif
 
 
-#endif /* _ASM_X86_K8_H */
+#endif /* _ASM_X86_AMD_NB_H */
diff --git a/arch/x86/include/asm/apb_timer.h b/arch/x86/include/asm/apb_timer.h
index a69b1ac9eaf8..2fefa501d3ba 100644
--- a/arch/x86/include/asm/apb_timer.h
+++ b/arch/x86/include/asm/apb_timer.h
@@ -54,7 +54,6 @@ extern struct clock_event_device *global_clock_event;
 extern unsigned long apbt_quick_calibrate(void);
 extern int arch_setup_apbt_irqs(int irq, int trigger, int mask, int cpu);
 extern void apbt_setup_secondary_clock(void);
-extern unsigned int boot_cpu_id;
 
 extern struct sfi_timer_table_entry *sfi_get_mtmr(int hint);
 extern void sfi_free_mtmr(struct sfi_timer_table_entry *mtmr);
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 1fa03e04ae44..286de34b0ed6 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -252,9 +252,7 @@ static inline int apic_is_clustered_box(void)
 }
 #endif
 
-extern u8 setup_APIC_eilvt_mce(u8 vector, u8 msg_type, u8 mask);
-extern u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask);
-
+extern int setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask);
 
 #else /* !CONFIG_X86_LOCAL_APIC */
 static inline void lapic_shutdown(void) { }
diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h
index 7fe3b3060f08..a859ca461fb0 100644
--- a/arch/x86/include/asm/apicdef.h
+++ b/arch/x86/include/asm/apicdef.h
@@ -131,6 +131,7 @@
 #define APIC_EILVTn(n)  (0x500 + 0x10 * n)
 #define         APIC_EILVT_NR_AMD_K8    1       /* # of extended interrupts */
 #define         APIC_EILVT_NR_AMD_10H   4
+#define         APIC_EILVT_NR_MAX       APIC_EILVT_NR_AMD_10H
 #define         APIC_EILVT_LVTOFF(x)    (((x) >> 4) & 0xF)
 #define         APIC_EILVT_MSG_FIX      0x0
 #define         APIC_EILVT_MSG_SMI      0x2
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index b185091bf19c..4fab24de26b1 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -32,6 +32,5 @@ extern void arch_unregister_cpu(int);
 
 DECLARE_PER_CPU(int, cpu_state);
 
-extern unsigned int boot_cpu_id;
 
 #endif /* _ASM_X86_CPU_H */
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 3f76523589af..220e2ea08e80 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -152,10 +152,14 @@
 #define X86_FEATURE_3DNOWPREFETCH (6*32+ 8) /* 3DNow prefetch instructions */
 #define X86_FEATURE_OSVW        (6*32+ 9) /* OS Visible Workaround */
 #define X86_FEATURE_IBS         (6*32+10) /* Instruction Based Sampling */
-#define X86_FEATURE_SSE5        (6*32+11) /* SSE-5 */
+#define X86_FEATURE_XOP         (6*32+11) /* extended AVX instructions */
 #define X86_FEATURE_SKINIT      (6*32+12) /* SKINIT/STGI instructions */
 #define X86_FEATURE_WDT         (6*32+13) /* Watchdog timer */
+#define X86_FEATURE_LWP         (6*32+15) /* Light Weight Profiling */
+#define X86_FEATURE_FMA4        (6*32+16) /* 4 operands MAC instructions */
 #define X86_FEATURE_NODEID_MSR  (6*32+19) /* NodeId MSR */
+#define X86_FEATURE_TBM         (6*32+21) /* trailing bit manipulations */
+#define X86_FEATURE_TOPOEXT     (6*32+22) /* topology extensions CPUID leafs */
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various
@@ -180,6 +184,13 @@
 #define X86_FEATURE_LBRV        (8*32+ 6) /* AMD LBR Virtualization support */
 #define X86_FEATURE_SVML        (8*32+ 7) /* "svm_lock" AMD SVM locking MSR */
 #define X86_FEATURE_NRIPS       (8*32+ 8) /* "nrip_save" AMD SVM next_rip save */
+#define X86_FEATURE_TSCRATEMSR  (8*32+ 9) /* "tsc_scale" AMD TSC scaling support */
+#define X86_FEATURE_VMCBCLEAN   (8*32+10) /* "vmcb_clean" AMD VMCB clean bits support */
+#define X86_FEATURE_FLUSHBYASID (8*32+11) /* AMD flush-by-ASID support */
+#define X86_FEATURE_DECODEASSISTS (8*32+12) /* AMD Decode Assists support */
+#define X86_FEATURE_PAUSEFILTER (8*32+13) /* AMD filtered pause intercept */
+#define X86_FEATURE_PFTHRESHOLD (8*32+14) /* AMD pause filter threshold */
+
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
 #define X86_FEATURE_FSGSBASE    (9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
diff --git a/arch/x86/include/asm/dwarf2.h b/arch/x86/include/asm/dwarf2.h
index 733f7e91e7a9..326099199318 100644
--- a/arch/x86/include/asm/dwarf2.h
+++ b/arch/x86/include/asm/dwarf2.h
@@ -89,6 +89,16 @@
         CFI_ADJUST_CFA_OFFSET -8
         .endm
 
+        .macro pushfq_cfi
+        pushfq
+        CFI_ADJUST_CFA_OFFSET 8
+        .endm
+
+        .macro popfq_cfi
+        popfq
+        CFI_ADJUST_CFA_OFFSET -8
+        .endm
+
         .macro movq_cfi reg offset=0
         movq %\reg, \offset(%rsp)
         CFI_REL_OFFSET \reg, \offset
@@ -109,6 +119,16 @@
         CFI_ADJUST_CFA_OFFSET -4
         .endm
 
+        .macro pushfl_cfi
+        pushfl
+        CFI_ADJUST_CFA_OFFSET 4
+        .endm
+
+        .macro popfl_cfi
+        popfl
+        CFI_ADJUST_CFA_OFFSET -4
+        .endm
+
         .macro movl_cfi reg offset=0
         movl %\reg, \offset(%esp)
         CFI_REL_OFFSET \reg, \offset
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index d07b44f7d1dc..4d293dced62f 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -214,5 +214,20 @@ static inline unsigned long virt_to_fix(const unsigned long vaddr)
         BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START);
         return __virt_to_fix(vaddr);
 }
+
+/* Return an pointer with offset calculated */
+static inline unsigned long __set_fixmap_offset(enum fixed_addresses idx,
+                                phys_addr_t phys, pgprot_t flags)
+{
+        __set_fixmap(idx, phys, flags);
+        return fix_to_virt(idx) + (phys & (PAGE_SIZE - 1));
+}
+
+#define set_fixmap_offset(idx, phys)                    \
+        __set_fixmap_offset(idx, phys, PAGE_KERNEL)
+
+#define set_fixmap_offset_nocache(idx, phys)                    \
+        __set_fixmap_offset(idx, phys, PAGE_KERNEL_NOCACHE)
+
 #endif /* !__ASSEMBLY__ */
 #endif /* _ASM_X86_FIXMAP_H */
diff --git a/arch/x86/include/asm/gart.h b/arch/x86/include/asm/gart.h
index 4ac5b0f33fc1..bf357f9b25f0 100644
--- a/arch/x86/include/asm/gart.h
+++ b/arch/x86/include/asm/gart.h
@@ -17,6 +17,7 @@ extern int fix_aperture;
 #define GARTEN          (1<<0)
 #define DISGARTCPU      (1<<4)
 #define DISGARTIO       (1<<5)
+#define DISTLBWALKPRB   (1<<6)
 
 /* GART cache control register bits. */
 #define INVGART         (1<<0)
@@ -27,7 +28,6 @@ extern int fix_aperture;
 #define AMD64_GARTAPERTUREBASE  0x94
 #define AMD64_GARTTABLEBASE     0x98
 #define AMD64_GARTCACHECTL      0x9c
-#define AMD64_GARTEN            (1<<0)
 
 #ifdef CONFIG_GART_IOMMU
 extern int gart_iommu_aperture;
@@ -57,6 +57,19 @@ static inline void gart_iommu_hole_init(void)
 
 extern int agp_amd64_init(void);
 
+static inline void gart_set_size_and_enable(struct pci_dev *dev, u32 order)
+{
+        u32 ctl;
+
+        /*
+         * Don't enable translation but enable GART IO and CPU accesses.
+         * Also, set DISTLBWALKPRB since GART tables memory is UC.
+         */
+        ctl = DISTLBWALKPRB | order << 1;
+
+        pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl);
+}
+
 static inline void enable_gart_translation(struct pci_dev *dev, u64 addr)
 {
         u32 tmp, ctl;
diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h
index 1d5c08a1bdfd..2c392d663dce 100644
--- a/arch/x86/include/asm/hpet.h
+++ b/arch/x86/include/asm/hpet.h
@@ -74,10 +74,12 @@ extern void hpet_disable(void);
 extern unsigned int hpet_readl(unsigned int a);
 extern void force_hpet_resume(void);
 
-extern void hpet_msi_unmask(unsigned int irq);
-extern void hpet_msi_mask(unsigned int irq);
-extern void hpet_msi_write(unsigned int irq, struct msi_msg *msg);
-extern void hpet_msi_read(unsigned int irq, struct msi_msg *msg);
+struct irq_data;
+extern void hpet_msi_unmask(struct irq_data *data);
+extern void hpet_msi_mask(struct irq_data *data);
+struct hpet_dev;
+extern void hpet_msi_write(struct hpet_dev *hdev, struct msi_msg *msg);
+extern void hpet_msi_read(struct hpet_dev *hdev, struct msi_msg *msg);
 
 #ifdef CONFIG_PCI_MSI
 extern int arch_setup_hpet_msi(unsigned int irq, unsigned int id);
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 3a54a1ca1a02..0274ec5a7e62 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -78,6 +78,13 @@ static inline void set_io_apic_irq_attr(struct io_apic_irq_attr *irq_attr,
         irq_attr->polarity      = polarity;
 }
 
+struct irq_2_iommu {
+        struct intel_iommu *iommu;
+        u16 irte_index;
+        u16 sub_handle;
+        u8  irte_mask;
+};
+
 /*
  * This is performance-critical, we want to do it O(1)
  *
@@ -89,15 +96,17 @@ struct irq_cfg {
         cpumask_var_t           old_domain;
         u8                      vector;
         u8                      move_in_progress : 1;
+#ifdef CONFIG_INTR_REMAP
+        struct irq_2_iommu      irq_2_iommu;
+#endif
 };
 
-extern struct irq_cfg *irq_cfg(unsigned int);
 extern int assign_irq_vector(int, struct irq_cfg *, const struct cpumask *);
 extern void send_cleanup_vector(struct irq_cfg *);
 
-struct irq_desc;
-extern unsigned int set_desc_affinity(struct irq_desc *, const struct cpumask *,
-                                      unsigned int *dest_id);
+struct irq_data;
+int __ioapic_set_affinity(struct irq_data *, const struct cpumask *,
+                          unsigned int *dest_id);
 extern int IO_APIC_get_PCI_irq_vector(int bus, int devfn, int pin, struct io_apic_irq_attr *irq_attr);
 extern void setup_ioapic_dest(void);
 
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index a73a8d5a5e69..4aa2bb3b242a 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -55,6 +55,12 @@ extern int save_i387_xstate_ia32(void __user *buf);
 extern int restore_i387_xstate_ia32(void __user *buf);
 #endif
 
+#ifdef CONFIG_MATH_EMULATION
+extern void finit_soft_fpu(struct i387_soft_struct *soft);
+#else
+static inline void finit_soft_fpu(struct i387_soft_struct *soft) {}
+#endif
+
 #define X87_FSW_ES (1 << 7)     /* Exception Summary */
 
 static __always_inline __pure bool use_xsaveopt(void)
@@ -67,6 +73,11 @@ static __always_inline __pure bool use_xsave(void)
         return static_cpu_has(X86_FEATURE_XSAVE);
 }
 
+static __always_inline __pure bool use_fxsr(void)
+{
+        return static_cpu_has(X86_FEATURE_FXSR);
+}
+
 extern void __sanitize_i387_state(struct task_struct *);
 
 static inline void sanitize_i387_state(struct task_struct *tsk)
@@ -77,19 +88,11 @@ static inline void sanitize_i387_state(struct task_struct *tsk)
 }
 
 #ifdef CONFIG_X86_64
-
-/* Ignore delayed exceptions from user space */
-static inline void tolerant_fwait(void)
-{
-        asm volatile("1: fwait\n"
-                     "2:\n"
-                     _ASM_EXTABLE(1b, 2b));
-}
-
 static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
 {
         int err;
 
+        /* See comment in fxsave() below. */
         asm volatile("1:  rex64/fxrstor (%[fx])\n\t"
                      "2:\n"
                      ".section .fixup,\"ax\"\n"
@@ -98,44 +101,10 @@ static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
                      ".previous\n"
                      _ASM_EXTABLE(1b, 3b)
                      : [err] "=r" (err)
-#if 0 /* See comment in fxsave() below. */
-                     : [fx] "r" (fx), "m" (*fx), "0" (0));
-#else
-                     : [fx] "cdaSDb" (fx), "m" (*fx), "0" (0));
-#endif
+                     : [fx] "R" (fx), "m" (*fx), "0" (0));
         return err;
 }
 
-/* AMD CPUs don't save/restore FDP/FIP/FOP unless an exception
-   is pending. Clear the x87 state here by setting it to fixed
-   values. The kernel data segment can be sometimes 0 and sometimes
-   new user value. Both should be ok.
-   Use the PDA as safe address because it should be already in L1. */
-static inline void fpu_clear(struct fpu *fpu)
-{
-        struct xsave_struct *xstate = &fpu->state->xsave;
-        struct i387_fxsave_struct *fx = &fpu->state->fxsave;
-
-        /*
-         * xsave header may indicate the init state of the FP.
-         */
-        if (use_xsave() &&
-            !(xstate->xsave_hdr.xstate_bv & XSTATE_FP))
-                return;
-
-        if (unlikely(fx->swd & X87_FSW_ES))
-                asm volatile("fnclex");
-        alternative_input(ASM_NOP8 ASM_NOP2,
-                          "    emms\n"          /* clear stack tags */
-                          "    fildl %%gs:0",   /* load to clear state */
-                          X86_FEATURE_FXSAVE_LEAK);
-}
-
-static inline void clear_fpu_state(struct task_struct *tsk)
-{
-        fpu_clear(&tsk->thread.fpu);
-}
-
 static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
 {
         int err;
@@ -149,6 +118,7 @@ static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
         if (unlikely(err))
                 return -EFAULT;
 
+        /* See comment in fxsave() below. */
         asm volatile("1:  rex64/fxsave (%[fx])\n\t"
                      "2:\n"
                      ".section .fixup,\"ax\"\n"
@@ -157,11 +127,7 @@ static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
                      ".previous\n"
                      _ASM_EXTABLE(1b, 3b)
                      : [err] "=r" (err), "=m" (*fx)
-#if 0 /* See comment in fxsave() below. */
-                     : [fx] "r" (fx), "0" (0));
-#else
-                     : [fx] "cdaSDb" (fx), "0" (0));
-#endif
+                     : [fx] "R" (fx), "0" (0));
         if (unlikely(err) &&
             __clear_user(fx, sizeof(struct i387_fxsave_struct)))
                 err = -EFAULT;
@@ -175,56 +141,29 @@ static inline void fpu_fxsave(struct fpu *fpu)
            uses any extended registers for addressing, a second REX prefix
            will be generated (to the assembler, rex64 followed by semicolon
            is a separate instruction), and hence the 64-bitness is lost. */
-#if 0
+
+#ifdef CONFIG_AS_FXSAVEQ
         /* Using "fxsaveq %0" would be the ideal choice, but is only supported
            starting with gas 2.16. */
         __asm__ __volatile__("fxsaveq %0"
                              : "=m" (fpu->state->fxsave));
-#elif 0
+#else
         /* Using, as a workaround, the properly prefixed form below isn't
            accepted by any binutils version so far released, complaining that
            the same type of prefix is used twice if an extended register is
-           needed for addressing (fix submitted to mainline 2005-11-21). */
-        __asm__ __volatile__("rex64/fxsave %0"
-                             : "=m" (fpu->state->fxsave));
-#else
-        /* This, however, we can work around by forcing the compiler to select
+           needed for addressing (fix submitted to mainline 2005-11-21).
+        asm volatile("rex64/fxsave %0"
+                     : "=m" (fpu->state->fxsave));
+           This, however, we can work around by forcing the compiler to select
            an addressing mode that doesn't require extended registers. */
-        __asm__ __volatile__("rex64/fxsave (%1)"
-                             : "=m" (fpu->state->fxsave)
-                             : "cdaSDb" (&fpu->state->fxsave));
+        asm volatile("rex64/fxsave (%[fx])"
+                     : "=m" (fpu->state->fxsave)
+                     : [fx] "R" (&fpu->state->fxsave));
 #endif
 }
 
-static inline void fpu_save_init(struct fpu *fpu)
-{
-        if (use_xsave())
-                fpu_xsave(fpu);
-        else
-                fpu_fxsave(fpu);
-
-        fpu_clear(fpu);
-}
-
-static inline void __save_init_fpu(struct task_struct *tsk)
-{
-        fpu_save_init(&tsk->thread.fpu);
-        task_thread_info(tsk)->status &= ~TS_USEDFPU;
-}
-
 #else  /* CONFIG_X86_32 */
 
-#ifdef CONFIG_MATH_EMULATION
-extern void finit_soft_fpu(struct i387_soft_struct *soft);
-#else
-static inline void finit_soft_fpu(struct i387_soft_struct *soft) {}
-#endif
-
-static inline void tolerant_fwait(void)
-{
-        asm volatile("fnclex ; fwait");
-}
-
 /* perform fxrstor iff the processor has extended states, otherwise frstor */
 static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
 {
@@ -241,6 +180,14 @@ static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
         return 0;
 }
 
+static inline void fpu_fxsave(struct fpu *fpu)
+{
+        asm volatile("fxsave %[fx]"
+                     : [fx] "=m" (fpu->state->fxsave));
+}
+
+#endif  /* CONFIG_X86_64 */
+
 /* We need a safe address that is cheap to find and that is already
    in L1 during context switch. The best choices are unfortunately
    different for UP and SMP */
@@ -256,47 +203,33 @@ static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
 static inline void fpu_save_init(struct fpu *fpu)
 {
         if (use_xsave()) {
-                struct xsave_struct *xstate = &fpu->state->xsave;
-                struct i387_fxsave_struct *fx = &fpu->state->fxsave;
-
                 fpu_xsave(fpu);
 
                 /*
                  * xsave header may indicate the init state of the FP.
                  */
-                if (!(xstate->xsave_hdr.xstate_bv & XSTATE_FP))
-                        goto end;
-
-                if (unlikely(fx->swd & X87_FSW_ES))
-                        asm volatile("fnclex");
-
-                /*
-                 * we can do a simple return here or be paranoid :)
-                 */
-                goto clear_state;
+                if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP))
+                        return;
+        } else if (use_fxsr()) {
+                fpu_fxsave(fpu);
+        } else {
+                asm volatile("fsave %[fx]; fwait"
+                             : [fx] "=m" (fpu->state->fsave));
+                return;
         }
 
-        /* Use more nops than strictly needed in case the compiler
-           varies code */
-        alternative_input(
-                "fnsave %[fx] ;fwait;" GENERIC_NOP8 GENERIC_NOP4,
-                "fxsave %[fx]\n"
-                "bt $7,%[fsw] ; jnc 1f ; fnclex\n1:",
-                X86_FEATURE_FXSR,
-                [fx] "m" (fpu->state->fxsave),
-                [fsw] "m" (fpu->state->fxsave.swd) : "memory");
-clear_state:
+        if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES))
+                asm volatile("fnclex");
+
         /* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
            is pending.  Clear the x87 state here by setting it to fixed
            values. safe_address is a random variable that should be in L1 */
         alternative_input(
-                GENERIC_NOP8 GENERIC_NOP2,
+                ASM_NOP8 ASM_NOP2,
                 "emms\n\t"              /* clear stack tags */
-                "fildl %[addr]",        /* set F?P to defined value */
+                "fildl %P[addr]",       /* set F?P to defined value */
                 X86_FEATURE_FXSAVE_LEAK,
                 [addr] "m" (safe_address));
-end:
-        ;
 }
 
 static inline void __save_init_fpu(struct task_struct *tsk)
@@ -305,9 +238,6 @@ static inline void __save_init_fpu(struct task_struct *tsk)
         task_thread_info(tsk)->status &= ~TS_USEDFPU;
 }
 
-
-#endif  /* CONFIG_X86_64 */
-
 static inline int fpu_fxrstor_checking(struct fpu *fpu)
 {
         return fxrstor_checking(&fpu->state->fxsave);
@@ -344,7 +274,10 @@ static inline void __unlazy_fpu(struct task_struct *tsk)
 static inline void __clear_fpu(struct task_struct *tsk)
 {
         if (task_thread_info(tsk)->status & TS_USEDFPU) {
-                tolerant_fwait();
+                /* Ignore delayed exceptions from user space */
+                asm volatile("1: fwait\n"
+                             "2:\n"
+                             _ASM_EXTABLE(1b, 2b));
                 task_thread_info(tsk)->status &= ~TS_USEDFPU;
                 stts();
         }
@@ -405,19 +338,6 @@ static inline void irq_ts_restore(int TS_state)
                 stts();
 }
 
-#ifdef CONFIG_X86_64
-
-static inline void save_init_fpu(struct task_struct *tsk)
-{
-        __save_init_fpu(tsk);
-        stts();
-}
-
-#define unlazy_fpu      __unlazy_fpu
-#define clear_fpu       __clear_fpu
-
-#else  /* CONFIG_X86_32 */
-
 /*
  * These disable preemption on their own and are safe
  */
@@ -443,8 +363,6 @@ static inline void clear_fpu(struct task_struct *tsk)
         preempt_enable();
 }
 
-#endif  /* CONFIG_X86_64 */
-
 /*
  * i387 state interaction
  */
@@ -508,7 +426,4 @@ extern void fpu_finit(struct fpu *fpu);
 
 #endif /* __ASSEMBLY__ */
 
-#define PSHUFB_XMM5_XMM0 .byte 0x66, 0x0f, 0x38, 0x00, 0xc5
-#define PSHUFB_XMM5_XMM6 .byte 0x66, 0x0f, 0x38, 0x00, 0xf5
-
 #endif /* _ASM_X86_I387_H */
diff --git a/arch/x86/include/asm/i8259.h b/arch/x86/include/asm/i8259.h
index 1655147646aa..a20365953bf8 100644
--- a/arch/x86/include/asm/i8259.h
+++ b/arch/x86/include/asm/i8259.h
@@ -55,6 +55,8 @@ extern struct irq_chip i8259A_chip;
 struct legacy_pic {
         int nr_legacy_irqs;
         struct irq_chip *chip;
+        void (*mask)(unsigned int irq);
+        void (*unmask)(unsigned int irq);
         void (*mask_all)(void);
         void (*restore_mask)(void);
         void (*init)(int auto_eoi);
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 30a3e9776123..6a45ec41ec26 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -206,6 +206,7 @@ static inline void __iomem *ioremap(resource_size_t offset, unsigned long size)
 
 extern void iounmap(volatile void __iomem *addr);
 
+extern void set_iounmap_nonlazy(void);
 
 #ifdef __KERNEL__
 
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 9cb2edb87c2f..c8be4566c3d2 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -170,12 +170,6 @@ extern int restore_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
 
 extern void probe_nr_irqs_gsi(void);
 
-extern int setup_ioapic_entry(int apic, int irq,
-                              struct IO_APIC_route_entry *entry,
-                              unsigned int destination, int trigger,
-                              int polarity, int vector, int pin);
-extern void ioapic_write_entry(int apic, int pin,
-                               struct IO_APIC_route_entry e);
 extern void setup_ioapic_ids_from_mpc(void);
 
 struct mp_ioapic_gsi{
diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h
index f275e2244505..1c23360fb2d8 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -3,4 +3,39 @@
 
 #define IRTE_DEST(dest) ((x2apic_mode) ? dest : dest << 8)
 
+#ifdef CONFIG_INTR_REMAP
+static inline void prepare_irte(struct irte *irte, int vector,
+                                unsigned int dest)
+{
+        memset(irte, 0, sizeof(*irte));
+
+        irte->present = 1;
+        irte->dst_mode = apic->irq_dest_mode;
+        /*
+         * Trigger mode in the IRTE will always be edge, and for IO-APIC, the
+         * actual level or edge trigger will be setup in the IO-APIC
+         * RTE. This will help simplify level triggered irq migration.
+         * For more details, see the comments (in io_apic.c) explainig IO-APIC
+         * irq migration in the presence of interrupt-remapping.
+        */
+        irte->trigger_mode = 0;
+        irte->dlvry_mode = apic->irq_delivery_mode;
+        irte->vector = vector;
+        irte->dest_id = IRTE_DEST(dest);
+        irte->redir_hint = 1;
+}
+static inline bool irq_remapped(struct irq_cfg *cfg)
+{
+        return cfg->irq_2_iommu.iommu != NULL;
+}
+#else
+static void prepare_irte(struct irte *irte, int vector, unsigned int dest)
+{
+}
+static inline bool irq_remapped(struct irq_cfg *cfg)
+{
+        return false;
+}
+#endif
+
 #endif  /* _ASM_X86_IRQ_REMAPPING_H */
diff --git a/arch/x86/include/asm/mrst.h b/arch/x86/include/asm/mrst.h
index 16350740edf6..4a711a684b17 100644
--- a/arch/x86/include/asm/mrst.h
+++ b/arch/x86/include/asm/mrst.h
@@ -10,6 +10,9 @@
  */
 #ifndef _ASM_X86_MRST_H
 #define _ASM_X86_MRST_H
+
+#include <linux/sfi.h>
+
 extern int pci_mrst_init(void);
 int __init sfi_parse_mrtc(struct sfi_table_header *table);
 
@@ -26,7 +29,7 @@ enum mrst_cpu_type {
 };
 
 extern enum mrst_cpu_type __mrst_cpu_chip;
-static enum mrst_cpu_type mrst_identify_cpu(void)
+static inline enum mrst_cpu_type mrst_identify_cpu(void)
 {
         return __mrst_cpu_chip;
 }
@@ -42,4 +45,9 @@ extern enum mrst_timer_options mrst_timer_options;
 #define SFI_MTMR_MAX_NUM 8
 #define SFI_MRTC_MAX    8
 
+extern struct console early_mrst_console;
+extern void mrst_early_console_init(void);
+
+extern struct console early_hsu_console;
+extern void hsu_early_console_init(void);
 #endif /* _ASM_X86_MRST_H */
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
new file mode 100644
index 000000000000..bcdff997668c
--- /dev/null
+++ b/arch/x86/include/asm/mwait.h
@@ -0,0 +1,15 @@
+#ifndef _ASM_X86_MWAIT_H
+#define _ASM_X86_MWAIT_H
+
+#define MWAIT_SUBSTATE_MASK             0xf
+#define MWAIT_CSTATE_MASK               0xf
+#define MWAIT_SUBSTATE_SIZE             4
+#define MWAIT_MAX_NUM_CSTATES           8
+
+#define CPUID_MWAIT_LEAF                5
+#define CPUID5_ECX_EXTENSIONS_SUPPORTED 0x1
+#define CPUID5_ECX_INTERRUPT_BREAK      0x2
+
+#define MWAIT_ECX_INTERRUPT_BREAK       0x1
+
+#endif /* _ASM_X86_MWAIT_H */
diff --git a/arch/x86/include/asm/olpc_ofw.h b/arch/x86/include/asm/olpc_ofw.h
index 08fde475cb3b..2a8478140bb3 100644
--- a/arch/x86/include/asm/olpc_ofw.h
+++ b/arch/x86/include/asm/olpc_ofw.h
@@ -21,10 +21,14 @@ extern void olpc_ofw_detect(void);
 /* install OFW's pde permanently into the kernel's pgtable */
 extern void setup_olpc_ofw_pgd(void);
 
+/* check if OFW was detected during boot */
+extern bool olpc_ofw_present(void);
+
 #else /* !CONFIG_OLPC_OPENFIRMWARE */
 
 static inline void olpc_ofw_detect(void) { }
 static inline void setup_olpc_ofw_pgd(void) { }
+static inline bool olpc_ofw_present(void) { return false; }
 
 #endif /* !CONFIG_OLPC_OPENFIRMWARE */
 
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index a667f24c7254..1df66211fd1b 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -8,7 +8,7 @@
 #define PAGE_SIZE       (_AC(1,UL) << PAGE_SHIFT)
 #define PAGE_MASK       (~(PAGE_SIZE-1))
 
-#define __PHYSICAL_MASK         ((phys_addr_t)(1ULL << __PHYSICAL_MASK_SHIFT) - 1)
+#define __PHYSICAL_MASK         ((phys_addr_t)((1ULL << __PHYSICAL_MASK_SHIFT) - 1))
 #define __VIRTUAL_MASK          ((1UL << __VIRTUAL_MASK_SHIFT) - 1)
 
 /* Cast PAGE_MASK to a signed type so that it is sign-extended if
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 5653f43d90e5..edecb4ed2210 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -416,11 +416,6 @@ static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn)
         PVOP_VCALL2(pv_mmu_ops.alloc_pmd, mm, pfn);
 }
 
-static inline void paravirt_alloc_pmd_clone(unsigned long pfn, unsigned long clonepfn,
-                                            unsigned long start, unsigned long count)
-{
-        PVOP_VCALL4(pv_mmu_ops.alloc_pmd_clone, pfn, clonepfn, start, count);
-}
 static inline void paravirt_release_pmd(unsigned long pfn)
 {
         PVOP_VCALL1(pv_mmu_ops.release_pmd, pfn);
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index db9ef5532341..b82bac975250 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -255,7 +255,6 @@ struct pv_mmu_ops {
          */
         void (*alloc_pte)(struct mm_struct *mm, unsigned long pfn);
         void (*alloc_pmd)(struct mm_struct *mm, unsigned long pfn);
-        void (*alloc_pmd_clone)(unsigned long pfn, unsigned long clonepfn, unsigned long start, unsigned long count);
         void (*alloc_pud)(struct mm_struct *mm, unsigned long pfn);
         void (*release_pte)(unsigned long pfn);
         void (*release_pmd)(unsigned long pfn);
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index a34c785c5a63..ada823a13c7c 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -28,6 +28,8 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 extern spinlock_t pgd_lock;
 extern struct list_head pgd_list;
 
+extern struct mm_struct *pgd_page_get_mm(struct page *page);
+
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #else  /* !CONFIG_PARAVIRT */
@@ -603,6 +605,8 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm,
         pte_update(mm, addr, ptep);
 }
 
+#define flush_tlb_fix_spurious_fault(vma, address)
+
 /*
  * clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
  *
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 076052cd62be..f96ac9bedf75 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -102,6 +102,8 @@ static inline void native_pgd_clear(pgd_t *pgd)
         native_set_pgd(pgd, native_make_pgd(0));
 }
 
+extern void sync_global_pgds(unsigned long start, unsigned long end);
+
 /*
  * Conversion functions: convert a page and protection to a page entry,
  * and a page entry and page directory to the page they refer to.
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 325b7bdbebaa..cae9c3cb95cf 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -110,6 +110,8 @@ struct cpuinfo_x86 {
         u16                     phys_proc_id;
         /* Core id: */
         u16                     cpu_core_id;
+        /* Compute unit id */
+        u8                      compute_unit_id;
         /* Index into per_cpu list: */
         u16                     cpu_index;
 #endif
@@ -602,7 +604,7 @@ extern unsigned long		mmu_cr4_features;
 
 static inline void set_in_cr4(unsigned long mask)
 {
-        unsigned cr4;
+        unsigned long cr4;
 
         mmu_cr4_features |= mask;
         cr4 = read_cr4();
@@ -612,7 +614,7 @@ static inline void set_in_cr4(unsigned long mask)
 
 static inline void clear_in_cr4(unsigned long mask)
 {
-        unsigned cr4;
+        unsigned long cr4;
 
         mmu_cr4_features &= ~mask;
         cr4 = read_cr4();
@@ -764,29 +766,6 @@ extern unsigned long		idle_halt;
 extern unsigned long            idle_nomwait;
 extern bool                     c1e_detected;
 
-/*
- * on systems with caches, caches must be flashed as the absolute
- * last instruction before going into a suspended halt.  Otherwise,
- * dirty data can linger in the cache and become stale on resume,
- * leading to strange errors.
- *
- * perform a variety of operations to guarantee that the compiler
- * will not reorder instructions.  wbinvd itself is serializing
- * so the processor will not reorder.
- *
- * Systems without cache can just go into halt.
- */
-static inline void wbinvd_halt(void)
-{
-        mb();
-        /* check for clflush to determine if wbinvd is legal */
-        if (cpu_has_clflush)
-                asm volatile("cli; wbinvd; 1: hlt; jmp 1b" : : : "memory");
-        else
-                while (1)
-                        halt();
-}
-
 extern void enable_sep_cpu(void);
 extern int sysenter_setup(void);
 
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index ef292c792d74..d6763b139a84 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -93,6 +93,11 @@ void *extend_brk(size_t size, size_t align);
                         : : "i" (sz));                                  \
         }
 
+/* Helper for reserving space for arrays of things */
+#define RESERVE_BRK_ARRAY(type, name, entries)          \
+        type *name;                                     \
+        RESERVE_BRK(name, sizeof(type) * entries)
+
 #ifdef __i386__
 
 void __init i386_start_kernel(void);
diff --git a/arch/x86/include/asm/vmi.h b/arch/x86/include/asm/vmi.h
deleted file mode 100644
index 61e08c0a2907..000000000000
--- a/arch/x86/include/asm/vmi.h
+++ /dev/null
@@ -1,269 +0,0 @@
-/*
- * VMI interface definition
- *
- * Copyright (C) 2005, VMware, Inc.
- *
- * 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, GOOD TITLE or
- * NON INFRINGEMENT.  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., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * Maintained by: Zachary Amsden zach@vmware.com
- *
- */
-#include <linux/types.h>
-
-/*
- *---------------------------------------------------------------------
- *
- *  VMI Option ROM API
- *
- *---------------------------------------------------------------------
- */
-#define VMI_SIGNATURE 0x696d5663   /* "cVmi" */
-
-#define PCI_VENDOR_ID_VMWARE            0x15AD
-#define PCI_DEVICE_ID_VMWARE_VMI        0x0801
-
-/*
- * We use two version numbers for compatibility, with the major
- * number signifying interface breakages, and the minor number
- * interface extensions.
- */
-#define VMI_API_REV_MAJOR       3
-#define VMI_API_REV_MINOR       0
-
-#define VMI_CALL_CPUID                  0
-#define VMI_CALL_WRMSR                  1
-#define VMI_CALL_RDMSR                  2
-#define VMI_CALL_SetGDT                 3
-#define VMI_CALL_SetLDT                 4
-#define VMI_CALL_SetIDT                 5
-#define VMI_CALL_SetTR                  6
-#define VMI_CALL_GetGDT                 7
-#define VMI_CALL_GetLDT                 8
-#define VMI_CALL_GetIDT                 9
-#define VMI_CALL_GetTR                  10
-#define VMI_CALL_WriteGDTEntry          11
-#define VMI_CALL_WriteLDTEntry          12
-#define VMI_CALL_WriteIDTEntry          13
-#define VMI_CALL_UpdateKernelStack      14
-#define VMI_CALL_SetCR0                 15
-#define VMI_CALL_SetCR2                 16
-#define VMI_CALL_SetCR3                 17
-#define VMI_CALL_SetCR4                 18
-#define VMI_CALL_GetCR0                 19
-#define VMI_CALL_GetCR2                 20
-#define VMI_CALL_GetCR3                 21
-#define VMI_CALL_GetCR4                 22
-#define VMI_CALL_WBINVD                 23
-#define VMI_CALL_SetDR                  24
-#define VMI_CALL_GetDR                  25
-#define VMI_CALL_RDPMC                  26
-#define VMI_CALL_RDTSC                  27
-#define VMI_CALL_CLTS                   28
-#define VMI_CALL_EnableInterrupts       29
-#define VMI_CALL_DisableInterrupts      30
-#define VMI_CALL_GetInterruptMask       31
-#define VMI_CALL_SetInterruptMask       32
-#define VMI_CALL_IRET                   33
-#define VMI_CALL_SYSEXIT                34
-#define VMI_CALL_Halt                   35
-#define VMI_CALL_Reboot                 36
-#define VMI_CALL_Shutdown               37
-#define VMI_CALL_SetPxE                 38
-#define VMI_CALL_SetPxELong             39
-#define VMI_CALL_UpdatePxE              40
-#define VMI_CALL_UpdatePxELong          41
-#define VMI_CALL_MachineToPhysical      42
-#define VMI_CALL_PhysicalToMachine      43
-#define VMI_CALL_AllocatePage           44
-#define VMI_CALL_ReleasePage            45
-#define VMI_CALL_InvalPage              46
-#define VMI_CALL_FlushTLB               47
-#define VMI_CALL_SetLinearMapping       48
-
-#define VMI_CALL_SetIOPLMask            61
-#define VMI_CALL_SetInitialAPState      62
-#define VMI_CALL_APICWrite              63
-#define VMI_CALL_APICRead               64
-#define VMI_CALL_IODelay                65
-#define VMI_CALL_SetLazyMode            73
-
-/*
- *---------------------------------------------------------------------
- *
- * MMU operation flags
- *
- *---------------------------------------------------------------------
- */
-
-/* Flags used by VMI_{Allocate|Release}Page call */
-#define VMI_PAGE_PAE             0x10  /* Allocate PAE shadow */
-#define VMI_PAGE_CLONE           0x20  /* Clone from another shadow */
-#define VMI_PAGE_ZEROED          0x40  /* Page is pre-zeroed */
-
-
-/* Flags shared by Allocate|Release Page and PTE updates */
-#define VMI_PAGE_PT              0x01
-#define VMI_PAGE_PD              0x02
-#define VMI_PAGE_PDP             0x04
-#define VMI_PAGE_PML4            0x08
-
-#define VMI_PAGE_NORMAL          0x00 /* for debugging */
-
-/* Flags used by PTE updates */
-#define VMI_PAGE_CURRENT_AS      0x10 /* implies VMI_PAGE_VA_MASK is valid */
-#define VMI_PAGE_DEFER           0x20 /* may queue update until TLB inval */
-#define VMI_PAGE_VA_MASK         0xfffff000
-
-#ifdef CONFIG_X86_PAE
-#define VMI_PAGE_L1             (VMI_PAGE_PT | VMI_PAGE_PAE | VMI_PAGE_ZEROED)
-#define VMI_PAGE_L2             (VMI_PAGE_PD | VMI_PAGE_PAE | VMI_PAGE_ZEROED)
-#else
-#define VMI_PAGE_L1             (VMI_PAGE_PT | VMI_PAGE_ZEROED)
-#define VMI_PAGE_L2             (VMI_PAGE_PD | VMI_PAGE_ZEROED)
-#endif
-
-/* Flags used by VMI_FlushTLB call */
-#define VMI_FLUSH_TLB            0x01
-#define VMI_FLUSH_GLOBAL         0x02
-
-/*
- *---------------------------------------------------------------------
- *
- *  VMI relocation definitions for ROM call get_reloc
- *
- *---------------------------------------------------------------------
- */
-
-/* VMI Relocation types */
-#define VMI_RELOCATION_NONE     0
-#define VMI_RELOCATION_CALL_REL 1
-#define VMI_RELOCATION_JUMP_REL 2
-#define VMI_RELOCATION_NOP      3
-
-#ifndef __ASSEMBLY__
-struct vmi_relocation_info {
-        unsigned char           *eip;
-        unsigned char           type;
-        unsigned char           reserved[3];
-};
-#endif
-
-
-/*
- *---------------------------------------------------------------------
- *
- *  Generic ROM structures and definitions
- *
- *---------------------------------------------------------------------
- */
-
-#ifndef __ASSEMBLY__
-
-struct vrom_header {
-        u16     rom_signature;  /* option ROM signature */
-        u8      rom_length;     /* ROM length in 512 byte chunks */
-        u8      rom_entry[4];   /* 16-bit code entry point */
-        u8      rom_pad0;       /* 4-byte align pad */
-        u32     vrom_signature; /* VROM identification signature */
-        u8      api_version_min;/* Minor version of API */
-        u8      api_version_maj;/* Major version of API */
-        u8      jump_slots;     /* Number of jump slots */
-        u8      reserved1;      /* Reserved for expansion */
-        u32     virtual_top;    /* Hypervisor virtual address start */
-        u16     reserved2;      /* Reserved for expansion */
-        u16     license_offs;   /* Offset to License string */
-        u16     pci_header_offs;/* Offset to PCI OPROM header */
-        u16     pnp_header_offs;/* Offset to PnP OPROM header */
-        u32     rom_pad3;       /* PnP reserverd / VMI reserved */
-        u8      reserved[96];   /* Reserved for headers */
-        char    vmi_init[8];    /* VMI_Init jump point */
-        char    get_reloc[8];   /* VMI_GetRelocationInfo jump point */
-} __attribute__((packed));
-
-struct pnp_header {
-        char sig[4];
-        char rev;
-        char size;
-        short next;
-        short res;
-        long devID;
-        unsigned short manufacturer_offset;
-        unsigned short product_offset;
-} __attribute__((packed));
-
-struct pci_header {
-        char sig[4];
-        short vendorID;
-        short deviceID;
-        short vpdData;
-        short size;
-        char rev;
-        char class;
-        char subclass;
-        char interface;
-        short chunks;
-        char rom_version_min;
-        char rom_version_maj;
-        char codetype;
-        char lastRom;
-        short reserved;
-} __attribute__((packed));
-
-/* Function prototypes for bootstrapping */
-#ifdef CONFIG_VMI
-extern void vmi_init(void);
-extern void vmi_activate(void);
-extern void vmi_bringup(void);
-#else
-static inline void vmi_init(void) {}
-static inline void vmi_activate(void) {}
-static inline void vmi_bringup(void) {}
-#endif
-
-/* State needed to start an application processor in an SMP system. */
-struct vmi_ap_state {
-        u32 cr0;
-        u32 cr2;
-        u32 cr3;
-        u32 cr4;
-
-        u64 efer;
-
-        u32 eip;
-        u32 eflags;
-        u32 eax;
-        u32 ebx;
-        u32 ecx;
-        u32 edx;
-        u32 esp;
-        u32 ebp;
-        u32 esi;
-        u32 edi;
-        u16 cs;
-        u16 ss;
-        u16 ds;
-        u16 es;
-        u16 fs;
-        u16 gs;
-        u16 ldtr;
-
-        u16 gdtr_limit;
-        u32 gdtr_base;
-        u32 idtr_base;
-        u16 idtr_limit;
-};
-
-#endif
diff --git a/arch/x86/include/asm/vmi_time.h b/arch/x86/include/asm/vmi_time.h
deleted file mode 100644
index c6e0bee93e3c..000000000000
--- a/arch/x86/include/asm/vmi_time.h
+++ /dev/null
@@ -1,98 +0,0 @@
-/*
- * VMI Time wrappers
- *
- * Copyright (C) 2006, VMware, Inc.
- *
- * 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, GOOD TITLE or
- * NON INFRINGEMENT.  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., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * Send feedback to dhecht@vmware.com
- *
- */
-
-#ifndef _ASM_X86_VMI_TIME_H
-#define _ASM_X86_VMI_TIME_H
-
-/*
- * Raw VMI call indices for timer functions
- */
-#define VMI_CALL_GetCycleFrequency      66
-#define VMI_CALL_GetCycleCounter        67
-#define VMI_CALL_SetAlarm               68
-#define VMI_CALL_CancelAlarm            69
-#define VMI_CALL_GetWallclockTime       70
-#define VMI_CALL_WallclockUpdated       71
-
-/* Cached VMI timer operations */
-extern struct vmi_timer_ops {
-        u64 (*get_cycle_frequency)(void);
-        u64 (*get_cycle_counter)(int);
-        u64 (*get_wallclock)(void);
-        int (*wallclock_updated)(void);
-        void (*set_alarm)(u32 flags, u64 expiry, u64 period);
-        void (*cancel_alarm)(u32 flags);
-} vmi_timer_ops;
-
-/* Prototypes */
-extern void __init vmi_time_init(void);
-extern unsigned long vmi_get_wallclock(void);
-extern int vmi_set_wallclock(unsigned long now);
-extern unsigned long long vmi_sched_clock(void);
-extern unsigned long vmi_tsc_khz(void);
-
-#ifdef CONFIG_X86_LOCAL_APIC
-extern void __devinit vmi_time_bsp_init(void);
-extern void __devinit vmi_time_ap_init(void);
-#endif
-
-/*
- * When run under a hypervisor, a vcpu is always in one of three states:
- * running, halted, or ready.  The vcpu is in the 'running' state if it
- * is executing.  When the vcpu executes the halt interface, the vcpu
- * enters the 'halted' state and remains halted until there is some work
- * pending for the vcpu (e.g. an alarm expires, host I/O completes on
- * behalf of virtual I/O).  At this point, the vcpu enters the 'ready'
- * state (waiting for the hypervisor to reschedule it).  Finally, at any
- * time when the vcpu is not in the 'running' state nor the 'halted'
- * state, it is in the 'ready' state.
- *
- * Real time is advances while the vcpu is 'running', 'ready', or
- * 'halted'.  Stolen time is the time in which the vcpu is in the
- * 'ready' state.  Available time is the remaining time -- the vcpu is
- * either 'running' or 'halted'.
- *
- * All three views of time are accessible through the VMI cycle
- * counters.
- */
-
-/* The cycle counters. */
-#define VMI_CYCLES_REAL         0
-#define VMI_CYCLES_AVAILABLE    1
-#define VMI_CYCLES_STOLEN       2
-
-/* The alarm interface 'flags' bits */
-#define VMI_ALARM_COUNTERS      2
-
-#define VMI_ALARM_COUNTER_MASK  0x000000ff
-
-#define VMI_ALARM_WIRED_IRQ0    0x00000000
-#define VMI_ALARM_WIRED_LVTT    0x00010000
-
-#define VMI_ALARM_IS_ONESHOT    0x00000000
-#define VMI_ALARM_IS_PERIODIC   0x00000100
-
-#define CONFIG_VMI_ALARM_HZ     100
-
-#endif /* _ASM_X86_VMI_TIME_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 7490bf8d1459..80a93dc99076 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -86,15 +86,15 @@ obj-$(CONFIG_DOUBLEFAULT) 	+= doublefault_32.o
 obj-$(CONFIG_KGDB)              += kgdb.o
 obj-$(CONFIG_VM86)              += vm86_32.o
 obj-$(CONFIG_EARLY_PRINTK)      += early_printk.o
+obj-$(CONFIG_EARLY_PRINTK_MRST) += early_printk_mrst.o
 
 obj-$(CONFIG_HPET_TIMER)        += hpet.o
 obj-$(CONFIG_APB_TIMER)         += apb_timer.o
 
-obj-$(CONFIG_K8_NB)             += k8.o
+obj-$(CONFIG_AMD_NB)            += amd_nb.o
 obj-$(CONFIG_DEBUG_RODATA_TEST) += test_rodata.o
 obj-$(CONFIG_DEBUG_NX_TEST)     += test_nx.o
 
-obj-$(CONFIG_VMI)               += vmi_32.o vmiclock_32.o
 obj-$(CONFIG_KVM_GUEST)         += kvm.o
 obj-$(CONFIG_KVM_CLOCK)         += kvmclock.o
 obj-$(CONFIG_PARAVIRT)          += paravirt.o paravirt_patch_$(BITS).o
@@ -107,6 +107,7 @@ obj-$(CONFIG_SCx200)		+= scx200.o
 scx200-y                        += scx200_32.o
 
 obj-$(CONFIG_OLPC)              += olpc.o
+obj-$(CONFIG_OLPC_XO1)          += olpc-xo1.o
 obj-$(CONFIG_OLPC_OPENFIRMWARE) += olpc_ofw.o
 obj-$(CONFIG_X86_MRST)          += mrst.o
 
@@ -123,7 +124,6 @@ obj-$(CONFIG_SWIOTLB)			+= pci-swiotlb.o
 # 64 bit specific files
 ifeq ($(CONFIG_X86_64),y)
         obj-$(CONFIG_X86_UV)            += tlb_uv.o bios_uv.o uv_irq.o uv_sysfs.o uv_time.o
-        obj-$(CONFIG_X86_PM_TIMER)      += pmtimer_64.o
         obj-$(CONFIG_AUDIT)             += audit_64.o
 
         obj-$(CONFIG_GART_IOMMU)        += pci-gart_64.o aperture_64.o
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index fb16f17e59be..5812404a0d4c 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -13,6 +13,7 @@
 
 #include <acpi/processor.h>
 #include <asm/acpi.h>
+#include <asm/mwait.h>
 
 /*
  * Initialize bm_flags based on the CPU cache properties
@@ -65,16 +66,6 @@ static struct cstate_entry __percpu *cpu_cstate_entry;	/* per CPU ptr */
 
 static short mwait_supported[ACPI_PROCESSOR_MAX_POWER];
 
-#define MWAIT_SUBSTATE_MASK     (0xf)
-#define MWAIT_CSTATE_MASK       (0xf)
-#define MWAIT_SUBSTATE_SIZE     (4)
-
-#define CPUID_MWAIT_LEAF (5)
-#define CPUID5_ECX_EXTENSIONS_SUPPORTED (0x1)
-#define CPUID5_ECX_INTERRUPT_BREAK      (0x2)
-
-#define MWAIT_ECX_INTERRUPT_BREAK       (0x1)
-
 #define NATIVE_CSTATE_BEYOND_HALT       (2)
 
 static long acpi_processor_ffh_cstate_probe_cpu(void *_cx)
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index 679b6450382b..d2fdb0826df2 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2007-2009 Advanced Micro Devices, Inc.
+ * Copyright (C) 2007-2010 Advanced Micro Devices, Inc.
  * Author: Joerg Roedel <joerg.roedel@amd.com>
  *         Leo Duran <leo.duran@amd.com>
  *
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 5a170cbbbed8..3cb482e123de 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2007-2009 Advanced Micro Devices, Inc.
+ * Copyright (C) 2007-2010 Advanced Micro Devices, Inc.
  * Author: Joerg Roedel <joerg.roedel@amd.com>
  *         Leo Duran <leo.duran@amd.com>
  *
@@ -194,6 +194,39 @@ static inline unsigned long tbl_size(int entry_size)
         return 1UL << shift;
 }
 
+/* Access to l1 and l2 indexed register spaces */
+
+static u32 iommu_read_l1(struct amd_iommu *iommu, u16 l1, u8 address)
+{
+        u32 val;
+
+        pci_write_config_dword(iommu->dev, 0xf8, (address | l1 << 16));
+        pci_read_config_dword(iommu->dev, 0xfc, &val);
+        return val;
+}
+
+static void iommu_write_l1(struct amd_iommu *iommu, u16 l1, u8 address, u32 val)
+{
+        pci_write_config_dword(iommu->dev, 0xf8, (address | l1 << 16 | 1 << 31));
+        pci_write_config_dword(iommu->dev, 0xfc, val);
+        pci_write_config_dword(iommu->dev, 0xf8, (address | l1 << 16));
+}
+
+static u32 iommu_read_l2(struct amd_iommu *iommu, u8 address)
+{
+        u32 val;
+
+        pci_write_config_dword(iommu->dev, 0xf0, address);
+        pci_read_config_dword(iommu->dev, 0xf4, &val);
+        return val;
+}
+
+static void iommu_write_l2(struct amd_iommu *iommu, u8 address, u32 val)
+{
+        pci_write_config_dword(iommu->dev, 0xf0, (address | 1 << 8));
+        pci_write_config_dword(iommu->dev, 0xf4, val);
+}
+
 /****************************************************************************
  *
  * AMD IOMMU MMIO register space handling functions
@@ -619,6 +652,7 @@ static void __init init_iommu_from_pci(struct amd_iommu *iommu)
 {
         int cap_ptr = iommu->cap_ptr;
         u32 range, misc;
+        int i, j;
 
         pci_read_config_dword(iommu->dev, cap_ptr + MMIO_CAP_HDR_OFFSET,
                               &iommu->cap);
@@ -633,12 +667,29 @@ static void __init init_iommu_from_pci(struct amd_iommu *iommu)
                                         MMIO_GET_LD(range));
         iommu->evt_msi_num = MMIO_MSI_NUM(misc);
 
-        if (is_rd890_iommu(iommu->dev)) {
-                pci_read_config_dword(iommu->dev, 0xf0, &iommu->cache_cfg[0]);
-                pci_read_config_dword(iommu->dev, 0xf4, &iommu->cache_cfg[1]);
-                pci_read_config_dword(iommu->dev, 0xf8, &iommu->cache_cfg[2]);
-                pci_read_config_dword(iommu->dev, 0xfc, &iommu->cache_cfg[3]);
-        }
+        if (!is_rd890_iommu(iommu->dev))
+                return;
+
+        /*
+         * Some rd890 systems may not be fully reconfigured by the BIOS, so
+         * it's necessary for us to store this information so it can be
+         * reprogrammed on resume
+         */
+
+        pci_read_config_dword(iommu->dev, iommu->cap_ptr + 4,
+                              &iommu->stored_addr_lo);
+        pci_read_config_dword(iommu->dev, iommu->cap_ptr + 8,
+                              &iommu->stored_addr_hi);
+
+        /* Low bit locks writes to configuration space */
+        iommu->stored_addr_lo &= ~1;
+
+        for (i = 0; i < 6; i++)
+                for (j = 0; j < 0x12; j++)
+                        iommu->stored_l1[i][j] = iommu_read_l1(iommu, i, j);
+
+        for (i = 0; i < 0x83; i++)
+                iommu->stored_l2[i] = iommu_read_l2(iommu, i);
 }
 
 /*
@@ -1127,14 +1178,53 @@ static void iommu_init_flags(struct amd_iommu *iommu)
         iommu_feature_enable(iommu, CONTROL_COHERENT_EN);
 }
 
-static void iommu_apply_quirks(struct amd_iommu *iommu)
+static void iommu_apply_resume_quirks(struct amd_iommu *iommu)
 {
-        if (is_rd890_iommu(iommu->dev)) {
-                pci_write_config_dword(iommu->dev, 0xf0, iommu->cache_cfg[0]);
-                pci_write_config_dword(iommu->dev, 0xf4, iommu->cache_cfg[1]);
-                pci_write_config_dword(iommu->dev, 0xf8, iommu->cache_cfg[2]);
-                pci_write_config_dword(iommu->dev, 0xfc, iommu->cache_cfg[3]);
-        }
+        int i, j;
+        u32 ioc_feature_control;
+        struct pci_dev *pdev = NULL;
+
+        /* RD890 BIOSes may not have completely reconfigured the iommu */
+        if (!is_rd890_iommu(iommu->dev))
+                return;
+
+        /*
+         * First, we need to ensure that the iommu is enabled. This is
+         * controlled by a register in the northbridge
+         */
+        pdev = pci_get_bus_and_slot(iommu->dev->bus->number, PCI_DEVFN(0, 0));
+
+        if (!pdev)
+                return;
+
+        /* Select Northbridge indirect register 0x75 and enable writing */
+        pci_write_config_dword(pdev, 0x60, 0x75 | (1 << 7));
+        pci_read_config_dword(pdev, 0x64, &ioc_feature_control);
+
+        /* Enable the iommu */
+        if (!(ioc_feature_control & 0x1))
+                pci_write_config_dword(pdev, 0x64, ioc_feature_control | 1);
+
+        pci_dev_put(pdev);
+
+        /* Restore the iommu BAR */
+        pci_write_config_dword(iommu->dev, iommu->cap_ptr + 4,
+                               iommu->stored_addr_lo);
+        pci_write_config_dword(iommu->dev, iommu->cap_ptr + 8,
+                               iommu->stored_addr_hi);
+
+        /* Restore the l1 indirect regs for each of the 6 l1s */
+        for (i = 0; i < 6; i++)
+                for (j = 0; j < 0x12; j++)
+                        iommu_write_l1(iommu, i, j, iommu->stored_l1[i][j]);
+
+        /* Restore the l2 indirect regs */
+        for (i = 0; i < 0x83; i++)
+                iommu_write_l2(iommu, i, iommu->stored_l2[i]);
+
+        /* Lock PCI setup registers */
+        pci_write_config_dword(iommu->dev, iommu->cap_ptr + 4,
+                               iommu->stored_addr_lo | 1);
 }
 
 /*
@@ -1147,7 +1237,6 @@ static void enable_iommus(void)
 
         for_each_iommu(iommu) {
                 iommu_disable(iommu);
-                iommu_apply_quirks(iommu);
                 iommu_init_flags(iommu);
                 iommu_set_device_table(iommu);
                 iommu_enable_command_buffer(iommu);
@@ -1173,6 +1262,11 @@ static void disable_iommus(void)
 
 static int amd_iommu_resume(struct sys_device *dev)
 {
+        struct amd_iommu *iommu;
+
+        for_each_iommu(iommu)
+                iommu_apply_resume_quirks(iommu);
+
         /* re-load the hardware */
         enable_iommus();
 
diff --git a/arch/x86/kernel/k8.c b/arch/x86/kernel/amd_nb.c
index 0f7bc20cfcde..8f6463d8ed0d 100644
--- a/arch/x86/kernel/k8.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -8,21 +8,19 @@
 #include <linux/errno.h>
 #include <linux/module.h>
 #include <linux/spinlock.h>
-#include <asm/k8.h>
-
-int num_k8_northbridges;
-EXPORT_SYMBOL(num_k8_northbridges);
+#include <asm/amd_nb.h>
 
 static u32 *flush_words;
 
 struct pci_device_id k8_nb_ids[] = {
         { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) },
         { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) },
+        { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_MISC) },
         {}
 };
 EXPORT_SYMBOL(k8_nb_ids);
 
-struct pci_dev **k8_northbridges;
+struct k8_northbridge_info k8_northbridges;
 EXPORT_SYMBOL(k8_northbridges);
 
 static struct pci_dev *next_k8_northbridge(struct pci_dev *dev)
@@ -40,36 +38,45 @@ int cache_k8_northbridges(void)
         int i;
         struct pci_dev *dev;
 
-        if (num_k8_northbridges)
+        if (k8_northbridges.num)
                 return 0;
 
         dev = NULL;
         while ((dev = next_k8_northbridge(dev)) != NULL)
-                num_k8_northbridges++;
+                k8_northbridges.num++;
+
+        /* some CPU families (e.g. family 0x11) do not support GART */
+        if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 ||
+            boot_cpu_data.x86 == 0x15)
+                k8_northbridges.gart_supported = 1;
 
-        k8_northbridges = kmalloc((num_k8_northbridges + 1) * sizeof(void *),
-                                  GFP_KERNEL);
-        if (!k8_northbridges)
+        k8_northbridges.nb_misc = kmalloc((k8_northbridges.num + 1) *
+                                          sizeof(void *), GFP_KERNEL);
+        if (!k8_northbridges.nb_misc)
                 return -ENOMEM;
 
-        if (!num_k8_northbridges) {
-                k8_northbridges[0] = NULL;
+        if (!k8_northbridges.num) {
+                k8_northbridges.nb_misc[0] = NULL;
                 return 0;
         }
 
-        flush_words = kmalloc(num_k8_northbridges * sizeof(u32), GFP_KERNEL);
-        if (!flush_words) {
-                kfree(k8_northbridges);
-                return -ENOMEM;
+        if (k8_northbridges.gart_supported) {
+                flush_words = kmalloc(k8_northbridges.num * sizeof(u32),
+                                      GFP_KERNEL);
+                if (!flush_words) {
+                        kfree(k8_northbridges.nb_misc);
+                        return -ENOMEM;
+                }
         }
 
         dev = NULL;
         i = 0;
         while ((dev = next_k8_northbridge(dev)) != NULL) {
-                k8_northbridges[i] = dev;
-                pci_read_config_dword(dev, 0x9c, &flush_words[i++]);
+                k8_northbridges.nb_misc[i] = dev;
+                if (k8_northbridges.gart_supported)
+                        pci_read_config_dword(dev, 0x9c, &flush_words[i++]);
         }
-        k8_northbridges[i] = NULL;
+        k8_northbridges.nb_misc[i] = NULL;
         return 0;
 }
 EXPORT_SYMBOL_GPL(cache_k8_northbridges);
@@ -93,22 +100,25 @@ void k8_flush_garts(void)
         unsigned long flags;
         static DEFINE_SPINLOCK(gart_lock);
 
+        if (!k8_northbridges.gart_supported)
+                return;
+
         /* Avoid races between AGP and IOMMU. In theory it's not needed
            but I'm not sure if the hardware won't lose flush requests
            when another is pending. This whole thing is so expensive anyways
            that it doesn't matter to serialize more. -AK */
         spin_lock_irqsave(&gart_lock, flags);
         flushed = 0;
-        for (i = 0; i < num_k8_northbridges; i++) {
-                pci_write_config_dword(k8_northbridges[i], 0x9c,
+        for (i = 0; i < k8_northbridges.num; i++) {
+                pci_write_config_dword(k8_northbridges.nb_misc[i], 0x9c,
                                        flush_words[i]|1);
                 flushed++;
         }
-        for (i = 0; i < num_k8_northbridges; i++) {
+        for (i = 0; i < k8_northbridges.num; i++) {
                 u32 w;
                 /* Make sure the hardware actually executed the flush*/
                 for (;;) {
-                        pci_read_config_dword(k8_northbridges[i],
+                        pci_read_config_dword(k8_northbridges.nb_misc[i],
                                               0x9c, &w);
                         if (!(w & 1))
                                 break;
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index 8dd77800ff5d..92543c73cf8e 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -231,34 +231,6 @@ static void apbt_restart_clocksource(struct clocksource *cs)
         apbt_start_counter(phy_cs_timer_id);
 }
 
-/* Setup IRQ routing via IOAPIC */
-#ifdef CONFIG_SMP
-static void apbt_setup_irq(struct apbt_dev *adev)
-{
-        struct irq_chip *chip;
-        struct irq_desc *desc;
-
-        /* timer0 irq has been setup early */
-        if (adev->irq == 0)
-                return;
-        desc = irq_to_desc(adev->irq);
-        chip = get_irq_chip(adev->irq);
-        disable_irq(adev->irq);
-        desc->status |= IRQ_MOVE_PCNTXT;
-        irq_set_affinity(adev->irq, cpumask_of(adev->cpu));
-        /* APB timer irqs are set up as mp_irqs, timer is edge triggerred */
-        set_irq_chip_and_handler_name(adev->irq, chip, handle_edge_irq, "edge");
-        enable_irq(adev->irq);
-        if (system_state == SYSTEM_BOOTING)
-                if (request_irq(adev->irq, apbt_interrupt_handler,
-                                IRQF_TIMER | IRQF_DISABLED | IRQF_NOBALANCING,
-                                adev->name, adev)) {
-                        printk(KERN_ERR "Failed request IRQ for APBT%d\n",
-                               adev->num);
-                }
-}
-#endif
-
 static void apbt_enable_int(int n)
 {
         unsigned long ctrl = apbt_readl(n, APBTMR_N_CONTROL);
@@ -334,6 +306,27 @@ static int __init apbt_clockevent_register(void)
 }
 
 #ifdef CONFIG_SMP
+
+static void apbt_setup_irq(struct apbt_dev *adev)
+{
+        /* timer0 irq has been setup early */
+        if (adev->irq == 0)
+                return;
+
+        if (system_state == SYSTEM_BOOTING) {
+                irq_modify_status(adev->irq, 0, IRQ_MOVE_PCNTXT);
+                /* APB timer irqs are set up as mp_irqs, timer is edge type */
+                __set_irq_handler(adev->irq, handle_edge_irq, 0, "edge");
+                if (request_irq(adev->irq, apbt_interrupt_handler,
+                                IRQF_TIMER | IRQF_DISABLED | IRQF_NOBALANCING,
+                                adev->name, adev)) {
+                        printk(KERN_ERR "Failed request IRQ for APBT%d\n",
+                               adev->num);
+                }
+        } else
+                enable_irq(adev->irq);
+}
+
 /* Should be called with per cpu */
 void apbt_setup_secondary_clock(void)
 {
@@ -343,7 +336,7 @@ void apbt_setup_secondary_clock(void)
 
         /* Don't register boot CPU clockevent */
         cpu = smp_processor_id();
-        if (cpu == boot_cpu_id)
+        if (!cpu)
                 return;
         /*
          * We need to calculate the scaled math multiplication factor for
@@ -389,16 +382,17 @@ static int apbt_cpuhp_notify(struct notifier_block *n,
 
         switch (action & 0xf) {
         case CPU_DEAD:
+                disable_irq(adev->irq);
                 apbt_disable_int(cpu);
-                if (system_state == SYSTEM_RUNNING)
+                if (system_state == SYSTEM_RUNNING) {
                         pr_debug("skipping APBT CPU %lu offline\n", cpu);
-                else if (adev) {
+                } else if (adev) {
                         pr_debug("APBT clockevent for cpu %lu offline\n", cpu);
                         free_irq(adev->irq, adev);
                 }
                 break;
         default:
-                pr_debug(KERN_INFO "APBT notified %lu, no action\n", action);
+                pr_debug("APBT notified %lu, no action\n", action);
         }
         return NOTIFY_OK;
 }
@@ -552,7 +546,7 @@ bad_count:
                 pr_debug("APB CS going back %lx:%lx:%lx ",
                          t2, last_read, t2 - last_read);
 bad_count_x3:
-                pr_debug(KERN_INFO "tripple check enforced\n");
+                pr_debug("triple check enforced\n");
                 t0 = apbt_readl(phy_cs_timer_id,
                                 APBTMR_N_CURRENT_VALUE);
                 udelay(1);
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index a2e0caf26e17..377f5db3b8b4 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -27,7 +27,7 @@
 #include <asm/gart.h>
 #include <asm/pci-direct.h>
 #include <asm/dma.h>
-#include <asm/k8.h>
+#include <asm/amd_nb.h>
 #include <asm/x86_init.h>
 
 int gart_iommu_aperture;
@@ -307,7 +307,7 @@ void __init early_gart_iommu_check(void)
                                 continue;
 
                         ctl = read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL);
-                        aper_enabled = ctl & AMD64_GARTEN;
+                        aper_enabled = ctl & GARTEN;
                         aper_order = (ctl >> 1) & 7;
                         aper_size = (32 * 1024 * 1024) << aper_order;
                         aper_base = read_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE) & 0x7fff;
@@ -362,7 +362,7 @@ void __init early_gart_iommu_check(void)
                                 continue;
 
                         ctl = read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL);
-                        ctl &= ~AMD64_GARTEN;
+                        ctl &= ~GARTEN;
                         write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, ctl);
                 }
         }
@@ -505,8 +505,13 @@ out:
 
         /* Fix up the north bridges */
         for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
-                int bus;
-                int dev_base, dev_limit;
+                int bus, dev_base, dev_limit;
+
+                /*
+                 * Don't enable translation yet but enable GART IO and CPU
+                 * accesses and set DISTLBWALKPRB since GART table memory is UC.
+                 */
+                u32 ctl = DISTLBWALKPRB | aper_order << 1;
 
                 bus = bus_dev_ranges[i].bus;
                 dev_base = bus_dev_ranges[i].dev_base;
@@ -515,10 +520,7 @@ out:
                         if (!early_is_k8_nb(read_pci_config(bus, slot, 3, 0x00)))
                                 continue;
 
-                        /* Don't enable translation yet. That is done later.
-                           Assume this BIOS didn't initialise the GART so
-                           just overwrite all previous bits */
-                        write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, aper_order << 1);
+                        write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, ctl);
                         write_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE, aper_alloc >> 25);
                 }
         }
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index e3b534cda49a..850657d1b0ed 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -52,6 +52,7 @@
 #include <asm/mce.h>
 #include <asm/kvm_para.h>
 #include <asm/tsc.h>
+#include <asm/atomic.h>
 
 unsigned int num_processors;
 
@@ -370,38 +371,87 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
 }
 
 /*
- * Setup extended LVT, AMD specific (K8, family 10h)
+ * Setup extended LVT, AMD specific
  *
- * Vector mappings are hard coded. On K8 only offset 0 (APIC500) and
- * MCE interrupts are supported. Thus MCE offset must be set to 0.
+ * Software should use the LVT offsets the BIOS provides.  The offsets
+ * are determined by the subsystems using it like those for MCE
+ * threshold or IBS.  On K8 only offset 0 (APIC500) and MCE interrupts
+ * are supported. Beginning with family 10h at least 4 offsets are
+ * available.
  *
- * If mask=1, the LVT entry does not generate interrupts while mask=0
- * enables the vector. See also the BKDGs.
+ * Since the offsets must be consistent for all cores, we keep track
+ * of the LVT offsets in software and reserve the offset for the same
+ * vector also to be used on other cores. An offset is freed by
+ * setting the entry to APIC_EILVT_MASKED.
+ *
+ * If the BIOS is right, there should be no conflicts. Otherwise a
+ * "[Firmware Bug]: ..." error message is generated. However, if
+ * software does not properly determines the offsets, it is not
+ * necessarily a BIOS bug.
  */
 
-#define APIC_EILVT_LVTOFF_MCE 0
-#define APIC_EILVT_LVTOFF_IBS 1
+static atomic_t eilvt_offsets[APIC_EILVT_NR_MAX];
 
-static void setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask)
+static inline int eilvt_entry_is_changeable(unsigned int old, unsigned int new)
 {
-        unsigned long reg = (lvt_off << 4) + APIC_EILVTn(0);
-        unsigned int  v   = (mask << 16) | (msg_type << 8) | vector;
-
-        apic_write(reg, v);
+        return (old & APIC_EILVT_MASKED)
+                || (new == APIC_EILVT_MASKED)
+                || ((new & ~APIC_EILVT_MASKED) == old);
 }
 
-u8 setup_APIC_eilvt_mce(u8 vector, u8 msg_type, u8 mask)
+static unsigned int reserve_eilvt_offset(int offset, unsigned int new)
 {
-        setup_APIC_eilvt(APIC_EILVT_LVTOFF_MCE, vector, msg_type, mask);
-        return APIC_EILVT_LVTOFF_MCE;
+        unsigned int rsvd;                      /* 0: uninitialized */
+
+        if (offset >= APIC_EILVT_NR_MAX)
+                return ~0;
+
+        rsvd = atomic_read(&eilvt_offsets[offset]) & ~APIC_EILVT_MASKED;
+        do {
+                if (rsvd &&
+                    !eilvt_entry_is_changeable(rsvd, new))
+                        /* may not change if vectors are different */
+                        return rsvd;
+                rsvd = atomic_cmpxchg(&eilvt_offsets[offset], rsvd, new);
+        } while (rsvd != new);
+
+        return new;
 }
 
-u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask)
+/*
+ * If mask=1, the LVT entry does not generate interrupts while mask=0
+ * enables the vector. See also the BKDGs.
+ */
+
+int setup_APIC_eilvt(u8 offset, u8 vector, u8 msg_type, u8 mask)
 {
-        setup_APIC_eilvt(APIC_EILVT_LVTOFF_IBS, vector, msg_type, mask);
-        return APIC_EILVT_LVTOFF_IBS;
+        unsigned long reg = APIC_EILVTn(offset);
+        unsigned int new, old, reserved;
+
+        new = (mask << 16) | (msg_type << 8) | vector;
+        old = apic_read(reg);
+        reserved = reserve_eilvt_offset(offset, new);
+
+        if (reserved != new) {
+                pr_err(FW_BUG "cpu %d, try to setup vector 0x%x, but "
+                       "vector 0x%x was already reserved by another core, "
+                       "APIC%lX=0x%x\n",
+                       smp_processor_id(), new, reserved, reg, old);
+                return -EINVAL;
+        }
+
+        if (!eilvt_entry_is_changeable(old, new)) {
+                pr_err(FW_BUG "cpu %d, try to setup vector 0x%x but "
+                       "register already in use, APIC%lX=0x%x\n",
+                       smp_processor_id(), new, reg, old);
+                return -EBUSY;
+        }
+
+        apic_write(reg, new);
+
+        return 0;
 }
-EXPORT_SYMBOL_GPL(setup_APIC_eilvt_ibs);
+EXPORT_SYMBOL_GPL(setup_APIC_eilvt);
 
 /*
  * Program the next event, relative to now
@@ -1665,10 +1715,7 @@ int __init APIC_init_uniprocessor(void)
         }
 #endif
 
-#ifndef CONFIG_SMP
-        enable_IR_x2apic();
         default_setup_apic_routing();
-#endif
 
         verify_local_APIC();
         connect_bsp_APIC();
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 5c5b8f3dddb5..8ae808d110f4 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -131,13 +131,9 @@ struct irq_pin_list {
         struct irq_pin_list *next;
 };
 
-static struct irq_pin_list *get_one_free_irq_2_pin(int node)
+static struct irq_pin_list *alloc_irq_pin_list(int node)
 {
-        struct irq_pin_list *pin;
-
-        pin = kzalloc_node(sizeof(*pin), GFP_ATOMIC, node);
-
-        return pin;
+        return kzalloc_node(sizeof(struct irq_pin_list), GFP_KERNEL, node);
 }
 
 /* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */
@@ -150,10 +146,7 @@ static struct irq_cfg irq_cfgx[NR_IRQS];
 int __init arch_early_irq_init(void)
 {
         struct irq_cfg *cfg;
-        struct irq_desc *desc;
-        int count;
-        int node;
-        int i;
+        int count, node, i;
 
         if (!legacy_pic->nr_legacy_irqs) {
                 nr_irqs_gsi = 0;
@@ -162,13 +155,15 @@ int __init arch_early_irq_init(void)
 
         cfg = irq_cfgx;
         count = ARRAY_SIZE(irq_cfgx);
-        node= cpu_to_node(boot_cpu_id);
+        node = cpu_to_node(0);
+
+        /* Make sure the legacy interrupts are marked in the bitmap */
+        irq_reserve_irqs(0, legacy_pic->nr_legacy_irqs);
 
         for (i = 0; i < count; i++) {
-                desc = irq_to_desc(i);
-                desc->chip_data = &cfg[i];
-                zalloc_cpumask_var_node(&cfg[i].domain, GFP_NOWAIT, node);
-                zalloc_cpumask_var_node(&cfg[i].old_domain, GFP_NOWAIT, node);
+                set_irq_chip_data(i, &cfg[i]);
+                zalloc_cpumask_var_node(&cfg[i].domain, GFP_KERNEL, node);
+                zalloc_cpumask_var_node(&cfg[i].old_domain, GFP_KERNEL, node);
                 /*
                  * For legacy IRQ's, start with assigning irq0 to irq15 to
                  * IRQ0_VECTOR to IRQ15_VECTOR on cpu 0.
@@ -183,170 +178,88 @@ int __init arch_early_irq_init(void)
 }
 
 #ifdef CONFIG_SPARSE_IRQ
-struct irq_cfg *irq_cfg(unsigned int irq)
+static struct irq_cfg *irq_cfg(unsigned int irq)
 {
-        struct irq_cfg *cfg = NULL;
-        struct irq_desc *desc;
-
-        desc = irq_to_desc(irq);
-        if (desc)
-                cfg = desc->chip_data;
-
-        return cfg;
+        return get_irq_chip_data(irq);
 }
 
-static struct irq_cfg *get_one_free_irq_cfg(int node)
+static struct irq_cfg *alloc_irq_cfg(unsigned int irq, int node)
 {
         struct irq_cfg *cfg;
 
-        cfg = kzalloc_node(sizeof(*cfg), GFP_ATOMIC, node);
-        if (cfg) {
-                if (!zalloc_cpumask_var_node(&cfg->domain, GFP_ATOMIC, node)) {
-                        kfree(cfg);
-                        cfg = NULL;
-                } else if (!zalloc_cpumask_var_node(&cfg->old_domain,
-                                                          GFP_ATOMIC, node)) {
-                        free_cpumask_var(cfg->domain);
-                        kfree(cfg);
-                        cfg = NULL;
-                }
-        }
-
+        cfg = kzalloc_node(sizeof(*cfg), GFP_KERNEL, node);
+        if (!cfg)
+                return NULL;
+        if (!zalloc_cpumask_var_node(&cfg->domain, GFP_KERNEL, node))
+                goto out_cfg;
+        if (!zalloc_cpumask_var_node(&cfg->old_domain, GFP_KERNEL, node))
+                goto out_domain;
         return cfg;
+out_domain:
+        free_cpumask_var(cfg->domain);
+out_cfg:
+        kfree(cfg);
+        return NULL;
 }
 
-int arch_init_chip_data(struct irq_desc *desc, int node)
-{
-        struct irq_cfg *cfg;
-
-        cfg = desc->chip_data;
-        if (!cfg) {
-                desc->chip_data = get_one_free_irq_cfg(node);
-                if (!desc->chip_data) {
-                        printk(KERN_ERR "can not alloc irq_cfg\n");
-                        BUG_ON(1);
-                }
-        }
-
-        return 0;
-}
-
-/* for move_irq_desc */
-static void
-init_copy_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg, int node)
+static void free_irq_cfg(unsigned int at, struct irq_cfg *cfg)
 {
-        struct irq_pin_list *old_entry, *head, *tail, *entry;
-
-        cfg->irq_2_pin = NULL;
-        old_entry = old_cfg->irq_2_pin;
-        if (!old_entry)
-                return;
-
-        entry = get_one_free_irq_2_pin(node);
-        if (!entry)
+        if (!cfg)
                 return;
+        set_irq_chip_data(at, NULL);
+        free_cpumask_var(cfg->domain);
+        free_cpumask_var(cfg->old_domain);
+        kfree(cfg);
+}
 
-        entry->apic     = old_entry->apic;
-        entry->pin      = old_entry->pin;
-        head            = entry;
-        tail            = entry;
-        old_entry       = old_entry->next;
-        while (old_entry) {
-                entry = get_one_free_irq_2_pin(node);
-                if (!entry) {
-                        entry = head;
-                        while (entry) {
-                                head = entry->next;
-                                kfree(entry);
-                                entry = head;
-                        }
-                        /* still use the old one */
-                        return;
-                }
-                entry->apic     = old_entry->apic;
-                entry->pin      = old_entry->pin;
-                tail->next      = entry;
-                tail            = entry;
-                old_entry       = old_entry->next;
-        }
+#else
 
-        tail->next = NULL;
-        cfg->irq_2_pin = head;
+struct irq_cfg *irq_cfg(unsigned int irq)
+{
+        return irq < nr_irqs ? irq_cfgx + irq : NULL;
 }
 
-static void free_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg)
+static struct irq_cfg *alloc_irq_cfg(unsigned int irq, int node)
 {
-        struct irq_pin_list *entry, *next;
-
-        if (old_cfg->irq_2_pin == cfg->irq_2_pin)
-                return;
+        return irq_cfgx + irq;
+}
 
-        entry = old_cfg->irq_2_pin;
+static inline void free_irq_cfg(unsigned int at, struct irq_cfg *cfg) { }
 
-        while (entry) {
-                next = entry->next;
-                kfree(entry);
-                entry = next;
-        }
-        old_cfg->irq_2_pin = NULL;
-}
+#endif
 
-void arch_init_copy_chip_data(struct irq_desc *old_desc,
-                                 struct irq_desc *desc, int node)
+static struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node)
 {
+        int res = irq_alloc_desc_at(at, node);
         struct irq_cfg *cfg;
-        struct irq_cfg *old_cfg;
-
-        cfg = get_one_free_irq_cfg(node);
 
-        if (!cfg)
-                return;
-
-        desc->chip_data = cfg;
-
-        old_cfg = old_desc->chip_data;
-
-        cfg->vector = old_cfg->vector;
-        cfg->move_in_progress = old_cfg->move_in_progress;
-        cpumask_copy(cfg->domain, old_cfg->domain);
-        cpumask_copy(cfg->old_domain, old_cfg->old_domain);
-
-        init_copy_irq_2_pin(old_cfg, cfg, node);
-}
+        if (res < 0) {
+                if (res != -EEXIST)
+                        return NULL;
+                cfg = get_irq_chip_data(at);
+                if (cfg)
+                        return cfg;
+        }
 
-static void free_irq_cfg(struct irq_cfg *cfg)
-{
-        free_cpumask_var(cfg->domain);
-        free_cpumask_var(cfg->old_domain);
-        kfree(cfg);
+        cfg = alloc_irq_cfg(at, node);
+        if (cfg)
+                set_irq_chip_data(at, cfg);
+        else
+                irq_free_desc(at);
+        return cfg;
 }
 
-void arch_free_chip_data(struct irq_desc *old_desc, struct irq_desc *desc)
+static int alloc_irq_from(unsigned int from, int node)
 {
-        struct irq_cfg *old_cfg, *cfg;
-
-        old_cfg = old_desc->chip_data;
-        cfg = desc->chip_data;
-
-        if (old_cfg == cfg)
-                return;
-
-        if (old_cfg) {
-                free_irq_2_pin(old_cfg, cfg);
-                free_irq_cfg(old_cfg);
-                old_desc->chip_data = NULL;
-        }
+        return irq_alloc_desc_from(from, node);
 }
-/* end for move_irq_desc */
 
-#else
-struct irq_cfg *irq_cfg(unsigned int irq)
+static void free_irq_at(unsigned int at, struct irq_cfg *cfg)
 {
-        return irq < nr_irqs ? irq_cfgx + irq : NULL;
+        free_irq_cfg(at, cfg);
+        irq_free_desc(at);
 }
 
-#endif
-
 struct io_apic {
         unsigned int index;
         unsigned int unused[3];
@@ -451,7 +364,7 @@ __ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
         io_apic_write(apic, 0x10 + 2*pin, eu.w1);
 }
 
-void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
+static void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
 {
         unsigned long flags;
         raw_spin_lock_irqsave(&ioapic_lock, flags);
@@ -481,7 +394,7 @@ static void ioapic_mask_entry(int apic, int pin)
  * fast in the common case, and fast for shared ISA-space IRQs.
  */
 static int
-add_pin_to_irq_node_nopanic(struct irq_cfg *cfg, int node, int apic, int pin)
+__add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
 {
         struct irq_pin_list **last, *entry;
 
@@ -493,7 +406,7 @@ add_pin_to_irq_node_nopanic(struct irq_cfg *cfg, int node, int apic, int pin)
                 last = &entry->next;
         }
 
-        entry = get_one_free_irq_2_pin(node);
+        entry = alloc_irq_pin_list(node);
         if (!entry) {
                 printk(KERN_ERR "can not alloc irq_pin_list (%d,%d,%d)\n",
                                 node, apic, pin);
@@ -508,7 +421,7 @@ add_pin_to_irq_node_nopanic(struct irq_cfg *cfg, int node, int apic, int pin)
 
 static void add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
 {
-        if (add_pin_to_irq_node_nopanic(cfg, node, apic, pin))
+        if (__add_pin_to_irq_node(cfg, node, apic, pin))
                 panic("IO-APIC: failed to add irq-pin. Can not proceed\n");
 }
 
@@ -571,11 +484,6 @@ static void __unmask_and_level_IO_APIC_irq(struct irq_pin_list *entry)
                              IO_APIC_REDIR_LEVEL_TRIGGER, NULL);
 }
 
-static void __unmask_IO_APIC_irq(struct irq_cfg *cfg)
-{
-        io_apic_modify_irq(cfg, ~IO_APIC_REDIR_MASKED, 0, NULL);
-}
-
 static void io_apic_sync(struct irq_pin_list *entry)
 {
         /*
@@ -587,44 +495,37 @@ static void io_apic_sync(struct irq_pin_list *entry)
         readl(&io_apic->data);
 }
 
-static void __mask_IO_APIC_irq(struct irq_cfg *cfg)
+static void mask_ioapic(struct irq_cfg *cfg)
 {
+        unsigned long flags;
+
+        raw_spin_lock_irqsave(&ioapic_lock, flags);
         io_apic_modify_irq(cfg, ~0, IO_APIC_REDIR_MASKED, &io_apic_sync);
+        raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
-static void mask_IO_APIC_irq_desc(struct irq_desc *desc)
+static void mask_ioapic_irq(struct irq_data *data)
 {
-        struct irq_cfg *cfg = desc->chip_data;
-        unsigned long flags;
-
-        BUG_ON(!cfg);
+        mask_ioapic(data->chip_data);
+}
 
-        raw_spin_lock_irqsave(&ioapic_lock, flags);
-        __mask_IO_APIC_irq(cfg);
-        raw_spin_unlock_irqrestore(&ioapic_lock, flags);
+static void __unmask_ioapic(struct irq_cfg *cfg)
+{
+        io_apic_modify_irq(cfg, ~IO_APIC_REDIR_MASKED, 0, NULL);
 }
 
-static void unmask_IO_APIC_irq_desc(struct irq_desc *desc)
+static void unmask_ioapic(struct irq_cfg *cfg)
 {
-        struct irq_cfg *cfg = desc->chip_data;
         unsigned long flags;
 
         raw_spin_lock_irqsave(&ioapic_lock, flags);
-        __unmask_IO_APIC_irq(cfg);
+        __unmask_ioapic(cfg);
         raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
-static void mask_IO_APIC_irq(unsigned int irq)
+static void unmask_ioapic_irq(struct irq_data *data)
 {
-        struct irq_desc *desc = irq_to_desc(irq);
-
-        mask_IO_APIC_irq_desc(desc);
-}
-static void unmask_IO_APIC_irq(unsigned int irq)
-{
-        struct irq_desc *desc = irq_to_desc(irq);
-
-        unmask_IO_APIC_irq_desc(desc);
+        unmask_ioapic(data->chip_data);
 }
 
 static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin)
@@ -694,14 +595,14 @@ struct IO_APIC_route_entry **alloc_ioapic_entries(void)
         struct IO_APIC_route_entry **ioapic_entries;
 
         ioapic_entries = kzalloc(sizeof(*ioapic_entries) * nr_ioapics,
-                                GFP_ATOMIC);
+                                GFP_KERNEL);
         if (!ioapic_entries)
                 return 0;
 
         for (apic = 0; apic < nr_ioapics; apic++) {
                 ioapic_entries[apic] =
                         kzalloc(sizeof(struct IO_APIC_route_entry) *
-                                nr_ioapic_registers[apic], GFP_ATOMIC);
+                                nr_ioapic_registers[apic], GFP_KERNEL);
                 if (!ioapic_entries[apic])
                         goto nomem;
         }
@@ -1259,7 +1160,6 @@ void __setup_vector_irq(int cpu)
         /* Initialize vector_irq on a new cpu */
         int irq, vector;
         struct irq_cfg *cfg;
-        struct irq_desc *desc;
 
         /*
          * vector_lock will make sure that we don't run into irq vector
@@ -1268,9 +1168,10 @@ void __setup_vector_irq(int cpu)
          */
         raw_spin_lock(&vector_lock);
         /* Mark the inuse vectors */
-        for_each_irq_desc(irq, desc) {
-                cfg = desc->chip_data;
-
+        for_each_active_irq(irq) {
+                cfg = get_irq_chip_data(irq);
+                if (!cfg)
+                        continue;
                 /*
                  * If it is a legacy IRQ handled by the legacy PIC, this cpu
                  * will be part of the irq_cfg's domain.
@@ -1327,17 +1228,17 @@ static inline int IO_APIC_irq_trigger(int irq)
 }
 #endif
 
-static void ioapic_register_intr(int irq, struct irq_desc *desc, unsigned long trigger)
+static void ioapic_register_intr(unsigned int irq, unsigned long trigger)
 {
 
         if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
             trigger == IOAPIC_LEVEL)
-                desc->status |= IRQ_LEVEL;
+                irq_set_status_flags(irq, IRQ_LEVEL);
         else
-                desc->status &= ~IRQ_LEVEL;
+                irq_clear_status_flags(irq, IRQ_LEVEL);
 
-        if (irq_remapped(irq)) {
-                desc->status |= IRQ_MOVE_PCNTXT;
+        if (irq_remapped(get_irq_chip_data(irq))) {
+                irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
                 if (trigger)
                         set_irq_chip_and_handler_name(irq, &ir_ioapic_chip,
                                                       handle_fasteoi_irq,
@@ -1358,10 +1259,10 @@ static void ioapic_register_intr(int irq, struct irq_desc *desc, unsigned long t
                                               handle_edge_irq, "edge");
 }
 
-int setup_ioapic_entry(int apic_id, int irq,
-                       struct IO_APIC_route_entry *entry,
-                       unsigned int destination, int trigger,
-                       int polarity, int vector, int pin)
+static int setup_ioapic_entry(int apic_id, int irq,
+                              struct IO_APIC_route_entry *entry,
+                              unsigned int destination, int trigger,
+                              int polarity, int vector, int pin)
 {
         /*
          * add it to the IO-APIC irq-routing table:
@@ -1382,21 +1283,7 @@ int setup_ioapic_entry(int apic_id, int irq,
                 if (index < 0)
                         panic("Failed to allocate IRTE for ioapic %d\n", apic_id);
 
-                memset(&irte, 0, sizeof(irte));
-
-                irte.present = 1;
-                irte.dst_mode = apic->irq_dest_mode;
-                /*
-                 * Trigger mode in the IRTE will always be edge, and the
-                 * actual level or edge trigger will be setup in the IO-APIC
-                 * RTE. This will help simplify level triggered irq migration.
-                 * For more details, see the comments above explainig IO-APIC
-                 * irq migration in the presence of interrupt-remapping.
-                 */
-                irte.trigger_mode = 0;
-                irte.dlvry_mode = apic->irq_delivery_mode;
-                irte.vector = vector;
-                irte.dest_id = IRTE_DEST(destination);
+                prepare_irte(&irte, vector, destination);
 
                 /* Set source-id of interrupt request */
                 set_ioapic_sid(&irte, apic_id);
@@ -1431,18 +1318,14 @@ int setup_ioapic_entry(int apic_id, int irq,
         return 0;
 }
 
-static void setup_IO_APIC_irq(int apic_id, int pin, unsigned int irq, struct irq_desc *desc,
-                              int trigger, int polarity)
+static void setup_ioapic_irq(int apic_id, int pin, unsigned int irq,
+                             struct irq_cfg *cfg, int trigger, int polarity)
 {
-        struct irq_cfg *cfg;
         struct IO_APIC_route_entry entry;
         unsigned int dest;
 
         if (!IO_APIC_IRQ(irq))
                 return;
-
-        cfg = desc->chip_data;
-
         /*
          * For legacy irqs, cfg->domain starts with cpu 0 for legacy
          * controllers like 8259. Now that IO-APIC can handle this irq, update
@@ -1471,9 +1354,9 @@ static void setup_IO_APIC_irq(int apic_id, int pin, unsigned int irq, struct irq
                 return;
         }
 
-        ioapic_register_intr(irq, desc, trigger);
+        ioapic_register_intr(irq, trigger);
         if (irq < legacy_pic->nr_legacy_irqs)
-                legacy_pic->chip->mask(irq);
+                legacy_pic->mask(irq);
 
         ioapic_write_entry(apic_id, pin, entry);
 }
@@ -1484,11 +1367,9 @@ static struct {
 
 static void __init setup_IO_APIC_irqs(void)
 {
-        int apic_id, pin, idx, irq;
-        int notcon = 0;
-        struct irq_desc *desc;
+        int apic_id, pin, idx, irq, notcon = 0;
+        int node = cpu_to_node(0);
         struct irq_cfg *cfg;
-        int node = cpu_to_node(boot_cpu_id);
 
         apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n");
 
@@ -1525,19 +1406,17 @@ static void __init setup_IO_APIC_irqs(void)
                                 apic->multi_timer_check(apic_id, irq))
                         continue;
 
-                desc = irq_to_desc_alloc_node(irq, node);
-                if (!desc) {
-                        printk(KERN_INFO "can not get irq_desc for %d\n", irq);
+                cfg = alloc_irq_and_cfg_at(irq, node);
+                if (!cfg)
                         continue;
-                }
-                cfg = desc->chip_data;
+
                 add_pin_to_irq_node(cfg, node, apic_id, pin);
                 /*
                  * don't mark it in pin_programmed, so later acpi could
                  * set it correctly when irq < 16
                  */
-                setup_IO_APIC_irq(apic_id, pin, irq, desc,
-                                irq_trigger(idx), irq_polarity(idx));
+                setup_ioapic_irq(apic_id, pin, irq, cfg, irq_trigger(idx),
+                                  irq_polarity(idx));
         }
 
         if (notcon)
@@ -1552,9 +1431,7 @@ static void __init setup_IO_APIC_irqs(void)
  */
 void setup_IO_APIC_irq_extra(u32 gsi)
 {
-        int apic_id = 0, pin, idx, irq;
-        int node = cpu_to_node(boot_cpu_id);
-        struct irq_desc *desc;
+        int apic_id = 0, pin, idx, irq, node = cpu_to_node(0);
         struct irq_cfg *cfg;
 
         /*
@@ -1570,18 +1447,15 @@ void setup_IO_APIC_irq_extra(u32 gsi)
                 return;
 
         irq = pin_2_irq(idx, apic_id, pin);
-#ifdef CONFIG_SPARSE_IRQ
-        desc = irq_to_desc(irq);
-        if (desc)
+
+        /* Only handle the non legacy irqs on secondary ioapics */
+        if (apic_id == 0 || irq < NR_IRQS_LEGACY)
                 return;
-#endif
-        desc = irq_to_desc_alloc_node(irq, node);
-        if (!desc) {
-                printk(KERN_INFO "can not get irq_desc for %d\n", irq);
+
+        cfg = alloc_irq_and_cfg_at(irq, node);
+        if (!cfg)
                 return;
-        }
 
-        cfg = desc->chip_data;
         add_pin_to_irq_node(cfg, node, apic_id, pin);
 
         if (test_bit(pin, mp_ioapic_routing[apic_id].pin_programmed)) {
@@ -1591,7 +1465,7 @@ void setup_IO_APIC_irq_extra(u32 gsi)
         }
         set_bit(pin, mp_ioapic_routing[apic_id].pin_programmed);
 
-        setup_IO_APIC_irq(apic_id, pin, irq, desc,
+        setup_ioapic_irq(apic_id, pin, irq, cfg,
                         irq_trigger(idx), irq_polarity(idx));
 }
 
@@ -1642,7 +1516,6 @@ __apicdebuginit(void) print_IO_APIC(void)
         union IO_APIC_reg_03 reg_03;
         unsigned long flags;
         struct irq_cfg *cfg;
-        struct irq_desc *desc;
         unsigned int irq;
 
         printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
@@ -1729,10 +1602,10 @@ __apicdebuginit(void) print_IO_APIC(void)
         }
         }
         printk(KERN_DEBUG "IRQ to pin mappings:\n");
-        for_each_irq_desc(irq, desc) {
+        for_each_active_irq(irq) {
                 struct irq_pin_list *entry;
 
-                cfg = desc->chip_data;
+                cfg = get_irq_chip_data(irq);
                 if (!cfg)
                         continue;
                 entry = cfg->irq_2_pin;
@@ -2239,29 +2112,26 @@ static int __init timer_irq_works(void)
  * an edge even if it isn't on the 8259A...
  */
 
-static unsigned int startup_ioapic_irq(unsigned int irq)
+static unsigned int startup_ioapic_irq(struct irq_data *data)
 {
-        int was_pending = 0;
+        int was_pending = 0, irq = data->irq;
         unsigned long flags;
-        struct irq_cfg *cfg;
 
         raw_spin_lock_irqsave(&ioapic_lock, flags);
         if (irq < legacy_pic->nr_legacy_irqs) {
-                legacy_pic->chip->mask(irq);
+                legacy_pic->mask(irq);
                 if (legacy_pic->irq_pending(irq))
                         was_pending = 1;
         }
-        cfg = irq_cfg(irq);
-        __unmask_IO_APIC_irq(cfg);
+        __unmask_ioapic(data->chip_data);
         raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 
         return was_pending;
 }
 
-static int ioapic_retrigger_irq(unsigned int irq)
+static int ioapic_retrigger_irq(struct irq_data *data)
 {
-
-        struct irq_cfg *cfg = irq_cfg(irq);
+        struct irq_cfg *cfg = data->chip_data;
         unsigned long flags;
 
         raw_spin_lock_irqsave(&vector_lock, flags);
@@ -2312,7 +2182,7 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq
                  * With interrupt-remapping, destination information comes
                  * from interrupt-remapping table entry.
                  */
-                if (!irq_remapped(irq))
+                if (!irq_remapped(cfg))
                         io_apic_write(apic, 0x11 + pin*2, dest);
                 reg = io_apic_read(apic, 0x10 + pin*2);
                 reg &= ~IO_APIC_REDIR_VECTOR_MASK;
@@ -2322,65 +2192,46 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq
 }
 
 /*
- * Either sets desc->affinity to a valid value, and returns
+ * Either sets data->affinity to a valid value, and returns
  * ->cpu_mask_to_apicid of that in dest_id, or returns -1 and
- * leaves desc->affinity untouched.
+ * leaves data->affinity untouched.
  */
-unsigned int
-set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask,
-                  unsigned int *dest_id)
+int __ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
+                          unsigned int *dest_id)
 {
-        struct irq_cfg *cfg;
-        unsigned int irq;
+        struct irq_cfg *cfg = data->chip_data;
 
         if (!cpumask_intersects(mask, cpu_online_mask))
                 return -1;
 
-        irq = desc->irq;
-        cfg = desc->chip_data;
-        if (assign_irq_vector(irq, cfg, mask))
+        if (assign_irq_vector(data->irq, data->chip_data, mask))
                 return -1;
 
-        cpumask_copy(desc->affinity, mask);
+        cpumask_copy(data->affinity, mask);
 
-        *dest_id = apic->cpu_mask_to_apicid_and(desc->affinity, cfg->domain);
+        *dest_id = apic->cpu_mask_to_apicid_and(mask, cfg->domain);
         return 0;
 }
 
 static int
-set_ioapic_affinity_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
+ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
+                    bool force)
 {
-        struct irq_cfg *cfg;
+        unsigned int dest, irq = data->irq;
         unsigned long flags;
-        unsigned int dest;
-        unsigned int irq;
-        int ret = -1;
-
-        irq = desc->irq;
-        cfg = desc->chip_data;
+        int ret;
 
         raw_spin_lock_irqsave(&ioapic_lock, flags);
-        ret = set_desc_affinity(desc, mask, &dest);
+        ret = __ioapic_set_affinity(data, mask, &dest);
         if (!ret) {
                 /* Only the high 8 bits are valid. */
                 dest = SET_APIC_LOGICAL_ID(dest);
-                __target_IO_APIC_irq(irq, dest, cfg);
+                __target_IO_APIC_irq(irq, dest, data->chip_data);
         }
         raw_spin_unlock_irqrestore(&ioapic_lock, flags);
-
         return ret;
 }
 
-static int
-set_ioapic_affinity_irq(unsigned int irq, const struct cpumask *mask)
-{
-        struct irq_desc *desc;
-
-        desc = irq_to_desc(irq);
-
-        return set_ioapic_affinity_irq_desc(desc, mask);
-}
-
 #ifdef CONFIG_INTR_REMAP
 
 /*
@@ -2395,24 +2246,21 @@ set_ioapic_affinity_irq(unsigned int irq, const struct cpumask *mask)
  * the interrupt-remapping table entry.
  */
 static int
-migrate_ioapic_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
+ir_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
+                       bool force)
 {
-        struct irq_cfg *cfg;
+        struct irq_cfg *cfg = data->chip_data;
+        unsigned int dest, irq = data->irq;
         struct irte irte;
-        unsigned int dest;
-        unsigned int irq;
-        int ret = -1;
 
         if (!cpumask_intersects(mask, cpu_online_mask))
-                return ret;
+                return -EINVAL;
 
-        irq = desc->irq;
         if (get_irte(irq, &irte))
-                return ret;
+                return -EBUSY;
 
-        cfg = desc->chip_data;
         if (assign_irq_vector(irq, cfg, mask))
-                return ret;
+                return -EBUSY;
 
         dest = apic->cpu_mask_to_apicid_and(cfg->domain, mask);
 
@@ -2427,29 +2275,14 @@ migrate_ioapic_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
         if (cfg->move_in_progress)
                 send_cleanup_vector(cfg);
 
-        cpumask_copy(desc->affinity, mask);
-
+        cpumask_copy(data->affinity, mask);
         return 0;
 }
 
-/*
- * Migrates the IRQ destination in the process context.
- */
-static int set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
-                                            const struct cpumask *mask)
-{
-        return migrate_ioapic_irq_desc(desc, mask);
-}
-static int set_ir_ioapic_affinity_irq(unsigned int irq,
-                                       const struct cpumask *mask)
-{
-        struct irq_desc *desc = irq_to_desc(irq);
-
-        return set_ir_ioapic_affinity_irq_desc(desc, mask);
-}
 #else
-static inline int set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
-                                                   const struct cpumask *mask)
+static inline int
+ir_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
+                       bool force)
 {
         return 0;
 }
@@ -2511,10 +2344,8 @@ unlock:
         irq_exit();
 }
 
-static void __irq_complete_move(struct irq_desc **descp, unsigned vector)
+static void __irq_complete_move(struct irq_cfg *cfg, unsigned vector)
 {
-        struct irq_desc *desc = *descp;
-        struct irq_cfg *cfg = desc->chip_data;
         unsigned me;
 
         if (likely(!cfg->move_in_progress))
@@ -2526,31 +2357,28 @@ static void __irq_complete_move(struct irq_desc **descp, unsigned vector)
                 send_cleanup_vector(cfg);
 }
 
-static void irq_complete_move(struct irq_desc **descp)
+static void irq_complete_move(struct irq_cfg *cfg)
 {
-        __irq_complete_move(descp, ~get_irq_regs()->orig_ax);
+        __irq_complete_move(cfg, ~get_irq_regs()->orig_ax);
 }
 
 void irq_force_complete_move(int irq)
 {
-        struct irq_desc *desc = irq_to_desc(irq);
-        struct irq_cfg *cfg = desc->chip_data;
+        struct irq_cfg *cfg = get_irq_chip_data(irq);
 
         if (!cfg)
                 return;
 
-        __irq_complete_move(&desc, cfg->vector);
+        __irq_complete_move(cfg, cfg->vector);
 }
 #else
-static inline void irq_complete_move(struct irq_desc **descp) {}
+static inline void irq_complete_move(struct irq_cfg *cfg) { }
 #endif
 
-static void ack_apic_edge(unsigned int irq)
+static void ack_apic_edge(struct irq_data *data)
 {
-        struct irq_desc *desc = irq_to_desc(irq);
-
-        irq_complete_move(&desc);
-        move_native_irq(irq);
+        irq_complete_move(data->chip_data);
+        move_native_irq(data->irq);
         ack_APIC_irq();
 }
 
@@ -2572,10 +2400,12 @@ atomic_t irq_mis_count;
  * Otherwise, we simulate the EOI message manually by changing the trigger
  * mode to edge and then back to level, with RTE being masked during this.
 */
-static void __eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
+static void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
 {
         struct irq_pin_list *entry;
+        unsigned long flags;
 
+        raw_spin_lock_irqsave(&ioapic_lock, flags);
         for_each_irq_pin(entry, cfg->irq_2_pin) {
                 if (mp_ioapics[entry->apic].apicver >= 0x20) {
                         /*
@@ -2584,7 +2414,7 @@ static void __eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
                          * intr-remapping table entry. Hence for the io-apic
                          * EOI we use the pin number.
                          */
-                        if (irq_remapped(irq))
+                        if (irq_remapped(cfg))
                                 io_apic_eoi(entry->apic, entry->pin);
                         else
                                 io_apic_eoi(entry->apic, cfg->vector);
@@ -2593,36 +2423,22 @@ static void __eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
                         __unmask_and_level_IO_APIC_irq(entry);
                 }
         }
-}
-
-static void eoi_ioapic_irq(struct irq_desc *desc)
-{
-        struct irq_cfg *cfg;
-        unsigned long flags;
-        unsigned int irq;
-
-        irq = desc->irq;
-        cfg = desc->chip_data;
-
-        raw_spin_lock_irqsave(&ioapic_lock, flags);
-        __eoi_ioapic_irq(irq, cfg);
         raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
-static void ack_apic_level(unsigned int irq)
+static void ack_apic_level(struct irq_data *data)
 {
+        struct irq_cfg *cfg = data->chip_data;
+        int i, do_unmask_irq = 0, irq = data->irq;
         struct irq_desc *desc = irq_to_desc(irq);
         unsigned long v;
-        int i;
-        struct irq_cfg *cfg;
-        int do_unmask_irq = 0;
 
-        irq_complete_move(&desc);
+        irq_complete_move(cfg);
 #ifdef CONFIG_GENERIC_PENDING_IRQ
         /* If we are moving the irq we need to mask it */
         if (unlikely(desc->status & IRQ_MOVE_PENDING)) {
                 do_unmask_irq = 1;
-                mask_IO_APIC_irq_desc(desc);
+                mask_ioapic(cfg);
         }
 #endif
 
@@ -2658,7 +2474,6 @@ static void ack_apic_level(unsigned int irq)
          * we use the above logic (mask+edge followed by unmask+level) from
          * Manfred Spraul to clear the remote IRR.
          */
-        cfg = desc->chip_data;
         i = cfg->vector;
         v = apic_read(APIC_TMR + ((i & ~0x1f) >> 1));
 
@@ -2678,7 +2493,7 @@ static void ack_apic_level(unsigned int irq)
         if (!(v & (1 << (i & 0x1f)))) {
                 atomic_inc(&irq_mis_count);
 
-                eoi_ioapic_irq(desc);
+                eoi_ioapic_irq(irq, cfg);
         }
 
         /* Now we can move and renable the irq */
@@ -2709,61 +2524,57 @@ static void ack_apic_level(unsigned int irq)
                  * accurate and is causing problems then it is a hardware bug
                  * and you can go talk to the chipset vendor about it.
                  */
-                cfg = desc->chip_data;
                 if (!io_apic_level_ack_pending(cfg))
                         move_masked_irq(irq);
-                unmask_IO_APIC_irq_desc(desc);
+                unmask_ioapic(cfg);
         }
 }
 
 #ifdef CONFIG_INTR_REMAP
-static void ir_ack_apic_edge(unsigned int irq)
+static void ir_ack_apic_edge(struct irq_data *data)
 {
         ack_APIC_irq();
 }
 
-static void ir_ack_apic_level(unsigned int irq)
+static void ir_ack_apic_level(struct irq_data *data)
 {
-        struct irq_desc *desc = irq_to_desc(irq);
-
         ack_APIC_irq();
-        eoi_ioapic_irq(desc);
+        eoi_ioapic_irq(data->irq, data->chip_data);
 }
 #endif /* CONFIG_INTR_REMAP */
 
 static struct irq_chip ioapic_chip __read_mostly = {
-        .name           = "IO-APIC",
-        .startup        = startup_ioapic_irq,
-        .mask           = mask_IO_APIC_irq,
-        .unmask         = unmask_IO_APIC_irq,
-        .ack            = ack_apic_edge,
-        .eoi            = ack_apic_level,
+        .name                   = "IO-APIC",
+        .irq_startup            = startup_ioapic_irq,
+        .irq_mask               = mask_ioapic_irq,
+        .irq_unmask             = unmask_ioapic_irq,
+        .irq_ack                = ack_apic_edge,
+        .irq_eoi                = ack_apic_level,
 #ifdef CONFIG_SMP
-        .set_affinity   = set_ioapic_affinity_irq,
+        .irq_set_affinity       = ioapic_set_affinity,
 #endif
-        .retrigger      = ioapic_retrigger_irq,
+        .irq_retrigger          = ioapic_retrigger_irq,
 };
 
 static struct irq_chip ir_ioapic_chip __read_mostly = {
-        .name           = "IR-IO-APIC",
-        .startup        = startup_ioapic_irq,
-        .mask           = mask_IO_APIC_irq,
-        .unmask         = unmask_IO_APIC_irq,
+        .name                   = "IR-IO-APIC",
+        .irq_startup            = startup_ioapic_irq,
+        .irq_mask               = mask_ioapic_irq,
+        .irq_unmask             = unmask_ioapic_irq,
 #ifdef CONFIG_INTR_REMAP
-        .ack            = ir_ack_apic_edge,
-        .eoi            = ir_ack_apic_level,
+        .irq_ack                = ir_ack_apic_edge,
+        .irq_eoi                = ir_ack_apic_level,
 #ifdef CONFIG_SMP
-        .set_affinity   = set_ir_ioapic_affinity_irq,
+        .irq_set_affinity       = ir_ioapic_set_affinity,
 #endif
 #endif
-        .retrigger      = ioapic_retrigger_irq,
+        .irq_retrigger          = ioapic_retrigger_irq,
 };
 
 static inline void init_IO_APIC_traps(void)
 {
-        int irq;
-        struct irq_desc *desc;
         struct irq_cfg *cfg;
+        unsigned int irq;
 
         /*
          * NOTE! The local APIC isn't very good at handling
@@ -2776,8 +2587,8 @@ static inline void init_IO_APIC_traps(void)
          * Also, we've got to be careful not to trash gate
          * 0x80, because int 0x80 is hm, kind of importantish. ;)
          */
-        for_each_irq_desc(irq, desc) {
-                cfg = desc->chip_data;
+        for_each_active_irq(irq) {
+                cfg = get_irq_chip_data(irq);
                 if (IO_APIC_IRQ(irq) && cfg && !cfg->vector) {
                         /*
                          * Hmm.. We don't have an entry for this,
@@ -2788,7 +2599,7 @@ static inline void init_IO_APIC_traps(void)
                                 legacy_pic->make_irq(irq);
                         else
                                 /* Strange. Oh, well.. */
-                                desc->chip = &no_irq_chip;
+                                set_irq_chip(irq, &no_irq_chip);
                 }
         }
 }
@@ -2797,7 +2608,7 @@ static inline void init_IO_APIC_traps(void)
  * The local APIC irq-chip implementation:
  */
 
-static void mask_lapic_irq(unsigned int irq)
+static void mask_lapic_irq(struct irq_data *data)
 {
         unsigned long v;
 
@@ -2805,7 +2616,7 @@ static void mask_lapic_irq(unsigned int irq)
         apic_write(APIC_LVT0, v | APIC_LVT_MASKED);
 }
 
-static void unmask_lapic_irq(unsigned int irq)
+static void unmask_lapic_irq(struct irq_data *data)
 {
         unsigned long v;
 
@@ -2813,21 +2624,21 @@ static void unmask_lapic_irq(unsigned int irq)
         apic_write(APIC_LVT0, v & ~APIC_LVT_MASKED);
 }
 
-static void ack_lapic_irq(unsigned int irq)
+static void ack_lapic_irq(struct irq_data *data)
 {
         ack_APIC_irq();
 }
 
 static struct irq_chip lapic_chip __read_mostly = {
         .name           = "local-APIC",
-        .mask           = mask_lapic_irq,
-        .unmask         = unmask_lapic_irq,
-        .ack            = ack_lapic_irq,
+        .irq_mask       = mask_lapic_irq,
+        .irq_unmask     = unmask_lapic_irq,
+        .irq_ack        = ack_lapic_irq,
 };
 
-static void lapic_register_intr(int irq, struct irq_desc *desc)
+static void lapic_register_intr(int irq)
 {
-        desc->status &= ~IRQ_LEVEL;
+        irq_clear_status_flags(irq, IRQ_LEVEL);
         set_irq_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq,
                                       "edge");
 }
@@ -2930,9 +2741,8 @@ int timer_through_8259 __initdata;
  */
 static inline void __init check_timer(void)
 {
-        struct irq_desc *desc = irq_to_desc(0);
-        struct irq_cfg *cfg = desc->chip_data;
-        int node = cpu_to_node(boot_cpu_id);
+        struct irq_cfg *cfg = get_irq_chip_data(0);
+        int node = cpu_to_node(0);
         int apic1, pin1, apic2, pin2;
         unsigned long flags;
         int no_pin1 = 0;
@@ -2942,7 +2752,7 @@ static inline void __init check_timer(void)
         /*
          * get/set the timer IRQ vector:
          */
-        legacy_pic->chip->mask(0);
+        legacy_pic->mask(0);
         assign_irq_vector(0, cfg, apic->target_cpus());
 
         /*
@@ -3001,7 +2811,7 @@ static inline void __init check_timer(void)
                         add_pin_to_irq_node(cfg, node, apic1, pin1);
                         setup_timer_IRQ0_pin(apic1, pin1, cfg->vector);
                 } else {
-                        /* for edge trigger, setup_IO_APIC_irq already
+                        /* for edge trigger, setup_ioapic_irq already
                          * leave it unmasked.
                          * so only need to unmask if it is level-trigger
                          * do we really have level trigger timer?
@@ -3009,12 +2819,12 @@ static inline void __init check_timer(void)
                         int idx;
                         idx = find_irq_entry(apic1, pin1, mp_INT);
                         if (idx != -1 && irq_trigger(idx))
-                                unmask_IO_APIC_irq_desc(desc);
+                                unmask_ioapic(cfg);
                 }
                 if (timer_irq_works()) {
                         if (nmi_watchdog == NMI_IO_APIC) {
                                 setup_nmi();
-                                legacy_pic->chip->unmask(0);
+                                legacy_pic->unmask(0);
                         }
                         if (disable_timer_pin_1 > 0)
                                 clear_IO_APIC_pin(0, pin1);
@@ -3037,14 +2847,14 @@ static inline void __init check_timer(void)
                  */
                 replace_pin_at_irq_node(cfg, node, apic1, pin1, apic2, pin2);
                 setup_timer_IRQ0_pin(apic2, pin2, cfg->vector);
-                legacy_pic->chip->unmask(0);
+                legacy_pic->unmask(0);
                 if (timer_irq_works()) {
                         apic_printk(APIC_QUIET, KERN_INFO "....... works.\n");
                         timer_through_8259 = 1;
                         if (nmi_watchdog == NMI_IO_APIC) {
-                                legacy_pic->chip->mask(0);
+                                legacy_pic->mask(0);
                                 setup_nmi();
-                                legacy_pic->chip->unmask(0);
+                                legacy_pic->unmask(0);
                         }
                         goto out;
                 }
@@ -3052,7 +2862,7 @@ static inline void __init check_timer(void)
                  * Cleanup, just in case ...
                  */
                 local_irq_disable();
-                legacy_pic->chip->mask(0);
+                legacy_pic->mask(0);
                 clear_IO_APIC_pin(apic2, pin2);
                 apic_printk(APIC_QUIET, KERN_INFO "....... failed.\n");
         }
@@ -3069,16 +2879,16 @@ static inline void __init check_timer(void)
         apic_printk(APIC_QUIET, KERN_INFO
                     "...trying to set up timer as Virtual Wire IRQ...\n");
 
-        lapic_register_intr(0, desc);
+        lapic_register_intr(0);
         apic_write(APIC_LVT0, APIC_DM_FIXED | cfg->vector);     /* Fixed mode */
-        legacy_pic->chip->unmask(0);
+        legacy_pic->unmask(0);
 
         if (timer_irq_works()) {
                 apic_printk(APIC_QUIET, KERN_INFO "..... works.\n");
                 goto out;
         }
         local_irq_disable();
-        legacy_pic->chip->mask(0);
+        legacy_pic->mask(0);
         apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | cfg->vector);
         apic_printk(APIC_QUIET, KERN_INFO "..... failed.\n");
 
@@ -3244,49 +3054,42 @@ device_initcall(ioapic_init_sysfs);
 /*
  * Dynamic irq allocate and deallocation
  */
-unsigned int create_irq_nr(unsigned int irq_want, int node)
+unsigned int create_irq_nr(unsigned int from, int node)
 {
-        /* Allocate an unused irq */
-        unsigned int irq;
-        unsigned int new;
+        struct irq_cfg *cfg;
         unsigned long flags;
-        struct irq_cfg *cfg_new = NULL;
-        struct irq_desc *desc_new = NULL;
-
-        irq = 0;
-        if (irq_want < nr_irqs_gsi)
-                irq_want = nr_irqs_gsi;
-
-        raw_spin_lock_irqsave(&vector_lock, flags);
-        for (new = irq_want; new < nr_irqs; new++) {
-                desc_new = irq_to_desc_alloc_node(new, node);
-                if (!desc_new) {
-                        printk(KERN_INFO "can not get irq_desc for %d\n", new);
-                        continue;
-                }
-                cfg_new = desc_new->chip_data;
-
-                if (cfg_new->vector != 0)
-                        continue;
+        unsigned int ret = 0;
+        int irq;
 
-                desc_new = move_irq_desc(desc_new, node);
-                cfg_new = desc_new->chip_data;
+        if (from < nr_irqs_gsi)
+                from = nr_irqs_gsi;
 
-                if (__assign_irq_vector(new, cfg_new, apic->target_cpus()) == 0)
-                        irq = new;
-                break;
+        irq = alloc_irq_from(from, node);
+        if (irq < 0)
+                return 0;
+        cfg = alloc_irq_cfg(irq, node);
+        if (!cfg) {
+                free_irq_at(irq, NULL);
+                return 0;
         }
-        raw_spin_unlock_irqrestore(&vector_lock, flags);
 
-        if (irq > 0)
-                dynamic_irq_init_keep_chip_data(irq);
+        raw_spin_lock_irqsave(&vector_lock, flags);
+        if (!__assign_irq_vector(irq, cfg, apic->target_cpus()))
+                ret = irq;
+        raw_spin_unlock_irqrestore(&vector_lock, flags);
 
-        return irq;
+        if (ret) {
+                set_irq_chip_data(irq, cfg);
+                irq_clear_status_flags(irq, IRQ_NOREQUEST);
+        } else {
+                free_irq_at(irq, cfg);
+        }
+        return ret;
 }
 
 int create_irq(void)
 {
-        int node = cpu_to_node(boot_cpu_id);
+        int node = cpu_to_node(0);
         unsigned int irq_want;
         int irq;
 
@@ -3301,14 +3104,17 @@ int create_irq(void)
 
 void destroy_irq(unsigned int irq)
 {
+        struct irq_cfg *cfg = get_irq_chip_data(irq);
         unsigned long flags;
 
-        dynamic_irq_cleanup_keep_chip_data(irq);
+        irq_set_status_flags(irq, IRQ_NOREQUEST|IRQ_NOPROBE);
 
-        free_irte(irq);
+        if (intr_remapping_enabled)
+                free_irte(irq);
         raw_spin_lock_irqsave(&vector_lock, flags);
-        __clear_irq_vector(irq, get_irq_chip_data(irq));
+        __clear_irq_vector(irq, cfg);
         raw_spin_unlock_irqrestore(&vector_lock, flags);
+        free_irq_at(irq, cfg);
 }
 
 /*
@@ -3332,7 +3138,7 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq,
 
         dest = apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus());
 
-        if (irq_remapped(irq)) {
+        if (irq_remapped(get_irq_chip_data(irq))) {
                 struct irte irte;
                 int ir_index;
                 u16 sub_handle;
@@ -3340,14 +3146,7 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq,
                 ir_index = map_irq_to_irte_handle(irq, &sub_handle);
                 BUG_ON(ir_index == -1);
 
-                memset (&irte, 0, sizeof(irte));
-
-                irte.present = 1;
-                irte.dst_mode = apic->irq_dest_mode;
-                irte.trigger_mode = 0; /* edge */
-                irte.dlvry_mode = apic->irq_delivery_mode;
-                irte.vector = cfg->vector;
-                irte.dest_id = IRTE_DEST(dest);
+                prepare_irte(&irte, cfg->vector, dest);
 
                 /* Set source-id of interrupt request */
                 if (pdev)
@@ -3392,26 +3191,24 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq,
 }
 
 #ifdef CONFIG_SMP
-static int set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
+static int
+msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
 {
-        struct irq_desc *desc = irq_to_desc(irq);
-        struct irq_cfg *cfg;
+        struct irq_cfg *cfg = data->chip_data;
         struct msi_msg msg;
         unsigned int dest;
 
-        if (set_desc_affinity(desc, mask, &dest))
+        if (__ioapic_set_affinity(data, mask, &dest))
                 return -1;
 
-        cfg = desc->chip_data;
-
-        get_cached_msi_msg_desc(desc, &msg);
+        __get_cached_msi_msg(data->msi_desc, &msg);
 
         msg.data &= ~MSI_DATA_VECTOR_MASK;
         msg.data |= MSI_DATA_VECTOR(cfg->vector);
         msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
         msg.address_lo |= MSI_ADDR_DEST_ID(dest);
 
-        write_msi_msg_desc(desc, &msg);
+        __write_msi_msg(data->msi_desc, &msg);
 
         return 0;
 }
@@ -3421,17 +3218,17 @@ static int set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
  * done in the process context using interrupt-remapping hardware.
  */
 static int
-ir_set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
+ir_msi_set_affinity(struct irq_data *data, const struct cpumask *mask,
+                    bool force)
 {
-        struct irq_desc *desc = irq_to_desc(irq);
-        struct irq_cfg *cfg = desc->chip_data;
-        unsigned int dest;
+        struct irq_cfg *cfg = data->chip_data;
+        unsigned int dest, irq = data->irq;
         struct irte irte;
 
         if (get_irte(irq, &irte))
                 return -1;
 
-        if (set_desc_affinity(desc, mask, &dest))
+        if (__ioapic_set_affinity(data, mask, &dest))
                 return -1;
 
         irte.vector = cfg->vector;
@@ -3461,27 +3258,27 @@ ir_set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
  * which implement the MSI or MSI-X Capability Structure.
  */
 static struct irq_chip msi_chip = {
-        .name           = "PCI-MSI",
-        .unmask         = unmask_msi_irq,
-        .mask           = mask_msi_irq,
-        .ack            = ack_apic_edge,
+        .name                   = "PCI-MSI",
+        .irq_unmask             = unmask_msi_irq,
+        .irq_mask               = mask_msi_irq,
+        .irq_ack                = ack_apic_edge,
 #ifdef CONFIG_SMP
-        .set_affinity   = set_msi_irq_affinity,
+        .irq_set_affinity       = msi_set_affinity,
 #endif
-        .retrigger      = ioapic_retrigger_irq,
+        .irq_retrigger          = ioapic_retrigger_irq,
 };
 
 static struct irq_chip msi_ir_chip = {
-        .name           = "IR-PCI-MSI",
-        .unmask         = unmask_msi_irq,
-        .mask           = mask_msi_irq,
+        .name                   = "IR-PCI-MSI",
+        .irq_unmask             = unmask_msi_irq,
+        .irq_mask               = mask_msi_irq,
 #ifdef CONFIG_INTR_REMAP
-        .ack            = ir_ack_apic_edge,
+        .irq_ack                = ir_ack_apic_edge,
 #ifdef CONFIG_SMP
-        .set_affinity   = ir_set_msi_irq_affinity,
+        .irq_set_affinity       = ir_msi_set_affinity,
 #endif
 #endif
-        .retrigger      = ioapic_retrigger_irq,
+        .irq_retrigger          = ioapic_retrigger_irq,
 };
 
 /*
@@ -3513,8 +3310,8 @@ static int msi_alloc_irte(struct pci_dev *dev, int irq, int nvec)
 
 static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
 {
-        int ret;
         struct msi_msg msg;
+        int ret;
 
         ret = msi_compose_msg(dev, irq, &msg, -1);
         if (ret < 0)
@@ -3523,12 +3320,8 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
         set_irq_msi(irq, msidesc);
         write_msi_msg(irq, &msg);
 
-        if (irq_remapped(irq)) {
-                struct irq_desc *desc = irq_to_desc(irq);
-                /*
-                 * irq migration in process context
-                 */
-                desc->status |= IRQ_MOVE_PCNTXT;
+        if (irq_remapped(get_irq_chip_data(irq))) {
+                irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
                 set_irq_chip_and_handler_name(irq, &msi_ir_chip, handle_edge_irq, "edge");
         } else
                 set_irq_chip_and_handler_name(irq, &msi_chip, handle_edge_irq, "edge");
@@ -3540,13 +3333,10 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
 
 int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 {
-        unsigned int irq;
-        int ret, sub_handle;
+        int node, ret, sub_handle, index = 0;
+        unsigned int irq, irq_want;
         struct msi_desc *msidesc;
-        unsigned int irq_want;
         struct intel_iommu *iommu = NULL;
-        int index = 0;
-        int node;
 
         /* x86 doesn't support multiple MSI yet */
         if (type == PCI_CAP_ID_MSI && nvec > 1)
@@ -3606,18 +3396,17 @@ void arch_teardown_msi_irq(unsigned int irq)
 
 #if defined (CONFIG_DMAR) || defined (CONFIG_INTR_REMAP)
 #ifdef CONFIG_SMP
-static int dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
+static int
+dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask,
+                      bool force)
 {
-        struct irq_desc *desc = irq_to_desc(irq);
-        struct irq_cfg *cfg;
+        struct irq_cfg *cfg = data->chip_data;
+        unsigned int dest, irq = data->irq;
         struct msi_msg msg;
-        unsigned int dest;
 
-        if (set_desc_affinity(desc, mask, &dest))
+        if (__ioapic_set_affinity(data, mask, &dest))
                 return -1;
 
-        cfg = desc->chip_data;
-
         dmar_msi_read(irq, &msg);
 
         msg.data &= ~MSI_DATA_VECTOR_MASK;
@@ -3633,14 +3422,14 @@ static int dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 #endif /* CONFIG_SMP */
 
 static struct irq_chip dmar_msi_type = {
-        .name = "DMAR_MSI",
-        .unmask = dmar_msi_unmask,
-        .mask = dmar_msi_mask,
-        .ack = ack_apic_edge,
+        .name                   = "DMAR_MSI",
+        .irq_unmask             = dmar_msi_unmask,
+        .irq_mask               = dmar_msi_mask,
+        .irq_ack                = ack_apic_edge,
 #ifdef CONFIG_SMP
-        .set_affinity = dmar_msi_set_affinity,
+        .irq_set_affinity       = dmar_msi_set_affinity,
 #endif
-        .retrigger = ioapic_retrigger_irq,
+        .irq_retrigger          = ioapic_retrigger_irq,
 };
 
 int arch_setup_dmar_msi(unsigned int irq)
@@ -3661,26 +3450,24 @@ int arch_setup_dmar_msi(unsigned int irq)
 #ifdef CONFIG_HPET_TIMER
 
 #ifdef CONFIG_SMP
-static int hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
+static int hpet_msi_set_affinity(struct irq_data *data,
+                                 const struct cpumask *mask, bool force)
 {
-        struct irq_desc *desc = irq_to_desc(irq);
-        struct irq_cfg *cfg;
+        struct irq_cfg *cfg = data->chip_data;
         struct msi_msg msg;
         unsigned int dest;
 
-        if (set_desc_affinity(desc, mask, &dest))
+        if (__ioapic_set_affinity(data, mask, &dest))
                 return -1;
 
-        cfg = desc->chip_data;
-
-        hpet_msi_read(irq, &msg);
+        hpet_msi_read(data->handler_data, &msg);
 
         msg.data &= ~MSI_DATA_VECTOR_MASK;
         msg.data |= MSI_DATA_VECTOR(cfg->vector);
         msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
         msg.address_lo |= MSI_ADDR_DEST_ID(dest);
 
-        hpet_msi_write(irq, &msg);
+        hpet_msi_write(data->handler_data, &msg);
 
         return 0;
 }
@@ -3688,34 +3475,33 @@ static int hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 #endif /* CONFIG_SMP */
 
 static struct irq_chip ir_hpet_msi_type = {
-        .name = "IR-HPET_MSI",
-        .unmask = hpet_msi_unmask,
-        .mask = hpet_msi_mask,
+        .name                   = "IR-HPET_MSI",
+        .irq_unmask             = hpet_msi_unmask,
+        .irq_mask               = hpet_msi_mask,
 #ifdef CONFIG_INTR_REMAP
-        .ack = ir_ack_apic_edge,
+        .irq_ack                = ir_ack_apic_edge,
 #ifdef CONFIG_SMP
-        .set_affinity = ir_set_msi_irq_affinity,
+        .irq_set_affinity       = ir_msi_set_affinity,
 #endif
 #endif
-        .retrigger = ioapic_retrigger_irq,
+        .irq_retrigger          = ioapic_retrigger_irq,
 };
 
 static struct irq_chip hpet_msi_type = {
         .name = "HPET_MSI",
-        .unmask = hpet_msi_unmask,
-        .mask = hpet_msi_mask,
-        .ack = ack_apic_edge,
+        .irq_unmask = hpet_msi_unmask,
+        .irq_mask = hpet_msi_mask,
+        .irq_ack = ack_apic_edge,
 #ifdef CONFIG_SMP
-        .set_affinity = hpet_msi_set_affinity,
+        .irq_set_affinity = hpet_msi_set_affinity,
 #endif
-        .retrigger = ioapic_retrigger_irq,
+        .irq_retrigger = ioapic_retrigger_irq,
 };
 
 int arch_setup_hpet_msi(unsigned int irq, unsigned int id)
 {
-        int ret;
         struct msi_msg msg;
-        struct irq_desc *desc = irq_to_desc(irq);
+        int ret;
 
         if (intr_remapping_enabled) {
                 struct intel_iommu *iommu = map_hpet_to_ir(id);
@@ -3733,9 +3519,9 @@ int arch_setup_hpet_msi(unsigned int irq, unsigned int id)
         if (ret < 0)
                 return ret;
 
-        hpet_msi_write(irq, &msg);
-        desc->status |= IRQ_MOVE_PCNTXT;
-        if (irq_remapped(irq))
+        hpet_msi_write(get_irq_data(irq), &msg);
+        irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
+        if (irq_remapped(get_irq_chip_data(irq)))
                 set_irq_chip_and_handler_name(irq, &ir_hpet_msi_type,
                                               handle_edge_irq, "edge");
         else
@@ -3768,33 +3554,30 @@ static void target_ht_irq(unsigned int irq, unsigned int dest, u8 vector)
         write_ht_irq_msg(irq, &msg);
 }
 
-static int set_ht_irq_affinity(unsigned int irq, const struct cpumask *mask)
+static int
+ht_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
 {
-        struct irq_desc *desc = irq_to_desc(irq);
-        struct irq_cfg *cfg;
+        struct irq_cfg *cfg = data->chip_data;
         unsigned int dest;
 
-        if (set_desc_affinity(desc, mask, &dest))
+        if (__ioapic_set_affinity(data, mask, &dest))
                 return -1;
 
-        cfg = desc->chip_data;
-
-        target_ht_irq(irq, dest, cfg->vector);
-
+        target_ht_irq(data->irq, dest, cfg->vector);
         return 0;
 }
 
 #endif
 
 static struct irq_chip ht_irq_chip = {
-        .name           = "PCI-HT",
-        .mask           = mask_ht_irq,
-        .unmask         = unmask_ht_irq,
-        .ack            = ack_apic_edge,
+        .name                   = "PCI-HT",
+        .irq_mask               = mask_ht_irq,
+        .irq_unmask             = unmask_ht_irq,
+        .irq_ack                = ack_apic_edge,
 #ifdef CONFIG_SMP
-        .set_affinity   = set_ht_irq_affinity,
+        .irq_set_affinity       = ht_set_affinity,
 #endif
-        .retrigger      = ioapic_retrigger_irq,
+        .irq_retrigger          = ioapic_retrigger_irq,
 };
 
 int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
@@ -3885,14 +3668,13 @@ int __init arch_probe_nr_irqs(void)
         if (nr < nr_irqs)
                 nr_irqs = nr;
 
-        return 0;
+        return NR_IRQS_LEGACY;
 }
 #endif
 
 static int __io_apic_set_pci_routing(struct device *dev, int irq,
                                 struct io_apic_irq_attr *irq_attr)
 {
-        struct irq_desc *desc;
         struct irq_cfg *cfg;
         int node;
         int ioapic, pin;
@@ -3908,13 +3690,11 @@ static int __io_apic_set_pci_routing(struct device *dev, int irq,
         if (dev)
                 node = dev_to_node(dev);
         else
-                node = cpu_to_node(boot_cpu_id);
+                node = cpu_to_node(0);
 
-        desc = irq_to_desc_alloc_node(irq, node);
-        if (!desc) {
-                printk(KERN_INFO "can not get irq_desc %d\n", irq);
+        cfg = alloc_irq_and_cfg_at(irq, node);
+        if (!cfg)
                 return 0;
-        }
 
         pin = irq_attr->ioapic_pin;
         trigger = irq_attr->trigger;
@@ -3924,15 +3704,14 @@ static int __io_apic_set_pci_routing(struct device *dev, int irq,
          * IRQs < 16 are already in the irq_2_pin[] map
          */
         if (irq >= legacy_pic->nr_legacy_irqs) {
-                cfg = desc->chip_data;
-                if (add_pin_to_irq_node_nopanic(cfg, node, ioapic, pin)) {
+                if (__add_pin_to_irq_node(cfg, node, ioapic, pin)) {
                         printk(KERN_INFO "can not add pin %d for irq %d\n",
                                 pin, irq);
                         return 0;
                 }
         }
 
-        setup_IO_APIC_irq(ioapic, pin, irq, desc, trigger, polarity);
+        setup_ioapic_irq(ioapic, pin, irq, cfg, trigger, polarity);
 
         return 0;
 }
@@ -4125,14 +3904,14 @@ void __init setup_ioapic_dest(void)
                  */
                 if (desc->status &
                     (IRQ_NO_BALANCING | IRQ_AFFINITY_SET))
-                        mask = desc->affinity;
+                        mask = desc->irq_data.affinity;
                 else
                         mask = apic->target_cpus();
 
                 if (intr_remapping_enabled)
-                        set_ir_ioapic_affinity_irq_desc(desc, mask);
+                        ir_ioapic_set_affinity(&desc->irq_data, mask, false);
                 else
-                        set_ioapic_affinity_irq_desc(desc, mask);
+                        ioapic_set_affinity(&desc->irq_data, mask, false);
         }
 
 }
@@ -4316,19 +4095,18 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
 void __init pre_init_apic_IRQ0(void)
 {
         struct irq_cfg *cfg;
-        struct irq_desc *desc;
 
         printk(KERN_INFO "Early APIC setup for system timer0\n");
 #ifndef CONFIG_SMP
         phys_cpu_present_map = physid_mask_of_physid(boot_cpu_physical_apicid);
 #endif
-        desc = irq_to_desc_alloc_node(0, 0);
+        /* Make sure the irq descriptor is set up */
+        cfg = alloc_irq_and_cfg_at(0, 0);
 
         setup_local_APIC();
 
-        cfg = irq_cfg(0);
         add_pin_to_irq_node(cfg, 0, 0, 0);
         set_irq_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, "edge");
 
-        setup_IO_APIC_irq(0, 0, 0, desc, 0, 0);
+        setup_ioapic_irq(0, 0, 0, cfg, 0, 0);
 }
diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c
index a43f71cb30f8..c90041ccb742 100644
--- a/arch/x86/kernel/apic/nmi.c
+++ b/arch/x86/kernel/apic/nmi.c
@@ -178,7 +178,7 @@ int __init check_nmi_watchdog(void)
 error:
         if (nmi_watchdog == NMI_IO_APIC) {
                 if (!timer_through_8259)
-                        legacy_pic->chip->mask(0);
+                        legacy_pic->mask(0);
                 on_each_cpu(__acpi_nmi_disable, NULL, 1);
         }
 
diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c
index 83e9be4778e2..f9e4e6a54073 100644
--- a/arch/x86/kernel/apic/probe_64.c
+++ b/arch/x86/kernel/apic/probe_64.c
@@ -54,6 +54,9 @@ static int apicid_phys_pkg_id(int initial_apic_id, int index_msb)
  */
 void __init default_setup_apic_routing(void)
 {
+
+        enable_IR_x2apic();
+
 #ifdef CONFIG_X86_X2APIC
         if (x2apic_mode
 #ifdef CONFIG_X86_UV
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index ba5f62f45f01..9e093f8fe78c 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -148,7 +148,7 @@ static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_SMP
         /* calling is from identify_secondary_cpu() ? */
-        if (c->cpu_index == boot_cpu_id)
+        if (!c->cpu_index)
                 return;
 
         /*
@@ -253,37 +253,51 @@ static int __cpuinit nearby_node(int apicid)
 #endif
 
 /*
- * Fixup core topology information for AMD multi-node processors.
- * Assumption: Number of cores in each internal node is the same.
+ * Fixup core topology information for
+ * (1) AMD multi-node processors
+ *     Assumption: Number of cores in each internal node is the same.
+ * (2) AMD processors supporting compute units
  */
 #ifdef CONFIG_X86_HT
-static void __cpuinit amd_fixup_dcm(struct cpuinfo_x86 *c)
+static void __cpuinit amd_get_topology(struct cpuinfo_x86 *c)
 {
-        unsigned long long value;
-        u32 nodes, cores_per_node;
+        u32 nodes;
+        u8 node_id;
         int cpu = smp_processor_id();
 
-        if (!cpu_has(c, X86_FEATURE_NODEID_MSR))
-                return;
+        /* get information required for multi-node processors */
+        if (cpu_has(c, X86_FEATURE_TOPOEXT)) {
+                u32 eax, ebx, ecx, edx;
 
-        /* fixup topology information only once for a core */
-        if (cpu_has(c, X86_FEATURE_AMD_DCM))
-                return;
+                cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
+                nodes = ((ecx >> 8) & 7) + 1;
+                node_id = ecx & 7;
 
-        rdmsrl(MSR_FAM10H_NODE_ID, value);
+                /* get compute unit information */
+                smp_num_siblings = ((ebx >> 8) & 3) + 1;
+                c->compute_unit_id = ebx & 0xff;
+        } else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
+                u64 value;
 
-        nodes = ((value >> 3) & 7) + 1;
-        if (nodes == 1)
+                rdmsrl(MSR_FAM10H_NODE_ID, value);
+                nodes = ((value >> 3) & 7) + 1;
+                node_id = value & 7;
+        } else
                 return;
 
-        set_cpu_cap(c, X86_FEATURE_AMD_DCM);
-        cores_per_node = c->x86_max_cores / nodes;
+        /* fixup multi-node processor information */
+        if (nodes > 1) {
+                u32 cores_per_node;
+
+                set_cpu_cap(c, X86_FEATURE_AMD_DCM);
+                cores_per_node = c->x86_max_cores / nodes;
 
-        /* store NodeID, use llc_shared_map to store sibling info */
-        per_cpu(cpu_llc_id, cpu) = value & 7;
+                /* store NodeID, use llc_shared_map to store sibling info */
+                per_cpu(cpu_llc_id, cpu) = node_id;
 
-        /* fixup core id to be in range from 0 to (cores_per_node - 1) */
-        c->cpu_core_id = c->cpu_core_id % cores_per_node;
+                /* core id to be in range from 0 to (cores_per_node - 1) */
+                c->cpu_core_id = c->cpu_core_id % cores_per_node;
+        }
 }
 #endif
 
@@ -304,9 +318,7 @@ static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c)
         c->phys_proc_id = c->initial_apicid >> bits;
         /* use socket ID also for last level cache */
         per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
-        /* fixup topology information on multi-node processors */
-        if ((c->x86 == 0x10) && (c->x86_model == 9))
-                amd_fixup_dcm(c);
+        amd_get_topology(c);
 #endif
 }
 
@@ -412,6 +424,23 @@ static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
                         set_cpu_cap(c, X86_FEATURE_EXTD_APICID);
         }
 #endif
+
+        /* We need to do the following only once */
+        if (c != &boot_cpu_data)
+                return;
+
+        if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) {
+
+                if (c->x86 > 0x10 ||
+                    (c->x86 == 0x10 && c->x86_model >= 0x2)) {
+                        u64 val;
+
+                        rdmsrl(MSR_K7_HWCR, val);
+                        if (!(val & BIT(24)))
+                                printk(KERN_WARNING FW_BUG "TSC doesn't count "
+                                        "with P0 frequency!\n");
+                }
+        }
 }
 
 static void __cpuinit init_amd(struct cpuinfo_x86 *c)
@@ -523,7 +552,7 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 #endif
 
         if (c->extended_cpuid_level >= 0x80000006) {
-                if ((c->x86 >= 0x0f) && (cpuid_edx(0x80000006) & 0xf000))
+                if (cpuid_edx(0x80000006) & 0xf000)
                         num_cache_leaves = 4;
                 else
                         num_cache_leaves = 3;
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index f2f9ac7da25c..4b68bda30938 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -665,7 +665,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
                 this_cpu->c_early_init(c);
 
 #ifdef CONFIG_SMP
-        c->cpu_index = boot_cpu_id;
+        c->cpu_index = 0;
 #endif
         filter_cpuid_features(c, false);
 }
@@ -704,16 +704,21 @@ void __init early_cpu_init(void)
 }
 
 /*
- * The NOPL instruction is supposed to exist on all CPUs with
- * family >= 6; unfortunately, that's not true in practice because
- * of early VIA chips and (more importantly) broken virtualizers that
- * are not easy to detect.  In the latter case it doesn't even *fail*
- * reliably, so probing for it doesn't even work.  Disable it completely
+ * The NOPL instruction is supposed to exist on all CPUs of family >= 6;
+ * unfortunately, that's not true in practice because of early VIA
+ * chips and (more importantly) broken virtualizers that are not easy
+ * to detect. In the latter case it doesn't even *fail* reliably, so
+ * probing for it doesn't even work. Disable it completely on 32-bit
  * unless we can find a reliable way to detect all the broken cases.
+ * Enable it explicitly on 64-bit for non-constant inputs of cpu_has().
  */
 static void __cpuinit detect_nopl(struct cpuinfo_x86 *c)
 {
+#ifdef CONFIG_X86_32
         clear_cpu_cap(c, X86_FEATURE_NOPL);
+#else
+        set_cpu_cap(c, X86_FEATURE_NOPL);
+#endif
 }
 
 static void __cpuinit generic_identify(struct cpuinfo_x86 *c)
@@ -1264,13 +1269,6 @@ void __cpuinit cpu_init(void)
         clear_all_debug_regs();
         dbg_restore_debug_regs();
 
-        /*
-         * Force FPU initialization:
-         */
-        current_thread_info()->status = 0;
-        clear_used_math();
-        mxcsr_feature_mask_init();
-
         fpu_init();
         xsave_init();
 }
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index f668bb1f7d43..e765633f210e 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -32,6 +32,7 @@ struct cpu_dev {
 extern const struct cpu_dev *const __x86_cpu_dev_start[],
                             *const __x86_cpu_dev_end[];
 
+extern void get_cpu_cap(struct cpuinfo_x86 *c);
 extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c);
 extern void get_cpu_cap(struct cpuinfo_x86 *c);
 
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index b4389441efbb..695f17731e23 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -170,7 +170,7 @@ static void __cpuinit intel_smp_check(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_SMP
         /* calling is from identify_secondary_cpu() ? */
-        if (c->cpu_index == boot_cpu_id)
+        if (!c->cpu_index)
                 return;
 
         /*
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 898c2f4eab88..12cd823c8d03 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -17,7 +17,7 @@
 
 #include <asm/processor.h>
 #include <linux/smp.h>
-#include <asm/k8.h>
+#include <asm/amd_nb.h>
 #include <asm/smp.h>
 
 #define LVL_1_INST      1
@@ -306,7 +306,7 @@ struct _cache_attr {
         ssize_t (*store)(struct _cpuid4_info *, const char *, size_t count);
 };
 
-#ifdef CONFIG_CPU_SUP_AMD
+#ifdef CONFIG_AMD_NB
 
 /*
  * L3 cache descriptors
@@ -369,7 +369,7 @@ static void __cpuinit amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf,
                         return;
 
         /* not in virtualized environments */
-        if (num_k8_northbridges == 0)
+        if (k8_northbridges.num == 0)
                 return;
 
         /*
@@ -377,7 +377,7 @@ static void __cpuinit amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf,
          * never freed but this is done only on shutdown so it doesn't matter.
          */
         if (!l3_caches) {
-                int size = num_k8_northbridges * sizeof(struct amd_l3_cache *);
+                int size = k8_northbridges.num * sizeof(struct amd_l3_cache *);
 
                 l3_caches = kzalloc(size, GFP_ATOMIC);
                 if (!l3_caches)
@@ -556,12 +556,12 @@ static struct _cache_attr cache_disable_0 = __ATTR(cache_disable_0, 0644,
 static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644,
                 show_cache_disable_1, store_cache_disable_1);
 
-#else   /* CONFIG_CPU_SUP_AMD */
+#else   /* CONFIG_AMD_NB */
 static void __cpuinit
 amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf, int index)
 {
 };
-#endif /* CONFIG_CPU_SUP_AMD */
+#endif /* CONFIG_AMD_NB */
 
 static int
 __cpuinit cpuid4_cache_lookup_regs(int index,
@@ -1000,7 +1000,7 @@ static struct attribute *default_attrs[] = {
 
 static struct attribute *default_l3_attrs[] = {
         DEFAULT_SYSFS_CACHE_ATTRS,
-#ifdef CONFIG_CPU_SUP_AMD
+#ifdef CONFIG_AMD_NB
         &cache_disable_0.attr,
         &cache_disable_1.attr,
 #endif
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 39aaee5c1ab2..80c482382d5c 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -131,7 +131,8 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
         u32 low = 0, high = 0, address = 0;
         unsigned int bank, block;
         struct thresh_restart tr;
-        u8 lvt_off;
+        int lvt_off = -1;
+        u8 offset;
 
         for (bank = 0; bank < NR_BANKS; ++bank) {
                 for (block = 0; block < NR_BLOCKS; ++block) {
@@ -162,8 +163,28 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
                         if (shared_bank[bank] && c->cpu_core_id)
                                 break;
 #endif
-                        lvt_off = setup_APIC_eilvt_mce(THRESHOLD_APIC_VECTOR,
-                                                       APIC_EILVT_MSG_FIX, 0);
+                        offset = (high & MASK_LVTOFF_HI) >> 20;
+                        if (lvt_off < 0) {
+                                if (setup_APIC_eilvt(offset,
+                                                     THRESHOLD_APIC_VECTOR,
+                                                     APIC_EILVT_MSG_FIX, 0)) {
+                                        pr_err(FW_BUG "cpu %d, failed to "
+                                               "setup threshold interrupt "
+                                               "for bank %d, block %d "
+                                               "(MSR%08X=0x%x%08x)",
+                                               smp_processor_id(), bank, block,
+                                               address, high, low);
+                                        continue;
+                                }
+                                lvt_off = offset;
+                        } else if (lvt_off != offset) {
+                                pr_err(FW_BUG "cpu %d, invalid threshold "
+                                       "interrupt offset %d for bank %d,"
+                                       "block %d (MSR%08X=0x%x%08x)",
+                                       smp_processor_id(), lvt_off, bank,
+                                       block, address, high, low);
+                                continue;
+                        }
 
                         high &= ~MASK_LVTOFF_HI;
                         high |= lvt_off << 20;
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 169d8804a9f8..4b683267eca5 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -350,7 +350,7 @@ static void intel_thermal_interrupt(void)
 
 static void unexpected_thermal_interrupt(void)
 {
-        printk(KERN_ERR "CPU%d: Unexpected LVT TMR interrupt!\n",
+        printk(KERN_ERR "CPU%d: Unexpected LVT thermal interrupt!\n",
                         smp_processor_id());
         add_taint(TAINT_MACHINE_CHECK);
 }
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index c5f59d071425..ac140c7be396 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -827,7 +827,7 @@ int __init amd_special_default_mtrr(void)
 
         if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
                 return 0;
-        if (boot_cpu_data.x86 < 0xf || boot_cpu_data.x86 > 0x11)
+        if (boot_cpu_data.x86 < 0xf)
                 return 0;
         /* In case some hypervisor doesn't pass SYSCFG through: */
         if (rdmsr_safe(MSR_K8_SYSCFG, &l, &h) < 0)
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 7d28d7d03885..9f27228ceffd 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -64,18 +64,59 @@ static inline void k8_check_syscfg_dram_mod_en(void)
         }
 }
 
+/* Get the size of contiguous MTRR range */
+static u64 get_mtrr_size(u64 mask)
+{
+        u64 size;
+
+        mask >>= PAGE_SHIFT;
+        mask |= size_or_mask;
+        size = -mask;
+        size <<= PAGE_SHIFT;
+        return size;
+}
+
 /*
- * Returns the effective MTRR type for the region
- * Error returns:
- * - 0xFE - when the range is "not entirely covered" by _any_ var range MTRR
- * - 0xFF - when MTRR is not enabled
+ * Check and return the effective type for MTRR-MTRR type overlap.
+ * Returns 1 if the effective type is UNCACHEABLE, else returns 0
  */
-u8 mtrr_type_lookup(u64 start, u64 end)
+static int check_type_overlap(u8 *prev, u8 *curr)
+{
+        if (*prev == MTRR_TYPE_UNCACHABLE || *curr == MTRR_TYPE_UNCACHABLE) {
+                *prev = MTRR_TYPE_UNCACHABLE;
+                *curr = MTRR_TYPE_UNCACHABLE;
+                return 1;
+        }
+
+        if ((*prev == MTRR_TYPE_WRBACK && *curr == MTRR_TYPE_WRTHROUGH) ||
+            (*prev == MTRR_TYPE_WRTHROUGH && *curr == MTRR_TYPE_WRBACK)) {
+                *prev = MTRR_TYPE_WRTHROUGH;
+                *curr = MTRR_TYPE_WRTHROUGH;
+        }
+
+        if (*prev != *curr) {
+                *prev = MTRR_TYPE_UNCACHABLE;
+                *curr = MTRR_TYPE_UNCACHABLE;
+                return 1;
+        }
+
+        return 0;
+}
+
+/*
+ * Error/Semi-error returns:
+ * 0xFF - when MTRR is not enabled
+ * *repeat == 1 implies [start:end] spanned across MTRR range and type returned
+ *              corresponds only to [start:*partial_end].
+ *              Caller has to lookup again for [*partial_end:end].
+ */
+static u8 __mtrr_type_lookup(u64 start, u64 end, u64 *partial_end, int *repeat)
 {
         int i;
         u64 base, mask;
         u8 prev_match, curr_match;
 
+        *repeat = 0;
         if (!mtrr_state_set)
                 return 0xFF;
 
@@ -126,8 +167,34 @@ u8 mtrr_type_lookup(u64 start, u64 end)
 
                 start_state = ((start & mask) == (base & mask));
                 end_state = ((end & mask) == (base & mask));
-                if (start_state != end_state)
-                        return 0xFE;
+
+                if (start_state != end_state) {
+                        /*
+                         * We have start:end spanning across an MTRR.
+                         * We split the region into
+                         * either
+                         * (start:mtrr_end) (mtrr_end:end)
+                         * or
+                         * (start:mtrr_start) (mtrr_start:end)
+                         * depending on kind of overlap.
+                         * Return the type for first region and a pointer to
+                         * the start of second region so that caller will
+                         * lookup again on the second region.
+                         * Note: This way we handle multiple overlaps as well.
+                         */
+                        if (start_state)
+                                *partial_end = base + get_mtrr_size(mask);
+                        else
+                                *partial_end = base;
+
+                        if (unlikely(*partial_end <= start)) {
+                                WARN_ON(1);
+                                *partial_end = start + PAGE_SIZE;
+                        }
+
+                        end = *partial_end - 1; /* end is inclusive */
+                        *repeat = 1;
+                }
 
                 if ((start & mask) != (base & mask))
                         continue;
@@ -138,21 +205,8 @@ u8 mtrr_type_lookup(u64 start, u64 end)
                         continue;
                 }
 
-                if (prev_match == MTRR_TYPE_UNCACHABLE ||
-                    curr_match == MTRR_TYPE_UNCACHABLE) {
-                        return MTRR_TYPE_UNCACHABLE;
-                }
-
-                if ((prev_match == MTRR_TYPE_WRBACK &&
-                     curr_match == MTRR_TYPE_WRTHROUGH) ||
-                    (prev_match == MTRR_TYPE_WRTHROUGH &&
-                     curr_match == MTRR_TYPE_WRBACK)) {
-                        prev_match = MTRR_TYPE_WRTHROUGH;
-                        curr_match = MTRR_TYPE_WRTHROUGH;
-                }
-
-                if (prev_match != curr_match)
-                        return MTRR_TYPE_UNCACHABLE;
+                if (check_type_overlap(&prev_match, &curr_match))
+                        return curr_match;
         }
 
         if (mtrr_tom2) {
@@ -166,6 +220,36 @@ u8 mtrr_type_lookup(u64 start, u64 end)
         return mtrr_state.def_type;
 }
 
+/*
+ * Returns the effective MTRR type for the region
+ * Error return:
+ * 0xFF - when MTRR is not enabled
+ */
+u8 mtrr_type_lookup(u64 start, u64 end)
+{
+        u8 type, prev_type;
+        int repeat;
+        u64 partial_end;
+
+        type = __mtrr_type_lookup(start, end, &partial_end, &repeat);
+
+        /*
+         * Common path is with repeat = 0.
+         * However, we can have cases where [start:end] spans across some
+         * MTRR range. Do repeated lookups for that case here.
+         */
+        while (repeat) {
+                prev_type = type;
+                start = partial_end;
+                type = __mtrr_type_lookup(start, end, &partial_end, &repeat);
+
+                if (check_type_overlap(&prev_type, &type))
+                        return type;
+        }
+
+        return type;
+}
+
 /* Get the MSR pair relating to a var range */
 static void
 get_mtrr_var_range(unsigned int index, struct mtrr_var_range *vr)
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index fb329e9f8494..d9f4ff8fcd69 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -700,11 +700,10 @@ static void probe_nmi_watchdog(void)
 {
         switch (boot_cpu_data.x86_vendor) {
         case X86_VENDOR_AMD:
-                if (boot_cpu_data.x86 != 6 && boot_cpu_data.x86 != 15 &&
-                    boot_cpu_data.x86 != 16 && boot_cpu_data.x86 != 17)
-                        return;
-                wd_ops = &k7_wd_ops;
-                break;
+                if (boot_cpu_data.x86 == 6 ||
+                    (boot_cpu_data.x86 >= 0xf && boot_cpu_data.x86 <= 0x15))
+                        wd_ops = &k7_wd_ops;
+                return;
         case X86_VENDOR_INTEL:
                 /* Work around where perfctr1 doesn't have a working enable
                  * bit as described in the following errata:
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index d49079515122..c7f64e6f537a 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -44,6 +44,12 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c)
                 { X86_FEATURE_LBRV,             CR_EDX, 1, 0x8000000a, 0 },
                 { X86_FEATURE_SVML,             CR_EDX, 2, 0x8000000a, 0 },
                 { X86_FEATURE_NRIPS,            CR_EDX, 3, 0x8000000a, 0 },
+                { X86_FEATURE_TSCRATEMSR,       CR_EDX, 4, 0x8000000a, 0 },
+                { X86_FEATURE_VMCBCLEAN,        CR_EDX, 5, 0x8000000a, 0 },
+                { X86_FEATURE_FLUSHBYASID,      CR_EDX, 6, 0x8000000a, 0 },
+                { X86_FEATURE_DECODEASSISTS,    CR_EDX, 7, 0x8000000a, 0 },
+                { X86_FEATURE_PAUSEFILTER,      CR_EDX,10, 0x8000000a, 0 },
+                { X86_FEATURE_PFTHRESHOLD,      CR_EDX,12, 0x8000000a, 0 },
                 { 0, 0, 0, 0, 0 }
         };
 
diff --git a/arch/x86/kernel/crash_dump_64.c b/arch/x86/kernel/crash_dump_64.c
index 045b36cada65..994828899e09 100644
--- a/arch/x86/kernel/crash_dump_64.c
+++ b/arch/x86/kernel/crash_dump_64.c
@@ -34,7 +34,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
         if (!csize)
                 return 0;
 
-        vaddr = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE);
+        vaddr = ioremap_cache(pfn << PAGE_SHIFT, PAGE_SIZE);
         if (!vaddr)
                 return -ENOMEM;
 
@@ -46,6 +46,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
         } else
                 memcpy(buf, vaddr + offset, csize);
 
+        set_iounmap_nonlazy();
         iounmap(vaddr);
         return csize;
 }
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index ebdb85cf2686..76b8cd953dee 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -97,7 +97,6 @@ static void __init nvidia_bugs(int num, int slot, int func)
 }
 
 #if defined(CONFIG_ACPI) && defined(CONFIG_X86_IO_APIC)
-#if defined(CONFIG_ACPI) && defined(CONFIG_X86_IO_APIC)
 static u32 __init ati_ixp4x0_rev(int num, int slot, int func)
 {
         u32 d;
@@ -115,7 +114,6 @@ static u32 __init ati_ixp4x0_rev(int num, int slot, int func)
         d &= 0xff;
         return d;
 }
-#endif
 
 static void __init ati_bugs(int num, int slot, int func)
 {
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index fa99bae75ace..4572f25f9325 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -14,6 +14,7 @@
 #include <xen/hvc-console.h>
 #include <asm/pci-direct.h>
 #include <asm/fixmap.h>
+#include <asm/mrst.h>
 #include <asm/pgtable.h>
 #include <linux/usb/ehci_def.h>
 
@@ -239,6 +240,18 @@ static int __init setup_early_printk(char *buf)
                 if (!strncmp(buf, "xen", 3))
                         early_console_register(&xenboot_console, keep);
 #endif
+#ifdef CONFIG_X86_MRST_EARLY_PRINTK
+                if (!strncmp(buf, "mrst", 4)) {
+                        mrst_early_console_init();
+                        early_console_register(&early_mrst_console, keep);
+                }
+
+                if (!strncmp(buf, "hsu", 3)) {
+                        hsu_early_console_init();
+                        early_console_register(&early_hsu_console, keep);
+                }
+
+#endif
                 buf++;
         }
         return 0;
diff --git a/arch/x86/kernel/early_printk_mrst.c b/arch/x86/kernel/early_printk_mrst.c
new file mode 100644
index 000000000000..65df603622b2
--- /dev/null
+++ b/arch/x86/kernel/early_printk_mrst.c
@@ -0,0 +1,319 @@
+/*
+ * early_printk_mrst.c - early consoles for Intel MID platforms
+ *
+ * Copyright (c) 2008-2010, Intel Corporation
+ *
+ * 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
+ * of the License.
+ */
+
+/*
+ * This file implements two early consoles named mrst and hsu.
+ * mrst is based on Maxim3110 spi-uart device, it exists in both
+ * Moorestown and Medfield platforms, while hsu is based on a High
+ * Speed UART device which only exists in the Medfield platform
+ */
+
+#include <linux/serial_reg.h>
+#include <linux/serial_mfd.h>
+#include <linux/kmsg_dump.h>
+#include <linux/console.h>
+#include <linux/kernel.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/io.h>
+
+#include <asm/fixmap.h>
+#include <asm/pgtable.h>
+#include <asm/mrst.h>
+
+#define MRST_SPI_TIMEOUT                0x200000
+#define MRST_REGBASE_SPI0               0xff128000
+#define MRST_REGBASE_SPI1               0xff128400
+#define MRST_CLK_SPI0_REG               0xff11d86c
+
+/* Bit fields in CTRLR0 */
+#define SPI_DFS_OFFSET                  0
+
+#define SPI_FRF_OFFSET                  4
+#define SPI_FRF_SPI                     0x0
+#define SPI_FRF_SSP                     0x1
+#define SPI_FRF_MICROWIRE               0x2
+#define SPI_FRF_RESV                    0x3
+
+#define SPI_MODE_OFFSET                 6
+#define SPI_SCPH_OFFSET                 6
+#define SPI_SCOL_OFFSET                 7
+#define SPI_TMOD_OFFSET                 8
+#define SPI_TMOD_TR                     0x0             /* xmit & recv */
+#define SPI_TMOD_TO                     0x1             /* xmit only */
+#define SPI_TMOD_RO                     0x2             /* recv only */
+#define SPI_TMOD_EPROMREAD              0x3             /* eeprom read mode */
+
+#define SPI_SLVOE_OFFSET                10
+#define SPI_SRL_OFFSET                  11
+#define SPI_CFS_OFFSET                  12
+
+/* Bit fields in SR, 7 bits */
+#define SR_MASK                         0x7f            /* cover 7 bits */
+#define SR_BUSY                         (1 << 0)
+#define SR_TF_NOT_FULL                  (1 << 1)
+#define SR_TF_EMPT                      (1 << 2)
+#define SR_RF_NOT_EMPT                  (1 << 3)
+#define SR_RF_FULL                      (1 << 4)
+#define SR_TX_ERR                       (1 << 5)
+#define SR_DCOL                         (1 << 6)
+
+struct dw_spi_reg {
+        u32     ctrl0;
+        u32     ctrl1;
+        u32     ssienr;
+        u32     mwcr;
+        u32     ser;
+        u32     baudr;
+        u32     txfltr;
+        u32     rxfltr;
+        u32     txflr;
+        u32     rxflr;
+        u32     sr;
+        u32     imr;
+        u32     isr;
+        u32     risr;
+        u32     txoicr;
+        u32     rxoicr;
+        u32     rxuicr;
+        u32     msticr;
+        u32     icr;
+        u32     dmacr;
+        u32     dmatdlr;
+        u32     dmardlr;
+        u32     idr;
+        u32     version;
+
+        /* Currently operates as 32 bits, though only the low 16 bits matter */
+        u32     dr;
+} __packed;
+
+#define dw_readl(dw, name)              __raw_readl(&(dw)->name)
+#define dw_writel(dw, name, val)        __raw_writel((val), &(dw)->name)
+
+/* Default use SPI0 register for mrst, we will detect Penwell and use SPI1 */
+static unsigned long mrst_spi_paddr = MRST_REGBASE_SPI0;
+
+static u32 *pclk_spi0;
+/* Always contains an accessable address, start with 0 */
+static struct dw_spi_reg *pspi;
+
+static struct kmsg_dumper dw_dumper;
+static int dumper_registered;
+
+static void dw_kmsg_dump(struct kmsg_dumper *dumper,
+                        enum kmsg_dump_reason reason,
+                        const char *s1, unsigned long l1,
+                        const char *s2, unsigned long l2)
+{
+        int i;
+
+        /* When run to this, we'd better re-init the HW */
+        mrst_early_console_init();
+
+        for (i = 0; i < l1; i++)
+                early_mrst_console.write(&early_mrst_console, s1 + i, 1);
+        for (i = 0; i < l2; i++)
+                early_mrst_console.write(&early_mrst_console, s2 + i, 1);
+}
+
+/* Set the ratio rate to 115200, 8n1, IRQ disabled */
+static void max3110_write_config(void)
+{
+        u16 config;
+
+        config = 0xc001;
+        dw_writel(pspi, dr, config);
+}
+
+/* Translate char to a eligible word and send to max3110 */
+static void max3110_write_data(char c)
+{
+        u16 data;
+
+        data = 0x8000 | c;
+        dw_writel(pspi, dr, data);
+}
+
+void mrst_early_console_init(void)
+{
+        u32 ctrlr0 = 0;
+        u32 spi0_cdiv;
+        u32 freq; /* Freqency info only need be searched once */
+
+        /* Base clk is 100 MHz, the actual clk = 100M / (clk_divider + 1) */
+        pclk_spi0 = (void *)set_fixmap_offset_nocache(FIX_EARLYCON_MEM_BASE,
+                                                        MRST_CLK_SPI0_REG);
+        spi0_cdiv = ((*pclk_spi0) & 0xe00) >> 9;
+        freq = 100000000 / (spi0_cdiv + 1);
+
+        if (mrst_identify_cpu() == MRST_CPU_CHIP_PENWELL)
+                mrst_spi_paddr = MRST_REGBASE_SPI1;
+
+        pspi = (void *)set_fixmap_offset_nocache(FIX_EARLYCON_MEM_BASE,
+                                                mrst_spi_paddr);
+
+        /* Disable SPI controller */
+        dw_writel(pspi, ssienr, 0);
+
+        /* Set control param, 8 bits, transmit only mode */
+        ctrlr0 = dw_readl(pspi, ctrl0);
+
+        ctrlr0 &= 0xfcc0;
+        ctrlr0 |= 0xf | (SPI_FRF_SPI << SPI_FRF_OFFSET)
+                      | (SPI_TMOD_TO << SPI_TMOD_OFFSET);
+        dw_writel(pspi, ctrl0, ctrlr0);
+
+        /*
+         * Change the spi0 clk to comply with 115200 bps, use 100000 to
+         * calculate the clk dividor to make the clock a little slower
+         * than real baud rate.
+         */
+        dw_writel(pspi, baudr, freq/100000);
+
+        /* Disable all INT for early phase */
+        dw_writel(pspi, imr, 0x0);
+
+        /* Set the cs to spi-uart */
+        dw_writel(pspi, ser, 0x2);
+
+        /* Enable the HW, the last step for HW init */
+        dw_writel(pspi, ssienr, 0x1);
+
+        /* Set the default configuration */
+        max3110_write_config();
+
+        /* Register the kmsg dumper */
+        if (!dumper_registered) {
+                dw_dumper.dump = dw_kmsg_dump;
+                kmsg_dump_register(&dw_dumper);
+                dumper_registered = 1;
+        }
+}
+
+/* Slave select should be called in the read/write function */
+static void early_mrst_spi_putc(char c)
+{
+        unsigned int timeout;
+        u32 sr;
+
+        timeout = MRST_SPI_TIMEOUT;
+        /* Early putc needs to make sure the TX FIFO is not full */
+        while (--timeout) {
+                sr = dw_readl(pspi, sr);
+                if (!(sr & SR_TF_NOT_FULL))
+                        cpu_relax();
+                else
+                        break;
+        }
+
+        if (!timeout)
+                pr_warning("MRST earlycon: timed out\n");
+        else
+                max3110_write_data(c);
+}
+
+/* Early SPI only uses polling mode */
+static void early_mrst_spi_write(struct console *con, const char *str, unsigned n)
+{
+        int i;
+
+        for (i = 0; i < n && *str; i++) {
+                if (*str == '\n')
+                        early_mrst_spi_putc('\r');
+                early_mrst_spi_putc(*str);
+                str++;
+        }
+}
+
+struct console early_mrst_console = {
+        .name =         "earlymrst",
+        .write =        early_mrst_spi_write,
+        .flags =        CON_PRINTBUFFER,
+        .index =        -1,
+};
+
+/*
+ * Following is the early console based on Medfield HSU (High
+ * Speed UART) device.
+ */
+#define HSU_PORT2_PADDR         0xffa28180
+
+static void __iomem *phsu;
+
+void hsu_early_console_init(void)
+{
+        u8 lcr;
+
+        phsu = (void *)set_fixmap_offset_nocache(FIX_EARLYCON_MEM_BASE,
+                                                        HSU_PORT2_PADDR);
+
+        /* Disable FIFO */
+        writeb(0x0, phsu + UART_FCR);
+
+        /* Set to default 115200 bps, 8n1 */
+        lcr = readb(phsu + UART_LCR);
+        writeb((0x80 | lcr), phsu + UART_LCR);
+        writeb(0x18, phsu + UART_DLL);
+        writeb(lcr,  phsu + UART_LCR);
+        writel(0x3600, phsu + UART_MUL*4);
+
+        writeb(0x8, phsu + UART_MCR);
+        writeb(0x7, phsu + UART_FCR);
+        writeb(0x3, phsu + UART_LCR);
+
+        /* Clear IRQ status */
+        readb(phsu + UART_LSR);
+        readb(phsu + UART_RX);
+        readb(phsu + UART_IIR);
+        readb(phsu + UART_MSR);
+
+        /* Enable FIFO */
+        writeb(0x7, phsu + UART_FCR);
+}
+
+#define BOTH_EMPTY (UART_LSR_TEMT | UART_LSR_THRE)
+
+static void early_hsu_putc(char ch)
+{
+        unsigned int timeout = 10000; /* 10ms */
+        u8 status;
+
+        while (--timeout) {
+                status = readb(phsu + UART_LSR);
+                if (status & BOTH_EMPTY)
+                        break;
+                udelay(1);
+        }
+
+        /* Only write the char when there was no timeout */
+        if (timeout)
+                writeb(ch, phsu + UART_TX);
+}
+
+static void early_hsu_write(struct console *con, const char *str, unsigned n)
+{
+        int i;
+
+        for (i = 0; i < n && *str; i++) {
+                if (*str == '\n')
+                        early_hsu_putc('\r');
+                early_hsu_putc(*str);
+                str++;
+        }
+}
+
+struct console early_hsu_console = {
+        .name =         "earlyhsu",
+        .write =        early_hsu_write,
+        .flags =        CON_PRINTBUFFER,
+        .index =        -1,
+};
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 227d00920d2f..9fb188d7bc76 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -115,8 +115,7 @@
 
  /* unfortunately push/pop can't be no-op */
 .macro PUSH_GS
-        pushl $0
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi $0
 .endm
 .macro POP_GS pop=0
         addl $(4 + \pop), %esp
@@ -140,14 +139,12 @@
 #else   /* CONFIG_X86_32_LAZY_GS */
 
 .macro PUSH_GS
-        pushl %gs
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %gs
         /*CFI_REL_OFFSET gs, 0*/
 .endm
 
 .macro POP_GS pop=0
-98:     popl %gs
-        CFI_ADJUST_CFA_OFFSET -4
+98:     popl_cfi %gs
         /*CFI_RESTORE gs*/
   .if \pop <> 0
         add $\pop, %esp
@@ -195,35 +192,25 @@
 .macro SAVE_ALL
         cld
         PUSH_GS
-        pushl %fs
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %fs
         /*CFI_REL_OFFSET fs, 0;*/
-        pushl %es
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %es
         /*CFI_REL_OFFSET es, 0;*/
-        pushl %ds
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %ds
         /*CFI_REL_OFFSET ds, 0;*/
-        pushl %eax
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %eax
         CFI_REL_OFFSET eax, 0
-        pushl %ebp
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %ebp
         CFI_REL_OFFSET ebp, 0
-        pushl %edi
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %edi
         CFI_REL_OFFSET edi, 0
-        pushl %esi
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %esi
         CFI_REL_OFFSET esi, 0
-        pushl %edx
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %edx
         CFI_REL_OFFSET edx, 0
-        pushl %ecx
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %ecx
         CFI_REL_OFFSET ecx, 0
-        pushl %ebx
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %ebx
         CFI_REL_OFFSET ebx, 0
         movl $(__USER_DS), %edx
         movl %edx, %ds
@@ -234,39 +221,29 @@
 .endm
 
 .macro RESTORE_INT_REGS
-        popl %ebx
-        CFI_ADJUST_CFA_OFFSET -4
+        popl_cfi %ebx
         CFI_RESTORE ebx
-        popl %ecx
-        CFI_ADJUST_CFA_OFFSET -4
+        popl_cfi %ecx
         CFI_RESTORE ecx
-        popl %edx
-        CFI_ADJUST_CFA_OFFSET -4
+        popl_cfi %edx
         CFI_RESTORE edx
-        popl %esi
-        CFI_ADJUST_CFA_OFFSET -4
+        popl_cfi %esi
         CFI_RESTORE esi
-        popl %edi
-        CFI_ADJUST_CFA_OFFSET -4
+        popl_cfi %edi
         CFI_RESTORE edi
-        popl %ebp
-        CFI_ADJUST_CFA_OFFSET -4
+        popl_cfi %ebp
         CFI_RESTORE ebp
-        popl %eax
-        CFI_ADJUST_CFA_OFFSET -4
+        popl_cfi %eax
         CFI_RESTORE eax
 .endm
 
 .macro RESTORE_REGS pop=0
         RESTORE_INT_REGS
-1:      popl %ds
-        CFI_ADJUST_CFA_OFFSET -4
+1:      popl_cfi %ds
         /*CFI_RESTORE ds;*/
-2:      popl %es
-        CFI_ADJUST_CFA_OFFSET -4
+2:      popl_cfi %es
         /*CFI_RESTORE es;*/
-3:      popl %fs
-        CFI_ADJUST_CFA_OFFSET -4
+3:      popl_cfi %fs
         /*CFI_RESTORE fs;*/
         POP_GS \pop
 .pushsection .fixup, "ax"
@@ -320,16 +297,12 @@
 
 ENTRY(ret_from_fork)
         CFI_STARTPROC
-        pushl %eax
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %eax
         call schedule_tail
         GET_THREAD_INFO(%ebp)
-        popl %eax
-        CFI_ADJUST_CFA_OFFSET -4
-        pushl $0x0202                   # Reset kernel eflags
-        CFI_ADJUST_CFA_OFFSET 4
-        popfl
-        CFI_ADJUST_CFA_OFFSET -4
+        popl_cfi %eax
+        pushl_cfi $0x0202               # Reset kernel eflags
+        popfl_cfi
         jmp syscall_exit
         CFI_ENDPROC
 END(ret_from_fork)
@@ -409,29 +382,23 @@ sysenter_past_esp:
          * enough kernel state to call TRACE_IRQS_OFF can be called - but
          * we immediately enable interrupts at that point anyway.
          */
-        pushl $(__USER_DS)
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi $(__USER_DS)
         /*CFI_REL_OFFSET ss, 0*/
-        pushl %ebp
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %ebp
         CFI_REL_OFFSET esp, 0
-        pushfl
+        pushfl_cfi
         orl $X86_EFLAGS_IF, (%esp)
-        CFI_ADJUST_CFA_OFFSET 4
-        pushl $(__USER_CS)
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi $(__USER_CS)
         /*CFI_REL_OFFSET cs, 0*/
         /*
          * Push current_thread_info()->sysenter_return to the stack.
          * A tiny bit of offset fixup is necessary - 4*4 means the 4 words
          * pushed above; +8 corresponds to copy_thread's esp0 setting.
          */
-        pushl (TI_sysenter_return-THREAD_SIZE+8+4*4)(%esp)
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi (TI_sysenter_return-THREAD_SIZE+8+4*4)(%esp)
         CFI_REL_OFFSET eip, 0
 
-        pushl %eax
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %eax
         SAVE_ALL
         ENABLE_INTERRUPTS(CLBR_NONE)
 
@@ -486,8 +453,7 @@ sysenter_audit:
         movl %eax,%edx                  /* 2nd arg: syscall number */
         movl $AUDIT_ARCH_I386,%eax      /* 1st arg: audit arch */
         call audit_syscall_entry
-        pushl %ebx
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %ebx
         movl PT_EAX(%esp),%eax          /* reload syscall number */
         jmp sysenter_do_call
 
@@ -529,8 +495,7 @@ ENDPROC(ia32_sysenter_target)
         # system call handler stub
 ENTRY(system_call)
         RING0_INT_FRAME                 # can't unwind into user space anyway
-        pushl %eax                      # save orig_eax
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %eax                  # save orig_eax
         SAVE_ALL
         GET_THREAD_INFO(%ebp)
                                         # system call tracing in operation / emulation
@@ -566,7 +531,6 @@ restore_all_notrace:
         je ldt_ss                       # returning to user-space with LDT SS
 restore_nocheck:
         RESTORE_REGS 4                  # skip orig_eax/error_code
-        CFI_ADJUST_CFA_OFFSET -4
 irq_return:
         INTERRUPT_RETURN
 .section .fixup,"ax"
@@ -619,10 +583,8 @@ ldt_ss:
         shr $16, %edx
         mov %dl, GDT_ESPFIX_SS + 4 /* bits 16..23 */
         mov %dh, GDT_ESPFIX_SS + 7 /* bits 24..31 */
-        pushl $__ESPFIX_SS
-        CFI_ADJUST_CFA_OFFSET 4
-        push %eax                       /* new kernel esp */
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi $__ESPFIX_SS
+        pushl_cfi %eax                  /* new kernel esp */
         /* Disable interrupts, but do not irqtrace this section: we
          * will soon execute iret and the tracer was already set to
          * the irqstate after the iret */
@@ -666,11 +628,9 @@ work_notifysig:				# deal with pending signals and
 
         ALIGN
 work_notifysig_v86:
-        pushl %ecx                      # save ti_flags for do_notify_resume
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %ecx                  # save ti_flags for do_notify_resume
         call save_v86_state             # %eax contains pt_regs pointer
-        popl %ecx
-        CFI_ADJUST_CFA_OFFSET -4
+        popl_cfi %ecx
         movl %eax, %esp
 #else
         movl %esp, %eax
@@ -750,14 +710,18 @@ ptregs_##name: \
 #define PTREGSCALL3(name) \
         ALIGN; \
 ptregs_##name: \
+        CFI_STARTPROC; \
         leal 4(%esp),%eax; \
-        pushl %eax; \
+        pushl_cfi %eax; \
         movl PT_EDX(%eax),%ecx; \
         movl PT_ECX(%eax),%edx; \
         movl PT_EBX(%eax),%eax; \
         call sys_##name; \
         addl $4,%esp; \
-        ret
+        CFI_ADJUST_CFA_OFFSET -4; \
+        ret; \
+        CFI_ENDPROC; \
+ENDPROC(ptregs_##name)
 
 PTREGSCALL1(iopl)
 PTREGSCALL0(fork)
@@ -772,15 +736,19 @@ PTREGSCALL1(vm86old)
 /* Clone is an oddball.  The 4th arg is in %edi */
         ALIGN;
 ptregs_clone:
+        CFI_STARTPROC
         leal 4(%esp),%eax
-        pushl %eax
-        pushl PT_EDI(%eax)
+        pushl_cfi %eax
+        pushl_cfi PT_EDI(%eax)
         movl PT_EDX(%eax),%ecx
         movl PT_ECX(%eax),%edx
         movl PT_EBX(%eax),%eax
         call sys_clone
         addl $8,%esp
+        CFI_ADJUST_CFA_OFFSET -8
         ret
+        CFI_ENDPROC
+ENDPROC(ptregs_clone)
 
 .macro FIXUP_ESPFIX_STACK
 /*
@@ -795,10 +763,8 @@ ptregs_clone:
         mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */
         shl $16, %eax
         addl %esp, %eax                 /* the adjusted stack pointer */
-        pushl $__KERNEL_DS
-        CFI_ADJUST_CFA_OFFSET 4
-        pushl %eax
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi $__KERNEL_DS
+        pushl_cfi %eax
         lss (%esp), %esp                /* switch to the normal stack segment */
         CFI_ADJUST_CFA_OFFSET -8
 .endm
@@ -835,8 +801,7 @@ vector=FIRST_EXTERNAL_VECTOR
       .if vector <> FIRST_EXTERNAL_VECTOR
         CFI_ADJUST_CFA_OFFSET -4
       .endif
-1:      pushl $(~vector+0x80)   /* Note: always in signed byte range */
-        CFI_ADJUST_CFA_OFFSET 4
+1:      pushl_cfi $(~vector+0x80)       /* Note: always in signed byte range */
       .if ((vector-FIRST_EXTERNAL_VECTOR)%7) <> 6
         jmp 2f
       .endif
@@ -876,8 +841,7 @@ ENDPROC(common_interrupt)
 #define BUILD_INTERRUPT3(name, nr, fn)  \
 ENTRY(name)                             \
         RING0_INT_FRAME;                \
-        pushl $~(nr);                   \
-        CFI_ADJUST_CFA_OFFSET 4;        \
+        pushl_cfi $~(nr);               \
         SAVE_ALL;                       \
         TRACE_IRQS_OFF                  \
         movl %esp,%eax;                 \
@@ -893,21 +857,18 @@ ENDPROC(name)
 
 ENTRY(coprocessor_error)
         RING0_INT_FRAME
-        pushl $0
-        CFI_ADJUST_CFA_OFFSET 4
-        pushl $do_coprocessor_error
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi $0
+        pushl_cfi $do_coprocessor_error
         jmp error_code
         CFI_ENDPROC
 END(coprocessor_error)
 
 ENTRY(simd_coprocessor_error)
         RING0_INT_FRAME
-        pushl $0
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi $0
 #ifdef CONFIG_X86_INVD_BUG
         /* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */
-661:    pushl $do_general_protection
+661:    pushl_cfi $do_general_protection
 662:
 .section .altinstructions,"a"
         .balign 4
@@ -922,19 +883,16 @@ ENTRY(simd_coprocessor_error)
 664:
 .previous
 #else
-        pushl $do_simd_coprocessor_error
+        pushl_cfi $do_simd_coprocessor_error
 #endif
-        CFI_ADJUST_CFA_OFFSET 4
         jmp error_code
         CFI_ENDPROC
 END(simd_coprocessor_error)
 
 ENTRY(device_not_available)
         RING0_INT_FRAME
-        pushl $-1                       # mark this as an int
-        CFI_ADJUST_CFA_OFFSET 4
-        pushl $do_device_not_available
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi $-1                   # mark this as an int
+        pushl_cfi $do_device_not_available
         jmp error_code
         CFI_ENDPROC
 END(device_not_available)
@@ -956,82 +914,68 @@ END(native_irq_enable_sysexit)
 
 ENTRY(overflow)
         RING0_INT_FRAME
-        pushl $0
-        CFI_ADJUST_CFA_OFFSET 4
-        pushl $do_overflow
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi $0
+        pushl_cfi $do_overflow
         jmp error_code
         CFI_ENDPROC
 END(overflow)
 
 ENTRY(bounds)
         RING0_INT_FRAME
-        pushl $0
-        CFI_ADJUST_CFA_OFFSET 4
-        pushl $do_bounds
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi $0
+        pushl_cfi $do_bounds
         jmp error_code
         CFI_ENDPROC
 END(bounds)
 
 ENTRY(invalid_op)
         RING0_INT_FRAME
-        pushl $0
-        CFI_ADJUST_CFA_OFFSET 4
-        pushl $do_invalid_op
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi $0
+        pushl_cfi $do_invalid_op
         jmp error_code
         CFI_ENDPROC
 END(invalid_op)
 
 ENTRY(coprocessor_segment_overrun)
         RING0_INT_FRAME
-        pushl $0
-        CFI_ADJUST_CFA_OFFSET 4
-        pushl $do_coprocessor_segment_overrun
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi $0
+        pushl_cfi $do_coprocessor_segment_overrun
         jmp error_code
         CFI_ENDPROC
 END(coprocessor_segment_overrun)
 
 ENTRY(invalid_TSS)
         RING0_EC_FRAME
-        pushl $do_invalid_TSS
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi $do_invalid_TSS
         jmp error_code
         CFI_ENDPROC
 END(invalid_TSS)
 
 ENTRY(segment_not_present)
         RING0_EC_FRAME
-        pushl $do_segment_not_present
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi $do_segment_not_present
         jmp error_code
         CFI_ENDPROC
 END(segment_not_present)
 
 ENTRY(stack_segment)
         RING0_EC_FRAME
-        pushl $do_stack_segment
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi $do_stack_segment
         jmp error_code
         CFI_ENDPROC
 END(stack_segment)
 
 ENTRY(alignment_check)
         RING0_EC_FRAME
-        pushl $do_alignment_check
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi $do_alignment_check
         jmp error_code
         CFI_ENDPROC
 END(alignment_check)
 
 ENTRY(divide_error)
         RING0_INT_FRAME
-        pushl $0                        # no error code
-        CFI_ADJUST_CFA_OFFSET 4
-        pushl $do_divide_error
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi $0                    # no error code
+        pushl_cfi $do_divide_error
         jmp error_code
         CFI_ENDPROC
 END(divide_error)
@@ -1039,10 +983,8 @@ END(divide_error)
 #ifdef CONFIG_X86_MCE
 ENTRY(machine_check)
         RING0_INT_FRAME
-        pushl $0
-        CFI_ADJUST_CFA_OFFSET 4
-        pushl machine_check_vector
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi $0
+        pushl_cfi machine_check_vector
         jmp error_code
         CFI_ENDPROC
 END(machine_check)
@@ -1050,10 +992,8 @@ END(machine_check)
 
 ENTRY(spurious_interrupt_bug)
         RING0_INT_FRAME
-        pushl $0
-        CFI_ADJUST_CFA_OFFSET 4
-        pushl $do_spurious_interrupt_bug
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi $0
+        pushl_cfi $do_spurious_interrupt_bug
         jmp error_code
         CFI_ENDPROC
 END(spurious_interrupt_bug)
@@ -1084,8 +1024,7 @@ ENTRY(xen_sysenter_target)
 
 ENTRY(xen_hypervisor_callback)
         CFI_STARTPROC
-        pushl $0
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi $0
         SAVE_ALL
         TRACE_IRQS_OFF
 
@@ -1121,23 +1060,20 @@ ENDPROC(xen_hypervisor_callback)
 # We distinguish between categories by maintaining a status value in EAX.
 ENTRY(xen_failsafe_callback)
         CFI_STARTPROC
-        pushl %eax
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %eax
         movl $1,%eax
 1:      mov 4(%esp),%ds
 2:      mov 8(%esp),%es
 3:      mov 12(%esp),%fs
 4:      mov 16(%esp),%gs
         testl %eax,%eax
-        popl %eax
-        CFI_ADJUST_CFA_OFFSET -4
+        popl_cfi %eax
         lea 16(%esp),%esp
         CFI_ADJUST_CFA_OFFSET -16
         jz 5f
         addl $16,%esp
         jmp iret_exc            # EAX != 0 => Category 2 (Bad IRET)
-5:      pushl $0                # EAX == 0 => Category 1 (Bad segment)
-        CFI_ADJUST_CFA_OFFSET 4
+5:      pushl_cfi $0            # EAX == 0 => Category 1 (Bad segment)
         SAVE_ALL
         jmp ret_from_exception
         CFI_ENDPROC
@@ -1287,40 +1223,29 @@ syscall_table_size=(.-sys_call_table)
 
 ENTRY(page_fault)
         RING0_EC_FRAME
-        pushl $do_page_fault
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi $do_page_fault
         ALIGN
 error_code:
         /* the function address is in %gs's slot on the stack */
-        pushl %fs
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %fs
         /*CFI_REL_OFFSET fs, 0*/
-        pushl %es
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %es
         /*CFI_REL_OFFSET es, 0*/
-        pushl %ds
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %ds
         /*CFI_REL_OFFSET ds, 0*/
-        pushl %eax
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %eax
         CFI_REL_OFFSET eax, 0
-        pushl %ebp
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %ebp
         CFI_REL_OFFSET ebp, 0
-        pushl %edi
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %edi
         CFI_REL_OFFSET edi, 0
-        pushl %esi
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %esi
         CFI_REL_OFFSET esi, 0
-        pushl %edx
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %edx
         CFI_REL_OFFSET edx, 0
-        pushl %ecx
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %ecx
         CFI_REL_OFFSET ecx, 0
-        pushl %ebx
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %ebx
         CFI_REL_OFFSET ebx, 0
         cld
         movl $(__KERNEL_PERCPU), %ecx
@@ -1362,12 +1287,9 @@ END(page_fault)
         movl TSS_sysenter_sp0 + \offset(%esp), %esp
         CFI_DEF_CFA esp, 0
         CFI_UNDEFINED eip
-        pushfl
-        CFI_ADJUST_CFA_OFFSET 4
-        pushl $__KERNEL_CS
-        CFI_ADJUST_CFA_OFFSET 4
-        pushl $sysenter_past_esp
-        CFI_ADJUST_CFA_OFFSET 4
+        pushfl_cfi
+        pushl_cfi $__KERNEL_CS
+        pushl_cfi $sysenter_past_esp
         CFI_REL_OFFSET eip, 0
 .endm
 
@@ -1377,8 +1299,7 @@ ENTRY(debug)
         jne debug_stack_correct
         FIX_STACK 12, debug_stack_correct, debug_esp_fix_insn
 debug_stack_correct:
-        pushl $-1                       # mark this as an int
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi $-1                   # mark this as an int
         SAVE_ALL
         TRACE_IRQS_OFF
         xorl %edx,%edx                  # error code 0
@@ -1398,32 +1319,27 @@ END(debug)
  */
 ENTRY(nmi)
         RING0_INT_FRAME
-        pushl %eax
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %eax
         movl %ss, %eax
         cmpw $__ESPFIX_SS, %ax
-        popl %eax
-        CFI_ADJUST_CFA_OFFSET -4
+        popl_cfi %eax
         je nmi_espfix_stack
         cmpl $ia32_sysenter_target,(%esp)
         je nmi_stack_fixup
-        pushl %eax
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %eax
         movl %esp,%eax
         /* Do not access memory above the end of our stack page,
          * it might not exist.
          */
         andl $(THREAD_SIZE-1),%eax
         cmpl $(THREAD_SIZE-20),%eax
-        popl %eax
-        CFI_ADJUST_CFA_OFFSET -4
+        popl_cfi %eax
         jae nmi_stack_correct
         cmpl $ia32_sysenter_target,12(%esp)
         je nmi_debug_stack_check
 nmi_stack_correct:
         /* We have a RING0_INT_FRAME here */
-        pushl %eax
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %eax
         SAVE_ALL
         xorl %edx,%edx          # zero error code
         movl %esp,%eax          # pt_regs pointer
@@ -1452,18 +1368,14 @@ nmi_espfix_stack:
          *
          * create the pointer to lss back
          */
-        pushl %ss
-        CFI_ADJUST_CFA_OFFSET 4
-        pushl %esp
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %ss
+        pushl_cfi %esp
         addl $4, (%esp)
         /* copy the iret frame of 12 bytes */
         .rept 3
-        pushl 16(%esp)
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi 16(%esp)
         .endr
-        pushl %eax
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi %eax
         SAVE_ALL
         FIXUP_ESPFIX_STACK              # %eax == %esp
         xorl %edx,%edx                  # zero error code
@@ -1477,8 +1389,7 @@ END(nmi)
 
 ENTRY(int3)
         RING0_INT_FRAME
-        pushl $-1                       # mark this as an int
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi $-1                   # mark this as an int
         SAVE_ALL
         TRACE_IRQS_OFF
         xorl %edx,%edx          # zero error code
@@ -1490,8 +1401,7 @@ END(int3)
 
 ENTRY(general_protection)
         RING0_EC_FRAME
-        pushl $do_general_protection
-        CFI_ADJUST_CFA_OFFSET 4
+        pushl_cfi $do_general_protection
         jmp error_code
         CFI_ENDPROC
 END(general_protection)
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index c375c79065f8..a7ae7fd1010f 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -213,23 +213,17 @@ ENDPROC(native_usergs_sysret64)
         .macro FAKE_STACK_FRAME child_rip
         /* push in order ss, rsp, eflags, cs, rip */
         xorl %eax, %eax
-        pushq $__KERNEL_DS /* ss */
-        CFI_ADJUST_CFA_OFFSET   8
+        pushq_cfi $__KERNEL_DS /* ss */
         /*CFI_REL_OFFSET        ss,0*/
-        pushq %rax /* rsp */
-        CFI_ADJUST_CFA_OFFSET   8
+        pushq_cfi %rax /* rsp */
         CFI_REL_OFFSET  rsp,0
-        pushq $X86_EFLAGS_IF /* eflags - interrupts on */
-        CFI_ADJUST_CFA_OFFSET   8
+        pushq_cfi $X86_EFLAGS_IF /* eflags - interrupts on */
         /*CFI_REL_OFFSET        rflags,0*/
-        pushq $__KERNEL_CS /* cs */
-        CFI_ADJUST_CFA_OFFSET   8
+        pushq_cfi $__KERNEL_CS /* cs */
         /*CFI_REL_OFFSET        cs,0*/
-        pushq \child_rip /* rip */
-        CFI_ADJUST_CFA_OFFSET   8
+        pushq_cfi \child_rip /* rip */
         CFI_REL_OFFSET  rip,0
-        pushq   %rax /* orig rax */
-        CFI_ADJUST_CFA_OFFSET   8
+        pushq_cfi %rax /* orig rax */
         .endm
 
         .macro UNFAKE_STACK_FRAME
@@ -398,10 +392,8 @@ ENTRY(ret_from_fork)
 
         LOCK ; btr $TIF_FORK,TI_flags(%r8)
 
-        push kernel_eflags(%rip)
-        CFI_ADJUST_CFA_OFFSET 8
-        popf                                    # reset kernel eflags
-        CFI_ADJUST_CFA_OFFSET -8
+        pushq_cfi kernel_eflags(%rip)
+        popfq_cfi                               # reset kernel eflags
 
         call schedule_tail                      # rdi: 'prev' task parameter
 
@@ -521,11 +513,9 @@ sysret_careful:
         jnc sysret_signal
         TRACE_IRQS_ON
         ENABLE_INTERRUPTS(CLBR_NONE)
-        pushq %rdi
-        CFI_ADJUST_CFA_OFFSET 8
+        pushq_cfi %rdi
         call schedule
-        popq  %rdi
-        CFI_ADJUST_CFA_OFFSET -8
+        popq_cfi %rdi
         jmp sysret_check
 
         /* Handle a signal */
@@ -634,11 +624,9 @@ int_careful:
         jnc  int_very_careful
         TRACE_IRQS_ON
         ENABLE_INTERRUPTS(CLBR_NONE)
-        pushq %rdi
-        CFI_ADJUST_CFA_OFFSET 8
+        pushq_cfi %rdi
         call schedule
-        popq %rdi
-        CFI_ADJUST_CFA_OFFSET -8
+        popq_cfi %rdi
         DISABLE_INTERRUPTS(CLBR_NONE)
         TRACE_IRQS_OFF
         jmp int_with_check
@@ -652,12 +640,10 @@ int_check_syscall_exit_work:
         /* Check for syscall exit trace */
         testl $_TIF_WORK_SYSCALL_EXIT,%edx
         jz int_signal
-        pushq %rdi
-        CFI_ADJUST_CFA_OFFSET 8
+        pushq_cfi %rdi
         leaq 8(%rsp),%rdi       # &ptregs -> arg1
         call syscall_trace_leave
-        popq %rdi
-        CFI_ADJUST_CFA_OFFSET -8
+        popq_cfi %rdi
         andl $~(_TIF_WORK_SYSCALL_EXIT|_TIF_SYSCALL_EMU),%edi
         jmp int_restore_rest
 
@@ -714,9 +700,8 @@ END(ptregscall_common)
 
 ENTRY(stub_execve)
         CFI_STARTPROC
-        popq %r11
-        CFI_ADJUST_CFA_OFFSET -8
-        CFI_REGISTER rip, r11
+        addq $8, %rsp
+        PARTIAL_FRAME 0
         SAVE_REST
         FIXUP_TOP_OF_STACK %r11
         movq %rsp, %rcx
@@ -735,7 +720,7 @@ END(stub_execve)
 ENTRY(stub_rt_sigreturn)
         CFI_STARTPROC
         addq $8, %rsp
-        CFI_ADJUST_CFA_OFFSET   -8
+        PARTIAL_FRAME 0
         SAVE_REST
         movq %rsp,%rdi
         FIXUP_TOP_OF_STACK %r11
@@ -766,8 +751,7 @@ vector=FIRST_EXTERNAL_VECTOR
       .if vector <> FIRST_EXTERNAL_VECTOR
         CFI_ADJUST_CFA_OFFSET -8
       .endif
-1:      pushq $(~vector+0x80)   /* Note: always in signed byte range */
-        CFI_ADJUST_CFA_OFFSET 8
+1:      pushq_cfi $(~vector+0x80)       /* Note: always in signed byte range */
       .if ((vector-FIRST_EXTERNAL_VECTOR)%7) <> 6
         jmp 2f
       .endif
@@ -796,8 +780,8 @@ END(interrupt)
 
 /* 0(%rsp): ~(interrupt number) */
         .macro interrupt func
-        subq $10*8, %rsp
-        CFI_ADJUST_CFA_OFFSET 10*8
+        subq $ORIG_RAX-ARGOFFSET+8, %rsp
+        CFI_ADJUST_CFA_OFFSET ORIG_RAX-ARGOFFSET+8
         call save_args
         PARTIAL_FRAME 0
         call \func
@@ -822,6 +806,7 @@ ret_from_intr:
         TRACE_IRQS_OFF
         decl PER_CPU_VAR(irq_count)
         leaveq
+        CFI_RESTORE             rbp
         CFI_DEF_CFA_REGISTER    rsp
         CFI_ADJUST_CFA_OFFSET   -8
 exit_intr:
@@ -903,11 +888,9 @@ retint_careful:
         jnc   retint_signal
         TRACE_IRQS_ON
         ENABLE_INTERRUPTS(CLBR_NONE)
-        pushq %rdi
-        CFI_ADJUST_CFA_OFFSET   8
+        pushq_cfi %rdi
         call  schedule
-        popq %rdi
-        CFI_ADJUST_CFA_OFFSET   -8
+        popq_cfi %rdi
         GET_THREAD_INFO(%rcx)
         DISABLE_INTERRUPTS(CLBR_NONE)
         TRACE_IRQS_OFF
@@ -956,8 +939,7 @@ END(common_interrupt)
 .macro apicinterrupt num sym do_sym
 ENTRY(\sym)
         INTR_FRAME
-        pushq $~(\num)
-        CFI_ADJUST_CFA_OFFSET 8
+        pushq_cfi $~(\num)
         interrupt \do_sym
         jmp ret_from_intr
         CFI_ENDPROC
@@ -1036,8 +1018,8 @@ ENTRY(\sym)
         INTR_FRAME
         PARAVIRT_ADJUST_EXCEPTION_FRAME
         pushq_cfi $-1           /* ORIG_RAX: no syscall to restart */
-        subq $15*8,%rsp
-        CFI_ADJUST_CFA_OFFSET 15*8
+        subq $ORIG_RAX-R15, %rsp
+        CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
         call error_entry
         DEFAULT_FRAME 0
         movq %rsp,%rdi          /* pt_regs pointer */
@@ -1052,9 +1034,9 @@ END(\sym)
 ENTRY(\sym)
         INTR_FRAME
         PARAVIRT_ADJUST_EXCEPTION_FRAME
-        pushq $-1               /* ORIG_RAX: no syscall to restart */
-        CFI_ADJUST_CFA_OFFSET 8
-        subq $15*8, %rsp
+        pushq_cfi $-1           /* ORIG_RAX: no syscall to restart */
+        subq $ORIG_RAX-R15, %rsp
+        CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
         call save_paranoid
         TRACE_IRQS_OFF
         movq %rsp,%rdi          /* pt_regs pointer */
@@ -1070,9 +1052,9 @@ END(\sym)
 ENTRY(\sym)
         INTR_FRAME
         PARAVIRT_ADJUST_EXCEPTION_FRAME
-        pushq $-1               /* ORIG_RAX: no syscall to restart */
-        CFI_ADJUST_CFA_OFFSET 8
-        subq $15*8, %rsp
+        pushq_cfi $-1           /* ORIG_RAX: no syscall to restart */
+        subq $ORIG_RAX-R15, %rsp
+        CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
         call save_paranoid
         TRACE_IRQS_OFF
         movq %rsp,%rdi          /* pt_regs pointer */
@@ -1089,8 +1071,8 @@ END(\sym)
 ENTRY(\sym)
         XCPT_FRAME
         PARAVIRT_ADJUST_EXCEPTION_FRAME
-        subq $15*8,%rsp
-        CFI_ADJUST_CFA_OFFSET 15*8
+        subq $ORIG_RAX-R15, %rsp
+        CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
         call error_entry
         DEFAULT_FRAME 0
         movq %rsp,%rdi                  /* pt_regs pointer */
@@ -1107,8 +1089,8 @@ END(\sym)
 ENTRY(\sym)
         XCPT_FRAME
         PARAVIRT_ADJUST_EXCEPTION_FRAME
-        subq $15*8,%rsp
-        CFI_ADJUST_CFA_OFFSET 15*8
+        subq $ORIG_RAX-R15, %rsp
+        CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
         call save_paranoid
         DEFAULT_FRAME 0
         TRACE_IRQS_OFF
@@ -1139,16 +1121,14 @@ zeroentry simd_coprocessor_error do_simd_coprocessor_error
         /* edi:  new selector */
 ENTRY(native_load_gs_index)
         CFI_STARTPROC
-        pushf
-        CFI_ADJUST_CFA_OFFSET 8
+        pushfq_cfi
         DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI)
         SWAPGS
 gs_change:
         movl %edi,%gs
 2:      mfence          /* workaround */
         SWAPGS
-        popf
-        CFI_ADJUST_CFA_OFFSET -8
+        popfq_cfi
         ret
         CFI_ENDPROC
 END(native_load_gs_index)
@@ -1215,8 +1195,7 @@ END(kernel_execve)
 /* Call softirq on interrupt stack. Interrupts are off. */
 ENTRY(call_softirq)
         CFI_STARTPROC
-        push %rbp
-        CFI_ADJUST_CFA_OFFSET   8
+        pushq_cfi %rbp
         CFI_REL_OFFSET rbp,0
         mov  %rsp,%rbp
         CFI_DEF_CFA_REGISTER rbp
@@ -1225,6 +1204,7 @@ ENTRY(call_softirq)
         push  %rbp                      # backlink for old unwinder
         call __do_softirq
         leaveq
+        CFI_RESTORE             rbp
         CFI_DEF_CFA_REGISTER    rsp
         CFI_ADJUST_CFA_OFFSET   -8
         decl PER_CPU_VAR(irq_count)
@@ -1368,7 +1348,7 @@ paranoidzeroentry machine_check *machine_check_vector(%rip)
 
         /* ebx: no swapgs flag */
 ENTRY(paranoid_exit)
-        INTR_FRAME
+        DEFAULT_FRAME
         DISABLE_INTERRUPTS(CLBR_NONE)
         TRACE_IRQS_OFF
         testl %ebx,%ebx                         /* swapgs needed? */
@@ -1445,7 +1425,6 @@ error_swapgs:
 error_sti:
         TRACE_IRQS_OFF
         ret
-        CFI_ENDPROC
 
 /*
  * There are two places in the kernel that can potentially fault with
@@ -1470,6 +1449,7 @@ bstep_iret:
         /* Fix truncated RIP */
         movq %rcx,RIP+8(%rsp)
         jmp error_swapgs
+        CFI_ENDPROC
 END(error_entry)
 
 
@@ -1498,8 +1478,8 @@ ENTRY(nmi)
         INTR_FRAME
         PARAVIRT_ADJUST_EXCEPTION_FRAME
         pushq_cfi $-1
-        subq $15*8, %rsp
-        CFI_ADJUST_CFA_OFFSET 15*8
+        subq $ORIG_RAX-R15, %rsp
+        CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
         call save_paranoid
         DEFAULT_FRAME 0
         /* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 7494999141b3..efaf906daf93 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -440,9 +440,9 @@ static int hpet_legacy_next_event(unsigned long delta,
 static DEFINE_PER_CPU(struct hpet_dev *, cpu_hpet_dev);
 static struct hpet_dev  *hpet_devs;
 
-void hpet_msi_unmask(unsigned int irq)
+void hpet_msi_unmask(struct irq_data *data)
 {
-        struct hpet_dev *hdev = get_irq_data(irq);
+        struct hpet_dev *hdev = data->handler_data;
         unsigned int cfg;
 
         /* unmask it */
@@ -451,10 +451,10 @@ void hpet_msi_unmask(unsigned int irq)
         hpet_writel(cfg, HPET_Tn_CFG(hdev->num));
 }
 
-void hpet_msi_mask(unsigned int irq)
+void hpet_msi_mask(struct irq_data *data)
 {
+        struct hpet_dev *hdev = data->handler_data;
         unsigned int cfg;
-        struct hpet_dev *hdev = get_irq_data(irq);
 
         /* mask it */
         cfg = hpet_readl(HPET_Tn_CFG(hdev->num));
@@ -462,18 +462,14 @@ void hpet_msi_mask(unsigned int irq)
         hpet_writel(cfg, HPET_Tn_CFG(hdev->num));
 }
 
-void hpet_msi_write(unsigned int irq, struct msi_msg *msg)
+void hpet_msi_write(struct hpet_dev *hdev, struct msi_msg *msg)
 {
-        struct hpet_dev *hdev = get_irq_data(irq);
-
         hpet_writel(msg->data, HPET_Tn_ROUTE(hdev->num));
         hpet_writel(msg->address_lo, HPET_Tn_ROUTE(hdev->num) + 4);
 }
 
-void hpet_msi_read(unsigned int irq, struct msi_msg *msg)
+void hpet_msi_read(struct hpet_dev *hdev, struct msi_msg *msg)
 {
-        struct hpet_dev *hdev = get_irq_data(irq);
-
         msg->data = hpet_readl(HPET_Tn_ROUTE(hdev->num));
         msg->address_lo = hpet_readl(HPET_Tn_ROUTE(hdev->num) + 4);
         msg->address_hi = 0;
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index a46cb3522c0c..58bb239a2fd7 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -68,19 +68,22 @@ static void __cpuinit init_thread_xstate(void)
          */
 
         if (!HAVE_HWFP) {
+                /*
+                 * Disable xsave as we do not support it if i387
+                 * emulation is enabled.
+                 */
+                setup_clear_cpu_cap(X86_FEATURE_XSAVE);
+                setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
                 xstate_size = sizeof(struct i387_soft_struct);
                 return;
         }
 
         if (cpu_has_fxsr)
                 xstate_size = sizeof(struct i387_fxsave_struct);
-#ifdef CONFIG_X86_32
         else
                 xstate_size = sizeof(struct i387_fsave_struct);
-#endif
 }
 
-#ifdef CONFIG_X86_64
 /*
  * Called at bootup to set up the initial FPU state that is later cloned
  * into all processes.
@@ -88,12 +91,21 @@ static void __cpuinit init_thread_xstate(void)
 
 void __cpuinit fpu_init(void)
 {
-        unsigned long oldcr0 = read_cr0();
-
-        set_in_cr4(X86_CR4_OSFXSR);
-        set_in_cr4(X86_CR4_OSXMMEXCPT);
+        unsigned long cr0;
+        unsigned long cr4_mask = 0;
 
-        write_cr0(oldcr0 & ~(X86_CR0_TS|X86_CR0_EM)); /* clear TS and EM */
+        if (cpu_has_fxsr)
+                cr4_mask |= X86_CR4_OSFXSR;
+        if (cpu_has_xmm)
+                cr4_mask |= X86_CR4_OSXMMEXCPT;
+        if (cr4_mask)
+                set_in_cr4(cr4_mask);
+
+        cr0 = read_cr0();
+        cr0 &= ~(X86_CR0_TS|X86_CR0_EM); /* clear TS and EM */
+        if (!HAVE_HWFP)
+                cr0 |= X86_CR0_EM;
+        write_cr0(cr0);
 
         if (!smp_processor_id())
                 init_thread_xstate();
@@ -104,24 +116,12 @@ void __cpuinit fpu_init(void)
         clear_used_math();
 }
 
-#else   /* CONFIG_X86_64 */
-
-void __cpuinit fpu_init(void)
-{
-        if (!smp_processor_id())
-                init_thread_xstate();
-}
-
-#endif  /* CONFIG_X86_32 */
-
 void fpu_finit(struct fpu *fpu)
 {
-#ifdef CONFIG_X86_32
         if (!HAVE_HWFP) {
                 finit_soft_fpu(&fpu->state->soft);
                 return;
         }
-#endif
 
         if (cpu_has_fxsr) {
                 struct i387_fxsave_struct *fx = &fpu->state->fxsave;
@@ -386,19 +386,17 @@ convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk)
 #ifdef CONFIG_X86_64
         env->fip = fxsave->rip;
         env->foo = fxsave->rdp;
+        /*
+         * should be actually ds/cs at fpu exception time, but
+         * that information is not available in 64bit mode.
+         */
+        env->fcs = task_pt_regs(tsk)->cs;
         if (tsk == current) {
-                /*
-                 * should be actually ds/cs at fpu exception time, but
-                 * that information is not available in 64bit mode.
-                 */
-                asm("mov %%ds, %[fos]" : [fos] "=r" (env->fos));
-                asm("mov %%cs, %[fcs]" : [fcs] "=r" (env->fcs));
+                savesegment(ds, env->fos);
         } else {
-                struct pt_regs *regs = task_pt_regs(tsk);
-
-                env->fos = 0xffff0000 | tsk->thread.ds;
-                env->fcs = regs->cs;
+                env->fos = tsk->thread.ds;
         }
+        env->fos |= 0xffff0000;
 #else
         env->fip = fxsave->fip;
         env->fcs = (u16) fxsave->fcs | ((u32) fxsave->fop << 16);
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index cafa7c80ac95..20757cb2efa3 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -29,24 +29,10 @@
  * plus some generic x86 specific things if generic specifics makes
  * any sense at all.
  */
+static void init_8259A(int auto_eoi);
 
 static int i8259A_auto_eoi;
 DEFINE_RAW_SPINLOCK(i8259A_lock);
-static void mask_and_ack_8259A(unsigned int);
-static void mask_8259A(void);
-static void unmask_8259A(void);
-static void disable_8259A_irq(unsigned int irq);
-static void enable_8259A_irq(unsigned int irq);
-static void init_8259A(int auto_eoi);
-static int i8259A_irq_pending(unsigned int irq);
-
-struct irq_chip i8259A_chip = {
-        .name           = "XT-PIC",
-        .mask           = disable_8259A_irq,
-        .disable        = disable_8259A_irq,
-        .unmask         = enable_8259A_irq,
-        .mask_ack       = mask_and_ack_8259A,
-};
 
 /*
  * 8259A PIC functions to handle ISA devices:
@@ -68,7 +54,7 @@ unsigned int cached_irq_mask = 0xffff;
  */
 unsigned long io_apic_irqs;
 
-static void disable_8259A_irq(unsigned int irq)
+static void mask_8259A_irq(unsigned int irq)
 {
         unsigned int mask = 1 << irq;
         unsigned long flags;
@@ -82,7 +68,12 @@ static void disable_8259A_irq(unsigned int irq)
         raw_spin_unlock_irqrestore(&i8259A_lock, flags);
 }
 
-static void enable_8259A_irq(unsigned int irq)
+static void disable_8259A_irq(struct irq_data *data)
+{
+        mask_8259A_irq(data->irq);
+}
+
+static void unmask_8259A_irq(unsigned int irq)
 {
         unsigned int mask = ~(1 << irq);
         unsigned long flags;
@@ -96,6 +87,11 @@ static void enable_8259A_irq(unsigned int irq)
         raw_spin_unlock_irqrestore(&i8259A_lock, flags);
 }
 
+static void enable_8259A_irq(struct irq_data *data)
+{
+        unmask_8259A_irq(data->irq);
+}
+
 static int i8259A_irq_pending(unsigned int irq)
 {
         unsigned int mask = 1<<irq;
@@ -117,7 +113,7 @@ static void make_8259A_irq(unsigned int irq)
         disable_irq_nosync(irq);
         io_apic_irqs &= ~(1<<irq);
         set_irq_chip_and_handler_name(irq, &i8259A_chip, handle_level_irq,
-                                      "XT");
+                                      i8259A_chip.name);
         enable_irq(irq);
 }
 
@@ -150,8 +146,9 @@ static inline int i8259A_irq_real(unsigned int irq)
  * first, _then_ send the EOI, and the order of EOI
  * to the two 8259s is important!
  */
-static void mask_and_ack_8259A(unsigned int irq)
+static void mask_and_ack_8259A(struct irq_data *data)
 {
+        unsigned int irq = data->irq;
         unsigned int irqmask = 1 << irq;
         unsigned long flags;
 
@@ -223,6 +220,14 @@ spurious_8259A_irq:
         }
 }
 
+struct irq_chip i8259A_chip = {
+        .name           = "XT-PIC",
+        .irq_mask       = disable_8259A_irq,
+        .irq_disable    = disable_8259A_irq,
+        .irq_unmask     = enable_8259A_irq,
+        .irq_mask_ack   = mask_and_ack_8259A,
+};
+
 static char irq_trigger[2];
 /**
  * ELCR registers (0x4d0, 0x4d1) control edge/level of IRQ
@@ -342,9 +347,9 @@ static void init_8259A(int auto_eoi)
                  * In AEOI mode we just have to mask the interrupt
                  * when acking.
                  */
-                i8259A_chip.mask_ack = disable_8259A_irq;
+                i8259A_chip.irq_mask_ack = disable_8259A_irq;
         else
-                i8259A_chip.mask_ack = mask_and_ack_8259A;
+                i8259A_chip.irq_mask_ack = mask_and_ack_8259A;
 
         udelay(100);            /* wait for 8259A to initialize */
 
@@ -363,14 +368,6 @@ static void init_8259A(int auto_eoi)
 static void legacy_pic_noop(void) { };
 static void legacy_pic_uint_noop(unsigned int unused) { };
 static void legacy_pic_int_noop(int unused) { };
-
-static struct irq_chip dummy_pic_chip  = {
-        .name = "dummy pic",
-        .mask = legacy_pic_uint_noop,
-        .unmask = legacy_pic_uint_noop,
-        .disable = legacy_pic_uint_noop,
-        .mask_ack = legacy_pic_uint_noop,
-};
 static int legacy_pic_irq_pending_noop(unsigned int irq)
 {
         return 0;
@@ -378,7 +375,9 @@ static int legacy_pic_irq_pending_noop(unsigned int irq)
 
 struct legacy_pic null_legacy_pic = {
         .nr_legacy_irqs = 0,
-        .chip = &dummy_pic_chip,
+        .chip = &dummy_irq_chip,
+        .mask = legacy_pic_uint_noop,
+        .unmask = legacy_pic_uint_noop,
         .mask_all = legacy_pic_noop,
         .restore_mask = legacy_pic_noop,
         .init = legacy_pic_int_noop,
@@ -389,7 +388,9 @@ struct legacy_pic null_legacy_pic = {
 struct legacy_pic default_legacy_pic = {
         .nr_legacy_irqs = NR_IRQS_LEGACY,
         .chip  = &i8259A_chip,
-        .mask_all  = mask_8259A,
+        .mask = mask_8259A_irq,
+        .unmask = unmask_8259A_irq,
+        .mask_all = mask_8259A,
         .restore_mask = unmask_8259A,
         .init = init_8259A,
         .irq_pending = i8259A_irq_pending,
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 44edb03fc9ec..83ec0175f986 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -159,7 +159,7 @@ int show_interrupts(struct seq_file *p, void *v)
         seq_printf(p, "%*d: ", prec, i);
         for_each_online_cpu(j)
                 seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
-        seq_printf(p, " %8s", desc->chip->name);
+        seq_printf(p, " %8s", desc->irq_data.chip->name);
         seq_printf(p, "-%-8s", desc->name);
 
         if (action) {
@@ -282,6 +282,7 @@ void fixup_irqs(void)
         unsigned int irq, vector;
         static int warned;
         struct irq_desc *desc;
+        struct irq_data *data;
 
         for_each_irq_desc(irq, desc) {
                 int break_affinity = 0;
@@ -296,7 +297,8 @@ void fixup_irqs(void)
                 /* interrupt's are disabled at this point */
                 raw_spin_lock(&desc->lock);
 
-                affinity = desc->affinity;
+                data = &desc->irq_data;
+                affinity = data->affinity;
                 if (!irq_has_action(irq) ||
                     cpumask_equal(affinity, cpu_online_mask)) {
                         raw_spin_unlock(&desc->lock);
@@ -315,16 +317,16 @@ void fixup_irqs(void)
                         affinity = cpu_all_mask;
                 }
 
-                if (!(desc->status & IRQ_MOVE_PCNTXT) && desc->chip->mask)
-                        desc->chip->mask(irq);
+                if (!(desc->status & IRQ_MOVE_PCNTXT) && data->chip->irq_mask)
+                        data->chip->irq_mask(data);
 
-                if (desc->chip->set_affinity)
-                        desc->chip->set_affinity(irq, affinity);
+                if (data->chip->irq_set_affinity)
+                        data->chip->irq_set_affinity(data, affinity, true);
                 else if (!(warned++))
                         set_affinity = 0;
 
-                if (!(desc->status & IRQ_MOVE_PCNTXT) && desc->chip->unmask)
-                        desc->chip->unmask(irq);
+                if (!(desc->status & IRQ_MOVE_PCNTXT) && data->chip->irq_unmask)
+                        data->chip->irq_unmask(data);
 
                 raw_spin_unlock(&desc->lock);
 
@@ -355,10 +357,10 @@ void fixup_irqs(void)
                 if (irr  & (1 << (vector % 32))) {
                         irq = __get_cpu_var(vector_irq)[vector];
 
-                        desc = irq_to_desc(irq);
+                        data = irq_get_irq_data(irq);
                         raw_spin_lock(&desc->lock);
-                        if (desc->chip->retrigger)
-                                desc->chip->retrigger(irq);
+                        if (data->chip->irq_retrigger)
+                                data->chip->irq_retrigger(data);
                         raw_spin_unlock(&desc->lock);
                 }
         }
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index 713969b9266b..c752e973958d 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -100,6 +100,8 @@ int vector_used_by_percpu_irq(unsigned int vector)
 
 void __init init_ISA_irqs(void)
 {
+        struct irq_chip *chip = legacy_pic->chip;
+        const char *name = chip->name;
         int i;
 
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC)
@@ -107,19 +109,8 @@ void __init init_ISA_irqs(void)
 #endif
         legacy_pic->init(0);
 
-        /*
-         * 16 old-style INTA-cycle interrupts:
-         */
-        for (i = 0; i < legacy_pic->nr_legacy_irqs; i++) {
-                struct irq_desc *desc = irq_to_desc(i);
-
-                desc->status = IRQ_DISABLED;
-                desc->action = NULL;
-                desc->depth = 1;
-
-                set_irq_chip_and_handler_name(i, &i8259A_chip,
-                                              handle_level_irq, "XT");
-        }
+        for (i = 0; i < legacy_pic->nr_legacy_irqs; i++)
+                set_irq_chip_and_handler_name(i, chip, handle_level_irq, name);
 }
 
 void __init init_IRQ(void)
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 035c8c529181..b3ea9db39db6 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -36,7 +36,7 @@ static int init_one_level2_page(struct kimage *image, pgd_t *pgd,
                 if (!page)
                         goto out;
                 pud = (pud_t *)page_address(page);
-                memset(pud, 0, PAGE_SIZE);
+                clear_page(pud);
                 set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE));
         }
         pud = pud_offset(pgd, addr);
@@ -45,7 +45,7 @@ static int init_one_level2_page(struct kimage *image, pgd_t *pgd,
                 if (!page)
                         goto out;
                 pmd = (pmd_t *)page_address(page);
-                memset(pmd, 0, PAGE_SIZE);
+                clear_page(pmd);
                 set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
         }
         pmd = pmd_offset(pud, addr);
diff --git a/arch/x86/kernel/olpc-xo1.c b/arch/x86/kernel/olpc-xo1.c
new file mode 100644
index 000000000000..f5442c03abc3
--- /dev/null
+++ b/arch/x86/kernel/olpc-xo1.c
@@ -0,0 +1,140 @@
+/*
+ * Support for features of the OLPC XO-1 laptop
+ *
+ * Copyright (C) 2010 One Laptop per Child
+ * Copyright (C) 2006 Red Hat, Inc.
+ * Copyright (C) 2006 Advanced Micro Devices, Inc.
+ *
+ * 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.
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/pci_ids.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+
+#include <asm/io.h>
+#include <asm/olpc.h>
+
+#define DRV_NAME "olpc-xo1"
+
+#define PMS_BAR         4
+#define ACPI_BAR        5
+
+/* PMC registers (PMS block) */
+#define PM_SCLK         0x10
+#define PM_IN_SLPCTL    0x20
+#define PM_WKXD         0x34
+#define PM_WKD          0x30
+#define PM_SSC          0x54
+
+/* PM registers (ACPI block) */
+#define PM1_CNT         0x08
+#define PM_GPE0_STS     0x18
+
+static unsigned long acpi_base;
+static unsigned long pms_base;
+
+static void xo1_power_off(void)
+{
+        printk(KERN_INFO "OLPC XO-1 power off sequence...\n");
+
+        /* Enable all of these controls with 0 delay */
+        outl(0x40000000, pms_base + PM_SCLK);
+        outl(0x40000000, pms_base + PM_IN_SLPCTL);
+        outl(0x40000000, pms_base + PM_WKXD);
+        outl(0x40000000, pms_base + PM_WKD);
+
+        /* Clear status bits (possibly unnecessary) */
+        outl(0x0002ffff, pms_base  + PM_SSC);
+        outl(0xffffffff, acpi_base + PM_GPE0_STS);
+
+        /* Write SLP_EN bit to start the machinery */
+        outl(0x00002000, acpi_base + PM1_CNT);
+}
+
+/* Read the base addresses from the PCI BAR info */
+static int __devinit setup_bases(struct pci_dev *pdev)
+{
+        int r;
+
+        r = pci_enable_device_io(pdev);
+        if (r) {
+                dev_err(&pdev->dev, "can't enable device IO\n");
+                return r;
+        }
+
+        r = pci_request_region(pdev, ACPI_BAR, DRV_NAME);
+        if (r) {
+                dev_err(&pdev->dev, "can't alloc PCI BAR #%d\n", ACPI_BAR);
+                return r;
+        }
+
+        r = pci_request_region(pdev, PMS_BAR, DRV_NAME);
+        if (r) {
+                dev_err(&pdev->dev, "can't alloc PCI BAR #%d\n", PMS_BAR);
+                pci_release_region(pdev, ACPI_BAR);
+                return r;
+        }
+
+        acpi_base = pci_resource_start(pdev, ACPI_BAR);
+        pms_base = pci_resource_start(pdev, PMS_BAR);
+
+        return 0;
+}
+
+static int __devinit olpc_xo1_probe(struct platform_device *pdev)
+{
+        struct pci_dev *pcidev;
+        int r;
+
+        pcidev = pci_get_device(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CS5536_ISA,
+                                NULL);
+        if (!pdev)
+                return -ENODEV;
+
+        r = setup_bases(pcidev);
+        if (r)
+                return r;
+
+        pm_power_off = xo1_power_off;
+
+        printk(KERN_INFO "OLPC XO-1 support registered\n");
+        return 0;
+}
+
+static int __devexit olpc_xo1_remove(struct platform_device *pdev)
+{
+        pm_power_off = NULL;
+        return 0;
+}
+
+static struct platform_driver olpc_xo1_driver = {
+        .driver = {
+                .name = DRV_NAME,
+                .owner = THIS_MODULE,
+        },
+        .probe = olpc_xo1_probe,
+        .remove = __devexit_p(olpc_xo1_remove),
+};
+
+static int __init olpc_xo1_init(void)
+{
+        return platform_driver_register(&olpc_xo1_driver);
+}
+
+static void __exit olpc_xo1_exit(void)
+{
+        platform_driver_unregister(&olpc_xo1_driver);
+}
+
+MODULE_AUTHOR("Daniel Drake <dsd@laptop.org>");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:olpc-xo1");
+
+module_init(olpc_xo1_init);
+module_exit(olpc_xo1_exit);
diff --git a/arch/x86/kernel/olpc.c b/arch/x86/kernel/olpc.c
index 0e0cdde519be..edaf3fe8dc5e 100644
--- a/arch/x86/kernel/olpc.c
+++ b/arch/x86/kernel/olpc.c
@@ -17,6 +17,7 @@
 #include <linux/spinlock.h>
 #include <linux/io.h>
 #include <linux/string.h>
+#include <linux/platform_device.h>
 
 #include <asm/geode.h>
 #include <asm/setup.h>
@@ -114,6 +115,7 @@ int olpc_ec_cmd(unsigned char cmd, unsigned char *inbuf, size_t inlen,
         unsigned long flags;
         int ret = -EIO;
         int i;
+        int restarts = 0;
 
         spin_lock_irqsave(&ec_lock, flags);
 
@@ -169,7 +171,9 @@ restart:
                         if (wait_on_obf(0x6c, 1)) {
                                 printk(KERN_ERR "olpc-ec:  timeout waiting for"
                                                 " EC to provide data!\n");
-                                goto restart;
+                                if (restarts++ < 10)
+                                        goto restart;
+                                goto err;
                         }
                         outbuf[i] = inb(0x68);
                         pr_devel("olpc-ec:  received 0x%x\n", outbuf[i]);
@@ -183,8 +187,21 @@ err:
 }
 EXPORT_SYMBOL_GPL(olpc_ec_cmd);
 
-#ifdef CONFIG_OLPC_OPENFIRMWARE
-static void __init platform_detect(void)
+static bool __init check_ofw_architecture(void)
+{
+        size_t propsize;
+        char olpc_arch[5];
+        const void *args[] = { NULL, "architecture", olpc_arch, (void *)5 };
+        void *res[] = { &propsize };
+
+        if (olpc_ofw("getprop", args, res)) {
+                printk(KERN_ERR "ofw: getprop call failed!\n");
+                return false;
+        }
+        return propsize == 5 && strncmp("OLPC", olpc_arch, 5) == 0;
+}
+
+static u32 __init get_board_revision(void)
 {
         size_t propsize;
         __be32 rev;
@@ -193,45 +210,43 @@ static void __init platform_detect(void)
 
         if (olpc_ofw("getprop", args, res) || propsize != 4) {
                 printk(KERN_ERR "ofw: getprop call failed!\n");
-                rev = cpu_to_be32(0);
+                return cpu_to_be32(0);
         }
-        olpc_platform_info.boardrev = be32_to_cpu(rev);
+        return be32_to_cpu(rev);
 }
-#else
-static void __init platform_detect(void)
+
+static bool __init platform_detect(void)
 {
-        /* stopgap until OFW support is added to the kernel */
-        olpc_platform_info.boardrev = olpc_board(0xc2);
+        if (!check_ofw_architecture())
+                return false;
+        olpc_platform_info.flags |= OLPC_F_PRESENT;
+        olpc_platform_info.boardrev = get_board_revision();
+        return true;
 }
-#endif
 
-static int __init olpc_init(void)
+static int __init add_xo1_platform_devices(void)
 {
-        unsigned char *romsig;
+        struct platform_device *pdev;
 
-        /* The ioremap check is dangerous; limit what we run it on */
-        if (!is_geode() || cs5535_has_vsa2())
-                return 0;
+        pdev = platform_device_register_simple("xo1-rfkill", -1, NULL, 0);
+        if (IS_ERR(pdev))
+                return PTR_ERR(pdev);
 
-        spin_lock_init(&ec_lock);
+        pdev = platform_device_register_simple("olpc-xo1", -1, NULL, 0);
+        if (IS_ERR(pdev))
+                return PTR_ERR(pdev);
 
-        romsig = ioremap(0xffffffc0, 16);
-        if (!romsig)
-                return 0;
+        return 0;
+}
 
-        if (strncmp(romsig, "CL1   Q", 7))
-                goto unmap;
-        if (strncmp(romsig+6, romsig+13, 3)) {
-                printk(KERN_INFO "OLPC BIOS signature looks invalid.  "
-                                "Assuming not OLPC\n");
-                goto unmap;
-        }
+static int __init olpc_init(void)
+{
+        int r = 0;
 
-        printk(KERN_INFO "OLPC board with OpenFirmware %.16s\n", romsig);
-        olpc_platform_info.flags |= OLPC_F_PRESENT;
+        if (!olpc_ofw_present() || !platform_detect())
+                return 0;
 
-        /* get the platform revision */
-        platform_detect();
+        spin_lock_init(&ec_lock);
 
         /* assume B1 and above models always have a DCON */
         if (olpc_board_at_least(olpc_board(0xb1)))
@@ -242,8 +257,10 @@ static int __init olpc_init(void)
                         (unsigned char *) &olpc_platform_info.ecver, 1);
 
 #ifdef CONFIG_PCI_OLPC
-        /* If the VSA exists let it emulate PCI, if not emulate in kernel */
-        if (!cs5535_has_vsa2())
+        /* If the VSA exists let it emulate PCI, if not emulate in kernel.
+         * XO-1 only. */
+        if (olpc_platform_info.boardrev < olpc_board_pre(0xd0) &&
+                        !cs5535_has_vsa2())
                 x86_init.pci.arch_init = pci_olpc_init;
 #endif
 
@@ -252,8 +269,12 @@ static int __init olpc_init(void)
                         olpc_platform_info.boardrev >> 4,
                         olpc_platform_info.ecver);
 
-unmap:
-        iounmap(romsig);
+        if (olpc_platform_info.boardrev < olpc_board_pre(0xd0)) { /* XO-1 */
+                r = add_xo1_platform_devices();
+                if (r)
+                        return r;
+        }
+
         return 0;
 }
 
diff --git a/arch/x86/kernel/olpc_ofw.c b/arch/x86/kernel/olpc_ofw.c
index 3218aa71ab5e..787320464379 100644
--- a/arch/x86/kernel/olpc_ofw.c
+++ b/arch/x86/kernel/olpc_ofw.c
@@ -74,6 +74,12 @@ int __olpc_ofw(const char *name, int nr_args, const void **args, int nr_res,
 }
 EXPORT_SYMBOL_GPL(__olpc_ofw);
 
+bool olpc_ofw_present(void)
+{
+        return olpc_ofw_cif != NULL;
+}
+EXPORT_SYMBOL_GPL(olpc_ofw_present);
+
 /* OFW cif _should_ be above this address */
 #define OFW_MIN 0xff000000
 
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 1db183ed7c01..c5b250011fd4 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -413,7 +413,6 @@ struct pv_mmu_ops pv_mmu_ops = {
 
         .alloc_pte = paravirt_nop,
         .alloc_pmd = paravirt_nop,
-        .alloc_pmd_clone = paravirt_nop,
         .alloc_pud = paravirt_nop,
         .release_pte = paravirt_nop,
         .release_pmd = paravirt_nop,
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index 0f7f130caa67..c562207b1b3d 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -39,7 +39,7 @@
 #include <asm/cacheflush.h>
 #include <asm/swiotlb.h>
 #include <asm/dma.h>
-#include <asm/k8.h>
+#include <asm/amd_nb.h>
 #include <asm/x86_init.h>
 
 static unsigned long iommu_bus_base;    /* GART remapping area (physical) */
@@ -560,8 +560,11 @@ static void enable_gart_translations(void)
 {
         int i;
 
-        for (i = 0; i < num_k8_northbridges; i++) {
-                struct pci_dev *dev = k8_northbridges[i];
+        if (!k8_northbridges.gart_supported)
+                return;
+
+        for (i = 0; i < k8_northbridges.num; i++) {
+                struct pci_dev *dev = k8_northbridges.nb_misc[i];
 
                 enable_gart_translation(dev, __pa(agp_gatt_table));
         }
@@ -592,16 +595,19 @@ static void gart_fixup_northbridges(struct sys_device *dev)
         if (!fix_up_north_bridges)
                 return;
 
+        if (!k8_northbridges.gart_supported)
+                return;
+
         pr_info("PCI-DMA: Restoring GART aperture settings\n");
 
-        for (i = 0; i < num_k8_northbridges; i++) {
-                struct pci_dev *dev = k8_northbridges[i];
+        for (i = 0; i < k8_northbridges.num; i++) {
+                struct pci_dev *dev = k8_northbridges.nb_misc[i];
 
                 /*
                  * Don't enable translations just yet.  That is the next
                  * step.  Restore the pre-suspend aperture settings.
                  */
-                pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, aperture_order << 1);
+                gart_set_size_and_enable(dev, aperture_order);
                 pci_write_config_dword(dev, AMD64_GARTAPERTUREBASE, aperture_alloc >> 25);
         }
 }
@@ -649,8 +655,8 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
 
         aper_size = aper_base = info->aper_size = 0;
         dev = NULL;
-        for (i = 0; i < num_k8_northbridges; i++) {
-                dev = k8_northbridges[i];
+        for (i = 0; i < k8_northbridges.num; i++) {
+                dev = k8_northbridges.nb_misc[i];
                 new_aper_base = read_aperture(dev, &new_aper_size);
                 if (!new_aper_base)
                         goto nommu;
@@ -718,10 +724,13 @@ static void gart_iommu_shutdown(void)
         if (!no_agp)
                 return;
 
-        for (i = 0; i < num_k8_northbridges; i++) {
+        if (!k8_northbridges.gart_supported)
+                return;
+
+        for (i = 0; i < k8_northbridges.num; i++) {
                 u32 ctl;
 
-                dev = k8_northbridges[i];
+                dev = k8_northbridges.nb_misc[i];
                 pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl);
 
                 ctl &= ~GARTEN;
@@ -739,7 +748,7 @@ int __init gart_iommu_init(void)
         unsigned long scratch;
         long i;
 
-        if (num_k8_northbridges == 0)
+        if (!k8_northbridges.gart_supported)
                 return 0;
 
 #ifndef CONFIG_AGP_AMD64
diff --git a/arch/x86/kernel/pmtimer_64.c b/arch/x86/kernel/pmtimer_64.c
deleted file mode 100644
index b112406f1996..000000000000
--- a/arch/x86/kernel/pmtimer_64.c
+++ /dev/null
@@ -1,69 +0,0 @@
-/* Ported over from i386 by AK, original copyright was:
- *
- * (C) Dominik Brodowski <linux@brodo.de> 2003
- *
- * Driver to use the Power Management Timer (PMTMR) available in some
- * southbridges as primary timing source for the Linux kernel.
- *
- * Based on parts of linux/drivers/acpi/hardware/hwtimer.c, timer_pit.c,
- * timer_hpet.c, and on Arjan van de Ven's implementation for 2.4.
- *
- * This file is licensed under the GPL v2.
- *
- * Dropped all the hardware bug workarounds for now. Hopefully they
- * are not needed on 64bit chipsets.
- */
-
-#include <linux/jiffies.h>
-#include <linux/kernel.h>
-#include <linux/time.h>
-#include <linux/init.h>
-#include <linux/cpumask.h>
-#include <linux/acpi_pmtmr.h>
-
-#include <asm/io.h>
-#include <asm/proto.h>
-#include <asm/msr.h>
-#include <asm/vsyscall.h>
-
-static inline u32 cyc2us(u32 cycles)
-{
-        /* The Power Management Timer ticks at 3.579545 ticks per microsecond.
-         * 1 / PM_TIMER_FREQUENCY == 0.27936511 =~ 286/1024 [error: 0.024%]
-         *
-         * Even with HZ = 100, delta is at maximum 35796 ticks, so it can
-         * easily be multiplied with 286 (=0x11E) without having to fear
-         * u32 overflows.
-         */
-        cycles *= 286;
-        return (cycles >> 10);
-}
-
-static unsigned pmtimer_wait_tick(void)
-{
-        u32 a, b;
-        for (a = b = inl(pmtmr_ioport) & ACPI_PM_MASK;
-             a == b;
-             b = inl(pmtmr_ioport) & ACPI_PM_MASK)
-                cpu_relax();
-        return b;
-}
-
-/* note: wait time is rounded up to one tick */
-void pmtimer_wait(unsigned us)
-{
-        u32 a, b;
-        a = pmtimer_wait_tick();
-        do {
-                b = inl(pmtmr_ioport);
-                cpu_relax();
-        } while (cyc2us(b - a) < us);
-}
-
-static int __init nopmtimer_setup(char *s)
-{
-        pmtmr_ioport = 0;
-        return 1;
-}
-
-__setup("nopmtimer", nopmtimer_setup);
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 3d9ea531ddd1..b3d7a3a04f38 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -424,7 +424,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
         load_TLS(next, cpu);
 
         /* Must be after DS reload */
-        unlazy_fpu(prev_p);
+        __unlazy_fpu(prev_p);
 
         /* Make sure cpu is ready for new context */
         if (preload_fpu)
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index e3af342fe83a..7a4cf14223ba 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -84,7 +84,7 @@ static int __init reboot_setup(char *str)
                         }
                                 /* we will leave sorting out the final value
                                    when we are ready to reboot, since we might not
-                                   have set up boot_cpu_id or smp_num_cpu */
+                                   have detected BSP APIC ID or smp_num_cpu */
                         break;
 #endif /* CONFIG_SMP */
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 00e167870f71..a59f6a6df5e2 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -83,7 +83,6 @@
 #include <asm/dmi.h>
 #include <asm/io_apic.h>
 #include <asm/ist.h>
-#include <asm/vmi.h>
 #include <asm/setup_arch.h>
 #include <asm/bios_ebda.h>
 #include <asm/cacheflush.h>
@@ -107,7 +106,7 @@
 #include <asm/percpu.h>
 #include <asm/topology.h>
 #include <asm/apicdef.h>
-#include <asm/k8.h>
+#include <asm/amd_nb.h>
 #ifdef CONFIG_X86_64
 #include <asm/numa_64.h>
 #endif
@@ -126,7 +125,6 @@ unsigned long max_pfn_mapped;
 RESERVE_BRK(dmi_alloc, 65536);
 #endif
 
-unsigned int boot_cpu_id __read_mostly;
 
 static __initdata unsigned long _brk_start = (unsigned long)__brk_base;
 unsigned long _brk_end = (unsigned long)__brk_base;
@@ -619,79 +617,7 @@ static __init void reserve_ibft_region(void)
                 reserve_early_overlap_ok(addr, addr + size, "ibft");
 }
 
-#ifdef CONFIG_X86_RESERVE_LOW_64K
-static int __init dmi_low_memory_corruption(const struct dmi_system_id *d)
-{
-        printk(KERN_NOTICE
-                "%s detected: BIOS may corrupt low RAM, working around it.\n",
-                d->ident);
-
-        e820_update_range(0, 0x10000, E820_RAM, E820_RESERVED);
-        sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
-
-        return 0;
-}
-#endif
-
-/* List of systems that have known low memory corruption BIOS problems */
-static struct dmi_system_id __initdata bad_bios_dmi_table[] = {
-#ifdef CONFIG_X86_RESERVE_LOW_64K
-        {
-                .callback = dmi_low_memory_corruption,
-                .ident = "AMI BIOS",
-                .matches = {
-                        DMI_MATCH(DMI_BIOS_VENDOR, "American Megatrends Inc."),
-                },
-        },
-        {
-                .callback = dmi_low_memory_corruption,
-                .ident = "Phoenix BIOS",
-                .matches = {
-                        DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies"),
-                },
-        },
-        {
-                .callback = dmi_low_memory_corruption,
-                .ident = "Phoenix/MSC BIOS",
-                .matches = {
-                        DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix/MSC"),
-                },
-        },
-        /*
-         * AMI BIOS with low memory corruption was found on Intel DG45ID and
-         * DG45FC boards.
-         * It has a different DMI_BIOS_VENDOR = "Intel Corp.", for now we will
-         * match only DMI_BOARD_NAME and see if there is more bad products
-         * with this vendor.
-         */
-        {
-                .callback = dmi_low_memory_corruption,
-                .ident = "AMI BIOS",
-                .matches = {
-                        DMI_MATCH(DMI_BOARD_NAME, "DG45ID"),
-                },
-        },
-        {
-                .callback = dmi_low_memory_corruption,
-                .ident = "AMI BIOS",
-                .matches = {
-                        DMI_MATCH(DMI_BOARD_NAME, "DG45FC"),
-                },
-        },
-        /*
-         * The Dell Inspiron Mini 1012 has DMI_BIOS_VENDOR = "Dell Inc.", so
-         * match on the product name.
-         */
-        {
-                .callback = dmi_low_memory_corruption,
-                .ident = "Phoenix BIOS",
-                .matches = {
-                        DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 1012"),
-                },
-        },
-#endif
-        {}
-};
+static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10;
 
 static void __init trim_bios_range(void)
 {
@@ -699,8 +625,14 @@ static void __init trim_bios_range(void)
          * A special case is the first 4Kb of memory;
          * This is a BIOS owned area, not kernel ram, but generally
          * not listed as such in the E820 table.
+         *
+         * This typically reserves additional memory (64KiB by default)
+         * since some BIOSes are known to corrupt low memory.  See the
+         * Kconfig help text for X86_RESERVE_LOW.
          */
-        e820_update_range(0, PAGE_SIZE, E820_RAM, E820_RESERVED);
+        e820_update_range(0, ALIGN(reserve_low, PAGE_SIZE),
+                          E820_RAM, E820_RESERVED);
+
         /*
          * special case: Some BIOSen report the PC BIOS
          * area (640->1Mb) as ram even though it is not.
@@ -710,6 +642,28 @@ static void __init trim_bios_range(void)
         sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
 }
 
+static int __init parse_reservelow(char *p)
+{
+        unsigned long long size;
+
+        if (!p)
+                return -EINVAL;
+
+        size = memparse(p, &p);
+
+        if (size < 4096)
+                size = 4096;
+
+        if (size > 640*1024)
+                size = 640*1024;
+
+        reserve_low = size;
+
+        return 0;
+}
+
+early_param("reservelow", parse_reservelow);
+
 /*
  * Determine if we were loaded by an EFI loader.  If so, then we have also been
  * passed the efi memmap, systab, etc., so we should use these data structures
@@ -736,10 +690,10 @@ void __init setup_arch(char **cmdline_p)
         printk(KERN_INFO "Command line: %s\n", boot_command_line);
 #endif
 
-        /* VMI may relocate the fixmap; do this before touching ioremap area */
-        vmi_init();
-
-        /* OFW also may relocate the fixmap */
+        /*
+         * If we have OLPC OFW, we might end up relocating the fixmap due to
+         * reserve_top(), so do this before touching the ioremap area.
+         */
         olpc_ofw_detect();
 
         early_trap_init();
@@ -840,9 +794,6 @@ void __init setup_arch(char **cmdline_p)
 
         x86_report_nx();
 
-        /* Must be before kernel pagetables are setup */
-        vmi_activate();
-
         /* after early param, so could get panic from serial */
         reserve_early_setup_data();
 
@@ -865,8 +816,6 @@ void __init setup_arch(char **cmdline_p)
 
         dmi_scan_machine();
 
-        dmi_check_system(bad_bios_dmi_table);
-
         /*
          * VMware detection requires dmi to be available, so this
          * needs to be done after dmi_scan_machine, for the BP.
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index a60df9ae6454..2335c15c93a4 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -253,7 +253,7 @@ void __init setup_per_cpu_areas(void)
                  * Up to this point, the boot CPU has been using .init.data
                  * area.  Reload any changed state for the boot CPU.
                  */
-                if (cpu == boot_cpu_id)
+                if (!cpu)
                         switch_to_new_gdt(cpu);
         }
 
diff --git a/arch/x86/kernel/sfi.c b/arch/x86/kernel/sfi.c
index cb22acf3ed09..dd4c281ffe57 100644
--- a/arch/x86/kernel/sfi.c
+++ b/arch/x86/kernel/sfi.c
@@ -34,7 +34,7 @@
 #ifdef CONFIG_X86_LOCAL_APIC
 static unsigned long sfi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE;
 
-void __init mp_sfi_register_lapic_address(unsigned long address)
+static void __init mp_sfi_register_lapic_address(unsigned long address)
 {
         mp_lapic_addr = address;
 
@@ -46,7 +46,7 @@ void __init mp_sfi_register_lapic_address(unsigned long address)
 }
 
 /* All CPUs enumerated by SFI must be present and enabled */
-void __cpuinit mp_sfi_register_lapic(u8 id)
+static void __cpuinit mp_sfi_register_lapic(u8 id)
 {
         if (MAX_APICS - id <= 0) {
                 pr_warning("Processor #%d invalid (max %d)\n",
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 8b3bfc4dd708..dfb50890b5b7 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -62,7 +62,7 @@
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/mtrr.h>
-#include <asm/vmi.h>
+#include <asm/mwait.h>
 #include <asm/apic.h>
 #include <asm/setup.h>
 #include <asm/uv/uv.h>
@@ -311,7 +311,6 @@ notrace static void __cpuinit start_secondary(void *unused)
         __flush_tlb_all();
 #endif
 
-        vmi_bringup();
         cpu_init();
         preempt_disable();
         smp_callin();
@@ -324,9 +323,9 @@ notrace static void __cpuinit start_secondary(void *unused)
         check_tsc_sync_target();
 
         if (nmi_watchdog == NMI_IO_APIC) {
-                legacy_pic->chip->mask(0);
+                legacy_pic->mask(0);
                 enable_NMI_through_LVT0();
-                legacy_pic->chip->unmask(0);
+                legacy_pic->unmask(0);
         }
 
         /* This must be done before setting cpu_online_mask */
@@ -397,6 +396,19 @@ void __cpuinit smp_store_cpu_info(int id)
                 identify_secondary_cpu(c);
 }
 
+static void __cpuinit link_thread_siblings(int cpu1, int cpu2)
+{
+        struct cpuinfo_x86 *c1 = &cpu_data(cpu1);
+        struct cpuinfo_x86 *c2 = &cpu_data(cpu2);
+
+        cpumask_set_cpu(cpu1, cpu_sibling_mask(cpu2));
+        cpumask_set_cpu(cpu2, cpu_sibling_mask(cpu1));
+        cpumask_set_cpu(cpu1, cpu_core_mask(cpu2));
+        cpumask_set_cpu(cpu2, cpu_core_mask(cpu1));
+        cpumask_set_cpu(cpu1, c2->llc_shared_map);
+        cpumask_set_cpu(cpu2, c1->llc_shared_map);
+}
+
 
 void __cpuinit set_cpu_sibling_map(int cpu)
 {
@@ -409,14 +421,13 @@ void __cpuinit set_cpu_sibling_map(int cpu)
                 for_each_cpu(i, cpu_sibling_setup_mask) {
                         struct cpuinfo_x86 *o = &cpu_data(i);
 
-                        if (c->phys_proc_id == o->phys_proc_id &&
-                            c->cpu_core_id == o->cpu_core_id) {
-                                cpumask_set_cpu(i, cpu_sibling_mask(cpu));
-                                cpumask_set_cpu(cpu, cpu_sibling_mask(i));
-                                cpumask_set_cpu(i, cpu_core_mask(cpu));
-                                cpumask_set_cpu(cpu, cpu_core_mask(i));
-                                cpumask_set_cpu(i, c->llc_shared_map);
-                                cpumask_set_cpu(cpu, o->llc_shared_map);
+                        if (cpu_has(c, X86_FEATURE_TOPOEXT)) {
+                                if (c->phys_proc_id == o->phys_proc_id &&
+                                    c->compute_unit_id == o->compute_unit_id)
+                                        link_thread_siblings(cpu, i);
+                        } else if (c->phys_proc_id == o->phys_proc_id &&
+                                   c->cpu_core_id == o->cpu_core_id) {
+                                link_thread_siblings(cpu, i);
                         }
                 }
         } else {
@@ -1109,8 +1120,6 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
         }
         set_cpu_sibling_map(0);
 
-        enable_IR_x2apic();
-        default_setup_apic_routing();
 
         if (smp_sanity_check(max_cpus) < 0) {
                 printk(KERN_INFO "SMP disabled\n");
@@ -1118,6 +1127,8 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
                 goto out;
         }
 
+        default_setup_apic_routing();
+
         preempt_disable();
         if (read_apic_id() != boot_cpu_physical_apicid) {
                 panic("Boot APIC ID in local APIC unexpected (%d vs %d)",
@@ -1383,11 +1394,88 @@ void play_dead_common(void)
         local_irq_disable();
 }
 
+/*
+ * We need to flush the caches before going to sleep, lest we have
+ * dirty data in our caches when we come back up.
+ */
+static inline void mwait_play_dead(void)
+{
+        unsigned int eax, ebx, ecx, edx;
+        unsigned int highest_cstate = 0;
+        unsigned int highest_subcstate = 0;
+        int i;
+        void *mwait_ptr;
+
+        if (!cpu_has(&current_cpu_data, X86_FEATURE_MWAIT))
+                return;
+        if (!cpu_has(&current_cpu_data, X86_FEATURE_CLFLSH))
+                return;
+        if (current_cpu_data.cpuid_level < CPUID_MWAIT_LEAF)
+                return;
+
+        eax = CPUID_MWAIT_LEAF;
+        ecx = 0;
+        native_cpuid(&eax, &ebx, &ecx, &edx);
+
+        /*
+         * eax will be 0 if EDX enumeration is not valid.
+         * Initialized below to cstate, sub_cstate value when EDX is valid.
+         */
+        if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED)) {
+                eax = 0;
+        } else {
+                edx >>= MWAIT_SUBSTATE_SIZE;
+                for (i = 0; i < 7 && edx; i++, edx >>= MWAIT_SUBSTATE_SIZE) {
+                        if (edx & MWAIT_SUBSTATE_MASK) {
+                                highest_cstate = i;
+                                highest_subcstate = edx & MWAIT_SUBSTATE_MASK;
+                        }
+                }
+                eax = (highest_cstate << MWAIT_SUBSTATE_SIZE) |
+                        (highest_subcstate - 1);
+        }
+
+        /*
+         * This should be a memory location in a cache line which is
+         * unlikely to be touched by other processors.  The actual
+         * content is immaterial as it is not actually modified in any way.
+         */
+        mwait_ptr = &current_thread_info()->flags;
+
+        wbinvd();
+
+        while (1) {
+                /*
+                 * The CLFLUSH is a workaround for erratum AAI65 for
+                 * the Xeon 7400 series.  It's not clear it is actually
+                 * needed, but it should be harmless in either case.
+                 * The WBINVD is insufficient due to the spurious-wakeup
+                 * case where we return around the loop.
+                 */
+                clflush(mwait_ptr);
+                __monitor(mwait_ptr, 0, 0);
+                mb();
+                __mwait(eax, 0);
+        }
+}
+
+static inline void hlt_play_dead(void)
+{
+        if (current_cpu_data.x86 >= 4)
+                wbinvd();
+
+        while (1) {
+                native_halt();
+        }
+}
+
 void native_play_dead(void)
 {
         play_dead_common();
         tboot_shutdown(TB_SHUTDOWN_WFS);
-        wbinvd_halt();
+
+        mwait_play_dead();      /* Only returns on failure */
+        hlt_play_dead();
 }
 
 #else /* ... !CONFIG_HOTPLUG_CPU */
diff --git a/arch/x86/kernel/sys_i386_32.c b/arch/x86/kernel/sys_i386_32.c
index d5e06624e34a..0b0cb5fede19 100644
--- a/arch/x86/kernel/sys_i386_32.c
+++ b/arch/x86/kernel/sys_i386_32.c
@@ -33,8 +33,8 @@ int kernel_execve(const char *filename,
                   const char *const envp[])
 {
         long __res;
-        asm volatile ("push %%ebx ; movl %2,%%ebx ; int $0x80 ; pop %%ebx"
+        asm volatile ("int $0x80"
         : "=a" (__res)
-        : "0" (__NR_execve), "ri" (filename), "c" (argv), "d" (envp) : "memory");
+        : "0" (__NR_execve), "b" (filename), "c" (argv), "d" (envp) : "memory");
         return __res;
 }
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 60788dee0f8a..d43968503dd2 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -776,21 +776,10 @@ asmlinkage void math_state_restore(void)
 }
 EXPORT_SYMBOL_GPL(math_state_restore);
 
-#ifndef CONFIG_MATH_EMULATION
-void math_emulate(struct math_emu_info *info)
-{
-        printk(KERN_EMERG
-                "math-emulation not enabled and no coprocessor found.\n");
-        printk(KERN_EMERG "killing %s.\n", current->comm);
-        force_sig(SIGFPE, current);
-        schedule();
-}
-#endif /* CONFIG_MATH_EMULATION */
-
 dotraplinkage void __kprobes
 do_device_not_available(struct pt_regs *regs, long error_code)
 {
-#ifdef CONFIG_X86_32
+#ifdef CONFIG_MATH_EMULATION
         if (read_cr0() & X86_CR0_EM) {
                 struct math_emu_info info = { };
 
@@ -798,12 +787,12 @@ do_device_not_available(struct pt_regs *regs, long error_code)
 
                 info.regs = regs;
                 math_emulate(&info);
-        } else {
-                math_state_restore(); /* interrupts still off */
-                conditional_sti(regs);
+                return;
         }
-#else
-        math_state_restore();
+#endif
+        math_state_restore(); /* interrupts still off */
+#ifdef CONFIG_X86_32
+        conditional_sti(regs);
 #endif
 }
 
@@ -881,18 +870,6 @@ void __init trap_init(void)
 #endif
 
 #ifdef CONFIG_X86_32
-        if (cpu_has_fxsr) {
-                printk(KERN_INFO "Enabling fast FPU save and restore... ");
-                set_in_cr4(X86_CR4_OSFXSR);
-                printk("done.\n");
-        }
-        if (cpu_has_xmm) {
-                printk(KERN_INFO
-                        "Enabling unmasked SIMD FPU exception support... ");
-                set_in_cr4(X86_CR4_OSXMMEXCPT);
-                printk("done.\n");
-        }
-
         set_system_trap_gate(SYSCALL_VECTOR, &system_call);
         set_bit(SYSCALL_VECTOR, used_vectors);
 #endif
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 26a863a9c2a8..0c40d8b72416 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -104,10 +104,14 @@ int __init notsc_setup(char *str)
 
 __setup("notsc", notsc_setup);
 
+static int no_sched_irq_time;
+
 static int __init tsc_setup(char *str)
 {
         if (!strcmp(str, "reliable"))
                 tsc_clocksource_reliable = 1;
+        if (!strncmp(str, "noirqtime", 9))
+                no_sched_irq_time = 1;
         return 1;
 }
 
@@ -801,6 +805,7 @@ void mark_tsc_unstable(char *reason)
         if (!tsc_unstable) {
                 tsc_unstable = 1;
                 sched_clock_stable = 0;
+                disable_sched_clock_irqtime();
                 printk(KERN_INFO "Marking TSC unstable due to %s\n", reason);
                 /* Change only the rating, when not registered */
                 if (clocksource_tsc.mult)
@@ -892,60 +897,6 @@ static void __init init_tsc_clocksource(void)
         clocksource_register_khz(&clocksource_tsc, tsc_khz);
 }
 
-#ifdef CONFIG_X86_64
-/*
- * calibrate_cpu is used on systems with fixed rate TSCs to determine
- * processor frequency
- */
-#define TICK_COUNT 100000000
-static unsigned long __init calibrate_cpu(void)
-{
-        int tsc_start, tsc_now;
-        int i, no_ctr_free;
-        unsigned long evntsel3 = 0, pmc3 = 0, pmc_now = 0;
-        unsigned long flags;
-
-        for (i = 0; i < 4; i++)
-                if (avail_to_resrv_perfctr_nmi_bit(i))
-                        break;
-        no_ctr_free = (i == 4);
-        if (no_ctr_free) {
-                WARN(1, KERN_WARNING "Warning: AMD perfctrs busy ... "
-                     "cpu_khz value may be incorrect.\n");
-                i = 3;
-                rdmsrl(MSR_K7_EVNTSEL3, evntsel3);
-                wrmsrl(MSR_K7_EVNTSEL3, 0);
-                rdmsrl(MSR_K7_PERFCTR3, pmc3);
-        } else {
-                reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i);
-                reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
-        }
-        local_irq_save(flags);
-        /* start measuring cycles, incrementing from 0 */
-        wrmsrl(MSR_K7_PERFCTR0 + i, 0);
-        wrmsrl(MSR_K7_EVNTSEL0 + i, 1 << 22 | 3 << 16 | 0x76);
-        rdtscl(tsc_start);
-        do {
-                rdmsrl(MSR_K7_PERFCTR0 + i, pmc_now);
-                tsc_now = get_cycles();
-        } while ((tsc_now - tsc_start) < TICK_COUNT);
-
-        local_irq_restore(flags);
-        if (no_ctr_free) {
-                wrmsrl(MSR_K7_EVNTSEL3, 0);
-                wrmsrl(MSR_K7_PERFCTR3, pmc3);
-                wrmsrl(MSR_K7_EVNTSEL3, evntsel3);
-        } else {
-                release_perfctr_nmi(MSR_K7_PERFCTR0 + i);
-                release_evntsel_nmi(MSR_K7_EVNTSEL0 + i);
-        }
-
-        return pmc_now * tsc_khz / (tsc_now - tsc_start);
-}
-#else
-static inline unsigned long calibrate_cpu(void) { return cpu_khz; }
-#endif
-
 void __init tsc_init(void)
 {
         u64 lpj;
@@ -964,10 +915,6 @@ void __init tsc_init(void)
                 return;
         }
 
-        if (cpu_has(&boot_cpu_data, X86_FEATURE_CONSTANT_TSC) &&
-                        (boot_cpu_data.x86_vendor == X86_VENDOR_AMD))
-                cpu_khz = calibrate_cpu();
-
         printk("Detected %lu.%03lu MHz processor.\n",
                         (unsigned long)cpu_khz / 1000,
                         (unsigned long)cpu_khz % 1000);
@@ -987,6 +934,9 @@ void __init tsc_init(void)
         /* now allow native_sched_clock() to use rdtsc */
         tsc_disabled = 0;
 
+        if (!no_sched_irq_time)
+                enable_sched_clock_irqtime();
+
         lpj = ((u64)tsc_khz * 1000);
         do_div(lpj, HZ);
         lpj_fine = lpj;
diff --git a/arch/x86/kernel/uv_irq.c b/arch/x86/kernel/uv_irq.c
index 1132129db792..7b24460917d5 100644
--- a/arch/x86/kernel/uv_irq.c
+++ b/arch/x86/kernel/uv_irq.c
@@ -28,34 +28,21 @@ struct uv_irq_2_mmr_pnode{
 static spinlock_t               uv_irq_lock;
 static struct rb_root           uv_irq_root;
 
-static int uv_set_irq_affinity(unsigned int, const struct cpumask *);
+static int uv_set_irq_affinity(struct irq_data *, const struct cpumask *, bool);
 
-static void uv_noop(unsigned int irq)
-{
-}
-
-static unsigned int uv_noop_ret(unsigned int irq)
-{
-        return 0;
-}
+static void uv_noop(struct irq_data *data) { }
 
-static void uv_ack_apic(unsigned int irq)
+static void uv_ack_apic(struct irq_data *data)
 {
         ack_APIC_irq();
 }
 
 static struct irq_chip uv_irq_chip = {
-        .name           = "UV-CORE",
-        .startup        = uv_noop_ret,
-        .shutdown       = uv_noop,
-        .enable         = uv_noop,
-        .disable        = uv_noop,
-        .ack            = uv_noop,
-        .mask           = uv_noop,
-        .unmask         = uv_noop,
-        .eoi            = uv_ack_apic,
-        .end            = uv_noop,
-        .set_affinity   = uv_set_irq_affinity,
+        .name                   = "UV-CORE",
+        .irq_mask               = uv_noop,
+        .irq_unmask             = uv_noop,
+        .irq_eoi                = uv_ack_apic,
+        .irq_set_affinity       = uv_set_irq_affinity,
 };
 
 /*
@@ -144,26 +131,22 @@ arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade,
                        unsigned long mmr_offset, int limit)
 {
         const struct cpumask *eligible_cpu = cpumask_of(cpu);
-        struct irq_desc *desc = irq_to_desc(irq);
-        struct irq_cfg *cfg;
-        int mmr_pnode;
+        struct irq_cfg *cfg = get_irq_chip_data(irq);
         unsigned long mmr_value;
         struct uv_IO_APIC_route_entry *entry;
-        int err;
+        int mmr_pnode, err;
 
         BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) !=
                         sizeof(unsigned long));
 
-        cfg = irq_cfg(irq);
-
         err = assign_irq_vector(irq, cfg, eligible_cpu);
         if (err != 0)
                 return err;
 
         if (limit == UV_AFFINITY_CPU)
-                desc->status |= IRQ_NO_BALANCING;
+                irq_set_status_flags(irq, IRQ_NO_BALANCING);
         else
-                desc->status |= IRQ_MOVE_PCNTXT;
+                irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
 
         set_irq_chip_and_handler_name(irq, &uv_irq_chip, handle_percpu_irq,
                                       irq_name);
@@ -206,17 +189,17 @@ static void arch_disable_uv_irq(int mmr_pnode, unsigned long mmr_offset)
         uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
 }
 
-static int uv_set_irq_affinity(unsigned int irq, const struct cpumask *mask)
+static int
+uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask,
+                    bool force)
 {
-        struct irq_desc *desc = irq_to_desc(irq);
-        struct irq_cfg *cfg = desc->chip_data;
+        struct irq_cfg *cfg = data->chip_data;
         unsigned int dest;
-        unsigned long mmr_value;
+        unsigned long mmr_value, mmr_offset;
         struct uv_IO_APIC_route_entry *entry;
-        unsigned long mmr_offset;
         int mmr_pnode;
 
-        if (set_desc_affinity(desc, mask, &dest))
+        if (__ioapic_set_affinity(data, mask, &dest))
                 return -1;
 
         mmr_value = 0;
@@ -231,7 +214,7 @@ static int uv_set_irq_affinity(unsigned int irq, const struct cpumask *mask)
         entry->dest             = dest;
 
         /* Get previously stored MMR and pnode of hub sourcing interrupts */
-        if (uv_irq_2_mmr_info(irq, &mmr_offset, &mmr_pnode))
+        if (uv_irq_2_mmr_info(data->irq, &mmr_offset, &mmr_pnode))
                 return -1;
 
         uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c
index e680ea52db9b..3371bd053b89 100644
--- a/arch/x86/kernel/visws_quirks.c
+++ b/arch/x86/kernel/visws_quirks.c
@@ -66,10 +66,7 @@ static void __init visws_time_init(void)
 }
 
 /* Replaces the default init_ISA_irqs in the generic setup */
-static void __init visws_pre_intr_init(void)
-{
-        init_VISWS_APIC_irqs();
-}
+static void __init visws_pre_intr_init(void);
 
 /* Quirk for machine specific memory setup. */
 
@@ -429,67 +426,34 @@ static int is_co_apic(unsigned int irq)
 /*
  * This is the SGI Cobalt (IO-)APIC:
  */
-
-static void enable_cobalt_irq(unsigned int irq)
+static void enable_cobalt_irq(struct irq_data *data)
 {
-        co_apic_set(is_co_apic(irq), irq);
+        co_apic_set(is_co_apic(data->irq), data->irq);
 }
 
-static void disable_cobalt_irq(unsigned int irq)
+static void disable_cobalt_irq(struct irq_data *data)
 {
-        int entry = is_co_apic(irq);
+        int entry = is_co_apic(data->irq);
 
         co_apic_write(CO_APIC_LO(entry), CO_APIC_MASK);
         co_apic_read(CO_APIC_LO(entry));
 }
 
-/*
- * "irq" really just serves to identify the device.  Here is where we
- * map this to the Cobalt APIC entry where it's physically wired.
- * This is called via request_irq -> setup_irq -> irq_desc->startup()
- */
-static unsigned int startup_cobalt_irq(unsigned int irq)
+static void ack_cobalt_irq(struct irq_data *data)
 {
         unsigned long flags;
-        struct irq_desc *desc = irq_to_desc(irq);
 
         spin_lock_irqsave(&cobalt_lock, flags);
-        if ((desc->status & (IRQ_DISABLED | IRQ_INPROGRESS | IRQ_WAITING)))
-                desc->status &= ~(IRQ_DISABLED | IRQ_INPROGRESS | IRQ_WAITING);
-        enable_cobalt_irq(irq);
-        spin_unlock_irqrestore(&cobalt_lock, flags);
-        return 0;
-}
-
-static void ack_cobalt_irq(unsigned int irq)
-{
-        unsigned long flags;
-
-        spin_lock_irqsave(&cobalt_lock, flags);
-        disable_cobalt_irq(irq);
+        disable_cobalt_irq(data);
         apic_write(APIC_EOI, APIC_EIO_ACK);
         spin_unlock_irqrestore(&cobalt_lock, flags);
 }
 
-static void end_cobalt_irq(unsigned int irq)
-{
-        unsigned long flags;
-        struct irq_desc *desc = irq_to_desc(irq);
-
-        spin_lock_irqsave(&cobalt_lock, flags);
-        if (!(desc->status & (IRQ_DISABLED | IRQ_INPROGRESS)))
-                enable_cobalt_irq(irq);
-        spin_unlock_irqrestore(&cobalt_lock, flags);
-}
-
 static struct irq_chip cobalt_irq_type = {
-        .name =         "Cobalt-APIC",
-        .startup =      startup_cobalt_irq,
-        .shutdown =     disable_cobalt_irq,
-        .enable =       enable_cobalt_irq,
-        .disable =      disable_cobalt_irq,
-        .ack =          ack_cobalt_irq,
-        .end =          end_cobalt_irq,
+        .name           = "Cobalt-APIC",
+        .irq_enable     = enable_cobalt_irq,
+        .irq_disable    = disable_cobalt_irq,
+        .irq_ack        = ack_cobalt_irq,
 };
 
 
@@ -503,35 +467,34 @@ static struct irq_chip cobalt_irq_type = {
  * interrupt controller type, and through a special virtual interrupt-
  * controller. Device drivers only see the virtual interrupt sources.
  */
-static unsigned int startup_piix4_master_irq(unsigned int irq)
+static unsigned int startup_piix4_master_irq(struct irq_data *data)
 {
         legacy_pic->init(0);
-
-        return startup_cobalt_irq(irq);
+        enable_cobalt_irq(data);
 }
 
-static void end_piix4_master_irq(unsigned int irq)
+static void end_piix4_master_irq(struct irq_data *data)
 {
         unsigned long flags;
 
         spin_lock_irqsave(&cobalt_lock, flags);
-        enable_cobalt_irq(irq);
+        enable_cobalt_irq(data);
         spin_unlock_irqrestore(&cobalt_lock, flags);
 }
 
 static struct irq_chip piix4_master_irq_type = {
-        .name =         "PIIX4-master",
-        .startup =      startup_piix4_master_irq,
-        .ack =          ack_cobalt_irq,
-        .end =          end_piix4_master_irq,
+        .name           = "PIIX4-master",
+        .irq_startup    = startup_piix4_master_irq,
+        .irq_ack        = ack_cobalt_irq,
 };
 
+static void pii4_mask(struct irq_data *data) { }
 
 static struct irq_chip piix4_virtual_irq_type = {
-        .name =         "PIIX4-virtual",
+        .name           = "PIIX4-virtual",
+        .mask           = pii4_mask,
 };
 
-
 /*
  * PIIX4-8259 master/virtual functions to handle interrupt requests
  * from legacy devices: floppy, parallel, serial, rtc.
@@ -549,9 +512,8 @@ static struct irq_chip piix4_virtual_irq_type = {
  */
 static irqreturn_t piix4_master_intr(int irq, void *dev_id)
 {
-        int realirq;
-        struct irq_desc *desc;
         unsigned long flags;
+        int realirq;
 
         raw_spin_lock_irqsave(&i8259A_lock, flags);
 
@@ -592,18 +554,10 @@ static irqreturn_t piix4_master_intr(int irq, void *dev_id)
 
         raw_spin_unlock_irqrestore(&i8259A_lock, flags);
 
-        desc = irq_to_desc(realirq);
-
         /*
          * handle this 'virtual interrupt' as a Cobalt one now.
          */
-        kstat_incr_irqs_this_cpu(realirq, desc);
-
-        if (likely(desc->action != NULL))
-                handle_IRQ_event(realirq, desc->action);
-
-        if (!(desc->status & IRQ_DISABLED))
-                legacy_pic->chip->unmask(realirq);
+        generic_handle_irq(realirq);
 
         return IRQ_HANDLED;
 
@@ -624,41 +578,35 @@ static struct irqaction cascade_action = {
 
 static inline void set_piix4_virtual_irq_type(void)
 {
-        piix4_virtual_irq_type.shutdown = i8259A_chip.mask;
         piix4_virtual_irq_type.enable = i8259A_chip.unmask;
         piix4_virtual_irq_type.disable = i8259A_chip.mask;
+        piix4_virtual_irq_type.unmask = i8259A_chip.unmask;
 }
 
-void init_VISWS_APIC_irqs(void)
+static void __init visws_pre_intr_init(void)
 {
         int i;
 
-        for (i = 0; i < CO_IRQ_APIC0 + CO_APIC_LAST + 1; i++) {
-                struct irq_desc *desc = irq_to_desc(i);
-
-                desc->status = IRQ_DISABLED;
-                desc->action = 0;
-                desc->depth = 1;
+        set_piix4_virtual_irq_type();
 
-                if (i == 0) {
-                        desc->chip = &cobalt_irq_type;
-                }
-                else if (i == CO_IRQ_IDE0) {
-                        desc->chip = &cobalt_irq_type;
-                }
-                else if (i == CO_IRQ_IDE1) {
-                        desc->chip = &cobalt_irq_type;
-                }
-                else if (i == CO_IRQ_8259) {
-                        desc->chip = &piix4_master_irq_type;
-                }
-                else if (i < CO_IRQ_APIC0) {
-                        set_piix4_virtual_irq_type();
-                        desc->chip = &piix4_virtual_irq_type;
-                }
-                else if (IS_CO_APIC(i)) {
-                        desc->chip = &cobalt_irq_type;
-                }
+        for (i = 0; i < CO_IRQ_APIC0 + CO_APIC_LAST + 1; i++) {
+                struct irq_chip *chip = NULL;
+
+                if (i == 0)
+                        chip = &cobalt_irq_type;
+                else if (i == CO_IRQ_IDE0)
+                        chip = &cobalt_irq_type;
+                else if (i == CO_IRQ_IDE1)
+                        >chip = &cobalt_irq_type;
+                else if (i == CO_IRQ_8259)
+                        chip = &piix4_master_irq_type;
+                else if (i < CO_IRQ_APIC0)
+                        chip = &piix4_virtual_irq_type;
+                else if (IS_CO_APIC(i))
+                        chip = &cobalt_irq_type;
+
+                if (chip)
+                        set_irq_chip(i, chip);
         }
 
         setup_irq(CO_IRQ_8259, &master_action);
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
deleted file mode 100644
index ce9fbacb7526..000000000000
--- a/arch/x86/kernel/vmi_32.c
+++ /dev/null
@@ -1,893 +0,0 @@
-/*
- * VMI specific paravirt-ops implementation
- *
- * Copyright (C) 2005, VMware, Inc.
- *
- * 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, GOOD TITLE or
- * NON INFRINGEMENT.  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., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * Send feedback to zach@vmware.com
- *
- */
-
-#include <linux/module.h>
-#include <linux/cpu.h>
-#include <linux/bootmem.h>
-#include <linux/mm.h>
-#include <linux/highmem.h>
-#include <linux/sched.h>
-#include <linux/gfp.h>
-#include <asm/vmi.h>
-#include <asm/io.h>
-#include <asm/fixmap.h>
-#include <asm/apicdef.h>
-#include <asm/apic.h>
-#include <asm/pgalloc.h>
-#include <asm/processor.h>
-#include <asm/timer.h>
-#include <asm/vmi_time.h>
-#include <asm/kmap_types.h>
-#include <asm/setup.h>
-
-/* Convenient for calling VMI functions indirectly in the ROM */
-typedef u32 __attribute__((regparm(1))) (VROMFUNC)(void);
-typedef u64 __attribute__((regparm(2))) (VROMLONGFUNC)(int);
-
-#define call_vrom_func(rom,func) \
-   (((VROMFUNC *)(rom->func))())
-
-#define call_vrom_long_func(rom,func,arg) \
-   (((VROMLONGFUNC *)(rom->func)) (arg))
-
-static struct vrom_header *vmi_rom;
-static int disable_pge;
-static int disable_pse;
-static int disable_sep;
-static int disable_tsc;
-static int disable_mtrr;
-static int disable_noidle;
-static int disable_vmi_timer;
-
-/* Cached VMI operations */
-static struct {
-        void (*cpuid)(void /* non-c */);
-        void (*_set_ldt)(u32 selector);
-        void (*set_tr)(u32 selector);
-        void (*write_idt_entry)(struct desc_struct *, int, u32, u32);
-        void (*write_gdt_entry)(struct desc_struct *, int, u32, u32);
-        void (*write_ldt_entry)(struct desc_struct *, int, u32, u32);
-        void (*set_kernel_stack)(u32 selector, u32 sp0);
-        void (*allocate_page)(u32, u32, u32, u32, u32);
-        void (*release_page)(u32, u32);
-        void (*set_pte)(pte_t, pte_t *, unsigned);
-        void (*update_pte)(pte_t *, unsigned);
-        void (*set_linear_mapping)(int, void *, u32, u32);
-        void (*_flush_tlb)(int);
-        void (*set_initial_ap_state)(int, int);
-        void (*halt)(void);
-        void (*set_lazy_mode)(int mode);
-} vmi_ops;
-
-/* Cached VMI operations */
-struct vmi_timer_ops vmi_timer_ops;
-
-/*
- * VMI patching routines.
- */
-#define MNEM_CALL 0xe8
-#define MNEM_JMP  0xe9
-#define MNEM_RET  0xc3
-
-#define IRQ_PATCH_INT_MASK 0
-#define IRQ_PATCH_DISABLE  5
-
-static inline void patch_offset(void *insnbuf,
-                                unsigned long ip, unsigned long dest)
-{
-        *(unsigned long *)(insnbuf+1) = dest-ip-5;
-}
-
-static unsigned patch_internal(int call, unsigned len, void *insnbuf,
-                               unsigned long ip)
-{
-        u64 reloc;
-        struct vmi_relocation_info *const rel = (struct vmi_relocation_info *)&reloc;
-        reloc = call_vrom_long_func(vmi_rom, get_reloc, call);
-        switch(rel->type) {
-                case VMI_RELOCATION_CALL_REL:
-                        BUG_ON(len < 5);
-                        *(char *)insnbuf = MNEM_CALL;
-                        patch_offset(insnbuf, ip, (unsigned long)rel->eip);
-                        return 5;
-
-                case VMI_RELOCATION_JUMP_REL:
-                        BUG_ON(len < 5);
-                        *(char *)insnbuf = MNEM_JMP;
-                        patch_offset(insnbuf, ip, (unsigned long)rel->eip);
-                        return 5;
-
-                case VMI_RELOCATION_NOP:
-                        /* obliterate the whole thing */
-                        return 0;
-
-                case VMI_RELOCATION_NONE:
-                        /* leave native code in place */
-                        break;
-
-                default:
-                        BUG();
-        }
-        return len;
-}
-
-/*
- * Apply patch if appropriate, return length of new instruction
- * sequence.  The callee does nop padding for us.
- */
-static unsigned vmi_patch(u8 type, u16 clobbers, void *insns,
-                          unsigned long ip, unsigned len)
-{
-        switch (type) {
-                case PARAVIRT_PATCH(pv_irq_ops.irq_disable):
-                        return patch_internal(VMI_CALL_DisableInterrupts, len,
-                                              insns, ip);
-                case PARAVIRT_PATCH(pv_irq_ops.irq_enable):
-                        return patch_internal(VMI_CALL_EnableInterrupts, len,
-                                              insns, ip);
-                case PARAVIRT_PATCH(pv_irq_ops.restore_fl):
-                        return patch_internal(VMI_CALL_SetInterruptMask, len,
-                                              insns, ip);
-                case PARAVIRT_PATCH(pv_irq_ops.save_fl):
-                        return patch_internal(VMI_CALL_GetInterruptMask, len,
-                                              insns, ip);
-                case PARAVIRT_PATCH(pv_cpu_ops.iret):
-                        return patch_internal(VMI_CALL_IRET, len, insns, ip);
-                case PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit):
-                        return patch_internal(VMI_CALL_SYSEXIT, len, insns, ip);
-                default:
-                        break;
-        }
-        return len;
-}
-
-/* CPUID has non-C semantics, and paravirt-ops API doesn't match hardware ISA */
-static void vmi_cpuid(unsigned int *ax, unsigned int *bx,
-                               unsigned int *cx, unsigned int *dx)
-{
-        int override = 0;
-        if (*ax == 1)
-                override = 1;
-        asm volatile ("call *%6"
-                      : "=a" (*ax),
-                        "=b" (*bx),
-                        "=c" (*cx),
-                        "=d" (*dx)
-                      : "0" (*ax), "2" (*cx), "r" (vmi_ops.cpuid));
-        if (override) {
-                if (disable_pse)
-                        *dx &= ~X86_FEATURE_PSE;
-                if (disable_pge)
-                        *dx &= ~X86_FEATURE_PGE;
-                if (disable_sep)
-                        *dx &= ~X86_FEATURE_SEP;
-                if (disable_tsc)
-                        *dx &= ~X86_FEATURE_TSC;
-                if (disable_mtrr)
-                        *dx &= ~X86_FEATURE_MTRR;
-        }
-}
-
-static inline void vmi_maybe_load_tls(struct desc_struct *gdt, int nr, struct desc_struct *new)
-{
-        if (gdt[nr].a != new->a || gdt[nr].b != new->b)
-                write_gdt_entry(gdt, nr, new, 0);
-}
-
-static void vmi_load_tls(struct thread_struct *t, unsigned int cpu)
-{
-        struct desc_struct *gdt = get_cpu_gdt_table(cpu);
-        vmi_maybe_load_tls(gdt, GDT_ENTRY_TLS_MIN + 0, &t->tls_array[0]);
-        vmi_maybe_load_tls(gdt, GDT_ENTRY_TLS_MIN + 1, &t->tls_array[1]);
-        vmi_maybe_load_tls(gdt, GDT_ENTRY_TLS_MIN + 2, &t->tls_array[2]);
-}
-
-static void vmi_set_ldt(const void *addr, unsigned entries)
-{
-        unsigned cpu = smp_processor_id();
-        struct desc_struct desc;
-
-        pack_descriptor(&desc, (unsigned long)addr,
-                        entries * sizeof(struct desc_struct) - 1,
-                        DESC_LDT, 0);
-        write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_LDT, &desc, DESC_LDT);
-        vmi_ops._set_ldt(entries ? GDT_ENTRY_LDT*sizeof(struct desc_struct) : 0);
-}
-
-static void vmi_set_tr(void)
-{
-        vmi_ops.set_tr(GDT_ENTRY_TSS*sizeof(struct desc_struct));
-}
-
-static void vmi_write_idt_entry(gate_desc *dt, int entry, const gate_desc *g)
-{
-        u32 *idt_entry = (u32 *)g;
-        vmi_ops.write_idt_entry(dt, entry, idt_entry[0], idt_entry[1]);
-}
-
-static void vmi_write_gdt_entry(struct desc_struct *dt, int entry,
-                                const void *desc, int type)
-{
-        u32 *gdt_entry = (u32 *)desc;
-        vmi_ops.write_gdt_entry(dt, entry, gdt_entry[0], gdt_entry[1]);
-}
-
-static void vmi_write_ldt_entry(struct desc_struct *dt, int entry,
-                                const void *desc)
-{
-        u32 *ldt_entry = (u32 *)desc;
-        vmi_ops.write_ldt_entry(dt, entry, ldt_entry[0], ldt_entry[1]);
-}
-
-static void vmi_load_sp0(struct tss_struct *tss,
-                                   struct thread_struct *thread)
-{
-        tss->x86_tss.sp0 = thread->sp0;
-
-        /* This can only happen when SEP is enabled, no need to test "SEP"arately */
-        if (unlikely(tss->x86_tss.ss1 != thread->sysenter_cs)) {
-                tss->x86_tss.ss1 = thread->sysenter_cs;
-                wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0);
-        }
-        vmi_ops.set_kernel_stack(__KERNEL_DS, tss->x86_tss.sp0);
-}
-
-static void vmi_flush_tlb_user(void)
-{
-        vmi_ops._flush_tlb(VMI_FLUSH_TLB);
-}
-
-static void vmi_flush_tlb_kernel(void)
-{
-        vmi_ops._flush_tlb(VMI_FLUSH_TLB | VMI_FLUSH_GLOBAL);
-}
-
-/* Stub to do nothing at all; used for delays and unimplemented calls */
-static void vmi_nop(void)
-{
-}
-
-static void vmi_allocate_pte(struct mm_struct *mm, unsigned long pfn)
-{
-        vmi_ops.allocate_page(pfn, VMI_PAGE_L1, 0, 0, 0);
-}
-
-static void vmi_allocate_pmd(struct mm_struct *mm, unsigned long pfn)
-{
-        /*
-         * This call comes in very early, before mem_map is setup.
-         * It is called only for swapper_pg_dir, which already has
-         * data on it.
-         */
-        vmi_ops.allocate_page(pfn, VMI_PAGE_L2, 0, 0, 0);
-}
-
-static void vmi_allocate_pmd_clone(unsigned long pfn, unsigned long clonepfn, unsigned long start, unsigned long count)
-{
-        vmi_ops.allocate_page(pfn, VMI_PAGE_L2 | VMI_PAGE_CLONE, clonepfn, start, count);
-}
-
-static void vmi_release_pte(unsigned long pfn)
-{
-        vmi_ops.release_page(pfn, VMI_PAGE_L1);
-}
-
-static void vmi_release_pmd(unsigned long pfn)
-{
-        vmi_ops.release_page(pfn, VMI_PAGE_L2);
-}
-
-/*
- * We use the pgd_free hook for releasing the pgd page:
- */
-static void vmi_pgd_free(struct mm_struct *mm, pgd_t *pgd)
-{
-        unsigned long pfn = __pa(pgd) >> PAGE_SHIFT;
-
-        vmi_ops.release_page(pfn, VMI_PAGE_L2);
-}
-
-/*
- * Helper macros for MMU update flags.  We can defer updates until a flush
- * or page invalidation only if the update is to the current address space
- * (otherwise, there is no flush).  We must check against init_mm, since
- * this could be a kernel update, which usually passes init_mm, although
- * sometimes this check can be skipped if we know the particular function
- * is only called on user mode PTEs.  We could change the kernel to pass
- * current->active_mm here, but in particular, I was unsure if changing
- * mm/highmem.c to do this would still be correct on other architectures.
- */
-#define is_current_as(mm, mustbeuser) ((mm) == current->active_mm ||    \
-                                       (!mustbeuser && (mm) == &init_mm))
-#define vmi_flags_addr(mm, addr, level, user)                           \
-        ((level) | (is_current_as(mm, user) ?                           \
-                (VMI_PAGE_CURRENT_AS | ((addr) & VMI_PAGE_VA_MASK)) : 0))
-#define vmi_flags_addr_defer(mm, addr, level, user)                     \
-        ((level) | (is_current_as(mm, user) ?                           \
-                (VMI_PAGE_DEFER | VMI_PAGE_CURRENT_AS | ((addr) & VMI_PAGE_VA_MASK)) : 0))
-
-static void vmi_update_pte(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
-{
-        vmi_ops.update_pte(ptep, vmi_flags_addr(mm, addr, VMI_PAGE_PT, 0));
-}
-
-static void vmi_update_pte_defer(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
-{
-        vmi_ops.update_pte(ptep, vmi_flags_addr_defer(mm, addr, VMI_PAGE_PT, 0));
-}
-
-static void vmi_set_pte(pte_t *ptep, pte_t pte)
-{
-        /* XXX because of set_pmd_pte, this can be called on PT or PD layers */
-        vmi_ops.set_pte(pte, ptep, VMI_PAGE_PT);
-}
-
-static void vmi_set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte)
-{
-        vmi_ops.set_pte(pte, ptep, vmi_flags_addr(mm, addr, VMI_PAGE_PT, 0));
-}
-
-static void vmi_set_pmd(pmd_t *pmdp, pmd_t pmdval)
-{
-#ifdef CONFIG_X86_PAE
-        const pte_t pte = { .pte = pmdval.pmd };
-#else
-        const pte_t pte = { pmdval.pud.pgd.pgd };
-#endif
-        vmi_ops.set_pte(pte, (pte_t *)pmdp, VMI_PAGE_PD);
-}
-
-#ifdef CONFIG_X86_PAE
-
-static void vmi_set_pte_atomic(pte_t *ptep, pte_t pteval)
-{
-        /*
-         * XXX This is called from set_pmd_pte, but at both PT
-         * and PD layers so the VMI_PAGE_PT flag is wrong.  But
-         * it is only called for large page mapping changes,
-         * the Xen backend, doesn't support large pages, and the
-         * ESX backend doesn't depend on the flag.
-         */
-        set_64bit((unsigned long long *)ptep,pte_val(pteval));
-        vmi_ops.update_pte(ptep, VMI_PAGE_PT);
-}
-
-static void vmi_set_pud(pud_t *pudp, pud_t pudval)
-{
-        /* Um, eww */
-        const pte_t pte = { .pte = pudval.pgd.pgd };
-        vmi_ops.set_pte(pte, (pte_t *)pudp, VMI_PAGE_PDP);
-}
-
-static void vmi_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
-{
-        const pte_t pte = { .pte = 0 };
-        vmi_ops.set_pte(pte, ptep, vmi_flags_addr(mm, addr, VMI_PAGE_PT, 0));
-}
-
-static void vmi_pmd_clear(pmd_t *pmd)
-{
-        const pte_t pte = { .pte = 0 };
-        vmi_ops.set_pte(pte, (pte_t *)pmd, VMI_PAGE_PD);
-}
-#endif
-
-#ifdef CONFIG_SMP
-static void __devinit
-vmi_startup_ipi_hook(int phys_apicid, unsigned long start_eip,
-                     unsigned long start_esp)
-{
-        struct vmi_ap_state ap;
-
-        /* Default everything to zero.  This is fine for most GPRs. */
-        memset(&ap, 0, sizeof(struct vmi_ap_state));
-
-        ap.gdtr_limit = GDT_SIZE - 1;
-        ap.gdtr_base = (unsigned long) get_cpu_gdt_table(phys_apicid);
-
-        ap.idtr_limit = IDT_ENTRIES * 8 - 1;
-        ap.idtr_base = (unsigned long) idt_table;
-
-        ap.ldtr = 0;
-
-        ap.cs = __KERNEL_CS;
-        ap.eip = (unsigned long) start_eip;
-        ap.ss = __KERNEL_DS;
-        ap.esp = (unsigned long) start_esp;
-
-        ap.ds = __USER_DS;
-        ap.es = __USER_DS;
-        ap.fs = __KERNEL_PERCPU;
-        ap.gs = __KERNEL_STACK_CANARY;
-
-        ap.eflags = 0;
-
-#ifdef CONFIG_X86_PAE
-        /* efer should match BSP efer. */
-        if (cpu_has_nx) {
-                unsigned l, h;
-                rdmsr(MSR_EFER, l, h);
-                ap.efer = (unsigned long long) h << 32 | l;
-        }
-#endif
-
-        ap.cr3 = __pa(swapper_pg_dir);
-        /* Protected mode, paging, AM, WP, NE, MP. */
-        ap.cr0 = 0x80050023;
-        ap.cr4 = mmu_cr4_features;
-        vmi_ops.set_initial_ap_state((u32)&ap, phys_apicid);
-}
-#endif
-
-static void vmi_start_context_switch(struct task_struct *prev)
-{
-        paravirt_start_context_switch(prev);
-        vmi_ops.set_lazy_mode(2);
-}
-
-static void vmi_end_context_switch(struct task_struct *next)
-{
-        vmi_ops.set_lazy_mode(0);
-        paravirt_end_context_switch(next);
-}
-
-static void vmi_enter_lazy_mmu(void)
-{
-        paravirt_enter_lazy_mmu();
-        vmi_ops.set_lazy_mode(1);
-}
-
-static void vmi_leave_lazy_mmu(void)
-{
-        vmi_ops.set_lazy_mode(0);
-        paravirt_leave_lazy_mmu();
-}
-
-static inline int __init check_vmi_rom(struct vrom_header *rom)
-{
-        struct pci_header *pci;
-        struct pnp_header *pnp;
-        const char *manufacturer = "UNKNOWN";
-        const char *product = "UNKNOWN";
-        const char *license = "unspecified";
-
-        if (rom->rom_signature != 0xaa55)
-                return 0;
-        if (rom->vrom_signature != VMI_SIGNATURE)
-                return 0;
-        if (rom->api_version_maj != VMI_API_REV_MAJOR ||
-            rom->api_version_min+1 < VMI_API_REV_MINOR+1) {
-                printk(KERN_WARNING "VMI: Found mismatched rom version %d.%d\n",
-                                rom->api_version_maj,
-                                rom->api_version_min);
-                return 0;
-        }
-
-        /*
-         * Relying on the VMI_SIGNATURE field is not 100% safe, so check
-         * the PCI header and device type to make sure this is really a
-         * VMI device.
-         */
-        if (!rom->pci_header_offs) {
-                printk(KERN_WARNING "VMI: ROM does not contain PCI header.\n");
-                return 0;
-        }
-
-        pci = (struct pci_header *)((char *)rom+rom->pci_header_offs);
-        if (pci->vendorID != PCI_VENDOR_ID_VMWARE ||
-            pci->deviceID != PCI_DEVICE_ID_VMWARE_VMI) {
-                /* Allow it to run... anyways, but warn */
-                printk(KERN_WARNING "VMI: ROM from unknown manufacturer\n");
-        }
-
-        if (rom->pnp_header_offs) {
-                pnp = (struct pnp_header *)((char *)rom+rom->pnp_header_offs);
-                if (pnp->manufacturer_offset)
-                        manufacturer = (const char *)rom+pnp->manufacturer_offset;
-                if (pnp->product_offset)
-                        product = (const char *)rom+pnp->product_offset;
-        }
-
-        if (rom->license_offs)
-                license = (char *)rom+rom->license_offs;
-
-        printk(KERN_INFO "VMI: Found %s %s, API version %d.%d, ROM version %d.%d\n",
-                manufacturer, product,
-                rom->api_version_maj, rom->api_version_min,
-                pci->rom_version_maj, pci->rom_version_min);
-
-        /* Don't allow BSD/MIT here for now because we don't want to end up
-           with any binary only shim layers */
-        if (strcmp(license, "GPL") && strcmp(license, "GPL v2")) {
-                printk(KERN_WARNING "VMI: Non GPL license `%s' found for ROM. Not used.\n",
-                        license);
-                return 0;
-        }
-
-        return 1;
-}
-
-/*
- * Probe for the VMI option ROM
- */
-static inline int __init probe_vmi_rom(void)
-{
-        unsigned long base;
-
-        /* VMI ROM is in option ROM area, check signature */
-        for (base = 0xC0000; base < 0xE0000; base += 2048) {
-                struct vrom_header *romstart;
-                romstart = (struct vrom_header *)isa_bus_to_virt(base);
-                if (check_vmi_rom(romstart)) {
-                        vmi_rom = romstart;
-                        return 1;
-                }
-        }
-        return 0;
-}
-
-/*
- * VMI setup common to all processors
- */
-void vmi_bringup(void)
-{
-        /* We must establish the lowmem mapping for MMU ops to work */
-        if (vmi_ops.set_linear_mapping)
-                vmi_ops.set_linear_mapping(0, (void *)__PAGE_OFFSET, MAXMEM_PFN, 0);
-}
-
-/*
- * Return a pointer to a VMI function or NULL if unimplemented
- */
-static void *vmi_get_function(int vmicall)
-{
-        u64 reloc;
-        const struct vmi_relocation_info *rel = (struct vmi_relocation_info *)&reloc;
-        reloc = call_vrom_long_func(vmi_rom, get_reloc, vmicall);
-        BUG_ON(rel->type == VMI_RELOCATION_JUMP_REL);
-        if (rel->type == VMI_RELOCATION_CALL_REL)
-                return (void *)rel->eip;
-        else
-                return NULL;
-}
-
-/*
- * Helper macro for making the VMI paravirt-ops fill code readable.
- * For unimplemented operations, fall back to default, unless nop
- * is returned by the ROM.
- */
-#define para_fill(opname, vmicall)                              \
-do {                                                            \
-        reloc = call_vrom_long_func(vmi_rom, get_reloc,         \
-                                    VMI_CALL_##vmicall);        \
-        if (rel->type == VMI_RELOCATION_CALL_REL)               \
-                opname = (void *)rel->eip;                      \
-        else if (rel->type == VMI_RELOCATION_NOP)               \
-                opname = (void *)vmi_nop;                       \
-        else if (rel->type != VMI_RELOCATION_NONE)              \
-                printk(KERN_WARNING "VMI: Unknown relocation "  \
-                                    "type %d for " #vmicall"\n",\
-                                        rel->type);             \
-} while (0)
-
-/*
- * Helper macro for making the VMI paravirt-ops fill code readable.
- * For cached operations which do not match the VMI ROM ABI and must
- * go through a tranlation stub.  Ignore NOPs, since it is not clear
- * a NOP * VMI function corresponds to a NOP paravirt-op when the
- * functions are not in 1-1 correspondence.
- */
-#define para_wrap(opname, wrapper, cache, vmicall)              \
-do {                                                            \
-        reloc = call_vrom_long_func(vmi_rom, get_reloc,         \
-                                    VMI_CALL_##vmicall);        \
-        BUG_ON(rel->type == VMI_RELOCATION_JUMP_REL);           \
-        if (rel->type == VMI_RELOCATION_CALL_REL) {             \
-                opname = wrapper;                               \
-                vmi_ops.cache = (void *)rel->eip;               \
-        }                                                       \
-} while (0)
-
-/*
- * Activate the VMI interface and switch into paravirtualized mode
- */
-static inline int __init activate_vmi(void)
-{
-        short kernel_cs;
-        u64 reloc;
-        const struct vmi_relocation_info *rel = (struct vmi_relocation_info *)&reloc;
-
-        /*
-         * Prevent page tables from being allocated in highmem, even if
-         * CONFIG_HIGHPTE is enabled.
-         */
-        __userpte_alloc_gfp &= ~__GFP_HIGHMEM;
-
-        if (call_vrom_func(vmi_rom, vmi_init) != 0) {
-                printk(KERN_ERR "VMI ROM failed to initialize!");
-                return 0;
-        }
-        savesegment(cs, kernel_cs);
-
-        pv_info.paravirt_enabled = 1;
-        pv_info.kernel_rpl = kernel_cs & SEGMENT_RPL_MASK;
-        pv_info.name = "vmi [deprecated]";
-
-        pv_init_ops.patch = vmi_patch;
-
-        /*
-         * Many of these operations are ABI compatible with VMI.
-         * This means we can fill in the paravirt-ops with direct
-         * pointers into the VMI ROM.  If the calling convention for
-         * these operations changes, this code needs to be updated.
-         *
-         * Exceptions
-         *  CPUID paravirt-op uses pointers, not the native ISA
-         *  halt has no VMI equivalent; all VMI halts are "safe"
-         *  no MSR support yet - just trap and emulate.  VMI uses the
-         *    same ABI as the native ISA, but Linux wants exceptions
-         *    from bogus MSR read / write handled
-         *  rdpmc is not yet used in Linux
-         */
-
-        /* CPUID is special, so very special it gets wrapped like a present */
-        para_wrap(pv_cpu_ops.cpuid, vmi_cpuid, cpuid, CPUID);
-
-        para_fill(pv_cpu_ops.clts, CLTS);
-        para_fill(pv_cpu_ops.get_debugreg, GetDR);
-        para_fill(pv_cpu_ops.set_debugreg, SetDR);
-        para_fill(pv_cpu_ops.read_cr0, GetCR0);
-        para_fill(pv_mmu_ops.read_cr2, GetCR2);
-        para_fill(pv_mmu_ops.read_cr3, GetCR3);
-        para_fill(pv_cpu_ops.read_cr4, GetCR4);
-        para_fill(pv_cpu_ops.write_cr0, SetCR0);
-        para_fill(pv_mmu_ops.write_cr2, SetCR2);
-        para_fill(pv_mmu_ops.write_cr3, SetCR3);
-        para_fill(pv_cpu_ops.write_cr4, SetCR4);
-
-        para_fill(pv_irq_ops.save_fl.func, GetInterruptMask);
-        para_fill(pv_irq_ops.restore_fl.func, SetInterruptMask);
-        para_fill(pv_irq_ops.irq_disable.func, DisableInterrupts);
-        para_fill(pv_irq_ops.irq_enable.func, EnableInterrupts);
-
-        para_fill(pv_cpu_ops.wbinvd, WBINVD);
-        para_fill(pv_cpu_ops.read_tsc, RDTSC);
-
-        /* The following we emulate with trap and emulate for now */
-        /* paravirt_ops.read_msr = vmi_rdmsr */
-        /* paravirt_ops.write_msr = vmi_wrmsr */
-        /* paravirt_ops.rdpmc = vmi_rdpmc */
-
-        /* TR interface doesn't pass TR value, wrap */
-        para_wrap(pv_cpu_ops.load_tr_desc, vmi_set_tr, set_tr, SetTR);
-
-        /* LDT is special, too */
-        para_wrap(pv_cpu_ops.set_ldt, vmi_set_ldt, _set_ldt, SetLDT);
-
-        para_fill(pv_cpu_ops.load_gdt, SetGDT);
-        para_fill(pv_cpu_ops.load_idt, SetIDT);
-        para_fill(pv_cpu_ops.store_gdt, GetGDT);
-        para_fill(pv_cpu_ops.store_idt, GetIDT);
-        para_fill(pv_cpu_ops.store_tr, GetTR);
-        pv_cpu_ops.load_tls = vmi_load_tls;
-        para_wrap(pv_cpu_ops.write_ldt_entry, vmi_write_ldt_entry,
-                  write_ldt_entry, WriteLDTEntry);
-        para_wrap(pv_cpu_ops.write_gdt_entry, vmi_write_gdt_entry,
-                  write_gdt_entry, WriteGDTEntry);
-        para_wrap(pv_cpu_ops.write_idt_entry, vmi_write_idt_entry,
-                  write_idt_entry, WriteIDTEntry);
-        para_wrap(pv_cpu_ops.load_sp0, vmi_load_sp0, set_kernel_stack, UpdateKernelStack);
-        para_fill(pv_cpu_ops.set_iopl_mask, SetIOPLMask);
-        para_fill(pv_cpu_ops.io_delay, IODelay);
-
-        para_wrap(pv_cpu_ops.start_context_switch, vmi_start_context_switch,
-                  set_lazy_mode, SetLazyMode);
-        para_wrap(pv_cpu_ops.end_context_switch, vmi_end_context_switch,
-                  set_lazy_mode, SetLazyMode);
-
-        para_wrap(pv_mmu_ops.lazy_mode.enter, vmi_enter_lazy_mmu,
-                  set_lazy_mode, SetLazyMode);
-        para_wrap(pv_mmu_ops.lazy_mode.leave, vmi_leave_lazy_mmu,
-                  set_lazy_mode, SetLazyMode);
-
-        /* user and kernel flush are just handled with different flags to FlushTLB */
-        para_wrap(pv_mmu_ops.flush_tlb_user, vmi_flush_tlb_user, _flush_tlb, FlushTLB);
-        para_wrap(pv_mmu_ops.flush_tlb_kernel, vmi_flush_tlb_kernel, _flush_tlb, FlushTLB);
-        para_fill(pv_mmu_ops.flush_tlb_single, InvalPage);
-
-        /*
-         * Until a standard flag format can be agreed on, we need to
-         * implement these as wrappers in Linux.  Get the VMI ROM
-         * function pointers for the two backend calls.
-         */
-#ifdef CONFIG_X86_PAE
-        vmi_ops.set_pte = vmi_get_function(VMI_CALL_SetPxELong);
-        vmi_ops.update_pte = vmi_get_function(VMI_CALL_UpdatePxELong);
-#else
-        vmi_ops.set_pte = vmi_get_function(VMI_CALL_SetPxE);
-        vmi_ops.update_pte = vmi_get_function(VMI_CALL_UpdatePxE);
-#endif
-
-        if (vmi_ops.set_pte) {
-                pv_mmu_ops.set_pte = vmi_set_pte;
-                pv_mmu_ops.set_pte_at = vmi_set_pte_at;
-                pv_mmu_ops.set_pmd = vmi_set_pmd;
-#ifdef CONFIG_X86_PAE
-                pv_mmu_ops.set_pte_atomic = vmi_set_pte_atomic;
-                pv_mmu_ops.set_pud = vmi_set_pud;
-                pv_mmu_ops.pte_clear = vmi_pte_clear;
-                pv_mmu_ops.pmd_clear = vmi_pmd_clear;
-#endif
-        }
-
-        if (vmi_ops.update_pte) {
-                pv_mmu_ops.pte_update = vmi_update_pte;
-                pv_mmu_ops.pte_update_defer = vmi_update_pte_defer;
-        }
-
-        vmi_ops.allocate_page = vmi_get_function(VMI_CALL_AllocatePage);
-        if (vmi_ops.allocate_page) {
-                pv_mmu_ops.alloc_pte = vmi_allocate_pte;
-                pv_mmu_ops.alloc_pmd = vmi_allocate_pmd;
-                pv_mmu_ops.alloc_pmd_clone = vmi_allocate_pmd_clone;
-        }
-
-        vmi_ops.release_page = vmi_get_function(VMI_CALL_ReleasePage);
-        if (vmi_ops.release_page) {
-                pv_mmu_ops.release_pte = vmi_release_pte;
-                pv_mmu_ops.release_pmd = vmi_release_pmd;
-                pv_mmu_ops.pgd_free = vmi_pgd_free;
-        }
-
-        /* Set linear is needed in all cases */
-        vmi_ops.set_linear_mapping = vmi_get_function(VMI_CALL_SetLinearMapping);
-
-        /*
-         * These MUST always be patched.  Don't support indirect jumps
-         * through these operations, as the VMI interface may use either
-         * a jump or a call to get to these operations, depending on
-         * the backend.  They are performance critical anyway, so requiring
-         * a patch is not a big problem.
-         */
-        pv_cpu_ops.irq_enable_sysexit = (void *)0xfeedbab0;
-        pv_cpu_ops.iret = (void *)0xbadbab0;
-
-#ifdef CONFIG_SMP
-        para_wrap(pv_apic_ops.startup_ipi_hook, vmi_startup_ipi_hook, set_initial_ap_state, SetInitialAPState);
-#endif
-
-#ifdef CONFIG_X86_LOCAL_APIC
-       para_fill(apic->read, APICRead);
-       para_fill(apic->write, APICWrite);
-#endif
-
-        /*
-         * Check for VMI timer functionality by probing for a cycle frequency method
-         */
-        reloc = call_vrom_long_func(vmi_rom, get_reloc, VMI_CALL_GetCycleFrequency);
-        if (!disable_vmi_timer && rel->type != VMI_RELOCATION_NONE) {
-                vmi_timer_ops.get_cycle_frequency = (void *)rel->eip;
-                vmi_timer_ops.get_cycle_counter =
-                        vmi_get_function(VMI_CALL_GetCycleCounter);
-                vmi_timer_ops.get_wallclock =
-                        vmi_get_function(VMI_CALL_GetWallclockTime);
-                vmi_timer_ops.wallclock_updated =
-                        vmi_get_function(VMI_CALL_WallclockUpdated);
-                vmi_timer_ops.set_alarm = vmi_get_function(VMI_CALL_SetAlarm);
-                vmi_timer_ops.cancel_alarm =
-                         vmi_get_function(VMI_CALL_CancelAlarm);
-                x86_init.timers.timer_init = vmi_time_init;
-#ifdef CONFIG_X86_LOCAL_APIC
-                x86_init.timers.setup_percpu_clockev = vmi_time_bsp_init;
-                x86_cpuinit.setup_percpu_clockev = vmi_time_ap_init;
-#endif
-                pv_time_ops.sched_clock = vmi_sched_clock;
-                x86_platform.calibrate_tsc = vmi_tsc_khz;
-                x86_platform.get_wallclock = vmi_get_wallclock;
-                x86_platform.set_wallclock = vmi_set_wallclock;
-
-                /* We have true wallclock functions; disable CMOS clock sync */
-                no_sync_cmos_clock = 1;
-        } else {
-                disable_noidle = 1;
-                disable_vmi_timer = 1;
-        }
-
-        para_fill(pv_irq_ops.safe_halt, Halt);
-
-        /*
-         * Alternative instruction rewriting doesn't happen soon enough
-         * to convert VMI_IRET to a call instead of a jump; so we have
-         * to do this before IRQs get reenabled.  Fortunately, it is
-         * idempotent.
-         */
-        apply_paravirt(__parainstructions, __parainstructions_end);
-
-        vmi_bringup();
-
-        return 1;
-}
-
-#undef para_fill
-
-void __init vmi_init(void)
-{
-        if (!vmi_rom)
-                probe_vmi_rom();
-        else
-                check_vmi_rom(vmi_rom);
-
-        /* In case probing for or validating the ROM failed, basil */
-        if (!vmi_rom)
-                return;
-
-        reserve_top_address(-vmi_rom->virtual_top);
-
-#ifdef CONFIG_X86_IO_APIC
-        /* This is virtual hardware; timer routing is wired correctly */
-        no_timer_check = 1;
-#endif
-}
-
-void __init vmi_activate(void)
-{
-        unsigned long flags;
-
-        if (!vmi_rom)
-                return;
-
-        local_irq_save(flags);
-        activate_vmi();
-        local_irq_restore(flags & X86_EFLAGS_IF);
-}
-
-static int __init parse_vmi(char *arg)
-{
-        if (!arg)
-                return -EINVAL;
-
-        if (!strcmp(arg, "disable_pge")) {
-                clear_cpu_cap(&boot_cpu_data, X86_FEATURE_PGE);
-                disable_pge = 1;
-        } else if (!strcmp(arg, "disable_pse")) {
-                clear_cpu_cap(&boot_cpu_data, X86_FEATURE_PSE);
-                disable_pse = 1;
-        } else if (!strcmp(arg, "disable_sep")) {
-                clear_cpu_cap(&boot_cpu_data, X86_FEATURE_SEP);
-                disable_sep = 1;
-        } else if (!strcmp(arg, "disable_tsc")) {
-                clear_cpu_cap(&boot_cpu_data, X86_FEATURE_TSC);
-                disable_tsc = 1;
-        } else if (!strcmp(arg, "disable_mtrr")) {
-                clear_cpu_cap(&boot_cpu_data, X86_FEATURE_MTRR);
-                disable_mtrr = 1;
-        } else if (!strcmp(arg, "disable_timer")) {
-                disable_vmi_timer = 1;
-                disable_noidle = 1;
-        } else if (!strcmp(arg, "disable_noidle"))
-                disable_noidle = 1;
-        return 0;
-}
-
-early_param("vmi", parse_vmi);
diff --git a/arch/x86/kernel/vmiclock_32.c b/arch/x86/kernel/vmiclock_32.c
deleted file mode 100644
index 5e1ff66ecd73..000000000000
--- a/arch/x86/kernel/vmiclock_32.c
+++ /dev/null
@@ -1,317 +0,0 @@
-/*
- * VMI paravirtual timer support routines.
- *
- * Copyright (C) 2007, VMware, Inc.
- *
- * 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, GOOD TITLE or
- * NON INFRINGEMENT.  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., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-
-#include <linux/smp.h>
-#include <linux/interrupt.h>
-#include <linux/cpumask.h>
-#include <linux/clocksource.h>
-#include <linux/clockchips.h>
-
-#include <asm/vmi.h>
-#include <asm/vmi_time.h>
-#include <asm/apicdef.h>
-#include <asm/apic.h>
-#include <asm/timer.h>
-#include <asm/i8253.h>
-#include <asm/irq_vectors.h>
-
-#define VMI_ONESHOT  (VMI_ALARM_IS_ONESHOT  | VMI_CYCLES_REAL | vmi_get_alarm_wiring())
-#define VMI_PERIODIC (VMI_ALARM_IS_PERIODIC | VMI_CYCLES_REAL | vmi_get_alarm_wiring())
-
-static DEFINE_PER_CPU(struct clock_event_device, local_events);
-
-static inline u32 vmi_counter(u32 flags)
-{
-        /* Given VMI_ONESHOT or VMI_PERIODIC, return the corresponding
-         * cycle counter. */
-        return flags & VMI_ALARM_COUNTER_MASK;
-}
-
-/* paravirt_ops.get_wallclock = vmi_get_wallclock */
-unsigned long vmi_get_wallclock(void)
-{
-        unsigned long long wallclock;
-        wallclock = vmi_timer_ops.get_wallclock(); // nsec
-        (void)do_div(wallclock, 1000000000);       // sec
-
-        return wallclock;
-}
-
-/* paravirt_ops.set_wallclock = vmi_set_wallclock */
-int vmi_set_wallclock(unsigned long now)
-{
-        return 0;
-}
-
-/* paravirt_ops.sched_clock = vmi_sched_clock */
-unsigned long long vmi_sched_clock(void)
-{
-        return cycles_2_ns(vmi_timer_ops.get_cycle_counter(VMI_CYCLES_AVAILABLE));
-}
-
-/* x86_platform.calibrate_tsc = vmi_tsc_khz */
-unsigned long vmi_tsc_khz(void)
-{
-        unsigned long long khz;
-        khz = vmi_timer_ops.get_cycle_frequency();
-        (void)do_div(khz, 1000);
-        return khz;
-}
-
-static inline unsigned int vmi_get_timer_vector(void)
-{
-        return IRQ0_VECTOR;
-}
-
-/** vmi clockchip */
-#ifdef CONFIG_X86_LOCAL_APIC
-static unsigned int startup_timer_irq(unsigned int irq)
-{
-        unsigned long val = apic_read(APIC_LVTT);
-        apic_write(APIC_LVTT, vmi_get_timer_vector());
-
-        return (val & APIC_SEND_PENDING);
-}
-
-static void mask_timer_irq(unsigned int irq)
-{
-        unsigned long val = apic_read(APIC_LVTT);
-        apic_write(APIC_LVTT, val | APIC_LVT_MASKED);
-}
-
-static void unmask_timer_irq(unsigned int irq)
-{
-        unsigned long val = apic_read(APIC_LVTT);
-        apic_write(APIC_LVTT, val & ~APIC_LVT_MASKED);
-}
-
-static void ack_timer_irq(unsigned int irq)
-{
-        ack_APIC_irq();
-}
-
-static struct irq_chip vmi_chip __read_mostly = {
-        .name           = "VMI-LOCAL",
-        .startup        = startup_timer_irq,
-        .mask           = mask_timer_irq,
-        .unmask         = unmask_timer_irq,
-        .ack            = ack_timer_irq
-};
-#endif
-
-/** vmi clockevent */
-#define VMI_ALARM_WIRED_IRQ0    0x00000000
-#define VMI_ALARM_WIRED_LVTT    0x00010000
-static int vmi_wiring = VMI_ALARM_WIRED_IRQ0;
-
-static inline int vmi_get_alarm_wiring(void)
-{
-        return vmi_wiring;
-}
-
-static void vmi_timer_set_mode(enum clock_event_mode mode,
-                               struct clock_event_device *evt)
-{
-        cycle_t now, cycles_per_hz;
-        BUG_ON(!irqs_disabled());
-
-        switch (mode) {
-        case CLOCK_EVT_MODE_ONESHOT:
-        case CLOCK_EVT_MODE_RESUME:
-                break;
-        case CLOCK_EVT_MODE_PERIODIC:
-                cycles_per_hz = vmi_timer_ops.get_cycle_frequency();
-                (void)do_div(cycles_per_hz, HZ);
-                now = vmi_timer_ops.get_cycle_counter(vmi_counter(VMI_PERIODIC));
-                vmi_timer_ops.set_alarm(VMI_PERIODIC, now, cycles_per_hz);
-                break;
-        case CLOCK_EVT_MODE_UNUSED:
-        case CLOCK_EVT_MODE_SHUTDOWN:
-                switch (evt->mode) {
-                case CLOCK_EVT_MODE_ONESHOT:
-                        vmi_timer_ops.cancel_alarm(VMI_ONESHOT);
-                        break;
-                case CLOCK_EVT_MODE_PERIODIC:
-                        vmi_timer_ops.cancel_alarm(VMI_PERIODIC);
-                        break;
-                default:
-                        break;
-                }
-                break;
-        default:
-                break;
-        }
-}
-
-static int vmi_timer_next_event(unsigned long delta,
-                                struct clock_event_device *evt)
-{
-        /* Unfortunately, set_next_event interface only passes relative
-         * expiry, but we want absolute expiry.  It'd be better if were
-         * were passed an absolute expiry, since a bunch of time may
-         * have been stolen between the time the delta is computed and
-         * when we set the alarm below. */
-        cycle_t now = vmi_timer_ops.get_cycle_counter(vmi_counter(VMI_ONESHOT));
-
-        BUG_ON(evt->mode != CLOCK_EVT_MODE_ONESHOT);
-        vmi_timer_ops.set_alarm(VMI_ONESHOT, now + delta, 0);
-        return 0;
-}
-
-static struct clock_event_device vmi_clockevent = {
-        .name           = "vmi-timer",
-        .features       = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
-        .shift          = 22,
-        .set_mode       = vmi_timer_set_mode,
-        .set_next_event = vmi_timer_next_event,
-        .rating         = 1000,
-        .irq            = 0,
-};
-
-static irqreturn_t vmi_timer_interrupt(int irq, void *dev_id)
-{
-        struct clock_event_device *evt = &__get_cpu_var(local_events);
-        evt->event_handler(evt);
-        return IRQ_HANDLED;
-}
-
-static struct irqaction vmi_clock_action  = {
-        .name           = "vmi-timer",
-        .handler        = vmi_timer_interrupt,
-        .flags          = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_TIMER,
-};
-
-static void __devinit vmi_time_init_clockevent(void)
-{
-        cycle_t cycles_per_msec;
-        struct clock_event_device *evt;
-
-        int cpu = smp_processor_id();
-        evt = &__get_cpu_var(local_events);
-
-        /* Use cycles_per_msec since div_sc params are 32-bits. */
-        cycles_per_msec = vmi_timer_ops.get_cycle_frequency();
-        (void)do_div(cycles_per_msec, 1000);
-
-        memcpy(evt, &vmi_clockevent, sizeof(*evt));
-        /* Must pick .shift such that .mult fits in 32-bits.  Choosing
-         * .shift to be 22 allows 2^(32-22) cycles per nano-seconds
-         * before overflow. */
-        evt->mult = div_sc(cycles_per_msec, NSEC_PER_MSEC, evt->shift);
-        /* Upper bound is clockevent's use of ulong for cycle deltas. */
-        evt->max_delta_ns = clockevent_delta2ns(ULONG_MAX, evt);
-        evt->min_delta_ns = clockevent_delta2ns(1, evt);
-        evt->cpumask = cpumask_of(cpu);
-
-        printk(KERN_WARNING "vmi: registering clock event %s. mult=%u shift=%u\n",
-               evt->name, evt->mult, evt->shift);
-        clockevents_register_device(evt);
-}
-
-void __init vmi_time_init(void)
-{
-        unsigned int cpu;
-        /* Disable PIT: BIOSes start PIT CH0 with 18.2hz peridic. */
-        outb_pit(0x3a, PIT_MODE); /* binary, mode 5, LSB/MSB, ch 0 */
-
-        vmi_time_init_clockevent();
-        setup_irq(0, &vmi_clock_action);
-        for_each_possible_cpu(cpu)
-                per_cpu(vector_irq, cpu)[vmi_get_timer_vector()] = 0;
-}
-
-#ifdef CONFIG_X86_LOCAL_APIC
-void __devinit vmi_time_bsp_init(void)
-{
-        /*
-         * On APIC systems, we want local timers to fire on each cpu.  We do
-         * this by programming LVTT to deliver timer events to the IRQ handler
-         * for IRQ-0, since we can't re-use the APIC local timer handler
-         * without interfering with that code.
-         */
-        clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL);
-        local_irq_disable();
-#ifdef CONFIG_SMP
-        /*
-         * XXX handle_percpu_irq only defined for SMP; we need to switch over
-         * to using it, since this is a local interrupt, which each CPU must
-         * handle individually without locking out or dropping simultaneous
-         * local timers on other CPUs.  We also don't want to trigger the
-         * quirk workaround code for interrupts which gets invoked from
-         * handle_percpu_irq via eoi, so we use our own IRQ chip.
-         */
-        set_irq_chip_and_handler_name(0, &vmi_chip, handle_percpu_irq, "lvtt");
-#else
-        set_irq_chip_and_handler_name(0, &vmi_chip, handle_edge_irq, "lvtt");
-#endif
-        vmi_wiring = VMI_ALARM_WIRED_LVTT;
-        apic_write(APIC_LVTT, vmi_get_timer_vector());
-        local_irq_enable();
-        clockevents_notify(CLOCK_EVT_NOTIFY_RESUME, NULL);
-}
-
-void __devinit vmi_time_ap_init(void)
-{
-        vmi_time_init_clockevent();
-        apic_write(APIC_LVTT, vmi_get_timer_vector());
-}
-#endif
-
-/** vmi clocksource */
-static struct clocksource clocksource_vmi;
-
-static cycle_t read_real_cycles(struct clocksource *cs)
-{
-        cycle_t ret = (cycle_t)vmi_timer_ops.get_cycle_counter(VMI_CYCLES_REAL);
-        return max(ret, clocksource_vmi.cycle_last);
-}
-
-static struct clocksource clocksource_vmi = {
-        .name                   = "vmi-timer",
-        .rating                 = 450,
-        .read                   = read_real_cycles,
-        .mask                   = CLOCKSOURCE_MASK(64),
-        .mult                   = 0, /* to be set */
-        .shift                  = 22,
-        .flags                  = CLOCK_SOURCE_IS_CONTINUOUS,
-};
-
-static int __init init_vmi_clocksource(void)
-{
-        cycle_t cycles_per_msec;
-
-        if (!vmi_timer_ops.get_cycle_frequency)
-                return 0;
-        /* Use khz2mult rather than hz2mult since hz arg is only 32-bits. */
-        cycles_per_msec = vmi_timer_ops.get_cycle_frequency();
-        (void)do_div(cycles_per_msec, 1000);
-
-        /* Note that clocksource.{mult, shift} converts in the opposite direction
-         * as clockevents.  */
-        clocksource_vmi.mult = clocksource_khz2mult(cycles_per_msec,
-                                                    clocksource_vmi.shift);
-
-        printk(KERN_WARNING "vmi: registering clock source khz=%lld\n", cycles_per_msec);
-        return clocksource_register(&clocksource_vmi);
-
-}
-module_init(init_vmi_clocksource);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 77d8c0f4817d..22b06f7660f4 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1056,14 +1056,13 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu)
 
         vcpu->arch.apic = apic;
 
-        apic->regs_page = alloc_page(GFP_KERNEL);
+        apic->regs_page = alloc_page(GFP_KERNEL|__GFP_ZERO);
         if (apic->regs_page == NULL) {
                 printk(KERN_ERR "malloc apic regs error for vcpu %x\n",
                        vcpu->vcpu_id);
                 goto nomem_free_apic;
         }
         apic->regs = page_address(apic->regs_page);
-        memset(apic->regs, 0, PAGE_SIZE);
         apic->vcpu = vcpu;
 
         hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3a09c625d526..6c2ecf0a806d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1991,13 +1991,14 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
                 0 /* Reserved */ | F(CX16) | 0 /* xTPR Update, PDCM */ |
                 0 /* Reserved, DCA */ | F(XMM4_1) |
                 F(XMM4_2) | F(X2APIC) | F(MOVBE) | F(POPCNT) |
-                0 /* Reserved, AES */ | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX);
+                0 /* Reserved*/ | F(AES) | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX) |
+                F(F16C);
         /* cpuid 0x80000001.ecx */
         const u32 kvm_supported_word6_x86_features =
                 F(LAHF_LM) | F(CMP_LEGACY) | F(SVM) | 0 /* ExtApicSpace */ |
                 F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) |
-                F(3DNOWPREFETCH) | 0 /* OSVW */ | 0 /* IBS */ | F(SSE5) |
-                0 /* SKINIT */ | 0 /* WDT */;
+                F(3DNOWPREFETCH) | 0 /* OSVW */ | 0 /* IBS */ | F(XOP) |
+                0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM);
 
         /* all calls to cpuid_count() should be made on the same cpu */
         get_cpu();
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 9d5f55848455..73b1e1a1f489 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -791,22 +791,22 @@ static void lguest_flush_tlb_kernel(void)
  * simple as setting a bit.  We don't actually "ack" interrupts as such, we
  * just mask and unmask them.  I wonder if we should be cleverer?
  */
-static void disable_lguest_irq(unsigned int irq)
+static void disable_lguest_irq(struct irq_data *data)
 {
-        set_bit(irq, lguest_data.blocked_interrupts);
+        set_bit(data->irq, lguest_data.blocked_interrupts);
 }
 
-static void enable_lguest_irq(unsigned int irq)
+static void enable_lguest_irq(struct irq_data *data)
 {
-        clear_bit(irq, lguest_data.blocked_interrupts);
+        clear_bit(data->irq, lguest_data.blocked_interrupts);
 }
 
 /* This structure describes the lguest IRQ controller. */
 static struct irq_chip lguest_irq_controller = {
         .name           = "lguest",
-        .mask           = disable_lguest_irq,
-        .mask_ack       = disable_lguest_irq,
-        .unmask         = enable_lguest_irq,
+        .irq_mask       = disable_lguest_irq,
+        .irq_mask_ack   = disable_lguest_irq,
+        .irq_unmask     = enable_lguest_irq,
 };
 
 /*
@@ -838,12 +838,12 @@ static void __init lguest_init_IRQ(void)
  * rather than set them in lguest_init_IRQ we are called here every time an
  * lguest device needs an interrupt.
  *
- * FIXME: irq_to_desc_alloc_node() can fail due to lack of memory, we should
+ * FIXME: irq_alloc_desc_at() can fail due to lack of memory, we should
  * pass that up!
  */
 void lguest_setup_irq(unsigned int irq)
 {
-        irq_to_desc_alloc_node(irq, 0);
+        irq_alloc_desc_at(irq, 0);
         set_irq_chip_and_handler_name(irq, &lguest_irq_controller,
                                       handle_level_irq, "level");
 }
diff --git a/arch/x86/lib/memcpy_32.c b/arch/x86/lib/memcpy_32.c
index 5415a9d06f53..b908a59eccf5 100644
--- a/arch/x86/lib/memcpy_32.c
+++ b/arch/x86/lib/memcpy_32.c
@@ -22,22 +22,187 @@ EXPORT_SYMBOL(memset);
 
 void *memmove(void *dest, const void *src, size_t n)
 {
-        int d0, d1, d2;
-
-        if (dest < src) {
-                memcpy(dest, src, n);
-        } else {
-                __asm__ __volatile__(
-                        "std\n\t"
-                        "rep\n\t"
-                        "movsb\n\t"
-                        "cld"
-                        : "=&c" (d0), "=&S" (d1), "=&D" (d2)
-                        :"0" (n),
-                         "1" (n-1+src),
-                         "2" (n-1+dest)
-                        :"memory");
-        }
-        return dest;
+        int d0,d1,d2,d3,d4,d5;
+        char *ret = dest;
+
+        __asm__ __volatile__(
+                /* Handle more 16bytes in loop */
+                "cmp $0x10, %0\n\t"
+                "jb     1f\n\t"
+
+                /* Decide forward/backward copy mode */
+                "cmp %2, %1\n\t"
+                "jb     2f\n\t"
+
+                /*
+                 * movs instruction have many startup latency
+                 * so we handle small size by general register.
+                 */
+                "cmp  $680, %0\n\t"
+                "jb 3f\n\t"
+                /*
+                 * movs instruction is only good for aligned case.
+                 */
+                "mov %1, %3\n\t"
+                "xor %2, %3\n\t"
+                "and $0xff, %3\n\t"
+                "jz 4f\n\t"
+                "3:\n\t"
+                "sub $0x10, %0\n\t"
+
+                /*
+                 * We gobble 16byts forward in each loop.
+                 */
+                "3:\n\t"
+                "sub $0x10, %0\n\t"
+                "mov 0*4(%1), %3\n\t"
+                "mov 1*4(%1), %4\n\t"
+                "mov  %3, 0*4(%2)\n\t"
+                "mov  %4, 1*4(%2)\n\t"
+                "mov 2*4(%1), %3\n\t"
+                "mov 3*4(%1), %4\n\t"
+                "mov  %3, 2*4(%2)\n\t"
+                "mov  %4, 3*4(%2)\n\t"
+                "lea  0x10(%1), %1\n\t"
+                "lea  0x10(%2), %2\n\t"
+                "jae 3b\n\t"
+                "add $0x10, %0\n\t"
+                "jmp 1f\n\t"
+
+                /*
+                 * Handle data forward by movs.
+                 */
+                ".p2align 4\n\t"
+                "4:\n\t"
+                "mov -4(%1, %0), %3\n\t"
+                "lea -4(%2, %0), %4\n\t"
+                "shr $2, %0\n\t"
+                "rep movsl\n\t"
+                "mov %3, (%4)\n\t"
+                "jmp 11f\n\t"
+                /*
+                 * Handle data backward by movs.
+                 */
+                ".p2align 4\n\t"
+                "6:\n\t"
+                "mov (%1), %3\n\t"
+                "mov %2, %4\n\t"
+                "lea -4(%1, %0), %1\n\t"
+                "lea -4(%2, %0), %2\n\t"
+                "shr $2, %0\n\t"
+                "std\n\t"
+                "rep movsl\n\t"
+                "mov %3,(%4)\n\t"
+                "cld\n\t"
+                "jmp 11f\n\t"
+
+                /*
+                 * Start to prepare for backward copy.
+                 */
+                ".p2align 4\n\t"
+                "2:\n\t"
+                "cmp  $680, %0\n\t"
+                "jb 5f\n\t"
+                "mov %1, %3\n\t"
+                "xor %2, %3\n\t"
+                "and $0xff, %3\n\t"
+                "jz 6b\n\t"
+
+                /*
+                 * Calculate copy position to tail.
+                 */
+                "5:\n\t"
+                "add %0, %1\n\t"
+                "add %0, %2\n\t"
+                "sub $0x10, %0\n\t"
+
+                /*
+                 * We gobble 16byts backward in each loop.
+                 */
+                "7:\n\t"
+                "sub $0x10, %0\n\t"
+
+                "mov -1*4(%1), %3\n\t"
+                "mov -2*4(%1), %4\n\t"
+                "mov  %3, -1*4(%2)\n\t"
+                "mov  %4, -2*4(%2)\n\t"
+                "mov -3*4(%1), %3\n\t"
+                "mov -4*4(%1), %4\n\t"
+                "mov  %3, -3*4(%2)\n\t"
+                "mov  %4, -4*4(%2)\n\t"
+                "lea  -0x10(%1), %1\n\t"
+                "lea  -0x10(%2), %2\n\t"
+                "jae 7b\n\t"
+                /*
+                 * Calculate copy position to head.
+                 */
+                "add $0x10, %0\n\t"
+                "sub %0, %1\n\t"
+                "sub %0, %2\n\t"
+
+                /*
+                 * Move data from 8 bytes to 15 bytes.
+                 */
+                ".p2align 4\n\t"
+                "1:\n\t"
+                "cmp $8, %0\n\t"
+                "jb 8f\n\t"
+                "mov 0*4(%1), %3\n\t"
+                "mov 1*4(%1), %4\n\t"
+                "mov -2*4(%1, %0), %5\n\t"
+                "mov -1*4(%1, %0), %1\n\t"
+
+                "mov  %3, 0*4(%2)\n\t"
+                "mov  %4, 1*4(%2)\n\t"
+                "mov  %5, -2*4(%2, %0)\n\t"
+                "mov  %1, -1*4(%2, %0)\n\t"
+                "jmp 11f\n\t"
+
+                /*
+                 * Move data from 4 bytes to 7 bytes.
+                 */
+                ".p2align 4\n\t"
+                "8:\n\t"
+                "cmp $4, %0\n\t"
+                "jb 9f\n\t"
+                "mov 0*4(%1), %3\n\t"
+                "mov -1*4(%1, %0), %4\n\t"
+                "mov  %3, 0*4(%2)\n\t"
+                "mov  %4, -1*4(%2, %0)\n\t"
+                "jmp 11f\n\t"
+
+                /*
+                 * Move data from 2 bytes to 3 bytes.
+                 */
+                ".p2align 4\n\t"
+                "9:\n\t"
+                "cmp $2, %0\n\t"
+                "jb 10f\n\t"
+                "movw 0*2(%1), %%dx\n\t"
+                "movw -1*2(%1, %0), %%bx\n\t"
+                "movw %%dx, 0*2(%2)\n\t"
+                "movw %%bx, -1*2(%2, %0)\n\t"
+                "jmp 11f\n\t"
+
+                /*
+                 * Move data for 1 byte.
+                 */
+                ".p2align 4\n\t"
+                "10:\n\t"
+                "cmp $1, %0\n\t"
+                "jb 11f\n\t"
+                "movb (%1), %%cl\n\t"
+                "movb %%cl, (%2)\n\t"
+                ".p2align 4\n\t"
+                "11:"
+                : "=&c" (d0), "=&S" (d1), "=&D" (d2),
+                  "=r" (d3),"=r" (d4), "=r"(d5)
+                :"0" (n),
+                 "1" (src),
+                 "2" (dest)
+                :"memory");
+
+        return ret;
+
 }
 EXPORT_SYMBOL(memmove);
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index bcbcd1e0f7d5..75ef61e35e38 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -40,84 +40,132 @@
 ENTRY(__memcpy)
 ENTRY(memcpy)
         CFI_STARTPROC
+        movq %rdi, %rax
 
         /*
-         * Put the number of full 64-byte blocks into %ecx.
-         * Tail portion is handled at the end:
+         * Use 32bit CMP here to avoid long NOP padding.
          */
-        movq %rdi, %rax
-        movl %edx, %ecx
-        shrl   $6, %ecx
-        jz .Lhandle_tail
+        cmp  $0x20, %edx
+        jb .Lhandle_tail
 
-        .p2align 4
-.Lloop_64:
         /*
-         * We decrement the loop index here - and the zero-flag is
-         * checked at the end of the loop (instructions inbetween do
-         * not change the zero flag):
+         * We check whether memory false dependece could occur,
+         * then jump to corresponding copy mode.
          */
-        decl %ecx
+        cmp  %dil, %sil
+        jl .Lcopy_backward
+        subl $0x20, %edx
+.Lcopy_forward_loop:
+        subq $0x20,     %rdx
 
         /*
-         * Move in blocks of 4x16 bytes:
+         * Move in blocks of 4x8 bytes:
          */
-        movq 0*8(%rsi),         %r11
-        movq 1*8(%rsi),         %r8
-        movq %r11,              0*8(%rdi)
-        movq %r8,               1*8(%rdi)
-
-        movq 2*8(%rsi),         %r9
-        movq 3*8(%rsi),         %r10
-        movq %r9,               2*8(%rdi)
-        movq %r10,              3*8(%rdi)
-
-        movq 4*8(%rsi),         %r11
-        movq 5*8(%rsi),         %r8
-        movq %r11,              4*8(%rdi)
-        movq %r8,               5*8(%rdi)
-
-        movq 6*8(%rsi),         %r9
-        movq 7*8(%rsi),         %r10
-        movq %r9,               6*8(%rdi)
-        movq %r10,              7*8(%rdi)
-
-        leaq 64(%rsi), %rsi
-        leaq 64(%rdi), %rdi
-
-        jnz  .Lloop_64
+        movq 0*8(%rsi), %r8
+        movq 1*8(%rsi), %r9
+        movq 2*8(%rsi), %r10
+        movq 3*8(%rsi), %r11
+        leaq 4*8(%rsi), %rsi
+
+        movq %r8,       0*8(%rdi)
+        movq %r9,       1*8(%rdi)
+        movq %r10,      2*8(%rdi)
+        movq %r11,      3*8(%rdi)
+        leaq 4*8(%rdi), %rdi
+        jae  .Lcopy_forward_loop
+        addq $0x20,     %rdx
+        jmp  .Lhandle_tail
+
+.Lcopy_backward:
+        /*
+         * Calculate copy position to tail.
+         */
+        addq %rdx,      %rsi
+        addq %rdx,      %rdi
+        subq $0x20,     %rdx
+        /*
+         * At most 3 ALU operations in one cycle,
+         * so append NOPS in the same 16bytes trunk.
+         */
+        .p2align 4
+.Lcopy_backward_loop:
+        subq $0x20,     %rdx
+        movq -1*8(%rsi),        %r8
+        movq -2*8(%rsi),        %r9
+        movq -3*8(%rsi),        %r10
+        movq -4*8(%rsi),        %r11
+        leaq -4*8(%rsi),        %rsi
+        movq %r8,               -1*8(%rdi)
+        movq %r9,               -2*8(%rdi)
+        movq %r10,              -3*8(%rdi)
+        movq %r11,              -4*8(%rdi)
+        leaq -4*8(%rdi),        %rdi
+        jae  .Lcopy_backward_loop
 
+        /*
+         * Calculate copy position to head.
+         */
+        addq $0x20,     %rdx
+        subq %rdx,      %rsi
+        subq %rdx,      %rdi
 .Lhandle_tail:
-        movl %edx, %ecx
-        andl  $63, %ecx
-        shrl   $3, %ecx
-        jz   .Lhandle_7
+        cmpq $16,       %rdx
+        jb   .Lless_16bytes
 
+        /*
+         * Move data from 16 bytes to 31 bytes.
+         */
+        movq 0*8(%rsi), %r8
+        movq 1*8(%rsi), %r9
+        movq -2*8(%rsi, %rdx),  %r10
+        movq -1*8(%rsi, %rdx),  %r11
+        movq %r8,       0*8(%rdi)
+        movq %r9,       1*8(%rdi)
+        movq %r10,      -2*8(%rdi, %rdx)
+        movq %r11,      -1*8(%rdi, %rdx)
+        retq
         .p2align 4
-.Lloop_8:
-        decl %ecx
-        movq (%rsi),            %r8
-        movq %r8,               (%rdi)
-        leaq 8(%rdi),           %rdi
-        leaq 8(%rsi),           %rsi
-        jnz  .Lloop_8
-
-.Lhandle_7:
-        movl %edx, %ecx
-        andl $7, %ecx
-        jz .Lend
+.Lless_16bytes:
+        cmpq $8,        %rdx
+        jb   .Lless_8bytes
+        /*
+         * Move data from 8 bytes to 15 bytes.
+         */
+        movq 0*8(%rsi), %r8
+        movq -1*8(%rsi, %rdx),  %r9
+        movq %r8,       0*8(%rdi)
+        movq %r9,       -1*8(%rdi, %rdx)
+        retq
+        .p2align 4
+.Lless_8bytes:
+        cmpq $4,        %rdx
+        jb   .Lless_3bytes
 
+        /*
+         * Move data from 4 bytes to 7 bytes.
+         */
+        movl (%rsi), %ecx
+        movl -4(%rsi, %rdx), %r8d
+        movl %ecx, (%rdi)
+        movl %r8d, -4(%rdi, %rdx)
+        retq
         .p2align 4
+.Lless_3bytes:
+        cmpl $0, %edx
+        je .Lend
+        /*
+         * Move data from 1 bytes to 3 bytes.
+         */
 .Lloop_1:
         movb (%rsi), %r8b
         movb %r8b, (%rdi)
         incq %rdi
         incq %rsi
-        decl %ecx
+        decl %edx
         jnz .Lloop_1
 
 .Lend:
-        ret
+        retq
         CFI_ENDPROC
 ENDPROC(memcpy)
 ENDPROC(__memcpy)
diff --git a/arch/x86/lib/memmove_64.c b/arch/x86/lib/memmove_64.c
index 0a33909bf122..6d0f0ec41b34 100644
--- a/arch/x86/lib/memmove_64.c
+++ b/arch/x86/lib/memmove_64.c
@@ -8,14 +8,185 @@
 #undef memmove
 void *memmove(void *dest, const void *src, size_t count)
 {
-        if (dest < src) {
-                return memcpy(dest, src, count);
-        } else {
-                char *p = dest + count;
-                const char *s = src + count;
-                while (count--)
-                        *--p = *--s;
-        }
-        return dest;
+        unsigned long d0,d1,d2,d3,d4,d5,d6,d7;
+        char *ret;
+
+        __asm__ __volatile__(
+                /* Handle more 32bytes in loop */
+                "mov %2, %3\n\t"
+                "cmp $0x20, %0\n\t"
+                "jb     1f\n\t"
+
+                /* Decide forward/backward copy mode */
+                "cmp %2, %1\n\t"
+                "jb     2f\n\t"
+
+                /*
+                 * movsq instruction have many startup latency
+                 * so we handle small size by general register.
+                 */
+                "cmp  $680, %0\n\t"
+                "jb 3f\n\t"
+                /*
+                 * movsq instruction is only good for aligned case.
+                 */
+                "cmpb %%dil, %%sil\n\t"
+                "je 4f\n\t"
+                "3:\n\t"
+                "sub $0x20, %0\n\t"
+                /*
+                 * We gobble 32byts forward in each loop.
+                 */
+                "5:\n\t"
+                "sub $0x20, %0\n\t"
+                "movq 0*8(%1), %4\n\t"
+                "movq 1*8(%1), %5\n\t"
+                "movq 2*8(%1), %6\n\t"
+                "movq 3*8(%1), %7\n\t"
+                "leaq 4*8(%1), %1\n\t"
+
+                "movq %4, 0*8(%2)\n\t"
+                "movq %5, 1*8(%2)\n\t"
+                "movq %6, 2*8(%2)\n\t"
+                "movq %7, 3*8(%2)\n\t"
+                "leaq 4*8(%2), %2\n\t"
+                "jae 5b\n\t"
+                "addq $0x20, %0\n\t"
+                "jmp 1f\n\t"
+                /*
+                 * Handle data forward by movsq.
+                 */
+                ".p2align 4\n\t"
+                "4:\n\t"
+                "movq %0, %8\n\t"
+                "movq -8(%1, %0), %4\n\t"
+                "lea -8(%2, %0), %5\n\t"
+                "shrq $3, %8\n\t"
+                "rep movsq\n\t"
+                "movq %4, (%5)\n\t"
+                "jmp 13f\n\t"
+                /*
+                 * Handle data backward by movsq.
+                 */
+                ".p2align 4\n\t"
+                "7:\n\t"
+                "movq %0, %8\n\t"
+                "movq (%1), %4\n\t"
+                "movq %2, %5\n\t"
+                "leaq -8(%1, %0), %1\n\t"
+                "leaq -8(%2, %0), %2\n\t"
+                "shrq $3, %8\n\t"
+                "std\n\t"
+                "rep movsq\n\t"
+                "cld\n\t"
+                "movq %4, (%5)\n\t"
+                "jmp 13f\n\t"
+
+                /*
+                 * Start to prepare for backward copy.
+                 */
+                ".p2align 4\n\t"
+                "2:\n\t"
+                "cmp $680, %0\n\t"
+                "jb 6f \n\t"
+                "cmp %%dil, %%sil\n\t"
+                "je 7b \n\t"
+                "6:\n\t"
+                /*
+                 * Calculate copy position to tail.
+                 */
+                "addq %0, %1\n\t"
+                "addq %0, %2\n\t"
+                "subq $0x20, %0\n\t"
+                /*
+                 * We gobble 32byts backward in each loop.
+                 */
+                "8:\n\t"
+                "subq $0x20, %0\n\t"
+                "movq -1*8(%1), %4\n\t"
+                "movq -2*8(%1), %5\n\t"
+                "movq -3*8(%1), %6\n\t"
+                "movq -4*8(%1), %7\n\t"
+                "leaq -4*8(%1), %1\n\t"
+
+                "movq %4, -1*8(%2)\n\t"
+                "movq %5, -2*8(%2)\n\t"
+                "movq %6, -3*8(%2)\n\t"
+                "movq %7, -4*8(%2)\n\t"
+                "leaq -4*8(%2), %2\n\t"
+                "jae 8b\n\t"
+                /*
+                 * Calculate copy position to head.
+                 */
+                "addq $0x20, %0\n\t"
+                "subq %0, %1\n\t"
+                "subq %0, %2\n\t"
+                "1:\n\t"
+                "cmpq $16, %0\n\t"
+                "jb 9f\n\t"
+                /*
+                 * Move data from 16 bytes to 31 bytes.
+                 */
+                "movq 0*8(%1), %4\n\t"
+                "movq 1*8(%1), %5\n\t"
+                "movq -2*8(%1, %0), %6\n\t"
+                "movq -1*8(%1, %0), %7\n\t"
+                "movq %4, 0*8(%2)\n\t"
+                "movq %5, 1*8(%2)\n\t"
+                "movq %6, -2*8(%2, %0)\n\t"
+                "movq %7, -1*8(%2, %0)\n\t"
+                "jmp 13f\n\t"
+                ".p2align 4\n\t"
+                "9:\n\t"
+                "cmpq $8, %0\n\t"
+                "jb 10f\n\t"
+                /*
+                 * Move data from 8 bytes to 15 bytes.
+                 */
+                "movq 0*8(%1), %4\n\t"
+                "movq -1*8(%1, %0), %5\n\t"
+                "movq %4, 0*8(%2)\n\t"
+                "movq %5, -1*8(%2, %0)\n\t"
+                "jmp 13f\n\t"
+                "10:\n\t"
+                "cmpq $4, %0\n\t"
+                "jb 11f\n\t"
+                /*
+                 * Move data from 4 bytes to 7 bytes.
+                 */
+                "movl (%1), %4d\n\t"
+                "movl -4(%1, %0), %5d\n\t"
+                "movl %4d, (%2)\n\t"
+                "movl %5d, -4(%2, %0)\n\t"
+                "jmp 13f\n\t"
+                "11:\n\t"
+                "cmp $2, %0\n\t"
+                "jb 12f\n\t"
+                /*
+                 * Move data from 2 bytes to 3 bytes.
+                 */
+                "movw (%1), %4w\n\t"
+                "movw -2(%1, %0), %5w\n\t"
+                "movw %4w, (%2)\n\t"
+                "movw %5w, -2(%2, %0)\n\t"
+                "jmp 13f\n\t"
+                "12:\n\t"
+                "cmp $1, %0\n\t"
+                "jb 13f\n\t"
+                /*
+                 * Move data for 1 byte.
+                 */
+                "movb (%1), %4b\n\t"
+                "movb %4b, (%2)\n\t"
+                "13:\n\t"
+                : "=&d" (d0), "=&S" (d1), "=&D" (d2), "=&a" (ret) ,
+                  "=r"(d3), "=r"(d4), "=r"(d5), "=r"(d6), "=&c" (d7)
+                :"0" (count),
+                 "1" (src),
+                 "2" (dest)
+                :"memory");
+
+                return ret;
+
 }
 EXPORT_SYMBOL(memmove);
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index a24c6cfdccc4..79b0b372d2d0 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -229,7 +229,16 @@ void vmalloc_sync_all(void)
 
                 spin_lock_irqsave(&pgd_lock, flags);
                 list_for_each_entry(page, &pgd_list, lru) {
-                        if (!vmalloc_sync_one(page_address(page), address))
+                        spinlock_t *pgt_lock;
+                        pmd_t *ret;
+
+                        pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
+
+                        spin_lock(pgt_lock);
+                        ret = vmalloc_sync_one(page_address(page), address);
+                        spin_unlock(pgt_lock);
+
+                        if (!ret)
                                 break;
                 }
                 spin_unlock_irqrestore(&pgd_lock, flags);
@@ -328,29 +337,7 @@ out:
 
 void vmalloc_sync_all(void)
 {
-        unsigned long address;
-
-        for (address = VMALLOC_START & PGDIR_MASK; address <= VMALLOC_END;
-             address += PGDIR_SIZE) {
-
-                const pgd_t *pgd_ref = pgd_offset_k(address);
-                unsigned long flags;
-                struct page *page;
-
-                if (pgd_none(*pgd_ref))
-                        continue;
-
-                spin_lock_irqsave(&pgd_lock, flags);
-                list_for_each_entry(page, &pgd_list, lru) {
-                        pgd_t *pgd;
-                        pgd = (pgd_t *)page_address(page) + pgd_index(address);
-                        if (pgd_none(*pgd))
-                                set_pgd(pgd, *pgd_ref);
-                        else
-                                BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
-                }
-                spin_unlock_irqrestore(&pgd_lock, flags);
-        }
+        sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END);
 }
 
 /*
@@ -898,8 +885,14 @@ spurious_fault(unsigned long error_code, unsigned long address)
         if (pmd_large(*pmd))
                 return spurious_fault_check(error_code, (pte_t *) pmd);
 
+        /*
+         * Note: don't use pte_present() here, since it returns true
+         * if the _PAGE_PROTNONE bit is set.  However, this aliases the
+         * _PAGE_GLOBAL bit, which for kernel pages give false positives
+         * when CONFIG_DEBUG_PAGEALLOC is used.
+         */
         pte = pte_offset_kernel(pmd, address);
-        if (!pte_present(*pte))
+        if (!(pte_flags(*pte) & _PAGE_PRESENT))
                 return 0;
 
         ret = spurious_fault_check(error_code, pte);
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index bca79091b9d6..558f2d332076 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -67,7 +67,7 @@ static __init void *alloc_low_page(void)
                 panic("alloc_low_page: ran out of memory");
 
         adr = __va(pfn * PAGE_SIZE);
-        memset(adr, 0, PAGE_SIZE);
+        clear_page(adr);
         return adr;
 }
 
@@ -558,7 +558,7 @@ char swsusp_pg_dir[PAGE_SIZE]
 
 static inline void save_pg_dir(void)
 {
-        memcpy(swsusp_pg_dir, swapper_pg_dir, PAGE_SIZE);
+        copy_page(swsusp_pg_dir, swapper_pg_dir);
 }
 #else /* !CONFIG_ACPI_SLEEP */
 static inline void save_pg_dir(void)
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 9a6674689a20..c55f900fbf89 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -98,6 +98,43 @@ static int __init nonx32_setup(char *str)
 __setup("noexec32=", nonx32_setup);
 
 /*
+ * When memory was added/removed make sure all the processes MM have
+ * suitable PGD entries in the local PGD level page.
+ */
+void sync_global_pgds(unsigned long start, unsigned long end)
+{
+        unsigned long address;
+
+        for (address = start; address <= end; address += PGDIR_SIZE) {
+                const pgd_t *pgd_ref = pgd_offset_k(address);
+                unsigned long flags;
+                struct page *page;
+
+                if (pgd_none(*pgd_ref))
+                        continue;
+
+                spin_lock_irqsave(&pgd_lock, flags);
+                list_for_each_entry(page, &pgd_list, lru) {
+                        pgd_t *pgd;
+                        spinlock_t *pgt_lock;
+
+                        pgd = (pgd_t *)page_address(page) + pgd_index(address);
+                        pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
+                        spin_lock(pgt_lock);
+
+                        if (pgd_none(*pgd))
+                                set_pgd(pgd, *pgd_ref);
+                        else
+                                BUG_ON(pgd_page_vaddr(*pgd)
+                                       != pgd_page_vaddr(*pgd_ref));
+
+                        spin_unlock(pgt_lock);
+                }
+                spin_unlock_irqrestore(&pgd_lock, flags);
+        }
+}
+
+/*
  * NOTE: This function is marked __ref because it calls __init function
  * (alloc_bootmem_pages). It's safe to do it ONLY when after_bootmem == 0.
  */
@@ -293,7 +330,7 @@ static __ref void *alloc_low_page(unsigned long *phys)
                 panic("alloc_low_page: ran out of memory");
 
         adr = early_memremap(pfn * PAGE_SIZE, PAGE_SIZE);
-        memset(adr, 0, PAGE_SIZE);
+        clear_page(adr);
         *phys  = pfn * PAGE_SIZE;
         return adr;
 }
@@ -534,11 +571,13 @@ kernel_physical_mapping_init(unsigned long start,
                              unsigned long end,
                              unsigned long page_size_mask)
 {
-
+        bool pgd_changed = false;
         unsigned long next, last_map_addr = end;
+        unsigned long addr;
 
         start = (unsigned long)__va(start);
         end = (unsigned long)__va(end);
+        addr = start;
 
         for (; start < end; start = next) {
                 pgd_t *pgd = pgd_offset_k(start);
@@ -563,7 +602,12 @@ kernel_physical_mapping_init(unsigned long start,
                 spin_lock(&init_mm.page_table_lock);
                 pgd_populate(&init_mm, pgd, __va(pud_phys));
                 spin_unlock(&init_mm.page_table_lock);
+                pgd_changed = true;
         }
+
+        if (pgd_changed)
+                sync_global_pgds(addr, end);
+
         __flush_tlb_all();
 
         return last_map_addr;
@@ -1003,6 +1047,7 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node)
                 }
 
         }
+        sync_global_pgds((unsigned long)start_page, end);
         return 0;
 }
 
diff --git a/arch/x86/mm/k8topology_64.c b/arch/x86/mm/k8topology_64.c
index 970ed579d4e4..52d54bfc1ebb 100644
--- a/arch/x86/mm/k8topology_64.c
+++ b/arch/x86/mm/k8topology_64.c
@@ -22,7 +22,7 @@
 #include <asm/numa.h>
 #include <asm/mpspec.h>
 #include <asm/apic.h>
-#include <asm/k8.h>
+#include <asm/amd_nb.h>
 
 static struct bootnode __initdata nodes[8];
 static nodemask_t __initdata nodes_parsed = NODE_MASK_NONE;
@@ -54,8 +54,8 @@ static __init int find_northbridge(void)
 static __init void early_get_boot_cpu_id(void)
 {
         /*
-         * need to get boot_cpu_id so can use that to create apicid_to_node
-         * in k8_scan_nodes()
+         * need to get the APIC ID of the BSP so can use that to
+         * create apicid_to_node in k8_scan_nodes()
          */
 #ifdef CONFIG_X86_MPPARSE
         /*
@@ -212,7 +212,7 @@ int __init k8_scan_nodes(void)
         bits = boot_cpu_data.x86_coreid_bits;
         cores = (1<<bits);
         apicid_base = 0;
-        /* need to get boot_cpu_id early for system with apicid lifting */
+        /* get the APIC ID of the BSP early for systems with apicid lifting */
         early_get_boot_cpu_id();
         if (boot_cpu_physical_apicid > 0) {
                 pr_info("BSP APIC ID: %02x\n", boot_cpu_physical_apicid);
diff --git a/arch/x86/mm/kmemcheck/opcode.c b/arch/x86/mm/kmemcheck/opcode.c
index 63c19e27aa6f..324aa3f07237 100644
--- a/arch/x86/mm/kmemcheck/opcode.c
+++ b/arch/x86/mm/kmemcheck/opcode.c
@@ -9,7 +9,7 @@ static bool opcode_is_prefix(uint8_t b)
                 b == 0xf0 || b == 0xf2 || b == 0xf3
                 /* Group 2 */
                 || b == 0x2e || b == 0x36 || b == 0x3e || b == 0x26
-                || b == 0x64 || b == 0x65 || b == 0x2e || b == 0x3e
+                || b == 0x64 || b == 0x65
                 /* Group 3 */
                 || b == 0x66
                 /* Group 4 */
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index a7bcc23ef96c..4962f1aeda6f 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -18,7 +18,7 @@
 #include <asm/dma.h>
 #include <asm/numa.h>
 #include <asm/acpi.h>
-#include <asm/k8.h>
+#include <asm/amd_nb.h>
 
 struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
 EXPORT_SYMBOL(node_data);
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 5c4ee422590e..8be8c7d7bc89 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -87,7 +87,19 @@ static inline void pgd_list_del(pgd_t *pgd)
 #define UNSHARED_PTRS_PER_PGD                           \
         (SHARED_KERNEL_PMD ? KERNEL_PGD_BOUNDARY : PTRS_PER_PGD)
 
-static void pgd_ctor(pgd_t *pgd)
+
+static void pgd_set_mm(pgd_t *pgd, struct mm_struct *mm)
+{
+        BUILD_BUG_ON(sizeof(virt_to_page(pgd)->index) < sizeof(mm));
+        virt_to_page(pgd)->index = (pgoff_t)mm;
+}
+
+struct mm_struct *pgd_page_get_mm(struct page *page)
+{
+        return (struct mm_struct *)page->index;
+}
+
+static void pgd_ctor(struct mm_struct *mm, pgd_t *pgd)
 {
         /* If the pgd points to a shared pagetable level (either the
            ptes in non-PAE, or shared PMD in PAE), then just copy the
@@ -98,15 +110,13 @@ static void pgd_ctor(pgd_t *pgd)
                 clone_pgd_range(pgd + KERNEL_PGD_BOUNDARY,
                                 swapper_pg_dir + KERNEL_PGD_BOUNDARY,
                                 KERNEL_PGD_PTRS);
-                paravirt_alloc_pmd_clone(__pa(pgd) >> PAGE_SHIFT,
-                                         __pa(swapper_pg_dir) >> PAGE_SHIFT,
-                                         KERNEL_PGD_BOUNDARY,
-                                         KERNEL_PGD_PTRS);
         }
 
         /* list required to sync kernel mapping updates */
-        if (!SHARED_KERNEL_PMD)
+        if (!SHARED_KERNEL_PMD) {
+                pgd_set_mm(pgd, mm);
                 pgd_list_add(pgd);
+        }
 }
 
 static void pgd_dtor(pgd_t *pgd)
@@ -272,7 +282,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
          */
         spin_lock_irqsave(&pgd_lock, flags);
 
-        pgd_ctor(pgd);
+        pgd_ctor(mm, pgd);
         pgd_prepopulate_pmd(mm, pgd, pmds);
 
         spin_unlock_irqrestore(&pgd_lock, flags);
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index c03f14ab6667..49358481c733 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -5,6 +5,7 @@
 #include <linux/smp.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
+#include <linux/cpu.h>
 
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
@@ -52,6 +53,8 @@ union smp_flush_state {
    want false sharing in the per cpu data segment. */
 static union smp_flush_state flush_state[NUM_INVALIDATE_TLB_VECTORS];
 
+static DEFINE_PER_CPU_READ_MOSTLY(int, tlb_vector_offset);
+
 /*
  * We cannot call mmdrop() because we are in interrupt context,
  * instead update mm->cpu_vm_mask.
@@ -173,7 +176,7 @@ static void flush_tlb_others_ipi(const struct cpumask *cpumask,
         union smp_flush_state *f;
 
         /* Caller has disabled preemption */
-        sender = smp_processor_id() % NUM_INVALIDATE_TLB_VECTORS;
+        sender = this_cpu_read(tlb_vector_offset);
         f = &flush_state[sender];
 
         /*
@@ -218,6 +221,47 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
         flush_tlb_others_ipi(cpumask, mm, va);
 }
 
+static void __cpuinit calculate_tlb_offset(void)
+{
+        int cpu, node, nr_node_vecs;
+        /*
+         * we are changing tlb_vector_offset for each CPU in runtime, but this
+         * will not cause inconsistency, as the write is atomic under X86. we
+         * might see more lock contentions in a short time, but after all CPU's
+         * tlb_vector_offset are changed, everything should go normal
+         *
+         * Note: if NUM_INVALIDATE_TLB_VECTORS % nr_online_nodes !=0, we might
+         * waste some vectors.
+         **/
+        if (nr_online_nodes > NUM_INVALIDATE_TLB_VECTORS)
+                nr_node_vecs = 1;
+        else
+                nr_node_vecs = NUM_INVALIDATE_TLB_VECTORS/nr_online_nodes;
+
+        for_each_online_node(node) {
+                int node_offset = (node % NUM_INVALIDATE_TLB_VECTORS) *
+                        nr_node_vecs;
+                int cpu_offset = 0;
+                for_each_cpu(cpu, cpumask_of_node(node)) {
+                        per_cpu(tlb_vector_offset, cpu) = node_offset +
+                                cpu_offset;
+                        cpu_offset++;
+                        cpu_offset = cpu_offset % nr_node_vecs;
+                }
+        }
+}
+
+static int tlb_cpuhp_notify(struct notifier_block *n,
+                unsigned long action, void *hcpu)
+{
+        switch (action & 0xf) {
+        case CPU_ONLINE:
+        case CPU_DEAD:
+                calculate_tlb_offset();
+        }
+        return NOTIFY_OK;
+}
+
 static int __cpuinit init_smp_flush(void)
 {
         int i;
@@ -225,6 +269,8 @@ static int __cpuinit init_smp_flush(void)
         for (i = 0; i < ARRAY_SIZE(flush_state); i++)
                 raw_spin_lock_init(&flush_state[i].tlbstate_lock);
 
+        calculate_tlb_offset();
+        hotcpu_notifier(tlb_cpuhp_notify, 0);
         return 0;
 }
 core_initcall(init_smp_flush);
diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c
index b67a6b5aa8d4..42fb46f83883 100644
--- a/arch/x86/oprofile/op_model_amd.c
+++ b/arch/x86/oprofile/op_model_amd.c
@@ -64,15 +64,22 @@ static u64 ibs_op_ctl;
  * IBS cpuid feature detection
  */
 
-#define IBS_CPUID_FEATURES      0x8000001b
+#define IBS_CPUID_FEATURES              0x8000001b
 
 /*
  * Same bit mask as for IBS cpuid feature flags (Fn8000_001B_EAX), but
  * bit 0 is used to indicate the existence of IBS.
  */
-#define IBS_CAPS_AVAIL                  (1LL<<0)
-#define IBS_CAPS_RDWROPCNT              (1LL<<3)
-#define IBS_CAPS_OPCNT                  (1LL<<4)
+#define IBS_CAPS_AVAIL                  (1U<<0)
+#define IBS_CAPS_RDWROPCNT              (1U<<3)
+#define IBS_CAPS_OPCNT                  (1U<<4)
+
+/*
+ * IBS APIC setup
+ */
+#define IBSCTL                          0x1cc
+#define IBSCTL_LVT_OFFSET_VALID         (1ULL<<8)
+#define IBSCTL_LVT_OFFSET_MASK          0x0F
 
 /*
  * IBS randomization macros
@@ -266,6 +273,74 @@ static void op_amd_stop_ibs(void)
                 wrmsrl(MSR_AMD64_IBSOPCTL, 0);
 }
 
+static inline int eilvt_is_available(int offset)
+{
+        /* check if we may assign a vector */
+        return !setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_NMI, 1);
+}
+
+static inline int ibs_eilvt_valid(void)
+{
+        u64 val;
+        int offset;
+
+        rdmsrl(MSR_AMD64_IBSCTL, val);
+        if (!(val & IBSCTL_LVT_OFFSET_VALID)) {
+                pr_err(FW_BUG "cpu %d, invalid IBS "
+                       "interrupt offset %d (MSR%08X=0x%016llx)",
+                       smp_processor_id(), offset,
+                       MSR_AMD64_IBSCTL, val);
+                return 0;
+        }
+
+        offset = val & IBSCTL_LVT_OFFSET_MASK;
+
+        if (eilvt_is_available(offset))
+                return !0;
+
+        pr_err(FW_BUG "cpu %d, IBS interrupt offset %d "
+               "not available (MSR%08X=0x%016llx)",
+               smp_processor_id(), offset,
+               MSR_AMD64_IBSCTL, val);
+
+        return 0;
+}
+
+static inline int get_ibs_offset(void)
+{
+        u64 val;
+
+        rdmsrl(MSR_AMD64_IBSCTL, val);
+        if (!(val & IBSCTL_LVT_OFFSET_VALID))
+                return -EINVAL;
+
+        return val & IBSCTL_LVT_OFFSET_MASK;
+}
+
+static void setup_APIC_ibs(void)
+{
+        int offset;
+
+        offset = get_ibs_offset();
+        if (offset < 0)
+                goto failed;
+
+        if (!setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_NMI, 0))
+                return;
+failed:
+        pr_warn("oprofile: IBS APIC setup failed on cpu #%d\n",
+                smp_processor_id());
+}
+
+static void clear_APIC_ibs(void)
+{
+        int offset;
+
+        offset = get_ibs_offset();
+        if (offset >= 0)
+                setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_FIX, 1);
+}
+
 #ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX
 
 static void op_mux_switch_ctrl(struct op_x86_model_spec const *model,
@@ -376,13 +451,13 @@ static void op_amd_setup_ctrs(struct op_x86_model_spec const *model,
         }
 
         if (ibs_caps)
-                setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_NMI, 0);
+                setup_APIC_ibs();
 }
 
 static void op_amd_cpu_shutdown(void)
 {
         if (ibs_caps)
-                setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_FIX, 1);
+                clear_APIC_ibs();
 }
 
 static int op_amd_check_ctrs(struct pt_regs * const regs,
@@ -445,16 +520,11 @@ static void op_amd_stop(struct op_msrs const * const msrs)
         op_amd_stop_ibs();
 }
 
-static int __init_ibs_nmi(void)
+static int setup_ibs_ctl(int ibs_eilvt_off)
 {
-#define IBSCTL_LVTOFFSETVAL             (1 << 8)
-#define IBSCTL                          0x1cc
         struct pci_dev *cpu_cfg;
         int nodes;
         u32 value = 0;
-        u8 ibs_eilvt_off;
-
-        ibs_eilvt_off = setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_FIX, 1);
 
         nodes = 0;
         cpu_cfg = NULL;
@@ -466,21 +536,60 @@ static int __init_ibs_nmi(void)
                         break;
                 ++nodes;
                 pci_write_config_dword(cpu_cfg, IBSCTL, ibs_eilvt_off
-                                       | IBSCTL_LVTOFFSETVAL);
+                                       | IBSCTL_LVT_OFFSET_VALID);
                 pci_read_config_dword(cpu_cfg, IBSCTL, &value);
-                if (value != (ibs_eilvt_off | IBSCTL_LVTOFFSETVAL)) {
+                if (value != (ibs_eilvt_off | IBSCTL_LVT_OFFSET_VALID)) {
                         pci_dev_put(cpu_cfg);
                         printk(KERN_DEBUG "Failed to setup IBS LVT offset, "
-                                "IBSCTL = 0x%08x", value);
-                        return 1;
+                               "IBSCTL = 0x%08x\n", value);
+                        return -EINVAL;
                 }
         } while (1);
 
         if (!nodes) {
-                printk(KERN_DEBUG "No CPU node configured for IBS");
-                return 1;
+                printk(KERN_DEBUG "No CPU node configured for IBS\n");
+                return -ENODEV;
+        }
+
+        return 0;
+}
+
+static int force_ibs_eilvt_setup(void)
+{
+        int i;
+        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;
+                return 0;
         }
 
+        printk(KERN_DEBUG "No EILVT entry available\n");
+
+        return -EBUSY;
+}
+
+static int __init_ibs_nmi(void)
+{
+        int ret;
+
+        if (ibs_eilvt_valid())
+                return 0;
+
+        ret = force_ibs_eilvt_setup();
+        if (ret)
+                return ret;
+
+        if (!ibs_eilvt_valid())
+                return -EFAULT;
+
+        pr_err(FW_BUG "workaround enabled for IBS LVT offset\n");
+
         return 0;
 }
 
diff --git a/arch/x86/pci/olpc.c b/arch/x86/pci/olpc.c
index b34815408f58..13700ec8e2e4 100644
--- a/arch/x86/pci/olpc.c
+++ b/arch/x86/pci/olpc.c
@@ -304,7 +304,7 @@ static struct pci_raw_ops pci_olpc_conf = {
 
 int __init pci_olpc_init(void)
 {
-        printk(KERN_INFO "PCI: Using configuration type OLPC\n");
+        printk(KERN_INFO "PCI: Using configuration type OLPC XO-1\n");
         raw_pci_ops = &pci_olpc_conf;
         is_lx = is_geode_lx();
         return 0;
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 42086ac406af..b2363fcbcd0f 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1969,7 +1969,6 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = {
         .alloc_pte = xen_alloc_pte_init,
         .release_pte = xen_release_pte_init,
         .alloc_pmd = xen_alloc_pmd_init,
-        .alloc_pmd_clone = paravirt_nop,
         .release_pmd = xen_release_pmd_init,
 
 #ifdef CONFIG_X86_64
diff --git a/arch/xtensa/kernel/irq.c b/arch/xtensa/kernel/irq.c
index c64a5d387de5..87508886cbbd 100644
--- a/arch/xtensa/kernel/irq.c
+++ b/arch/xtensa/kernel/irq.c
@@ -92,7 +92,7 @@ int show_interrupts(struct seq_file *p, void *v)
                 for_each_online_cpu(j)
                         seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #endif
-                seq_printf(p, " %14s", irq_desc[i].chip->typename);
+                seq_printf(p, " %14s", irq_desc[i].chip->name);
                 seq_printf(p, "  %s", action->name);
 
                 for (action=action->next; action; action = action->next)
diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c
index 6b115f6c4313..6afceb3d4034 100644
--- a/drivers/acpi/acpi_pad.c
+++ b/drivers/acpi/acpi_pad.c
@@ -30,18 +30,13 @@
 #include <linux/slab.h>
 #include <acpi/acpi_bus.h>
 #include <acpi/acpi_drivers.h>
+#include <asm/mwait.h>
 
 #define ACPI_PROCESSOR_AGGREGATOR_CLASS "acpi_pad"
 #define ACPI_PROCESSOR_AGGREGATOR_DEVICE_NAME "Processor Aggregator"
 #define ACPI_PROCESSOR_AGGREGATOR_NOTIFY 0x80
 static DEFINE_MUTEX(isolated_cpus_lock);
 
-#define MWAIT_SUBSTATE_MASK     (0xf)
-#define MWAIT_CSTATE_MASK       (0xf)
-#define MWAIT_SUBSTATE_SIZE     (4)
-#define CPUID_MWAIT_LEAF (5)
-#define CPUID5_ECX_EXTENSIONS_SUPPORTED (0x1)
-#define CPUID5_ECX_INTERRUPT_BREAK      (0x2)
 static unsigned long power_saving_mwait_eax;
 
 static unsigned char tsc_detected_unstable;
diff --git a/drivers/base/topology.c b/drivers/base/topology.c
index 9fc630ce1ddb..f6f37a05a0c3 100644
--- a/drivers/base/topology.c
+++ b/drivers/base/topology.c
@@ -45,7 +45,8 @@ static ssize_t show_##name(struct sys_device *dev,		\
         return sprintf(buf, "%d\n", topology_##name(cpu));      \
 }
 
-#if defined(topology_thread_cpumask) || defined(topology_core_cpumask)
+#if defined(topology_thread_cpumask) || defined(topology_core_cpumask) || \
+    defined(topology_book_cpumask)
 static ssize_t show_cpumap(int type, const struct cpumask *mask, char *buf)
 {
         ptrdiff_t len = PTR_ALIGN(buf + PAGE_SIZE - 1, PAGE_SIZE) - buf;
@@ -114,6 +115,14 @@ define_siblings_show_func(core_cpumask);
 define_one_ro_named(core_siblings, show_core_cpumask);
 define_one_ro_named(core_siblings_list, show_core_cpumask_list);
 
+#ifdef CONFIG_SCHED_BOOK
+define_id_show_func(book_id);
+define_one_ro(book_id);
+define_siblings_show_func(book_cpumask);
+define_one_ro_named(book_siblings, show_book_cpumask);
+define_one_ro_named(book_siblings_list, show_book_cpumask_list);
+#endif
+
 static struct attribute *default_attrs[] = {
         &attr_physical_package_id.attr,
         &attr_core_id.attr,
@@ -121,6 +130,11 @@ static struct attribute *default_attrs[] = {
         &attr_thread_siblings_list.attr,
         &attr_core_siblings.attr,
         &attr_core_siblings_list.attr,
+#ifdef CONFIG_SCHED_BOOK
+        &attr_book_id.attr,
+        &attr_book_siblings.attr,
+        &attr_book_siblings_list.attr,
+#endif
         NULL
 };
 
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index de277689da61..4b9359a6f6ca 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -488,4 +488,21 @@ config BLK_DEV_HD
 
           If unsure, say N.
 
+config BLK_DEV_RBD
+        tristate "Rados block device (RBD)"
+        depends on INET && EXPERIMENTAL && BLOCK
+        select CEPH_LIB
+        select LIBCRC32C
+        select CRYPTO_AES
+        select CRYPTO
+        default n
+        help
+          Say Y here if you want include the Rados block device, which stripes
+          a block device over objects stored in the Ceph distributed object
+          store.
+
+          More information at http://ceph.newdream.net/.
+
+          If unsure, say N.
+
 endif # BLK_DEV
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index aff5ac925c34..d7f463d6312d 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -37,5 +37,6 @@ obj-$(CONFIG_BLK_DEV_HD)	+= hd.o
 
 obj-$(CONFIG_XEN_BLKDEV_FRONTEND)       += xen-blkfront.o
 obj-$(CONFIG_BLK_DEV_DRBD)     += drbd/
+obj-$(CONFIG_BLK_DEV_RBD)     += rbd.o
 
 swim_mod-objs   := swim.o swim_asm.o
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
new file mode 100644
index 000000000000..6ec9d53806c5
--- /dev/null
+++ b/drivers/block/rbd.c
@@ -0,0 +1,1841 @@
+/*
+   rbd.c -- Export ceph rados objects as a Linux block device
+
+
+   based on drivers/block/osdblk.c:
+
+   Copyright 2009 Red Hat, Inc.
+
+   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.
+
+   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; see the file COPYING.  If not, write to
+   the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
+
+
+
+   Instructions for use
+   --------------------
+
+   1) Map a Linux block device to an existing rbd image.
+
+      Usage: <mon ip addr> <options> <pool name> <rbd image name> [snap name]
+
+      $ echo "192.168.0.1 name=admin rbd foo" > /sys/class/rbd/add
+
+      The snapshot name can be "-" or omitted to map the image read/write.
+
+   2) List all active blkdev<->object mappings.
+
+      In this example, we have performed step #1 twice, creating two blkdevs,
+      mapped to two separate rados objects in the rados rbd pool
+
+      $ cat /sys/class/rbd/list
+      #id     major   client_name     pool    name    snap    KB
+      0       254     client4143      rbd     foo     -      1024000
+
+      The columns, in order, are:
+      - blkdev unique id
+      - blkdev assigned major
+      - rados client id
+      - rados pool name
+      - rados block device name
+      - mapped snapshot ("-" if none)
+      - device size in KB
+
+
+   3) Create a snapshot.
+
+      Usage: <blkdev id> <snapname>
+
+      $ echo "0 mysnap" > /sys/class/rbd/snap_create
+
+
+   4) Listing a snapshot.
+
+      $ cat /sys/class/rbd/snaps_list
+      #id     snap    KB
+      0       -       1024000 (*)
+      0       foo     1024000
+
+      The columns, in order, are:
+      - blkdev unique id
+      - snapshot name, '-' means none (active read/write version)
+      - size of device at time of snapshot
+      - the (*) indicates this is the active version
+
+   5) Rollback to snapshot.
+
+      Usage: <blkdev id> <snapname>
+
+      $ echo "0 mysnap" > /sys/class/rbd/snap_rollback
+
+
+   6) Mapping an image using snapshot.
+
+      A snapshot mapping is read-only. This is being done by passing
+      snap=<snapname> to the options when adding a device.
+
+      $ echo "192.168.0.1 name=admin,snap=mysnap rbd foo" > /sys/class/rbd/add
+
+
+   7) Remove an active blkdev<->rbd image mapping.
+
+      In this example, we remove the mapping with blkdev unique id 1.
+
+      $ echo 1 > /sys/class/rbd/remove
+
+
+   NOTE:  The actual creation and deletion of rados objects is outside the scope
+   of this driver.
+
+ */
+
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/osd_client.h>
+#include <linux/ceph/mon_client.h>
+#include <linux/ceph/decode.h>
+
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/blkdev.h>
+
+#include "rbd_types.h"
+
+#define DRV_NAME "rbd"
+#define DRV_NAME_LONG "rbd (rados block device)"
+
+#define RBD_MINORS_PER_MAJOR    256             /* max minors per blkdev */
+
+#define RBD_MAX_MD_NAME_LEN     (96 + sizeof(RBD_SUFFIX))
+#define RBD_MAX_POOL_NAME_LEN   64
+#define RBD_MAX_SNAP_NAME_LEN   32
+#define RBD_MAX_OPT_LEN         1024
+
+#define RBD_SNAP_HEAD_NAME      "-"
+
+#define DEV_NAME_LEN            32
+
+/*
+ * block device image metadata (in-memory version)
+ */
+struct rbd_image_header {
+        u64 image_size;
+        char block_name[32];
+        __u8 obj_order;
+        __u8 crypt_type;
+        __u8 comp_type;
+        struct rw_semaphore snap_rwsem;
+        struct ceph_snap_context *snapc;
+        size_t snap_names_len;
+        u64 snap_seq;
+        u32 total_snaps;
+
+        char *snap_names;
+        u64 *snap_sizes;
+};
+
+/*
+ * an instance of the client.  multiple devices may share a client.
+ */
+struct rbd_client {
+        struct ceph_client      *client;
+        struct kref             kref;
+        struct list_head        node;
+};
+
+/*
+ * a single io request
+ */
+struct rbd_request {
+        struct request          *rq;            /* blk layer request */
+        struct bio              *bio;           /* cloned bio */
+        struct page             **pages;        /* list of used pages */
+        u64                     len;
+};
+
+/*
+ * a single device
+ */
+struct rbd_device {
+        int                     id;             /* blkdev unique id */
+
+        int                     major;          /* blkdev assigned major */
+        struct gendisk          *disk;          /* blkdev's gendisk and rq */
+        struct request_queue    *q;
+
+        struct ceph_client      *client;
+        struct rbd_client       *rbd_client;
+
+        char                    name[DEV_NAME_LEN]; /* blkdev name, e.g. rbd3 */
+
+        spinlock_t              lock;           /* queue lock */
+
+        struct rbd_image_header header;
+        char                    obj[RBD_MAX_OBJ_NAME_LEN]; /* rbd image name */
+        int                     obj_len;
+        char                    obj_md_name[RBD_MAX_MD_NAME_LEN]; /* hdr nm. */
+        char                    pool_name[RBD_MAX_POOL_NAME_LEN];
+        int                     poolid;
+
+        char                    snap_name[RBD_MAX_SNAP_NAME_LEN];
+        u32 cur_snap;   /* index+1 of current snapshot within snap context
+                           0 - for the head */
+        int read_only;
+
+        struct list_head        node;
+};
+
+static spinlock_t node_lock;      /* protects client get/put */
+
+static struct class *class_rbd;   /* /sys/class/rbd */
+static DEFINE_MUTEX(ctl_mutex);   /* Serialize open/close/setup/teardown */
+static LIST_HEAD(rbd_dev_list);    /* devices */
+static LIST_HEAD(rbd_client_list);      /* clients */
+
+
+static int rbd_open(struct block_device *bdev, fmode_t mode)
+{
+        struct gendisk *disk = bdev->bd_disk;
+        struct rbd_device *rbd_dev = disk->private_data;
+
+        set_device_ro(bdev, rbd_dev->read_only);
+
+        if ((mode & FMODE_WRITE) && rbd_dev->read_only)
+                return -EROFS;
+
+        return 0;
+}
+
+static const struct block_device_operations rbd_bd_ops = {
+        .owner                  = THIS_MODULE,
+        .open                   = rbd_open,
+};
+
+/*
+ * Initialize an rbd client instance.
+ * We own *opt.
+ */
+static struct rbd_client *rbd_client_create(struct ceph_options *opt)
+{
+        struct rbd_client *rbdc;
+        int ret = -ENOMEM;
+
+        dout("rbd_client_create\n");
+        rbdc = kmalloc(sizeof(struct rbd_client), GFP_KERNEL);
+        if (!rbdc)
+                goto out_opt;
+
+        kref_init(&rbdc->kref);
+        INIT_LIST_HEAD(&rbdc->node);
+
+        rbdc->client = ceph_create_client(opt, rbdc);
+        if (IS_ERR(rbdc->client))
+                goto out_rbdc;
+        opt = NULL; /* Now rbdc->client is responsible for opt */
+
+        ret = ceph_open_session(rbdc->client);
+        if (ret < 0)
+                goto out_err;
+
+        spin_lock(&node_lock);
+        list_add_tail(&rbdc->node, &rbd_client_list);
+        spin_unlock(&node_lock);
+
+        dout("rbd_client_create created %p\n", rbdc);
+        return rbdc;
+
+out_err:
+        ceph_destroy_client(rbdc->client);
+out_rbdc:
+        kfree(rbdc);
+out_opt:
+        if (opt)
+                ceph_destroy_options(opt);
+        return ERR_PTR(ret);
+}
+
+/*
+ * Find a ceph client with specific addr and configuration.
+ */
+static struct rbd_client *__rbd_client_find(struct ceph_options *opt)
+{
+        struct rbd_client *client_node;
+
+        if (opt->flags & CEPH_OPT_NOSHARE)
+                return NULL;
+
+        list_for_each_entry(client_node, &rbd_client_list, node)
+                if (ceph_compare_options(opt, client_node->client) == 0)
+                        return client_node;
+        return NULL;
+}
+
+/*
+ * Get a ceph client with specific addr and configuration, if one does
+ * not exist create it.
+ */
+static int rbd_get_client(struct rbd_device *rbd_dev, const char *mon_addr,
+                          char *options)
+{
+        struct rbd_client *rbdc;
+        struct ceph_options *opt;
+        int ret;
+
+        ret = ceph_parse_options(&opt, options, mon_addr,
+                                 mon_addr + strlen(mon_addr), NULL, NULL);
+        if (ret < 0)
+                return ret;
+
+        spin_lock(&node_lock);
+        rbdc = __rbd_client_find(opt);
+        if (rbdc) {
+                ceph_destroy_options(opt);
+
+                /* using an existing client */
+                kref_get(&rbdc->kref);
+                rbd_dev->rbd_client = rbdc;
+                rbd_dev->client = rbdc->client;
+                spin_unlock(&node_lock);
+                return 0;
+        }
+        spin_unlock(&node_lock);
+
+        rbdc = rbd_client_create(opt);
+        if (IS_ERR(rbdc))
+                return PTR_ERR(rbdc);
+
+        rbd_dev->rbd_client = rbdc;
+        rbd_dev->client = rbdc->client;
+        return 0;
+}
+
+/*
+ * Destroy ceph client
+ */
+static void rbd_client_release(struct kref *kref)
+{
+        struct rbd_client *rbdc = container_of(kref, struct rbd_client, kref);
+
+        dout("rbd_release_client %p\n", rbdc);
+        spin_lock(&node_lock);
+        list_del(&rbdc->node);
+        spin_unlock(&node_lock);
+
+        ceph_destroy_client(rbdc->client);
+        kfree(rbdc);
+}
+
+/*
+ * Drop reference to ceph client node. If it's not referenced anymore, release
+ * it.
+ */
+static void rbd_put_client(struct rbd_device *rbd_dev)
+{
+        kref_put(&rbd_dev->rbd_client->kref, rbd_client_release);
+        rbd_dev->rbd_client = NULL;
+        rbd_dev->client = NULL;
+}
+
+
+/*
+ * Create a new header structure, translate header format from the on-disk
+ * header.
+ */
+static int rbd_header_from_disk(struct rbd_image_header *header,
+                                 struct rbd_image_header_ondisk *ondisk,
+                                 int allocated_snaps,
+                                 gfp_t gfp_flags)
+{
+        int i;
+        u32 snap_count = le32_to_cpu(ondisk->snap_count);
+        int ret = -ENOMEM;
+
+        init_rwsem(&header->snap_rwsem);
+
+        header->snap_names_len = le64_to_cpu(ondisk->snap_names_len);
+        header->snapc = kmalloc(sizeof(struct ceph_snap_context) +
+                                snap_count *
+                                 sizeof(struct rbd_image_snap_ondisk),
+                                gfp_flags);
+        if (!header->snapc)
+                return -ENOMEM;
+        if (snap_count) {
+                header->snap_names = kmalloc(header->snap_names_len,
+                                             GFP_KERNEL);
+                if (!header->snap_names)
+                        goto err_snapc;
+                header->snap_sizes = kmalloc(snap_count * sizeof(u64),
+                                             GFP_KERNEL);
+                if (!header->snap_sizes)
+                        goto err_names;
+        } else {
+                header->snap_names = NULL;
+                header->snap_sizes = NULL;
+        }
+        memcpy(header->block_name, ondisk->block_name,
+               sizeof(ondisk->block_name));
+
+        header->image_size = le64_to_cpu(ondisk->image_size);
+        header->obj_order = ondisk->options.order;
+        header->crypt_type = ondisk->options.crypt_type;
+        header->comp_type = ondisk->options.comp_type;
+
+        atomic_set(&header->snapc->nref, 1);
+        header->snap_seq = le64_to_cpu(ondisk->snap_seq);
+        header->snapc->num_snaps = snap_count;
+        header->total_snaps = snap_count;
+
+        if (snap_count &&
+            allocated_snaps == snap_count) {
+                for (i = 0; i < snap_count; i++) {
+                        header->snapc->snaps[i] =
+                                le64_to_cpu(ondisk->snaps[i].id);
+                        header->snap_sizes[i] =
+                                le64_to_cpu(ondisk->snaps[i].image_size);
+                }
+
+                /* copy snapshot names */
+                memcpy(header->snap_names, &ondisk->snaps[i],
+                        header->snap_names_len);
+        }
+
+        return 0;
+
+err_names:
+        kfree(header->snap_names);
+err_snapc:
+        kfree(header->snapc);
+        return ret;
+}
+
+static int snap_index(struct rbd_image_header *header, int snap_num)
+{
+        return header->total_snaps - snap_num;
+}
+
+static u64 cur_snap_id(struct rbd_device *rbd_dev)
+{
+        struct rbd_image_header *header = &rbd_dev->header;
+
+        if (!rbd_dev->cur_snap)
+                return 0;
+
+        return header->snapc->snaps[snap_index(header, rbd_dev->cur_snap)];
+}
+
+static int snap_by_name(struct rbd_image_header *header, const char *snap_name,
+                        u64 *seq, u64 *size)
+{
+        int i;
+        char *p = header->snap_names;
+
+        for (i = 0; i < header->total_snaps; i++, p += strlen(p) + 1) {
+                if (strcmp(snap_name, p) == 0)
+                        break;
+        }
+        if (i == header->total_snaps)
+                return -ENOENT;
+        if (seq)
+                *seq = header->snapc->snaps[i];
+
+        if (size)
+                *size = header->snap_sizes[i];
+
+        return i;
+}
+
+static int rbd_header_set_snap(struct rbd_device *dev,
+                               const char *snap_name,
+                               u64 *size)
+{
+        struct rbd_image_header *header = &dev->header;
+        struct ceph_snap_context *snapc = header->snapc;
+        int ret = -ENOENT;
+
+        down_write(&header->snap_rwsem);
+
+        if (!snap_name ||
+            !*snap_name ||
+            strcmp(snap_name, "-") == 0 ||
+            strcmp(snap_name, RBD_SNAP_HEAD_NAME) == 0) {
+                if (header->total_snaps)
+                        snapc->seq = header->snap_seq;
+                else
+                        snapc->seq = 0;
+                dev->cur_snap = 0;
+                dev->read_only = 0;
+                if (size)
+                        *size = header->image_size;
+        } else {
+                ret = snap_by_name(header, snap_name, &snapc->seq, size);
+                if (ret < 0)
+                        goto done;
+
+                dev->cur_snap = header->total_snaps - ret;
+                dev->read_only = 1;
+        }
+
+        ret = 0;
+done:
+        up_write(&header->snap_rwsem);
+        return ret;
+}
+
+static void rbd_header_free(struct rbd_image_header *header)
+{
+        kfree(header->snapc);
+        kfree(header->snap_names);
+        kfree(header->snap_sizes);
+}
+
+/*
+ * get the actual striped segment name, offset and length
+ */
+static u64 rbd_get_segment(struct rbd_image_header *header,
+                           const char *block_name,
+                           u64 ofs, u64 len,
+                           char *seg_name, u64 *segofs)
+{
+        u64 seg = ofs >> header->obj_order;
+
+        if (seg_name)
+                snprintf(seg_name, RBD_MAX_SEG_NAME_LEN,
+                         "%s.%012llx", block_name, seg);
+
+        ofs = ofs & ((1 << header->obj_order) - 1);
+        len = min_t(u64, len, (1 << header->obj_order) - ofs);
+
+        if (segofs)
+                *segofs = ofs;
+
+        return len;
+}
+
+/*
+ * bio helpers
+ */
+
+static void bio_chain_put(struct bio *chain)
+{
+        struct bio *tmp;
+
+        while (chain) {
+                tmp = chain;
+                chain = chain->bi_next;
+                bio_put(tmp);
+        }
+}
+
+/*
+ * zeros a bio chain, starting at specific offset
+ */
+static void zero_bio_chain(struct bio *chain, int start_ofs)
+{
+        struct bio_vec *bv;
+        unsigned long flags;
+        void *buf;
+        int i;
+        int pos = 0;
+
+        while (chain) {
+                bio_for_each_segment(bv, chain, i) {
+                        if (pos + bv->bv_len > start_ofs) {
+                                int remainder = max(start_ofs - pos, 0);
+                                buf = bvec_kmap_irq(bv, &flags);
+                                memset(buf + remainder, 0,
+                                       bv->bv_len - remainder);
+                                bvec_kunmap_irq(buf, &flags);
+                        }
+                        pos += bv->bv_len;
+                }
+
+                chain = chain->bi_next;
+        }
+}
+
+/*
+ * bio_chain_clone - clone a chain of bios up to a certain length.
+ * might return a bio_pair that will need to be released.
+ */
+static struct bio *bio_chain_clone(struct bio **old, struct bio **next,
+                                   struct bio_pair **bp,
+                                   int len, gfp_t gfpmask)
+{
+        struct bio *tmp, *old_chain = *old, *new_chain = NULL, *tail = NULL;
+        int total = 0;
+
+        if (*bp) {
+                bio_pair_release(*bp);
+                *bp = NULL;
+        }
+
+        while (old_chain && (total < len)) {
+                tmp = bio_kmalloc(gfpmask, old_chain->bi_max_vecs);
+                if (!tmp)
+                        goto err_out;
+
+                if (total + old_chain->bi_size > len) {
+                        struct bio_pair *bp;
+
+                        /*
+                         * this split can only happen with a single paged bio,
+                         * split_bio will BUG_ON if this is not the case
+                         */
+                        dout("bio_chain_clone split! total=%d remaining=%d"
+                             "bi_size=%d\n",
+                             (int)total, (int)len-total,
+                             (int)old_chain->bi_size);
+
+                        /* split the bio. We'll release it either in the next
+                           call, or it will have to be released outside */
+                        bp = bio_split(old_chain, (len - total) / 512ULL);
+                        if (!bp)
+                                goto err_out;
+
+                        __bio_clone(tmp, &bp->bio1);
+
+                        *next = &bp->bio2;
+                } else {
+                        __bio_clone(tmp, old_chain);
+                        *next = old_chain->bi_next;
+                }
+
+                tmp->bi_bdev = NULL;
+                gfpmask &= ~__GFP_WAIT;
+                tmp->bi_next = NULL;
+
+                if (!new_chain) {
+                        new_chain = tail = tmp;
+                } else {
+                        tail->bi_next = tmp;
+                        tail = tmp;
+                }
+                old_chain = old_chain->bi_next;
+
+                total += tmp->bi_size;
+        }
+
+        BUG_ON(total < len);
+
+        if (tail)
+                tail->bi_next = NULL;
+
+        *old = old_chain;
+
+        return new_chain;
+
+err_out:
+        dout("bio_chain_clone with err\n");
+        bio_chain_put(new_chain);
+        return NULL;
+}
+
+/*
+ * helpers for osd request op vectors.
+ */
+static int rbd_create_rw_ops(struct ceph_osd_req_op **ops,
+                            int num_ops,
+                            int opcode,
+                            u32 payload_len)
+{
+        *ops = kzalloc(sizeof(struct ceph_osd_req_op) * (num_ops + 1),
+                       GFP_NOIO);
+        if (!*ops)
+                return -ENOMEM;
+        (*ops)[0].op = opcode;
+        /*
+         * op extent offset and length will be set later on
+         * in calc_raw_layout()
+         */
+        (*ops)[0].payload_len = payload_len;
+        return 0;
+}
+
+static void rbd_destroy_ops(struct ceph_osd_req_op *ops)
+{
+        kfree(ops);
+}
+
+/*
+ * Send ceph osd request
+ */
+static int rbd_do_request(struct request *rq,
+                          struct rbd_device *dev,
+                          struct ceph_snap_context *snapc,
+                          u64 snapid,
+                          const char *obj, u64 ofs, u64 len,
+                          struct bio *bio,
+                          struct page **pages,
+                          int num_pages,
+                          int flags,
+                          struct ceph_osd_req_op *ops,
+                          int num_reply,
+                          void (*rbd_cb)(struct ceph_osd_request *req,
+                                         struct ceph_msg *msg))
+{
+        struct ceph_osd_request *req;
+        struct ceph_file_layout *layout;
+        int ret;
+        u64 bno;
+        struct timespec mtime = CURRENT_TIME;
+        struct rbd_request *req_data;
+        struct ceph_osd_request_head *reqhead;
+        struct rbd_image_header *header = &dev->header;
+
+        ret = -ENOMEM;
+        req_data = kzalloc(sizeof(*req_data), GFP_NOIO);
+        if (!req_data)
+                goto done;
+
+        dout("rbd_do_request len=%lld ofs=%lld\n", len, ofs);
+
+        down_read(&header->snap_rwsem);
+
+        req = ceph_osdc_alloc_request(&dev->client->osdc, flags,
+                                      snapc,
+                                      ops,
+                                      false,
+                                      GFP_NOIO, pages, bio);
+        if (IS_ERR(req)) {
+                up_read(&header->snap_rwsem);
+                ret = PTR_ERR(req);
+                goto done_pages;
+        }
+
+        req->r_callback = rbd_cb;
+
+        req_data->rq = rq;
+        req_data->bio = bio;
+        req_data->pages = pages;
+        req_data->len = len;
+
+        req->r_priv = req_data;
+
+        reqhead = req->r_request->front.iov_base;
+        reqhead->snapid = cpu_to_le64(CEPH_NOSNAP);
+
+        strncpy(req->r_oid, obj, sizeof(req->r_oid));
+        req->r_oid_len = strlen(req->r_oid);
+
+        layout = &req->r_file_layout;
+        memset(layout, 0, sizeof(*layout));
+        layout->fl_stripe_unit = cpu_to_le32(1 << RBD_MAX_OBJ_ORDER);
+        layout->fl_stripe_count = cpu_to_le32(1);
+        layout->fl_object_size = cpu_to_le32(1 << RBD_MAX_OBJ_ORDER);
+        layout->fl_pg_preferred = cpu_to_le32(-1);
+        layout->fl_pg_pool = cpu_to_le32(dev->poolid);
+        ceph_calc_raw_layout(&dev->client->osdc, layout, snapid,
+                             ofs, &len, &bno, req, ops);
+
+        ceph_osdc_build_request(req, ofs, &len,
+                                ops,
+                                snapc,
+                                &mtime,
+                                req->r_oid, req->r_oid_len);
+        up_read(&header->snap_rwsem);
+
+        ret = ceph_osdc_start_request(&dev->client->osdc, req, false);
+        if (ret < 0)
+                goto done_err;
+
+        if (!rbd_cb) {
+                ret = ceph_osdc_wait_request(&dev->client->osdc, req);
+                ceph_osdc_put_request(req);
+        }
+        return ret;
+
+done_err:
+        bio_chain_put(req_data->bio);
+        ceph_osdc_put_request(req);
+done_pages:
+        kfree(req_data);
+done:
+        if (rq)
+                blk_end_request(rq, ret, len);
+        return ret;
+}
+
+/*
+ * Ceph osd op callback
+ */
+static void rbd_req_cb(struct ceph_osd_request *req, struct ceph_msg *msg)
+{
+        struct rbd_request *req_data = req->r_priv;
+        struct ceph_osd_reply_head *replyhead;
+        struct ceph_osd_op *op;
+        __s32 rc;
+        u64 bytes;
+        int read_op;
+
+        /* parse reply */
+        replyhead = msg->front.iov_base;
+        WARN_ON(le32_to_cpu(replyhead->num_ops) == 0);
+        op = (void *)(replyhead + 1);
+        rc = le32_to_cpu(replyhead->result);
+        bytes = le64_to_cpu(op->extent.length);
+        read_op = (le32_to_cpu(op->op) == CEPH_OSD_OP_READ);
+
+        dout("rbd_req_cb bytes=%lld readop=%d rc=%d\n", bytes, read_op, rc);
+
+        if (rc == -ENOENT && read_op) {
+                zero_bio_chain(req_data->bio, 0);
+                rc = 0;
+        } else if (rc == 0 && read_op && bytes < req_data->len) {
+                zero_bio_chain(req_data->bio, bytes);
+                bytes = req_data->len;
+        }
+
+        blk_end_request(req_data->rq, rc, bytes);
+
+        if (req_data->bio)
+                bio_chain_put(req_data->bio);
+
+        ceph_osdc_put_request(req);
+        kfree(req_data);
+}
+
+/*
+ * Do a synchronous ceph osd operation
+ */
+static int rbd_req_sync_op(struct rbd_device *dev,
+                           struct ceph_snap_context *snapc,
+                           u64 snapid,
+                           int opcode,
+                           int flags,
+                           struct ceph_osd_req_op *orig_ops,
+                           int num_reply,
+                           const char *obj,
+                           u64 ofs, u64 len,
+                           char *buf)
+{
+        int ret;
+        struct page **pages;
+        int num_pages;
+        struct ceph_osd_req_op *ops = orig_ops;
+        u32 payload_len;
+
+        num_pages = calc_pages_for(ofs , len);
+        pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL);
+        if (IS_ERR(pages))
+                return PTR_ERR(pages);
+
+        if (!orig_ops) {
+                payload_len = (flags & CEPH_OSD_FLAG_WRITE ? len : 0);
+                ret = rbd_create_rw_ops(&ops, 1, opcode, payload_len);
+                if (ret < 0)
+                        goto done;
+
+                if ((flags & CEPH_OSD_FLAG_WRITE) && buf) {
+                        ret = ceph_copy_to_page_vector(pages, buf, ofs, len);
+                        if (ret < 0)
+                                goto done_ops;
+                }
+        }
+
+        ret = rbd_do_request(NULL, dev, snapc, snapid,
+                          obj, ofs, len, NULL,
+                          pages, num_pages,
+                          flags,
+                          ops,
+                          2,
+                          NULL);
+        if (ret < 0)
+                goto done_ops;
+
+        if ((flags & CEPH_OSD_FLAG_READ) && buf)
+                ret = ceph_copy_from_page_vector(pages, buf, ofs, ret);
+
+done_ops:
+        if (!orig_ops)
+                rbd_destroy_ops(ops);
+done:
+        ceph_release_page_vector(pages, num_pages);
+        return ret;
+}
+
+/*
+ * Do an asynchronous ceph osd operation
+ */
+static int rbd_do_op(struct request *rq,
+                     struct rbd_device *rbd_dev ,
+                     struct ceph_snap_context *snapc,
+                     u64 snapid,
+                     int opcode, int flags, int num_reply,
+                     u64 ofs, u64 len,
+                     struct bio *bio)
+{
+        char *seg_name;
+        u64 seg_ofs;
+        u64 seg_len;
+        int ret;
+        struct ceph_osd_req_op *ops;
+        u32 payload_len;
+
+        seg_name = kmalloc(RBD_MAX_SEG_NAME_LEN + 1, GFP_NOIO);
+        if (!seg_name)
+                return -ENOMEM;
+
+        seg_len = rbd_get_segment(&rbd_dev->header,
+                                  rbd_dev->header.block_name,
+                                  ofs, len,
+                                  seg_name, &seg_ofs);
+
+        payload_len = (flags & CEPH_OSD_FLAG_WRITE ? seg_len : 0);
+
+        ret = rbd_create_rw_ops(&ops, 1, opcode, payload_len);
+        if (ret < 0)
+                goto done;
+
+        /* we've taken care of segment sizes earlier when we
+           cloned the bios. We should never have a segment
+           truncated at this point */
+        BUG_ON(seg_len < len);
+
+        ret = rbd_do_request(rq, rbd_dev, snapc, snapid,
+                             seg_name, seg_ofs, seg_len,
+                             bio,
+                             NULL, 0,
+                             flags,
+                             ops,
+                             num_reply,
+                             rbd_req_cb);
+done:
+        kfree(seg_name);
+        return ret;
+}
+
+/*
+ * Request async osd write
+ */
+static int rbd_req_write(struct request *rq,
+                         struct rbd_device *rbd_dev,
+                         struct ceph_snap_context *snapc,
+                         u64 ofs, u64 len,
+                         struct bio *bio)
+{
+        return rbd_do_op(rq, rbd_dev, snapc, CEPH_NOSNAP,
+                         CEPH_OSD_OP_WRITE,
+                         CEPH_OSD_FLAG_WRITE | CEPH_OSD_FLAG_ONDISK,
+                         2,
+                         ofs, len, bio);
+}
+
+/*
+ * Request async osd read
+ */
+static int rbd_req_read(struct request *rq,
+                         struct rbd_device *rbd_dev,
+                         u64 snapid,
+                         u64 ofs, u64 len,
+                         struct bio *bio)
+{
+        return rbd_do_op(rq, rbd_dev, NULL,
+                         (snapid ? snapid : CEPH_NOSNAP),
+                         CEPH_OSD_OP_READ,
+                         CEPH_OSD_FLAG_READ,
+                         2,
+                         ofs, len, bio);
+}
+
+/*
+ * Request sync osd read
+ */
+static int rbd_req_sync_read(struct rbd_device *dev,
+                          struct ceph_snap_context *snapc,
+                          u64 snapid,
+                          const char *obj,
+                          u64 ofs, u64 len,
+                          char *buf)
+{
+        return rbd_req_sync_op(dev, NULL,
+                               (snapid ? snapid : CEPH_NOSNAP),
+                               CEPH_OSD_OP_READ,
+                               CEPH_OSD_FLAG_READ,
+                               NULL,
+                               1, obj, ofs, len, buf);
+}
+
+/*
+ * Request sync osd read
+ */
+static int rbd_req_sync_rollback_obj(struct rbd_device *dev,
+                                     u64 snapid,
+                                     const char *obj)
+{
+        struct ceph_osd_req_op *ops;
+        int ret = rbd_create_rw_ops(&ops, 1, CEPH_OSD_OP_ROLLBACK, 0);
+        if (ret < 0)
+                return ret;
+
+        ops[0].snap.snapid = snapid;
+
+        ret = rbd_req_sync_op(dev, NULL,
+                               CEPH_NOSNAP,
+                               0,
+                               CEPH_OSD_FLAG_WRITE | CEPH_OSD_FLAG_ONDISK,
+                               ops,
+                               1, obj, 0, 0, NULL);
+
+        rbd_destroy_ops(ops);
+
+        if (ret < 0)
+                return ret;
+
+        return ret;
+}
+
+/*
+ * Request sync osd read
+ */
+static int rbd_req_sync_exec(struct rbd_device *dev,
+                             const char *obj,
+                             const char *cls,
+                             const char *method,
+                             const char *data,
+                             int len)
+{
+        struct ceph_osd_req_op *ops;
+        int cls_len = strlen(cls);
+        int method_len = strlen(method);
+        int ret = rbd_create_rw_ops(&ops, 1, CEPH_OSD_OP_CALL,
+                                    cls_len + method_len + len);
+        if (ret < 0)
+                return ret;
+
+        ops[0].cls.class_name = cls;
+        ops[0].cls.class_len = (__u8)cls_len;
+        ops[0].cls.method_name = method;
+        ops[0].cls.method_len = (__u8)method_len;
+        ops[0].cls.argc = 0;
+        ops[0].cls.indata = data;
+        ops[0].cls.indata_len = len;
+
+        ret = rbd_req_sync_op(dev, NULL,
+                               CEPH_NOSNAP,
+                               0,
+                               CEPH_OSD_FLAG_WRITE | CEPH_OSD_FLAG_ONDISK,
+                               ops,
+                               1, obj, 0, 0, NULL);
+
+        rbd_destroy_ops(ops);
+
+        dout("cls_exec returned %d\n", ret);
+        return ret;
+}
+
+/*
+ * block device queue callback
+ */
+static void rbd_rq_fn(struct request_queue *q)
+{
+        struct rbd_device *rbd_dev = q->queuedata;
+        struct request *rq;
+        struct bio_pair *bp = NULL;
+
+        rq = blk_fetch_request(q);
+
+        while (1) {
+                struct bio *bio;
+                struct bio *rq_bio, *next_bio = NULL;
+                bool do_write;
+                int size, op_size = 0;
+                u64 ofs;
+
+                /* peek at request from block layer */
+                if (!rq)
+                        break;
+
+                dout("fetched request\n");
+
+                /* filter out block requests we don't understand */
+                if ((rq->cmd_type != REQ_TYPE_FS)) {
+                        __blk_end_request_all(rq, 0);
+                        goto next;
+                }
+
+                /* deduce our operation (read, write) */
+                do_write = (rq_data_dir(rq) == WRITE);
+
+                size = blk_rq_bytes(rq);
+                ofs = blk_rq_pos(rq) * 512ULL;
+                rq_bio = rq->bio;
+                if (do_write && rbd_dev->read_only) {
+                        __blk_end_request_all(rq, -EROFS);
+                        goto next;
+                }
+
+                spin_unlock_irq(q->queue_lock);
+
+                dout("%s 0x%x bytes at 0x%llx\n",
+                     do_write ? "write" : "read",
+                     size, blk_rq_pos(rq) * 512ULL);
+
+                do {
+                        /* a bio clone to be passed down to OSD req */
+                        dout("rq->bio->bi_vcnt=%d\n", rq->bio->bi_vcnt);
+                        op_size = rbd_get_segment(&rbd_dev->header,
+                                                  rbd_dev->header.block_name,
+                                                  ofs, size,
+                                                  NULL, NULL);
+                        bio = bio_chain_clone(&rq_bio, &next_bio, &bp,
+                                              op_size, GFP_ATOMIC);
+                        if (!bio) {
+                                spin_lock_irq(q->queue_lock);
+                                __blk_end_request_all(rq, -ENOMEM);
+                                goto next;
+                        }
+
+                        /* init OSD command: write or read */
+                        if (do_write)
+                                rbd_req_write(rq, rbd_dev,
+                                              rbd_dev->header.snapc,
+                                              ofs,
+                                              op_size, bio);
+                        else
+                                rbd_req_read(rq, rbd_dev,
+                                             cur_snap_id(rbd_dev),
+                                             ofs,
+                                             op_size, bio);
+
+                        size -= op_size;
+                        ofs += op_size;
+
+                        rq_bio = next_bio;
+                } while (size > 0);
+
+                if (bp)
+                        bio_pair_release(bp);
+
+                spin_lock_irq(q->queue_lock);
+next:
+                rq = blk_fetch_request(q);
+        }
+}
+
+/*
+ * a queue callback. Makes sure that we don't create a bio that spans across
+ * multiple osd objects. One exception would be with a single page bios,
+ * which we handle later at bio_chain_clone
+ */
+static int rbd_merge_bvec(struct request_queue *q, struct bvec_merge_data *bmd,
+                          struct bio_vec *bvec)
+{
+        struct rbd_device *rbd_dev = q->queuedata;
+        unsigned int chunk_sectors = 1 << (rbd_dev->header.obj_order - 9);
+        sector_t sector = bmd->bi_sector + get_start_sect(bmd->bi_bdev);
+        unsigned int bio_sectors = bmd->bi_size >> 9;
+        int max;
+
+        max =  (chunk_sectors - ((sector & (chunk_sectors - 1))
+                                 + bio_sectors)) << 9;
+        if (max < 0)
+                max = 0; /* bio_add cannot handle a negative return */
+        if (max <= bvec->bv_len && bio_sectors == 0)
+                return bvec->bv_len;
+        return max;
+}
+
+static void rbd_free_disk(struct rbd_device *rbd_dev)
+{
+        struct gendisk *disk = rbd_dev->disk;
+
+        if (!disk)
+                return;
+
+        rbd_header_free(&rbd_dev->header);
+
+        if (disk->flags & GENHD_FL_UP)
+                del_gendisk(disk);
+        if (disk->queue)
+                blk_cleanup_queue(disk->queue);
+        put_disk(disk);
+}
+
+/*
+ * reload the ondisk the header 
+ */
+static int rbd_read_header(struct rbd_device *rbd_dev,
+                           struct rbd_image_header *header)
+{
+        ssize_t rc;
+        struct rbd_image_header_ondisk *dh;
+        int snap_count = 0;
+        u64 snap_names_len = 0;
+
+        while (1) {
+                int len = sizeof(*dh) +
+                          snap_count * sizeof(struct rbd_image_snap_ondisk) +
+                          snap_names_len;
+
+                rc = -ENOMEM;
+                dh = kmalloc(len, GFP_KERNEL);
+                if (!dh)
+                        return -ENOMEM;
+
+                rc = rbd_req_sync_read(rbd_dev,
+                                       NULL, CEPH_NOSNAP,
+                                       rbd_dev->obj_md_name,
+                                       0, len,
+                                       (char *)dh);
+                if (rc < 0)
+                        goto out_dh;
+
+                rc = rbd_header_from_disk(header, dh, snap_count, GFP_KERNEL);
+                if (rc < 0)
+                        goto out_dh;
+
+                if (snap_count != header->total_snaps) {
+                        snap_count = header->total_snaps;
+                        snap_names_len = header->snap_names_len;
+                        rbd_header_free(header);
+                        kfree(dh);
+                        continue;
+                }
+                break;
+        }
+
+out_dh:
+        kfree(dh);
+        return rc;
+}
+
+/*
+ * create a snapshot
+ */
+static int rbd_header_add_snap(struct rbd_device *dev,
+                               const char *snap_name,
+                               gfp_t gfp_flags)
+{
+        int name_len = strlen(snap_name);
+        u64 new_snapid;
+        int ret;
+        void *data, *data_start, *data_end;
+
+        /* we should create a snapshot only if we're pointing at the head */
+        if (dev->cur_snap)
+                return -EINVAL;
+
+        ret = ceph_monc_create_snapid(&dev->client->monc, dev->poolid,
+                                      &new_snapid);
+        dout("created snapid=%lld\n", new_snapid);
+        if (ret < 0)
+                return ret;
+
+        data = kmalloc(name_len + 16, gfp_flags);
+        if (!data)
+                return -ENOMEM;
+
+        data_start = data;
+        data_end = data + name_len + 16;
+
+        ceph_encode_string_safe(&data, data_end, snap_name, name_len, bad);
+        ceph_encode_64_safe(&data, data_end, new_snapid, bad);
+
+        ret = rbd_req_sync_exec(dev, dev->obj_md_name, "rbd", "snap_add",
+                                data_start, data - data_start);
+
+        kfree(data_start);
+
+        if (ret < 0)
+                return ret;
+
+        dev->header.snapc->seq =  new_snapid;
+
+        return 0;
+bad:
+        return -ERANGE;
+}
+
+/*
+ * only read the first part of the ondisk header, without the snaps info
+ */
+static int rbd_update_snaps(struct rbd_device *rbd_dev)
+{
+        int ret;
+        struct rbd_image_header h;
+        u64 snap_seq;
+
+        ret = rbd_read_header(rbd_dev, &h);
+        if (ret < 0)
+                return ret;
+
+        down_write(&rbd_dev->header.snap_rwsem);
+
+        snap_seq = rbd_dev->header.snapc->seq;
+
+        kfree(rbd_dev->header.snapc);
+        kfree(rbd_dev->header.snap_names);
+        kfree(rbd_dev->header.snap_sizes);
+
+        rbd_dev->header.total_snaps = h.total_snaps;
+        rbd_dev->header.snapc = h.snapc;
+        rbd_dev->header.snap_names = h.snap_names;
+        rbd_dev->header.snap_sizes = h.snap_sizes;
+        rbd_dev->header.snapc->seq = snap_seq;
+
+        up_write(&rbd_dev->header.snap_rwsem);
+
+        return 0;
+}
+
+static int rbd_init_disk(struct rbd_device *rbd_dev)
+{
+        struct gendisk *disk;
+        struct request_queue *q;
+        int rc;
+        u64 total_size = 0;
+
+        /* contact OSD, request size info about the object being mapped */
+        rc = rbd_read_header(rbd_dev, &rbd_dev->header);
+        if (rc)
+                return rc;
+
+        rc = rbd_header_set_snap(rbd_dev, rbd_dev->snap_name, &total_size);
+        if (rc)
+                return rc;
+
+        /* create gendisk info */
+        rc = -ENOMEM;
+        disk = alloc_disk(RBD_MINORS_PER_MAJOR);
+        if (!disk)
+                goto out;
+
+        sprintf(disk->disk_name, DRV_NAME "%d", rbd_dev->id);
+        disk->major = rbd_dev->major;
+        disk->first_minor = 0;
+        disk->fops = &rbd_bd_ops;
+        disk->private_data = rbd_dev;
+
+        /* init rq */
+        rc = -ENOMEM;
+        q = blk_init_queue(rbd_rq_fn, &rbd_dev->lock);
+        if (!q)
+                goto out_disk;
+        blk_queue_merge_bvec(q, rbd_merge_bvec);
+        disk->queue = q;
+
+        q->queuedata = rbd_dev;
+
+        rbd_dev->disk = disk;
+        rbd_dev->q = q;
+
+        /* finally, announce the disk to the world */
+        set_capacity(disk, total_size / 512ULL);
+        add_disk(disk);
+
+        pr_info("%s: added with size 0x%llx\n",
+                disk->disk_name, (unsigned long long)total_size);
+        return 0;
+
+out_disk:
+        put_disk(disk);
+out:
+        return rc;
+}
+
+/********************************************************************
+ * /sys/class/rbd/
+ *                   add        map rados objects to blkdev
+ *                   remove     unmap rados objects
+ *                   list       show mappings
+ *******************************************************************/
+
+static void class_rbd_release(struct class *cls)
+{
+        kfree(cls);
+}
+
+static ssize_t class_rbd_list(struct class *c,
+                              struct class_attribute *attr,
+                              char *data)
+{
+        int n = 0;
+        struct list_head *tmp;
+        int max = PAGE_SIZE;
+
+        mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+        n += snprintf(data, max,
+                      "#id\tmajor\tclient_name\tpool\tname\tsnap\tKB\n");
+
+        list_for_each(tmp, &rbd_dev_list) {
+                struct rbd_device *rbd_dev;
+
+                rbd_dev = list_entry(tmp, struct rbd_device, node);
+                n += snprintf(data+n, max-n,
+                              "%d\t%d\tclient%lld\t%s\t%s\t%s\t%lld\n",
+                              rbd_dev->id,
+                              rbd_dev->major,
+                              ceph_client_id(rbd_dev->client),
+                              rbd_dev->pool_name,
+                              rbd_dev->obj, rbd_dev->snap_name,
+                              rbd_dev->header.image_size >> 10);
+                if (n == max)
+                        break;
+        }
+
+        mutex_unlock(&ctl_mutex);
+        return n;
+}
+
+static ssize_t class_rbd_add(struct class *c,
+                             struct class_attribute *attr,
+                             const char *buf, size_t count)
+{
+        struct ceph_osd_client *osdc;
+        struct rbd_device *rbd_dev;
+        ssize_t rc = -ENOMEM;
+        int irc, new_id = 0;
+        struct list_head *tmp;
+        char *mon_dev_name;
+        char *options;
+
+        if (!try_module_get(THIS_MODULE))
+                return -ENODEV;
+
+        mon_dev_name = kmalloc(RBD_MAX_OPT_LEN, GFP_KERNEL);
+        if (!mon_dev_name)
+                goto err_out_mod;
+
+        options = kmalloc(RBD_MAX_OPT_LEN, GFP_KERNEL);
+        if (!options)
+                goto err_mon_dev;
+
+        /* new rbd_device object */
+        rbd_dev = kzalloc(sizeof(*rbd_dev), GFP_KERNEL);
+        if (!rbd_dev)
+                goto err_out_opt;
+
+        /* static rbd_device initialization */
+        spin_lock_init(&rbd_dev->lock);
+        INIT_LIST_HEAD(&rbd_dev->node);
+
+        /* generate unique id: find highest unique id, add one */
+        mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+        list_for_each(tmp, &rbd_dev_list) {
+                struct rbd_device *rbd_dev;
+
+                rbd_dev = list_entry(tmp, struct rbd_device, node);
+                if (rbd_dev->id >= new_id)
+                        new_id = rbd_dev->id + 1;
+        }
+
+        rbd_dev->id = new_id;
+
+        /* add to global list */
+        list_add_tail(&rbd_dev->node, &rbd_dev_list);
+
+        /* parse add command */
+        if (sscanf(buf, "%" __stringify(RBD_MAX_OPT_LEN) "s "
+                   "%" __stringify(RBD_MAX_OPT_LEN) "s "
+                   "%" __stringify(RBD_MAX_POOL_NAME_LEN) "s "
+                   "%" __stringify(RBD_MAX_OBJ_NAME_LEN) "s"
+                   "%" __stringify(RBD_MAX_SNAP_NAME_LEN) "s",
+                   mon_dev_name, options, rbd_dev->pool_name,
+                   rbd_dev->obj, rbd_dev->snap_name) < 4) {
+                rc = -EINVAL;
+                goto err_out_slot;
+        }
+
+        if (rbd_dev->snap_name[0] == 0)
+                rbd_dev->snap_name[0] = '-';
+
+        rbd_dev->obj_len = strlen(rbd_dev->obj);
+        snprintf(rbd_dev->obj_md_name, sizeof(rbd_dev->obj_md_name), "%s%s",
+                 rbd_dev->obj, RBD_SUFFIX);
+
+        /* initialize rest of new object */
+        snprintf(rbd_dev->name, DEV_NAME_LEN, DRV_NAME "%d", rbd_dev->id);
+        rc = rbd_get_client(rbd_dev, mon_dev_name, options);
+        if (rc < 0)
+                goto err_out_slot;
+
+        mutex_unlock(&ctl_mutex);
+
+        /* pick the pool */
+        osdc = &rbd_dev->client->osdc;
+        rc = ceph_pg_poolid_by_name(osdc->osdmap, rbd_dev->pool_name);
+        if (rc < 0)
+                goto err_out_client;
+        rbd_dev->poolid = rc;
+
+        /* register our block device */
+        irc = register_blkdev(0, rbd_dev->name);
+        if (irc < 0) {
+                rc = irc;
+                goto err_out_client;
+        }
+        rbd_dev->major = irc;
+
+        /* set up and announce blkdev mapping */
+        rc = rbd_init_disk(rbd_dev);
+        if (rc)
+                goto err_out_blkdev;
+
+        return count;
+
+err_out_blkdev:
+        unregister_blkdev(rbd_dev->major, rbd_dev->name);
+err_out_client:
+        rbd_put_client(rbd_dev);
+        mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+err_out_slot:
+        list_del_init(&rbd_dev->node);
+        mutex_unlock(&ctl_mutex);
+
+        kfree(rbd_dev);
+err_out_opt:
+        kfree(options);
+err_mon_dev:
+        kfree(mon_dev_name);
+err_out_mod:
+        dout("Error adding device %s\n", buf);
+        module_put(THIS_MODULE);
+        return rc;
+}
+
+static struct rbd_device *__rbd_get_dev(unsigned long id)
+{
+        struct list_head *tmp;
+        struct rbd_device *rbd_dev;
+
+        list_for_each(tmp, &rbd_dev_list) {
+                rbd_dev = list_entry(tmp, struct rbd_device, node);
+                if (rbd_dev->id == id)
+                        return rbd_dev;
+        }
+        return NULL;
+}
+
+static ssize_t class_rbd_remove(struct class *c,
+                                struct class_attribute *attr,
+                                const char *buf,
+                                size_t count)
+{
+        struct rbd_device *rbd_dev = NULL;
+        int target_id, rc;
+        unsigned long ul;
+
+        rc = strict_strtoul(buf, 10, &ul);
+        if (rc)
+                return rc;
+
+        /* convert to int; abort if we lost anything in the conversion */
+        target_id = (int) ul;
+        if (target_id != ul)
+                return -EINVAL;
+
+        /* remove object from list immediately */
+        mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+        rbd_dev = __rbd_get_dev(target_id);
+        if (rbd_dev)
+                list_del_init(&rbd_dev->node);
+
+        mutex_unlock(&ctl_mutex);
+
+        if (!rbd_dev)
+                return -ENOENT;
+
+        rbd_put_client(rbd_dev);
+
+        /* clean up and free blkdev */
+        rbd_free_disk(rbd_dev);
+        unregister_blkdev(rbd_dev->major, rbd_dev->name);
+        kfree(rbd_dev);
+
+        /* release module ref */
+        module_put(THIS_MODULE);
+
+        return count;
+}
+
+static ssize_t class_rbd_snaps_list(struct class *c,
+                              struct class_attribute *attr,
+                              char *data)
+{
+        struct rbd_device *rbd_dev = NULL;
+        struct list_head *tmp;
+        struct rbd_image_header *header;
+        int i, n = 0, max = PAGE_SIZE;
+        int ret;
+
+        mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+        n += snprintf(data, max, "#id\tsnap\tKB\n");
+
+        list_for_each(tmp, &rbd_dev_list) {
+                char *names, *p;
+                struct ceph_snap_context *snapc;
+
+                rbd_dev = list_entry(tmp, struct rbd_device, node);
+                header = &rbd_dev->header;
+
+                down_read(&header->snap_rwsem);
+
+                names = header->snap_names;
+                snapc = header->snapc;
+
+                n += snprintf(data + n, max - n, "%d\t%s\t%lld%s\n",
+                              rbd_dev->id, RBD_SNAP_HEAD_NAME,
+                              header->image_size >> 10,
+                              (!rbd_dev->cur_snap ? " (*)" : ""));
+                if (n == max)
+                        break;
+
+                p = names;
+                for (i = 0; i < header->total_snaps; i++, p += strlen(p) + 1) {
+                        n += snprintf(data + n, max - n, "%d\t%s\t%lld%s\n",
+                              rbd_dev->id, p, header->snap_sizes[i] >> 10,
+                              (rbd_dev->cur_snap &&
+                               (snap_index(header, i) == rbd_dev->cur_snap) ?
+                               " (*)" : ""));
+                        if (n == max)
+                                break;
+                }
+
+                up_read(&header->snap_rwsem);
+        }
+
+
+        ret = n;
+        mutex_unlock(&ctl_mutex);
+        return ret;
+}
+
+static ssize_t class_rbd_snaps_refresh(struct class *c,
+                                struct class_attribute *attr,
+                                const char *buf,
+                                size_t count)
+{
+        struct rbd_device *rbd_dev = NULL;
+        int target_id, rc;
+        unsigned long ul;
+        int ret = count;
+
+        rc = strict_strtoul(buf, 10, &ul);
+        if (rc)
+                return rc;
+
+        /* convert to int; abort if we lost anything in the conversion */
+        target_id = (int) ul;
+        if (target_id != ul)
+                return -EINVAL;
+
+        mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+        rbd_dev = __rbd_get_dev(target_id);
+        if (!rbd_dev) {
+                ret = -ENOENT;
+                goto done;
+        }
+
+        rc = rbd_update_snaps(rbd_dev);
+        if (rc < 0)
+                ret = rc;
+
+done:
+        mutex_unlock(&ctl_mutex);
+        return ret;
+}
+
+static ssize_t class_rbd_snap_create(struct class *c,
+                                struct class_attribute *attr,
+                                const char *buf,
+                                size_t count)
+{
+        struct rbd_device *rbd_dev = NULL;
+        int target_id, ret;
+        char *name;
+
+        name = kmalloc(RBD_MAX_SNAP_NAME_LEN + 1, GFP_KERNEL);
+        if (!name)
+                return -ENOMEM;
+
+        /* parse snaps add command */
+        if (sscanf(buf, "%d "
+                   "%" __stringify(RBD_MAX_SNAP_NAME_LEN) "s",
+                   &target_id,
+                   name) != 2) {
+                ret = -EINVAL;
+                goto done;
+        }
+
+        mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+        rbd_dev = __rbd_get_dev(target_id);
+        if (!rbd_dev) {
+                ret = -ENOENT;
+                goto done_unlock;
+        }
+
+        ret = rbd_header_add_snap(rbd_dev,
+                                  name, GFP_KERNEL);
+        if (ret < 0)
+                goto done_unlock;
+
+        ret = rbd_update_snaps(rbd_dev);
+        if (ret < 0)
+                goto done_unlock;
+
+        ret = count;
+done_unlock:
+        mutex_unlock(&ctl_mutex);
+done:
+        kfree(name);
+        return ret;
+}
+
+static ssize_t class_rbd_rollback(struct class *c,
+                                struct class_attribute *attr,
+                                const char *buf,
+                                size_t count)
+{
+        struct rbd_device *rbd_dev = NULL;
+        int target_id, ret;
+        u64 snapid;
+        char snap_name[RBD_MAX_SNAP_NAME_LEN];
+        u64 cur_ofs;
+        char *seg_name;
+
+        /* parse snaps add command */
+        if (sscanf(buf, "%d "
+                   "%" __stringify(RBD_MAX_SNAP_NAME_LEN) "s",
+                   &target_id,
+                   snap_name) != 2) {
+                return -EINVAL;
+        }
+
+        ret = -ENOMEM;
+        seg_name = kmalloc(RBD_MAX_SEG_NAME_LEN + 1, GFP_NOIO);
+        if (!seg_name)
+                return ret;
+
+        mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+        rbd_dev = __rbd_get_dev(target_id);
+        if (!rbd_dev) {
+                ret = -ENOENT;
+                goto done_unlock;
+        }
+
+        ret = snap_by_name(&rbd_dev->header, snap_name, &snapid, NULL);
+        if (ret < 0)
+                goto done_unlock;
+
+        dout("snapid=%lld\n", snapid);
+
+        cur_ofs = 0;
+        while (cur_ofs < rbd_dev->header.image_size) {
+                cur_ofs += rbd_get_segment(&rbd_dev->header,
+                                           rbd_dev->obj,
+                                           cur_ofs, (u64)-1,
+                                           seg_name, NULL);
+                dout("seg_name=%s\n", seg_name);
+
+                ret = rbd_req_sync_rollback_obj(rbd_dev, snapid, seg_name);
+                if (ret < 0)
+                        pr_warning("could not roll back obj %s err=%d\n",
+                                   seg_name, ret);
+        }
+
+        ret = rbd_update_snaps(rbd_dev);
+        if (ret < 0)
+                goto done_unlock;
+
+        ret = count;
+
+done_unlock:
+        mutex_unlock(&ctl_mutex);
+        kfree(seg_name);
+
+        return ret;
+}
+
+static struct class_attribute class_rbd_attrs[] = {
+        __ATTR(add,             0200, NULL, class_rbd_add),
+        __ATTR(remove,          0200, NULL, class_rbd_remove),
+        __ATTR(list,            0444, class_rbd_list, NULL),
+        __ATTR(snaps_refresh,   0200, NULL, class_rbd_snaps_refresh),
+        __ATTR(snap_create,     0200, NULL, class_rbd_snap_create),
+        __ATTR(snaps_list,      0444, class_rbd_snaps_list, NULL),
+        __ATTR(snap_rollback,   0200, NULL, class_rbd_rollback),
+        __ATTR_NULL
+};
+
+/*
+ * create control files in sysfs
+ * /sys/class/rbd/...
+ */
+static int rbd_sysfs_init(void)
+{
+        int ret = -ENOMEM;
+
+        class_rbd = kzalloc(sizeof(*class_rbd), GFP_KERNEL);
+        if (!class_rbd)
+                goto out;
+
+        class_rbd->name = DRV_NAME;
+        class_rbd->owner = THIS_MODULE;
+        class_rbd->class_release = class_rbd_release;
+        class_rbd->class_attrs = class_rbd_attrs;
+
+        ret = class_register(class_rbd);
+        if (ret)
+                goto out_class;
+        return 0;
+
+out_class:
+        kfree(class_rbd);
+        class_rbd = NULL;
+        pr_err(DRV_NAME ": failed to create class rbd\n");
+out:
+        return ret;
+}
+
+static void rbd_sysfs_cleanup(void)
+{
+        if (class_rbd)
+                class_destroy(class_rbd);
+        class_rbd = NULL;
+}
+
+int __init rbd_init(void)
+{
+        int rc;
+
+        rc = rbd_sysfs_init();
+        if (rc)
+                return rc;
+        spin_lock_init(&node_lock);
+        pr_info("loaded " DRV_NAME_LONG "\n");
+        return 0;
+}
+
+void __exit rbd_exit(void)
+{
+        rbd_sysfs_cleanup();
+}
+
+module_init(rbd_init);
+module_exit(rbd_exit);
+
+MODULE_AUTHOR("Sage Weil <sage@newdream.net>");
+MODULE_AUTHOR("Yehuda Sadeh <yehuda@hq.newdream.net>");
+MODULE_DESCRIPTION("rados block device");
+
+/* following authorship retained from original osdblk.c */
+MODULE_AUTHOR("Jeff Garzik <jeff@garzik.org>");
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/block/rbd_types.h b/drivers/block/rbd_types.h
new file mode 100644
index 000000000000..fc6c678aa2cb
--- /dev/null
+++ b/drivers/block/rbd_types.h
@@ -0,0 +1,73 @@
+/*
+ * Ceph - scalable distributed file system
+ *
+ * Copyright (C) 2004-2010 Sage Weil <sage@newdream.net>
+ *
+ * This is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License version 2.1, as published by the Free Software
+ * Foundation.  See file COPYING.
+ *
+ */
+
+#ifndef CEPH_RBD_TYPES_H
+#define CEPH_RBD_TYPES_H
+
+#include <linux/types.h>
+
+/*
+ * rbd image 'foo' consists of objects
+ *   foo.rbd      - image metadata
+ *   foo.00000000
+ *   foo.00000001
+ *   ...          - data
+ */
+
+#define RBD_SUFFIX              ".rbd"
+#define RBD_DIRECTORY           "rbd_directory"
+#define RBD_INFO                "rbd_info"
+
+#define RBD_DEFAULT_OBJ_ORDER   22   /* 4MB */
+#define RBD_MIN_OBJ_ORDER       16
+#define RBD_MAX_OBJ_ORDER       30
+
+#define RBD_MAX_OBJ_NAME_LEN    96
+#define RBD_MAX_SEG_NAME_LEN    128
+
+#define RBD_COMP_NONE           0
+#define RBD_CRYPT_NONE          0
+
+#define RBD_HEADER_TEXT         "<<< Rados Block Device Image >>>\n"
+#define RBD_HEADER_SIGNATURE    "RBD"
+#define RBD_HEADER_VERSION      "001.005"
+
+struct rbd_info {
+        __le64 max_id;
+} __attribute__ ((packed));
+
+struct rbd_image_snap_ondisk {
+        __le64 id;
+        __le64 image_size;
+} __attribute__((packed));
+
+struct rbd_image_header_ondisk {
+        char text[40];
+        char block_name[24];
+        char signature[4];
+        char version[8];
+        struct {
+                __u8 order;
+                __u8 crypt_type;
+                __u8 comp_type;
+                __u8 unused;
+        } __attribute__((packed)) options;
+        __le64 image_size;
+        __le64 snap_seq;
+        __le32 snap_count;
+        __le32 reserved;
+        __le64 snap_names_len;
+        struct rbd_image_snap_ondisk snaps[0];
+} __attribute__((packed));
+
+
+#endif
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 1101e251a629..8320490226b7 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -2,7 +2,6 @@
 #include <linux/spinlock.h>
 #include <linux/slab.h>
 #include <linux/blkdev.h>
-#include <linux/smp_lock.h>
 #include <linux/hdreg.h>
 #include <linux/virtio.h>
 #include <linux/virtio_blk.h>
@@ -222,8 +221,8 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str)
         return err;
 }
 
-static int virtblk_locked_ioctl(struct block_device *bdev, fmode_t mode,
-                         unsigned cmd, unsigned long data)
+static int virtblk_ioctl(struct block_device *bdev, fmode_t mode,
+                             unsigned int cmd, unsigned long data)
 {
         struct gendisk *disk = bdev->bd_disk;
         struct virtio_blk *vblk = disk->private_data;
@@ -238,18 +237,6 @@ static int virtblk_locked_ioctl(struct block_device *bdev, fmode_t mode,
                               (void __user *)data);
 }
 
-static int virtblk_ioctl(struct block_device *bdev, fmode_t mode,
-                             unsigned int cmd, unsigned long param)
-{
-        int ret;
-
-        lock_kernel();
-        ret = virtblk_locked_ioctl(bdev, mode, cmd, param);
-        unlock_kernel();
-
-        return ret;
-}
-
 /* We provide getgeo only to please some old bootloader/partitioning tools */
 static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo)
 {
diff --git a/drivers/char/agp/Kconfig b/drivers/char/agp/Kconfig
index 4b66c69eaf57..5ddf67e76f8b 100644
--- a/drivers/char/agp/Kconfig
+++ b/drivers/char/agp/Kconfig
@@ -57,7 +57,7 @@ config AGP_AMD
 
 config AGP_AMD64
         tristate "AMD Opteron/Athlon64 on-CPU GART support"
-        depends on AGP && X86 && K8_NB
+        depends on AGP && X86 && AMD_NB
         help
           This option gives you AGP support for the GLX component of
           X using the on-CPU northbridge of the AMD Athlon64/Opteron CPUs.
diff --git a/drivers/char/agp/amd64-agp.c b/drivers/char/agp/amd64-agp.c
index 70312da4c968..42396df55556 100644
--- a/drivers/char/agp/amd64-agp.c
+++ b/drivers/char/agp/amd64-agp.c
@@ -15,7 +15,7 @@
 #include <linux/mmzone.h>
 #include <asm/page.h>           /* PAGE_SIZE */
 #include <asm/e820.h>
-#include <asm/k8.h>
+#include <asm/amd_nb.h>
 #include <asm/gart.h>
 #include "agp.h"
 
@@ -124,7 +124,7 @@ static int amd64_fetch_size(void)
         u32 temp;
         struct aper_size_info_32 *values;
 
-        dev = k8_northbridges[0];
+        dev = k8_northbridges.nb_misc[0];
         if (dev==NULL)
                 return 0;
 
@@ -181,10 +181,14 @@ static int amd_8151_configure(void)
         unsigned long gatt_bus = virt_to_phys(agp_bridge->gatt_table_real);
         int i;
 
+        if (!k8_northbridges.gart_supported)
+                return 0;
+
         /* Configure AGP regs in each x86-64 host bridge. */
-        for (i = 0; i < num_k8_northbridges; i++) {
+        for (i = 0; i < k8_northbridges.num; i++) {
                 agp_bridge->gart_bus_addr =
-                                amd64_configure(k8_northbridges[i], gatt_bus);
+                                amd64_configure(k8_northbridges.nb_misc[i],
+                                                gatt_bus);
         }
         k8_flush_garts();
         return 0;
@@ -195,11 +199,15 @@ static void amd64_cleanup(void)
 {
         u32 tmp;
         int i;
-        for (i = 0; i < num_k8_northbridges; i++) {
-                struct pci_dev *dev = k8_northbridges[i];
+
+        if (!k8_northbridges.gart_supported)
+                return;
+
+        for (i = 0; i < k8_northbridges.num; i++) {
+                struct pci_dev *dev = k8_northbridges.nb_misc[i];
                 /* disable gart translation */
                 pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &tmp);
-                tmp &= ~AMD64_GARTEN;
+                tmp &= ~GARTEN;
                 pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, tmp);
         }
 }
@@ -313,22 +321,25 @@ static __devinit int fix_northbridge(struct pci_dev *nb, struct pci_dev *agp,
         if (order < 0 || !agp_aperture_valid(aper, (32*1024*1024)<<order))
                 return -1;
 
-        pci_write_config_dword(nb, AMD64_GARTAPERTURECTL, order << 1);
+        gart_set_size_and_enable(nb, order);
         pci_write_config_dword(nb, AMD64_GARTAPERTUREBASE, aper >> 25);
 
         return 0;
 }
 
-static __devinit int cache_nbs (struct pci_dev *pdev, u32 cap_ptr)
+static __devinit int cache_nbs(struct pci_dev *pdev, u32 cap_ptr)
 {
         int i;
 
         if (cache_k8_northbridges() < 0)
                 return -ENODEV;
 
+        if (!k8_northbridges.gart_supported)
+                return -ENODEV;
+
         i = 0;
-        for (i = 0; i < num_k8_northbridges; i++) {
-                struct pci_dev *dev = k8_northbridges[i];
+        for (i = 0; i < k8_northbridges.num; i++) {
+                struct pci_dev *dev = k8_northbridges.nb_misc[i];
                 if (fix_northbridge(dev, pdev, cap_ptr) < 0) {
                         dev_err(&dev->dev, "no usable aperture found\n");
 #ifdef __x86_64__
@@ -405,7 +416,8 @@ static int __devinit uli_agp_init(struct pci_dev *pdev)
         }
 
         /* shadow x86-64 registers into ULi registers */
-        pci_read_config_dword (k8_northbridges[0], AMD64_GARTAPERTUREBASE, &httfea);
+        pci_read_config_dword (k8_northbridges.nb_misc[0], AMD64_GARTAPERTUREBASE,
+                               &httfea);
 
         /* if x86-64 aperture base is beyond 4G, exit here */
         if ((httfea & 0x7fff) >> (32 - 25)) {
@@ -472,7 +484,8 @@ static int nforce3_agp_init(struct pci_dev *pdev)
         pci_write_config_dword(dev1, NVIDIA_X86_64_1_APSIZE, tmp);
 
         /* shadow x86-64 registers into NVIDIA registers */
-        pci_read_config_dword (k8_northbridges[0], AMD64_GARTAPERTUREBASE, &apbase);
+        pci_read_config_dword (k8_northbridges.nb_misc[0], AMD64_GARTAPERTUREBASE,
+                               &apbase);
 
         /* if x86-64 aperture base is beyond 4G, exit here */
         if ( (apbase & 0x7fff) >> (32 - 25) ) {
diff --git a/drivers/char/agp/generic.c b/drivers/char/agp/generic.c
index d2abf5143983..64255cef8a7d 100644
--- a/drivers/char/agp/generic.c
+++ b/drivers/char/agp/generic.c
@@ -984,7 +984,9 @@ int agp_generic_create_gatt_table(struct agp_bridge_data *bridge)
 
         bridge->driver->cache_flush();
 #ifdef CONFIG_X86
-        set_memory_uc((unsigned long)table, 1 << page_order);
+        if (set_memory_uc((unsigned long)table, 1 << page_order))
+                printk(KERN_WARNING "Could not set GATT table memory to UC!");
+
         bridge->gatt_table = (void *)table;
 #else
         bridge->gatt_table = ioremap_nocache(virt_to_phys(table),
diff --git a/drivers/char/tpm/tpm.c b/drivers/char/tpm/tpm.c
index 05ad4a17a28f..7c4133582dba 100644
--- a/drivers/char/tpm/tpm.c
+++ b/drivers/char/tpm/tpm.c
@@ -47,6 +47,16 @@ enum tpm_duration {
 #define TPM_MAX_PROTECTED_ORDINAL 12
 #define TPM_PROTECTED_ORDINAL_MASK 0xFF
 
+/*
+ * Bug workaround - some TPM's don't flush the most
+ * recently changed pcr on suspend, so force the flush
+ * with an extend to the selected _unused_ non-volatile pcr.
+ */
+static int tpm_suspend_pcr;
+module_param_named(suspend_pcr, tpm_suspend_pcr, uint, 0644);
+MODULE_PARM_DESC(suspend_pcr,
+                 "PCR to use for dummy writes to faciltate flush on suspend.");
+
 static LIST_HEAD(tpm_chip_list);
 static DEFINE_SPINLOCK(driver_lock);
 static DECLARE_BITMAP(dev_mask, TPM_NUM_DEVICES);
@@ -1077,18 +1087,6 @@ static struct tpm_input_header savestate_header = {
         .ordinal = TPM_ORD_SAVESTATE
 };
 
-/* Bug workaround - some TPM's don't flush the most
- * recently changed pcr on suspend, so force the flush
- * with an extend to the selected _unused_ non-volatile pcr.
- */
-static int tpm_suspend_pcr;
-static int __init tpm_suspend_setup(char *str)
-{
-        get_option(&str, &tpm_suspend_pcr);
-        return 1;
-}
-__setup("tpm_suspend_pcr=", tpm_suspend_setup);
-
 /*
  * We are about to suspend. Save the TPM state
  * so that it can be restored.
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 0f69c5ec0ecd..6c1b676643a9 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -48,6 +48,9 @@ struct ports_driver_data {
         /* Used for exporting per-port information to debugfs */
         struct dentry *debugfs_dir;
 
+        /* List of all the devices we're handling */
+        struct list_head portdevs;
+
         /* Number of devices this driver is handling */
         unsigned int index;
 
@@ -108,6 +111,9 @@ struct port_buffer {
  * ports for that device (vdev->priv).
  */
 struct ports_device {
+        /* Next portdev in the list, head is in the pdrvdata struct */
+        struct list_head list;
+
         /*
          * Workqueue handlers where we process deferred work after
          * notification
@@ -178,15 +184,21 @@ struct port {
         struct console cons;
 
         /* Each port associates with a separate char device */
-        struct cdev cdev;
+        struct cdev *cdev;
         struct device *dev;
 
+        /* Reference-counting to handle port hot-unplugs and file operations */
+        struct kref kref;
+
         /* A waitqueue for poll() or blocking read operations */
         wait_queue_head_t waitqueue;
 
         /* The 'name' of the port that we expose via sysfs properties */
         char *name;
 
+        /* We can notify apps of host connect / disconnect events via SIGIO */
+        struct fasync_struct *async_queue;
+
         /* The 'id' to identify the port with the Host */
         u32 id;
 
@@ -221,6 +233,41 @@ out:
         return port;
 }
 
+static struct port *find_port_by_devt_in_portdev(struct ports_device *portdev,
+                                                 dev_t dev)
+{
+        struct port *port;
+        unsigned long flags;
+
+        spin_lock_irqsave(&portdev->ports_lock, flags);
+        list_for_each_entry(port, &portdev->ports, list)
+                if (port->cdev->dev == dev)
+                        goto out;
+        port = NULL;
+out:
+        spin_unlock_irqrestore(&portdev->ports_lock, flags);
+
+        return port;
+}
+
+static struct port *find_port_by_devt(dev_t dev)
+{
+        struct ports_device *portdev;
+        struct port *port;
+        unsigned long flags;
+
+        spin_lock_irqsave(&pdrvdata_lock, flags);
+        list_for_each_entry(portdev, &pdrvdata.portdevs, list) {
+                port = find_port_by_devt_in_portdev(portdev, dev);
+                if (port)
+                        goto out;
+        }
+        port = NULL;
+out:
+        spin_unlock_irqrestore(&pdrvdata_lock, flags);
+        return port;
+}
+
 static struct port *find_port_by_id(struct ports_device *portdev, u32 id)
 {
         struct port *port;
@@ -410,7 +457,10 @@ static ssize_t __send_control_msg(struct ports_device *portdev, u32 port_id,
 static ssize_t send_control_msg(struct port *port, unsigned int event,
                                 unsigned int value)
 {
-        return __send_control_msg(port->portdev, port->id, event, value);
+        /* Did the port get unplugged before userspace closed it? */
+        if (port->portdev)
+                return __send_control_msg(port->portdev, port->id, event, value);
+        return 0;
 }
 
 /* Callers must take the port->outvq_lock */
@@ -525,6 +575,10 @@ static ssize_t fill_readbuf(struct port *port, char *out_buf, size_t out_count,
 /* The condition that must be true for polling to end */
 static bool will_read_block(struct port *port)
 {
+        if (!port->guest_connected) {
+                /* Port got hot-unplugged. Let's exit. */
+                return false;
+        }
         return !port_has_data(port) && port->host_connected;
 }
 
@@ -575,6 +629,9 @@ static ssize_t port_fops_read(struct file *filp, char __user *ubuf,
                 if (ret < 0)
                         return ret;
         }
+        /* Port got hot-unplugged. */
+        if (!port->guest_connected)
+                return -ENODEV;
         /*
          * We could've received a disconnection message while we were
          * waiting for more data.
@@ -616,6 +673,9 @@ static ssize_t port_fops_write(struct file *filp, const char __user *ubuf,
                 if (ret < 0)
                         return ret;
         }
+        /* Port got hot-unplugged. */
+        if (!port->guest_connected)
+                return -ENODEV;
 
         count = min((size_t)(32 * 1024), count);
 
@@ -656,6 +716,10 @@ static unsigned int port_fops_poll(struct file *filp, poll_table *wait)
         port = filp->private_data;
         poll_wait(filp, &port->waitqueue, wait);
 
+        if (!port->guest_connected) {
+                /* Port got unplugged */
+                return POLLHUP;
+        }
         ret = 0;
         if (!will_read_block(port))
                 ret |= POLLIN | POLLRDNORM;
@@ -667,6 +731,8 @@ static unsigned int port_fops_poll(struct file *filp, poll_table *wait)
         return ret;
 }
 
+static void remove_port(struct kref *kref);
+
 static int port_fops_release(struct inode *inode, struct file *filp)
 {
         struct port *port;
@@ -687,6 +753,16 @@ static int port_fops_release(struct inode *inode, struct file *filp)
         reclaim_consumed_buffers(port);
         spin_unlock_irq(&port->outvq_lock);
 
+        /*
+         * Locks aren't necessary here as a port can't be opened after
+         * unplug, and if a port isn't unplugged, a kref would already
+         * exist for the port.  Plus, taking ports_lock here would
+         * create a dependency on other locks taken by functions
+         * inside remove_port if we're the last holder of the port,
+         * creating many problems.
+         */
+        kref_put(&port->kref, remove_port);
+
         return 0;
 }
 
@@ -694,22 +770,31 @@ static int port_fops_open(struct inode *inode, struct file *filp)
 {
         struct cdev *cdev = inode->i_cdev;
         struct port *port;
+        int ret;
 
-        port = container_of(cdev, struct port, cdev);
+        port = find_port_by_devt(cdev->dev);
         filp->private_data = port;
 
+        /* Prevent against a port getting hot-unplugged at the same time */
+        spin_lock_irq(&port->portdev->ports_lock);
+        kref_get(&port->kref);
+        spin_unlock_irq(&port->portdev->ports_lock);
+
         /*
          * Don't allow opening of console port devices -- that's done
          * via /dev/hvc
          */
-        if (is_console_port(port))
-                return -ENXIO;
+        if (is_console_port(port)) {
+                ret = -ENXIO;
+                goto out;
+        }
 
         /* Allow only one process to open a particular port at a time */
         spin_lock_irq(&port->inbuf_lock);
         if (port->guest_connected) {
                 spin_unlock_irq(&port->inbuf_lock);
-                return -EMFILE;
+                ret = -EMFILE;
+                goto out;
         }
 
         port->guest_connected = true;
@@ -724,10 +809,23 @@ static int port_fops_open(struct inode *inode, struct file *filp)
         reclaim_consumed_buffers(port);
         spin_unlock_irq(&port->outvq_lock);
 
+        nonseekable_open(inode, filp);
+
         /* Notify host of port being opened */
         send_control_msg(filp->private_data, VIRTIO_CONSOLE_PORT_OPEN, 1);
 
         return 0;
+out:
+        kref_put(&port->kref, remove_port);
+        return ret;
+}
+
+static int port_fops_fasync(int fd, struct file *filp, int mode)
+{
+        struct port *port;
+
+        port = filp->private_data;
+        return fasync_helper(fd, filp, mode, &port->async_queue);
 }
 
 /*
@@ -743,6 +841,8 @@ static const struct file_operations port_fops = {
         .write = port_fops_write,
         .poll  = port_fops_poll,
         .release = port_fops_release,
+        .fasync = port_fops_fasync,
+        .llseek = no_llseek,
 };
 
 /*
@@ -1001,6 +1101,12 @@ static unsigned int fill_queue(struct virtqueue *vq, spinlock_t *lock)
         return nr_added_bufs;
 }
 
+static void send_sigio_to_port(struct port *port)
+{
+        if (port->async_queue && port->guest_connected)
+                kill_fasync(&port->async_queue, SIGIO, POLL_OUT);
+}
+
 static int add_port(struct ports_device *portdev, u32 id)
 {
         char debugfs_name[16];
@@ -1015,6 +1121,7 @@ static int add_port(struct ports_device *portdev, u32 id)
                 err = -ENOMEM;
                 goto fail;
         }
+        kref_init(&port->kref);
 
         port->portdev = portdev;
         port->id = id;
@@ -1022,6 +1129,7 @@ static int add_port(struct ports_device *portdev, u32 id)
         port->name = NULL;
         port->inbuf = NULL;
         port->cons.hvc = NULL;
+        port->async_queue = NULL;
 
         port->cons.ws.ws_row = port->cons.ws.ws_col = 0;
 
@@ -1032,14 +1140,20 @@ static int add_port(struct ports_device *portdev, u32 id)
         port->in_vq = portdev->in_vqs[port->id];
         port->out_vq = portdev->out_vqs[port->id];
 
-        cdev_init(&port->cdev, &port_fops);
+        port->cdev = cdev_alloc();
+        if (!port->cdev) {
+                dev_err(&port->portdev->vdev->dev, "Error allocating cdev\n");
+                err = -ENOMEM;
+                goto free_port;
+        }
+        port->cdev->ops = &port_fops;
 
         devt = MKDEV(portdev->chr_major, id);
-        err = cdev_add(&port->cdev, devt, 1);
+        err = cdev_add(port->cdev, devt, 1);
         if (err < 0) {
                 dev_err(&port->portdev->vdev->dev,
                         "Error %d adding cdev for port %u\n", err, id);
-                goto free_port;
+                goto free_cdev;
         }
         port->dev = device_create(pdrvdata.class, &port->portdev->vdev->dev,
                                   devt, port, "vport%up%u",
@@ -1104,7 +1218,7 @@ free_inbufs:
 free_device:
         device_destroy(pdrvdata.class, port->dev->devt);
 free_cdev:
-        cdev_del(&port->cdev);
+        cdev_del(port->cdev);
 free_port:
         kfree(port);
 fail:
@@ -1113,21 +1227,45 @@ fail:
         return err;
 }
 
-/* Remove all port-specific data. */
-static int remove_port(struct port *port)
+/* No users remain, remove all port-specific data. */
+static void remove_port(struct kref *kref)
+{
+        struct port *port;
+
+        port = container_of(kref, struct port, kref);
+
+        sysfs_remove_group(&port->dev->kobj, &port_attribute_group);
+        device_destroy(pdrvdata.class, port->dev->devt);
+        cdev_del(port->cdev);
+
+        kfree(port->name);
+
+        debugfs_remove(port->debugfs_file);
+
+        kfree(port);
+}
+
+/*
+ * Port got unplugged.  Remove port from portdev's list and drop the
+ * kref reference.  If no userspace has this port opened, it will
+ * result in immediate removal the port.
+ */
+static void unplug_port(struct port *port)
 {
         struct port_buffer *buf;
 
+        spin_lock_irq(&port->portdev->ports_lock);
+        list_del(&port->list);
+        spin_unlock_irq(&port->portdev->ports_lock);
+
         if (port->guest_connected) {
                 port->guest_connected = false;
                 port->host_connected = false;
                 wake_up_interruptible(&port->waitqueue);
-                send_control_msg(port, VIRTIO_CONSOLE_PORT_OPEN, 0);
-        }
 
-        spin_lock_irq(&port->portdev->ports_lock);
-        list_del(&port->list);
-        spin_unlock_irq(&port->portdev->ports_lock);
+                /* Let the app know the port is going down. */
+                send_sigio_to_port(port);
+        }
 
         if (is_console_port(port)) {
                 spin_lock_irq(&pdrvdata_lock);
@@ -1146,9 +1284,6 @@ static int remove_port(struct port *port)
                 hvc_remove(port->cons.hvc);
 #endif
         }
-        sysfs_remove_group(&port->dev->kobj, &port_attribute_group);
-        device_destroy(pdrvdata.class, port->dev->devt);
-        cdev_del(&port->cdev);
 
         /* Remove unused data this port might have received. */
         discard_port_data(port);
@@ -1159,12 +1294,19 @@ static int remove_port(struct port *port)
         while ((buf = virtqueue_detach_unused_buf(port->in_vq)))
                 free_buf(buf);
 
-        kfree(port->name);
-
-        debugfs_remove(port->debugfs_file);
+        /*
+         * We should just assume the device itself has gone off --
+         * else a close on an open port later will try to send out a
+         * control message.
+         */
+        port->portdev = NULL;
 
-        kfree(port);
-        return 0;
+        /*
+         * Locks around here are not necessary - a port can't be
+         * opened after we removed the port struct from ports_list
+         * above.
+         */
+        kref_put(&port->kref, remove_port);
 }
 
 /* Any private messages that the Host and Guest want to share */
@@ -1203,7 +1345,7 @@ static void handle_control_message(struct ports_device *portdev,
                 add_port(portdev, cpkt->id);
                 break;
         case VIRTIO_CONSOLE_PORT_REMOVE:
-                remove_port(port);
+                unplug_port(port);
                 break;
         case VIRTIO_CONSOLE_CONSOLE_PORT:
                 if (!cpkt->value)
@@ -1245,6 +1387,12 @@ static void handle_control_message(struct ports_device *portdev,
                 spin_lock_irq(&port->outvq_lock);
                 reclaim_consumed_buffers(port);
                 spin_unlock_irq(&port->outvq_lock);
+
+                /*
+                 * If the guest is connected, it'll be interested in
+                 * knowing the host connection state changed.
+                 */
+                send_sigio_to_port(port);
                 break;
         case VIRTIO_CONSOLE_PORT_NAME:
                 /*
@@ -1341,6 +1489,9 @@ static void in_intr(struct virtqueue *vq)
 
         wake_up_interruptible(&port->waitqueue);
 
+        /* Send a SIGIO indicating new data in case the process asked for it */
+        send_sigio_to_port(port);
+
         if (is_console_port(port) && hvc_poll(port->cons.hvc))
                 hvc_kick();
 }
@@ -1577,6 +1728,10 @@ static int __devinit virtcons_probe(struct virtio_device *vdev)
                 add_port(portdev, 0);
         }
 
+        spin_lock_irq(&pdrvdata_lock);
+        list_add_tail(&portdev->list, &pdrvdata.portdevs);
+        spin_unlock_irq(&pdrvdata_lock);
+
         __send_control_msg(portdev, VIRTIO_CONSOLE_BAD_ID,
                            VIRTIO_CONSOLE_DEVICE_READY, 1);
         return 0;
@@ -1600,23 +1755,41 @@ static void virtcons_remove(struct virtio_device *vdev)
 {
         struct ports_device *portdev;
         struct port *port, *port2;
-        struct port_buffer *buf;
-        unsigned int len;
 
         portdev = vdev->priv;
 
+        spin_lock_irq(&pdrvdata_lock);
+        list_del(&portdev->list);
+        spin_unlock_irq(&pdrvdata_lock);
+
+        /* Disable interrupts for vqs */
+        vdev->config->reset(vdev);
+        /* Finish up work that's lined up */
         cancel_work_sync(&portdev->control_work);
 
         list_for_each_entry_safe(port, port2, &portdev->ports, list)
-                remove_port(port);
+                unplug_port(port);
 
         unregister_chrdev(portdev->chr_major, "virtio-portsdev");
 
-        while ((buf = virtqueue_get_buf(portdev->c_ivq, &len)))
-                free_buf(buf);
+        /*
+         * When yanking out a device, we immediately lose the
+         * (device-side) queues.  So there's no point in keeping the
+         * guest side around till we drop our final reference.  This
+         * also means that any ports which are in an open state will
+         * have to just stop using the port, as the vqs are going
+         * away.
+         */
+        if (use_multiport(portdev)) {
+                struct port_buffer *buf;
+                unsigned int len;
 
-        while ((buf = virtqueue_detach_unused_buf(portdev->c_ivq)))
-                free_buf(buf);
+                while ((buf = virtqueue_get_buf(portdev->c_ivq, &len)))
+                        free_buf(buf);
+
+                while ((buf = virtqueue_detach_unused_buf(portdev->c_ivq)))
+                        free_buf(buf);
+        }
 
         vdev->config->del_vqs(vdev);
         kfree(portdev->in_vqs);
@@ -1663,6 +1836,7 @@ static int __init init(void)
                            PTR_ERR(pdrvdata.debugfs_dir));
         }
         INIT_LIST_HEAD(&pdrvdata.consoles);
+        INIT_LIST_HEAD(&pdrvdata.portdevs);
 
         return register_virtio_driver(&virtio_console);
 }
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index 70bb350de996..9dbb28b9559f 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -39,7 +39,7 @@ config EDAC_DEBUG
           there're four debug levels (x=0,1,2,3 from low to high).
           Usually you should select 'N'.
 
- config EDAC_DECODE_MCE
+config EDAC_DECODE_MCE
         tristate "Decode MCEs in human-readable form (only on AMD for now)"
         depends on CPU_SUP_AMD && X86_MCE
         default y
@@ -51,6 +51,16 @@ config EDAC_DEBUG
           which occur really early upon boot, before the module infrastructure
           has been initialized.
 
+config EDAC_MCE_INJ
+        tristate "Simple MCE injection interface over /sysfs"
+        depends on EDAC_DECODE_MCE
+        default n
+        help
+          This is a simple interface to inject MCEs over /sysfs and test
+          the MCE decoding code in EDAC.
+
+          This is currently AMD-only.
+
 config EDAC_MM_EDAC
         tristate "Main Memory EDAC (Error Detection And Correction) reporting"
         help
@@ -66,13 +76,13 @@ config EDAC_MCE
 
 config EDAC_AMD64
         tristate "AMD64 (Opteron, Athlon64) K8, F10h, F11h"
-        depends on EDAC_MM_EDAC && K8_NB && X86_64 && PCI && EDAC_DECODE_MCE
+        depends on EDAC_MM_EDAC && AMD_NB && X86_64 && PCI && EDAC_DECODE_MCE
         help
           Support for error detection and correction on the AMD 64
           Families of Memory Controllers (K8, F10h and F11h)
 
 config EDAC_AMD64_ERROR_INJECTION
-        bool "Sysfs Error Injection facilities"
+        bool "Sysfs HW Error injection facilities"
         depends on EDAC_AMD64
         help
           Recent Opterons (Family 10h and later) provide for Memory Error
diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile
index ca6b1bb24ccc..32c7bc93c525 100644
--- a/drivers/edac/Makefile
+++ b/drivers/edac/Makefile
@@ -17,6 +17,9 @@ ifdef CONFIG_PCI
 edac_core-objs  += edac_pci.o edac_pci_sysfs.o
 endif
 
+obj-$(CONFIG_EDAC_MCE_INJ)              += mce_amd_inj.o
+
+edac_mce_amd-objs                       := mce_amd.o
 obj-$(CONFIG_EDAC_DECODE_MCE)           += edac_mce_amd.o
 
 obj-$(CONFIG_EDAC_AMD76X)               += amd76x_edac.o
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index e7d5d6b5dcf6..8521401bbd75 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -1,5 +1,5 @@
 #include "amd64_edac.h"
-#include <asm/k8.h>
+#include <asm/amd_nb.h>
 
 static struct edac_pci_ctl_info *amd64_ctl_pci;
 
@@ -2073,11 +2073,18 @@ static inline void __amd64_decode_bus_error(struct mem_ctl_info *mci,
                 amd64_handle_ue(mci, info);
 }
 
-void amd64_decode_bus_error(int node_id, struct err_regs *regs)
+void amd64_decode_bus_error(int node_id, struct mce *m, u32 nbcfg)
 {
         struct mem_ctl_info *mci = mci_lookup[node_id];
+        struct err_regs regs;
 
-        __amd64_decode_bus_error(mci, regs);
+        regs.nbsl  = (u32) m->status;
+        regs.nbsh  = (u32)(m->status >> 32);
+        regs.nbeal = (u32) m->addr;
+        regs.nbeah = (u32)(m->addr >> 32);
+        regs.nbcfg = nbcfg;
+
+        __amd64_decode_bus_error(mci, &regs);
 
         /*
          * Check the UE bit of the NB status high register, if set generate some
@@ -2086,7 +2093,7 @@ void amd64_decode_bus_error(int node_id, struct err_regs *regs)
          *
          * FIXME: this should go somewhere else, if at all.
          */
-        if (regs->nbsh & K8_NBSH_UC_ERR && !report_gart_errors)
+        if (regs.nbsh & K8_NBSH_UC_ERR && !report_gart_errors)
                 edac_mc_handle_ue_no_info(mci, "UE bit is set");
 
 }
@@ -2927,7 +2934,7 @@ static int __init amd64_edac_init(void)
          * to finish initialization of the MC instances.
          */
         err = -ENODEV;
-        for (nb = 0; nb < num_k8_northbridges; nb++) {
+        for (nb = 0; nb < k8_northbridges.num; nb++) {
                 if (!pvt_lookup[nb])
                         continue;
 
diff --git a/drivers/edac/amd64_edac.h b/drivers/edac/amd64_edac.h
index 613b9381e71a..044aee4f944d 100644
--- a/drivers/edac/amd64_edac.h
+++ b/drivers/edac/amd64_edac.h
@@ -72,7 +72,7 @@
 #include <linux/edac.h>
 #include <asm/msr.h>
 #include "edac_core.h"
-#include "edac_mce_amd.h"
+#include "mce_amd.h"
 
 #define amd64_printk(level, fmt, arg...) \
         edac_printk(level, "amd64", fmt, ##arg)
@@ -482,11 +482,10 @@ extern const char *rrrr_msgs[16];
 extern const char *to_msgs[2];
 extern const char *pp_msgs[4];
 extern const char *ii_msgs[4];
-extern const char *ext_msgs[32];
 extern const char *htlink_msgs[8];
 
 #ifdef CONFIG_EDAC_DEBUG
-#define NUM_DBG_ATTRS 9
+#define NUM_DBG_ATTRS 5
 #else
 #define NUM_DBG_ATTRS 0
 #endif
diff --git a/drivers/edac/amd64_edac_dbg.c b/drivers/edac/amd64_edac_dbg.c
index 59cf2cf6e11e..e3562288f4ce 100644
--- a/drivers/edac/amd64_edac_dbg.c
+++ b/drivers/edac/amd64_edac_dbg.c
@@ -1,167 +1,16 @@
 #include "amd64_edac.h"
 
-/*
- * accept a hex value and store it into the virtual error register file, field:
- * nbeal and nbeah. Assume virtual error values have already been set for: NBSL,
- * NBSH and NBCFG. Then proceed to map the error values to a MC, CSROW and
- * CHANNEL
- */
-static ssize_t amd64_nbea_store(struct mem_ctl_info *mci, const char *data,
-                                size_t count)
-{
-        struct amd64_pvt *pvt = mci->pvt_info;
-        unsigned long long value;
-        int ret = 0;
-
-        ret = strict_strtoull(data, 16, &value);
-        if (ret != -EINVAL) {
-                debugf0("received NBEA= 0x%llx\n", value);
-
-                /* place the value into the virtual error packet */
-                pvt->ctl_error_info.nbeal = (u32) value;
-                value >>= 32;
-                pvt->ctl_error_info.nbeah = (u32) value;
-
-                /* Process the Mapping request */
-                /* TODO: Add race prevention */
-                amd_decode_nb_mce(pvt->mc_node_id, &pvt->ctl_error_info, 1);
-
-                return count;
-        }
-        return ret;
-}
-
-/* display back what the last NBEA (MCA NB Address (MC4_ADDR)) was written */
-static ssize_t amd64_nbea_show(struct mem_ctl_info *mci, char *data)
-{
-        struct amd64_pvt *pvt = mci->pvt_info;
-        u64 value;
-
-        value = pvt->ctl_error_info.nbeah;
-        value <<= 32;
-        value |= pvt->ctl_error_info.nbeal;
-
-        return sprintf(data, "%llx\n", value);
-}
-
-/* store the NBSL (MCA NB Status Low (MC4_STATUS)) value user desires */
-static ssize_t amd64_nbsl_store(struct mem_ctl_info *mci, const char *data,
-                                size_t count)
-{
-        struct amd64_pvt *pvt = mci->pvt_info;
-        unsigned long value;
-        int ret = 0;
-
-        ret = strict_strtoul(data, 16, &value);
-        if (ret != -EINVAL) {
-                debugf0("received NBSL= 0x%lx\n", value);
-
-                pvt->ctl_error_info.nbsl = (u32) value;
-
-                return count;
-        }
-        return ret;
-}
-
-/* display back what the last NBSL value written */
-static ssize_t amd64_nbsl_show(struct mem_ctl_info *mci, char *data)
-{
-        struct amd64_pvt *pvt = mci->pvt_info;
-        u32 value;
-
-        value = pvt->ctl_error_info.nbsl;
-
-        return sprintf(data, "%x\n", value);
-}
-
-/* store the NBSH (MCA NB Status High) value user desires */
-static ssize_t amd64_nbsh_store(struct mem_ctl_info *mci, const char *data,
-                                size_t count)
-{
-        struct amd64_pvt *pvt = mci->pvt_info;
-        unsigned long value;
-        int ret = 0;
-
-        ret = strict_strtoul(data, 16, &value);
-        if (ret != -EINVAL) {
-                debugf0("received NBSH= 0x%lx\n", value);
-
-                pvt->ctl_error_info.nbsh = (u32) value;
-
-                return count;
-        }
-        return ret;
-}
-
-/* display back what the last NBSH value written */
-static ssize_t amd64_nbsh_show(struct mem_ctl_info *mci, char *data)
-{
-        struct amd64_pvt *pvt = mci->pvt_info;
-        u32 value;
-
-        value = pvt->ctl_error_info.nbsh;
-
-        return sprintf(data, "%x\n", value);
+#define EDAC_DCT_ATTR_SHOW(reg)                                         \
+static ssize_t amd64_##reg##_show(struct mem_ctl_info *mci, char *data) \
+{                                                                       \
+        struct amd64_pvt *pvt = mci->pvt_info;                          \
+                return sprintf(data, "0x%016llx\n", (u64)pvt->reg);     \
 }
 
-/* accept and store the NBCFG (MCA NB Configuration) value user desires */
-static ssize_t amd64_nbcfg_store(struct mem_ctl_info *mci,
-                                        const char *data, size_t count)
-{
-        struct amd64_pvt *pvt = mci->pvt_info;
-        unsigned long value;
-        int ret = 0;
-
-        ret = strict_strtoul(data, 16, &value);
-        if (ret != -EINVAL) {
-                debugf0("received NBCFG= 0x%lx\n", value);
-
-                pvt->ctl_error_info.nbcfg = (u32) value;
-
-                return count;
-        }
-        return ret;
-}
-
-/* various show routines for the controls of a MCI */
-static ssize_t amd64_nbcfg_show(struct mem_ctl_info *mci, char *data)
-{
-        struct amd64_pvt *pvt = mci->pvt_info;
-
-        return sprintf(data, "%x\n", pvt->ctl_error_info.nbcfg);
-}
-
-
-static ssize_t amd64_dhar_show(struct mem_ctl_info *mci, char *data)
-{
-        struct amd64_pvt *pvt = mci->pvt_info;
-
-        return sprintf(data, "%x\n", pvt->dhar);
-}
-
-
-static ssize_t amd64_dbam_show(struct mem_ctl_info *mci, char *data)
-{
-        struct amd64_pvt *pvt = mci->pvt_info;
-
-        return sprintf(data, "%x\n", pvt->dbam0);
-}
-
-
-static ssize_t amd64_topmem_show(struct mem_ctl_info *mci, char *data)
-{
-        struct amd64_pvt *pvt = mci->pvt_info;
-
-        return sprintf(data, "%llx\n", pvt->top_mem);
-}
-
-
-static ssize_t amd64_topmem2_show(struct mem_ctl_info *mci, char *data)
-{
-        struct amd64_pvt *pvt = mci->pvt_info;
-
-        return sprintf(data, "%llx\n", pvt->top_mem2);
-}
+EDAC_DCT_ATTR_SHOW(dhar);
+EDAC_DCT_ATTR_SHOW(dbam0);
+EDAC_DCT_ATTR_SHOW(top_mem);
+EDAC_DCT_ATTR_SHOW(top_mem2);
 
 static ssize_t amd64_hole_show(struct mem_ctl_info *mci, char *data)
 {
@@ -182,38 +31,6 @@ struct mcidev_sysfs_attribute amd64_dbg_attrs[] = {
 
         {
                 .attr = {
-                        .name = "nbea_ctl",
-                        .mode = (S_IRUGO | S_IWUSR)
-                },
-                .show = amd64_nbea_show,
-                .store = amd64_nbea_store,
-        },
-        {
-                .attr = {
-                        .name = "nbsl_ctl",
-                        .mode = (S_IRUGO | S_IWUSR)
-                },
-                .show = amd64_nbsl_show,
-                .store = amd64_nbsl_store,
-        },
-        {
-                .attr = {
-                        .name = "nbsh_ctl",
-                        .mode = (S_IRUGO | S_IWUSR)
-                },
-                .show = amd64_nbsh_show,
-                .store = amd64_nbsh_store,
-        },
-        {
-                .attr = {
-                        .name = "nbcfg_ctl",
-                        .mode = (S_IRUGO | S_IWUSR)
-                },
-                .show = amd64_nbcfg_show,
-                .store = amd64_nbcfg_store,
-        },
-        {
-                .attr = {
                         .name = "dhar",
                         .mode = (S_IRUGO)
                 },
@@ -225,7 +42,7 @@ struct mcidev_sysfs_attribute amd64_dbg_attrs[] = {
                         .name = "dbam",
                         .mode = (S_IRUGO)
                 },
-                .show = amd64_dbam_show,
+                .show = amd64_dbam0_show,
                 .store = NULL,
         },
         {
@@ -233,7 +50,7 @@ struct mcidev_sysfs_attribute amd64_dbg_attrs[] = {
                         .name = "topmem",
                         .mode = (S_IRUGO)
                 },
-                .show = amd64_topmem_show,
+                .show = amd64_top_mem_show,
                 .store = NULL,
         },
         {
@@ -241,7 +58,7 @@ struct mcidev_sysfs_attribute amd64_dbg_attrs[] = {
                         .name = "topmem2",
                         .mode = (S_IRUGO)
                 },
-                .show = amd64_topmem2_show,
+                .show = amd64_top_mem2_show,
                 .store = NULL,
         },
         {
diff --git a/drivers/edac/edac_device_sysfs.c b/drivers/edac/edac_device_sysfs.c
index 070968178a24..2941dca91aae 100644
--- a/drivers/edac/edac_device_sysfs.c
+++ b/drivers/edac/edac_device_sysfs.c
@@ -13,6 +13,7 @@
 #include <linux/ctype.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/edac.h>
 
 #include "edac_core.h"
 #include "edac_module.h"
@@ -235,7 +236,7 @@ int edac_device_register_sysfs_main_kobj(struct edac_device_ctl_info *edac_dev)
         debugf1("%s()\n", __func__);
 
         /* get the /sys/devices/system/edac reference */
-        edac_class = edac_get_edac_class();
+        edac_class = edac_get_sysfs_class();
         if (edac_class == NULL) {
                 debugf1("%s() no edac_class error\n", __func__);
                 err = -ENODEV;
@@ -255,7 +256,7 @@ int edac_device_register_sysfs_main_kobj(struct edac_device_ctl_info *edac_dev)
 
         if (!try_module_get(edac_dev->owner)) {
                 err = -ENODEV;
-                goto err_out;
+                goto err_mod_get;
         }
 
         /* register */
@@ -282,6 +283,9 @@ int edac_device_register_sysfs_main_kobj(struct edac_device_ctl_info *edac_dev)
 err_kobj_reg:
         module_put(edac_dev->owner);
 
+err_mod_get:
+        edac_put_sysfs_class();
+
 err_out:
         return err;
 }
@@ -290,12 +294,11 @@ err_out:
  * edac_device_unregister_sysfs_main_kobj:
  *      the '..../edac/<name>' kobject
  */
-void edac_device_unregister_sysfs_main_kobj(
-                                        struct edac_device_ctl_info *edac_dev)
+void edac_device_unregister_sysfs_main_kobj(struct edac_device_ctl_info *dev)
 {
         debugf0("%s()\n", __func__);
         debugf4("%s() name of kobject is: %s\n",
-                __func__, kobject_name(&edac_dev->kobj));
+                __func__, kobject_name(&dev->kobj));
 
         /*
          * Unregister the edac device's kobject and
@@ -304,7 +307,8 @@ void edac_device_unregister_sysfs_main_kobj(
          *   a) module_put() this module
          *   b) 'kfree' the memory
          */
-        kobject_put(&edac_dev->kobj);
+        kobject_put(&dev->kobj);
+        edac_put_sysfs_class();
 }
 
 /* edac_dev -> instance information */
diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c
index 8aad94d10c0c..a4135860149b 100644
--- a/drivers/edac/edac_mc_sysfs.c
+++ b/drivers/edac/edac_mc_sysfs.c
@@ -11,6 +11,7 @@
 
 #include <linux/ctype.h>
 #include <linux/slab.h>
+#include <linux/edac.h>
 #include <linux/bug.h>
 
 #include "edac_core.h"
@@ -1011,13 +1012,13 @@ void edac_remove_sysfs_mci_device(struct mem_ctl_info *mci)
  */
 int edac_sysfs_setup_mc_kset(void)
 {
-        int err = 0;
+        int err = -EINVAL;
         struct sysdev_class *edac_class;
 
         debugf1("%s()\n", __func__);
 
         /* get the /sys/devices/system/edac class reference */
-        edac_class = edac_get_edac_class();
+        edac_class = edac_get_sysfs_class();
         if (edac_class == NULL) {
                 debugf1("%s() no edac_class error=%d\n", __func__, err);
                 goto fail_out;
@@ -1028,15 +1029,16 @@ int edac_sysfs_setup_mc_kset(void)
         if (!mc_kset) {
                 err = -ENOMEM;
                 debugf1("%s() Failed to register '.../edac/mc'\n", __func__);
-                goto fail_out;
+                goto fail_kset;
         }
 
         debugf1("%s() Registered '.../edac/mc' kobject\n", __func__);
 
         return 0;
 
+fail_kset:
+        edac_put_sysfs_class();
 
-        /* error unwind stack */
 fail_out:
         return err;
 }
@@ -1049,5 +1051,6 @@ fail_out:
 void edac_sysfs_teardown_mc_kset(void)
 {
         kset_unregister(mc_kset);
+        edac_put_sysfs_class();
 }
 
diff --git a/drivers/edac/edac_mce_amd.c b/drivers/edac/edac_mce_amd.c
deleted file mode 100644
index 9014df6f605d..000000000000
--- a/drivers/edac/edac_mce_amd.c
+++ /dev/null
@@ -1,452 +0,0 @@
-#include <linux/module.h>
-#include "edac_mce_amd.h"
-
-static bool report_gart_errors;
-static void (*nb_bus_decoder)(int node_id, struct err_regs *regs);
-
-void amd_report_gart_errors(bool v)
-{
-        report_gart_errors = v;
-}
-EXPORT_SYMBOL_GPL(amd_report_gart_errors);
-
-void amd_register_ecc_decoder(void (*f)(int, struct err_regs *))
-{
-        nb_bus_decoder = f;
-}
-EXPORT_SYMBOL_GPL(amd_register_ecc_decoder);
-
-void amd_unregister_ecc_decoder(void (*f)(int, struct err_regs *))
-{
-        if (nb_bus_decoder) {
-                WARN_ON(nb_bus_decoder != f);
-
-                nb_bus_decoder = NULL;
-        }
-}
-EXPORT_SYMBOL_GPL(amd_unregister_ecc_decoder);
-
-/*
- * string representation for the different MCA reported error types, see F3x48
- * or MSR0000_0411.
- */
-const char *tt_msgs[] = {        /* transaction type */
-        "instruction",
-        "data",
-        "generic",
-        "reserved"
-};
-EXPORT_SYMBOL_GPL(tt_msgs);
-
-const char *ll_msgs[] = {       /* cache level */
-        "L0",
-        "L1",
-        "L2",
-        "L3/generic"
-};
-EXPORT_SYMBOL_GPL(ll_msgs);
-
-const char *rrrr_msgs[] = {
-        "generic",
-        "generic read",
-        "generic write",
-        "data read",
-        "data write",
-        "inst fetch",
-        "prefetch",
-        "evict",
-        "snoop",
-        "reserved RRRR= 9",
-        "reserved RRRR= 10",
-        "reserved RRRR= 11",
-        "reserved RRRR= 12",
-        "reserved RRRR= 13",
-        "reserved RRRR= 14",
-        "reserved RRRR= 15"
-};
-EXPORT_SYMBOL_GPL(rrrr_msgs);
-
-const char *pp_msgs[] = {       /* participating processor */
-        "local node originated (SRC)",
-        "local node responded to request (RES)",
-        "local node observed as 3rd party (OBS)",
-        "generic"
-};
-EXPORT_SYMBOL_GPL(pp_msgs);
-
-const char *to_msgs[] = {
-        "no timeout",
-        "timed out"
-};
-EXPORT_SYMBOL_GPL(to_msgs);
-
-const char *ii_msgs[] = {       /* memory or i/o */
-        "mem access",
-        "reserved",
-        "i/o access",
-        "generic"
-};
-EXPORT_SYMBOL_GPL(ii_msgs);
-
-/*
- * Map the 4 or 5 (family-specific) bits of Extended Error code to the
- * string table.
- */
-const char *ext_msgs[] = {
-        "K8 ECC error",                                 /* 0_0000b */
-        "CRC error on link",                            /* 0_0001b */
-        "Sync error packets on link",                   /* 0_0010b */
-        "Master Abort during link operation",           /* 0_0011b */
-        "Target Abort during link operation",           /* 0_0100b */
-        "Invalid GART PTE entry during table walk",     /* 0_0101b */
-        "Unsupported atomic RMW command received",      /* 0_0110b */
-        "WDT error: NB transaction timeout",            /* 0_0111b */
-        "ECC/ChipKill ECC error",                       /* 0_1000b */
-        "SVM DEV Error",                                /* 0_1001b */
-        "Link Data error",                              /* 0_1010b */
-        "Link/L3/Probe Filter Protocol error",          /* 0_1011b */
-        "NB Internal Arrays Parity error",              /* 0_1100b */
-        "DRAM Address/Control Parity error",            /* 0_1101b */
-        "Link Transmission error",                      /* 0_1110b */
-        "GART/DEV Table Walk Data error"                /* 0_1111b */
-        "Res 0x100 error",                              /* 1_0000b */
-        "Res 0x101 error",                              /* 1_0001b */
-        "Res 0x102 error",                              /* 1_0010b */
-        "Res 0x103 error",                              /* 1_0011b */
-        "Res 0x104 error",                              /* 1_0100b */
-        "Res 0x105 error",                              /* 1_0101b */
-        "Res 0x106 error",                              /* 1_0110b */
-        "Res 0x107 error",                              /* 1_0111b */
-        "Res 0x108 error",                              /* 1_1000b */
-        "Res 0x109 error",                              /* 1_1001b */
-        "Res 0x10A error",                              /* 1_1010b */
-        "Res 0x10B error",                              /* 1_1011b */
-        "ECC error in L3 Cache Data",                   /* 1_1100b */
-        "L3 Cache Tag error",                           /* 1_1101b */
-        "L3 Cache LRU Parity error",                    /* 1_1110b */
-        "Probe Filter error"                            /* 1_1111b */
-};
-EXPORT_SYMBOL_GPL(ext_msgs);
-
-static void amd_decode_dc_mce(u64 mc0_status)
-{
-        u32 ec  = mc0_status & 0xffff;
-        u32 xec = (mc0_status >> 16) & 0xf;
-
-        pr_emerg("Data Cache Error");
-
-        if (xec == 1 && TLB_ERROR(ec))
-                pr_cont(": %s TLB multimatch.\n", LL_MSG(ec));
-        else if (xec == 0) {
-                if (mc0_status & (1ULL << 40))
-                        pr_cont(" during Data Scrub.\n");
-                else if (TLB_ERROR(ec))
-                        pr_cont(": %s TLB parity error.\n", LL_MSG(ec));
-                else if (MEM_ERROR(ec)) {
-                        u8 ll   = ec & 0x3;
-                        u8 tt   = (ec >> 2) & 0x3;
-                        u8 rrrr = (ec >> 4) & 0xf;
-
-                        /* see F10h BKDG (31116), Table 92. */
-                        if (ll == 0x1) {
-                                if (tt != 0x1)
-                                        goto wrong_dc_mce;
-
-                                pr_cont(": Data/Tag %s error.\n", RRRR_MSG(ec));
-
-                        } else if (ll == 0x2 && rrrr == 0x3)
-                                pr_cont(" during L1 linefill from L2.\n");
-                        else
-                                goto wrong_dc_mce;
-                } else if (BUS_ERROR(ec) && boot_cpu_data.x86 == 0xf)
-                        pr_cont(" during system linefill.\n");
-                else
-                        goto wrong_dc_mce;
-        } else
-                goto wrong_dc_mce;
-
-        return;
-
-wrong_dc_mce:
-        pr_warning("Corrupted DC MCE info?\n");
-}
-
-static void amd_decode_ic_mce(u64 mc1_status)
-{
-        u32 ec  = mc1_status & 0xffff;
-        u32 xec = (mc1_status >> 16) & 0xf;
-
-        pr_emerg("Instruction Cache Error");
-
-        if (xec == 1 && TLB_ERROR(ec))
-                pr_cont(": %s TLB multimatch.\n", LL_MSG(ec));
-        else if (xec == 0) {
-                if (TLB_ERROR(ec))
-                        pr_cont(": %s TLB Parity error.\n", LL_MSG(ec));
-                else if (BUS_ERROR(ec)) {
-                        if (boot_cpu_data.x86 == 0xf &&
-                            (mc1_status & (1ULL << 58)))
-                                pr_cont(" during system linefill.\n");
-                        else
-                                pr_cont(" during attempted NB data read.\n");
-                } else if (MEM_ERROR(ec)) {
-                        u8 ll   = ec & 0x3;
-                        u8 rrrr = (ec >> 4) & 0xf;
-
-                        if (ll == 0x2)
-                                pr_cont(" during a linefill from L2.\n");
-                        else if (ll == 0x1) {
-
-                                switch (rrrr) {
-                                case 0x5:
-                                        pr_cont(": Parity error during "
-                                               "data load.\n");
-                                        break;
-
-                                case 0x7:
-                                        pr_cont(": Copyback Parity/Victim"
-                                                " error.\n");
-                                        break;
-
-                                case 0x8:
-                                        pr_cont(": Tag Snoop error.\n");
-                                        break;
-
-                                default:
-                                        goto wrong_ic_mce;
-                                        break;
-                                }
-                        }
-                } else
-                        goto wrong_ic_mce;
-        } else
-                goto wrong_ic_mce;
-
-        return;
-
-wrong_ic_mce:
-        pr_warning("Corrupted IC MCE info?\n");
-}
-
-static void amd_decode_bu_mce(u64 mc2_status)
-{
-        u32 ec = mc2_status & 0xffff;
-        u32 xec = (mc2_status >> 16) & 0xf;
-
-        pr_emerg("Bus Unit Error");
-
-        if (xec == 0x1)
-                pr_cont(" in the write data buffers.\n");
-        else if (xec == 0x3)
-                pr_cont(" in the victim data buffers.\n");
-        else if (xec == 0x2 && MEM_ERROR(ec))
-                pr_cont(": %s error in the L2 cache tags.\n", RRRR_MSG(ec));
-        else if (xec == 0x0) {
-                if (TLB_ERROR(ec))
-                        pr_cont(": %s error in a Page Descriptor Cache or "
-                                "Guest TLB.\n", TT_MSG(ec));
-                else if (BUS_ERROR(ec))
-                        pr_cont(": %s/ECC error in data read from NB: %s.\n",
-                                RRRR_MSG(ec), PP_MSG(ec));
-                else if (MEM_ERROR(ec)) {
-                        u8 rrrr = (ec >> 4) & 0xf;
-
-                        if (rrrr >= 0x7)
-                                pr_cont(": %s error during data copyback.\n",
-                                        RRRR_MSG(ec));
-                        else if (rrrr <= 0x1)
-                                pr_cont(": %s parity/ECC error during data "
-                                        "access from L2.\n", RRRR_MSG(ec));
-                        else
-                                goto wrong_bu_mce;
-                } else
-                        goto wrong_bu_mce;
-        } else
-                goto wrong_bu_mce;
-
-        return;
-
-wrong_bu_mce:
-        pr_warning("Corrupted BU MCE info?\n");
-}
-
-static void amd_decode_ls_mce(u64 mc3_status)
-{
-        u32 ec  = mc3_status & 0xffff;
-        u32 xec = (mc3_status >> 16) & 0xf;
-
-        pr_emerg("Load Store Error");
-
-        if (xec == 0x0) {
-                u8 rrrr = (ec >> 4) & 0xf;
-
-                if (!BUS_ERROR(ec) || (rrrr != 0x3 && rrrr != 0x4))
-                        goto wrong_ls_mce;
-
-                pr_cont(" during %s.\n", RRRR_MSG(ec));
-        }
-        return;
-
-wrong_ls_mce:
-        pr_warning("Corrupted LS MCE info?\n");
-}
-
-void amd_decode_nb_mce(int node_id, struct err_regs *regs, int handle_errors)
-{
-        u32 ec  = ERROR_CODE(regs->nbsl);
-
-        if (!handle_errors)
-                return;
-
-        /*
-         * GART TLB error reporting is disabled by default. Bail out early.
-         */
-        if (TLB_ERROR(ec) && !report_gart_errors)
-                return;
-
-        pr_emerg("Northbridge Error, node %d", node_id);
-
-        /*
-         * F10h, revD can disable ErrCpu[3:0] so check that first and also the
-         * value encoding has changed so interpret those differently
-         */
-        if ((boot_cpu_data.x86 == 0x10) &&
-            (boot_cpu_data.x86_model > 7)) {
-                if (regs->nbsh & K8_NBSH_ERR_CPU_VAL)
-                        pr_cont(", core: %u\n", (u8)(regs->nbsh & 0xf));
-        } else {
-                u8 assoc_cpus = regs->nbsh & 0xf;
-
-                if (assoc_cpus > 0)
-                        pr_cont(", core: %d", fls(assoc_cpus) - 1);
-
-                pr_cont("\n");
-        }
-
-        pr_emerg("%s.\n", EXT_ERR_MSG(regs->nbsl));
-
-        if (BUS_ERROR(ec) && nb_bus_decoder)
-                nb_bus_decoder(node_id, regs);
-}
-EXPORT_SYMBOL_GPL(amd_decode_nb_mce);
-
-static void amd_decode_fr_mce(u64 mc5_status)
-{
-        /* we have only one error signature so match all fields at once. */
-        if ((mc5_status & 0xffff) == 0x0f0f)
-                pr_emerg(" FR Error: CPU Watchdog timer expire.\n");
-        else
-                pr_warning("Corrupted FR MCE info?\n");
-}
-
-static inline void amd_decode_err_code(unsigned int ec)
-{
-        if (TLB_ERROR(ec)) {
-                pr_emerg("Transaction: %s, Cache Level %s\n",
-                         TT_MSG(ec), LL_MSG(ec));
-        } else if (MEM_ERROR(ec)) {
-                pr_emerg("Transaction: %s, Type: %s, Cache Level: %s",
-                         RRRR_MSG(ec), TT_MSG(ec), LL_MSG(ec));
-        } else if (BUS_ERROR(ec)) {
-                pr_emerg("Transaction type: %s(%s), %s, Cache Level: %s, "
-                         "Participating Processor: %s\n",
-                          RRRR_MSG(ec), II_MSG(ec), TO_MSG(ec), LL_MSG(ec),
-                          PP_MSG(ec));
-        } else
-                pr_warning("Huh? Unknown MCE error 0x%x\n", ec);
-}
-
-static int amd_decode_mce(struct notifier_block *nb, unsigned long val,
-                           void *data)
-{
-        struct mce *m = (struct mce *)data;
-        struct err_regs regs;
-        int node, ecc;
-
-        pr_emerg("MC%d_STATUS: ", m->bank);
-
-        pr_cont("%sorrected error, other errors lost: %s, "
-                 "CPU context corrupt: %s",
-                 ((m->status & MCI_STATUS_UC) ? "Unc"  : "C"),
-                 ((m->status & MCI_STATUS_OVER) ? "yes"  : "no"),
-                 ((m->status & MCI_STATUS_PCC) ? "yes" : "no"));
-
-        /* do the two bits[14:13] together */
-        ecc = (m->status >> 45) & 0x3;
-        if (ecc)
-                pr_cont(", %sECC Error", ((ecc == 2) ? "C" : "U"));
-
-        pr_cont("\n");
-
-        switch (m->bank) {
-        case 0:
-                amd_decode_dc_mce(m->status);
-                break;
-
-        case 1:
-                amd_decode_ic_mce(m->status);
-                break;
-
-        case 2:
-                amd_decode_bu_mce(m->status);
-                break;
-
-        case 3:
-                amd_decode_ls_mce(m->status);
-                break;
-
-        case 4:
-                regs.nbsl  = (u32) m->status;
-                regs.nbsh  = (u32)(m->status >> 32);
-                regs.nbeal = (u32) m->addr;
-                regs.nbeah = (u32)(m->addr >> 32);
-                node       = amd_get_nb_id(m->extcpu);
-
-                amd_decode_nb_mce(node, &regs, 1);
-                break;
-
-        case 5:
-                amd_decode_fr_mce(m->status);
-                break;
-
-        default:
-                break;
-        }
-
-        amd_decode_err_code(m->status & 0xffff);
-
-        return NOTIFY_STOP;
-}
-
-static struct notifier_block amd_mce_dec_nb = {
-        .notifier_call  = amd_decode_mce,
-};
-
-static int __init mce_amd_init(void)
-{
-        /*
-         * We can decode MCEs for K8, F10h and F11h CPUs:
-         */
-        if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
-                return 0;
-
-        if (boot_cpu_data.x86 < 0xf || boot_cpu_data.x86 > 0x11)
-                return 0;
-
-        atomic_notifier_chain_register(&x86_mce_decoder_chain, &amd_mce_dec_nb);
-
-        return 0;
-}
-early_initcall(mce_amd_init);
-
-#ifdef MODULE
-static void __exit mce_amd_exit(void)
-{
-        atomic_notifier_chain_unregister(&x86_mce_decoder_chain, &amd_mce_dec_nb);
-}
-
-MODULE_DESCRIPTION("AMD MCE decoder");
-MODULE_ALIAS("edac-mce-amd");
-MODULE_LICENSE("GPL");
-module_exit(mce_amd_exit);
-#endif
diff --git a/drivers/edac/edac_module.c b/drivers/edac/edac_module.c
index 7e1374afd967..be4b075c3098 100644
--- a/drivers/edac/edac_module.c
+++ b/drivers/edac/edac_module.c
@@ -27,15 +27,6 @@ EXPORT_SYMBOL_GPL(edac_debug_level);
 struct workqueue_struct *edac_workqueue;
 
 /*
- * sysfs object: /sys/devices/system/edac
- *      need to export to other files in this modules
- */
-static struct sysdev_class edac_class = {
-        .name = "edac",
-};
-static int edac_class_valid;
-
-/*
  * edac_op_state_to_string()
  */
 char *edac_op_state_to_string(int opstate)
@@ -55,60 +46,6 @@ char *edac_op_state_to_string(int opstate)
 }
 
 /*
- * edac_get_edac_class()
- *
- *      return pointer to the edac class of 'edac'
- */
-struct sysdev_class *edac_get_edac_class(void)
-{
-        struct sysdev_class *classptr = NULL;
-
-        if (edac_class_valid)
-                classptr = &edac_class;
-
-        return classptr;
-}
-
-/*
- * edac_register_sysfs_edac_name()
- *
- *      register the 'edac' into /sys/devices/system
- *
- * return:
- *      0  success
- *      !0 error
- */
-static int edac_register_sysfs_edac_name(void)
-{
-        int err;
-
-        /* create the /sys/devices/system/edac directory */
-        err = sysdev_class_register(&edac_class);
-
-        if (err) {
-                debugf1("%s() error=%d\n", __func__, err);
-                return err;
-        }
-
-        edac_class_valid = 1;
-        return 0;
-}
-
-/*
- * sysdev_class_unregister()
- *
- *      unregister the 'edac' from /sys/devices/system
- */
-static void edac_unregister_sysfs_edac_name(void)
-{
-        /* only if currently registered, then unregister it */
-        if (edac_class_valid)
-                sysdev_class_unregister(&edac_class);
-
-        edac_class_valid = 0;
-}
-
-/*
  * edac_workqueue_setup
  *      initialize the edac work queue for polling operations
  */
@@ -154,21 +91,11 @@ static int __init edac_init(void)
         edac_pci_clear_parity_errors();
 
         /*
-         * perform the registration of the /sys/devices/system/edac class object
-         */
-        if (edac_register_sysfs_edac_name()) {
-                edac_printk(KERN_ERR, EDAC_MC,
-                        "Error initializing 'edac' kobject\n");
-                err = -ENODEV;
-                goto error;
-        }
-
-        /*
          * now set up the mc_kset under the edac class object
          */
         err = edac_sysfs_setup_mc_kset();
         if (err)
-                goto sysfs_setup_fail;
+                goto error;
 
         /* Setup/Initialize the workq for this core */
         err = edac_workqueue_setup();
@@ -183,9 +110,6 @@ static int __init edac_init(void)
 workq_fail:
         edac_sysfs_teardown_mc_kset();
 
-sysfs_setup_fail:
-        edac_unregister_sysfs_edac_name();
-
 error:
         return err;
 }
@@ -201,7 +125,6 @@ static void __exit edac_exit(void)
         /* tear down the various subsystems */
         edac_workqueue_teardown();
         edac_sysfs_teardown_mc_kset();
-        edac_unregister_sysfs_edac_name();
 }
 
 /*
diff --git a/drivers/edac/edac_module.h b/drivers/edac/edac_module.h
index 233d4798c3aa..17aabb7b90ec 100644
--- a/drivers/edac/edac_module.h
+++ b/drivers/edac/edac_module.h
@@ -42,7 +42,6 @@ extern void edac_device_unregister_sysfs_main_kobj(
                                 struct edac_device_ctl_info *edac_dev);
 extern int edac_device_create_sysfs(struct edac_device_ctl_info *edac_dev);
 extern void edac_device_remove_sysfs(struct edac_device_ctl_info *edac_dev);
-extern struct sysdev_class *edac_get_edac_class(void);
 
 /* edac core workqueue: single CPU mode */
 extern struct workqueue_struct *edac_workqueue;
diff --git a/drivers/edac/edac_pci_sysfs.c b/drivers/edac/edac_pci_sysfs.c
index c39697df9cb4..023b01cb5175 100644
--- a/drivers/edac/edac_pci_sysfs.c
+++ b/drivers/edac/edac_pci_sysfs.c
@@ -7,7 +7,7 @@
  *
  */
 #include <linux/module.h>
-#include <linux/sysdev.h>
+#include <linux/edac.h>
 #include <linux/slab.h>
 #include <linux/ctype.h>
 
@@ -354,7 +354,7 @@ static int edac_pci_main_kobj_setup(void)
         /* First time, so create the main kobject and its
          * controls and atributes
          */
-        edac_class = edac_get_edac_class();
+        edac_class = edac_get_sysfs_class();
         if (edac_class == NULL) {
                 debugf1("%s() no edac_class\n", __func__);
                 err = -ENODEV;
@@ -368,7 +368,7 @@ static int edac_pci_main_kobj_setup(void)
         if (!try_module_get(THIS_MODULE)) {
                 debugf1("%s() try_module_get() failed\n", __func__);
                 err = -ENODEV;
-                goto decrement_count_fail;
+                goto mod_get_fail;
         }
 
         edac_pci_top_main_kobj = kzalloc(sizeof(struct kobject), GFP_KERNEL);
@@ -403,6 +403,9 @@ kobject_init_and_add_fail:
 kzalloc_fail:
         module_put(THIS_MODULE);
 
+mod_get_fail:
+        edac_put_sysfs_class();
+
 decrement_count_fail:
         /* if are on this error exit, nothing to tear down */
         atomic_dec(&edac_pci_sysfs_refcount);
@@ -429,6 +432,7 @@ static void edac_pci_main_kobj_teardown(void)
                         __func__);
                 kobject_put(edac_pci_top_main_kobj);
         }
+        edac_put_sysfs_class();
 }
 
 /*
diff --git a/drivers/edac/edac_stub.c b/drivers/edac/edac_stub.c
index 20b428aa155e..aab970760b75 100644
--- a/drivers/edac/edac_stub.c
+++ b/drivers/edac/edac_stub.c
@@ -3,10 +3,13 @@
  *
  * Author: Dave Jiang <djiang@mvista.com>
  *
- * 2007 (c) MontaVista Software, Inc. This file is licensed under
- * the terms of the GNU General Public License version 2. This program
- * is licensed "as is" without any warranty of any kind, whether express
- * or implied.
+ * 2007 (c) MontaVista Software, Inc.
+ * 2010 (c) Advanced Micro Devices Inc.
+ *          Borislav Petkov <borislav.petkov@amd.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
  *
  */
 #include <linux/module.h>
@@ -23,6 +26,8 @@ EXPORT_SYMBOL_GPL(edac_handlers);
 int edac_err_assert = 0;
 EXPORT_SYMBOL_GPL(edac_err_assert);
 
+static atomic_t edac_class_valid = ATOMIC_INIT(0);
+
 /*
  * called to determine if there is an EDAC driver interested in
  * knowing an event (such as NMI) occurred
@@ -44,3 +49,41 @@ void edac_atomic_assert_error(void)
         edac_err_assert++;
 }
 EXPORT_SYMBOL_GPL(edac_atomic_assert_error);
+
+/*
+ * sysfs object: /sys/devices/system/edac
+ *      need to export to other files
+ */
+struct sysdev_class edac_class = {
+        .name = "edac",
+};
+EXPORT_SYMBOL_GPL(edac_class);
+
+/* return pointer to the 'edac' node in sysfs */
+struct sysdev_class *edac_get_sysfs_class(void)
+{
+        int err = 0;
+
+        if (atomic_read(&edac_class_valid))
+                goto out;
+
+        /* create the /sys/devices/system/edac directory */
+        err = sysdev_class_register(&edac_class);
+        if (err) {
+                printk(KERN_ERR "Error registering toplevel EDAC sysfs dir\n");
+                return NULL;
+        }
+
+out:
+        atomic_inc(&edac_class_valid);
+        return &edac_class;
+}
+EXPORT_SYMBOL_GPL(edac_get_sysfs_class);
+
+void edac_put_sysfs_class(void)
+{
+        /* last user unregisters it */
+        if (atomic_dec_and_test(&edac_class_valid))
+                sysdev_class_unregister(&edac_class);
+}
+EXPORT_SYMBOL_GPL(edac_put_sysfs_class);
diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
new file mode 100644
index 000000000000..c0181093b490
--- /dev/null
+++ b/drivers/edac/mce_amd.c
@@ -0,0 +1,680 @@
+#include <linux/module.h>
+#include <linux/slab.h>
+
+#include "mce_amd.h"
+
+static struct amd_decoder_ops *fam_ops;
+
+static u8 nb_err_cpumask = 0xf;
+
+static bool report_gart_errors;
+static void (*nb_bus_decoder)(int node_id, struct mce *m, u32 nbcfg);
+
+void amd_report_gart_errors(bool v)
+{
+        report_gart_errors = v;
+}
+EXPORT_SYMBOL_GPL(amd_report_gart_errors);
+
+void amd_register_ecc_decoder(void (*f)(int, struct mce *, u32))
+{
+        nb_bus_decoder = f;
+}
+EXPORT_SYMBOL_GPL(amd_register_ecc_decoder);
+
+void amd_unregister_ecc_decoder(void (*f)(int, struct mce *, u32))
+{
+        if (nb_bus_decoder) {
+                WARN_ON(nb_bus_decoder != f);
+
+                nb_bus_decoder = NULL;
+        }
+}
+EXPORT_SYMBOL_GPL(amd_unregister_ecc_decoder);
+
+/*
+ * string representation for the different MCA reported error types, see F3x48
+ * or MSR0000_0411.
+ */
+
+/* transaction type */
+const char *tt_msgs[] = { "INSN", "DATA", "GEN", "RESV" };
+EXPORT_SYMBOL_GPL(tt_msgs);
+
+/* cache level */
+const char *ll_msgs[] = { "RESV", "L1", "L2", "L3/GEN" };
+EXPORT_SYMBOL_GPL(ll_msgs);
+
+/* memory transaction type */
+const char *rrrr_msgs[] = {
+       "GEN", "RD", "WR", "DRD", "DWR", "IRD", "PRF", "EV", "SNP"
+};
+EXPORT_SYMBOL_GPL(rrrr_msgs);
+
+/* participating processor */
+const char *pp_msgs[] = { "SRC", "RES", "OBS", "GEN" };
+EXPORT_SYMBOL_GPL(pp_msgs);
+
+/* request timeout */
+const char *to_msgs[] = { "no timeout", "timed out" };
+EXPORT_SYMBOL_GPL(to_msgs);
+
+/* memory or i/o */
+const char *ii_msgs[] = { "MEM", "RESV", "IO", "GEN" };
+EXPORT_SYMBOL_GPL(ii_msgs);
+
+static const char *f10h_nb_mce_desc[] = {
+        "HT link data error",
+        "Protocol error (link, L3, probe filter, etc.)",
+        "Parity error in NB-internal arrays",
+        "Link Retry due to IO link transmission error",
+        "L3 ECC data cache error",
+        "ECC error in L3 cache tag",
+        "L3 LRU parity bits error",
+        "ECC Error in the Probe Filter directory"
+};
+
+static bool f12h_dc_mce(u16 ec)
+{
+        bool ret = false;
+
+        if (MEM_ERROR(ec)) {
+                u8 ll = ec & 0x3;
+                ret = true;
+
+                if (ll == LL_L2)
+                        pr_cont("during L1 linefill from L2.\n");
+                else if (ll == LL_L1)
+                        pr_cont("Data/Tag %s error.\n", RRRR_MSG(ec));
+                else
+                        ret = false;
+        }
+        return ret;
+}
+
+static bool f10h_dc_mce(u16 ec)
+{
+        u8 r4  = (ec >> 4) & 0xf;
+        u8 ll  = ec & 0x3;
+
+        if (r4 == R4_GEN && ll == LL_L1) {
+                pr_cont("during data scrub.\n");
+                return true;
+        }
+        return f12h_dc_mce(ec);
+}
+
+static bool k8_dc_mce(u16 ec)
+{
+        if (BUS_ERROR(ec)) {
+                pr_cont("during system linefill.\n");
+                return true;
+        }
+
+        return f10h_dc_mce(ec);
+}
+
+static bool f14h_dc_mce(u16 ec)
+{
+        u8 r4    = (ec >> 4) & 0xf;
+        u8 ll    = ec & 0x3;
+        u8 tt    = (ec >> 2) & 0x3;
+        u8 ii    = tt;
+        bool ret = true;
+
+        if (MEM_ERROR(ec)) {
+
+                if (tt != TT_DATA || ll != LL_L1)
+                        return false;
+
+                switch (r4) {
+                case R4_DRD:
+                case R4_DWR:
+                        pr_cont("Data/Tag parity error due to %s.\n",
+                                (r4 == R4_DRD ? "load/hw prf" : "store"));
+                        break;
+                case R4_EVICT:
+                        pr_cont("Copyback parity error on a tag miss.\n");
+                        break;
+                case R4_SNOOP:
+                        pr_cont("Tag parity error during snoop.\n");
+                        break;
+                default:
+                        ret = false;
+                }
+        } else if (BUS_ERROR(ec)) {
+
+                if ((ii != II_MEM && ii != II_IO) || ll != LL_LG)
+                        return false;
+
+                pr_cont("System read data error on a ");
+
+                switch (r4) {
+                case R4_RD:
+                        pr_cont("TLB reload.\n");
+                        break;
+                case R4_DWR:
+                        pr_cont("store.\n");
+                        break;
+                case R4_DRD:
+                        pr_cont("load.\n");
+                        break;
+                default:
+                        ret = false;
+                }
+        } else {
+                ret = false;
+        }
+
+        return ret;
+}
+
+static void amd_decode_dc_mce(struct mce *m)
+{
+        u16 ec = m->status & 0xffff;
+        u8 xec = (m->status >> 16) & 0xf;
+
+        pr_emerg(HW_ERR "Data Cache Error: ");
+
+        /* TLB error signatures are the same across families */
+        if (TLB_ERROR(ec)) {
+                u8 tt = (ec >> 2) & 0x3;
+
+                if (tt == TT_DATA) {
+                        pr_cont("%s TLB %s.\n", LL_MSG(ec),
+                                (xec ? "multimatch" : "parity error"));
+                        return;
+                }
+                else
+                        goto wrong_dc_mce;
+        }
+
+        if (!fam_ops->dc_mce(ec))
+                goto wrong_dc_mce;
+
+        return;
+
+wrong_dc_mce:
+        pr_emerg(HW_ERR "Corrupted DC MCE info?\n");
+}
+
+static bool k8_ic_mce(u16 ec)
+{
+        u8 ll    = ec & 0x3;
+        u8 r4    = (ec >> 4) & 0xf;
+        bool ret = true;
+
+        if (!MEM_ERROR(ec))
+                return false;
+
+        if (ll == 0x2)
+                pr_cont("during a linefill from L2.\n");
+        else if (ll == 0x1) {
+                switch (r4) {
+                case R4_IRD:
+                        pr_cont("Parity error during data load.\n");
+                        break;
+
+                case R4_EVICT:
+                        pr_cont("Copyback Parity/Victim error.\n");
+                        break;
+
+                case R4_SNOOP:
+                        pr_cont("Tag Snoop error.\n");
+                        break;
+
+                default:
+                        ret = false;
+                        break;
+                }
+        } else
+                ret = false;
+
+        return ret;
+}
+
+static bool f14h_ic_mce(u16 ec)
+{
+        u8 ll    = ec & 0x3;
+        u8 tt    = (ec >> 2) & 0x3;
+        u8 r4  = (ec >> 4) & 0xf;
+        bool ret = true;
+
+        if (MEM_ERROR(ec)) {
+                if (tt != 0 || ll != 1)
+                        ret = false;
+
+                if (r4 == R4_IRD)
+                        pr_cont("Data/tag array parity error for a tag hit.\n");
+                else if (r4 == R4_SNOOP)
+                        pr_cont("Tag error during snoop/victimization.\n");
+                else
+                        ret = false;
+        }
+        return ret;
+}
+
+static void amd_decode_ic_mce(struct mce *m)
+{
+        u16 ec = m->status & 0xffff;
+        u8 xec = (m->status >> 16) & 0xf;
+
+        pr_emerg(HW_ERR "Instruction Cache Error: ");
+
+        if (TLB_ERROR(ec))
+                pr_cont("%s TLB %s.\n", LL_MSG(ec),
+                        (xec ? "multimatch" : "parity error"));
+        else if (BUS_ERROR(ec)) {
+                bool k8 = (boot_cpu_data.x86 == 0xf && (m->status & BIT_64(58)));
+
+                pr_cont("during %s.\n", (k8 ? "system linefill" : "NB data read"));
+        } else if (fam_ops->ic_mce(ec))
+                ;
+        else
+                pr_emerg(HW_ERR "Corrupted IC MCE info?\n");
+}
+
+static void amd_decode_bu_mce(struct mce *m)
+{
+        u32 ec = m->status & 0xffff;
+        u32 xec = (m->status >> 16) & 0xf;
+
+        pr_emerg(HW_ERR "Bus Unit Error");
+
+        if (xec == 0x1)
+                pr_cont(" in the write data buffers.\n");
+        else if (xec == 0x3)
+                pr_cont(" in the victim data buffers.\n");
+        else if (xec == 0x2 && MEM_ERROR(ec))
+                pr_cont(": %s error in the L2 cache tags.\n", RRRR_MSG(ec));
+        else if (xec == 0x0) {
+                if (TLB_ERROR(ec))
+                        pr_cont(": %s error in a Page Descriptor Cache or "
+                                "Guest TLB.\n", TT_MSG(ec));
+                else if (BUS_ERROR(ec))
+                        pr_cont(": %s/ECC error in data read from NB: %s.\n",
+                                RRRR_MSG(ec), PP_MSG(ec));
+                else if (MEM_ERROR(ec)) {
+                        u8 rrrr = (ec >> 4) & 0xf;
+
+                        if (rrrr >= 0x7)
+                                pr_cont(": %s error during data copyback.\n",
+                                        RRRR_MSG(ec));
+                        else if (rrrr <= 0x1)
+                                pr_cont(": %s parity/ECC error during data "
+                                        "access from L2.\n", RRRR_MSG(ec));
+                        else
+                                goto wrong_bu_mce;
+                } else
+                        goto wrong_bu_mce;
+        } else
+                goto wrong_bu_mce;
+
+        return;
+
+wrong_bu_mce:
+        pr_emerg(HW_ERR "Corrupted BU MCE info?\n");
+}
+
+static void amd_decode_ls_mce(struct mce *m)
+{
+        u16 ec = m->status & 0xffff;
+        u8 xec = (m->status >> 16) & 0xf;
+
+        if (boot_cpu_data.x86 == 0x14) {
+                pr_emerg("You shouldn't be seeing an LS MCE on this cpu family,"
+                         " please report on LKML.\n");
+                return;
+        }
+
+        pr_emerg(HW_ERR "Load Store Error");
+
+        if (xec == 0x0) {
+                u8 r4 = (ec >> 4) & 0xf;
+
+                if (!BUS_ERROR(ec) || (r4 != R4_DRD && r4 != R4_DWR))
+                        goto wrong_ls_mce;
+
+                pr_cont(" during %s.\n", RRRR_MSG(ec));
+        } else
+                goto wrong_ls_mce;
+
+        return;
+
+wrong_ls_mce:
+        pr_emerg(HW_ERR "Corrupted LS MCE info?\n");
+}
+
+static bool k8_nb_mce(u16 ec, u8 xec)
+{
+        bool ret = true;
+
+        switch (xec) {
+        case 0x1:
+                pr_cont("CRC error detected on HT link.\n");
+                break;
+
+        case 0x5:
+                pr_cont("Invalid GART PTE entry during GART table walk.\n");
+                break;
+
+        case 0x6:
+                pr_cont("Unsupported atomic RMW received from an IO link.\n");
+                break;
+
+        case 0x0:
+        case 0x8:
+                if (boot_cpu_data.x86 == 0x11)
+                        return false;
+
+                pr_cont("DRAM ECC error detected on the NB.\n");
+                break;
+
+        case 0xd:
+                pr_cont("Parity error on the DRAM addr/ctl signals.\n");
+                break;
+
+        default:
+                ret = false;
+                break;
+        }
+
+        return ret;
+}
+
+static bool f10h_nb_mce(u16 ec, u8 xec)
+{
+        bool ret = true;
+        u8 offset = 0;
+
+        if (k8_nb_mce(ec, xec))
+                return true;
+
+        switch(xec) {
+        case 0xa ... 0xc:
+                offset = 10;
+                break;
+
+        case 0xe:
+                offset = 11;
+                break;
+
+        case 0xf:
+                if (TLB_ERROR(ec))
+                        pr_cont("GART Table Walk data error.\n");
+                else if (BUS_ERROR(ec))
+                        pr_cont("DMA Exclusion Vector Table Walk error.\n");
+                else
+                        ret = false;
+
+                goto out;
+                break;
+
+        case 0x1c ... 0x1f:
+                offset = 24;
+                break;
+
+        default:
+                ret = false;
+
+                goto out;
+                break;
+        }
+
+        pr_cont("%s.\n", f10h_nb_mce_desc[xec - offset]);
+
+out:
+        return ret;
+}
+
+static bool nb_noop_mce(u16 ec, u8 xec)
+{
+        return false;
+}
+
+void amd_decode_nb_mce(int node_id, struct mce *m, u32 nbcfg)
+{
+        u8 xec   = (m->status >> 16) & 0x1f;
+        u16 ec   = m->status & 0xffff;
+        u32 nbsh = (u32)(m->status >> 32);
+
+        pr_emerg(HW_ERR "Northbridge Error, node %d: ", node_id);
+
+        /*
+         * F10h, revD can disable ErrCpu[3:0] so check that first and also the
+         * value encoding has changed so interpret those differently
+         */
+        if ((boot_cpu_data.x86 == 0x10) &&
+            (boot_cpu_data.x86_model > 7)) {
+                if (nbsh & K8_NBSH_ERR_CPU_VAL)
+                        pr_cont(", core: %u", (u8)(nbsh & nb_err_cpumask));
+        } else {
+                u8 assoc_cpus = nbsh & nb_err_cpumask;
+
+                if (assoc_cpus > 0)
+                        pr_cont(", core: %d", fls(assoc_cpus) - 1);
+        }
+
+        switch (xec) {
+        case 0x2:
+                pr_cont("Sync error (sync packets on HT link detected).\n");
+                return;
+
+        case 0x3:
+                pr_cont("HT Master abort.\n");
+                return;
+
+        case 0x4:
+                pr_cont("HT Target abort.\n");
+                return;
+
+        case 0x7:
+                pr_cont("NB Watchdog timeout.\n");
+                return;
+
+        case 0x9:
+                pr_cont("SVM DMA Exclusion Vector error.\n");
+                return;
+
+        default:
+                break;
+        }
+
+        if (!fam_ops->nb_mce(ec, xec))
+                goto wrong_nb_mce;
+
+        if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10)
+                if ((xec == 0x8 || xec == 0x0) && nb_bus_decoder)
+                        nb_bus_decoder(node_id, m, nbcfg);
+
+        return;
+
+wrong_nb_mce:
+        pr_emerg(HW_ERR "Corrupted NB MCE info?\n");
+}
+EXPORT_SYMBOL_GPL(amd_decode_nb_mce);
+
+static void amd_decode_fr_mce(struct mce *m)
+{
+        if (boot_cpu_data.x86 == 0xf ||
+            boot_cpu_data.x86 == 0x11)
+                goto wrong_fr_mce;
+
+        /* we have only one error signature so match all fields at once. */
+        if ((m->status & 0xffff) == 0x0f0f) {
+                pr_emerg(HW_ERR "FR Error: CPU Watchdog timer expire.\n");
+                return;
+        }
+
+wrong_fr_mce:
+        pr_emerg(HW_ERR "Corrupted FR MCE info?\n");
+}
+
+static inline void amd_decode_err_code(u16 ec)
+{
+        if (TLB_ERROR(ec)) {
+                pr_emerg(HW_ERR "Transaction: %s, Cache Level: %s\n",
+                         TT_MSG(ec), LL_MSG(ec));
+        } else if (MEM_ERROR(ec)) {
+                pr_emerg(HW_ERR "Transaction: %s, Type: %s, Cache Level: %s\n",
+                         RRRR_MSG(ec), TT_MSG(ec), LL_MSG(ec));
+        } else if (BUS_ERROR(ec)) {
+                pr_emerg(HW_ERR "Transaction: %s (%s), %s, Cache Level: %s, "
+                         "Participating Processor: %s\n",
+                          RRRR_MSG(ec), II_MSG(ec), TO_MSG(ec), LL_MSG(ec),
+                          PP_MSG(ec));
+        } else
+                pr_emerg(HW_ERR "Huh? Unknown MCE error 0x%x\n", ec);
+}
+
+/*
+ * Filter out unwanted MCE signatures here.
+ */
+static bool amd_filter_mce(struct mce *m)
+{
+        u8 xec = (m->status >> 16) & 0x1f;
+
+        /*
+         * NB GART TLB error reporting is disabled by default.
+         */
+        if (m->bank == 4 && xec == 0x5 && !report_gart_errors)
+                return true;
+
+        return false;
+}
+
+int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
+{
+        struct mce *m = (struct mce *)data;
+        int node, ecc;
+
+        if (amd_filter_mce(m))
+                return NOTIFY_STOP;
+
+        pr_emerg(HW_ERR "MC%d_STATUS: ", m->bank);
+
+        pr_cont("%sorrected error, other errors lost: %s, "
+                 "CPU context corrupt: %s",
+                 ((m->status & MCI_STATUS_UC) ? "Unc"  : "C"),
+                 ((m->status & MCI_STATUS_OVER) ? "yes"  : "no"),
+                 ((m->status & MCI_STATUS_PCC) ? "yes" : "no"));
+
+        /* do the two bits[14:13] together */
+        ecc = (m->status >> 45) & 0x3;
+        if (ecc)
+                pr_cont(", %sECC Error", ((ecc == 2) ? "C" : "U"));
+
+        pr_cont("\n");
+
+        switch (m->bank) {
+        case 0:
+                amd_decode_dc_mce(m);
+                break;
+
+        case 1:
+                amd_decode_ic_mce(m);
+                break;
+
+        case 2:
+                amd_decode_bu_mce(m);
+                break;
+
+        case 3:
+                amd_decode_ls_mce(m);
+                break;
+
+        case 4:
+                node = amd_get_nb_id(m->extcpu);
+                amd_decode_nb_mce(node, m, 0);
+                break;
+
+        case 5:
+                amd_decode_fr_mce(m);
+                break;
+
+        default:
+                break;
+        }
+
+        amd_decode_err_code(m->status & 0xffff);
+
+        return NOTIFY_STOP;
+}
+EXPORT_SYMBOL_GPL(amd_decode_mce);
+
+static struct notifier_block amd_mce_dec_nb = {
+        .notifier_call  = amd_decode_mce,
+};
+
+static int __init mce_amd_init(void)
+{
+        if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
+                return 0;
+
+        if ((boot_cpu_data.x86 < 0xf || boot_cpu_data.x86 > 0x12) &&
+            (boot_cpu_data.x86 != 0x14 || boot_cpu_data.x86_model > 0xf))
+                return 0;
+
+        fam_ops = kzalloc(sizeof(struct amd_decoder_ops), GFP_KERNEL);
+        if (!fam_ops)
+                return -ENOMEM;
+
+        switch (boot_cpu_data.x86) {
+        case 0xf:
+                fam_ops->dc_mce = k8_dc_mce;
+                fam_ops->ic_mce = k8_ic_mce;
+                fam_ops->nb_mce = k8_nb_mce;
+                break;
+
+        case 0x10:
+                fam_ops->dc_mce = f10h_dc_mce;
+                fam_ops->ic_mce = k8_ic_mce;
+                fam_ops->nb_mce = f10h_nb_mce;
+                break;
+
+        case 0x11:
+                fam_ops->dc_mce = k8_dc_mce;
+                fam_ops->ic_mce = k8_ic_mce;
+                fam_ops->nb_mce = f10h_nb_mce;
+                break;
+
+        case 0x12:
+                fam_ops->dc_mce = f12h_dc_mce;
+                fam_ops->ic_mce = k8_ic_mce;
+                fam_ops->nb_mce = nb_noop_mce;
+                break;
+
+        case 0x14:
+                nb_err_cpumask  = 0x3;
+                fam_ops->dc_mce = f14h_dc_mce;
+                fam_ops->ic_mce = f14h_ic_mce;
+                fam_ops->nb_mce = nb_noop_mce;
+                break;
+
+        default:
+                printk(KERN_WARNING "Huh? What family is that: %d?!\n",
+                                    boot_cpu_data.x86);
+                kfree(fam_ops);
+                return -EINVAL;
+        }
+
+        pr_info("MCE: In-kernel MCE decoding enabled.\n");
+
+        atomic_notifier_chain_register(&x86_mce_decoder_chain, &amd_mce_dec_nb);
+
+        return 0;
+}
+early_initcall(mce_amd_init);
+
+#ifdef MODULE
+static void __exit mce_amd_exit(void)
+{
+        atomic_notifier_chain_unregister(&x86_mce_decoder_chain, &amd_mce_dec_nb);
+        kfree(fam_ops);
+}
+
+MODULE_DESCRIPTION("AMD MCE decoder");
+MODULE_ALIAS("edac-mce-amd");
+MODULE_LICENSE("GPL");
+module_exit(mce_amd_exit);
+#endif
diff --git a/drivers/edac/edac_mce_amd.h b/drivers/edac/mce_amd.h
index df23ee065f79..35f6e0e3b297 100644
--- a/drivers/edac/edac_mce_amd.h
+++ b/drivers/edac/mce_amd.h
@@ -1,11 +1,14 @@
 #ifndef _EDAC_MCE_AMD_H
 #define _EDAC_MCE_AMD_H
 
+#include <linux/notifier.h>
+
 #include <asm/mce.h>
 
+#define BIT_64(n)                       (U64_C(1) << (n))
+
 #define ERROR_CODE(x)                   ((x) & 0xffff)
 #define EXT_ERROR_CODE(x)               (((x) >> 16) & 0x1f)
-#define EXT_ERR_MSG(x)                  ext_msgs[EXT_ERROR_CODE(x)]
 
 #define LOW_SYNDROME(x)                 (((x) >> 15) & 0xff)
 #define HIGH_SYNDROME(x)                (((x) >> 24) & 0xff)
@@ -20,13 +23,14 @@
 #define II_MSG(x)                       ii_msgs[II(x)]
 #define LL(x)                           (((x) >> 0) & 0x3)
 #define LL_MSG(x)                       ll_msgs[LL(x)]
-#define RRRR(x)                         (((x) >> 4) & 0xf)
-#define RRRR_MSG(x)                     rrrr_msgs[RRRR(x)]
 #define TO(x)                           (((x) >> 8) & 0x1)
 #define TO_MSG(x)                       to_msgs[TO(x)]
 #define PP(x)                           (((x) >> 9) & 0x3)
 #define PP_MSG(x)                       pp_msgs[PP(x)]
 
+#define RRRR(x)                         (((x) >> 4) & 0xf)
+#define RRRR_MSG(x)                     ((RRRR(x) < 9) ?  rrrr_msgs[RRRR(x)] : "Wrong R4!")
+
 #define K8_NBSH                         0x4C
 
 #define K8_NBSH_VALID_BIT               BIT(31)
@@ -41,13 +45,45 @@
 #define K8_NBSH_UECC                    BIT(13)
 #define K8_NBSH_ERR_SCRUBER             BIT(8)
 
+enum tt_ids {
+        TT_INSTR = 0,
+        TT_DATA,
+        TT_GEN,
+        TT_RESV,
+};
+
+enum ll_ids {
+        LL_RESV = 0,
+        LL_L1,
+        LL_L2,
+        LL_LG,
+};
+
+enum ii_ids {
+        II_MEM = 0,
+        II_RESV,
+        II_IO,
+        II_GEN,
+};
+
+enum rrrr_ids {
+        R4_GEN  = 0,
+        R4_RD,
+        R4_WR,
+        R4_DRD,
+        R4_DWR,
+        R4_IRD,
+        R4_PREF,
+        R4_EVICT,
+        R4_SNOOP,
+};
+
 extern const char *tt_msgs[];
 extern const char *ll_msgs[];
 extern const char *rrrr_msgs[];
 extern const char *pp_msgs[];
 extern const char *to_msgs[];
 extern const char *ii_msgs[];
-extern const char *ext_msgs[];
 
 /*
  * relevant NB regs
@@ -60,10 +96,19 @@ struct err_regs {
         u32 nbeal;
 };
 
+/*
+ * per-family decoder ops
+ */
+struct amd_decoder_ops {
+        bool (*dc_mce)(u16);
+        bool (*ic_mce)(u16);
+        bool (*nb_mce)(u16, u8);
+};
 
 void amd_report_gart_errors(bool);
-void amd_register_ecc_decoder(void (*f)(int, struct err_regs *));
-void amd_unregister_ecc_decoder(void (*f)(int, struct err_regs *));
-void amd_decode_nb_mce(int, struct err_regs *, int);
+void amd_register_ecc_decoder(void (*f)(int, struct mce *, u32));
+void amd_unregister_ecc_decoder(void (*f)(int, struct mce *, u32));
+void amd_decode_nb_mce(int, struct mce *, u32);
+int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data);
 
 #endif /* _EDAC_MCE_AMD_H */
diff --git a/drivers/edac/mce_amd_inj.c b/drivers/edac/mce_amd_inj.c
new file mode 100644
index 000000000000..8d0688f36d4c
--- /dev/null
+++ b/drivers/edac/mce_amd_inj.c
@@ -0,0 +1,171 @@
+/*
+ * A simple MCE injection facility for testing the MCE decoding code. This
+ * driver should be built as module so that it can be loaded on production
+ * kernels for testing purposes.
+ *
+ * This file may be distributed under the terms of the GNU General Public
+ * License version 2.
+ *
+ * Copyright (c) 2010:  Borislav Petkov <borislav.petkov@amd.com>
+ *                      Advanced Micro Devices Inc.
+ */
+
+#include <linux/kobject.h>
+#include <linux/sysdev.h>
+#include <linux/edac.h>
+#include <asm/mce.h>
+
+#include "mce_amd.h"
+
+struct edac_mce_attr {
+        struct attribute attr;
+        ssize_t (*show) (struct kobject *kobj, struct edac_mce_attr *attr, char *buf);
+        ssize_t (*store)(struct kobject *kobj, struct edac_mce_attr *attr,
+                         const char *buf, size_t count);
+};
+
+#define EDAC_MCE_ATTR(_name, _mode, _show, _store)                      \
+static struct edac_mce_attr mce_attr_##_name = __ATTR(_name, _mode, _show, _store)
+
+static struct kobject *mce_kobj;
+
+/*
+ * Collect all the MCi_XXX settings
+ */
+static struct mce i_mce;
+
+#define MCE_INJECT_STORE(reg)                                           \
+static ssize_t edac_inject_##reg##_store(struct kobject *kobj,          \
+                                         struct edac_mce_attr *attr,    \
+                                         const char *data, size_t count)\
+{                                                                       \
+        int ret = 0;                                                    \
+        unsigned long value;                                            \
+                                                                        \
+        ret = strict_strtoul(data, 16, &value);                         \
+        if (ret < 0)                                                    \
+                printk(KERN_ERR "Error writing MCE " #reg " field.\n"); \
+                                                                        \
+        i_mce.reg = value;                                              \
+                                                                        \
+        return count;                                                   \
+}
+
+MCE_INJECT_STORE(status);
+MCE_INJECT_STORE(misc);
+MCE_INJECT_STORE(addr);
+
+#define MCE_INJECT_SHOW(reg)                                            \
+static ssize_t edac_inject_##reg##_show(struct kobject *kobj,           \
+                                        struct edac_mce_attr *attr,     \
+                                        char *buf)                      \
+{                                                                       \
+        return sprintf(buf, "0x%016llx\n", i_mce.reg);                  \
+}
+
+MCE_INJECT_SHOW(status);
+MCE_INJECT_SHOW(misc);
+MCE_INJECT_SHOW(addr);
+
+EDAC_MCE_ATTR(status, 0644, edac_inject_status_show, edac_inject_status_store);
+EDAC_MCE_ATTR(misc, 0644, edac_inject_misc_show, edac_inject_misc_store);
+EDAC_MCE_ATTR(addr, 0644, edac_inject_addr_show, edac_inject_addr_store);
+
+/*
+ * This denotes into which bank we're injecting and triggers
+ * the injection, at the same time.
+ */
+static ssize_t edac_inject_bank_store(struct kobject *kobj,
+                                      struct edac_mce_attr *attr,
+                                      const char *data, size_t count)
+{
+        int ret = 0;
+        unsigned long value;
+
+        ret = strict_strtoul(data, 10, &value);
+        if (ret < 0) {
+                printk(KERN_ERR "Invalid bank value!\n");
+                return -EINVAL;
+        }
+
+        if (value > 5) {
+                printk(KERN_ERR "Non-existant MCE bank: %lu\n", value);
+                return -EINVAL;
+        }
+
+        i_mce.bank = value;
+
+        amd_decode_mce(NULL, 0, &i_mce);
+
+        return count;
+}
+
+static ssize_t edac_inject_bank_show(struct kobject *kobj,
+                                     struct edac_mce_attr *attr, char *buf)
+{
+        return sprintf(buf, "%d\n", i_mce.bank);
+}
+
+EDAC_MCE_ATTR(bank, 0644, edac_inject_bank_show, edac_inject_bank_store);
+
+static struct edac_mce_attr *sysfs_attrs[] = { &mce_attr_status, &mce_attr_misc,
+                                               &mce_attr_addr, &mce_attr_bank
+};
+
+static int __init edac_init_mce_inject(void)
+{
+        struct sysdev_class *edac_class = NULL;
+        int i, err = 0;
+
+        edac_class = edac_get_sysfs_class();
+        if (!edac_class)
+                return -EINVAL;
+
+        mce_kobj = kobject_create_and_add("mce", &edac_class->kset.kobj);
+        if (!mce_kobj) {
+                printk(KERN_ERR "Error creating a mce kset.\n");
+                err = -ENOMEM;
+                goto err_mce_kobj;
+        }
+
+        for (i = 0; i < ARRAY_SIZE(sysfs_attrs); i++) {
+                err = sysfs_create_file(mce_kobj, &sysfs_attrs[i]->attr);
+                if (err) {
+                        printk(KERN_ERR "Error creating %s in sysfs.\n",
+                                        sysfs_attrs[i]->attr.name);
+                        goto err_sysfs_create;
+                }
+        }
+        return 0;
+
+err_sysfs_create:
+        while (i-- >= 0)
+                sysfs_remove_file(mce_kobj, &sysfs_attrs[i]->attr);
+
+        kobject_del(mce_kobj);
+
+err_mce_kobj:
+        edac_put_sysfs_class();
+
+        return err;
+}
+
+static void __exit edac_exit_mce_inject(void)
+{
+        int i;
+
+        for (i = 0; i < ARRAY_SIZE(sysfs_attrs); i++)
+                sysfs_remove_file(mce_kobj, &sysfs_attrs[i]->attr);
+
+        kobject_del(mce_kobj);
+
+        edac_put_sysfs_class();
+}
+
+module_init(edac_init_mce_inject);
+module_exit(edac_exit_mce_inject);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Borislav Petkov <borislav.petkov@amd.com>");
+MODULE_AUTHOR("AMD Inc.");
+MODULE_DESCRIPTION("MCE injection facility for testing MCE decoding");
diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig
index 280c9b5ad9e3..88a3ae6cd023 100644
--- a/drivers/firmware/Kconfig
+++ b/drivers/firmware/Kconfig
@@ -125,7 +125,7 @@ config ISCSI_IBFT_FIND
 config ISCSI_IBFT
         tristate "iSCSI Boot Firmware Table Attributes module"
         select ISCSI_BOOT_SYSFS
-        depends on ISCSI_IBFT_FIND && SCSI
+        depends on ISCSI_IBFT_FIND && SCSI && SCSI_LOWLEVEL
         default n
         help
           This option enables support for detection and exposing of iSCSI
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index c37ef64d1465..cb3ccf3ed221 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -59,18 +59,11 @@
 #include <linux/hrtimer.h>      /* ktime_get_real() */
 #include <trace/events/power.h>
 #include <linux/sched.h>
+#include <asm/mwait.h>
 
 #define INTEL_IDLE_VERSION "0.4"
 #define PREFIX "intel_idle: "
 
-#define MWAIT_SUBSTATE_MASK     (0xf)
-#define MWAIT_CSTATE_MASK       (0xf)
-#define MWAIT_SUBSTATE_SIZE     (4)
-#define MWAIT_MAX_NUM_CSTATES   8
-#define CPUID_MWAIT_LEAF (5)
-#define CPUID5_ECX_EXTENSIONS_SUPPORTED (0x1)
-#define CPUID5_ECX_INTERRUPT_BREAK      (0x2)
-
 static struct cpuidle_driver intel_idle_driver = {
         .name = "intel_idle",
         .owner = THIS_MODULE,
diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c
index 9ddafc30f432..af9ee313c10b 100644
--- a/drivers/input/evdev.c
+++ b/drivers/input/evdev.c
@@ -28,7 +28,7 @@ struct evdev {
         int minor;
         struct input_handle handle;
         wait_queue_head_t wait;
-        struct evdev_client *grab;
+        struct evdev_client __rcu *grab;
         struct list_head client_list;
         spinlock_t client_lock; /* protects client_list */
         struct mutex mutex;
diff --git a/drivers/input/misc/hp_sdc_rtc.c b/drivers/input/misc/hp_sdc_rtc.c
index c19066479057..7e2c12a5b839 100644
--- a/drivers/input/misc/hp_sdc_rtc.c
+++ b/drivers/input/misc/hp_sdc_rtc.c
@@ -104,7 +104,7 @@ static int hp_sdc_rtc_do_read_bbrtc (struct rtc_time *rtctm)
         t.endidx =              91;
         t.seq =                 tseq;
         t.act.semaphore =       &tsem;
-        init_MUTEX_LOCKED(&tsem);
+        sema_init(&tsem, 0);
         
         if (hp_sdc_enqueue_transaction(&t)) return -1;
         
@@ -698,7 +698,7 @@ static int __init hp_sdc_rtc_init(void)
                 return -ENODEV;
 #endif
 
-        init_MUTEX(&i8042tregs);
+        sema_init(&i8042tregs, 1);
 
         if ((ret = hp_sdc_request_timer_irq(&hp_sdc_rtc_isr)))
                 return ret;
diff --git a/drivers/input/serio/hil_mlc.c b/drivers/input/serio/hil_mlc.c
index c92f4edfee7b..e5624d8f1709 100644
--- a/drivers/input/serio/hil_mlc.c
+++ b/drivers/input/serio/hil_mlc.c
@@ -915,15 +915,15 @@ int hil_mlc_register(hil_mlc *mlc)
         mlc->ostarted = 0;
 
         rwlock_init(&mlc->lock);
-        init_MUTEX(&mlc->osem);
+        sema_init(&mlc->osem, 1);
 
-        init_MUTEX(&mlc->isem);
+        sema_init(&mlc->isem, 1);
         mlc->icount = -1;
         mlc->imatch = 0;
 
         mlc->opercnt = 0;
 
-        init_MUTEX_LOCKED(&(mlc->csem));
+        sema_init(&(mlc->csem), 0);
 
         hil_mlc_clear_di_scratch(mlc);
         hil_mlc_clear_di_map(mlc, 0);
diff --git a/drivers/input/serio/hp_sdc.c b/drivers/input/serio/hp_sdc.c
index bcc2d30ec245..8c0b51c31424 100644
--- a/drivers/input/serio/hp_sdc.c
+++ b/drivers/input/serio/hp_sdc.c
@@ -905,7 +905,7 @@ static int __init hp_sdc_init(void)
         ts_sync[1]      = 0x0f;
         ts_sync[2] = ts_sync[3] = ts_sync[4] = ts_sync[5] = 0;
         t_sync.act.semaphore = &s_sync;
-        init_MUTEX_LOCKED(&s_sync);
+        sema_init(&s_sync, 0);
         hp_sdc_enqueue_transaction(&t_sync);
         down(&s_sync); /* Wait for t_sync to complete */
 
@@ -1039,7 +1039,7 @@ static int __init hp_sdc_register(void)
                 return hp_sdc.dev_err;
         }
 
-        init_MUTEX_LOCKED(&tq_init_sem);
+        sema_init(&tq_init_sem, 0);
 
         tq_init.actidx          = 0;
         tq_init.idx             = 1;
diff --git a/drivers/isdn/act2000/act2000.h b/drivers/isdn/act2000/act2000.h
index d4c50512a1ff..88c9423500d8 100644
--- a/drivers/isdn/act2000/act2000.h
+++ b/drivers/isdn/act2000/act2000.h
@@ -141,9 +141,9 @@ typedef struct irq_data_isa {
         __u8            rcvhdr[8];
 } irq_data_isa;
 
-typedef union irq_data {
+typedef union act2000_irq_data {
         irq_data_isa isa;
-} irq_data;
+} act2000_irq_data;
 
 /*
  * Per card driver data
@@ -176,7 +176,7 @@ typedef struct act2000_card {
         char   *status_buf_read;
         char   *status_buf_write;
         char   *status_buf_end;
-        irq_data idat;                  /* Data used for IRQ handler        */
+        act2000_irq_data idat;          /* Data used for IRQ handler        */
         isdn_if interface;              /* Interface to upper layer         */
         char regname[35];               /* Name used for request_region     */
 } act2000_card;
diff --git a/drivers/isdn/hisax/config.c b/drivers/isdn/hisax/config.c
index 6f9afcd5ca4e..b133378d4dc9 100644
--- a/drivers/isdn/hisax/config.c
+++ b/drivers/isdn/hisax/config.c
@@ -801,6 +801,16 @@ static void closecard(int cardnr)
         ll_unload(csta);
 }
 
+static irqreturn_t card_irq(int intno, void *dev_id)
+{
+        struct IsdnCardState *cs = dev_id;
+        irqreturn_t ret = cs->irq_func(intno, cs);
+
+        if (ret == IRQ_HANDLED)
+                cs->irq_cnt++;
+        return ret;
+}
+
 static int init_card(struct IsdnCardState *cs)
 {
         int     irq_cnt, cnt = 3, ret;
@@ -809,10 +819,10 @@ static int init_card(struct IsdnCardState *cs)
                 ret = cs->cardmsg(cs, CARD_INIT, NULL);
                 return(ret);
         }
-        irq_cnt = kstat_irqs(cs->irq);
+        irq_cnt = cs->irq_cnt = 0;
         printk(KERN_INFO "%s: IRQ %d count %d\n", CardType[cs->typ],
                cs->irq, irq_cnt);
-        if (request_irq(cs->irq, cs->irq_func, cs->irq_flags, "HiSax", cs)) {
+        if (request_irq(cs->irq, card_irq, cs->irq_flags, "HiSax", cs)) {
                 printk(KERN_WARNING "HiSax: couldn't get interrupt %d\n",
                        cs->irq);
                 return 1;
@@ -822,8 +832,8 @@ static int init_card(struct IsdnCardState *cs)
                 /* Timeout 10ms */
                 msleep(10);
                 printk(KERN_INFO "%s: IRQ %d count %d\n",
-                       CardType[cs->typ], cs->irq, kstat_irqs(cs->irq));
-                if (kstat_irqs(cs->irq) == irq_cnt) {
+                       CardType[cs->typ], cs->irq, cs->irq_cnt);
+                if (cs->irq_cnt == irq_cnt) {
                         printk(KERN_WARNING
                                "%s: IRQ(%d) getting no interrupts during init %d\n",
                                CardType[cs->typ], cs->irq, 4 - cnt);
diff --git a/drivers/isdn/hisax/hisax.h b/drivers/isdn/hisax/hisax.h
index 832a87855ffb..32ab3924aa73 100644
--- a/drivers/isdn/hisax/hisax.h
+++ b/drivers/isdn/hisax/hisax.h
@@ -959,6 +959,7 @@ struct IsdnCardState {
         u_long          event;
         struct work_struct tqueue;
         struct timer_list dbusytimer;
+        unsigned int    irq_cnt;
 #ifdef ERROR_STATISTIC
         int             err_crc;
         int             err_tx;
diff --git a/drivers/macintosh/adb.c b/drivers/macintosh/adb.c
index 1c4ee6e77937..bf64e49d996a 100644
--- a/drivers/macintosh/adb.c
+++ b/drivers/macintosh/adb.c
@@ -83,7 +83,7 @@ static struct adb_driver *adb_controller;
 BLOCKING_NOTIFIER_HEAD(adb_client_list);
 static int adb_got_sleep;
 static int adb_inited;
-static DECLARE_MUTEX(adb_probe_mutex);
+static DEFINE_SEMAPHORE(adb_probe_mutex);
 static int sleepy_trackpad;
 static int autopoll_devs;
 int __adb_probe_sync;
diff --git a/drivers/mfd/twl4030-irq.c b/drivers/mfd/twl4030-irq.c
index 097f24d8bceb..b9fda7018cef 100644
--- a/drivers/mfd/twl4030-irq.c
+++ b/drivers/mfd/twl4030-irq.c
@@ -78,7 +78,7 @@ struct sih {
         u8      irq_lines;              /* number of supported irq lines */
 
         /* SIR ignored -- set interrupt, for testing only */
-        struct irq_data {
+        struct sih_irq_data {
                 u8      isr_offset;
                 u8      imr_offset;
         } mask[2];
@@ -810,7 +810,7 @@ int twl4030_init_irq(int irq_num, unsigned irq_base, unsigned irq_end)
         twl4030_irq_chip = dummy_irq_chip;
         twl4030_irq_chip.name = "twl4030";
 
-        twl4030_sih_irq_chip.ack = dummy_irq_chip.ack;
+        twl4030_sih_irq_chip.irq_ack = dummy_irq_chip.irq_ack;
 
         for (i = irq_base; i < irq_end; i++) {
                 set_irq_chip_and_handler(i, &twl4030_irq_chip,
diff --git a/drivers/net/3c527.c b/drivers/net/3c527.c
index 70705d1306b9..eca55c52bdfd 100644
--- a/drivers/net/3c527.c
+++ b/drivers/net/3c527.c
@@ -522,7 +522,7 @@ static int __init mc32_probe1(struct net_device *dev, int slot)
         lp->tx_len              = lp->exec_box->data[9];   /* Transmit list count */
         lp->rx_len              = lp->exec_box->data[11];  /* Receive list count */
 
-        init_MUTEX_LOCKED(&lp->cmd_mutex);
+        sema_init(&lp->cmd_mutex, 0);
         init_completion(&lp->execution_cmd);
         init_completion(&lp->xceiver_cmd);
 
diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c
index 4b52c767ad05..3e5d0b6b6516 100644
--- a/drivers/net/hamradio/6pack.c
+++ b/drivers/net/hamradio/6pack.c
@@ -608,7 +608,7 @@ static int sixpack_open(struct tty_struct *tty)
 
         spin_lock_init(&sp->lock);
         atomic_set(&sp->refcnt, 1);
-        init_MUTEX_LOCKED(&sp->dead_sem);
+        sema_init(&sp->dead_sem, 0);
 
         /* !!! length of the buffers. MTU is IP MTU, not PACLEN!  */
 
diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c
index 66e88bd59caa..4c628393c8b1 100644
--- a/drivers/net/hamradio/mkiss.c
+++ b/drivers/net/hamradio/mkiss.c
@@ -747,7 +747,7 @@ static int mkiss_open(struct tty_struct *tty)
 
         spin_lock_init(&ax->buflock);
         atomic_set(&ax->refcnt, 1);
-        init_MUTEX_LOCKED(&ax->dead_sem);
+        sema_init(&ax->dead_sem, 0);
 
         ax->tty = tty;
         tty->disc_data = ax;
diff --git a/drivers/net/irda/sir_dev.c b/drivers/net/irda/sir_dev.c
index 1b051dab7b29..51d74447f8f8 100644
--- a/drivers/net/irda/sir_dev.c
+++ b/drivers/net/irda/sir_dev.c
@@ -909,7 +909,7 @@ struct sir_dev * sirdev_get_instance(const struct sir_driver *drv, const char *n
         dev->tx_skb = NULL;
 
         spin_lock_init(&dev->tx_lock);
-        init_MUTEX(&dev->fsm.sem);
+        sema_init(&dev->fsm.sem, 1);
 
         dev->drv = drv;
         dev->netdev = ndev;
diff --git a/drivers/net/ppp_async.c b/drivers/net/ppp_async.c
index af50a530daee..78d70a6481bf 100644
--- a/drivers/net/ppp_async.c
+++ b/drivers/net/ppp_async.c
@@ -184,7 +184,7 @@ ppp_asynctty_open(struct tty_struct *tty)
         tasklet_init(&ap->tsk, ppp_async_process, (unsigned long) ap);
 
         atomic_set(&ap->refcnt, 1);
-        init_MUTEX_LOCKED(&ap->dead_sem);
+        sema_init(&ap->dead_sem, 0);
 
         ap->chan.private = ap;
         ap->chan.ops = &async_ops;
diff --git a/drivers/net/wan/cosa.c b/drivers/net/wan/cosa.c
index 04c6cd4333f1..10bafd59f9c3 100644
--- a/drivers/net/wan/cosa.c
+++ b/drivers/net/wan/cosa.c
@@ -575,7 +575,7 @@ static int cosa_probe(int base, int irq, int dma)
 
                 /* Initialize the chardev data structures */
                 mutex_init(&chan->rlock);
-                init_MUTEX(&chan->wsem);
+                sema_init(&chan->wsem, 1);
 
                 /* Register the network interface */
                 if (!(chan->netdev = alloc_hdlcdev(chan))) {
diff --git a/drivers/parport/share.c b/drivers/parport/share.c
index dffa5d4fb298..a2d9d1e59260 100644
--- a/drivers/parport/share.c
+++ b/drivers/parport/share.c
@@ -306,7 +306,7 @@ struct parport *parport_register_port(unsigned long base, int irq, int dma,
         spin_lock_init(&tmp->pardevice_lock);
         tmp->ieee1284.mode = IEEE1284_MODE_COMPAT;
         tmp->ieee1284.phase = IEEE1284_PH_FWD_IDLE;
-        init_MUTEX_LOCKED (&tmp->ieee1284.irq); /* actually a semaphore at 0 */
+        sema_init(&tmp->ieee1284.irq, 0);
         tmp->spintime = parport_default_spintime;
         atomic_set (&tmp->ref_count, 1);
         INIT_LIST_HEAD(&tmp->full_list);
diff --git a/drivers/pci/dmar.c b/drivers/pci/dmar.c
index 0a19708074c2..3de3a436a432 100644
--- a/drivers/pci/dmar.c
+++ b/drivers/pci/dmar.c
@@ -1221,9 +1221,9 @@ const char *dmar_get_fault_reason(u8 fault_reason, int *fault_type)
         }
 }
 
-void dmar_msi_unmask(unsigned int irq)
+void dmar_msi_unmask(struct irq_data *data)
 {
-        struct intel_iommu *iommu = get_irq_data(irq);
+        struct intel_iommu *iommu = irq_data_get_irq_data(data);
         unsigned long flag;
 
         /* unmask it */
@@ -1234,10 +1234,10 @@ void dmar_msi_unmask(unsigned int irq)
         spin_unlock_irqrestore(&iommu->register_lock, flag);
 }
 
-void dmar_msi_mask(unsigned int irq)
+void dmar_msi_mask(struct irq_data *data)
 {
         unsigned long flag;
-        struct intel_iommu *iommu = get_irq_data(irq);
+        struct intel_iommu *iommu = irq_data_get_irq_data(data);
 
         /* mask it */
         spin_lock_irqsave(&iommu->register_lock, flag);
diff --git a/drivers/pci/htirq.c b/drivers/pci/htirq.c
index 98abf8b91294..834842aa5bbf 100644
--- a/drivers/pci/htirq.c
+++ b/drivers/pci/htirq.c
@@ -57,28 +57,22 @@ void fetch_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg)
         *msg = cfg->msg;
 }
 
-void mask_ht_irq(unsigned int irq)
+void mask_ht_irq(struct irq_data *data)
 {
-        struct ht_irq_cfg *cfg;
-        struct ht_irq_msg msg;
-
-        cfg = get_irq_data(irq);
+        struct ht_irq_cfg *cfg = irq_data_get_irq_data(data);
+        struct ht_irq_msg msg = cfg->msg;
 
-        msg = cfg->msg;
         msg.address_lo |= 1;
-        write_ht_irq_msg(irq, &msg);
+        write_ht_irq_msg(data->irq, &msg);
 }
 
-void unmask_ht_irq(unsigned int irq)
+void unmask_ht_irq(struct irq_data *data)
 {
-        struct ht_irq_cfg *cfg;
-        struct ht_irq_msg msg;
-
-        cfg = get_irq_data(irq);
+        struct ht_irq_cfg *cfg = irq_data_get_irq_data(data);
+        struct ht_irq_msg msg = cfg->msg;
 
-        msg = cfg->msg;
         msg.address_lo &= ~1;
-        write_ht_irq_msg(irq, &msg);
+        write_ht_irq_msg(data->irq, &msg);
 }
 
 /**
diff --git a/drivers/pci/intr_remapping.c b/drivers/pci/intr_remapping.c
index fd1d2867cdcc..ec87cd66f3eb 100644
--- a/drivers/pci/intr_remapping.c
+++ b/drivers/pci/intr_remapping.c
@@ -46,109 +46,24 @@ static __init int setup_intremap(char *str)
 }
 early_param("intremap", setup_intremap);
 
-struct irq_2_iommu {
-        struct intel_iommu *iommu;
-        u16 irte_index;
-        u16 sub_handle;
-        u8  irte_mask;
-};
-
-#ifdef CONFIG_GENERIC_HARDIRQS
-static struct irq_2_iommu *get_one_free_irq_2_iommu(int node)
-{
-        struct irq_2_iommu *iommu;
-
-        iommu = kzalloc_node(sizeof(*iommu), GFP_ATOMIC, node);
-        printk(KERN_DEBUG "alloc irq_2_iommu on node %d\n", node);
-
-        return iommu;
-}
-
-static struct irq_2_iommu *irq_2_iommu(unsigned int irq)
-{
-        struct irq_desc *desc;
-
-        desc = irq_to_desc(irq);
-
-        if (WARN_ON_ONCE(!desc))
-                return NULL;
-
-        return desc->irq_2_iommu;
-}
-
-static struct irq_2_iommu *irq_2_iommu_alloc(unsigned int irq)
-{
-        struct irq_desc *desc;
-        struct irq_2_iommu *irq_iommu;
-
-        desc = irq_to_desc(irq);
-        if (!desc) {
-                printk(KERN_INFO "can not get irq_desc for %d\n", irq);
-                return NULL;
-        }
-
-        irq_iommu = desc->irq_2_iommu;
-
-        if (!irq_iommu)
-                desc->irq_2_iommu = get_one_free_irq_2_iommu(irq_node(irq));
-
-        return desc->irq_2_iommu;
-}
-
-#else /* !CONFIG_SPARSE_IRQ */
-
-static struct irq_2_iommu irq_2_iommuX[NR_IRQS];
-
-static struct irq_2_iommu *irq_2_iommu(unsigned int irq)
-{
-        if (irq < nr_irqs)
-                return &irq_2_iommuX[irq];
-
-        return NULL;
-}
-static struct irq_2_iommu *irq_2_iommu_alloc(unsigned int irq)
-{
-        return irq_2_iommu(irq);
-}
-#endif
-
 static DEFINE_SPINLOCK(irq_2_ir_lock);
 
-static struct irq_2_iommu *valid_irq_2_iommu(unsigned int irq)
-{
-        struct irq_2_iommu *irq_iommu;
-
-        irq_iommu = irq_2_iommu(irq);
-
-        if (!irq_iommu)
-                return NULL;
-
-        if (!irq_iommu->iommu)
-                return NULL;
-
-        return irq_iommu;
-}
-
-int irq_remapped(int irq)
+static struct irq_2_iommu *irq_2_iommu(unsigned int irq)
 {
-        return valid_irq_2_iommu(irq) != NULL;
+        struct irq_cfg *cfg = get_irq_chip_data(irq);
+        return cfg ? &cfg->irq_2_iommu : NULL;
 }
 
 int get_irte(int irq, struct irte *entry)
 {
-        int index;
-        struct irq_2_iommu *irq_iommu;
+        struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
         unsigned long flags;
+        int index;
 
-        if (!entry)
+        if (!entry || !irq_iommu)
                 return -1;
 
         spin_lock_irqsave(&irq_2_ir_lock, flags);
-        irq_iommu = valid_irq_2_iommu(irq);
-        if (!irq_iommu) {
-                spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-                return -1;
-        }
 
         index = irq_iommu->irte_index + irq_iommu->sub_handle;
         *entry = *(irq_iommu->iommu->ir_table->base + index);
@@ -160,20 +75,14 @@ int get_irte(int irq, struct irte *entry)
 int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
 {
         struct ir_table *table = iommu->ir_table;
-        struct irq_2_iommu *irq_iommu;
+        struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
         u16 index, start_index;
         unsigned int mask = 0;
         unsigned long flags;
         int i;
 
-        if (!count)
-                return -1;
-
-#ifndef CONFIG_SPARSE_IRQ
-        /* protect irq_2_iommu_alloc later */
-        if (irq >= nr_irqs)
+        if (!count || !irq_iommu)
                 return -1;
-#endif
 
         /*
          * start the IRTE search from index 0.
@@ -214,13 +123,6 @@ int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
         for (i = index; i < index + count; i++)
                 table->base[i].present = 1;
 
-        irq_iommu = irq_2_iommu_alloc(irq);
-        if (!irq_iommu) {
-                spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-                printk(KERN_ERR "can't allocate irq_2_iommu\n");
-                return -1;
-        }
-
         irq_iommu->iommu = iommu;
         irq_iommu->irte_index =  index;
         irq_iommu->sub_handle = 0;
@@ -244,17 +146,14 @@ static int qi_flush_iec(struct intel_iommu *iommu, int index, int mask)
 
 int map_irq_to_irte_handle(int irq, u16 *sub_handle)
 {
-        int index;
-        struct irq_2_iommu *irq_iommu;
+        struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
         unsigned long flags;
+        int index;
 
-        spin_lock_irqsave(&irq_2_ir_lock, flags);
-        irq_iommu = valid_irq_2_iommu(irq);
-        if (!irq_iommu) {
-                spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+        if (!irq_iommu)
                 return -1;
-        }
 
+        spin_lock_irqsave(&irq_2_ir_lock, flags);
         *sub_handle = irq_iommu->sub_handle;
         index = irq_iommu->irte_index;
         spin_unlock_irqrestore(&irq_2_ir_lock, flags);
@@ -263,18 +162,13 @@ int map_irq_to_irte_handle(int irq, u16 *sub_handle)
 
 int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subhandle)
 {
-        struct irq_2_iommu *irq_iommu;
+        struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
         unsigned long flags;
 
-        spin_lock_irqsave(&irq_2_ir_lock, flags);
-
-        irq_iommu = irq_2_iommu_alloc(irq);
-
-        if (!irq_iommu) {
-                spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-                printk(KERN_ERR "can't allocate irq_2_iommu\n");
+        if (!irq_iommu)
                 return -1;
-        }
+
+        spin_lock_irqsave(&irq_2_ir_lock, flags);
 
         irq_iommu->iommu = iommu;
         irq_iommu->irte_index = index;
@@ -286,43 +180,18 @@ int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subhandle)
         return 0;
 }
 
-int clear_irte_irq(int irq, struct intel_iommu *iommu, u16 index)
-{
-        struct irq_2_iommu *irq_iommu;
-        unsigned long flags;
-
-        spin_lock_irqsave(&irq_2_ir_lock, flags);
-        irq_iommu = valid_irq_2_iommu(irq);
-        if (!irq_iommu) {
-                spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-                return -1;
-        }
-
-        irq_iommu->iommu = NULL;
-        irq_iommu->irte_index = 0;
-        irq_iommu->sub_handle = 0;
-        irq_2_iommu(irq)->irte_mask = 0;
-
-        spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-
-        return 0;
-}
-
 int modify_irte(int irq, struct irte *irte_modified)
 {
-        int rc;
-        int index;
-        struct irte *irte;
+        struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
         struct intel_iommu *iommu;
-        struct irq_2_iommu *irq_iommu;
         unsigned long flags;
+        struct irte *irte;
+        int rc, index;
 
-        spin_lock_irqsave(&irq_2_ir_lock, flags);
-        irq_iommu = valid_irq_2_iommu(irq);
-        if (!irq_iommu) {
-                spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+        if (!irq_iommu)
                 return -1;
-        }
+
+        spin_lock_irqsave(&irq_2_ir_lock, flags);
 
         iommu = irq_iommu->iommu;
 
@@ -339,31 +208,6 @@ int modify_irte(int irq, struct irte *irte_modified)
         return rc;
 }
 
-int flush_irte(int irq)
-{
-        int rc;
-        int index;
-        struct intel_iommu *iommu;
-        struct irq_2_iommu *irq_iommu;
-        unsigned long flags;
-
-        spin_lock_irqsave(&irq_2_ir_lock, flags);
-        irq_iommu = valid_irq_2_iommu(irq);
-        if (!irq_iommu) {
-                spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-                return -1;
-        }
-
-        iommu = irq_iommu->iommu;
-
-        index = irq_iommu->irte_index + irq_iommu->sub_handle;
-
-        rc = qi_flush_iec(iommu, index, irq_iommu->irte_mask);
-        spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-
-        return rc;
-}
-
 struct intel_iommu *map_hpet_to_ir(u8 hpet_id)
 {
         int i;
@@ -420,16 +264,14 @@ static int clear_entries(struct irq_2_iommu *irq_iommu)
 
 int free_irte(int irq)
 {
-        int rc = 0;
-        struct irq_2_iommu *irq_iommu;
+        struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
         unsigned long flags;
+        int rc;
 
-        spin_lock_irqsave(&irq_2_ir_lock, flags);
-        irq_iommu = valid_irq_2_iommu(irq);
-        if (!irq_iommu) {
-                spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+        if (!irq_iommu)
                 return -1;
-        }
+
+        spin_lock_irqsave(&irq_2_ir_lock, flags);
 
         rc = clear_entries(irq_iommu);
 
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 69b7be33b3a2..5fcf5aec680f 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -170,33 +170,31 @@ static void msix_mask_irq(struct msi_desc *desc, u32 flag)
         desc->masked = __msix_mask_irq(desc, flag);
 }
 
-static void msi_set_mask_bit(unsigned irq, u32 flag)
+static void msi_set_mask_bit(struct irq_data *data, u32 flag)
 {
-        struct msi_desc *desc = get_irq_msi(irq);
+        struct msi_desc *desc = irq_data_get_msi(data);
 
         if (desc->msi_attrib.is_msix) {
                 msix_mask_irq(desc, flag);
                 readl(desc->mask_base);         /* Flush write to device */
         } else {
-                unsigned offset = irq - desc->dev->irq;
+                unsigned offset = data->irq - desc->dev->irq;
                 msi_mask_irq(desc, 1 << offset, flag << offset);
         }
 }
 
-void mask_msi_irq(unsigned int irq)
+void mask_msi_irq(struct irq_data *data)
 {
-        msi_set_mask_bit(irq, 1);
+        msi_set_mask_bit(data, 1);
 }
 
-void unmask_msi_irq(unsigned int irq)
+void unmask_msi_irq(struct irq_data *data)
 {
-        msi_set_mask_bit(irq, 0);
+        msi_set_mask_bit(data, 0);
 }
 
-void read_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg)
+void __read_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
 {
-        struct msi_desc *entry = get_irq_desc_msi(desc);
-
         BUG_ON(entry->dev->current_state != PCI_D0);
 
         if (entry->msi_attrib.is_msix) {
@@ -227,15 +225,13 @@ void read_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg)
 
 void read_msi_msg(unsigned int irq, struct msi_msg *msg)
 {
-        struct irq_desc *desc = irq_to_desc(irq);
+        struct msi_desc *entry = get_irq_msi(irq);
 
-        read_msi_msg_desc(desc, msg);
+        __read_msi_msg(entry, msg);
 }
 
-void get_cached_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg)
+void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
 {
-        struct msi_desc *entry = get_irq_desc_msi(desc);
-
         /* Assert that the cache is valid, assuming that
          * valid messages are not all-zeroes. */
         BUG_ON(!(entry->msg.address_hi | entry->msg.address_lo |
@@ -246,15 +242,13 @@ void get_cached_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg)
 
 void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg)
 {
-        struct irq_desc *desc = irq_to_desc(irq);
+        struct msi_desc *entry = get_irq_msi(irq);
 
-        get_cached_msi_msg_desc(desc, msg);
+        __get_cached_msi_msg(entry, msg);
 }
 
-void write_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg)
+void __write_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
 {
-        struct msi_desc *entry = get_irq_desc_msi(desc);
-
         if (entry->dev->current_state != PCI_D0) {
                 /* Don't touch the hardware now */
         } else if (entry->msi_attrib.is_msix) {
@@ -292,9 +286,9 @@ void write_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg)
 
 void write_msi_msg(unsigned int irq, struct msi_msg *msg)
 {
-        struct irq_desc *desc = irq_to_desc(irq);
+        struct msi_desc *entry = get_irq_msi(irq);
 
-        write_msi_msg_desc(desc, msg);
+        __write_msi_msg(entry, msg);
 }
 
 static void free_msi_irqs(struct pci_dev *dev)
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 7c8008225ee3..17927b1f9334 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -127,7 +127,10 @@ static void handle_tx(struct vhost_net *net)
         size_t len, total_len = 0;
         int err, wmem;
         size_t hdr_size;
-        struct socket *sock = rcu_dereference(vq->private_data);
+        struct socket *sock;
+
+        sock = rcu_dereference_check(vq->private_data,
+                                     lockdep_is_held(&vq->mutex));
         if (!sock)
                 return;
 
@@ -582,7 +585,10 @@ static void vhost_net_disable_vq(struct vhost_net *n,
 static void vhost_net_enable_vq(struct vhost_net *n,
                                 struct vhost_virtqueue *vq)
 {
-        struct socket *sock = vq->private_data;
+        struct socket *sock;
+
+        sock = rcu_dereference_protected(vq->private_data,
+                                         lockdep_is_held(&vq->mutex));
         if (!sock)
                 return;
         if (vq == n->vqs + VHOST_NET_VQ_TX) {
@@ -598,7 +604,8 @@ static struct socket *vhost_net_stop_vq(struct vhost_net *n,
         struct socket *sock;
 
         mutex_lock(&vq->mutex);
-        sock = vq->private_data;
+        sock = rcu_dereference_protected(vq->private_data,
+                                         lockdep_is_held(&vq->mutex));
         vhost_net_disable_vq(n, vq);
         rcu_assign_pointer(vq->private_data, NULL);
         mutex_unlock(&vq->mutex);
@@ -736,7 +743,8 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
         }
 
         /* start polling new socket */
-        oldsock = vq->private_data;
+        oldsock = rcu_dereference_protected(vq->private_data,
+                                            lockdep_is_held(&vq->mutex));
         if (sock != oldsock) {
                 vhost_net_disable_vq(n, vq);
                 rcu_assign_pointer(vq->private_data, sock);
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index dd3d6f7406f8..8b5a1b33d0fe 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -320,7 +320,7 @@ long vhost_dev_reset_owner(struct vhost_dev *dev)
         vhost_dev_cleanup(dev);
 
         memory->nregions = 0;
-        dev->memory = memory;
+        RCU_INIT_POINTER(dev->memory, memory);
         return 0;
 }
 
@@ -352,8 +352,9 @@ void vhost_dev_cleanup(struct vhost_dev *dev)
                 fput(dev->log_file);
         dev->log_file = NULL;
         /* No one will access memory at this point */
-        kfree(dev->memory);
-        dev->memory = NULL;
+        kfree(rcu_dereference_protected(dev->memory,
+                                        lockdep_is_held(&dev->mutex)));
+        RCU_INIT_POINTER(dev->memory, NULL);
         if (dev->mm)
                 mmput(dev->mm);
         dev->mm = NULL;
@@ -440,14 +441,22 @@ static int vq_access_ok(unsigned int num,
 /* Caller should have device mutex but not vq mutex */
 int vhost_log_access_ok(struct vhost_dev *dev)
 {
-        return memory_access_ok(dev, dev->memory, 1);
+        struct vhost_memory *mp;
+
+        mp = rcu_dereference_protected(dev->memory,
+                                       lockdep_is_held(&dev->mutex));
+        return memory_access_ok(dev, mp, 1);
 }
 
 /* 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)
 {
-        return vq_memory_access_ok(log_base, vq->dev->memory,
+        struct vhost_memory *mp;
+
+        mp = rcu_dereference_protected(vq->dev->memory,
+                                       lockdep_is_held(&vq->mutex));
+        return vq_memory_access_ok(log_base, mp,
                             vhost_has_feature(vq->dev, VHOST_F_LOG_ALL)) &&
                 (!vq->log_used || log_access_ok(log_base, vq->log_addr,
                                         sizeof *vq->used +
@@ -487,7 +496,8 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
                 kfree(newmem);
                 return -EFAULT;
         }
-        oldmem = d->memory;
+        oldmem = rcu_dereference_protected(d->memory,
+                                           lockdep_is_held(&d->mutex));
         rcu_assign_pointer(d->memory, newmem);
         synchronize_rcu();
         kfree(oldmem);
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index afd77295971c..af3c11ded5fd 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -106,7 +106,7 @@ struct vhost_virtqueue {
          * vhost_work execution acts instead of rcu_read_lock() and the end of
          * vhost_work execution acts instead of rcu_read_lock().
          * Writers use virtqueue mutex. */
-        void *private_data;
+        void __rcu *private_data;
         /* Log write descriptors */
         void __user *log_base;
         struct vhost_log log[VHOST_NET_MAX_SG];
@@ -116,7 +116,7 @@ struct vhost_dev {
         /* Readers use RCU to access memory table pointer
          * log base pointer and features.
          * Writers use mutex below.*/
-        struct vhost_memory *memory;
+        struct vhost_memory __rcu *memory;
         struct mm_struct *mm;
         struct mutex mutex;
         unsigned acked_features;
@@ -173,7 +173,11 @@ enum {
 
 static inline int vhost_has_feature(struct vhost_dev *dev, int bit)
 {
-        unsigned acked_features = rcu_dereference(dev->acked_features);
+        unsigned acked_features;
+
+        acked_features =
+                rcu_dereference_index_check(dev->acked_features,
+                                            lockdep_is_held(&dev->mutex));
         return acked_features & (1 << bit);
 }
 
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 13365ba35218..7d24b0d94ed4 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -338,30 +338,29 @@ static void unmask_evtchn(int port)
 
 static int find_unbound_irq(void)
 {
-        int irq;
-        struct irq_desc *desc;
+        struct irq_data *data;
+        int irq, res;
 
         for (irq = 0; irq < nr_irqs; irq++) {
-                desc = irq_to_desc(irq);
+                data = irq_get_irq_data(irq);
                 /* only 0->15 have init'd desc; handle irq > 16 */
-                if (desc == NULL)
+                if (!data)
                         break;
-                if (desc->chip == &no_irq_chip)
+                if (data->chip == &no_irq_chip)
                         break;
-                if (desc->chip != &xen_dynamic_chip)
+                if (data->chip != &xen_dynamic_chip)
                         continue;
                 if (irq_info[irq].type == IRQT_UNBOUND)
-                        break;
+                        return irq;
         }
 
         if (irq == nr_irqs)
                 panic("No available IRQ to bind to: increase nr_irqs!\n");
 
-        desc = irq_to_desc_alloc_node(irq, 0);
-        if (WARN_ON(desc == NULL))
-                return -1;
+        res = irq_alloc_desc_at(irq, 0);
 
-        dynamic_irq_init_keep_chip_data(irq);
+        if (WARN_ON(res != irq))
+                return -1;
 
         return irq;
 }
@@ -495,7 +494,7 @@ static void unbind_from_irq(unsigned int irq)
         if (irq_info[irq].type != IRQT_UNBOUND) {
                 irq_info[irq] = mk_unbound_info();
 
-                dynamic_irq_cleanup(irq);
+                irq_free_desc(irq);
         }
 
         spin_unlock(&irq_mapping_update_lock);
diff --git a/fs/affs/super.c b/fs/affs/super.c
index 33c4e7eef470..9581ea94d5a1 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -109,8 +109,8 @@ static void init_once(void *foo)
 {
         struct affs_inode_info *ei = (struct affs_inode_info *) foo;
 
-        init_MUTEX(&ei->i_link_lock);
-        init_MUTEX(&ei->i_ext_lock);
+        sema_init(&ei->i_link_lock, 1);
+        sema_init(&ei->i_ext_lock, 1);
         inode_init_once(&ei->vfs_inode);
 }
 
diff --git a/fs/ceph/Kconfig b/fs/ceph/Kconfig
index 0fcd2640c23f..9eb134ea6eb2 100644
--- a/fs/ceph/Kconfig
+++ b/fs/ceph/Kconfig
@@ -1,9 +1,11 @@
 config CEPH_FS
         tristate "Ceph distributed file system (EXPERIMENTAL)"
         depends on INET && EXPERIMENTAL
+        select CEPH_LIB
         select LIBCRC32C
         select CRYPTO_AES
         select CRYPTO
+        default n
         help
           Choose Y or M here to include support for mounting the
           experimental Ceph distributed file system.  Ceph is an extremely
@@ -14,15 +16,3 @@ config CEPH_FS
 
           If unsure, say N.
 
-config CEPH_FS_PRETTYDEBUG
-        bool "Include file:line in ceph debug output"
-        depends on CEPH_FS
-        default n
-        help
-          If you say Y here, debug output will include a filename and
-          line to aid debugging.  This icnreases kernel size and slows
-          execution slightly when debug call sites are enabled (e.g.,
-          via CONFIG_DYNAMIC_DEBUG).
-
-          If unsure, say N.
-
diff --git a/fs/ceph/Makefile b/fs/ceph/Makefile
index 278e1172600d..9e6c4f2e8ff1 100644
--- a/fs/ceph/Makefile
+++ b/fs/ceph/Makefile
@@ -8,15 +8,8 @@ obj-$(CONFIG_CEPH_FS) += ceph.o
 
 ceph-objs := super.o inode.o dir.o file.o locks.o addr.o ioctl.o \
         export.o caps.o snap.o xattr.o \
-        messenger.o msgpool.o buffer.o pagelist.o \
-        mds_client.o mdsmap.o \
-        mon_client.o \
-        osd_client.o osdmap.o crush/crush.o crush/mapper.o crush/hash.o \
-        debugfs.o \
-        auth.o auth_none.o \
-        crypto.o armor.o \
-        auth_x.o \
-        ceph_fs.o ceph_strings.o ceph_hash.o ceph_frag.o
+        mds_client.o mdsmap.o strings.o ceph_frag.o \
+        debugfs.o
 
 else
 #Otherwise we were called directly from the command
diff --git a/fs/ceph/README b/fs/ceph/README
deleted file mode 100644
index 18352fab37c0..000000000000
--- a/fs/ceph/README
+++ /dev/null
@@ -1,20 +0,0 @@
-#
-# The following files are shared by (and manually synchronized
-# between) the Ceph userland and kernel client.
-#
-# userland                  kernel
-src/include/ceph_fs.h       fs/ceph/ceph_fs.h
-src/include/ceph_fs.cc      fs/ceph/ceph_fs.c
-src/include/msgr.h          fs/ceph/msgr.h
-src/include/rados.h         fs/ceph/rados.h
-src/include/ceph_strings.cc fs/ceph/ceph_strings.c
-src/include/ceph_frag.h     fs/ceph/ceph_frag.h
-src/include/ceph_frag.cc    fs/ceph/ceph_frag.c
-src/include/ceph_hash.h     fs/ceph/ceph_hash.h
-src/include/ceph_hash.cc    fs/ceph/ceph_hash.c
-src/crush/crush.c           fs/ceph/crush/crush.c
-src/crush/crush.h           fs/ceph/crush/crush.h
-src/crush/mapper.c          fs/ceph/crush/mapper.c
-src/crush/mapper.h          fs/ceph/crush/mapper.h
-src/crush/hash.h            fs/ceph/crush/hash.h
-src/crush/hash.c            fs/ceph/crush/hash.c
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index efbc604001c8..51bcc5ce3230 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1,4 +1,4 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/backing-dev.h>
 #include <linux/fs.h>
@@ -10,7 +10,8 @@
 #include <linux/task_io_accounting_ops.h>
 
 #include "super.h"
-#include "osd_client.h"
+#include "mds_client.h"
+#include <linux/ceph/osd_client.h>
 
 /*
  * Ceph address space ops.
@@ -193,7 +194,8 @@ static int readpage_nounlock(struct file *filp, struct page *page)
 {
         struct inode *inode = filp->f_dentry->d_inode;
         struct ceph_inode_info *ci = ceph_inode(inode);
-        struct ceph_osd_client *osdc = &ceph_inode_to_client(inode)->osdc;
+        struct ceph_osd_client *osdc = 
+                &ceph_inode_to_client(inode)->client->osdc;
         int err = 0;
         u64 len = PAGE_CACHE_SIZE;
 
@@ -265,7 +267,8 @@ static int ceph_readpages(struct file *file, struct address_space *mapping,
 {
         struct inode *inode = file->f_dentry->d_inode;
         struct ceph_inode_info *ci = ceph_inode(inode);
-        struct ceph_osd_client *osdc = &ceph_inode_to_client(inode)->osdc;
+        struct ceph_osd_client *osdc =
+                &ceph_inode_to_client(inode)->client->osdc;
         int rc = 0;
         struct page **pages;
         loff_t offset;
@@ -365,7 +368,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 {
         struct inode *inode;
         struct ceph_inode_info *ci;
-        struct ceph_client *client;
+        struct ceph_fs_client *fsc;
         struct ceph_osd_client *osdc;
         loff_t page_off = page->index << PAGE_CACHE_SHIFT;
         int len = PAGE_CACHE_SIZE;
@@ -383,8 +386,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
         }
         inode = page->mapping->host;
         ci = ceph_inode(inode);
-        client = ceph_inode_to_client(inode);
-        osdc = &client->osdc;
+        fsc = ceph_inode_to_client(inode);
+        osdc = &fsc->client->osdc;
 
         /* verify this is a writeable snap context */
         snapc = (void *)page->private;
@@ -414,10 +417,10 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
         dout("writepage %p page %p index %lu on %llu~%u snapc %p\n",
              inode, page, page->index, page_off, len, snapc);
 
-        writeback_stat = atomic_long_inc_return(&client->writeback_count);
+        writeback_stat = atomic_long_inc_return(&fsc->writeback_count);
         if (writeback_stat >
-            CONGESTION_ON_THRESH(client->mount_args->congestion_kb))
-                set_bdi_congested(&client->backing_dev_info, BLK_RW_ASYNC);
+            CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb))
+                set_bdi_congested(&fsc->backing_dev_info, BLK_RW_ASYNC);
 
         set_page_writeback(page);
         err = ceph_osdc_writepages(osdc, ceph_vino(inode),
@@ -496,7 +499,7 @@ static void writepages_finish(struct ceph_osd_request *req,
         struct address_space *mapping = inode->i_mapping;
         __s32 rc = -EIO;
         u64 bytes = 0;
-        struct ceph_client *client = ceph_inode_to_client(inode);
+        struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
         long writeback_stat;
         unsigned issued = ceph_caps_issued(ci);
 
@@ -529,10 +532,10 @@ static void writepages_finish(struct ceph_osd_request *req,
                 WARN_ON(!PageUptodate(page));
 
                 writeback_stat =
-                        atomic_long_dec_return(&client->writeback_count);
+                        atomic_long_dec_return(&fsc->writeback_count);
                 if (writeback_stat <
-                    CONGESTION_OFF_THRESH(client->mount_args->congestion_kb))
-                        clear_bdi_congested(&client->backing_dev_info,
+                    CONGESTION_OFF_THRESH(fsc->mount_options->congestion_kb))
+                        clear_bdi_congested(&fsc->backing_dev_info,
                                             BLK_RW_ASYNC);
 
                 ceph_put_snap_context((void *)page->private);
@@ -569,13 +572,13 @@ static void writepages_finish(struct ceph_osd_request *req,
  * mempool.  we avoid the mempool if we can because req->r_num_pages
  * may be less than the maximum write size.
  */
-static void alloc_page_vec(struct ceph_client *client,
+static void alloc_page_vec(struct ceph_fs_client *fsc,
                            struct ceph_osd_request *req)
 {
         req->r_pages = kmalloc(sizeof(struct page *) * req->r_num_pages,
                                GFP_NOFS);
         if (!req->r_pages) {
-                req->r_pages = mempool_alloc(client->wb_pagevec_pool, GFP_NOFS);
+                req->r_pages = mempool_alloc(fsc->wb_pagevec_pool, GFP_NOFS);
                 req->r_pages_from_pool = 1;
                 WARN_ON(!req->r_pages);
         }
@@ -590,7 +593,7 @@ static int ceph_writepages_start(struct address_space *mapping,
         struct inode *inode = mapping->host;
         struct backing_dev_info *bdi = mapping->backing_dev_info;
         struct ceph_inode_info *ci = ceph_inode(inode);
-        struct ceph_client *client;
+        struct ceph_fs_client *fsc;
         pgoff_t index, start, end;
         int range_whole = 0;
         int should_loop = 1;
@@ -617,13 +620,13 @@ static int ceph_writepages_start(struct address_space *mapping,
              wbc->sync_mode == WB_SYNC_NONE ? "NONE" :
              (wbc->sync_mode == WB_SYNC_ALL ? "ALL" : "HOLD"));
 
-        client = ceph_inode_to_client(inode);
-        if (client->mount_state == CEPH_MOUNT_SHUTDOWN) {
+        fsc = ceph_inode_to_client(inode);
+        if (fsc->mount_state == CEPH_MOUNT_SHUTDOWN) {
                 pr_warning("writepage_start %p on forced umount\n", inode);
                 return -EIO; /* we're in a forced umount, don't write! */
         }
-        if (client->mount_args->wsize && client->mount_args->wsize < wsize)
-                wsize = client->mount_args->wsize;
+        if (fsc->mount_options->wsize && fsc->mount_options->wsize < wsize)
+                wsize = fsc->mount_options->wsize;
         if (wsize < PAGE_CACHE_SIZE)
                 wsize = PAGE_CACHE_SIZE;
         max_pages_ever = wsize >> PAGE_CACHE_SHIFT;
@@ -769,7 +772,7 @@ get_more_pages:
                                 offset = (unsigned long long)page->index
                                         << PAGE_CACHE_SHIFT;
                                 len = wsize;
-                                req = ceph_osdc_new_request(&client->osdc,
+                                req = ceph_osdc_new_request(&fsc->client->osdc,
                                             &ci->i_layout,
                                             ceph_vino(inode),
                                             offset, &len,
@@ -782,7 +785,7 @@ get_more_pages:
                                             &inode->i_mtime, true, 1);
                                 max_pages = req->r_num_pages;
 
-                                alloc_page_vec(client, req);
+                                alloc_page_vec(fsc, req);
                                 req->r_callback = writepages_finish;
                                 req->r_inode = inode;
                         }
@@ -794,10 +797,10 @@ get_more_pages:
                              inode, page, page->index);
 
                         writeback_stat =
-                               atomic_long_inc_return(&client->writeback_count);
+                               atomic_long_inc_return(&fsc->writeback_count);
                         if (writeback_stat > CONGESTION_ON_THRESH(
-                                    client->mount_args->congestion_kb)) {
-                                set_bdi_congested(&client->backing_dev_info,
+                                    fsc->mount_options->congestion_kb)) {
+                                set_bdi_congested(&fsc->backing_dev_info,
                                                   BLK_RW_ASYNC);
                         }
 
@@ -846,7 +849,7 @@ get_more_pages:
                 op->payload_len = cpu_to_le32(len);
                 req->r_request->hdr.data_len = cpu_to_le32(len);
 
-                ceph_osdc_start_request(&client->osdc, req, true);
+                ceph_osdc_start_request(&fsc->client->osdc, req, true);
                 req = NULL;
 
                 /* continue? */
@@ -915,7 +918,7 @@ static int ceph_update_writeable_page(struct file *file,
 {
         struct inode *inode = file->f_dentry->d_inode;
         struct ceph_inode_info *ci = ceph_inode(inode);
-        struct ceph_mds_client *mdsc = &ceph_inode_to_client(inode)->mdsc;
+        struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
         loff_t page_off = pos & PAGE_CACHE_MASK;
         int pos_in_page = pos & ~PAGE_CACHE_MASK;
         int end_in_page = pos_in_page + len;
@@ -1053,8 +1056,8 @@ static int ceph_write_end(struct file *file, struct address_space *mapping,
                           struct page *page, void *fsdata)
 {
         struct inode *inode = file->f_dentry->d_inode;
-        struct ceph_client *client = ceph_inode_to_client(inode);
-        struct ceph_mds_client *mdsc = &client->mdsc;
+        struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+        struct ceph_mds_client *mdsc = fsc->mdsc;
         unsigned from = pos & (PAGE_CACHE_SIZE - 1);
         int check_cap = 0;
 
@@ -1123,7 +1126,7 @@ static int ceph_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
         struct inode *inode = vma->vm_file->f_dentry->d_inode;
         struct page *page = vmf->page;
-        struct ceph_mds_client *mdsc = &ceph_inode_to_client(inode)->mdsc;
+        struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
         loff_t off = page->index << PAGE_CACHE_SHIFT;
         loff_t size, len;
         int ret;
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 5e9da996a151..98ab13e2b71d 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1,4 +1,4 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/fs.h>
 #include <linux/kernel.h>
@@ -9,8 +9,9 @@
 #include <linux/writeback.h>
 
 #include "super.h"
-#include "decode.h"
-#include "messenger.h"
+#include "mds_client.h"
+#include <linux/ceph/decode.h>
+#include <linux/ceph/messenger.h>
 
 /*
  * Capability management
@@ -287,11 +288,11 @@ void ceph_put_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap)
         spin_unlock(&mdsc->caps_list_lock);
 }
 
-void ceph_reservation_status(struct ceph_client *client,
+void ceph_reservation_status(struct ceph_fs_client *fsc,
                              int *total, int *avail, int *used, int *reserved,
                              int *min)
 {
-        struct ceph_mds_client *mdsc = &client->mdsc;
+        struct ceph_mds_client *mdsc = fsc->mdsc;
 
         if (total)
                 *total = mdsc->caps_total_count;
@@ -399,7 +400,7 @@ static void __insert_cap_node(struct ceph_inode_info *ci,
 static void __cap_set_timeouts(struct ceph_mds_client *mdsc,
                                struct ceph_inode_info *ci)
 {
-        struct ceph_mount_args *ma = mdsc->client->mount_args;
+        struct ceph_mount_options *ma = mdsc->fsc->mount_options;
 
         ci->i_hold_caps_min = round_jiffies(jiffies +
                                             ma->caps_wanted_delay_min * HZ);
@@ -515,7 +516,7 @@ int ceph_add_cap(struct inode *inode,
                  unsigned seq, unsigned mseq, u64 realmino, int flags,
                  struct ceph_cap_reservation *caps_reservation)
 {
-        struct ceph_mds_client *mdsc = &ceph_inode_to_client(inode)->mdsc;
+        struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
         struct ceph_inode_info *ci = ceph_inode(inode);
         struct ceph_cap *new_cap = NULL;
         struct ceph_cap *cap;
@@ -873,7 +874,7 @@ void __ceph_remove_cap(struct ceph_cap *cap)
         struct ceph_mds_session *session = cap->session;
         struct ceph_inode_info *ci = cap->ci;
         struct ceph_mds_client *mdsc =
-                &ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc;
+                ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc;
         int removed = 0;
 
         dout("__ceph_remove_cap %p from %p\n", cap, &ci->vfs_inode);
@@ -1210,7 +1211,7 @@ void __ceph_flush_snaps(struct ceph_inode_info *ci,
         int mds;
         struct ceph_cap_snap *capsnap;
         u32 mseq;
-        struct ceph_mds_client *mdsc = &ceph_inode_to_client(inode)->mdsc;
+        struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
         struct ceph_mds_session *session = NULL; /* if session != NULL, we hold
                                                     session->s_mutex */
         u64 next_follows = 0;  /* keep track of how far we've gotten through the
@@ -1336,7 +1337,7 @@ static void ceph_flush_snaps(struct ceph_inode_info *ci)
 void __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask)
 {
         struct ceph_mds_client *mdsc =
-                &ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc;
+                ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc;
         struct inode *inode = &ci->vfs_inode;
         int was = ci->i_dirty_caps;
         int dirty = 0;
@@ -1378,7 +1379,7 @@ void __ceph_mark_dirty_caps(struct ceph_inode_info *ci, int mask)
 static int __mark_caps_flushing(struct inode *inode,
                                  struct ceph_mds_session *session)
 {
-        struct ceph_mds_client *mdsc = &ceph_sb_to_client(inode->i_sb)->mdsc;
+        struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
         struct ceph_inode_info *ci = ceph_inode(inode);
         int flushing;
 
@@ -1416,17 +1417,6 @@ static int __mark_caps_flushing(struct inode *inode,
 /*
  * try to invalidate mapping pages without blocking.
  */
-static int mapping_is_empty(struct address_space *mapping)
-{
-        struct page *page = find_get_page(mapping, 0);
-
-        if (!page)
-                return 1;
-
-        put_page(page);
-        return 0;
-}
-
 static int try_nonblocking_invalidate(struct inode *inode)
 {
         struct ceph_inode_info *ci = ceph_inode(inode);
@@ -1436,7 +1426,7 @@ static int try_nonblocking_invalidate(struct inode *inode)
         invalidate_mapping_pages(&inode->i_data, 0, -1);
         spin_lock(&inode->i_lock);
 
-        if (mapping_is_empty(&inode->i_data) &&
+        if (inode->i_data.nrpages == 0 &&
             invalidating_gen == ci->i_rdcache_gen) {
                 /* success. */
                 dout("try_nonblocking_invalidate %p success\n", inode);
@@ -1462,8 +1452,8 @@ static int try_nonblocking_invalidate(struct inode *inode)
 void ceph_check_caps(struct ceph_inode_info *ci, int flags,
                      struct ceph_mds_session *session)
 {
-        struct ceph_client *client = ceph_inode_to_client(&ci->vfs_inode);
-        struct ceph_mds_client *mdsc = &client->mdsc;
+        struct ceph_fs_client *fsc = ceph_inode_to_client(&ci->vfs_inode);
+        struct ceph_mds_client *mdsc = fsc->mdsc;
         struct inode *inode = &ci->vfs_inode;
         struct ceph_cap *cap;
         int file_wanted, used;
@@ -1533,7 +1523,7 @@ retry_locked:
          */
         if ((!is_delayed || mdsc->stopping) &&
             ci->i_wrbuffer_ref == 0 &&               /* no dirty pages... */
-            ci->i_rdcache_gen &&                     /* may have cached pages */
+            inode->i_data.nrpages &&                 /* have cached pages */
             (file_wanted == 0 ||                     /* no open files */
              (revoking & (CEPH_CAP_FILE_CACHE|
                           CEPH_CAP_FILE_LAZYIO))) && /*  or revoking cache */
@@ -1706,7 +1696,7 @@ ack:
 static int try_flush_caps(struct inode *inode, struct ceph_mds_session *session,
                           unsigned *flush_tid)
 {
-        struct ceph_mds_client *mdsc = &ceph_sb_to_client(inode->i_sb)->mdsc;
+        struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
         struct ceph_inode_info *ci = ceph_inode(inode);
         int unlock_session = session ? 0 : 1;
         int flushing = 0;
@@ -1872,7 +1862,7 @@ int ceph_write_inode(struct inode *inode, struct writeback_control *wbc)
                                        caps_are_flushed(inode, flush_tid));
         } else {
                 struct ceph_mds_client *mdsc =
-                        &ceph_sb_to_client(inode->i_sb)->mdsc;
+                        ceph_sb_to_client(inode->i_sb)->mdsc;
 
                 spin_lock(&inode->i_lock);
                 if (__ceph_caps_dirty(ci))
@@ -2465,7 +2455,7 @@ static void handle_cap_flush_ack(struct inode *inode, u64 flush_tid,
         __releases(inode->i_lock)
 {
         struct ceph_inode_info *ci = ceph_inode(inode);
-        struct ceph_mds_client *mdsc = &ceph_sb_to_client(inode->i_sb)->mdsc;
+        struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
         unsigned seq = le32_to_cpu(m->seq);
         int dirty = le32_to_cpu(m->dirty);
         int cleaned = 0;
@@ -2713,7 +2703,7 @@ void ceph_handle_caps(struct ceph_mds_session *session,
                       struct ceph_msg *msg)
 {
         struct ceph_mds_client *mdsc = session->s_mdsc;
-        struct super_block *sb = mdsc->client->sb;
+        struct super_block *sb = mdsc->fsc->sb;
         struct inode *inode;
         struct ceph_cap *cap;
         struct ceph_mds_caps *h;
diff --git a/fs/ceph/ceph_frag.c b/fs/ceph/ceph_frag.c
index ab6cf35c4091..bdce8b1fbd06 100644
--- a/fs/ceph/ceph_frag.c
+++ b/fs/ceph/ceph_frag.c
@@ -1,7 +1,8 @@
 /*
  * Ceph 'frag' type
  */
-#include "types.h"
+#include <linux/module.h>
+#include <linux/ceph/types.h>
 
 int ceph_frag_compare(__u32 a, __u32 b)
 {
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index 6fd8b20a8611..7ae1b3d55b58 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -1,4 +1,4 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/device.h>
 #include <linux/slab.h>
@@ -7,143 +7,49 @@
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/mon_client.h>
+#include <linux/ceph/auth.h>
+#include <linux/ceph/debugfs.h>
+
 #include "super.h"
-#include "mds_client.h"
-#include "mon_client.h"
-#include "auth.h"
 
 #ifdef CONFIG_DEBUG_FS
 
-/*
- * Implement /sys/kernel/debug/ceph fun
- *
- * /sys/kernel/debug/ceph/client*  - an instance of the ceph client
- *      .../osdmap      - current osdmap
- *      .../mdsmap      - current mdsmap
- *      .../monmap      - current monmap
- *      .../osdc        - active osd requests
- *      .../mdsc        - active mds requests
- *      .../monc        - mon client state
- *      .../dentry_lru  - dump contents of dentry lru
- *      .../caps        - expose cap (reservation) stats
- *      .../bdi         - symlink to ../../bdi/something
- */
-
-static struct dentry *ceph_debugfs_dir;
-
-static int monmap_show(struct seq_file *s, void *p)
-{
-        int i;
-        struct ceph_client *client = s->private;
-
-        if (client->monc.monmap == NULL)
-                return 0;
-
-        seq_printf(s, "epoch %d\n", client->monc.monmap->epoch);
-        for (i = 0; i < client->monc.monmap->num_mon; i++) {
-                struct ceph_entity_inst *inst =
-                        &client->monc.monmap->mon_inst[i];
-
-                seq_printf(s, "\t%s%lld\t%s\n",
-                           ENTITY_NAME(inst->name),
-                           pr_addr(&inst->addr.in_addr));
-        }
-        return 0;
-}
+#include "mds_client.h"
 
 static int mdsmap_show(struct seq_file *s, void *p)
 {
         int i;
-        struct ceph_client *client = s->private;
+        struct ceph_fs_client *fsc = s->private;
 
-        if (client->mdsc.mdsmap == NULL)
+        if (fsc->mdsc == NULL || fsc->mdsc->mdsmap == NULL)
                 return 0;
-        seq_printf(s, "epoch %d\n", client->mdsc.mdsmap->m_epoch);
-        seq_printf(s, "root %d\n", client->mdsc.mdsmap->m_root);
+        seq_printf(s, "epoch %d\n", fsc->mdsc->mdsmap->m_epoch);
+        seq_printf(s, "root %d\n", fsc->mdsc->mdsmap->m_root);
         seq_printf(s, "session_timeout %d\n",
-                       client->mdsc.mdsmap->m_session_timeout);
+                       fsc->mdsc->mdsmap->m_session_timeout);
         seq_printf(s, "session_autoclose %d\n",
-                       client->mdsc.mdsmap->m_session_autoclose);
-        for (i = 0; i < client->mdsc.mdsmap->m_max_mds; i++) {
+                       fsc->mdsc->mdsmap->m_session_autoclose);
+        for (i = 0; i < fsc->mdsc->mdsmap->m_max_mds; i++) {
                 struct ceph_entity_addr *addr =
-                        &client->mdsc.mdsmap->m_info[i].addr;
-                int state = client->mdsc.mdsmap->m_info[i].state;
+                        &fsc->mdsc->mdsmap->m_info[i].addr;
+                int state = fsc->mdsc->mdsmap->m_info[i].state;
 
-                seq_printf(s, "\tmds%d\t%s\t(%s)\n", i, pr_addr(&addr->in_addr),
+                seq_printf(s, "\tmds%d\t%s\t(%s)\n", i,
+                               ceph_pr_addr(&addr->in_addr),
                                ceph_mds_state_name(state));
         }
         return 0;
 }
 
-static int osdmap_show(struct seq_file *s, void *p)
-{
-        int i;
-        struct ceph_client *client = s->private;
-        struct rb_node *n;
-
-        if (client->osdc.osdmap == NULL)
-                return 0;
-        seq_printf(s, "epoch %d\n", client->osdc.osdmap->epoch);
-        seq_printf(s, "flags%s%s\n",
-                   (client->osdc.osdmap->flags & CEPH_OSDMAP_NEARFULL) ?
-                   " NEARFULL" : "",
-                   (client->osdc.osdmap->flags & CEPH_OSDMAP_FULL) ?
-                   " FULL" : "");
-        for (n = rb_first(&client->osdc.osdmap->pg_pools); n; n = rb_next(n)) {
-                struct ceph_pg_pool_info *pool =
-                        rb_entry(n, struct ceph_pg_pool_info, node);
-                seq_printf(s, "pg_pool %d pg_num %d / %d, lpg_num %d / %d\n",
-                           pool->id, pool->v.pg_num, pool->pg_num_mask,
-                           pool->v.lpg_num, pool->lpg_num_mask);
-        }
-        for (i = 0; i < client->osdc.osdmap->max_osd; i++) {
-                struct ceph_entity_addr *addr =
-                        &client->osdc.osdmap->osd_addr[i];
-                int state = client->osdc.osdmap->osd_state[i];
-                char sb[64];
-
-                seq_printf(s, "\tosd%d\t%s\t%3d%%\t(%s)\n",
-                           i, pr_addr(&addr->in_addr),
-                           ((client->osdc.osdmap->osd_weight[i]*100) >> 16),
-                           ceph_osdmap_state_str(sb, sizeof(sb), state));
-        }
-        return 0;
-}
-
-static int monc_show(struct seq_file *s, void *p)
-{
-        struct ceph_client *client = s->private;
-        struct ceph_mon_generic_request *req;
-        struct ceph_mon_client *monc = &client->monc;
-        struct rb_node *rp;
-
-        mutex_lock(&monc->mutex);
-
-        if (monc->have_mdsmap)
-                seq_printf(s, "have mdsmap %u\n", (unsigned)monc->have_mdsmap);
-        if (monc->have_osdmap)
-                seq_printf(s, "have osdmap %u\n", (unsigned)monc->have_osdmap);
-        if (monc->want_next_osdmap)
-                seq_printf(s, "want next osdmap\n");
-
-        for (rp = rb_first(&monc->generic_request_tree); rp; rp = rb_next(rp)) {
-                __u16 op;
-                req = rb_entry(rp, struct ceph_mon_generic_request, node);
-                op = le16_to_cpu(req->request->hdr.type);
-                if (op == CEPH_MSG_STATFS)
-                        seq_printf(s, "%lld statfs\n", req->tid);
-                else
-                        seq_printf(s, "%lld unknown\n", req->tid);
-        }
-
-        mutex_unlock(&monc->mutex);
-        return 0;
-}
-
+/*
+ * mdsc debugfs
+ */
 static int mdsc_show(struct seq_file *s, void *p)
 {
-        struct ceph_client *client = s->private;
-        struct ceph_mds_client *mdsc = &client->mdsc;
+        struct ceph_fs_client *fsc = s->private;
+        struct ceph_mds_client *mdsc = fsc->mdsc;
         struct ceph_mds_request *req;
         struct rb_node *rp;
         int pathlen;
@@ -214,61 +120,12 @@ static int mdsc_show(struct seq_file *s, void *p)
         return 0;
 }
 
-static int osdc_show(struct seq_file *s, void *pp)
-{
-        struct ceph_client *client = s->private;
-        struct ceph_osd_client *osdc = &client->osdc;
-        struct rb_node *p;
-
-        mutex_lock(&osdc->request_mutex);
-        for (p = rb_first(&osdc->requests); p; p = rb_next(p)) {
-                struct ceph_osd_request *req;
-                struct ceph_osd_request_head *head;
-                struct ceph_osd_op *op;
-                int num_ops;
-                int opcode, olen;
-                int i;
-
-                req = rb_entry(p, struct ceph_osd_request, r_node);
-
-                seq_printf(s, "%lld\tosd%d\t%d.%x\t", req->r_tid,
-                           req->r_osd ? req->r_osd->o_osd : -1,
-                           le32_to_cpu(req->r_pgid.pool),
-                           le16_to_cpu(req->r_pgid.ps));
-
-                head = req->r_request->front.iov_base;
-                op = (void *)(head + 1);
-
-                num_ops = le16_to_cpu(head->num_ops);
-                olen = le32_to_cpu(head->object_len);
-                seq_printf(s, "%.*s", olen,
-                           (const char *)(head->ops + num_ops));
-
-                if (req->r_reassert_version.epoch)
-                        seq_printf(s, "\t%u'%llu",
-                           (unsigned)le32_to_cpu(req->r_reassert_version.epoch),
-                           le64_to_cpu(req->r_reassert_version.version));
-                else
-                        seq_printf(s, "\t");
-
-                for (i = 0; i < num_ops; i++) {
-                        opcode = le16_to_cpu(op->op);
-                        seq_printf(s, "\t%s", ceph_osd_op_name(opcode));
-                        op++;
-                }
-
-                seq_printf(s, "\n");
-        }
-        mutex_unlock(&osdc->request_mutex);
-        return 0;
-}
-
 static int caps_show(struct seq_file *s, void *p)
 {
-        struct ceph_client *client = s->private;
+        struct ceph_fs_client *fsc = s->private;
         int total, avail, used, reserved, min;
 
-        ceph_reservation_status(client, &total, &avail, &used, &reserved, &min);
+        ceph_reservation_status(fsc, &total, &avail, &used, &reserved, &min);
         seq_printf(s, "total\t\t%d\n"
                    "avail\t\t%d\n"
                    "used\t\t%d\n"
@@ -280,8 +137,8 @@ static int caps_show(struct seq_file *s, void *p)
 
 static int dentry_lru_show(struct seq_file *s, void *ptr)
 {
-        struct ceph_client *client = s->private;
-        struct ceph_mds_client *mdsc = &client->mdsc;
+        struct ceph_fs_client *fsc = s->private;
+        struct ceph_mds_client *mdsc = fsc->mdsc;
         struct ceph_dentry_info *di;
 
         spin_lock(&mdsc->dentry_lru_lock);
@@ -295,199 +152,124 @@ static int dentry_lru_show(struct seq_file *s, void *ptr)
         return 0;
 }
 
-#define DEFINE_SHOW_FUNC(name)                                          \
-static int name##_open(struct inode *inode, struct file *file)          \
-{                                                                       \
-        struct seq_file *sf;                                            \
-        int ret;                                                        \
-                                                                        \
-        ret = single_open(file, name, NULL);                            \
-        sf = file->private_data;                                        \
-        sf->private = inode->i_private;                                 \
-        return ret;                                                     \
-}                                                                       \
-                                                                        \
-static const struct file_operations name##_fops = {                     \
-        .open           = name##_open,                                  \
-        .read           = seq_read,                                     \
-        .llseek         = seq_lseek,                                    \
-        .release        = single_release,                               \
-};
-
-DEFINE_SHOW_FUNC(monmap_show)
-DEFINE_SHOW_FUNC(mdsmap_show)
-DEFINE_SHOW_FUNC(osdmap_show)
-DEFINE_SHOW_FUNC(monc_show)
-DEFINE_SHOW_FUNC(mdsc_show)
-DEFINE_SHOW_FUNC(osdc_show)
-DEFINE_SHOW_FUNC(dentry_lru_show)
-DEFINE_SHOW_FUNC(caps_show)
+CEPH_DEFINE_SHOW_FUNC(mdsmap_show)
+CEPH_DEFINE_SHOW_FUNC(mdsc_show)
+CEPH_DEFINE_SHOW_FUNC(caps_show)
+CEPH_DEFINE_SHOW_FUNC(dentry_lru_show)
+
 
+/*
+ * debugfs
+ */
 static int congestion_kb_set(void *data, u64 val)
 {
-        struct ceph_client *client = (struct ceph_client *)data;
-
-        if (client)
-                client->mount_args->congestion_kb = (int)val;
+        struct ceph_fs_client *fsc = (struct ceph_fs_client *)data;
 
+        fsc->mount_options->congestion_kb = (int)val;
         return 0;
 }
 
 static int congestion_kb_get(void *data, u64 *val)
 {
-        struct ceph_client *client = (struct ceph_client *)data;
-
-        if (client)
-                *val = (u64)client->mount_args->congestion_kb;
+        struct ceph_fs_client *fsc = (struct ceph_fs_client *)data;
 
+        *val = (u64)fsc->mount_options->congestion_kb;
         return 0;
 }
 
-
 DEFINE_SIMPLE_ATTRIBUTE(congestion_kb_fops, congestion_kb_get,
                         congestion_kb_set, "%llu\n");
 
-int __init ceph_debugfs_init(void)
-{
-        ceph_debugfs_dir = debugfs_create_dir("ceph", NULL);
-        if (!ceph_debugfs_dir)
-                return -ENOMEM;
-        return 0;
-}
 
-void ceph_debugfs_cleanup(void)
+void ceph_fs_debugfs_cleanup(struct ceph_fs_client *fsc)
 {
-        debugfs_remove(ceph_debugfs_dir);
+        dout("ceph_fs_debugfs_cleanup\n");
+        debugfs_remove(fsc->debugfs_bdi);
+        debugfs_remove(fsc->debugfs_congestion_kb);
+        debugfs_remove(fsc->debugfs_mdsmap);
+        debugfs_remove(fsc->debugfs_caps);
+        debugfs_remove(fsc->debugfs_mdsc);
+        debugfs_remove(fsc->debugfs_dentry_lru);
 }
 
-int ceph_debugfs_client_init(struct ceph_client *client)
+int ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
 {
-        int ret = 0;
-        char name[80];
-
-        snprintf(name, sizeof(name), "%pU.client%lld", &client->fsid,
-                 client->monc.auth->global_id);
+        char name[100];
+        int err = -ENOMEM;
 
-        client->debugfs_dir = debugfs_create_dir(name, ceph_debugfs_dir);
-        if (!client->debugfs_dir)
-                goto out;
-
-        client->monc.debugfs_file = debugfs_create_file("monc",
-                                                      0600,
-                                                      client->debugfs_dir,
-                                                      client,
-                                                      &monc_show_fops);
-        if (!client->monc.debugfs_file)
+        dout("ceph_fs_debugfs_init\n");
+        fsc->debugfs_congestion_kb =
+                debugfs_create_file("writeback_congestion_kb",
+                                    0600,
+                                    fsc->client->debugfs_dir,
+                                    fsc,
+                                    &congestion_kb_fops);
+        if (!fsc->debugfs_congestion_kb)
                 goto out;
 
-        client->mdsc.debugfs_file = debugfs_create_file("mdsc",
-                                                      0600,
-                                                      client->debugfs_dir,
-                                                      client,
-                                                      &mdsc_show_fops);
-        if (!client->mdsc.debugfs_file)
-                goto out;
+        dout("a\n");
 
-        client->osdc.debugfs_file = debugfs_create_file("osdc",
-                                                      0600,
-                                                      client->debugfs_dir,
-                                                      client,
-                                                      &osdc_show_fops);
-        if (!client->osdc.debugfs_file)
+        snprintf(name, sizeof(name), "../../bdi/%s",
+                 dev_name(fsc->backing_dev_info.dev));
+        fsc->debugfs_bdi =
+                debugfs_create_symlink("bdi",
+                                       fsc->client->debugfs_dir,
+                                       name);
+        if (!fsc->debugfs_bdi)
                 goto out;
 
-        client->debugfs_monmap = debugfs_create_file("monmap",
+        dout("b\n");
+        fsc->debugfs_mdsmap = debugfs_create_file("mdsmap",
                                         0600,
-                                        client->debugfs_dir,
-                                        client,
-                                        &monmap_show_fops);
-        if (!client->debugfs_monmap)
-                goto out;
-
-        client->debugfs_mdsmap = debugfs_create_file("mdsmap",
-                                        0600,
-                                        client->debugfs_dir,
-                                        client,
+                                        fsc->client->debugfs_dir,
+                                        fsc,
                                         &mdsmap_show_fops);
-        if (!client->debugfs_mdsmap)
-                goto out;
-
-        client->debugfs_osdmap = debugfs_create_file("osdmap",
-                                        0600,
-                                        client->debugfs_dir,
-                                        client,
-                                        &osdmap_show_fops);
-        if (!client->debugfs_osdmap)
+        if (!fsc->debugfs_mdsmap)
                 goto out;
 
-        client->debugfs_dentry_lru = debugfs_create_file("dentry_lru",
-                                        0600,
-                                        client->debugfs_dir,
-                                        client,
-                                        &dentry_lru_show_fops);
-        if (!client->debugfs_dentry_lru)
+        dout("ca\n");
+        fsc->debugfs_mdsc = debugfs_create_file("mdsc",
+                                                0600,
+                                                fsc->client->debugfs_dir,
+                                                fsc,
+                                                &mdsc_show_fops);
+        if (!fsc->debugfs_mdsc)
                 goto out;
 
-        client->debugfs_caps = debugfs_create_file("caps",
+        dout("da\n");
+        fsc->debugfs_caps = debugfs_create_file("caps",
                                                    0400,
-                                                   client->debugfs_dir,
-                                                   client,
+                                                   fsc->client->debugfs_dir,
+                                                   fsc,
                                                    &caps_show_fops);
-        if (!client->debugfs_caps)
+        if (!fsc->debugfs_caps)
                 goto out;
 
-        client->debugfs_congestion_kb =
-                debugfs_create_file("writeback_congestion_kb",
-                                    0600,
-                                    client->debugfs_dir,
-                                    client,
-                                    &congestion_kb_fops);
-        if (!client->debugfs_congestion_kb)
+        dout("ea\n");
+        fsc->debugfs_dentry_lru = debugfs_create_file("dentry_lru",
+                                        0600,
+                                        fsc->client->debugfs_dir,
+                                        fsc,
+                                        &dentry_lru_show_fops);
+        if (!fsc->debugfs_dentry_lru)
                 goto out;
 
-        sprintf(name, "../../bdi/%s", dev_name(client->sb->s_bdi->dev));
-        client->debugfs_bdi = debugfs_create_symlink("bdi", client->debugfs_dir,
-                                                     name);
-
         return 0;
 
 out:
-        ceph_debugfs_client_cleanup(client);
-        return ret;
+        ceph_fs_debugfs_cleanup(fsc);
+        return err;
 }
 
-void ceph_debugfs_client_cleanup(struct ceph_client *client)
-{
-        debugfs_remove(client->debugfs_bdi);
-        debugfs_remove(client->debugfs_caps);
-        debugfs_remove(client->debugfs_dentry_lru);
-        debugfs_remove(client->debugfs_osdmap);
-        debugfs_remove(client->debugfs_mdsmap);
-        debugfs_remove(client->debugfs_monmap);
-        debugfs_remove(client->osdc.debugfs_file);
-        debugfs_remove(client->mdsc.debugfs_file);
-        debugfs_remove(client->monc.debugfs_file);
-        debugfs_remove(client->debugfs_congestion_kb);
-        debugfs_remove(client->debugfs_dir);
-}
 
 #else  /* CONFIG_DEBUG_FS */
 
-int __init ceph_debugfs_init(void)
-{
-        return 0;
-}
-
-void ceph_debugfs_cleanup(void)
-{
-}
-
-int ceph_debugfs_client_init(struct ceph_client *client)
+int ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
 {
         return 0;
 }
 
-void ceph_debugfs_client_cleanup(struct ceph_client *client)
+void ceph_fs_debugfs_cleanup(struct ceph_fs_client *fsc)
 {
 }
 
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index a1986eb52045..e0a2dc6fcafc 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1,4 +1,4 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/spinlock.h>
 #include <linux/fs_struct.h>
@@ -7,6 +7,7 @@
 #include <linux/sched.h>
 
 #include "super.h"
+#include "mds_client.h"
 
 /*
  * Directory operations: readdir, lookup, create, link, unlink,
@@ -94,10 +95,7 @@ static unsigned fpos_off(loff_t p)
  */
 static int __dcache_readdir(struct file *filp,
                             void *dirent, filldir_t filldir)
-                __releases(inode->i_lock)
-                __acquires(inode->i_lock)
 {
-        struct inode *inode = filp->f_dentry->d_inode;
         struct ceph_file_info *fi = filp->private_data;
         struct dentry *parent = filp->f_dentry;
         struct inode *dir = parent->d_inode;
@@ -153,7 +151,6 @@ more:
 
         atomic_inc(&dentry->d_count);
         spin_unlock(&dcache_lock);
-        spin_unlock(&inode->i_lock);
 
         dout(" %llu (%llu) dentry %p %.*s %p\n", di->offset, filp->f_pos,
              dentry, dentry->d_name.len, dentry->d_name.name, dentry->d_inode);
@@ -171,35 +168,30 @@ more:
                 } else {
                         dput(last);
                 }
-                last = NULL;
         }
-
-        spin_lock(&inode->i_lock);
-        spin_lock(&dcache_lock);
-
         last = dentry;
 
         if (err < 0)
-                goto out_unlock;
+                goto out;
 
-        p = p->prev;
         filp->f_pos++;
 
         /* make sure a dentry wasn't dropped while we didn't have dcache_lock */
-        if ((ceph_inode(dir)->i_ceph_flags & CEPH_I_COMPLETE))
-                goto more;
-        dout(" lost I_COMPLETE on %p; falling back to mds\n", dir);
-        err = -EAGAIN;
+        if (!ceph_i_test(dir, CEPH_I_COMPLETE)) {
+                dout(" lost I_COMPLETE on %p; falling back to mds\n", dir);
+                err = -EAGAIN;
+                goto out;
+        }
+
+        spin_lock(&dcache_lock);
+        p = p->prev;    /* advance to next dentry */
+        goto more;
 
 out_unlock:
         spin_unlock(&dcache_lock);
-
-        if (last) {
-                spin_unlock(&inode->i_lock);
+out:
+        if (last)
                 dput(last);
-                spin_lock(&inode->i_lock);
-        }
-
         return err;
 }
 
@@ -227,15 +219,15 @@ static int ceph_readdir(struct file *filp, void *dirent, filldir_t filldir)
         struct ceph_file_info *fi = filp->private_data;
         struct inode *inode = filp->f_dentry->d_inode;
         struct ceph_inode_info *ci = ceph_inode(inode);
-        struct ceph_client *client = ceph_inode_to_client(inode);
-        struct ceph_mds_client *mdsc = &client->mdsc;
+        struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
+        struct ceph_mds_client *mdsc = fsc->mdsc;
         unsigned frag = fpos_frag(filp->f_pos);
         int off = fpos_off(filp->f_pos);
         int err;
         u32 ftype;
         struct ceph_mds_reply_info_parsed *rinfo;
-        const int max_entries = client->mount_args->max_readdir;
-        const int max_bytes = client->mount_args->max_readdir_bytes;
+        const int max_entries = fsc->mount_options->max_readdir;
+        const int max_bytes = fsc->mount_options->max_readdir_bytes;
 
         dout("readdir %p filp %p frag %u off %u\n", inode, filp, frag, off);
         if (fi->at_end)
@@ -267,17 +259,17 @@ static int ceph_readdir(struct file *filp, void *dirent, filldir_t filldir)
         /* can we use the dcache? */
         spin_lock(&inode->i_lock);
         if ((filp->f_pos == 2 || fi->dentry) &&
-            !ceph_test_opt(client, NOASYNCREADDIR) &&
+            !ceph_test_mount_opt(fsc, NOASYNCREADDIR) &&
             ceph_snap(inode) != CEPH_SNAPDIR &&
             (ci->i_ceph_flags & CEPH_I_COMPLETE) &&
             __ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1)) {
+                spin_unlock(&inode->i_lock);
                 err = __dcache_readdir(filp, dirent, filldir);
-                if (err != -EAGAIN) {
-                        spin_unlock(&inode->i_lock);
+                if (err != -EAGAIN)
                         return err;
-                }
+        } else {
+                spin_unlock(&inode->i_lock);
         }
-        spin_unlock(&inode->i_lock);
         if (fi->dentry) {
                 err = note_last_dentry(fi, fi->dentry->d_name.name,
                                        fi->dentry->d_name.len);
@@ -487,14 +479,13 @@ static loff_t ceph_dir_llseek(struct file *file, loff_t offset, int origin)
 struct dentry *ceph_finish_lookup(struct ceph_mds_request *req,
                                   struct dentry *dentry, int err)
 {
-        struct ceph_client *client = ceph_sb_to_client(dentry->d_sb);
+        struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
         struct inode *parent = dentry->d_parent->d_inode;
 
         /* .snap dir? */
         if (err == -ENOENT &&
-            ceph_vino(parent).ino != CEPH_INO_ROOT && /* no .snap in root dir */
             strcmp(dentry->d_name.name,
-                   client->mount_args->snapdir_name) == 0) {
+                   fsc->mount_options->snapdir_name) == 0) {
                 struct inode *inode = ceph_get_snapdir(parent);
                 dout("ENOENT on snapdir %p '%.*s', linking to snapdir %p\n",
                      dentry, dentry->d_name.len, dentry->d_name.name, inode);
@@ -539,8 +530,8 @@ static int is_root_ceph_dentry(struct inode *inode, struct dentry *dentry)
 static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
                                   struct nameidata *nd)
 {
-        struct ceph_client *client = ceph_sb_to_client(dir->i_sb);
-        struct ceph_mds_client *mdsc = &client->mdsc;
+        struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
+        struct ceph_mds_client *mdsc = fsc->mdsc;
         struct ceph_mds_request *req;
         int op;
         int err;
@@ -572,7 +563,7 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
                 spin_lock(&dir->i_lock);
                 dout(" dir %p flags are %d\n", dir, ci->i_ceph_flags);
                 if (strncmp(dentry->d_name.name,
-                            client->mount_args->snapdir_name,
+                            fsc->mount_options->snapdir_name,
                             dentry->d_name.len) &&
                     !is_root_ceph_dentry(dir, dentry) &&
                     (ci->i_ceph_flags & CEPH_I_COMPLETE) &&
@@ -629,8 +620,8 @@ int ceph_handle_notrace_create(struct inode *dir, struct dentry *dentry)
 static int ceph_mknod(struct inode *dir, struct dentry *dentry,
                       int mode, dev_t rdev)
 {
-        struct ceph_client *client = ceph_sb_to_client(dir->i_sb);
-        struct ceph_mds_client *mdsc = &client->mdsc;
+        struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
+        struct ceph_mds_client *mdsc = fsc->mdsc;
         struct ceph_mds_request *req;
         int err;
 
@@ -685,8 +676,8 @@ static int ceph_create(struct inode *dir, struct dentry *dentry, int mode,
 static int ceph_symlink(struct inode *dir, struct dentry *dentry,
                             const char *dest)
 {
-        struct ceph_client *client = ceph_sb_to_client(dir->i_sb);
-        struct ceph_mds_client *mdsc = &client->mdsc;
+        struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
+        struct ceph_mds_client *mdsc = fsc->mdsc;
         struct ceph_mds_request *req;
         int err;
 
@@ -716,8 +707,8 @@ static int ceph_symlink(struct inode *dir, struct dentry *dentry,
 
 static int ceph_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 {
-        struct ceph_client *client = ceph_sb_to_client(dir->i_sb);
-        struct ceph_mds_client *mdsc = &client->mdsc;
+        struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
+        struct ceph_mds_client *mdsc = fsc->mdsc;
         struct ceph_mds_request *req;
         int err = -EROFS;
         int op;
@@ -758,8 +749,8 @@ out:
 static int ceph_link(struct dentry *old_dentry, struct inode *dir,
                      struct dentry *dentry)
 {
-        struct ceph_client *client = ceph_sb_to_client(dir->i_sb);
-        struct ceph_mds_client *mdsc = &client->mdsc;
+        struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
+        struct ceph_mds_client *mdsc = fsc->mdsc;
         struct ceph_mds_request *req;
         int err;
 
@@ -813,8 +804,8 @@ static int drop_caps_for_unlink(struct inode *inode)
  */
 static int ceph_unlink(struct inode *dir, struct dentry *dentry)
 {
-        struct ceph_client *client = ceph_sb_to_client(dir->i_sb);
-        struct ceph_mds_client *mdsc = &client->mdsc;
+        struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
+        struct ceph_mds_client *mdsc = fsc->mdsc;
         struct inode *inode = dentry->d_inode;
         struct ceph_mds_request *req;
         int err = -EROFS;
@@ -854,8 +845,8 @@ out:
 static int ceph_rename(struct inode *old_dir, struct dentry *old_dentry,
                        struct inode *new_dir, struct dentry *new_dentry)
 {
-        struct ceph_client *client = ceph_sb_to_client(old_dir->i_sb);
-        struct ceph_mds_client *mdsc = &client->mdsc;
+        struct ceph_fs_client *fsc = ceph_sb_to_client(old_dir->i_sb);
+        struct ceph_mds_client *mdsc = fsc->mdsc;
         struct ceph_mds_request *req;
         int err;
 
@@ -1076,7 +1067,7 @@ static ssize_t ceph_read_dir(struct file *file, char __user *buf, size_t size,
         struct ceph_inode_info *ci = ceph_inode(inode);
         int left;
 
-        if (!ceph_test_opt(ceph_sb_to_client(inode->i_sb), DIRSTAT))
+        if (!ceph_test_mount_opt(ceph_sb_to_client(inode->i_sb), DIRSTAT))
                 return -EISDIR;
 
         if (!cf->dir_info) {
@@ -1177,7 +1168,7 @@ void ceph_dentry_lru_add(struct dentry *dn)
         dout("dentry_lru_add %p %p '%.*s'\n", di, dn,
              dn->d_name.len, dn->d_name.name);
         if (di) {
-                mdsc = &ceph_sb_to_client(dn->d_sb)->mdsc;
+                mdsc = ceph_sb_to_client(dn->d_sb)->mdsc;
                 spin_lock(&mdsc->dentry_lru_lock);
                 list_add_tail(&di->lru, &mdsc->dentry_lru);
                 mdsc->num_dentry++;
@@ -1193,7 +1184,7 @@ void ceph_dentry_lru_touch(struct dentry *dn)
         dout("dentry_lru_touch %p %p '%.*s' (offset %lld)\n", di, dn,
              dn->d_name.len, dn->d_name.name, di->offset);
         if (di) {
-                mdsc = &ceph_sb_to_client(dn->d_sb)->mdsc;
+                mdsc = ceph_sb_to_client(dn->d_sb)->mdsc;
                 spin_lock(&mdsc->dentry_lru_lock);
                 list_move_tail(&di->lru, &mdsc->dentry_lru);
                 spin_unlock(&mdsc->dentry_lru_lock);
@@ -1208,7 +1199,7 @@ void ceph_dentry_lru_del(struct dentry *dn)
         dout("dentry_lru_del %p %p '%.*s'\n", di, dn,
              dn->d_name.len, dn->d_name.name);
         if (di) {
-                mdsc = &ceph_sb_to_client(dn->d_sb)->mdsc;
+                mdsc = ceph_sb_to_client(dn->d_sb)->mdsc;
                 spin_lock(&mdsc->dentry_lru_lock);
                 list_del_init(&di->lru);
                 mdsc->num_dentry--;
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index e38423e82f2e..2297d9426992 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -1,10 +1,11 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/exportfs.h>
 #include <linux/slab.h>
 #include <asm/unaligned.h>
 
 #include "super.h"
+#include "mds_client.h"
 
 /*
  * NFS export support
@@ -120,7 +121,7 @@ static struct dentry *__fh_to_dentry(struct super_block *sb,
 static struct dentry *__cfh_to_dentry(struct super_block *sb,
                                       struct ceph_nfs_confh *cfh)
 {
-        struct ceph_mds_client *mdsc = &ceph_sb_to_client(sb)->mdsc;
+        struct ceph_mds_client *mdsc = ceph_sb_to_client(sb)->mdsc;
         struct inode *inode;
         struct dentry *dentry;
         struct ceph_vino vino;
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 66e4da6dba22..e77c28cf3690 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -1,5 +1,6 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
+#include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/file.h>
@@ -38,8 +39,8 @@
 static struct ceph_mds_request *
 prepare_open_request(struct super_block *sb, int flags, int create_mode)
 {
-        struct ceph_client *client = ceph_sb_to_client(sb);
-        struct ceph_mds_client *mdsc = &client->mdsc;
+        struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
+        struct ceph_mds_client *mdsc = fsc->mdsc;
         struct ceph_mds_request *req;
         int want_auth = USE_ANY_MDS;
         int op = (flags & O_CREAT) ? CEPH_MDS_OP_CREATE : CEPH_MDS_OP_OPEN;
@@ -117,8 +118,8 @@ static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
 int ceph_open(struct inode *inode, struct file *file)
 {
         struct ceph_inode_info *ci = ceph_inode(inode);
-        struct ceph_client *client = ceph_sb_to_client(inode->i_sb);
-        struct ceph_mds_client *mdsc = &client->mdsc;
+        struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
+        struct ceph_mds_client *mdsc = fsc->mdsc;
         struct ceph_mds_request *req;
         struct ceph_file_info *cf = file->private_data;
         struct inode *parent_inode = file->f_dentry->d_parent->d_inode;
@@ -216,8 +217,8 @@ struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry,
                                 struct nameidata *nd, int mode,
                                 int locked_dir)
 {
-        struct ceph_client *client = ceph_sb_to_client(dir->i_sb);
-        struct ceph_mds_client *mdsc = &client->mdsc;
+        struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
+        struct ceph_mds_client *mdsc = fsc->mdsc;
         struct file *file = nd->intent.open.file;
         struct inode *parent_inode = get_dentry_parent_inode(file->f_dentry);
         struct ceph_mds_request *req;
@@ -270,163 +271,6 @@ int ceph_release(struct inode *inode, struct file *file)
 }
 
 /*
- * build a vector of user pages
- */
-static struct page **get_direct_page_vector(const char __user *data,
-                                            int num_pages,
-                                            loff_t off, size_t len)
-{
-        struct page **pages;
-        int rc;
-
-        pages = kmalloc(sizeof(*pages) * num_pages, GFP_NOFS);
-        if (!pages)
-                return ERR_PTR(-ENOMEM);
-
-        down_read(&current->mm->mmap_sem);
-        rc = get_user_pages(current, current->mm, (unsigned long)data,
-                            num_pages, 0, 0, pages, NULL);
-        up_read(&current->mm->mmap_sem);
-        if (rc < 0)
-                goto fail;
-        return pages;
-
-fail:
-        kfree(pages);
-        return ERR_PTR(rc);
-}
-
-static void put_page_vector(struct page **pages, int num_pages)
-{
-        int i;
-
-        for (i = 0; i < num_pages; i++)
-                put_page(pages[i]);
-        kfree(pages);
-}
-
-void ceph_release_page_vector(struct page **pages, int num_pages)
-{
-        int i;
-
-        for (i = 0; i < num_pages; i++)
-                __free_pages(pages[i], 0);
-        kfree(pages);
-}
-
-/*
- * allocate a vector new pages
- */
-static struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags)
-{
-        struct page **pages;
-        int i;
-
-        pages = kmalloc(sizeof(*pages) * num_pages, flags);
-        if (!pages)
-                return ERR_PTR(-ENOMEM);
-        for (i = 0; i < num_pages; i++) {
-                pages[i] = __page_cache_alloc(flags);
-                if (pages[i] == NULL) {
-                        ceph_release_page_vector(pages, i);
-                        return ERR_PTR(-ENOMEM);
-                }
-        }
-        return pages;
-}
-
-/*
- * copy user data into a page vector
- */
-static int copy_user_to_page_vector(struct page **pages,
-                                    const char __user *data,
-                                    loff_t off, size_t len)
-{
-        int i = 0;
-        int po = off & ~PAGE_CACHE_MASK;
-        int left = len;
-        int l, bad;
-
-        while (left > 0) {
-                l = min_t(int, PAGE_CACHE_SIZE-po, left);
-                bad = copy_from_user(page_address(pages[i]) + po, data, l);
-                if (bad == l)
-                        return -EFAULT;
-                data += l - bad;
-                left -= l - bad;
-                po += l - bad;
-                if (po == PAGE_CACHE_SIZE) {
-                        po = 0;
-                        i++;
-                }
-        }
-        return len;
-}
-
-/*
- * copy user data from a page vector into a user pointer
- */
-static int copy_page_vector_to_user(struct page **pages, char __user *data,
-                                    loff_t off, size_t len)
-{
-        int i = 0;
-        int po = off & ~PAGE_CACHE_MASK;
-        int left = len;
-        int l, bad;
-
-        while (left > 0) {
-                l = min_t(int, left, PAGE_CACHE_SIZE-po);
-                bad = copy_to_user(data, page_address(pages[i]) + po, l);
-                if (bad == l)
-                        return -EFAULT;
-                data += l - bad;
-                left -= l - bad;
-                if (po) {
-                        po += l - bad;
-                        if (po == PAGE_CACHE_SIZE)
-                                po = 0;
-                }
-                i++;
-        }
-        return len;
-}
-
-/*
- * Zero an extent within a page vector.  Offset is relative to the
- * start of the first page.
- */
-static void zero_page_vector_range(int off, int len, struct page **pages)
-{
-        int i = off >> PAGE_CACHE_SHIFT;
-
-        off &= ~PAGE_CACHE_MASK;
-
-        dout("zero_page_vector_page %u~%u\n", off, len);
-
-        /* leading partial page? */
-        if (off) {
-                int end = min((int)PAGE_CACHE_SIZE, off + len);
-                dout("zeroing %d %p head from %d\n", i, pages[i],
-                     (int)off);
-                zero_user_segment(pages[i], off, end);
-                len -= (end - off);
-                i++;
-        }
-        while (len >= PAGE_CACHE_SIZE) {
-                dout("zeroing %d %p len=%d\n", i, pages[i], len);
-                zero_user_segment(pages[i], 0, PAGE_CACHE_SIZE);
-                len -= PAGE_CACHE_SIZE;
-                i++;
-        }
-        /* trailing partial page? */
-        if (len) {
-                dout("zeroing %d %p tail to %d\n", i, pages[i], (int)len);
-                zero_user_segment(pages[i], 0, len);
-        }
-}
-
-
-/*
  * Read a range of bytes striped over one or more objects.  Iterate over
  * objects we stripe over.  (That's not atomic, but good enough for now.)
  *
@@ -438,7 +282,7 @@ static int striped_read(struct inode *inode,
                         struct page **pages, int num_pages,
                         int *checkeof)
 {
-        struct ceph_client *client = ceph_inode_to_client(inode);
+        struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
         struct ceph_inode_info *ci = ceph_inode(inode);
         u64 pos, this_len;
         int page_off = off & ~PAGE_CACHE_MASK; /* first byte's offset in page */
@@ -459,7 +303,7 @@ static int striped_read(struct inode *inode,
 
 more:
         this_len = left;
-        ret = ceph_osdc_readpages(&client->osdc, ceph_vino(inode),
+        ret = ceph_osdc_readpages(&fsc->client->osdc, ceph_vino(inode),
                                   &ci->i_layout, pos, &this_len,
                                   ci->i_truncate_seq,
                                   ci->i_truncate_size,
@@ -477,8 +321,8 @@ more:
 
                 if (read < pos - off) {
                         dout(" zero gap %llu to %llu\n", off + read, pos);
-                        zero_page_vector_range(page_off + read,
-                                               pos - off - read, pages);
+                        ceph_zero_page_vector_range(page_off + read,
+                                                    pos - off - read, pages);
                 }
                 pos += ret;
                 read = pos - off;
@@ -495,8 +339,8 @@ more:
                 /* was original extent fully inside i_size? */
                 if (pos + left <= inode->i_size) {
                         dout("zero tail\n");
-                        zero_page_vector_range(page_off + read, len - read,
-                                               pages);
+                        ceph_zero_page_vector_range(page_off + read, len - read,
+                                                    pages);
                         read = len;
                         goto out;
                 }
@@ -531,7 +375,7 @@ static ssize_t ceph_sync_read(struct file *file, char __user *data,
              (file->f_flags & O_DIRECT) ? "O_DIRECT" : "");
 
         if (file->f_flags & O_DIRECT) {
-                pages = get_direct_page_vector(data, num_pages, off, len);
+                pages = ceph_get_direct_page_vector(data, num_pages, off, len);
 
                 /*
                  * flush any page cache pages in this range.  this
@@ -552,13 +396,13 @@ static ssize_t ceph_sync_read(struct file *file, char __user *data,
         ret = striped_read(inode, off, len, pages, num_pages, checkeof);
 
         if (ret >= 0 && (file->f_flags & O_DIRECT) == 0)
-                ret = copy_page_vector_to_user(pages, data, off, ret);
+                ret = ceph_copy_page_vector_to_user(pages, data, off, ret);
         if (ret >= 0)
                 *poff = off + ret;
 
 done:
         if (file->f_flags & O_DIRECT)
-                put_page_vector(pages, num_pages);
+                ceph_put_page_vector(pages, num_pages);
         else
                 ceph_release_page_vector(pages, num_pages);
         dout("sync_read result %d\n", ret);
@@ -594,7 +438,7 @@ static ssize_t ceph_sync_write(struct file *file, const char __user *data,
 {
         struct inode *inode = file->f_dentry->d_inode;
         struct ceph_inode_info *ci = ceph_inode(inode);
-        struct ceph_client *client = ceph_inode_to_client(inode);
+        struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
         struct ceph_osd_request *req;
         struct page **pages;
         int num_pages;
@@ -642,7 +486,7 @@ static ssize_t ceph_sync_write(struct file *file, const char __user *data,
          */
 more:
         len = left;
-        req = ceph_osdc_new_request(&client->osdc, &ci->i_layout,
+        req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
                                     ceph_vino(inode), pos, &len,
                                     CEPH_OSD_OP_WRITE, flags,
                                     ci->i_snap_realm->cached_context,
@@ -655,7 +499,7 @@ more:
         num_pages = calc_pages_for(pos, len);
 
         if (file->f_flags & O_DIRECT) {
-                pages = get_direct_page_vector(data, num_pages, pos, len);
+                pages = ceph_get_direct_page_vector(data, num_pages, pos, len);
                 if (IS_ERR(pages)) {
                         ret = PTR_ERR(pages);
                         goto out;
@@ -673,7 +517,7 @@ more:
                         ret = PTR_ERR(pages);
                         goto out;
                 }
-                ret = copy_user_to_page_vector(pages, data, pos, len);
+                ret = ceph_copy_user_to_page_vector(pages, data, pos, len);
                 if (ret < 0) {
                         ceph_release_page_vector(pages, num_pages);
                         goto out;
@@ -689,7 +533,7 @@ more:
         req->r_num_pages = num_pages;
         req->r_inode = inode;
 
-        ret = ceph_osdc_start_request(&client->osdc, req, false);
+        ret = ceph_osdc_start_request(&fsc->client->osdc, req, false);
         if (!ret) {
                 if (req->r_safe_callback) {
                         /*
@@ -701,11 +545,11 @@ more:
                         spin_unlock(&ci->i_unsafe_lock);
                         ceph_get_cap_refs(ci, CEPH_CAP_FILE_WR);
                 }
-                ret = ceph_osdc_wait_request(&client->osdc, req);
+                ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
         }
 
         if (file->f_flags & O_DIRECT)
-                put_page_vector(pages, num_pages);
+                ceph_put_page_vector(pages, num_pages);
         else if (file->f_flags & O_SYNC)
                 ceph_release_page_vector(pages, num_pages);
 
@@ -814,7 +658,8 @@ static ssize_t ceph_aio_write(struct kiocb *iocb, const struct iovec *iov,
         struct ceph_file_info *fi = file->private_data;
         struct inode *inode = file->f_dentry->d_inode;
         struct ceph_inode_info *ci = ceph_inode(inode);
-        struct ceph_osd_client *osdc = &ceph_sb_to_client(inode->i_sb)->osdc;
+        struct ceph_osd_client *osdc =
+                &ceph_sb_to_client(inode->i_sb)->client->osdc;
         loff_t endoff = pos + iov->iov_len;
         int want, got = 0;
         int ret, err;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 62377ec37edf..1d6a45b5a04c 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1,4 +1,4 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/module.h>
 #include <linux/fs.h>
@@ -13,7 +13,8 @@
 #include <linux/pagevec.h>
 
 #include "super.h"
-#include "decode.h"
+#include "mds_client.h"
+#include <linux/ceph/decode.h>
 
 /*
  * Ceph inode operations
@@ -384,7 +385,7 @@ void ceph_destroy_inode(struct inode *inode)
          */
         if (ci->i_snap_realm) {
                 struct ceph_mds_client *mdsc =
-                        &ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc;
+                        ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc;
                 struct ceph_snap_realm *realm = ci->i_snap_realm;
 
                 dout(" dropping residual ref to snap realm %p\n", realm);
@@ -685,7 +686,7 @@ static int fill_inode(struct inode *inode,
                 }
 
                 /* it may be better to set st_size in getattr instead? */
-                if (ceph_test_opt(ceph_sb_to_client(inode->i_sb), RBYTES))
+                if (ceph_test_mount_opt(ceph_sb_to_client(inode->i_sb), RBYTES))
                         inode->i_size = ci->i_rbytes;
                 break;
         default:
@@ -901,7 +902,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
         struct inode *in = NULL;
         struct ceph_mds_reply_inode *ininfo;
         struct ceph_vino vino;
-        struct ceph_client *client = ceph_sb_to_client(sb);
+        struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
         int i = 0;
         int err = 0;
 
@@ -965,7 +966,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
          */
         if (rinfo->head->is_dentry && !req->r_aborted &&
             (rinfo->head->is_target || strncmp(req->r_dentry->d_name.name,
-                                               client->mount_args->snapdir_name,
+                                               fsc->mount_options->snapdir_name,
                                                req->r_dentry->d_name.len))) {
                 /*
                  * lookup link rename   : null -> possibly existing inode
@@ -1533,7 +1534,7 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr)
         struct inode *parent_inode = dentry->d_parent->d_inode;
         const unsigned int ia_valid = attr->ia_valid;
         struct ceph_mds_request *req;
-        struct ceph_mds_client *mdsc = &ceph_sb_to_client(dentry->d_sb)->mdsc;
+        struct ceph_mds_client *mdsc = ceph_sb_to_client(dentry->d_sb)->mdsc;
         int issued;
         int release = 0, dirtied = 0;
         int mask = 0;
@@ -1728,8 +1729,8 @@ out:
  */
 int ceph_do_getattr(struct inode *inode, int mask)
 {
-        struct ceph_client *client = ceph_sb_to_client(inode->i_sb);
-        struct ceph_mds_client *mdsc = &client->mdsc;
+        struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
+        struct ceph_mds_client *mdsc = fsc->mdsc;
         struct ceph_mds_request *req;
         int err;
 
diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c
index 76e307d2aba1..8888c9ba68db 100644
--- a/fs/ceph/ioctl.c
+++ b/fs/ceph/ioctl.c
@@ -1,8 +1,10 @@
 #include <linux/in.h>
 
-#include "ioctl.h"
 #include "super.h"
-#include "ceph_debug.h"
+#include "mds_client.h"
+#include <linux/ceph/ceph_debug.h>
+
+#include "ioctl.h"
 
 
 /*
@@ -37,7 +39,7 @@ static long ceph_ioctl_set_layout(struct file *file, void __user *arg)
 {
         struct inode *inode = file->f_dentry->d_inode;
         struct inode *parent_inode = file->f_dentry->d_parent->d_inode;
-        struct ceph_mds_client *mdsc = &ceph_sb_to_client(inode->i_sb)->mdsc;
+        struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
         struct ceph_mds_request *req;
         struct ceph_ioctl_layout l;
         int err, i;
@@ -90,6 +92,68 @@ static long ceph_ioctl_set_layout(struct file *file, void __user *arg)
 }
 
 /*
+ * Set a layout policy on a directory inode. All items in the tree
+ * rooted at this inode will inherit this layout on creation,
+ * (It doesn't apply retroactively )
+ * unless a subdirectory has its own layout policy.
+ */
+static long ceph_ioctl_set_layout_policy (struct file *file, void __user *arg)
+{
+        struct inode *inode = file->f_dentry->d_inode;
+        struct ceph_mds_request *req;
+        struct ceph_ioctl_layout l;
+        int err, i;
+        struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
+
+        /* copy and validate */
+        if (copy_from_user(&l, arg, sizeof(l)))
+                return -EFAULT;
+
+        if ((l.object_size & ~PAGE_MASK) ||
+            (l.stripe_unit & ~PAGE_MASK) ||
+            !l.stripe_unit ||
+            (l.object_size &&
+                (unsigned)l.object_size % (unsigned)l.stripe_unit))
+                return -EINVAL;
+
+        /* make sure it's a valid data pool */
+        if (l.data_pool > 0) {
+                mutex_lock(&mdsc->mutex);
+                err = -EINVAL;
+                for (i = 0; i < mdsc->mdsmap->m_num_data_pg_pools; i++)
+                        if (mdsc->mdsmap->m_data_pg_pools[i] == l.data_pool) {
+                                err = 0;
+                                break;
+                        }
+                mutex_unlock(&mdsc->mutex);
+                if (err)
+                        return err;
+        }
+
+        req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETDIRLAYOUT,
+                                       USE_AUTH_MDS);
+
+        if (IS_ERR(req))
+                return PTR_ERR(req);
+        req->r_inode = igrab(inode);
+
+        req->r_args.setlayout.layout.fl_stripe_unit =
+                        cpu_to_le32(l.stripe_unit);
+        req->r_args.setlayout.layout.fl_stripe_count =
+                        cpu_to_le32(l.stripe_count);
+        req->r_args.setlayout.layout.fl_object_size =
+                        cpu_to_le32(l.object_size);
+        req->r_args.setlayout.layout.fl_pg_pool =
+                        cpu_to_le32(l.data_pool);
+        req->r_args.setlayout.layout.fl_pg_preferred =
+                        cpu_to_le32(l.preferred_osd);
+
+        err = ceph_mdsc_do_request(mdsc, inode, req);
+        ceph_mdsc_put_request(req);
+        return err;
+}
+
+/*
  * Return object name, size/offset information, and location (OSD
  * number, network address) for a given file offset.
  */
@@ -98,7 +162,8 @@ static long ceph_ioctl_get_dataloc(struct file *file, void __user *arg)
         struct ceph_ioctl_dataloc dl;
         struct inode *inode = file->f_dentry->d_inode;
         struct ceph_inode_info *ci = ceph_inode(inode);
-        struct ceph_osd_client *osdc = &ceph_sb_to_client(inode->i_sb)->osdc;
+        struct ceph_osd_client *osdc =
+                &ceph_sb_to_client(inode->i_sb)->client->osdc;
         u64 len = 1, olen;
         u64 tmp;
         struct ceph_object_layout ol;
@@ -174,11 +239,15 @@ long ceph_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
         case CEPH_IOC_SET_LAYOUT:
                 return ceph_ioctl_set_layout(file, (void __user *)arg);
 
+        case CEPH_IOC_SET_LAYOUT_POLICY:
+                return ceph_ioctl_set_layout_policy(file, (void __user *)arg);
+
         case CEPH_IOC_GET_DATALOC:
                 return ceph_ioctl_get_dataloc(file, (void __user *)arg);
 
         case CEPH_IOC_LAZYIO:
                 return ceph_ioctl_lazyio(file);
         }
+
         return -ENOTTY;
 }
diff --git a/fs/ceph/ioctl.h b/fs/ceph/ioctl.h
index 88451a3b6857..a6ce54e94eb5 100644
--- a/fs/ceph/ioctl.h
+++ b/fs/ceph/ioctl.h
@@ -4,7 +4,7 @@
 #include <linux/ioctl.h>
 #include <linux/types.h>
 
-#define CEPH_IOCTL_MAGIC 0x97
+#define CEPH_IOCTL_MAGIC 0x98
 
 /* just use u64 to align sanely on all archs */
 struct ceph_ioctl_layout {
@@ -17,6 +17,8 @@ struct ceph_ioctl_layout {
                                    struct ceph_ioctl_layout)
 #define CEPH_IOC_SET_LAYOUT _IOW(CEPH_IOCTL_MAGIC, 2,           \
                                    struct ceph_ioctl_layout)
+#define CEPH_IOC_SET_LAYOUT_POLICY _IOW(CEPH_IOCTL_MAGIC, 5,    \
+                                   struct ceph_ioctl_layout)
 
 /*
  * Extract identity, address of the OSD and object storing a given
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index ff4e753aae92..40abde93c345 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -1,11 +1,11 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/file.h>
 #include <linux/namei.h>
 
 #include "super.h"
 #include "mds_client.h"
-#include "pagelist.h"
+#include <linux/ceph/pagelist.h>
 
 /**
  * Implement fcntl and flock locking functions.
@@ -16,7 +16,7 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file,
 {
         struct inode *inode = file->f_dentry->d_inode;
         struct ceph_mds_client *mdsc =
-                &ceph_sb_to_client(inode->i_sb)->mdsc;
+                ceph_sb_to_client(inode->i_sb)->mdsc;
         struct ceph_mds_request *req;
         int err;
 
@@ -181,8 +181,9 @@ void ceph_count_locks(struct inode *inode, int *fcntl_count, int *flock_count)
  * Encode the flock and fcntl locks for the given inode into the pagelist.
  * Format is: #fcntl locks, sequential fcntl locks, #flock locks,
  * sequential flock locks.
- * Must be called with BLK already held, and the lock numbers should have
- * been gathered under the same lock holding window.
+ * Must be called with lock_flocks() already held.
+ * If we encounter more of a specific lock type than expected,
+ * we return the value 1.
  */
 int ceph_encode_locks(struct inode *inode, struct ceph_pagelist *pagelist,
                       int num_fcntl_locks, int num_flock_locks)
@@ -190,6 +191,8 @@ int ceph_encode_locks(struct inode *inode, struct ceph_pagelist *pagelist,
         struct file_lock *lock;
         struct ceph_filelock cephlock;
         int err = 0;
+        int seen_fcntl = 0;
+        int seen_flock = 0;
 
         dout("encoding %d flock and %d fcntl locks", num_flock_locks,
              num_fcntl_locks);
@@ -198,6 +201,11 @@ int ceph_encode_locks(struct inode *inode, struct ceph_pagelist *pagelist,
                 goto fail;
         for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) {
                 if (lock->fl_flags & FL_POSIX) {
+                        ++seen_fcntl;
+                        if (seen_fcntl > num_fcntl_locks) {
+                                err = -ENOSPC;
+                                goto fail;
+                        }
                         err = lock_to_ceph_filelock(lock, &cephlock);
                         if (err)
                                 goto fail;
@@ -213,6 +221,11 @@ int ceph_encode_locks(struct inode *inode, struct ceph_pagelist *pagelist,
                 goto fail;
         for (lock = inode->i_flock; lock != NULL; lock = lock->fl_next) {
                 if (lock->fl_flags & FL_FLOCK) {
+                        ++seen_flock;
+                        if (seen_flock > num_flock_locks) {
+                                err = -ENOSPC;
+                                goto fail;
+                        }
                         err = lock_to_ceph_filelock(lock, &cephlock);
                         if (err)
                                 goto fail;
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index fad95f8f2608..3142b15940c2 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1,17 +1,21 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
+#include <linux/fs.h>
 #include <linux/wait.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
 #include <linux/smp_lock.h>
 
-#include "mds_client.h"
-#include "mon_client.h"
 #include "super.h"
-#include "messenger.h"
-#include "decode.h"
-#include "auth.h"
-#include "pagelist.h"
+#include "mds_client.h"
+
+#include <linux/ceph/messenger.h>
+#include <linux/ceph/decode.h>
+#include <linux/ceph/pagelist.h>
+#include <linux/ceph/auth.h>
+#include <linux/ceph/debugfs.h>
 
 /*
  * A cluster of MDS (metadata server) daemons is responsible for
@@ -286,8 +290,9 @@ void ceph_put_mds_session(struct ceph_mds_session *s)
              atomic_read(&s->s_ref), atomic_read(&s->s_ref)-1);
         if (atomic_dec_and_test(&s->s_ref)) {
                 if (s->s_authorizer)
-                        s->s_mdsc->client->monc.auth->ops->destroy_authorizer(
-                                s->s_mdsc->client->monc.auth, s->s_authorizer);
+                     s->s_mdsc->fsc->client->monc.auth->ops->destroy_authorizer(
+                             s->s_mdsc->fsc->client->monc.auth,
+                             s->s_authorizer);
                 kfree(s);
         }
 }
@@ -344,7 +349,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
         s->s_seq = 0;
         mutex_init(&s->s_mutex);
 
-        ceph_con_init(mdsc->client->msgr, &s->s_con);
+        ceph_con_init(mdsc->fsc->client->msgr, &s->s_con);
         s->s_con.private = s;
         s->s_con.ops = &mds_con_ops;
         s->s_con.peer_name.type = CEPH_ENTITY_TYPE_MDS;
@@ -599,7 +604,7 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
         } else if (req->r_dentry) {
                 struct inode *dir = req->r_dentry->d_parent->d_inode;
 
-                if (dir->i_sb != mdsc->client->sb) {
+                if (dir->i_sb != mdsc->fsc->sb) {
                         /* not this fs! */
                         inode = req->r_dentry->d_inode;
                 } else if (ceph_snap(dir) != CEPH_NOSNAP) {
@@ -884,7 +889,7 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
         __ceph_remove_cap(cap);
         if (!__ceph_is_any_real_caps(ci)) {
                 struct ceph_mds_client *mdsc =
-                        &ceph_sb_to_client(inode->i_sb)->mdsc;
+                        ceph_sb_to_client(inode->i_sb)->mdsc;
 
                 spin_lock(&mdsc->cap_dirty_lock);
                 if (!list_empty(&ci->i_dirty_item)) {
@@ -1146,7 +1151,7 @@ int ceph_add_cap_releases(struct ceph_mds_client *mdsc,
         struct ceph_msg *msg, *partial = NULL;
         struct ceph_mds_cap_release *head;
         int err = -ENOMEM;
-        int extra = mdsc->client->mount_args->cap_release_safety;
+        int extra = mdsc->fsc->mount_options->cap_release_safety;
         int num;
 
         dout("add_cap_releases %p mds%d extra %d\n", session, session->s_mds,
@@ -2085,7 +2090,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 
         /* insert trace into our cache */
         mutex_lock(&req->r_fill_mutex);
-        err = ceph_fill_trace(mdsc->client->sb, req, req->r_session);
+        err = ceph_fill_trace(mdsc->fsc->sb, req, req->r_session);
         if (err == 0) {
                 if (result == 0 && rinfo->dir_nr)
                         ceph_readdir_prepopulate(req, req->r_session);
@@ -2361,19 +2366,35 @@ static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap,
 
         if (recon_state->flock) {
                 int num_fcntl_locks, num_flock_locks;
-
-                lock_kernel();
-                ceph_count_locks(inode, &num_fcntl_locks, &num_flock_locks);
-                rec.v2.flock_len = (2*sizeof(u32) +
-                                    (num_fcntl_locks+num_flock_locks) *
-                                    sizeof(struct ceph_filelock));
-
-                err = ceph_pagelist_append(pagelist, &rec, reclen);
-                if (!err)
-                        err = ceph_encode_locks(inode, pagelist,
-                                                num_fcntl_locks,
-                                                num_flock_locks);
-                unlock_kernel();
+                struct ceph_pagelist_cursor trunc_point;
+
+                ceph_pagelist_set_cursor(pagelist, &trunc_point);
+                do {
+                        lock_flocks();
+                        ceph_count_locks(inode, &num_fcntl_locks,
+                                         &num_flock_locks);
+                        rec.v2.flock_len = (2*sizeof(u32) +
+                                            (num_fcntl_locks+num_flock_locks) *
+                                            sizeof(struct ceph_filelock));
+                        unlock_flocks();
+
+                        /* pre-alloc pagelist */
+                        ceph_pagelist_truncate(pagelist, &trunc_point);
+                        err = ceph_pagelist_append(pagelist, &rec, reclen);
+                        if (!err)
+                                err = ceph_pagelist_reserve(pagelist,
+                                                            rec.v2.flock_len);
+
+                        /* encode locks */
+                        if (!err) {
+                                lock_flocks();
+                                err = ceph_encode_locks(inode,
+                                                        pagelist,
+                                                        num_fcntl_locks,
+                                                        num_flock_locks);
+                                unlock_flocks();
+                        }
+                } while (err == -ENOSPC);
         } else {
                 err = ceph_pagelist_append(pagelist, &rec, reclen);
         }
@@ -2613,7 +2634,7 @@ static void handle_lease(struct ceph_mds_client *mdsc,
                          struct ceph_mds_session *session,
                          struct ceph_msg *msg)
 {
-        struct super_block *sb = mdsc->client->sb;
+        struct super_block *sb = mdsc->fsc->sb;
         struct inode *inode;
         struct ceph_inode_info *ci;
         struct dentry *parent, *dentry;
@@ -2891,10 +2912,16 @@ static void delayed_work(struct work_struct *work)
         schedule_delayed(mdsc);
 }
 
+int ceph_mdsc_init(struct ceph_fs_client *fsc)
 
-int ceph_mdsc_init(struct ceph_mds_client *mdsc, struct ceph_client *client)
 {
-        mdsc->client = client;
+        struct ceph_mds_client *mdsc;
+
+        mdsc = kzalloc(sizeof(struct ceph_mds_client), GFP_NOFS);
+        if (!mdsc)
+                return -ENOMEM;
+        mdsc->fsc = fsc;
+        fsc->mdsc = mdsc;
         mutex_init(&mdsc->mutex);
         mdsc->mdsmap = kzalloc(sizeof(*mdsc->mdsmap), GFP_NOFS);
         if (mdsc->mdsmap == NULL)
@@ -2927,7 +2954,7 @@ int ceph_mdsc_init(struct ceph_mds_client *mdsc, struct ceph_client *client)
         INIT_LIST_HEAD(&mdsc->dentry_lru);
 
         ceph_caps_init(mdsc);
-        ceph_adjust_min_caps(mdsc, client->min_caps);
+        ceph_adjust_min_caps(mdsc, fsc->min_caps);
 
         return 0;
 }
@@ -2939,7 +2966,7 @@ int ceph_mdsc_init(struct ceph_mds_client *mdsc, struct ceph_client *client)
 static void wait_requests(struct ceph_mds_client *mdsc)
 {
         struct ceph_mds_request *req;
-        struct ceph_client *client = mdsc->client;
+        struct ceph_fs_client *fsc = mdsc->fsc;
 
         mutex_lock(&mdsc->mutex);
         if (__get_oldest_req(mdsc)) {
@@ -2947,7 +2974,7 @@ static void wait_requests(struct ceph_mds_client *mdsc)
 
                 dout("wait_requests waiting for requests\n");
                 wait_for_completion_timeout(&mdsc->safe_umount_waiters,
-                                    client->mount_args->mount_timeout * HZ);
+                                    fsc->client->options->mount_timeout * HZ);
 
                 /* tear down remaining requests */
                 mutex_lock(&mdsc->mutex);
@@ -3030,7 +3057,7 @@ void ceph_mdsc_sync(struct ceph_mds_client *mdsc)
 {
         u64 want_tid, want_flush;
 
-        if (mdsc->client->mount_state == CEPH_MOUNT_SHUTDOWN)
+        if (mdsc->fsc->mount_state == CEPH_MOUNT_SHUTDOWN)
                 return;
 
         dout("sync\n");
@@ -3053,7 +3080,7 @@ bool done_closing_sessions(struct ceph_mds_client *mdsc)
 {
         int i, n = 0;
 
-        if (mdsc->client->mount_state == CEPH_MOUNT_SHUTDOWN)
+        if (mdsc->fsc->mount_state == CEPH_MOUNT_SHUTDOWN)
                 return true;
 
         mutex_lock(&mdsc->mutex);
@@ -3071,8 +3098,8 @@ void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc)
 {
         struct ceph_mds_session *session;
         int i;
-        struct ceph_client *client = mdsc->client;
-        unsigned long timeout = client->mount_args->mount_timeout * HZ;
+        struct ceph_fs_client *fsc = mdsc->fsc;
+        unsigned long timeout = fsc->client->options->mount_timeout * HZ;
 
         dout("close_sessions\n");
 
@@ -3119,7 +3146,7 @@ void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc)
         dout("stopped\n");
 }
 
-void ceph_mdsc_stop(struct ceph_mds_client *mdsc)
+static void ceph_mdsc_stop(struct ceph_mds_client *mdsc)
 {
         dout("stop\n");
         cancel_delayed_work_sync(&mdsc->delayed_work); /* cancel timer */
@@ -3129,6 +3156,15 @@ void ceph_mdsc_stop(struct ceph_mds_client *mdsc)
         ceph_caps_finalize(mdsc);
 }
 
+void ceph_mdsc_destroy(struct ceph_fs_client *fsc)
+{
+        struct ceph_mds_client *mdsc = fsc->mdsc;
+
+        ceph_mdsc_stop(mdsc);
+        fsc->mdsc = NULL;
+        kfree(mdsc);
+}
+
 
 /*
  * handle mds map update.
@@ -3145,14 +3181,14 @@ void ceph_mdsc_handle_map(struct ceph_mds_client *mdsc, struct ceph_msg *msg)
 
         ceph_decode_need(&p, end, sizeof(fsid)+2*sizeof(u32), bad);
         ceph_decode_copy(&p, &fsid, sizeof(fsid));
-        if (ceph_check_fsid(mdsc->client, &fsid) < 0)
+        if (ceph_check_fsid(mdsc->fsc->client, &fsid) < 0)
                 return;
         epoch = ceph_decode_32(&p);
         maplen = ceph_decode_32(&p);
         dout("handle_map epoch %u len %d\n", epoch, (int)maplen);
 
         /* do we need it? */
-        ceph_monc_got_mdsmap(&mdsc->client->monc, epoch);
+        ceph_monc_got_mdsmap(&mdsc->fsc->client->monc, epoch);
         mutex_lock(&mdsc->mutex);
         if (mdsc->mdsmap && epoch <= mdsc->mdsmap->m_epoch) {
                 dout("handle_map epoch %u <= our %u\n",
@@ -3176,7 +3212,7 @@ void ceph_mdsc_handle_map(struct ceph_mds_client *mdsc, struct ceph_msg *msg)
         } else {
                 mdsc->mdsmap = newmap;  /* first mds map */
         }
-        mdsc->client->sb->s_maxbytes = mdsc->mdsmap->m_max_file_size;
+        mdsc->fsc->sb->s_maxbytes = mdsc->mdsmap->m_max_file_size;
 
         __wake_requests(mdsc, &mdsc->waiting_for_map);
 
@@ -3277,7 +3313,7 @@ static int get_authorizer(struct ceph_connection *con,
 {
         struct ceph_mds_session *s = con->private;
         struct ceph_mds_client *mdsc = s->s_mdsc;
-        struct ceph_auth_client *ac = mdsc->client->monc.auth;
+        struct ceph_auth_client *ac = mdsc->fsc->client->monc.auth;
         int ret = 0;
 
         if (force_new && s->s_authorizer) {
@@ -3311,7 +3347,7 @@ static int verify_authorizer_reply(struct ceph_connection *con, int len)
 {
         struct ceph_mds_session *s = con->private;
         struct ceph_mds_client *mdsc = s->s_mdsc;
-        struct ceph_auth_client *ac = mdsc->client->monc.auth;
+        struct ceph_auth_client *ac = mdsc->fsc->client->monc.auth;
 
         return ac->ops->verify_authorizer_reply(ac, s->s_authorizer, len);
 }
@@ -3320,12 +3356,12 @@ static int invalidate_authorizer(struct ceph_connection *con)
 {
         struct ceph_mds_session *s = con->private;
         struct ceph_mds_client *mdsc = s->s_mdsc;
-        struct ceph_auth_client *ac = mdsc->client->monc.auth;
+        struct ceph_auth_client *ac = mdsc->fsc->client->monc.auth;
 
         if (ac->ops->invalidate_authorizer)
                 ac->ops->invalidate_authorizer(ac, CEPH_ENTITY_TYPE_MDS);
 
-        return ceph_monc_validate_auth(&mdsc->client->monc);
+        return ceph_monc_validate_auth(&mdsc->fsc->client->monc);
 }
 
 static const struct ceph_connection_operations mds_con_ops = {
@@ -3338,7 +3374,4 @@ static const struct ceph_connection_operations mds_con_ops = {
         .peer_reset = peer_reset,
 };
 
-
-
-
 /* eof */
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index c98267ce6d2a..d66d63c72355 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -8,9 +8,9 @@
 #include <linux/rbtree.h>
 #include <linux/spinlock.h>
 
-#include "types.h"
-#include "messenger.h"
-#include "mdsmap.h"
+#include <linux/ceph/types.h>
+#include <linux/ceph/messenger.h>
+#include <linux/ceph/mdsmap.h>
 
 /*
  * Some lock dependencies:
@@ -26,7 +26,7 @@
  *
  */
 
-struct ceph_client;
+struct ceph_fs_client;
 struct ceph_cap;
 
 /*
@@ -230,7 +230,7 @@ struct ceph_mds_request {
  * mds client state
  */
 struct ceph_mds_client {
-        struct ceph_client      *client;
+        struct ceph_fs_client  *fsc;
         struct mutex            mutex;         /* all nested structures */
 
         struct ceph_mdsmap      *mdsmap;
@@ -289,11 +289,6 @@ struct ceph_mds_client {
         int             caps_avail_count;    /* unused, unreserved */
         int             caps_min_count;      /* keep at least this many
                                                 (unreserved) */
-
-#ifdef CONFIG_DEBUG_FS
-        struct dentry     *debugfs_file;
-#endif
-
         spinlock_t        dentry_lru_lock;
         struct list_head  dentry_lru;
         int               num_dentry;
@@ -316,10 +311,9 @@ extern void ceph_put_mds_session(struct ceph_mds_session *s);
 extern int ceph_send_msg_mds(struct ceph_mds_client *mdsc,
                              struct ceph_msg *msg, int mds);
 
-extern int ceph_mdsc_init(struct ceph_mds_client *mdsc,
-                           struct ceph_client *client);
+extern int ceph_mdsc_init(struct ceph_fs_client *fsc);
 extern void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc);
-extern void ceph_mdsc_stop(struct ceph_mds_client *mdsc);
+extern void ceph_mdsc_destroy(struct ceph_fs_client *fsc);
 
 extern void ceph_mdsc_sync(struct ceph_mds_client *mdsc);
 
diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c
index 040be6d1150b..73b7d44e8a35 100644
--- a/fs/ceph/mdsmap.c
+++ b/fs/ceph/mdsmap.c
@@ -1,4 +1,4 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/bug.h>
 #include <linux/err.h>
@@ -6,9 +6,9 @@
 #include <linux/slab.h>
 #include <linux/types.h>
 
-#include "mdsmap.h"
-#include "messenger.h"
-#include "decode.h"
+#include <linux/ceph/mdsmap.h>
+#include <linux/ceph/messenger.h>
+#include <linux/ceph/decode.h>
 
 #include "super.h"
 
@@ -117,7 +117,8 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
                 }
 
                 dout("mdsmap_decode %d/%d %lld mds%d.%d %s %s\n",
-                     i+1, n, global_id, mds, inc, pr_addr(&addr.in_addr),
+                     i+1, n, global_id, mds, inc,
+                     ceph_pr_addr(&addr.in_addr),
                      ceph_mds_state_name(state));
                 if (mds >= 0 && mds < m->m_max_mds && state > 0) {
                         m->m_info[mds].global_id = global_id;
diff --git a/fs/ceph/pagelist.c b/fs/ceph/pagelist.c
deleted file mode 100644
index 46a368b6dce5..000000000000
--- a/fs/ceph/pagelist.c
+++ /dev/null
@@ -1,63 +0,0 @@
-
-#include <linux/gfp.h>
-#include <linux/pagemap.h>
-#include <linux/highmem.h>
-
-#include "pagelist.h"
-
-static void ceph_pagelist_unmap_tail(struct ceph_pagelist *pl)
-{
-        struct page *page = list_entry(pl->head.prev, struct page,
-                                       lru);
-        kunmap(page);
-}
-
-int ceph_pagelist_release(struct ceph_pagelist *pl)
-{
-        if (pl->mapped_tail)
-                ceph_pagelist_unmap_tail(pl);
-
-        while (!list_empty(&pl->head)) {
-                struct page *page = list_first_entry(&pl->head, struct page,
-                                                     lru);
-                list_del(&page->lru);
-                __free_page(page);
-        }
-        return 0;
-}
-
-static int ceph_pagelist_addpage(struct ceph_pagelist *pl)
-{
-        struct page *page = __page_cache_alloc(GFP_NOFS);
-        if (!page)
-                return -ENOMEM;
-        pl->room += PAGE_SIZE;
-        list_add_tail(&page->lru, &pl->head);
-        if (pl->mapped_tail)
-                ceph_pagelist_unmap_tail(pl);
-        pl->mapped_tail = kmap(page);
-        return 0;
-}
-
-int ceph_pagelist_append(struct ceph_pagelist *pl, void *buf, size_t len)
-{
-        while (pl->room < len) {
-                size_t bit = pl->room;
-                int ret;
-
-                memcpy(pl->mapped_tail + (pl->length & ~PAGE_CACHE_MASK),
-                       buf, bit);
-                pl->length += bit;
-                pl->room -= bit;
-                buf += bit;
-                len -= bit;
-                ret = ceph_pagelist_addpage(pl);
-                if (ret)
-                        return ret;
-        }
-
-        memcpy(pl->mapped_tail + (pl->length & ~PAGE_CACHE_MASK), buf, len);
-        pl->length += len;
-        pl->room -= len;
-        return 0;
-}
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 190b6c4a6f2b..39c243acd062 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -1,10 +1,12 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/sort.h>
 #include <linux/slab.h>
 
 #include "super.h"
-#include "decode.h"
+#include "mds_client.h"
+
+#include <linux/ceph/decode.h>
 
 /*
  * Snapshots in ceph are driven in large part by cooperation from the
@@ -526,7 +528,7 @@ int __ceph_finish_cap_snap(struct ceph_inode_info *ci,
                             struct ceph_cap_snap *capsnap)
 {
         struct inode *inode = &ci->vfs_inode;
-        struct ceph_mds_client *mdsc = &ceph_sb_to_client(inode->i_sb)->mdsc;
+        struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
 
         BUG_ON(capsnap->writing);
         capsnap->size = inode->i_size;
@@ -747,7 +749,7 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc,
                       struct ceph_mds_session *session,
                       struct ceph_msg *msg)
 {
-        struct super_block *sb = mdsc->client->sb;
+        struct super_block *sb = mdsc->fsc->sb;
         int mds = session->s_mds;
         u64 split;
         int op;
diff --git a/fs/ceph/ceph_strings.c b/fs/ceph/strings.c
index c6179d3a26a2..cd5097d7c804 100644
--- a/fs/ceph/ceph_strings.c
+++ b/fs/ceph/strings.c
@@ -1,71 +1,9 @@
 /*
- * Ceph string constants
+ * Ceph fs string constants
  */
-#include "types.h"
+#include <linux/module.h>
+#include <linux/ceph/types.h>
 
-const char *ceph_entity_type_name(int type)
-{
-        switch (type) {
-        case CEPH_ENTITY_TYPE_MDS: return "mds";
-        case CEPH_ENTITY_TYPE_OSD: return "osd";
-        case CEPH_ENTITY_TYPE_MON: return "mon";
-        case CEPH_ENTITY_TYPE_CLIENT: return "client";
-        case CEPH_ENTITY_TYPE_AUTH: return "auth";
-        default: return "unknown";
-        }
-}
-
-const char *ceph_osd_op_name(int op)
-{
-        switch (op) {
-        case CEPH_OSD_OP_READ: return "read";
-        case CEPH_OSD_OP_STAT: return "stat";
-
-        case CEPH_OSD_OP_MASKTRUNC: return "masktrunc";
-
-        case CEPH_OSD_OP_WRITE: return "write";
-        case CEPH_OSD_OP_DELETE: return "delete";
-        case CEPH_OSD_OP_TRUNCATE: return "truncate";
-        case CEPH_OSD_OP_ZERO: return "zero";
-        case CEPH_OSD_OP_WRITEFULL: return "writefull";
-        case CEPH_OSD_OP_ROLLBACK: return "rollback";
-
-        case CEPH_OSD_OP_APPEND: return "append";
-        case CEPH_OSD_OP_STARTSYNC: return "startsync";
-        case CEPH_OSD_OP_SETTRUNC: return "settrunc";
-        case CEPH_OSD_OP_TRIMTRUNC: return "trimtrunc";
-
-        case CEPH_OSD_OP_TMAPUP: return "tmapup";
-        case CEPH_OSD_OP_TMAPGET: return "tmapget";
-        case CEPH_OSD_OP_TMAPPUT: return "tmapput";
-
-        case CEPH_OSD_OP_GETXATTR: return "getxattr";
-        case CEPH_OSD_OP_GETXATTRS: return "getxattrs";
-        case CEPH_OSD_OP_SETXATTR: return "setxattr";
-        case CEPH_OSD_OP_SETXATTRS: return "setxattrs";
-        case CEPH_OSD_OP_RESETXATTRS: return "resetxattrs";
-        case CEPH_OSD_OP_RMXATTR: return "rmxattr";
-        case CEPH_OSD_OP_CMPXATTR: return "cmpxattr";
-
-        case CEPH_OSD_OP_PULL: return "pull";
-        case CEPH_OSD_OP_PUSH: return "push";
-        case CEPH_OSD_OP_BALANCEREADS: return "balance-reads";
-        case CEPH_OSD_OP_UNBALANCEREADS: return "unbalance-reads";
-        case CEPH_OSD_OP_SCRUB: return "scrub";
-
-        case CEPH_OSD_OP_WRLOCK: return "wrlock";
-        case CEPH_OSD_OP_WRUNLOCK: return "wrunlock";
-        case CEPH_OSD_OP_RDLOCK: return "rdlock";
-        case CEPH_OSD_OP_RDUNLOCK: return "rdunlock";
-        case CEPH_OSD_OP_UPLOCK: return "uplock";
-        case CEPH_OSD_OP_DNLOCK: return "dnlock";
-
-        case CEPH_OSD_OP_CALL: return "call";
-
-        case CEPH_OSD_OP_PGLS: return "pgls";
-        }
-        return "???";
-}
 
 const char *ceph_mds_state_name(int s)
 {
@@ -177,17 +115,3 @@ const char *ceph_snap_op_name(int o)
         }
         return "???";
 }
-
-const char *ceph_pool_op_name(int op)
-{
-        switch (op) {
-        case POOL_OP_CREATE: return "create";
-        case POOL_OP_DELETE: return "delete";
-        case POOL_OP_AUID_CHANGE: return "auid change";
-        case POOL_OP_CREATE_SNAP: return "create snap";
-        case POOL_OP_DELETE_SNAP: return "delete snap";
-        case POOL_OP_CREATE_UNMANAGED_SNAP: return "create unmanaged snap";
-        case POOL_OP_DELETE_UNMANAGED_SNAP: return "delete unmanaged snap";
-        }
-        return "???";
-}
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 9922628532b2..d6e0e0421891 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -1,5 +1,5 @@
 
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/backing-dev.h>
 #include <linux/ctype.h>
@@ -15,10 +15,13 @@
 #include <linux/statfs.h>
 #include <linux/string.h>
 
-#include "decode.h"
 #include "super.h"
-#include "mon_client.h"
-#include "auth.h"
+#include "mds_client.h"
+
+#include <linux/ceph/decode.h>
+#include <linux/ceph/mon_client.h>
+#include <linux/ceph/auth.h>
+#include <linux/ceph/debugfs.h>
 
 /*
  * Ceph superblock operations
@@ -26,36 +29,22 @@
  * Handle the basics of mounting, unmounting.
  */
 
-
-/*
- * find filename portion of a path (/foo/bar/baz -> baz)
- */
-const char *ceph_file_part(const char *s, int len)
-{
-        const char *e = s + len;
-
-        while (e != s && *(e-1) != '/')
-                e--;
-        return e;
-}
-
-
 /*
  * super ops
  */
 static void ceph_put_super(struct super_block *s)
 {
-        struct ceph_client *client = ceph_sb_to_client(s);
+        struct ceph_fs_client *fsc = ceph_sb_to_client(s);
 
         dout("put_super\n");
-        ceph_mdsc_close_sessions(&client->mdsc);
+        ceph_mdsc_close_sessions(fsc->mdsc);
 
         /*
          * ensure we release the bdi before put_anon_super releases
          * the device name.
          */
-        if (s->s_bdi == &client->backing_dev_info) {
-                bdi_unregister(&client->backing_dev_info);
+        if (s->s_bdi == &fsc->backing_dev_info) {
+                bdi_unregister(&fsc->backing_dev_info);
                 s->s_bdi = NULL;
         }
 
@@ -64,14 +53,14 @@ static void ceph_put_super(struct super_block *s)
 
 static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
-        struct ceph_client *client = ceph_inode_to_client(dentry->d_inode);
-        struct ceph_monmap *monmap = client->monc.monmap;
+        struct ceph_fs_client *fsc = ceph_inode_to_client(dentry->d_inode);
+        struct ceph_monmap *monmap = fsc->client->monc.monmap;
         struct ceph_statfs st;
         u64 fsid;
         int err;
 
         dout("statfs\n");
-        err = ceph_monc_do_statfs(&client->monc, &st);
+        err = ceph_monc_do_statfs(&fsc->client->monc, &st);
         if (err < 0)
                 return err;
 
@@ -104,238 +93,28 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 static int ceph_sync_fs(struct super_block *sb, int wait)
 {
-        struct ceph_client *client = ceph_sb_to_client(sb);
+        struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
 
         if (!wait) {
                 dout("sync_fs (non-blocking)\n");
-                ceph_flush_dirty_caps(&client->mdsc);
+                ceph_flush_dirty_caps(fsc->mdsc);
                 dout("sync_fs (non-blocking) done\n");
                 return 0;
         }
 
         dout("sync_fs (blocking)\n");
-        ceph_osdc_sync(&ceph_sb_to_client(sb)->osdc);
-        ceph_mdsc_sync(&ceph_sb_to_client(sb)->mdsc);
+        ceph_osdc_sync(&fsc->client->osdc);
+        ceph_mdsc_sync(fsc->mdsc);
         dout("sync_fs (blocking) done\n");
         return 0;
 }
 
-static int default_congestion_kb(void)
-{
-        int congestion_kb;
-
-        /*
-         * Copied from NFS
-         *
-         * congestion size, scale with available memory.
-         *
-         *  64MB:    8192k
-         * 128MB:   11585k
-         * 256MB:   16384k
-         * 512MB:   23170k
-         *   1GB:   32768k
-         *   2GB:   46340k
-         *   4GB:   65536k
-         *   8GB:   92681k
-         *  16GB:  131072k
-         *
-         * This allows larger machines to have larger/more transfers.
-         * Limit the default to 256M
-         */
-        congestion_kb = (16*int_sqrt(totalram_pages)) << (PAGE_SHIFT-10);
-        if (congestion_kb > 256*1024)
-                congestion_kb = 256*1024;
-
-        return congestion_kb;
-}
-
-/**
- * ceph_show_options - Show mount options in /proc/mounts
- * @m: seq_file to write to
- * @mnt: mount descriptor
- */
-static int ceph_show_options(struct seq_file *m, struct vfsmount *mnt)
-{
-        struct ceph_client *client = ceph_sb_to_client(mnt->mnt_sb);
-        struct ceph_mount_args *args = client->mount_args;
-
-        if (args->flags & CEPH_OPT_FSID)
-                seq_printf(m, ",fsid=%pU", &args->fsid);
-        if (args->flags & CEPH_OPT_NOSHARE)
-                seq_puts(m, ",noshare");
-        if (args->flags & CEPH_OPT_DIRSTAT)
-                seq_puts(m, ",dirstat");
-        if ((args->flags & CEPH_OPT_RBYTES) == 0)
-                seq_puts(m, ",norbytes");
-        if (args->flags & CEPH_OPT_NOCRC)
-                seq_puts(m, ",nocrc");
-        if (args->flags & CEPH_OPT_NOASYNCREADDIR)
-                seq_puts(m, ",noasyncreaddir");
-
-        if (args->mount_timeout != CEPH_MOUNT_TIMEOUT_DEFAULT)
-                seq_printf(m, ",mount_timeout=%d", args->mount_timeout);
-        if (args->osd_idle_ttl != CEPH_OSD_IDLE_TTL_DEFAULT)
-                seq_printf(m, ",osd_idle_ttl=%d", args->osd_idle_ttl);
-        if (args->osd_timeout != CEPH_OSD_TIMEOUT_DEFAULT)
-                seq_printf(m, ",osdtimeout=%d", args->osd_timeout);
-        if (args->osd_keepalive_timeout != CEPH_OSD_KEEPALIVE_DEFAULT)
-                seq_printf(m, ",osdkeepalivetimeout=%d",
-                         args->osd_keepalive_timeout);
-        if (args->wsize)
-                seq_printf(m, ",wsize=%d", args->wsize);
-        if (args->rsize != CEPH_MOUNT_RSIZE_DEFAULT)
-                seq_printf(m, ",rsize=%d", args->rsize);
-        if (args->congestion_kb != default_congestion_kb())
-                seq_printf(m, ",write_congestion_kb=%d", args->congestion_kb);
-        if (args->caps_wanted_delay_min != CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT)
-                seq_printf(m, ",caps_wanted_delay_min=%d",
-                         args->caps_wanted_delay_min);
-        if (args->caps_wanted_delay_max != CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT)
-                seq_printf(m, ",caps_wanted_delay_max=%d",
-                           args->caps_wanted_delay_max);
-        if (args->cap_release_safety != CEPH_CAP_RELEASE_SAFETY_DEFAULT)
-                seq_printf(m, ",cap_release_safety=%d",
-                           args->cap_release_safety);
-        if (args->max_readdir != CEPH_MAX_READDIR_DEFAULT)
-                seq_printf(m, ",readdir_max_entries=%d", args->max_readdir);
-        if (args->max_readdir_bytes != CEPH_MAX_READDIR_BYTES_DEFAULT)
-                seq_printf(m, ",readdir_max_bytes=%d", args->max_readdir_bytes);
-        if (strcmp(args->snapdir_name, CEPH_SNAPDIRNAME_DEFAULT))
-                seq_printf(m, ",snapdirname=%s", args->snapdir_name);
-        if (args->name)
-                seq_printf(m, ",name=%s", args->name);
-        if (args->secret)
-                seq_puts(m, ",secret=<hidden>");
-        return 0;
-}
-
-/*
- * caches
- */
-struct kmem_cache *ceph_inode_cachep;
-struct kmem_cache *ceph_cap_cachep;
-struct kmem_cache *ceph_dentry_cachep;
-struct kmem_cache *ceph_file_cachep;
-
-static void ceph_inode_init_once(void *foo)
-{
-        struct ceph_inode_info *ci = foo;
-        inode_init_once(&ci->vfs_inode);
-}
-
-static int __init init_caches(void)
-{
-        ceph_inode_cachep = kmem_cache_create("ceph_inode_info",
-                                      sizeof(struct ceph_inode_info),
-                                      __alignof__(struct ceph_inode_info),
-                                      (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD),
-                                      ceph_inode_init_once);
-        if (ceph_inode_cachep == NULL)
-                return -ENOMEM;
-
-        ceph_cap_cachep = KMEM_CACHE(ceph_cap,
-                                     SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD);
-        if (ceph_cap_cachep == NULL)
-                goto bad_cap;
-
-        ceph_dentry_cachep = KMEM_CACHE(ceph_dentry_info,
-                                        SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD);
-        if (ceph_dentry_cachep == NULL)
-                goto bad_dentry;
-
-        ceph_file_cachep = KMEM_CACHE(ceph_file_info,
-                                      SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD);
-        if (ceph_file_cachep == NULL)
-                goto bad_file;
-
-        return 0;
-
-bad_file:
-        kmem_cache_destroy(ceph_dentry_cachep);
-bad_dentry:
-        kmem_cache_destroy(ceph_cap_cachep);
-bad_cap:
-        kmem_cache_destroy(ceph_inode_cachep);
-        return -ENOMEM;
-}
-
-static void destroy_caches(void)
-{
-        kmem_cache_destroy(ceph_inode_cachep);
-        kmem_cache_destroy(ceph_cap_cachep);
-        kmem_cache_destroy(ceph_dentry_cachep);
-        kmem_cache_destroy(ceph_file_cachep);
-}
-
-
-/*
- * ceph_umount_begin - initiate forced umount.  Tear down down the
- * mount, skipping steps that may hang while waiting for server(s).
- */
-static void ceph_umount_begin(struct super_block *sb)
-{
-        struct ceph_client *client = ceph_sb_to_client(sb);
-
-        dout("ceph_umount_begin - starting forced umount\n");
-        if (!client)
-                return;
-        client->mount_state = CEPH_MOUNT_SHUTDOWN;
-        return;
-}
-
-static const struct super_operations ceph_super_ops = {
-        .alloc_inode    = ceph_alloc_inode,
-        .destroy_inode  = ceph_destroy_inode,
-        .write_inode    = ceph_write_inode,
-        .sync_fs        = ceph_sync_fs,
-        .put_super      = ceph_put_super,
-        .show_options   = ceph_show_options,
-        .statfs         = ceph_statfs,
-        .umount_begin   = ceph_umount_begin,
-};
-
-
-const char *ceph_msg_type_name(int type)
-{
-        switch (type) {
-        case CEPH_MSG_SHUTDOWN: return "shutdown";
-        case CEPH_MSG_PING: return "ping";
-        case CEPH_MSG_AUTH: return "auth";
-        case CEPH_MSG_AUTH_REPLY: return "auth_reply";
-        case CEPH_MSG_MON_MAP: return "mon_map";
-        case CEPH_MSG_MON_GET_MAP: return "mon_get_map";
-        case CEPH_MSG_MON_SUBSCRIBE: return "mon_subscribe";
-        case CEPH_MSG_MON_SUBSCRIBE_ACK: return "mon_subscribe_ack";
-        case CEPH_MSG_STATFS: return "statfs";
-        case CEPH_MSG_STATFS_REPLY: return "statfs_reply";
-        case CEPH_MSG_MDS_MAP: return "mds_map";
-        case CEPH_MSG_CLIENT_SESSION: return "client_session";
-        case CEPH_MSG_CLIENT_RECONNECT: return "client_reconnect";
-        case CEPH_MSG_CLIENT_REQUEST: return "client_request";
-        case CEPH_MSG_CLIENT_REQUEST_FORWARD: return "client_request_forward";
-        case CEPH_MSG_CLIENT_REPLY: return "client_reply";
-        case CEPH_MSG_CLIENT_CAPS: return "client_caps";
-        case CEPH_MSG_CLIENT_CAPRELEASE: return "client_cap_release";
-        case CEPH_MSG_CLIENT_SNAP: return "client_snap";
-        case CEPH_MSG_CLIENT_LEASE: return "client_lease";
-        case CEPH_MSG_OSD_MAP: return "osd_map";
-        case CEPH_MSG_OSD_OP: return "osd_op";
-        case CEPH_MSG_OSD_OPREPLY: return "osd_opreply";
-        default: return "unknown";
-        }
-}
-
-
 /*
  * mount options
  */
 enum {
         Opt_wsize,
         Opt_rsize,
-        Opt_osdtimeout,
-        Opt_osdkeepalivetimeout,
-        Opt_mount_timeout,
-        Opt_osd_idle_ttl,
         Opt_caps_wanted_delay_min,
         Opt_caps_wanted_delay_max,
         Opt_cap_release_safety,
@@ -344,29 +123,19 @@ enum {
         Opt_congestion_kb,
         Opt_last_int,
         /* int args above */
-        Opt_fsid,
         Opt_snapdirname,
-        Opt_name,
-        Opt_secret,
         Opt_last_string,
         /* string args above */
-        Opt_ip,
-        Opt_noshare,
         Opt_dirstat,
         Opt_nodirstat,
         Opt_rbytes,
         Opt_norbytes,
-        Opt_nocrc,
         Opt_noasyncreaddir,
 };
 
-static match_table_t arg_tokens = {
+static match_table_t fsopt_tokens = {
         {Opt_wsize, "wsize=%d"},
         {Opt_rsize, "rsize=%d"},
-        {Opt_osdtimeout, "osdtimeout=%d"},
-        {Opt_osdkeepalivetimeout, "osdkeepalive=%d"},
-        {Opt_mount_timeout, "mount_timeout=%d"},
-        {Opt_osd_idle_ttl, "osd_idle_ttl=%d"},
         {Opt_caps_wanted_delay_min, "caps_wanted_delay_min=%d"},
         {Opt_caps_wanted_delay_max, "caps_wanted_delay_max=%d"},
         {Opt_cap_release_safety, "cap_release_safety=%d"},
@@ -374,403 +143,459 @@ static match_table_t arg_tokens = {
         {Opt_readdir_max_bytes, "readdir_max_bytes=%d"},
         {Opt_congestion_kb, "write_congestion_kb=%d"},
         /* int args above */
-        {Opt_fsid, "fsid=%s"},
         {Opt_snapdirname, "snapdirname=%s"},
-        {Opt_name, "name=%s"},
-        {Opt_secret, "secret=%s"},
         /* string args above */
-        {Opt_ip, "ip=%s"},
-        {Opt_noshare, "noshare"},
         {Opt_dirstat, "dirstat"},
         {Opt_nodirstat, "nodirstat"},
         {Opt_rbytes, "rbytes"},
         {Opt_norbytes, "norbytes"},
-        {Opt_nocrc, "nocrc"},
         {Opt_noasyncreaddir, "noasyncreaddir"},
         {-1, NULL}
 };
 
-static int parse_fsid(const char *str, struct ceph_fsid *fsid)
+static int parse_fsopt_token(char *c, void *private)
 {
-        int i = 0;
-        char tmp[3];
-        int err = -EINVAL;
-        int d;
-
-        dout("parse_fsid '%s'\n", str);
-        tmp[2] = 0;
-        while (*str && i < 16) {
-                if (ispunct(*str)) {
-                        str++;
-                        continue;
+        struct ceph_mount_options *fsopt = private;
+        substring_t argstr[MAX_OPT_ARGS];
+        int token, intval, ret;
+
+        token = match_token((char *)c, fsopt_tokens, argstr);
+        if (token < 0)
+                return -EINVAL;
+
+        if (token < Opt_last_int) {
+                ret = match_int(&argstr[0], &intval);
+                if (ret < 0) {
+                        pr_err("bad mount option arg (not int) "
+                               "at '%s'\n", c);
+                        return ret;
                 }
-                if (!isxdigit(str[0]) || !isxdigit(str[1]))
-                        break;
-                tmp[0] = str[0];
-                tmp[1] = str[1];
-                if (sscanf(tmp, "%x", &d) < 1)
-                        break;
-                fsid->fsid[i] = d & 0xff;
-                i++;
-                str += 2;
+                dout("got int token %d val %d\n", token, intval);
+        } else if (token > Opt_last_int && token < Opt_last_string) {
+                dout("got string token %d val %s\n", token,
+                     argstr[0].from);
+        } else {
+                dout("got token %d\n", token);
         }
 
-        if (i == 16)
-                err = 0;
-        dout("parse_fsid ret %d got fsid %pU", err, fsid);
-        return err;
+        switch (token) {
+        case Opt_snapdirname:
+                kfree(fsopt->snapdir_name);
+                fsopt->snapdir_name = kstrndup(argstr[0].from,
+                                               argstr[0].to-argstr[0].from,
+                                               GFP_KERNEL);
+                if (!fsopt->snapdir_name)
+                        return -ENOMEM;
+                break;
+
+                /* misc */
+        case Opt_wsize:
+                fsopt->wsize = intval;
+                break;
+        case Opt_rsize:
+                fsopt->rsize = intval;
+                break;
+        case Opt_caps_wanted_delay_min:
+                fsopt->caps_wanted_delay_min = intval;
+                break;
+        case Opt_caps_wanted_delay_max:
+                fsopt->caps_wanted_delay_max = intval;
+                break;
+        case Opt_readdir_max_entries:
+                fsopt->max_readdir = intval;
+                break;
+        case Opt_readdir_max_bytes:
+                fsopt->max_readdir_bytes = intval;
+                break;
+        case Opt_congestion_kb:
+                fsopt->congestion_kb = intval;
+                break;
+        case Opt_dirstat:
+                fsopt->flags |= CEPH_MOUNT_OPT_DIRSTAT;
+                break;
+        case Opt_nodirstat:
+                fsopt->flags &= ~CEPH_MOUNT_OPT_DIRSTAT;
+                break;
+        case Opt_rbytes:
+                fsopt->flags |= CEPH_MOUNT_OPT_RBYTES;
+                break;
+        case Opt_norbytes:
+                fsopt->flags &= ~CEPH_MOUNT_OPT_RBYTES;
+                break;
+        case Opt_noasyncreaddir:
+                fsopt->flags |= CEPH_MOUNT_OPT_NOASYNCREADDIR;
+                break;
+        default:
+                BUG_ON(token);
+        }
+        return 0;
 }
 
-static struct ceph_mount_args *parse_mount_args(int flags, char *options,
-                                                const char *dev_name,
-                                                const char **path)
+static void destroy_mount_options(struct ceph_mount_options *args)
 {
-        struct ceph_mount_args *args;
-        const char *c;
-        int err = -ENOMEM;
-        substring_t argstr[MAX_OPT_ARGS];
+        dout("destroy_mount_options %p\n", args);
+        kfree(args->snapdir_name);
+        kfree(args);
+}
 
-        args = kzalloc(sizeof(*args), GFP_KERNEL);
-        if (!args)
-                return ERR_PTR(-ENOMEM);
-        args->mon_addr = kcalloc(CEPH_MAX_MON, sizeof(*args->mon_addr),
-                                 GFP_KERNEL);
-        if (!args->mon_addr)
-                goto out;
+static int strcmp_null(const char *s1, const char *s2)
+{
+        if (!s1 && !s2)
+                return 0;
+        if (s1 && !s2)
+                return -1;
+        if (!s1 && s2)
+                return 1;
+        return strcmp(s1, s2);
+}
 
-        dout("parse_mount_args %p, dev_name '%s'\n", args, dev_name);
-
-        /* start with defaults */
-        args->sb_flags = flags;
-        args->flags = CEPH_OPT_DEFAULT;
-        args->osd_timeout = CEPH_OSD_TIMEOUT_DEFAULT;
-        args->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT;
-        args->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT; /* seconds */
-        args->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT;   /* seconds */
-        args->caps_wanted_delay_min = CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT;
-        args->caps_wanted_delay_max = CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT;
-        args->rsize = CEPH_MOUNT_RSIZE_DEFAULT;
-        args->snapdir_name = kstrdup(CEPH_SNAPDIRNAME_DEFAULT, GFP_KERNEL);
-        args->cap_release_safety = CEPH_CAP_RELEASE_SAFETY_DEFAULT;
-        args->max_readdir = CEPH_MAX_READDIR_DEFAULT;
-        args->max_readdir_bytes = CEPH_MAX_READDIR_BYTES_DEFAULT;
-        args->congestion_kb = default_congestion_kb();
-
-        /* ip1[:port1][,ip2[:port2]...]:/subdir/in/fs */
-        err = -EINVAL;
-        if (!dev_name)
-                goto out;
-        *path = strstr(dev_name, ":/");
-        if (*path == NULL) {
-                pr_err("device name is missing path (no :/ in %s)\n",
-                       dev_name);
-                goto out;
-        }
+static int compare_mount_options(struct ceph_mount_options *new_fsopt,
+                                 struct ceph_options *new_opt,
+                                 struct ceph_fs_client *fsc)
+{
+        struct ceph_mount_options *fsopt1 = new_fsopt;
+        struct ceph_mount_options *fsopt2 = fsc->mount_options;
+        int ofs = offsetof(struct ceph_mount_options, snapdir_name);
+        int ret;
 
-        /* get mon ip(s) */
-        err = ceph_parse_ips(dev_name, *path, args->mon_addr,
-                             CEPH_MAX_MON, &args->num_mon);
-        if (err < 0)
-                goto out;
+        ret = memcmp(fsopt1, fsopt2, ofs);
+        if (ret)
+                return ret;
+
+        ret = strcmp_null(fsopt1->snapdir_name, fsopt2->snapdir_name);
+        if (ret)
+                return ret;
+
+        return ceph_compare_options(new_opt, fsc->client);
+}
+
+static int parse_mount_options(struct ceph_mount_options **pfsopt,
+                               struct ceph_options **popt,
+                               int flags, char *options,
+                               const char *dev_name,
+                               const char **path)
+{
+        struct ceph_mount_options *fsopt;
+        const char *dev_name_end;
+        int err = -ENOMEM;
+
+        fsopt = kzalloc(sizeof(*fsopt), GFP_KERNEL);
+        if (!fsopt)
+                return -ENOMEM;
+
+        dout("parse_mount_options %p, dev_name '%s'\n", fsopt, dev_name);
+
+        fsopt->sb_flags = flags;
+        fsopt->flags = CEPH_MOUNT_OPT_DEFAULT;
+
+        fsopt->rsize = CEPH_MOUNT_RSIZE_DEFAULT;
+        fsopt->snapdir_name = kstrdup(CEPH_SNAPDIRNAME_DEFAULT, GFP_KERNEL);
+        fsopt->cap_release_safety = CEPH_CAP_RELEASE_SAFETY_DEFAULT;
+        fsopt->max_readdir = CEPH_MAX_READDIR_DEFAULT;
+        fsopt->max_readdir_bytes = CEPH_MAX_READDIR_BYTES_DEFAULT;
+        fsopt->congestion_kb = default_congestion_kb();
+        
+        /* ip1[:port1][,ip2[:port2]...]:/subdir/in/fs */
+        err = -EINVAL;
+        if (!dev_name)
+                goto out;
+        *path = strstr(dev_name, ":/");
+        if (*path == NULL) {
+                pr_err("device name is missing path (no :/ in %s)\n",
+                       dev_name);
+                goto out;
+        }
+        dev_name_end = *path;
+        dout("device name '%.*s'\n", (int)(dev_name_end - dev_name), dev_name);
 
         /* path on server */
         *path += 2;
         dout("server path '%s'\n", *path);
 
-        /* parse mount options */
-        while ((c = strsep(&options, ",")) != NULL) {
-                int token, intval, ret;
-                if (!*c)
-                        continue;
-                err = -EINVAL;
-                token = match_token((char *)c, arg_tokens, argstr);
-                if (token < 0) {
-                        pr_err("bad mount option at '%s'\n", c);
-                        goto out;
-                }
-                if (token < Opt_last_int) {
-                        ret = match_int(&argstr[0], &intval);
-                        if (ret < 0) {
-                                pr_err("bad mount option arg (not int) "
-                                       "at '%s'\n", c);
-                                continue;
-                        }
-                        dout("got int token %d val %d\n", token, intval);
-                } else if (token > Opt_last_int && token < Opt_last_string) {
-                        dout("got string token %d val %s\n", token,
-                             argstr[0].from);
-                } else {
-                        dout("got token %d\n", token);
-                }
-                switch (token) {
-                case Opt_ip:
-                        err = ceph_parse_ips(argstr[0].from,
-                                             argstr[0].to,
-                                             &args->my_addr,
-                                             1, NULL);
-                        if (err < 0)
-                                goto out;
-                        args->flags |= CEPH_OPT_MYIP;
-                        break;
-
-                case Opt_fsid:
-                        err = parse_fsid(argstr[0].from, &args->fsid);
-                        if (err == 0)
-                                args->flags |= CEPH_OPT_FSID;
-                        break;
-                case Opt_snapdirname:
-                        kfree(args->snapdir_name);
-                        args->snapdir_name = kstrndup(argstr[0].from,
-                                              argstr[0].to-argstr[0].from,
-                                              GFP_KERNEL);
-                        break;
-                case Opt_name:
-                        args->name = kstrndup(argstr[0].from,
-                                              argstr[0].to-argstr[0].from,
-                                              GFP_KERNEL);
-                        break;
-                case Opt_secret:
-                        args->secret = kstrndup(argstr[0].from,
-                                                argstr[0].to-argstr[0].from,
-                                                GFP_KERNEL);
-                        break;
-
-                        /* misc */
-                case Opt_wsize:
-                        args->wsize = intval;
-                        break;
-                case Opt_rsize:
-                        args->rsize = intval;
-                        break;
-                case Opt_osdtimeout:
-                        args->osd_timeout = intval;
-                        break;
-                case Opt_osdkeepalivetimeout:
-                        args->osd_keepalive_timeout = intval;
-                        break;
-                case Opt_osd_idle_ttl:
-                        args->osd_idle_ttl = intval;
-                        break;
-                case Opt_mount_timeout:
-                        args->mount_timeout = intval;
-                        break;
-                case Opt_caps_wanted_delay_min:
-                        args->caps_wanted_delay_min = intval;
-                        break;
-                case Opt_caps_wanted_delay_max:
-                        args->caps_wanted_delay_max = intval;
-                        break;
-                case Opt_readdir_max_entries:
-                        args->max_readdir = intval;
-                        break;
-                case Opt_readdir_max_bytes:
-                        args->max_readdir_bytes = intval;
-                        break;
-                case Opt_congestion_kb:
-                        args->congestion_kb = intval;
-                        break;
-
-                case Opt_noshare:
-                        args->flags |= CEPH_OPT_NOSHARE;
-                        break;
-
-                case Opt_dirstat:
-                        args->flags |= CEPH_OPT_DIRSTAT;
-                        break;
-                case Opt_nodirstat:
-                        args->flags &= ~CEPH_OPT_DIRSTAT;
-                        break;
-                case Opt_rbytes:
-                        args->flags |= CEPH_OPT_RBYTES;
-                        break;
-                case Opt_norbytes:
-                        args->flags &= ~CEPH_OPT_RBYTES;
-                        break;
-                case Opt_nocrc:
-                        args->flags |= CEPH_OPT_NOCRC;
-                        break;
-                case Opt_noasyncreaddir:
-                        args->flags |= CEPH_OPT_NOASYNCREADDIR;
-                        break;
-
-                default:
-                        BUG_ON(token);
-                }
-        }
-        return args;
+        err = ceph_parse_options(popt, options, dev_name, dev_name_end,
+                                 parse_fsopt_token, (void *)fsopt);
+        if (err)
+                goto out;
+
+        /* success */
+        *pfsopt = fsopt;
+        return 0;
 
 out:
-        kfree(args->mon_addr);
-        kfree(args);
-        return ERR_PTR(err);
+        destroy_mount_options(fsopt);
+        return err;
 }
 
-static void destroy_mount_args(struct ceph_mount_args *args)
+/**
+ * ceph_show_options - Show mount options in /proc/mounts
+ * @m: seq_file to write to
+ * @mnt: mount descriptor
+ */
+static int ceph_show_options(struct seq_file *m, struct vfsmount *mnt)
 {
-        dout("destroy_mount_args %p\n", args);
-        kfree(args->snapdir_name);
-        args->snapdir_name = NULL;
-        kfree(args->name);
-        args->name = NULL;
-        kfree(args->secret);
-        args->secret = NULL;
-        kfree(args);
+        struct ceph_fs_client *fsc = ceph_sb_to_client(mnt->mnt_sb);
+        struct ceph_mount_options *fsopt = fsc->mount_options;
+        struct ceph_options *opt = fsc->client->options;
+
+        if (opt->flags & CEPH_OPT_FSID)
+                seq_printf(m, ",fsid=%pU", &opt->fsid);
+        if (opt->flags & CEPH_OPT_NOSHARE)
+                seq_puts(m, ",noshare");
+        if (opt->flags & CEPH_OPT_NOCRC)
+                seq_puts(m, ",nocrc");
+
+        if (opt->name)
+                seq_printf(m, ",name=%s", opt->name);
+        if (opt->secret)
+                seq_puts(m, ",secret=<hidden>");
+
+        if (opt->mount_timeout != CEPH_MOUNT_TIMEOUT_DEFAULT)
+                seq_printf(m, ",mount_timeout=%d", opt->mount_timeout);
+        if (opt->osd_idle_ttl != CEPH_OSD_IDLE_TTL_DEFAULT)
+                seq_printf(m, ",osd_idle_ttl=%d", opt->osd_idle_ttl);
+        if (opt->osd_timeout != CEPH_OSD_TIMEOUT_DEFAULT)
+                seq_printf(m, ",osdtimeout=%d", opt->osd_timeout);
+        if (opt->osd_keepalive_timeout != CEPH_OSD_KEEPALIVE_DEFAULT)
+                seq_printf(m, ",osdkeepalivetimeout=%d",
+                           opt->osd_keepalive_timeout);
+
+        if (fsopt->flags & CEPH_MOUNT_OPT_DIRSTAT)
+                seq_puts(m, ",dirstat");
+        if ((fsopt->flags & CEPH_MOUNT_OPT_RBYTES) == 0)
+                seq_puts(m, ",norbytes");
+        if (fsopt->flags & CEPH_MOUNT_OPT_NOASYNCREADDIR)
+                seq_puts(m, ",noasyncreaddir");
+
+        if (fsopt->wsize)
+                seq_printf(m, ",wsize=%d", fsopt->wsize);
+        if (fsopt->rsize != CEPH_MOUNT_RSIZE_DEFAULT)
+                seq_printf(m, ",rsize=%d", fsopt->rsize);
+        if (fsopt->congestion_kb != default_congestion_kb())
+                seq_printf(m, ",write_congestion_kb=%d", fsopt->congestion_kb);
+        if (fsopt->caps_wanted_delay_min != CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT)
+                seq_printf(m, ",caps_wanted_delay_min=%d",
+                         fsopt->caps_wanted_delay_min);
+        if (fsopt->caps_wanted_delay_max != CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT)
+                seq_printf(m, ",caps_wanted_delay_max=%d",
+                           fsopt->caps_wanted_delay_max);
+        if (fsopt->cap_release_safety != CEPH_CAP_RELEASE_SAFETY_DEFAULT)
+                seq_printf(m, ",cap_release_safety=%d",
+                           fsopt->cap_release_safety);
+        if (fsopt->max_readdir != CEPH_MAX_READDIR_DEFAULT)
+                seq_printf(m, ",readdir_max_entries=%d", fsopt->max_readdir);
+        if (fsopt->max_readdir_bytes != CEPH_MAX_READDIR_BYTES_DEFAULT)
+                seq_printf(m, ",readdir_max_bytes=%d", fsopt->max_readdir_bytes);
+        if (strcmp(fsopt->snapdir_name, CEPH_SNAPDIRNAME_DEFAULT))
+                seq_printf(m, ",snapdirname=%s", fsopt->snapdir_name);
+        return 0;
 }
 
 /*
- * create a fresh client instance
+ * handle any mon messages the standard library doesn't understand.
+ * return error if we don't either.
  */
-static struct ceph_client *ceph_create_client(struct ceph_mount_args *args)
+static int extra_mon_dispatch(struct ceph_client *client, struct ceph_msg *msg)
 {
-        struct ceph_client *client;
+        struct ceph_fs_client *fsc = client->private;
+        int type = le16_to_cpu(msg->hdr.type);
+
+        switch (type) {
+        case CEPH_MSG_MDS_MAP:
+                ceph_mdsc_handle_map(fsc->mdsc, msg);
+                return 0;
+
+        default:
+                return -1;
+        }
+}
+
+/*
+ * create a new fs client
+ */
+struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
+                                        struct ceph_options *opt)
+{
+        struct ceph_fs_client *fsc;
         int err = -ENOMEM;
 
-        client = kzalloc(sizeof(*client), GFP_KERNEL);
-        if (client == NULL)
+        fsc = kzalloc(sizeof(*fsc), GFP_KERNEL);
+        if (!fsc)
                 return ERR_PTR(-ENOMEM);
 
-        mutex_init(&client->mount_mutex);
-
-        init_waitqueue_head(&client->auth_wq);
+        fsc->client = ceph_create_client(opt, fsc);
+        if (IS_ERR(fsc->client)) {
+                err = PTR_ERR(fsc->client);
+                goto fail;
+        }
+        fsc->client->extra_mon_dispatch = extra_mon_dispatch;
+        fsc->client->supported_features |= CEPH_FEATURE_FLOCK;
+        fsc->client->monc.want_mdsmap = 1;
 
-        client->sb = NULL;
-        client->mount_state = CEPH_MOUNT_MOUNTING;
-        client->mount_args = args;
+        fsc->mount_options = fsopt;
 
-        client->msgr = NULL;
+        fsc->sb = NULL;
+        fsc->mount_state = CEPH_MOUNT_MOUNTING;
 
-        client->auth_err = 0;
-        atomic_long_set(&client->writeback_count, 0);
+        atomic_long_set(&fsc->writeback_count, 0);
 
-        err = bdi_init(&client->backing_dev_info);
+        err = bdi_init(&fsc->backing_dev_info);
         if (err < 0)
-                goto fail;
+                goto fail_client;
 
         err = -ENOMEM;
-        client->wb_wq = create_workqueue("ceph-writeback");
-        if (client->wb_wq == NULL)
+        fsc->wb_wq = create_workqueue("ceph-writeback");
+        if (fsc->wb_wq == NULL)
                 goto fail_bdi;
-        client->pg_inv_wq = create_singlethread_workqueue("ceph-pg-invalid");
-        if (client->pg_inv_wq == NULL)
+        fsc->pg_inv_wq = create_singlethread_workqueue("ceph-pg-invalid");
+        if (fsc->pg_inv_wq == NULL)
                 goto fail_wb_wq;
-        client->trunc_wq = create_singlethread_workqueue("ceph-trunc");
-        if (client->trunc_wq == NULL)
+        fsc->trunc_wq = create_singlethread_workqueue("ceph-trunc");
+        if (fsc->trunc_wq == NULL)
                 goto fail_pg_inv_wq;
 
         /* set up mempools */
         err = -ENOMEM;
-        client->wb_pagevec_pool = mempool_create_kmalloc_pool(10,
-                              client->mount_args->wsize >> PAGE_CACHE_SHIFT);
-        if (!client->wb_pagevec_pool)
+        fsc->wb_pagevec_pool = mempool_create_kmalloc_pool(10,
+                              fsc->mount_options->wsize >> PAGE_CACHE_SHIFT);
+        if (!fsc->wb_pagevec_pool)
                 goto fail_trunc_wq;
 
         /* caps */
-        client->min_caps = args->max_readdir;
+        fsc->min_caps = fsopt->max_readdir;
+
+        return fsc;
 
-        /* subsystems */
-        err = ceph_monc_init(&client->monc, client);
-        if (err < 0)
-                goto fail_mempool;
-        err = ceph_osdc_init(&client->osdc, client);
-        if (err < 0)
-                goto fail_monc;
-        err = ceph_mdsc_init(&client->mdsc, client);
-        if (err < 0)
-                goto fail_osdc;
-        return client;
-
-fail_osdc:
-        ceph_osdc_stop(&client->osdc);
-fail_monc:
-        ceph_monc_stop(&client->monc);
-fail_mempool:
-        mempool_destroy(client->wb_pagevec_pool);
 fail_trunc_wq:
-        destroy_workqueue(client->trunc_wq);
+        destroy_workqueue(fsc->trunc_wq);
 fail_pg_inv_wq:
-        destroy_workqueue(client->pg_inv_wq);
+        destroy_workqueue(fsc->pg_inv_wq);
 fail_wb_wq:
-        destroy_workqueue(client->wb_wq);
+        destroy_workqueue(fsc->wb_wq);
 fail_bdi:
-        bdi_destroy(&client->backing_dev_info);
+        bdi_destroy(&fsc->backing_dev_info);
+fail_client:
+        ceph_destroy_client(fsc->client);
 fail:
-        kfree(client);
+        kfree(fsc);
         return ERR_PTR(err);
 }
 
-static void ceph_destroy_client(struct ceph_client *client)
+void destroy_fs_client(struct ceph_fs_client *fsc)
 {
-        dout("destroy_client %p\n", client);
+        dout("destroy_fs_client %p\n", fsc);
 
-        /* unmount */
-        ceph_mdsc_stop(&client->mdsc);
-        ceph_osdc_stop(&client->osdc);
+        destroy_workqueue(fsc->wb_wq);
+        destroy_workqueue(fsc->pg_inv_wq);
+        destroy_workqueue(fsc->trunc_wq);
 
-        /*
-         * make sure mds and osd connections close out before destroying
-         * the auth module, which is needed to free those connections'
-         * ceph_authorizers.
-         */
-        ceph_msgr_flush();
-
-        ceph_monc_stop(&client->monc);
+        bdi_destroy(&fsc->backing_dev_info);
 
-        ceph_debugfs_client_cleanup(client);
-        destroy_workqueue(client->wb_wq);
-        destroy_workqueue(client->pg_inv_wq);
-        destroy_workqueue(client->trunc_wq);
+        mempool_destroy(fsc->wb_pagevec_pool);
 
-        bdi_destroy(&client->backing_dev_info);
+        destroy_mount_options(fsc->mount_options);
 
-        if (client->msgr)
-                ceph_messenger_destroy(client->msgr);
-        mempool_destroy(client->wb_pagevec_pool);
+        ceph_fs_debugfs_cleanup(fsc);
 
-        destroy_mount_args(client->mount_args);
+        ceph_destroy_client(fsc->client);
 
-        kfree(client);
-        dout("destroy_client %p done\n", client);
+        kfree(fsc);
+        dout("destroy_fs_client %p done\n", fsc);
 }
 
 /*
- * Initially learn our fsid, or verify an fsid matches.
+ * caches
  */
-int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid)
+struct kmem_cache *ceph_inode_cachep;
+struct kmem_cache *ceph_cap_cachep;
+struct kmem_cache *ceph_dentry_cachep;
+struct kmem_cache *ceph_file_cachep;
+
+static void ceph_inode_init_once(void *foo)
 {
-        if (client->have_fsid) {
-                if (ceph_fsid_compare(&client->fsid, fsid)) {
-                        pr_err("bad fsid, had %pU got %pU",
-                               &client->fsid, fsid);
-                        return -1;
-                }
-        } else {
-                pr_info("client%lld fsid %pU\n", client->monc.auth->global_id,
-                        fsid);
-                memcpy(&client->fsid, fsid, sizeof(*fsid));
-                ceph_debugfs_client_init(client);
-                client->have_fsid = true;
-        }
+        struct ceph_inode_info *ci = foo;
+        inode_init_once(&ci->vfs_inode);
+}
+
+static int __init init_caches(void)
+{
+        ceph_inode_cachep = kmem_cache_create("ceph_inode_info",
+                                      sizeof(struct ceph_inode_info),
+                                      __alignof__(struct ceph_inode_info),
+                                      (SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD),
+                                      ceph_inode_init_once);
+        if (ceph_inode_cachep == NULL)
+                return -ENOMEM;
+
+        ceph_cap_cachep = KMEM_CACHE(ceph_cap,
+                                     SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD);
+        if (ceph_cap_cachep == NULL)
+                goto bad_cap;
+
+        ceph_dentry_cachep = KMEM_CACHE(ceph_dentry_info,
+                                        SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD);
+        if (ceph_dentry_cachep == NULL)
+                goto bad_dentry;
+
+        ceph_file_cachep = KMEM_CACHE(ceph_file_info,
+                                      SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD);
+        if (ceph_file_cachep == NULL)
+                goto bad_file;
+
         return 0;
+
+bad_file:
+        kmem_cache_destroy(ceph_dentry_cachep);
+bad_dentry:
+        kmem_cache_destroy(ceph_cap_cachep);
+bad_cap:
+        kmem_cache_destroy(ceph_inode_cachep);
+        return -ENOMEM;
 }
 
+static void destroy_caches(void)
+{
+        kmem_cache_destroy(ceph_inode_cachep);
+        kmem_cache_destroy(ceph_cap_cachep);
+        kmem_cache_destroy(ceph_dentry_cachep);
+        kmem_cache_destroy(ceph_file_cachep);
+}
+
+
 /*
- * true if we have the mon map (and have thus joined the cluster)
+ * ceph_umount_begin - initiate forced umount.  Tear down down the
+ * mount, skipping steps that may hang while waiting for server(s).
  */
-static int have_mon_and_osd_map(struct ceph_client *client)
+static void ceph_umount_begin(struct super_block *sb)
 {
-        return client->monc.monmap && client->monc.monmap->epoch &&
-               client->osdc.osdmap && client->osdc.osdmap->epoch;
+        struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
+
+        dout("ceph_umount_begin - starting forced umount\n");
+        if (!fsc)
+                return;
+        fsc->mount_state = CEPH_MOUNT_SHUTDOWN;
+        return;
 }
 
+static const struct super_operations ceph_super_ops = {
+        .alloc_inode    = ceph_alloc_inode,
+        .destroy_inode  = ceph_destroy_inode,
+        .write_inode    = ceph_write_inode,
+        .sync_fs        = ceph_sync_fs,
+        .put_super      = ceph_put_super,
+        .show_options   = ceph_show_options,
+        .statfs         = ceph_statfs,
+        .umount_begin   = ceph_umount_begin,
+};
+
 /*
  * Bootstrap mount by opening the root directory.  Note the mount
  * @started time from caller, and time out if this takes too long.
  */
-static struct dentry *open_root_dentry(struct ceph_client *client,
+static struct dentry *open_root_dentry(struct ceph_fs_client *fsc,
                                        const char *path,
                                        unsigned long started)
 {
-        struct ceph_mds_client *mdsc = &client->mdsc;
+        struct ceph_mds_client *mdsc = fsc->mdsc;
         struct ceph_mds_request *req = NULL;
         int err;
         struct dentry *root;
@@ -784,14 +609,14 @@ static struct dentry *open_root_dentry(struct ceph_client *client,
         req->r_ino1.ino = CEPH_INO_ROOT;
         req->r_ino1.snap = CEPH_NOSNAP;
         req->r_started = started;
-        req->r_timeout = client->mount_args->mount_timeout * HZ;
+        req->r_timeout = fsc->client->options->mount_timeout * HZ;
         req->r_args.getattr.mask = cpu_to_le32(CEPH_STAT_CAP_INODE);
         req->r_num_caps = 2;
         err = ceph_mdsc_do_request(mdsc, NULL, req);
         if (err == 0) {
                 dout("open_root_inode success\n");
                 if (ceph_ino(req->r_target_inode) == CEPH_INO_ROOT &&
-                    client->sb->s_root == NULL)
+                    fsc->sb->s_root == NULL)
                         root = d_alloc_root(req->r_target_inode);
                 else
                         root = d_obtain_alias(req->r_target_inode);
@@ -804,105 +629,86 @@ static struct dentry *open_root_dentry(struct ceph_client *client,
         return root;
 }
 
+
+
+
 /*
  * mount: join the ceph cluster, and open root directory.
  */
-static int ceph_mount(struct ceph_client *client, struct vfsmount *mnt,
+static int ceph_mount(struct ceph_fs_client *fsc, struct vfsmount *mnt,
                       const char *path)
 {
-        struct ceph_entity_addr *myaddr = NULL;
         int err;
-        unsigned long timeout = client->mount_args->mount_timeout * HZ;
         unsigned long started = jiffies;  /* note the start time */
         struct dentry *root;
+        int first = 0;   /* first vfsmount for this super_block */
 
         dout("mount start\n");
-        mutex_lock(&client->mount_mutex);
-
-        /* initialize the messenger */
-        if (client->msgr == NULL) {
-                if (ceph_test_opt(client, MYIP))
-                        myaddr = &client->mount_args->my_addr;
-                client->msgr = ceph_messenger_create(myaddr);
-                if (IS_ERR(client->msgr)) {
-                        err = PTR_ERR(client->msgr);
-                        client->msgr = NULL;
-                        goto out;
-                }
-                client->msgr->nocrc = ceph_test_opt(client, NOCRC);
-        }
+        mutex_lock(&fsc->client->mount_mutex);
 
-        /* open session, and wait for mon, mds, and osd maps */
-        err = ceph_monc_open_session(&client->monc);
+        err = __ceph_open_session(fsc->client, started);
         if (err < 0)
                 goto out;
 
-        while (!have_mon_and_osd_map(client)) {
-                err = -EIO;
-                if (timeout && time_after_eq(jiffies, started + timeout))
-                        goto out;
-
-                /* wait */
-                dout("mount waiting for mon_map\n");
-                err = wait_event_interruptible_timeout(client->auth_wq,
-                       have_mon_and_osd_map(client) || (client->auth_err < 0),
-                       timeout);
-                if (err == -EINTR || err == -ERESTARTSYS)
-                        goto out;
-                if (client->auth_err < 0) {
-                        err = client->auth_err;
-                        goto out;
-                }
-        }
-
         dout("mount opening root\n");
-        root = open_root_dentry(client, "", started);
+        root = open_root_dentry(fsc, "", started);
         if (IS_ERR(root)) {
                 err = PTR_ERR(root);
                 goto out;
         }
-        if (client->sb->s_root)
+        if (fsc->sb->s_root) {
                 dput(root);
-        else
-                client->sb->s_root = root;
+        } else {
+                fsc->sb->s_root = root;
+                first = 1;
+
+                err = ceph_fs_debugfs_init(fsc);
+                if (err < 0)
+                        goto fail;
+        }
 
         if (path[0] == 0) {
                 dget(root);
         } else {
                 dout("mount opening base mountpoint\n");
-                root = open_root_dentry(client, path, started);
+                root = open_root_dentry(fsc, path, started);
                 if (IS_ERR(root)) {
                         err = PTR_ERR(root);
-                        dput(client->sb->s_root);
-                        client->sb->s_root = NULL;
-                        goto out;
+                        goto fail;
                 }
         }
 
         mnt->mnt_root = root;
-        mnt->mnt_sb = client->sb;
+        mnt->mnt_sb = fsc->sb;
 
-        client->mount_state = CEPH_MOUNT_MOUNTED;
+        fsc->mount_state = CEPH_MOUNT_MOUNTED;
         dout("mount success\n");
         err = 0;
 
 out:
-        mutex_unlock(&client->mount_mutex);
+        mutex_unlock(&fsc->client->mount_mutex);
         return err;
+
+fail:
+        if (first) {
+                dput(fsc->sb->s_root);
+                fsc->sb->s_root = NULL;
+        }
+        goto out;
 }
 
 static int ceph_set_super(struct super_block *s, void *data)
 {
-        struct ceph_client *client = data;
+        struct ceph_fs_client *fsc = data;
         int ret;
 
         dout("set_super %p data %p\n", s, data);
 
-        s->s_flags = client->mount_args->sb_flags;
+        s->s_flags = fsc->mount_options->sb_flags;
         s->s_maxbytes = 1ULL << 40;  /* temp value until we get mdsmap */
 
-        s->s_fs_info = client;
-        client->sb = s;
+        s->s_fs_info = fsc;
+        fsc->sb = s;
 
         s->s_op = &ceph_super_ops;
         s->s_export_op = &ceph_export_ops;
@@ -917,7 +723,7 @@ static int ceph_set_super(struct super_block *s, void *data)
 
 fail:
         s->s_fs_info = NULL;
-        client->sb = NULL;
+        fsc->sb = NULL;
         return ret;
 }
 
@@ -926,30 +732,23 @@ fail:
  */
 static int ceph_compare_super(struct super_block *sb, void *data)
 {
-        struct ceph_client *new = data;
-        struct ceph_mount_args *args = new->mount_args;
-        struct ceph_client *other = ceph_sb_to_client(sb);
-        int i;
+        struct ceph_fs_client *new = data;
+        struct ceph_mount_options *fsopt = new->mount_options;
+        struct ceph_options *opt = new->client->options;
+        struct ceph_fs_client *other = ceph_sb_to_client(sb);
 
         dout("ceph_compare_super %p\n", sb);
-        if (args->flags & CEPH_OPT_FSID) {
-                if (ceph_fsid_compare(&args->fsid, &other->fsid)) {
-                        dout("fsid doesn't match\n");
-                        return 0;
-                }
-        } else {
-                /* do we share (a) monitor? */
-                for (i = 0; i < new->monc.monmap->num_mon; i++)
-                        if (ceph_monmap_contains(other->monc.monmap,
-                                         &new->monc.monmap->mon_inst[i].addr))
-                                break;
-                if (i == new->monc.monmap->num_mon) {
-                        dout("mon ip not part of monmap\n");
-                        return 0;
-                }
-                dout("mon ip matches existing sb %p\n", sb);
+
+        if (compare_mount_options(fsopt, opt, other)) {
+                dout("monitor(s)/mount options don't match\n");
+                return 0;
         }
-        if (args->sb_flags != other->mount_args->sb_flags) {
+        if ((opt->flags & CEPH_OPT_FSID) &&
+            ceph_fsid_compare(&opt->fsid, &other->client->fsid)) {
+                dout("fsid doesn't match\n");
+                return 0;
+        }
+        if (fsopt->sb_flags != other->mount_options->sb_flags) {
                 dout("flags differ\n");
                 return 0;
         }
@@ -961,19 +760,20 @@ static int ceph_compare_super(struct super_block *sb, void *data)
  */
 static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
 
-static int ceph_register_bdi(struct super_block *sb, struct ceph_client *client)
+static int ceph_register_bdi(struct super_block *sb,
+                             struct ceph_fs_client *fsc)
 {
         int err;
 
         /* set ra_pages based on rsize mount option? */
-        if (client->mount_args->rsize >= PAGE_CACHE_SIZE)
-                client->backing_dev_info.ra_pages =
-                        (client->mount_args->rsize + PAGE_CACHE_SIZE - 1)
+        if (fsc->mount_options->rsize >= PAGE_CACHE_SIZE)
+                fsc->backing_dev_info.ra_pages =
+                        (fsc->mount_options->rsize + PAGE_CACHE_SIZE - 1)
                         >> PAGE_SHIFT;
-        err = bdi_register(&client->backing_dev_info, NULL, "ceph-%d",
+        err = bdi_register(&fsc->backing_dev_info, NULL, "ceph-%d",
                            atomic_long_inc_return(&bdi_seq));
         if (!err)
-                sb->s_bdi = &client->backing_dev_info;
+                sb->s_bdi = &fsc->backing_dev_info;
         return err;
 }
 
@@ -982,46 +782,52 @@ static int ceph_get_sb(struct file_system_type *fs_type,
                        struct vfsmount *mnt)
 {
         struct super_block *sb;
-        struct ceph_client *client;
+        struct ceph_fs_client *fsc;
         int err;
         int (*compare_super)(struct super_block *, void *) = ceph_compare_super;
         const char *path = NULL;
-        struct ceph_mount_args *args;
+        struct ceph_mount_options *fsopt = NULL;
+        struct ceph_options *opt = NULL;
 
         dout("ceph_get_sb\n");
-        args = parse_mount_args(flags, data, dev_name, &path);
-        if (IS_ERR(args)) {
-                err = PTR_ERR(args);
+        err = parse_mount_options(&fsopt, &opt, flags, data, dev_name, &path);
+        if (err < 0)
                 goto out_final;
-        }
 
         /* create client (which we may/may not use) */
-        client = ceph_create_client(args);
-        if (IS_ERR(client)) {
-                err = PTR_ERR(client);
+        fsc = create_fs_client(fsopt, opt);
+        if (IS_ERR(fsc)) {
+                err = PTR_ERR(fsc);
+                kfree(fsopt);
+                kfree(opt);
                 goto out_final;
         }
 
-        if (client->mount_args->flags & CEPH_OPT_NOSHARE)
+        err = ceph_mdsc_init(fsc);
+        if (err < 0)
+                goto out;
+
+        if (ceph_test_opt(fsc->client, NOSHARE))
                 compare_super = NULL;
-        sb = sget(fs_type, compare_super, ceph_set_super, client);
+        sb = sget(fs_type, compare_super, ceph_set_super, fsc);
         if (IS_ERR(sb)) {
                 err = PTR_ERR(sb);
                 goto out;
         }
 
-        if (ceph_sb_to_client(sb) != client) {
-                ceph_destroy_client(client);
-                client = ceph_sb_to_client(sb);
-                dout("get_sb got existing client %p\n", client);
+        if (ceph_sb_to_client(sb) != fsc) {
+                ceph_mdsc_destroy(fsc);
+                destroy_fs_client(fsc);
+                fsc = ceph_sb_to_client(sb);
+                dout("get_sb got existing client %p\n", fsc);
         } else {
-                dout("get_sb using new client %p\n", client);
-                err = ceph_register_bdi(sb, client);
+                dout("get_sb using new client %p\n", fsc);
+                err = ceph_register_bdi(sb, fsc);
                 if (err < 0)
                         goto out_splat;
         }
 
-        err = ceph_mount(client, mnt, path);
+        err = ceph_mount(fsc, mnt, path);
         if (err < 0)
                 goto out_splat;
         dout("root %p inode %p ino %llx.%llx\n", mnt->mnt_root,
@@ -1029,12 +835,13 @@ static int ceph_get_sb(struct file_system_type *fs_type,
         return 0;
 
 out_splat:
-        ceph_mdsc_close_sessions(&client->mdsc);
+        ceph_mdsc_close_sessions(fsc->mdsc);
         deactivate_locked_super(sb);
         goto out_final;
 
 out:
-        ceph_destroy_client(client);
+        ceph_mdsc_destroy(fsc);
+        destroy_fs_client(fsc);
 out_final:
         dout("ceph_get_sb fail %d\n", err);
         return err;
@@ -1042,11 +849,12 @@ out_final:
 
 static void ceph_kill_sb(struct super_block *s)
 {
-        struct ceph_client *client = ceph_sb_to_client(s);
+        struct ceph_fs_client *fsc = ceph_sb_to_client(s);
         dout("kill_sb %p\n", s);
-        ceph_mdsc_pre_umount(&client->mdsc);
+        ceph_mdsc_pre_umount(fsc->mdsc);
         kill_anon_super(s);    /* will call put_super after sb is r/o */
-        ceph_destroy_client(client);
+        ceph_mdsc_destroy(fsc);
+        destroy_fs_client(fsc);
 }
 
 static struct file_system_type ceph_fs_type = {
@@ -1062,36 +870,20 @@ static struct file_system_type ceph_fs_type = {
 
 static int __init init_ceph(void)
 {
-        int ret = 0;
-
-        ret = ceph_debugfs_init();
-        if (ret < 0)
-                goto out;
-
-        ret = ceph_msgr_init();
-        if (ret < 0)
-                goto out_debugfs;
-
-        ret = init_caches();
+        int ret = init_caches();
         if (ret)
-                goto out_msgr;
+                goto out;
 
         ret = register_filesystem(&ceph_fs_type);
         if (ret)
                 goto out_icache;
 
-        pr_info("loaded (mon/mds/osd proto %d/%d/%d, osdmap %d/%d %d/%d)\n",
-                CEPH_MONC_PROTOCOL, CEPH_MDSC_PROTOCOL, CEPH_OSDC_PROTOCOL,
-                CEPH_OSDMAP_VERSION, CEPH_OSDMAP_VERSION_EXT,
-                CEPH_OSDMAP_INC_VERSION, CEPH_OSDMAP_INC_VERSION_EXT);
+        pr_info("loaded (mds proto %d)\n", CEPH_MDSC_PROTOCOL);
+
         return 0;
 
 out_icache:
         destroy_caches();
-out_msgr:
-        ceph_msgr_exit();
-out_debugfs:
-        ceph_debugfs_cleanup();
 out:
         return ret;
 }
@@ -1101,8 +893,6 @@ static void __exit exit_ceph(void)
         dout("exit_ceph\n");
         unregister_filesystem(&ceph_fs_type);
         destroy_caches();
-        ceph_msgr_exit();
-        ceph_debugfs_cleanup();
 }
 
 module_init(init_ceph);
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index b87638e84c4b..1886294e12f7 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -1,7 +1,7 @@
 #ifndef _FS_CEPH_SUPER_H
 #define _FS_CEPH_SUPER_H
 
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <asm/unaligned.h>
 #include <linux/backing-dev.h>
@@ -14,13 +14,7 @@
 #include <linux/writeback.h>
 #include <linux/slab.h>
 
-#include "types.h"
-#include "messenger.h"
-#include "msgpool.h"
-#include "mon_client.h"
-#include "mds_client.h"
-#include "osd_client.h"
-#include "ceph_fs.h"
+#include <linux/ceph/libceph.h>
 
 /* f_type in struct statfs */
 #define CEPH_SUPER_MAGIC 0x00c36400
@@ -30,42 +24,25 @@
 #define CEPH_BLOCK_SHIFT   20  /* 1 MB */
 #define CEPH_BLOCK         (1 << CEPH_BLOCK_SHIFT)
 
-/*
- * Supported features
- */
-#define CEPH_FEATURE_SUPPORTED CEPH_FEATURE_NOSRCADDR | CEPH_FEATURE_FLOCK
-#define CEPH_FEATURE_REQUIRED  CEPH_FEATURE_NOSRCADDR
+#define CEPH_MOUNT_OPT_DIRSTAT         (1<<4) /* `cat dirname` for stats */
+#define CEPH_MOUNT_OPT_RBYTES          (1<<5) /* dir st_bytes = rbytes */
+#define CEPH_MOUNT_OPT_NOASYNCREADDIR  (1<<7) /* no dcache readdir */
 
-/*
- * mount options
- */
-#define CEPH_OPT_FSID             (1<<0)
-#define CEPH_OPT_NOSHARE          (1<<1) /* don't share client with other sbs */
-#define CEPH_OPT_MYIP             (1<<2) /* specified my ip */
-#define CEPH_OPT_DIRSTAT          (1<<4) /* funky `cat dirname` for stats */
-#define CEPH_OPT_RBYTES           (1<<5) /* dir st_bytes = rbytes */
-#define CEPH_OPT_NOCRC            (1<<6) /* no data crc on writes */
-#define CEPH_OPT_NOASYNCREADDIR   (1<<7) /* no dcache readdir */
+#define CEPH_MOUNT_OPT_DEFAULT    (CEPH_MOUNT_OPT_RBYTES)
 
-#define CEPH_OPT_DEFAULT   (CEPH_OPT_RBYTES)
+#define ceph_set_mount_opt(fsc, opt) \
+        (fsc)->mount_options->flags |= CEPH_MOUNT_OPT_##opt;
+#define ceph_test_mount_opt(fsc, opt) \
+        (!!((fsc)->mount_options->flags & CEPH_MOUNT_OPT_##opt))
 
-#define ceph_set_opt(client, opt) \
-        (client)->mount_args->flags |= CEPH_OPT_##opt;
-#define ceph_test_opt(client, opt) \
-        (!!((client)->mount_args->flags & CEPH_OPT_##opt))
+#define CEPH_MAX_READDIR_DEFAULT        1024
+#define CEPH_MAX_READDIR_BYTES_DEFAULT  (512*1024)
+#define CEPH_SNAPDIRNAME_DEFAULT        ".snap"
 
-
-struct ceph_mount_args {
-        int sb_flags;
+struct ceph_mount_options {
         int flags;
-        struct ceph_fsid fsid;
-        struct ceph_entity_addr my_addr;
-        int num_mon;
-        struct ceph_entity_addr *mon_addr;
-        int mount_timeout;
-        int osd_idle_ttl;
-        int osd_timeout;
-        int osd_keepalive_timeout;
+        int sb_flags;
+
         int wsize;
         int rsize;            /* max readahead */
         int congestion_kb;    /* max writeback in flight */
@@ -73,82 +50,25 @@ struct ceph_mount_args {
         int cap_release_safety;
         int max_readdir;       /* max readdir result (entires) */
         int max_readdir_bytes; /* max readdir result (bytes) */
-        char *snapdir_name;   /* default ".snap" */
-        char *name;
-        char *secret;
-};
 
-/*
- * defaults
- */
-#define CEPH_MOUNT_TIMEOUT_DEFAULT  60
-#define CEPH_OSD_TIMEOUT_DEFAULT    60  /* seconds */
-#define CEPH_OSD_KEEPALIVE_DEFAULT  5
-#define CEPH_OSD_IDLE_TTL_DEFAULT    60
-#define CEPH_MOUNT_RSIZE_DEFAULT    (512*1024) /* readahead */
-#define CEPH_MAX_READDIR_DEFAULT    1024
-#define CEPH_MAX_READDIR_BYTES_DEFAULT    (512*1024)
-
-#define CEPH_MSG_MAX_FRONT_LEN  (16*1024*1024)
-#define CEPH_MSG_MAX_DATA_LEN   (16*1024*1024)
-
-#define CEPH_SNAPDIRNAME_DEFAULT ".snap"
-#define CEPH_AUTH_NAME_DEFAULT   "guest"
-/*
- * Delay telling the MDS we no longer want caps, in case we reopen
- * the file.  Delay a minimum amount of time, even if we send a cap
- * message for some other reason.  Otherwise, take the oppotunity to
- * update the mds to avoid sending another message later.
- */
-#define CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT      5  /* cap release delay */
-#define CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT     60  /* cap release delay */
-
-#define CEPH_CAP_RELEASE_SAFETY_DEFAULT        (CEPH_CAPS_PER_RELEASE * 4)
-
-/* mount state */
-enum {
-        CEPH_MOUNT_MOUNTING,
-        CEPH_MOUNT_MOUNTED,
-        CEPH_MOUNT_UNMOUNTING,
-        CEPH_MOUNT_UNMOUNTED,
-        CEPH_MOUNT_SHUTDOWN,
-};
-
-/*
- * subtract jiffies
- */
-static inline unsigned long time_sub(unsigned long a, unsigned long b)
-{
-        BUG_ON(time_after(b, a));
-        return (long)a - (long)b;
-}
-
-/*
- * per-filesystem client state
- *
- * possibly shared by multiple mount points, if they are
- * mounting the same ceph filesystem/cluster.
- */
-struct ceph_client {
-        struct ceph_fsid fsid;
-        bool have_fsid;
+        /*
+         * everything above this point can be memcmp'd; everything below
+         * is handled in compare_mount_options()
+         */
 
-        struct mutex mount_mutex;       /* serialize mount attempts */
-        struct ceph_mount_args *mount_args;
+        char *snapdir_name;   /* default ".snap" */
+};
 
+struct ceph_fs_client {
         struct super_block *sb;
 
-        unsigned long mount_state;
-        wait_queue_head_t auth_wq;
-
-        int auth_err;
+        struct ceph_mount_options *mount_options;
+        struct ceph_client *client;
 
+        unsigned long mount_state;
         int min_caps;                  /* min caps i added */
 
-        struct ceph_messenger *msgr;   /* messenger instance */
-        struct ceph_mon_client monc;
-        struct ceph_mds_client mdsc;
-        struct ceph_osd_client osdc;
+        struct ceph_mds_client *mdsc;
 
         /* writeback */
         mempool_t *wb_pagevec_pool;
@@ -160,14 +80,14 @@ struct ceph_client {
         struct backing_dev_info backing_dev_info;
 
 #ifdef CONFIG_DEBUG_FS
-        struct dentry *debugfs_monmap;
-        struct dentry *debugfs_mdsmap, *debugfs_osdmap;
-        struct dentry *debugfs_dir, *debugfs_dentry_lru, *debugfs_caps;
+        struct dentry *debugfs_dentry_lru, *debugfs_caps;
         struct dentry *debugfs_congestion_kb;
         struct dentry *debugfs_bdi;
+        struct dentry *debugfs_mdsc, *debugfs_mdsmap;
 #endif
 };
 
+
 /*
  * File i/o capability.  This tracks shared state with the metadata
  * server that allows us to cache or writeback attributes or to read
@@ -275,6 +195,20 @@ struct ceph_inode_xattr {
         int should_free_val;
 };
 
+/*
+ * Ceph dentry state
+ */
+struct ceph_dentry_info {
+        struct ceph_mds_session *lease_session;
+        u32 lease_gen, lease_shared_gen;
+        u32 lease_seq;
+        unsigned long lease_renew_after, lease_renew_from;
+        struct list_head lru;
+        struct dentry *dentry;
+        u64 time;
+        u64 offset;
+};
+
 struct ceph_inode_xattrs_info {
         /*
          * (still encoded) xattr blob. we avoid the overhead of parsing
@@ -296,11 +230,6 @@ struct ceph_inode_xattrs_info {
 /*
  * Ceph inode.
  */
-#define CEPH_I_COMPLETE  1  /* we have complete directory cached */
-#define CEPH_I_NODELAY   4  /* do not delay cap release */
-#define CEPH_I_FLUSH     8  /* do not delay flush of dirty metadata */
-#define CEPH_I_NOFLUSH  16  /* do not flush dirty caps */
-
 struct ceph_inode_info {
         struct ceph_vino i_vino;   /* ceph ino + snap */
 
@@ -391,6 +320,63 @@ static inline struct ceph_inode_info *ceph_inode(struct inode *inode)
         return container_of(inode, struct ceph_inode_info, vfs_inode);
 }
 
+static inline struct ceph_vino ceph_vino(struct inode *inode)
+{
+        return ceph_inode(inode)->i_vino;
+}
+
+/*
+ * ino_t is <64 bits on many architectures, blech.
+ *
+ * don't include snap in ino hash, at least for now.
+ */
+static inline ino_t ceph_vino_to_ino(struct ceph_vino vino)
+{
+        ino_t ino = (ino_t)vino.ino;  /* ^ (vino.snap << 20); */
+#if BITS_PER_LONG == 32
+        ino ^= vino.ino >> (sizeof(u64)-sizeof(ino_t)) * 8;
+        if (!ino)
+                ino = 1;
+#endif
+        return ino;
+}
+
+/* for printf-style formatting */
+#define ceph_vinop(i) ceph_inode(i)->i_vino.ino, ceph_inode(i)->i_vino.snap
+
+static inline u64 ceph_ino(struct inode *inode)
+{
+        return ceph_inode(inode)->i_vino.ino;
+}
+static inline u64 ceph_snap(struct inode *inode)
+{
+        return ceph_inode(inode)->i_vino.snap;
+}
+
+static inline int ceph_ino_compare(struct inode *inode, void *data)
+{
+        struct ceph_vino *pvino = (struct ceph_vino *)data;
+        struct ceph_inode_info *ci = ceph_inode(inode);
+        return ci->i_vino.ino == pvino->ino &&
+                ci->i_vino.snap == pvino->snap;
+}
+
+static inline struct inode *ceph_find_inode(struct super_block *sb,
+                                            struct ceph_vino vino)
+{
+        ino_t t = ceph_vino_to_ino(vino);
+        return ilookup5(sb, t, ceph_ino_compare, &vino);
+}
+
+
+/*
+ * Ceph inode.
+ */
+#define CEPH_I_COMPLETE  1  /* we have complete directory cached */
+#define CEPH_I_NODELAY   4  /* do not delay cap release */
+#define CEPH_I_FLUSH     8  /* do not delay flush of dirty metadata */
+#define CEPH_I_NOFLUSH  16  /* do not flush dirty caps */
+
 static inline void ceph_i_clear(struct inode *inode, unsigned mask)
 {
         struct ceph_inode_info *ci = ceph_inode(inode);
@@ -414,8 +400,9 @@ static inline bool ceph_i_test(struct inode *inode, unsigned mask)
         struct ceph_inode_info *ci = ceph_inode(inode);
         bool r;
 
-        smp_mb();
+        spin_lock(&inode->i_lock);
         r = (ci->i_ceph_flags & mask) == mask;
+        spin_unlock(&inode->i_lock);
         return r;
 }
 
@@ -432,20 +419,6 @@ extern u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v,
                             struct ceph_inode_frag *pfrag,
                             int *found);
 
-/*
- * Ceph dentry state
- */
-struct ceph_dentry_info {
-        struct ceph_mds_session *lease_session;
-        u32 lease_gen, lease_shared_gen;
-        u32 lease_seq;
-        unsigned long lease_renew_after, lease_renew_from;
-        struct list_head lru;
-        struct dentry *dentry;
-        u64 time;
-        u64 offset;
-};
-
 static inline struct ceph_dentry_info *ceph_dentry(struct dentry *dentry)
 {
         return (struct ceph_dentry_info *)dentry->d_fsdata;
@@ -456,22 +429,6 @@ static inline loff_t ceph_make_fpos(unsigned frag, unsigned off)
         return ((loff_t)frag << 32) | (loff_t)off;
 }
 
-/*
- * ino_t is <64 bits on many architectures, blech.
- *
- * don't include snap in ino hash, at least for now.
- */
-static inline ino_t ceph_vino_to_ino(struct ceph_vino vino)
-{
-        ino_t ino = (ino_t)vino.ino;  /* ^ (vino.snap << 20); */
-#if BITS_PER_LONG == 32
-        ino ^= vino.ino >> (sizeof(u64)-sizeof(ino_t)) * 8;
-        if (!ino)
-                ino = 1;
-#endif
-        return ino;
-}
-
 static inline int ceph_set_ino_cb(struct inode *inode, void *data)
 {
         ceph_inode(inode)->i_vino = *(struct ceph_vino *)data;
@@ -479,39 +436,6 @@ static inline int ceph_set_ino_cb(struct inode *inode, void *data)
         return 0;
 }
 
-static inline struct ceph_vino ceph_vino(struct inode *inode)
-{
-        return ceph_inode(inode)->i_vino;
-}
-
-/* for printf-style formatting */
-#define ceph_vinop(i) ceph_inode(i)->i_vino.ino, ceph_inode(i)->i_vino.snap
-
-static inline u64 ceph_ino(struct inode *inode)
-{
-        return ceph_inode(inode)->i_vino.ino;
-}
-static inline u64 ceph_snap(struct inode *inode)
-{
-        return ceph_inode(inode)->i_vino.snap;
-}
-
-static inline int ceph_ino_compare(struct inode *inode, void *data)
-{
-        struct ceph_vino *pvino = (struct ceph_vino *)data;
-        struct ceph_inode_info *ci = ceph_inode(inode);
-        return ci->i_vino.ino == pvino->ino &&
-                ci->i_vino.snap == pvino->snap;
-}
-
-static inline struct inode *ceph_find_inode(struct super_block *sb,
-                                            struct ceph_vino vino)
-{
-        ino_t t = ceph_vino_to_ino(vino);
-        return ilookup5(sb, t, ceph_ino_compare, &vino);
-}
-
-
 /*
  * caps helpers
  */
@@ -576,18 +500,18 @@ extern int ceph_reserve_caps(struct ceph_mds_client *mdsc,
                              struct ceph_cap_reservation *ctx, int need);
 extern int ceph_unreserve_caps(struct ceph_mds_client *mdsc,
                                struct ceph_cap_reservation *ctx);
-extern void ceph_reservation_status(struct ceph_client *client,
+extern void ceph_reservation_status(struct ceph_fs_client *client,
                                     int *total, int *avail, int *used,
                                     int *reserved, int *min);
 
-static inline struct ceph_client *ceph_inode_to_client(struct inode *inode)
+static inline struct ceph_fs_client *ceph_inode_to_client(struct inode *inode)
 {
-        return (struct ceph_client *)inode->i_sb->s_fs_info;
+        return (struct ceph_fs_client *)inode->i_sb->s_fs_info;
 }
 
-static inline struct ceph_client *ceph_sb_to_client(struct super_block *sb)
+static inline struct ceph_fs_client *ceph_sb_to_client(struct super_block *sb)
 {
-        return (struct ceph_client *)sb->s_fs_info;
+        return (struct ceph_fs_client *)sb->s_fs_info;
 }
 
 
@@ -617,51 +541,6 @@ struct ceph_file_info {
 
 
 /*
- * snapshots
- */
-
-/*
- * A "snap context" is the set of existing snapshots when we
- * write data.  It is used by the OSD to guide its COW behavior.
- *
- * The ceph_snap_context is refcounted, and attached to each dirty
- * page, indicating which context the dirty data belonged when it was
- * dirtied.
- */
-struct ceph_snap_context {
-        atomic_t nref;
-        u64 seq;
-        int num_snaps;
-        u64 snaps[];
-};
-
-static inline struct ceph_snap_context *
-ceph_get_snap_context(struct ceph_snap_context *sc)
-{
-        /*
-        printk("get_snap_context %p %d -> %d\n", sc, atomic_read(&sc->nref),
-               atomic_read(&sc->nref)+1);
-        */
-        if (sc)
-                atomic_inc(&sc->nref);
-        return sc;
-}
-
-static inline void ceph_put_snap_context(struct ceph_snap_context *sc)
-{
-        if (!sc)
-                return;
-        /*
-        printk("put_snap_context %p %d -> %d\n", sc, atomic_read(&sc->nref),
-               atomic_read(&sc->nref)-1);
-        */
-        if (atomic_dec_and_test(&sc->nref)) {
-                /*printk(" deleting snap_context %p\n", sc);*/
-                kfree(sc);
-        }
-}
-
-/*
  * A "snap realm" describes a subset of the file hierarchy sharing
  * the same set of snapshots that apply to it.  The realms themselves
  * are organized into a hierarchy, such that children inherit (some of)
@@ -699,16 +578,33 @@ struct ceph_snap_realm {
         spinlock_t inodes_with_caps_lock;
 };
 
-
-
-/*
- * calculate the number of pages a given length and offset map onto,
- * if we align the data.
- */
-static inline int calc_pages_for(u64 off, u64 len)
+static inline int default_congestion_kb(void)
 {
-        return ((off+len+PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT) -
-                (off >> PAGE_CACHE_SHIFT);
+        int congestion_kb;
+
+        /*
+         * Copied from NFS
+         *
+         * congestion size, scale with available memory.
+         *
+         *  64MB:    8192k
+         * 128MB:   11585k
+         * 256MB:   16384k
+         * 512MB:   23170k
+         *   1GB:   32768k
+         *   2GB:   46340k
+         *   4GB:   65536k
+         *   8GB:   92681k
+         *  16GB:  131072k
+         *
+         * This allows larger machines to have larger/more transfers.
+         * Limit the default to 256M
+         */
+        congestion_kb = (16*int_sqrt(totalram_pages)) << (PAGE_SHIFT-10);
+        if (congestion_kb > 256*1024)
+                congestion_kb = 256*1024;
+
+        return congestion_kb;
 }
 
 
@@ -741,16 +637,6 @@ static inline bool __ceph_have_pending_cap_snap(struct ceph_inode_info *ci)
                            ci_item)->writing;
 }
 
-
-/* super.c */
-extern struct kmem_cache *ceph_inode_cachep;
-extern struct kmem_cache *ceph_cap_cachep;
-extern struct kmem_cache *ceph_dentry_cachep;
-extern struct kmem_cache *ceph_file_cachep;
-
-extern const char *ceph_msg_type_name(int type);
-extern int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid);
-
 /* inode.c */
 extern const struct inode_operations ceph_file_iops;
 
@@ -857,12 +743,18 @@ extern int ceph_mmap(struct file *file, struct vm_area_struct *vma);
 /* file.c */
 extern const struct file_operations ceph_file_fops;
 extern const struct address_space_operations ceph_aops;
+extern int ceph_copy_to_page_vector(struct page **pages,
+                                    const char *data,
+                                    loff_t off, size_t len);
+extern int ceph_copy_from_page_vector(struct page **pages,
+                                    char *data,
+                                    loff_t off, size_t len);
+extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags);
 extern int ceph_open(struct inode *inode, struct file *file);
 extern struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry,
                                        struct nameidata *nd, int mode,
                                        int locked_dir);
 extern int ceph_release(struct inode *inode, struct file *filp);
-extern void ceph_release_page_vector(struct page **pages, int num_pages);
 
 /* dir.c */
 extern const struct file_operations ceph_dir_fops;
@@ -892,12 +784,6 @@ extern long ceph_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 /* export.c */
 extern const struct export_operations ceph_export_ops;
 
-/* debugfs.c */
-extern int ceph_debugfs_init(void);
-extern void ceph_debugfs_cleanup(void);
-extern int ceph_debugfs_client_init(struct ceph_client *client);
-extern void ceph_debugfs_client_cleanup(struct ceph_client *client);
-
 /* locks.c */
 extern int ceph_lock(struct file *file, int cmd, struct file_lock *fl);
 extern int ceph_flock(struct file *file, int cmd, struct file_lock *fl);
@@ -914,4 +800,8 @@ static inline struct inode *get_dentry_parent_inode(struct dentry *dentry)
         return NULL;
 }
 
+/* debugfs.c */
+extern int ceph_fs_debugfs_init(struct ceph_fs_client *client);
+extern void ceph_fs_debugfs_cleanup(struct ceph_fs_client *client);
+
 #endif /* _FS_CEPH_SUPER_H */
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 9578af610b73..6e12a6ba5f79 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -1,6 +1,9 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
+
 #include "super.h"
-#include "decode.h"
+#include "mds_client.h"
+
+#include <linux/ceph/decode.h>
 
 #include <linux/xattr.h>
 #include <linux/slab.h>
@@ -620,12 +623,12 @@ out:
 static int ceph_sync_setxattr(struct dentry *dentry, const char *name,
                               const char *value, size_t size, int flags)
 {
-        struct ceph_client *client = ceph_sb_to_client(dentry->d_sb);
+        struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
         struct inode *inode = dentry->d_inode;
         struct ceph_inode_info *ci = ceph_inode(inode);
         struct inode *parent_inode = dentry->d_parent->d_inode;
         struct ceph_mds_request *req;
-        struct ceph_mds_client *mdsc = &client->mdsc;
+        struct ceph_mds_client *mdsc = fsc->mdsc;
         int err;
         int i, nr_pages;
         struct page **pages = NULL;
@@ -713,10 +716,9 @@ int ceph_setxattr(struct dentry *dentry, const char *name,
 
         /* preallocate memory for xattr name, value, index node */
         err = -ENOMEM;
-        newname = kmalloc(name_len + 1, GFP_NOFS);
+        newname = kmemdup(name, name_len + 1, GFP_NOFS);
         if (!newname)
                 goto out;
-        memcpy(newname, name, name_len + 1);
 
         if (val_len) {
                 newval = kmalloc(val_len + 1, GFP_NOFS);
@@ -777,8 +779,8 @@ out:
 
 static int ceph_send_removexattr(struct dentry *dentry, const char *name)
 {
-        struct ceph_client *client = ceph_sb_to_client(dentry->d_sb);
-        struct ceph_mds_client *mdsc = &client->mdsc;
+        struct ceph_fs_client *fsc = ceph_sb_to_client(dentry->d_sb);
+        struct ceph_mds_client *mdsc = fsc->mdsc;
         struct inode *inode = dentry->d_inode;
         struct inode *parent_inode = dentry->d_parent->d_inode;
         struct ceph_mds_request *req;
diff --git a/fs/gfs2/Kconfig b/fs/gfs2/Kconfig
index cc9665522148..c465ae066c62 100644
--- a/fs/gfs2/Kconfig
+++ b/fs/gfs2/Kconfig
@@ -1,6 +1,6 @@
 config GFS2_FS
         tristate "GFS2 file system support"
-        depends on EXPERIMENTAL && (64BIT || LBDAF)
+        depends on (64BIT || LBDAF)
         select DLM if GFS2_FS_LOCKING_DLM
         select CONFIGFS_FS if GFS2_FS_LOCKING_DLM
         select SYSFS if GFS2_FS_LOCKING_DLM
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 194fe16d8418..6b24afb96aae 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -36,8 +36,8 @@
 #include "glops.h"
 
 
-static void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page,
-                                   unsigned int from, unsigned int to)
+void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page,
+                            unsigned int from, unsigned int to)
 {
         struct buffer_head *head = page_buffers(page);
         unsigned int bsize = head->b_size;
@@ -615,7 +615,7 @@ static int gfs2_write_begin(struct file *file, struct address_space *mapping,
         unsigned int data_blocks = 0, ind_blocks = 0, rblocks;
         int alloc_required;
         int error = 0;
-        struct gfs2_alloc *al;
+        struct gfs2_alloc *al = NULL;
         pgoff_t index = pos >> PAGE_CACHE_SHIFT;
         unsigned from = pos & (PAGE_CACHE_SIZE - 1);
         unsigned to = from + len;
@@ -663,6 +663,8 @@ static int gfs2_write_begin(struct file *file, struct address_space *mapping,
                 rblocks += RES_STATFS + RES_QUOTA;
         if (&ip->i_inode == sdp->sd_rindex)
                 rblocks += 2 * RES_STATFS;
+        if (alloc_required)
+                rblocks += gfs2_rg_blocks(al);
 
         error = gfs2_trans_begin(sdp, rblocks,
                                  PAGE_CACHE_SIZE/sdp->sd_sb.sb_bsize);
@@ -696,13 +698,11 @@ out:
 
         page_cache_release(page);
 
-        /*
-         * XXX(truncate): the call below should probably be replaced with
-         * a call to the gfs2-specific truncate blocks helper to actually
-         * release disk blocks..
-         */
+        gfs2_trans_end(sdp);
         if (pos + len > ip->i_inode.i_size)
-                truncate_setsize(&ip->i_inode, ip->i_inode.i_size);
+                gfs2_trim_blocks(&ip->i_inode);
+        goto out_trans_fail;
+
 out_endtrans:
         gfs2_trans_end(sdp);
 out_trans_fail:
@@ -802,10 +802,8 @@ static int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
         page_cache_release(page);
 
         if (copied) {
-                if (inode->i_size < to) {
+                if (inode->i_size < to)
                         i_size_write(inode, to);
-                        ip->i_disksize = inode->i_size;
-                }
                 gfs2_dinode_out(ip, di);
                 mark_inode_dirty(inode);
         }
@@ -876,8 +874,6 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping,
 
         ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
         if (ret > 0) {
-                if (inode->i_size > ip->i_disksize)
-                        ip->i_disksize = inode->i_size;
                 gfs2_dinode_out(ip, dibh->b_data);
                 mark_inode_dirty(inode);
         }
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 6f482809d1a3..5476c066d4ee 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -50,7 +50,7 @@ struct strip_mine {
  * @ip: the inode
  * @dibh: the dinode buffer
  * @block: the block number that was allocated
- * @private: any locked page held by the caller process
+ * @page: The (optional) page. This is looked up if @page is NULL
  *
  * Returns: errno
  */
@@ -109,8 +109,7 @@ static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh,
 /**
  * gfs2_unstuff_dinode - Unstuff a dinode when the data has grown too big
  * @ip: The GFS2 inode to unstuff
- * @unstuffer: the routine that handles unstuffing a non-zero length file
- * @private: private data for the unstuffer
+ * @page: The (optional) page. This is looked up if the @page is NULL
  *
  * This routine unstuffs a dinode and returns it to a "normal" state such
  * that the height can be grown in the traditional way.
@@ -132,7 +131,7 @@ int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page)
         if (error)
                 goto out;
 
-        if (ip->i_disksize) {
+        if (i_size_read(&ip->i_inode)) {
                 /* Get a free block, fill it with the stuffed data,
                    and write it out to disk */
 
@@ -161,7 +160,7 @@ int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page)
         di = (struct gfs2_dinode *)dibh->b_data;
         gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode));
 
-        if (ip->i_disksize) {
+        if (i_size_read(&ip->i_inode)) {
                 *(__be64 *)(di + 1) = cpu_to_be64(block);
                 gfs2_add_inode_blocks(&ip->i_inode, 1);
                 di->di_blocks = cpu_to_be64(gfs2_get_inode_blocks(&ip->i_inode));
@@ -885,83 +884,14 @@ out:
 }
 
 /**
- * do_grow - Make a file look bigger than it is
- * @ip: the inode
- * @size: the size to set the file to
- *
- * Called with an exclusive lock on @ip.
- *
- * Returns: errno
- */
-
-static int do_grow(struct gfs2_inode *ip, u64 size)
-{
-        struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-        struct gfs2_alloc *al;
-        struct buffer_head *dibh;
-        int error;
-
-        al = gfs2_alloc_get(ip);
-        if (!al)
-                return -ENOMEM;
-
-        error = gfs2_quota_lock_check(ip);
-        if (error)
-                goto out;
-
-        al->al_requested = sdp->sd_max_height + RES_DATA;
-
-        error = gfs2_inplace_reserve(ip);
-        if (error)
-                goto out_gunlock_q;
-
-        error = gfs2_trans_begin(sdp,
-                        sdp->sd_max_height + al->al_rgd->rd_length +
-                        RES_JDATA + RES_DINODE + RES_STATFS + RES_QUOTA, 0);
-        if (error)
-                goto out_ipres;
-
-        error = gfs2_meta_inode_buffer(ip, &dibh);
-        if (error)
-                goto out_end_trans;
-
-        if (size > sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode)) {
-                if (gfs2_is_stuffed(ip)) {
-                        error = gfs2_unstuff_dinode(ip, NULL);
-                        if (error)
-                                goto out_brelse;
-                }
-        }
-
-        ip->i_disksize = size;
-        ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
-        gfs2_trans_add_bh(ip->i_gl, dibh, 1);
-        gfs2_dinode_out(ip, dibh->b_data);
-
-out_brelse:
-        brelse(dibh);
-out_end_trans:
-        gfs2_trans_end(sdp);
-out_ipres:
-        gfs2_inplace_release(ip);
-out_gunlock_q:
-        gfs2_quota_unlock(ip);
-out:
-        gfs2_alloc_put(ip);
-        return error;
-}
-
-
-/**
  * gfs2_block_truncate_page - Deal with zeroing out data for truncate
  *
  * This is partly borrowed from ext3.
  */
-static int gfs2_block_truncate_page(struct address_space *mapping)
+static int gfs2_block_truncate_page(struct address_space *mapping, loff_t from)
 {
         struct inode *inode = mapping->host;
         struct gfs2_inode *ip = GFS2_I(inode);
-        loff_t from = inode->i_size;
         unsigned long index = from >> PAGE_CACHE_SHIFT;
         unsigned offset = from & (PAGE_CACHE_SIZE-1);
         unsigned blocksize, iblock, length, pos;
@@ -1023,9 +953,11 @@ unlock:
         return err;
 }
 
-static int trunc_start(struct gfs2_inode *ip, u64 size)
+static int trunc_start(struct inode *inode, u64 oldsize, u64 newsize)
 {
-        struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+        struct gfs2_inode *ip = GFS2_I(inode);
+        struct gfs2_sbd *sdp = GFS2_SB(inode);
+        struct address_space *mapping = inode->i_mapping;
         struct buffer_head *dibh;
         int journaled = gfs2_is_jdata(ip);
         int error;
@@ -1039,31 +971,26 @@ static int trunc_start(struct gfs2_inode *ip, u64 size)
         if (error)
                 goto out;
 
+        gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+
         if (gfs2_is_stuffed(ip)) {
-                u64 dsize = size + sizeof(struct gfs2_dinode);
-                ip->i_disksize = size;
-                ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
-                gfs2_trans_add_bh(ip->i_gl, dibh, 1);
-                gfs2_dinode_out(ip, dibh->b_data);
-                if (dsize > dibh->b_size)
-                        dsize = dibh->b_size;
-                gfs2_buffer_clear_tail(dibh, dsize);
-                error = 1;
+                gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode) + newsize);
         } else {
-                if (size & (u64)(sdp->sd_sb.sb_bsize - 1))
-                        error = gfs2_block_truncate_page(ip->i_inode.i_mapping);
-
-                if (!error) {
-                        ip->i_disksize = size;
-                        ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
-                        ip->i_diskflags |= GFS2_DIF_TRUNC_IN_PROG;
-                        gfs2_trans_add_bh(ip->i_gl, dibh, 1);
-                        gfs2_dinode_out(ip, dibh->b_data);
+                if (newsize & (u64)(sdp->sd_sb.sb_bsize - 1)) {
+                        error = gfs2_block_truncate_page(mapping, newsize);
+                        if (error)
+                                goto out_brelse;
                 }
+                ip->i_diskflags |= GFS2_DIF_TRUNC_IN_PROG;
         }
 
-        brelse(dibh);
+        i_size_write(inode, newsize);
+        ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
+        gfs2_dinode_out(ip, dibh->b_data);
 
+        truncate_pagecache(inode, oldsize, newsize);
+out_brelse:
+        brelse(dibh);
 out:
         gfs2_trans_end(sdp);
         return error;
@@ -1123,7 +1050,7 @@ static int trunc_end(struct gfs2_inode *ip)
         if (error)
                 goto out;
 
-        if (!ip->i_disksize) {
+        if (!i_size_read(&ip->i_inode)) {
                 ip->i_height = 0;
                 ip->i_goal = ip->i_no_addr;
                 gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode));
@@ -1143,92 +1070,154 @@ out:
 
 /**
  * do_shrink - make a file smaller
- * @ip: the inode
- * @size: the size to make the file
- * @truncator: function to truncate the last partial block
+ * @inode: the inode
+ * @oldsize: the current inode size
+ * @newsize: the size to make the file
  *
- * Called with an exclusive lock on @ip.
+ * Called with an exclusive lock on @inode. The @size must
+ * be equal to or smaller than the current inode size.
  *
  * Returns: errno
  */
 
-static int do_shrink(struct gfs2_inode *ip, u64 size)
+static int do_shrink(struct inode *inode, u64 oldsize, u64 newsize)
 {
+        struct gfs2_inode *ip = GFS2_I(inode);
         int error;
 
-        error = trunc_start(ip, size);
+        error = trunc_start(inode, oldsize, newsize);
         if (error < 0)
                 return error;
-        if (error > 0)
+        if (gfs2_is_stuffed(ip))
                 return 0;
 
-        error = trunc_dealloc(ip, size);
-        if (!error)
+        error = trunc_dealloc(ip, newsize);
+        if (error == 0)
                 error = trunc_end(ip);
 
         return error;
 }
 
-static int do_touch(struct gfs2_inode *ip, u64 size)
+void gfs2_trim_blocks(struct inode *inode)
 {
-        struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+        u64 size = inode->i_size;
+        int ret;
+
+        ret = do_shrink(inode, size, size);
+        WARN_ON(ret != 0);
+}
+
+/**
+ * do_grow - Touch and update inode size
+ * @inode: The inode
+ * @size: The new size
+ *
+ * This function updates the timestamps on the inode and
+ * may also increase the size of the inode. This function
+ * must not be called with @size any smaller than the current
+ * inode size.
+ *
+ * Although it is not strictly required to unstuff files here,
+ * earlier versions of GFS2 have a bug in the stuffed file reading
+ * code which will result in a buffer overrun if the size is larger
+ * than the max stuffed file size. In order to prevent this from
+ * occuring, such files are unstuffed, but in other cases we can
+ * just update the inode size directly.
+ *
+ * Returns: 0 on success, or -ve on error
+ */
+
+static int do_grow(struct inode *inode, u64 size)
+{
+        struct gfs2_inode *ip = GFS2_I(inode);
+        struct gfs2_sbd *sdp = GFS2_SB(inode);
         struct buffer_head *dibh;
+        struct gfs2_alloc *al = NULL;
         int error;
 
-        error = gfs2_trans_begin(sdp, RES_DINODE, 0);
+        if (gfs2_is_stuffed(ip) &&
+            (size > (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode)))) {
+                al = gfs2_alloc_get(ip);
+                if (al == NULL)
+                        return -ENOMEM;
+
+                error = gfs2_quota_lock_check(ip);
+                if (error)
+                        goto do_grow_alloc_put;
+
+                al->al_requested = 1;
+                error = gfs2_inplace_reserve(ip);
+                if (error)
+                        goto do_grow_qunlock;
+        }
+
+        error = gfs2_trans_begin(sdp, RES_DINODE + RES_STATFS + RES_RG_BIT, 0);
         if (error)
-                return error;
+                goto do_grow_release;
 
-        down_write(&ip->i_rw_mutex);
+        if (al) {
+                error = gfs2_unstuff_dinode(ip, NULL);
+                if (error)
+                        goto do_end_trans;
+        }
 
         error = gfs2_meta_inode_buffer(ip, &dibh);
         if (error)
-                goto do_touch_out;
+                goto do_end_trans;
 
+        i_size_write(inode, size);
         ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
         gfs2_trans_add_bh(ip->i_gl, dibh, 1);
         gfs2_dinode_out(ip, dibh->b_data);
         brelse(dibh);
 
-do_touch_out:
-        up_write(&ip->i_rw_mutex);
+do_end_trans:
         gfs2_trans_end(sdp);
+do_grow_release:
+        if (al) {
+                gfs2_inplace_release(ip);
+do_grow_qunlock:
+                gfs2_quota_unlock(ip);
+do_grow_alloc_put:
+                gfs2_alloc_put(ip);
+        }
         return error;
 }
 
 /**
- * gfs2_truncatei - make a file a given size
- * @ip: the inode
- * @size: the size to make the file
- * @truncator: function to truncate the last partial block
+ * gfs2_setattr_size - make a file a given size
+ * @inode: the inode
+ * @newsize: the size to make the file
  *
- * The file size can grow, shrink, or stay the same size.
+ * The file size can grow, shrink, or stay the same size. This
+ * is called holding i_mutex and an exclusive glock on the inode
+ * in question.
  *
  * Returns: errno
  */
 
-int gfs2_truncatei(struct gfs2_inode *ip, u64 size)
+int gfs2_setattr_size(struct inode *inode, u64 newsize)
 {
-        int error;
+        int ret;
+        u64 oldsize;
 
-        if (gfs2_assert_warn(GFS2_SB(&ip->i_inode), S_ISREG(ip->i_inode.i_mode)))
-                return -EINVAL;
+        BUG_ON(!S_ISREG(inode->i_mode));
 
-        if (size > ip->i_disksize)
-                error = do_grow(ip, size);
-        else if (size < ip->i_disksize)
-                error = do_shrink(ip, size);
-        else
-                /* update time stamps */
-                error = do_touch(ip, size);
+        ret = inode_newsize_ok(inode, newsize);
+        if (ret)
+                return ret;
 
-        return error;
+        oldsize = inode->i_size;
+        if (newsize >= oldsize)
+                return do_grow(inode, newsize);
+
+        return do_shrink(inode, oldsize, newsize);
 }
 
 int gfs2_truncatei_resume(struct gfs2_inode *ip)
 {
         int error;
-        error = trunc_dealloc(ip, ip->i_disksize);
+        error = trunc_dealloc(ip, i_size_read(&ip->i_inode));
         if (!error)
                 error = trunc_end(ip);
         return error;
@@ -1269,7 +1258,7 @@ int gfs2_write_alloc_required(struct gfs2_inode *ip, u64 offset,
 
         shift = sdp->sd_sb.sb_bsize_shift;
         BUG_ON(gfs2_is_dir(ip));
-        end_of_file = (ip->i_disksize + sdp->sd_sb.sb_bsize - 1) >> shift;
+        end_of_file = (i_size_read(&ip->i_inode) + sdp->sd_sb.sb_bsize - 1) >> shift;
         lblock = offset >> shift;
         lblock_stop = (offset + len + sdp->sd_sb.sb_bsize - 1) >> shift;
         if (lblock_stop > end_of_file)
diff --git a/fs/gfs2/bmap.h b/fs/gfs2/bmap.h
index a20a5213135a..42fea03e2bd9 100644
--- a/fs/gfs2/bmap.h
+++ b/fs/gfs2/bmap.h
@@ -44,14 +44,16 @@ static inline void gfs2_write_calc_reserv(const struct gfs2_inode *ip,
         }
 }
 
-int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page);
-int gfs2_block_map(struct inode *inode, sector_t lblock, struct buffer_head *bh, int create);
-int gfs2_extent_map(struct inode *inode, u64 lblock, int *new, u64 *dblock, unsigned *extlen);
-
-int gfs2_truncatei(struct gfs2_inode *ip, u64 size);
-int gfs2_truncatei_resume(struct gfs2_inode *ip);
-int gfs2_file_dealloc(struct gfs2_inode *ip);
-int gfs2_write_alloc_required(struct gfs2_inode *ip, u64 offset,
-                              unsigned int len);
+extern int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page);
+extern int gfs2_block_map(struct inode *inode, sector_t lblock,
+                          struct buffer_head *bh, int create);
+extern int gfs2_extent_map(struct inode *inode, u64 lblock, int *new,
+                           u64 *dblock, unsigned *extlen);
+extern int gfs2_setattr_size(struct inode *inode, u64 size);
+extern void gfs2_trim_blocks(struct inode *inode);
+extern int gfs2_truncatei_resume(struct gfs2_inode *ip);
+extern int gfs2_file_dealloc(struct gfs2_inode *ip);
+extern int gfs2_write_alloc_required(struct gfs2_inode *ip, u64 offset,
+                                     unsigned int len);
 
 #endif /* __BMAP_DOT_H__ */
diff --git a/fs/gfs2/dentry.c b/fs/gfs2/dentry.c
index bb7907bde3d8..6798755b3858 100644
--- a/fs/gfs2/dentry.c
+++ b/fs/gfs2/dentry.c
@@ -49,7 +49,7 @@ static int gfs2_drevalidate(struct dentry *dentry, struct nameidata *nd)
                 ip = GFS2_I(inode);
         }
 
-        if (sdp->sd_args.ar_localcaching)
+        if (sdp->sd_lockstruct.ls_ops->lm_mount == NULL)
                 goto valid;
 
         had_lock = (gfs2_glock_is_locked_by_me(dip->i_gl) != NULL);
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index b9dd88a78dd4..5c356d09c321 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -79,6 +79,9 @@
 #define gfs2_disk_hash2offset(h) (((u64)(h)) >> 1)
 #define gfs2_dir_offset2hash(p) ((u32)(((u64)(p)) << 1))
 
+struct qstr gfs2_qdot __read_mostly;
+struct qstr gfs2_qdotdot __read_mostly;
+
 typedef int (*leaf_call_t) (struct gfs2_inode *dip, u32 index, u32 len,
                             u64 leaf_no, void *data);
 typedef int (*gfs2_dscan_t)(const struct gfs2_dirent *dent,
@@ -127,8 +130,8 @@ static int gfs2_dir_write_stuffed(struct gfs2_inode *ip, const char *buf,
 
         gfs2_trans_add_bh(ip->i_gl, dibh, 1);
         memcpy(dibh->b_data + offset + sizeof(struct gfs2_dinode), buf, size);
-        if (ip->i_disksize < offset + size)
-                ip->i_disksize = offset + size;
+        if (ip->i_inode.i_size < offset + size)
+                i_size_write(&ip->i_inode, offset + size);
         ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
         gfs2_dinode_out(ip, dibh->b_data);
 
@@ -225,8 +228,8 @@ out:
         if (error)
                 return error;
 
-        if (ip->i_disksize < offset + copied)
-                ip->i_disksize = offset + copied;
+        if (ip->i_inode.i_size < offset + copied)
+                i_size_write(&ip->i_inode, offset + copied);
         ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
 
         gfs2_trans_add_bh(ip->i_gl, dibh, 1);
@@ -275,12 +278,13 @@ static int gfs2_dir_read_data(struct gfs2_inode *ip, char *buf, u64 offset,
         unsigned int o;
         int copied = 0;
         int error = 0;
+        u64 disksize = i_size_read(&ip->i_inode);
 
-        if (offset >= ip->i_disksize)
+        if (offset >= disksize)
                 return 0;
 
-        if (offset + size > ip->i_disksize)
-                size = ip->i_disksize - offset;
+        if (offset + size > disksize)
+                size = disksize - offset;
 
         if (!size)
                 return 0;
@@ -727,7 +731,7 @@ static struct gfs2_dirent *gfs2_dirent_search(struct inode *inode,
                 unsigned hsize = 1 << ip->i_depth;
                 unsigned index;
                 u64 ln;
-                if (hsize * sizeof(u64) != ip->i_disksize) {
+                if (hsize * sizeof(u64) != i_size_read(inode)) {
                         gfs2_consist_inode(ip);
                         return ERR_PTR(-EIO);
                 }
@@ -879,7 +883,7 @@ static int dir_make_exhash(struct inode *inode)
         for (x = sdp->sd_hash_ptrs; x--; lp++)
                 *lp = cpu_to_be64(bn);
 
-        dip->i_disksize = sdp->sd_sb.sb_bsize / 2;
+        i_size_write(inode, sdp->sd_sb.sb_bsize / 2);
         gfs2_add_inode_blocks(&dip->i_inode, 1);
         dip->i_diskflags |= GFS2_DIF_EXHASH;
 
@@ -1057,11 +1061,12 @@ static int dir_double_exhash(struct gfs2_inode *dip)
         u64 *buf;
         u64 *from, *to;
         u64 block;
+        u64 disksize = i_size_read(&dip->i_inode);
         int x;
         int error = 0;
 
         hsize = 1 << dip->i_depth;
-        if (hsize * sizeof(u64) != dip->i_disksize) {
+        if (hsize * sizeof(u64) != disksize) {
                 gfs2_consist_inode(dip);
                 return -EIO;
         }
@@ -1072,7 +1077,7 @@ static int dir_double_exhash(struct gfs2_inode *dip)
         if (!buf)
                 return -ENOMEM;
 
-        for (block = dip->i_disksize >> sdp->sd_hash_bsize_shift; block--;) {
+        for (block = disksize >> sdp->sd_hash_bsize_shift; block--;) {
                 error = gfs2_dir_read_data(dip, (char *)buf,
                                             block * sdp->sd_hash_bsize,
                                             sdp->sd_hash_bsize, 1);
@@ -1370,7 +1375,7 @@ static int dir_e_read(struct inode *inode, u64 *offset, void *opaque,
         unsigned depth = 0;
 
         hsize = 1 << dip->i_depth;
-        if (hsize * sizeof(u64) != dip->i_disksize) {
+        if (hsize * sizeof(u64) != i_size_read(inode)) {
                 gfs2_consist_inode(dip);
                 return -EIO;
         }
@@ -1784,7 +1789,7 @@ static int foreach_leaf(struct gfs2_inode *dip, leaf_call_t lc, void *data)
         int error = 0;
 
         hsize = 1 << dip->i_depth;
-        if (hsize * sizeof(u64) != dip->i_disksize) {
+        if (hsize * sizeof(u64) != i_size_read(&dip->i_inode)) {
                 gfs2_consist_inode(dip);
                 return -EIO;
         }
diff --git a/fs/gfs2/dir.h b/fs/gfs2/dir.h
index 4f919440c3be..a98f644bd3df 100644
--- a/fs/gfs2/dir.h
+++ b/fs/gfs2/dir.h
@@ -17,23 +17,24 @@ struct inode;
 struct gfs2_inode;
 struct gfs2_inum;
 
-struct inode *gfs2_dir_search(struct inode *dir, const struct qstr *filename);
-int gfs2_dir_check(struct inode *dir, const struct qstr *filename,
-                   const struct gfs2_inode *ip);
-int gfs2_dir_add(struct inode *inode, const struct qstr *filename,
-                 const struct gfs2_inode *ip, unsigned int type);
-int gfs2_dir_del(struct gfs2_inode *dip, const struct qstr *filename);
-int gfs2_dir_read(struct inode *inode, u64 *offset, void *opaque,
-                  filldir_t filldir);
-int gfs2_dir_mvino(struct gfs2_inode *dip, const struct qstr *filename,
-                   const struct gfs2_inode *nip, unsigned int new_type);
+extern struct inode *gfs2_dir_search(struct inode *dir,
+                                     const struct qstr *filename);
+extern int gfs2_dir_check(struct inode *dir, const struct qstr *filename,
+                          const struct gfs2_inode *ip);
+extern int gfs2_dir_add(struct inode *inode, const struct qstr *filename,
+                        const struct gfs2_inode *ip, unsigned int type);
+extern int gfs2_dir_del(struct gfs2_inode *dip, const struct qstr *filename);
+extern int gfs2_dir_read(struct inode *inode, u64 *offset, void *opaque,
+                         filldir_t filldir);
+extern int gfs2_dir_mvino(struct gfs2_inode *dip, const struct qstr *filename,
+                          const struct gfs2_inode *nip, unsigned int new_type);
 
-int gfs2_dir_exhash_dealloc(struct gfs2_inode *dip);
+extern int gfs2_dir_exhash_dealloc(struct gfs2_inode *dip);
 
-int gfs2_diradd_alloc_required(struct inode *dir,
-                               const struct qstr *filename);
-int gfs2_dir_get_new_buffer(struct gfs2_inode *ip, u64 block,
-                            struct buffer_head **bhp);
+extern int gfs2_diradd_alloc_required(struct inode *dir,
+                                      const struct qstr *filename);
+extern int gfs2_dir_get_new_buffer(struct gfs2_inode *ip, u64 block,
+                                   struct buffer_head **bhp);
 
 static inline u32 gfs2_disk_hash(const char *data, int len)
 {
@@ -61,4 +62,7 @@ static inline void gfs2_qstr2dirent(const struct qstr *name, u16 reclen, struct
         memcpy(dent + 1, name->name, name->len);
 }
 
+extern struct qstr gfs2_qdot;
+extern struct qstr gfs2_qdotdot;
+
 #endif /* __DIR_DOT_H__ */
diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c
index dfe237a3f8ad..06d582732d34 100644
--- a/fs/gfs2/export.c
+++ b/fs/gfs2/export.c
@@ -126,16 +126,9 @@ static int gfs2_get_name(struct dentry *parent, char *name,
 
 static struct dentry *gfs2_get_parent(struct dentry *child)
 {
-        struct qstr dotdot;
         struct dentry *dentry;
 
-        /*
-         * XXX(hch): it would be a good idea to keep this around as a
-         *           static variable.
-         */
-        gfs2_str2qstr(&dotdot, "..");
-
-        dentry = d_obtain_alias(gfs2_lookupi(child->d_inode, &dotdot, 1));
+        dentry = d_obtain_alias(gfs2_lookupi(child->d_inode, &gfs2_qdotdot, 1));
         if (!IS_ERR(dentry))
                 dentry->d_op = &gfs2_dops;
         return dentry;
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 4edd662c8232..237ee6a940df 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -382,8 +382,10 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
         rblocks = RES_DINODE + ind_blocks;
         if (gfs2_is_jdata(ip))
                 rblocks += data_blocks ? data_blocks : 1;
-        if (ind_blocks || data_blocks)
+        if (ind_blocks || data_blocks) {
                 rblocks += RES_STATFS + RES_QUOTA;
+                rblocks += gfs2_rg_blocks(al);
+        }
         ret = gfs2_trans_begin(sdp, rblocks, 0);
         if (ret)
                 goto out_trans_fail;
@@ -491,7 +493,7 @@ static int gfs2_open(struct inode *inode, struct file *file)
                         goto fail;
 
                 if (!(file->f_flags & O_LARGEFILE) &&
-                    ip->i_disksize > MAX_NON_LFS) {
+                    i_size_read(inode) > MAX_NON_LFS) {
                         error = -EOVERFLOW;
                         goto fail_gunlock;
                 }
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 9adf8f924e08..87778857f099 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -441,6 +441,8 @@ static void state_change(struct gfs2_glock *gl, unsigned int new_state)
                 else
                         gfs2_glock_put_nolock(gl);
         }
+        if (held1 && held2 && list_empty(&gl->gl_holders))
+                clear_bit(GLF_QUEUED, &gl->gl_flags);
 
         gl->gl_state = new_state;
         gl->gl_tchange = jiffies;
@@ -1012,6 +1014,7 @@ fail:
                 if (unlikely((gh->gh_flags & LM_FLAG_PRIORITY) && !insert_pt))
                         insert_pt = &gh2->gh_list;
         }
+        set_bit(GLF_QUEUED, &gl->gl_flags);
         if (likely(insert_pt == NULL)) {
                 list_add_tail(&gh->gh_list, &gl->gl_holders);
                 if (unlikely(gh->gh_flags & LM_FLAG_PRIORITY))
@@ -1310,10 +1313,12 @@ void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state)
 
         gfs2_glock_hold(gl);
         holdtime = gl->gl_tchange + gl->gl_ops->go_min_hold_time;
-        if (time_before(now, holdtime))
-                delay = holdtime - now;
-        if (test_bit(GLF_REPLY_PENDING, &gl->gl_flags))
-                delay = gl->gl_ops->go_min_hold_time;
+        if (test_bit(GLF_QUEUED, &gl->gl_flags)) {
+                if (time_before(now, holdtime))
+                        delay = holdtime - now;
+                if (test_bit(GLF_REPLY_PENDING, &gl->gl_flags))
+                        delay = gl->gl_ops->go_min_hold_time;
+        }
 
         spin_lock(&gl->gl_spin);
         handle_callback(gl, state, delay);
@@ -1512,7 +1517,7 @@ static void clear_glock(struct gfs2_glock *gl)
         spin_unlock(&lru_lock);
 
         spin_lock(&gl->gl_spin);
-        if (find_first_holder(gl) == NULL && gl->gl_state != LM_ST_UNLOCKED)
+        if (gl->gl_state != LM_ST_UNLOCKED)
                 handle_callback(gl, LM_ST_UNLOCKED, 0);
         spin_unlock(&gl->gl_spin);
         gfs2_glock_hold(gl);
@@ -1660,6 +1665,8 @@ static const char *gflags2str(char *buf, const unsigned long *gflags)
                 *p++ = 'I';
         if (test_bit(GLF_FROZEN, gflags))
                 *p++ = 'F';
+        if (test_bit(GLF_QUEUED, gflags))
+                *p++ = 'q';
         *p = 0;
         return buf;
 }
@@ -1776,10 +1783,12 @@ int __init gfs2_glock_init(void)
         }
 #endif
 
-        glock_workqueue = create_workqueue("glock_workqueue");
+        glock_workqueue = alloc_workqueue("glock_workqueue", WQ_RESCUER |
+                                          WQ_HIGHPRI | WQ_FREEZEABLE, 0);
         if (IS_ERR(glock_workqueue))
                 return PTR_ERR(glock_workqueue);
-        gfs2_delete_workqueue = create_workqueue("delete_workqueue");
+        gfs2_delete_workqueue = alloc_workqueue("delete_workqueue", WQ_RESCUER |
+                                                WQ_FREEZEABLE, 0);
         if (IS_ERR(gfs2_delete_workqueue)) {
                 destroy_workqueue(glock_workqueue);
                 return PTR_ERR(gfs2_delete_workqueue);
diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h
index 2bda1911b156..db1c26d6d220 100644
--- a/fs/gfs2/glock.h
+++ b/fs/gfs2/glock.h
@@ -215,7 +215,7 @@ void gfs2_glock_dq_uninit_m(unsigned int num_gh, struct gfs2_holder *ghs);
 void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...);
 
 /**
- * gfs2_glock_nq_init - intialize a holder and enqueue it on a glock
+ * gfs2_glock_nq_init - initialize a holder and enqueue it on a glock
  * @gl: the glock
  * @state: the state we're requesting
  * @flags: the modifier flags
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 49f97d3bb690..0d149dcc04e5 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -262,13 +262,12 @@ static int inode_go_dump(struct seq_file *seq, const struct gfs2_glock *gl)
         const struct gfs2_inode *ip = gl->gl_object;
         if (ip == NULL)
                 return 0;
-        gfs2_print_dbg(seq, " I: n:%llu/%llu t:%u f:0x%02lx d:0x%08x s:%llu/%llu\n",
+        gfs2_print_dbg(seq, " I: n:%llu/%llu t:%u f:0x%02lx d:0x%08x s:%llu\n",
                   (unsigned long long)ip->i_no_formal_ino,
                   (unsigned long long)ip->i_no_addr,
                   IF2DT(ip->i_inode.i_mode), ip->i_flags,
                   (unsigned int)ip->i_diskflags,
-                  (unsigned long long)ip->i_inode.i_size,
-                  (unsigned long long)ip->i_disksize);
+                  (unsigned long long)i_size_read(&ip->i_inode));
         return 0;
 }
 
@@ -453,7 +452,6 @@ const struct gfs2_glock_operations *gfs2_glops_list[] = {
         [LM_TYPE_META] = &gfs2_meta_glops,
         [LM_TYPE_INODE] = &gfs2_inode_glops,
         [LM_TYPE_RGRP] = &gfs2_rgrp_glops,
-        [LM_TYPE_NONDISK] = &gfs2_trans_glops,
         [LM_TYPE_IOPEN] = &gfs2_iopen_glops,
         [LM_TYPE_FLOCK] = &gfs2_flock_glops,
         [LM_TYPE_NONDISK] = &gfs2_nondisk_glops,
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index fdbf4b366fa5..764fbb49efc8 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -196,6 +196,7 @@ enum {
         GLF_REPLY_PENDING               = 9,
         GLF_INITIAL                     = 10,
         GLF_FROZEN                      = 11,
+        GLF_QUEUED                      = 12,
 };
 
 struct gfs2_glock {
@@ -267,7 +268,6 @@ struct gfs2_inode {
         u64 i_no_formal_ino;
         u64 i_generation;
         u64 i_eattr;
-        loff_t i_disksize;
         unsigned long i_flags;          /* GIF_... */
         struct gfs2_glock *i_gl; /* Move into i_gh? */
         struct gfs2_holder i_iopen_gh;
@@ -416,11 +416,8 @@ struct gfs2_args {
         char ar_locktable[GFS2_LOCKNAME_LEN];   /* Name of the Lock Table */
         char ar_hostdata[GFS2_LOCKNAME_LEN];    /* Host specific data */
         unsigned int ar_spectator:1;            /* Don't get a journal */
-        unsigned int ar_ignore_local_fs:1;      /* Ignore optimisations */
         unsigned int ar_localflocks:1;          /* Let the VFS do flock|fcntl */
-        unsigned int ar_localcaching:1;         /* Local caching */
         unsigned int ar_debug:1;                /* Oops on errors */
-        unsigned int ar_upgrade:1;              /* Upgrade ondisk format */
         unsigned int ar_posix_acl:1;            /* Enable posix acls */
         unsigned int ar_quota:2;                /* off/account/on */
         unsigned int ar_suiddir:1;              /* suiddir support */
@@ -497,7 +494,7 @@ struct gfs2_sb_host {
  */
 
 struct lm_lockstruct {
-        unsigned int ls_jid;
+        int ls_jid;
         unsigned int ls_first;
         unsigned int ls_first_done;
         unsigned int ls_nodir;
@@ -572,6 +569,7 @@ struct gfs2_sbd {
         struct list_head sd_rindex_mru_list;
         struct gfs2_rgrpd *sd_rindex_forward;
         unsigned int sd_rgrps;
+        unsigned int sd_max_rg_data;
 
         /* Journal index stuff */
 
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 08140f185a37..06370f8bd8cf 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -359,8 +359,7 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
          * to do that.
          */
         ip->i_inode.i_nlink = be32_to_cpu(str->di_nlink);
-        ip->i_disksize = be64_to_cpu(str->di_size);
-        i_size_write(&ip->i_inode, ip->i_disksize);
+        i_size_write(&ip->i_inode, be64_to_cpu(str->di_size));
         gfs2_set_inode_blocks(&ip->i_inode, be64_to_cpu(str->di_blocks));
         atime.tv_sec = be64_to_cpu(str->di_atime);
         atime.tv_nsec = be32_to_cpu(str->di_atime_nsec);
@@ -1055,7 +1054,7 @@ void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf)
         str->di_uid = cpu_to_be32(ip->i_inode.i_uid);
         str->di_gid = cpu_to_be32(ip->i_inode.i_gid);
         str->di_nlink = cpu_to_be32(ip->i_inode.i_nlink);
-        str->di_size = cpu_to_be64(ip->i_disksize);
+        str->di_size = cpu_to_be64(i_size_read(&ip->i_inode));
         str->di_blocks = cpu_to_be64(gfs2_get_inode_blocks(&ip->i_inode));
         str->di_atime = cpu_to_be64(ip->i_inode.i_atime.tv_sec);
         str->di_mtime = cpu_to_be64(ip->i_inode.i_mtime.tv_sec);
@@ -1085,8 +1084,8 @@ void gfs2_dinode_print(const struct gfs2_inode *ip)
                (unsigned long long)ip->i_no_formal_ino);
         printk(KERN_INFO "  no_addr = %llu\n",
                (unsigned long long)ip->i_no_addr);
-        printk(KERN_INFO "  i_disksize = %llu\n",
-               (unsigned long long)ip->i_disksize);
+        printk(KERN_INFO "  i_size = %llu\n",
+               (unsigned long long)i_size_read(&ip->i_inode));
         printk(KERN_INFO "  blocks = %llu\n",
                (unsigned long long)gfs2_get_inode_blocks(&ip->i_inode));
         printk(KERN_INFO "  i_goal = %llu\n",
diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h
index 300ada3f21de..6720d7d5fbc6 100644
--- a/fs/gfs2/inode.h
+++ b/fs/gfs2/inode.h
@@ -19,6 +19,8 @@ extern int gfs2_releasepage(struct page *page, gfp_t gfp_mask);
 extern int gfs2_internal_read(struct gfs2_inode *ip,
                               struct file_ra_state *ra_state,
                               char *buf, loff_t *pos, unsigned size);
+extern void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page,
+                                   unsigned int from, unsigned int to);
 extern void gfs2_set_aops(struct inode *inode);
 
 static inline int gfs2_is_stuffed(const struct gfs2_inode *ip)
@@ -80,6 +82,19 @@ static inline void gfs2_inum_out(const struct gfs2_inode *ip,
         dent->de_inum.no_addr = cpu_to_be64(ip->i_no_addr);
 }
 
+static inline int gfs2_check_internal_file_size(struct inode *inode,
+                                                u64 minsize, u64 maxsize)
+{
+        u64 size = i_size_read(inode);
+        if (size < minsize || size > maxsize)
+                goto err;
+        if (size & ((1 << inode->i_blkbits) - 1))
+                goto err;
+        return 0;
+err:
+        gfs2_consist_inode(GFS2_I(inode));
+        return -EIO;
+}
 
 extern void gfs2_set_iop(struct inode *inode);
 extern struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned type, 
diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index 0e0470ed34c2..1c09425b45fd 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -42,9 +42,9 @@ static void gdlm_ast(void *arg)
                 ret |= LM_OUT_CANCELED;
                 goto out;
         case -EAGAIN: /* Try lock fails */
+        case -EDEADLK: /* Deadlock detected */
                 goto out;
-        case -EINVAL: /* Invalid */
-        case -ENOMEM: /* Out of memory */
+        case -ETIMEDOUT: /* Canceled due to timeout */
                 ret |= LM_OUT_ERROR;
                 goto out;
         case 0: /* Success */
diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index b1e9630eb46a..d7eb1e209aa8 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -24,6 +24,7 @@
 #include "glock.h"
 #include "quota.h"
 #include "recovery.h"
+#include "dir.h"
 
 static struct shrinker qd_shrinker = {
         .shrink = gfs2_shrink_qd_memory,
@@ -78,6 +79,9 @@ static int __init init_gfs2_fs(void)
 {
         int error;
 
+        gfs2_str2qstr(&gfs2_qdot, ".");
+        gfs2_str2qstr(&gfs2_qdotdot, "..");
+
         error = gfs2_sys_init();
         if (error)
                 return error;
@@ -140,7 +144,7 @@ static int __init init_gfs2_fs(void)
 
         error = -ENOMEM;
         gfs_recovery_wq = alloc_workqueue("gfs_recovery",
-                                          WQ_NON_REENTRANT | WQ_RESCUER, 0);
+                                          WQ_RESCUER | WQ_FREEZEABLE, 0);
         if (!gfs_recovery_wq)
                 goto fail_wq;
 
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 4d4b1e8ac64c..aeafc233dc89 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -38,14 +38,6 @@
 #define DO 0
 #define UNDO 1
 
-static const u32 gfs2_old_fs_formats[] = {
-        0
-};
-
-static const u32 gfs2_old_multihost_formats[] = {
-        0
-};
-
 /**
  * gfs2_tune_init - Fill a gfs2_tune structure with default values
  * @gt: tune
@@ -135,8 +127,6 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
 
 static int gfs2_check_sb(struct gfs2_sbd *sdp, struct gfs2_sb_host *sb, int silent)
 {
-        unsigned int x;
-
         if (sb->sb_magic != GFS2_MAGIC ||
             sb->sb_type != GFS2_METATYPE_SB) {
                 if (!silent)
@@ -150,55 +140,9 @@ static int gfs2_check_sb(struct gfs2_sbd *sdp, struct gfs2_sb_host *sb, int sile
             sb->sb_multihost_format == GFS2_FORMAT_MULTI)
                 return 0;
 
-        if (sb->sb_fs_format != GFS2_FORMAT_FS) {
-                for (x = 0; gfs2_old_fs_formats[x]; x++)
-                        if (gfs2_old_fs_formats[x] == sb->sb_fs_format)
-                                break;
+        fs_warn(sdp, "Unknown on-disk format, unable to mount\n");
 
-                if (!gfs2_old_fs_formats[x]) {
-                        printk(KERN_WARNING
-                               "GFS2: code version (%u, %u) is incompatible "
-                               "with ondisk format (%u, %u)\n",
-                               GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
-                               sb->sb_fs_format, sb->sb_multihost_format);
-                        printk(KERN_WARNING
-                               "GFS2: I don't know how to upgrade this FS\n");
-                        return -EINVAL;
-                }
-        }
-
-        if (sb->sb_multihost_format != GFS2_FORMAT_MULTI) {
-                for (x = 0; gfs2_old_multihost_formats[x]; x++)
-                        if (gfs2_old_multihost_formats[x] ==
-                            sb->sb_multihost_format)
-                                break;
-
-                if (!gfs2_old_multihost_formats[x]) {
-                        printk(KERN_WARNING
-                               "GFS2: code version (%u, %u) is incompatible "
-                               "with ondisk format (%u, %u)\n",
-                               GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
-                               sb->sb_fs_format, sb->sb_multihost_format);
-                        printk(KERN_WARNING
-                               "GFS2: I don't know how to upgrade this FS\n");
-                        return -EINVAL;
-                }
-        }
-
-        if (!sdp->sd_args.ar_upgrade) {
-                printk(KERN_WARNING
-                       "GFS2: code version (%u, %u) is incompatible "
-                       "with ondisk format (%u, %u)\n",
-                       GFS2_FORMAT_FS, GFS2_FORMAT_MULTI,
-                       sb->sb_fs_format, sb->sb_multihost_format);
-                printk(KERN_INFO
-                       "GFS2: Use the \"upgrade\" mount option to upgrade "
-                       "the FS\n");
-                printk(KERN_INFO "GFS2: See the manual for more details\n");
-                return -EINVAL;
-        }
-
-        return 0;
+        return -EINVAL;
 }
 
 static void end_bio_io_page(struct bio *bio, int error)
@@ -586,7 +530,7 @@ static int map_journal_extents(struct gfs2_sbd *sdp)
 
         prev_db = 0;
 
-        for (lb = 0; lb < ip->i_disksize >> sdp->sd_sb.sb_bsize_shift; lb++) {
+        for (lb = 0; lb < i_size_read(jd->jd_inode) >> sdp->sd_sb.sb_bsize_shift; lb++) {
                 bh.b_state = 0;
                 bh.b_blocknr = 0;
                 bh.b_size = 1 << ip->i_inode.i_blkbits;
@@ -1022,7 +966,6 @@ static int gfs2_lm_mount(struct gfs2_sbd *sdp, int silent)
         if (!strcmp("lock_nolock", proto)) {
                 lm = &nolock_ops;
                 sdp->sd_args.ar_localflocks = 1;
-                sdp->sd_args.ar_localcaching = 1;
 #ifdef CONFIG_GFS2_FS_LOCKING_DLM
         } else if (!strcmp("lock_dlm", proto)) {
                 lm = &gfs2_dlm_ops;
@@ -1113,8 +1056,6 @@ static int gfs2_journalid_wait(void *word)
 
 static int wait_on_journal(struct gfs2_sbd *sdp)
 {
-        if (sdp->sd_args.ar_spectator)
-                return 0;
         if (sdp->sd_lockstruct.ls_ops->lm_mount == NULL)
                 return 0;
 
@@ -1217,6 +1158,20 @@ static int fill_super(struct super_block *sb, struct gfs2_args *args, int silent
         if (error)
                 goto fail_sb;
 
+        /*
+         * If user space has failed to join the cluster or some similar
+         * failure has occurred, then the journal id will contain a
+         * negative (error) number. This will then be returned to the
+         * caller (of the mount syscall). We do this even for spectator
+         * mounts (which just write a jid of 0 to indicate "ok" even though
+         * the jid is unused in the spectator case)
+         */
+        if (sdp->sd_lockstruct.ls_jid < 0) {
+                error = sdp->sd_lockstruct.ls_jid;
+                sdp->sd_lockstruct.ls_jid = 0;
+                goto fail_sb;
+        }
+
         error = init_inodes(sdp, DO);
         if (error)
                 goto fail_sb;
diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c
index 1009be2c9737..0534510200d5 100644
--- a/fs/gfs2/ops_inode.c
+++ b/fs/gfs2/ops_inode.c
@@ -18,6 +18,8 @@
 #include <linux/gfs2_ondisk.h>
 #include <linux/crc32.h>
 #include <linux/fiemap.h>
+#include <linux/swap.h>
+#include <linux/falloc.h>
 #include <asm/uaccess.h>
 
 #include "gfs2.h"
@@ -217,7 +219,7 @@ static int gfs2_link(struct dentry *old_dentry, struct inode *dir,
                         goto out_gunlock_q;
 
                 error = gfs2_trans_begin(sdp, sdp->sd_max_dirres +
-                                         al->al_rgd->rd_length +
+                                         gfs2_rg_blocks(al) +
                                          2 * RES_DINODE + RES_STATFS +
                                          RES_QUOTA, 0);
                 if (error)
@@ -406,7 +408,6 @@ static int gfs2_symlink(struct inode *dir, struct dentry *dentry,
 
         ip = ghs[1].gh_gl->gl_object;
 
-        ip->i_disksize = size;
         i_size_write(inode, size);
 
         error = gfs2_meta_inode_buffer(ip, &dibh);
@@ -461,7 +462,7 @@ static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, int mode)
         ip = ghs[1].gh_gl->gl_object;
 
         ip->i_inode.i_nlink = 2;
-        ip->i_disksize = sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode);
+        i_size_write(inode, sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode));
         ip->i_diskflags |= GFS2_DIF_JDATA;
         ip->i_entries = 2;
 
@@ -470,18 +471,15 @@ static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, int mode)
         if (!gfs2_assert_withdraw(sdp, !error)) {
                 struct gfs2_dinode *di = (struct gfs2_dinode *)dibh->b_data;
                 struct gfs2_dirent *dent = (struct gfs2_dirent *)(di+1);
-                struct qstr str;
 
-                gfs2_str2qstr(&str, ".");
                 gfs2_trans_add_bh(ip->i_gl, dibh, 1);
-                gfs2_qstr2dirent(&str, GFS2_DIRENT_SIZE(str.len), dent);
+                gfs2_qstr2dirent(&gfs2_qdot, GFS2_DIRENT_SIZE(gfs2_qdot.len), dent);
                 dent->de_inum = di->di_num; /* already GFS2 endian */
                 dent->de_type = cpu_to_be16(DT_DIR);
                 di->di_entries = cpu_to_be32(1);
 
-                gfs2_str2qstr(&str, "..");
                 dent = (struct gfs2_dirent *)((char*)dent + GFS2_DIRENT_SIZE(1));
-                gfs2_qstr2dirent(&str, dibh->b_size - GFS2_DIRENT_SIZE(1) - sizeof(struct gfs2_dinode), dent);
+                gfs2_qstr2dirent(&gfs2_qdotdot, dibh->b_size - GFS2_DIRENT_SIZE(1) - sizeof(struct gfs2_dinode), dent);
 
                 gfs2_inum_out(dip, dent);
                 dent->de_type = cpu_to_be16(DT_DIR);
@@ -522,7 +520,6 @@ static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 static int gfs2_rmdiri(struct gfs2_inode *dip, const struct qstr *name,
                        struct gfs2_inode *ip)
 {
-        struct qstr dotname;
         int error;
 
         if (ip->i_entries != 2) {
@@ -539,13 +536,11 @@ static int gfs2_rmdiri(struct gfs2_inode *dip, const struct qstr *name,
         if (error)
                 return error;
 
-        gfs2_str2qstr(&dotname, ".");
-        error = gfs2_dir_del(ip, &dotname);
+        error = gfs2_dir_del(ip, &gfs2_qdot);
         if (error)
                 return error;
 
-        gfs2_str2qstr(&dotname, "..");
-        error = gfs2_dir_del(ip, &dotname);
+        error = gfs2_dir_del(ip, &gfs2_qdotdot);
         if (error)
                 return error;
 
@@ -694,11 +689,8 @@ static int gfs2_ok_to_move(struct gfs2_inode *this, struct gfs2_inode *to)
         struct inode *dir = &to->i_inode;
         struct super_block *sb = dir->i_sb;
         struct inode *tmp;
-        struct qstr dotdot;
         int error = 0;
 
-        gfs2_str2qstr(&dotdot, "..");
-
         igrab(dir);
 
         for (;;) {
@@ -711,7 +703,7 @@ static int gfs2_ok_to_move(struct gfs2_inode *this, struct gfs2_inode *to)
                         break;
                 }
 
-                tmp = gfs2_lookupi(dir, &dotdot, 1);
+                tmp = gfs2_lookupi(dir, &gfs2_qdotdot, 1);
                 if (IS_ERR(tmp)) {
                         error = PTR_ERR(tmp);
                         break;
@@ -744,7 +736,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
         struct gfs2_inode *ip = GFS2_I(odentry->d_inode);
         struct gfs2_inode *nip = NULL;
         struct gfs2_sbd *sdp = GFS2_SB(odir);
-        struct gfs2_holder ghs[5], r_gh = { .gh_gl = NULL, };
+        struct gfs2_holder ghs[5], r_gh = { .gh_gl = NULL, }, ri_gh;
         struct gfs2_rgrpd *nrgd;
         unsigned int num_gh;
         int dir_rename = 0;
@@ -758,6 +750,9 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
                         return 0;
         }
 
+        error = gfs2_rindex_hold(sdp, &ri_gh);
+        if (error)
+                return error;
 
         if (odip != ndip) {
                 error = gfs2_glock_nq_init(sdp->sd_rename_gl, LM_ST_EXCLUSIVE,
@@ -887,12 +882,12 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
 
                 al->al_requested = sdp->sd_max_dirres;
 
-                error = gfs2_inplace_reserve(ndip);
+                error = gfs2_inplace_reserve_ri(ndip);
                 if (error)
                         goto out_gunlock_q;
 
                 error = gfs2_trans_begin(sdp, sdp->sd_max_dirres +
-                                         al->al_rgd->rd_length +
+                                         gfs2_rg_blocks(al) +
                                          4 * RES_DINODE + 4 * RES_LEAF +
                                          RES_STATFS + RES_QUOTA + 4, 0);
                 if (error)
@@ -920,9 +915,6 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
         }
 
         if (dir_rename) {
-                struct qstr name;
-                gfs2_str2qstr(&name, "..");
-
                 error = gfs2_change_nlink(ndip, +1);
                 if (error)
                         goto out_end_trans;
@@ -930,7 +922,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
                 if (error)
                         goto out_end_trans;
 
-                error = gfs2_dir_mvino(ip, &name, ndip, DT_DIR);
+                error = gfs2_dir_mvino(ip, &gfs2_qdotdot, ndip, DT_DIR);
                 if (error)
                         goto out_end_trans;
         } else {
@@ -972,6 +964,7 @@ out_gunlock_r:
         if (r_gh.gh_gl)
                 gfs2_glock_dq_uninit(&r_gh);
 out:
+        gfs2_glock_dq_uninit(&ri_gh);
         return error;
 }
 
@@ -990,7 +983,7 @@ static void *gfs2_follow_link(struct dentry *dentry, struct nameidata *nd)
         struct gfs2_inode *ip = GFS2_I(dentry->d_inode);
         struct gfs2_holder i_gh;
         struct buffer_head *dibh;
-        unsigned int x;
+        unsigned int x, size;
         char *buf;
         int error;
 
@@ -1002,7 +995,8 @@ static void *gfs2_follow_link(struct dentry *dentry, struct nameidata *nd)
                 return NULL;
         }
 
-        if (!ip->i_disksize) {
+        size = (unsigned int)i_size_read(&ip->i_inode);
+        if (size == 0) {
                 gfs2_consist_inode(ip);
                 buf = ERR_PTR(-EIO);
                 goto out;
@@ -1014,7 +1008,7 @@ static void *gfs2_follow_link(struct dentry *dentry, struct nameidata *nd)
                 goto out;
         }
 
-        x = ip->i_disksize + 1;
+        x = size + 1;
         buf = kmalloc(x, GFP_NOFS);
         if (!buf)
                 buf = ERR_PTR(-ENOMEM);
@@ -1071,30 +1065,6 @@ int gfs2_permission(struct inode *inode, int mask)
         return error;
 }
 
-/*
- * XXX(truncate): the truncate_setsize calls should be moved to the end.
- */
-static int setattr_size(struct inode *inode, struct iattr *attr)
-{
-        struct gfs2_inode *ip = GFS2_I(inode);
-        struct gfs2_sbd *sdp = GFS2_SB(inode);
-        int error;
-
-        if (attr->ia_size != ip->i_disksize) {
-                error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks);
-                if (error)
-                        return error;
-                truncate_setsize(inode, attr->ia_size);
-                gfs2_trans_end(sdp);
-        }
-
-        error = gfs2_truncatei(ip, attr->ia_size);
-        if (error && (inode->i_size != ip->i_disksize))
-                i_size_write(inode, ip->i_disksize);
-
-        return error;
-}
-
 static int setattr_chown(struct inode *inode, struct iattr *attr)
 {
         struct gfs2_inode *ip = GFS2_I(inode);
@@ -1195,7 +1165,7 @@ static int gfs2_setattr(struct dentry *dentry, struct iattr *attr)
                 goto out;
 
         if (attr->ia_valid & ATTR_SIZE)
-                error = setattr_size(inode, attr);
+                error = gfs2_setattr_size(inode, attr->ia_size);
         else if (attr->ia_valid & (ATTR_UID | ATTR_GID))
                 error = setattr_chown(inode, attr);
         else if ((attr->ia_valid & ATTR_MODE) && IS_POSIXACL(inode))
@@ -1301,6 +1271,257 @@ static int gfs2_removexattr(struct dentry *dentry, const char *name)
         return ret;
 }
 
+static void empty_write_end(struct page *page, unsigned from,
+                           unsigned to)
+{
+        struct gfs2_inode *ip = GFS2_I(page->mapping->host);
+
+        page_zero_new_buffers(page, from, to);
+        flush_dcache_page(page);
+        mark_page_accessed(page);
+
+        if (!gfs2_is_writeback(ip))
+                gfs2_page_add_databufs(ip, page, from, to);
+
+        block_commit_write(page, from, to);
+}
+
+
+static int write_empty_blocks(struct page *page, unsigned from, unsigned to)
+{
+        unsigned start, end, next;
+        struct buffer_head *bh, *head;
+        int error;
+
+        if (!page_has_buffers(page)) {
+                error = block_prepare_write(page, from, to, gfs2_block_map);
+                if (unlikely(error))
+                        return error;
+
+                empty_write_end(page, from, to);
+                return 0;
+        }
+
+        bh = head = page_buffers(page);
+        next = end = 0;
+        while (next < from) {
+                next += bh->b_size;
+                bh = bh->b_this_page;
+        }
+        start = next;
+        do {
+                next += bh->b_size;
+                if (buffer_mapped(bh)) {
+                        if (end) {
+                                error = block_prepare_write(page, start, end,
+                                                            gfs2_block_map);
+                                if (unlikely(error))
+                                        return error;
+                                empty_write_end(page, start, end);
+                                end = 0;
+                        }
+                        start = next;
+                }
+                else
+                        end = next;
+                bh = bh->b_this_page;
+        } while (next < to);
+
+        if (end) {
+                error = block_prepare_write(page, start, end, gfs2_block_map);
+                if (unlikely(error))
+                        return error;
+                empty_write_end(page, start, end);
+        }
+
+        return 0;
+}
+
+static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
+                           int mode)
+{
+        struct gfs2_inode *ip = GFS2_I(inode);
+        struct buffer_head *dibh;
+        int error;
+        u64 start = offset >> PAGE_CACHE_SHIFT;
+        unsigned int start_offset = offset & ~PAGE_CACHE_MASK;
+        u64 end = (offset + len - 1) >> PAGE_CACHE_SHIFT;
+        pgoff_t curr;
+        struct page *page;
+        unsigned int end_offset = (offset + len) & ~PAGE_CACHE_MASK;
+        unsigned int from, to;
+
+        if (!end_offset)
+                end_offset = PAGE_CACHE_SIZE;
+
+        error = gfs2_meta_inode_buffer(ip, &dibh);
+        if (unlikely(error))
+                goto out;
+
+        gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+
+        if (gfs2_is_stuffed(ip)) {
+                error = gfs2_unstuff_dinode(ip, NULL);
+                if (unlikely(error))
+                        goto out;
+        }
+
+        curr = start;
+        offset = start << PAGE_CACHE_SHIFT;
+        from = start_offset;
+        to = PAGE_CACHE_SIZE;
+        while (curr <= end) {
+                page = grab_cache_page_write_begin(inode->i_mapping, curr,
+                                                   AOP_FLAG_NOFS);
+                if (unlikely(!page)) {
+                        error = -ENOMEM;
+                        goto out;
+                }
+
+                if (curr == end)
+                        to = end_offset;
+                error = write_empty_blocks(page, from, to);
+                if (!error && offset + to > inode->i_size &&
+                    !(mode & FALLOC_FL_KEEP_SIZE)) {
+                        i_size_write(inode, offset + to);
+                }
+                unlock_page(page);
+                page_cache_release(page);
+                if (error)
+                        goto out;
+                curr++;
+                offset += PAGE_CACHE_SIZE;
+                from = 0;
+        }
+
+        gfs2_dinode_out(ip, dibh->b_data);
+        mark_inode_dirty(inode);
+
+        brelse(dibh);
+
+out:
+        return error;
+}
+
+static void calc_max_reserv(struct gfs2_inode *ip, loff_t max, loff_t *len,
+                            unsigned int *data_blocks, unsigned int *ind_blocks)
+{
+        const struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+        unsigned int max_blocks = ip->i_alloc->al_rgd->rd_free_clone;
+        unsigned int tmp, max_data = max_blocks - 3 * (sdp->sd_max_height - 1);
+
+        for (tmp = max_data; tmp > sdp->sd_diptrs;) {
+                tmp = DIV_ROUND_UP(tmp, sdp->sd_inptrs);
+                max_data -= tmp;
+        }
+        /* This calculation isn't the exact reverse of gfs2_write_calc_reserve,
+           so it might end up with fewer data blocks */
+        if (max_data <= *data_blocks)
+                return;
+        *data_blocks = max_data;
+        *ind_blocks = max_blocks - max_data;
+        *len = ((loff_t)max_data - 3) << sdp->sd_sb.sb_bsize_shift;
+        if (*len > max) {
+                *len = max;
+                gfs2_write_calc_reserv(ip, max, data_blocks, ind_blocks);
+        }
+}
+
+static long gfs2_fallocate(struct inode *inode, int mode, loff_t offset,
+                           loff_t len)
+{
+        struct gfs2_sbd *sdp = GFS2_SB(inode);
+        struct gfs2_inode *ip = GFS2_I(inode);
+        unsigned int data_blocks = 0, ind_blocks = 0, rblocks;
+        loff_t bytes, max_bytes;
+        struct gfs2_alloc *al;
+        int error;
+        loff_t next = (offset + len - 1) >> sdp->sd_sb.sb_bsize_shift;
+        next = (next + 1) << sdp->sd_sb.sb_bsize_shift;
+
+        offset = (offset >> sdp->sd_sb.sb_bsize_shift) <<
+                 sdp->sd_sb.sb_bsize_shift;
+
+        len = next - offset;
+        bytes = sdp->sd_max_rg_data * sdp->sd_sb.sb_bsize / 2;
+        if (!bytes)
+                bytes = UINT_MAX;
+
+        gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &ip->i_gh);
+        error = gfs2_glock_nq(&ip->i_gh);
+        if (unlikely(error))
+                goto out_uninit;
+
+        if (!gfs2_write_alloc_required(ip, offset, len))
+                goto out_unlock;
+
+        while (len > 0) {
+                if (len < bytes)
+                        bytes = len;
+                al = gfs2_alloc_get(ip);
+                if (!al) {
+                        error = -ENOMEM;
+                        goto out_unlock;
+                }
+
+                error = gfs2_quota_lock_check(ip);
+                if (error)
+                        goto out_alloc_put;
+
+retry:
+                gfs2_write_calc_reserv(ip, bytes, &data_blocks, &ind_blocks);
+
+                al->al_requested = data_blocks + ind_blocks;
+                error = gfs2_inplace_reserve(ip);
+                if (error) {
+                        if (error == -ENOSPC && bytes > sdp->sd_sb.sb_bsize) {
+                                bytes >>= 1;
+                                goto retry;
+                        }
+                        goto out_qunlock;
+                }
+                max_bytes = bytes;
+                calc_max_reserv(ip, len, &max_bytes, &data_blocks, &ind_blocks);
+                al->al_requested = data_blocks + ind_blocks;
+
+                rblocks = RES_DINODE + ind_blocks + RES_STATFS + RES_QUOTA +
+                          RES_RG_HDR + gfs2_rg_blocks(al);
+                if (gfs2_is_jdata(ip))
+                        rblocks += data_blocks ? data_blocks : 1;
+
+                error = gfs2_trans_begin(sdp, rblocks,
+                                         PAGE_CACHE_SIZE/sdp->sd_sb.sb_bsize);
+                if (error)
+                        goto out_trans_fail;
+
+                error = fallocate_chunk(inode, offset, max_bytes, mode);
+                gfs2_trans_end(sdp);
+
+                if (error)
+                        goto out_trans_fail;
+
+                len -= max_bytes;
+                offset += max_bytes;
+                gfs2_inplace_release(ip);
+                gfs2_quota_unlock(ip);
+                gfs2_alloc_put(ip);
+        }
+        goto out_unlock;
+
+out_trans_fail:
+        gfs2_inplace_release(ip);
+out_qunlock:
+        gfs2_quota_unlock(ip);
+out_alloc_put:
+        gfs2_alloc_put(ip);
+out_unlock:
+        gfs2_glock_dq(&ip->i_gh);
+out_uninit:
+        gfs2_holder_uninit(&ip->i_gh);
+        return error;
+}
+
+
 static int gfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
                        u64 start, u64 len)
 {
@@ -1351,6 +1572,7 @@ const struct inode_operations gfs2_file_iops = {
         .getxattr = gfs2_getxattr,
         .listxattr = gfs2_listxattr,
         .removexattr = gfs2_removexattr,
+        .fallocate = gfs2_fallocate,
         .fiemap = gfs2_fiemap,
 };
 
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 1bc6b5695e6d..58a9b9998b42 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -735,10 +735,8 @@ get_a_page:
                 goto out;
 
         size = loc + sizeof(struct gfs2_quota);
-        if (size > inode->i_size) {
-                ip->i_disksize = size;
+        if (size > inode->i_size)
                 i_size_write(inode, size);
-        }
         inode->i_mtime = inode->i_atime = CURRENT_TIME;
         gfs2_trans_add_bh(ip->i_gl, dibh, 1);
         gfs2_dinode_out(ip, dibh->b_data);
@@ -817,7 +815,7 @@ static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda)
                 goto out_alloc;
 
         if (nalloc)
-                blocks += al->al_rgd->rd_length + nalloc * ind_blocks + RES_STATFS;
+                blocks += gfs2_rg_blocks(al) + nalloc * ind_blocks + RES_STATFS;
 
         error = gfs2_trans_begin(sdp, blocks, 0);
         if (error)
@@ -1190,18 +1188,17 @@ static void gfs2_quota_change_in(struct gfs2_quota_change_host *qc, const void *
 int gfs2_quota_init(struct gfs2_sbd *sdp)
 {
         struct gfs2_inode *ip = GFS2_I(sdp->sd_qc_inode);
-        unsigned int blocks = ip->i_disksize >> sdp->sd_sb.sb_bsize_shift;
+        u64 size = i_size_read(sdp->sd_qc_inode);
+        unsigned int blocks = size >> sdp->sd_sb.sb_bsize_shift;
         unsigned int x, slot = 0;
         unsigned int found = 0;
         u64 dblock;
         u32 extlen = 0;
         int error;
 
-        if (!ip->i_disksize || ip->i_disksize > (64 << 20) ||
-            ip->i_disksize & (sdp->sd_sb.sb_bsize - 1)) {
-                gfs2_consist_inode(ip);
+        if (gfs2_check_internal_file_size(sdp->sd_qc_inode, 1, 64 << 20))
                 return -EIO;
-        }
+
         sdp->sd_quota_slots = blocks * sdp->sd_qc_per_block;
         sdp->sd_quota_chunks = DIV_ROUND_UP(sdp->sd_quota_slots, 8 * PAGE_SIZE);
 
@@ -1589,6 +1586,7 @@ static int gfs2_set_dqblk(struct super_block *sb, int type, qid_t id,
                 error = gfs2_inplace_reserve(ip);
                 if (error)
                         goto out_alloc;
+                blocks += gfs2_rg_blocks(al);
         }
 
         error = gfs2_trans_begin(sdp, blocks + RES_DINODE + 1, 0);
diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c
index f7f89a94a5a4..f2a02edcac8f 100644
--- a/fs/gfs2/recovery.c
+++ b/fs/gfs2/recovery.c
@@ -455,11 +455,13 @@ void gfs2_recover_func(struct work_struct *work)
         int ro = 0;
         unsigned int pass;
         int error;
+        int jlocked = 0;
 
-        if (jd->jd_jid != sdp->sd_lockstruct.ls_jid) {
+        if (sdp->sd_args.ar_spectator ||
+            (jd->jd_jid != sdp->sd_lockstruct.ls_jid)) {
                 fs_info(sdp, "jid=%u: Trying to acquire journal lock...\n",
                         jd->jd_jid);
-
+                jlocked = 1;
                 /* Acquire the journal lock so we can do recovery */
 
                 error = gfs2_glock_nq_num(sdp, jd->jd_jid, &gfs2_journal_glops,
@@ -554,13 +556,12 @@ void gfs2_recover_func(struct work_struct *work)
                         jd->jd_jid, t);
         }
 
-        if (jd->jd_jid != sdp->sd_lockstruct.ls_jid)
-                gfs2_glock_dq_uninit(&ji_gh);
-
         gfs2_recovery_done(sdp, jd->jd_jid, LM_RD_SUCCESS);
 
-        if (jd->jd_jid != sdp->sd_lockstruct.ls_jid)
+        if (jlocked) {
+                gfs2_glock_dq_uninit(&ji_gh);
                 gfs2_glock_dq_uninit(&j_gh);
+        }
 
         fs_info(sdp, "jid=%u: Done\n", jd->jd_jid);
         goto done;
@@ -568,7 +569,7 @@ void gfs2_recover_func(struct work_struct *work)
 fail_gunlock_tr:
         gfs2_glock_dq_uninit(&t_gh);
 fail_gunlock_ji:
-        if (jd->jd_jid != sdp->sd_lockstruct.ls_jid) {
+        if (jlocked) {
                 gfs2_glock_dq_uninit(&ji_gh);
 fail_gunlock_j:
                 gfs2_glock_dq_uninit(&j_gh);
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 171a744f8e45..fb67f593f408 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -500,7 +500,7 @@ u64 gfs2_ri_total(struct gfs2_sbd *sdp)
         for (rgrps = 0;; rgrps++) {
                 loff_t pos = rgrps * sizeof(struct gfs2_rindex);
 
-                if (pos + sizeof(struct gfs2_rindex) >= ip->i_disksize)
+                if (pos + sizeof(struct gfs2_rindex) >= i_size_read(inode))
                         break;
                 error = gfs2_internal_read(ip, &ra_state, buf, &pos,
                                            sizeof(struct gfs2_rindex));
@@ -588,7 +588,9 @@ static int gfs2_ri_update(struct gfs2_inode *ip)
         struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
         struct inode *inode = &ip->i_inode;
         struct file_ra_state ra_state;
-        u64 rgrp_count = ip->i_disksize;
+        u64 rgrp_count = i_size_read(inode);
+        struct gfs2_rgrpd *rgd;
+        unsigned int max_data = 0;
         int error;
 
         do_div(rgrp_count, sizeof(struct gfs2_rindex));
@@ -603,6 +605,10 @@ static int gfs2_ri_update(struct gfs2_inode *ip)
                 }
         }
 
+        list_for_each_entry(rgd, &sdp->sd_rindex_list, rd_list)
+                if (rgd->rd_data > max_data)
+                        max_data = rgd->rd_data;
+        sdp->sd_max_rg_data = max_data;
         sdp->sd_rindex_uptodate = 1;
         return 0;
 }
@@ -622,13 +628,15 @@ static int gfs2_ri_update_special(struct gfs2_inode *ip)
         struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
         struct inode *inode = &ip->i_inode;
         struct file_ra_state ra_state;
+        struct gfs2_rgrpd *rgd;
+        unsigned int max_data = 0;
         int error;
 
         file_ra_state_init(&ra_state, inode->i_mapping);
         for (sdp->sd_rgrps = 0;; sdp->sd_rgrps++) {
                 /* Ignore partials */
                 if ((sdp->sd_rgrps + 1) * sizeof(struct gfs2_rindex) >
-                    ip->i_disksize)
+                    i_size_read(inode))
                         break;
                 error = read_rindex_entry(ip, &ra_state);
                 if (error) {
@@ -636,6 +644,10 @@ static int gfs2_ri_update_special(struct gfs2_inode *ip)
                         return error;
                 }
         }
+        list_for_each_entry(rgd, &sdp->sd_rindex_list, rd_list)
+                if (rgd->rd_data > max_data)
+                        max_data = rgd->rd_data;
+        sdp->sd_max_rg_data = max_data;
 
         sdp->sd_rindex_uptodate = 1;
         return 0;
@@ -1188,7 +1200,8 @@ out:
  * Returns: errno
  */
 
-int gfs2_inplace_reserve_i(struct gfs2_inode *ip, char *file, unsigned int line)
+int gfs2_inplace_reserve_i(struct gfs2_inode *ip, int hold_rindex,
+                           char *file, unsigned int line)
 {
         struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
         struct gfs2_alloc *al = ip->i_alloc;
@@ -1199,12 +1212,15 @@ int gfs2_inplace_reserve_i(struct gfs2_inode *ip, char *file, unsigned int line)
                 return -EINVAL;
 
 try_again:
-        /* We need to hold the rindex unless the inode we're using is
-           the rindex itself, in which case it's already held. */
-        if (ip != GFS2_I(sdp->sd_rindex))
-                error = gfs2_rindex_hold(sdp, &al->al_ri_gh);
-        else if (!sdp->sd_rgrps) /* We may not have the rindex read in, so: */
-                error = gfs2_ri_update_special(ip);
+        if (hold_rindex) {
+                /* We need to hold the rindex unless the inode we're using is
+                   the rindex itself, in which case it's already held. */
+                if (ip != GFS2_I(sdp->sd_rindex))
+                        error = gfs2_rindex_hold(sdp, &al->al_ri_gh);
+                else if (!sdp->sd_rgrps) /* We may not have the rindex read
+                                            in, so: */
+                        error = gfs2_ri_update_special(ip);
+        }
 
         if (error)
                 return error;
@@ -1215,7 +1231,7 @@ try_again:
            try to free it, and try the allocation again. */
         error = get_local_rgrp(ip, &unlinked, &last_unlinked);
         if (error) {
-                if (ip != GFS2_I(sdp->sd_rindex))
+                if (hold_rindex && ip != GFS2_I(sdp->sd_rindex))
                         gfs2_glock_dq_uninit(&al->al_ri_gh);
                 if (error != -EAGAIN)
                         return error;
@@ -1257,7 +1273,7 @@ void gfs2_inplace_release(struct gfs2_inode *ip)
         al->al_rgd = NULL;
         if (al->al_rgd_gh.gh_gl)
                 gfs2_glock_dq_uninit(&al->al_rgd_gh);
-        if (ip != GFS2_I(sdp->sd_rindex))
+        if (ip != GFS2_I(sdp->sd_rindex) && al->al_ri_gh.gh_gl)
                 gfs2_glock_dq_uninit(&al->al_ri_gh);
 }
 
@@ -1496,11 +1512,19 @@ int gfs2_alloc_block(struct gfs2_inode *ip, u64 *bn, unsigned int *n)
         struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
         struct buffer_head *dibh;
         struct gfs2_alloc *al = ip->i_alloc;
-        struct gfs2_rgrpd *rgd = al->al_rgd;
+        struct gfs2_rgrpd *rgd;
         u32 goal, blk;
         u64 block;
         int error;
 
+        /* Only happens if there is a bug in gfs2, return something distinctive
+         * to ensure that it is noticed.
+         */
+        if (al == NULL)
+                return -ECANCELED;
+
+        rgd = al->al_rgd;
+
         if (rgrp_contains_block(rgd, ip->i_goal))
                 goal = ip->i_goal - rgd->rd_data0;
         else
diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h
index f07119d89557..0e35c0466f9a 100644
--- a/fs/gfs2/rgrp.h
+++ b/fs/gfs2/rgrp.h
@@ -39,10 +39,12 @@ static inline void gfs2_alloc_put(struct gfs2_inode *ip)
         ip->i_alloc = NULL;
 }
 
-extern int gfs2_inplace_reserve_i(struct gfs2_inode *ip, char *file,
-                                  unsigned int line);
+extern int gfs2_inplace_reserve_i(struct gfs2_inode *ip, int hold_rindex,
+                                  char *file, unsigned int line);
 #define gfs2_inplace_reserve(ip) \
-gfs2_inplace_reserve_i((ip), __FILE__, __LINE__)
+        gfs2_inplace_reserve_i((ip), 1, __FILE__, __LINE__)
+#define gfs2_inplace_reserve_ri(ip) \
+        gfs2_inplace_reserve_i((ip), 0, __FILE__, __LINE__)
 
 extern void gfs2_inplace_release(struct gfs2_inode *ip);
 
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 77cb9f830ee4..047d1176096c 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -85,6 +85,7 @@ static const match_table_t tokens = {
         {Opt_locktable, "locktable=%s"},
         {Opt_hostdata, "hostdata=%s"},
         {Opt_spectator, "spectator"},
+        {Opt_spectator, "norecovery"},
         {Opt_ignore_local_fs, "ignore_local_fs"},
         {Opt_localflocks, "localflocks"},
         {Opt_localcaching, "localcaching"},
@@ -159,13 +160,13 @@ int gfs2_mount_args(struct gfs2_args *args, char *options)
                         args->ar_spectator = 1;
                         break;
                 case Opt_ignore_local_fs:
-                        args->ar_ignore_local_fs = 1;
+                        /* Retained for backwards compat only */
                         break;
                 case Opt_localflocks:
                         args->ar_localflocks = 1;
                         break;
                 case Opt_localcaching:
-                        args->ar_localcaching = 1;
+                        /* Retained for backwards compat only */
                         break;
                 case Opt_debug:
                         if (args->ar_errors == GFS2_ERRORS_PANIC) {
@@ -179,7 +180,7 @@ int gfs2_mount_args(struct gfs2_args *args, char *options)
                         args->ar_debug = 0;
                         break;
                 case Opt_upgrade:
-                        args->ar_upgrade = 1;
+                        /* Retained for backwards compat only */
                         break;
                 case Opt_acl:
                         args->ar_posix_acl = 1;
@@ -342,15 +343,14 @@ int gfs2_jdesc_check(struct gfs2_jdesc *jd)
 {
         struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
         struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+        u64 size = i_size_read(jd->jd_inode);
 
-        if (ip->i_disksize < (8 << 20) || ip->i_disksize > (1 << 30) ||
-            (ip->i_disksize & (sdp->sd_sb.sb_bsize - 1))) {
-                gfs2_consist_inode(ip);
+        if (gfs2_check_internal_file_size(jd->jd_inode, 8 << 20, 1 << 30))
                 return -EIO;
-        }
-        jd->jd_blocks = ip->i_disksize >> sdp->sd_sb.sb_bsize_shift;
 
-        if (gfs2_write_alloc_required(ip, 0, ip->i_disksize)) {
+        jd->jd_blocks = size >> sdp->sd_sb.sb_bsize_shift;
+
+        if (gfs2_write_alloc_required(ip, 0, size)) {
                 gfs2_consist_inode(ip);
                 return -EIO;
         }
@@ -1129,9 +1129,7 @@ static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data)
 
         /* Some flags must not be changed */
         if (args_neq(&args, &sdp->sd_args, spectator) ||
-            args_neq(&args, &sdp->sd_args, ignore_local_fs) ||
             args_neq(&args, &sdp->sd_args, localflocks) ||
-            args_neq(&args, &sdp->sd_args, localcaching) ||
             args_neq(&args, &sdp->sd_args, meta))
                 return -EINVAL;
 
@@ -1234,16 +1232,10 @@ static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
                 seq_printf(s, ",hostdata=%s", args->ar_hostdata);
         if (args->ar_spectator)
                 seq_printf(s, ",spectator");
-        if (args->ar_ignore_local_fs)
-                seq_printf(s, ",ignore_local_fs");
         if (args->ar_localflocks)
                 seq_printf(s, ",localflocks");
-        if (args->ar_localcaching)
-                seq_printf(s, ",localcaching");
         if (args->ar_debug)
                 seq_printf(s, ",debug");
-        if (args->ar_upgrade)
-                seq_printf(s, ",upgrade");
         if (args->ar_posix_acl)
                 seq_printf(s, ",acl");
         if (args->ar_quota != GFS2_QUOTA_DEFAULT) {
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index ccacffd2faaa..748ccb557c18 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -230,7 +230,10 @@ static ssize_t demote_rq_store(struct gfs2_sbd *sdp, const char *buf, size_t len
 
         if (gltype > LM_TYPE_JOURNAL)
                 return -EINVAL;
-        glops = gfs2_glops_list[gltype];
+        if (gltype == LM_TYPE_NONDISK && glnum == GFS2_TRANS_LOCK)
+                glops = &gfs2_trans_glops;
+        else
+                glops = gfs2_glops_list[gltype];
         if (glops == NULL)
                 return -EINVAL;
         if (!test_and_set_bit(SDF_DEMOTE, &sdp->sd_flags))
@@ -399,31 +402,32 @@ static ssize_t recover_status_show(struct gfs2_sbd *sdp, char *buf)
 
 static ssize_t jid_show(struct gfs2_sbd *sdp, char *buf)
 {
-        return sprintf(buf, "%u\n", sdp->sd_lockstruct.ls_jid);
+        return sprintf(buf, "%d\n", sdp->sd_lockstruct.ls_jid);
 }
 
 static ssize_t jid_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
 {
-        unsigned jid;
+        int jid;
         int rv;
 
-        rv = sscanf(buf, "%u", &jid);
+        rv = sscanf(buf, "%d", &jid);
         if (rv != 1)
                 return -EINVAL;
 
         spin_lock(&sdp->sd_jindex_spin);
         rv = -EINVAL;
-        if (sdp->sd_args.ar_spectator)
-                goto out;
         if (sdp->sd_lockstruct.ls_ops->lm_mount == NULL)
                 goto out;
         rv = -EBUSY;
-        if (test_and_clear_bit(SDF_NOJOURNALID, &sdp->sd_flags) == 0)
+        if (test_bit(SDF_NOJOURNALID, &sdp->sd_flags) == 0)
                 goto out;
+        rv = 0;
+        if (sdp->sd_args.ar_spectator && jid > 0)
+                rv = jid = -EINVAL;
         sdp->sd_lockstruct.ls_jid = jid;
+        clear_bit(SDF_NOJOURNALID, &sdp->sd_flags);
         smp_mb__after_clear_bit();
         wake_up_bit(&sdp->sd_flags, SDF_NOJOURNALID);
-        rv = 0;
 out:
         spin_unlock(&sdp->sd_jindex_spin);
         return rv ? rv : len;
@@ -617,7 +621,7 @@ static int gfs2_uevent(struct kset *kset, struct kobject *kobj,
         add_uevent_var(env, "LOCKTABLE=%s", sdp->sd_table_name);
         add_uevent_var(env, "LOCKPROTO=%s", sdp->sd_proto_name);
         if (!test_bit(SDF_NOJOURNALID, &sdp->sd_flags))
-                add_uevent_var(env, "JOURNALID=%u", sdp->sd_lockstruct.ls_jid);
+                add_uevent_var(env, "JOURNALID=%d", sdp->sd_lockstruct.ls_jid);
         if (gfs2_uuid_valid(uuid))
                 add_uevent_var(env, "UUID=%pUB", uuid);
         return 0;
diff --git a/fs/gfs2/trace_gfs2.h b/fs/gfs2/trace_gfs2.h
index 148d55c14171..cedb0bb96d96 100644
--- a/fs/gfs2/trace_gfs2.h
+++ b/fs/gfs2/trace_gfs2.h
@@ -39,7 +39,8 @@
         {(1UL << GLF_INVALIDATE_IN_PROGRESS),   "i" },          \
         {(1UL << GLF_REPLY_PENDING),            "r" },          \
         {(1UL << GLF_INITIAL),                  "I" },          \
-        {(1UL << GLF_FROZEN),                   "F" })
+        {(1UL << GLF_FROZEN),                   "F" },          \
+        {(1UL << GLF_QUEUED),                   "q" })
 
 #ifndef NUMPTY
 #define NUMPTY
diff --git a/fs/gfs2/trans.h b/fs/gfs2/trans.h
index edf9d4bd908e..fb56b783e028 100644
--- a/fs/gfs2/trans.h
+++ b/fs/gfs2/trans.h
@@ -20,11 +20,20 @@ struct gfs2_glock;
 #define RES_JDATA       1
 #define RES_DATA        1
 #define RES_LEAF        1
+#define RES_RG_HDR      1
 #define RES_RG_BIT      2
 #define RES_EATTR       1
 #define RES_STATFS      1
 #define RES_QUOTA       2
 
+/* reserve either the number of blocks to be allocated plus the rg header
+ * block, or all of the blocks in the rg, whichever is smaller */
+static inline unsigned int gfs2_rg_blocks(const struct gfs2_alloc *al)
+{
+        return (al->al_requested < al->al_rgd->rd_length)?
+               al->al_requested + 1 : al->al_rgd->rd_length;
+}
+
 int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
                      unsigned int revokes);
 
diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c
index 776af6eb4bcb..30b58f07c8a6 100644
--- a/fs/gfs2/xattr.c
+++ b/fs/gfs2/xattr.c
@@ -734,7 +734,7 @@ static int ea_alloc_skeleton(struct gfs2_inode *ip, struct gfs2_ea_request *er,
                 goto out_gunlock_q;
 
         error = gfs2_trans_begin(GFS2_SB(&ip->i_inode),
-                                 blks + al->al_rgd->rd_length +
+                                 blks + gfs2_rg_blocks(al) +
                                  RES_DINODE + RES_STATFS + RES_QUOTA, 0);
         if (error)
                 goto out_ipres;
diff --git a/fs/hfs/bfind.c b/fs/hfs/bfind.c
index 4129cdb3f0d8..571abe97b42a 100644
--- a/fs/hfs/bfind.c
+++ b/fs/hfs/bfind.c
@@ -23,7 +23,7 @@ int hfs_find_init(struct hfs_btree *tree, struct hfs_find_data *fd)
         fd->search_key = ptr;
         fd->key = ptr + tree->max_key_len + 2;
         dprint(DBG_BNODE_REFS, "find_init: %d (%p)\n", tree->cnid, __builtin_return_address(0));
-        down(&tree->tree_lock);
+        mutex_lock(&tree->tree_lock);
         return 0;
 }
 
@@ -32,7 +32,7 @@ void hfs_find_exit(struct hfs_find_data *fd)
         hfs_bnode_put(fd->bnode);
         kfree(fd->search_key);
         dprint(DBG_BNODE_REFS, "find_exit: %d (%p)\n", fd->tree->cnid, __builtin_return_address(0));
-        up(&fd->tree->tree_lock);
+        mutex_unlock(&fd->tree->tree_lock);
         fd->tree = NULL;
 }
 
diff --git a/fs/hfs/btree.c b/fs/hfs/btree.c
index 38a0a9917d7f..3ebc437736fe 100644
--- a/fs/hfs/btree.c
+++ b/fs/hfs/btree.c
@@ -27,7 +27,7 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id, btree_keycmp ke
         if (!tree)
                 return NULL;
 
-        init_MUTEX(&tree->tree_lock);
+        mutex_init(&tree->tree_lock);
         spin_lock_init(&tree->hash_lock);
         /* Set the correct compare function */
         tree->sb = sb;
diff --git a/fs/hfs/btree.h b/fs/hfs/btree.h
index cc51905ac21d..2a1d712f85dc 100644
--- a/fs/hfs/btree.h
+++ b/fs/hfs/btree.h
@@ -33,7 +33,7 @@ struct hfs_btree {
         unsigned int depth;
 
         //unsigned int map1_size, map_size;
-        struct semaphore tree_lock;
+        struct mutex tree_lock;
 
         unsigned int pages_per_bnode;
         spinlock_t hash_lock;
diff --git a/fs/hfsplus/bfind.c b/fs/hfsplus/bfind.c
index 5007a41f1be9..d182438c7ae4 100644
--- a/fs/hfsplus/bfind.c
+++ b/fs/hfsplus/bfind.c
@@ -23,7 +23,7 @@ int hfs_find_init(struct hfs_btree *tree, struct hfs_find_data *fd)
         fd->search_key = ptr;
         fd->key = ptr + tree->max_key_len + 2;
         dprint(DBG_BNODE_REFS, "find_init: %d (%p)\n", tree->cnid, __builtin_return_address(0));
-        down(&tree->tree_lock);
+        mutex_lock(&tree->tree_lock);
         return 0;
 }
 
@@ -32,7 +32,7 @@ void hfs_find_exit(struct hfs_find_data *fd)
         hfs_bnode_put(fd->bnode);
         kfree(fd->search_key);
         dprint(DBG_BNODE_REFS, "find_exit: %d (%p)\n", fd->tree->cnid, __builtin_return_address(0));
-        up(&fd->tree->tree_lock);
+        mutex_unlock(&fd->tree->tree_lock);
         fd->tree = NULL;
 }
 
@@ -52,6 +52,10 @@ int __hfs_brec_find(struct hfs_bnode *bnode, struct hfs_find_data *fd)
                 rec = (e + b) / 2;
                 len = hfs_brec_lenoff(bnode, rec, &off);
                 keylen = hfs_brec_keylen(bnode, rec);
+                if (keylen == 0) {
+                        res = -EINVAL;
+                        goto fail;
+                }
                 hfs_bnode_read(bnode, fd->key, off, keylen);
                 cmpval = bnode->tree->keycmp(fd->key, fd->search_key);
                 if (!cmpval) {
@@ -67,6 +71,10 @@ int __hfs_brec_find(struct hfs_bnode *bnode, struct hfs_find_data *fd)
         if (rec != e && e >= 0) {
                 len = hfs_brec_lenoff(bnode, e, &off);
                 keylen = hfs_brec_keylen(bnode, e);
+                if (keylen == 0) {
+                        res = -EINVAL;
+                        goto fail;
+                }
                 hfs_bnode_read(bnode, fd->key, off, keylen);
         }
 done:
@@ -75,6 +83,7 @@ done:
         fd->keylength = keylen;
         fd->entryoffset = off + keylen;
         fd->entrylength = len - keylen;
+fail:
         return res;
 }
 
@@ -198,6 +207,10 @@ int hfs_brec_goto(struct hfs_find_data *fd, int cnt)
 
         len = hfs_brec_lenoff(bnode, fd->record, &off);
         keylen = hfs_brec_keylen(bnode, fd->record);
+        if (keylen == 0) {
+                res = -EINVAL;
+                goto out;
+        }
         fd->keyoffset = off;
         fd->keylength = keylen;
         fd->entryoffset = off + keylen;
diff --git a/fs/hfsplus/bitmap.c b/fs/hfsplus/bitmap.c
index ea30afc2a03c..ad57f5991eb1 100644
--- a/fs/hfsplus/bitmap.c
+++ b/fs/hfsplus/bitmap.c
@@ -17,6 +17,7 @@
 
 int hfsplus_block_allocate(struct super_block *sb, u32 size, u32 offset, u32 *max)
 {
+        struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
         struct page *page;
         struct address_space *mapping;
         __be32 *pptr, *curr, *end;
@@ -29,8 +30,8 @@ int hfsplus_block_allocate(struct super_block *sb, u32 size, u32 offset, u32 *ma
                 return size;
 
         dprint(DBG_BITMAP, "block_allocate: %u,%u,%u\n", size, offset, len);
-        mutex_lock(&HFSPLUS_SB(sb).alloc_file->i_mutex);
-        mapping = HFSPLUS_SB(sb).alloc_file->i_mapping;
+        mutex_lock(&sbi->alloc_mutex);
+        mapping = sbi->alloc_file->i_mapping;
         page = read_mapping_page(mapping, offset / PAGE_CACHE_BITS, NULL);
         if (IS_ERR(page)) {
                 start = size;
@@ -150,16 +151,17 @@ done:
         set_page_dirty(page);
         kunmap(page);
         *max = offset + (curr - pptr) * 32 + i - start;
-        HFSPLUS_SB(sb).free_blocks -= *max;
+        sbi->free_blocks -= *max;
         sb->s_dirt = 1;
         dprint(DBG_BITMAP, "-> %u,%u\n", start, *max);
 out:
-        mutex_unlock(&HFSPLUS_SB(sb).alloc_file->i_mutex);
+        mutex_unlock(&sbi->alloc_mutex);
         return start;
 }
 
 int hfsplus_block_free(struct super_block *sb, u32 offset, u32 count)
 {
+        struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
         struct page *page;
         struct address_space *mapping;
         __be32 *pptr, *curr, *end;
@@ -172,11 +174,11 @@ int hfsplus_block_free(struct super_block *sb, u32 offset, u32 count)
 
         dprint(DBG_BITMAP, "block_free: %u,%u\n", offset, count);
         /* are all of the bits in range? */
-        if ((offset + count) > HFSPLUS_SB(sb).total_blocks)
+        if ((offset + count) > sbi->total_blocks)
                 return -2;
 
-        mutex_lock(&HFSPLUS_SB(sb).alloc_file->i_mutex);
-        mapping = HFSPLUS_SB(sb).alloc_file->i_mapping;
+        mutex_lock(&sbi->alloc_mutex);
+        mapping = sbi->alloc_file->i_mapping;
         pnr = offset / PAGE_CACHE_BITS;
         page = read_mapping_page(mapping, pnr, NULL);
         pptr = kmap(page);
@@ -224,9 +226,9 @@ done:
 out:
         set_page_dirty(page);
         kunmap(page);
-        HFSPLUS_SB(sb).free_blocks += len;
+        sbi->free_blocks += len;
         sb->s_dirt = 1;
-        mutex_unlock(&HFSPLUS_SB(sb).alloc_file->i_mutex);
+        mutex_unlock(&sbi->alloc_mutex);
 
         return 0;
 }
diff --git a/fs/hfsplus/brec.c b/fs/hfsplus/brec.c
index c88e5d72a402..2f39d05443e1 100644
--- a/fs/hfsplus/brec.c
+++ b/fs/hfsplus/brec.c
@@ -42,10 +42,13 @@ u16 hfs_brec_keylen(struct hfs_bnode *node, u16 rec)
                 recoff = hfs_bnode_read_u16(node, node->tree->node_size - (rec + 1) * 2);
                 if (!recoff)
                         return 0;
-                if (node->tree->attributes & HFS_TREE_BIGKEYS)
-                        retval = hfs_bnode_read_u16(node, recoff) + 2;
-                else
-                        retval = (hfs_bnode_read_u8(node, recoff) | 1) + 1;
+
+                retval = hfs_bnode_read_u16(node, recoff) + 2;
+                if (retval > node->tree->max_key_len + 2) {
+                        printk(KERN_ERR "hfs: keylen %d too large\n",
+                                retval);
+                        retval = 0;
+                }
         }
         return retval;
 }
@@ -216,7 +219,7 @@ skip:
 static struct hfs_bnode *hfs_bnode_split(struct hfs_find_data *fd)
 {
         struct hfs_btree *tree;
-        struct hfs_bnode *node, *new_node;
+        struct hfs_bnode *node, *new_node, *next_node;
         struct hfs_bnode_desc node_desc;
         int num_recs, new_rec_off, new_off, old_rec_off;
         int data_start, data_end, size;
@@ -235,6 +238,17 @@ static struct hfs_bnode *hfs_bnode_split(struct hfs_find_data *fd)
         new_node->type = node->type;
         new_node->height = node->height;
 
+        if (node->next)
+                next_node = hfs_bnode_find(tree, node->next);
+        else
+                next_node = NULL;
+
+        if (IS_ERR(next_node)) {
+                hfs_bnode_put(node);
+                hfs_bnode_put(new_node);
+                return next_node;
+        }
+
         size = tree->node_size / 2 - node->num_recs * 2 - 14;
         old_rec_off = tree->node_size - 4;
         num_recs = 1;
@@ -248,6 +262,8 @@ static struct hfs_bnode *hfs_bnode_split(struct hfs_find_data *fd)
                 /* panic? */
                 hfs_bnode_put(node);
                 hfs_bnode_put(new_node);
+                if (next_node)
+                        hfs_bnode_put(next_node);
                 return ERR_PTR(-ENOSPC);
         }
 
@@ -302,8 +318,7 @@ static struct hfs_bnode *hfs_bnode_split(struct hfs_find_data *fd)
         hfs_bnode_write(node, &node_desc, 0, sizeof(node_desc));
 
         /* update next bnode header */
-        if (new_node->next) {
-                struct hfs_bnode *next_node = hfs_bnode_find(tree, new_node->next);
+        if (next_node) {
                 next_node->prev = new_node->this;
                 hfs_bnode_read(next_node, &node_desc, 0, sizeof(node_desc));
                 node_desc.prev = cpu_to_be32(next_node->prev);
diff --git a/fs/hfsplus/btree.c b/fs/hfsplus/btree.c
index e49fcee1e293..22e4d4e32999 100644
--- a/fs/hfsplus/btree.c
+++ b/fs/hfsplus/btree.c
@@ -30,7 +30,7 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id)
         if (!tree)
                 return NULL;
 
-        init_MUTEX(&tree->tree_lock);
+        mutex_init(&tree->tree_lock);
         spin_lock_init(&tree->hash_lock);
         tree->sb = sb;
         tree->cnid = id;
@@ -39,10 +39,16 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id)
                 goto free_tree;
         tree->inode = inode;
 
+        if (!HFSPLUS_I(tree->inode)->first_blocks) {
+                printk(KERN_ERR
+                       "hfs: invalid btree extent records (0 size).\n");
+                goto free_inode;
+        }
+
         mapping = tree->inode->i_mapping;
         page = read_mapping_page(mapping, 0, NULL);
         if (IS_ERR(page))
-                goto free_tree;
+                goto free_inode;
 
         /* Load the header */
         head = (struct hfs_btree_header_rec *)(kmap(page) + sizeof(struct hfs_bnode_desc));
@@ -57,27 +63,56 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id)
         tree->max_key_len = be16_to_cpu(head->max_key_len);
         tree->depth = be16_to_cpu(head->depth);
 
-        /* Set the correct compare function */
-        if (id == HFSPLUS_EXT_CNID) {
+        /* Verify the tree and set the correct compare function */
+        switch (id) {
+        case HFSPLUS_EXT_CNID:
+                if (tree->max_key_len != HFSPLUS_EXT_KEYLEN - sizeof(u16)) {
+                        printk(KERN_ERR "hfs: invalid extent max_key_len %d\n",
+                                tree->max_key_len);
+                        goto fail_page;
+                }
+                if (tree->attributes & HFS_TREE_VARIDXKEYS) {
+                        printk(KERN_ERR "hfs: invalid extent btree flag\n");
+                        goto fail_page;
+                }
+
                 tree->keycmp = hfsplus_ext_cmp_key;
-        } else if (id == HFSPLUS_CAT_CNID) {
-                if ((HFSPLUS_SB(sb).flags & HFSPLUS_SB_HFSX) &&
+                break;
+        case HFSPLUS_CAT_CNID:
+                if (tree->max_key_len != HFSPLUS_CAT_KEYLEN - sizeof(u16)) {
+                        printk(KERN_ERR "hfs: invalid catalog max_key_len %d\n",
+                                tree->max_key_len);
+                        goto fail_page;
+                }
+                if (!(tree->attributes & HFS_TREE_VARIDXKEYS)) {
+                        printk(KERN_ERR "hfs: invalid catalog btree flag\n");
+                        goto fail_page;
+                }
+
+                if (test_bit(HFSPLUS_SB_HFSX, &HFSPLUS_SB(sb)->flags) &&
                     (head->key_type == HFSPLUS_KEY_BINARY))
                         tree->keycmp = hfsplus_cat_bin_cmp_key;
                 else {
                         tree->keycmp = hfsplus_cat_case_cmp_key;
-                        HFSPLUS_SB(sb).flags |= HFSPLUS_SB_CASEFOLD;
+                        set_bit(HFSPLUS_SB_CASEFOLD, &HFSPLUS_SB(sb)->flags);
                 }
-        } else {
+                break;
+        default:
                 printk(KERN_ERR "hfs: unknown B*Tree requested\n");
                 goto fail_page;
         }
 
+        if (!(tree->attributes & HFS_TREE_BIGKEYS)) {
+                printk(KERN_ERR "hfs: invalid btree flag\n");
+                goto fail_page;
+        }
+
         size = tree->node_size;
         if (!is_power_of_2(size))
                 goto fail_page;
         if (!tree->node_count)
                 goto fail_page;
+
         tree->node_size_shift = ffs(size) - 1;
 
         tree->pages_per_bnode = (tree->node_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
@@ -87,10 +122,11 @@ struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id)
         return tree;
 
  fail_page:
-        tree->inode->i_mapping->a_ops = &hfsplus_aops;
         page_cache_release(page);
- free_tree:
+ free_inode:
+        tree->inode->i_mapping->a_ops = &hfsplus_aops;
         iput(tree->inode);
+ free_tree:
         kfree(tree);
         return NULL;
 }
@@ -192,17 +228,18 @@ struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree)
 
         while (!tree->free_nodes) {
                 struct inode *inode = tree->inode;
+                struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
                 u32 count;
                 int res;
 
                 res = hfsplus_file_extend(inode);
                 if (res)
                         return ERR_PTR(res);
-                HFSPLUS_I(inode).phys_size = inode->i_size =
-                                (loff_t)HFSPLUS_I(inode).alloc_blocks <<
-                                HFSPLUS_SB(tree->sb).alloc_blksz_shift;
-                HFSPLUS_I(inode).fs_blocks = HFSPLUS_I(inode).alloc_blocks <<
-                                             HFSPLUS_SB(tree->sb).fs_shift;
+                hip->phys_size = inode->i_size =
+                        (loff_t)hip->alloc_blocks <<
+                                HFSPLUS_SB(tree->sb)->alloc_blksz_shift;
+                hip->fs_blocks =
+                        hip->alloc_blocks << HFSPLUS_SB(tree->sb)->fs_shift;
                 inode_set_bytes(inode, inode->i_size);
                 count = inode->i_size >> tree->node_size_shift;
                 tree->free_nodes = count - tree->node_count;
diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c
index f6874acb2cf2..8af45fc5b051 100644
--- a/fs/hfsplus/catalog.c
+++ b/fs/hfsplus/catalog.c
@@ -67,7 +67,7 @@ static void hfsplus_cat_build_key_uni(hfsplus_btree_key *key, u32 parent,
         key->key_len = cpu_to_be16(6 + ustrlen);
 }
 
-static void hfsplus_set_perms(struct inode *inode, struct hfsplus_perm *perms)
+void hfsplus_cat_set_perms(struct inode *inode, struct hfsplus_perm *perms)
 {
         if (inode->i_flags & S_IMMUTABLE)
                 perms->rootflags |= HFSPLUS_FLG_IMMUTABLE;
@@ -77,15 +77,24 @@ static void hfsplus_set_perms(struct inode *inode, struct hfsplus_perm *perms)
                 perms->rootflags |= HFSPLUS_FLG_APPEND;
         else
                 perms->rootflags &= ~HFSPLUS_FLG_APPEND;
-        HFSPLUS_I(inode).rootflags = perms->rootflags;
-        HFSPLUS_I(inode).userflags = perms->userflags;
+
+        perms->userflags = HFSPLUS_I(inode)->userflags;
         perms->mode = cpu_to_be16(inode->i_mode);
         perms->owner = cpu_to_be32(inode->i_uid);
         perms->group = cpu_to_be32(inode->i_gid);
+
+        if (S_ISREG(inode->i_mode))
+                perms->dev = cpu_to_be32(inode->i_nlink);
+        else if (S_ISBLK(inode->i_mode) || S_ISCHR(inode->i_mode))
+                perms->dev = cpu_to_be32(inode->i_rdev);
+        else
+                perms->dev = 0;
 }
 
 static int hfsplus_cat_build_record(hfsplus_cat_entry *entry, u32 cnid, struct inode *inode)
 {
+        struct hfsplus_sb_info *sbi = HFSPLUS_SB(inode->i_sb);
+
         if (S_ISDIR(inode->i_mode)) {
                 struct hfsplus_cat_folder *folder;
 
@@ -93,13 +102,13 @@ static int hfsplus_cat_build_record(hfsplus_cat_entry *entry, u32 cnid, struct i
                 memset(folder, 0, sizeof(*folder));
                 folder->type = cpu_to_be16(HFSPLUS_FOLDER);
                 folder->id = cpu_to_be32(inode->i_ino);
-                HFSPLUS_I(inode).create_date =
+                HFSPLUS_I(inode)->create_date =
                         folder->create_date =
                         folder->content_mod_date =
                         folder->attribute_mod_date =
                         folder->access_date = hfsp_now2mt();
-                hfsplus_set_perms(inode, &folder->permissions);
-                if (inode == HFSPLUS_SB(inode->i_sb).hidden_dir)
+                hfsplus_cat_set_perms(inode, &folder->permissions);
+                if (inode == sbi->hidden_dir)
                         /* invisible and namelocked */
                         folder->user_info.frFlags = cpu_to_be16(0x5000);
                 return sizeof(*folder);
@@ -111,19 +120,19 @@ static int hfsplus_cat_build_record(hfsplus_cat_entry *entry, u32 cnid, struct i
                 file->type = cpu_to_be16(HFSPLUS_FILE);
                 file->flags = cpu_to_be16(HFSPLUS_FILE_THREAD_EXISTS);
                 file->id = cpu_to_be32(cnid);
-                HFSPLUS_I(inode).create_date =
+                HFSPLUS_I(inode)->create_date =
                         file->create_date =
                         file->content_mod_date =
                         file->attribute_mod_date =
                         file->access_date = hfsp_now2mt();
                 if (cnid == inode->i_ino) {
-                        hfsplus_set_perms(inode, &file->permissions);
+                        hfsplus_cat_set_perms(inode, &file->permissions);
                         if (S_ISLNK(inode->i_mode)) {
                                 file->user_info.fdType = cpu_to_be32(HFSP_SYMLINK_TYPE);
                                 file->user_info.fdCreator = cpu_to_be32(HFSP_SYMLINK_CREATOR);
                         } else {
-                                file->user_info.fdType = cpu_to_be32(HFSPLUS_SB(inode->i_sb).type);
-                                file->user_info.fdCreator = cpu_to_be32(HFSPLUS_SB(inode->i_sb).creator);
+                                file->user_info.fdType = cpu_to_be32(sbi->type);
+                                file->user_info.fdCreator = cpu_to_be32(sbi->creator);
                         }
                         if ((file->permissions.rootflags | file->permissions.userflags) & HFSPLUS_FLG_IMMUTABLE)
                                 file->flags |= cpu_to_be16(HFSPLUS_FILE_LOCKED);
@@ -131,8 +140,8 @@ static int hfsplus_cat_build_record(hfsplus_cat_entry *entry, u32 cnid, struct i
                         file->user_info.fdType = cpu_to_be32(HFSP_HARDLINK_TYPE);
                         file->user_info.fdCreator = cpu_to_be32(HFSP_HFSPLUS_CREATOR);
                         file->user_info.fdFlags = cpu_to_be16(0x100);
-                        file->create_date = HFSPLUS_I(HFSPLUS_SB(inode->i_sb).hidden_dir).create_date;
-                        file->permissions.dev = cpu_to_be32(HFSPLUS_I(inode).dev);
+                        file->create_date = HFSPLUS_I(sbi->hidden_dir)->create_date;
+                        file->permissions.dev = cpu_to_be32(HFSPLUS_I(inode)->linkid);
                 }
                 return sizeof(*file);
         }
@@ -180,15 +189,14 @@ int hfsplus_find_cat(struct super_block *sb, u32 cnid,
 
 int hfsplus_create_cat(u32 cnid, struct inode *dir, struct qstr *str, struct inode *inode)
 {
+        struct super_block *sb = dir->i_sb;
         struct hfs_find_data fd;
-        struct super_block *sb;
         hfsplus_cat_entry entry;
         int entry_size;
         int err;
 
         dprint(DBG_CAT_MOD, "create_cat: %s,%u(%d)\n", str->name, cnid, inode->i_nlink);
-        sb = dir->i_sb;
-        hfs_find_init(HFSPLUS_SB(sb).cat_tree, &fd);
+        hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd);
 
         hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL);
         entry_size = hfsplus_fill_cat_thread(sb, &entry, S_ISDIR(inode->i_mode) ?
@@ -234,7 +242,7 @@ err2:
 
 int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str)
 {
-        struct super_block *sb;
+        struct super_block *sb = dir->i_sb;
         struct hfs_find_data fd;
         struct hfsplus_fork_raw fork;
         struct list_head *pos;
@@ -242,8 +250,7 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str)
         u16 type;
 
         dprint(DBG_CAT_MOD, "delete_cat: %s,%u\n", str ? str->name : NULL, cnid);
-        sb = dir->i_sb;
-        hfs_find_init(HFSPLUS_SB(sb).cat_tree, &fd);
+        hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd);
 
         if (!str) {
                 int len;
@@ -279,7 +286,7 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str)
                 hfsplus_free_fork(sb, cnid, &fork, HFSPLUS_TYPE_RSRC);
         }
 
-        list_for_each(pos, &HFSPLUS_I(dir).open_dir_list) {
+        list_for_each(pos, &HFSPLUS_I(dir)->open_dir_list) {
                 struct hfsplus_readdir_data *rd =
                         list_entry(pos, struct hfsplus_readdir_data, list);
                 if (fd.tree->keycmp(fd.search_key, (void *)&rd->key) < 0)
@@ -312,7 +319,7 @@ int hfsplus_rename_cat(u32 cnid,
                        struct inode *src_dir, struct qstr *src_name,
                        struct inode *dst_dir, struct qstr *dst_name)
 {
-        struct super_block *sb;
+        struct super_block *sb = src_dir->i_sb;
         struct hfs_find_data src_fd, dst_fd;
         hfsplus_cat_entry entry;
         int entry_size, type;
@@ -320,8 +327,7 @@ int hfsplus_rename_cat(u32 cnid,
 
         dprint(DBG_CAT_MOD, "rename_cat: %u - %lu,%s - %lu,%s\n", cnid, src_dir->i_ino, src_name->name,
                 dst_dir->i_ino, dst_name->name);
-        sb = src_dir->i_sb;
-        hfs_find_init(HFSPLUS_SB(sb).cat_tree, &src_fd);
+        hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &src_fd);
         dst_fd = src_fd;
 
         /* find the old dir entry and read the data */
diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c
index 764fd1bdca88..d236d85ec9d7 100644
--- a/fs/hfsplus/dir.c
+++ b/fs/hfsplus/dir.c
@@ -39,7 +39,7 @@ static struct dentry *hfsplus_lookup(struct inode *dir, struct dentry *dentry,
 
         dentry->d_op = &hfsplus_dentry_operations;
         dentry->d_fsdata = NULL;
-        hfs_find_init(HFSPLUS_SB(sb).cat_tree, &fd);
+        hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd);
         hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, &dentry->d_name);
 again:
         err = hfs_brec_read(&fd, &entry, sizeof(entry));
@@ -68,9 +68,9 @@ again:
                 cnid = be32_to_cpu(entry.file.id);
                 if (entry.file.user_info.fdType == cpu_to_be32(HFSP_HARDLINK_TYPE) &&
                     entry.file.user_info.fdCreator == cpu_to_be32(HFSP_HFSPLUS_CREATOR) &&
-                    (entry.file.create_date == HFSPLUS_I(HFSPLUS_SB(sb).hidden_dir).create_date ||
-                     entry.file.create_date == HFSPLUS_I(sb->s_root->d_inode).create_date) &&
-                    HFSPLUS_SB(sb).hidden_dir) {
+                    (entry.file.create_date == HFSPLUS_I(HFSPLUS_SB(sb)->hidden_dir)->create_date ||
+                     entry.file.create_date == HFSPLUS_I(sb->s_root->d_inode)->create_date) &&
+                    HFSPLUS_SB(sb)->hidden_dir) {
                         struct qstr str;
                         char name[32];
 
@@ -86,7 +86,8 @@ again:
                                 linkid = be32_to_cpu(entry.file.permissions.dev);
                                 str.len = sprintf(name, "iNode%d", linkid);
                                 str.name = name;
-                                hfsplus_cat_build_key(sb, fd.search_key, HFSPLUS_SB(sb).hidden_dir->i_ino, &str);
+                                hfsplus_cat_build_key(sb, fd.search_key,
+                                        HFSPLUS_SB(sb)->hidden_dir->i_ino, &str);
                                 goto again;
                         }
                 } else if (!dentry->d_fsdata)
@@ -101,7 +102,7 @@ again:
         if (IS_ERR(inode))
                 return ERR_CAST(inode);
         if (S_ISREG(inode->i_mode))
-                HFSPLUS_I(inode).dev = linkid;
+                HFSPLUS_I(inode)->linkid = linkid;
 out:
         d_add(dentry, inode);
         return NULL;
@@ -124,7 +125,7 @@ static int hfsplus_readdir(struct file *filp, void *dirent, filldir_t filldir)
         if (filp->f_pos >= inode->i_size)
                 return 0;
 
-        hfs_find_init(HFSPLUS_SB(sb).cat_tree, &fd);
+        hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd);
         hfsplus_cat_build_key(sb, fd.search_key, inode->i_ino, NULL);
         err = hfs_brec_find(&fd);
         if (err)
@@ -180,8 +181,9 @@ static int hfsplus_readdir(struct file *filp, void *dirent, filldir_t filldir)
                                 err = -EIO;
                                 goto out;
                         }
-                        if (HFSPLUS_SB(sb).hidden_dir &&
-                            HFSPLUS_SB(sb).hidden_dir->i_ino == be32_to_cpu(entry.folder.id))
+                        if (HFSPLUS_SB(sb)->hidden_dir &&
+                            HFSPLUS_SB(sb)->hidden_dir->i_ino ==
+                                        be32_to_cpu(entry.folder.id))
                                 goto next;
                         if (filldir(dirent, strbuf, len, filp->f_pos,
                                     be32_to_cpu(entry.folder.id), DT_DIR))
@@ -217,7 +219,7 @@ static int hfsplus_readdir(struct file *filp, void *dirent, filldir_t filldir)
                 }
                 filp->private_data = rd;
                 rd->file = filp;
-                list_add(&rd->list, &HFSPLUS_I(inode).open_dir_list);
+                list_add(&rd->list, &HFSPLUS_I(inode)->open_dir_list);
         }
         memcpy(&rd->key, fd.key, sizeof(struct hfsplus_cat_key));
 out:
@@ -229,38 +231,18 @@ static int hfsplus_dir_release(struct inode *inode, struct file *file)
 {
         struct hfsplus_readdir_data *rd = file->private_data;
         if (rd) {
+                mutex_lock(&inode->i_mutex);
                 list_del(&rd->list);
+                mutex_unlock(&inode->i_mutex);
                 kfree(rd);
         }
         return 0;
 }
 
-static int hfsplus_create(struct inode *dir, struct dentry *dentry, int mode,
-                          struct nameidata *nd)
-{
-        struct inode *inode;
-        int res;
-
-        inode = hfsplus_new_inode(dir->i_sb, mode);
-        if (!inode)
-                return -ENOSPC;
-
-        res = hfsplus_create_cat(inode->i_ino, dir, &dentry->d_name, inode);
-        if (res) {
-                inode->i_nlink = 0;
-                hfsplus_delete_inode(inode);
-                iput(inode);
-                return res;
-        }
-        hfsplus_instantiate(dentry, inode, inode->i_ino);
-        mark_inode_dirty(inode);
-        return 0;
-}
-
 static int hfsplus_link(struct dentry *src_dentry, struct inode *dst_dir,
                         struct dentry *dst_dentry)
 {
-        struct super_block *sb = dst_dir->i_sb;
+        struct hfsplus_sb_info *sbi = HFSPLUS_SB(dst_dir->i_sb);
         struct inode *inode = src_dentry->d_inode;
         struct inode *src_dir = src_dentry->d_parent->d_inode;
         struct qstr str;
@@ -270,7 +252,10 @@ static int hfsplus_link(struct dentry *src_dentry, struct inode *dst_dir,
 
         if (HFSPLUS_IS_RSRC(inode))
                 return -EPERM;
+        if (!S_ISREG(inode->i_mode))
+                return -EPERM;
 
+        mutex_lock(&sbi->vh_mutex);
         if (inode->i_ino == (u32)(unsigned long)src_dentry->d_fsdata) {
                 for (;;) {
                         get_random_bytes(&id, sizeof(cnid));
@@ -279,40 +264,41 @@ static int hfsplus_link(struct dentry *src_dentry, struct inode *dst_dir,
                         str.len = sprintf(name, "iNode%d", id);
                         res = hfsplus_rename_cat(inode->i_ino,
                                                  src_dir, &src_dentry->d_name,
-                                                 HFSPLUS_SB(sb).hidden_dir, &str);
+                                                 sbi->hidden_dir, &str);
                         if (!res)
                                 break;
                         if (res != -EEXIST)
-                                return res;
+                                goto out;
                 }
-                HFSPLUS_I(inode).dev = id;
-                cnid = HFSPLUS_SB(sb).next_cnid++;
+                HFSPLUS_I(inode)->linkid = id;
+                cnid = sbi->next_cnid++;
                 src_dentry->d_fsdata = (void *)(unsigned long)cnid;
                 res = hfsplus_create_cat(cnid, src_dir, &src_dentry->d_name, inode);
                 if (res)
                         /* panic? */
-                        return res;
-                HFSPLUS_SB(sb).file_count++;
+                        goto out;
+                sbi->file_count++;
         }
-        cnid = HFSPLUS_SB(sb).next_cnid++;
+        cnid = sbi->next_cnid++;
         res = hfsplus_create_cat(cnid, dst_dir, &dst_dentry->d_name, inode);
         if (res)
-                return res;
+                goto out;
 
         inc_nlink(inode);
         hfsplus_instantiate(dst_dentry, inode, cnid);
         atomic_inc(&inode->i_count);
         inode->i_ctime = CURRENT_TIME_SEC;
         mark_inode_dirty(inode);
-        HFSPLUS_SB(sb).file_count++;
-        sb->s_dirt = 1;
-
-        return 0;
+        sbi->file_count++;
+        dst_dir->i_sb->s_dirt = 1;
+out:
+        mutex_unlock(&sbi->vh_mutex);
+        return res;
 }
 
 static int hfsplus_unlink(struct inode *dir, struct dentry *dentry)
 {
-        struct super_block *sb = dir->i_sb;
+        struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb);
         struct inode *inode = dentry->d_inode;
         struct qstr str;
         char name[32];
@@ -322,21 +308,22 @@ static int hfsplus_unlink(struct inode *dir, struct dentry *dentry)
         if (HFSPLUS_IS_RSRC(inode))
                 return -EPERM;
 
+        mutex_lock(&sbi->vh_mutex);
         cnid = (u32)(unsigned long)dentry->d_fsdata;
         if (inode->i_ino == cnid &&
-            atomic_read(&HFSPLUS_I(inode).opencnt)) {
+            atomic_read(&HFSPLUS_I(inode)->opencnt)) {
                 str.name = name;
                 str.len = sprintf(name, "temp%lu", inode->i_ino);
                 res = hfsplus_rename_cat(inode->i_ino,
                                          dir, &dentry->d_name,
-                                         HFSPLUS_SB(sb).hidden_dir, &str);
+                                         sbi->hidden_dir, &str);
                 if (!res)
                         inode->i_flags |= S_DEAD;
-                return res;
+                goto out;
         }
         res = hfsplus_delete_cat(cnid, dir, &dentry->d_name);
         if (res)
-                return res;
+                goto out;
 
         if (inode->i_nlink > 0)
                 drop_nlink(inode);
@@ -344,10 +331,10 @@ static int hfsplus_unlink(struct inode *dir, struct dentry *dentry)
                 clear_nlink(inode);
         if (!inode->i_nlink) {
                 if (inode->i_ino != cnid) {
-                        HFSPLUS_SB(sb).file_count--;
-                        if (!atomic_read(&HFSPLUS_I(inode).opencnt)) {
+                        sbi->file_count--;
+                        if (!atomic_read(&HFSPLUS_I(inode)->opencnt)) {
                                 res = hfsplus_delete_cat(inode->i_ino,
-                                                         HFSPLUS_SB(sb).hidden_dir,
+                                                         sbi->hidden_dir,
                                                          NULL);
                                 if (!res)
                                         hfsplus_delete_inode(inode);
@@ -356,107 +343,108 @@ static int hfsplus_unlink(struct inode *dir, struct dentry *dentry)
                 } else
                         hfsplus_delete_inode(inode);
         } else
-                HFSPLUS_SB(sb).file_count--;
+                sbi->file_count--;
         inode->i_ctime = CURRENT_TIME_SEC;
         mark_inode_dirty(inode);
-
+out:
+        mutex_unlock(&sbi->vh_mutex);
         return res;
 }
 
-static int hfsplus_mkdir(struct inode *dir, struct dentry *dentry, int mode)
-{
-        struct inode *inode;
-        int res;
-
-        inode = hfsplus_new_inode(dir->i_sb, S_IFDIR | mode);
-        if (!inode)
-                return -ENOSPC;
-
-        res = hfsplus_create_cat(inode->i_ino, dir, &dentry->d_name, inode);
-        if (res) {
-                inode->i_nlink = 0;
-                hfsplus_delete_inode(inode);
-                iput(inode);
-                return res;
-        }
-        hfsplus_instantiate(dentry, inode, inode->i_ino);
-        mark_inode_dirty(inode);
-        return 0;
-}
-
 static int hfsplus_rmdir(struct inode *dir, struct dentry *dentry)
 {
-        struct inode *inode;
+        struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb);
+        struct inode *inode = dentry->d_inode;
         int res;
 
-        inode = dentry->d_inode;
         if (inode->i_size != 2)
                 return -ENOTEMPTY;
+
+        mutex_lock(&sbi->vh_mutex);
         res = hfsplus_delete_cat(inode->i_ino, dir, &dentry->d_name);
         if (res)
-                return res;
+                goto out;
         clear_nlink(inode);
         inode->i_ctime = CURRENT_TIME_SEC;
         hfsplus_delete_inode(inode);
         mark_inode_dirty(inode);
-        return 0;
+out:
+        mutex_unlock(&sbi->vh_mutex);
+        return res;
 }
 
 static int hfsplus_symlink(struct inode *dir, struct dentry *dentry,
                            const char *symname)
 {
-        struct super_block *sb;
+        struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb);
         struct inode *inode;
-        int res;
+        int res = -ENOSPC;
 
-        sb = dir->i_sb;
-        inode = hfsplus_new_inode(sb, S_IFLNK | S_IRWXUGO);
+        mutex_lock(&sbi->vh_mutex);
+        inode = hfsplus_new_inode(dir->i_sb, S_IFLNK | S_IRWXUGO);
         if (!inode)
-                return -ENOSPC;
+                goto out;
 
         res = page_symlink(inode, symname, strlen(symname) + 1);
-        if (res) {
-                inode->i_nlink = 0;
-                hfsplus_delete_inode(inode);
-                iput(inode);
-                return res;
-        }
+        if (res)
+                goto out_err;
 
-        mark_inode_dirty(inode);
         res = hfsplus_create_cat(inode->i_ino, dir, &dentry->d_name, inode);
+        if (res)
+                goto out_err;
 
-        if (!res) {
-                hfsplus_instantiate(dentry, inode, inode->i_ino);
-                mark_inode_dirty(inode);
-        }
+        hfsplus_instantiate(dentry, inode, inode->i_ino);
+        mark_inode_dirty(inode);
+        goto out;
 
+out_err:
+        inode->i_nlink = 0;
+        hfsplus_delete_inode(inode);
+        iput(inode);
+out:
+        mutex_unlock(&sbi->vh_mutex);
         return res;
 }
 
 static int hfsplus_mknod(struct inode *dir, struct dentry *dentry,
                          int mode, dev_t rdev)
 {
-        struct super_block *sb;
+        struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb);
         struct inode *inode;
-        int res;
+        int res = -ENOSPC;
 
-        sb = dir->i_sb;
-        inode = hfsplus_new_inode(sb, mode);
+        mutex_lock(&sbi->vh_mutex);
+        inode = hfsplus_new_inode(dir->i_sb, mode);
         if (!inode)
-                return -ENOSPC;
+                goto out;
+
+        if (S_ISBLK(mode) || S_ISCHR(mode) || S_ISFIFO(mode) || S_ISSOCK(mode))
+                init_special_inode(inode, mode, rdev);
 
         res = hfsplus_create_cat(inode->i_ino, dir, &dentry->d_name, inode);
         if (res) {
                 inode->i_nlink = 0;
                 hfsplus_delete_inode(inode);
                 iput(inode);
-                return res;
+                goto out;
         }
-        init_special_inode(inode, mode, rdev);
+
         hfsplus_instantiate(dentry, inode, inode->i_ino);
         mark_inode_dirty(inode);
+out:
+        mutex_unlock(&sbi->vh_mutex);
+        return res;
+}
 
-        return 0;
+static int hfsplus_create(struct inode *dir, struct dentry *dentry, int mode,
+                          struct nameidata *nd)
+{
+        return hfsplus_mknod(dir, dentry, mode, 0);
+}
+
+static int hfsplus_mkdir(struct inode *dir, struct dentry *dentry, int mode)
+{
+        return hfsplus_mknod(dir, dentry, mode | S_IFDIR, 0);
 }
 
 static int hfsplus_rename(struct inode *old_dir, struct dentry *old_dentry,
@@ -466,7 +454,10 @@ static int hfsplus_rename(struct inode *old_dir, struct dentry *old_dentry,
 
         /* Unlink destination if it already exists */
         if (new_dentry->d_inode) {
-                res = hfsplus_unlink(new_dir, new_dentry);
+                if (S_ISDIR(new_dentry->d_inode->i_mode))
+                        res = hfsplus_rmdir(new_dir, new_dentry);
+                else
+                        res = hfsplus_unlink(new_dir, new_dentry);
                 if (res)
                         return res;
         }
diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c
index 0022eec63cda..0c9cb1820a52 100644
--- a/fs/hfsplus/extents.c
+++ b/fs/hfsplus/extents.c
@@ -85,35 +85,49 @@ static u32 hfsplus_ext_lastblock(struct hfsplus_extent *ext)
 
 static void __hfsplus_ext_write_extent(struct inode *inode, struct hfs_find_data *fd)
 {
+        struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
         int res;
 
-        hfsplus_ext_build_key(fd->search_key, inode->i_ino, HFSPLUS_I(inode).cached_start,
-                              HFSPLUS_IS_RSRC(inode) ?  HFSPLUS_TYPE_RSRC : HFSPLUS_TYPE_DATA);
+        WARN_ON(!mutex_is_locked(&hip->extents_lock));
+
+        hfsplus_ext_build_key(fd->search_key, inode->i_ino, hip->cached_start,
+                              HFSPLUS_IS_RSRC(inode) ?
+                                HFSPLUS_TYPE_RSRC : HFSPLUS_TYPE_DATA);
+
         res = hfs_brec_find(fd);
-        if (HFSPLUS_I(inode).flags & HFSPLUS_FLG_EXT_NEW) {
+        if (hip->flags & HFSPLUS_FLG_EXT_NEW) {
                 if (res != -ENOENT)
                         return;
-                hfs_brec_insert(fd, HFSPLUS_I(inode).cached_extents, sizeof(hfsplus_extent_rec));
-                HFSPLUS_I(inode).flags &= ~(HFSPLUS_FLG_EXT_DIRTY | HFSPLUS_FLG_EXT_NEW);
+                hfs_brec_insert(fd, hip->cached_extents,
+                                sizeof(hfsplus_extent_rec));
+                hip->flags &= ~(HFSPLUS_FLG_EXT_DIRTY | HFSPLUS_FLG_EXT_NEW);
         } else {
                 if (res)
                         return;
-                hfs_bnode_write(fd->bnode, HFSPLUS_I(inode).cached_extents, fd->entryoffset, fd->entrylength);
-                HFSPLUS_I(inode).flags &= ~HFSPLUS_FLG_EXT_DIRTY;
+                hfs_bnode_write(fd->bnode, hip->cached_extents,
+                                fd->entryoffset, fd->entrylength);
+                hip->flags &= ~HFSPLUS_FLG_EXT_DIRTY;
         }
 }
 
-void hfsplus_ext_write_extent(struct inode *inode)
+static void hfsplus_ext_write_extent_locked(struct inode *inode)
 {
-        if (HFSPLUS_I(inode).flags & HFSPLUS_FLG_EXT_DIRTY) {
+        if (HFSPLUS_I(inode)->flags & HFSPLUS_FLG_EXT_DIRTY) {
                 struct hfs_find_data fd;
 
-                hfs_find_init(HFSPLUS_SB(inode->i_sb).ext_tree, &fd);
+                hfs_find_init(HFSPLUS_SB(inode->i_sb)->ext_tree, &fd);
                 __hfsplus_ext_write_extent(inode, &fd);
                 hfs_find_exit(&fd);
         }
 }
 
+void hfsplus_ext_write_extent(struct inode *inode)
+{
+        mutex_lock(&HFSPLUS_I(inode)->extents_lock);
+        hfsplus_ext_write_extent_locked(inode);
+        mutex_unlock(&HFSPLUS_I(inode)->extents_lock);
+}
+
 static inline int __hfsplus_ext_read_extent(struct hfs_find_data *fd,
                                             struct hfsplus_extent *extent,
                                             u32 cnid, u32 block, u8 type)
@@ -136,33 +150,39 @@ static inline int __hfsplus_ext_read_extent(struct hfs_find_data *fd,
 
 static inline int __hfsplus_ext_cache_extent(struct hfs_find_data *fd, struct inode *inode, u32 block)
 {
+        struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
         int res;
 
-        if (HFSPLUS_I(inode).flags & HFSPLUS_FLG_EXT_DIRTY)
+        WARN_ON(!mutex_is_locked(&hip->extents_lock));
+
+        if (hip->flags & HFSPLUS_FLG_EXT_DIRTY)
                 __hfsplus_ext_write_extent(inode, fd);
 
-        res = __hfsplus_ext_read_extent(fd, HFSPLUS_I(inode).cached_extents, inode->i_ino,
-                                        block, HFSPLUS_IS_RSRC(inode) ? HFSPLUS_TYPE_RSRC : HFSPLUS_TYPE_DATA);
+        res = __hfsplus_ext_read_extent(fd, hip->cached_extents, inode->i_ino,
+                                        block, HFSPLUS_IS_RSRC(inode) ?
+                                                HFSPLUS_TYPE_RSRC :
+                                                HFSPLUS_TYPE_DATA);
         if (!res) {
-                HFSPLUS_I(inode).cached_start = be32_to_cpu(fd->key->ext.start_block);
-                HFSPLUS_I(inode).cached_blocks = hfsplus_ext_block_count(HFSPLUS_I(inode).cached_extents);
+                hip->cached_start = be32_to_cpu(fd->key->ext.start_block);
+                hip->cached_blocks = hfsplus_ext_block_count(hip->cached_extents);
         } else {
-                HFSPLUS_I(inode).cached_start = HFSPLUS_I(inode).cached_blocks = 0;
-                HFSPLUS_I(inode).flags &= ~(HFSPLUS_FLG_EXT_DIRTY | HFSPLUS_FLG_EXT_NEW);
+                hip->cached_start = hip->cached_blocks = 0;
+                hip->flags &= ~(HFSPLUS_FLG_EXT_DIRTY | HFSPLUS_FLG_EXT_NEW);
         }
         return res;
 }
 
 static int hfsplus_ext_read_extent(struct inode *inode, u32 block)
 {
+        struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
         struct hfs_find_data fd;
         int res;
 
-        if (block >= HFSPLUS_I(inode).cached_start &&
-            block < HFSPLUS_I(inode).cached_start + HFSPLUS_I(inode).cached_blocks)
+        if (block >= hip->cached_start &&
+            block < hip->cached_start + hip->cached_blocks)
                 return 0;
 
-        hfs_find_init(HFSPLUS_SB(inode->i_sb).ext_tree, &fd);
+        hfs_find_init(HFSPLUS_SB(inode->i_sb)->ext_tree, &fd);
         res = __hfsplus_ext_cache_extent(&fd, inode, block);
         hfs_find_exit(&fd);
         return res;
@@ -172,21 +192,21 @@ static int hfsplus_ext_read_extent(struct inode *inode, u32 block)
 int hfsplus_get_block(struct inode *inode, sector_t iblock,
                       struct buffer_head *bh_result, int create)
 {
-        struct super_block *sb;
+        struct super_block *sb = inode->i_sb;
+        struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
+        struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
         int res = -EIO;
         u32 ablock, dblock, mask;
         int shift;
 
-        sb = inode->i_sb;
-
         /* Convert inode block to disk allocation block */
-        shift = HFSPLUS_SB(sb).alloc_blksz_shift - sb->s_blocksize_bits;
-        ablock = iblock >> HFSPLUS_SB(sb).fs_shift;
+        shift = sbi->alloc_blksz_shift - sb->s_blocksize_bits;
+        ablock = iblock >> sbi->fs_shift;
 
-        if (iblock >= HFSPLUS_I(inode).fs_blocks) {
-                if (iblock > HFSPLUS_I(inode).fs_blocks || !create)
+        if (iblock >= hip->fs_blocks) {
+                if (iblock > hip->fs_blocks || !create)
                         return -EIO;
-                if (ablock >= HFSPLUS_I(inode).alloc_blocks) {
+                if (ablock >= hip->alloc_blocks) {
                         res = hfsplus_file_extend(inode);
                         if (res)
                                 return res;
@@ -194,33 +214,33 @@ int hfsplus_get_block(struct inode *inode, sector_t iblock,
         } else
                 create = 0;
 
-        if (ablock < HFSPLUS_I(inode).first_blocks) {
-                dblock = hfsplus_ext_find_block(HFSPLUS_I(inode).first_extents, ablock);
+        if (ablock < hip->first_blocks) {
+                dblock = hfsplus_ext_find_block(hip->first_extents, ablock);
                 goto done;
         }
 
         if (inode->i_ino == HFSPLUS_EXT_CNID)
                 return -EIO;
 
-        mutex_lock(&HFSPLUS_I(inode).extents_lock);
+        mutex_lock(&hip->extents_lock);
         res = hfsplus_ext_read_extent(inode, ablock);
         if (!res) {
-                dblock = hfsplus_ext_find_block(HFSPLUS_I(inode).cached_extents, ablock -
-                                             HFSPLUS_I(inode).cached_start);
+                dblock = hfsplus_ext_find_block(hip->cached_extents,
+                                                ablock - hip->cached_start);
         } else {
-                mutex_unlock(&HFSPLUS_I(inode).extents_lock);
+                mutex_unlock(&hip->extents_lock);
                 return -EIO;
         }
-        mutex_unlock(&HFSPLUS_I(inode).extents_lock);
+        mutex_unlock(&hip->extents_lock);
 
 done:
         dprint(DBG_EXTENT, "get_block(%lu): %llu - %u\n", inode->i_ino, (long long)iblock, dblock);
-        mask = (1 << HFSPLUS_SB(sb).fs_shift) - 1;
-        map_bh(bh_result, sb, (dblock << HFSPLUS_SB(sb).fs_shift) + HFSPLUS_SB(sb).blockoffset + (iblock & mask));
+        mask = (1 << sbi->fs_shift) - 1;
+        map_bh(bh_result, sb, (dblock << sbi->fs_shift) + sbi->blockoffset + (iblock & mask));
         if (create) {
                 set_buffer_new(bh_result);
-                HFSPLUS_I(inode).phys_size += sb->s_blocksize;
-                HFSPLUS_I(inode).fs_blocks++;
+                hip->phys_size += sb->s_blocksize;
+                hip->fs_blocks++;
                 inode_add_bytes(inode, sb->s_blocksize);
                 mark_inode_dirty(inode);
         }
@@ -327,7 +347,7 @@ int hfsplus_free_fork(struct super_block *sb, u32 cnid, struct hfsplus_fork_raw
         if (total_blocks == blocks)
                 return 0;
 
-        hfs_find_init(HFSPLUS_SB(sb).ext_tree, &fd);
+        hfs_find_init(HFSPLUS_SB(sb)->ext_tree, &fd);
         do {
                 res = __hfsplus_ext_read_extent(&fd, ext_entry, cnid,
                                                 total_blocks, type);
@@ -348,29 +368,33 @@ int hfsplus_free_fork(struct super_block *sb, u32 cnid, struct hfsplus_fork_raw
 int hfsplus_file_extend(struct inode *inode)
 {
         struct super_block *sb = inode->i_sb;
+        struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
+        struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
         u32 start, len, goal;
         int res;
 
-        if (HFSPLUS_SB(sb).alloc_file->i_size * 8 < HFSPLUS_SB(sb).total_blocks - HFSPLUS_SB(sb).free_blocks + 8) {
+        if (sbi->alloc_file->i_size * 8 <
+            sbi->total_blocks - sbi->free_blocks + 8) {
                 // extend alloc file
-                printk(KERN_ERR "hfs: extend alloc file! (%Lu,%u,%u)\n", HFSPLUS_SB(sb).alloc_file->i_size * 8,
-                        HFSPLUS_SB(sb).total_blocks, HFSPLUS_SB(sb).free_blocks);
+                printk(KERN_ERR "hfs: extend alloc file! (%Lu,%u,%u)\n",
+                                sbi->alloc_file->i_size * 8,
+                                sbi->total_blocks, sbi->free_blocks);
                 return -ENOSPC;
         }
 
-        mutex_lock(&HFSPLUS_I(inode).extents_lock);
-        if (HFSPLUS_I(inode).alloc_blocks == HFSPLUS_I(inode).first_blocks)
-                goal = hfsplus_ext_lastblock(HFSPLUS_I(inode).first_extents);
+        mutex_lock(&hip->extents_lock);
+        if (hip->alloc_blocks == hip->first_blocks)
+                goal = hfsplus_ext_lastblock(hip->first_extents);
         else {
-                res = hfsplus_ext_read_extent(inode, HFSPLUS_I(inode).alloc_blocks);
+                res = hfsplus_ext_read_extent(inode, hip->alloc_blocks);
                 if (res)
                         goto out;
-                goal = hfsplus_ext_lastblock(HFSPLUS_I(inode).cached_extents);
+                goal = hfsplus_ext_lastblock(hip->cached_extents);
         }
 
-        len = HFSPLUS_I(inode).clump_blocks;
-        start = hfsplus_block_allocate(sb, HFSPLUS_SB(sb).total_blocks, goal, &len);
-        if (start >= HFSPLUS_SB(sb).total_blocks) {
+        len = hip->clump_blocks;
+        start = hfsplus_block_allocate(sb, sbi->total_blocks, goal, &len);
+        if (start >= sbi->total_blocks) {
                 start = hfsplus_block_allocate(sb, goal, 0, &len);
                 if (start >= goal) {
                         res = -ENOSPC;
@@ -379,56 +403,56 @@ int hfsplus_file_extend(struct inode *inode)
         }
 
         dprint(DBG_EXTENT, "extend %lu: %u,%u\n", inode->i_ino, start, len);
-        if (HFSPLUS_I(inode).alloc_blocks <= HFSPLUS_I(inode).first_blocks) {
-                if (!HFSPLUS_I(inode).first_blocks) {
+
+        if (hip->alloc_blocks <= hip->first_blocks) {
+                if (!hip->first_blocks) {
                         dprint(DBG_EXTENT, "first extents\n");
                         /* no extents yet */
-                        HFSPLUS_I(inode).first_extents[0].start_block = cpu_to_be32(start);
-                        HFSPLUS_I(inode).first_extents[0].block_count = cpu_to_be32(len);
+                        hip->first_extents[0].start_block = cpu_to_be32(start);
+                        hip->first_extents[0].block_count = cpu_to_be32(len);
                         res = 0;
                 } else {
                         /* try to append to extents in inode */
-                        res = hfsplus_add_extent(HFSPLUS_I(inode).first_extents,
-                                                 HFSPLUS_I(inode).alloc_blocks,
+                        res = hfsplus_add_extent(hip->first_extents,
+                                                 hip->alloc_blocks,
                                                  start, len);
                         if (res == -ENOSPC)
                                 goto insert_extent;
                 }
                 if (!res) {
-                        hfsplus_dump_extent(HFSPLUS_I(inode).first_extents);
-                        HFSPLUS_I(inode).first_blocks += len;
+                        hfsplus_dump_extent(hip->first_extents);
+                        hip->first_blocks += len;
                 }
         } else {
-                res = hfsplus_add_extent(HFSPLUS_I(inode).cached_extents,
-                                         HFSPLUS_I(inode).alloc_blocks -
-                                         HFSPLUS_I(inode).cached_start,
+                res = hfsplus_add_extent(hip->cached_extents,
+                                         hip->alloc_blocks - hip->cached_start,
                                          start, len);
                 if (!res) {
-                        hfsplus_dump_extent(HFSPLUS_I(inode).cached_extents);
-                        HFSPLUS_I(inode).flags |= HFSPLUS_FLG_EXT_DIRTY;
-                        HFSPLUS_I(inode).cached_blocks += len;
+                        hfsplus_dump_extent(hip->cached_extents);
+                        hip->flags |= HFSPLUS_FLG_EXT_DIRTY;
+                        hip->cached_blocks += len;
                 } else if (res == -ENOSPC)
                         goto insert_extent;
         }
 out:
-        mutex_unlock(&HFSPLUS_I(inode).extents_lock);
+        mutex_unlock(&hip->extents_lock);
         if (!res) {
-                HFSPLUS_I(inode).alloc_blocks += len;
+                hip->alloc_blocks += len;
                 mark_inode_dirty(inode);
         }
         return res;
 
 insert_extent:
         dprint(DBG_EXTENT, "insert new extent\n");
-        hfsplus_ext_write_extent(inode);
+        hfsplus_ext_write_extent_locked(inode);
 
-        memset(HFSPLUS_I(inode).cached_extents, 0, sizeof(hfsplus_extent_rec));
-        HFSPLUS_I(inode).cached_extents[0].start_block = cpu_to_be32(start);
-        HFSPLUS_I(inode).cached_extents[0].block_count = cpu_to_be32(len);
-        hfsplus_dump_extent(HFSPLUS_I(inode).cached_extents);
-        HFSPLUS_I(inode).flags |= HFSPLUS_FLG_EXT_DIRTY | HFSPLUS_FLG_EXT_NEW;
-        HFSPLUS_I(inode).cached_start = HFSPLUS_I(inode).alloc_blocks;
-        HFSPLUS_I(inode).cached_blocks = len;
+        memset(hip->cached_extents, 0, sizeof(hfsplus_extent_rec));
+        hip->cached_extents[0].start_block = cpu_to_be32(start);
+        hip->cached_extents[0].block_count = cpu_to_be32(len);
+        hfsplus_dump_extent(hip->cached_extents);
+        hip->flags |= HFSPLUS_FLG_EXT_DIRTY | HFSPLUS_FLG_EXT_NEW;
+        hip->cached_start = hip->alloc_blocks;
+        hip->cached_blocks = len;
 
         res = 0;
         goto out;
@@ -437,13 +461,15 @@ insert_extent:
 void hfsplus_file_truncate(struct inode *inode)
 {
         struct super_block *sb = inode->i_sb;
+        struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
         struct hfs_find_data fd;
         u32 alloc_cnt, blk_cnt, start;
         int res;
 
-        dprint(DBG_INODE, "truncate: %lu, %Lu -> %Lu\n", inode->i_ino,
-               (long long)HFSPLUS_I(inode).phys_size, inode->i_size);
-        if (inode->i_size > HFSPLUS_I(inode).phys_size) {
+        dprint(DBG_INODE, "truncate: %lu, %Lu -> %Lu\n",
+                inode->i_ino, (long long)hip->phys_size, inode->i_size);
+
+        if (inode->i_size > hip->phys_size) {
                 struct address_space *mapping = inode->i_mapping;
                 struct page *page;
                 void *fsdata;
@@ -460,47 +486,48 @@ void hfsplus_file_truncate(struct inode *inode)
                         return;
                 mark_inode_dirty(inode);
                 return;
-        } else if (inode->i_size == HFSPLUS_I(inode).phys_size)
+        } else if (inode->i_size == hip->phys_size)
                 return;
 
-        blk_cnt = (inode->i_size + HFSPLUS_SB(sb).alloc_blksz - 1) >> HFSPLUS_SB(sb).alloc_blksz_shift;
-        alloc_cnt = HFSPLUS_I(inode).alloc_blocks;
+        blk_cnt = (inode->i_size + HFSPLUS_SB(sb)->alloc_blksz - 1) >>
+                        HFSPLUS_SB(sb)->alloc_blksz_shift;
+        alloc_cnt = hip->alloc_blocks;
         if (blk_cnt == alloc_cnt)
                 goto out;
 
-        mutex_lock(&HFSPLUS_I(inode).extents_lock);
-        hfs_find_init(HFSPLUS_SB(sb).ext_tree, &fd);
+        mutex_lock(&hip->extents_lock);
+        hfs_find_init(HFSPLUS_SB(sb)->ext_tree, &fd);
         while (1) {
-                if (alloc_cnt == HFSPLUS_I(inode).first_blocks) {
-                        hfsplus_free_extents(sb, HFSPLUS_I(inode).first_extents,
+                if (alloc_cnt == hip->first_blocks) {
+                        hfsplus_free_extents(sb, hip->first_extents,
                                              alloc_cnt, alloc_cnt - blk_cnt);
-                        hfsplus_dump_extent(HFSPLUS_I(inode).first_extents);
-                        HFSPLUS_I(inode).first_blocks = blk_cnt;
+                        hfsplus_dump_extent(hip->first_extents);
+                        hip->first_blocks = blk_cnt;
                         break;
                 }
                 res = __hfsplus_ext_cache_extent(&fd, inode, alloc_cnt);
                 if (res)
                         break;
-                start = HFSPLUS_I(inode).cached_start;
-                hfsplus_free_extents(sb, HFSPLUS_I(inode).cached_extents,
+                start = hip->cached_start;
+                hfsplus_free_extents(sb, hip->cached_extents,
                                      alloc_cnt - start, alloc_cnt - blk_cnt);
-                hfsplus_dump_extent(HFSPLUS_I(inode).cached_extents);
+                hfsplus_dump_extent(hip->cached_extents);
                 if (blk_cnt > start) {
-                        HFSPLUS_I(inode).flags |= HFSPLUS_FLG_EXT_DIRTY;
+                        hip->flags |= HFSPLUS_FLG_EXT_DIRTY;
                         break;
                 }
                 alloc_cnt = start;
-                HFSPLUS_I(inode).cached_start = HFSPLUS_I(inode).cached_blocks = 0;
-                HFSPLUS_I(inode).flags &= ~(HFSPLUS_FLG_EXT_DIRTY | HFSPLUS_FLG_EXT_NEW);
+                hip->cached_start = hip->cached_blocks = 0;
+                hip->flags &= ~(HFSPLUS_FLG_EXT_DIRTY | HFSPLUS_FLG_EXT_NEW);
                 hfs_brec_remove(&fd);
         }
         hfs_find_exit(&fd);
-        mutex_unlock(&HFSPLUS_I(inode).extents_lock);
+        mutex_unlock(&hip->extents_lock);
 
-        HFSPLUS_I(inode).alloc_blocks = blk_cnt;
+        hip->alloc_blocks = blk_cnt;
 out:
-        HFSPLUS_I(inode).phys_size = inode->i_size;
-        HFSPLUS_I(inode).fs_blocks = (inode->i_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits;
-        inode_set_bytes(inode, HFSPLUS_I(inode).fs_blocks << sb->s_blocksize_bits);
+        hip->phys_size = inode->i_size;
+        hip->fs_blocks = (inode->i_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits;
+        inode_set_bytes(inode, hip->fs_blocks << sb->s_blocksize_bits);
         mark_inode_dirty(inode);
 }
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index dc856be3c2b0..cb3653efb57a 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -62,7 +62,7 @@ struct hfs_btree {
         unsigned int depth;
 
         //unsigned int map1_size, map_size;
-        struct semaphore tree_lock;
+        struct mutex tree_lock;
 
         unsigned int pages_per_bnode;
         spinlock_t hash_lock;
@@ -121,16 +121,21 @@ struct hfsplus_sb_info {
         u32 sect_count;
         int fs_shift;
 
-        /* Stuff in host order from Vol Header */
+        /* immutable data from the volume header */
         u32 alloc_blksz;
         int alloc_blksz_shift;
         u32 total_blocks;
+        u32 data_clump_blocks, rsrc_clump_blocks;
+
+        /* mutable data from the volume header, protected by alloc_mutex */
         u32 free_blocks;
-        u32 next_alloc;
+        struct mutex alloc_mutex;
+
+        /* mutable data from the volume header, protected by vh_mutex */
         u32 next_cnid;
         u32 file_count;
         u32 folder_count;
-        u32 data_clump_blocks, rsrc_clump_blocks;
+        struct mutex vh_mutex;
 
         /* Config options */
         u32 creator;
@@ -143,40 +148,50 @@ struct hfsplus_sb_info {
         int part, session;
 
         unsigned long flags;
-
-        struct hlist_head rsrc_inodes;
 };
 
-#define HFSPLUS_SB_WRITEBACKUP  0x0001
-#define HFSPLUS_SB_NODECOMPOSE  0x0002
-#define HFSPLUS_SB_FORCE        0x0004
-#define HFSPLUS_SB_HFSX         0x0008
-#define HFSPLUS_SB_CASEFOLD     0x0010
+#define HFSPLUS_SB_WRITEBACKUP  0
+#define HFSPLUS_SB_NODECOMPOSE  1
+#define HFSPLUS_SB_FORCE        2
+#define HFSPLUS_SB_HFSX         3
+#define HFSPLUS_SB_CASEFOLD     4
 
 
 struct hfsplus_inode_info {
-        struct mutex extents_lock;
-        u32 clump_blocks, alloc_blocks;
-        sector_t fs_blocks;
-        /* Allocation extents from catalog record or volume header */
-        hfsplus_extent_rec first_extents;
-        u32 first_blocks;
-        hfsplus_extent_rec cached_extents;
-        u32 cached_start, cached_blocks;
         atomic_t opencnt;
 
-        struct inode *rsrc_inode;
+        /*
+         * Extent allocation information, protected by extents_lock.
+         */
+        u32 first_blocks;
+        u32 clump_blocks;
+        u32 alloc_blocks;
+        u32 cached_start;
+        u32 cached_blocks;
+        hfsplus_extent_rec first_extents;
+        hfsplus_extent_rec cached_extents;
         unsigned long flags;
+        struct mutex extents_lock;
 
+        /*
+         * Immutable data.
+         */
+        struct inode *rsrc_inode;
         __be32 create_date;
-        /* Device number in hfsplus_permissions in catalog */
-        u32 dev;
-        /* BSD system and user file flags */
-        u8 rootflags;
-        u8 userflags;
 
+        /*
+         * Protected by sbi->vh_mutex.
+         */
+        u32 linkid;
+
+        /*
+         * Protected by i_mutex.
+         */
+        sector_t fs_blocks;
+        u8 userflags;           /* BSD user file flags */
         struct list_head open_dir_list;
         loff_t phys_size;
+
         struct inode vfs_inode;
 };
 
@@ -184,8 +199,8 @@ struct hfsplus_inode_info {
 #define HFSPLUS_FLG_EXT_DIRTY   0x0002
 #define HFSPLUS_FLG_EXT_NEW     0x0004
 
-#define HFSPLUS_IS_DATA(inode)   (!(HFSPLUS_I(inode).flags & HFSPLUS_FLG_RSRC))
-#define HFSPLUS_IS_RSRC(inode)   (HFSPLUS_I(inode).flags & HFSPLUS_FLG_RSRC)
+#define HFSPLUS_IS_DATA(inode)   (!(HFSPLUS_I(inode)->flags & HFSPLUS_FLG_RSRC))
+#define HFSPLUS_IS_RSRC(inode)   (HFSPLUS_I(inode)->flags & HFSPLUS_FLG_RSRC)
 
 struct hfs_find_data {
         /* filled by caller */
@@ -311,6 +326,7 @@ int hfsplus_create_cat(u32, struct inode *, struct qstr *, struct inode *);
 int hfsplus_delete_cat(u32, struct inode *, struct qstr *);
 int hfsplus_rename_cat(u32, struct inode *, struct qstr *,
                        struct inode *, struct qstr *);
+void hfsplus_cat_set_perms(struct inode *inode, struct hfsplus_perm *perms);
 
 /* dir.c */
 extern const struct inode_operations hfsplus_dir_inode_operations;
@@ -372,26 +388,15 @@ int hfsplus_read_wrapper(struct super_block *);
 int hfs_part_find(struct super_block *, sector_t *, sector_t *);
 
 /* access macros */
-/*
 static inline struct hfsplus_sb_info *HFSPLUS_SB(struct super_block *sb)
 {
         return sb->s_fs_info;
 }
+
 static inline struct hfsplus_inode_info *HFSPLUS_I(struct inode *inode)
 {
         return list_entry(inode, struct hfsplus_inode_info, vfs_inode);
 }
-*/
-#define HFSPLUS_SB(super)       (*(struct hfsplus_sb_info *)(super)->s_fs_info)
-#define HFSPLUS_I(inode)        (*list_entry(inode, struct hfsplus_inode_info, vfs_inode))
-
-#if 1
-#define hfsplus_kmap(p)         ({ struct page *__p = (p); kmap(__p); })
-#define hfsplus_kunmap(p)       ({ struct page *__p = (p); kunmap(__p); __p; })
-#else
-#define hfsplus_kmap(p)         kmap(p)
-#define hfsplus_kunmap(p)       kunmap(p)
-#endif
 
 #define sb_bread512(sb, sec, data) ({                   \
         struct buffer_head *__bh;                       \
@@ -419,6 +424,4 @@ static inline struct hfsplus_inode_info *HFSPLUS_I(struct inode *inode)
 #define hfsp_ut2mt(t)           __hfsp_ut2mt((t).tv_sec)
 #define hfsp_now2mt()           __hfsp_ut2mt(get_seconds())
 
-#define kdev_t_to_nr(x)         (x)
-
 #endif
diff --git a/fs/hfsplus/hfsplus_raw.h b/fs/hfsplus/hfsplus_raw.h
index fe99fe8db61a..6892899fd6fb 100644
--- a/fs/hfsplus/hfsplus_raw.h
+++ b/fs/hfsplus/hfsplus_raw.h
@@ -200,6 +200,7 @@ struct hfsplus_cat_key {
         struct hfsplus_unistr name;
 } __packed;
 
+#define HFSPLUS_CAT_KEYLEN      (sizeof(struct hfsplus_cat_key))
 
 /* Structs from hfs.h */
 struct hfsp_point {
@@ -323,7 +324,7 @@ struct hfsplus_ext_key {
         __be32 start_block;
 } __packed;
 
-#define HFSPLUS_EXT_KEYLEN 12
+#define HFSPLUS_EXT_KEYLEN      sizeof(struct hfsplus_ext_key)
 
 /* HFS+ generic BTree key */
 typedef union {
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index c5a979d62c65..78449280dae0 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -36,7 +36,7 @@ static int hfsplus_write_begin(struct file *file, struct address_space *mapping,
         *pagep = NULL;
         ret = cont_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
                                 hfsplus_get_block,
-                                &HFSPLUS_I(mapping->host).phys_size);
+                                &HFSPLUS_I(mapping->host)->phys_size);
         if (unlikely(ret)) {
                 loff_t isize = mapping->host->i_size;
                 if (pos + len > isize)
@@ -62,13 +62,13 @@ static int hfsplus_releasepage(struct page *page, gfp_t mask)
 
         switch (inode->i_ino) {
         case HFSPLUS_EXT_CNID:
-                tree = HFSPLUS_SB(sb).ext_tree;
+                tree = HFSPLUS_SB(sb)->ext_tree;
                 break;
         case HFSPLUS_CAT_CNID:
-                tree = HFSPLUS_SB(sb).cat_tree;
+                tree = HFSPLUS_SB(sb)->cat_tree;
                 break;
         case HFSPLUS_ATTR_CNID:
-                tree = HFSPLUS_SB(sb).attr_tree;
+                tree = HFSPLUS_SB(sb)->attr_tree;
                 break;
         default:
                 BUG();
@@ -172,12 +172,13 @@ static struct dentry *hfsplus_file_lookup(struct inode *dir, struct dentry *dent
         struct hfs_find_data fd;
         struct super_block *sb = dir->i_sb;
         struct inode *inode = NULL;
+        struct hfsplus_inode_info *hip;
         int err;
 
         if (HFSPLUS_IS_RSRC(dir) || strcmp(dentry->d_name.name, "rsrc"))
                 goto out;
 
-        inode = HFSPLUS_I(dir).rsrc_inode;
+        inode = HFSPLUS_I(dir)->rsrc_inode;
         if (inode)
                 goto out;
 
@@ -185,12 +186,13 @@ static struct dentry *hfsplus_file_lookup(struct inode *dir, struct dentry *dent
         if (!inode)
                 return ERR_PTR(-ENOMEM);
 
+        hip = HFSPLUS_I(inode);
         inode->i_ino = dir->i_ino;
-        INIT_LIST_HEAD(&HFSPLUS_I(inode).open_dir_list);
-        mutex_init(&HFSPLUS_I(inode).extents_lock);
-        HFSPLUS_I(inode).flags = HFSPLUS_FLG_RSRC;
+        INIT_LIST_HEAD(&hip->open_dir_list);
+        mutex_init(&hip->extents_lock);
+        hip->flags = HFSPLUS_FLG_RSRC;
 
-        hfs_find_init(HFSPLUS_SB(sb).cat_tree, &fd);
+        hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd);
         err = hfsplus_find_cat(sb, dir->i_ino, &fd);
         if (!err)
                 err = hfsplus_cat_read_inode(inode, &fd);
@@ -199,10 +201,18 @@ static struct dentry *hfsplus_file_lookup(struct inode *dir, struct dentry *dent
                 iput(inode);
                 return ERR_PTR(err);
         }
-        HFSPLUS_I(inode).rsrc_inode = dir;
-        HFSPLUS_I(dir).rsrc_inode = inode;
+        hip->rsrc_inode = dir;
+        HFSPLUS_I(dir)->rsrc_inode = inode;
         igrab(dir);
-        hlist_add_head(&inode->i_hash, &HFSPLUS_SB(sb).rsrc_inodes);
+
+        /*
+         * __mark_inode_dirty expects inodes to be hashed.  Since we don't
+         * want resource fork inodes in the regular inode space, we make them
+         * appear hashed, but do not put on any lists.  hlist_del()
+         * will work fine and require no locking.
+         */
+        inode->i_hash.pprev = &inode->i_hash.next;
+
         mark_inode_dirty(inode);
 out:
         d_add(dentry, inode);
@@ -211,30 +221,27 @@ out:
 
 static void hfsplus_get_perms(struct inode *inode, struct hfsplus_perm *perms, int dir)
 {
-        struct super_block *sb = inode->i_sb;
+        struct hfsplus_sb_info *sbi = HFSPLUS_SB(inode->i_sb);
         u16 mode;
 
         mode = be16_to_cpu(perms->mode);
 
         inode->i_uid = be32_to_cpu(perms->owner);
         if (!inode->i_uid && !mode)
-                inode->i_uid = HFSPLUS_SB(sb).uid;
+                inode->i_uid = sbi->uid;
 
         inode->i_gid = be32_to_cpu(perms->group);
         if (!inode->i_gid && !mode)
-                inode->i_gid = HFSPLUS_SB(sb).gid;
+                inode->i_gid = sbi->gid;
 
         if (dir) {
-                mode = mode ? (mode & S_IALLUGO) :
-                        (S_IRWXUGO & ~(HFSPLUS_SB(sb).umask));
+                mode = mode ? (mode & S_IALLUGO) : (S_IRWXUGO & ~(sbi->umask));
                 mode |= S_IFDIR;
         } else if (!mode)
-                mode = S_IFREG | ((S_IRUGO|S_IWUGO) &
-                        ~(HFSPLUS_SB(sb).umask));
+                mode = S_IFREG | ((S_IRUGO|S_IWUGO) & ~(sbi->umask));
         inode->i_mode = mode;
 
-        HFSPLUS_I(inode).rootflags = perms->rootflags;
-        HFSPLUS_I(inode).userflags = perms->userflags;
+        HFSPLUS_I(inode)->userflags = perms->userflags;
         if (perms->rootflags & HFSPLUS_FLG_IMMUTABLE)
                 inode->i_flags |= S_IMMUTABLE;
         else
@@ -245,30 +252,13 @@ static void hfsplus_get_perms(struct inode *inode, struct hfsplus_perm *perms, i
                 inode->i_flags &= ~S_APPEND;
 }
 
-static void hfsplus_set_perms(struct inode *inode, struct hfsplus_perm *perms)
-{
-        if (inode->i_flags & S_IMMUTABLE)
-                perms->rootflags |= HFSPLUS_FLG_IMMUTABLE;
-        else
-                perms->rootflags &= ~HFSPLUS_FLG_IMMUTABLE;
-        if (inode->i_flags & S_APPEND)
-                perms->rootflags |= HFSPLUS_FLG_APPEND;
-        else
-                perms->rootflags &= ~HFSPLUS_FLG_APPEND;
-        perms->userflags = HFSPLUS_I(inode).userflags;
-        perms->mode = cpu_to_be16(inode->i_mode);
-        perms->owner = cpu_to_be32(inode->i_uid);
-        perms->group = cpu_to_be32(inode->i_gid);
-        perms->dev = cpu_to_be32(HFSPLUS_I(inode).dev);
-}
-
 static int hfsplus_file_open(struct inode *inode, struct file *file)
 {
         if (HFSPLUS_IS_RSRC(inode))
-                inode = HFSPLUS_I(inode).rsrc_inode;
+                inode = HFSPLUS_I(inode)->rsrc_inode;
         if (!(file->f_flags & O_LARGEFILE) && i_size_read(inode) > MAX_NON_LFS)
                 return -EOVERFLOW;
-        atomic_inc(&HFSPLUS_I(inode).opencnt);
+        atomic_inc(&HFSPLUS_I(inode)->opencnt);
         return 0;
 }
 
@@ -277,12 +267,13 @@ static int hfsplus_file_release(struct inode *inode, struct file *file)
         struct super_block *sb = inode->i_sb;
 
         if (HFSPLUS_IS_RSRC(inode))
-                inode = HFSPLUS_I(inode).rsrc_inode;
-        if (atomic_dec_and_test(&HFSPLUS_I(inode).opencnt)) {
+                inode = HFSPLUS_I(inode)->rsrc_inode;
+        if (atomic_dec_and_test(&HFSPLUS_I(inode)->opencnt)) {
                 mutex_lock(&inode->i_mutex);
                 hfsplus_file_truncate(inode);
                 if (inode->i_flags & S_DEAD) {
-                        hfsplus_delete_cat(inode->i_ino, HFSPLUS_SB(sb).hidden_dir, NULL);
+                        hfsplus_delete_cat(inode->i_ino,
+                                           HFSPLUS_SB(sb)->hidden_dir, NULL);
                         hfsplus_delete_inode(inode);
                 }
                 mutex_unlock(&inode->i_mutex);
@@ -361,47 +352,52 @@ static const struct file_operations hfsplus_file_operations = {
 
 struct inode *hfsplus_new_inode(struct super_block *sb, int mode)
 {
+        struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
         struct inode *inode = new_inode(sb);
+        struct hfsplus_inode_info *hip;
+
         if (!inode)
                 return NULL;
 
-        inode->i_ino = HFSPLUS_SB(sb).next_cnid++;
+        inode->i_ino = sbi->next_cnid++;
         inode->i_mode = mode;
         inode->i_uid = current_fsuid();
         inode->i_gid = current_fsgid();
         inode->i_nlink = 1;
         inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC;
-        INIT_LIST_HEAD(&HFSPLUS_I(inode).open_dir_list);
-        mutex_init(&HFSPLUS_I(inode).extents_lock);
-        atomic_set(&HFSPLUS_I(inode).opencnt, 0);
-        HFSPLUS_I(inode).flags = 0;
-        memset(HFSPLUS_I(inode).first_extents, 0, sizeof(hfsplus_extent_rec));
-        memset(HFSPLUS_I(inode).cached_extents, 0, sizeof(hfsplus_extent_rec));
-        HFSPLUS_I(inode).alloc_blocks = 0;
-        HFSPLUS_I(inode).first_blocks = 0;
-        HFSPLUS_I(inode).cached_start = 0;
-        HFSPLUS_I(inode).cached_blocks = 0;
-        HFSPLUS_I(inode).phys_size = 0;
-        HFSPLUS_I(inode).fs_blocks = 0;
-        HFSPLUS_I(inode).rsrc_inode = NULL;
+
+        hip = HFSPLUS_I(inode);
+        INIT_LIST_HEAD(&hip->open_dir_list);
+        mutex_init(&hip->extents_lock);
+        atomic_set(&hip->opencnt, 0);
+        hip->flags = 0;
+        memset(hip->first_extents, 0, sizeof(hfsplus_extent_rec));
+        memset(hip->cached_extents, 0, sizeof(hfsplus_extent_rec));
+        hip->alloc_blocks = 0;
+        hip->first_blocks = 0;
+        hip->cached_start = 0;
+        hip->cached_blocks = 0;
+        hip->phys_size = 0;
+        hip->fs_blocks = 0;
+        hip->rsrc_inode = NULL;
         if (S_ISDIR(inode->i_mode)) {
                 inode->i_size = 2;
-                HFSPLUS_SB(sb).folder_count++;
+                sbi->folder_count++;
                 inode->i_op = &hfsplus_dir_inode_operations;
                 inode->i_fop = &hfsplus_dir_operations;
         } else if (S_ISREG(inode->i_mode)) {
-                HFSPLUS_SB(sb).file_count++;
+                sbi->file_count++;
                 inode->i_op = &hfsplus_file_inode_operations;
                 inode->i_fop = &hfsplus_file_operations;
                 inode->i_mapping->a_ops = &hfsplus_aops;
-                HFSPLUS_I(inode).clump_blocks = HFSPLUS_SB(sb).data_clump_blocks;
+                hip->clump_blocks = sbi->data_clump_blocks;
         } else if (S_ISLNK(inode->i_mode)) {
-                HFSPLUS_SB(sb).file_count++;
+                sbi->file_count++;
                 inode->i_op = &page_symlink_inode_operations;
                 inode->i_mapping->a_ops = &hfsplus_aops;
-                HFSPLUS_I(inode).clump_blocks = 1;
+                hip->clump_blocks = 1;
         } else
-                HFSPLUS_SB(sb).file_count++;
+                sbi->file_count++;
         insert_inode_hash(inode);
         mark_inode_dirty(inode);
         sb->s_dirt = 1;
@@ -414,11 +410,11 @@ void hfsplus_delete_inode(struct inode *inode)
         struct super_block *sb = inode->i_sb;
 
         if (S_ISDIR(inode->i_mode)) {
-                HFSPLUS_SB(sb).folder_count--;
+                HFSPLUS_SB(sb)->folder_count--;
                 sb->s_dirt = 1;
                 return;
         }
-        HFSPLUS_SB(sb).file_count--;
+        HFSPLUS_SB(sb)->file_count--;
         if (S_ISREG(inode->i_mode)) {
                 if (!inode->i_nlink) {
                         inode->i_size = 0;
@@ -434,34 +430,39 @@ void hfsplus_delete_inode(struct inode *inode)
 void hfsplus_inode_read_fork(struct inode *inode, struct hfsplus_fork_raw *fork)
 {
         struct super_block *sb = inode->i_sb;
+        struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
+        struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
         u32 count;
         int i;
 
-        memcpy(&HFSPLUS_I(inode).first_extents, &fork->extents,
-               sizeof(hfsplus_extent_rec));
+        memcpy(&hip->first_extents, &fork->extents, sizeof(hfsplus_extent_rec));
         for (count = 0, i = 0; i < 8; i++)
                 count += be32_to_cpu(fork->extents[i].block_count);
-        HFSPLUS_I(inode).first_blocks = count;
-        memset(HFSPLUS_I(inode).cached_extents, 0, sizeof(hfsplus_extent_rec));
-        HFSPLUS_I(inode).cached_start = 0;
-        HFSPLUS_I(inode).cached_blocks = 0;
-
-        HFSPLUS_I(inode).alloc_blocks = be32_to_cpu(fork->total_blocks);
-        inode->i_size = HFSPLUS_I(inode).phys_size = be64_to_cpu(fork->total_size);
-        HFSPLUS_I(inode).fs_blocks = (inode->i_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits;
-        inode_set_bytes(inode, HFSPLUS_I(inode).fs_blocks << sb->s_blocksize_bits);
-        HFSPLUS_I(inode).clump_blocks = be32_to_cpu(fork->clump_size) >> HFSPLUS_SB(sb).alloc_blksz_shift;
-        if (!HFSPLUS_I(inode).clump_blocks)
-                HFSPLUS_I(inode).clump_blocks = HFSPLUS_IS_RSRC(inode) ? HFSPLUS_SB(sb).rsrc_clump_blocks :
-                                HFSPLUS_SB(sb).data_clump_blocks;
+        hip->first_blocks = count;
+        memset(hip->cached_extents, 0, sizeof(hfsplus_extent_rec));
+        hip->cached_start = 0;
+        hip->cached_blocks = 0;
+
+        hip->alloc_blocks = be32_to_cpu(fork->total_blocks);
+        hip->phys_size = inode->i_size = be64_to_cpu(fork->total_size);
+        hip->fs_blocks =
+                (inode->i_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits;
+        inode_set_bytes(inode, hip->fs_blocks << sb->s_blocksize_bits);
+        hip->clump_blocks =
+                be32_to_cpu(fork->clump_size) >> sbi->alloc_blksz_shift;
+        if (!hip->clump_blocks) {
+                hip->clump_blocks = HFSPLUS_IS_RSRC(inode) ?
+                        sbi->rsrc_clump_blocks :
+                        sbi->data_clump_blocks;
+        }
 }
 
 void hfsplus_inode_write_fork(struct inode *inode, struct hfsplus_fork_raw *fork)
 {
-        memcpy(&fork->extents, &HFSPLUS_I(inode).first_extents,
+        memcpy(&fork->extents, &HFSPLUS_I(inode)->first_extents,
                sizeof(hfsplus_extent_rec));
         fork->total_size = cpu_to_be64(inode->i_size);
-        fork->total_blocks = cpu_to_be32(HFSPLUS_I(inode).alloc_blocks);
+        fork->total_blocks = cpu_to_be32(HFSPLUS_I(inode)->alloc_blocks);
 }
 
 int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd)
@@ -472,7 +473,7 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd)
 
         type = hfs_bnode_read_u16(fd->bnode, fd->entryoffset);
 
-        HFSPLUS_I(inode).dev = 0;
+        HFSPLUS_I(inode)->linkid = 0;
         if (type == HFSPLUS_FOLDER) {
                 struct hfsplus_cat_folder *folder = &entry.folder;
 
@@ -486,8 +487,8 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd)
                 inode->i_atime = hfsp_mt2ut(folder->access_date);
                 inode->i_mtime = hfsp_mt2ut(folder->content_mod_date);
                 inode->i_ctime = hfsp_mt2ut(folder->attribute_mod_date);
-                HFSPLUS_I(inode).create_date = folder->create_date;
-                HFSPLUS_I(inode).fs_blocks = 0;
+                HFSPLUS_I(inode)->create_date = folder->create_date;
+                HFSPLUS_I(inode)->fs_blocks = 0;
                 inode->i_op = &hfsplus_dir_inode_operations;
                 inode->i_fop = &hfsplus_dir_operations;
         } else if (type == HFSPLUS_FILE) {
@@ -518,7 +519,7 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd)
                 inode->i_atime = hfsp_mt2ut(file->access_date);
                 inode->i_mtime = hfsp_mt2ut(file->content_mod_date);
                 inode->i_ctime = hfsp_mt2ut(file->attribute_mod_date);
-                HFSPLUS_I(inode).create_date = file->create_date;
+                HFSPLUS_I(inode)->create_date = file->create_date;
         } else {
                 printk(KERN_ERR "hfs: bad catalog entry used to create inode\n");
                 res = -EIO;
@@ -533,12 +534,12 @@ int hfsplus_cat_write_inode(struct inode *inode)
         hfsplus_cat_entry entry;
 
         if (HFSPLUS_IS_RSRC(inode))
-                main_inode = HFSPLUS_I(inode).rsrc_inode;
+                main_inode = HFSPLUS_I(inode)->rsrc_inode;
 
         if (!main_inode->i_nlink)
                 return 0;
 
-        if (hfs_find_init(HFSPLUS_SB(main_inode->i_sb).cat_tree, &fd))
+        if (hfs_find_init(HFSPLUS_SB(main_inode->i_sb)->cat_tree, &fd))
                 /* panic? */
                 return -EIO;
 
@@ -554,7 +555,7 @@ int hfsplus_cat_write_inode(struct inode *inode)
                 hfs_bnode_read(fd.bnode, &entry, fd.entryoffset,
                                         sizeof(struct hfsplus_cat_folder));
                 /* simple node checks? */
-                hfsplus_set_perms(inode, &folder->permissions);
+                hfsplus_cat_set_perms(inode, &folder->permissions);
                 folder->access_date = hfsp_ut2mt(inode->i_atime);
                 folder->content_mod_date = hfsp_ut2mt(inode->i_mtime);
                 folder->attribute_mod_date = hfsp_ut2mt(inode->i_ctime);
@@ -576,11 +577,7 @@ int hfsplus_cat_write_inode(struct inode *inode)
                 hfs_bnode_read(fd.bnode, &entry, fd.entryoffset,
                                         sizeof(struct hfsplus_cat_file));
                 hfsplus_inode_write_fork(inode, &file->data_fork);
-                if (S_ISREG(inode->i_mode))
-                        HFSPLUS_I(inode).dev = inode->i_nlink;
-                if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode))
-                        HFSPLUS_I(inode).dev = kdev_t_to_nr(inode->i_rdev);
-                hfsplus_set_perms(inode, &file->permissions);
+                hfsplus_cat_set_perms(inode, &file->permissions);
                 if ((file->permissions.rootflags | file->permissions.userflags) & HFSPLUS_FLG_IMMUTABLE)
                         file->flags |= cpu_to_be16(HFSPLUS_FILE_LOCKED);
                 else
diff --git a/fs/hfsplus/ioctl.c b/fs/hfsplus/ioctl.c
index ac405f099026..5b4667e08ef7 100644
--- a/fs/hfsplus/ioctl.c
+++ b/fs/hfsplus/ioctl.c
@@ -17,83 +17,98 @@
 #include <linux/mount.h>
 #include <linux/sched.h>
 #include <linux/xattr.h>
-#include <linux/smp_lock.h>
 #include <asm/uaccess.h>
 #include "hfsplus_fs.h"
 
-long hfsplus_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+static int hfsplus_ioctl_getflags(struct file *file, int __user *user_flags)
 {
-        struct inode *inode = filp->f_path.dentry->d_inode;
+        struct inode *inode = file->f_path.dentry->d_inode;
+        struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
+        unsigned int flags = 0;
+
+        if (inode->i_flags & S_IMMUTABLE)
+                flags |= FS_IMMUTABLE_FL;
+        if (inode->i_flags |= S_APPEND)
+                flags |= FS_APPEND_FL;
+        if (hip->userflags & HFSPLUS_FLG_NODUMP)
+                flags |= FS_NODUMP_FL;
+
+        return put_user(flags, user_flags);
+}
+
+static int hfsplus_ioctl_setflags(struct file *file, int __user *user_flags)
+{
+        struct inode *inode = file->f_path.dentry->d_inode;
+        struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
         unsigned int flags;
+        int err = 0;
 
-        lock_kernel();
-        switch (cmd) {
-        case HFSPLUS_IOC_EXT2_GETFLAGS:
-                flags = 0;
-                if (HFSPLUS_I(inode).rootflags & HFSPLUS_FLG_IMMUTABLE)
-                        flags |= FS_IMMUTABLE_FL; /* EXT2_IMMUTABLE_FL */
-                if (HFSPLUS_I(inode).rootflags & HFSPLUS_FLG_APPEND)
-                        flags |= FS_APPEND_FL; /* EXT2_APPEND_FL */
-                if (HFSPLUS_I(inode).userflags & HFSPLUS_FLG_NODUMP)
-                        flags |= FS_NODUMP_FL; /* EXT2_NODUMP_FL */
-                return put_user(flags, (int __user *)arg);
-        case HFSPLUS_IOC_EXT2_SETFLAGS: {
-                int err = 0;
-                err = mnt_want_write(filp->f_path.mnt);
-                if (err) {
-                        unlock_kernel();
-                        return err;
-                }
+        err = mnt_want_write(file->f_path.mnt);
+        if (err)
+                goto out;
 
-                if (!is_owner_or_cap(inode)) {
-                        err = -EACCES;
-                        goto setflags_out;
-                }
-                if (get_user(flags, (int __user *)arg)) {
-                        err = -EFAULT;
-                        goto setflags_out;
-                }
-                if (flags & (FS_IMMUTABLE_FL|FS_APPEND_FL) ||
-                    HFSPLUS_I(inode).rootflags & (HFSPLUS_FLG_IMMUTABLE|HFSPLUS_FLG_APPEND)) {
-                        if (!capable(CAP_LINUX_IMMUTABLE)) {
-                                err = -EPERM;
-                                goto setflags_out;
-                        }
-                }
+        if (!is_owner_or_cap(inode)) {
+                err = -EACCES;
+                goto out_drop_write;
+        }
 
-                /* don't silently ignore unsupported ext2 flags */
-                if (flags & ~(FS_IMMUTABLE_FL|FS_APPEND_FL|FS_NODUMP_FL)) {
-                        err = -EOPNOTSUPP;
-                        goto setflags_out;
-                }
-                if (flags & FS_IMMUTABLE_FL) { /* EXT2_IMMUTABLE_FL */
-                        inode->i_flags |= S_IMMUTABLE;
-                        HFSPLUS_I(inode).rootflags |= HFSPLUS_FLG_IMMUTABLE;
-                } else {
-                        inode->i_flags &= ~S_IMMUTABLE;
-                        HFSPLUS_I(inode).rootflags &= ~HFSPLUS_FLG_IMMUTABLE;
-                }
-                if (flags & FS_APPEND_FL) { /* EXT2_APPEND_FL */
-                        inode->i_flags |= S_APPEND;
-                        HFSPLUS_I(inode).rootflags |= HFSPLUS_FLG_APPEND;
-                } else {
-                        inode->i_flags &= ~S_APPEND;
-                        HFSPLUS_I(inode).rootflags &= ~HFSPLUS_FLG_APPEND;
+        if (get_user(flags, user_flags)) {
+                err = -EFAULT;
+                goto out_drop_write;
+        }
+
+        mutex_lock(&inode->i_mutex);
+
+        if ((flags & (FS_IMMUTABLE_FL|FS_APPEND_FL)) ||
+            inode->i_flags & (S_IMMUTABLE|S_APPEND)) {
+                if (!capable(CAP_LINUX_IMMUTABLE)) {
+                        err = -EPERM;
+                        goto out_unlock_inode;
                 }
-                if (flags & FS_NODUMP_FL) /* EXT2_NODUMP_FL */
-                        HFSPLUS_I(inode).userflags |= HFSPLUS_FLG_NODUMP;
-                else
-                        HFSPLUS_I(inode).userflags &= ~HFSPLUS_FLG_NODUMP;
-
-                inode->i_ctime = CURRENT_TIME_SEC;
-                mark_inode_dirty(inode);
-setflags_out:
-                mnt_drop_write(filp->f_path.mnt);
-                unlock_kernel();
-                return err;
         }
+
+        /* don't silently ignore unsupported ext2 flags */
+        if (flags & ~(FS_IMMUTABLE_FL|FS_APPEND_FL|FS_NODUMP_FL)) {
+                err = -EOPNOTSUPP;
+                goto out_unlock_inode;
+        }
+
+        if (flags & FS_IMMUTABLE_FL)
+                inode->i_flags |= S_IMMUTABLE;
+        else
+                inode->i_flags &= ~S_IMMUTABLE;
+
+        if (flags & FS_APPEND_FL)
+                inode->i_flags |= S_APPEND;
+        else
+                inode->i_flags &= ~S_APPEND;
+
+        if (flags & FS_NODUMP_FL)
+                hip->userflags |= HFSPLUS_FLG_NODUMP;
+        else
+                hip->userflags &= ~HFSPLUS_FLG_NODUMP;
+
+        inode->i_ctime = CURRENT_TIME_SEC;
+        mark_inode_dirty(inode);
+
+out_unlock_inode:
+        mutex_lock(&inode->i_mutex);
+out_drop_write:
+        mnt_drop_write(file->f_path.mnt);
+out:
+        return err;
+}
+
+long hfsplus_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+        void __user *argp = (void __user *)arg;
+
+        switch (cmd) {
+        case HFSPLUS_IOC_EXT2_GETFLAGS:
+                return hfsplus_ioctl_getflags(file, argp);
+        case HFSPLUS_IOC_EXT2_SETFLAGS:
+                return hfsplus_ioctl_setflags(file, argp);
         default:
-                unlock_kernel();
                 return -ENOTTY;
         }
 }
@@ -110,7 +125,7 @@ int hfsplus_setxattr(struct dentry *dentry, const char *name,
         if (!S_ISREG(inode->i_mode) || HFSPLUS_IS_RSRC(inode))
                 return -EOPNOTSUPP;
 
-        res = hfs_find_init(HFSPLUS_SB(inode->i_sb).cat_tree, &fd);
+        res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd);
         if (res)
                 return res;
         res = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd);
@@ -153,7 +168,7 @@ ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name,
                 return -EOPNOTSUPP;
 
         if (size) {
-                res = hfs_find_init(HFSPLUS_SB(inode->i_sb).cat_tree, &fd);
+                res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd);
                 if (res)
                         return res;
                 res = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd);
@@ -177,7 +192,7 @@ ssize_t hfsplus_getxattr(struct dentry *dentry, const char *name,
                 } else
                         res = size ? -ERANGE : 4;
         } else
-                res = -ENODATA;
+                res = -EOPNOTSUPP;
 out:
         if (size)
                 hfs_find_exit(&fd);
diff --git a/fs/hfsplus/options.c b/fs/hfsplus/options.c
index 572628b4b07d..f9ab276a4d8d 100644
--- a/fs/hfsplus/options.c
+++ b/fs/hfsplus/options.c
@@ -143,13 +143,13 @@ int hfsplus_parse_options(char *input, struct hfsplus_sb_info *sbi)
                         kfree(p);
                         break;
                 case opt_decompose:
-                        sbi->flags &= ~HFSPLUS_SB_NODECOMPOSE;
+                        clear_bit(HFSPLUS_SB_NODECOMPOSE, &sbi->flags);
                         break;
                 case opt_nodecompose:
-                        sbi->flags |= HFSPLUS_SB_NODECOMPOSE;
+                        set_bit(HFSPLUS_SB_NODECOMPOSE, &sbi->flags);
                         break;
                 case opt_force:
-                        sbi->flags |= HFSPLUS_SB_FORCE;
+                        set_bit(HFSPLUS_SB_FORCE, &sbi->flags);
                         break;
                 default:
                         return 0;
@@ -171,7 +171,7 @@ done:
 
 int hfsplus_show_options(struct seq_file *seq, struct vfsmount *mnt)
 {
-        struct hfsplus_sb_info *sbi = &HFSPLUS_SB(mnt->mnt_sb);
+        struct hfsplus_sb_info *sbi = HFSPLUS_SB(mnt->mnt_sb);
 
         if (sbi->creator != HFSPLUS_DEF_CR_TYPE)
                 seq_printf(seq, ",creator=%.4s", (char *)&sbi->creator);
@@ -184,7 +184,7 @@ int hfsplus_show_options(struct seq_file *seq, struct vfsmount *mnt)
                 seq_printf(seq, ",session=%u", sbi->session);
         if (sbi->nls)
                 seq_printf(seq, ",nls=%s", sbi->nls->charset);
-        if (sbi->flags & HFSPLUS_SB_NODECOMPOSE)
+        if (test_bit(HFSPLUS_SB_NODECOMPOSE, &sbi->flags))
                 seq_printf(seq, ",nodecompose");
         return 0;
 }
diff --git a/fs/hfsplus/part_tbl.c b/fs/hfsplus/part_tbl.c
index 1528a6fd0299..208b16c645cc 100644
--- a/fs/hfsplus/part_tbl.c
+++ b/fs/hfsplus/part_tbl.c
@@ -74,6 +74,7 @@ struct old_pmap {
 int hfs_part_find(struct super_block *sb,
                   sector_t *part_start, sector_t *part_size)
 {
+        struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
         struct buffer_head *bh;
         __be16 *data;
         int i, size, res;
@@ -95,7 +96,7 @@ int hfs_part_find(struct super_block *sb,
                 for (i = 0; i < size; p++, i++) {
                         if (p->pdStart && p->pdSize &&
                             p->pdFSID == cpu_to_be32(0x54465331)/*"TFS1"*/ &&
-                            (HFSPLUS_SB(sb).part < 0 || HFSPLUS_SB(sb).part == i)) {
+                            (sbi->part < 0 || sbi->part == i)) {
                                 *part_start += be32_to_cpu(p->pdStart);
                                 *part_size = be32_to_cpu(p->pdSize);
                                 res = 0;
@@ -111,7 +112,7 @@ int hfs_part_find(struct super_block *sb,
                 size = be32_to_cpu(pm->pmMapBlkCnt);
                 for (i = 0; i < size;) {
                         if (!memcmp(pm->pmPartType,"Apple_HFS", 9) &&
-                            (HFSPLUS_SB(sb).part < 0 || HFSPLUS_SB(sb).part == i)) {
+                            (sbi->part < 0 || sbi->part == i)) {
                                 *part_start += be32_to_cpu(pm->pmPyPartStart);
                                 *part_size = be32_to_cpu(pm->pmPartBlkCnt);
                                 res = 0;
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 3b55c050c742..9a88d7536103 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -12,7 +12,6 @@
 #include <linux/pagemap.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/vfs.h>
 #include <linux/nls.h>
 
@@ -21,40 +20,11 @@ static void hfsplus_destroy_inode(struct inode *inode);
 
 #include "hfsplus_fs.h"
 
-struct inode *hfsplus_iget(struct super_block *sb, unsigned long ino)
+static int hfsplus_system_read_inode(struct inode *inode)
 {
-        struct hfs_find_data fd;
-        struct hfsplus_vh *vhdr;
-        struct inode *inode;
-        long err = -EIO;
-
-        inode = iget_locked(sb, ino);
-        if (!inode)
-                return ERR_PTR(-ENOMEM);
-        if (!(inode->i_state & I_NEW))
-                return inode;
+        struct hfsplus_vh *vhdr = HFSPLUS_SB(inode->i_sb)->s_vhdr;
 
-        INIT_LIST_HEAD(&HFSPLUS_I(inode).open_dir_list);
-        mutex_init(&HFSPLUS_I(inode).extents_lock);
-        HFSPLUS_I(inode).flags = 0;
-        HFSPLUS_I(inode).rsrc_inode = NULL;
-        atomic_set(&HFSPLUS_I(inode).opencnt, 0);
-
-        if (inode->i_ino >= HFSPLUS_FIRSTUSER_CNID) {
-        read_inode:
-                hfs_find_init(HFSPLUS_SB(inode->i_sb).cat_tree, &fd);
-                err = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd);
-                if (!err)
-                        err = hfsplus_cat_read_inode(inode, &fd);
-                hfs_find_exit(&fd);
-                if (err)
-                        goto bad_inode;
-                goto done;
-        }
-        vhdr = HFSPLUS_SB(inode->i_sb).s_vhdr;
-        switch(inode->i_ino) {
-        case HFSPLUS_ROOT_CNID:
-                goto read_inode;
+        switch (inode->i_ino) {
         case HFSPLUS_EXT_CNID:
                 hfsplus_inode_read_fork(inode, &vhdr->ext_file);
                 inode->i_mapping->a_ops = &hfsplus_btree_aops;
@@ -75,74 +45,101 @@ struct inode *hfsplus_iget(struct super_block *sb, unsigned long ino)
                 inode->i_mapping->a_ops = &hfsplus_btree_aops;
                 break;
         default:
-                goto bad_inode;
+                return -EIO;
+        }
+
+        return 0;
+}
+
+struct inode *hfsplus_iget(struct super_block *sb, unsigned long ino)
+{
+        struct hfs_find_data fd;
+        struct inode *inode;
+        int err;
+
+        inode = iget_locked(sb, ino);
+        if (!inode)
+                return ERR_PTR(-ENOMEM);
+        if (!(inode->i_state & I_NEW))
+                return inode;
+
+        INIT_LIST_HEAD(&HFSPLUS_I(inode)->open_dir_list);
+        mutex_init(&HFSPLUS_I(inode)->extents_lock);
+        HFSPLUS_I(inode)->flags = 0;
+        HFSPLUS_I(inode)->rsrc_inode = NULL;
+        atomic_set(&HFSPLUS_I(inode)->opencnt, 0);
+
+        if (inode->i_ino >= HFSPLUS_FIRSTUSER_CNID ||
+            inode->i_ino == HFSPLUS_ROOT_CNID) {
+                hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &fd);
+                err = hfsplus_find_cat(inode->i_sb, inode->i_ino, &fd);
+                if (!err)
+                        err = hfsplus_cat_read_inode(inode, &fd);
+                hfs_find_exit(&fd);
+        } else {
+                err = hfsplus_system_read_inode(inode);
+        }
+
+        if (err) {
+                iget_failed(inode);
+                return ERR_PTR(err);
         }
 
-done:
         unlock_new_inode(inode);
         return inode;
-
-bad_inode:
-        iget_failed(inode);
-        return ERR_PTR(err);
 }
 
-static int hfsplus_write_inode(struct inode *inode,
-                struct writeback_control *wbc)
+static int hfsplus_system_write_inode(struct inode *inode)
 {
-        struct hfsplus_vh *vhdr;
-        int ret = 0;
+        struct hfsplus_sb_info *sbi = HFSPLUS_SB(inode->i_sb);
+        struct hfsplus_vh *vhdr = sbi->s_vhdr;
+        struct hfsplus_fork_raw *fork;
+        struct hfs_btree *tree = NULL;
 
-        dprint(DBG_INODE, "hfsplus_write_inode: %lu\n", inode->i_ino);
-        hfsplus_ext_write_extent(inode);
-        if (inode->i_ino >= HFSPLUS_FIRSTUSER_CNID) {
-                return hfsplus_cat_write_inode(inode);
-        }
-        vhdr = HFSPLUS_SB(inode->i_sb).s_vhdr;
         switch (inode->i_ino) {
-        case HFSPLUS_ROOT_CNID:
-                ret = hfsplus_cat_write_inode(inode);
-                break;
         case HFSPLUS_EXT_CNID:
-                if (vhdr->ext_file.total_size != cpu_to_be64(inode->i_size)) {
-                        HFSPLUS_SB(inode->i_sb).flags |= HFSPLUS_SB_WRITEBACKUP;
-                        inode->i_sb->s_dirt = 1;
-                }
-                hfsplus_inode_write_fork(inode, &vhdr->ext_file);
-                hfs_btree_write(HFSPLUS_SB(inode->i_sb).ext_tree);
+                fork = &vhdr->ext_file;
+                tree = sbi->ext_tree;
                 break;
         case HFSPLUS_CAT_CNID:
-                if (vhdr->cat_file.total_size != cpu_to_be64(inode->i_size)) {
-                        HFSPLUS_SB(inode->i_sb).flags |= HFSPLUS_SB_WRITEBACKUP;
-                        inode->i_sb->s_dirt = 1;
-                }
-                hfsplus_inode_write_fork(inode, &vhdr->cat_file);
-                hfs_btree_write(HFSPLUS_SB(inode->i_sb).cat_tree);
+                fork = &vhdr->cat_file;
+                tree = sbi->cat_tree;
                 break;
         case HFSPLUS_ALLOC_CNID:
-                if (vhdr->alloc_file.total_size != cpu_to_be64(inode->i_size)) {
-                        HFSPLUS_SB(inode->i_sb).flags |= HFSPLUS_SB_WRITEBACKUP;
-                        inode->i_sb->s_dirt = 1;
-                }
-                hfsplus_inode_write_fork(inode, &vhdr->alloc_file);
+                fork = &vhdr->alloc_file;
                 break;
         case HFSPLUS_START_CNID:
-                if (vhdr->start_file.total_size != cpu_to_be64(inode->i_size)) {
-                        HFSPLUS_SB(inode->i_sb).flags |= HFSPLUS_SB_WRITEBACKUP;
-                        inode->i_sb->s_dirt = 1;
-                }
-                hfsplus_inode_write_fork(inode, &vhdr->start_file);
+                fork = &vhdr->start_file;
                 break;
         case HFSPLUS_ATTR_CNID:
-                if (vhdr->attr_file.total_size != cpu_to_be64(inode->i_size)) {
-                        HFSPLUS_SB(inode->i_sb).flags |= HFSPLUS_SB_WRITEBACKUP;
-                        inode->i_sb->s_dirt = 1;
-                }
-                hfsplus_inode_write_fork(inode, &vhdr->attr_file);
-                hfs_btree_write(HFSPLUS_SB(inode->i_sb).attr_tree);
-                break;
+                fork = &vhdr->attr_file;
+                tree = sbi->attr_tree;
+        default:
+                return -EIO;
+        }
+
+        if (fork->total_size != cpu_to_be64(inode->i_size)) {
+                set_bit(HFSPLUS_SB_WRITEBACKUP, &sbi->flags);
+                inode->i_sb->s_dirt = 1;
         }
-        return ret;
+        hfsplus_inode_write_fork(inode, fork);
+        if (tree)
+                hfs_btree_write(tree);
+        return 0;
+}
+
+static int hfsplus_write_inode(struct inode *inode,
+                struct writeback_control *wbc)
+{
+        dprint(DBG_INODE, "hfsplus_write_inode: %lu\n", inode->i_ino);
+
+        hfsplus_ext_write_extent(inode);
+
+        if (inode->i_ino >= HFSPLUS_FIRSTUSER_CNID ||
+            inode->i_ino == HFSPLUS_ROOT_CNID)
+                return hfsplus_cat_write_inode(inode);
+        else
+                return hfsplus_system_write_inode(inode);
 }
 
 static void hfsplus_evict_inode(struct inode *inode)
@@ -151,51 +148,53 @@ static void hfsplus_evict_inode(struct inode *inode)
         truncate_inode_pages(&inode->i_data, 0);
         end_writeback(inode);
         if (HFSPLUS_IS_RSRC(inode)) {
-                HFSPLUS_I(HFSPLUS_I(inode).rsrc_inode).rsrc_inode = NULL;
-                iput(HFSPLUS_I(inode).rsrc_inode);
+                HFSPLUS_I(HFSPLUS_I(inode)->rsrc_inode)->rsrc_inode = NULL;
+                iput(HFSPLUS_I(inode)->rsrc_inode);
         }
 }
 
 int hfsplus_sync_fs(struct super_block *sb, int wait)
 {
-        struct hfsplus_vh *vhdr = HFSPLUS_SB(sb).s_vhdr;
+        struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
+        struct hfsplus_vh *vhdr = sbi->s_vhdr;
 
         dprint(DBG_SUPER, "hfsplus_write_super\n");
 
-        lock_super(sb);
+        mutex_lock(&sbi->vh_mutex);
+        mutex_lock(&sbi->alloc_mutex);
         sb->s_dirt = 0;
 
-        vhdr->free_blocks = cpu_to_be32(HFSPLUS_SB(sb).free_blocks);
-        vhdr->next_alloc = cpu_to_be32(HFSPLUS_SB(sb).next_alloc);
-        vhdr->next_cnid = cpu_to_be32(HFSPLUS_SB(sb).next_cnid);
-        vhdr->folder_count = cpu_to_be32(HFSPLUS_SB(sb).folder_count);
-        vhdr->file_count = cpu_to_be32(HFSPLUS_SB(sb).file_count);
+        vhdr->free_blocks = cpu_to_be32(sbi->free_blocks);
+        vhdr->next_cnid = cpu_to_be32(sbi->next_cnid);
+        vhdr->folder_count = cpu_to_be32(sbi->folder_count);
+        vhdr->file_count = cpu_to_be32(sbi->file_count);
 
-        mark_buffer_dirty(HFSPLUS_SB(sb).s_vhbh);
-        if (HFSPLUS_SB(sb).flags & HFSPLUS_SB_WRITEBACKUP) {
-                if (HFSPLUS_SB(sb).sect_count) {
+        mark_buffer_dirty(sbi->s_vhbh);
+        if (test_and_clear_bit(HFSPLUS_SB_WRITEBACKUP, &sbi->flags)) {
+                if (sbi->sect_count) {
                         struct buffer_head *bh;
                         u32 block, offset;
 
-                        block = HFSPLUS_SB(sb).blockoffset;
-                        block += (HFSPLUS_SB(sb).sect_count - 2) >> (sb->s_blocksize_bits - 9);
-                        offset = ((HFSPLUS_SB(sb).sect_count - 2) << 9) & (sb->s_blocksize - 1);
-                        printk(KERN_DEBUG "hfs: backup: %u,%u,%u,%u\n", HFSPLUS_SB(sb).blockoffset,
-                                HFSPLUS_SB(sb).sect_count, block, offset);
+                        block = sbi->blockoffset;
+                        block += (sbi->sect_count - 2) >> (sb->s_blocksize_bits - 9);
+                        offset = ((sbi->sect_count - 2) << 9) & (sb->s_blocksize - 1);
+                        printk(KERN_DEBUG "hfs: backup: %u,%u,%u,%u\n",
+                                          sbi->blockoffset, sbi->sect_count,
+                                          block, offset);
                         bh = sb_bread(sb, block);
                         if (bh) {
                                 vhdr = (struct hfsplus_vh *)(bh->b_data + offset);
                                 if (be16_to_cpu(vhdr->signature) == HFSPLUS_VOLHEAD_SIG) {
-                                        memcpy(vhdr, HFSPLUS_SB(sb).s_vhdr, sizeof(*vhdr));
+                                        memcpy(vhdr, sbi->s_vhdr, sizeof(*vhdr));
                                         mark_buffer_dirty(bh);
                                         brelse(bh);
                                 } else
                                         printk(KERN_WARNING "hfs: backup not found!\n");
                         }
                 }
-                HFSPLUS_SB(sb).flags &= ~HFSPLUS_SB_WRITEBACKUP;
         }
-        unlock_super(sb);
+        mutex_unlock(&sbi->alloc_mutex);
+        mutex_unlock(&sbi->vh_mutex);
         return 0;
 }
 
@@ -209,48 +208,48 @@ static void hfsplus_write_super(struct super_block *sb)
 
 static void hfsplus_put_super(struct super_block *sb)
 {
+        struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
+
         dprint(DBG_SUPER, "hfsplus_put_super\n");
+
         if (!sb->s_fs_info)
                 return;
 
-        lock_kernel();
-
         if (sb->s_dirt)
                 hfsplus_write_super(sb);
-        if (!(sb->s_flags & MS_RDONLY) && HFSPLUS_SB(sb).s_vhdr) {
-                struct hfsplus_vh *vhdr = HFSPLUS_SB(sb).s_vhdr;
+        if (!(sb->s_flags & MS_RDONLY) && sbi->s_vhdr) {
+                struct hfsplus_vh *vhdr = sbi->s_vhdr;
 
                 vhdr->modify_date = hfsp_now2mt();
                 vhdr->attributes |= cpu_to_be32(HFSPLUS_VOL_UNMNT);
                 vhdr->attributes &= cpu_to_be32(~HFSPLUS_VOL_INCNSTNT);
-                mark_buffer_dirty(HFSPLUS_SB(sb).s_vhbh);
-                sync_dirty_buffer(HFSPLUS_SB(sb).s_vhbh);
+                mark_buffer_dirty(sbi->s_vhbh);
+                sync_dirty_buffer(sbi->s_vhbh);
         }
 
-        hfs_btree_close(HFSPLUS_SB(sb).cat_tree);
-        hfs_btree_close(HFSPLUS_SB(sb).ext_tree);
-        iput(HFSPLUS_SB(sb).alloc_file);
-        iput(HFSPLUS_SB(sb).hidden_dir);
-        brelse(HFSPLUS_SB(sb).s_vhbh);
-        unload_nls(HFSPLUS_SB(sb).nls);
+        hfs_btree_close(sbi->cat_tree);
+        hfs_btree_close(sbi->ext_tree);
+        iput(sbi->alloc_file);
+        iput(sbi->hidden_dir);
+        brelse(sbi->s_vhbh);
+        unload_nls(sbi->nls);
         kfree(sb->s_fs_info);
         sb->s_fs_info = NULL;
-
-        unlock_kernel();
 }
 
 static int hfsplus_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
         struct super_block *sb = dentry->d_sb;
+        struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
         u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
 
         buf->f_type = HFSPLUS_SUPER_MAGIC;
         buf->f_bsize = sb->s_blocksize;
-        buf->f_blocks = HFSPLUS_SB(sb).total_blocks << HFSPLUS_SB(sb).fs_shift;
-        buf->f_bfree = HFSPLUS_SB(sb).free_blocks << HFSPLUS_SB(sb).fs_shift;
+        buf->f_blocks = sbi->total_blocks << sbi->fs_shift;
+        buf->f_bfree = sbi->free_blocks << sbi->fs_shift;
         buf->f_bavail = buf->f_bfree;
         buf->f_files = 0xFFFFFFFF;
-        buf->f_ffree = 0xFFFFFFFF - HFSPLUS_SB(sb).next_cnid;
+        buf->f_ffree = 0xFFFFFFFF - sbi->next_cnid;
         buf->f_fsid.val[0] = (u32)id;
         buf->f_fsid.val[1] = (u32)(id >> 32);
         buf->f_namelen = HFSPLUS_MAX_STRLEN;
@@ -263,11 +262,11 @@ static int hfsplus_remount(struct super_block *sb, int *flags, char *data)
         if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
                 return 0;
         if (!(*flags & MS_RDONLY)) {
-                struct hfsplus_vh *vhdr = HFSPLUS_SB(sb).s_vhdr;
+                struct hfsplus_vh *vhdr = HFSPLUS_SB(sb)->s_vhdr;
                 struct hfsplus_sb_info sbi;
 
                 memset(&sbi, 0, sizeof(struct hfsplus_sb_info));
-                sbi.nls = HFSPLUS_SB(sb).nls;
+                sbi.nls = HFSPLUS_SB(sb)->nls;
                 if (!hfsplus_parse_options(data, &sbi))
                         return -EINVAL;
 
@@ -276,7 +275,7 @@ static int hfsplus_remount(struct super_block *sb, int *flags, char *data)
                                "running fsck.hfsplus is recommended.  leaving read-only.\n");
                         sb->s_flags |= MS_RDONLY;
                         *flags |= MS_RDONLY;
-                } else if (sbi.flags & HFSPLUS_SB_FORCE) {
+                } else if (test_bit(HFSPLUS_SB_FORCE, &sbi.flags)) {
                         /* nothing */
                 } else if (vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_SOFTLOCK)) {
                         printk(KERN_WARNING "hfs: filesystem is marked locked, leaving read-only.\n");
@@ -320,7 +319,8 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
                 return -ENOMEM;
 
         sb->s_fs_info = sbi;
-        INIT_HLIST_HEAD(&sbi->rsrc_inodes);
+        mutex_init(&sbi->alloc_mutex);
+        mutex_init(&sbi->vh_mutex);
         hfsplus_fill_defaults(sbi);
         if (!hfsplus_parse_options(data, sbi)) {
                 printk(KERN_ERR "hfs: unable to parse mount options\n");
@@ -344,7 +344,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
                 err = -EINVAL;
                 goto cleanup;
         }
-        vhdr = HFSPLUS_SB(sb).s_vhdr;
+        vhdr = sbi->s_vhdr;
 
         /* Copy parts of the volume header into the superblock */
         sb->s_magic = HFSPLUS_VOLHEAD_SIG;
@@ -353,18 +353,19 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
                 printk(KERN_ERR "hfs: wrong filesystem version\n");
                 goto cleanup;
         }
-        HFSPLUS_SB(sb).total_blocks = be32_to_cpu(vhdr->total_blocks);
-        HFSPLUS_SB(sb).free_blocks = be32_to_cpu(vhdr->free_blocks);
-        HFSPLUS_SB(sb).next_alloc = be32_to_cpu(vhdr->next_alloc);
-        HFSPLUS_SB(sb).next_cnid = be32_to_cpu(vhdr->next_cnid);
-        HFSPLUS_SB(sb).file_count = be32_to_cpu(vhdr->file_count);
-        HFSPLUS_SB(sb).folder_count = be32_to_cpu(vhdr->folder_count);
-        HFSPLUS_SB(sb).data_clump_blocks = be32_to_cpu(vhdr->data_clump_sz) >> HFSPLUS_SB(sb).alloc_blksz_shift;
-        if (!HFSPLUS_SB(sb).data_clump_blocks)
-                HFSPLUS_SB(sb).data_clump_blocks = 1;
-        HFSPLUS_SB(sb).rsrc_clump_blocks = be32_to_cpu(vhdr->rsrc_clump_sz) >> HFSPLUS_SB(sb).alloc_blksz_shift;
-        if (!HFSPLUS_SB(sb).rsrc_clump_blocks)
-                HFSPLUS_SB(sb).rsrc_clump_blocks = 1;
+        sbi->total_blocks = be32_to_cpu(vhdr->total_blocks);
+        sbi->free_blocks = be32_to_cpu(vhdr->free_blocks);
+        sbi->next_cnid = be32_to_cpu(vhdr->next_cnid);
+        sbi->file_count = be32_to_cpu(vhdr->file_count);
+        sbi->folder_count = be32_to_cpu(vhdr->folder_count);
+        sbi->data_clump_blocks =
+                be32_to_cpu(vhdr->data_clump_sz) >> sbi->alloc_blksz_shift;
+        if (!sbi->data_clump_blocks)
+                sbi->data_clump_blocks = 1;
+        sbi->rsrc_clump_blocks =
+                be32_to_cpu(vhdr->rsrc_clump_sz) >> sbi->alloc_blksz_shift;
+        if (!sbi->rsrc_clump_blocks)
+                sbi->rsrc_clump_blocks = 1;
 
         /* Set up operations so we can load metadata */
         sb->s_op = &hfsplus_sops;
@@ -374,7 +375,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
                 printk(KERN_WARNING "hfs: Filesystem was not cleanly unmounted, "
                        "running fsck.hfsplus is recommended.  mounting read-only.\n");
                 sb->s_flags |= MS_RDONLY;
-        } else if (sbi->flags & HFSPLUS_SB_FORCE) {
+        } else if (test_and_clear_bit(HFSPLUS_SB_FORCE, &sbi->flags)) {
                 /* nothing */
         } else if (vhdr->attributes & cpu_to_be32(HFSPLUS_VOL_SOFTLOCK)) {
                 printk(KERN_WARNING "hfs: Filesystem is marked locked, mounting read-only.\n");
@@ -384,16 +385,15 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
                        "use the force option at your own risk, mounting read-only.\n");
                 sb->s_flags |= MS_RDONLY;
         }
-        sbi->flags &= ~HFSPLUS_SB_FORCE;
 
         /* Load metadata objects (B*Trees) */
-        HFSPLUS_SB(sb).ext_tree = hfs_btree_open(sb, HFSPLUS_EXT_CNID);
-        if (!HFSPLUS_SB(sb).ext_tree) {
+        sbi->ext_tree = hfs_btree_open(sb, HFSPLUS_EXT_CNID);
+        if (!sbi->ext_tree) {
                 printk(KERN_ERR "hfs: failed to load extents file\n");
                 goto cleanup;
         }
-        HFSPLUS_SB(sb).cat_tree = hfs_btree_open(sb, HFSPLUS_CAT_CNID);
-        if (!HFSPLUS_SB(sb).cat_tree) {
+        sbi->cat_tree = hfs_btree_open(sb, HFSPLUS_CAT_CNID);
+        if (!sbi->cat_tree) {
                 printk(KERN_ERR "hfs: failed to load catalog file\n");
                 goto cleanup;
         }
@@ -404,7 +404,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
                 err = PTR_ERR(inode);
                 goto cleanup;
         }
-        HFSPLUS_SB(sb).alloc_file = inode;
+        sbi->alloc_file = inode;
 
         /* Load the root directory */
         root = hfsplus_iget(sb, HFSPLUS_ROOT_CNID);
@@ -423,7 +423,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
 
         str.len = sizeof(HFSP_HIDDENDIR_NAME) - 1;
         str.name = HFSP_HIDDENDIR_NAME;
-        hfs_find_init(HFSPLUS_SB(sb).cat_tree, &fd);
+        hfs_find_init(sbi->cat_tree, &fd);
         hfsplus_cat_build_key(sb, fd.search_key, HFSPLUS_ROOT_CNID, &str);
         if (!hfs_brec_read(&fd, &entry, sizeof(entry))) {
                 hfs_find_exit(&fd);
@@ -434,7 +434,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
                         err = PTR_ERR(inode);
                         goto cleanup;
                 }
-                HFSPLUS_SB(sb).hidden_dir = inode;
+                sbi->hidden_dir = inode;
         } else
                 hfs_find_exit(&fd);
 
@@ -449,15 +449,19 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
         be32_add_cpu(&vhdr->write_count, 1);
         vhdr->attributes &= cpu_to_be32(~HFSPLUS_VOL_UNMNT);
         vhdr->attributes |= cpu_to_be32(HFSPLUS_VOL_INCNSTNT);
-        mark_buffer_dirty(HFSPLUS_SB(sb).s_vhbh);
-        sync_dirty_buffer(HFSPLUS_SB(sb).s_vhbh);
+        mark_buffer_dirty(sbi->s_vhbh);
+        sync_dirty_buffer(sbi->s_vhbh);
 
-        if (!HFSPLUS_SB(sb).hidden_dir) {
+        if (!sbi->hidden_dir) {
                 printk(KERN_DEBUG "hfs: create hidden dir...\n");
-                HFSPLUS_SB(sb).hidden_dir = hfsplus_new_inode(sb, S_IFDIR);
-                hfsplus_create_cat(HFSPLUS_SB(sb).hidden_dir->i_ino, sb->s_root->d_inode,
-                                   &str, HFSPLUS_SB(sb).hidden_dir);
-                mark_inode_dirty(HFSPLUS_SB(sb).hidden_dir);
+
+                mutex_lock(&sbi->vh_mutex);
+                sbi->hidden_dir = hfsplus_new_inode(sb, S_IFDIR);
+                hfsplus_create_cat(sbi->hidden_dir->i_ino, sb->s_root->d_inode,
+                                   &str, sbi->hidden_dir);
+                mutex_unlock(&sbi->vh_mutex);
+
+                mark_inode_dirty(sbi->hidden_dir);
         }
 out:
         unload_nls(sbi->nls);
@@ -486,7 +490,7 @@ static struct inode *hfsplus_alloc_inode(struct super_block *sb)
 
 static void hfsplus_destroy_inode(struct inode *inode)
 {
-        kmem_cache_free(hfsplus_inode_cachep, &HFSPLUS_I(inode));
+        kmem_cache_free(hfsplus_inode_cachep, HFSPLUS_I(inode));
 }
 
 #define HFSPLUS_INODE_SIZE      sizeof(struct hfsplus_inode_info)
diff --git a/fs/hfsplus/unicode.c b/fs/hfsplus/unicode.c
index 628ccf6fa402..b66d67de882c 100644
--- a/fs/hfsplus/unicode.c
+++ b/fs/hfsplus/unicode.c
@@ -121,7 +121,7 @@ static u16 *hfsplus_compose_lookup(u16 *p, u16 cc)
 int hfsplus_uni2asc(struct super_block *sb, const struct hfsplus_unistr *ustr, char *astr, int *len_p)
 {
         const hfsplus_unichr *ip;
-        struct nls_table *nls = HFSPLUS_SB(sb).nls;
+        struct nls_table *nls = HFSPLUS_SB(sb)->nls;
         u8 *op;
         u16 cc, c0, c1;
         u16 *ce1, *ce2;
@@ -132,7 +132,7 @@ int hfsplus_uni2asc(struct super_block *sb, const struct hfsplus_unistr *ustr, c
         ustrlen = be16_to_cpu(ustr->length);
         len = *len_p;
         ce1 = NULL;
-        compose = !(HFSPLUS_SB(sb).flags & HFSPLUS_SB_NODECOMPOSE);
+        compose = !test_bit(HFSPLUS_SB_NODECOMPOSE, &HFSPLUS_SB(sb)->flags);
 
         while (ustrlen > 0) {
                 c0 = be16_to_cpu(*ip++);
@@ -246,7 +246,7 @@ out:
 static inline int asc2unichar(struct super_block *sb, const char *astr, int len,
                               wchar_t *uc)
 {
-        int size = HFSPLUS_SB(sb).nls->char2uni(astr, len, uc);
+        int size = HFSPLUS_SB(sb)->nls->char2uni(astr, len, uc);
         if (size <= 0) {
                 *uc = '?';
                 size = 1;
@@ -293,7 +293,7 @@ int hfsplus_asc2uni(struct super_block *sb, struct hfsplus_unistr *ustr,
         u16 *dstr, outlen = 0;
         wchar_t c;
 
-        decompose = !(HFSPLUS_SB(sb).flags & HFSPLUS_SB_NODECOMPOSE);
+        decompose = !test_bit(HFSPLUS_SB_NODECOMPOSE, &HFSPLUS_SB(sb)->flags);
         while (outlen < HFSPLUS_MAX_STRLEN && len > 0) {
                 size = asc2unichar(sb, astr, len, &c);
 
@@ -330,8 +330,8 @@ int hfsplus_hash_dentry(struct dentry *dentry, struct qstr *str)
         wchar_t c;
         u16 c2;
 
-        casefold = (HFSPLUS_SB(sb).flags & HFSPLUS_SB_CASEFOLD);
-        decompose = !(HFSPLUS_SB(sb).flags & HFSPLUS_SB_NODECOMPOSE);
+        casefold = test_bit(HFSPLUS_SB_CASEFOLD, &HFSPLUS_SB(sb)->flags);
+        decompose = !test_bit(HFSPLUS_SB_NODECOMPOSE, &HFSPLUS_SB(sb)->flags);
         hash = init_name_hash();
         astr = str->name;
         len = str->len;
@@ -373,8 +373,8 @@ int hfsplus_compare_dentry(struct dentry *dentry, struct qstr *s1, struct qstr *
         u16 c1, c2;
         wchar_t c;
 
-        casefold = (HFSPLUS_SB(sb).flags & HFSPLUS_SB_CASEFOLD);
-        decompose = !(HFSPLUS_SB(sb).flags & HFSPLUS_SB_NODECOMPOSE);
+        casefold = test_bit(HFSPLUS_SB_CASEFOLD, &HFSPLUS_SB(sb)->flags);
+        decompose = !test_bit(HFSPLUS_SB_NODECOMPOSE, &HFSPLUS_SB(sb)->flags);
         astr1 = s1->name;
         len1 = s1->len;
         astr2 = s2->name;
diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c
index bed78ac8f6d1..8972c20b3216 100644
--- a/fs/hfsplus/wrapper.c
+++ b/fs/hfsplus/wrapper.c
@@ -65,8 +65,8 @@ static int hfsplus_get_last_session(struct super_block *sb,
         *start = 0;
         *size = sb->s_bdev->bd_inode->i_size >> 9;
 
-        if (HFSPLUS_SB(sb).session >= 0) {
-                te.cdte_track = HFSPLUS_SB(sb).session;
+        if (HFSPLUS_SB(sb)->session >= 0) {
+                te.cdte_track = HFSPLUS_SB(sb)->session;
                 te.cdte_format = CDROM_LBA;
                 res = ioctl_by_bdev(sb->s_bdev, CDROMREADTOCENTRY, (unsigned long)&te);
                 if (!res && (te.cdte_ctrl & CDROM_DATA_TRACK) == 4) {
@@ -87,6 +87,7 @@ static int hfsplus_get_last_session(struct super_block *sb,
 /* Takes in super block, returns true if good data read */
 int hfsplus_read_wrapper(struct super_block *sb)
 {
+        struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb);
         struct buffer_head *bh;
         struct hfsplus_vh *vhdr;
         struct hfsplus_wd wd;
@@ -122,7 +123,7 @@ int hfsplus_read_wrapper(struct super_block *sb)
                 if (vhdr->signature == cpu_to_be16(HFSPLUS_VOLHEAD_SIG))
                         break;
                 if (vhdr->signature == cpu_to_be16(HFSPLUS_VOLHEAD_SIGX)) {
-                        HFSPLUS_SB(sb).flags |= HFSPLUS_SB_HFSX;
+                        set_bit(HFSPLUS_SB_HFSX, &sbi->flags);
                         break;
                 }
                 brelse(bh);
@@ -143,11 +144,11 @@ int hfsplus_read_wrapper(struct super_block *sb)
         if (blocksize < HFSPLUS_SECTOR_SIZE ||
             ((blocksize - 1) & blocksize))
                 return -EINVAL;
-        HFSPLUS_SB(sb).alloc_blksz = blocksize;
-        HFSPLUS_SB(sb).alloc_blksz_shift = 0;
+        sbi->alloc_blksz = blocksize;
+        sbi->alloc_blksz_shift = 0;
         while ((blocksize >>= 1) != 0)
-                HFSPLUS_SB(sb).alloc_blksz_shift++;
-        blocksize = min(HFSPLUS_SB(sb).alloc_blksz, (u32)PAGE_SIZE);
+                sbi->alloc_blksz_shift++;
+        blocksize = min(sbi->alloc_blksz, (u32)PAGE_SIZE);
 
         /* align block size to block offset */
         while (part_start & ((blocksize >> HFSPLUS_SECTOR_SHIFT) - 1))
@@ -158,23 +159,26 @@ int hfsplus_read_wrapper(struct super_block *sb)
                 return -EINVAL;
         }
 
-        HFSPLUS_SB(sb).blockoffset = part_start >>
-                        (sb->s_blocksize_bits - HFSPLUS_SECTOR_SHIFT);
-        HFSPLUS_SB(sb).sect_count = part_size;
-        HFSPLUS_SB(sb).fs_shift = HFSPLUS_SB(sb).alloc_blksz_shift -
-                        sb->s_blocksize_bits;
+        sbi->blockoffset =
+                part_start >> (sb->s_blocksize_bits - HFSPLUS_SECTOR_SHIFT);
+        sbi->sect_count = part_size;
+        sbi->fs_shift = sbi->alloc_blksz_shift - sb->s_blocksize_bits;
 
         bh = sb_bread512(sb, part_start + HFSPLUS_VOLHEAD_SECTOR, vhdr);
         if (!bh)
                 return -EIO;
 
         /* should still be the same... */
-        if (vhdr->signature != (HFSPLUS_SB(sb).flags & HFSPLUS_SB_HFSX ?
-                                cpu_to_be16(HFSPLUS_VOLHEAD_SIGX) :
-                                cpu_to_be16(HFSPLUS_VOLHEAD_SIG)))
-                goto error;
-        HFSPLUS_SB(sb).s_vhbh = bh;
-        HFSPLUS_SB(sb).s_vhdr = vhdr;
+        if (test_bit(HFSPLUS_SB_HFSX, &sbi->flags)) {
+                if (vhdr->signature != cpu_to_be16(HFSPLUS_VOLHEAD_SIGX))
+                        goto error;
+        } else {
+                if (vhdr->signature != cpu_to_be16(HFSPLUS_VOLHEAD_SIG))
+                        goto error;
+        }
+
+        sbi->s_vhbh = bh;
+        sbi->s_vhdr = vhdr;
 
         return 0;
  error:
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index e2bd73e8f9c0..f4d4120e5128 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -129,6 +129,10 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres
 #define move_pte(pte, prot, old_addr, new_addr) (pte)
 #endif
 
+#ifndef flush_tlb_fix_spurious_fault
+#define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address)
+#endif
+
 #ifndef pgprot_noncached
 #define pgprot_noncached(prot)  (prot)
 #endif
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index ef2af9948eac..f4229fb315e1 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -687,7 +687,9 @@
                                 - LOAD_OFFSET) {                        \
                 VMLINUX_SYMBOL(__per_cpu_start) = .;                    \
                 *(.data..percpu..first)                                 \
+                . = ALIGN(PAGE_SIZE);                                   \
                 *(.data..percpu..page_aligned)                          \
+                *(.data..percpu..readmostly)                            \
                 *(.data..percpu)                                        \
                 *(.data..percpu..shared_aligned)                        \
                 VMLINUX_SYMBOL(__per_cpu_end) = .;                      \
@@ -713,7 +715,9 @@
                 VMLINUX_SYMBOL(__per_cpu_load) = .;                     \
                 VMLINUX_SYMBOL(__per_cpu_start) = .;                    \
                 *(.data..percpu..first)                                 \
+                . = ALIGN(PAGE_SIZE);                                   \
                 *(.data..percpu..page_aligned)                          \
+                *(.data..percpu..readmostly)                            \
                 *(.data..percpu)                                        \
                 *(.data..percpu..shared_aligned)                        \
                 VMLINUX_SYMBOL(__per_cpu_end) = .;                      \
diff --git a/include/linux/acpi_pmtmr.h b/include/linux/acpi_pmtmr.h
index 7e3d2859be50..1d0ef1ae8036 100644
--- a/include/linux/acpi_pmtmr.h
+++ b/include/linux/acpi_pmtmr.h
@@ -25,8 +25,6 @@ static inline u32 acpi_pm_read_early(void)
         return acpi_pm_read_verified() & ACPI_PM_MASK;
 }
 
-extern void pmtimer_wait(unsigned);
-
 #else
 
 static inline u32 acpi_pm_read_early(void)
diff --git a/fs/ceph/auth.h b/include/linux/ceph/auth.h
index d38a2fb4a137..7fff521d7eb5 100644
--- a/fs/ceph/auth.h
+++ b/include/linux/ceph/auth.h
@@ -1,8 +1,8 @@
 #ifndef _FS_CEPH_AUTH_H
 #define _FS_CEPH_AUTH_H
 
-#include "types.h"
-#include "buffer.h"
+#include <linux/ceph/types.h>
+#include <linux/ceph/buffer.h>
 
 /*
  * Abstract interface for communicating with the authenticate module.
diff --git a/fs/ceph/buffer.h b/include/linux/ceph/buffer.h
index 58d19014068f..58d19014068f 100644
--- a/fs/ceph/buffer.h
+++ b/include/linux/ceph/buffer.h
diff --git a/fs/ceph/ceph_debug.h b/include/linux/ceph/ceph_debug.h
index 1818c2305610..aa2e19182d99 100644
--- a/fs/ceph/ceph_debug.h
+++ b/include/linux/ceph/ceph_debug.h
@@ -3,7 +3,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#ifdef CONFIG_CEPH_FS_PRETTYDEBUG
+#ifdef CONFIG_CEPH_LIB_PRETTYDEBUG
 
 /*
  * wrap pr_debug to include a filename:lineno prefix on each line.
@@ -14,7 +14,8 @@
 # if defined(DEBUG) || defined(CONFIG_DYNAMIC_DEBUG)
 extern const char *ceph_file_part(const char *s, int len);
 #  define dout(fmt, ...)                                                \
-        pr_debug(" %12.12s:%-4d : " fmt,                                \
+        pr_debug("%.*s %12.12s:%-4d : " fmt,                            \
+                 8 - (int)sizeof(KBUILD_MODNAME), "    ",               \
                  ceph_file_part(__FILE__, sizeof(__FILE__)),            \
                  __LINE__, ##__VA_ARGS__)
 # else
diff --git a/fs/ceph/ceph_frag.h b/include/linux/ceph/ceph_frag.h
index 5babb8e95352..5babb8e95352 100644
--- a/fs/ceph/ceph_frag.h
+++ b/include/linux/ceph/ceph_frag.h
diff --git a/fs/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index d5619ac86711..c3c74aef289d 100644
--- a/fs/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -299,6 +299,7 @@ enum {
         CEPH_MDS_OP_SETATTR    = 0x01108,
         CEPH_MDS_OP_SETFILELOCK= 0x01109,
         CEPH_MDS_OP_GETFILELOCK= 0x00110,
+        CEPH_MDS_OP_SETDIRLAYOUT=0x0110a,
 
         CEPH_MDS_OP_MKNOD      = 0x01201,
         CEPH_MDS_OP_LINK       = 0x01202,
diff --git a/fs/ceph/ceph_hash.h b/include/linux/ceph/ceph_hash.h
index d099c3f90236..d099c3f90236 100644
--- a/fs/ceph/ceph_hash.h
+++ b/include/linux/ceph/ceph_hash.h
diff --git a/include/linux/ceph/debugfs.h b/include/linux/ceph/debugfs.h
new file mode 100644
index 000000000000..2a79702e092b
--- /dev/null
+++ b/include/linux/ceph/debugfs.h
@@ -0,0 +1,33 @@
+#ifndef _FS_CEPH_DEBUGFS_H
+#define _FS_CEPH_DEBUGFS_H
+
+#include "ceph_debug.h"
+#include "types.h"
+
+#define CEPH_DEFINE_SHOW_FUNC(name)                                     \
+static int name##_open(struct inode *inode, struct file *file)          \
+{                                                                       \
+        struct seq_file *sf;                                            \
+        int ret;                                                        \
+                                                                        \
+        ret = single_open(file, name, NULL);                            \
+        sf = file->private_data;                                        \
+        sf->private = inode->i_private;                                 \
+        return ret;                                                     \
+}                                                                       \
+                                                                        \
+static const struct file_operations name##_fops = {                     \
+        .open           = name##_open,                                  \
+        .read           = seq_read,                                     \
+        .llseek         = seq_lseek,                                    \
+        .release        = single_release,                               \
+};
+
+/* debugfs.c */
+extern int ceph_debugfs_init(void);
+extern void ceph_debugfs_cleanup(void);
+extern int ceph_debugfs_client_init(struct ceph_client *client);
+extern void ceph_debugfs_client_cleanup(struct ceph_client *client);
+
+#endif
+
diff --git a/fs/ceph/decode.h b/include/linux/ceph/decode.h
index 3d25415afe63..c5b6939fb32a 100644
--- a/fs/ceph/decode.h
+++ b/include/linux/ceph/decode.h
@@ -191,6 +191,11 @@ static inline void ceph_encode_string(void **p, void *end,
                 ceph_encode_need(p, end, n, bad);               \
                 ceph_encode_copy(p, pv, n);                     \
         } while (0)
+#define ceph_encode_string_safe(p, end, s, n, bad)              \
+        do {                                                    \
+                ceph_encode_need(p, end, n, bad);               \
+                ceph_encode_string(p, end, s, n);               \
+        } while (0)
 
 
 #endif
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
new file mode 100644
index 000000000000..f22b2e941686
--- /dev/null
+++ b/include/linux/ceph/libceph.h
@@ -0,0 +1,249 @@
+#ifndef _FS_CEPH_LIBCEPH_H
+#define _FS_CEPH_LIBCEPH_H
+
+#include "ceph_debug.h"
+
+#include <asm/unaligned.h>
+#include <linux/backing-dev.h>
+#include <linux/completion.h>
+#include <linux/exportfs.h>
+#include <linux/fs.h>
+#include <linux/mempool.h>
+#include <linux/pagemap.h>
+#include <linux/wait.h>
+#include <linux/writeback.h>
+#include <linux/slab.h>
+
+#include "types.h"
+#include "messenger.h"
+#include "msgpool.h"
+#include "mon_client.h"
+#include "osd_client.h"
+#include "ceph_fs.h"
+
+/*
+ * Supported features
+ */
+#define CEPH_FEATURE_SUPPORTED_DEFAULT CEPH_FEATURE_NOSRCADDR
+#define CEPH_FEATURE_REQUIRED_DEFAULT  CEPH_FEATURE_NOSRCADDR
+
+/*
+ * mount options
+ */
+#define CEPH_OPT_FSID             (1<<0)
+#define CEPH_OPT_NOSHARE          (1<<1) /* don't share client with other sbs */
+#define CEPH_OPT_MYIP             (1<<2) /* specified my ip */
+#define CEPH_OPT_NOCRC            (1<<3) /* no data crc on writes */
+
+#define CEPH_OPT_DEFAULT   (0);
+
+#define ceph_set_opt(client, opt) \
+        (client)->options->flags |= CEPH_OPT_##opt;
+#define ceph_test_opt(client, opt) \
+        (!!((client)->options->flags & CEPH_OPT_##opt))
+
+struct ceph_options {
+        int flags;
+        struct ceph_fsid fsid;
+        struct ceph_entity_addr my_addr;
+        int mount_timeout;
+        int osd_idle_ttl;
+        int osd_timeout;
+        int osd_keepalive_timeout;
+
+        /*
+         * any type that can't be simply compared or doesn't need need
+         * to be compared should go beyond this point,
+         * ceph_compare_options() should be updated accordingly
+         */
+
+        struct ceph_entity_addr *mon_addr; /* should be the first
+                                              pointer type of args */
+        int num_mon;
+        char *name;
+        char *secret;
+};
+
+/*
+ * defaults
+ */
+#define CEPH_MOUNT_TIMEOUT_DEFAULT  60
+#define CEPH_OSD_TIMEOUT_DEFAULT    60  /* seconds */
+#define CEPH_OSD_KEEPALIVE_DEFAULT  5
+#define CEPH_OSD_IDLE_TTL_DEFAULT    60
+#define CEPH_MOUNT_RSIZE_DEFAULT    (512*1024) /* readahead */
+
+#define CEPH_MSG_MAX_FRONT_LEN  (16*1024*1024)
+#define CEPH_MSG_MAX_DATA_LEN   (16*1024*1024)
+
+#define CEPH_AUTH_NAME_DEFAULT   "guest"
+
+/*
+ * Delay telling the MDS we no longer want caps, in case we reopen
+ * the file.  Delay a minimum amount of time, even if we send a cap
+ * message for some other reason.  Otherwise, take the oppotunity to
+ * update the mds to avoid sending another message later.
+ */
+#define CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT      5  /* cap release delay */
+#define CEPH_CAPS_WANTED_DELAY_MAX_DEFAULT     60  /* cap release delay */
+
+#define CEPH_CAP_RELEASE_SAFETY_DEFAULT        (CEPH_CAPS_PER_RELEASE * 4)
+
+/* mount state */
+enum {
+        CEPH_MOUNT_MOUNTING,
+        CEPH_MOUNT_MOUNTED,
+        CEPH_MOUNT_UNMOUNTING,
+        CEPH_MOUNT_UNMOUNTED,
+        CEPH_MOUNT_SHUTDOWN,
+};
+
+/*
+ * subtract jiffies
+ */
+static inline unsigned long time_sub(unsigned long a, unsigned long b)
+{
+        BUG_ON(time_after(b, a));
+        return (long)a - (long)b;
+}
+
+struct ceph_mds_client;
+
+/*
+ * per client state
+ *
+ * possibly shared by multiple mount points, if they are
+ * mounting the same ceph filesystem/cluster.
+ */
+struct ceph_client {
+        struct ceph_fsid fsid;
+        bool have_fsid;
+
+        void *private;
+
+        struct ceph_options *options;
+
+        struct mutex mount_mutex;      /* serialize mount attempts */
+        wait_queue_head_t auth_wq;
+        int auth_err;
+
+        int (*extra_mon_dispatch)(struct ceph_client *, struct ceph_msg *);
+
+        u32 supported_features;
+        u32 required_features;
+
+        struct ceph_messenger *msgr;   /* messenger instance */
+        struct ceph_mon_client monc;
+        struct ceph_osd_client osdc;
+
+#ifdef CONFIG_DEBUG_FS
+        struct dentry *debugfs_dir;
+        struct dentry *debugfs_monmap;
+        struct dentry *debugfs_osdmap;
+#endif
+};
+
+
+
+/*
+ * snapshots
+ */
+
+/*
+ * A "snap context" is the set of existing snapshots when we
+ * write data.  It is used by the OSD to guide its COW behavior.
+ *
+ * The ceph_snap_context is refcounted, and attached to each dirty
+ * page, indicating which context the dirty data belonged when it was
+ * dirtied.
+ */
+struct ceph_snap_context {
+        atomic_t nref;
+        u64 seq;
+        int num_snaps;
+        u64 snaps[];
+};
+
+static inline struct ceph_snap_context *
+ceph_get_snap_context(struct ceph_snap_context *sc)
+{
+        /*
+        printk("get_snap_context %p %d -> %d\n", sc, atomic_read(&sc->nref),
+               atomic_read(&sc->nref)+1);
+        */
+        if (sc)
+                atomic_inc(&sc->nref);
+        return sc;
+}
+
+static inline void ceph_put_snap_context(struct ceph_snap_context *sc)
+{
+        if (!sc)
+                return;
+        /*
+        printk("put_snap_context %p %d -> %d\n", sc, atomic_read(&sc->nref),
+               atomic_read(&sc->nref)-1);
+        */
+        if (atomic_dec_and_test(&sc->nref)) {
+                /*printk(" deleting snap_context %p\n", sc);*/
+                kfree(sc);
+        }
+}
+
+/*
+ * calculate the number of pages a given length and offset map onto,
+ * if we align the data.
+ */
+static inline int calc_pages_for(u64 off, u64 len)
+{
+        return ((off+len+PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT) -
+                (off >> PAGE_CACHE_SHIFT);
+}
+
+/* ceph_common.c */
+extern const char *ceph_msg_type_name(int type);
+extern int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid);
+extern struct kmem_cache *ceph_inode_cachep;
+extern struct kmem_cache *ceph_cap_cachep;
+extern struct kmem_cache *ceph_dentry_cachep;
+extern struct kmem_cache *ceph_file_cachep;
+
+extern int ceph_parse_options(struct ceph_options **popt, char *options,
+                              const char *dev_name, const char *dev_name_end,
+                              int (*parse_extra_token)(char *c, void *private),
+                              void *private);
+extern void ceph_destroy_options(struct ceph_options *opt);
+extern int ceph_compare_options(struct ceph_options *new_opt,
+                                struct ceph_client *client);
+extern struct ceph_client *ceph_create_client(struct ceph_options *opt,
+                                              void *private);
+extern u64 ceph_client_id(struct ceph_client *client);
+extern void ceph_destroy_client(struct ceph_client *client);
+extern int __ceph_open_session(struct ceph_client *client,
+                               unsigned long started);
+extern int ceph_open_session(struct ceph_client *client);
+
+/* pagevec.c */
+extern void ceph_release_page_vector(struct page **pages, int num_pages);
+
+extern struct page **ceph_get_direct_page_vector(const char __user *data,
+                                            int num_pages,
+                                            loff_t off, size_t len);
+extern void ceph_put_page_vector(struct page **pages, int num_pages);
+extern void ceph_release_page_vector(struct page **pages, int num_pages);
+extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags);
+extern int ceph_copy_user_to_page_vector(struct page **pages,
+                                         const char __user *data,
+                                         loff_t off, size_t len);
+extern int ceph_copy_to_page_vector(struct page **pages,
+                                    const char *data,
+                                    loff_t off, size_t len);
+extern int ceph_copy_from_page_vector(struct page **pages,
+                                    char *data,
+                                    loff_t off, size_t len);
+extern int ceph_copy_page_vector_to_user(struct page **pages, char __user *data,
+                                    loff_t off, size_t len);
+extern void ceph_zero_page_vector_range(int off, int len, struct page **pages);
+
+
+#endif /* _FS_CEPH_SUPER_H */
diff --git a/fs/ceph/mdsmap.h b/include/linux/ceph/mdsmap.h
index 4c5cb0880bba..4c5cb0880bba 100644
--- a/fs/ceph/mdsmap.h
+++ b/include/linux/ceph/mdsmap.h
diff --git a/fs/ceph/messenger.h b/include/linux/ceph/messenger.h
index 76fbc957bc13..5956d62c3057 100644
--- a/fs/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -65,6 +65,9 @@ struct ceph_messenger {
          */
         u32 global_seq;
         spinlock_t global_seq_lock;
+
+        u32 supported_features;
+        u32 required_features;
 };
 
 /*
@@ -82,6 +85,10 @@ struct ceph_msg {
         struct ceph_pagelist *pagelist; /* instead of pages */
         struct list_head list_head;
         struct kref kref;
+        struct bio  *bio;               /* instead of pages/pagelist */
+        struct bio  *bio_iter;          /* bio iterator */
+        int bio_seg;                    /* current bio segment */
+        struct ceph_pagelist *trail;    /* the trailing part of the data */
         bool front_is_vmalloc;
         bool more_to_follow;
         bool needs_out_seq;
@@ -205,7 +212,7 @@ struct ceph_connection {
 };
 
 
-extern const char *pr_addr(const struct sockaddr_storage *ss);
+extern const char *ceph_pr_addr(const struct sockaddr_storage *ss);
 extern int ceph_parse_ips(const char *c, const char *end,
                           struct ceph_entity_addr *addr,
                           int max_count, int *count);
@@ -216,7 +223,8 @@ extern void ceph_msgr_exit(void);
 extern void ceph_msgr_flush(void);
 
 extern struct ceph_messenger *ceph_messenger_create(
-        struct ceph_entity_addr *myaddr);
+        struct ceph_entity_addr *myaddr,
+        u32 features, u32 required);
 extern void ceph_messenger_destroy(struct ceph_messenger *);
 
 extern void ceph_con_init(struct ceph_messenger *msgr,
diff --git a/fs/ceph/mon_client.h b/include/linux/ceph/mon_client.h
index 8e396f2c0963..545f85917780 100644
--- a/fs/ceph/mon_client.h
+++ b/include/linux/ceph/mon_client.h
@@ -79,6 +79,7 @@ struct ceph_mon_client {
         u64 last_tid;
 
         /* mds/osd map */
+        int want_mdsmap;
         int want_next_osdmap; /* 1 = want, 2 = want+asked */
         u32 have_osdmap, have_mdsmap;
 
diff --git a/fs/ceph/msgpool.h b/include/linux/ceph/msgpool.h
index a362605f9368..a362605f9368 100644
--- a/fs/ceph/msgpool.h
+++ b/include/linux/ceph/msgpool.h
diff --git a/fs/ceph/msgr.h b/include/linux/ceph/msgr.h
index 680d3d648cac..680d3d648cac 100644
--- a/fs/ceph/msgr.h
+++ b/include/linux/ceph/msgr.h
diff --git a/fs/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index ce776989ef6a..6c91fb032c39 100644
--- a/fs/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -15,6 +15,7 @@ struct ceph_snap_context;
 struct ceph_osd_request;
 struct ceph_osd_client;
 struct ceph_authorizer;
+struct ceph_pagelist;
 
 /*
  * completion callback for async writepages
@@ -68,6 +69,7 @@ struct ceph_osd_request {
         struct list_head  r_unsafe_item;
 
         struct inode *r_inode;                /* for use by callbacks */
+        void *r_priv;                         /* ditto */
 
         char              r_oid[40];          /* object name */
         int               r_oid_len;
@@ -80,6 +82,11 @@ struct ceph_osd_request {
         struct page     **r_pages;            /* pages for data payload */
         int               r_pages_from_pool;
         int               r_own_pages;        /* if true, i own page list */
+#ifdef CONFIG_BLOCK
+        struct bio       *r_bio;              /* instead of pages */
+#endif
+
+        struct ceph_pagelist *r_trail;        /* trailing part of the data */
 };
 
 struct ceph_osd_client {
@@ -110,6 +117,42 @@ struct ceph_osd_client {
         struct ceph_msgpool     msgpool_op_reply;
 };
 
+struct ceph_osd_req_op {
+        u16 op;           /* CEPH_OSD_OP_* */
+        u32 flags;        /* CEPH_OSD_FLAG_* */
+        union {
+                struct {
+                        u64 offset, length;
+                        u64 truncate_size;
+                        u32 truncate_seq;
+                } extent;
+                struct {
+                        const char *name;
+                        u32 name_len;
+                        const char  *val;
+                        u32 value_len;
+                        __u8 cmp_op;       /* CEPH_OSD_CMPXATTR_OP_* */
+                        __u8 cmp_mode;     /* CEPH_OSD_CMPXATTR_MODE_* */
+                } xattr;
+                struct {
+                        const char *class_name;
+                        __u8 class_len;
+                        const char *method_name;
+                        __u8 method_len;
+                        __u8 argc;
+                        const char *indata;
+                        u32 indata_len;
+                } cls;
+                struct {
+                        u64 cookie, count;
+                } pgls;
+                struct {
+                        u64 snapid;
+                } snap;
+        };
+        u32 payload_len;
+};
+
 extern int ceph_osdc_init(struct ceph_osd_client *osdc,
                           struct ceph_client *client);
 extern void ceph_osdc_stop(struct ceph_osd_client *osdc);
@@ -119,6 +162,30 @@ extern void ceph_osdc_handle_reply(struct ceph_osd_client *osdc,
 extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc,
                                  struct ceph_msg *msg);
 
+extern void ceph_calc_raw_layout(struct ceph_osd_client *osdc,
+                        struct ceph_file_layout *layout,
+                        u64 snapid,
+                        u64 off, u64 *plen, u64 *bno,
+                        struct ceph_osd_request *req,
+                        struct ceph_osd_req_op *op);
+
+extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
+                                               int flags,
+                                               struct ceph_snap_context *snapc,
+                                               struct ceph_osd_req_op *ops,
+                                               bool use_mempool,
+                                               gfp_t gfp_flags,
+                                               struct page **pages,
+                                               struct bio *bio);
+
+extern void ceph_osdc_build_request(struct ceph_osd_request *req,
+                                    u64 off, u64 *plen,
+                                    struct ceph_osd_req_op *src_ops,
+                                    struct ceph_snap_context *snapc,
+                                    struct timespec *mtime,
+                                    const char *oid,
+                                    int oid_len);
+
 extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *,
                                       struct ceph_file_layout *layout,
                                       struct ceph_vino vino,
diff --git a/fs/ceph/osdmap.h b/include/linux/ceph/osdmap.h
index 970b547e510d..ba4c205cbb01 100644
--- a/fs/ceph/osdmap.h
+++ b/include/linux/ceph/osdmap.h
@@ -4,7 +4,7 @@
 #include <linux/rbtree.h>
 #include "types.h"
 #include "ceph_fs.h"
-#include "crush/crush.h"
+#include <linux/crush/crush.h>
 
 /*
  * The osd map describes the current membership of the osd cluster and
@@ -125,4 +125,6 @@ extern int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
 extern int ceph_calc_pg_primary(struct ceph_osdmap *osdmap,
                                 struct ceph_pg pgid);
 
+extern int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name);
+
 #endif
diff --git a/fs/ceph/pagelist.h b/include/linux/ceph/pagelist.h
index e8a4187e1087..9660d6b0a35d 100644
--- a/fs/ceph/pagelist.h
+++ b/include/linux/ceph/pagelist.h
@@ -8,6 +8,14 @@ struct ceph_pagelist {
         void *mapped_tail;
         size_t length;
         size_t room;
+        struct list_head free_list;
+        size_t num_pages_free;
+};
+
+struct ceph_pagelist_cursor {
+        struct ceph_pagelist *pl;   /* pagelist, for error checking */
+        struct list_head *page_lru; /* page in list */
+        size_t room;                /* room remaining to reset to */
 };
 
 static inline void ceph_pagelist_init(struct ceph_pagelist *pl)
@@ -16,10 +24,23 @@ static inline void ceph_pagelist_init(struct ceph_pagelist *pl)
         pl->mapped_tail = NULL;
         pl->length = 0;
         pl->room = 0;
+        INIT_LIST_HEAD(&pl->free_list);
+        pl->num_pages_free = 0;
 }
+
 extern int ceph_pagelist_release(struct ceph_pagelist *pl);
 
-extern int ceph_pagelist_append(struct ceph_pagelist *pl, void *d, size_t l);
+extern int ceph_pagelist_append(struct ceph_pagelist *pl, const void *d, size_t l);
+
+extern int ceph_pagelist_reserve(struct ceph_pagelist *pl, size_t space);
+
+extern int ceph_pagelist_free_reserve(struct ceph_pagelist *pl);
+
+extern void ceph_pagelist_set_cursor(struct ceph_pagelist *pl,
+                                     struct ceph_pagelist_cursor *c);
+
+extern int ceph_pagelist_truncate(struct ceph_pagelist *pl,
+                                  struct ceph_pagelist_cursor *c);
 
 static inline int ceph_pagelist_encode_64(struct ceph_pagelist *pl, u64 v)
 {
diff --git a/fs/ceph/rados.h b/include/linux/ceph/rados.h
index 6d5247f2e81b..6d5247f2e81b 100644
--- a/fs/ceph/rados.h
+++ b/include/linux/ceph/rados.h
diff --git a/fs/ceph/types.h b/include/linux/ceph/types.h
index 28b35a005ec2..28b35a005ec2 100644
--- a/fs/ceph/types.h
+++ b/include/linux/ceph/types.h
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 0c991023ee47..709dfb901d11 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -75,7 +75,7 @@ struct cgroup_subsys_state {
 
         unsigned long flags;
         /* ID for this css, if possible */
-        struct css_id *id;
+        struct css_id __rcu *id;
 };
 
 /* bits in struct cgroup_subsys_state flags field */
@@ -205,7 +205,7 @@ struct cgroup {
         struct list_head children;      /* my children */
 
         struct cgroup *parent;          /* my parent */
-        struct dentry *dentry;          /* cgroup fs entry, RCU protected */
+        struct dentry __rcu *dentry;    /* cgroup fs entry, RCU protected */
 
         /* Private pointers for each registered subsystem */
         struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT];
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index c1a62c56a660..320d6c94ff84 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -16,7 +16,11 @@
 # define __release(x)   __context__(x,-1)
 # define __cond_lock(x,c)       ((c) ? ({ __acquire(x); 1; }) : 0)
 # define __percpu       __attribute__((noderef, address_space(3)))
+#ifdef CONFIG_SPARSE_RCU_POINTER
+# define __rcu          __attribute__((noderef, address_space(4)))
+#else
 # define __rcu
+#endif
 extern void __chk_user_ptr(const volatile void __user *);
 extern void __chk_io_ptr(const volatile void __iomem *);
 #else
diff --git a/include/linux/cred.h b/include/linux/cred.h
index 4d2c39573f36..4aaeab376446 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -84,7 +84,7 @@ struct thread_group_cred {
         atomic_t        usage;
         pid_t           tgid;                   /* thread group process ID */
         spinlock_t      lock;
-        struct key      *session_keyring;       /* keyring inherited over fork */
+        struct key __rcu *session_keyring;      /* keyring inherited over fork */
         struct key      *process_keyring;       /* keyring private to this process */
         struct rcu_head rcu;                    /* RCU deletion hook */
 };
diff --git a/fs/ceph/crush/crush.h b/include/linux/crush/crush.h
index 97e435b191f4..97e435b191f4 100644
--- a/fs/ceph/crush/crush.h
+++ b/include/linux/crush/crush.h
diff --git a/fs/ceph/crush/hash.h b/include/linux/crush/hash.h
index 91e884230d5d..91e884230d5d 100644
--- a/fs/ceph/crush/hash.h
+++ b/include/linux/crush/hash.h
diff --git a/fs/ceph/crush/mapper.h b/include/linux/crush/mapper.h
index c46b99c18bb0..c46b99c18bb0 100644
--- a/fs/ceph/crush/mapper.h
+++ b/include/linux/crush/mapper.h
diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h
index 29b3ce3f2a1d..2833452ea01c 100644
--- a/include/linux/debug_locks.h
+++ b/include/linux/debug_locks.h
@@ -49,7 +49,6 @@ struct task_struct;
 
 #ifdef CONFIG_LOCKDEP
 extern void debug_show_all_locks(void);
-extern void __debug_show_held_locks(struct task_struct *task);
 extern void debug_show_held_locks(struct task_struct *task);
 extern void debug_check_no_locks_freed(const void *from, unsigned long len);
 extern void debug_check_no_locks_held(struct task_struct *task);
@@ -58,10 +57,6 @@ static inline void debug_show_all_locks(void)
 {
 }
 
-static inline void __debug_show_held_locks(struct task_struct *task)
-{
-}
-
 static inline void debug_show_held_locks(struct task_struct *task)
 {
 }
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index d7cecc90ed34..51651b76d40f 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -106,6 +106,7 @@ struct irte {
                 __u64 high;
         };
 };
+
 #ifdef CONFIG_INTR_REMAP
 extern int intr_remapping_enabled;
 extern int intr_remapping_supported(void);
@@ -119,11 +120,8 @@ extern int alloc_irte(struct intel_iommu *iommu, int irq, u16 count);
 extern int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index,
                         u16 sub_handle);
 extern int map_irq_to_irte_handle(int irq, u16 *sub_handle);
-extern int clear_irte_irq(int irq, struct intel_iommu *iommu, u16 index);
-extern int flush_irte(int irq);
 extern int free_irte(int irq);
 
-extern int irq_remapped(int irq);
 extern struct intel_iommu *map_dev_to_ir(struct pci_dev *dev);
 extern struct intel_iommu *map_ioapic_to_ir(int apic);
 extern struct intel_iommu *map_hpet_to_ir(u8 id);
@@ -177,7 +175,6 @@ static inline int set_msi_sid(struct irte *irte, struct pci_dev *dev)
         return 0;
 }
 
-#define irq_remapped(irq)               (0)
 #define enable_intr_remapping(mode)     (-1)
 #define disable_intr_remapping()        (0)
 #define reenable_intr_remapping(mode)   (0)
@@ -187,8 +184,9 @@ static inline int set_msi_sid(struct irte *irte, struct pci_dev *dev)
 /* Can't use the common MSI interrupt functions
  * since DMAR is not a pci device
  */
-extern void dmar_msi_unmask(unsigned int irq);
-extern void dmar_msi_mask(unsigned int irq);
+struct irq_data;
+extern void dmar_msi_unmask(struct irq_data *data);
+extern void dmar_msi_mask(struct irq_data *data);
 extern void dmar_msi_read(int irq, struct msi_msg *msg);
 extern void dmar_msi_write(int irq, struct msi_msg *msg);
 extern int dmar_set_interrupt(struct intel_iommu *iommu);
diff --git a/include/linux/edac.h b/include/linux/edac.h
index 7cf92e8a4196..36c66443bdfd 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -13,6 +13,7 @@
 #define _LINUX_EDAC_H_
 
 #include <asm/atomic.h>
+#include <linux/sysdev.h>
 
 #define EDAC_OPSTATE_INVAL      -1
 #define EDAC_OPSTATE_POLL       0
@@ -22,9 +23,12 @@
 extern int edac_op_state;
 extern int edac_err_assert;
 extern atomic_t edac_handlers;
+extern struct sysdev_class edac_class;
 
 extern int edac_handler_set(void);
 extern void edac_atomic_assert_error(void);
+extern struct sysdev_class *edac_get_sysfs_class(void);
+extern void edac_put_sysfs_class(void);
 
 static inline void opstate_init(void)
 {
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index f59ed297b661..133c0ba25e30 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -31,7 +31,7 @@ struct embedded_fd_set {
 
 struct fdtable {
         unsigned int max_fds;
-        struct file ** fd;      /* current fd array */
+        struct file __rcu **fd;      /* current fd array */
         fd_set *close_on_exec;
         fd_set *open_fds;
         struct rcu_head rcu;
@@ -46,7 +46,7 @@ struct files_struct {
    * read mostly part
    */
         atomic_t count;
-        struct fdtable *fdt;
+        struct fdtable __rcu *fdt;
         struct fdtable fdtab;
   /*
    * written part on a separate cache line in SMP
@@ -55,7 +55,7 @@ struct files_struct {
         int next_fd;
         struct embedded_fd_set close_on_exec_init;
         struct embedded_fd_set open_fds_init;
-        struct file * fd_array[NR_OPEN_DEFAULT];
+        struct file __rcu * fd_array[NR_OPEN_DEFAULT];
 };
 
 #define rcu_dereference_check_fdtable(files, fdtfd) \
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 63d069bd80b7..3168dcfb94f2 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1384,7 +1384,7 @@ struct super_block {
          * Saved mount options for lazy filesystems using
          * generic_show_options()
          */
-        char *s_options;
+        char __rcu *s_options;
 };
 
 extern struct timespec current_fs_time(struct super_block *sb);
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 5f2f4c4d8fb0..af3f06b41dc1 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -129,8 +129,8 @@ struct blk_scsi_cmd_filter {
 struct disk_part_tbl {
         struct rcu_head rcu_head;
         int len;
-        struct hd_struct *last_lookup;
-        struct hd_struct *part[];
+        struct hd_struct __rcu *last_lookup;
+        struct hd_struct __rcu *part[];
 };
 
 struct gendisk {
@@ -149,7 +149,7 @@ struct gendisk {
          * non-critical accesses use RCU.  Always access through
          * helpers.
          */
-        struct disk_part_tbl *part_tbl;
+        struct disk_part_tbl __rcu *part_tbl;
         struct hd_struct part0;
 
         const struct block_device_operations *fops;
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index d5b387669dab..96c323ac44df 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -64,6 +64,8 @@
 #define HARDIRQ_OFFSET  (1UL << HARDIRQ_SHIFT)
 #define NMI_OFFSET      (1UL << NMI_SHIFT)
 
+#define SOFTIRQ_DISABLE_OFFSET  (2 * SOFTIRQ_OFFSET)
+
 #ifndef PREEMPT_ACTIVE
 #define PREEMPT_ACTIVE_BITS     1
 #define PREEMPT_ACTIVE_SHIFT    (NMI_SHIFT + NMI_BITS)
@@ -82,10 +84,13 @@
 /*
  * Are we doing bottom half or hardware interrupt processing?
  * Are we in a softirq context? Interrupt context?
+ * in_softirq - Are we currently processing softirq or have bh disabled?
+ * in_serving_softirq - Are we currently processing softirq?
  */
 #define in_irq()                (hardirq_count())
 #define in_softirq()            (softirq_count())
 #define in_interrupt()          (irq_count())
+#define in_serving_softirq()    (softirq_count() & SOFTIRQ_OFFSET)
 
 /*
  * Are we in NMI context?
@@ -132,14 +137,16 @@ extern void synchronize_irq(unsigned int irq);
 
 struct task_struct;
 
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+#if !defined(CONFIG_VIRT_CPU_ACCOUNTING) && !defined(CONFIG_IRQ_TIME_ACCOUNTING)
 static inline void account_system_vtime(struct task_struct *tsk)
 {
 }
+#else
+extern void account_system_vtime(struct task_struct *tsk);
 #endif
 
 #if defined(CONFIG_NO_HZ)
-#if defined(CONFIG_TINY_RCU)
+#if defined(CONFIG_TINY_RCU) || defined(CONFIG_TINY_PREEMPT_RCU)
 extern void rcu_enter_nohz(void);
 extern void rcu_exit_nohz(void);
 
diff --git a/include/linux/htirq.h b/include/linux/htirq.h
index c96ea46737d0..70a1dbbf2093 100644
--- a/include/linux/htirq.h
+++ b/include/linux/htirq.h
@@ -9,8 +9,9 @@ struct ht_irq_msg {
 /* Helper functions.. */
 void fetch_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg);
 void write_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg);
-void mask_ht_irq(unsigned int irq);
-void unmask_ht_irq(unsigned int irq);
+struct irq_data;
+void mask_ht_irq(struct irq_data *data);
+void unmask_ht_irq(struct irq_data *data);
 
 /* The arch hook for getting things started */
 int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev);
diff --git a/include/linux/idr.h b/include/linux/idr.h
index e968db71e33a..cdb715e58e3e 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -50,14 +50,14 @@
 
 struct idr_layer {
         unsigned long            bitmap; /* A zero bit means "space here" */
-        struct idr_layer        *ary[1<<IDR_BITS];
+        struct idr_layer __rcu  *ary[1<<IDR_BITS];
         int                      count;  /* When zero, we can release it */
         int                      layer;  /* distance from leaf */
         struct rcu_head          rcu_head;
 };
 
 struct idr {
-        struct idr_layer *top;
+        struct idr_layer __rcu *top;
         struct idr_layer *id_free;
         int               layers; /* only valid without concurrent changes */
         int               id_free_cnt;
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 1f43fa56f600..2fea6c8ef6ba 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -82,11 +82,17 @@ extern struct group_info init_groups;
 # define CAP_INIT_BSET  CAP_FULL_SET
 
 #ifdef CONFIG_TREE_PREEMPT_RCU
+#define INIT_TASK_RCU_TREE_PREEMPT()                                    \
+        .rcu_blocked_node = NULL,
+#else
+#define INIT_TASK_RCU_TREE_PREEMPT(tsk)
+#endif
+#ifdef CONFIG_PREEMPT_RCU
 #define INIT_TASK_RCU_PREEMPT(tsk)                                      \
         .rcu_read_lock_nesting = 0,                                     \
         .rcu_read_unlock_special = 0,                                   \
-        .rcu_blocked_node = NULL,                                       \
-        .rcu_node_entry = LIST_HEAD_INIT(tsk.rcu_node_entry),
+        .rcu_node_entry = LIST_HEAD_INIT(tsk.rcu_node_entry),           \
+        INIT_TASK_RCU_TREE_PREEMPT()
 #else
 #define INIT_TASK_RCU_PREEMPT(tsk)
 #endif
@@ -137,8 +143,8 @@ extern struct cred init_cred;
         .children       = LIST_HEAD_INIT(tsk.children),                 \
         .sibling        = LIST_HEAD_INIT(tsk.sibling),                  \
         .group_leader   = &tsk,                                         \
-        .real_cred      = &init_cred,                                   \
-        .cred           = &init_cred,                                   \
+        RCU_INIT_POINTER(.real_cred, &init_cred),                       \
+        RCU_INIT_POINTER(.cred, &init_cred),                            \
         .cred_guard_mutex =                                             \
                  __MUTEX_INITIALIZER(tsk.cred_guard_mutex),             \
         .comm           = "swapper",                                    \
diff --git a/include/linux/input.h b/include/linux/input.h
index 896a92227bc4..d6ae1761be97 100644
--- a/include/linux/input.h
+++ b/include/linux/input.h
@@ -1196,7 +1196,7 @@ struct input_dev {
         int (*flush)(struct input_dev *dev, struct file *file);
         int (*event)(struct input_dev *dev, unsigned int type, unsigned int code, int value);
 
-        struct input_handle *grab;
+        struct input_handle __rcu *grab;
 
         spinlock_t event_lock;
         struct mutex mutex;
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 531495db1708..414328577ced 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -647,11 +647,8 @@ static inline void init_irq_proc(void)
 struct seq_file;
 int show_interrupts(struct seq_file *p, void *v);
 
-struct irq_desc;
-
 extern int early_irq_init(void);
 extern int arch_probe_nr_irqs(void);
 extern int arch_early_irq_init(void);
-extern int arch_init_chip_data(struct irq_desc *desc, int node);
 
 #endif
diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h
index 64d529133031..3e70b21884a9 100644
--- a/include/linux/iocontext.h
+++ b/include/linux/iocontext.h
@@ -53,7 +53,7 @@ struct io_context {
 
         struct radix_tree_root radix_root;
         struct hlist_head cic_list;
-        void *ioc_data;
+        void __rcu *ioc_data;
 };
 
 static inline struct io_context *ioc_task_link(struct io_context *ioc)
diff --git a/include/linux/irq.h b/include/linux/irq.h
index c03243ad84b4..e9639115dff1 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -72,6 +72,10 @@ typedef	void (*irq_flow_handler_t)(unsigned int irq,
 #define IRQ_ONESHOT             0x08000000      /* IRQ is not unmasked after hardirq */
 #define IRQ_NESTED_THREAD       0x10000000      /* IRQ is nested into another, no own handler thread */
 
+#define IRQF_MODIFY_MASK        \
+        (IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \
+         IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL)
+
 #ifdef CONFIG_IRQ_PER_CPU
 # define CHECK_IRQ_PER_CPU(var) ((var) & IRQ_PER_CPU)
 # define IRQ_NO_BALANCING_MASK  (IRQ_PER_CPU | IRQ_NO_BALANCING)
@@ -80,36 +84,77 @@ typedef	void (*irq_flow_handler_t)(unsigned int irq,
 # define IRQ_NO_BALANCING_MASK  IRQ_NO_BALANCING
 #endif
 
-struct proc_dir_entry;
 struct msi_desc;
 
 /**
+ * struct irq_data - per irq and irq chip data passed down to chip functions
+ * @irq:                interrupt number
+ * @node:               node index useful for balancing
+ * @chip:               low level interrupt hardware access
+ * @handler_data:       per-IRQ data for the irq_chip methods
+ * @chip_data:          platform-specific per-chip private data for the chip
+ *                      methods, to allow shared chip implementations
+ * @msi_desc:           MSI descriptor
+ * @affinity:           IRQ affinity on SMP
+ *
+ * The fields here need to overlay the ones in irq_desc until we
+ * cleaned up the direct references and switched everything over to
+ * irq_data.
+ */
+struct irq_data {
+        unsigned int            irq;
+        unsigned int            node;
+        struct irq_chip         *chip;
+        void                    *handler_data;
+        void                    *chip_data;
+        struct msi_desc         *msi_desc;
+#ifdef CONFIG_SMP
+        cpumask_var_t           affinity;
+#endif
+};
+
+/**
  * struct irq_chip - hardware interrupt chip descriptor
  *
  * @name:               name for /proc/interrupts
- * @startup:            start up the interrupt (defaults to ->enable if NULL)
- * @shutdown:           shut down the interrupt (defaults to ->disable if NULL)
- * @enable:             enable the interrupt (defaults to chip->unmask if NULL)
- * @disable:            disable the interrupt
- * @ack:                start of a new interrupt
- * @mask:               mask an interrupt source
- * @mask_ack:           ack and mask an interrupt source
- * @unmask:             unmask an interrupt source
- * @eoi:                end of interrupt - chip level
- * @end:                end of interrupt - flow level
- * @set_affinity:       set the CPU affinity on SMP machines
- * @retrigger:          resend an IRQ to the CPU
- * @set_type:           set the flow type (IRQ_TYPE_LEVEL/etc.) of an IRQ
- * @set_wake:           enable/disable power-management wake-on of an IRQ
+ * @startup:            deprecated, replaced by irq_startup
+ * @shutdown:           deprecated, replaced by irq_shutdown
+ * @enable:             deprecated, replaced by irq_enable
+ * @disable:            deprecated, replaced by irq_disable
+ * @ack:                deprecated, replaced by irq_ack
+ * @mask:               deprecated, replaced by irq_mask
+ * @mask_ack:           deprecated, replaced by irq_mask_ack
+ * @unmask:             deprecated, replaced by irq_unmask
+ * @eoi:                deprecated, replaced by irq_eoi
+ * @end:                deprecated, will go away with __do_IRQ()
+ * @set_affinity:       deprecated, replaced by irq_set_affinity
+ * @retrigger:          deprecated, replaced by irq_retrigger
+ * @set_type:           deprecated, replaced by irq_set_type
+ * @set_wake:           deprecated, replaced by irq_wake
+ * @bus_lock:           deprecated, replaced by irq_bus_lock
+ * @bus_sync_unlock:    deprecated, replaced by irq_bus_sync_unlock
  *
- * @bus_lock:           function to lock access to slow bus (i2c) chips
- * @bus_sync_unlock:    function to sync and unlock slow bus (i2c) chips
+ * @irq_startup:        start up the interrupt (defaults to ->enable if NULL)
+ * @irq_shutdown:       shut down the interrupt (defaults to ->disable if NULL)
+ * @irq_enable:         enable the interrupt (defaults to chip->unmask if NULL)
+ * @irq_disable:        disable the interrupt
+ * @irq_ack:            start of a new interrupt
+ * @irq_mask:           mask an interrupt source
+ * @irq_mask_ack:       ack and mask an interrupt source
+ * @irq_unmask:         unmask an interrupt source
+ * @irq_eoi:            end of interrupt
+ * @irq_set_affinity:   set the CPU affinity on SMP machines
+ * @irq_retrigger:      resend an IRQ to the CPU
+ * @irq_set_type:       set the flow type (IRQ_TYPE_LEVEL/etc.) of an IRQ
+ * @irq_set_wake:       enable/disable power-management wake-on of an IRQ
+ * @irq_bus_lock:       function to lock access to slow bus (i2c) chips
+ * @irq_bus_sync_unlock:function to sync and unlock slow bus (i2c) chips
  *
  * @release:            release function solely used by UML
- * @typename:           obsoleted by name, kept as migration helper
  */
 struct irq_chip {
         const char      *name;
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
         unsigned int    (*startup)(unsigned int irq);
         void            (*shutdown)(unsigned int irq);
         void            (*enable)(unsigned int irq);
@@ -130,154 +175,66 @@ struct irq_chip {
 
         void            (*bus_lock)(unsigned int irq);
         void            (*bus_sync_unlock)(unsigned int irq);
+#endif
+        unsigned int    (*irq_startup)(struct irq_data *data);
+        void            (*irq_shutdown)(struct irq_data *data);
+        void            (*irq_enable)(struct irq_data *data);
+        void            (*irq_disable)(struct irq_data *data);
+
+        void            (*irq_ack)(struct irq_data *data);
+        void            (*irq_mask)(struct irq_data *data);
+        void            (*irq_mask_ack)(struct irq_data *data);
+        void            (*irq_unmask)(struct irq_data *data);
+        void            (*irq_eoi)(struct irq_data *data);
+
+        int             (*irq_set_affinity)(struct irq_data *data, const struct cpumask *dest, bool force);
+        int             (*irq_retrigger)(struct irq_data *data);
+        int             (*irq_set_type)(struct irq_data *data, unsigned int flow_type);
+        int             (*irq_set_wake)(struct irq_data *data, unsigned int on);
+
+        void            (*irq_bus_lock)(struct irq_data *data);
+        void            (*irq_bus_sync_unlock)(struct irq_data *data);
 
         /* Currently used only by UML, might disappear one day.*/
 #ifdef CONFIG_IRQ_RELEASE_METHOD
         void            (*release)(unsigned int irq, void *dev_id);
 #endif
-        /*
-         * For compatibility, ->typename is copied into ->name.
-         * Will disappear.
-         */
-        const char      *typename;
 };
 
-struct timer_rand_state;
-struct irq_2_iommu;
-/**
- * struct irq_desc - interrupt descriptor
- * @irq:                interrupt number for this descriptor
- * @timer_rand_state:   pointer to timer rand state struct
- * @kstat_irqs:         irq stats per cpu
- * @irq_2_iommu:        iommu with this irq
- * @handle_irq:         highlevel irq-events handler [if NULL, __do_IRQ()]
- * @chip:               low level interrupt hardware access
- * @msi_desc:           MSI descriptor
- * @handler_data:       per-IRQ data for the irq_chip methods
- * @chip_data:          platform-specific per-chip private data for the chip
- *                      methods, to allow shared chip implementations
- * @action:             the irq action chain
- * @status:             status information
- * @depth:              disable-depth, for nested irq_disable() calls
- * @wake_depth:         enable depth, for multiple set_irq_wake() callers
- * @irq_count:          stats field to detect stalled irqs
- * @last_unhandled:     aging timer for unhandled count
- * @irqs_unhandled:     stats field for spurious unhandled interrupts
- * @lock:               locking for SMP
- * @affinity:           IRQ affinity on SMP
- * @node:               node index useful for balancing
- * @pending_mask:       pending rebalanced interrupts
- * @threads_active:     number of irqaction threads currently running
- * @wait_for_threads:   wait queue for sync_irq to wait for threaded handlers
- * @dir:                /proc/irq/ procfs entry
- * @name:               flow handler name for /proc/interrupts output
- */
-struct irq_desc {
-        unsigned int            irq;
-        struct timer_rand_state *timer_rand_state;
-        unsigned int            *kstat_irqs;
-#ifdef CONFIG_INTR_REMAP
-        struct irq_2_iommu      *irq_2_iommu;
-#endif
-        irq_flow_handler_t      handle_irq;
-        struct irq_chip         *chip;
-        struct msi_desc         *msi_desc;
-        void                    *handler_data;
-        void                    *chip_data;
-        struct irqaction        *action;        /* IRQ action list */
-        unsigned int            status;         /* IRQ status */
-
-        unsigned int            depth;          /* nested irq disables */
-        unsigned int            wake_depth;     /* nested wake enables */
-        unsigned int            irq_count;      /* For detecting broken IRQs */
-        unsigned long           last_unhandled; /* Aging timer for unhandled count */
-        unsigned int            irqs_unhandled;
-        raw_spinlock_t          lock;
-#ifdef CONFIG_SMP
-        cpumask_var_t           affinity;
-        const struct cpumask    *affinity_hint;
-        unsigned int            node;
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-        cpumask_var_t           pending_mask;
-#endif
-#endif
-        atomic_t                threads_active;
-        wait_queue_head_t       wait_for_threads;
-#ifdef CONFIG_PROC_FS
-        struct proc_dir_entry   *dir;
-#endif
-        const char              *name;
-} ____cacheline_internodealigned_in_smp;
+/* This include will go away once we isolated irq_desc usage to core code */
+#include <linux/irqdesc.h>
 
-extern void arch_init_copy_chip_data(struct irq_desc *old_desc,
-                                        struct irq_desc *desc, int node);
-extern void arch_free_chip_data(struct irq_desc *old_desc, struct irq_desc *desc);
+/*
+ * Pick up the arch-dependent methods:
+ */
+#include <asm/hw_irq.h>
 
-#ifndef CONFIG_SPARSE_IRQ
-extern struct irq_desc irq_desc[NR_IRQS];
+#ifndef NR_IRQS_LEGACY
+# define NR_IRQS_LEGACY 0
 #endif
 
-#ifdef CONFIG_NUMA_IRQ_DESC
-extern struct irq_desc *move_irq_desc(struct irq_desc *old_desc, int node);
-#else
-static inline struct irq_desc *move_irq_desc(struct irq_desc *desc, int node)
-{
-        return desc;
-}
+#ifndef ARCH_IRQ_INIT_FLAGS
+# define ARCH_IRQ_INIT_FLAGS    0
 #endif
 
-extern struct irq_desc *irq_to_desc_alloc_node(unsigned int irq, int node);
-
-/*
- * Pick up the arch-dependent methods:
- */
-#include <asm/hw_irq.h>
+#define IRQ_DEFAULT_INIT_FLAGS  (IRQ_DISABLED | ARCH_IRQ_INIT_FLAGS)
 
+struct irqaction;
 extern int setup_irq(unsigned int irq, struct irqaction *new);
 extern void remove_irq(unsigned int irq, struct irqaction *act);
 
 #ifdef CONFIG_GENERIC_HARDIRQS
 
-#ifdef CONFIG_SMP
-
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-
+#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_PENDING_IRQ)
 void move_native_irq(int irq);
 void move_masked_irq(int irq);
-
-#else /* CONFIG_GENERIC_PENDING_IRQ */
-
-static inline void move_irq(int irq)
-{
-}
-
-static inline void move_native_irq(int irq)
-{
-}
-
-static inline void move_masked_irq(int irq)
-{
-}
-
-#endif /* CONFIG_GENERIC_PENDING_IRQ */
-
-#else /* CONFIG_SMP */
-
-#define move_native_irq(x)
-#define move_masked_irq(x)
-
-#endif /* CONFIG_SMP */
+#else
+static inline void move_native_irq(int irq) { }
+static inline void move_masked_irq(int irq) { }
+#endif
 
 extern int no_irq_affinity;
 
-static inline int irq_balancing_disabled(unsigned int irq)
-{
-        struct irq_desc *desc;
-
-        desc = irq_to_desc(irq);
-        return desc->status & IRQ_NO_BALANCING_MASK;
-}
-
 /* Handle irq action chains: */
 extern irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action);
 
@@ -293,42 +250,10 @@ extern void handle_percpu_irq(unsigned int irq, struct irq_desc *desc);
 extern void handle_bad_irq(unsigned int irq, struct irq_desc *desc);
 extern void handle_nested_irq(unsigned int irq);
 
-/*
- * Monolithic do_IRQ implementation.
- */
-#ifndef CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ
-extern unsigned int __do_IRQ(unsigned int irq);
-#endif
-
-/*
- * Architectures call this to let the generic IRQ layer
- * handle an interrupt. If the descriptor is attached to an
- * irqchip-style controller then we call the ->handle_irq() handler,
- * and it calls __do_IRQ() if it's attached to an irqtype-style controller.
- */
-static inline void generic_handle_irq_desc(unsigned int irq, struct irq_desc *desc)
-{
-#ifdef CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ
-        desc->handle_irq(irq, desc);
-#else
-        if (likely(desc->handle_irq))
-                desc->handle_irq(irq, desc);
-        else
-                __do_IRQ(irq);
-#endif
-}
-
-static inline void generic_handle_irq(unsigned int irq)
-{
-        generic_handle_irq_desc(irq, irq_to_desc(irq));
-}
-
 /* Handling of unhandled and spurious interrupts: */
 extern void note_interrupt(unsigned int irq, struct irq_desc *desc,
                            irqreturn_t action_ret);
 
-/* Resending of interrupts :*/
-void check_irq_resend(struct irq_desc *desc, unsigned int irq);
 
 /* Enable/disable irq debugging output: */
 extern int noirqdebug_setup(char *str);
@@ -351,16 +276,6 @@ extern void
 __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
                   const char *name);
 
-/* caller has locked the irq_desc and both params are valid */
-static inline void __set_irq_handler_unlocked(int irq,
-                                              irq_flow_handler_t handler)
-{
-        struct irq_desc *desc;
-
-        desc = irq_to_desc(irq);
-        desc->handle_irq = handler;
-}
-
 /*
  * Set a highlevel flow handler for a given IRQ:
  */
@@ -384,141 +299,121 @@ set_irq_chained_handler(unsigned int irq,
 
 extern void set_irq_nested_thread(unsigned int irq, int nest);
 
-extern void set_irq_noprobe(unsigned int irq);
-extern void set_irq_probe(unsigned int irq);
+void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set);
+
+static inline void irq_set_status_flags(unsigned int irq, unsigned long set)
+{
+        irq_modify_status(irq, 0, set);
+}
+
+static inline void irq_clear_status_flags(unsigned int irq, unsigned long clr)
+{
+        irq_modify_status(irq, clr, 0);
+}
+
+static inline void set_irq_noprobe(unsigned int irq)
+{
+        irq_modify_status(irq, 0, IRQ_NOPROBE);
+}
+
+static inline void set_irq_probe(unsigned int irq)
+{
+        irq_modify_status(irq, IRQ_NOPROBE, 0);
+}
 
 /* Handle dynamic irq creation and destruction */
 extern unsigned int create_irq_nr(unsigned int irq_want, int node);
 extern int create_irq(void);
 extern void destroy_irq(unsigned int irq);
 
-/* Test to see if a driver has successfully requested an irq */
-static inline int irq_has_action(unsigned int irq)
+/*
+ * Dynamic irq helper functions. Obsolete. Use irq_alloc_desc* and
+ * irq_free_desc instead.
+ */
+extern void dynamic_irq_cleanup(unsigned int irq);
+static inline void dynamic_irq_init(unsigned int irq)
 {
-        struct irq_desc *desc = irq_to_desc(irq);
-        return desc->action != NULL;
+        dynamic_irq_cleanup(irq);
 }
 
-/* Dynamic irq helper functions */
-extern void dynamic_irq_init(unsigned int irq);
-void dynamic_irq_init_keep_chip_data(unsigned int irq);
-extern void dynamic_irq_cleanup(unsigned int irq);
-void dynamic_irq_cleanup_keep_chip_data(unsigned int irq);
-
 /* Set/get chip/data for an IRQ: */
 extern int set_irq_chip(unsigned int irq, struct irq_chip *chip);
 extern int set_irq_data(unsigned int irq, void *data);
 extern int set_irq_chip_data(unsigned int irq, void *data);
 extern int set_irq_type(unsigned int irq, unsigned int type);
 extern int set_irq_msi(unsigned int irq, struct msi_desc *entry);
+extern struct irq_data *irq_get_irq_data(unsigned int irq);
 
-#define get_irq_chip(irq)       (irq_to_desc(irq)->chip)
-#define get_irq_chip_data(irq)  (irq_to_desc(irq)->chip_data)
-#define get_irq_data(irq)       (irq_to_desc(irq)->handler_data)
-#define get_irq_msi(irq)        (irq_to_desc(irq)->msi_desc)
-
-#define get_irq_desc_chip(desc)         ((desc)->chip)
-#define get_irq_desc_chip_data(desc)    ((desc)->chip_data)
-#define get_irq_desc_data(desc)         ((desc)->handler_data)
-#define get_irq_desc_msi(desc)          ((desc)->msi_desc)
-
-#endif /* CONFIG_GENERIC_HARDIRQS */
-
-#endif /* !CONFIG_S390 */
-
-#ifdef CONFIG_SMP
-/**
- * alloc_desc_masks - allocate cpumasks for irq_desc
- * @desc:       pointer to irq_desc struct
- * @node:       node which will be handling the cpumasks
- * @boot:       true if need bootmem
- *
- * Allocates affinity and pending_mask cpumask if required.
- * Returns true if successful (or not required).
- */
-static inline bool alloc_desc_masks(struct irq_desc *desc, int node,
-                                                        bool boot)
+static inline struct irq_chip *get_irq_chip(unsigned int irq)
 {
-        gfp_t gfp = GFP_ATOMIC;
-
-        if (boot)
-                gfp = GFP_NOWAIT;
-
-#ifdef CONFIG_CPUMASK_OFFSTACK
-        if (!alloc_cpumask_var_node(&desc->affinity, gfp, node))
-                return false;
+        struct irq_data *d = irq_get_irq_data(irq);
+        return d ? d->chip : NULL;
+}
 
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-        if (!alloc_cpumask_var_node(&desc->pending_mask, gfp, node)) {
-                free_cpumask_var(desc->affinity);
-                return false;
-        }
-#endif
-#endif
-        return true;
+static inline struct irq_chip *irq_data_get_irq_chip(struct irq_data *d)
+{
+        return d->chip;
 }
 
-static inline void init_desc_masks(struct irq_desc *desc)
+static inline void *get_irq_chip_data(unsigned int irq)
 {
-        cpumask_setall(desc->affinity);
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-        cpumask_clear(desc->pending_mask);
-#endif
+        struct irq_data *d = irq_get_irq_data(irq);
+        return d ? d->chip_data : NULL;
 }
 
-/**
- * init_copy_desc_masks - copy cpumasks for irq_desc
- * @old_desc:   pointer to old irq_desc struct
- * @new_desc:   pointer to new irq_desc struct
- *
- * Insures affinity and pending_masks are copied to new irq_desc.
- * If !CONFIG_CPUMASKS_OFFSTACK the cpumasks are embedded in the
- * irq_desc struct so the copy is redundant.
- */
+static inline void *irq_data_get_irq_chip_data(struct irq_data *d)
+{
+        return d->chip_data;
+}
 
-static inline void init_copy_desc_masks(struct irq_desc *old_desc,
-                                        struct irq_desc *new_desc)
+static inline void *get_irq_data(unsigned int irq)
 {
-#ifdef CONFIG_CPUMASK_OFFSTACK
-        cpumask_copy(new_desc->affinity, old_desc->affinity);
+        struct irq_data *d = irq_get_irq_data(irq);
+        return d ? d->handler_data : NULL;
+}
 
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-        cpumask_copy(new_desc->pending_mask, old_desc->pending_mask);
-#endif
-#endif
+static inline void *irq_data_get_irq_data(struct irq_data *d)
+{
+        return d->handler_data;
 }
 
-static inline void free_desc_masks(struct irq_desc *old_desc,
-                                   struct irq_desc *new_desc)
+static inline struct msi_desc *get_irq_msi(unsigned int irq)
 {
-        free_cpumask_var(old_desc->affinity);
+        struct irq_data *d = irq_get_irq_data(irq);
+        return d ? d->msi_desc : NULL;
+}
 
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-        free_cpumask_var(old_desc->pending_mask);
-#endif
+static inline struct msi_desc *irq_data_get_msi(struct irq_data *d)
+{
+        return d->msi_desc;
 }
 
-#else /* !CONFIG_SMP */
+int irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node);
+void irq_free_descs(unsigned int irq, unsigned int cnt);
+int irq_reserve_irqs(unsigned int from, unsigned int cnt);
 
-static inline bool alloc_desc_masks(struct irq_desc *desc, int node,
-                                                                bool boot)
+static inline int irq_alloc_desc(int node)
 {
-        return true;
+        return irq_alloc_descs(-1, 0, 1, node);
 }
 
-static inline void init_desc_masks(struct irq_desc *desc)
+static inline int irq_alloc_desc_at(unsigned int at, int node)
 {
+        return irq_alloc_descs(at, at, 1, node);
 }
 
-static inline void init_copy_desc_masks(struct irq_desc *old_desc,
-                                        struct irq_desc *new_desc)
+static inline int irq_alloc_desc_from(unsigned int from, int node)
 {
+        return irq_alloc_descs(-1, from, 1, node);
 }
 
-static inline void free_desc_masks(struct irq_desc *old_desc,
-                                   struct irq_desc *new_desc)
+static inline void irq_free_desc(unsigned int irq)
 {
+        irq_free_descs(irq, 1);
 }
-#endif  /* CONFIG_SMP */
+
+#endif /* CONFIG_GENERIC_HARDIRQS */
+
+#endif /* !CONFIG_S390 */
 
 #endif /* _LINUX_IRQ_H */
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
new file mode 100644
index 000000000000..979c68cc7458
--- /dev/null
+++ b/include/linux/irqdesc.h
@@ -0,0 +1,159 @@
+#ifndef _LINUX_IRQDESC_H
+#define _LINUX_IRQDESC_H
+
+/*
+ * Core internal functions to deal with irq descriptors
+ *
+ * This include will move to kernel/irq once we cleaned up the tree.
+ * For now it's included from <linux/irq.h>
+ */
+
+struct proc_dir_entry;
+struct timer_rand_state;
+/**
+ * struct irq_desc - interrupt descriptor
+ * @irq_data:           per irq and chip data passed down to chip functions
+ * @timer_rand_state:   pointer to timer rand state struct
+ * @kstat_irqs:         irq stats per cpu
+ * @handle_irq:         highlevel irq-events handler [if NULL, __do_IRQ()]
+ * @action:             the irq action chain
+ * @status:             status information
+ * @depth:              disable-depth, for nested irq_disable() calls
+ * @wake_depth:         enable depth, for multiple set_irq_wake() callers
+ * @irq_count:          stats field to detect stalled irqs
+ * @last_unhandled:     aging timer for unhandled count
+ * @irqs_unhandled:     stats field for spurious unhandled interrupts
+ * @lock:               locking for SMP
+ * @pending_mask:       pending rebalanced interrupts
+ * @threads_active:     number of irqaction threads currently running
+ * @wait_for_threads:   wait queue for sync_irq to wait for threaded handlers
+ * @dir:                /proc/irq/ procfs entry
+ * @name:               flow handler name for /proc/interrupts output
+ */
+struct irq_desc {
+
+#ifdef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
+        struct irq_data         irq_data;
+#else
+        /*
+         * This union will go away, once we fixed the direct access to
+         * irq_desc all over the place. The direct fields are a 1:1
+         * overlay of irq_data.
+         */
+        union {
+                struct irq_data         irq_data;
+                struct {
+                        unsigned int            irq;
+                        unsigned int            node;
+                        struct irq_chip         *chip;
+                        void                    *handler_data;
+                        void                    *chip_data;
+                        struct msi_desc         *msi_desc;
+#ifdef CONFIG_SMP
+                        cpumask_var_t           affinity;
+#endif
+                };
+        };
+#endif
+
+        struct timer_rand_state *timer_rand_state;
+        unsigned int            *kstat_irqs;
+        irq_flow_handler_t      handle_irq;
+        struct irqaction        *action;        /* IRQ action list */
+        unsigned int            status;         /* IRQ status */
+
+        unsigned int            depth;          /* nested irq disables */
+        unsigned int            wake_depth;     /* nested wake enables */
+        unsigned int            irq_count;      /* For detecting broken IRQs */
+        unsigned long           last_unhandled; /* Aging timer for unhandled count */
+        unsigned int            irqs_unhandled;
+        raw_spinlock_t          lock;
+#ifdef CONFIG_SMP
+        const struct cpumask    *affinity_hint;
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+        cpumask_var_t           pending_mask;
+#endif
+#endif
+        atomic_t                threads_active;
+        wait_queue_head_t       wait_for_threads;
+#ifdef CONFIG_PROC_FS
+        struct proc_dir_entry   *dir;
+#endif
+        const char              *name;
+} ____cacheline_internodealigned_in_smp;
+
+#ifndef CONFIG_SPARSE_IRQ
+extern struct irq_desc irq_desc[NR_IRQS];
+#endif
+
+/* Will be removed once the last users in power and sh are gone */
+extern struct irq_desc *irq_to_desc_alloc_node(unsigned int irq, int node);
+static inline struct irq_desc *move_irq_desc(struct irq_desc *desc, int node)
+{
+        return desc;
+}
+
+#ifdef CONFIG_GENERIC_HARDIRQS
+
+#define get_irq_desc_chip(desc)         ((desc)->irq_data.chip)
+#define get_irq_desc_chip_data(desc)    ((desc)->irq_data.chip_data)
+#define get_irq_desc_data(desc)         ((desc)->irq_data.handler_data)
+#define get_irq_desc_msi(desc)          ((desc)->irq_data.msi_desc)
+
+/*
+ * Monolithic do_IRQ implementation.
+ */
+#ifndef CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ
+extern unsigned int __do_IRQ(unsigned int irq);
+#endif
+
+/*
+ * Architectures call this to let the generic IRQ layer
+ * handle an interrupt. If the descriptor is attached to an
+ * irqchip-style controller then we call the ->handle_irq() handler,
+ * and it calls __do_IRQ() if it's attached to an irqtype-style controller.
+ */
+static inline void generic_handle_irq_desc(unsigned int irq, struct irq_desc *desc)
+{
+#ifdef CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ
+        desc->handle_irq(irq, desc);
+#else
+        if (likely(desc->handle_irq))
+                desc->handle_irq(irq, desc);
+        else
+                __do_IRQ(irq);
+#endif
+}
+
+static inline void generic_handle_irq(unsigned int irq)
+{
+        generic_handle_irq_desc(irq, irq_to_desc(irq));
+}
+
+/* Test to see if a driver has successfully requested an irq */
+static inline int irq_has_action(unsigned int irq)
+{
+        struct irq_desc *desc = irq_to_desc(irq);
+        return desc->action != NULL;
+}
+
+static inline int irq_balancing_disabled(unsigned int irq)
+{
+        struct irq_desc *desc;
+
+        desc = irq_to_desc(irq);
+        return desc->status & IRQ_NO_BALANCING_MASK;
+}
+
+/* caller has locked the irq_desc and both params are valid */
+static inline void __set_irq_handler_unlocked(int irq,
+                                              irq_flow_handler_t handler)
+{
+        struct irq_desc *desc;
+
+        desc = irq_to_desc(irq);
+        desc->handle_irq = handler;
+}
+#endif
+
+#endif
diff --git a/include/linux/irqnr.h b/include/linux/irqnr.h
index 7bf89bc8cbca..05aa8c23483f 100644
--- a/include/linux/irqnr.h
+++ b/include/linux/irqnr.h
@@ -25,6 +25,7 @@
 
 extern int nr_irqs;
 extern struct irq_desc *irq_to_desc(unsigned int irq);
+unsigned int irq_get_next_irq(unsigned int offset);
 
 # define for_each_irq_desc(irq, desc)                                   \
         for (irq = 0, desc = irq_to_desc(irq); irq < nr_irqs;           \
@@ -47,6 +48,10 @@ extern struct irq_desc *irq_to_desc(unsigned int irq);
 #define irq_node(irq)   0
 #endif
 
+# define for_each_active_irq(irq)                       \
+        for (irq = irq_get_next_irq(0); irq < nr_irqs;  \
+             irq = irq_get_next_irq(irq + 1))
+
 #endif /* CONFIG_GENERIC_HARDIRQS */
 
 #define for_each_irq_nr(irq)                   \
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 2b0a35e6bc69..1759ba5adce8 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -58,7 +58,18 @@ extern const char linux_proc_banner[];
 
 #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f))
 #define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d))
-#define roundup(x, y) ((((x) + ((y) - 1)) / (y)) * (y))
+#define roundup(x, y) (                                 \
+{                                                       \
+        typeof(y) __y = y;                              \
+        (((x) + (__y - 1)) / __y) * __y;                \
+}                                                       \
+)
+#define rounddown(x, y) (                               \
+{                                                       \
+        typeof(x) __x = (x);                            \
+        __x - (__x % (y));                              \
+}                                                       \
+)
 #define DIV_ROUND_CLOSEST(x, divisor)(                  \
 {                                                       \
         typeof(divisor) __divisor = divisor;            \
diff --git a/include/linux/key.h b/include/linux/key.h
index cd50dfa1d4c2..3db0adce1fda 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -178,8 +178,9 @@ struct key {
          */
         union {
                 unsigned long           value;
+                void __rcu              *rcudata;
                 void                    *data;
-                struct keyring_list     *subscriptions;
+                struct keyring_list __rcu *subscriptions;
         } payload;
 };
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index c13cc48697aa..ac740b26eb10 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -205,7 +205,7 @@ struct kvm {
 
         struct mutex irq_lock;
 #ifdef CONFIG_HAVE_KVM_IRQCHIP
-        struct kvm_irq_routing_table *irq_routing;
+        struct kvm_irq_routing_table __rcu *irq_routing;
         struct hlist_head mask_notifier_list;
         struct hlist_head irq_ack_notifier_list;
 #endif
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 06aed8305bf3..71c09b26c759 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -32,6 +32,17 @@ extern int lock_stat;
 #define MAX_LOCKDEP_SUBCLASSES          8UL
 
 /*
+ * NR_LOCKDEP_CACHING_CLASSES ... Number of classes
+ * cached in the instance of lockdep_map
+ *
+ * Currently main class (subclass == 0) and signle depth subclass
+ * are cached in lockdep_map. This optimization is mainly targeting
+ * on rq->lock. double_rq_lock() acquires this highly competitive with
+ * single depth.
+ */
+#define NR_LOCKDEP_CACHING_CLASSES      2
+
+/*
  * Lock-classes are keyed via unique addresses, by embedding the
  * lockclass-key into the kernel (or module) .data section. (For
  * static locks we use the lock address itself as the key.)
@@ -138,7 +149,7 @@ void clear_lock_stats(struct lock_class *class);
  */
 struct lockdep_map {
         struct lock_class_key           *key;
-        struct lock_class               *class_cache;
+        struct lock_class               *class_cache[NR_LOCKDEP_CACHING_CLASSES];
         const char                      *name;
 #ifdef CONFIG_LOCK_STAT
         int                             cpu;
@@ -424,14 +435,6 @@ do {								\
 
 #endif /* CONFIG_LOCKDEP */
 
-#ifdef CONFIG_GENERIC_HARDIRQS
-extern void early_init_irq_lock_class(void);
-#else
-static inline void early_init_irq_lock_class(void)
-{
-}
-#endif
-
 #ifdef CONFIG_TRACE_IRQFLAGS
 extern void early_boot_irqs_off(void);
 extern void early_boot_irqs_on(void);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index ee7e258627f9..cb57d657ce4d 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -299,7 +299,7 @@ struct mm_struct {
          * new_owner->mm == mm
          * new_owner->alloc_lock is held
          */
-        struct task_struct *owner;
+        struct task_struct __rcu *owner;
 #endif
 
 #ifdef CONFIG_PROC_FS
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 91b05c171854..05acced439a3 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -10,12 +10,13 @@ struct msi_msg {
 };
 
 /* Helper functions */
-struct irq_desc;
-extern void mask_msi_irq(unsigned int irq);
-extern void unmask_msi_irq(unsigned int irq);
-extern void read_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg);
-extern void get_cached_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg);
-extern void write_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg);
+struct irq_data;
+struct msi_desc;
+extern void mask_msi_irq(struct irq_data *data);
+extern void unmask_msi_irq(struct irq_data *data);
+extern void __read_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
+extern void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
+extern void __write_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
 extern void read_msi_msg(unsigned int irq, struct msi_msg *msg);
 extern void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg);
 extern void write_msi_msg(unsigned int irq, struct msi_msg *msg);
diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h
index 9ed534c991b9..70cd0603911c 100644
--- a/include/linux/netfilter/nfnetlink_conntrack.h
+++ b/include/linux/netfilter/nfnetlink_conntrack.h
@@ -39,8 +39,9 @@ enum ctattr_type {
         CTA_TUPLE_MASTER,
         CTA_NAT_SEQ_ADJ_ORIG,
         CTA_NAT_SEQ_ADJ_REPLY,
-        CTA_SECMARK,
+        CTA_SECMARK,            /* obsolete */
         CTA_ZONE,
+        CTA_SECCTX,
         __CTA_MAX
 };
 #define CTA_MAX (__CTA_MAX - 1)
@@ -172,4 +173,11 @@ enum ctattr_help {
 };
 #define CTA_HELP_MAX (__CTA_HELP_MAX - 1)
 
+enum ctattr_secctx {
+        CTA_SECCTX_UNSPEC,
+        CTA_SECCTX_NAME,
+        __CTA_SECCTX_MAX
+};
+#define CTA_SECCTX_MAX (__CTA_SECCTX_MAX - 1)
+
 #endif /* _IPCONNTRACK_NETLINK_H */
diff --git a/include/linux/netfilter/xt_SECMARK.h b/include/linux/netfilter/xt_SECMARK.h
index 6fcd3448b186..989092bd6274 100644
--- a/include/linux/netfilter/xt_SECMARK.h
+++ b/include/linux/netfilter/xt_SECMARK.h
@@ -11,18 +11,12 @@
  * packets are being marked for.
  */
 #define SECMARK_MODE_SEL        0x01            /* SELinux */
-#define SECMARK_SELCTX_MAX      256
-
-struct xt_secmark_target_selinux_info {
-        __u32 selsid;
-        char selctx[SECMARK_SELCTX_MAX];
-};
+#define SECMARK_SECCTX_MAX      256
 
 struct xt_secmark_target_info {
         __u8 mode;
-        union {
-                struct xt_secmark_target_selinux_info sel;
-        } u;
+        __u32 secid;
+        char secctx[SECMARK_SECCTX_MAX];
 };
 
 #endif /*_XT_SECMARK_H_target */
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 508f8cf6da37..d0edf7d823ae 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -185,7 +185,7 @@ struct nfs_inode {
         struct nfs4_cached_acl  *nfs4_acl;
         /* NFSv4 state */
         struct list_head        open_states;
-        struct nfs_delegation   *delegation;
+        struct nfs_delegation __rcu *delegation;
         fmode_t                  delegation_state;
         struct rw_semaphore     rwsem;
 #endif /* CONFIG_NFS_V4*/
diff --git a/include/linux/notifier.h b/include/linux/notifier.h
index b2f1a4d83550..2026f9e1ceb8 100644
--- a/include/linux/notifier.h
+++ b/include/linux/notifier.h
@@ -49,28 +49,28 @@
 
 struct notifier_block {
         int (*notifier_call)(struct notifier_block *, unsigned long, void *);
-        struct notifier_block *next;
+        struct notifier_block __rcu *next;
         int priority;
 };
 
 struct atomic_notifier_head {
         spinlock_t lock;
-        struct notifier_block *head;
+        struct notifier_block __rcu *head;
 };
 
 struct blocking_notifier_head {
         struct rw_semaphore rwsem;
-        struct notifier_block *head;
+        struct notifier_block __rcu *head;
 };
 
 struct raw_notifier_head {
-        struct notifier_block *head;
+        struct notifier_block __rcu *head;
 };
 
 struct srcu_notifier_head {
         struct mutex mutex;
         struct srcu_struct srcu;
-        struct notifier_block *head;
+        struct notifier_block __rcu *head;
 };
 
 #define ATOMIC_INIT_NOTIFIER_HEAD(name) do {    \
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 570fddeb0388..2615c37c8fe5 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -517,6 +517,7 @@
 #define PCI_DEVICE_ID_AMD_11H_NB_DRAM   0x1302
 #define PCI_DEVICE_ID_AMD_11H_NB_MISC   0x1303
 #define PCI_DEVICE_ID_AMD_11H_NB_LINK   0x1304
+#define PCI_DEVICE_ID_AMD_15H_NB_MISC   0x1603
 #define PCI_DEVICE_ID_AMD_LANCE         0x2000
 #define PCI_DEVICE_ID_AMD_LANCE_HOME    0x2001
 #define PCI_DEVICE_ID_AMD_SCSI          0x2020
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index ce2dc655cd1d..27ef6b190ea6 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -139,6 +139,15 @@
         __aligned(PAGE_SIZE)
 
 /*
+ * Declaration/definition used for per-CPU variables that must be read mostly.
+ */
+#define DECLARE_PER_CPU_READ_MOSTLY(type, name)                 \
+        DECLARE_PER_CPU_SECTION(type, name, "..readmostly")
+
+#define DEFINE_PER_CPU_READ_MOSTLY(type, name)                          \
+        DEFINE_PER_CPU_SECTION(type, name, "..readmostly")
+
+/*
  * Intermodule exports for per-CPU variables.  sparse forgets about
  * address space across EXPORT_SYMBOL(), change EXPORT_SYMBOL() to
  * noop if __CHECKER__.
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 634b8e674ac5..a39cbed9ee17 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -47,6 +47,8 @@ static inline void *radix_tree_indirect_to_ptr(void *ptr)
 {
         return (void *)((unsigned long)ptr & ~RADIX_TREE_INDIRECT_PTR);
 }
+#define radix_tree_indirect_to_ptr(ptr) \
+        radix_tree_indirect_to_ptr((void __force *)(ptr))
 
 static inline int radix_tree_is_indirect_ptr(void *ptr)
 {
@@ -61,7 +63,7 @@ static inline int radix_tree_is_indirect_ptr(void *ptr)
 struct radix_tree_root {
         unsigned int            height;
         gfp_t                   gfp_mask;
-        struct radix_tree_node  *rnode;
+        struct radix_tree_node  __rcu *rnode;
 };
 
 #define RADIX_TREE_INIT(mask)   {                                       \
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index 4ec3b38ce9c5..f31ef61f1c65 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -10,6 +10,21 @@
 #include <linux/rcupdate.h>
 
 /*
+ * Why is there no list_empty_rcu()?  Because list_empty() serves this
+ * purpose.  The list_empty() function fetches the RCU-protected pointer
+ * and compares it to the address of the list head, but neither dereferences
+ * this pointer itself nor provides this pointer to the caller.  Therefore,
+ * it is not necessary to use rcu_dereference(), so that list_empty() can
+ * be used anywhere you would want to use a list_empty_rcu().
+ */
+
+/*
+ * return the ->next pointer of a list_head in an rcu safe
+ * way, we must not access it directly
+ */
+#define list_next_rcu(list)     (*((struct list_head __rcu **)(&(list)->next)))
+
+/*
  * Insert a new entry between two known consecutive entries.
  *
  * This is only for internal list manipulation where we know
@@ -20,7 +35,7 @@ static inline void __list_add_rcu(struct list_head *new,
 {
         new->next = next;
         new->prev = prev;
-        rcu_assign_pointer(prev->next, new);
+        rcu_assign_pointer(list_next_rcu(prev), new);
         next->prev = new;
 }
 
@@ -138,7 +153,7 @@ static inline void list_replace_rcu(struct list_head *old,
 {
         new->next = old->next;
         new->prev = old->prev;
-        rcu_assign_pointer(new->prev->next, new);
+        rcu_assign_pointer(list_next_rcu(new->prev), new);
         new->next->prev = new;
         old->prev = LIST_POISON2;
 }
@@ -193,7 +208,7 @@ static inline void list_splice_init_rcu(struct list_head *list,
          */
 
         last->next = at;
-        rcu_assign_pointer(head->next, first);
+        rcu_assign_pointer(list_next_rcu(head), first);
         first->prev = head;
         at->prev = last;
 }
@@ -208,7 +223,9 @@ static inline void list_splice_init_rcu(struct list_head *list,
  * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock().
  */
 #define list_entry_rcu(ptr, type, member) \
-        container_of(rcu_dereference_raw(ptr), type, member)
+        ({typeof (*ptr) __rcu *__ptr = (typeof (*ptr) __rcu __force *)ptr; \
+         container_of((typeof(ptr))rcu_dereference_raw(__ptr), type, member); \
+        })
 
 /**
  * list_first_entry_rcu - get the first element from a list
@@ -225,9 +242,9 @@ static inline void list_splice_init_rcu(struct list_head *list,
         list_entry_rcu((ptr)->next, type, member)
 
 #define __list_for_each_rcu(pos, head) \
-        for (pos = rcu_dereference_raw((head)->next); \
+        for (pos = rcu_dereference_raw(list_next_rcu(head)); \
                 pos != (head); \
-                pos = rcu_dereference_raw(pos->next))
+                pos = rcu_dereference_raw(list_next_rcu((pos)))
 
 /**
  * list_for_each_entry_rcu      -       iterate over rcu list of given type
@@ -257,9 +274,9 @@ static inline void list_splice_init_rcu(struct list_head *list,
  * as long as the traversal is guarded by rcu_read_lock().
  */
 #define list_for_each_continue_rcu(pos, head) \
-        for ((pos) = rcu_dereference_raw((pos)->next); \
+        for ((pos) = rcu_dereference_raw(list_next_rcu(pos)); \
                 prefetch((pos)->next), (pos) != (head); \
-                (pos) = rcu_dereference_raw((pos)->next))
+                (pos) = rcu_dereference_raw(list_next_rcu(pos)))
 
 /**
  * list_for_each_entry_continue_rcu - continue iteration over list of given type
@@ -314,12 +331,19 @@ static inline void hlist_replace_rcu(struct hlist_node *old,
 
         new->next = next;
         new->pprev = old->pprev;
-        rcu_assign_pointer(*new->pprev, new);
+        rcu_assign_pointer(*(struct hlist_node __rcu **)new->pprev, new);
         if (next)
                 new->next->pprev = &new->next;
         old->pprev = LIST_POISON2;
 }
 
+/*
+ * return the first or the next element in an RCU protected hlist
+ */
+#define hlist_first_rcu(head)   (*((struct hlist_node __rcu **)(&(head)->first)))
+#define hlist_next_rcu(node)    (*((struct hlist_node __rcu **)(&(node)->next)))
+#define hlist_pprev_rcu(node)   (*((struct hlist_node __rcu **)((node)->pprev)))
+
 /**
  * hlist_add_head_rcu
  * @n: the element to add to the hash list.
@@ -346,7 +370,7 @@ static inline void hlist_add_head_rcu(struct hlist_node *n,
 
         n->next = first;
         n->pprev = &h->first;
-        rcu_assign_pointer(h->first, n);
+        rcu_assign_pointer(hlist_first_rcu(h), n);
         if (first)
                 first->pprev = &n->next;
 }
@@ -374,7 +398,7 @@ static inline void hlist_add_before_rcu(struct hlist_node *n,
 {
         n->pprev = next->pprev;
         n->next = next;
-        rcu_assign_pointer(*(n->pprev), n);
+        rcu_assign_pointer(hlist_pprev_rcu(n), n);
         next->pprev = &n->next;
 }
 
@@ -401,15 +425,15 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev,
 {
         n->next = prev->next;
         n->pprev = &prev->next;
-        rcu_assign_pointer(prev->next, n);
+        rcu_assign_pointer(hlist_next_rcu(prev), n);
         if (n->next)
                 n->next->pprev = &n->next;
 }
 
-#define __hlist_for_each_rcu(pos, head)                 \
-        for (pos = rcu_dereference((head)->first);      \
-             pos && ({ prefetch(pos->next); 1; });      \
-             pos = rcu_dereference(pos->next))
+#define __hlist_for_each_rcu(pos, head)                         \
+        for (pos = rcu_dereference(hlist_first_rcu(head));      \
+             pos && ({ prefetch(pos->next); 1; });              \
+             pos = rcu_dereference(hlist_next_rcu(pos)))
 
 /**
  * hlist_for_each_entry_rcu - iterate over rcu list of given type
@@ -422,11 +446,11 @@ static inline void hlist_add_after_rcu(struct hlist_node *prev,
  * the _rcu list-mutation primitives such as hlist_add_head_rcu()
  * as long as the traversal is guarded by rcu_read_lock().
  */
-#define hlist_for_each_entry_rcu(tpos, pos, head, member)                \
-        for (pos = rcu_dereference_raw((head)->first);                   \
+#define hlist_for_each_entry_rcu(tpos, pos, head, member)               \
+        for (pos = rcu_dereference_raw(hlist_first_rcu(head));          \
                 pos && ({ prefetch(pos->next); 1; }) &&                  \
                 ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); \
-                pos = rcu_dereference_raw(pos->next))
+                pos = rcu_dereference_raw(hlist_next_rcu(pos)))
 
 /**
  * hlist_for_each_entry_rcu_bh - iterate over rcu list of given type
diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h
index b70ffe53cb9f..2ae13714828b 100644
--- a/include/linux/rculist_nulls.h
+++ b/include/linux/rculist_nulls.h
@@ -37,6 +37,12 @@ static inline void hlist_nulls_del_init_rcu(struct hlist_nulls_node *n)
         }
 }
 
+#define hlist_nulls_first_rcu(head) \
+        (*((struct hlist_nulls_node __rcu __force **)&(head)->first))
+
+#define hlist_nulls_next_rcu(node) \
+        (*((struct hlist_nulls_node __rcu __force **)&(node)->next))
+
 /**
  * hlist_nulls_del_rcu - deletes entry from hash list without re-initialization
  * @n: the element to delete from the hash list.
@@ -88,7 +94,7 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n,
 
         n->next = first;
         n->pprev = &h->first;
-        rcu_assign_pointer(h->first, n);
+        rcu_assign_pointer(hlist_nulls_first_rcu(h), n);
         if (!is_a_nulls(first))
                 first->pprev = &n->next;
 }
@@ -100,11 +106,11 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n,
  * @member:     the name of the hlist_nulls_node within the struct.
  *
  */
-#define hlist_nulls_for_each_entry_rcu(tpos, pos, head, member) \
-        for (pos = rcu_dereference_raw((head)->first);                   \
-                (!is_a_nulls(pos)) &&                   \
+#define hlist_nulls_for_each_entry_rcu(tpos, pos, head, member)                 \
+        for (pos = rcu_dereference_raw(hlist_nulls_first_rcu(head));            \
+                (!is_a_nulls(pos)) &&                                           \
                 ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1; }); \
-                pos = rcu_dereference_raw(pos->next))
+                pos = rcu_dereference_raw(hlist_nulls_next_rcu(pos)))
 
 #endif
 #endif
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 83af1f8d8b74..03cda7bed985 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -41,11 +41,15 @@
 #include <linux/lockdep.h>
 #include <linux/completion.h>
 #include <linux/debugobjects.h>
+#include <linux/compiler.h>
 
 #ifdef CONFIG_RCU_TORTURE_TEST
 extern int rcutorture_runnable; /* for sysctl */
 #endif /* #ifdef CONFIG_RCU_TORTURE_TEST */
 
+#define ULONG_CMP_GE(a, b)      (ULONG_MAX / 2 >= (a) - (b))
+#define ULONG_CMP_LT(a, b)      (ULONG_MAX / 2 < (a) - (b))
+
 /**
  * struct rcu_head - callback structure for use with RCU
  * @next: next update requests in a list
@@ -57,29 +61,94 @@ struct rcu_head {
 };
 
 /* Exported common interfaces */
-extern void rcu_barrier(void);
+extern void call_rcu_sched(struct rcu_head *head,
+                           void (*func)(struct rcu_head *rcu));
+extern void synchronize_sched(void);
 extern void rcu_barrier_bh(void);
 extern void rcu_barrier_sched(void);
 extern void synchronize_sched_expedited(void);
 extern int sched_expedited_torture_stats(char *page);
 
+static inline void __rcu_read_lock_bh(void)
+{
+        local_bh_disable();
+}
+
+static inline void __rcu_read_unlock_bh(void)
+{
+        local_bh_enable();
+}
+
+#ifdef CONFIG_PREEMPT_RCU
+
+extern void __rcu_read_lock(void);
+extern void __rcu_read_unlock(void);
+void synchronize_rcu(void);
+
+/*
+ * Defined as a macro as it is a very low level header included from
+ * areas that don't even know about current.  This gives the rcu_read_lock()
+ * nesting depth, but makes sense only if CONFIG_PREEMPT_RCU -- in other
+ * types of kernel builds, the rcu_read_lock() nesting depth is unknowable.
+ */
+#define rcu_preempt_depth() (current->rcu_read_lock_nesting)
+
+#else /* #ifdef CONFIG_PREEMPT_RCU */
+
+static inline void __rcu_read_lock(void)
+{
+        preempt_disable();
+}
+
+static inline void __rcu_read_unlock(void)
+{
+        preempt_enable();
+}
+
+static inline void synchronize_rcu(void)
+{
+        synchronize_sched();
+}
+
+static inline int rcu_preempt_depth(void)
+{
+        return 0;
+}
+
+#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
+
 /* Internal to kernel */
 extern void rcu_init(void);
+extern void rcu_sched_qs(int cpu);
+extern void rcu_bh_qs(int cpu);
+extern void rcu_check_callbacks(int cpu, int user);
+struct notifier_block;
+
+#ifdef CONFIG_NO_HZ
+
+extern void rcu_enter_nohz(void);
+extern void rcu_exit_nohz(void);
+
+#else /* #ifdef CONFIG_NO_HZ */
+
+static inline void rcu_enter_nohz(void)
+{
+}
+
+static inline void rcu_exit_nohz(void)
+{
+}
+
+#endif /* #else #ifdef CONFIG_NO_HZ */
 
 #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU)
 #include <linux/rcutree.h>
-#elif defined(CONFIG_TINY_RCU)
+#elif defined(CONFIG_TINY_RCU) || defined(CONFIG_TINY_PREEMPT_RCU)
 #include <linux/rcutiny.h>
 #else
 #error "Unknown RCU implementation specified to kernel configuration"
 #endif
 
-#define RCU_HEAD_INIT   { .next = NULL, .func = NULL }
-#define RCU_HEAD(head) struct rcu_head head = RCU_HEAD_INIT
-#define INIT_RCU_HEAD(ptr) do { \
-       (ptr)->next = NULL; (ptr)->func = NULL; \
-} while (0)
-
 /*
  * init_rcu_head_on_stack()/destroy_rcu_head_on_stack() are needed for dynamic
  * initialization and destruction of rcu_head on the stack. rcu_head structures
@@ -120,14 +189,15 @@ extern struct lockdep_map rcu_sched_lock_map;
 extern int debug_lockdep_rcu_enabled(void);
 
 /**
- * rcu_read_lock_held - might we be in RCU read-side critical section?
+ * rcu_read_lock_held() - might we be in RCU read-side critical section?
  *
  * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an RCU
  * read-side critical section.  In absence of CONFIG_DEBUG_LOCK_ALLOC,
  * this assumes we are in an RCU read-side critical section unless it can
- * prove otherwise.
+ * prove otherwise.  This is useful for debug checks in functions that
+ * require that they be called within an RCU read-side critical section.
  *
- * Check debug_lockdep_rcu_enabled() to prevent false positives during boot
+ * Checks debug_lockdep_rcu_enabled() to prevent false positives during boot
  * and while lockdep is disabled.
  */
 static inline int rcu_read_lock_held(void)
@@ -144,14 +214,16 @@ static inline int rcu_read_lock_held(void)
 extern int rcu_read_lock_bh_held(void);
 
 /**
- * rcu_read_lock_sched_held - might we be in RCU-sched read-side critical section?
+ * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section?
  *
  * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an
  * RCU-sched read-side critical section.  In absence of
  * CONFIG_DEBUG_LOCK_ALLOC, this assumes we are in an RCU-sched read-side
  * critical section unless it can prove otherwise.  Note that disabling
  * of preemption (including disabling irqs) counts as an RCU-sched
- * read-side critical section.
+ * read-side critical section.  This is useful for debug checks in functions
+ * that required that they be called within an RCU-sched read-side
+ * critical section.
  *
  * Check debug_lockdep_rcu_enabled() to prevent false positives during boot
  * and while lockdep is disabled.
@@ -211,7 +283,11 @@ static inline int rcu_read_lock_sched_held(void)
 
 extern int rcu_my_thread_group_empty(void);
 
-#define __do_rcu_dereference_check(c)                                   \
+/**
+ * rcu_lockdep_assert - emit lockdep splat if specified condition not met
+ * @c: condition to check
+ */
+#define rcu_lockdep_assert(c)                                           \
         do {                                                            \
                 static bool __warned;                                   \
                 if (debug_lockdep_rcu_enabled() && !__warned && !(c)) { \
@@ -220,41 +296,163 @@ extern int rcu_my_thread_group_empty(void);
                 }                                                       \
         } while (0)
 
+#else /* #ifdef CONFIG_PROVE_RCU */
+
+#define rcu_lockdep_assert(c) do { } while (0)
+
+#endif /* #else #ifdef CONFIG_PROVE_RCU */
+
+/*
+ * Helper functions for rcu_dereference_check(), rcu_dereference_protected()
+ * and rcu_assign_pointer().  Some of these could be folded into their
+ * callers, but they are left separate in order to ease introduction of
+ * multiple flavors of pointers to match the multiple flavors of RCU
+ * (e.g., __rcu_bh, * __rcu_sched, and __srcu), should this make sense in
+ * the future.
+ */
+
+#ifdef __CHECKER__
+#define rcu_dereference_sparse(p, space) \
+        ((void)(((typeof(*p) space *)p) == p))
+#else /* #ifdef __CHECKER__ */
+#define rcu_dereference_sparse(p, space)
+#endif /* #else #ifdef __CHECKER__ */
+
+#define __rcu_access_pointer(p, space) \
+        ({ \
+                typeof(*p) *_________p1 = (typeof(*p)*__force )ACCESS_ONCE(p); \
+                rcu_dereference_sparse(p, space); \
+                ((typeof(*p) __force __kernel *)(_________p1)); \
+        })
+#define __rcu_dereference_check(p, c, space) \
+        ({ \
+                typeof(*p) *_________p1 = (typeof(*p)*__force )ACCESS_ONCE(p); \
+                rcu_lockdep_assert(c); \
+                rcu_dereference_sparse(p, space); \
+                smp_read_barrier_depends(); \
+                ((typeof(*p) __force __kernel *)(_________p1)); \
+        })
+#define __rcu_dereference_protected(p, c, space) \
+        ({ \
+                rcu_lockdep_assert(c); \
+                rcu_dereference_sparse(p, space); \
+                ((typeof(*p) __force __kernel *)(p)); \
+        })
+
+#define __rcu_dereference_index_check(p, c) \
+        ({ \
+                typeof(p) _________p1 = ACCESS_ONCE(p); \
+                rcu_lockdep_assert(c); \
+                smp_read_barrier_depends(); \
+                (_________p1); \
+        })
+#define __rcu_assign_pointer(p, v, space) \
+        ({ \
+                if (!__builtin_constant_p(v) || \
+                    ((v) != NULL)) \
+                        smp_wmb(); \
+                (p) = (typeof(*v) __force space *)(v); \
+        })
+
+
+/**
+ * rcu_access_pointer() - fetch RCU pointer with no dereferencing
+ * @p: The pointer to read
+ *
+ * Return the value of the specified RCU-protected pointer, but omit the
+ * smp_read_barrier_depends() and keep the ACCESS_ONCE().  This is useful
+ * when the value of this pointer is accessed, but the pointer is not
+ * dereferenced, for example, when testing an RCU-protected pointer against
+ * NULL.  Although rcu_access_pointer() may also be used in cases where
+ * update-side locks prevent the value of the pointer from changing, you
+ * should instead use rcu_dereference_protected() for this use case.
+ */
+#define rcu_access_pointer(p) __rcu_access_pointer((p), __rcu)
+
 /**
- * rcu_dereference_check - rcu_dereference with debug checking
+ * rcu_dereference_check() - rcu_dereference with debug checking
  * @p: The pointer to read, prior to dereferencing
  * @c: The conditions under which the dereference will take place
  *
  * Do an rcu_dereference(), but check that the conditions under which the
- * dereference will take place are correct.  Typically the conditions indicate
- * the various locking conditions that should be held at that point.  The check
- * should return true if the conditions are satisfied.
+ * dereference will take place are correct.  Typically the conditions
+ * indicate the various locking conditions that should be held at that
+ * point.  The check should return true if the conditions are satisfied.
+ * An implicit check for being in an RCU read-side critical section
+ * (rcu_read_lock()) is included.
  *
  * For example:
  *
- *      bar = rcu_dereference_check(foo->bar, rcu_read_lock_held() ||
- *                                            lockdep_is_held(&foo->lock));
+ *      bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock));
  *
  * could be used to indicate to lockdep that foo->bar may only be dereferenced
- * if either the RCU read lock is held, or that the lock required to replace
+ * if either rcu_read_lock() is held, or that the lock required to replace
  * the bar struct at foo->bar is held.
  *
  * Note that the list of conditions may also include indications of when a lock
  * need not be held, for example during initialisation or destruction of the
  * target struct:
  *
- *      bar = rcu_dereference_check(foo->bar, rcu_read_lock_held() ||
- *                                            lockdep_is_held(&foo->lock) ||
+ *      bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock) ||
  *                                            atomic_read(&foo->usage) == 0);
+ *
+ * Inserts memory barriers on architectures that require them
+ * (currently only the Alpha), prevents the compiler from refetching
+ * (and from merging fetches), and, more importantly, documents exactly
+ * which pointers are protected by RCU and checks that the pointer is
+ * annotated as __rcu.
  */
 #define rcu_dereference_check(p, c) \
-        ({ \
-                __do_rcu_dereference_check(c); \
-                rcu_dereference_raw(p); \
-        })
+        __rcu_dereference_check((p), rcu_read_lock_held() || (c), __rcu)
+
+/**
+ * rcu_dereference_bh_check() - rcu_dereference_bh with debug checking
+ * @p: The pointer to read, prior to dereferencing
+ * @c: The conditions under which the dereference will take place
+ *
+ * This is the RCU-bh counterpart to rcu_dereference_check().
+ */
+#define rcu_dereference_bh_check(p, c) \
+        __rcu_dereference_check((p), rcu_read_lock_bh_held() || (c), __rcu)
 
 /**
- * rcu_dereference_protected - fetch RCU pointer when updates prevented
+ * rcu_dereference_sched_check() - rcu_dereference_sched with debug checking
+ * @p: The pointer to read, prior to dereferencing
+ * @c: The conditions under which the dereference will take place
+ *
+ * This is the RCU-sched counterpart to rcu_dereference_check().
+ */
+#define rcu_dereference_sched_check(p, c) \
+        __rcu_dereference_check((p), rcu_read_lock_sched_held() || (c), \
+                                __rcu)
+
+#define rcu_dereference_raw(p) rcu_dereference_check(p, 1) /*@@@ needed? @@@*/
+
+/**
+ * rcu_dereference_index_check() - rcu_dereference for indices with debug checking
+ * @p: The pointer to read, prior to dereferencing
+ * @c: The conditions under which the dereference will take place
+ *
+ * Similar to rcu_dereference_check(), but omits the sparse checking.
+ * This allows rcu_dereference_index_check() to be used on integers,
+ * which can then be used as array indices.  Attempting to use
+ * rcu_dereference_check() on an integer will give compiler warnings
+ * because the sparse address-space mechanism relies on dereferencing
+ * the RCU-protected pointer.  Dereferencing integers is not something
+ * that even gcc will put up with.
+ *
+ * Note that this function does not implicitly check for RCU read-side
+ * critical sections.  If this function gains lots of uses, it might
+ * make sense to provide versions for each flavor of RCU, but it does
+ * not make sense as of early 2010.
+ */
+#define rcu_dereference_index_check(p, c) \
+        __rcu_dereference_index_check((p), (c))
+
+/**
+ * rcu_dereference_protected() - fetch RCU pointer when updates prevented
+ * @p: The pointer to read, prior to dereferencing
+ * @c: The conditions under which the dereference will take place
  *
  * Return the value of the specified RCU-protected pointer, but omit
  * both the smp_read_barrier_depends() and the ACCESS_ONCE().  This
@@ -263,35 +461,61 @@ extern int rcu_my_thread_group_empty(void);
  * prevent the compiler from repeating this reference or combining it
  * with other references, so it should not be used without protection
  * of appropriate locks.
+ *
+ * This function is only for update-side use.  Using this function
+ * when protected only by rcu_read_lock() will result in infrequent
+ * but very ugly failures.
  */
 #define rcu_dereference_protected(p, c) \
-        ({ \
-                __do_rcu_dereference_check(c); \
-                (p); \
-        })
+        __rcu_dereference_protected((p), (c), __rcu)
 
-#else /* #ifdef CONFIG_PROVE_RCU */
+/**
+ * rcu_dereference_bh_protected() - fetch RCU-bh pointer when updates prevented
+ * @p: The pointer to read, prior to dereferencing
+ * @c: The conditions under which the dereference will take place
+ *
+ * This is the RCU-bh counterpart to rcu_dereference_protected().
+ */
+#define rcu_dereference_bh_protected(p, c) \
+        __rcu_dereference_protected((p), (c), __rcu)
 
-#define rcu_dereference_check(p, c)     rcu_dereference_raw(p)
-#define rcu_dereference_protected(p, c) (p)
+/**
+ * rcu_dereference_sched_protected() - fetch RCU-sched pointer when updates prevented
+ * @p: The pointer to read, prior to dereferencing
+ * @c: The conditions under which the dereference will take place
+ *
+ * This is the RCU-sched counterpart to rcu_dereference_protected().
+ */
+#define rcu_dereference_sched_protected(p, c) \
+        __rcu_dereference_protected((p), (c), __rcu)
 
-#endif /* #else #ifdef CONFIG_PROVE_RCU */
 
 /**
- * rcu_access_pointer - fetch RCU pointer with no dereferencing
+ * rcu_dereference() - fetch RCU-protected pointer for dereferencing
+ * @p: The pointer to read, prior to dereferencing
  *
- * Return the value of the specified RCU-protected pointer, but omit the
- * smp_read_barrier_depends() and keep the ACCESS_ONCE().  This is useful
- * when the value of this pointer is accessed, but the pointer is not
- * dereferenced, for example, when testing an RCU-protected pointer against
- * NULL.  This may also be used in cases where update-side locks prevent
- * the value of the pointer from changing, but rcu_dereference_protected()
- * is a lighter-weight primitive for this use case.
+ * This is a simple wrapper around rcu_dereference_check().
+ */
+#define rcu_dereference(p) rcu_dereference_check(p, 0)
+
+/**
+ * rcu_dereference_bh() - fetch an RCU-bh-protected pointer for dereferencing
+ * @p: The pointer to read, prior to dereferencing
+ *
+ * Makes rcu_dereference_check() do the dirty work.
+ */
+#define rcu_dereference_bh(p) rcu_dereference_bh_check(p, 0)
+
+/**
+ * rcu_dereference_sched() - fetch RCU-sched-protected pointer for dereferencing
+ * @p: The pointer to read, prior to dereferencing
+ *
+ * Makes rcu_dereference_check() do the dirty work.
  */
-#define rcu_access_pointer(p)   ACCESS_ONCE(p)
+#define rcu_dereference_sched(p) rcu_dereference_sched_check(p, 0)
 
 /**
- * rcu_read_lock - mark the beginning of an RCU read-side critical section.
+ * rcu_read_lock() - mark the beginning of an RCU read-side critical section
  *
  * When synchronize_rcu() is invoked on one CPU while other CPUs
  * are within RCU read-side critical sections, then the
@@ -302,7 +526,7 @@ extern int rcu_my_thread_group_empty(void);
  * until after the all the other CPUs exit their critical sections.
  *
  * Note, however, that RCU callbacks are permitted to run concurrently
- * with RCU read-side critical sections.  One way that this can happen
+ * with new RCU read-side critical sections.  One way that this can happen
  * is via the following sequence of events: (1) CPU 0 enters an RCU
  * read-side critical section, (2) CPU 1 invokes call_rcu() to register
  * an RCU callback, (3) CPU 0 exits the RCU read-side critical section,
@@ -317,7 +541,20 @@ extern int rcu_my_thread_group_empty(void);
  * will be deferred until the outermost RCU read-side critical section
  * completes.
  *
- * It is illegal to block while in an RCU read-side critical section.
+ * You can avoid reading and understanding the next paragraph by
+ * following this rule: don't put anything in an rcu_read_lock() RCU
+ * read-side critical section that would block in a !PREEMPT kernel.
+ * But if you want the full story, read on!
+ *
+ * In non-preemptible RCU implementations (TREE_RCU and TINY_RCU), it
+ * is illegal to block while in an RCU read-side critical section.  In
+ * preemptible RCU implementations (TREE_PREEMPT_RCU and TINY_PREEMPT_RCU)
+ * in CONFIG_PREEMPT kernel builds, RCU read-side critical sections may
+ * be preempted, but explicit blocking is illegal.  Finally, in preemptible
+ * RCU implementations in real-time (CONFIG_PREEMPT_RT) kernel builds,
+ * RCU read-side critical sections may be preempted and they may also
+ * block, but only when acquiring spinlocks that are subject to priority
+ * inheritance.
  */
 static inline void rcu_read_lock(void)
 {
@@ -337,7 +574,7 @@ static inline void rcu_read_lock(void)
  */
 
 /**
- * rcu_read_unlock - marks the end of an RCU read-side critical section.
+ * rcu_read_unlock() - marks the end of an RCU read-side critical section.
  *
  * See rcu_read_lock() for more information.
  */
@@ -349,15 +586,16 @@ static inline void rcu_read_unlock(void)
 }
 
 /**
- * rcu_read_lock_bh - mark the beginning of a softirq-only RCU critical section
+ * rcu_read_lock_bh() - mark the beginning of an RCU-bh critical section
  *
  * This is equivalent of rcu_read_lock(), but to be used when updates
- * are being done using call_rcu_bh(). Since call_rcu_bh() callbacks
- * consider completion of a softirq handler to be a quiescent state,
- * a process in RCU read-side critical section must be protected by
- * disabling softirqs. Read-side critical sections in interrupt context
- * can use just rcu_read_lock().
- *
+ * are being done using call_rcu_bh() or synchronize_rcu_bh(). Since
+ * both call_rcu_bh() and synchronize_rcu_bh() consider completion of a
+ * softirq handler to be a quiescent state, a process in RCU read-side
+ * critical section must be protected by disabling softirqs. Read-side
+ * critical sections in interrupt context can use just rcu_read_lock(),
+ * though this should at least be commented to avoid confusing people
+ * reading the code.
  */
 static inline void rcu_read_lock_bh(void)
 {
@@ -379,13 +617,12 @@ static inline void rcu_read_unlock_bh(void)
 }
 
 /**
- * rcu_read_lock_sched - mark the beginning of a RCU-classic critical section
+ * rcu_read_lock_sched() - mark the beginning of a RCU-sched critical section
  *
- * Should be used with either
- * - synchronize_sched()
- * or
- * - call_rcu_sched() and rcu_barrier_sched()
- * on the write-side to insure proper synchronization.
+ * This is equivalent of rcu_read_lock(), but to be used when updates
+ * are being done using call_rcu_sched() or synchronize_rcu_sched().
+ * Read-side critical sections can also be introduced by anything that
+ * disables preemption, including local_irq_disable() and friends.
  */
 static inline void rcu_read_lock_sched(void)
 {
@@ -420,54 +657,14 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
         preempt_enable_notrace();
 }
 
-
 /**
- * rcu_dereference_raw - fetch an RCU-protected pointer
+ * rcu_assign_pointer() - assign to RCU-protected pointer
+ * @p: pointer to assign to
+ * @v: value to assign (publish)
  *
- * The caller must be within some flavor of RCU read-side critical
- * section, or must be otherwise preventing the pointer from changing,
- * for example, by holding an appropriate lock.  This pointer may later
- * be safely dereferenced.  It is the caller's responsibility to have
- * done the right thing, as this primitive does no checking of any kind.
- *
- * Inserts memory barriers on architectures that require them
- * (currently only the Alpha), and, more importantly, documents
- * exactly which pointers are protected by RCU.
- */
-#define rcu_dereference_raw(p)  ({ \
-                                typeof(p) _________p1 = ACCESS_ONCE(p); \
-                                smp_read_barrier_depends(); \
-                                (_________p1); \
-                                })
-
-/**
- * rcu_dereference - fetch an RCU-protected pointer, checking for RCU
- *
- * Makes rcu_dereference_check() do the dirty work.
- */
-#define rcu_dereference(p) \
-        rcu_dereference_check(p, rcu_read_lock_held())
-
-/**
- * rcu_dereference_bh - fetch an RCU-protected pointer, checking for RCU-bh
- *
- * Makes rcu_dereference_check() do the dirty work.
- */
-#define rcu_dereference_bh(p) \
-                rcu_dereference_check(p, rcu_read_lock_bh_held() || irqs_disabled())
-
-/**
- * rcu_dereference_sched - fetch RCU-protected pointer, checking for RCU-sched
- *
- * Makes rcu_dereference_check() do the dirty work.
- */
-#define rcu_dereference_sched(p) \
-                rcu_dereference_check(p, rcu_read_lock_sched_held())
-
-/**
- * rcu_assign_pointer - assign (publicize) a pointer to a newly
- * initialized structure that will be dereferenced by RCU read-side
- * critical sections.  Returns the value assigned.
+ * Assigns the specified value to the specified RCU-protected
+ * pointer, ensuring that any concurrent RCU readers will see
+ * any prior initialization.  Returns the value assigned.
  *
  * Inserts memory barriers on architectures that require them
  * (pretty much all of them other than x86), and also prevents
@@ -476,14 +673,17 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
  * call documents which pointers will be dereferenced by RCU read-side
  * code.
  */
-
 #define rcu_assign_pointer(p, v) \
-        ({ \
-                if (!__builtin_constant_p(v) || \
-                    ((v) != NULL)) \
-                        smp_wmb(); \
-                (p) = (v); \
-        })
+        __rcu_assign_pointer((p), (v), __rcu)
+
+/**
+ * RCU_INIT_POINTER() - initialize an RCU protected pointer
+ *
+ * Initialize an RCU-protected pointer in such a way to avoid RCU-lockdep
+ * splats.
+ */
+#define RCU_INIT_POINTER(p, v) \
+                p = (typeof(*v) __force __rcu *)(v)
 
 /* Infrastructure to implement the synchronize_() primitives. */
 
@@ -494,26 +694,37 @@ struct rcu_synchronize {
 
 extern void wakeme_after_rcu(struct rcu_head  *head);
 
+#ifdef CONFIG_PREEMPT_RCU
+
 /**
- * call_rcu - Queue an RCU callback for invocation after a grace period.
+ * call_rcu() - Queue an RCU callback for invocation after a grace period.
  * @head: structure to be used for queueing the RCU updates.
- * @func: actual update function to be invoked after the grace period
+ * @func: actual callback function to be invoked after the grace period
  *
- * The update function will be invoked some time after a full grace
- * period elapses, in other words after all currently executing RCU
- * read-side critical sections have completed.  RCU read-side critical
+ * The callback function will be invoked some time after a full grace
+ * period elapses, in other words after all pre-existing RCU read-side
+ * critical sections have completed.  However, the callback function
+ * might well execute concurrently with RCU read-side critical sections
+ * that started after call_rcu() was invoked.  RCU read-side critical
  * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
  * and may be nested.
  */
 extern void call_rcu(struct rcu_head *head,
                               void (*func)(struct rcu_head *head));
 
+#else /* #ifdef CONFIG_PREEMPT_RCU */
+
+/* In classic RCU, call_rcu() is just call_rcu_sched(). */
+#define call_rcu        call_rcu_sched
+
+#endif /* #else #ifdef CONFIG_PREEMPT_RCU */
+
 /**
- * call_rcu_bh - Queue an RCU for invocation after a quicker grace period.
+ * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period.
  * @head: structure to be used for queueing the RCU updates.
- * @func: actual update function to be invoked after the grace period
+ * @func: actual callback function to be invoked after the grace period
  *
- * The update function will be invoked some time after a full grace
+ * The callback function will be invoked some time after a full grace
  * period elapses, in other words after all currently executing RCU
  * read-side critical sections have completed. call_rcu_bh() assumes
  * that the read-side critical sections end on completion of a softirq
@@ -566,37 +777,4 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head)
 }
 #endif  /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */
 
-#ifndef CONFIG_PROVE_RCU
-#define __do_rcu_dereference_check(c) do { } while (0)
-#endif /* #ifdef CONFIG_PROVE_RCU */
-
-#define __rcu_dereference_index_check(p, c) \
-        ({ \
-                typeof(p) _________p1 = ACCESS_ONCE(p); \
-                __do_rcu_dereference_check(c); \
-                smp_read_barrier_depends(); \
-                (_________p1); \
-        })
-
-/**
- * rcu_dereference_index_check() - rcu_dereference for indices with debug checking
- * @p: The pointer to read, prior to dereferencing
- * @c: The conditions under which the dereference will take place
- *
- * Similar to rcu_dereference_check(), but omits the sparse checking.
- * This allows rcu_dereference_index_check() to be used on integers,
- * which can then be used as array indices.  Attempting to use
- * rcu_dereference_check() on an integer will give compiler warnings
- * because the sparse address-space mechanism relies on dereferencing
- * the RCU-protected pointer.  Dereferencing integers is not something
- * that even gcc will put up with.
- *
- * Note that this function does not implicitly check for RCU read-side
- * critical sections.  If this function gains lots of uses, it might
- * make sense to provide versions for each flavor of RCU, but it does
- * not make sense as of early 2010.
- */
-#define rcu_dereference_index_check(p, c) \
-        __rcu_dereference_index_check((p), (c))
-
 #endif /* __LINUX_RCUPDATE_H */
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index e2e893144a84..13877cb93a60 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -27,103 +27,101 @@
 
 #include <linux/cache.h>
 
-void rcu_sched_qs(int cpu);
-void rcu_bh_qs(int cpu);
-static inline void rcu_note_context_switch(int cpu)
-{
-        rcu_sched_qs(cpu);
-}
+#define rcu_init_sched()        do { } while (0)
 
-#define __rcu_read_lock()       preempt_disable()
-#define __rcu_read_unlock()     preempt_enable()
-#define __rcu_read_lock_bh()    local_bh_disable()
-#define __rcu_read_unlock_bh()  local_bh_enable()
-#define call_rcu_sched          call_rcu
+#ifdef CONFIG_TINY_RCU
 
-#define rcu_init_sched()        do { } while (0)
-extern void rcu_check_callbacks(int cpu, int user);
+static inline void synchronize_rcu_expedited(void)
+{
+        synchronize_sched();    /* Only one CPU, so pretty fast anyway!!! */
+}
 
-static inline int rcu_needs_cpu(int cpu)
+static inline void rcu_barrier(void)
 {
-        return 0;
+        rcu_barrier_sched();  /* Only one CPU, so only one list of callbacks! */
 }
 
-/*
- * Return the number of grace periods.
- */
-static inline long rcu_batches_completed(void)
+#else /* #ifdef CONFIG_TINY_RCU */
+
+void rcu_barrier(void);
+void synchronize_rcu_expedited(void);
+
+#endif /* #else #ifdef CONFIG_TINY_RCU */
+
+static inline void synchronize_rcu_bh(void)
 {
-        return 0;
+        synchronize_sched();
 }
 
-/*
- * Return the number of bottom-half grace periods.
- */
-static inline long rcu_batches_completed_bh(void)
+static inline void synchronize_rcu_bh_expedited(void)
 {
-        return 0;
+        synchronize_sched();
 }
 
-static inline void rcu_force_quiescent_state(void)
+#ifdef CONFIG_TINY_RCU
+
+static inline void rcu_preempt_note_context_switch(void)
 {
 }
 
-static inline void rcu_bh_force_quiescent_state(void)
+static inline void exit_rcu(void)
 {
 }
 
-static inline void rcu_sched_force_quiescent_state(void)
+static inline int rcu_needs_cpu(int cpu)
 {
+        return 0;
 }
 
-extern void synchronize_sched(void);
+#else /* #ifdef CONFIG_TINY_RCU */
+
+void rcu_preempt_note_context_switch(void);
+extern void exit_rcu(void);
+int rcu_preempt_needs_cpu(void);
 
-static inline void synchronize_rcu(void)
+static inline int rcu_needs_cpu(int cpu)
 {
-        synchronize_sched();
+        return rcu_preempt_needs_cpu();
 }
 
-static inline void synchronize_rcu_bh(void)
+#endif /* #else #ifdef CONFIG_TINY_RCU */
+
+static inline void rcu_note_context_switch(int cpu)
 {
-        synchronize_sched();
+        rcu_sched_qs(cpu);
+        rcu_preempt_note_context_switch();
 }
 
-static inline void synchronize_rcu_expedited(void)
+/*
+ * Return the number of grace periods.
+ */
+static inline long rcu_batches_completed(void)
 {
-        synchronize_sched();
+        return 0;
 }
 
-static inline void synchronize_rcu_bh_expedited(void)
+/*
+ * Return the number of bottom-half grace periods.
+ */
+static inline long rcu_batches_completed_bh(void)
 {
-        synchronize_sched();
+        return 0;
 }
 
-struct notifier_block;
-
-#ifdef CONFIG_NO_HZ
-
-extern void rcu_enter_nohz(void);
-extern void rcu_exit_nohz(void);
-
-#else /* #ifdef CONFIG_NO_HZ */
-
-static inline void rcu_enter_nohz(void)
+static inline void rcu_force_quiescent_state(void)
 {
 }
 
-static inline void rcu_exit_nohz(void)
+static inline void rcu_bh_force_quiescent_state(void)
 {
 }
 
-#endif /* #else #ifdef CONFIG_NO_HZ */
-
-static inline void exit_rcu(void)
+static inline void rcu_sched_force_quiescent_state(void)
 {
 }
 
-static inline int rcu_preempt_depth(void)
+static inline void rcu_cpu_stall_reset(void)
 {
-        return 0;
 }
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index c0ed1c056f29..95518e628794 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -30,64 +30,23 @@
 #ifndef __LINUX_RCUTREE_H
 #define __LINUX_RCUTREE_H
 
-struct notifier_block;
-
-extern void rcu_sched_qs(int cpu);
-extern void rcu_bh_qs(int cpu);
 extern void rcu_note_context_switch(int cpu);
 extern int rcu_needs_cpu(int cpu);
+extern void rcu_cpu_stall_reset(void);
 
 #ifdef CONFIG_TREE_PREEMPT_RCU
 
-extern void __rcu_read_lock(void);
-extern void __rcu_read_unlock(void);
-extern void synchronize_rcu(void);
 extern void exit_rcu(void);
 
-/*
- * Defined as macro as it is a very low level header
- * included from areas that don't even know about current
- */
-#define rcu_preempt_depth() (current->rcu_read_lock_nesting)
-
 #else /* #ifdef CONFIG_TREE_PREEMPT_RCU */
 
-static inline void __rcu_read_lock(void)
-{
-        preempt_disable();
-}
-
-static inline void __rcu_read_unlock(void)
-{
-        preempt_enable();
-}
-
-#define synchronize_rcu synchronize_sched
-
 static inline void exit_rcu(void)
 {
 }
 
-static inline int rcu_preempt_depth(void)
-{
-        return 0;
-}
-
 #endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */
 
-static inline void __rcu_read_lock_bh(void)
-{
-        local_bh_disable();
-}
-static inline void __rcu_read_unlock_bh(void)
-{
-        local_bh_enable();
-}
-
-extern void call_rcu_sched(struct rcu_head *head,
-                           void (*func)(struct rcu_head *rcu));
 extern void synchronize_rcu_bh(void);
-extern void synchronize_sched(void);
 extern void synchronize_rcu_expedited(void);
 
 static inline void synchronize_rcu_bh_expedited(void)
@@ -95,7 +54,7 @@ static inline void synchronize_rcu_bh_expedited(void)
         synchronize_sched_expedited();
 }
 
-extern void rcu_check_callbacks(int cpu, int user);
+extern void rcu_barrier(void);
 
 extern long rcu_batches_completed(void);
 extern long rcu_batches_completed_bh(void);
@@ -104,18 +63,6 @@ extern void rcu_force_quiescent_state(void);
 extern void rcu_bh_force_quiescent_state(void);
 extern void rcu_sched_force_quiescent_state(void);
 
-#ifdef CONFIG_NO_HZ
-void rcu_enter_nohz(void);
-void rcu_exit_nohz(void);
-#else /* CONFIG_NO_HZ */
-static inline void rcu_enter_nohz(void)
-{
-}
-static inline void rcu_exit_nohz(void)
-{
-}
-#endif /* CONFIG_NO_HZ */
-
 /* A context switch is a grace period for RCU-sched and RCU-bh. */
 static inline int rcu_blocking_is_gp(void)
 {
diff --git a/include/linux/sched.h b/include/linux/sched.h
index eb3c1ceec06e..0383601a927c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -875,6 +875,7 @@ enum sched_domain_level {
         SD_LV_NONE = 0,
         SD_LV_SIBLING,
         SD_LV_MC,
+        SD_LV_BOOK,
         SD_LV_CPU,
         SD_LV_NODE,
         SD_LV_ALLNODES,
@@ -1209,11 +1210,13 @@ struct task_struct {
         unsigned int policy;
         cpumask_t cpus_allowed;
 
-#ifdef CONFIG_TREE_PREEMPT_RCU
+#ifdef CONFIG_PREEMPT_RCU
         int rcu_read_lock_nesting;
         char rcu_read_unlock_special;
-        struct rcu_node *rcu_blocked_node;
         struct list_head rcu_node_entry;
+#endif /* #ifdef CONFIG_PREEMPT_RCU */
+#ifdef CONFIG_TREE_PREEMPT_RCU
+        struct rcu_node *rcu_blocked_node;
 #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
 
 #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
@@ -1295,9 +1298,9 @@ struct task_struct {
         struct list_head cpu_timers[3];
 
 /* process credentials */
-        const struct cred *real_cred;   /* objective and real subjective task
+        const struct cred __rcu *real_cred; /* objective and real subjective task
                                          * credentials (COW) */
-        const struct cred *cred;        /* effective (overridable) subjective task
+        const struct cred __rcu *cred;  /* effective (overridable) subjective task
                                          * credentials (COW) */
         struct mutex cred_guard_mutex;  /* guard against foreign influences on
                                          * credential calculations
@@ -1425,7 +1428,7 @@ struct task_struct {
 #endif
 #ifdef CONFIG_CGROUPS
         /* Control Group info protected by css_set_lock */
-        struct css_set *cgroups;
+        struct css_set __rcu *cgroups;
         /* cg_list protected by css_set_lock and tsk->alloc_lock */
         struct list_head cg_list;
 #endif
@@ -1688,8 +1691,7 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *
 /*
  * Per process flags
  */
-#define PF_ALIGNWARN    0x00000001      /* Print alignment warning msgs */
-                                        /* Not implemented yet, only for 486*/
+#define PF_KSOFTIRQD    0x00000001      /* I am ksoftirqd */
 #define PF_STARTING     0x00000002      /* being created */
 #define PF_EXITING      0x00000004      /* getting shut down */
 #define PF_EXITPIDONE   0x00000008      /* pi exit done on shut down */
@@ -1747,7 +1749,7 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *
 #define tsk_used_math(p) ((p)->flags & PF_USED_MATH)
 #define used_math() tsk_used_math(current)
 
-#ifdef CONFIG_TREE_PREEMPT_RCU
+#ifdef CONFIG_PREEMPT_RCU
 
 #define RCU_READ_UNLOCK_BLOCKED (1 << 0) /* blocked while in RCU read-side. */
 #define RCU_READ_UNLOCK_NEED_QS (1 << 1) /* RCU core needs CPU response. */
@@ -1756,7 +1758,9 @@ static inline void rcu_copy_process(struct task_struct *p)
 {
         p->rcu_read_lock_nesting = 0;
         p->rcu_read_unlock_special = 0;
+#ifdef CONFIG_TREE_PREEMPT_RCU
         p->rcu_blocked_node = NULL;
+#endif
         INIT_LIST_HEAD(&p->rcu_node_entry);
 }
 
@@ -1833,6 +1837,19 @@ extern void sched_clock_idle_sleep_event(void);
 extern void sched_clock_idle_wakeup_event(u64 delta_ns);
 #endif
 
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+/*
+ * An i/f to runtime opt-in for irq time accounting based off of sched_clock.
+ * The reason for this explicit opt-in is not to have perf penalty with
+ * slow sched_clocks.
+ */
+extern void enable_sched_clock_irqtime(void);
+extern void disable_sched_clock_irqtime(void);
+#else
+static inline void enable_sched_clock_irqtime(void) {}
+static inline void disable_sched_clock_irqtime(void) {}
+#endif
+
 extern unsigned long long
 task_sched_runtime(struct task_struct *task);
 extern unsigned long long thread_group_sched_runtime(struct task_struct *task);
@@ -2374,9 +2391,9 @@ extern int __cond_resched_lock(spinlock_t *lock);
 
 extern int __cond_resched_softirq(void);
 
-#define cond_resched_softirq() ({                               \
-        __might_sleep(__FILE__, __LINE__, SOFTIRQ_OFFSET);      \
-        __cond_resched_softirq();                               \
+#define cond_resched_softirq() ({                                       \
+        __might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET);      \
+        __cond_resched_softirq();                                       \
 })
 
 /*
diff --git a/include/linux/security.h b/include/linux/security.h
index a22219afff09..b8246a8df7d2 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -74,7 +74,7 @@ extern int cap_file_mmap(struct file *file, unsigned long reqprot,
 extern int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags);
 extern int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3,
                           unsigned long arg4, unsigned long arg5);
-extern int cap_task_setscheduler(struct task_struct *p, int policy, struct sched_param *lp);
+extern int cap_task_setscheduler(struct task_struct *p);
 extern int cap_task_setioprio(struct task_struct *p, int ioprio);
 extern int cap_task_setnice(struct task_struct *p, int nice);
 extern int cap_syslog(int type, bool from_file);
@@ -959,6 +959,12 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *      Sets the new child socket's sid to the openreq sid.
  * @inet_conn_established:
  *      Sets the connection's peersid to the secmark on skb.
+ * @secmark_relabel_packet:
+ *      check if the process should be allowed to relabel packets to the given secid
+ * @security_secmark_refcount_inc
+ *      tells the LSM to increment the number of secmark labeling rules loaded
+ * @security_secmark_refcount_dec
+ *      tells the LSM to decrement the number of secmark labeling rules loaded
  * @req_classify_flow:
  *      Sets the flow's sid to the openreq sid.
  * @tun_dev_create:
@@ -1279,9 +1285,13 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *      Return 0 if permission is granted.
  *
  * @secid_to_secctx:
- *      Convert secid to security context.
+ *      Convert secid to security context.  If secdata is NULL the length of
+ *      the result will be returned in seclen, but no secdata will be returned.
+ *      This does mean that the length could change between calls to check the
+ *      length and the next call which actually allocates and returns the secdata.
  *      @secid contains the security ID.
  *      @secdata contains the pointer that stores the converted security context.
+ *      @seclen pointer which contains the length of the data
  * @secctx_to_secid:
  *      Convert security context to secid.
  *      @secid contains the pointer to the generated security ID.
@@ -1501,8 +1511,7 @@ struct security_operations {
         int (*task_getioprio) (struct task_struct *p);
         int (*task_setrlimit) (struct task_struct *p, unsigned int resource,
                         struct rlimit *new_rlim);
-        int (*task_setscheduler) (struct task_struct *p, int policy,
-                                  struct sched_param *lp);
+        int (*task_setscheduler) (struct task_struct *p);
         int (*task_getscheduler) (struct task_struct *p);
         int (*task_movememory) (struct task_struct *p);
         int (*task_kill) (struct task_struct *p,
@@ -1594,6 +1603,9 @@ struct security_operations {
                                   struct request_sock *req);
         void (*inet_csk_clone) (struct sock *newsk, const struct request_sock *req);
         void (*inet_conn_established) (struct sock *sk, struct sk_buff *skb);
+        int (*secmark_relabel_packet) (u32 secid);
+        void (*secmark_refcount_inc) (void);
+        void (*secmark_refcount_dec) (void);
         void (*req_classify_flow) (const struct request_sock *req, struct flowi *fl);
         int (*tun_dev_create)(void);
         void (*tun_dev_post_create)(struct sock *sk);
@@ -1752,8 +1764,7 @@ int security_task_setioprio(struct task_struct *p, int ioprio);
 int security_task_getioprio(struct task_struct *p);
 int security_task_setrlimit(struct task_struct *p, unsigned int resource,
                 struct rlimit *new_rlim);
-int security_task_setscheduler(struct task_struct *p,
-                                int policy, struct sched_param *lp);
+int security_task_setscheduler(struct task_struct *p);
 int security_task_getscheduler(struct task_struct *p);
 int security_task_movememory(struct task_struct *p);
 int security_task_kill(struct task_struct *p, struct siginfo *info,
@@ -2320,11 +2331,9 @@ static inline int security_task_setrlimit(struct task_struct *p,
         return 0;
 }
 
-static inline int security_task_setscheduler(struct task_struct *p,
-                                             int policy,
-                                             struct sched_param *lp)
+static inline int security_task_setscheduler(struct task_struct *p)
 {
-        return cap_task_setscheduler(p, policy, lp);
+        return cap_task_setscheduler(p);
 }
 
 static inline int security_task_getscheduler(struct task_struct *p)
@@ -2551,6 +2560,9 @@ void security_inet_csk_clone(struct sock *newsk,
                         const struct request_sock *req);
 void security_inet_conn_established(struct sock *sk,
                         struct sk_buff *skb);
+int security_secmark_relabel_packet(u32 secid);
+void security_secmark_refcount_inc(void);
+void security_secmark_refcount_dec(void);
 int security_tun_dev_create(void);
 void security_tun_dev_post_create(struct sock *sk);
 int security_tun_dev_attach(struct sock *sk);
@@ -2705,6 +2717,19 @@ static inline void security_inet_conn_established(struct sock *sk,
 {
 }
 
+static inline int security_secmark_relabel_packet(u32 secid)
+{
+        return 0;
+}
+
+static inline void security_secmark_refcount_inc(void)
+{
+}
+
+static inline void security_secmark_refcount_dec(void)
+{
+}
+
 static inline int security_tun_dev_create(void)
 {
         return 0;
diff --git a/include/linux/selinux.h b/include/linux/selinux.h
index 82e0f26a1299..44f459612690 100644
--- a/include/linux/selinux.h
+++ b/include/linux/selinux.h
@@ -21,74 +21,11 @@ struct kern_ipc_perm;
 #ifdef CONFIG_SECURITY_SELINUX
 
 /**
- *     selinux_string_to_sid - map a security context string to a security ID
- *     @str: the security context string to be mapped
- *     @sid: ID value returned via this.
- *
- *     Returns 0 if successful, with the SID stored in sid.  A value
- *     of zero for sid indicates no SID could be determined (but no error
- *     occurred).
- */
-int selinux_string_to_sid(char *str, u32 *sid);
-
-/**
- *     selinux_secmark_relabel_packet_permission - secmark permission check
- *     @sid: SECMARK ID value to be applied to network packet
- *
- *     Returns 0 if the current task is allowed to set the SECMARK label of
- *     packets with the supplied security ID.  Note that it is implicit that
- *     the packet is always being relabeled from the default unlabeled value,
- *     and that the access control decision is made in the AVC.
- */
-int selinux_secmark_relabel_packet_permission(u32 sid);
-
-/**
- *     selinux_secmark_refcount_inc - increments the secmark use counter
- *
- *     SELinux keeps track of the current SECMARK targets in use so it knows
- *     when to apply SECMARK label access checks to network packets.  This
- *     function incements this reference count to indicate that a new SECMARK
- *     target has been configured.
- */
-void selinux_secmark_refcount_inc(void);
-
-/**
- *     selinux_secmark_refcount_dec - decrements the secmark use counter
- *
- *     SELinux keeps track of the current SECMARK targets in use so it knows
- *     when to apply SECMARK label access checks to network packets.  This
- *     function decements this reference count to indicate that one of the
- *     existing SECMARK targets has been removed/flushed.
- */
-void selinux_secmark_refcount_dec(void);
-
-/**
  * selinux_is_enabled - is SELinux enabled?
  */
 bool selinux_is_enabled(void);
 #else
 
-static inline int selinux_string_to_sid(const char *str, u32 *sid)
-{
-       *sid = 0;
-       return 0;
-}
-
-static inline int selinux_secmark_relabel_packet_permission(u32 sid)
-{
-        return 0;
-}
-
-static inline void selinux_secmark_refcount_inc(void)
-{
-        return;
-}
-
-static inline void selinux_secmark_refcount_dec(void)
-{
-        return;
-}
-
 static inline bool selinux_is_enabled(void)
 {
         return false;
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index 4d5d2f546dbf..58971e891f48 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -108,19 +108,43 @@ static inline int srcu_read_lock_held(struct srcu_struct *sp)
 #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
 /**
- * srcu_dereference - fetch SRCU-protected pointer with checking
+ * srcu_dereference_check - fetch SRCU-protected pointer for later dereferencing
+ * @p: the pointer to fetch and protect for later dereferencing
+ * @sp: pointer to the srcu_struct, which is used to check that we
+ *      really are in an SRCU read-side critical section.
+ * @c: condition to check for update-side use
  *
- * Makes rcu_dereference_check() do the dirty work.
+ * If PROVE_RCU is enabled, invoking this outside of an RCU read-side
+ * critical section will result in an RCU-lockdep splat, unless @c evaluates
+ * to 1.  The @c argument will normally be a logical expression containing
+ * lockdep_is_held() calls.
  */
-#define srcu_dereference(p, sp) \
-                rcu_dereference_check(p, srcu_read_lock_held(sp))
+#define srcu_dereference_check(p, sp, c) \
+        __rcu_dereference_check((p), srcu_read_lock_held(sp) || (c), __rcu)
+
+/**
+ * srcu_dereference - fetch SRCU-protected pointer for later dereferencing
+ * @p: the pointer to fetch and protect for later dereferencing
+ * @sp: pointer to the srcu_struct, which is used to check that we
+ *      really are in an SRCU read-side critical section.
+ *
+ * Makes rcu_dereference_check() do the dirty work.  If PROVE_RCU
+ * is enabled, invoking this outside of an RCU read-side critical
+ * section will result in an RCU-lockdep splat.
+ */
+#define srcu_dereference(p, sp) srcu_dereference_check((p), (sp), 0)
 
 /**
  * srcu_read_lock - register a new reader for an SRCU-protected structure.
  * @sp: srcu_struct in which to register the new reader.
  *
  * Enter an SRCU read-side critical section.  Note that SRCU read-side
- * critical sections may be nested.
+ * critical sections may be nested.  However, it is illegal to
+ * call anything that waits on an SRCU grace period for the same
+ * srcu_struct, whether directly or indirectly.  Please note that
+ * one way to indirectly wait on an SRCU grace period is to acquire
+ * a mutex that is held elsewhere while calling synchronize_srcu() or
+ * synchronize_srcu_expedited().
  */
 static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp)
 {
diff --git a/include/linux/sunrpc/auth_gss.h b/include/linux/sunrpc/auth_gss.h
index 671538d25bc1..8eee9dbbfe7a 100644
--- a/include/linux/sunrpc/auth_gss.h
+++ b/include/linux/sunrpc/auth_gss.h
@@ -69,7 +69,7 @@ struct gss_cl_ctx {
         enum rpc_gss_proc       gc_proc;
         u32                     gc_seq;
         spinlock_t              gc_seq_lock;
-        struct gss_ctx          *gc_gss_ctx;
+        struct gss_ctx __rcu    *gc_gss_ctx;
         struct xdr_netobj       gc_wire_ctx;
         u32                     gc_win;
         unsigned long           gc_expiry;
@@ -80,7 +80,7 @@ struct gss_upcall_msg;
 struct gss_cred {
         struct rpc_cred         gc_base;
         enum rpc_gss_svc        gc_service;
-        struct gss_cl_ctx       *gc_ctx;
+        struct gss_cl_ctx __rcu *gc_ctx;
         struct gss_upcall_msg   *gc_upcall;
         unsigned long           gc_upcall_timestamp;
         unsigned char           gc_machine_cred : 1;
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index a8cc4e13434c..c90696544176 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -23,12 +23,12 @@ struct restart_block {
                 };
                 /* For futex_wait and futex_wait_requeue_pi */
                 struct {
-                        u32 *uaddr;
+                        u32 __user *uaddr;
                         u32 val;
                         u32 flags;
                         u32 bitset;
                         u64 time;
-                        u32 *uaddr2;
+                        u32 __user *uaddr2;
                 } futex;
                 /* For nanosleep */
                 struct {
diff --git a/include/linux/topology.h b/include/linux/topology.h
index 64e084ff5e5c..b91a40e847d2 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -201,6 +201,12 @@ int arch_update_cpu_topology(void);
         .balance_interval       = 64,                                   \
 }
 
+#ifdef CONFIG_SCHED_BOOK
+#ifndef SD_BOOK_INIT
+#error Please define an appropriate SD_BOOK_INIT in include/asm/topology.h!!!
+#endif
+#endif /* CONFIG_SCHED_BOOK */
+
 #ifdef CONFIG_NUMA
 #ifndef SD_NODE_INIT
 #error Please define an appropriate SD_NODE_INIT in include/asm/topology.h!!!
diff --git a/include/net/cls_cgroup.h b/include/net/cls_cgroup.h
index ef6c24a529e1..a4dc5b027bd9 100644
--- a/include/net/cls_cgroup.h
+++ b/include/net/cls_cgroup.h
@@ -51,7 +51,8 @@ static inline u32 task_cls_classid(struct task_struct *p)
                 return 0;
 
         rcu_read_lock();
-        id = rcu_dereference(net_cls_subsys_id);
+        id = rcu_dereference_index_check(net_cls_subsys_id,
+                                         rcu_read_lock_held());
         if (id >= 0)
                 classid = container_of(task_subsys_state(p, id),
                                        struct cgroup_cls_state, css)->classid;
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index e624dae54fa4..caf17db87dbc 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -75,7 +75,7 @@ struct nf_conntrack_helper;
 /* nf_conn feature for connections that have a helper */
 struct nf_conn_help {
         /* Helper. if any */
-        struct nf_conntrack_helper *helper;
+        struct nf_conntrack_helper __rcu *helper;
 
         union nf_conntrack_help help;
 
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 9208c92aeab5..f6334782a593 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -362,6 +362,35 @@ TRACE_EVENT(sched_stat_runtime,
                         (unsigned long long)__entry->vruntime)
 );
 
+/*
+ * Tracepoint for showing priority inheritance modifying a tasks
+ * priority.
+ */
+TRACE_EVENT(sched_pi_setprio,
+
+        TP_PROTO(struct task_struct *tsk, int newprio),
+
+        TP_ARGS(tsk, newprio),
+
+        TP_STRUCT__entry(
+                __array( char,  comm,   TASK_COMM_LEN   )
+                __field( pid_t, pid                     )
+                __field( int,   oldprio                 )
+                __field( int,   newprio                 )
+        ),
+
+        TP_fast_assign(
+                memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+                __entry->pid            = tsk->pid;
+                __entry->oldprio        = tsk->prio;
+                __entry->newprio        = newprio;
+        ),
+
+        TP_printk("comm=%s pid=%d oldprio=%d newprio=%d",
+                        __entry->comm, __entry->pid,
+                        __entry->oldprio, __entry->newprio)
+);
+
 #endif /* _TRACE_SCHED_H */
 
 /* This part must be outside protection */
diff --git a/init/Kconfig b/init/Kconfig
index 1ef0b439908e..36890f0c8456 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -339,6 +339,8 @@ config AUDIT_TREE
         depends on AUDITSYSCALL
         select FSNOTIFY
 
+source "kernel/irq/Kconfig"
+
 menu "RCU Subsystem"
 
 choice
@@ -347,6 +349,7 @@ choice
 
 config TREE_RCU
         bool "Tree-based hierarchical RCU"
+        depends on !PREEMPT && SMP
         help
           This option selects the RCU implementation that is
           designed for very large SMP system with hundreds or
@@ -354,7 +357,7 @@ config TREE_RCU
           smaller systems.
 
 config TREE_PREEMPT_RCU
-        bool "Preemptable tree-based hierarchical RCU"
+        bool "Preemptible tree-based hierarchical RCU"
         depends on PREEMPT
         help
           This option selects the RCU implementation that is
@@ -372,8 +375,22 @@ config TINY_RCU
           is not required.  This option greatly reduces the
           memory footprint of RCU.
 
+config TINY_PREEMPT_RCU
+        bool "Preemptible UP-only small-memory-footprint RCU"
+        depends on !SMP && PREEMPT
+        help
+          This option selects the RCU implementation that is designed
+          for real-time UP systems.  This option greatly reduces the
+          memory footprint of RCU.
+
 endchoice
 
+config PREEMPT_RCU
+        def_bool ( TREE_PREEMPT_RCU || TINY_PREEMPT_RCU )
+        help
+          This option enables preemptible-RCU code that is common between
+          the TREE_PREEMPT_RCU and TINY_PREEMPT_RCU implementations.
+
 config RCU_TRACE
         bool "Enable tracing for RCU"
         depends on TREE_RCU || TREE_PREEMPT_RCU
@@ -394,9 +411,12 @@ config RCU_FANOUT
         help
           This option controls the fanout of hierarchical implementations
           of RCU, allowing RCU to work efficiently on machines with
-          large numbers of CPUs.  This value must be at least the cube
-          root of NR_CPUS, which allows NR_CPUS up to 32,768 for 32-bit
-          systems and up to 262,144 for 64-bit systems.
+          large numbers of CPUs.  This value must be at least the fourth
+          root of NR_CPUS, which allows NR_CPUS to be insanely large.
+          The default value of RCU_FANOUT should be used for production
+          systems, but if you are stress-testing the RCU implementation
+          itself, small RCU_FANOUT values allow you to test large-system
+          code paths on small(er) systems.
 
           Select a specific number if testing RCU itself.
           Take the default if unsure.
diff --git a/init/main.c b/init/main.c
index 94ab488039aa..9684c9670b48 100644
--- a/init/main.c
+++ b/init/main.c
@@ -556,7 +556,6 @@ asmlinkage void __init start_kernel(void)
 
         local_irq_disable();
         early_boot_irqs_off();
-        early_init_irq_lock_class();
 
 /*
  * Interrupts are still disabled. Do necessary setups, then
diff --git a/kernel/Makefile b/kernel/Makefile
index 4d9bf5f8531f..e2c9d52cfe9e 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -87,6 +87,7 @@ obj-$(CONFIG_TREE_RCU) += rcutree.o
 obj-$(CONFIG_TREE_PREEMPT_RCU) += rcutree.o
 obj-$(CONFIG_TREE_RCU_TRACE) += rcutree_trace.o
 obj-$(CONFIG_TINY_RCU) += rcutiny.o
+obj-$(CONFIG_TINY_PREEMPT_RCU) += rcutiny.o
 obj-$(CONFIG_RELAY) += relay.o
 obj-$(CONFIG_SYSCTL) += utsname_sysctl.o
 obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index c9483d8f6140..291ba3d04bea 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -138,7 +138,7 @@ struct css_id {
          * is called after synchronize_rcu(). But for safe use, css_is_removed()
          * css_tryget() should be used for avoiding race.
          */
-        struct cgroup_subsys_state *css;
+        struct cgroup_subsys_state __rcu *css;
         /*
          * ID of this css.
          */
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index b23c0979bbe7..51b143e2a07a 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1397,7 +1397,7 @@ static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cont,
         if (tsk->flags & PF_THREAD_BOUND)
                 return -EINVAL;
 
-        ret = security_task_setscheduler(tsk, 0, NULL);
+        ret = security_task_setscheduler(tsk);
         if (ret)
                 return ret;
         if (threadgroup) {
@@ -1405,7 +1405,7 @@ static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cont,
 
                 rcu_read_lock();
                 list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
-                        ret = security_task_setscheduler(c, 0, NULL);
+                        ret = security_task_setscheduler(c);
                         if (ret) {
                                 rcu_read_unlock();
                                 return ret;
diff --git a/kernel/futex.c b/kernel/futex.c
index 6a3a5fa1526d..a118bf160e0b 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -91,6 +91,7 @@ struct futex_pi_state {
 
 /**
  * struct futex_q - The hashed futex queue entry, one per waiting task
+ * @list:               priority-sorted list of tasks waiting on this futex
  * @task:               the task waiting on the futex
  * @lock_ptr:           the hash bucket lock
  * @key:                the key the futex is hashed on
@@ -104,7 +105,7 @@ struct futex_pi_state {
  *
  * A futex_q has a woken state, just like tasks have TASK_RUNNING.
  * It is considered woken when plist_node_empty(&q->list) || q->lock_ptr == 0.
- * The order of wakup is always to make the first condition true, then
+ * The order of wakeup is always to make the first condition true, then
  * the second.
  *
  * PI futexes are typically woken before they are removed from the hash list via
@@ -295,7 +296,7 @@ void put_futex_key(int fshared, union futex_key *key)
  * Slow path to fixup the fault we just took in the atomic write
  * access to @uaddr.
  *
- * We have no generic implementation of a non destructive write to the
+ * We have no generic implementation of a non-destructive write to the
  * user address. We know that we faulted in the atomic pagefault
  * disabled section so we can as well avoid the #PF overhead by
  * calling get_user_pages() right away.
@@ -515,7 +516,7 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
                          */
                         pi_state = this->pi_state;
                         /*
-                         * Userspace might have messed up non PI and PI futexes
+                         * Userspace might have messed up non-PI and PI futexes
                          */
                         if (unlikely(!pi_state))
                                 return -EINVAL;
@@ -736,8 +737,8 @@ static void wake_futex(struct futex_q *q)
 
         /*
          * We set q->lock_ptr = NULL _before_ we wake up the task. If
-         * a non futex wake up happens on another CPU then the task
-         * might exit and p would dereference a non existing task
+         * a non-futex wake up happens on another CPU then the task
+         * might exit and p would dereference a non-existing task
          * struct. Prevent this by holding a reference on p across the
          * wake up.
          */
@@ -1131,11 +1132,13 @@ static int futex_proxy_trylock_atomic(u32 __user *pifutex,
 
 /**
  * futex_requeue() - Requeue waiters from uaddr1 to uaddr2
- * uaddr1:      source futex user address
- * uaddr2:      target futex user address
- * nr_wake:     number of waiters to wake (must be 1 for requeue_pi)
- * nr_requeue:  number of waiters to requeue (0-INT_MAX)
- * requeue_pi:  if we are attempting to requeue from a non-pi futex to a
+ * @uaddr1:     source futex user address
+ * @fshared:    0 for a PROCESS_PRIVATE futex, 1 for PROCESS_SHARED
+ * @uaddr2:     target futex user address
+ * @nr_wake:    number of waiters to wake (must be 1 for requeue_pi)
+ * @nr_requeue: number of waiters to requeue (0-INT_MAX)
+ * @cmpval:     @uaddr1 expected value (or %NULL)
+ * @requeue_pi: if we are attempting to requeue from a non-pi futex to a
  *              pi futex (pi to pi requeue is not supported)
  *
  * Requeue waiters on uaddr1 to uaddr2. In the requeue_pi case, try to acquire
@@ -1360,10 +1363,10 @@ out:
 
 /* The key must be already stored in q->key. */
 static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
+        __acquires(&hb->lock)
 {
         struct futex_hash_bucket *hb;
 
-        get_futex_key_refs(&q->key);
         hb = hash_futex(&q->key);
         q->lock_ptr = &hb->lock;
 
@@ -1373,9 +1376,9 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q)
 
 static inline void
 queue_unlock(struct futex_q *q, struct futex_hash_bucket *hb)
+        __releases(&hb->lock)
 {
         spin_unlock(&hb->lock);
-        drop_futex_key_refs(&q->key);
 }
 
 /**
@@ -1391,6 +1394,7 @@ queue_unlock(struct futex_q *q, struct futex_hash_bucket *hb)
  * an example).
  */
 static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
+        __releases(&hb->lock)
 {
         int prio;
 
@@ -1471,6 +1475,7 @@ retry:
  * and dropped here.
  */
 static void unqueue_me_pi(struct futex_q *q)
+        __releases(q->lock_ptr)
 {
         WARN_ON(plist_node_empty(&q->list));
         plist_del(&q->list, &q->list.plist);
@@ -1480,8 +1485,6 @@ static void unqueue_me_pi(struct futex_q *q)
         q->pi_state = NULL;
 
         spin_unlock(q->lock_ptr);
-
-        drop_futex_key_refs(&q->key);
 }
 
 /*
@@ -1812,7 +1815,10 @@ static int futex_wait(u32 __user *uaddr, int fshared,
         }
 
 retry:
-        /* Prepare to wait on uaddr. */
+        /*
+         * Prepare to wait on uaddr. On success, holds hb lock and increments
+         * q.key refs.
+         */
         ret = futex_wait_setup(uaddr, val, fshared, &q, &hb);
         if (ret)
                 goto out;
@@ -1822,28 +1828,27 @@ retry:
 
         /* If we were woken (and unqueued), we succeeded, whatever. */
         ret = 0;
+        /* unqueue_me() drops q.key ref */
         if (!unqueue_me(&q))
-                goto out_put_key;
+                goto out;
         ret = -ETIMEDOUT;
         if (to && !to->task)
-                goto out_put_key;
+                goto out;
 
         /*
          * We expect signal_pending(current), but we might be the
          * victim of a spurious wakeup as well.
          */
-        if (!signal_pending(current)) {
-                put_futex_key(fshared, &q.key);
+        if (!signal_pending(current))
                 goto retry;
-        }
 
         ret = -ERESTARTSYS;
         if (!abs_time)
-                goto out_put_key;
+                goto out;
 
         restart = &current_thread_info()->restart_block;
         restart->fn = futex_wait_restart;
-        restart->futex.uaddr = (u32 *)uaddr;
+        restart->futex.uaddr = uaddr;
         restart->futex.val = val;
         restart->futex.time = abs_time->tv64;
         restart->futex.bitset = bitset;
@@ -1856,8 +1861,6 @@ retry:
 
         ret = -ERESTART_RESTARTBLOCK;
 
-out_put_key:
-        put_futex_key(fshared, &q.key);
 out:
         if (to) {
                 hrtimer_cancel(&to->timer);
@@ -1869,7 +1872,7 @@ out:
 
 static long futex_wait_restart(struct restart_block *restart)
 {
-        u32 __user *uaddr = (u32 __user *)restart->futex.uaddr;
+        u32 __user *uaddr = restart->futex.uaddr;
         int fshared = 0;
         ktime_t t, *tp = NULL;
 
@@ -2236,7 +2239,10 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared,
         q.rt_waiter = &rt_waiter;
         q.requeue_pi_key = &key2;
 
-        /* Prepare to wait on uaddr. */
+        /*
+         * Prepare to wait on uaddr. On success, increments q.key (key1) ref
+         * count.
+         */
         ret = futex_wait_setup(uaddr, val, fshared, &q, &hb);
         if (ret)
                 goto out_key2;
@@ -2254,7 +2260,9 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared,
          * In order for us to be here, we know our q.key == key2, and since
          * we took the hb->lock above, we also know that futex_requeue() has
          * completed and we no longer have to concern ourselves with a wakeup
-         * race with the atomic proxy lock acquition by the requeue code.
+         * race with the atomic proxy lock acquisition by the requeue code. The
+         * futex_requeue dropped our key1 reference and incremented our key2
+         * reference count.
          */
 
         /* Check if the requeue code acquired the second futex for us. */
@@ -2458,7 +2466,7 @@ retry:
  */
 static inline int fetch_robust_entry(struct robust_list __user **entry,
                                      struct robust_list __user * __user *head,
-                                     int *pi)
+                                     unsigned int *pi)
 {
         unsigned long uentry;
 
@@ -2647,7 +2655,7 @@ static int __init futex_init(void)
          * of the complex code paths. Also we want to prevent
          * registration of robust lists in that case. NULL is
          * guaranteed to fault and we get -EFAULT on functional
-         * implementation, the non functional ones will return
+         * implementation, the non-functional ones will return
          * -ENOSYS.
          */
         curval = cmpxchg_futex_value_locked(NULL, 0, 0);
diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c
index d49afb2395e5..06da4dfc339b 100644
--- a/kernel/futex_compat.c
+++ b/kernel/futex_compat.c
@@ -19,7 +19,7 @@
  */
 static inline int
 fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry,
-                   compat_uptr_t __user *head, int *pi)
+                   compat_uptr_t __user *head, unsigned int *pi)
 {
         if (get_user(*uentry, head))
                 return -EFAULT;
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 0c642d51aac2..53ead174da2f 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -98,7 +98,7 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
         printk(KERN_ERR "\"echo 0 > /proc/sys/kernel/hung_task_timeout_secs\""
                         " disables this message.\n");
         sched_show_task(t);
-        __debug_show_held_locks(t);
+        debug_show_held_locks(t);
 
         touch_nmi_watchdog();
 
@@ -111,7 +111,7 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
  * periodically exit the critical section and enter a new one.
  *
  * For preemptible RCU it is sufficient to call rcu_read_unlock in order
- * exit the grace period. For classic RCU, a reschedule is required.
+ * to exit the grace period. For classic RCU, a reschedule is required.
  */
 static void rcu_lock_break(struct task_struct *g, struct task_struct *t)
 {
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
new file mode 100644
index 000000000000..31d766bf5d2e
--- /dev/null
+++ b/kernel/irq/Kconfig
@@ -0,0 +1,53 @@
+config HAVE_GENERIC_HARDIRQS
+        def_bool n
+
+if HAVE_GENERIC_HARDIRQS
+menu "IRQ subsystem"
+#
+# Interrupt subsystem related configuration options
+#
+config GENERIC_HARDIRQS
+       def_bool y
+
+config GENERIC_HARDIRQS_NO__DO_IRQ
+       def_bool y
+
+# Select this to disable the deprecated stuff
+config GENERIC_HARDIRQS_NO_DEPRECATED
+       def_bool n
+
+# Options selectable by the architecture code
+config HAVE_SPARSE_IRQ
+       def_bool n
+
+config GENERIC_IRQ_PROBE
+        def_bool n
+
+config GENERIC_PENDING_IRQ
+        def_bool n
+
+config AUTO_IRQ_AFFINITY
+       def_bool n
+
+config IRQ_PER_CPU
+       def_bool n
+
+config HARDIRQS_SW_RESEND
+       def_bool n
+
+config SPARSE_IRQ
+        bool "Support sparse irq numbering"
+        depends on HAVE_SPARSE_IRQ
+        ---help---
+
+          Sparse irq numbering is useful for distro kernels that want
+          to define a high CONFIG_NR_CPUS value but still want to have
+          low kernel memory footprint on smaller machines.
+
+          ( Sparse irqs can also be beneficial on NUMA boxes, as they spread
+            out the interrupt descriptors in a more NUMA-friendly way. )
+
+          If you don't know what to do here, say N.
+
+endmenu
+endif
diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile
index 7d047808419d..54329cd7b3ee 100644
--- a/kernel/irq/Makefile
+++ b/kernel/irq/Makefile
@@ -1,7 +1,6 @@
 
-obj-y := handle.o manage.o spurious.o resend.o chip.o devres.o
+obj-y := irqdesc.o handle.o manage.o spurious.o resend.o chip.o dummychip.o devres.o
 obj-$(CONFIG_GENERIC_IRQ_PROBE) += autoprobe.o
 obj-$(CONFIG_PROC_FS) += proc.o
 obj-$(CONFIG_GENERIC_PENDING_IRQ) += migration.o
-obj-$(CONFIG_NUMA_IRQ_DESC) += numa_migrate.o
 obj-$(CONFIG_PM_SLEEP) += pm.o
diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c
index 2295a31ef110..505798f86c36 100644
--- a/kernel/irq/autoprobe.c
+++ b/kernel/irq/autoprobe.c
@@ -57,9 +57,10 @@ unsigned long probe_irq_on(void)
                          * Some chips need to know about probing in
                          * progress:
                          */
-                        if (desc->chip->set_type)
-                                desc->chip->set_type(i, IRQ_TYPE_PROBE);
-                        desc->chip->startup(i);
+                        if (desc->irq_data.chip->irq_set_type)
+                                desc->irq_data.chip->irq_set_type(&desc->irq_data,
+                                                         IRQ_TYPE_PROBE);
+                        desc->irq_data.chip->irq_startup(&desc->irq_data);
                 }
                 raw_spin_unlock_irq(&desc->lock);
         }
@@ -76,7 +77,7 @@ unsigned long probe_irq_on(void)
                 raw_spin_lock_irq(&desc->lock);
                 if (!desc->action && !(desc->status & IRQ_NOPROBE)) {
                         desc->status |= IRQ_AUTODETECT | IRQ_WAITING;
-                        if (desc->chip->startup(i))
+                        if (desc->irq_data.chip->irq_startup(&desc->irq_data))
                                 desc->status |= IRQ_PENDING;
                 }
                 raw_spin_unlock_irq(&desc->lock);
@@ -98,7 +99,7 @@ unsigned long probe_irq_on(void)
                         /* It triggered already - consider it spurious. */
                         if (!(status & IRQ_WAITING)) {
                                 desc->status = status & ~IRQ_AUTODETECT;
-                                desc->chip->shutdown(i);
+                                desc->irq_data.chip->irq_shutdown(&desc->irq_data);
                         } else
                                 if (i < 32)
                                         mask |= 1 << i;
@@ -137,7 +138,7 @@ unsigned int probe_irq_mask(unsigned long val)
                                 mask |= 1 << i;
 
                         desc->status = status & ~IRQ_AUTODETECT;
-                        desc->chip->shutdown(i);
+                        desc->irq_data.chip->irq_shutdown(&desc->irq_data);
                 }
                 raw_spin_unlock_irq(&desc->lock);
         }
@@ -181,7 +182,7 @@ int probe_irq_off(unsigned long val)
                                 nr_of_irqs++;
                         }
                         desc->status = status & ~IRQ_AUTODETECT;
-                        desc->chip->shutdown(i);
+                        desc->irq_data.chip->irq_shutdown(&desc->irq_data);
                 }
                 raw_spin_unlock_irq(&desc->lock);
         }
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index b7091d5ca2f8..baa5c4acad83 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -18,108 +18,6 @@
 
 #include "internals.h"
 
-static void dynamic_irq_init_x(unsigned int irq, bool keep_chip_data)
-{
-        struct irq_desc *desc;
-        unsigned long flags;
-
-        desc = irq_to_desc(irq);
-        if (!desc) {
-                WARN(1, KERN_ERR "Trying to initialize invalid IRQ%d\n", irq);
-                return;
-        }
-
-        /* Ensure we don't have left over values from a previous use of this irq */
-        raw_spin_lock_irqsave(&desc->lock, flags);
-        desc->status = IRQ_DISABLED;
-        desc->chip = &no_irq_chip;
-        desc->handle_irq = handle_bad_irq;
-        desc->depth = 1;
-        desc->msi_desc = NULL;
-        desc->handler_data = NULL;
-        if (!keep_chip_data)
-                desc->chip_data = NULL;
-        desc->action = NULL;
-        desc->irq_count = 0;
-        desc->irqs_unhandled = 0;
-#ifdef CONFIG_SMP
-        cpumask_setall(desc->affinity);
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-        cpumask_clear(desc->pending_mask);
-#endif
-#endif
-        raw_spin_unlock_irqrestore(&desc->lock, flags);
-}
-
-/**
- *      dynamic_irq_init - initialize a dynamically allocated irq
- *      @irq:   irq number to initialize
- */
-void dynamic_irq_init(unsigned int irq)
-{
-        dynamic_irq_init_x(irq, false);
-}
-
-/**
- *      dynamic_irq_init_keep_chip_data - initialize a dynamically allocated irq
- *      @irq:   irq number to initialize
- *
- *      does not set irq_to_desc(irq)->chip_data to NULL
- */
-void dynamic_irq_init_keep_chip_data(unsigned int irq)
-{
-        dynamic_irq_init_x(irq, true);
-}
-
-static void dynamic_irq_cleanup_x(unsigned int irq, bool keep_chip_data)
-{
-        struct irq_desc *desc = irq_to_desc(irq);
-        unsigned long flags;
-
-        if (!desc) {
-                WARN(1, KERN_ERR "Trying to cleanup invalid IRQ%d\n", irq);
-                return;
-        }
-
-        raw_spin_lock_irqsave(&desc->lock, flags);
-        if (desc->action) {
-                raw_spin_unlock_irqrestore(&desc->lock, flags);
-                WARN(1, KERN_ERR "Destroying IRQ%d without calling free_irq\n",
-                        irq);
-                return;
-        }
-        desc->msi_desc = NULL;
-        desc->handler_data = NULL;
-        if (!keep_chip_data)
-                desc->chip_data = NULL;
-        desc->handle_irq = handle_bad_irq;
-        desc->chip = &no_irq_chip;
-        desc->name = NULL;
-        clear_kstat_irqs(desc);
-        raw_spin_unlock_irqrestore(&desc->lock, flags);
-}
-
-/**
- *      dynamic_irq_cleanup - cleanup a dynamically allocated irq
- *      @irq:   irq number to initialize
- */
-void dynamic_irq_cleanup(unsigned int irq)
-{
-        dynamic_irq_cleanup_x(irq, false);
-}
-
-/**
- *      dynamic_irq_cleanup_keep_chip_data - cleanup a dynamically allocated irq
- *      @irq:   irq number to initialize
- *
- *      does not set irq_to_desc(irq)->chip_data to NULL
- */
-void dynamic_irq_cleanup_keep_chip_data(unsigned int irq)
-{
-        dynamic_irq_cleanup_x(irq, true);
-}
-
-
 /**
  *      set_irq_chip - set the irq chip for an irq
  *      @irq:   irq number
@@ -140,7 +38,7 @@ int set_irq_chip(unsigned int irq, struct irq_chip *chip)
 
         raw_spin_lock_irqsave(&desc->lock, flags);
         irq_chip_set_defaults(chip);
-        desc->chip = chip;
+        desc->irq_data.chip = chip;
         raw_spin_unlock_irqrestore(&desc->lock, flags);
 
         return 0;
@@ -193,7 +91,7 @@ int set_irq_data(unsigned int irq, void *data)
         }
 
         raw_spin_lock_irqsave(&desc->lock, flags);
-        desc->handler_data = data;
+        desc->irq_data.handler_data = data;
         raw_spin_unlock_irqrestore(&desc->lock, flags);
         return 0;
 }
@@ -218,7 +116,7 @@ int set_irq_msi(unsigned int irq, struct msi_desc *entry)
         }
 
         raw_spin_lock_irqsave(&desc->lock, flags);
-        desc->msi_desc = entry;
+        desc->irq_data.msi_desc = entry;
         if (entry)
                 entry->irq = irq;
         raw_spin_unlock_irqrestore(&desc->lock, flags);
@@ -243,19 +141,27 @@ int set_irq_chip_data(unsigned int irq, void *data)
                 return -EINVAL;
         }
 
-        if (!desc->chip) {
+        if (!desc->irq_data.chip) {
                 printk(KERN_ERR "BUG: bad set_irq_chip_data(IRQ#%d)\n", irq);
                 return -EINVAL;
         }
 
         raw_spin_lock_irqsave(&desc->lock, flags);
-        desc->chip_data = data;
+        desc->irq_data.chip_data = data;
         raw_spin_unlock_irqrestore(&desc->lock, flags);
 
         return 0;
 }
 EXPORT_SYMBOL(set_irq_chip_data);
 
+struct irq_data *irq_get_irq_data(unsigned int irq)
+{
+        struct irq_desc *desc = irq_to_desc(irq);
+
+        return desc ? &desc->irq_data : NULL;
+}
+EXPORT_SYMBOL_GPL(irq_get_irq_data);
+
 /**
  *      set_irq_nested_thread - Set/Reset the IRQ_NESTED_THREAD flag of an irq
  *
@@ -287,93 +193,216 @@ EXPORT_SYMBOL_GPL(set_irq_nested_thread);
 /*
  * default enable function
  */
-static void default_enable(unsigned int irq)
+static void default_enable(struct irq_data *data)
 {
-        struct irq_desc *desc = irq_to_desc(irq);
+        struct irq_desc *desc = irq_data_to_desc(data);
 
-        desc->chip->unmask(irq);
+        desc->irq_data.chip->irq_unmask(&desc->irq_data);
         desc->status &= ~IRQ_MASKED;
 }
 
 /*
  * default disable function
  */
-static void default_disable(unsigned int irq)
+static void default_disable(struct irq_data *data)
 {
 }
 
 /*
  * default startup function
  */
-static unsigned int default_startup(unsigned int irq)
+static unsigned int default_startup(struct irq_data *data)
 {
-        struct irq_desc *desc = irq_to_desc(irq);
+        struct irq_desc *desc = irq_data_to_desc(data);
 
-        desc->chip->enable(irq);
+        desc->irq_data.chip->irq_enable(data);
         return 0;
 }
 
 /*
  * default shutdown function
  */
-static void default_shutdown(unsigned int irq)
+static void default_shutdown(struct irq_data *data)
 {
-        struct irq_desc *desc = irq_to_desc(irq);
+        struct irq_desc *desc = irq_data_to_desc(data);
 
-        desc->chip->mask(irq);
+        desc->irq_data.chip->irq_mask(&desc->irq_data);
         desc->status |= IRQ_MASKED;
 }
 
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
+/* Temporary migration helpers */
+static void compat_irq_mask(struct irq_data *data)
+{
+        data->chip->mask(data->irq);
+}
+
+static void compat_irq_unmask(struct irq_data *data)
+{
+        data->chip->unmask(data->irq);
+}
+
+static void compat_irq_ack(struct irq_data *data)
+{
+        data->chip->ack(data->irq);
+}
+
+static void compat_irq_mask_ack(struct irq_data *data)
+{
+        data->chip->mask_ack(data->irq);
+}
+
+static void compat_irq_eoi(struct irq_data *data)
+{
+        data->chip->eoi(data->irq);
+}
+
+static void compat_irq_enable(struct irq_data *data)
+{
+        data->chip->enable(data->irq);
+}
+
+static void compat_irq_disable(struct irq_data *data)
+{
+        data->chip->disable(data->irq);
+}
+
+static void compat_irq_shutdown(struct irq_data *data)
+{
+        data->chip->shutdown(data->irq);
+}
+
+static unsigned int compat_irq_startup(struct irq_data *data)
+{
+        return data->chip->startup(data->irq);
+}
+
+static int compat_irq_set_affinity(struct irq_data *data,
+                                   const struct cpumask *dest, bool force)
+{
+        return data->chip->set_affinity(data->irq, dest);
+}
+
+static int compat_irq_set_type(struct irq_data *data, unsigned int type)
+{
+        return data->chip->set_type(data->irq, type);
+}
+
+static int compat_irq_set_wake(struct irq_data *data, unsigned int on)
+{
+        return data->chip->set_wake(data->irq, on);
+}
+
+static int compat_irq_retrigger(struct irq_data *data)
+{
+        return data->chip->retrigger(data->irq);
+}
+
+static void compat_bus_lock(struct irq_data *data)
+{
+        data->chip->bus_lock(data->irq);
+}
+
+static void compat_bus_sync_unlock(struct irq_data *data)
+{
+        data->chip->bus_sync_unlock(data->irq);
+}
+#endif
+
 /*
  * Fixup enable/disable function pointers
  */
 void irq_chip_set_defaults(struct irq_chip *chip)
 {
-        if (!chip->enable)
-                chip->enable = default_enable;
-        if (!chip->disable)
-                chip->disable = default_disable;
-        if (!chip->startup)
-                chip->startup = default_startup;
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
         /*
-         * We use chip->disable, when the user provided its own. When
-         * we have default_disable set for chip->disable, then we need
+         * Compat fixup functions need to be before we set the
+         * defaults for enable/disable/startup/shutdown
+         */
+        if (chip->enable)
+                chip->irq_enable = compat_irq_enable;
+        if (chip->disable)
+                chip->irq_disable = compat_irq_disable;
+        if (chip->shutdown)
+                chip->irq_shutdown = compat_irq_shutdown;
+        if (chip->startup)
+                chip->irq_startup = compat_irq_startup;
+#endif
+        /*
+         * The real defaults
+         */
+        if (!chip->irq_enable)
+                chip->irq_enable = default_enable;
+        if (!chip->irq_disable)
+                chip->irq_disable = default_disable;
+        if (!chip->irq_startup)
+                chip->irq_startup = default_startup;
+        /*
+         * We use chip->irq_disable, when the user provided its own. When
+         * we have default_disable set for chip->irq_disable, then we need
          * to use default_shutdown, otherwise the irq line is not
          * disabled on free_irq():
          */
-        if (!chip->shutdown)
-                chip->shutdown = chip->disable != default_disable ?
-                        chip->disable : default_shutdown;
-        if (!chip->name)
-                chip->name = chip->typename;
+        if (!chip->irq_shutdown)
+                chip->irq_shutdown = chip->irq_disable != default_disable ?
+                        chip->irq_disable : default_shutdown;
+
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
         if (!chip->end)
                 chip->end = dummy_irq_chip.end;
+
+        /*
+         * Now fix up the remaining compat handlers
+         */
+        if (chip->bus_lock)
+                chip->irq_bus_lock = compat_bus_lock;
+        if (chip->bus_sync_unlock)
+                chip->irq_bus_sync_unlock = compat_bus_sync_unlock;
+        if (chip->mask)
+                chip->irq_mask = compat_irq_mask;
+        if (chip->unmask)
+                chip->irq_unmask = compat_irq_unmask;
+        if (chip->ack)
+                chip->irq_ack = compat_irq_ack;
+        if (chip->mask_ack)
+                chip->irq_mask_ack = compat_irq_mask_ack;
+        if (chip->eoi)
+                chip->irq_eoi = compat_irq_eoi;
+        if (chip->set_affinity)
+                chip->irq_set_affinity = compat_irq_set_affinity;
+        if (chip->set_type)
+                chip->irq_set_type = compat_irq_set_type;
+        if (chip->set_wake)
+                chip->irq_set_wake = compat_irq_set_wake;
+        if (chip->retrigger)
+                chip->irq_retrigger = compat_irq_retrigger;
+#endif
 }
 
-static inline void mask_ack_irq(struct irq_desc *desc, int irq)
+static inline void mask_ack_irq(struct irq_desc *desc)
 {
-        if (desc->chip->mask_ack)
-                desc->chip->mask_ack(irq);
+        if (desc->irq_data.chip->irq_mask_ack)
+                desc->irq_data.chip->irq_mask_ack(&desc->irq_data);
         else {
-                desc->chip->mask(irq);
-                if (desc->chip->ack)
-                        desc->chip->ack(irq);
+                desc->irq_data.chip->irq_mask(&desc->irq_data);
+                if (desc->irq_data.chip->irq_ack)
+                        desc->irq_data.chip->irq_ack(&desc->irq_data);
         }
         desc->status |= IRQ_MASKED;
 }
 
-static inline void mask_irq(struct irq_desc *desc, int irq)
+static inline void mask_irq(struct irq_desc *desc)
 {
-        if (desc->chip->mask) {
-                desc->chip->mask(irq);
+        if (desc->irq_data.chip->irq_mask) {
+                desc->irq_data.chip->irq_mask(&desc->irq_data);
                 desc->status |= IRQ_MASKED;
         }
 }
 
-static inline void unmask_irq(struct irq_desc *desc, int irq)
+static inline void unmask_irq(struct irq_desc *desc)
 {
-        if (desc->chip->unmask) {
-                desc->chip->unmask(irq);
+        if (desc->irq_data.chip->irq_unmask) {
+                desc->irq_data.chip->irq_unmask(&desc->irq_data);
                 desc->status &= ~IRQ_MASKED;
         }
 }
@@ -476,7 +505,7 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
         irqreturn_t action_ret;
 
         raw_spin_lock(&desc->lock);
-        mask_ack_irq(desc, irq);
+        mask_ack_irq(desc);
 
         if (unlikely(desc->status & IRQ_INPROGRESS))
                 goto out_unlock;
@@ -502,7 +531,7 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
         desc->status &= ~IRQ_INPROGRESS;
 
         if (!(desc->status & (IRQ_DISABLED | IRQ_ONESHOT)))
-                unmask_irq(desc, irq);
+                unmask_irq(desc);
 out_unlock:
         raw_spin_unlock(&desc->lock);
 }
@@ -539,7 +568,7 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
         action = desc->action;
         if (unlikely(!action || (desc->status & IRQ_DISABLED))) {
                 desc->status |= IRQ_PENDING;
-                mask_irq(desc, irq);
+                mask_irq(desc);
                 goto out;
         }
 
@@ -554,7 +583,7 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
         raw_spin_lock(&desc->lock);
         desc->status &= ~IRQ_INPROGRESS;
 out:
-        desc->chip->eoi(irq);
+        desc->irq_data.chip->irq_eoi(&desc->irq_data);
 
         raw_spin_unlock(&desc->lock);
 }
@@ -590,14 +619,13 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
         if (unlikely((desc->status & (IRQ_INPROGRESS | IRQ_DISABLED)) ||
                     !desc->action)) {
                 desc->status |= (IRQ_PENDING | IRQ_MASKED);
-                mask_ack_irq(desc, irq);
+                mask_ack_irq(desc);
                 goto out_unlock;
         }
         kstat_incr_irqs_this_cpu(irq, desc);
 
         /* Start handling the irq */
-        if (desc->chip->ack)
-                desc->chip->ack(irq);
+        desc->irq_data.chip->irq_ack(&desc->irq_data);
 
         /* Mark the IRQ currently in progress.*/
         desc->status |= IRQ_INPROGRESS;
@@ -607,7 +635,7 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
                 irqreturn_t action_ret;
 
                 if (unlikely(!action)) {
-                        mask_irq(desc, irq);
+                        mask_irq(desc);
                         goto out_unlock;
                 }
 
@@ -619,7 +647,7 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
                 if (unlikely((desc->status &
                                (IRQ_PENDING | IRQ_MASKED | IRQ_DISABLED)) ==
                               (IRQ_PENDING | IRQ_MASKED))) {
-                        unmask_irq(desc, irq);
+                        unmask_irq(desc);
                 }
 
                 desc->status &= ~IRQ_PENDING;
@@ -650,15 +678,15 @@ handle_percpu_irq(unsigned int irq, struct irq_desc *desc)
 
         kstat_incr_irqs_this_cpu(irq, desc);
 
-        if (desc->chip->ack)
-                desc->chip->ack(irq);
+        if (desc->irq_data.chip->irq_ack)
+                desc->irq_data.chip->irq_ack(&desc->irq_data);
 
         action_ret = handle_IRQ_event(irq, desc->action);
         if (!noirqdebug)
                 note_interrupt(irq, desc, action_ret);
 
-        if (desc->chip->eoi)
-                desc->chip->eoi(irq);
+        if (desc->irq_data.chip->irq_eoi)
+                desc->irq_data.chip->irq_eoi(&desc->irq_data);
 }
 
 void
@@ -676,7 +704,7 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 
         if (!handle)
                 handle = handle_bad_irq;
-        else if (desc->chip == &no_irq_chip) {
+        else if (desc->irq_data.chip == &no_irq_chip) {
                 printk(KERN_WARNING "Trying to install %sinterrupt handler "
                        "for IRQ%d\n", is_chained ? "chained " : "", irq);
                 /*
@@ -686,16 +714,16 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
                  * prevent us to setup the interrupt at all. Switch it to
                  * dummy_irq_chip for easy transition.
                  */
-                desc->chip = &dummy_irq_chip;
+                desc->irq_data.chip = &dummy_irq_chip;
         }
 
-        chip_bus_lock(irq, desc);
+        chip_bus_lock(desc);
         raw_spin_lock_irqsave(&desc->lock, flags);
 
         /* Uninstall? */
         if (handle == handle_bad_irq) {
-                if (desc->chip != &no_irq_chip)
-                        mask_ack_irq(desc, irq);
+                if (desc->irq_data.chip != &no_irq_chip)
+                        mask_ack_irq(desc);
                 desc->status |= IRQ_DISABLED;
                 desc->depth = 1;
         }
@@ -706,10 +734,10 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
                 desc->status &= ~IRQ_DISABLED;
                 desc->status |= IRQ_NOREQUEST | IRQ_NOPROBE;
                 desc->depth = 0;
-                desc->chip->startup(irq);
+                desc->irq_data.chip->irq_startup(&desc->irq_data);
         }
         raw_spin_unlock_irqrestore(&desc->lock, flags);
-        chip_bus_sync_unlock(irq, desc);
+        chip_bus_sync_unlock(desc);
 }
 EXPORT_SYMBOL_GPL(__set_irq_handler);
 
@@ -729,32 +757,20 @@ set_irq_chip_and_handler_name(unsigned int irq, struct irq_chip *chip,
         __set_irq_handler(irq, handle, 0, name);
 }
 
-void set_irq_noprobe(unsigned int irq)
+void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set)
 {
         struct irq_desc *desc = irq_to_desc(irq);
         unsigned long flags;
 
-        if (!desc) {
-                printk(KERN_ERR "Trying to mark IRQ%d non-probeable\n", irq);
+        if (!desc)
                 return;
-        }
-
-        raw_spin_lock_irqsave(&desc->lock, flags);
-        desc->status |= IRQ_NOPROBE;
-        raw_spin_unlock_irqrestore(&desc->lock, flags);
-}
-
-void set_irq_probe(unsigned int irq)
-{
-        struct irq_desc *desc = irq_to_desc(irq);
-        unsigned long flags;
 
-        if (!desc) {
-                printk(KERN_ERR "Trying to mark IRQ%d probeable\n", irq);
-                return;
-        }
+        /* Sanitize flags */
+        set &= IRQF_MODIFY_MASK;
+        clr &= IRQF_MODIFY_MASK;
 
         raw_spin_lock_irqsave(&desc->lock, flags);
-        desc->status &= ~IRQ_NOPROBE;
+        desc->status &= ~clr;
+        desc->status |= set;
         raw_spin_unlock_irqrestore(&desc->lock, flags);
 }
diff --git a/kernel/irq/dummychip.c b/kernel/irq/dummychip.c
new file mode 100644
index 000000000000..20dc5474947e
--- /dev/null
+++ b/kernel/irq/dummychip.c
@@ -0,0 +1,68 @@
+/*
+ * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar
+ * Copyright (C) 2005-2006, Thomas Gleixner, Russell King
+ *
+ * This file contains the dummy interrupt chip implementation
+ */
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+
+#include "internals.h"
+
+/*
+ * What should we do if we get a hw irq event on an illegal vector?
+ * Each architecture has to answer this themself.
+ */
+static void ack_bad(struct irq_data *data)
+{
+        struct irq_desc *desc = irq_data_to_desc(data);
+
+        print_irq_desc(data->irq, desc);
+        ack_bad_irq(data->irq);
+}
+
+/*
+ * NOP functions
+ */
+static void noop(struct irq_data *data) { }
+
+static unsigned int noop_ret(struct irq_data *data)
+{
+        return 0;
+}
+
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
+static void compat_noop(unsigned int irq) { }
+#define END_INIT .end = compat_noop
+#else
+#define END_INIT
+#endif
+
+/*
+ * Generic no controller implementation
+ */
+struct irq_chip no_irq_chip = {
+        .name           = "none",
+        .irq_startup    = noop_ret,
+        .irq_shutdown   = noop,
+        .irq_enable     = noop,
+        .irq_disable    = noop,
+        .irq_ack        = ack_bad,
+        END_INIT
+};
+
+/*
+ * Generic dummy implementation which can be used for
+ * real dumb interrupt sources
+ */
+struct irq_chip dummy_irq_chip = {
+        .name           = "dummy",
+        .irq_startup    = noop_ret,
+        .irq_shutdown   = noop,
+        .irq_enable     = noop,
+        .irq_disable    = noop,
+        .irq_ack        = noop,
+        .irq_mask       = noop,
+        .irq_unmask     = noop,
+        END_INIT
+};
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 27e5c6911223..e2347eb63306 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -11,24 +11,15 @@
  */
 
 #include <linux/irq.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/module.h>
 #include <linux/random.h>
+#include <linux/sched.h>
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
-#include <linux/rculist.h>
-#include <linux/hash.h>
-#include <linux/radix-tree.h>
+
 #include <trace/events/irq.h>
 
 #include "internals.h"
 
-/*
- * lockdep: we want to handle all irq_desc locks as a single lock-class:
- */
-struct lock_class_key irq_desc_lock_class;
-
 /**
  * handle_bad_irq - handle spurious and unhandled irqs
  * @irq:       the interrupt number
@@ -43,304 +34,6 @@ void handle_bad_irq(unsigned int irq, struct irq_desc *desc)
         ack_bad_irq(irq);
 }
 
-#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS)
-static void __init init_irq_default_affinity(void)
-{
-        alloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
-        cpumask_setall(irq_default_affinity);
-}
-#else
-static void __init init_irq_default_affinity(void)
-{
-}
-#endif
-
-/*
- * Linux has a controller-independent interrupt architecture.
- * Every controller has a 'controller-template', that is used
- * by the main code to do the right thing. Each driver-visible
- * interrupt source is transparently wired to the appropriate
- * controller. Thus drivers need not be aware of the
- * interrupt-controller.
- *
- * The code is designed to be easily extended with new/different
- * interrupt controllers, without having to do assembly magic or
- * having to touch the generic code.
- *
- * Controller mappings for all interrupt sources:
- */
-int nr_irqs = NR_IRQS;
-EXPORT_SYMBOL_GPL(nr_irqs);
-
-#ifdef CONFIG_SPARSE_IRQ
-
-static struct irq_desc irq_desc_init = {
-        .irq        = -1,
-        .status     = IRQ_DISABLED,
-        .chip       = &no_irq_chip,
-        .handle_irq = handle_bad_irq,
-        .depth      = 1,
-        .lock       = __RAW_SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
-};
-
-void __ref init_kstat_irqs(struct irq_desc *desc, int node, int nr)
-{
-        void *ptr;
-
-        ptr = kzalloc_node(nr * sizeof(*desc->kstat_irqs),
-                           GFP_ATOMIC, node);
-
-        /*
-         * don't overwite if can not get new one
-         * init_copy_kstat_irqs() could still use old one
-         */
-        if (ptr) {
-                printk(KERN_DEBUG "  alloc kstat_irqs on node %d\n", node);
-                desc->kstat_irqs = ptr;
-        }
-}
-
-static void init_one_irq_desc(int irq, struct irq_desc *desc, int node)
-{
-        memcpy(desc, &irq_desc_init, sizeof(struct irq_desc));
-
-        raw_spin_lock_init(&desc->lock);
-        desc->irq = irq;
-#ifdef CONFIG_SMP
-        desc->node = node;
-#endif
-        lockdep_set_class(&desc->lock, &irq_desc_lock_class);
-        init_kstat_irqs(desc, node, nr_cpu_ids);
-        if (!desc->kstat_irqs) {
-                printk(KERN_ERR "can not alloc kstat_irqs\n");
-                BUG_ON(1);
-        }
-        if (!alloc_desc_masks(desc, node, false)) {
-                printk(KERN_ERR "can not alloc irq_desc cpumasks\n");
-                BUG_ON(1);
-        }
-        init_desc_masks(desc);
-        arch_init_chip_data(desc, node);
-}
-
-/*
- * Protect the sparse_irqs:
- */
-DEFINE_RAW_SPINLOCK(sparse_irq_lock);
-
-static RADIX_TREE(irq_desc_tree, GFP_ATOMIC);
-
-static void set_irq_desc(unsigned int irq, struct irq_desc *desc)
-{
-        radix_tree_insert(&irq_desc_tree, irq, desc);
-}
-
-struct irq_desc *irq_to_desc(unsigned int irq)
-{
-        return radix_tree_lookup(&irq_desc_tree, irq);
-}
-
-void replace_irq_desc(unsigned int irq, struct irq_desc *desc)
-{
-        void **ptr;
-
-        ptr = radix_tree_lookup_slot(&irq_desc_tree, irq);
-        if (ptr)
-                radix_tree_replace_slot(ptr, desc);
-}
-
-static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_smp = {
-        [0 ... NR_IRQS_LEGACY-1] = {
-                .irq        = -1,
-                .status     = IRQ_DISABLED,
-                .chip       = &no_irq_chip,
-                .handle_irq = handle_bad_irq,
-                .depth      = 1,
-                .lock       = __RAW_SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
-        }
-};
-
-static unsigned int *kstat_irqs_legacy;
-
-int __init early_irq_init(void)
-{
-        struct irq_desc *desc;
-        int legacy_count;
-        int node;
-        int i;
-
-        init_irq_default_affinity();
-
-         /* initialize nr_irqs based on nr_cpu_ids */
-        arch_probe_nr_irqs();
-        printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d\n", NR_IRQS, nr_irqs);
-
-        desc = irq_desc_legacy;
-        legacy_count = ARRAY_SIZE(irq_desc_legacy);
-        node = first_online_node;
-
-        /* allocate based on nr_cpu_ids */
-        kstat_irqs_legacy = kzalloc_node(NR_IRQS_LEGACY * nr_cpu_ids *
-                                          sizeof(int), GFP_NOWAIT, node);
-
-        for (i = 0; i < legacy_count; i++) {
-                desc[i].irq = i;
-#ifdef CONFIG_SMP
-                desc[i].node = node;
-#endif
-                desc[i].kstat_irqs = kstat_irqs_legacy + i * nr_cpu_ids;
-                lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
-                alloc_desc_masks(&desc[i], node, true);
-                init_desc_masks(&desc[i]);
-                set_irq_desc(i, &desc[i]);
-        }
-
-        return arch_early_irq_init();
-}
-
-struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node)
-{
-        struct irq_desc *desc;
-        unsigned long flags;
-
-        if (irq >= nr_irqs) {
-                WARN(1, "irq (%d) >= nr_irqs (%d) in irq_to_desc_alloc\n",
-                        irq, nr_irqs);
-                return NULL;
-        }
-
-        desc = irq_to_desc(irq);
-        if (desc)
-                return desc;
-
-        raw_spin_lock_irqsave(&sparse_irq_lock, flags);
-
-        /* We have to check it to avoid races with another CPU */
-        desc = irq_to_desc(irq);
-        if (desc)
-                goto out_unlock;
-
-        desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
-
-        printk(KERN_DEBUG "  alloc irq_desc for %d on node %d\n", irq, node);
-        if (!desc) {
-                printk(KERN_ERR "can not alloc irq_desc\n");
-                BUG_ON(1);
-        }
-        init_one_irq_desc(irq, desc, node);
-
-        set_irq_desc(irq, desc);
-
-out_unlock:
-        raw_spin_unlock_irqrestore(&sparse_irq_lock, flags);
-
-        return desc;
-}
-
-#else /* !CONFIG_SPARSE_IRQ */
-
-struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
-        [0 ... NR_IRQS-1] = {
-                .status = IRQ_DISABLED,
-                .chip = &no_irq_chip,
-                .handle_irq = handle_bad_irq,
-                .depth = 1,
-                .lock = __RAW_SPIN_LOCK_UNLOCKED(irq_desc->lock),
-        }
-};
-
-static unsigned int kstat_irqs_all[NR_IRQS][NR_CPUS];
-int __init early_irq_init(void)
-{
-        struct irq_desc *desc;
-        int count;
-        int i;
-
-        init_irq_default_affinity();
-
-        printk(KERN_INFO "NR_IRQS:%d\n", NR_IRQS);
-
-        desc = irq_desc;
-        count = ARRAY_SIZE(irq_desc);
-
-        for (i = 0; i < count; i++) {
-                desc[i].irq = i;
-                alloc_desc_masks(&desc[i], 0, true);
-                init_desc_masks(&desc[i]);
-                desc[i].kstat_irqs = kstat_irqs_all[i];
-        }
-        return arch_early_irq_init();
-}
-
-struct irq_desc *irq_to_desc(unsigned int irq)
-{
-        return (irq < NR_IRQS) ? irq_desc + irq : NULL;
-}
-
-struct irq_desc *irq_to_desc_alloc_node(unsigned int irq, int node)
-{
-        return irq_to_desc(irq);
-}
-#endif /* !CONFIG_SPARSE_IRQ */
-
-void clear_kstat_irqs(struct irq_desc *desc)
-{
-        memset(desc->kstat_irqs, 0, nr_cpu_ids * sizeof(*(desc->kstat_irqs)));
-}
-
-/*
- * What should we do if we get a hw irq event on an illegal vector?
- * Each architecture has to answer this themself.
- */
-static void ack_bad(unsigned int irq)
-{
-        struct irq_desc *desc = irq_to_desc(irq);
-
-        print_irq_desc(irq, desc);
-        ack_bad_irq(irq);
-}
-
-/*
- * NOP functions
- */
-static void noop(unsigned int irq)
-{
-}
-
-static unsigned int noop_ret(unsigned int irq)
-{
-        return 0;
-}
-
-/*
- * Generic no controller implementation
- */
-struct irq_chip no_irq_chip = {
-        .name           = "none",
-        .startup        = noop_ret,
-        .shutdown       = noop,
-        .enable         = noop,
-        .disable        = noop,
-        .ack            = ack_bad,
-        .end            = noop,
-};
-
-/*
- * Generic dummy implementation which can be used for
- * real dumb interrupt sources
- */
-struct irq_chip dummy_irq_chip = {
-        .name           = "dummy",
-        .startup        = noop_ret,
-        .shutdown       = noop,
-        .enable         = noop,
-        .disable        = noop,
-        .ack            = noop,
-        .mask           = noop,
-        .unmask         = noop,
-        .end            = noop,
-};
-
 /*
  * Special, empty irq handler:
  */
@@ -457,20 +150,20 @@ unsigned int __do_IRQ(unsigned int irq)
                 /*
                  * No locking required for CPU-local interrupts:
                  */
-                if (desc->chip->ack)
-                        desc->chip->ack(irq);
+                if (desc->irq_data.chip->ack)
+                        desc->irq_data.chip->ack(irq);
                 if (likely(!(desc->status & IRQ_DISABLED))) {
                         action_ret = handle_IRQ_event(irq, desc->action);
                         if (!noirqdebug)
                                 note_interrupt(irq, desc, action_ret);
                 }
-                desc->chip->end(irq);
+                desc->irq_data.chip->end(irq);
                 return 1;
         }
 
         raw_spin_lock(&desc->lock);
-        if (desc->chip->ack)
-                desc->chip->ack(irq);
+        if (desc->irq_data.chip->ack)
+                desc->irq_data.chip->ack(irq);
         /*
          * REPLAY is when Linux resends an IRQ that was dropped earlier
          * WAITING is used by probe to mark irqs that are being tested
@@ -530,27 +223,9 @@ out:
          * The ->end() handler has to deal with interrupts which got
          * disabled while the handler was running.
          */
-        desc->chip->end(irq);
+        desc->irq_data.chip->end(irq);
         raw_spin_unlock(&desc->lock);
 
         return 1;
 }
 #endif
-
-void early_init_irq_lock_class(void)
-{
-        struct irq_desc *desc;
-        int i;
-
-        for_each_irq_desc(i, desc) {
-                lockdep_set_class(&desc->lock, &irq_desc_lock_class);
-        }
-}
-
-unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
-{
-        struct irq_desc *desc = irq_to_desc(irq);
-        return desc ? desc->kstat_irqs[cpu] : 0;
-}
-EXPORT_SYMBOL(kstat_irqs_cpu);
-
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index c63f3bc88f0b..4571ae7e085a 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -1,9 +1,12 @@
 /*
  * IRQ subsystem internal functions and variables:
  */
+#include <linux/irqdesc.h>
 
 extern int noirqdebug;
 
+#define irq_data_to_desc(data)  container_of(data, struct irq_desc, irq_data)
+
 /* Set default functions for irq_chip structures: */
 extern void irq_chip_set_defaults(struct irq_chip *chip);
 
@@ -15,21 +18,19 @@ extern int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 extern void __disable_irq(struct irq_desc *desc, unsigned int irq, bool susp);
 extern void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume);
 
-extern struct lock_class_key irq_desc_lock_class;
 extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr);
-extern void clear_kstat_irqs(struct irq_desc *desc);
-extern raw_spinlock_t sparse_irq_lock;
 
-#ifdef CONFIG_SPARSE_IRQ
-void replace_irq_desc(unsigned int irq, struct irq_desc *desc);
-#endif
+/* Resending of interrupts :*/
+void check_irq_resend(struct irq_desc *desc, unsigned int irq);
 
 #ifdef CONFIG_PROC_FS
 extern void register_irq_proc(unsigned int irq, struct irq_desc *desc);
+extern void unregister_irq_proc(unsigned int irq, struct irq_desc *desc);
 extern void register_handler_proc(unsigned int irq, struct irqaction *action);
 extern void unregister_handler_proc(unsigned int irq, struct irqaction *action);
 #else
 static inline void register_irq_proc(unsigned int irq, struct irq_desc *desc) { }
+static inline void unregister_irq_proc(unsigned int irq, struct irq_desc *desc) { }
 static inline void register_handler_proc(unsigned int irq,
                                          struct irqaction *action) { }
 static inline void unregister_handler_proc(unsigned int irq,
@@ -40,17 +41,27 @@ extern int irq_select_affinity_usr(unsigned int irq);
 
 extern void irq_set_thread_affinity(struct irq_desc *desc);
 
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
+static inline void irq_end(unsigned int irq, struct irq_desc *desc)
+{
+        if (desc->irq_data.chip && desc->irq_data.chip->end)
+                desc->irq_data.chip->end(irq);
+}
+#else
+static inline void irq_end(unsigned int irq, struct irq_desc *desc) { }
+#endif
+
 /* Inline functions for support of irq chips on slow busses */
-static inline void chip_bus_lock(unsigned int irq, struct irq_desc *desc)
+static inline void chip_bus_lock(struct irq_desc *desc)
 {
-        if (unlikely(desc->chip->bus_lock))
-                desc->chip->bus_lock(irq);
+        if (unlikely(desc->irq_data.chip->irq_bus_lock))
+                desc->irq_data.chip->irq_bus_lock(&desc->irq_data);
 }
 
-static inline void chip_bus_sync_unlock(unsigned int irq, struct irq_desc *desc)
+static inline void chip_bus_sync_unlock(struct irq_desc *desc)
 {
-        if (unlikely(desc->chip->bus_sync_unlock))
-                desc->chip->bus_sync_unlock(irq);
+        if (unlikely(desc->irq_data.chip->irq_bus_sync_unlock))
+                desc->irq_data.chip->irq_bus_sync_unlock(&desc->irq_data);
 }
 
 /*
@@ -67,8 +78,8 @@ static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
                 irq, desc, desc->depth, desc->irq_count, desc->irqs_unhandled);
         printk("->handle_irq():  %p, ", desc->handle_irq);
         print_symbol("%s\n", (unsigned long)desc->handle_irq);
-        printk("->chip(): %p, ", desc->chip);
-        print_symbol("%s\n", (unsigned long)desc->chip);
+        printk("->irq_data.chip(): %p, ", desc->irq_data.chip);
+        print_symbol("%s\n", (unsigned long)desc->irq_data.chip);
         printk("->action(): %p\n", desc->action);
         if (desc->action) {
                 printk("->action->handler(): %p, ", desc->action->handler);
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
new file mode 100644
index 000000000000..9d917ff72675
--- /dev/null
+++ b/kernel/irq/irqdesc.c
@@ -0,0 +1,395 @@
+/*
+ * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar
+ * Copyright (C) 2005-2006, Thomas Gleixner, Russell King
+ *
+ * This file contains the interrupt descriptor management code
+ *
+ * Detailed information is available in Documentation/DocBook/genericirq
+ *
+ */
+#include <linux/irq.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/kernel_stat.h>
+#include <linux/radix-tree.h>
+#include <linux/bitmap.h>
+
+#include "internals.h"
+
+/*
+ * lockdep: we want to handle all irq_desc locks as a single lock-class:
+ */
+static struct lock_class_key irq_desc_lock_class;
+
+#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS)
+static void __init init_irq_default_affinity(void)
+{
+        alloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
+        cpumask_setall(irq_default_affinity);
+}
+#else
+static void __init init_irq_default_affinity(void)
+{
+}
+#endif
+
+#ifdef CONFIG_SMP
+static int alloc_masks(struct irq_desc *desc, gfp_t gfp, int node)
+{
+        if (!zalloc_cpumask_var_node(&desc->irq_data.affinity, gfp, node))
+                return -ENOMEM;
+
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+        if (!zalloc_cpumask_var_node(&desc->pending_mask, gfp, node)) {
+                free_cpumask_var(desc->irq_data.affinity);
+                return -ENOMEM;
+        }
+#endif
+        return 0;
+}
+
+static void desc_smp_init(struct irq_desc *desc, int node)
+{
+        desc->irq_data.node = node;
+        cpumask_copy(desc->irq_data.affinity, irq_default_affinity);
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+        cpumask_clear(desc->pending_mask);
+#endif
+}
+
+static inline int desc_node(struct irq_desc *desc)
+{
+        return desc->irq_data.node;
+}
+
+#else
+static inline int
+alloc_masks(struct irq_desc *desc, gfp_t gfp, int node) { return 0; }
+static inline void desc_smp_init(struct irq_desc *desc, int node) { }
+static inline int desc_node(struct irq_desc *desc) { return 0; }
+#endif
+
+static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node)
+{
+        desc->irq_data.irq = irq;
+        desc->irq_data.chip = &no_irq_chip;
+        desc->irq_data.chip_data = NULL;
+        desc->irq_data.handler_data = NULL;
+        desc->irq_data.msi_desc = NULL;
+        desc->status = IRQ_DEFAULT_INIT_FLAGS;
+        desc->handle_irq = handle_bad_irq;
+        desc->depth = 1;
+        desc->irq_count = 0;
+        desc->irqs_unhandled = 0;
+        desc->name = NULL;
+        memset(desc->kstat_irqs, 0, nr_cpu_ids * sizeof(*(desc->kstat_irqs)));
+        desc_smp_init(desc, node);
+}
+
+int nr_irqs = NR_IRQS;
+EXPORT_SYMBOL_GPL(nr_irqs);
+
+static DEFINE_MUTEX(sparse_irq_lock);
+static DECLARE_BITMAP(allocated_irqs, NR_IRQS);
+
+#ifdef CONFIG_SPARSE_IRQ
+
+static RADIX_TREE(irq_desc_tree, GFP_KERNEL);
+
+static void irq_insert_desc(unsigned int irq, struct irq_desc *desc)
+{
+        radix_tree_insert(&irq_desc_tree, irq, desc);
+}
+
+struct irq_desc *irq_to_desc(unsigned int irq)
+{
+        return radix_tree_lookup(&irq_desc_tree, irq);
+}
+
+static void delete_irq_desc(unsigned int irq)
+{
+        radix_tree_delete(&irq_desc_tree, irq);
+}
+
+#ifdef CONFIG_SMP
+static void free_masks(struct irq_desc *desc)
+{
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+        free_cpumask_var(desc->pending_mask);
+#endif
+        free_cpumask_var(desc->irq_data.affinity);
+}
+#else
+static inline void free_masks(struct irq_desc *desc) { }
+#endif
+
+static struct irq_desc *alloc_desc(int irq, int node)
+{
+        struct irq_desc *desc;
+        gfp_t gfp = GFP_KERNEL;
+
+        desc = kzalloc_node(sizeof(*desc), gfp, node);
+        if (!desc)
+                return NULL;
+        /* allocate based on nr_cpu_ids */
+        desc->kstat_irqs = kzalloc_node(nr_cpu_ids * sizeof(*desc->kstat_irqs),
+                                         gfp, node);
+        if (!desc->kstat_irqs)
+                goto err_desc;
+
+        if (alloc_masks(desc, gfp, node))
+                goto err_kstat;
+
+        raw_spin_lock_init(&desc->lock);
+        lockdep_set_class(&desc->lock, &irq_desc_lock_class);
+
+        desc_set_defaults(irq, desc, node);
+
+        return desc;
+
+err_kstat:
+        kfree(desc->kstat_irqs);
+err_desc:
+        kfree(desc);
+        return NULL;
+}
+
+static void free_desc(unsigned int irq)
+{
+        struct irq_desc *desc = irq_to_desc(irq);
+
+        unregister_irq_proc(irq, desc);
+
+        mutex_lock(&sparse_irq_lock);
+        delete_irq_desc(irq);
+        mutex_unlock(&sparse_irq_lock);
+
+        free_masks(desc);
+        kfree(desc->kstat_irqs);
+        kfree(desc);
+}
+
+static int alloc_descs(unsigned int start, unsigned int cnt, int node)
+{
+        struct irq_desc *desc;
+        int i;
+
+        for (i = 0; i < cnt; i++) {
+                desc = alloc_desc(start + i, node);
+                if (!desc)
+                        goto err;
+                mutex_lock(&sparse_irq_lock);
+                irq_insert_desc(start + i, desc);
+                mutex_unlock(&sparse_irq_lock);
+        }
+        return start;
+
+err:
+        for (i--; i >= 0; i--)
+                free_desc(start + i);
+
+        mutex_lock(&sparse_irq_lock);
+        bitmap_clear(allocated_irqs, start, cnt);
+        mutex_unlock(&sparse_irq_lock);
+        return -ENOMEM;
+}
+
+struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node)
+{
+        int res = irq_alloc_descs(irq, irq, 1, node);
+
+        if (res == -EEXIST || res == irq)
+                return irq_to_desc(irq);
+        return NULL;
+}
+
+int __init early_irq_init(void)
+{
+        int i, initcnt, node = first_online_node;
+        struct irq_desc *desc;
+
+        init_irq_default_affinity();
+
+        /* Let arch update nr_irqs and return the nr of preallocated irqs */
+        initcnt = arch_probe_nr_irqs();
+        printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d %d\n", NR_IRQS, nr_irqs, initcnt);
+
+        for (i = 0; i < initcnt; i++) {
+                desc = alloc_desc(i, node);
+                set_bit(i, allocated_irqs);
+                irq_insert_desc(i, desc);
+        }
+        return arch_early_irq_init();
+}
+
+#else /* !CONFIG_SPARSE_IRQ */
+
+struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
+        [0 ... NR_IRQS-1] = {
+                .status         = IRQ_DEFAULT_INIT_FLAGS,
+                .handle_irq     = handle_bad_irq,
+                .depth          = 1,
+                .lock           = __RAW_SPIN_LOCK_UNLOCKED(irq_desc->lock),
+        }
+};
+
+static unsigned int kstat_irqs_all[NR_IRQS][NR_CPUS];
+int __init early_irq_init(void)
+{
+        int count, i, node = first_online_node;
+        struct irq_desc *desc;
+
+        init_irq_default_affinity();
+
+        printk(KERN_INFO "NR_IRQS:%d\n", NR_IRQS);
+
+        desc = irq_desc;
+        count = ARRAY_SIZE(irq_desc);
+
+        for (i = 0; i < count; i++) {
+                desc[i].irq_data.irq = i;
+                desc[i].irq_data.chip = &no_irq_chip;
+                desc[i].kstat_irqs = kstat_irqs_all[i];
+                alloc_masks(desc + i, GFP_KERNEL, node);
+                desc_smp_init(desc + i, node);
+                lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
+        }
+        return arch_early_irq_init();
+}
+
+struct irq_desc *irq_to_desc(unsigned int irq)
+{
+        return (irq < NR_IRQS) ? irq_desc + irq : NULL;
+}
+
+struct irq_desc *irq_to_desc_alloc_node(unsigned int irq, int node)
+{
+        return irq_to_desc(irq);
+}
+
+static void free_desc(unsigned int irq)
+{
+        dynamic_irq_cleanup(irq);
+}
+
+static inline int alloc_descs(unsigned int start, unsigned int cnt, int node)
+{
+        return start;
+}
+#endif /* !CONFIG_SPARSE_IRQ */
+
+/* Dynamic interrupt handling */
+
+/**
+ * irq_free_descs - free irq descriptors
+ * @from:       Start of descriptor range
+ * @cnt:        Number of consecutive irqs to free
+ */
+void irq_free_descs(unsigned int from, unsigned int cnt)
+{
+        int i;
+
+        if (from >= nr_irqs || (from + cnt) > nr_irqs)
+                return;
+
+        for (i = 0; i < cnt; i++)
+                free_desc(from + i);
+
+        mutex_lock(&sparse_irq_lock);
+        bitmap_clear(allocated_irqs, from, cnt);
+        mutex_unlock(&sparse_irq_lock);
+}
+
+/**
+ * irq_alloc_descs - allocate and initialize a range of irq descriptors
+ * @irq:        Allocate for specific irq number if irq >= 0
+ * @from:       Start the search from this irq number
+ * @cnt:        Number of consecutive irqs to allocate.
+ * @node:       Preferred node on which the irq descriptor should be allocated
+ *
+ * Returns the first irq number or error code
+ */
+int __ref
+irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node)
+{
+        int start, ret;
+
+        if (!cnt)
+                return -EINVAL;
+
+        mutex_lock(&sparse_irq_lock);
+
+        start = bitmap_find_next_zero_area(allocated_irqs, nr_irqs, from, cnt, 0);
+        ret = -EEXIST;
+        if (irq >=0 && start != irq)
+                goto err;
+
+        ret = -ENOMEM;
+        if (start >= nr_irqs)
+                goto err;
+
+        bitmap_set(allocated_irqs, start, cnt);
+        mutex_unlock(&sparse_irq_lock);
+        return alloc_descs(start, cnt, node);
+
+err:
+        mutex_unlock(&sparse_irq_lock);
+        return ret;
+}
+
+/**
+ * irq_reserve_irqs - mark irqs allocated
+ * @from:       mark from irq number
+ * @cnt:        number of irqs to mark
+ *
+ * Returns 0 on success or an appropriate error code
+ */
+int irq_reserve_irqs(unsigned int from, unsigned int cnt)
+{
+        unsigned int start;
+        int ret = 0;
+
+        if (!cnt || (from + cnt) > nr_irqs)
+                return -EINVAL;
+
+        mutex_lock(&sparse_irq_lock);
+        start = bitmap_find_next_zero_area(allocated_irqs, nr_irqs, from, cnt, 0);
+        if (start == from)
+                bitmap_set(allocated_irqs, start, cnt);
+        else
+                ret = -EEXIST;
+        mutex_unlock(&sparse_irq_lock);
+        return ret;
+}
+
+/**
+ * irq_get_next_irq - get next allocated irq number
+ * @offset:     where to start the search
+ *
+ * Returns next irq number after offset or nr_irqs if none is found.
+ */
+unsigned int irq_get_next_irq(unsigned int offset)
+{
+        return find_next_bit(allocated_irqs, nr_irqs, offset);
+}
+
+/**
+ * dynamic_irq_cleanup - cleanup a dynamically allocated irq
+ * @irq:        irq number to initialize
+ */
+void dynamic_irq_cleanup(unsigned int irq)
+{
+        struct irq_desc *desc = irq_to_desc(irq);
+        unsigned long flags;
+
+        raw_spin_lock_irqsave(&desc->lock, flags);
+        desc_set_defaults(irq, desc, desc_node(desc));
+        raw_spin_unlock_irqrestore(&desc->lock, flags);
+}
+
+unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
+{
+        struct irq_desc *desc = irq_to_desc(irq);
+        return desc ? desc->kstat_irqs[cpu] : 0;
+}
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index c3003e9d91a3..644e8d5fa367 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -73,8 +73,8 @@ int irq_can_set_affinity(unsigned int irq)
 {
         struct irq_desc *desc = irq_to_desc(irq);
 
-        if (CHECK_IRQ_PER_CPU(desc->status) || !desc->chip ||
-            !desc->chip->set_affinity)
+        if (CHECK_IRQ_PER_CPU(desc->status) || !desc->irq_data.chip ||
+            !desc->irq_data.chip->irq_set_affinity)
                 return 0;
 
         return 1;
@@ -109,17 +109,18 @@ void irq_set_thread_affinity(struct irq_desc *desc)
 int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 {
         struct irq_desc *desc = irq_to_desc(irq);
+        struct irq_chip *chip = desc->irq_data.chip;
         unsigned long flags;
 
-        if (!desc->chip->set_affinity)
+        if (!chip->irq_set_affinity)
                 return -EINVAL;
 
         raw_spin_lock_irqsave(&desc->lock, flags);
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
         if (desc->status & IRQ_MOVE_PCNTXT) {
-                if (!desc->chip->set_affinity(irq, cpumask)) {
-                        cpumask_copy(desc->affinity, cpumask);
+                if (!chip->irq_set_affinity(&desc->irq_data, cpumask, false)) {
+                        cpumask_copy(desc->irq_data.affinity, cpumask);
                         irq_set_thread_affinity(desc);
                 }
         }
@@ -128,8 +129,8 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
                 cpumask_copy(desc->pending_mask, cpumask);
         }
 #else
-        if (!desc->chip->set_affinity(irq, cpumask)) {
-                cpumask_copy(desc->affinity, cpumask);
+        if (!chip->irq_set_affinity(&desc->irq_data, cpumask, false)) {
+                cpumask_copy(desc->irq_data.affinity, cpumask);
                 irq_set_thread_affinity(desc);
         }
 #endif
@@ -168,16 +169,16 @@ static int setup_affinity(unsigned int irq, struct irq_desc *desc)
          * one of the targets is online.
          */
         if (desc->status & (IRQ_AFFINITY_SET | IRQ_NO_BALANCING)) {
-                if (cpumask_any_and(desc->affinity, cpu_online_mask)
+                if (cpumask_any_and(desc->irq_data.affinity, cpu_online_mask)
                     < nr_cpu_ids)
                         goto set_affinity;
                 else
                         desc->status &= ~IRQ_AFFINITY_SET;
         }
 
-        cpumask_and(desc->affinity, cpu_online_mask, irq_default_affinity);
+        cpumask_and(desc->irq_data.affinity, cpu_online_mask, irq_default_affinity);
 set_affinity:
-        desc->chip->set_affinity(irq, desc->affinity);
+        desc->irq_data.chip->irq_set_affinity(&desc->irq_data, desc->irq_data.affinity, false);
 
         return 0;
 }
@@ -223,7 +224,7 @@ void __disable_irq(struct irq_desc *desc, unsigned int irq, bool suspend)
 
         if (!desc->depth++) {
                 desc->status |= IRQ_DISABLED;
-                desc->chip->disable(irq);
+                desc->irq_data.chip->irq_disable(&desc->irq_data);
         }
 }
 
@@ -246,11 +247,11 @@ void disable_irq_nosync(unsigned int irq)
         if (!desc)
                 return;
 
-        chip_bus_lock(irq, desc);
+        chip_bus_lock(desc);
         raw_spin_lock_irqsave(&desc->lock, flags);
         __disable_irq(desc, irq, false);
         raw_spin_unlock_irqrestore(&desc->lock, flags);
-        chip_bus_sync_unlock(irq, desc);
+        chip_bus_sync_unlock(desc);
 }
 EXPORT_SYMBOL(disable_irq_nosync);
 
@@ -313,7 +314,7 @@ void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume)
  *      IRQ line is re-enabled.
  *
  *      This function may be called from IRQ context only when
- *      desc->chip->bus_lock and desc->chip->bus_sync_unlock are NULL !
+ *      desc->irq_data.chip->bus_lock and desc->chip->bus_sync_unlock are NULL !
  */
 void enable_irq(unsigned int irq)
 {
@@ -323,11 +324,11 @@ void enable_irq(unsigned int irq)
         if (!desc)
                 return;
 
-        chip_bus_lock(irq, desc);
+        chip_bus_lock(desc);
         raw_spin_lock_irqsave(&desc->lock, flags);
         __enable_irq(desc, irq, false);
         raw_spin_unlock_irqrestore(&desc->lock, flags);
-        chip_bus_sync_unlock(irq, desc);
+        chip_bus_sync_unlock(desc);
 }
 EXPORT_SYMBOL(enable_irq);
 
@@ -336,8 +337,8 @@ static int set_irq_wake_real(unsigned int irq, unsigned int on)
         struct irq_desc *desc = irq_to_desc(irq);
         int ret = -ENXIO;
 
-        if (desc->chip->set_wake)
-                ret = desc->chip->set_wake(irq, on);
+        if (desc->irq_data.chip->irq_set_wake)
+                ret = desc->irq_data.chip->irq_set_wake(&desc->irq_data, on);
 
         return ret;
 }
@@ -429,12 +430,12 @@ void compat_irq_chip_set_default_handler(struct irq_desc *desc)
 }
 
 int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
-                unsigned long flags)
+                      unsigned long flags)
 {
         int ret;
-        struct irq_chip *chip = desc->chip;
+        struct irq_chip *chip = desc->irq_data.chip;
 
-        if (!chip || !chip->set_type) {
+        if (!chip || !chip->irq_set_type) {
                 /*
                  * IRQF_TRIGGER_* but the PIC does not support multiple
                  * flow-types?
@@ -445,11 +446,11 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
         }
 
         /* caller masked out all except trigger mode flags */
-        ret = chip->set_type(irq, flags);
+        ret = chip->irq_set_type(&desc->irq_data, flags);
 
         if (ret)
-                pr_err("setting trigger mode %d for irq %u failed (%pF)\n",
-                                (int)flags, irq, chip->set_type);
+                pr_err("setting trigger mode %lu for irq %u failed (%pF)\n",
+                       flags, irq, chip->irq_set_type);
         else {
                 if (flags & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
                         flags |= IRQ_LEVEL;
@@ -457,8 +458,8 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
                 desc->status &= ~(IRQ_LEVEL | IRQ_TYPE_SENSE_MASK);
                 desc->status |= flags;
 
-                if (chip != desc->chip)
-                        irq_chip_set_defaults(desc->chip);
+                if (chip != desc->irq_data.chip)
+                        irq_chip_set_defaults(desc->irq_data.chip);
         }
 
         return ret;
@@ -507,7 +508,7 @@ static int irq_wait_for_interrupt(struct irqaction *action)
 static void irq_finalize_oneshot(unsigned int irq, struct irq_desc *desc)
 {
 again:
-        chip_bus_lock(irq, desc);
+        chip_bus_lock(desc);
         raw_spin_lock_irq(&desc->lock);
 
         /*
@@ -521,17 +522,17 @@ again:
          */
         if (unlikely(desc->status & IRQ_INPROGRESS)) {
                 raw_spin_unlock_irq(&desc->lock);
-                chip_bus_sync_unlock(irq, desc);
+                chip_bus_sync_unlock(desc);
                 cpu_relax();
                 goto again;
         }
 
         if (!(desc->status & IRQ_DISABLED) && (desc->status & IRQ_MASKED)) {
                 desc->status &= ~IRQ_MASKED;
-                desc->chip->unmask(irq);
+                desc->irq_data.chip->irq_unmask(&desc->irq_data);
         }
         raw_spin_unlock_irq(&desc->lock);
-        chip_bus_sync_unlock(irq, desc);
+        chip_bus_sync_unlock(desc);
 }
 
 #ifdef CONFIG_SMP
@@ -556,7 +557,7 @@ irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action)
         }
 
         raw_spin_lock_irq(&desc->lock);
-        cpumask_copy(mask, desc->affinity);
+        cpumask_copy(mask, desc->irq_data.affinity);
         raw_spin_unlock_irq(&desc->lock);
 
         set_cpus_allowed_ptr(current, mask);
@@ -657,7 +658,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
         if (!desc)
                 return -EINVAL;
 
-        if (desc->chip == &no_irq_chip)
+        if (desc->irq_data.chip == &no_irq_chip)
                 return -ENOSYS;
         /*
          * Some drivers like serial.c use request_irq() heavily,
@@ -752,7 +753,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
         }
 
         if (!shared) {
-                irq_chip_set_defaults(desc->chip);
+                irq_chip_set_defaults(desc->irq_data.chip);
 
                 init_waitqueue_head(&desc->wait_for_threads);
 
@@ -779,7 +780,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
                 if (!(desc->status & IRQ_NOAUTOEN)) {
                         desc->depth = 0;
                         desc->status &= ~IRQ_DISABLED;
-                        desc->chip->startup(irq);
+                        desc->irq_data.chip->irq_startup(&desc->irq_data);
                 } else
                         /* Undo nested disables: */
                         desc->depth = 1;
@@ -912,17 +913,17 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
 
         /* Currently used only by UML, might disappear one day: */
 #ifdef CONFIG_IRQ_RELEASE_METHOD
-        if (desc->chip->release)
-                desc->chip->release(irq, dev_id);
+        if (desc->irq_data.chip->release)
+                desc->irq_data.chip->release(irq, dev_id);
 #endif
 
         /* If this was the last handler, shut down the IRQ line: */
         if (!desc->action) {
                 desc->status |= IRQ_DISABLED;
-                if (desc->chip->shutdown)
-                        desc->chip->shutdown(irq);
+                if (desc->irq_data.chip->irq_shutdown)
+                        desc->irq_data.chip->irq_shutdown(&desc->irq_data);
                 else
-                        desc->chip->disable(irq);
+                        desc->irq_data.chip->irq_disable(&desc->irq_data);
         }
 
 #ifdef CONFIG_SMP
@@ -997,9 +998,9 @@ void free_irq(unsigned int irq, void *dev_id)
         if (!desc)
                 return;
 
-        chip_bus_lock(irq, desc);
+        chip_bus_lock(desc);
         kfree(__free_irq(irq, dev_id));
-        chip_bus_sync_unlock(irq, desc);
+        chip_bus_sync_unlock(desc);
 }
 EXPORT_SYMBOL(free_irq);
 
@@ -1086,9 +1087,9 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
         action->name = devname;
         action->dev_id = dev_id;
 
-        chip_bus_lock(irq, desc);
+        chip_bus_lock(desc);
         retval = __setup_irq(irq, desc, action);
-        chip_bus_sync_unlock(irq, desc);
+        chip_bus_sync_unlock(desc);
 
         if (retval)
                 kfree(action);
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index 241962280836..1d2541940480 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -7,6 +7,7 @@
 void move_masked_irq(int irq)
 {
         struct irq_desc *desc = irq_to_desc(irq);
+        struct irq_chip *chip = desc->irq_data.chip;
 
         if (likely(!(desc->status & IRQ_MOVE_PENDING)))
                 return;
@@ -24,7 +25,7 @@ void move_masked_irq(int irq)
         if (unlikely(cpumask_empty(desc->pending_mask)))
                 return;
 
-        if (!desc->chip->set_affinity)
+        if (!chip->irq_set_affinity)
                 return;
 
         assert_raw_spin_locked(&desc->lock);
@@ -43,8 +44,9 @@ void move_masked_irq(int irq)
          */
         if (likely(cpumask_any_and(desc->pending_mask, cpu_online_mask)
                    < nr_cpu_ids))
-                if (!desc->chip->set_affinity(irq, desc->pending_mask)) {
-                        cpumask_copy(desc->affinity, desc->pending_mask);
+                if (!chip->irq_set_affinity(&desc->irq_data,
+                                            desc->pending_mask, false)) {
+                        cpumask_copy(desc->irq_data.affinity, desc->pending_mask);
                         irq_set_thread_affinity(desc);
                 }
 
@@ -61,8 +63,8 @@ void move_native_irq(int irq)
         if (unlikely(desc->status & IRQ_DISABLED))
                 return;
 
-        desc->chip->mask(irq);
+        desc->irq_data.chip->irq_mask(&desc->irq_data);
         move_masked_irq(irq);
-        desc->chip->unmask(irq);
+        desc->irq_data.chip->irq_unmask(&desc->irq_data);
 }
 
diff --git a/kernel/irq/numa_migrate.c b/kernel/irq/numa_migrate.c
deleted file mode 100644
index 65d3845665ac..000000000000
--- a/kernel/irq/numa_migrate.c
+++ /dev/null
@@ -1,120 +0,0 @@
-/*
- * NUMA irq-desc migration code
- *
- * Migrate IRQ data structures (irq_desc, chip_data, etc.) over to
- * the new "home node" of the IRQ.
- */
-
-#include <linux/irq.h>
-#include <linux/slab.h>
-#include <linux/module.h>
-#include <linux/random.h>
-#include <linux/interrupt.h>
-#include <linux/kernel_stat.h>
-
-#include "internals.h"
-
-static void init_copy_kstat_irqs(struct irq_desc *old_desc,
-                                 struct irq_desc *desc,
-                                 int node, int nr)
-{
-        init_kstat_irqs(desc, node, nr);
-
-        if (desc->kstat_irqs != old_desc->kstat_irqs)
-                memcpy(desc->kstat_irqs, old_desc->kstat_irqs,
-                         nr * sizeof(*desc->kstat_irqs));
-}
-
-static void free_kstat_irqs(struct irq_desc *old_desc, struct irq_desc *desc)
-{
-        if (old_desc->kstat_irqs == desc->kstat_irqs)
-                return;
-
-        kfree(old_desc->kstat_irqs);
-        old_desc->kstat_irqs = NULL;
-}
-
-static bool init_copy_one_irq_desc(int irq, struct irq_desc *old_desc,
-                 struct irq_desc *desc, int node)
-{
-        memcpy(desc, old_desc, sizeof(struct irq_desc));
-        if (!alloc_desc_masks(desc, node, false)) {
-                printk(KERN_ERR "irq %d: can not get new irq_desc cpumask "
-                                "for migration.\n", irq);
-                return false;
-        }
-        raw_spin_lock_init(&desc->lock);
-        desc->node = node;
-        lockdep_set_class(&desc->lock, &irq_desc_lock_class);
-        init_copy_kstat_irqs(old_desc, desc, node, nr_cpu_ids);
-        init_copy_desc_masks(old_desc, desc);
-        arch_init_copy_chip_data(old_desc, desc, node);
-        return true;
-}
-
-static void free_one_irq_desc(struct irq_desc *old_desc, struct irq_desc *desc)
-{
-        free_kstat_irqs(old_desc, desc);
-        free_desc_masks(old_desc, desc);
-        arch_free_chip_data(old_desc, desc);
-}
-
-static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
-                                                int node)
-{
-        struct irq_desc *desc;
-        unsigned int irq;
-        unsigned long flags;
-
-        irq = old_desc->irq;
-
-        raw_spin_lock_irqsave(&sparse_irq_lock, flags);
-
-        /* We have to check it to avoid races with another CPU */
-        desc = irq_to_desc(irq);
-
-        if (desc && old_desc != desc)
-                goto out_unlock;
-
-        desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
-        if (!desc) {
-                printk(KERN_ERR "irq %d: can not get new irq_desc "
-                                "for migration.\n", irq);
-                /* still use old one */
-                desc = old_desc;
-                goto out_unlock;
-        }
-        if (!init_copy_one_irq_desc(irq, old_desc, desc, node)) {
-                /* still use old one */
-                kfree(desc);
-                desc = old_desc;
-                goto out_unlock;
-        }
-
-        replace_irq_desc(irq, desc);
-        raw_spin_unlock_irqrestore(&sparse_irq_lock, flags);
-
-        /* free the old one */
-        free_one_irq_desc(old_desc, desc);
-        kfree(old_desc);
-
-        return desc;
-
-out_unlock:
-        raw_spin_unlock_irqrestore(&sparse_irq_lock, flags);
-
-        return desc;
-}
-
-struct irq_desc *move_irq_desc(struct irq_desc *desc, int node)
-{
-        /* those static or target node is -1, do not move them */
-        if (desc->irq < NR_IRQS_LEGACY || node == -1)
-                return desc;
-
-        if (desc->node != node)
-                desc = __real_move_irq_desc(desc, node);
-
-        return desc;
-}
-
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 09a2ee540bd2..01b1d3a88983 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -21,7 +21,7 @@ static struct proc_dir_entry *root_irq_dir;
 static int irq_affinity_proc_show(struct seq_file *m, void *v)
 {
         struct irq_desc *desc = irq_to_desc((long)m->private);
-        const struct cpumask *mask = desc->affinity;
+        const struct cpumask *mask = desc->irq_data.affinity;
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
         if (desc->status & IRQ_MOVE_PENDING)
@@ -65,7 +65,7 @@ static ssize_t irq_affinity_proc_write(struct file *file,
         cpumask_var_t new_value;
         int err;
 
-        if (!irq_to_desc(irq)->chip->set_affinity || no_irq_affinity ||
+        if (!irq_to_desc(irq)->irq_data.chip->irq_set_affinity || no_irq_affinity ||
             irq_balancing_disabled(irq))
                 return -EIO;
 
@@ -185,7 +185,7 @@ static int irq_node_proc_show(struct seq_file *m, void *v)
 {
         struct irq_desc *desc = irq_to_desc((long) m->private);
 
-        seq_printf(m, "%d\n", desc->node);
+        seq_printf(m, "%d\n", desc->irq_data.node);
         return 0;
 }
 
@@ -269,7 +269,7 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc)
 {
         char name [MAX_NAMELEN];
 
-        if (!root_irq_dir || (desc->chip == &no_irq_chip) || desc->dir)
+        if (!root_irq_dir || (desc->irq_data.chip == &no_irq_chip) || desc->dir)
                 return;
 
         memset(name, 0, MAX_NAMELEN);
@@ -297,6 +297,24 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc)
                          &irq_spurious_proc_fops, (void *)(long)irq);
 }
 
+void unregister_irq_proc(unsigned int irq, struct irq_desc *desc)
+{
+        char name [MAX_NAMELEN];
+
+        if (!root_irq_dir || !desc->dir)
+                return;
+#ifdef CONFIG_SMP
+        remove_proc_entry("smp_affinity", desc->dir);
+        remove_proc_entry("affinity_hint", desc->dir);
+        remove_proc_entry("node", desc->dir);
+#endif
+        remove_proc_entry("spurious", desc->dir);
+
+        memset(name, 0, MAX_NAMELEN);
+        sprintf(name, "%u", irq);
+        remove_proc_entry(name, root_irq_dir);
+}
+
 #undef MAX_NAMELEN
 
 void unregister_handler_proc(unsigned int irq, struct irqaction *action)
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index 090c3763f3a2..891115a929aa 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -60,7 +60,7 @@ void check_irq_resend(struct irq_desc *desc, unsigned int irq)
         /*
          * Make sure the interrupt is enabled, before resending it:
          */
-        desc->chip->enable(irq);
+        desc->irq_data.chip->irq_enable(&desc->irq_data);
 
         /*
          * We do not resend level type interrupts. Level type
@@ -70,7 +70,8 @@ void check_irq_resend(struct irq_desc *desc, unsigned int irq)
         if ((status & (IRQ_LEVEL | IRQ_PENDING | IRQ_REPLAY)) == IRQ_PENDING) {
                 desc->status = (status & ~IRQ_PENDING) | IRQ_REPLAY;
 
-                if (!desc->chip->retrigger || !desc->chip->retrigger(irq)) {
+                if (!desc->irq_data.chip->irq_retrigger ||
+                    !desc->irq_data.chip->irq_retrigger(&desc->irq_data)) {
 #ifdef CONFIG_HARDIRQS_SW_RESEND
                         /* Set it pending and activate the softirq: */
                         set_bit(irq, irqs_resend);
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 89fb90ae534f..3089d3b9d5f3 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -14,6 +14,8 @@
 #include <linux/moduleparam.h>
 #include <linux/timer.h>
 
+#include "internals.h"
+
 static int irqfixup __read_mostly;
 
 #define POLL_SPURIOUS_IRQ_INTERVAL (HZ/10)
@@ -78,8 +80,8 @@ static int try_one_irq(int irq, struct irq_desc *desc)
          * If we did actual work for the real IRQ line we must let the
          * IRQ controller clean up too
          */
-        if (work && desc->chip && desc->chip->end)
-                desc->chip->end(irq);
+        if (work)
+                irq_end(irq, desc);
         raw_spin_unlock(&desc->lock);
 
         return ok;
@@ -254,7 +256,7 @@ void note_interrupt(unsigned int irq, struct irq_desc *desc,
                 printk(KERN_EMERG "Disabling IRQ #%d\n", irq);
                 desc->status |= IRQ_DISABLED | IRQ_SPURIOUS_DISABLED;
                 desc->depth++;
-                desc->chip->disable(irq);
+                desc->irq_data.chip->irq_disable(&desc->irq_data);
 
                 mod_timer(&poll_spurious_irq_timer,
                           jiffies + POLL_SPURIOUS_IRQ_INTERVAL);
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index f2852a510232..42ba65dff7d9 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -639,6 +639,16 @@ look_up_lock_class(struct lockdep_map *lock, unsigned int subclass)
         }
 #endif
 
+        if (unlikely(subclass >= MAX_LOCKDEP_SUBCLASSES)) {
+                debug_locks_off();
+                printk(KERN_ERR
+                        "BUG: looking up invalid subclass: %u\n", subclass);
+                printk(KERN_ERR
+                        "turning off the locking correctness validator.\n");
+                dump_stack();
+                return NULL;
+        }
+
         /*
          * Static locks do not have their class-keys yet - for them the key
          * is the lock object itself:
@@ -774,7 +784,9 @@ out_unlock_set:
         raw_local_irq_restore(flags);
 
         if (!subclass || force)
-                lock->class_cache = class;
+                lock->class_cache[0] = class;
+        else if (subclass < NR_LOCKDEP_CACHING_CLASSES)
+                lock->class_cache[subclass] = class;
 
         if (DEBUG_LOCKS_WARN_ON(class->subclass != subclass))
                 return NULL;
@@ -2679,7 +2691,11 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
 void lockdep_init_map(struct lockdep_map *lock, const char *name,
                       struct lock_class_key *key, int subclass)
 {
-        lock->class_cache = NULL;
+        int i;
+
+        for (i = 0; i < NR_LOCKDEP_CACHING_CLASSES; i++)
+                lock->class_cache[i] = NULL;
+
 #ifdef CONFIG_LOCK_STAT
         lock->cpu = raw_smp_processor_id();
 #endif
@@ -2739,21 +2755,13 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
         if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
                 return 0;
 
-        if (unlikely(subclass >= MAX_LOCKDEP_SUBCLASSES)) {
-                debug_locks_off();
-                printk("BUG: MAX_LOCKDEP_SUBCLASSES too low!\n");
-                printk("turning off the locking correctness validator.\n");
-                dump_stack();
-                return 0;
-        }
-
         if (lock->key == &__lockdep_no_validate__)
                 check = 1;
 
-        if (!subclass)
-                class = lock->class_cache;
+        if (subclass < NR_LOCKDEP_CACHING_CLASSES)
+                class = lock->class_cache[subclass];
         /*
-         * Not cached yet or subclass?
+         * Not cached?
          */
         if (unlikely(!class)) {
                 class = register_lock_class(lock, subclass, 0);
@@ -2918,7 +2926,7 @@ static int match_held_lock(struct held_lock *hlock, struct lockdep_map *lock)
                 return 1;
 
         if (hlock->references) {
-                struct lock_class *class = lock->class_cache;
+                struct lock_class *class = lock->class_cache[0];
 
                 if (!class)
                         class = look_up_lock_class(lock, 0);
@@ -3559,7 +3567,12 @@ void lockdep_reset_lock(struct lockdep_map *lock)
                 if (list_empty(head))
                         continue;
                 list_for_each_entry_safe(class, next, head, hash_entry) {
-                        if (unlikely(class == lock->class_cache)) {
+                        int match = 0;
+
+                        for (j = 0; j < NR_LOCKDEP_CACHING_CLASSES; j++)
+                                match |= class == lock->class_cache[j];
+
+                        if (unlikely(match)) {
                                 if (debug_locks_off_graph_unlock())
                                         WARN_ON(1);
                                 goto out_restore;
@@ -3775,7 +3788,7 @@ EXPORT_SYMBOL_GPL(debug_show_all_locks);
  * Careful: only use this function if you are sure that
  * the task cannot run in parallel!
  */
-void __debug_show_held_locks(struct task_struct *task)
+void debug_show_held_locks(struct task_struct *task)
 {
         if (unlikely(!debug_locks)) {
                 printk("INFO: lockdep is turned off.\n");
@@ -3783,12 +3796,6 @@ void __debug_show_held_locks(struct task_struct *task)
         }
         lockdep_print_held_locks(task);
 }
-EXPORT_SYMBOL_GPL(__debug_show_held_locks);
-
-void debug_show_held_locks(struct task_struct *task)
-{
-                __debug_show_held_locks(task);
-}
 EXPORT_SYMBOL_GPL(debug_show_held_locks);
 
 void lockdep_sys_exit(void)
diff --git a/kernel/pid.c b/kernel/pid.c
index d55c6fb8d087..39b65b69584f 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -401,7 +401,7 @@ struct task_struct *pid_task(struct pid *pid, enum pid_type type)
         struct task_struct *result = NULL;
         if (pid) {
                 struct hlist_node *first;
-                first = rcu_dereference_check(pid->tasks[type].first,
+                first = rcu_dereference_check(hlist_first_rcu(&pid->tasks[type]),
                                               rcu_read_lock_held() ||
                                               lockdep_tasklist_lock_is_held());
                 if (first)
@@ -416,6 +416,7 @@ EXPORT_SYMBOL(pid_task);
  */
 struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns)
 {
+        rcu_lockdep_assert(rcu_read_lock_held());
         return pid_task(find_pid_ns(nr, ns), PIDTYPE_PID);
 }
 
diff --git a/kernel/printk.c b/kernel/printk.c
index 8fe465ac008a..2531017795f6 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -85,7 +85,7 @@ EXPORT_SYMBOL(oops_in_progress);
  * provides serialisation for access to the entire console
  * driver system.
  */
-static DECLARE_MUTEX(console_sem);
+static DEFINE_SEMAPHORE(console_sem);
 struct console *console_drivers;
 EXPORT_SYMBOL_GPL(console_drivers);
 
@@ -556,7 +556,7 @@ static void zap_locks(void)
         /* If a crash is occurring, make sure we can't deadlock */
         spin_lock_init(&logbuf_lock);
         /* And make sure that we print immediately */
-        init_MUTEX(&console_sem);
+        sema_init(&console_sem, 1);
 }
 
 #if defined(CONFIG_PRINTK_TIME)
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index 4d169835fb36..a23a57a976d1 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -73,12 +73,14 @@ int debug_lockdep_rcu_enabled(void)
 EXPORT_SYMBOL_GPL(debug_lockdep_rcu_enabled);
 
 /**
- * rcu_read_lock_bh_held - might we be in RCU-bh read-side critical section?
+ * rcu_read_lock_bh_held() - might we be in RCU-bh read-side critical section?
  *
  * Check for bottom half being disabled, which covers both the
  * CONFIG_PROVE_RCU and not cases.  Note that if someone uses
  * rcu_read_lock_bh(), but then later enables BH, lockdep (if enabled)
- * will show the situation.
+ * will show the situation.  This is useful for debug checks in functions
+ * that require that they be called within an RCU read-side critical
+ * section.
  *
  * Check debug_lockdep_rcu_enabled() to prevent false positives during boot.
  */
@@ -86,7 +88,7 @@ int rcu_read_lock_bh_held(void)
 {
         if (!debug_lockdep_rcu_enabled())
                 return 1;
-        return in_softirq();
+        return in_softirq() || irqs_disabled();
 }
 EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held);
 
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index 196ec02f8be0..d806735342ac 100644
--- a/kernel/rcutiny.c
+++ b/kernel/rcutiny.c
@@ -59,6 +59,14 @@ int rcu_scheduler_active __read_mostly;
 EXPORT_SYMBOL_GPL(rcu_scheduler_active);
 #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
+/* Forward declarations for rcutiny_plugin.h. */
+static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp);
+static void __call_rcu(struct rcu_head *head,
+                       void (*func)(struct rcu_head *rcu),
+                       struct rcu_ctrlblk *rcp);
+
+#include "rcutiny_plugin.h"
+
 #ifdef CONFIG_NO_HZ
 
 static long rcu_dynticks_nesting = 1;
@@ -140,6 +148,7 @@ void rcu_check_callbacks(int cpu, int user)
                 rcu_sched_qs(cpu);
         else if (!in_softirq())
                 rcu_bh_qs(cpu);
+        rcu_preempt_check_callbacks();
 }
 
 /*
@@ -162,6 +171,7 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp)
         *rcp->donetail = NULL;
         if (rcp->curtail == rcp->donetail)
                 rcp->curtail = &rcp->rcucblist;
+        rcu_preempt_remove_callbacks(rcp);
         rcp->donetail = &rcp->rcucblist;
         local_irq_restore(flags);
 
@@ -182,6 +192,7 @@ static void rcu_process_callbacks(struct softirq_action *unused)
 {
         __rcu_process_callbacks(&rcu_sched_ctrlblk);
         __rcu_process_callbacks(&rcu_bh_ctrlblk);
+        rcu_preempt_process_callbacks();
 }
 
 /*
@@ -223,15 +234,15 @@ static void __call_rcu(struct rcu_head *head,
 }
 
 /*
- * Post an RCU callback to be invoked after the end of an RCU grace
+ * Post an RCU callback to be invoked after the end of an RCU-sched grace
  * period.  But since we have but one CPU, that would be after any
  * quiescent state.
  */
-void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
+void call_rcu_sched(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
 {
         __call_rcu(head, func, &rcu_sched_ctrlblk);
 }
-EXPORT_SYMBOL_GPL(call_rcu);
+EXPORT_SYMBOL_GPL(call_rcu_sched);
 
 /*
  * Post an RCU bottom-half callback to be invoked after any subsequent
@@ -243,20 +254,6 @@ void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
 }
 EXPORT_SYMBOL_GPL(call_rcu_bh);
 
-void rcu_barrier(void)
-{
-        struct rcu_synchronize rcu;
-
-        init_rcu_head_on_stack(&rcu.head);
-        init_completion(&rcu.completion);
-        /* Will wake me after RCU finished. */
-        call_rcu(&rcu.head, wakeme_after_rcu);
-        /* Wait for it. */
-        wait_for_completion(&rcu.completion);
-        destroy_rcu_head_on_stack(&rcu.head);
-}
-EXPORT_SYMBOL_GPL(rcu_barrier);
-
 void rcu_barrier_bh(void)
 {
         struct rcu_synchronize rcu;
@@ -289,5 +286,3 @@ void __init rcu_init(void)
 {
         open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
 }
-
-#include "rcutiny_plugin.h"
diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h
index d223a92bc742..6ceca4f745ff 100644
--- a/kernel/rcutiny_plugin.h
+++ b/kernel/rcutiny_plugin.h
@@ -1,7 +1,7 @@
 /*
- * Read-Copy Update mechanism for mutual exclusion (tree-based version)
+ * Read-Copy Update mechanism for mutual exclusion, the Bloatwatch edition
  * Internal non-public definitions that provide either classic
- * or preemptable semantics.
+ * or preemptible semantics.
  *
  * 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
@@ -17,11 +17,587 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  *
- * Copyright IBM Corporation, 2009
+ * Copyright (c) 2010 Linaro
  *
  * Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
  */
 
+#ifdef CONFIG_TINY_PREEMPT_RCU
+
+#include <linux/delay.h>
+
+/* Global control variables for preemptible RCU. */
+struct rcu_preempt_ctrlblk {
+        struct rcu_ctrlblk rcb; /* curtail: ->next ptr of last CB for GP. */
+        struct rcu_head **nexttail;
+                                /* Tasks blocked in a preemptible RCU */
+                                /*  read-side critical section while an */
+                                /*  preemptible-RCU grace period is in */
+                                /*  progress must wait for a later grace */
+                                /*  period.  This pointer points to the */
+                                /*  ->next pointer of the last task that */
+                                /*  must wait for a later grace period, or */
+                                /*  to &->rcb.rcucblist if there is no */
+                                /*  such task. */
+        struct list_head blkd_tasks;
+                                /* Tasks blocked in RCU read-side critical */
+                                /*  section.  Tasks are placed at the head */
+                                /*  of this list and age towards the tail. */
+        struct list_head *gp_tasks;
+                                /* Pointer to the first task blocking the */
+                                /*  current grace period, or NULL if there */
+                                /*  is not such task. */
+        struct list_head *exp_tasks;
+                                /* Pointer to first task blocking the */
+                                /*  current expedited grace period, or NULL */
+                                /*  if there is no such task.  If there */
+                                /*  is no current expedited grace period, */
+                                /*  then there cannot be any such task. */
+        u8 gpnum;               /* Current grace period. */
+        u8 gpcpu;               /* Last grace period blocked by the CPU. */
+        u8 completed;           /* Last grace period completed. */
+                                /*  If all three are equal, RCU is idle. */
+};
+
+static struct rcu_preempt_ctrlblk rcu_preempt_ctrlblk = {
+        .rcb.donetail = &rcu_preempt_ctrlblk.rcb.rcucblist,
+        .rcb.curtail = &rcu_preempt_ctrlblk.rcb.rcucblist,
+        .nexttail = &rcu_preempt_ctrlblk.rcb.rcucblist,
+        .blkd_tasks = LIST_HEAD_INIT(rcu_preempt_ctrlblk.blkd_tasks),
+};
+
+static int rcu_preempted_readers_exp(void);
+static void rcu_report_exp_done(void);
+
+/*
+ * Return true if the CPU has not yet responded to the current grace period.
+ */
+static int rcu_cpu_blocking_cur_gp(void)
+{
+        return rcu_preempt_ctrlblk.gpcpu != rcu_preempt_ctrlblk.gpnum;
+}
+
+/*
+ * Check for a running RCU reader.  Because there is only one CPU,
+ * there can be but one running RCU reader at a time.  ;-)
+ */
+static int rcu_preempt_running_reader(void)
+{
+        return current->rcu_read_lock_nesting;
+}
+
+/*
+ * Check for preempted RCU readers blocking any grace period.
+ * If the caller needs a reliable answer, it must disable hard irqs.
+ */
+static int rcu_preempt_blocked_readers_any(void)
+{
+        return !list_empty(&rcu_preempt_ctrlblk.blkd_tasks);
+}
+
+/*
+ * Check for preempted RCU readers blocking the current grace period.
+ * If the caller needs a reliable answer, it must disable hard irqs.
+ */
+static int rcu_preempt_blocked_readers_cgp(void)
+{
+        return rcu_preempt_ctrlblk.gp_tasks != NULL;
+}
+
+/*
+ * Return true if another preemptible-RCU grace period is needed.
+ */
+static int rcu_preempt_needs_another_gp(void)
+{
+        return *rcu_preempt_ctrlblk.rcb.curtail != NULL;
+}
+
+/*
+ * Return true if a preemptible-RCU grace period is in progress.
+ * The caller must disable hardirqs.
+ */
+static int rcu_preempt_gp_in_progress(void)
+{
+        return rcu_preempt_ctrlblk.completed != rcu_preempt_ctrlblk.gpnum;
+}
+
+/*
+ * Record a preemptible-RCU quiescent state for the specified CPU.  Note
+ * that this just means that the task currently running on the CPU is
+ * in a quiescent state.  There might be any number of tasks blocked
+ * while in an RCU read-side critical section.
+ *
+ * Unlike the other rcu_*_qs() functions, callers to this function
+ * must disable irqs in order to protect the assignment to
+ * ->rcu_read_unlock_special.
+ *
+ * Because this is a single-CPU implementation, the only way a grace
+ * period can end is if the CPU is in a quiescent state.  The reason is
+ * that a blocked preemptible-RCU reader can exit its critical section
+ * only if the CPU is running it at the time.  Therefore, when the
+ * last task blocking the current grace period exits its RCU read-side
+ * critical section, neither the CPU nor blocked tasks will be stopping
+ * the current grace period.  (In contrast, SMP implementations
+ * might have CPUs running in RCU read-side critical sections that
+ * block later grace periods -- but this is not possible given only
+ * one CPU.)
+ */
+static void rcu_preempt_cpu_qs(void)
+{
+        /* Record both CPU and task as having responded to current GP. */
+        rcu_preempt_ctrlblk.gpcpu = rcu_preempt_ctrlblk.gpnum;
+        current->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS;
+
+        /*
+         * If there is no GP, or if blocked readers are still blocking GP,
+         * then there is nothing more to do.
+         */
+        if (!rcu_preempt_gp_in_progress() || rcu_preempt_blocked_readers_cgp())
+                return;
+
+        /* Advance callbacks. */
+        rcu_preempt_ctrlblk.completed = rcu_preempt_ctrlblk.gpnum;
+        rcu_preempt_ctrlblk.rcb.donetail = rcu_preempt_ctrlblk.rcb.curtail;
+        rcu_preempt_ctrlblk.rcb.curtail = rcu_preempt_ctrlblk.nexttail;
+
+        /* If there are no blocked readers, next GP is done instantly. */
+        if (!rcu_preempt_blocked_readers_any())
+                rcu_preempt_ctrlblk.rcb.donetail = rcu_preempt_ctrlblk.nexttail;
+
+        /* If there are done callbacks, make RCU_SOFTIRQ process them. */
+        if (*rcu_preempt_ctrlblk.rcb.donetail != NULL)
+                raise_softirq(RCU_SOFTIRQ);
+}
+
+/*
+ * Start a new RCU grace period if warranted.  Hard irqs must be disabled.
+ */
+static void rcu_preempt_start_gp(void)
+{
+        if (!rcu_preempt_gp_in_progress() && rcu_preempt_needs_another_gp()) {
+
+                /* Official start of GP. */
+                rcu_preempt_ctrlblk.gpnum++;
+
+                /* Any blocked RCU readers block new GP. */
+                if (rcu_preempt_blocked_readers_any())
+                        rcu_preempt_ctrlblk.gp_tasks =
+                                rcu_preempt_ctrlblk.blkd_tasks.next;
+
+                /* If there is no running reader, CPU is done with GP. */
+                if (!rcu_preempt_running_reader())
+                        rcu_preempt_cpu_qs();
+        }
+}
+
+/*
+ * We have entered the scheduler, and the current task might soon be
+ * context-switched away from.  If this task is in an RCU read-side
+ * critical section, we will no longer be able to rely on the CPU to
+ * record that fact, so we enqueue the task on the blkd_tasks list.
+ * If the task started after the current grace period began, as recorded
+ * by ->gpcpu, we enqueue at the beginning of the list.  Otherwise
+ * before the element referenced by ->gp_tasks (or at the tail if
+ * ->gp_tasks is NULL) and point ->gp_tasks at the newly added element.
+ * The task will dequeue itself when it exits the outermost enclosing
+ * RCU read-side critical section.  Therefore, the current grace period
+ * cannot be permitted to complete until the ->gp_tasks pointer becomes
+ * NULL.
+ *
+ * Caller must disable preemption.
+ */
+void rcu_preempt_note_context_switch(void)
+{
+        struct task_struct *t = current;
+        unsigned long flags;
+
+        local_irq_save(flags); /* must exclude scheduler_tick(). */
+        if (rcu_preempt_running_reader() &&
+            (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) {
+
+                /* Possibly blocking in an RCU read-side critical section. */
+                t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
+
+                /*
+                 * If this CPU has already checked in, then this task
+                 * will hold up the next grace period rather than the
+                 * current grace period.  Queue the task accordingly.
+                 * If the task is queued for the current grace period
+                 * (i.e., this CPU has not yet passed through a quiescent
+                 * state for the current grace period), then as long
+                 * as that task remains queued, the current grace period
+                 * cannot end.
+                 */
+                list_add(&t->rcu_node_entry, &rcu_preempt_ctrlblk.blkd_tasks);
+                if (rcu_cpu_blocking_cur_gp())
+                        rcu_preempt_ctrlblk.gp_tasks = &t->rcu_node_entry;
+        }
+
+        /*
+         * Either we were not in an RCU read-side critical section to
+         * begin with, or we have now recorded that critical section
+         * globally.  Either way, we can now note a quiescent state
+         * for this CPU.  Again, if we were in an RCU read-side critical
+         * section, and if that critical section was blocking the current
+         * grace period, then the fact that the task has been enqueued
+         * means that current grace period continues to be blocked.
+         */
+        rcu_preempt_cpu_qs();
+        local_irq_restore(flags);
+}
+
+/*
+ * Tiny-preemptible RCU implementation for rcu_read_lock().
+ * Just increment ->rcu_read_lock_nesting, shared state will be updated
+ * if we block.
+ */
+void __rcu_read_lock(void)
+{
+        current->rcu_read_lock_nesting++;
+        barrier();  /* needed if we ever invoke rcu_read_lock in rcutiny.c */
+}
+EXPORT_SYMBOL_GPL(__rcu_read_lock);
+
+/*
+ * Handle special cases during rcu_read_unlock(), such as needing to
+ * notify RCU core processing or task having blocked during the RCU
+ * read-side critical section.
+ */
+static void rcu_read_unlock_special(struct task_struct *t)
+{
+        int empty;
+        int empty_exp;
+        unsigned long flags;
+        struct list_head *np;
+        int special;
+
+        /*
+         * NMI handlers cannot block and cannot safely manipulate state.
+         * They therefore cannot possibly be special, so just leave.
+         */
+        if (in_nmi())
+                return;
+
+        local_irq_save(flags);
+
+        /*
+         * If RCU core is waiting for this CPU to exit critical section,
+         * let it know that we have done so.
+         */
+        special = t->rcu_read_unlock_special;
+        if (special & RCU_READ_UNLOCK_NEED_QS)
+                rcu_preempt_cpu_qs();
+
+        /* Hardware IRQ handlers cannot block. */
+        if (in_irq()) {
+                local_irq_restore(flags);
+                return;
+        }
+
+        /* Clean up if blocked during RCU read-side critical section. */
+        if (special & RCU_READ_UNLOCK_BLOCKED) {
+                t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_BLOCKED;
+
+                /*
+                 * Remove this task from the ->blkd_tasks list and adjust
+                 * any pointers that might have been referencing it.
+                 */
+                empty = !rcu_preempt_blocked_readers_cgp();
+                empty_exp = rcu_preempt_ctrlblk.exp_tasks == NULL;
+                np = t->rcu_node_entry.next;
+                if (np == &rcu_preempt_ctrlblk.blkd_tasks)
+                        np = NULL;
+                list_del(&t->rcu_node_entry);
+                if (&t->rcu_node_entry == rcu_preempt_ctrlblk.gp_tasks)
+                        rcu_preempt_ctrlblk.gp_tasks = np;
+                if (&t->rcu_node_entry == rcu_preempt_ctrlblk.exp_tasks)
+                        rcu_preempt_ctrlblk.exp_tasks = np;
+                INIT_LIST_HEAD(&t->rcu_node_entry);
+
+                /*
+                 * If this was the last task on the current list, and if
+                 * we aren't waiting on the CPU, report the quiescent state
+                 * and start a new grace period if needed.
+                 */
+                if (!empty && !rcu_preempt_blocked_readers_cgp()) {
+                        rcu_preempt_cpu_qs();
+                        rcu_preempt_start_gp();
+                }
+
+                /*
+                 * If this was the last task on the expedited lists,
+                 * then we need wake up the waiting task.
+                 */
+                if (!empty_exp && rcu_preempt_ctrlblk.exp_tasks == NULL)
+                        rcu_report_exp_done();
+        }
+        local_irq_restore(flags);
+}
+
+/*
+ * Tiny-preemptible RCU implementation for rcu_read_unlock().
+ * Decrement ->rcu_read_lock_nesting.  If the result is zero (outermost
+ * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then
+ * invoke rcu_read_unlock_special() to clean up after a context switch
+ * in an RCU read-side critical section and other special cases.
+ */
+void __rcu_read_unlock(void)
+{
+        struct task_struct *t = current;
+
+        barrier();  /* needed if we ever invoke rcu_read_unlock in rcutiny.c */
+        --t->rcu_read_lock_nesting;
+        barrier();  /* decrement before load of ->rcu_read_unlock_special */
+        if (t->rcu_read_lock_nesting == 0 &&
+            unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
+                rcu_read_unlock_special(t);
+#ifdef CONFIG_PROVE_LOCKING
+        WARN_ON_ONCE(t->rcu_read_lock_nesting < 0);
+#endif /* #ifdef CONFIG_PROVE_LOCKING */
+}
+EXPORT_SYMBOL_GPL(__rcu_read_unlock);
+
+/*
+ * Check for a quiescent state from the current CPU.  When a task blocks,
+ * the task is recorded in the rcu_preempt_ctrlblk structure, which is
+ * checked elsewhere.  This is called from the scheduling-clock interrupt.
+ *
+ * Caller must disable hard irqs.
+ */
+static void rcu_preempt_check_callbacks(void)
+{
+        struct task_struct *t = current;
+
+        if (rcu_preempt_gp_in_progress() &&
+            (!rcu_preempt_running_reader() ||
+             !rcu_cpu_blocking_cur_gp()))
+                rcu_preempt_cpu_qs();
+        if (&rcu_preempt_ctrlblk.rcb.rcucblist !=
+            rcu_preempt_ctrlblk.rcb.donetail)
+                raise_softirq(RCU_SOFTIRQ);
+        if (rcu_preempt_gp_in_progress() &&
+            rcu_cpu_blocking_cur_gp() &&
+            rcu_preempt_running_reader())
+                t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS;
+}
+
+/*
+ * TINY_PREEMPT_RCU has an extra callback-list tail pointer to
+ * update, so this is invoked from __rcu_process_callbacks() to
+ * handle that case.  Of course, it is invoked for all flavors of
+ * RCU, but RCU callbacks can appear only on one of the lists, and
+ * neither ->nexttail nor ->donetail can possibly be NULL, so there
+ * is no need for an explicit check.
+ */
+static void rcu_preempt_remove_callbacks(struct rcu_ctrlblk *rcp)
+{
+        if (rcu_preempt_ctrlblk.nexttail == rcp->donetail)
+                rcu_preempt_ctrlblk.nexttail = &rcp->rcucblist;
+}
+
+/*
+ * Process callbacks for preemptible RCU.
+ */
+static void rcu_preempt_process_callbacks(void)
+{
+        __rcu_process_callbacks(&rcu_preempt_ctrlblk.rcb);
+}
+
+/*
+ * Queue a preemptible -RCU callback for invocation after a grace period.
+ */
+void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
+{
+        unsigned long flags;
+
+        debug_rcu_head_queue(head);
+        head->func = func;
+        head->next = NULL;
+
+        local_irq_save(flags);
+        *rcu_preempt_ctrlblk.nexttail = head;
+        rcu_preempt_ctrlblk.nexttail = &head->next;
+        rcu_preempt_start_gp();  /* checks to see if GP needed. */
+        local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(call_rcu);
+
+void rcu_barrier(void)
+{
+        struct rcu_synchronize rcu;
+
+        init_rcu_head_on_stack(&rcu.head);
+        init_completion(&rcu.completion);
+        /* Will wake me after RCU finished. */
+        call_rcu(&rcu.head, wakeme_after_rcu);
+        /* Wait for it. */
+        wait_for_completion(&rcu.completion);
+        destroy_rcu_head_on_stack(&rcu.head);
+}
+EXPORT_SYMBOL_GPL(rcu_barrier);
+
+/*
+ * synchronize_rcu - wait until a grace period has elapsed.
+ *
+ * Control will return to the caller some time after a full grace
+ * period has elapsed, in other words after all currently executing RCU
+ * read-side critical sections have completed.  RCU read-side critical
+ * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
+ * and may be nested.
+ */
+void synchronize_rcu(void)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+        if (!rcu_scheduler_active)
+                return;
+#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
+
+        WARN_ON_ONCE(rcu_preempt_running_reader());
+        if (!rcu_preempt_blocked_readers_any())
+                return;
+
+        /* Once we get past the fastpath checks, same code as rcu_barrier(). */
+        rcu_barrier();
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu);
+
+static DECLARE_WAIT_QUEUE_HEAD(sync_rcu_preempt_exp_wq);
+static unsigned long sync_rcu_preempt_exp_count;
+static DEFINE_MUTEX(sync_rcu_preempt_exp_mutex);
+
+/*
+ * Return non-zero if there are any tasks in RCU read-side critical
+ * sections blocking the current preemptible-RCU expedited grace period.
+ * If there is no preemptible-RCU expedited grace period currently in
+ * progress, returns zero unconditionally.
+ */
+static int rcu_preempted_readers_exp(void)
+{
+        return rcu_preempt_ctrlblk.exp_tasks != NULL;
+}
+
+/*
+ * Report the exit from RCU read-side critical section for the last task
+ * that queued itself during or before the current expedited preemptible-RCU
+ * grace period.
+ */
+static void rcu_report_exp_done(void)
+{
+        wake_up(&sync_rcu_preempt_exp_wq);
+}
+
+/*
+ * Wait for an rcu-preempt grace period, but expedite it.  The basic idea
+ * is to rely in the fact that there is but one CPU, and that it is
+ * illegal for a task to invoke synchronize_rcu_expedited() while in a
+ * preemptible-RCU read-side critical section.  Therefore, any such
+ * critical sections must correspond to blocked tasks, which must therefore
+ * be on the ->blkd_tasks list.  So just record the current head of the
+ * list in the ->exp_tasks pointer, and wait for all tasks including and
+ * after the task pointed to by ->exp_tasks to drain.
+ */
+void synchronize_rcu_expedited(void)
+{
+        unsigned long flags;
+        struct rcu_preempt_ctrlblk *rpcp = &rcu_preempt_ctrlblk;
+        unsigned long snap;
+
+        barrier(); /* ensure prior action seen before grace period. */
+
+        WARN_ON_ONCE(rcu_preempt_running_reader());
+
+        /*
+         * Acquire lock so that there is only one preemptible RCU grace
+         * period in flight.  Of course, if someone does the expedited
+         * grace period for us while we are acquiring the lock, just leave.
+         */
+        snap = sync_rcu_preempt_exp_count + 1;
+        mutex_lock(&sync_rcu_preempt_exp_mutex);
+        if (ULONG_CMP_LT(snap, sync_rcu_preempt_exp_count))
+                goto unlock_mb_ret; /* Others did our work for us. */
+
+        local_irq_save(flags);
+
+        /*
+         * All RCU readers have to already be on blkd_tasks because
+         * we cannot legally be executing in an RCU read-side critical
+         * section.
+         */
+
+        /* Snapshot current head of ->blkd_tasks list. */
+        rpcp->exp_tasks = rpcp->blkd_tasks.next;
+        if (rpcp->exp_tasks == &rpcp->blkd_tasks)
+                rpcp->exp_tasks = NULL;
+        local_irq_restore(flags);
+
+        /* Wait for tail of ->blkd_tasks list to drain. */
+        if (rcu_preempted_readers_exp())
+                wait_event(sync_rcu_preempt_exp_wq,
+                           !rcu_preempted_readers_exp());
+
+        /* Clean up and exit. */
+        barrier(); /* ensure expedited GP seen before counter increment. */
+        sync_rcu_preempt_exp_count++;
+unlock_mb_ret:
+        mutex_unlock(&sync_rcu_preempt_exp_mutex);
+        barrier(); /* ensure subsequent action seen after grace period. */
+}
+EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);
+
+/*
+ * Does preemptible RCU need the CPU to stay out of dynticks mode?
+ */
+int rcu_preempt_needs_cpu(void)
+{
+        if (!rcu_preempt_running_reader())
+                rcu_preempt_cpu_qs();
+        return rcu_preempt_ctrlblk.rcb.rcucblist != NULL;
+}
+
+/*
+ * Check for a task exiting while in a preemptible -RCU read-side
+ * critical section, clean up if so.  No need to issue warnings,
+ * as debug_check_no_locks_held() already does this if lockdep
+ * is enabled.
+ */
+void exit_rcu(void)
+{
+        struct task_struct *t = current;
+
+        if (t->rcu_read_lock_nesting == 0)
+                return;
+        t->rcu_read_lock_nesting = 1;
+        rcu_read_unlock();
+}
+
+#else /* #ifdef CONFIG_TINY_PREEMPT_RCU */
+
+/*
+ * Because preemptible RCU does not exist, it never has any callbacks
+ * to check.
+ */
+static void rcu_preempt_check_callbacks(void)
+{
+}
+
+/*
+ * Because preemptible RCU does not exist, it never has any callbacks
+ * to remove.
+ */
+static void rcu_preempt_remove_callbacks(struct rcu_ctrlblk *rcp)
+{
+}
+
+/*
+ * Because preemptible RCU does not exist, it never has any callbacks
+ * to process.
+ */
+static void rcu_preempt_process_callbacks(void)
+{
+}
+
+#endif /* #else #ifdef CONFIG_TINY_PREEMPT_RCU */
+
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 
 #include <linux/kernel_stat.h>
diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c
index 2e2726d790b9..9d8e8fb2515f 100644
--- a/kernel/rcutorture.c
+++ b/kernel/rcutorture.c
@@ -120,7 +120,7 @@ struct rcu_torture {
 };
 
 static LIST_HEAD(rcu_torture_freelist);
-static struct rcu_torture *rcu_torture_current;
+static struct rcu_torture __rcu *rcu_torture_current;
 static long rcu_torture_current_version;
 static struct rcu_torture rcu_tortures[10 * RCU_TORTURE_PIPE_LEN];
 static DEFINE_SPINLOCK(rcu_torture_lock);
@@ -153,8 +153,10 @@ int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT;
 #define FULLSTOP_SHUTDOWN 1     /* System shutdown with rcutorture running. */
 #define FULLSTOP_RMMOD    2     /* Normal rmmod of rcutorture. */
 static int fullstop = FULLSTOP_RMMOD;
-DEFINE_MUTEX(fullstop_mutex);   /* Protect fullstop transitions and spawning */
-                                /*  of kthreads. */
+/*
+ * Protect fullstop transitions and spawning of kthreads.
+ */
+static DEFINE_MUTEX(fullstop_mutex);
 
 /*
  * Detect and respond to a system shutdown.
@@ -303,6 +305,10 @@ static void rcu_read_delay(struct rcu_random_state *rrsp)
                 mdelay(longdelay_ms);
         if (!(rcu_random(rrsp) % (nrealreaders * 2 * shortdelay_us)))
                 udelay(shortdelay_us);
+#ifdef CONFIG_PREEMPT
+        if (!preempt_count() && !(rcu_random(rrsp) % (nrealreaders * 20000)))
+                preempt_schedule();  /* No QS if preempt_disable() in effect */
+#endif
 }
 
 static void rcu_torture_read_unlock(int idx) __releases(RCU)
@@ -536,6 +542,8 @@ static void srcu_read_delay(struct rcu_random_state *rrsp)
         delay = rcu_random(rrsp) % (nrealreaders * 2 * longdelay * uspertick);
         if (!delay)
                 schedule_timeout_interruptible(longdelay);
+        else
+                rcu_read_delay(rrsp);
 }
 
 static void srcu_torture_read_unlock(int idx) __releases(&srcu_ctl)
@@ -731,7 +739,8 @@ rcu_torture_writer(void *arg)
                         continue;
                 rp->rtort_pipe_count = 0;
                 udelay(rcu_random(&rand) & 0x3ff);
-                old_rp = rcu_torture_current;
+                old_rp = rcu_dereference_check(rcu_torture_current,
+                                               current == writer_task);
                 rp->rtort_mbtest = 1;
                 rcu_assign_pointer(rcu_torture_current, rp);
                 smp_wmb(); /* Mods to old_rp must follow rcu_assign_pointer() */
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index d5bc43976c5a..ccdc04c47981 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -143,6 +143,11 @@ module_param(blimit, int, 0);
 module_param(qhimark, int, 0);
 module_param(qlowmark, int, 0);
 
+#ifdef CONFIG_RCU_CPU_STALL_DETECTOR
+int rcu_cpu_stall_suppress __read_mostly = RCU_CPU_STALL_SUPPRESS_INIT;
+module_param(rcu_cpu_stall_suppress, int, 0644);
+#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+
 static void force_quiescent_state(struct rcu_state *rsp, int relaxed);
 static int rcu_pending(int cpu);
 
@@ -450,7 +455,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 
 #ifdef CONFIG_RCU_CPU_STALL_DETECTOR
 
-int rcu_cpu_stall_panicking __read_mostly;
+int rcu_cpu_stall_suppress __read_mostly;
 
 static void record_gp_stall_check_time(struct rcu_state *rsp)
 {
@@ -482,8 +487,11 @@ static void print_other_cpu_stall(struct rcu_state *rsp)
         rcu_print_task_stall(rnp);
         raw_spin_unlock_irqrestore(&rnp->lock, flags);
 
-        /* OK, time to rat on our buddy... */
-
+        /*
+         * OK, time to rat on our buddy...
+         * See Documentation/RCU/stallwarn.txt for info on how to debug
+         * RCU CPU stall warnings.
+         */
         printk(KERN_ERR "INFO: %s detected stalls on CPUs/tasks: {",
                rsp->name);
         rcu_for_each_leaf_node(rsp, rnp) {
@@ -512,6 +520,11 @@ static void print_cpu_stall(struct rcu_state *rsp)
         unsigned long flags;
         struct rcu_node *rnp = rcu_get_root(rsp);
 
+        /*
+         * OK, time to rat on ourselves...
+         * See Documentation/RCU/stallwarn.txt for info on how to debug
+         * RCU CPU stall warnings.
+         */
         printk(KERN_ERR "INFO: %s detected stall on CPU %d (t=%lu jiffies)\n",
                rsp->name, smp_processor_id(), jiffies - rsp->gp_start);
         trigger_all_cpu_backtrace();
@@ -530,11 +543,11 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
         long delta;
         struct rcu_node *rnp;
 
-        if (rcu_cpu_stall_panicking)
+        if (rcu_cpu_stall_suppress)
                 return;
-        delta = jiffies - rsp->jiffies_stall;
+        delta = jiffies - ACCESS_ONCE(rsp->jiffies_stall);
         rnp = rdp->mynode;
-        if ((rnp->qsmask & rdp->grpmask) && delta >= 0) {
+        if ((ACCESS_ONCE(rnp->qsmask) & rdp->grpmask) && delta >= 0) {
 
                 /* We haven't checked in, so go dump stack. */
                 print_cpu_stall(rsp);
@@ -548,10 +561,26 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
 
 static int rcu_panic(struct notifier_block *this, unsigned long ev, void *ptr)
 {
-        rcu_cpu_stall_panicking = 1;
+        rcu_cpu_stall_suppress = 1;
         return NOTIFY_DONE;
 }
 
+/**
+ * rcu_cpu_stall_reset - prevent further stall warnings in current grace period
+ *
+ * Set the stall-warning timeout way off into the future, thus preventing
+ * any RCU CPU stall-warning messages from appearing in the current set of
+ * RCU grace periods.
+ *
+ * The caller must disable hard irqs.
+ */
+void rcu_cpu_stall_reset(void)
+{
+        rcu_sched_state.jiffies_stall = jiffies + ULONG_MAX / 2;
+        rcu_bh_state.jiffies_stall = jiffies + ULONG_MAX / 2;
+        rcu_preempt_stall_reset();
+}
+
 static struct notifier_block rcu_panic_block = {
         .notifier_call = rcu_panic,
 };
@@ -571,6 +600,10 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
 {
 }
 
+void rcu_cpu_stall_reset(void)
+{
+}
+
 static void __init check_cpu_stall_init(void)
 {
 }
@@ -712,7 +745,7 @@ static void
 rcu_start_gp(struct rcu_state *rsp, unsigned long flags)
         __releases(rcu_get_root(rsp)->lock)
 {
-        struct rcu_data *rdp = rsp->rda[smp_processor_id()];
+        struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
         struct rcu_node *rnp = rcu_get_root(rsp);
 
         if (!cpu_needs_another_gp(rsp, rdp) || rsp->fqs_active) {
@@ -960,7 +993,7 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
 static void rcu_send_cbs_to_orphanage(struct rcu_state *rsp)
 {
         int i;
-        struct rcu_data *rdp = rsp->rda[smp_processor_id()];
+        struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
 
         if (rdp->nxtlist == NULL)
                 return;  /* irqs disabled, so comparison is stable. */
@@ -971,6 +1004,7 @@ static void rcu_send_cbs_to_orphanage(struct rcu_state *rsp)
         for (i = 0; i < RCU_NEXT_SIZE; i++)
                 rdp->nxttail[i] = &rdp->nxtlist;
         rsp->orphan_qlen += rdp->qlen;
+        rdp->n_cbs_orphaned += rdp->qlen;
         rdp->qlen = 0;
         raw_spin_unlock(&rsp->onofflock);  /* irqs remain disabled. */
 }
@@ -984,7 +1018,7 @@ static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
         struct rcu_data *rdp;
 
         raw_spin_lock_irqsave(&rsp->onofflock, flags);
-        rdp = rsp->rda[smp_processor_id()];
+        rdp = this_cpu_ptr(rsp->rda);
         if (rsp->orphan_cbs_list == NULL) {
                 raw_spin_unlock_irqrestore(&rsp->onofflock, flags);
                 return;
@@ -992,6 +1026,7 @@ static void rcu_adopt_orphan_cbs(struct rcu_state *rsp)
         *rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_cbs_list;
         rdp->nxttail[RCU_NEXT_TAIL] = rsp->orphan_cbs_tail;
         rdp->qlen += rsp->orphan_qlen;
+        rdp->n_cbs_adopted += rsp->orphan_qlen;
         rsp->orphan_cbs_list = NULL;
         rsp->orphan_cbs_tail = &rsp->orphan_cbs_list;
         rsp->orphan_qlen = 0;
@@ -1007,7 +1042,7 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp)
         unsigned long flags;
         unsigned long mask;
         int need_report = 0;
-        struct rcu_data *rdp = rsp->rda[cpu];
+        struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
         struct rcu_node *rnp;
 
         /* Exclude any attempts to start a new grace period. */
@@ -1123,6 +1158,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
 
         /* Update count, and requeue any remaining callbacks. */
         rdp->qlen -= count;
+        rdp->n_cbs_invoked += count;
         if (list != NULL) {
                 *tail = rdp->nxtlist;
                 rdp->nxtlist = list;
@@ -1226,7 +1262,8 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *))
                 cpu = rnp->grplo;
                 bit = 1;
                 for (; cpu <= rnp->grphi; cpu++, bit <<= 1) {
-                        if ((rnp->qsmask & bit) != 0 && f(rsp->rda[cpu]))
+                        if ((rnp->qsmask & bit) != 0 &&
+                            f(per_cpu_ptr(rsp->rda, cpu)))
                                 mask |= bit;
                 }
                 if (mask != 0) {
@@ -1402,7 +1439,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
          * a quiescent state betweentimes.
          */
         local_irq_save(flags);
-        rdp = rsp->rda[smp_processor_id()];
+        rdp = this_cpu_ptr(rsp->rda);
         rcu_process_gp_end(rsp, rdp);
         check_for_new_grace_period(rsp, rdp);
 
@@ -1701,7 +1738,7 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
 {
         unsigned long flags;
         int i;
-        struct rcu_data *rdp = rsp->rda[cpu];
+        struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
         struct rcu_node *rnp = rcu_get_root(rsp);
 
         /* Set up local state, ensuring consistent view of global state. */
@@ -1729,7 +1766,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptable)
 {
         unsigned long flags;
         unsigned long mask;
-        struct rcu_data *rdp = rsp->rda[cpu];
+        struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
         struct rcu_node *rnp = rcu_get_root(rsp);
 
         /* Set up local state, ensuring consistent view of global state. */
@@ -1865,7 +1902,8 @@ static void __init rcu_init_levelspread(struct rcu_state *rsp)
 /*
  * Helper function for rcu_init() that initializes one rcu_state structure.
  */
-static void __init rcu_init_one(struct rcu_state *rsp)
+static void __init rcu_init_one(struct rcu_state *rsp,
+                struct rcu_data __percpu *rda)
 {
         static char *buf[] = { "rcu_node_level_0",
                                "rcu_node_level_1",
@@ -1918,37 +1956,23 @@ static void __init rcu_init_one(struct rcu_state *rsp)
                 }
         }
 
+        rsp->rda = rda;
         rnp = rsp->level[NUM_RCU_LVLS - 1];
         for_each_possible_cpu(i) {
                 while (i > rnp->grphi)
                         rnp++;
-                rsp->rda[i]->mynode = rnp;
+                per_cpu_ptr(rsp->rda, i)->mynode = rnp;
                 rcu_boot_init_percpu_data(i, rsp);
         }
 }
 
-/*
- * Helper macro for __rcu_init() and __rcu_init_preempt().  To be used
- * nowhere else!  Assigns leaf node pointers into each CPU's rcu_data
- * structure.
- */
-#define RCU_INIT_FLAVOR(rsp, rcu_data) \
-do { \
-        int i; \
-        \
-        for_each_possible_cpu(i) { \
-                (rsp)->rda[i] = &per_cpu(rcu_data, i); \
-        } \
-        rcu_init_one(rsp); \
-} while (0)
-
 void __init rcu_init(void)
 {
         int cpu;
 
         rcu_bootup_announce();
-        RCU_INIT_FLAVOR(&rcu_sched_state, rcu_sched_data);
-        RCU_INIT_FLAVOR(&rcu_bh_state, rcu_bh_data);
+        rcu_init_one(&rcu_sched_state, &rcu_sched_data);
+        rcu_init_one(&rcu_bh_state, &rcu_bh_data);
         __rcu_init_preempt();
         open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);
 
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 14c040b18ed0..91d4170c5c13 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -202,6 +202,9 @@ struct rcu_data {
         long            qlen;           /* # of queued callbacks */
         long            qlen_last_fqs_check;
                                         /* qlen at last check for QS forcing */
+        unsigned long   n_cbs_invoked;  /* count of RCU cbs invoked. */
+        unsigned long   n_cbs_orphaned; /* RCU cbs sent to orphanage. */
+        unsigned long   n_cbs_adopted;  /* RCU cbs adopted from orphanage. */
         unsigned long   n_force_qs_snap;
                                         /* did other CPU force QS recently? */
         long            blimit;         /* Upper limit on a processed batch */
@@ -254,19 +257,23 @@ struct rcu_data {
 #define RCU_STALL_DELAY_DELTA          0
 #endif
 
-#define RCU_SECONDS_TILL_STALL_CHECK   (10 * HZ + RCU_STALL_DELAY_DELTA)
+#define RCU_SECONDS_TILL_STALL_CHECK   (CONFIG_RCU_CPU_STALL_TIMEOUT * HZ + \
+                                        RCU_STALL_DELAY_DELTA)
                                                 /* for rsp->jiffies_stall */
-#define RCU_SECONDS_TILL_STALL_RECHECK (30 * HZ + RCU_STALL_DELAY_DELTA)
+#define RCU_SECONDS_TILL_STALL_RECHECK (3 * RCU_SECONDS_TILL_STALL_CHECK + 30)
                                                 /* for rsp->jiffies_stall */
 #define RCU_STALL_RAT_DELAY             2       /* Allow other CPUs time */
                                                 /*  to take at least one */
                                                 /*  scheduling clock irq */
                                                 /*  before ratting on them. */
 
-#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
+#ifdef CONFIG_RCU_CPU_STALL_DETECTOR_RUNNABLE
+#define RCU_CPU_STALL_SUPPRESS_INIT 0
+#else
+#define RCU_CPU_STALL_SUPPRESS_INIT 1
+#endif
 
-#define ULONG_CMP_GE(a, b)      (ULONG_MAX / 2 >= (a) - (b))
-#define ULONG_CMP_LT(a, b)      (ULONG_MAX / 2 < (a) - (b))
+#endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 
 /*
  * RCU global state, including node hierarchy.  This hierarchy is
@@ -283,7 +290,7 @@ struct rcu_state {
         struct rcu_node *level[NUM_RCU_LVLS];   /* Hierarchy levels. */
         u32 levelcnt[MAX_RCU_LVLS + 1];         /* # nodes in each level. */
         u8 levelspread[NUM_RCU_LVLS];           /* kids/node in each level. */
-        struct rcu_data *rda[NR_CPUS];          /* array of rdp pointers. */
+        struct rcu_data __percpu *rda;          /* pointer of percu rcu_data. */
 
         /* The following fields are guarded by the root rcu_node's lock. */
 
@@ -365,6 +372,7 @@ static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp,
 #ifdef CONFIG_RCU_CPU_STALL_DETECTOR
 static void rcu_print_detail_task_stall(struct rcu_state *rsp);
 static void rcu_print_task_stall(struct rcu_node *rnp);
+static void rcu_preempt_stall_reset(void);
 #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 0e4f420245d9..71a4147473f9 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -57,7 +57,7 @@ static void __init rcu_bootup_announce_oddness(void)
         printk(KERN_INFO
                "\tRCU-based detection of stalled CPUs is disabled.\n");
 #endif
-#ifndef CONFIG_RCU_CPU_STALL_VERBOSE
+#if defined(CONFIG_TREE_PREEMPT_RCU) && !defined(CONFIG_RCU_CPU_STALL_VERBOSE)
         printk(KERN_INFO "\tVerbose stalled-CPUs detection is disabled.\n");
 #endif
 #if NUM_RCU_LVL_4 != 0
@@ -154,7 +154,7 @@ static void rcu_preempt_note_context_switch(int cpu)
             (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) {
 
                 /* Possibly blocking in an RCU read-side critical section. */
-                rdp = rcu_preempt_state.rda[cpu];
+                rdp = per_cpu_ptr(rcu_preempt_state.rda, cpu);
                 rnp = rdp->mynode;
                 raw_spin_lock_irqsave(&rnp->lock, flags);
                 t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
@@ -201,7 +201,7 @@ static void rcu_preempt_note_context_switch(int cpu)
  */
 void __rcu_read_lock(void)
 {
-        ACCESS_ONCE(current->rcu_read_lock_nesting)++;
+        current->rcu_read_lock_nesting++;
         barrier();  /* needed if we ever invoke rcu_read_lock in rcutree.c */
 }
 EXPORT_SYMBOL_GPL(__rcu_read_lock);
@@ -344,7 +344,9 @@ void __rcu_read_unlock(void)
         struct task_struct *t = current;
 
         barrier();  /* needed if we ever invoke rcu_read_unlock in rcutree.c */
-        if (--ACCESS_ONCE(t->rcu_read_lock_nesting) == 0 &&
+        --t->rcu_read_lock_nesting;
+        barrier();  /* decrement before load of ->rcu_read_unlock_special */
+        if (t->rcu_read_lock_nesting == 0 &&
             unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
                 rcu_read_unlock_special(t);
 #ifdef CONFIG_PROVE_LOCKING
@@ -417,6 +419,16 @@ static void rcu_print_task_stall(struct rcu_node *rnp)
         }
 }
 
+/*
+ * Suppress preemptible RCU's CPU stall warnings by pushing the
+ * time of the next stall-warning message comfortably far into the
+ * future.
+ */
+static void rcu_preempt_stall_reset(void)
+{
+        rcu_preempt_state.jiffies_stall = jiffies + ULONG_MAX / 2;
+}
+
 #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 
 /*
@@ -546,9 +558,11 @@ EXPORT_SYMBOL_GPL(call_rcu);
  *
  * Control will return to the caller some time after a full grace
  * period has elapsed, in other words after all currently executing RCU
- * read-side critical sections have completed.  RCU read-side critical
- * sections are delimited by rcu_read_lock() and rcu_read_unlock(),
- * and may be nested.
+ * read-side critical sections have completed.  Note, however, that
+ * upon return from synchronize_rcu(), the caller might well be executing
+ * concurrently with new RCU read-side critical sections that began while
+ * synchronize_rcu() was waiting.  RCU read-side critical sections are
+ * delimited by rcu_read_lock() and rcu_read_unlock(), and may be nested.
  */
 void synchronize_rcu(void)
 {
@@ -771,7 +785,7 @@ static void rcu_preempt_send_cbs_to_orphanage(void)
  */
 static void __init __rcu_init_preempt(void)
 {
-        RCU_INIT_FLAVOR(&rcu_preempt_state, rcu_preempt_data);
+        rcu_init_one(&rcu_preempt_state, &rcu_preempt_data);
 }
 
 /*
@@ -865,6 +879,14 @@ static void rcu_print_task_stall(struct rcu_node *rnp)
 {
 }
 
+/*
+ * Because preemptible RCU does not exist, there is no need to suppress
+ * its CPU stall warnings.
+ */
+static void rcu_preempt_stall_reset(void)
+{
+}
+
 #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 
 /*
@@ -919,15 +941,6 @@ static void rcu_preempt_process_callbacks(void)
 }
 
 /*
- * In classic RCU, call_rcu() is just call_rcu_sched().
- */
-void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu))
-{
-        call_rcu_sched(head, func);
-}
-EXPORT_SYMBOL_GPL(call_rcu);
-
-/*
  * Wait for an rcu-preempt grace period, but make it happen quickly.
  * But because preemptable RCU does not exist, map to rcu-sched.
  */
diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c
index 36c95b45738e..d15430b9d122 100644
--- a/kernel/rcutree_trace.c
+++ b/kernel/rcutree_trace.c
@@ -64,7 +64,9 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
                    rdp->dynticks_fqs);
 #endif /* #ifdef CONFIG_NO_HZ */
         seq_printf(m, " of=%lu ri=%lu", rdp->offline_fqs, rdp->resched_ipi);
-        seq_printf(m, " ql=%ld b=%ld\n", rdp->qlen, rdp->blimit);
+        seq_printf(m, " ql=%ld b=%ld", rdp->qlen, rdp->blimit);
+        seq_printf(m, " ci=%lu co=%lu ca=%lu\n",
+                   rdp->n_cbs_invoked, rdp->n_cbs_orphaned, rdp->n_cbs_adopted);
 }
 
 #define PRINT_RCU_DATA(name, func, m) \
@@ -119,7 +121,9 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp)
                    rdp->dynticks_fqs);
 #endif /* #ifdef CONFIG_NO_HZ */
         seq_printf(m, ",%lu,%lu", rdp->offline_fqs, rdp->resched_ipi);
-        seq_printf(m, ",%ld,%ld\n", rdp->qlen, rdp->blimit);
+        seq_printf(m, ",%ld,%ld", rdp->qlen, rdp->blimit);
+        seq_printf(m, ",%lu,%lu,%lu\n",
+                   rdp->n_cbs_invoked, rdp->n_cbs_orphaned, rdp->n_cbs_adopted);
 }
 
 static int show_rcudata_csv(struct seq_file *m, void *unused)
@@ -128,7 +132,7 @@ static int show_rcudata_csv(struct seq_file *m, void *unused)
 #ifdef CONFIG_NO_HZ
         seq_puts(m, "\"dt\",\"dt nesting\",\"dn\",\"df\",");
 #endif /* #ifdef CONFIG_NO_HZ */
-        seq_puts(m, "\"of\",\"ri\",\"ql\",\"b\"\n");
+        seq_puts(m, "\"of\",\"ri\",\"ql\",\"b\",\"ci\",\"co\",\"ca\"\n");
 #ifdef CONFIG_TREE_PREEMPT_RCU
         seq_puts(m, "\"rcu_preempt:\"\n");
         PRINT_RCU_DATA(rcu_preempt_data, print_one_rcu_data_csv, m);
@@ -262,7 +266,7 @@ static void print_rcu_pendings(struct seq_file *m, struct rcu_state *rsp)
         struct rcu_data *rdp;
 
         for_each_possible_cpu(cpu) {
-                rdp = rsp->rda[cpu];
+                rdp = per_cpu_ptr(rsp->rda, cpu);
                 if (rdp->beenonline)
                         print_one_rcu_pending(m, rdp);
         }
diff --git a/kernel/sched.c b/kernel/sched.c
index c0d2067f3e0d..d42992bccdfa 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -426,9 +426,7 @@ struct root_domain {
          */
         cpumask_var_t rto_mask;
         atomic_t rto_count;
-#ifdef CONFIG_SMP
         struct cpupri cpupri;
-#endif
 };
 
 /*
@@ -437,7 +435,7 @@ struct root_domain {
  */
 static struct root_domain def_root_domain;
 
-#endif
+#endif /* CONFIG_SMP */
 
 /*
  * This is the main, per-CPU runqueue data structure.
@@ -488,11 +486,12 @@ struct rq {
          */
         unsigned long nr_uninterruptible;
 
-        struct task_struct *curr, *idle;
+        struct task_struct *curr, *idle, *stop;
         unsigned long next_balance;
         struct mm_struct *prev_mm;
 
         u64 clock;
+        u64 clock_task;
 
         atomic_t nr_iowait;
 
@@ -520,6 +519,10 @@ struct rq {
         u64 avg_idle;
 #endif
 
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+        u64 prev_irq_time;
+#endif
+
         /* calc_load related fields */
         unsigned long calc_load_update;
         long calc_load_active;
@@ -643,10 +646,22 @@ static inline struct task_group *task_group(struct task_struct *p)
 
 #endif /* CONFIG_CGROUP_SCHED */
 
+static u64 irq_time_cpu(int cpu);
+static void sched_irq_time_avg_update(struct rq *rq, u64 irq_time);
+
 inline void update_rq_clock(struct rq *rq)
 {
-        if (!rq->skip_clock_update)
-                rq->clock = sched_clock_cpu(cpu_of(rq));
+        if (!rq->skip_clock_update) {
+                int cpu = cpu_of(rq);
+                u64 irq_time;
+
+                rq->clock = sched_clock_cpu(cpu);
+                irq_time = irq_time_cpu(cpu);
+                if (rq->clock - irq_time > rq->clock_task)
+                        rq->clock_task = rq->clock - irq_time;
+
+                sched_irq_time_avg_update(rq, irq_time);
+        }
 }
 
 /*
@@ -723,7 +738,7 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
                 size_t cnt, loff_t *ppos)
 {
         char buf[64];
-        char *cmp = buf;
+        char *cmp;
         int neg = 0;
         int i;
 
@@ -734,6 +749,7 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
                 return -EFAULT;
 
         buf[cnt] = 0;
+        cmp = strstrip(buf);
 
         if (strncmp(buf, "NO_", 3) == 0) {
                 neg = 1;
@@ -741,9 +757,7 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
         }
 
         for (i = 0; sched_feat_names[i]; i++) {
-                int len = strlen(sched_feat_names[i]);
-
-                if (strncmp(cmp, sched_feat_names[i], len) == 0) {
+                if (strcmp(cmp, sched_feat_names[i]) == 0) {
                         if (neg)
                                 sysctl_sched_features &= ~(1UL << i);
                         else
@@ -1840,7 +1854,7 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
 
 static const struct sched_class rt_sched_class;
 
-#define sched_class_highest (&rt_sched_class)
+#define sched_class_highest (&stop_sched_class)
 #define for_each_class(class) \
    for (class = sched_class_highest; class; class = class->next)
 
@@ -1858,12 +1872,6 @@ static void dec_nr_running(struct rq *rq)
 
 static void set_load_weight(struct task_struct *p)
 {
-        if (task_has_rt_policy(p)) {
-                p->se.load.weight = 0;
-                p->se.load.inv_weight = WMULT_CONST;
-                return;
-        }
-
         /*
          * SCHED_IDLE tasks get minimal weight:
          */
@@ -1917,13 +1925,132 @@ static void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
         dec_nr_running(rq);
 }
 
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+
+/*
+ * There are no locks covering percpu hardirq/softirq time.
+ * They are only modified in account_system_vtime, on corresponding CPU
+ * with interrupts disabled. So, writes are safe.
+ * They are read and saved off onto struct rq in update_rq_clock().
+ * This may result in other CPU reading this CPU's irq time and can
+ * race with irq/account_system_vtime on this CPU. We would either get old
+ * or new value (or semi updated value on 32 bit) with a side effect of
+ * accounting a slice of irq time to wrong task when irq is in progress
+ * while we read rq->clock. That is a worthy compromise in place of having
+ * locks on each irq in account_system_time.
+ */
+static DEFINE_PER_CPU(u64, cpu_hardirq_time);
+static DEFINE_PER_CPU(u64, cpu_softirq_time);
+
+static DEFINE_PER_CPU(u64, irq_start_time);
+static int sched_clock_irqtime;
+
+void enable_sched_clock_irqtime(void)
+{
+        sched_clock_irqtime = 1;
+}
+
+void disable_sched_clock_irqtime(void)
+{
+        sched_clock_irqtime = 0;
+}
+
+static u64 irq_time_cpu(int cpu)
+{
+        if (!sched_clock_irqtime)
+                return 0;
+
+        return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu);
+}
+
+void account_system_vtime(struct task_struct *curr)
+{
+        unsigned long flags;
+        int cpu;
+        u64 now, delta;
+
+        if (!sched_clock_irqtime)
+                return;
+
+        local_irq_save(flags);
+
+        cpu = smp_processor_id();
+        now = sched_clock_cpu(cpu);
+        delta = now - per_cpu(irq_start_time, cpu);
+        per_cpu(irq_start_time, cpu) = now;
+        /*
+         * We do not account for softirq time from ksoftirqd here.
+         * We want to continue accounting softirq time to ksoftirqd thread
+         * in that case, so as not to confuse scheduler with a special task
+         * that do not consume any time, but still wants to run.
+         */
+        if (hardirq_count())
+                per_cpu(cpu_hardirq_time, cpu) += delta;
+        else if (in_serving_softirq() && !(curr->flags & PF_KSOFTIRQD))
+                per_cpu(cpu_softirq_time, cpu) += delta;
+
+        local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(account_system_vtime);
+
+static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time)
+{
+        if (sched_clock_irqtime && sched_feat(NONIRQ_POWER)) {
+                u64 delta_irq = curr_irq_time - rq->prev_irq_time;
+                rq->prev_irq_time = curr_irq_time;
+                sched_rt_avg_update(rq, delta_irq);
+        }
+}
+
+#else
+
+static u64 irq_time_cpu(int cpu)
+{
+        return 0;
+}
+
+static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time) { }
+
+#endif
+
 #include "sched_idletask.c"
 #include "sched_fair.c"
 #include "sched_rt.c"
+#include "sched_stoptask.c"
 #ifdef CONFIG_SCHED_DEBUG
 # include "sched_debug.c"
 #endif
 
+void sched_set_stop_task(int cpu, struct task_struct *stop)
+{
+        struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
+        struct task_struct *old_stop = cpu_rq(cpu)->stop;
+
+        if (stop) {
+                /*
+                 * Make it appear like a SCHED_FIFO task, its something
+                 * userspace knows about and won't get confused about.
+                 *
+                 * Also, it will make PI more or less work without too
+                 * much confusion -- but then, stop work should not
+                 * rely on PI working anyway.
+                 */
+                sched_setscheduler_nocheck(stop, SCHED_FIFO, &param);
+
+                stop->sched_class = &stop_sched_class;
+        }
+
+        cpu_rq(cpu)->stop = stop;
+
+        if (old_stop) {
+                /*
+                 * Reset it back to a normal scheduling class so that
+                 * it can die in pieces.
+                 */
+                old_stop->sched_class = &rt_sched_class;
+        }
+}
+
 /*
  * __normal_prio - return the priority that is based on the static prio
  */
@@ -2003,6 +2130,9 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
         if (p->sched_class != &fair_sched_class)
                 return 0;
 
+        if (unlikely(p->policy == SCHED_IDLE))
+                return 0;
+
         /*
          * Buddy candidates are cache hot:
          */
@@ -2852,14 +2982,14 @@ context_switch(struct rq *rq, struct task_struct *prev,
          */
         arch_start_context_switch(prev);
 
-        if (likely(!mm)) {
+        if (!mm) {
                 next->active_mm = oldmm;
                 atomic_inc(&oldmm->mm_count);
                 enter_lazy_tlb(oldmm, next);
         } else
                 switch_mm(oldmm, mm, next);
 
-        if (likely(!prev->mm)) {
+        if (!prev->mm) {
                 prev->active_mm = NULL;
                 rq->prev_mm = oldmm;
         }
@@ -3248,7 +3378,7 @@ static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq)
 
         if (task_current(rq, p)) {
                 update_rq_clock(rq);
-                ns = rq->clock - p->se.exec_start;
+                ns = rq->clock_task - p->se.exec_start;
                 if ((s64)ns < 0)
                         ns = 0;
         }
@@ -3397,7 +3527,7 @@ void account_system_time(struct task_struct *p, int hardirq_offset,
         tmp = cputime_to_cputime64(cputime);
         if (hardirq_count() - hardirq_offset)
                 cpustat->irq = cputime64_add(cpustat->irq, tmp);
-        else if (softirq_count())
+        else if (in_serving_softirq())
                 cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
         else
                 cpustat->system = cputime64_add(cpustat->system, tmp);
@@ -3723,17 +3853,13 @@ pick_next_task(struct rq *rq)
                         return p;
         }
 
-        class = sched_class_highest;
-        for ( ; ; ) {
+        for_each_class(class) {
                 p = class->pick_next_task(rq);
                 if (p)
                         return p;
-                /*
-                 * Will never be NULL as the idle class always
-                 * returns a non-NULL p:
-                 */
-                class = class->next;
         }
+
+        BUG(); /* the idle class will always have a runnable task */
 }
 
 /*
@@ -4358,6 +4484,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 
         rq = task_rq_lock(p, &flags);
 
+        trace_sched_pi_setprio(p, prio);
         oldprio = p->prio;
         prev_class = p->sched_class;
         on_rq = p->se.on_rq;
@@ -4645,7 +4772,7 @@ recheck:
         }
 
         if (user) {
-                retval = security_task_setscheduler(p, policy, param);
+                retval = security_task_setscheduler(p);
                 if (retval)
                         return retval;
         }
@@ -4661,6 +4788,15 @@ recheck:
          */
         rq = __task_rq_lock(p);
 
+        /*
+         * Changing the policy of the stop threads its a very bad idea
+         */
+        if (p == rq->stop) {
+                __task_rq_unlock(rq);
+                raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+                return -EINVAL;
+        }
+
 #ifdef CONFIG_RT_GROUP_SCHED
         if (user) {
                 /*
@@ -4887,13 +5023,13 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
         if (!check_same_owner(p) && !capable(CAP_SYS_NICE))
                 goto out_unlock;
 
-        retval = security_task_setscheduler(p, 0, NULL);
+        retval = security_task_setscheduler(p);
         if (retval)
                 goto out_unlock;
 
         cpuset_cpus_allowed(p, cpus_allowed);
         cpumask_and(new_mask, in_mask, cpus_allowed);
- again:
+again:
         retval = set_cpus_allowed_ptr(p, new_mask);
 
         if (!retval) {
@@ -5337,7 +5473,19 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
         idle->se.exec_start = sched_clock();
 
         cpumask_copy(&idle->cpus_allowed, 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
+         * lockdep check in task_group() will fail.
+         *
+         * Similar case to sched_fork(). / Alternatively we could
+         * use task_rq_lock() here and obtain the other rq->lock.
+         *
+         * Silence PROVE_RCU
+         */
+        rcu_read_lock();
         __set_task_cpu(idle, cpu);
+        rcu_read_unlock();
 
         rq->curr = rq->idle = idle;
 #if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
@@ -6514,6 +6662,7 @@ struct s_data {
         cpumask_var_t           nodemask;
         cpumask_var_t           this_sibling_map;
         cpumask_var_t           this_core_map;
+        cpumask_var_t           this_book_map;
         cpumask_var_t           send_covered;
         cpumask_var_t           tmpmask;
         struct sched_group      **sched_group_nodes;
@@ -6525,6 +6674,7 @@ enum s_alloc {
         sa_rootdomain,
         sa_tmpmask,
         sa_send_covered,
+        sa_this_book_map,
         sa_this_core_map,
         sa_this_sibling_map,
         sa_nodemask,
@@ -6560,31 +6710,48 @@ cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map,
 #ifdef CONFIG_SCHED_MC
 static DEFINE_PER_CPU(struct static_sched_domain, core_domains);
 static DEFINE_PER_CPU(struct static_sched_group, sched_group_core);
-#endif /* CONFIG_SCHED_MC */
 
-#if defined(CONFIG_SCHED_MC) && defined(CONFIG_SCHED_SMT)
 static int
 cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
                   struct sched_group **sg, struct cpumask *mask)
 {
         int group;
-
+#ifdef CONFIG_SCHED_SMT
         cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
         group = cpumask_first(mask);
+#else
+        group = cpu;
+#endif
         if (sg)
                 *sg = &per_cpu(sched_group_core, group).sg;
         return group;
 }
-#elif defined(CONFIG_SCHED_MC)
+#endif /* CONFIG_SCHED_MC */
+
+/*
+ * book sched-domains:
+ */
+#ifdef CONFIG_SCHED_BOOK
+static DEFINE_PER_CPU(struct static_sched_domain, book_domains);
+static DEFINE_PER_CPU(struct static_sched_group, sched_group_book);
+
 static int
-cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
-                  struct sched_group **sg, struct cpumask *unused)
+cpu_to_book_group(int cpu, const struct cpumask *cpu_map,
+                  struct sched_group **sg, struct cpumask *mask)
 {
+        int group = cpu;
+#ifdef CONFIG_SCHED_MC
+        cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
+        group = cpumask_first(mask);
+#elif defined(CONFIG_SCHED_SMT)
+        cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
+        group = cpumask_first(mask);
+#endif
         if (sg)
-                *sg = &per_cpu(sched_group_core, cpu).sg;
-        return cpu;
+                *sg = &per_cpu(sched_group_book, group).sg;
+        return group;
 }
-#endif
+#endif /* CONFIG_SCHED_BOOK */
 
 static DEFINE_PER_CPU(struct static_sched_domain, phys_domains);
 static DEFINE_PER_CPU(struct static_sched_group, sched_group_phys);
@@ -6594,7 +6761,10 @@ cpu_to_phys_group(int cpu, const struct cpumask *cpu_map,
                   struct sched_group **sg, struct cpumask *mask)
 {
         int group;
-#ifdef CONFIG_SCHED_MC
+#ifdef CONFIG_SCHED_BOOK
+        cpumask_and(mask, cpu_book_mask(cpu), cpu_map);
+        group = cpumask_first(mask);
+#elif defined(CONFIG_SCHED_MC)
         cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
         group = cpumask_first(mask);
 #elif defined(CONFIG_SCHED_SMT)
@@ -6855,6 +7025,9 @@ SD_INIT_FUNC(CPU)
 #ifdef CONFIG_SCHED_MC
  SD_INIT_FUNC(MC)
 #endif
+#ifdef CONFIG_SCHED_BOOK
+ SD_INIT_FUNC(BOOK)
+#endif
 
 static int default_relax_domain_level = -1;
 
@@ -6904,6 +7077,8 @@ static void __free_domain_allocs(struct s_data *d, enum s_alloc what,
                 free_cpumask_var(d->tmpmask); /* fall through */
         case sa_send_covered:
                 free_cpumask_var(d->send_covered); /* fall through */
+        case sa_this_book_map:
+                free_cpumask_var(d->this_book_map); /* fall through */
         case sa_this_core_map:
                 free_cpumask_var(d->this_core_map); /* fall through */
         case sa_this_sibling_map:
@@ -6950,8 +7125,10 @@ static enum s_alloc __visit_domain_allocation_hell(struct s_data *d,
                 return sa_nodemask;
         if (!alloc_cpumask_var(&d->this_core_map, GFP_KERNEL))
                 return sa_this_sibling_map;
-        if (!alloc_cpumask_var(&d->send_covered, GFP_KERNEL))
+        if (!alloc_cpumask_var(&d->this_book_map, GFP_KERNEL))
                 return sa_this_core_map;
+        if (!alloc_cpumask_var(&d->send_covered, GFP_KERNEL))
+                return sa_this_book_map;
         if (!alloc_cpumask_var(&d->tmpmask, GFP_KERNEL))
                 return sa_send_covered;
         d->rd = alloc_rootdomain();
@@ -7009,6 +7186,23 @@ static struct sched_domain *__build_cpu_sched_domain(struct s_data *d,
         return sd;
 }
 
+static struct sched_domain *__build_book_sched_domain(struct s_data *d,
+        const struct cpumask *cpu_map, struct sched_domain_attr *attr,
+        struct sched_domain *parent, int i)
+{
+        struct sched_domain *sd = parent;
+#ifdef CONFIG_SCHED_BOOK
+        sd = &per_cpu(book_domains, i).sd;
+        SD_INIT(sd, BOOK);
+        set_domain_attribute(sd, attr);
+        cpumask_and(sched_domain_span(sd), cpu_map, cpu_book_mask(i));
+        sd->parent = parent;
+        parent->child = sd;
+        cpu_to_book_group(i, cpu_map, &sd->groups, d->tmpmask);
+#endif
+        return sd;
+}
+
 static struct sched_domain *__build_mc_sched_domain(struct s_data *d,
         const struct cpumask *cpu_map, struct sched_domain_attr *attr,
         struct sched_domain *parent, int i)
@@ -7066,6 +7260,15 @@ static void build_sched_groups(struct s_data *d, enum sched_domain_level l,
                                                 d->send_covered, d->tmpmask);
                 break;
 #endif
+#ifdef CONFIG_SCHED_BOOK
+        case SD_LV_BOOK: /* set up book groups */
+                cpumask_and(d->this_book_map, cpu_map, cpu_book_mask(cpu));
+                if (cpu == cpumask_first(d->this_book_map))
+                        init_sched_build_groups(d->this_book_map, cpu_map,
+                                                &cpu_to_book_group,
+                                                d->send_covered, d->tmpmask);
+                break;
+#endif
         case SD_LV_CPU: /* set up physical groups */
                 cpumask_and(d->nodemask, cpumask_of_node(cpu), cpu_map);
                 if (!cpumask_empty(d->nodemask))
@@ -7113,12 +7316,14 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
 
                 sd = __build_numa_sched_domains(&d, cpu_map, attr, i);
                 sd = __build_cpu_sched_domain(&d, cpu_map, attr, sd, i);
+                sd = __build_book_sched_domain(&d, cpu_map, attr, sd, i);
                 sd = __build_mc_sched_domain(&d, cpu_map, attr, sd, i);
                 sd = __build_smt_sched_domain(&d, cpu_map, attr, sd, i);
         }
 
         for_each_cpu(i, cpu_map) {
                 build_sched_groups(&d, SD_LV_SIBLING, cpu_map, i);
+                build_sched_groups(&d, SD_LV_BOOK, cpu_map, i);
                 build_sched_groups(&d, SD_LV_MC, cpu_map, i);
         }
 
@@ -7149,6 +7354,12 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
                 init_sched_groups_power(i, sd);
         }
 #endif
+#ifdef CONFIG_SCHED_BOOK
+        for_each_cpu(i, cpu_map) {
+                sd = &per_cpu(book_domains, i).sd;
+                init_sched_groups_power(i, sd);
+        }
+#endif
 
         for_each_cpu(i, cpu_map) {
                 sd = &per_cpu(phys_domains, i).sd;
@@ -7174,6 +7385,8 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
                 sd = &per_cpu(cpu_domains, i).sd;
 #elif defined(CONFIG_SCHED_MC)
                 sd = &per_cpu(core_domains, i).sd;
+#elif defined(CONFIG_SCHED_BOOK)
+                sd = &per_cpu(book_domains, i).sd;
 #else
                 sd = &per_cpu(phys_domains, i).sd;
 #endif
@@ -8078,9 +8291,9 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 
         return 1;
 
- err_free_rq:
+err_free_rq:
         kfree(cfs_rq);
- err:
+err:
         return 0;
 }
 
@@ -8168,9 +8381,9 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
 
         return 1;
 
- err_free_rq:
+err_free_rq:
         kfree(rt_rq);
- err:
+err:
         return 0;
 }
 
@@ -8528,7 +8741,7 @@ static int tg_set_bandwidth(struct task_group *tg,
                 raw_spin_unlock(&rt_rq->rt_runtime_lock);
         }
         raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock);
- unlock:
+unlock:
         read_unlock(&tasklist_lock);
         mutex_unlock(&rt_constraints_mutex);
 
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index db3f674ca49d..933f3d1b62ea 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -25,7 +25,7 @@
 
 /*
  * Targeted preemption latency for CPU-bound tasks:
- * (default: 5ms * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 6ms * (1 + ilog(ncpus)), units: nanoseconds)
  *
  * NOTE: this latency value is not the same as the concept of
  * 'timeslice length' - timeslices in CFS are of variable length
@@ -52,7 +52,7 @@ enum sched_tunable_scaling sysctl_sched_tunable_scaling
 
 /*
  * Minimal preemption granularity for CPU-bound tasks:
- * (default: 2 msec * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 0.75 msec * (1 + ilog(ncpus)), units: nanoseconds)
  */
 unsigned int sysctl_sched_min_granularity = 750000ULL;
 unsigned int normalized_sysctl_sched_min_granularity = 750000ULL;
@@ -519,7 +519,7 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
 static void update_curr(struct cfs_rq *cfs_rq)
 {
         struct sched_entity *curr = cfs_rq->curr;
-        u64 now = rq_of(cfs_rq)->clock;
+        u64 now = rq_of(cfs_rq)->clock_task;
         unsigned long delta_exec;
 
         if (unlikely(!curr))
@@ -602,7 +602,7 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
         /*
          * We are starting a new run period:
          */
-        se->exec_start = rq_of(cfs_rq)->clock;
+        se->exec_start = rq_of(cfs_rq)->clock_task;
 }
 
 /**************************************************
@@ -1764,6 +1764,10 @@ static void pull_task(struct rq *src_rq, struct task_struct *p,
         set_task_cpu(p, this_cpu);
         activate_task(this_rq, p, 0);
         check_preempt_curr(this_rq, p, 0);
+
+        /* re-arm NEWIDLE balancing when moving tasks */
+        src_rq->avg_idle = this_rq->avg_idle = 2*sysctl_sched_migration_cost;
+        this_rq->idle_stamp = 0;
 }
 
 /*
@@ -1798,7 +1802,7 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
          * 2) too many balance attempts have failed.
          */
 
-        tsk_cache_hot = task_hot(p, rq->clock, sd);
+        tsk_cache_hot = task_hot(p, rq->clock_task, sd);
         if (!tsk_cache_hot ||
                 sd->nr_balance_failed > sd->cache_nice_tries) {
 #ifdef CONFIG_SCHEDSTATS
@@ -2030,12 +2034,14 @@ struct sd_lb_stats {
         unsigned long this_load;
         unsigned long this_load_per_task;
         unsigned long this_nr_running;
+        unsigned long this_has_capacity;
 
         /* Statistics of the busiest group */
         unsigned long max_load;
         unsigned long busiest_load_per_task;
         unsigned long busiest_nr_running;
         unsigned long busiest_group_capacity;
+        unsigned long busiest_has_capacity;
 
         int group_imb; /* Is there imbalance in this sd */
 #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
@@ -2058,6 +2064,7 @@ struct sg_lb_stats {
         unsigned long sum_weighted_load; /* Weighted load of group's tasks */
         unsigned long group_capacity;
         int group_imb; /* Is there an imbalance in the group ? */
+        int group_has_capacity; /* Is there extra capacity in the group? */
 };
 
 /**
@@ -2268,7 +2275,13 @@ unsigned long scale_rt_power(int cpu)
         u64 total, available;
 
         total = sched_avg_period() + (rq->clock - rq->age_stamp);
-        available = total - rq->rt_avg;
+
+        if (unlikely(total < rq->rt_avg)) {
+                /* Ensures that power won't end up being negative */
+                available = 0;
+        } else {
+                available = total - rq->rt_avg;
+        }
 
         if (unlikely((s64)total < SCHED_LOAD_SCALE))
                 total = SCHED_LOAD_SCALE;
@@ -2378,7 +2391,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
                         int local_group, const struct cpumask *cpus,
                         int *balance, struct sg_lb_stats *sgs)
 {
-        unsigned long load, max_cpu_load, min_cpu_load;
+        unsigned long load, max_cpu_load, min_cpu_load, max_nr_running;
         int i;
         unsigned int balance_cpu = -1, first_idle_cpu = 0;
         unsigned long avg_load_per_task = 0;
@@ -2389,6 +2402,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
         /* Tally up the load of all CPUs in the group */
         max_cpu_load = 0;
         min_cpu_load = ~0UL;
+        max_nr_running = 0;
 
         for_each_cpu_and(i, sched_group_cpus(group), cpus) {
                 struct rq *rq = cpu_rq(i);
@@ -2406,8 +2420,10 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
                         load = target_load(i, load_idx);
                 } else {
                         load = source_load(i, load_idx);
-                        if (load > max_cpu_load)
+                        if (load > max_cpu_load) {
                                 max_cpu_load = load;
+                                max_nr_running = rq->nr_running;
+                        }
                         if (min_cpu_load > load)
                                 min_cpu_load = load;
                 }
@@ -2447,13 +2463,15 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
         if (sgs->sum_nr_running)
                 avg_load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;
 
-        if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
+        if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task && max_nr_running > 1)
                 sgs->group_imb = 1;
 
-        sgs->group_capacity =
-                DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
+        sgs->group_capacity = DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
         if (!sgs->group_capacity)
                 sgs->group_capacity = fix_small_capacity(sd, group);
+
+        if (sgs->group_capacity > sgs->sum_nr_running)
+                sgs->group_has_capacity = 1;
 }
 
 /**
@@ -2542,9 +2560,14 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
                 /*
                  * In case the child domain prefers tasks go to siblings
                  * first, lower the sg capacity to one so that we'll try
-                 * and move all the excess tasks away.
+                 * and move all the excess tasks away. We lower the capacity
+                 * of a group only if the local group has the capacity to fit
+                 * these excess tasks, i.e. nr_running < group_capacity. The
+                 * extra check prevents the case where you always pull from the
+                 * heaviest group when it is already under-utilized (possible
+                 * with a large weight task outweighs the tasks on the system).
                  */
-                if (prefer_sibling)
+                if (prefer_sibling && !local_group && sds->this_has_capacity)
                         sgs.group_capacity = min(sgs.group_capacity, 1UL);
 
                 if (local_group) {
@@ -2552,12 +2575,14 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
                         sds->this = sg;
                         sds->this_nr_running = sgs.sum_nr_running;
                         sds->this_load_per_task = sgs.sum_weighted_load;
+                        sds->this_has_capacity = sgs.group_has_capacity;
                 } else if (update_sd_pick_busiest(sd, sds, sg, &sgs, this_cpu)) {
                         sds->max_load = sgs.avg_load;
                         sds->busiest = sg;
                         sds->busiest_nr_running = sgs.sum_nr_running;
                         sds->busiest_group_capacity = sgs.group_capacity;
                         sds->busiest_load_per_task = sgs.sum_weighted_load;
+                        sds->busiest_has_capacity = sgs.group_has_capacity;
                         sds->group_imb = sgs.group_imb;
                 }
 
@@ -2754,6 +2779,7 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
                 return fix_small_imbalance(sds, this_cpu, imbalance);
 
 }
+
 /******* find_busiest_group() helpers end here *********************/
 
 /**
@@ -2805,6 +2831,11 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
          * 4) This group is more busy than the avg busieness at this
          *    sched_domain.
          * 5) The imbalance is within the specified limit.
+         *
+         * Note: when doing newidle balance, if the local group has excess
+         * capacity (i.e. nr_running < group_capacity) and the busiest group
+         * does not have any capacity, we force a load balance to pull tasks
+         * to the local group. In this case, we skip past checks 3, 4 and 5.
          */
         if (!(*balance))
                 goto ret;
@@ -2816,6 +2847,11 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
         if (!sds.busiest || sds.busiest_nr_running == 0)
                 goto out_balanced;
 
+        /*  SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
+        if (idle == CPU_NEWLY_IDLE && sds.this_has_capacity &&
+                        !sds.busiest_has_capacity)
+                goto force_balance;
+
         if (sds.this_load >= sds.max_load)
                 goto out_balanced;
 
@@ -2827,6 +2863,7 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
         if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
                 goto out_balanced;
 
+force_balance:
         /* Looks like there is an imbalance. Compute it */
         calculate_imbalance(&sds, this_cpu, imbalance);
         return sds.busiest;
@@ -3031,7 +3068,14 @@ redo:
 
         if (!ld_moved) {
                 schedstat_inc(sd, lb_failed[idle]);
-                sd->nr_balance_failed++;
+                /*
+                 * Increment the failure counter only on periodic balance.
+                 * We do not want newidle balance, which can be very
+                 * frequent, pollute the failure counter causing
+                 * excessive cache_hot migrations and active balances.
+                 */
+                if (idle != CPU_NEWLY_IDLE)
+                        sd->nr_balance_failed++;
 
                 if (need_active_balance(sd, sd_idle, idle, cpu_of(busiest),
                                         this_cpu)) {
@@ -3153,10 +3197,8 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
                 interval = msecs_to_jiffies(sd->balance_interval);
                 if (time_after(next_balance, sd->last_balance + interval))
                         next_balance = sd->last_balance + interval;
-                if (pulled_task) {
-                        this_rq->idle_stamp = 0;
+                if (pulled_task)
                         break;
-                }
         }
 
         raw_spin_lock(&this_rq->lock);
@@ -3751,8 +3793,11 @@ static void task_fork_fair(struct task_struct *p)
 
         update_rq_clock(rq);
 
-        if (unlikely(task_cpu(p) != this_cpu))
+        if (unlikely(task_cpu(p) != this_cpu)) {
+                rcu_read_lock();
                 __set_task_cpu(p, this_cpu);
+                rcu_read_unlock();
+        }
 
         update_curr(cfs_rq);
 
diff --git a/kernel/sched_features.h b/kernel/sched_features.h
index 83c66e8ad3ee..185f920ec1a2 100644
--- a/kernel/sched_features.h
+++ b/kernel/sched_features.h
@@ -61,3 +61,8 @@ SCHED_FEAT(ASYM_EFF_LOAD, 1)
  * release the lock. Decreases scheduling overhead.
  */
 SCHED_FEAT(OWNER_SPIN, 1)
+
+/*
+ * Decrement CPU power based on irq activity
+ */
+SCHED_FEAT(NONIRQ_POWER, 1)
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index d10c80ebb67a..bea7d79f7e9c 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -609,7 +609,7 @@ static void update_curr_rt(struct rq *rq)
         if (!task_has_rt_policy(curr))
                 return;
 
-        delta_exec = rq->clock - curr->se.exec_start;
+        delta_exec = rq->clock_task - curr->se.exec_start;
         if (unlikely((s64)delta_exec < 0))
                 delta_exec = 0;
 
@@ -618,7 +618,7 @@ static void update_curr_rt(struct rq *rq)
         curr->se.sum_exec_runtime += delta_exec;
         account_group_exec_runtime(curr, delta_exec);
 
-        curr->se.exec_start = rq->clock;
+        curr->se.exec_start = rq->clock_task;
         cpuacct_charge(curr, delta_exec);
 
         sched_rt_avg_update(rq, delta_exec);
@@ -960,18 +960,19 @@ select_task_rq_rt(struct rq *rq, struct task_struct *p, int sd_flag, int flags)
          * runqueue. Otherwise simply start this RT task
          * on its current runqueue.
          *
-         * We want to avoid overloading runqueues. Even if
-         * the RT task is of higher priority than the current RT task.
-         * RT tasks behave differently than other tasks. If
-         * one gets preempted, we try to push it off to another queue.
-         * So trying to keep a preempting RT task on the same
-         * cache hot CPU will force the running RT task to
-         * a cold CPU. So we waste all the cache for the lower
-         * RT task in hopes of saving some of a RT task
-         * that is just being woken and probably will have
-         * cold cache anyway.
+         * We want to avoid overloading runqueues. If the woken
+         * task is a higher priority, then it will stay on this CPU
+         * and the lower prio task should be moved to another CPU.
+         * Even though this will probably make the lower prio task
+         * lose its cache, we do not want to bounce a higher task
+         * around just because it gave up its CPU, perhaps for a
+         * lock?
+         *
+         * For equal prio tasks, we just let the scheduler sort it out.
          */
         if (unlikely(rt_task(rq->curr)) &&
+            (rq->curr->rt.nr_cpus_allowed < 2 ||
+             rq->curr->prio < p->prio) &&
             (p->rt.nr_cpus_allowed > 1)) {
                 int cpu = find_lowest_rq(p);
 
@@ -1074,7 +1075,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
         } while (rt_rq);
 
         p = rt_task_of(rt_se);
-        p->se.exec_start = rq->clock;
+        p->se.exec_start = rq->clock_task;
 
         return p;
 }
@@ -1139,7 +1140,7 @@ static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu)
         for_each_leaf_rt_rq(rt_rq, rq) {
                 array = &rt_rq->active;
                 idx = sched_find_first_bit(array->bitmap);
- next_idx:
+next_idx:
                 if (idx >= MAX_RT_PRIO)
                         continue;
                 if (next && next->prio < idx)
@@ -1315,7 +1316,7 @@ static int push_rt_task(struct rq *rq)
         if (!next_task)
                 return 0;
 
- retry:
+retry:
         if (unlikely(next_task == rq->curr)) {
                 WARN_ON(1);
                 return 0;
@@ -1463,7 +1464,7 @@ static int pull_rt_task(struct rq *this_rq)
                          * but possible)
                          */
                 }
- skip:
+skip:
                 double_unlock_balance(this_rq, src_rq);
         }
 
@@ -1491,7 +1492,10 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p)
         if (!task_running(rq, p) &&
             !test_tsk_need_resched(rq->curr) &&
             has_pushable_tasks(rq) &&
-            p->rt.nr_cpus_allowed > 1)
+            p->rt.nr_cpus_allowed > 1 &&
+            rt_task(rq->curr) &&
+            (rq->curr->rt.nr_cpus_allowed < 2 ||
+             rq->curr->prio < p->prio))
                 push_rt_tasks(rq);
 }
 
@@ -1709,7 +1713,7 @@ static void set_curr_task_rt(struct rq *rq)
 {
         struct task_struct *p = rq->curr;
 
-        p->se.exec_start = rq->clock;
+        p->se.exec_start = rq->clock_task;
 
         /* The running task is never eligible for pushing */
         dequeue_pushable_task(rq, p);
diff --git a/kernel/sched_stoptask.c b/kernel/sched_stoptask.c
new file mode 100644
index 000000000000..45bddc0c1048
--- /dev/null
+++ b/kernel/sched_stoptask.c
@@ -0,0 +1,108 @@
+/*
+ * stop-task scheduling class.
+ *
+ * The stop task is the highest priority task in the system, it preempts
+ * everything and will be preempted by nothing.
+ *
+ * See kernel/stop_machine.c
+ */
+
+#ifdef CONFIG_SMP
+static int
+select_task_rq_stop(struct rq *rq, struct task_struct *p,
+                    int sd_flag, int flags)
+{
+        return task_cpu(p); /* stop tasks as never migrate */
+}
+#endif /* CONFIG_SMP */
+
+static void
+check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags)
+{
+        resched_task(rq->curr); /* we preempt everything */
+}
+
+static struct task_struct *pick_next_task_stop(struct rq *rq)
+{
+        struct task_struct *stop = rq->stop;
+
+        if (stop && stop->state == TASK_RUNNING)
+                return stop;
+
+        return NULL;
+}
+
+static void
+enqueue_task_stop(struct rq *rq, struct task_struct *p, int flags)
+{
+}
+
+static void
+dequeue_task_stop(struct rq *rq, struct task_struct *p, int flags)
+{
+}
+
+static void yield_task_stop(struct rq *rq)
+{
+        BUG(); /* the stop task should never yield, its pointless. */
+}
+
+static void put_prev_task_stop(struct rq *rq, struct task_struct *prev)
+{
+}
+
+static void task_tick_stop(struct rq *rq, struct task_struct *curr, int queued)
+{
+}
+
+static void set_curr_task_stop(struct rq *rq)
+{
+}
+
+static void switched_to_stop(struct rq *rq, struct task_struct *p,
+                             int running)
+{
+        BUG(); /* its impossible to change to this class */
+}
+
+static void prio_changed_stop(struct rq *rq, struct task_struct *p,
+                              int oldprio, int running)
+{
+        BUG(); /* how!?, what priority? */
+}
+
+static unsigned int
+get_rr_interval_stop(struct rq *rq, struct task_struct *task)
+{
+        return 0;
+}
+
+/*
+ * Simple, special scheduling class for the per-CPU stop tasks:
+ */
+static const struct sched_class stop_sched_class = {
+        .next                   = &rt_sched_class,
+
+        .enqueue_task           = enqueue_task_stop,
+        .dequeue_task           = dequeue_task_stop,
+        .yield_task             = yield_task_stop,
+
+        .check_preempt_curr     = check_preempt_curr_stop,
+
+        .pick_next_task         = pick_next_task_stop,
+        .put_prev_task          = put_prev_task_stop,
+
+#ifdef CONFIG_SMP
+        .select_task_rq         = select_task_rq_stop,
+#endif
+
+        .set_curr_task          = set_curr_task_stop,
+        .task_tick              = task_tick_stop,
+
+        .get_rr_interval        = get_rr_interval_stop,
+
+        .prio_changed           = prio_changed_stop,
+        .switched_to            = switched_to_stop,
+
+        /* no .task_new for stop tasks */
+};
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 07b4f1b1a73a..fc978889b194 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -77,11 +77,21 @@ void wakeup_softirqd(void)
 }
 
 /*
+ * preempt_count and SOFTIRQ_OFFSET usage:
+ * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving
+ *   softirq processing.
+ * - preempt_count is changed by SOFTIRQ_DISABLE_OFFSET (= 2 * SOFTIRQ_OFFSET)
+ *   on local_bh_disable or local_bh_enable.
+ * This lets us distinguish between whether we are currently processing
+ * softirq and whether we just have bh disabled.
+ */
+
+/*
  * This one is for softirq.c-internal use,
  * where hardirqs are disabled legitimately:
  */
 #ifdef CONFIG_TRACE_IRQFLAGS
-static void __local_bh_disable(unsigned long ip)
+static void __local_bh_disable(unsigned long ip, unsigned int cnt)
 {
         unsigned long flags;
 
@@ -95,32 +105,43 @@ static void __local_bh_disable(unsigned long ip)
          * We must manually increment preempt_count here and manually
          * call the trace_preempt_off later.
          */
-        preempt_count() += SOFTIRQ_OFFSET;
+        preempt_count() += cnt;
         /*
          * Were softirqs turned off above:
          */
-        if (softirq_count() == SOFTIRQ_OFFSET)
+        if (softirq_count() == cnt)
                 trace_softirqs_off(ip);
         raw_local_irq_restore(flags);
 
-        if (preempt_count() == SOFTIRQ_OFFSET)
+        if (preempt_count() == cnt)
                 trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
 }
 #else /* !CONFIG_TRACE_IRQFLAGS */
-static inline void __local_bh_disable(unsigned long ip)
+static inline void __local_bh_disable(unsigned long ip, unsigned int cnt)
 {
-        add_preempt_count(SOFTIRQ_OFFSET);
+        add_preempt_count(cnt);
         barrier();
 }
 #endif /* CONFIG_TRACE_IRQFLAGS */
 
 void local_bh_disable(void)
 {
-        __local_bh_disable((unsigned long)__builtin_return_address(0));
+        __local_bh_disable((unsigned long)__builtin_return_address(0),
+                                SOFTIRQ_DISABLE_OFFSET);
 }
 
 EXPORT_SYMBOL(local_bh_disable);
 
+static void __local_bh_enable(unsigned int cnt)
+{
+        WARN_ON_ONCE(in_irq());
+        WARN_ON_ONCE(!irqs_disabled());
+
+        if (softirq_count() == cnt)
+                trace_softirqs_on((unsigned long)__builtin_return_address(0));
+        sub_preempt_count(cnt);
+}
+
 /*
  * Special-case - softirqs can safely be enabled in
  * cond_resched_softirq(), or by __do_softirq(),
@@ -128,12 +149,7 @@ EXPORT_SYMBOL(local_bh_disable);
  */
 void _local_bh_enable(void)
 {
-        WARN_ON_ONCE(in_irq());
-        WARN_ON_ONCE(!irqs_disabled());
-
-        if (softirq_count() == SOFTIRQ_OFFSET)
-                trace_softirqs_on((unsigned long)__builtin_return_address(0));
-        sub_preempt_count(SOFTIRQ_OFFSET);
+        __local_bh_enable(SOFTIRQ_DISABLE_OFFSET);
 }
 
 EXPORT_SYMBOL(_local_bh_enable);
@@ -147,13 +163,13 @@ static inline void _local_bh_enable_ip(unsigned long ip)
         /*
          * Are softirqs going to be turned on now:
          */
-        if (softirq_count() == SOFTIRQ_OFFSET)
+        if (softirq_count() == SOFTIRQ_DISABLE_OFFSET)
                 trace_softirqs_on(ip);
         /*
          * Keep preemption disabled until we are done with
          * softirq processing:
          */
-        sub_preempt_count(SOFTIRQ_OFFSET - 1);
+        sub_preempt_count(SOFTIRQ_DISABLE_OFFSET - 1);
 
         if (unlikely(!in_interrupt() && local_softirq_pending()))
                 do_softirq();
@@ -198,7 +214,8 @@ asmlinkage void __do_softirq(void)
         pending = local_softirq_pending();
         account_system_vtime(current);
 
-        __local_bh_disable((unsigned long)__builtin_return_address(0));
+        __local_bh_disable((unsigned long)__builtin_return_address(0),
+                                SOFTIRQ_OFFSET);
         lockdep_softirq_enter();
 
         cpu = smp_processor_id();
@@ -245,7 +262,7 @@ restart:
         lockdep_softirq_exit();
 
         account_system_vtime(current);
-        _local_bh_enable();
+        __local_bh_enable(SOFTIRQ_OFFSET);
 }
 
 #ifndef __ARCH_HAS_DO_SOFTIRQ
@@ -279,10 +296,16 @@ void irq_enter(void)
 
         rcu_irq_enter();
         if (idle_cpu(cpu) && !in_interrupt()) {
-                __irq_enter();
+                /*
+                 * Prevent raise_softirq from needlessly waking up ksoftirqd
+                 * here, as softirq will be serviced on return from interrupt.
+                 */
+                local_bh_disable();
                 tick_check_idle(cpu);
-        } else
-                __irq_enter();
+                _local_bh_enable();
+        }
+
+        __irq_enter();
 }
 
 #ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED
@@ -696,6 +719,7 @@ static int run_ksoftirqd(void * __bind_cpu)
 {
         set_current_state(TASK_INTERRUPTIBLE);
 
+        current->flags |= PF_KSOFTIRQD;
         while (!kthread_should_stop()) {
                 preempt_disable();
                 if (!local_softirq_pending()) {
@@ -886,17 +910,14 @@ int __init __weak early_irq_init(void)
         return 0;
 }
 
+#ifdef CONFIG_GENERIC_HARDIRQS
 int __init __weak arch_probe_nr_irqs(void)
 {
-        return 0;
+        return NR_IRQS_LEGACY;
 }
 
 int __init __weak arch_early_irq_init(void)
 {
         return 0;
 }
-
-int __weak arch_init_chip_data(struct irq_desc *desc, int node)
-{
-        return 0;
-}
+#endif
diff --git a/kernel/srcu.c b/kernel/srcu.c
index 2980da3fd509..c71e07500536 100644
--- a/kernel/srcu.c
+++ b/kernel/srcu.c
@@ -46,11 +46,9 @@ static int init_srcu_struct_fields(struct srcu_struct *sp)
 int __init_srcu_struct(struct srcu_struct *sp, const char *name,
                        struct lock_class_key *key)
 {
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
         /* Don't re-initialize a lock while it is held. */
         debug_check_no_locks_freed((void *)sp, sizeof(*sp));
         lockdep_init_map(&sp->dep_map, name, key, 0);
-#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
         return init_srcu_struct_fields(sp);
 }
 EXPORT_SYMBOL_GPL(__init_srcu_struct);
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 4372ccb25127..090c28812ce1 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -287,11 +287,12 @@ repeat:
         goto repeat;
 }
 
+extern void sched_set_stop_task(int cpu, struct task_struct *stop);
+
 /* manage stopper for a cpu, mostly lifted from sched migration thread mgmt */
 static int __cpuinit cpu_stop_cpu_callback(struct notifier_block *nfb,
                                            unsigned long action, void *hcpu)
 {
-        struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
         unsigned int cpu = (unsigned long)hcpu;
         struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
         struct task_struct *p;
@@ -304,13 +305,13 @@ static int __cpuinit cpu_stop_cpu_callback(struct notifier_block *nfb,
                                    cpu);
                 if (IS_ERR(p))
                         return NOTIFY_BAD;
-                sched_setscheduler_nocheck(p, SCHED_FIFO, &param);
                 get_task_struct(p);
+                kthread_bind(p, cpu);
+                sched_set_stop_task(cpu, p);
                 stopper->thread = p;
                 break;
 
         case CPU_ONLINE:
-                kthread_bind(stopper->thread, cpu);
                 /* strictly unnecessary, as first user will wake it */
                 wake_up_process(stopper->thread);
                 /* mark enabled */
@@ -325,6 +326,7 @@ static int __cpuinit cpu_stop_cpu_callback(struct notifier_block *nfb,
         {
                 struct cpu_stop_work *work;
 
+                sched_set_stop_task(cpu, NULL);
                 /* kill the stopper */
                 kthread_stop(stopper->thread);
                 /* drain remaining works */
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index c63116863a80..d2321891538f 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -149,10 +149,18 @@ static void ntp_update_offset(long offset)
         time_reftime = get_seconds();
 
         offset64    = offset;
-        freq_adj    = (offset64 * secs) <<
-                        (NTP_SCALE_SHIFT - 2 * (SHIFT_PLL + 2 + time_constant));
+        freq_adj    = ntp_update_offset_fll(offset64, secs);
 
-        freq_adj    += ntp_update_offset_fll(offset64, secs);
+        /*
+         * Clamp update interval to reduce PLL gain with low
+         * sampling rate (e.g. intermittent network connection)
+         * to avoid instability.
+         */
+        if (unlikely(secs > 1 << (SHIFT_PLL + 1 + time_constant)))
+                secs = 1 << (SHIFT_PLL + 1 + time_constant);
+
+        freq_adj    += (offset64 * secs) <<
+                        (NTP_SCALE_SHIFT - 2 * (SHIFT_PLL + 2 + time_constant));
 
         freq_adj    = min(freq_adj + time_freq, MAXFREQ_SCALED);
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 65fb077ea79c..ebd80d50c474 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1638,8 +1638,8 @@ ftrace_failures_open(struct inode *inode, struct file *file)
 
         ret = ftrace_avail_open(inode, file);
         if (!ret) {
-                m = (struct seq_file *)file->private_data;
-                iter = (struct ftrace_iterator *)m->private;
+                m = file->private_data;
+                iter = m->private;
                 iter->flags = FTRACE_ITER_FAILURES;
         }
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 9ec59f541156..001bcd2ccf4a 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2196,7 +2196,7 @@ int tracing_open_generic(struct inode *inode, struct file *filp)
 
 static int tracing_release(struct inode *inode, struct file *file)
 {
-        struct seq_file *m = (struct seq_file *)file->private_data;
+        struct seq_file *m = file->private_data;
         struct trace_iterator *iter;
         int cpu;
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index d39b3c5454a5..9021f8c0c0c3 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -343,6 +343,10 @@ void trace_function(struct trace_array *tr,
                     unsigned long ip,
                     unsigned long parent_ip,
                     unsigned long flags, int pc);
+void trace_graph_function(struct trace_array *tr,
+                    unsigned long ip,
+                    unsigned long parent_ip,
+                    unsigned long flags, int pc);
 void trace_default_header(struct seq_file *m);
 void print_trace_header(struct seq_file *m, struct trace_iterator *iter);
 int trace_empty(struct trace_iterator *iter);
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index ef49e9370b25..76b05980225c 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -262,6 +262,34 @@ int trace_graph_thresh_entry(struct ftrace_graph_ent *trace)
                 return trace_graph_entry(trace);
 }
 
+static void
+__trace_graph_function(struct trace_array *tr,
+                unsigned long ip, unsigned long flags, int pc)
+{
+        u64 time = trace_clock_local();
+        struct ftrace_graph_ent ent = {
+                .func  = ip,
+                .depth = 0,
+        };
+        struct ftrace_graph_ret ret = {
+                .func     = ip,
+                .depth    = 0,
+                .calltime = time,
+                .rettime  = time,
+        };
+
+        __trace_graph_entry(tr, &ent, flags, pc);
+        __trace_graph_return(tr, &ret, flags, pc);
+}
+
+void
+trace_graph_function(struct trace_array *tr,
+                unsigned long ip, unsigned long parent_ip,
+                unsigned long flags, int pc)
+{
+        __trace_graph_function(tr, ip, flags, pc);
+}
+
 void __trace_graph_return(struct trace_array *tr,
                                 struct ftrace_graph_ret *trace,
                                 unsigned long flags,
@@ -888,12 +916,20 @@ check_irq_entry(struct trace_iterator *iter, u32 flags,
                 unsigned long addr, int depth)
 {
         int cpu = iter->cpu;
+        int *depth_irq;
         struct fgraph_data *data = iter->private;
-        int *depth_irq = &(per_cpu_ptr(data->cpu_data, cpu)->depth_irq);
 
-        if (flags & TRACE_GRAPH_PRINT_IRQS)
+        /*
+         * If we are either displaying irqs, or we got called as
+         * a graph event and private data does not exist,
+         * then we bypass the irq check.
+         */
+        if ((flags & TRACE_GRAPH_PRINT_IRQS) ||
+            (!data))
                 return 0;
 
+        depth_irq = &(per_cpu_ptr(data->cpu_data, cpu)->depth_irq);
+
         /*
          * We are inside the irq code
          */
@@ -926,12 +962,20 @@ static int
 check_irq_return(struct trace_iterator *iter, u32 flags, int depth)
 {
         int cpu = iter->cpu;
+        int *depth_irq;
         struct fgraph_data *data = iter->private;
-        int *depth_irq = &(per_cpu_ptr(data->cpu_data, cpu)->depth_irq);
 
-        if (flags & TRACE_GRAPH_PRINT_IRQS)
+        /*
+         * If we are either displaying irqs, or we got called as
+         * a graph event and private data does not exist,
+         * then we bypass the irq check.
+         */
+        if ((flags & TRACE_GRAPH_PRINT_IRQS) ||
+            (!data))
                 return 0;
 
+        depth_irq = &(per_cpu_ptr(data->cpu_data, cpu)->depth_irq);
+
         /*
          * We are not inside the irq code.
          */
@@ -1163,7 +1207,7 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent,
 
 
 enum print_line_t
-print_graph_function_flags(struct trace_iterator *iter, u32 flags)
+__print_graph_function_flags(struct trace_iterator *iter, u32 flags)
 {
         struct ftrace_graph_ent_entry *field;
         struct fgraph_data *data = iter->private;
@@ -1226,7 +1270,18 @@ print_graph_function_flags(struct trace_iterator *iter, u32 flags)
 static enum print_line_t
 print_graph_function(struct trace_iterator *iter)
 {
-        return print_graph_function_flags(iter, tracer_flags.val);
+        return __print_graph_function_flags(iter, tracer_flags.val);
+}
+
+enum print_line_t print_graph_function_flags(struct trace_iterator *iter,
+                                             u32 flags)
+{
+        if (trace_flags & TRACE_ITER_LATENCY_FMT)
+                flags |= TRACE_GRAPH_PRINT_DURATION;
+        else
+                flags |= TRACE_GRAPH_PRINT_ABS_TIME;
+
+        return __print_graph_function_flags(iter, flags);
 }
 
 static enum print_line_t
@@ -1258,7 +1313,7 @@ static void print_lat_header(struct seq_file *s, u32 flags)
         seq_printf(s, "#%.*s|||| /                     \n", size, spaces);
 }
 
-void print_graph_headers_flags(struct seq_file *s, u32 flags)
+static void __print_graph_headers_flags(struct seq_file *s, u32 flags)
 {
         int lat = trace_flags & TRACE_ITER_LATENCY_FMT;
 
@@ -1299,6 +1354,23 @@ void print_graph_headers(struct seq_file *s)
         print_graph_headers_flags(s, tracer_flags.val);
 }
 
+void print_graph_headers_flags(struct seq_file *s, u32 flags)
+{
+        struct trace_iterator *iter = s->private;
+
+        if (trace_flags & TRACE_ITER_LATENCY_FMT) {
+                /* print nothing if the buffers are empty */
+                if (trace_empty(iter))
+                        return;
+
+                print_trace_header(s, iter);
+                flags |= TRACE_GRAPH_PRINT_DURATION;
+        } else
+                flags |= TRACE_GRAPH_PRINT_ABS_TIME;
+
+        __print_graph_headers_flags(s, flags);
+}
+
 void graph_trace_open(struct trace_iterator *iter)
 {
         /* pid and depth on the last trace processed */
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 73a6b0601f2e..5cf8c602b880 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -87,14 +87,22 @@ static __cacheline_aligned_in_smp	unsigned long max_sequence;
 
 #ifdef CONFIG_FUNCTION_TRACER
 /*
- * irqsoff uses its own tracer function to keep the overhead down:
+ * Prologue for the preempt and irqs off function tracers.
+ *
+ * Returns 1 if it is OK to continue, and data->disabled is
+ *            incremented.
+ *         0 if the trace is to be ignored, and data->disabled
+ *            is kept the same.
+ *
+ * Note, this function is also used outside this ifdef but
+ *  inside the #ifdef of the function graph tracer below.
+ *  This is OK, since the function graph tracer is
+ *  dependent on the function tracer.
  */
-static void
-irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip)
+static int func_prolog_dec(struct trace_array *tr,
+                           struct trace_array_cpu **data,
+                           unsigned long *flags)
 {
-        struct trace_array *tr = irqsoff_trace;
-        struct trace_array_cpu *data;
-        unsigned long flags;
         long disabled;
         int cpu;
 
@@ -106,18 +114,38 @@ irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip)
          */
         cpu = raw_smp_processor_id();
         if (likely(!per_cpu(tracing_cpu, cpu)))
-                return;
+                return 0;
 
-        local_save_flags(flags);
+        local_save_flags(*flags);
         /* slight chance to get a false positive on tracing_cpu */
-        if (!irqs_disabled_flags(flags))
-                return;
+        if (!irqs_disabled_flags(*flags))
+                return 0;
 
-        data = tr->data[cpu];
-        disabled = atomic_inc_return(&data->disabled);
+        *data = tr->data[cpu];
+        disabled = atomic_inc_return(&(*data)->disabled);
 
         if (likely(disabled == 1))
-                trace_function(tr, ip, parent_ip, flags, preempt_count());
+                return 1;
+
+        atomic_dec(&(*data)->disabled);
+
+        return 0;
+}
+
+/*
+ * irqsoff uses its own tracer function to keep the overhead down:
+ */
+static void
+irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip)
+{
+        struct trace_array *tr = irqsoff_trace;
+        struct trace_array_cpu *data;
+        unsigned long flags;
+
+        if (!func_prolog_dec(tr, &data, &flags))
+                return;
+
+        trace_function(tr, ip, parent_ip, flags, preempt_count());
 
         atomic_dec(&data->disabled);
 }
@@ -155,30 +183,16 @@ static int irqsoff_graph_entry(struct ftrace_graph_ent *trace)
         struct trace_array *tr = irqsoff_trace;
         struct trace_array_cpu *data;
         unsigned long flags;
-        long disabled;
         int ret;
-        int cpu;
         int pc;
 
-        cpu = raw_smp_processor_id();
-        if (likely(!per_cpu(tracing_cpu, cpu)))
+        if (!func_prolog_dec(tr, &data, &flags))
                 return 0;
 
-        local_save_flags(flags);
-        /* slight chance to get a false positive on tracing_cpu */
-        if (!irqs_disabled_flags(flags))
-                return 0;
-
-        data = tr->data[cpu];
-        disabled = atomic_inc_return(&data->disabled);
-
-        if (likely(disabled == 1)) {
-                pc = preempt_count();
-                ret = __trace_graph_entry(tr, trace, flags, pc);
-        } else
-                ret = 0;
-
+        pc = preempt_count();
+        ret = __trace_graph_entry(tr, trace, flags, pc);
         atomic_dec(&data->disabled);
+
         return ret;
 }
 
@@ -187,27 +201,13 @@ static void irqsoff_graph_return(struct ftrace_graph_ret *trace)
         struct trace_array *tr = irqsoff_trace;
         struct trace_array_cpu *data;
         unsigned long flags;
-        long disabled;
-        int cpu;
         int pc;
 
-        cpu = raw_smp_processor_id();
-        if (likely(!per_cpu(tracing_cpu, cpu)))
+        if (!func_prolog_dec(tr, &data, &flags))
                 return;
 
-        local_save_flags(flags);
-        /* slight chance to get a false positive on tracing_cpu */
-        if (!irqs_disabled_flags(flags))
-                return;
-
-        data = tr->data[cpu];
-        disabled = atomic_inc_return(&data->disabled);
-
-        if (likely(disabled == 1)) {
-                pc = preempt_count();
-                __trace_graph_return(tr, trace, flags, pc);
-        }
-
+        pc = preempt_count();
+        __trace_graph_return(tr, trace, flags, pc);
         atomic_dec(&data->disabled);
 }
 
@@ -229,75 +229,33 @@ static void irqsoff_trace_close(struct trace_iterator *iter)
 
 static enum print_line_t irqsoff_print_line(struct trace_iterator *iter)
 {
-        u32 flags = GRAPH_TRACER_FLAGS;
-
-        if (trace_flags & TRACE_ITER_LATENCY_FMT)
-                flags |= TRACE_GRAPH_PRINT_DURATION;
-        else
-                flags |= TRACE_GRAPH_PRINT_ABS_TIME;
-
         /*
          * In graph mode call the graph tracer output function,
          * otherwise go with the TRACE_FN event handler
          */
         if (is_graph())
-                return print_graph_function_flags(iter, flags);
+                return print_graph_function_flags(iter, GRAPH_TRACER_FLAGS);
 
         return TRACE_TYPE_UNHANDLED;
 }
 
 static void irqsoff_print_header(struct seq_file *s)
 {
-        if (is_graph()) {
-                struct trace_iterator *iter = s->private;
-                u32 flags = GRAPH_TRACER_FLAGS;
-
-                if (trace_flags & TRACE_ITER_LATENCY_FMT) {
-                        /* print nothing if the buffers are empty */
-                        if (trace_empty(iter))
-                                return;
-
-                        print_trace_header(s, iter);
-                        flags |= TRACE_GRAPH_PRINT_DURATION;
-                } else
-                        flags |= TRACE_GRAPH_PRINT_ABS_TIME;
-
-                print_graph_headers_flags(s, flags);
-        } else
+        if (is_graph())
+                print_graph_headers_flags(s, GRAPH_TRACER_FLAGS);
+        else
                 trace_default_header(s);
 }
 
 static void
-trace_graph_function(struct trace_array *tr,
-                 unsigned long ip, unsigned long flags, int pc)
-{
-        u64 time = trace_clock_local();
-        struct ftrace_graph_ent ent = {
-                .func  = ip,
-                .depth = 0,
-        };
-        struct ftrace_graph_ret ret = {
-                .func     = ip,
-                .depth    = 0,
-                .calltime = time,
-                .rettime  = time,
-        };
-
-        __trace_graph_entry(tr, &ent, flags, pc);
-        __trace_graph_return(tr, &ret, flags, pc);
-}
-
-static void
 __trace_function(struct trace_array *tr,
                  unsigned long ip, unsigned long parent_ip,
                  unsigned long flags, int pc)
 {
-        if (!is_graph())
+        if (is_graph())
+                trace_graph_function(tr, ip, parent_ip, flags, pc);
+        else
                 trace_function(tr, ip, parent_ip, flags, pc);
-        else {
-                trace_graph_function(tr, parent_ip, flags, pc);
-                trace_graph_function(tr, ip, flags, pc);
-        }
 }
 
 #else
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 4086eae6e81b..7319559ed59f 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -31,48 +31,98 @@ static int			wakeup_rt;
 static arch_spinlock_t wakeup_lock =
         (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
 
+static void wakeup_reset(struct trace_array *tr);
 static void __wakeup_reset(struct trace_array *tr);
+static int wakeup_graph_entry(struct ftrace_graph_ent *trace);
+static void wakeup_graph_return(struct ftrace_graph_ret *trace);
 
 static int save_lat_flag;
 
+#define TRACE_DISPLAY_GRAPH     1
+
+static struct tracer_opt trace_opts[] = {
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+        /* display latency trace as call graph */
+        { TRACER_OPT(display-graph, TRACE_DISPLAY_GRAPH) },
+#endif
+        { } /* Empty entry */
+};
+
+static struct tracer_flags tracer_flags = {
+        .val  = 0,
+        .opts = trace_opts,
+};
+
+#define is_graph() (tracer_flags.val & TRACE_DISPLAY_GRAPH)
+
 #ifdef CONFIG_FUNCTION_TRACER
+
 /*
- * irqsoff uses its own tracer function to keep the overhead down:
+ * Prologue for the wakeup function tracers.
+ *
+ * Returns 1 if it is OK to continue, and preemption
+ *            is disabled and data->disabled is incremented.
+ *         0 if the trace is to be ignored, and preemption
+ *            is not disabled and data->disabled is
+ *            kept the same.
+ *
+ * Note, this function is also used outside this ifdef but
+ *  inside the #ifdef of the function graph tracer below.
+ *  This is OK, since the function graph tracer is
+ *  dependent on the function tracer.
  */
-static void
-wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
+static int
+func_prolog_preempt_disable(struct trace_array *tr,
+                            struct trace_array_cpu **data,
+                            int *pc)
 {
-        struct trace_array *tr = wakeup_trace;
-        struct trace_array_cpu *data;
-        unsigned long flags;
         long disabled;
         int cpu;
-        int pc;
 
         if (likely(!wakeup_task))
-                return;
+                return 0;
 
-        pc = preempt_count();
+        *pc = preempt_count();
         preempt_disable_notrace();
 
         cpu = raw_smp_processor_id();
         if (cpu != wakeup_current_cpu)
                 goto out_enable;
 
-        data = tr->data[cpu];
-        disabled = atomic_inc_return(&data->disabled);
+        *data = tr->data[cpu];
+        disabled = atomic_inc_return(&(*data)->disabled);
         if (unlikely(disabled != 1))
                 goto out;
 
-        local_irq_save(flags);
+        return 1;
 
-        trace_function(tr, ip, parent_ip, flags, pc);
+out:
+        atomic_dec(&(*data)->disabled);
+
+out_enable:
+        preempt_enable_notrace();
+        return 0;
+}
 
+/*
+ * wakeup uses its own tracer function to keep the overhead down:
+ */
+static void
+wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
+{
+        struct trace_array *tr = wakeup_trace;
+        struct trace_array_cpu *data;
+        unsigned long flags;
+        int pc;
+
+        if (!func_prolog_preempt_disable(tr, &data, &pc))
+                return;
+
+        local_irq_save(flags);
+        trace_function(tr, ip, parent_ip, flags, pc);
         local_irq_restore(flags);
 
- out:
         atomic_dec(&data->disabled);
- out_enable:
         preempt_enable_notrace();
 }
 
@@ -82,6 +132,156 @@ static struct ftrace_ops trace_ops __read_mostly =
 };
 #endif /* CONFIG_FUNCTION_TRACER */
 
+static int start_func_tracer(int graph)
+{
+        int ret;
+
+        if (!graph)
+                ret = register_ftrace_function(&trace_ops);
+        else
+                ret = register_ftrace_graph(&wakeup_graph_return,
+                                            &wakeup_graph_entry);
+
+        if (!ret && tracing_is_enabled())
+                tracer_enabled = 1;
+        else
+                tracer_enabled = 0;
+
+        return ret;
+}
+
+static void stop_func_tracer(int graph)
+{
+        tracer_enabled = 0;
+
+        if (!graph)
+                unregister_ftrace_function(&trace_ops);
+        else
+                unregister_ftrace_graph();
+}
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static int wakeup_set_flag(u32 old_flags, u32 bit, int set)
+{
+
+        if (!(bit & TRACE_DISPLAY_GRAPH))
+                return -EINVAL;
+
+        if (!(is_graph() ^ set))
+                return 0;
+
+        stop_func_tracer(!set);
+
+        wakeup_reset(wakeup_trace);
+        tracing_max_latency = 0;
+
+        return start_func_tracer(set);
+}
+
+static int wakeup_graph_entry(struct ftrace_graph_ent *trace)
+{
+        struct trace_array *tr = wakeup_trace;
+        struct trace_array_cpu *data;
+        unsigned long flags;
+        int pc, ret = 0;
+
+        if (!func_prolog_preempt_disable(tr, &data, &pc))
+                return 0;
+
+        local_save_flags(flags);
+        ret = __trace_graph_entry(tr, trace, flags, pc);
+        atomic_dec(&data->disabled);
+        preempt_enable_notrace();
+
+        return ret;
+}
+
+static void wakeup_graph_return(struct ftrace_graph_ret *trace)
+{
+        struct trace_array *tr = wakeup_trace;
+        struct trace_array_cpu *data;
+        unsigned long flags;
+        int pc;
+
+        if (!func_prolog_preempt_disable(tr, &data, &pc))
+                return;
+
+        local_save_flags(flags);
+        __trace_graph_return(tr, trace, flags, pc);
+        atomic_dec(&data->disabled);
+
+        preempt_enable_notrace();
+        return;
+}
+
+static void wakeup_trace_open(struct trace_iterator *iter)
+{
+        if (is_graph())
+                graph_trace_open(iter);
+}
+
+static void wakeup_trace_close(struct trace_iterator *iter)
+{
+        if (iter->private)
+                graph_trace_close(iter);
+}
+
+#define GRAPH_TRACER_FLAGS (TRACE_GRAPH_PRINT_PROC)
+
+static enum print_line_t wakeup_print_line(struct trace_iterator *iter)
+{
+        /*
+         * In graph mode call the graph tracer output function,
+         * otherwise go with the TRACE_FN event handler
+         */
+        if (is_graph())
+                return print_graph_function_flags(iter, GRAPH_TRACER_FLAGS);
+
+        return TRACE_TYPE_UNHANDLED;
+}
+
+static void wakeup_print_header(struct seq_file *s)
+{
+        if (is_graph())
+                print_graph_headers_flags(s, GRAPH_TRACER_FLAGS);
+        else
+                trace_default_header(s);
+}
+
+static void
+__trace_function(struct trace_array *tr,
+                 unsigned long ip, unsigned long parent_ip,
+                 unsigned long flags, int pc)
+{
+        if (is_graph())
+                trace_graph_function(tr, ip, parent_ip, flags, pc);
+        else
+                trace_function(tr, ip, parent_ip, flags, pc);
+}
+#else
+#define __trace_function trace_function
+
+static int wakeup_set_flag(u32 old_flags, u32 bit, int set)
+{
+        return -EINVAL;
+}
+
+static int wakeup_graph_entry(struct ftrace_graph_ent *trace)
+{
+        return -1;
+}
+
+static enum print_line_t wakeup_print_line(struct trace_iterator *iter)
+{
+        return TRACE_TYPE_UNHANDLED;
+}
+
+static void wakeup_graph_return(struct ftrace_graph_ret *trace) { }
+static void wakeup_print_header(struct seq_file *s) { }
+static void wakeup_trace_open(struct trace_iterator *iter) { }
+static void wakeup_trace_close(struct trace_iterator *iter) { }
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
 /*
  * Should this new latency be reported/recorded?
  */
@@ -152,7 +352,7 @@ probe_wakeup_sched_switch(void *ignore,
         /* The task we are waiting for is waking up */
         data = wakeup_trace->data[wakeup_cpu];
 
-        trace_function(wakeup_trace, CALLER_ADDR0, CALLER_ADDR1, flags, pc);
+        __trace_function(wakeup_trace, CALLER_ADDR0, CALLER_ADDR1, flags, pc);
         tracing_sched_switch_trace(wakeup_trace, prev, next, flags, pc);
 
         T0 = data->preempt_timestamp;
@@ -252,7 +452,7 @@ probe_wakeup(void *ignore, struct task_struct *p, int success)
          * is not called by an assembly function  (where as schedule is)
          * it should be safe to use it here.
          */
-        trace_function(wakeup_trace, CALLER_ADDR1, CALLER_ADDR2, flags, pc);
+        __trace_function(wakeup_trace, CALLER_ADDR1, CALLER_ADDR2, flags, pc);
 
 out_locked:
         arch_spin_unlock(&wakeup_lock);
@@ -303,12 +503,8 @@ static void start_wakeup_tracer(struct trace_array *tr)
          */
         smp_wmb();
 
-        register_ftrace_function(&trace_ops);
-
-        if (tracing_is_enabled())
-                tracer_enabled = 1;
-        else
-                tracer_enabled = 0;
+        if (start_func_tracer(is_graph()))
+                printk(KERN_ERR "failed to start wakeup tracer\n");
 
         return;
 fail_deprobe_wake_new:
@@ -320,7 +516,7 @@ fail_deprobe:
 static void stop_wakeup_tracer(struct trace_array *tr)
 {
         tracer_enabled = 0;
-        unregister_ftrace_function(&trace_ops);
+        stop_func_tracer(is_graph());
         unregister_trace_sched_switch(probe_wakeup_sched_switch, NULL);
         unregister_trace_sched_wakeup_new(probe_wakeup, NULL);
         unregister_trace_sched_wakeup(probe_wakeup, NULL);
@@ -379,9 +575,15 @@ static struct tracer wakeup_tracer __read_mostly =
         .start          = wakeup_tracer_start,
         .stop           = wakeup_tracer_stop,
         .print_max      = 1,
+        .print_header   = wakeup_print_header,
+        .print_line     = wakeup_print_line,
+        .flags          = &tracer_flags,
+        .set_flag       = wakeup_set_flag,
 #ifdef CONFIG_FTRACE_SELFTEST
         .selftest    = trace_selftest_startup_wakeup,
 #endif
+        .open           = wakeup_trace_open,
+        .close          = wakeup_trace_close,
         .use_max_tr     = 1,
 };
 
@@ -394,9 +596,15 @@ static struct tracer wakeup_rt_tracer __read_mostly =
         .stop           = wakeup_tracer_stop,
         .wait_pipe      = poll_wait_pipe,
         .print_max      = 1,
+        .print_header   = wakeup_print_header,
+        .print_line     = wakeup_print_line,
+        .flags          = &tracer_flags,
+        .set_flag       = wakeup_set_flag,
 #ifdef CONFIG_FTRACE_SELFTEST
         .selftest    = trace_selftest_startup_wakeup,
 #endif
+        .open           = wakeup_trace_open,
+        .close          = wakeup_trace_close,
         .use_max_tr     = 1,
 };
 
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index dc8e16824b51..bafba687a6d8 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -196,7 +196,7 @@ static struct perf_event_attr wd_hw_attr = {
 };
 
 /* Callback function for perf event subsystem */
-void watchdog_overflow_callback(struct perf_event *event, int nmi,
+static void watchdog_overflow_callback(struct perf_event *event, int nmi,
                  struct perf_sample_data *data,
                  struct pt_regs *regs)
 {
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index e85d549b6eac..21ac83070a80 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -540,6 +540,23 @@ config PROVE_RCU_REPEATEDLY
          disabling, allowing multiple RCU-lockdep warnings to be printed
          on a single reboot.
 
+         Say Y to allow multiple RCU-lockdep warnings per boot.
+
+         Say N if you are unsure.
+
+config SPARSE_RCU_POINTER
+        bool "RCU debugging: sparse-based checks for pointer usage"
+        default n
+        help
+         This feature enables the __rcu sparse annotation for
+         RCU-protected pointers.  This annotation will cause sparse
+         to flag any non-RCU used of annotated pointers.  This can be
+         helpful when debugging RCU usage.  Please note that this feature
+         is not intended to enforce code cleanliness; it is instead merely
+         a debugging aid.
+
+         Say Y to make sparse flag questionable use of RCU-protected pointers
+
          Say N if you are unsure.
 
 config LOCKDEP
@@ -832,6 +849,30 @@ config RCU_CPU_STALL_DETECTOR
 
           Say Y if you are unsure.
 
+config RCU_CPU_STALL_TIMEOUT
+        int "RCU CPU stall timeout in seconds"
+        depends on RCU_CPU_STALL_DETECTOR
+        range 3 300
+        default 60
+        help
+          If a given RCU grace period extends more than the specified
+          number of seconds, a CPU stall warning is printed.  If the
+          RCU grace period persists, additional CPU stall warnings are
+          printed at more widely spaced intervals.
+
+config RCU_CPU_STALL_DETECTOR_RUNNABLE
+        bool "RCU CPU stall checking starts automatically at boot"
+        depends on RCU_CPU_STALL_DETECTOR
+        default y
+        help
+          If set, start checking for RCU CPU stalls immediately on
+          boot.  Otherwise, RCU CPU stall checking must be manually
+          enabled.
+
+          Say Y if you are unsure.
+
+          Say N if you wish to suppress RCU CPU stall checking during boot.
+
 config RCU_CPU_STALL_VERBOSE
         bool "Print additional per-task information for RCU_CPU_STALL_DETECTOR"
         depends on RCU_CPU_STALL_DETECTOR && TREE_PREEMPT_RCU
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index efd16fa80b1c..6f412ab4c24f 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -49,7 +49,7 @@ struct radix_tree_node {
         unsigned int    height;         /* Height from the bottom */
         unsigned int    count;
         struct rcu_head rcu_head;
-        void            *slots[RADIX_TREE_MAP_SIZE];
+        void __rcu      *slots[RADIX_TREE_MAP_SIZE];
         unsigned long   tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS];
 };
 
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 34e3082632d8..7c06ee51a29a 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -70,7 +70,7 @@ static unsigned long io_tlb_nslabs;
  */
 static unsigned long io_tlb_overflow = 32*1024;
 
-void *io_tlb_overflow_buffer;
+static void *io_tlb_overflow_buffer;
 
 /*
  * This is a free list describing the number of free entries available from
@@ -147,16 +147,16 @@ void __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
          * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE
          * between io_tlb_start and io_tlb_end.
          */
-        io_tlb_list = alloc_bootmem(io_tlb_nslabs * sizeof(int));
+        io_tlb_list = alloc_bootmem_pages(PAGE_ALIGN(io_tlb_nslabs * sizeof(int)));
         for (i = 0; i < io_tlb_nslabs; i++)
                 io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
         io_tlb_index = 0;
-        io_tlb_orig_addr = alloc_bootmem(io_tlb_nslabs * sizeof(phys_addr_t));
+        io_tlb_orig_addr = alloc_bootmem_pages(PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t)));
 
         /*
          * Get the overflow emergency buffer
          */
-        io_tlb_overflow_buffer = alloc_bootmem_low(io_tlb_overflow);
+        io_tlb_overflow_buffer = alloc_bootmem_low_pages(PAGE_ALIGN(io_tlb_overflow));
         if (!io_tlb_overflow_buffer)
                 panic("Cannot allocate SWIOTLB overflow buffer!\n");
         if (verbose)
@@ -182,7 +182,7 @@ swiotlb_init_with_default_size(size_t default_size, int verbose)
         /*
          * Get IO TLB memory from the low pages
          */
-        io_tlb_start = alloc_bootmem_low_pages(bytes);
+        io_tlb_start = alloc_bootmem_low_pages(PAGE_ALIGN(bytes));
         if (!io_tlb_start)
                 panic("Cannot allocate SWIOTLB buffer");
 
@@ -308,13 +308,13 @@ void __init swiotlb_free(void)
                            get_order(io_tlb_nslabs << IO_TLB_SHIFT));
         } else {
                 free_bootmem_late(__pa(io_tlb_overflow_buffer),
-                                  io_tlb_overflow);
+                                  PAGE_ALIGN(io_tlb_overflow));
                 free_bootmem_late(__pa(io_tlb_orig_addr),
-                                  io_tlb_nslabs * sizeof(phys_addr_t));
+                                  PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t)));
                 free_bootmem_late(__pa(io_tlb_list),
-                                  io_tlb_nslabs * sizeof(int));
+                                  PAGE_ALIGN(io_tlb_nslabs * sizeof(int)));
                 free_bootmem_late(__pa(io_tlb_start),
-                                  io_tlb_nslabs << IO_TLB_SHIFT);
+                                  PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
         }
 }
 
diff --git a/mm/memory.c b/mm/memory.c
index 0e18b4d649ec..98b58fecedef 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3185,7 +3185,7 @@ static inline int handle_pte_fault(struct mm_struct *mm,
                  * with threads.
                  */
                 if (flags & FAULT_FLAG_WRITE)
-                        flush_tlb_page(vma, address);
+                        flush_tlb_fix_spurious_fault(vma, address);
         }
 unlock:
         pte_unmap_unlock(pte, ptl);
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 6b8889da69a6..d8087f0db507 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -517,6 +517,15 @@ static atomic_t vmap_lazy_nr = ATOMIC_INIT(0);
 static void purge_fragmented_blocks_allcpus(void);
 
 /*
+ * called before a call to iounmap() if the caller wants vm_area_struct's
+ * immediately freed.
+ */
+void set_iounmap_nonlazy(void)
+{
+        atomic_set(&vmap_lazy_nr, lazy_max_pages()+1);
+}
+
+/*
  * Purges all lazily-freed vmap areas.
  *
  * If sync is 0 then don't purge if there is already a purge in progress.
diff --git a/net/Kconfig b/net/Kconfig
index e926884c1675..55fd82e9ffd9 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -293,6 +293,7 @@ source "net/wimax/Kconfig"
 source "net/rfkill/Kconfig"
 source "net/9p/Kconfig"
 source "net/caif/Kconfig"
+source "net/ceph/Kconfig"
 
 
 endif   # if NET
diff --git a/net/Makefile b/net/Makefile
index ea60fbce9b1b..6b7bfd7f1416 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -68,3 +68,4 @@ obj-$(CONFIG_SYSCTL)		+= sysctl_net.o
 endif
 obj-$(CONFIG_WIMAX)             += wimax/
 obj-$(CONFIG_DNS_RESOLVER)      += dns_resolver/
+obj-$(CONFIG_CEPH_LIB)          += ceph/
diff --git a/net/ceph/Kconfig b/net/ceph/Kconfig
new file mode 100644
index 000000000000..ad424049b0cf
--- /dev/null
+++ b/net/ceph/Kconfig
@@ -0,0 +1,28 @@
+config CEPH_LIB
+        tristate "Ceph core library (EXPERIMENTAL)"
+        depends on INET && EXPERIMENTAL
+        select LIBCRC32C
+        select CRYPTO_AES
+        select CRYPTO
+        default n
+        help
+          Choose Y or M here to include cephlib, which provides the
+          common functionality to both the Ceph filesystem and
+          to the rados block device (rbd).
+
+          More information at http://ceph.newdream.net/.
+
+          If unsure, say N.
+
+config CEPH_LIB_PRETTYDEBUG
+        bool "Include file:line in ceph debug output"
+        depends on CEPH_LIB
+        default n
+        help
+          If you say Y here, debug output will include a filename and
+          line to aid debugging.  This increases kernel size and slows
+          execution slightly when debug call sites are enabled (e.g.,
+          via CONFIG_DYNAMIC_DEBUG).
+
+          If unsure, say N.
+
diff --git a/net/ceph/Makefile b/net/ceph/Makefile
new file mode 100644
index 000000000000..aab1cabb8035
--- /dev/null
+++ b/net/ceph/Makefile
@@ -0,0 +1,37 @@
+#
+# Makefile for CEPH filesystem.
+#
+
+ifneq ($(KERNELRELEASE),)
+
+obj-$(CONFIG_CEPH_LIB) += libceph.o
+
+libceph-objs := ceph_common.o messenger.o msgpool.o buffer.o pagelist.o \
+        mon_client.o \
+        osd_client.o osdmap.o crush/crush.o crush/mapper.o crush/hash.o \
+        debugfs.o \
+        auth.o auth_none.o \
+        crypto.o armor.o \
+        auth_x.o \
+        ceph_fs.o ceph_strings.o ceph_hash.o \
+        pagevec.o
+
+else
+#Otherwise we were called directly from the command
+# line; invoke the kernel build system.
+
+KERNELDIR ?= /lib/modules/$(shell uname -r)/build
+PWD := $(shell pwd)
+
+default: all
+
+all:
+        $(MAKE) -C $(KERNELDIR) M=$(PWD) CONFIG_CEPH_LIB=m modules
+
+modules_install:
+        $(MAKE) -C $(KERNELDIR) M=$(PWD) CONFIG_CEPH_LIB=m modules_install
+
+clean:
+        $(MAKE) -C $(KERNELDIR) M=$(PWD) clean
+
+endif
diff --git a/fs/ceph/armor.c b/net/ceph/armor.c
index eb2a666b0be7..eb2a666b0be7 100644
--- a/fs/ceph/armor.c
+++ b/net/ceph/armor.c
diff --git a/fs/ceph/auth.c b/net/ceph/auth.c
index 6d2e30600627..549c1f43e1d5 100644
--- a/fs/ceph/auth.c
+++ b/net/ceph/auth.c
@@ -1,16 +1,16 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/module.h>
 #include <linux/err.h>
 #include <linux/slab.h>
 
-#include "types.h"
+#include <linux/ceph/types.h>
+#include <linux/ceph/decode.h>
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/messenger.h>
 #include "auth_none.h"
 #include "auth_x.h"
-#include "decode.h"
-#include "super.h"
 
-#include "messenger.h"
 
 /*
  * get protocol handler
diff --git a/fs/ceph/auth_none.c b/net/ceph/auth_none.c
index ad1dc21286c7..214c2bb43d62 100644
--- a/fs/ceph/auth_none.c
+++ b/net/ceph/auth_none.c
@@ -1,14 +1,15 @@
 
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/random.h>
 #include <linux/slab.h>
 
+#include <linux/ceph/decode.h>
+#include <linux/ceph/auth.h>
+
 #include "auth_none.h"
-#include "auth.h"
-#include "decode.h"
 
 static void reset(struct ceph_auth_client *ac)
 {
diff --git a/fs/ceph/auth_none.h b/net/ceph/auth_none.h
index 8164df1a08be..ed7d088b1bc9 100644
--- a/fs/ceph/auth_none.h
+++ b/net/ceph/auth_none.h
@@ -2,8 +2,7 @@
 #define _FS_CEPH_AUTH_NONE_H
 
 #include <linux/slab.h>
-
-#include "auth.h"
+#include <linux/ceph/auth.h>
 
 /*
  * null security mode.
diff --git a/fs/ceph/auth_x.c b/net/ceph/auth_x.c
index a2d002cbdec2..7fd5dfcf6e18 100644
--- a/fs/ceph/auth_x.c
+++ b/net/ceph/auth_x.c
@@ -1,16 +1,17 @@
 
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/random.h>
 #include <linux/slab.h>
 
+#include <linux/ceph/decode.h>
+#include <linux/ceph/auth.h>
+
+#include "crypto.h"
 #include "auth_x.h"
 #include "auth_x_protocol.h"
-#include "crypto.h"
-#include "auth.h"
-#include "decode.h"
 
 #define TEMP_TICKET_BUF_LEN     256
 
diff --git a/fs/ceph/auth_x.h b/net/ceph/auth_x.h
index ff6f8180e681..e02da7a5c5a1 100644
--- a/fs/ceph/auth_x.h
+++ b/net/ceph/auth_x.h
@@ -3,8 +3,9 @@
 
 #include <linux/rbtree.h>
 
+#include <linux/ceph/auth.h>
+
 #include "crypto.h"
-#include "auth.h"
 #include "auth_x_protocol.h"
 
 /*
diff --git a/fs/ceph/auth_x_protocol.h b/net/ceph/auth_x_protocol.h
index 671d30576c4f..671d30576c4f 100644
--- a/fs/ceph/auth_x_protocol.h
+++ b/net/ceph/auth_x_protocol.h
diff --git a/fs/ceph/buffer.c b/net/ceph/buffer.c
index cd39f17021de..53d8abfa25d5 100644
--- a/fs/ceph/buffer.c
+++ b/net/ceph/buffer.c
@@ -1,10 +1,11 @@
 
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
+#include <linux/module.h>
 #include <linux/slab.h>
 
-#include "buffer.h"
-#include "decode.h"
+#include <linux/ceph/buffer.h>
+#include <linux/ceph/decode.h>
 
 struct ceph_buffer *ceph_buffer_new(size_t len, gfp_t gfp)
 {
@@ -32,6 +33,7 @@ struct ceph_buffer *ceph_buffer_new(size_t len, gfp_t gfp)
         dout("buffer_new %p\n", b);
         return b;
 }
+EXPORT_SYMBOL(ceph_buffer_new);
 
 void ceph_buffer_release(struct kref *kref)
 {
@@ -46,6 +48,7 @@ void ceph_buffer_release(struct kref *kref)
         }
         kfree(b);
 }
+EXPORT_SYMBOL(ceph_buffer_release);
 
 int ceph_decode_buffer(struct ceph_buffer **b, void **p, void *end)
 {
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
new file mode 100644
index 000000000000..f3e4a13fea0c
--- /dev/null
+++ b/net/ceph/ceph_common.c
@@ -0,0 +1,529 @@
+
+#include <linux/ceph/ceph_debug.h>
+#include <linux/backing-dev.h>
+#include <linux/ctype.h>
+#include <linux/fs.h>
+#include <linux/inet.h>
+#include <linux/in6.h>
+#include <linux/module.h>
+#include <linux/mount.h>
+#include <linux/parser.h>
+#include <linux/sched.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/statfs.h>
+#include <linux/string.h>
+
+
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/debugfs.h>
+#include <linux/ceph/decode.h>
+#include <linux/ceph/mon_client.h>
+#include <linux/ceph/auth.h>
+
+
+
+/*
+ * find filename portion of a path (/foo/bar/baz -> baz)
+ */
+const char *ceph_file_part(const char *s, int len)
+{
+        const char *e = s + len;
+
+        while (e != s && *(e-1) != '/')
+                e--;
+        return e;
+}
+EXPORT_SYMBOL(ceph_file_part);
+
+const char *ceph_msg_type_name(int type)
+{
+        switch (type) {
+        case CEPH_MSG_SHUTDOWN: return "shutdown";
+        case CEPH_MSG_PING: return "ping";
+        case CEPH_MSG_AUTH: return "auth";
+        case CEPH_MSG_AUTH_REPLY: return "auth_reply";
+        case CEPH_MSG_MON_MAP: return "mon_map";
+        case CEPH_MSG_MON_GET_MAP: return "mon_get_map";
+        case CEPH_MSG_MON_SUBSCRIBE: return "mon_subscribe";
+        case CEPH_MSG_MON_SUBSCRIBE_ACK: return "mon_subscribe_ack";
+        case CEPH_MSG_STATFS: return "statfs";
+        case CEPH_MSG_STATFS_REPLY: return "statfs_reply";
+        case CEPH_MSG_MDS_MAP: return "mds_map";
+        case CEPH_MSG_CLIENT_SESSION: return "client_session";
+        case CEPH_MSG_CLIENT_RECONNECT: return "client_reconnect";
+        case CEPH_MSG_CLIENT_REQUEST: return "client_request";
+        case CEPH_MSG_CLIENT_REQUEST_FORWARD: return "client_request_forward";
+        case CEPH_MSG_CLIENT_REPLY: return "client_reply";
+        case CEPH_MSG_CLIENT_CAPS: return "client_caps";
+        case CEPH_MSG_CLIENT_CAPRELEASE: return "client_cap_release";
+        case CEPH_MSG_CLIENT_SNAP: return "client_snap";
+        case CEPH_MSG_CLIENT_LEASE: return "client_lease";
+        case CEPH_MSG_OSD_MAP: return "osd_map";
+        case CEPH_MSG_OSD_OP: return "osd_op";
+        case CEPH_MSG_OSD_OPREPLY: return "osd_opreply";
+        default: return "unknown";
+        }
+}
+EXPORT_SYMBOL(ceph_msg_type_name);
+
+/*
+ * Initially learn our fsid, or verify an fsid matches.
+ */
+int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid)
+{
+        if (client->have_fsid) {
+                if (ceph_fsid_compare(&client->fsid, fsid)) {
+                        pr_err("bad fsid, had %pU got %pU",
+                               &client->fsid, fsid);
+                        return -1;
+                }
+        } else {
+                pr_info("client%lld fsid %pU\n", ceph_client_id(client), fsid);
+                memcpy(&client->fsid, fsid, sizeof(*fsid));
+                ceph_debugfs_client_init(client);
+                client->have_fsid = true;
+        }
+        return 0;
+}
+EXPORT_SYMBOL(ceph_check_fsid);
+
+static int strcmp_null(const char *s1, const char *s2)
+{
+        if (!s1 && !s2)
+                return 0;
+        if (s1 && !s2)
+                return -1;
+        if (!s1 && s2)
+                return 1;
+        return strcmp(s1, s2);
+}
+
+int ceph_compare_options(struct ceph_options *new_opt,
+                         struct ceph_client *client)
+{
+        struct ceph_options *opt1 = new_opt;
+        struct ceph_options *opt2 = client->options;
+        int ofs = offsetof(struct ceph_options, mon_addr);
+        int i;
+        int ret;
+
+        ret = memcmp(opt1, opt2, ofs);
+        if (ret)
+                return ret;
+
+        ret = strcmp_null(opt1->name, opt2->name);
+        if (ret)
+                return ret;
+
+        ret = strcmp_null(opt1->secret, opt2->secret);
+        if (ret)
+                return ret;
+
+        /* any matching mon ip implies a match */
+        for (i = 0; i < opt1->num_mon; i++) {
+                if (ceph_monmap_contains(client->monc.monmap,
+                                 &opt1->mon_addr[i]))
+                        return 0;
+        }
+        return -1;
+}
+EXPORT_SYMBOL(ceph_compare_options);
+
+
+static int parse_fsid(const char *str, struct ceph_fsid *fsid)
+{
+        int i = 0;
+        char tmp[3];
+        int err = -EINVAL;
+        int d;
+
+        dout("parse_fsid '%s'\n", str);
+        tmp[2] = 0;
+        while (*str && i < 16) {
+                if (ispunct(*str)) {
+                        str++;
+                        continue;
+                }
+                if (!isxdigit(str[0]) || !isxdigit(str[1]))
+                        break;
+                tmp[0] = str[0];
+                tmp[1] = str[1];
+                if (sscanf(tmp, "%x", &d) < 1)
+                        break;
+                fsid->fsid[i] = d & 0xff;
+                i++;
+                str += 2;
+        }
+
+        if (i == 16)
+                err = 0;
+        dout("parse_fsid ret %d got fsid %pU", err, fsid);
+        return err;
+}
+
+/*
+ * ceph options
+ */
+enum {
+        Opt_osdtimeout,
+        Opt_osdkeepalivetimeout,
+        Opt_mount_timeout,
+        Opt_osd_idle_ttl,
+        Opt_last_int,
+        /* int args above */
+        Opt_fsid,
+        Opt_name,
+        Opt_secret,
+        Opt_ip,
+        Opt_last_string,
+        /* string args above */
+        Opt_noshare,
+        Opt_nocrc,
+};
+
+static match_table_t opt_tokens = {
+        {Opt_osdtimeout, "osdtimeout=%d"},
+        {Opt_osdkeepalivetimeout, "osdkeepalive=%d"},
+        {Opt_mount_timeout, "mount_timeout=%d"},
+        {Opt_osd_idle_ttl, "osd_idle_ttl=%d"},
+        /* int args above */
+        {Opt_fsid, "fsid=%s"},
+        {Opt_name, "name=%s"},
+        {Opt_secret, "secret=%s"},
+        {Opt_ip, "ip=%s"},
+        /* string args above */
+        {Opt_noshare, "noshare"},
+        {Opt_nocrc, "nocrc"},
+        {-1, NULL}
+};
+
+void ceph_destroy_options(struct ceph_options *opt)
+{
+        dout("destroy_options %p\n", opt);
+        kfree(opt->name);
+        kfree(opt->secret);
+        kfree(opt);
+}
+EXPORT_SYMBOL(ceph_destroy_options);
+
+int ceph_parse_options(struct ceph_options **popt, char *options,
+                       const char *dev_name, const char *dev_name_end,
+                       int (*parse_extra_token)(char *c, void *private),
+                       void *private)
+{
+        struct ceph_options *opt;
+        const char *c;
+        int err = -ENOMEM;
+        substring_t argstr[MAX_OPT_ARGS];
+
+        opt = kzalloc(sizeof(*opt), GFP_KERNEL);
+        if (!opt)
+                return err;
+        opt->mon_addr = kcalloc(CEPH_MAX_MON, sizeof(*opt->mon_addr),
+                                GFP_KERNEL);
+        if (!opt->mon_addr)
+                goto out;
+
+        dout("parse_options %p options '%s' dev_name '%s'\n", opt, options,
+             dev_name);
+
+        /* start with defaults */
+        opt->flags = CEPH_OPT_DEFAULT;
+        opt->osd_timeout = CEPH_OSD_TIMEOUT_DEFAULT;
+        opt->osd_keepalive_timeout = CEPH_OSD_KEEPALIVE_DEFAULT;
+        opt->mount_timeout = CEPH_MOUNT_TIMEOUT_DEFAULT; /* seconds */
+        opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT;   /* seconds */
+
+        /* get mon ip(s) */
+        /* ip1[:port1][,ip2[:port2]...] */
+        err = ceph_parse_ips(dev_name, dev_name_end, opt->mon_addr,
+                             CEPH_MAX_MON, &opt->num_mon);
+        if (err < 0)
+                goto out;
+
+        /* parse mount options */
+        while ((c = strsep(&options, ",")) != NULL) {
+                int token, intval, ret;
+                if (!*c)
+                        continue;
+                err = -EINVAL;
+                token = match_token((char *)c, opt_tokens, argstr);
+                if (token < 0 && parse_extra_token) {
+                        /* extra? */
+                        err = parse_extra_token((char *)c, private);
+                        if (err < 0) {
+                                pr_err("bad option at '%s'\n", c);
+                                goto out;
+                        }
+                        continue;
+                }
+                if (token < Opt_last_int) {
+                        ret = match_int(&argstr[0], &intval);
+                        if (ret < 0) {
+                                pr_err("bad mount option arg (not int) "
+                                       "at '%s'\n", c);
+                                continue;
+                        }
+                        dout("got int token %d val %d\n", token, intval);
+                } else if (token > Opt_last_int && token < Opt_last_string) {
+                        dout("got string token %d val %s\n", token,
+                             argstr[0].from);
+                } else {
+                        dout("got token %d\n", token);
+                }
+                switch (token) {
+                case Opt_ip:
+                        err = ceph_parse_ips(argstr[0].from,
+                                             argstr[0].to,
+                                             &opt->my_addr,
+                                             1, NULL);
+                        if (err < 0)
+                                goto out;
+                        opt->flags |= CEPH_OPT_MYIP;
+                        break;
+
+                case Opt_fsid:
+                        err = parse_fsid(argstr[0].from, &opt->fsid);
+                        if (err == 0)
+                                opt->flags |= CEPH_OPT_FSID;
+                        break;
+                case Opt_name:
+                        opt->name = kstrndup(argstr[0].from,
+                                              argstr[0].to-argstr[0].from,
+                                              GFP_KERNEL);
+                        break;
+                case Opt_secret:
+                        opt->secret = kstrndup(argstr[0].from,
+                                                argstr[0].to-argstr[0].from,
+                                                GFP_KERNEL);
+                        break;
+
+                        /* misc */
+                case Opt_osdtimeout:
+                        opt->osd_timeout = intval;
+                        break;
+                case Opt_osdkeepalivetimeout:
+                        opt->osd_keepalive_timeout = intval;
+                        break;
+                case Opt_osd_idle_ttl:
+                        opt->osd_idle_ttl = intval;
+                        break;
+                case Opt_mount_timeout:
+                        opt->mount_timeout = intval;
+                        break;
+
+                case Opt_noshare:
+                        opt->flags |= CEPH_OPT_NOSHARE;
+                        break;
+
+                case Opt_nocrc:
+                        opt->flags |= CEPH_OPT_NOCRC;
+                        break;
+
+                default:
+                        BUG_ON(token);
+                }
+        }
+
+        /* success */
+        *popt = opt;
+        return 0;
+
+out:
+        ceph_destroy_options(opt);
+        return err;
+}
+EXPORT_SYMBOL(ceph_parse_options);
+
+u64 ceph_client_id(struct ceph_client *client)
+{
+        return client->monc.auth->global_id;
+}
+EXPORT_SYMBOL(ceph_client_id);
+
+/*
+ * create a fresh client instance
+ */
+struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private)
+{
+        struct ceph_client *client;
+        int err = -ENOMEM;
+
+        client = kzalloc(sizeof(*client), GFP_KERNEL);
+        if (client == NULL)
+                return ERR_PTR(-ENOMEM);
+
+        client->private = private;
+        client->options = opt;
+
+        mutex_init(&client->mount_mutex);
+        init_waitqueue_head(&client->auth_wq);
+        client->auth_err = 0;
+
+        client->extra_mon_dispatch = NULL;
+        client->supported_features = CEPH_FEATURE_SUPPORTED_DEFAULT;
+        client->required_features = CEPH_FEATURE_REQUIRED_DEFAULT;
+
+        client->msgr = NULL;
+
+        /* subsystems */
+        err = ceph_monc_init(&client->monc, client);
+        if (err < 0)
+                goto fail;
+        err = ceph_osdc_init(&client->osdc, client);
+        if (err < 0)
+                goto fail_monc;
+
+        return client;
+
+fail_monc:
+        ceph_monc_stop(&client->monc);
+fail:
+        kfree(client);
+        return ERR_PTR(err);
+}
+EXPORT_SYMBOL(ceph_create_client);
+
+void ceph_destroy_client(struct ceph_client *client)
+{
+        dout("destroy_client %p\n", client);
+
+        /* unmount */
+        ceph_osdc_stop(&client->osdc);
+
+        /*
+         * make sure mds and osd connections close out before destroying
+         * the auth module, which is needed to free those connections'
+         * ceph_authorizers.
+         */
+        ceph_msgr_flush();
+
+        ceph_monc_stop(&client->monc);
+
+        ceph_debugfs_client_cleanup(client);
+
+        if (client->msgr)
+                ceph_messenger_destroy(client->msgr);
+
+        ceph_destroy_options(client->options);
+
+        kfree(client);
+        dout("destroy_client %p done\n", client);
+}
+EXPORT_SYMBOL(ceph_destroy_client);
+
+/*
+ * true if we have the mon map (and have thus joined the cluster)
+ */
+static int have_mon_and_osd_map(struct ceph_client *client)
+{
+        return client->monc.monmap && client->monc.monmap->epoch &&
+               client->osdc.osdmap && client->osdc.osdmap->epoch;
+}
+
+/*
+ * mount: join the ceph cluster, and open root directory.
+ */
+int __ceph_open_session(struct ceph_client *client, unsigned long started)
+{
+        struct ceph_entity_addr *myaddr = NULL;
+        int err;
+        unsigned long timeout = client->options->mount_timeout * HZ;
+
+        /* initialize the messenger */
+        if (client->msgr == NULL) {
+                if (ceph_test_opt(client, MYIP))
+                        myaddr = &client->options->my_addr;
+                client->msgr = ceph_messenger_create(myaddr,
+                                        client->supported_features,
+                                        client->required_features);
+                if (IS_ERR(client->msgr)) {
+                        client->msgr = NULL;
+                        return PTR_ERR(client->msgr);
+                }
+                client->msgr->nocrc = ceph_test_opt(client, NOCRC);
+        }
+
+        /* open session, and wait for mon and osd maps */
+        err = ceph_monc_open_session(&client->monc);
+        if (err < 0)
+                return err;
+
+        while (!have_mon_and_osd_map(client)) {
+                err = -EIO;
+                if (timeout && time_after_eq(jiffies, started + timeout))
+                        return err;
+
+                /* wait */
+                dout("mount waiting for mon_map\n");
+                err = wait_event_interruptible_timeout(client->auth_wq,
+                        have_mon_and_osd_map(client) || (client->auth_err < 0),
+                        timeout);
+                if (err == -EINTR || err == -ERESTARTSYS)
+                        return err;
+                if (client->auth_err < 0)
+                        return client->auth_err;
+        }
+
+        return 0;
+}
+EXPORT_SYMBOL(__ceph_open_session);
+
+
+int ceph_open_session(struct ceph_client *client)
+{
+        int ret;
+        unsigned long started = jiffies;  /* note the start time */
+
+        dout("open_session start\n");
+        mutex_lock(&client->mount_mutex);
+
+        ret = __ceph_open_session(client, started);
+
+        mutex_unlock(&client->mount_mutex);
+        return ret;
+}
+EXPORT_SYMBOL(ceph_open_session);
+
+
+static int __init init_ceph_lib(void)
+{
+        int ret = 0;
+
+        ret = ceph_debugfs_init();
+        if (ret < 0)
+                goto out;
+
+        ret = ceph_msgr_init();
+        if (ret < 0)
+                goto out_debugfs;
+
+        pr_info("loaded (mon/osd proto %d/%d, osdmap %d/%d %d/%d)\n",
+                CEPH_MONC_PROTOCOL, CEPH_OSDC_PROTOCOL,
+                CEPH_OSDMAP_VERSION, CEPH_OSDMAP_VERSION_EXT,
+                CEPH_OSDMAP_INC_VERSION, CEPH_OSDMAP_INC_VERSION_EXT);
+
+        return 0;
+
+out_debugfs:
+        ceph_debugfs_cleanup();
+out:
+        return ret;
+}
+
+static void __exit exit_ceph_lib(void)
+{
+        dout("exit_ceph_lib\n");
+        ceph_msgr_exit();
+        ceph_debugfs_cleanup();
+}
+
+module_init(init_ceph_lib);
+module_exit(exit_ceph_lib);
+
+MODULE_AUTHOR("Sage Weil <sage@newdream.net>");
+MODULE_AUTHOR("Yehuda Sadeh <yehuda@hq.newdream.net>");
+MODULE_AUTHOR("Patience Warnick <patience@newdream.net>");
+MODULE_DESCRIPTION("Ceph filesystem for Linux");
+MODULE_LICENSE("GPL");
diff --git a/fs/ceph/ceph_fs.c b/net/ceph/ceph_fs.c
index 3ac6cc7c1156..a3a3a31d3c37 100644
--- a/fs/ceph/ceph_fs.c
+++ b/net/ceph/ceph_fs.c
@@ -1,7 +1,8 @@
 /*
  * Some non-inline ceph helpers
  */
-#include "types.h"
+#include <linux/module.h>
+#include <linux/ceph/types.h>
 
 /*
  * return true if @layout appears to be valid
@@ -52,6 +53,7 @@ int ceph_flags_to_mode(int flags)
 
         return mode;
 }
+EXPORT_SYMBOL(ceph_flags_to_mode);
 
 int ceph_caps_for_mode(int mode)
 {
@@ -70,3 +72,4 @@ int ceph_caps_for_mode(int mode)
 
         return caps;
 }
+EXPORT_SYMBOL(ceph_caps_for_mode);
diff --git a/fs/ceph/ceph_hash.c b/net/ceph/ceph_hash.c
index bd570015d147..815ef8826796 100644
--- a/fs/ceph/ceph_hash.c
+++ b/net/ceph/ceph_hash.c
@@ -1,5 +1,5 @@
 
-#include "types.h"
+#include <linux/ceph/types.h>
 
 /*
  * Robert Jenkin's hash function.
diff --git a/net/ceph/ceph_strings.c b/net/ceph/ceph_strings.c
new file mode 100644
index 000000000000..3fbda04de29c
--- /dev/null
+++ b/net/ceph/ceph_strings.c
@@ -0,0 +1,84 @@
+/*
+ * Ceph string constants
+ */
+#include <linux/module.h>
+#include <linux/ceph/types.h>
+
+const char *ceph_entity_type_name(int type)
+{
+        switch (type) {
+        case CEPH_ENTITY_TYPE_MDS: return "mds";
+        case CEPH_ENTITY_TYPE_OSD: return "osd";
+        case CEPH_ENTITY_TYPE_MON: return "mon";
+        case CEPH_ENTITY_TYPE_CLIENT: return "client";
+        case CEPH_ENTITY_TYPE_AUTH: return "auth";
+        default: return "unknown";
+        }
+}
+
+const char *ceph_osd_op_name(int op)
+{
+        switch (op) {
+        case CEPH_OSD_OP_READ: return "read";
+        case CEPH_OSD_OP_STAT: return "stat";
+
+        case CEPH_OSD_OP_MASKTRUNC: return "masktrunc";
+
+        case CEPH_OSD_OP_WRITE: return "write";
+        case CEPH_OSD_OP_DELETE: return "delete";
+        case CEPH_OSD_OP_TRUNCATE: return "truncate";
+        case CEPH_OSD_OP_ZERO: return "zero";
+        case CEPH_OSD_OP_WRITEFULL: return "writefull";
+        case CEPH_OSD_OP_ROLLBACK: return "rollback";
+
+        case CEPH_OSD_OP_APPEND: return "append";
+        case CEPH_OSD_OP_STARTSYNC: return "startsync";
+        case CEPH_OSD_OP_SETTRUNC: return "settrunc";
+        case CEPH_OSD_OP_TRIMTRUNC: return "trimtrunc";
+
+        case CEPH_OSD_OP_TMAPUP: return "tmapup";
+        case CEPH_OSD_OP_TMAPGET: return "tmapget";
+        case CEPH_OSD_OP_TMAPPUT: return "tmapput";
+
+        case CEPH_OSD_OP_GETXATTR: return "getxattr";
+        case CEPH_OSD_OP_GETXATTRS: return "getxattrs";
+        case CEPH_OSD_OP_SETXATTR: return "setxattr";
+        case CEPH_OSD_OP_SETXATTRS: return "setxattrs";
+        case CEPH_OSD_OP_RESETXATTRS: return "resetxattrs";
+        case CEPH_OSD_OP_RMXATTR: return "rmxattr";
+        case CEPH_OSD_OP_CMPXATTR: return "cmpxattr";
+
+        case CEPH_OSD_OP_PULL: return "pull";
+        case CEPH_OSD_OP_PUSH: return "push";
+        case CEPH_OSD_OP_BALANCEREADS: return "balance-reads";
+        case CEPH_OSD_OP_UNBALANCEREADS: return "unbalance-reads";
+        case CEPH_OSD_OP_SCRUB: return "scrub";
+
+        case CEPH_OSD_OP_WRLOCK: return "wrlock";
+        case CEPH_OSD_OP_WRUNLOCK: return "wrunlock";
+        case CEPH_OSD_OP_RDLOCK: return "rdlock";
+        case CEPH_OSD_OP_RDUNLOCK: return "rdunlock";
+        case CEPH_OSD_OP_UPLOCK: return "uplock";
+        case CEPH_OSD_OP_DNLOCK: return "dnlock";
+
+        case CEPH_OSD_OP_CALL: return "call";
+
+        case CEPH_OSD_OP_PGLS: return "pgls";
+        }
+        return "???";
+}
+
+
+const char *ceph_pool_op_name(int op)
+{
+        switch (op) {
+        case POOL_OP_CREATE: return "create";
+        case POOL_OP_DELETE: return "delete";
+        case POOL_OP_AUID_CHANGE: return "auid change";
+        case POOL_OP_CREATE_SNAP: return "create snap";
+        case POOL_OP_DELETE_SNAP: return "delete snap";
+        case POOL_OP_CREATE_UNMANAGED_SNAP: return "create unmanaged snap";
+        case POOL_OP_DELETE_UNMANAGED_SNAP: return "delete unmanaged snap";
+        }
+        return "???";
+}
diff --git a/fs/ceph/crush/crush.c b/net/ceph/crush/crush.c
index fabd302e5779..d6ebb13a18a4 100644
--- a/fs/ceph/crush/crush.c
+++ b/net/ceph/crush/crush.c
@@ -8,7 +8,7 @@
 # define BUG_ON(x) assert(!(x))
 #endif
 
-#include "crush.h"
+#include <linux/crush/crush.h>
 
 const char *crush_bucket_alg_name(int alg)
 {
diff --git a/fs/ceph/crush/hash.c b/net/ceph/crush/hash.c
index 5873aed694bf..5bb63e37a8a1 100644
--- a/fs/ceph/crush/hash.c
+++ b/net/ceph/crush/hash.c
@@ -1,6 +1,6 @@
 
 #include <linux/types.h>
-#include "hash.h"
+#include <linux/crush/hash.h>
 
 /*
  * Robert Jenkins' function for mixing 32-bit values
diff --git a/fs/ceph/crush/mapper.c b/net/ceph/crush/mapper.c
index a4eec133258e..42599e31dcad 100644
--- a/fs/ceph/crush/mapper.c
+++ b/net/ceph/crush/mapper.c
@@ -18,8 +18,8 @@
 # define kfree(x) free(x)
 #endif
 
-#include "crush.h"
-#include "hash.h"
+#include <linux/crush/crush.h>
+#include <linux/crush/hash.h>
 
 /*
  * Implement the core CRUSH mapping algorithm.
diff --git a/fs/ceph/crypto.c b/net/ceph/crypto.c
index a3e627f63293..7b505b0c983f 100644
--- a/fs/ceph/crypto.c
+++ b/net/ceph/crypto.c
@@ -1,13 +1,13 @@
 
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/err.h>
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
 #include <crypto/hash.h>
 
+#include <linux/ceph/decode.h>
 #include "crypto.h"
-#include "decode.h"
 
 int ceph_crypto_key_encode(struct ceph_crypto_key *key, void **p, void *end)
 {
diff --git a/fs/ceph/crypto.h b/net/ceph/crypto.h
index bdf38607323c..f9eccace592b 100644
--- a/fs/ceph/crypto.h
+++ b/net/ceph/crypto.h
@@ -1,8 +1,8 @@
 #ifndef _FS_CEPH_CRYPTO_H
 #define _FS_CEPH_CRYPTO_H
 
-#include "types.h"
-#include "buffer.h"
+#include <linux/ceph/types.h>
+#include <linux/ceph/buffer.h>
 
 /*
  * cryptographic secret
diff --git a/net/ceph/debugfs.c b/net/ceph/debugfs.c
new file mode 100644
index 000000000000..27d4ea315d12
--- /dev/null
+++ b/net/ceph/debugfs.c
@@ -0,0 +1,267 @@
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/ctype.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/mon_client.h>
+#include <linux/ceph/auth.h>
+#include <linux/ceph/debugfs.h>
+
+#ifdef CONFIG_DEBUG_FS
+
+/*
+ * Implement /sys/kernel/debug/ceph fun
+ *
+ * /sys/kernel/debug/ceph/client*  - an instance of the ceph client
+ *      .../osdmap      - current osdmap
+ *      .../monmap      - current monmap
+ *      .../osdc        - active osd requests
+ *      .../monc        - mon client state
+ *      .../dentry_lru  - dump contents of dentry lru
+ *      .../caps        - expose cap (reservation) stats
+ *      .../bdi         - symlink to ../../bdi/something
+ */
+
+static struct dentry *ceph_debugfs_dir;
+
+static int monmap_show(struct seq_file *s, void *p)
+{
+        int i;
+        struct ceph_client *client = s->private;
+
+        if (client->monc.monmap == NULL)
+                return 0;
+
+        seq_printf(s, "epoch %d\n", client->monc.monmap->epoch);
+        for (i = 0; i < client->monc.monmap->num_mon; i++) {
+                struct ceph_entity_inst *inst =
+                        &client->monc.monmap->mon_inst[i];
+
+                seq_printf(s, "\t%s%lld\t%s\n",
+                           ENTITY_NAME(inst->name),
+                           ceph_pr_addr(&inst->addr.in_addr));
+        }
+        return 0;
+}
+
+static int osdmap_show(struct seq_file *s, void *p)
+{
+        int i;
+        struct ceph_client *client = s->private;
+        struct rb_node *n;
+
+        if (client->osdc.osdmap == NULL)
+                return 0;
+        seq_printf(s, "epoch %d\n", client->osdc.osdmap->epoch);
+        seq_printf(s, "flags%s%s\n",
+                   (client->osdc.osdmap->flags & CEPH_OSDMAP_NEARFULL) ?
+                   " NEARFULL" : "",
+                   (client->osdc.osdmap->flags & CEPH_OSDMAP_FULL) ?
+                   " FULL" : "");
+        for (n = rb_first(&client->osdc.osdmap->pg_pools); n; n = rb_next(n)) {
+                struct ceph_pg_pool_info *pool =
+                        rb_entry(n, struct ceph_pg_pool_info, node);
+                seq_printf(s, "pg_pool %d pg_num %d / %d, lpg_num %d / %d\n",
+                           pool->id, pool->v.pg_num, pool->pg_num_mask,
+                           pool->v.lpg_num, pool->lpg_num_mask);
+        }
+        for (i = 0; i < client->osdc.osdmap->max_osd; i++) {
+                struct ceph_entity_addr *addr =
+                        &client->osdc.osdmap->osd_addr[i];
+                int state = client->osdc.osdmap->osd_state[i];
+                char sb[64];
+
+                seq_printf(s, "\tosd%d\t%s\t%3d%%\t(%s)\n",
+                           i, ceph_pr_addr(&addr->in_addr),
+                           ((client->osdc.osdmap->osd_weight[i]*100) >> 16),
+                           ceph_osdmap_state_str(sb, sizeof(sb), state));
+        }
+        return 0;
+}
+
+static int monc_show(struct seq_file *s, void *p)
+{
+        struct ceph_client *client = s->private;
+        struct ceph_mon_generic_request *req;
+        struct ceph_mon_client *monc = &client->monc;
+        struct rb_node *rp;
+
+        mutex_lock(&monc->mutex);
+
+        if (monc->have_mdsmap)
+                seq_printf(s, "have mdsmap %u\n", (unsigned)monc->have_mdsmap);
+        if (monc->have_osdmap)
+                seq_printf(s, "have osdmap %u\n", (unsigned)monc->have_osdmap);
+        if (monc->want_next_osdmap)
+                seq_printf(s, "want next osdmap\n");
+
+        for (rp = rb_first(&monc->generic_request_tree); rp; rp = rb_next(rp)) {
+                __u16 op;
+                req = rb_entry(rp, struct ceph_mon_generic_request, node);
+                op = le16_to_cpu(req->request->hdr.type);
+                if (op == CEPH_MSG_STATFS)
+                        seq_printf(s, "%lld statfs\n", req->tid);
+                else
+                        seq_printf(s, "%lld unknown\n", req->tid);
+        }
+
+        mutex_unlock(&monc->mutex);
+        return 0;
+}
+
+static int osdc_show(struct seq_file *s, void *pp)
+{
+        struct ceph_client *client = s->private;
+        struct ceph_osd_client *osdc = &client->osdc;
+        struct rb_node *p;
+
+        mutex_lock(&osdc->request_mutex);
+        for (p = rb_first(&osdc->requests); p; p = rb_next(p)) {
+                struct ceph_osd_request *req;
+                struct ceph_osd_request_head *head;
+                struct ceph_osd_op *op;
+                int num_ops;
+                int opcode, olen;
+                int i;
+
+                req = rb_entry(p, struct ceph_osd_request, r_node);
+
+                seq_printf(s, "%lld\tosd%d\t%d.%x\t", req->r_tid,
+                           req->r_osd ? req->r_osd->o_osd : -1,
+                           le32_to_cpu(req->r_pgid.pool),
+                           le16_to_cpu(req->r_pgid.ps));
+
+                head = req->r_request->front.iov_base;
+                op = (void *)(head + 1);
+
+                num_ops = le16_to_cpu(head->num_ops);
+                olen = le32_to_cpu(head->object_len);
+                seq_printf(s, "%.*s", olen,
+                           (const char *)(head->ops + num_ops));
+
+                if (req->r_reassert_version.epoch)
+                        seq_printf(s, "\t%u'%llu",
+                           (unsigned)le32_to_cpu(req->r_reassert_version.epoch),
+                           le64_to_cpu(req->r_reassert_version.version));
+                else
+                        seq_printf(s, "\t");
+
+                for (i = 0; i < num_ops; i++) {
+                        opcode = le16_to_cpu(op->op);
+                        seq_printf(s, "\t%s", ceph_osd_op_name(opcode));
+                        op++;
+                }
+
+                seq_printf(s, "\n");
+        }
+        mutex_unlock(&osdc->request_mutex);
+        return 0;
+}
+
+CEPH_DEFINE_SHOW_FUNC(monmap_show)
+CEPH_DEFINE_SHOW_FUNC(osdmap_show)
+CEPH_DEFINE_SHOW_FUNC(monc_show)
+CEPH_DEFINE_SHOW_FUNC(osdc_show)
+
+int ceph_debugfs_init(void)
+{
+        ceph_debugfs_dir = debugfs_create_dir("ceph", NULL);
+        if (!ceph_debugfs_dir)
+                return -ENOMEM;
+        return 0;
+}
+
+void ceph_debugfs_cleanup(void)
+{
+        debugfs_remove(ceph_debugfs_dir);
+}
+
+int ceph_debugfs_client_init(struct ceph_client *client)
+{
+        int ret = -ENOMEM;
+        char name[80];
+
+        snprintf(name, sizeof(name), "%pU.client%lld", &client->fsid,
+                 client->monc.auth->global_id);
+
+        client->debugfs_dir = debugfs_create_dir(name, ceph_debugfs_dir);
+        if (!client->debugfs_dir)
+                goto out;
+
+        client->monc.debugfs_file = debugfs_create_file("monc",
+                                                      0600,
+                                                      client->debugfs_dir,
+                                                      client,
+                                                      &monc_show_fops);
+        if (!client->monc.debugfs_file)
+                goto out;
+
+        client->osdc.debugfs_file = debugfs_create_file("osdc",
+                                                      0600,
+                                                      client->debugfs_dir,
+                                                      client,
+                                                      &osdc_show_fops);
+        if (!client->osdc.debugfs_file)
+                goto out;
+
+        client->debugfs_monmap = debugfs_create_file("monmap",
+                                        0600,
+                                        client->debugfs_dir,
+                                        client,
+                                        &monmap_show_fops);
+        if (!client->debugfs_monmap)
+                goto out;
+
+        client->debugfs_osdmap = debugfs_create_file("osdmap",
+                                        0600,
+                                        client->debugfs_dir,
+                                        client,
+                                        &osdmap_show_fops);
+        if (!client->debugfs_osdmap)
+                goto out;
+
+        return 0;
+
+out:
+        ceph_debugfs_client_cleanup(client);
+        return ret;
+}
+
+void ceph_debugfs_client_cleanup(struct ceph_client *client)
+{
+        debugfs_remove(client->debugfs_osdmap);
+        debugfs_remove(client->debugfs_monmap);
+        debugfs_remove(client->osdc.debugfs_file);
+        debugfs_remove(client->monc.debugfs_file);
+        debugfs_remove(client->debugfs_dir);
+}
+
+#else  /* CONFIG_DEBUG_FS */
+
+int ceph_debugfs_init(void)
+{
+        return 0;
+}
+
+void ceph_debugfs_cleanup(void)
+{
+}
+
+int ceph_debugfs_client_init(struct ceph_client *client)
+{
+        return 0;
+}
+
+void ceph_debugfs_client_cleanup(struct ceph_client *client)
+{
+}
+
+#endif  /* CONFIG_DEBUG_FS */
+
+EXPORT_SYMBOL(ceph_debugfs_init);
+EXPORT_SYMBOL(ceph_debugfs_cleanup);
diff --git a/fs/ceph/messenger.c b/net/ceph/messenger.c
index 2502d76fcec1..0e8157ee5d43 100644
--- a/fs/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -1,4 +1,4 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/crc32c.h>
 #include <linux/ctype.h>
@@ -9,12 +9,14 @@
 #include <linux/slab.h>
 #include <linux/socket.h>
 #include <linux/string.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
 #include <net/tcp.h>
 
-#include "super.h"
-#include "messenger.h"
-#include "decode.h"
-#include "pagelist.h"
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/messenger.h>
+#include <linux/ceph/decode.h>
+#include <linux/ceph/pagelist.h>
 
 /*
  * Ceph uses the messenger to exchange ceph_msg messages with other
@@ -48,7 +50,7 @@ static char addr_str[MAX_ADDR_STR][MAX_ADDR_STR_LEN];
 static DEFINE_SPINLOCK(addr_str_lock);
 static int last_addr_str;
 
-const char *pr_addr(const struct sockaddr_storage *ss)
+const char *ceph_pr_addr(const struct sockaddr_storage *ss)
 {
         int i;
         char *s;
@@ -79,6 +81,7 @@ const char *pr_addr(const struct sockaddr_storage *ss)
 
         return s;
 }
+EXPORT_SYMBOL(ceph_pr_addr);
 
 static void encode_my_addr(struct ceph_messenger *msgr)
 {
@@ -91,7 +94,7 @@ static void encode_my_addr(struct ceph_messenger *msgr)
  */
 struct workqueue_struct *ceph_msgr_wq;
 
-int __init ceph_msgr_init(void)
+int ceph_msgr_init(void)
 {
         ceph_msgr_wq = create_workqueue("ceph-msgr");
         if (IS_ERR(ceph_msgr_wq)) {
@@ -102,16 +105,19 @@ int __init ceph_msgr_init(void)
         }
         return 0;
 }
+EXPORT_SYMBOL(ceph_msgr_init);
 
 void ceph_msgr_exit(void)
 {
         destroy_workqueue(ceph_msgr_wq);
 }
+EXPORT_SYMBOL(ceph_msgr_exit);
 
 void ceph_msgr_flush(void)
 {
         flush_workqueue(ceph_msgr_wq);
 }
+EXPORT_SYMBOL(ceph_msgr_flush);
 
 
 /*
@@ -221,19 +227,19 @@ static struct socket *ceph_tcp_connect(struct ceph_connection *con)
 
         set_sock_callbacks(sock, con);
 
-        dout("connect %s\n", pr_addr(&con->peer_addr.in_addr));
+        dout("connect %s\n", ceph_pr_addr(&con->peer_addr.in_addr));
 
         ret = sock->ops->connect(sock, (struct sockaddr *)paddr, sizeof(*paddr),
                                  O_NONBLOCK);
         if (ret == -EINPROGRESS) {
                 dout("connect %s EINPROGRESS sk_state = %u\n",
-                     pr_addr(&con->peer_addr.in_addr),
+                     ceph_pr_addr(&con->peer_addr.in_addr),
                      sock->sk->sk_state);
                 ret = 0;
         }
         if (ret < 0) {
                 pr_err("connect %s error %d\n",
-                       pr_addr(&con->peer_addr.in_addr), ret);
+                       ceph_pr_addr(&con->peer_addr.in_addr), ret);
                 sock_release(sock);
                 con->sock = NULL;
                 con->error_msg = "connect error";
@@ -334,7 +340,8 @@ static void reset_connection(struct ceph_connection *con)
  */
 void ceph_con_close(struct ceph_connection *con)
 {
-        dout("con_close %p peer %s\n", con, pr_addr(&con->peer_addr.in_addr));
+        dout("con_close %p peer %s\n", con,
+             ceph_pr_addr(&con->peer_addr.in_addr));
         set_bit(CLOSED, &con->state);  /* in case there's queued work */
         clear_bit(STANDBY, &con->state);  /* avoid connect_seq bump */
         clear_bit(LOSSYTX, &con->state);  /* so we retry next connect */
@@ -347,19 +354,21 @@ void ceph_con_close(struct ceph_connection *con)
         mutex_unlock(&con->mutex);
         queue_con(con);
 }
+EXPORT_SYMBOL(ceph_con_close);
 
 /*
  * Reopen a closed connection, with a new peer address.
  */
 void ceph_con_open(struct ceph_connection *con, struct ceph_entity_addr *addr)
 {
-        dout("con_open %p %s\n", con, pr_addr(&addr->in_addr));
+        dout("con_open %p %s\n", con, ceph_pr_addr(&addr->in_addr));
         set_bit(OPENING, &con->state);
         clear_bit(CLOSED, &con->state);
         memcpy(&con->peer_addr, addr, sizeof(*addr));
         con->delay = 0;      /* reset backoff memory */
         queue_con(con);
 }
+EXPORT_SYMBOL(ceph_con_open);
 
 /*
  * return true if this connection ever successfully opened
@@ -406,6 +415,7 @@ void ceph_con_init(struct ceph_messenger *msgr, struct ceph_connection *con)
         INIT_LIST_HEAD(&con->out_sent);
         INIT_DELAYED_WORK(&con->work, con_work);
 }
+EXPORT_SYMBOL(ceph_con_init);
 
 
 /*
@@ -529,8 +539,11 @@ static void prepare_write_message(struct ceph_connection *con)
         if (le32_to_cpu(m->hdr.data_len) > 0) {
                 /* initialize page iterator */
                 con->out_msg_pos.page = 0;
-                con->out_msg_pos.page_pos =
-                        le16_to_cpu(m->hdr.data_off) & ~PAGE_MASK;
+                if (m->pages)
+                        con->out_msg_pos.page_pos =
+                                le16_to_cpu(m->hdr.data_off) & ~PAGE_MASK;
+                else
+                        con->out_msg_pos.page_pos = 0;
                 con->out_msg_pos.data_pos = 0;
                 con->out_msg_pos.did_page_crc = 0;
                 con->out_more = 1;  /* data + footer will follow */
@@ -647,7 +660,7 @@ static void prepare_write_connect(struct ceph_messenger *msgr,
         dout("prepare_write_connect %p cseq=%d gseq=%d proto=%d\n", con,
              con->connect_seq, global_seq, proto);
 
-        con->out_connect.features = cpu_to_le64(CEPH_FEATURE_SUPPORTED);
+        con->out_connect.features = cpu_to_le64(msgr->supported_features);
         con->out_connect.host_type = cpu_to_le32(CEPH_ENTITY_TYPE_CLIENT);
         con->out_connect.connect_seq = cpu_to_le32(con->connect_seq);
         con->out_connect.global_seq = cpu_to_le32(global_seq);
@@ -712,6 +725,31 @@ out:
         return ret;  /* done! */
 }
 
+#ifdef CONFIG_BLOCK
+static void init_bio_iter(struct bio *bio, struct bio **iter, int *seg)
+{
+        if (!bio) {
+                *iter = NULL;
+                *seg = 0;
+                return;
+        }
+        *iter = bio;
+        *seg = bio->bi_idx;
+}
+
+static void iter_bio_next(struct bio **bio_iter, int *seg)
+{
+        if (*bio_iter == NULL)
+                return;
+
+        BUG_ON(*seg >= (*bio_iter)->bi_vcnt);
+
+        (*seg)++;
+        if (*seg == (*bio_iter)->bi_vcnt)
+                init_bio_iter((*bio_iter)->bi_next, bio_iter, seg);
+}
+#endif
+
 /*
  * Write as much message data payload as we can.  If we finish, queue
  * up the footer.
@@ -726,21 +764,46 @@ static int write_partial_msg_pages(struct ceph_connection *con)
         size_t len;
         int crc = con->msgr->nocrc;
         int ret;
+        int total_max_write;
+        int in_trail = 0;
+        size_t trail_len = (msg->trail ? msg->trail->length : 0);
 
         dout("write_partial_msg_pages %p msg %p page %d/%d offset %d\n",
              con, con->out_msg, con->out_msg_pos.page, con->out_msg->nr_pages,
              con->out_msg_pos.page_pos);
 
-        while (con->out_msg_pos.page < con->out_msg->nr_pages) {
+#ifdef CONFIG_BLOCK
+        if (msg->bio && !msg->bio_iter)
+                init_bio_iter(msg->bio, &msg->bio_iter, &msg->bio_seg);
+#endif
+
+        while (data_len > con->out_msg_pos.data_pos) {
                 struct page *page = NULL;
                 void *kaddr = NULL;
+                int max_write = PAGE_SIZE;
+                int page_shift = 0;
+
+                total_max_write = data_len - trail_len -
+                        con->out_msg_pos.data_pos;
 
                 /*
                  * if we are calculating the data crc (the default), we need
                  * to map the page.  if our pages[] has been revoked, use the
                  * zero page.
                  */
-                if (msg->pages) {
+
+                /* have we reached the trail part of the data? */
+                if (con->out_msg_pos.data_pos >= data_len - trail_len) {
+                        in_trail = 1;
+
+                        total_max_write = data_len - con->out_msg_pos.data_pos;
+
+                        page = list_first_entry(&msg->trail->head,
+                                                struct page, lru);
+                        if (crc)
+                                kaddr = kmap(page);
+                        max_write = PAGE_SIZE;
+                } else if (msg->pages) {
                         page = msg->pages[con->out_msg_pos.page];
                         if (crc)
                                 kaddr = kmap(page);
@@ -749,13 +812,25 @@ static int write_partial_msg_pages(struct ceph_connection *con)
                                                 struct page, lru);
                         if (crc)
                                 kaddr = kmap(page);
+#ifdef CONFIG_BLOCK
+                } else if (msg->bio) {
+                        struct bio_vec *bv;
+
+                        bv = bio_iovec_idx(msg->bio_iter, msg->bio_seg);
+                        page = bv->bv_page;
+                        page_shift = bv->bv_offset;
+                        if (crc)
+                                kaddr = kmap(page) + page_shift;
+                        max_write = bv->bv_len;
+#endif
                 } else {
                         page = con->msgr->zero_page;
                         if (crc)
                                 kaddr = page_address(con->msgr->zero_page);
                 }
-                len = min((int)(PAGE_SIZE - con->out_msg_pos.page_pos),
-                          (int)(data_len - con->out_msg_pos.data_pos));
+                len = min_t(int, max_write - con->out_msg_pos.page_pos,
+                            total_max_write);
+
                 if (crc && !con->out_msg_pos.did_page_crc) {
                         void *base = kaddr + con->out_msg_pos.page_pos;
                         u32 tmpcrc = le32_to_cpu(con->out_msg->footer.data_crc);
@@ -765,13 +840,14 @@ static int write_partial_msg_pages(struct ceph_connection *con)
                                 cpu_to_le32(crc32c(tmpcrc, base, len));
                         con->out_msg_pos.did_page_crc = 1;
                 }
-
                 ret = kernel_sendpage(con->sock, page,
-                                      con->out_msg_pos.page_pos, len,
+                                      con->out_msg_pos.page_pos + page_shift,
+                                      len,
                                       MSG_DONTWAIT | MSG_NOSIGNAL |
                                       MSG_MORE);
 
-                if (crc && (msg->pages || msg->pagelist))
+                if (crc &&
+                    (msg->pages || msg->pagelist || msg->bio || in_trail))
                         kunmap(page);
 
                 if (ret <= 0)
@@ -783,9 +859,16 @@ static int write_partial_msg_pages(struct ceph_connection *con)
                         con->out_msg_pos.page_pos = 0;
                         con->out_msg_pos.page++;
                         con->out_msg_pos.did_page_crc = 0;
-                        if (msg->pagelist)
+                        if (in_trail)
+                                list_move_tail(&page->lru,
+                                               &msg->trail->head);
+                        else if (msg->pagelist)
                                 list_move_tail(&page->lru,
                                                &msg->pagelist->head);
+#ifdef CONFIG_BLOCK
+                        else if (msg->bio)
+                                iter_bio_next(&msg->bio_iter, &msg->bio_seg);
+#endif
                 }
         }
 
@@ -938,7 +1021,7 @@ static int verify_hello(struct ceph_connection *con)
 {
         if (memcmp(con->in_banner, CEPH_BANNER, strlen(CEPH_BANNER))) {
                 pr_err("connect to %s got bad banner\n",
-                       pr_addr(&con->peer_addr.in_addr));
+                       ceph_pr_addr(&con->peer_addr.in_addr));
                 con->error_msg = "protocol error, bad banner";
                 return -1;
         }
@@ -1041,7 +1124,7 @@ int ceph_parse_ips(const char *c, const char *end,
 
                 addr_set_port(ss, port);
 
-                dout("parse_ips got %s\n", pr_addr(ss));
+                dout("parse_ips got %s\n", ceph_pr_addr(ss));
 
                 if (p == end)
                         break;
@@ -1061,6 +1144,7 @@ bad:
         pr_err("parse_ips bad ip '%.*s'\n", (int)(end - c), c);
         return -EINVAL;
 }
+EXPORT_SYMBOL(ceph_parse_ips);
 
 static int process_banner(struct ceph_connection *con)
 {
@@ -1082,9 +1166,9 @@ static int process_banner(struct ceph_connection *con)
             !(addr_is_blank(&con->actual_peer_addr.in_addr) &&
               con->actual_peer_addr.nonce == con->peer_addr.nonce)) {
                 pr_warning("wrong peer, want %s/%d, got %s/%d\n",
-                           pr_addr(&con->peer_addr.in_addr),
+                           ceph_pr_addr(&con->peer_addr.in_addr),
                            (int)le32_to_cpu(con->peer_addr.nonce),
-                           pr_addr(&con->actual_peer_addr.in_addr),
+                           ceph_pr_addr(&con->actual_peer_addr.in_addr),
                            (int)le32_to_cpu(con->actual_peer_addr.nonce));
                 con->error_msg = "wrong peer at address";
                 return -1;
@@ -1102,7 +1186,7 @@ static int process_banner(struct ceph_connection *con)
                 addr_set_port(&con->msgr->inst.addr.in_addr, port);
                 encode_my_addr(con->msgr);
                 dout("process_banner learned my addr is %s\n",
-                     pr_addr(&con->msgr->inst.addr.in_addr));
+                     ceph_pr_addr(&con->msgr->inst.addr.in_addr));
         }
 
         set_bit(NEGOTIATING, &con->state);
@@ -1123,8 +1207,8 @@ static void fail_protocol(struct ceph_connection *con)
 
 static int process_connect(struct ceph_connection *con)
 {
-        u64 sup_feat = CEPH_FEATURE_SUPPORTED;
-        u64 req_feat = CEPH_FEATURE_REQUIRED;
+        u64 sup_feat = con->msgr->supported_features;
+        u64 req_feat = con->msgr->required_features;
         u64 server_feat = le64_to_cpu(con->in_reply.features);
 
         dout("process_connect on %p tag %d\n", con, (int)con->in_tag);
@@ -1134,7 +1218,7 @@ static int process_connect(struct ceph_connection *con)
                 pr_err("%s%lld %s feature set mismatch,"
                        " my %llx < server's %llx, missing %llx\n",
                        ENTITY_NAME(con->peer_name),
-                       pr_addr(&con->peer_addr.in_addr),
+                       ceph_pr_addr(&con->peer_addr.in_addr),
                        sup_feat, server_feat, server_feat & ~sup_feat);
                 con->error_msg = "missing required protocol features";
                 fail_protocol(con);
@@ -1144,7 +1228,7 @@ static int process_connect(struct ceph_connection *con)
                 pr_err("%s%lld %s protocol version mismatch,"
                        " my %d != server's %d\n",
                        ENTITY_NAME(con->peer_name),
-                       pr_addr(&con->peer_addr.in_addr),
+                       ceph_pr_addr(&con->peer_addr.in_addr),
                        le32_to_cpu(con->out_connect.protocol_version),
                        le32_to_cpu(con->in_reply.protocol_version));
                 con->error_msg = "protocol version mismatch";
@@ -1178,7 +1262,7 @@ static int process_connect(struct ceph_connection *con)
                      le32_to_cpu(con->in_connect.connect_seq));
                 pr_err("%s%lld %s connection reset\n",
                        ENTITY_NAME(con->peer_name),
-                       pr_addr(&con->peer_addr.in_addr));
+                       ceph_pr_addr(&con->peer_addr.in_addr));
                 reset_connection(con);
                 prepare_write_connect(con->msgr, con, 0);
                 prepare_read_connect(con);
@@ -1223,7 +1307,7 @@ static int process_connect(struct ceph_connection *con)
                         pr_err("%s%lld %s protocol feature mismatch,"
                                " my required %llx > server's %llx, need %llx\n",
                                ENTITY_NAME(con->peer_name),
-                               pr_addr(&con->peer_addr.in_addr),
+                               ceph_pr_addr(&con->peer_addr.in_addr),
                                req_feat, server_feat, req_feat & ~server_feat);
                         con->error_msg = "missing required protocol features";
                         fail_protocol(con);
@@ -1305,8 +1389,7 @@ static int read_partial_message_section(struct ceph_connection *con,
                                         struct kvec *section,
                                         unsigned int sec_len, u32 *crc)
 {
-        int left;
-        int ret;
+        int ret, left;
 
         BUG_ON(!section);
 
@@ -1329,13 +1412,83 @@ static int read_partial_message_section(struct ceph_connection *con,
 static struct ceph_msg *ceph_alloc_msg(struct ceph_connection *con,
                                 struct ceph_msg_header *hdr,
                                 int *skip);
+
+
+static int read_partial_message_pages(struct ceph_connection *con,
+                                      struct page **pages,
+                                      unsigned data_len, int datacrc)
+{
+        void *p;
+        int ret;
+        int left;
+
+        left = min((int)(data_len - con->in_msg_pos.data_pos),
+                   (int)(PAGE_SIZE - con->in_msg_pos.page_pos));
+        /* (page) data */
+        BUG_ON(pages == NULL);
+        p = kmap(pages[con->in_msg_pos.page]);
+        ret = ceph_tcp_recvmsg(con->sock, p + con->in_msg_pos.page_pos,
+                               left);
+        if (ret > 0 && datacrc)
+                con->in_data_crc =
+                        crc32c(con->in_data_crc,
+                                  p + con->in_msg_pos.page_pos, ret);
+        kunmap(pages[con->in_msg_pos.page]);
+        if (ret <= 0)
+                return ret;
+        con->in_msg_pos.data_pos += ret;
+        con->in_msg_pos.page_pos += ret;
+        if (con->in_msg_pos.page_pos == PAGE_SIZE) {
+                con->in_msg_pos.page_pos = 0;
+                con->in_msg_pos.page++;
+        }
+
+        return ret;
+}
+
+#ifdef CONFIG_BLOCK
+static int read_partial_message_bio(struct ceph_connection *con,
+                                    struct bio **bio_iter, int *bio_seg,
+                                    unsigned data_len, int datacrc)
+{
+        struct bio_vec *bv = bio_iovec_idx(*bio_iter, *bio_seg);
+        void *p;
+        int ret, left;
+
+        if (IS_ERR(bv))
+                return PTR_ERR(bv);
+
+        left = min((int)(data_len - con->in_msg_pos.data_pos),
+                   (int)(bv->bv_len - con->in_msg_pos.page_pos));
+
+        p = kmap(bv->bv_page) + bv->bv_offset;
+
+        ret = ceph_tcp_recvmsg(con->sock, p + con->in_msg_pos.page_pos,
+                               left);
+        if (ret > 0 && datacrc)
+                con->in_data_crc =
+                        crc32c(con->in_data_crc,
+                                  p + con->in_msg_pos.page_pos, ret);
+        kunmap(bv->bv_page);
+        if (ret <= 0)
+                return ret;
+        con->in_msg_pos.data_pos += ret;
+        con->in_msg_pos.page_pos += ret;
+        if (con->in_msg_pos.page_pos == bv->bv_len) {
+                con->in_msg_pos.page_pos = 0;
+                iter_bio_next(bio_iter, bio_seg);
+        }
+
+        return ret;
+}
+#endif
+
 /*
  * read (part of) a message.
  */
 static int read_partial_message(struct ceph_connection *con)
 {
         struct ceph_msg *m = con->in_msg;
-        void *p;
         int ret;
         int to, left;
         unsigned front_len, middle_len, data_len, data_off;
@@ -1381,7 +1534,7 @@ static int read_partial_message(struct ceph_connection *con)
         if ((s64)seq - (s64)con->in_seq < 1) {
                 pr_info("skipping %s%lld %s seq %lld, expected %lld\n",
                         ENTITY_NAME(con->peer_name),
-                        pr_addr(&con->peer_addr.in_addr),
+                        ceph_pr_addr(&con->peer_addr.in_addr),
                         seq, con->in_seq + 1);
                 con->in_base_pos = -front_len - middle_len - data_len -
                         sizeof(m->footer);
@@ -1422,7 +1575,10 @@ static int read_partial_message(struct ceph_connection *con)
                         m->middle->vec.iov_len = 0;
 
                 con->in_msg_pos.page = 0;
-                con->in_msg_pos.page_pos = data_off & ~PAGE_MASK;
+                if (m->pages)
+                        con->in_msg_pos.page_pos = data_off & ~PAGE_MASK;
+                else
+                        con->in_msg_pos.page_pos = 0;
                 con->in_msg_pos.data_pos = 0;
         }
 
@@ -1440,27 +1596,29 @@ static int read_partial_message(struct ceph_connection *con)
                 if (ret <= 0)
                         return ret;
         }
+#ifdef CONFIG_BLOCK
+        if (m->bio && !m->bio_iter)
+                init_bio_iter(m->bio, &m->bio_iter, &m->bio_seg);
+#endif
 
         /* (page) data */
         while (con->in_msg_pos.data_pos < data_len) {
-                left = min((int)(data_len - con->in_msg_pos.data_pos),
-                           (int)(PAGE_SIZE - con->in_msg_pos.page_pos));
-                BUG_ON(m->pages == NULL);
-                p = kmap(m->pages[con->in_msg_pos.page]);
-                ret = ceph_tcp_recvmsg(con->sock, p + con->in_msg_pos.page_pos,
-                                       left);
-                if (ret > 0 && datacrc)
-                        con->in_data_crc =
-                                crc32c(con->in_data_crc,
-                                          p + con->in_msg_pos.page_pos, ret);
-                kunmap(m->pages[con->in_msg_pos.page]);
-                if (ret <= 0)
-                        return ret;
-                con->in_msg_pos.data_pos += ret;
-                con->in_msg_pos.page_pos += ret;
-                if (con->in_msg_pos.page_pos == PAGE_SIZE) {
-                        con->in_msg_pos.page_pos = 0;
-                        con->in_msg_pos.page++;
+                if (m->pages) {
+                        ret = read_partial_message_pages(con, m->pages,
+                                                 data_len, datacrc);
+                        if (ret <= 0)
+                                return ret;
+#ifdef CONFIG_BLOCK
+                } else if (m->bio) {
+
+                        ret = read_partial_message_bio(con,
+                                                 &m->bio_iter, &m->bio_seg,
+                                                 data_len, datacrc);
+                        if (ret <= 0)
+                                return ret;
+#endif
+                } else {
+                        BUG_ON(1);
                 }
         }
 
@@ -1874,9 +2032,9 @@ out:
 static void ceph_fault(struct ceph_connection *con)
 {
         pr_err("%s%lld %s %s\n", ENTITY_NAME(con->peer_name),
-               pr_addr(&con->peer_addr.in_addr), con->error_msg);
+               ceph_pr_addr(&con->peer_addr.in_addr), con->error_msg);
         dout("fault %p state %lu to peer %s\n",
-             con, con->state, pr_addr(&con->peer_addr.in_addr));
+             con, con->state, ceph_pr_addr(&con->peer_addr.in_addr));
 
         if (test_bit(LOSSYTX, &con->state)) {
                 dout("fault on LOSSYTX channel\n");
@@ -1936,7 +2094,9 @@ out:
 /*
  * create a new messenger instance
  */
-struct ceph_messenger *ceph_messenger_create(struct ceph_entity_addr *myaddr)
+struct ceph_messenger *ceph_messenger_create(struct ceph_entity_addr *myaddr,
+                                             u32 supported_features,
+                                             u32 required_features)
 {
         struct ceph_messenger *msgr;
 
@@ -1944,6 +2104,9 @@ struct ceph_messenger *ceph_messenger_create(struct ceph_entity_addr *myaddr)
         if (msgr == NULL)
                 return ERR_PTR(-ENOMEM);
 
+        msgr->supported_features = supported_features;
+        msgr->required_features = required_features;
+
         spin_lock_init(&msgr->global_seq_lock);
 
         /* the zero page is needed if a request is "canceled" while the message
@@ -1966,6 +2129,7 @@ struct ceph_messenger *ceph_messenger_create(struct ceph_entity_addr *myaddr)
         dout("messenger_create %p\n", msgr);
         return msgr;
 }
+EXPORT_SYMBOL(ceph_messenger_create);
 
 void ceph_messenger_destroy(struct ceph_messenger *msgr)
 {
@@ -1975,6 +2139,7 @@ void ceph_messenger_destroy(struct ceph_messenger *msgr)
         kfree(msgr);
         dout("destroyed messenger %p\n", msgr);
 }
+EXPORT_SYMBOL(ceph_messenger_destroy);
 
 /*
  * Queue up an outgoing message on the given connection.
@@ -2011,6 +2176,7 @@ void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg)
         if (test_and_set_bit(WRITE_PENDING, &con->state) == 0)
                 queue_con(con);
 }
+EXPORT_SYMBOL(ceph_con_send);
 
 /*
  * Revoke a message that was previously queued for send
@@ -2076,6 +2242,7 @@ void ceph_con_keepalive(struct ceph_connection *con)
             test_and_set_bit(WRITE_PENDING, &con->state) == 0)
                 queue_con(con);
 }
+EXPORT_SYMBOL(ceph_con_keepalive);
 
 
 /*
@@ -2136,6 +2303,10 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags)
         m->nr_pages = 0;
         m->pages = NULL;
         m->pagelist = NULL;
+        m->bio = NULL;
+        m->bio_iter = NULL;
+        m->bio_seg = 0;
+        m->trail = NULL;
 
         dout("ceph_msg_new %p front %d\n", m, front_len);
         return m;
@@ -2146,6 +2317,7 @@ out:
         pr_err("msg_new can't create type %d front %d\n", type, front_len);
         return NULL;
 }
+EXPORT_SYMBOL(ceph_msg_new);
 
 /*
  * Allocate "middle" portion of a message, if it is needed and wasn't
@@ -2250,11 +2422,14 @@ void ceph_msg_last_put(struct kref *kref)
                 m->pagelist = NULL;
         }
 
+        m->trail = NULL;
+
         if (m->pool)
                 ceph_msgpool_put(m->pool, m);
         else
                 ceph_msg_kfree(m);
 }
+EXPORT_SYMBOL(ceph_msg_last_put);
 
 void ceph_msg_dump(struct ceph_msg *msg)
 {
@@ -2275,3 +2450,4 @@ void ceph_msg_dump(struct ceph_msg *msg)
                        DUMP_PREFIX_OFFSET, 16, 1,
                        &msg->footer, sizeof(msg->footer), true);
 }
+EXPORT_SYMBOL(ceph_msg_dump);
diff --git a/fs/ceph/mon_client.c b/net/ceph/mon_client.c
index b2a5a3e4a671..8a079399174a 100644
--- a/fs/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -1,14 +1,16 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
+#include <linux/module.h>
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/random.h>
 #include <linux/sched.h>
 
-#include "mon_client.h"
-#include "super.h"
-#include "auth.h"
-#include "decode.h"
+#include <linux/ceph/mon_client.h>
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/decode.h>
+
+#include <linux/ceph/auth.h>
 
 /*
  * Interact with Ceph monitor cluster.  Handle requests for new map
@@ -74,7 +76,7 @@ struct ceph_monmap *ceph_monmap_decode(void *p, void *end)
              m->num_mon);
         for (i = 0; i < m->num_mon; i++)
                 dout("monmap_decode  mon%d is %s\n", i,
-                     pr_addr(&m->mon_inst[i].addr.in_addr));
+                     ceph_pr_addr(&m->mon_inst[i].addr.in_addr));
         return m;
 
 bad:
@@ -191,30 +193,33 @@ static void __send_subscribe(struct ceph_mon_client *monc)
                 struct ceph_msg *msg = monc->m_subscribe;
                 struct ceph_mon_subscribe_item *i;
                 void *p, *end;
+                int num;
 
                 p = msg->front.iov_base;
                 end = p + msg->front_max;
 
-                dout("__send_subscribe to 'mdsmap' %u+\n",
-                     (unsigned)monc->have_mdsmap);
+                num = 1 + !!monc->want_next_osdmap + !!monc->want_mdsmap;
+                ceph_encode_32(&p, num);
+
                 if (monc->want_next_osdmap) {
                         dout("__send_subscribe to 'osdmap' %u\n",
                              (unsigned)monc->have_osdmap);
-                        ceph_encode_32(&p, 3);
                         ceph_encode_string(&p, end, "osdmap", 6);
                         i = p;
                         i->have = cpu_to_le64(monc->have_osdmap);
                         i->onetime = 1;
                         p += sizeof(*i);
                         monc->want_next_osdmap = 2;  /* requested */
-                } else {
-                        ceph_encode_32(&p, 2);
                 }
-                ceph_encode_string(&p, end, "mdsmap", 6);
-                i = p;
-                i->have = cpu_to_le64(monc->have_mdsmap);
-                i->onetime = 0;
-                p += sizeof(*i);
+                if (monc->want_mdsmap) {
+                        dout("__send_subscribe to 'mdsmap' %u+\n",
+                             (unsigned)monc->have_mdsmap);
+                        ceph_encode_string(&p, end, "mdsmap", 6);
+                        i = p;
+                        i->have = cpu_to_le64(monc->have_mdsmap);
+                        i->onetime = 0;
+                        p += sizeof(*i);
+                }
                 ceph_encode_string(&p, end, "monmap", 6);
                 i = p;
                 i->have = 0;
@@ -243,7 +248,8 @@ static void handle_subscribe_ack(struct ceph_mon_client *monc,
         mutex_lock(&monc->mutex);
         if (monc->hunting) {
                 pr_info("mon%d %s session established\n",
-                        monc->cur_mon, pr_addr(&monc->con->peer_addr.in_addr));
+                        monc->cur_mon,
+                        ceph_pr_addr(&monc->con->peer_addr.in_addr));
                 monc->hunting = false;
         }
         dout("handle_subscribe_ack after %d seconds\n", seconds);
@@ -266,6 +272,7 @@ int ceph_monc_got_mdsmap(struct ceph_mon_client *monc, u32 got)
         mutex_unlock(&monc->mutex);
         return 0;
 }
+EXPORT_SYMBOL(ceph_monc_got_mdsmap);
 
 int ceph_monc_got_osdmap(struct ceph_mon_client *monc, u32 got)
 {
@@ -310,6 +317,7 @@ int ceph_monc_open_session(struct ceph_mon_client *monc)
         mutex_unlock(&monc->mutex);
         return 0;
 }
+EXPORT_SYMBOL(ceph_monc_open_session);
 
 /*
  * The monitor responds with mount ack indicate mount success.  The
@@ -540,6 +548,7 @@ out:
         kref_put(&req->kref, release_generic_request);
         return err;
 }
+EXPORT_SYMBOL(ceph_monc_do_statfs);
 
 /*
  * pool ops
@@ -651,6 +660,7 @@ int ceph_monc_create_snapid(struct ceph_mon_client *monc,
                                    pool, 0, (char *)snapid, sizeof(*snapid));
 
 }
+EXPORT_SYMBOL(ceph_monc_create_snapid);
 
 int ceph_monc_delete_snapid(struct ceph_mon_client *monc,
                             u32 pool, u64 snapid)
@@ -708,9 +718,9 @@ static void delayed_work(struct work_struct *work)
  */
 static int build_initial_monmap(struct ceph_mon_client *monc)
 {
-        struct ceph_mount_args *args = monc->client->mount_args;
-        struct ceph_entity_addr *mon_addr = args->mon_addr;
-        int num_mon = args->num_mon;
+        struct ceph_options *opt = monc->client->options;
+        struct ceph_entity_addr *mon_addr = opt->mon_addr;
+        int num_mon = opt->num_mon;
         int i;
 
         /* build initial monmap */
@@ -728,11 +738,6 @@ static int build_initial_monmap(struct ceph_mon_client *monc)
         }
         monc->monmap->num_mon = num_mon;
         monc->have_fsid = false;
-
-        /* release addr memory */
-        kfree(args->mon_addr);
-        args->mon_addr = NULL;
-        args->num_mon = 0;
         return 0;
 }
 
@@ -753,8 +758,8 @@ int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl)
         monc->con = NULL;
 
         /* authentication */
-        monc->auth = ceph_auth_init(cl->mount_args->name,
-                                    cl->mount_args->secret);
+        monc->auth = ceph_auth_init(cl->options->name,
+                                    cl->options->secret);
         if (IS_ERR(monc->auth))
                 return PTR_ERR(monc->auth);
         monc->auth->want_keys =
@@ -808,6 +813,7 @@ out_monmap:
 out:
         return err;
 }
+EXPORT_SYMBOL(ceph_monc_init);
 
 void ceph_monc_stop(struct ceph_mon_client *monc)
 {
@@ -832,6 +838,7 @@ void ceph_monc_stop(struct ceph_mon_client *monc)
 
         kfree(monc->monmap);
 }
+EXPORT_SYMBOL(ceph_monc_stop);
 
 static void handle_auth_reply(struct ceph_mon_client *monc,
                               struct ceph_msg *msg)
@@ -889,6 +896,7 @@ int ceph_monc_validate_auth(struct ceph_mon_client *monc)
         mutex_unlock(&monc->mutex);
         return ret;
 }
+EXPORT_SYMBOL(ceph_monc_validate_auth);
 
 /*
  * handle incoming message
@@ -922,15 +930,16 @@ static void dispatch(struct ceph_connection *con, struct ceph_msg *msg)
                 ceph_monc_handle_map(monc, msg);
                 break;
 
-        case CEPH_MSG_MDS_MAP:
-                ceph_mdsc_handle_map(&monc->client->mdsc, msg);
-                break;
-
         case CEPH_MSG_OSD_MAP:
                 ceph_osdc_handle_map(&monc->client->osdc, msg);
                 break;
 
         default:
+                /* can the chained handler handle it? */
+                if (monc->client->extra_mon_dispatch &&
+                    monc->client->extra_mon_dispatch(monc->client, msg) == 0)
+                        break;
+                        
                 pr_err("received unknown message type %d %s\n", type,
                        ceph_msg_type_name(type));
         }
@@ -994,7 +1003,7 @@ static void mon_fault(struct ceph_connection *con)
         if (monc->con && !monc->hunting)
                 pr_info("mon%d %s session lost, "
                         "hunting for new mon\n", monc->cur_mon,
-                        pr_addr(&monc->con->peer_addr.in_addr));
+                        ceph_pr_addr(&monc->con->peer_addr.in_addr));
 
         __close_session(monc);
         if (!monc->hunting) {
diff --git a/fs/ceph/msgpool.c b/net/ceph/msgpool.c
index dd65a6438131..d5f2d97ac05c 100644
--- a/fs/ceph/msgpool.c
+++ b/net/ceph/msgpool.c
@@ -1,11 +1,11 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
 #include <linux/err.h>
 #include <linux/sched.h>
 #include <linux/types.h>
 #include <linux/vmalloc.h>
 
-#include "msgpool.h"
+#include <linux/ceph/msgpool.h>
 
 static void *alloc_fn(gfp_t gfp_mask, void *arg)
 {
diff --git a/fs/ceph/osd_client.c b/net/ceph/osd_client.c
index 3b5571b8ce22..79391994b3ed 100644
--- a/fs/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1,17 +1,22 @@
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
+#include <linux/module.h>
 #include <linux/err.h>
 #include <linux/highmem.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
+#ifdef CONFIG_BLOCK
+#include <linux/bio.h>
+#endif
 
-#include "super.h"
-#include "osd_client.h"
-#include "messenger.h"
-#include "decode.h"
-#include "auth.h"
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/osd_client.h>
+#include <linux/ceph/messenger.h>
+#include <linux/ceph/decode.h>
+#include <linux/ceph/auth.h>
+#include <linux/ceph/pagelist.h>
 
 #define OSD_OP_FRONT_LEN        4096
 #define OSD_OPREPLY_FRONT_LEN   512
@@ -22,6 +27,59 @@ static int __kick_requests(struct ceph_osd_client *osdc,
 
 static void kick_requests(struct ceph_osd_client *osdc, struct ceph_osd *osd);
 
+static int op_needs_trail(int op)
+{
+        switch (op) {
+        case CEPH_OSD_OP_GETXATTR:
+        case CEPH_OSD_OP_SETXATTR:
+        case CEPH_OSD_OP_CMPXATTR:
+        case CEPH_OSD_OP_CALL:
+                return 1;
+        default:
+                return 0;
+        }
+}
+
+static int op_has_extent(int op)
+{
+        return (op == CEPH_OSD_OP_READ ||
+                op == CEPH_OSD_OP_WRITE);
+}
+
+void ceph_calc_raw_layout(struct ceph_osd_client *osdc,
+                        struct ceph_file_layout *layout,
+                        u64 snapid,
+                        u64 off, u64 *plen, u64 *bno,
+                        struct ceph_osd_request *req,
+                        struct ceph_osd_req_op *op)
+{
+        struct ceph_osd_request_head *reqhead = req->r_request->front.iov_base;
+        u64 orig_len = *plen;
+        u64 objoff, objlen;    /* extent in object */
+
+        reqhead->snapid = cpu_to_le64(snapid);
+
+        /* object extent? */
+        ceph_calc_file_object_mapping(layout, off, plen, bno,
+                                      &objoff, &objlen);
+        if (*plen < orig_len)
+                dout(" skipping last %llu, final file extent %llu~%llu\n",
+                     orig_len - *plen, off, *plen);
+
+        if (op_has_extent(op->op)) {
+                op->extent.offset = objoff;
+                op->extent.length = objlen;
+        }
+        req->r_num_pages = calc_pages_for(off, *plen);
+        if (op->op == CEPH_OSD_OP_WRITE)
+                op->payload_len = *plen;
+
+        dout("calc_layout bno=%llx %llu~%llu (%d pages)\n",
+             *bno, objoff, objlen, req->r_num_pages);
+
+}
+EXPORT_SYMBOL(ceph_calc_raw_layout);
+
 /*
  * Implement client access to distributed object storage cluster.
  *
@@ -48,34 +106,19 @@ static void kick_requests(struct ceph_osd_client *osdc, struct ceph_osd *osd);
  * fill osd op in request message.
  */
 static void calc_layout(struct ceph_osd_client *osdc,
-                        struct ceph_vino vino, struct ceph_file_layout *layout,
+                        struct ceph_vino vino,
+                        struct ceph_file_layout *layout,
                         u64 off, u64 *plen,
-                        struct ceph_osd_request *req)
+                        struct ceph_osd_request *req,
+                        struct ceph_osd_req_op *op)
 {
-        struct ceph_osd_request_head *reqhead = req->r_request->front.iov_base;
-        struct ceph_osd_op *op = (void *)(reqhead + 1);
-        u64 orig_len = *plen;
-        u64 objoff, objlen;    /* extent in object */
         u64 bno;
 
-        reqhead->snapid = cpu_to_le64(vino.snap);
-
-        /* object extent? */
-        ceph_calc_file_object_mapping(layout, off, plen, &bno,
-                                      &objoff, &objlen);
-        if (*plen < orig_len)
-                dout(" skipping last %llu, final file extent %llu~%llu\n",
-                     orig_len - *plen, off, *plen);
+        ceph_calc_raw_layout(osdc, layout, vino.snap, off,
+                             plen, &bno, req, op);
 
         sprintf(req->r_oid, "%llx.%08llx", vino.ino, bno);
         req->r_oid_len = strlen(req->r_oid);
-
-        op->extent.offset = cpu_to_le64(objoff);
-        op->extent.length = cpu_to_le64(objlen);
-        req->r_num_pages = calc_pages_for(off, *plen);
-
-        dout("calc_layout %s (%d) %llu~%llu (%d pages)\n",
-             req->r_oid, req->r_oid_len, objoff, objlen, req->r_num_pages);
 }
 
 /*
@@ -101,56 +144,66 @@ void ceph_osdc_release_request(struct kref *kref)
         if (req->r_own_pages)
                 ceph_release_page_vector(req->r_pages,
                                          req->r_num_pages);
+#ifdef CONFIG_BLOCK
+        if (req->r_bio)
+                bio_put(req->r_bio);
+#endif
         ceph_put_snap_context(req->r_snapc);
+        if (req->r_trail) {
+                ceph_pagelist_release(req->r_trail);
+                kfree(req->r_trail);
+        }
         if (req->r_mempool)
                 mempool_free(req, req->r_osdc->req_mempool);
         else
                 kfree(req);
 }
+EXPORT_SYMBOL(ceph_osdc_release_request);
 
-/*
- * build new request AND message, calculate layout, and adjust file
- * extent as needed.
- *
- * if the file was recently truncated, we include information about its
- * old and new size so that the object can be updated appropriately.  (we
- * avoid synchronously deleting truncated objects because it's slow.)
- *
- * if @do_sync, include a 'startsync' command so that the osd will flush
- * data quickly.
- */
-struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
-                                               struct ceph_file_layout *layout,
-                                               struct ceph_vino vino,
-                                               u64 off, u64 *plen,
-                                               int opcode, int flags,
+static int get_num_ops(struct ceph_osd_req_op *ops, int *needs_trail)
+{
+        int i = 0;
+
+        if (needs_trail)
+                *needs_trail = 0;
+        while (ops[i].op) {
+                if (needs_trail && op_needs_trail(ops[i].op))
+                        *needs_trail = 1;
+                i++;
+        }
+
+        return i;
+}
+
+struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
+                                               int flags,
                                                struct ceph_snap_context *snapc,
-                                               int do_sync,
-                                               u32 truncate_seq,
-                                               u64 truncate_size,
-                                               struct timespec *mtime,
-                                               bool use_mempool, int num_reply)
+                                               struct ceph_osd_req_op *ops,
+                                               bool use_mempool,
+                                               gfp_t gfp_flags,
+                                               struct page **pages,
+                                               struct bio *bio)
 {
         struct ceph_osd_request *req;
         struct ceph_msg *msg;
-        struct ceph_osd_request_head *head;
-        struct ceph_osd_op *op;
-        void *p;
-        int num_op = 1 + do_sync;
-        size_t msg_size = sizeof(*head) + num_op*sizeof(*op);
-        int i;
+        int needs_trail;
+        int num_op = get_num_ops(ops, &needs_trail);
+        size_t msg_size = sizeof(struct ceph_osd_request_head);
+
+        msg_size += num_op*sizeof(struct ceph_osd_op);
 
         if (use_mempool) {
-                req = mempool_alloc(osdc->req_mempool, GFP_NOFS);
+                req = mempool_alloc(osdc->req_mempool, gfp_flags);
                 memset(req, 0, sizeof(*req));
         } else {
-                req = kzalloc(sizeof(*req), GFP_NOFS);
+                req = kzalloc(sizeof(*req), gfp_flags);
         }
         if (req == NULL)
                 return NULL;
 
         req->r_osdc = osdc;
         req->r_mempool = use_mempool;
+
         kref_init(&req->r_kref);
         init_completion(&req->r_completion);
         init_completion(&req->r_safe_completion);
@@ -164,13 +217,22 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
                 msg = ceph_msgpool_get(&osdc->msgpool_op_reply, 0);
         else
                 msg = ceph_msg_new(CEPH_MSG_OSD_OPREPLY,
-                                   OSD_OPREPLY_FRONT_LEN, GFP_NOFS);
+                                   OSD_OPREPLY_FRONT_LEN, gfp_flags);
         if (!msg) {
                 ceph_osdc_put_request(req);
                 return NULL;
         }
         req->r_reply = msg;
 
+        /* allocate space for the trailing data */
+        if (needs_trail) {
+                req->r_trail = kmalloc(sizeof(struct ceph_pagelist), gfp_flags);
+                if (!req->r_trail) {
+                        ceph_osdc_put_request(req);
+                        return NULL;
+                }
+                ceph_pagelist_init(req->r_trail);
+        }
         /* create request message; allow space for oid */
         msg_size += 40;
         if (snapc)
@@ -178,18 +240,115 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
         if (use_mempool)
                 msg = ceph_msgpool_get(&osdc->msgpool_op, 0);
         else
-                msg = ceph_msg_new(CEPH_MSG_OSD_OP, msg_size, GFP_NOFS);
+                msg = ceph_msg_new(CEPH_MSG_OSD_OP, msg_size, gfp_flags);
         if (!msg) {
                 ceph_osdc_put_request(req);
                 return NULL;
         }
+
         msg->hdr.type = cpu_to_le16(CEPH_MSG_OSD_OP);
         memset(msg->front.iov_base, 0, msg->front.iov_len);
+
+        req->r_request = msg;
+        req->r_pages = pages;
+#ifdef CONFIG_BLOCK
+        if (bio) {
+                req->r_bio = bio;
+                bio_get(req->r_bio);
+        }
+#endif
+
+        return req;
+}
+EXPORT_SYMBOL(ceph_osdc_alloc_request);
+
+static void osd_req_encode_op(struct ceph_osd_request *req,
+                              struct ceph_osd_op *dst,
+                              struct ceph_osd_req_op *src)
+{
+        dst->op = cpu_to_le16(src->op);
+
+        switch (dst->op) {
+        case CEPH_OSD_OP_READ:
+        case CEPH_OSD_OP_WRITE:
+                dst->extent.offset =
+                        cpu_to_le64(src->extent.offset);
+                dst->extent.length =
+                        cpu_to_le64(src->extent.length);
+                dst->extent.truncate_size =
+                        cpu_to_le64(src->extent.truncate_size);
+                dst->extent.truncate_seq =
+                        cpu_to_le32(src->extent.truncate_seq);
+                break;
+
+        case CEPH_OSD_OP_GETXATTR:
+        case CEPH_OSD_OP_SETXATTR:
+        case CEPH_OSD_OP_CMPXATTR:
+                BUG_ON(!req->r_trail);
+
+                dst->xattr.name_len = cpu_to_le32(src->xattr.name_len);
+                dst->xattr.value_len = cpu_to_le32(src->xattr.value_len);
+                dst->xattr.cmp_op = src->xattr.cmp_op;
+                dst->xattr.cmp_mode = src->xattr.cmp_mode;
+                ceph_pagelist_append(req->r_trail, src->xattr.name,
+                                     src->xattr.name_len);
+                ceph_pagelist_append(req->r_trail, src->xattr.val,
+                                     src->xattr.value_len);
+                break;
+        case CEPH_OSD_OP_CALL:
+                BUG_ON(!req->r_trail);
+
+                dst->cls.class_len = src->cls.class_len;
+                dst->cls.method_len = src->cls.method_len;
+                dst->cls.indata_len = cpu_to_le32(src->cls.indata_len);
+
+                ceph_pagelist_append(req->r_trail, src->cls.class_name,
+                                     src->cls.class_len);
+                ceph_pagelist_append(req->r_trail, src->cls.method_name,
+                                     src->cls.method_len);
+                ceph_pagelist_append(req->r_trail, src->cls.indata,
+                                     src->cls.indata_len);
+                break;
+        case CEPH_OSD_OP_ROLLBACK:
+                dst->snap.snapid = cpu_to_le64(src->snap.snapid);
+                break;
+        case CEPH_OSD_OP_STARTSYNC:
+                break;
+        default:
+                pr_err("unrecognized osd opcode %d\n", dst->op);
+                WARN_ON(1);
+                break;
+        }
+        dst->payload_len = cpu_to_le32(src->payload_len);
+}
+
+/*
+ * build new request AND message
+ *
+ */
+void ceph_osdc_build_request(struct ceph_osd_request *req,
+                             u64 off, u64 *plen,
+                             struct ceph_osd_req_op *src_ops,
+                             struct ceph_snap_context *snapc,
+                             struct timespec *mtime,
+                             const char *oid,
+                             int oid_len)
+{
+        struct ceph_msg *msg = req->r_request;
+        struct ceph_osd_request_head *head;
+        struct ceph_osd_req_op *src_op;
+        struct ceph_osd_op *op;
+        void *p;
+        int num_op = get_num_ops(src_ops, NULL);
+        size_t msg_size = sizeof(*head) + num_op*sizeof(*op);
+        int flags = req->r_flags;
+        u64 data_len = 0;
+        int i;
+
         head = msg->front.iov_base;
         op = (void *)(head + 1);
         p = (void *)(op + num_op);
 
-        req->r_request = msg;
         req->r_snapc = ceph_get_snap_context(snapc);
 
         head->client_inc = cpu_to_le32(1); /* always, for now. */
@@ -197,29 +356,23 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
         if (flags & CEPH_OSD_FLAG_WRITE)
                 ceph_encode_timespec(&head->mtime, mtime);
         head->num_ops = cpu_to_le16(num_op);
-        op->op = cpu_to_le16(opcode);
 
-        /* calculate max write size */
-        calc_layout(osdc, vino, layout, off, plen, req);
-        req->r_file_layout = *layout;  /* keep a copy */
-
-        if (flags & CEPH_OSD_FLAG_WRITE) {
-                req->r_request->hdr.data_off = cpu_to_le16(off);
-                req->r_request->hdr.data_len = cpu_to_le32(*plen);
-                op->payload_len = cpu_to_le32(*plen);
-        }
-        op->extent.truncate_size = cpu_to_le64(truncate_size);
-        op->extent.truncate_seq = cpu_to_le32(truncate_seq);
 
         /* fill in oid */
-        head->object_len = cpu_to_le32(req->r_oid_len);
-        memcpy(p, req->r_oid, req->r_oid_len);
-        p += req->r_oid_len;
-
-        if (do_sync) {
+        head->object_len = cpu_to_le32(oid_len);
+        memcpy(p, oid, oid_len);
+        p += oid_len;
+
+        src_op = src_ops;
+        while (src_op->op) {
+                osd_req_encode_op(req, op, src_op);
+                src_op++;
                 op++;
-                op->op = cpu_to_le16(CEPH_OSD_OP_STARTSYNC);
         }
+
+        if (req->r_trail)
+                data_len += req->r_trail->length;
+
         if (snapc) {
                 head->snap_seq = cpu_to_le64(snapc->seq);
                 head->num_snaps = cpu_to_le32(snapc->num_snaps);
@@ -229,12 +382,79 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
                 }
         }
 
+        if (flags & CEPH_OSD_FLAG_WRITE) {
+                req->r_request->hdr.data_off = cpu_to_le16(off);
+                req->r_request->hdr.data_len = cpu_to_le32(*plen + data_len);
+        } else if (data_len) {
+                req->r_request->hdr.data_off = 0;
+                req->r_request->hdr.data_len = cpu_to_le32(data_len);
+        }
+
         BUG_ON(p > msg->front.iov_base + msg->front.iov_len);
         msg_size = p - msg->front.iov_base;
         msg->front.iov_len = msg_size;
         msg->hdr.front_len = cpu_to_le32(msg_size);
+        return;
+}
+EXPORT_SYMBOL(ceph_osdc_build_request);
+
+/*
+ * build new request AND message, calculate layout, and adjust file
+ * extent as needed.
+ *
+ * if the file was recently truncated, we include information about its
+ * old and new size so that the object can be updated appropriately.  (we
+ * avoid synchronously deleting truncated objects because it's slow.)
+ *
+ * if @do_sync, include a 'startsync' command so that the osd will flush
+ * data quickly.
+ */
+struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
+                                               struct ceph_file_layout *layout,
+                                               struct ceph_vino vino,
+                                               u64 off, u64 *plen,
+                                               int opcode, int flags,
+                                               struct ceph_snap_context *snapc,
+                                               int do_sync,
+                                               u32 truncate_seq,
+                                               u64 truncate_size,
+                                               struct timespec *mtime,
+                                               bool use_mempool, int num_reply)
+{
+        struct ceph_osd_req_op ops[3];
+        struct ceph_osd_request *req;
+
+        ops[0].op = opcode;
+        ops[0].extent.truncate_seq = truncate_seq;
+        ops[0].extent.truncate_size = truncate_size;
+        ops[0].payload_len = 0;
+
+        if (do_sync) {
+                ops[1].op = CEPH_OSD_OP_STARTSYNC;
+                ops[1].payload_len = 0;
+                ops[2].op = 0;
+        } else
+                ops[1].op = 0;
+
+        req = ceph_osdc_alloc_request(osdc, flags,
+                                         snapc, ops,
+                                         use_mempool,
+                                         GFP_NOFS, NULL, NULL);
+        if (IS_ERR(req))
+                return req;
+
+        /* calculate max write size */
+        calc_layout(osdc, vino, layout, off, plen, req, ops);
+        req->r_file_layout = *layout;  /* keep a copy */
+
+        ceph_osdc_build_request(req, off, plen, ops,
+                                snapc,
+                                mtime,
+                                req->r_oid, req->r_oid_len);
+
         return req;
 }
+EXPORT_SYMBOL(ceph_osdc_new_request);
 
 /*
  * We keep osd requests in an rbtree, sorted by ->r_tid.
@@ -389,7 +609,7 @@ static void __move_osd_to_lru(struct ceph_osd_client *osdc,
         dout("__move_osd_to_lru %p\n", osd);
         BUG_ON(!list_empty(&osd->o_osd_lru));
         list_add_tail(&osd->o_osd_lru, &osdc->osd_lru);
-        osd->lru_ttl = jiffies + osdc->client->mount_args->osd_idle_ttl * HZ;
+        osd->lru_ttl = jiffies + osdc->client->options->osd_idle_ttl * HZ;
 }
 
 static void __remove_osd_from_lru(struct ceph_osd *osd)
@@ -483,7 +703,7 @@ static struct ceph_osd *__lookup_osd(struct ceph_osd_client *osdc, int o)
 static void __schedule_osd_timeout(struct ceph_osd_client *osdc)
 {
         schedule_delayed_work(&osdc->timeout_work,
-                        osdc->client->mount_args->osd_keepalive_timeout * HZ);
+                        osdc->client->options->osd_keepalive_timeout * HZ);
 }
 
 static void __cancel_osd_timeout(struct ceph_osd_client *osdc)
@@ -684,9 +904,9 @@ static void handle_timeout(struct work_struct *work)
                 container_of(work, struct ceph_osd_client, timeout_work.work);
         struct ceph_osd_request *req, *last_req = NULL;
         struct ceph_osd *osd;
-        unsigned long timeout = osdc->client->mount_args->osd_timeout * HZ;
+        unsigned long timeout = osdc->client->options->osd_timeout * HZ;
         unsigned long keepalive =
-                osdc->client->mount_args->osd_keepalive_timeout * HZ;
+                osdc->client->options->osd_keepalive_timeout * HZ;
         unsigned long last_stamp = 0;
         struct rb_node *p;
         struct list_head slow_osds;
@@ -773,7 +993,7 @@ static void handle_osds_timeout(struct work_struct *work)
                 container_of(work, struct ceph_osd_client,
                              osds_timeout_work.work);
         unsigned long delay =
-                osdc->client->mount_args->osd_idle_ttl * HZ >> 2;
+                osdc->client->options->osd_idle_ttl * HZ >> 2;
 
         dout("osds timeout\n");
         down_read(&osdc->map_sem);
@@ -1104,6 +1324,10 @@ int ceph_osdc_start_request(struct ceph_osd_client *osdc,
 
         req->r_request->pages = req->r_pages;
         req->r_request->nr_pages = req->r_num_pages;
+#ifdef CONFIG_BLOCK
+        req->r_request->bio = req->r_bio;
+#endif
+        req->r_request->trail = req->r_trail;
 
         register_request(osdc, req);
 
@@ -1131,6 +1355,7 @@ int ceph_osdc_start_request(struct ceph_osd_client *osdc,
         up_read(&osdc->map_sem);
         return rc;
 }
+EXPORT_SYMBOL(ceph_osdc_start_request);
 
 /*
  * wait for a request to complete
@@ -1153,6 +1378,7 @@ int ceph_osdc_wait_request(struct ceph_osd_client *osdc,
         dout("wait_request tid %llu result %d\n", req->r_tid, req->r_result);
         return req->r_result;
 }
+EXPORT_SYMBOL(ceph_osdc_wait_request);
 
 /*
  * sync - wait for all in-flight requests to flush.  avoid starvation.
@@ -1186,6 +1412,7 @@ void ceph_osdc_sync(struct ceph_osd_client *osdc)
         mutex_unlock(&osdc->request_mutex);
         dout("sync done (thru tid %llu)\n", last_tid);
 }
+EXPORT_SYMBOL(ceph_osdc_sync);
 
 /*
  * init, shutdown
@@ -1211,7 +1438,7 @@ int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client)
         INIT_DELAYED_WORK(&osdc->osds_timeout_work, handle_osds_timeout);
 
         schedule_delayed_work(&osdc->osds_timeout_work,
-           round_jiffies_relative(osdc->client->mount_args->osd_idle_ttl * HZ));
+           round_jiffies_relative(osdc->client->options->osd_idle_ttl * HZ));
 
         err = -ENOMEM;
         osdc->req_mempool = mempool_create_kmalloc_pool(10,
@@ -1237,6 +1464,7 @@ out_mempool:
 out:
         return err;
 }
+EXPORT_SYMBOL(ceph_osdc_init);
 
 void ceph_osdc_stop(struct ceph_osd_client *osdc)
 {
@@ -1251,6 +1479,7 @@ void ceph_osdc_stop(struct ceph_osd_client *osdc)
         ceph_msgpool_destroy(&osdc->msgpool_op);
         ceph_msgpool_destroy(&osdc->msgpool_op_reply);
 }
+EXPORT_SYMBOL(ceph_osdc_stop);
 
 /*
  * Read some contiguous pages.  If we cross a stripe boundary, shorten
@@ -1288,6 +1517,7 @@ int ceph_osdc_readpages(struct ceph_osd_client *osdc,
         dout("readpages result %d\n", rc);
         return rc;
 }
+EXPORT_SYMBOL(ceph_osdc_readpages);
 
 /*
  * do a synchronous write on N pages
@@ -1330,6 +1560,7 @@ int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino,
         dout("writepages result %d\n", rc);
         return rc;
 }
+EXPORT_SYMBOL(ceph_osdc_writepages);
 
 /*
  * handle incoming message
@@ -1420,6 +1651,9 @@ static struct ceph_msg *get_reply(struct ceph_connection *con,
                 }
                 m->pages = req->r_pages;
                 m->nr_pages = req->r_num_pages;
+#ifdef CONFIG_BLOCK
+                m->bio = req->r_bio;
+#endif
         }
         *skip = 0;
         req->r_con_filling_msg = ceph_con_get(con);
diff --git a/fs/ceph/osdmap.c b/net/ceph/osdmap.c
index e31f118f1392..d73f3f6efa36 100644
--- a/fs/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -1,14 +1,15 @@
 
-#include "ceph_debug.h"
+#include <linux/ceph/ceph_debug.h>
 
+#include <linux/module.h>
 #include <linux/slab.h>
 #include <asm/div64.h>
 
-#include "super.h"
-#include "osdmap.h"
-#include "crush/hash.h"
-#include "crush/mapper.h"
-#include "decode.h"
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/osdmap.h>
+#include <linux/ceph/decode.h>
+#include <linux/crush/hash.h>
+#include <linux/crush/mapper.h>
 
 char *ceph_osdmap_state_str(char *str, int len, int state)
 {
@@ -417,6 +418,20 @@ static struct ceph_pg_pool_info *__lookup_pg_pool(struct rb_root *root, int id)
         return NULL;
 }
 
+int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name)
+{
+        struct rb_node *rbp;
+
+        for (rbp = rb_first(&map->pg_pools); rbp; rbp = rb_next(rbp)) {
+                struct ceph_pg_pool_info *pi =
+                        rb_entry(rbp, struct ceph_pg_pool_info, node);
+                if (pi->name && strcmp(pi->name, name) == 0)
+                        return pi->id;
+        }
+        return -ENOENT;
+}
+EXPORT_SYMBOL(ceph_pg_poolid_by_name);
+
 static void __remove_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *pi)
 {
         rb_erase(&pi->node, root);
@@ -966,6 +981,7 @@ void ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
 
         dout(" obj extent %llu~%llu\n", *oxoff, *oxlen);
 }
+EXPORT_SYMBOL(ceph_calc_file_object_mapping);
 
 /*
  * calculate an object layout (i.e. pgid) from an oid,
@@ -1011,6 +1027,7 @@ int ceph_calc_object_layout(struct ceph_object_layout *ol,
         ol->ol_stripe_unit = fl->fl_object_stripe_unit;
         return 0;
 }
+EXPORT_SYMBOL(ceph_calc_object_layout);
 
 /*
  * Calculate raw osd vector for the given pgid.  Return pointer to osd
@@ -1108,3 +1125,4 @@ int ceph_calc_pg_primary(struct ceph_osdmap *osdmap, struct ceph_pg pgid)
                         return osds[i];
         return -1;
 }
+EXPORT_SYMBOL(ceph_calc_pg_primary);
diff --git a/net/ceph/pagelist.c b/net/ceph/pagelist.c
new file mode 100644
index 000000000000..13cb409a7bba
--- /dev/null
+++ b/net/ceph/pagelist.c
@@ -0,0 +1,154 @@
+
+#include <linux/module.h>
+#include <linux/gfp.h>
+#include <linux/pagemap.h>
+#include <linux/highmem.h>
+#include <linux/ceph/pagelist.h>
+
+static void ceph_pagelist_unmap_tail(struct ceph_pagelist *pl)
+{
+        if (pl->mapped_tail) {
+                struct page *page = list_entry(pl->head.prev, struct page, lru);
+                kunmap(page);
+                pl->mapped_tail = NULL;
+        }
+}
+
+int ceph_pagelist_release(struct ceph_pagelist *pl)
+{
+        ceph_pagelist_unmap_tail(pl);
+        while (!list_empty(&pl->head)) {
+                struct page *page = list_first_entry(&pl->head, struct page,
+                                                     lru);
+                list_del(&page->lru);
+                __free_page(page);
+        }
+        ceph_pagelist_free_reserve(pl);
+        return 0;
+}
+EXPORT_SYMBOL(ceph_pagelist_release);
+
+static int ceph_pagelist_addpage(struct ceph_pagelist *pl)
+{
+        struct page *page;
+
+        if (!pl->num_pages_free) {
+                page = __page_cache_alloc(GFP_NOFS);
+        } else {
+                page = list_first_entry(&pl->free_list, struct page, lru);
+                list_del(&page->lru);
+                --pl->num_pages_free;
+        }
+        if (!page)
+                return -ENOMEM;
+        pl->room += PAGE_SIZE;
+        ceph_pagelist_unmap_tail(pl);
+        list_add_tail(&page->lru, &pl->head);
+        pl->mapped_tail = kmap(page);
+        return 0;
+}
+
+int ceph_pagelist_append(struct ceph_pagelist *pl, const void *buf, size_t len)
+{
+        while (pl->room < len) {
+                size_t bit = pl->room;
+                int ret;
+
+                memcpy(pl->mapped_tail + (pl->length & ~PAGE_CACHE_MASK),
+                       buf, bit);
+                pl->length += bit;
+                pl->room -= bit;
+                buf += bit;
+                len -= bit;
+                ret = ceph_pagelist_addpage(pl);
+                if (ret)
+                        return ret;
+        }
+
+        memcpy(pl->mapped_tail + (pl->length & ~PAGE_CACHE_MASK), buf, len);
+        pl->length += len;
+        pl->room -= len;
+        return 0;
+}
+EXPORT_SYMBOL(ceph_pagelist_append);
+
+/**
+ * Allocate enough pages for a pagelist to append the given amount
+ * of data without without allocating.
+ * Returns: 0 on success, -ENOMEM on error.
+ */
+int ceph_pagelist_reserve(struct ceph_pagelist *pl, size_t space)
+{
+        if (space <= pl->room)
+                return 0;
+        space -= pl->room;
+        space = (space + PAGE_SIZE - 1) >> PAGE_SHIFT;   /* conv to num pages */
+
+        while (space > pl->num_pages_free) {
+                struct page *page = __page_cache_alloc(GFP_NOFS);
+                if (!page)
+                        return -ENOMEM;
+                list_add_tail(&page->lru, &pl->free_list);
+                ++pl->num_pages_free;
+        }
+        return 0;
+}
+EXPORT_SYMBOL(ceph_pagelist_reserve);
+
+/**
+ * Free any pages that have been preallocated.
+ */
+int ceph_pagelist_free_reserve(struct ceph_pagelist *pl)
+{
+        while (!list_empty(&pl->free_list)) {
+                struct page *page = list_first_entry(&pl->free_list,
+                                                     struct page, lru);
+                list_del(&page->lru);
+                __free_page(page);
+                --pl->num_pages_free;
+        }
+        BUG_ON(pl->num_pages_free);
+        return 0;
+}
+EXPORT_SYMBOL(ceph_pagelist_free_reserve);
+
+/**
+ * Create a truncation point.
+ */
+void ceph_pagelist_set_cursor(struct ceph_pagelist *pl,
+                              struct ceph_pagelist_cursor *c)
+{
+        c->pl = pl;
+        c->page_lru = pl->head.prev;
+        c->room = pl->room;
+}
+EXPORT_SYMBOL(ceph_pagelist_set_cursor);
+
+/**
+ * Truncate a pagelist to the given point. Move extra pages to reserve.
+ * This won't sleep.
+ * Returns: 0 on success,
+ *          -EINVAL if the pagelist doesn't match the trunc point pagelist
+ */
+int ceph_pagelist_truncate(struct ceph_pagelist *pl,
+                           struct ceph_pagelist_cursor *c)
+{
+        struct page *page;
+
+        if (pl != c->pl)
+                return -EINVAL;
+        ceph_pagelist_unmap_tail(pl);
+        while (pl->head.prev != c->page_lru) {
+                page = list_entry(pl->head.prev, struct page, lru);
+                list_del(&page->lru);                /* remove from pagelist */
+                list_add_tail(&page->lru, &pl->free_list); /* add to reserve */
+                ++pl->num_pages_free;
+        }
+        pl->room = c->room;
+        if (!list_empty(&pl->head)) {
+                page = list_entry(pl->head.prev, struct page, lru);
+                pl->mapped_tail = kmap(page);
+        }
+        return 0;
+}
+EXPORT_SYMBOL(ceph_pagelist_truncate);
diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c
new file mode 100644
index 000000000000..54caf0687155
--- /dev/null
+++ b/net/ceph/pagevec.c
@@ -0,0 +1,223 @@
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/file.h>
+#include <linux/namei.h>
+#include <linux/writeback.h>
+
+#include <linux/ceph/libceph.h>
+
+/*
+ * build a vector of user pages
+ */
+struct page **ceph_get_direct_page_vector(const char __user *data,
+                                                 int num_pages,
+                                                 loff_t off, size_t len)
+{
+        struct page **pages;
+        int rc;
+
+        pages = kmalloc(sizeof(*pages) * num_pages, GFP_NOFS);
+        if (!pages)
+                return ERR_PTR(-ENOMEM);
+
+        down_read(&current->mm->mmap_sem);
+        rc = get_user_pages(current, current->mm, (unsigned long)data,
+                            num_pages, 0, 0, pages, NULL);
+        up_read(&current->mm->mmap_sem);
+        if (rc < 0)
+                goto fail;
+        return pages;
+
+fail:
+        kfree(pages);
+        return ERR_PTR(rc);
+}
+EXPORT_SYMBOL(ceph_get_direct_page_vector);
+
+void ceph_put_page_vector(struct page **pages, int num_pages)
+{
+        int i;
+
+        for (i = 0; i < num_pages; i++)
+                put_page(pages[i]);
+        kfree(pages);
+}
+EXPORT_SYMBOL(ceph_put_page_vector);
+
+void ceph_release_page_vector(struct page **pages, int num_pages)
+{
+        int i;
+
+        for (i = 0; i < num_pages; i++)
+                __free_pages(pages[i], 0);
+        kfree(pages);
+}
+EXPORT_SYMBOL(ceph_release_page_vector);
+
+/*
+ * allocate a vector new pages
+ */
+struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags)
+{
+        struct page **pages;
+        int i;
+
+        pages = kmalloc(sizeof(*pages) * num_pages, flags);
+        if (!pages)
+                return ERR_PTR(-ENOMEM);
+        for (i = 0; i < num_pages; i++) {
+                pages[i] = __page_cache_alloc(flags);
+                if (pages[i] == NULL) {
+                        ceph_release_page_vector(pages, i);
+                        return ERR_PTR(-ENOMEM);
+                }
+        }
+        return pages;
+}
+EXPORT_SYMBOL(ceph_alloc_page_vector);
+
+/*
+ * copy user data into a page vector
+ */
+int ceph_copy_user_to_page_vector(struct page **pages,
+                                         const char __user *data,
+                                         loff_t off, size_t len)
+{
+        int i = 0;
+        int po = off & ~PAGE_CACHE_MASK;
+        int left = len;
+        int l, bad;
+
+        while (left > 0) {
+                l = min_t(int, PAGE_CACHE_SIZE-po, left);
+                bad = copy_from_user(page_address(pages[i]) + po, data, l);
+                if (bad == l)
+                        return -EFAULT;
+                data += l - bad;
+                left -= l - bad;
+                po += l - bad;
+                if (po == PAGE_CACHE_SIZE) {
+                        po = 0;
+                        i++;
+                }
+        }
+        return len;
+}
+EXPORT_SYMBOL(ceph_copy_user_to_page_vector);
+
+int ceph_copy_to_page_vector(struct page **pages,
+                                    const char *data,
+                                    loff_t off, size_t len)
+{
+        int i = 0;
+        size_t po = off & ~PAGE_CACHE_MASK;
+        size_t left = len;
+        size_t l;
+
+        while (left > 0) {
+                l = min_t(size_t, PAGE_CACHE_SIZE-po, left);
+                memcpy(page_address(pages[i]) + po, data, l);
+                data += l;
+                left -= l;
+                po += l;
+                if (po == PAGE_CACHE_SIZE) {
+                        po = 0;
+                        i++;
+                }
+        }
+        return len;
+}
+EXPORT_SYMBOL(ceph_copy_to_page_vector);
+
+int ceph_copy_from_page_vector(struct page **pages,
+                                    char *data,
+                                    loff_t off, size_t len)
+{
+        int i = 0;
+        size_t po = off & ~PAGE_CACHE_MASK;
+        size_t left = len;
+        size_t l;
+
+        while (left > 0) {
+                l = min_t(size_t, PAGE_CACHE_SIZE-po, left);
+                memcpy(data, page_address(pages[i]) + po, l);
+                data += l;
+                left -= l;
+                po += l;
+                if (po == PAGE_CACHE_SIZE) {
+                        po = 0;
+                        i++;
+                }
+        }
+        return len;
+}
+EXPORT_SYMBOL(ceph_copy_from_page_vector);
+
+/*
+ * copy user data from a page vector into a user pointer
+ */
+int ceph_copy_page_vector_to_user(struct page **pages,
+                                         char __user *data,
+                                         loff_t off, size_t len)
+{
+        int i = 0;
+        int po = off & ~PAGE_CACHE_MASK;
+        int left = len;
+        int l, bad;
+
+        while (left > 0) {
+                l = min_t(int, left, PAGE_CACHE_SIZE-po);
+                bad = copy_to_user(data, page_address(pages[i]) + po, l);
+                if (bad == l)
+                        return -EFAULT;
+                data += l - bad;
+                left -= l - bad;
+                if (po) {
+                        po += l - bad;
+                        if (po == PAGE_CACHE_SIZE)
+                                po = 0;
+                }
+                i++;
+        }
+        return len;
+}
+EXPORT_SYMBOL(ceph_copy_page_vector_to_user);
+
+/*
+ * Zero an extent within a page vector.  Offset is relative to the
+ * start of the first page.
+ */
+void ceph_zero_page_vector_range(int off, int len, struct page **pages)
+{
+        int i = off >> PAGE_CACHE_SHIFT;
+
+        off &= ~PAGE_CACHE_MASK;
+
+        dout("zero_page_vector_page %u~%u\n", off, len);
+
+        /* leading partial page? */
+        if (off) {
+                int end = min((int)PAGE_CACHE_SIZE, off + len);
+                dout("zeroing %d %p head from %d\n", i, pages[i],
+                     (int)off);
+                zero_user_segment(pages[i], off, end);
+                len -= (end - off);
+                i++;
+        }
+        while (len >= PAGE_CACHE_SIZE) {
+                dout("zeroing %d %p len=%d\n", i, pages[i], len);
+                zero_user_segment(pages[i], 0, PAGE_CACHE_SIZE);
+                len -= PAGE_CACHE_SIZE;
+                i++;
+        }
+        /* trailing partial page? */
+        if (len) {
+                dout("zeroing %d %p tail to %d\n", i, pages[i], (int)len);
+                zero_user_segment(pages[i], 0, len);
+        }
+}
+EXPORT_SYMBOL(ceph_zero_page_vector_range);
+
diff --git a/net/core/sock.c b/net/core/sock.c
index ef30e9d286e7..7d99e13148e6 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1078,8 +1078,11 @@ static void sk_prot_free(struct proto *prot, struct sock *sk)
 #ifdef CONFIG_CGROUPS
 void sock_update_classid(struct sock *sk)
 {
-        u32 classid = task_cls_classid(current);
+        u32 classid;
 
+        rcu_read_lock();  /* doing current task, which cannot vanish. */
+        classid = task_cls_classid(current);
+        rcu_read_unlock();
         if (classid && classid != sk->sk_classid)
                 sk->sk_classid = classid;
 }
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
index 244f7cb08d68..37f8adb68c79 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
@@ -11,6 +11,7 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/percpu.h>
+#include <linux/security.h>
 #include <net/net_namespace.h>
 
 #include <linux/netfilter.h>
@@ -87,6 +88,29 @@ static void ct_seq_stop(struct seq_file *s, void *v)
         rcu_read_unlock();
 }
 
+#ifdef CONFIG_NF_CONNTRACK_SECMARK
+static int ct_show_secctx(struct seq_file *s, const struct nf_conn *ct)
+{
+        int ret;
+        u32 len;
+        char *secctx;
+
+        ret = security_secid_to_secctx(ct->secmark, &secctx, &len);
+        if (ret)
+                return ret;
+
+        ret = seq_printf(s, "secctx=%s ", secctx);
+
+        security_release_secctx(secctx, len);
+        return ret;
+}
+#else
+static inline int ct_show_secctx(struct seq_file *s, const struct nf_conn *ct)
+{
+        return 0;
+}
+#endif
+
 static int ct_seq_show(struct seq_file *s, void *v)
 {
         struct nf_conntrack_tuple_hash *hash = v;
@@ -148,10 +172,8 @@ static int ct_seq_show(struct seq_file *s, void *v)
                 goto release;
 #endif
 
-#ifdef CONFIG_NF_CONNTRACK_SECMARK
-        if (seq_printf(s, "secmark=%u ", ct->secmark))
+        if (ct_show_secctx(s, ct))
                 goto release;
-#endif
 
         if (seq_printf(s, "use=%u\n", atomic_read(&ct->ct_general.use)))
                 goto release;
diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c
index 8c8632d9b93c..957c9241fb0c 100644
--- a/net/ipv4/netfilter/nf_nat_core.c
+++ b/net/ipv4/netfilter/nf_nat_core.c
@@ -38,7 +38,7 @@ static DEFINE_SPINLOCK(nf_nat_lock);
 static struct nf_conntrack_l3proto *l3proto __read_mostly;
 
 #define MAX_IP_NAT_PROTO 256
-static const struct nf_nat_protocol *nf_nat_protos[MAX_IP_NAT_PROTO]
+static const struct nf_nat_protocol __rcu *nf_nat_protos[MAX_IP_NAT_PROTO]
                                                 __read_mostly;
 
 static inline const struct nf_nat_protocol *
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 78b505d33bfb..fdaec7daff1d 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -27,7 +27,7 @@
 
 static DEFINE_MUTEX(afinfo_mutex);
 
-const struct nf_afinfo *nf_afinfo[NFPROTO_NUMPROTO] __read_mostly;
+const struct nf_afinfo __rcu *nf_afinfo[NFPROTO_NUMPROTO] __read_mostly;
 EXPORT_SYMBOL(nf_afinfo);
 
 int nf_register_afinfo(const struct nf_afinfo *afinfo)
diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c
index cdcc7649476b..5702de35e2bb 100644
--- a/net/netfilter/nf_conntrack_ecache.c
+++ b/net/netfilter/nf_conntrack_ecache.c
@@ -26,10 +26,10 @@
 
 static DEFINE_MUTEX(nf_ct_ecache_mutex);
 
-struct nf_ct_event_notifier *nf_conntrack_event_cb __read_mostly;
+struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb __read_mostly;
 EXPORT_SYMBOL_GPL(nf_conntrack_event_cb);
 
-struct nf_exp_event_notifier *nf_expect_event_cb __read_mostly;
+struct nf_exp_event_notifier __rcu *nf_expect_event_cb __read_mostly;
 EXPORT_SYMBOL_GPL(nf_expect_event_cb);
 
 /* deliver cached events and clear cache entry - must be called with locally
diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c
index 8d9e4c949b96..bd82450c193f 100644
--- a/net/netfilter/nf_conntrack_extend.c
+++ b/net/netfilter/nf_conntrack_extend.c
@@ -16,7 +16,7 @@
 #include <linux/skbuff.h>
 #include <net/netfilter/nf_conntrack_extend.h>
 
-static struct nf_ct_ext_type *nf_ct_ext_types[NF_CT_EXT_NUM];
+static struct nf_ct_ext_type __rcu *nf_ct_ext_types[NF_CT_EXT_NUM];
 static DEFINE_MUTEX(nf_ct_ext_type_mutex);
 
 void __nf_ct_ext_destroy(struct nf_conn *ct)
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 5bae1cd15eea..146476c6441a 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -22,6 +22,7 @@
 #include <linux/rculist_nulls.h>
 #include <linux/types.h>
 #include <linux/timer.h>
+#include <linux/security.h>
 #include <linux/skbuff.h>
 #include <linux/errno.h>
 #include <linux/netlink.h>
@@ -245,16 +246,31 @@ nla_put_failure:
 
 #ifdef CONFIG_NF_CONNTRACK_SECMARK
 static inline int
-ctnetlink_dump_secmark(struct sk_buff *skb, const struct nf_conn *ct)
+ctnetlink_dump_secctx(struct sk_buff *skb, const struct nf_conn *ct)
 {
-        NLA_PUT_BE32(skb, CTA_SECMARK, htonl(ct->secmark));
-        return 0;
+        struct nlattr *nest_secctx;
+        int len, ret;
+        char *secctx;
+
+        ret = security_secid_to_secctx(ct->secmark, &secctx, &len);
+        if (ret)
+                return ret;
+
+        ret = -1;
+        nest_secctx = nla_nest_start(skb, CTA_SECCTX | NLA_F_NESTED);
+        if (!nest_secctx)
+                goto nla_put_failure;
+
+        NLA_PUT_STRING(skb, CTA_SECCTX_NAME, secctx);
+        nla_nest_end(skb, nest_secctx);
 
+        ret = 0;
 nla_put_failure:
-        return -1;
+        security_release_secctx(secctx, len);
+        return ret;
 }
 #else
-#define ctnetlink_dump_secmark(a, b) (0)
+#define ctnetlink_dump_secctx(a, b) (0)
 #endif
 
 #define master_tuple(ct) &(ct->master->tuplehash[IP_CT_DIR_ORIGINAL].tuple)
@@ -391,7 +407,7 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 pid, u32 seq,
             ctnetlink_dump_protoinfo(skb, ct) < 0 ||
             ctnetlink_dump_helpinfo(skb, ct) < 0 ||
             ctnetlink_dump_mark(skb, ct) < 0 ||
-            ctnetlink_dump_secmark(skb, ct) < 0 ||
+            ctnetlink_dump_secctx(skb, ct) < 0 ||
             ctnetlink_dump_id(skb, ct) < 0 ||
             ctnetlink_dump_use(skb, ct) < 0 ||
             ctnetlink_dump_master(skb, ct) < 0 ||
@@ -437,6 +453,17 @@ ctnetlink_counters_size(const struct nf_conn *ct)
                ;
 }
 
+#ifdef CONFIG_NF_CONNTRACK_SECMARK
+static int ctnetlink_nlmsg_secctx_size(const struct nf_conn *ct)
+{
+        int len;
+
+        security_secid_to_secctx(ct->secmark, NULL, &len);
+
+        return sizeof(char) * len;
+}
+#endif
+
 static inline size_t
 ctnetlink_nlmsg_size(const struct nf_conn *ct)
 {
@@ -453,7 +480,8 @@ ctnetlink_nlmsg_size(const struct nf_conn *ct)
                + nla_total_size(0) /* CTA_HELP */
                + nla_total_size(NF_CT_HELPER_NAME_LEN) /* CTA_HELP_NAME */
 #ifdef CONFIG_NF_CONNTRACK_SECMARK
-               + nla_total_size(sizeof(u_int32_t)) /* CTA_SECMARK */
+               + nla_total_size(0) /* CTA_SECCTX */
+               + nla_total_size(ctnetlink_nlmsg_secctx_size(ct)) /* CTA_SECCTX_NAME */
 #endif
 #ifdef CONFIG_NF_NAT_NEEDED
                + 2 * nla_total_size(0) /* CTA_NAT_SEQ_ADJ_ORIG|REPL */
@@ -556,7 +584,7 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item)
 
 #ifdef CONFIG_NF_CONNTRACK_SECMARK
                 if ((events & (1 << IPCT_SECMARK) || ct->secmark)
-                    && ctnetlink_dump_secmark(skb, ct) < 0)
+                    && ctnetlink_dump_secctx(skb, ct) < 0)
                         goto nla_put_failure;
 #endif
 
diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index 5886ba1d52a0..ed6d92958023 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -28,8 +28,8 @@
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_core.h>
 
-static struct nf_conntrack_l4proto **nf_ct_protos[PF_MAX] __read_mostly;
-struct nf_conntrack_l3proto *nf_ct_l3protos[AF_MAX] __read_mostly;
+static struct nf_conntrack_l4proto __rcu **nf_ct_protos[PF_MAX] __read_mostly;
+struct nf_conntrack_l3proto __rcu *nf_ct_l3protos[AF_MAX] __read_mostly;
 EXPORT_SYMBOL_GPL(nf_ct_l3protos);
 
 static DEFINE_MUTEX(nf_ct_proto_mutex);
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index eb973fcd67ab..0fb65705b44b 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -15,6 +15,7 @@
 #include <linux/seq_file.h>
 #include <linux/percpu.h>
 #include <linux/netdevice.h>
+#include <linux/security.h>
 #include <net/net_namespace.h>
 #ifdef CONFIG_SYSCTL
 #include <linux/sysctl.h>
@@ -108,6 +109,29 @@ static void ct_seq_stop(struct seq_file *s, void *v)
         rcu_read_unlock();
 }
 
+#ifdef CONFIG_NF_CONNTRACK_SECMARK
+static int ct_show_secctx(struct seq_file *s, const struct nf_conn *ct)
+{
+        int ret;
+        u32 len;
+        char *secctx;
+
+        ret = security_secid_to_secctx(ct->secmark, &secctx, &len);
+        if (ret)
+                return ret;
+
+        ret = seq_printf(s, "secctx=%s ", secctx);
+
+        security_release_secctx(secctx, len);
+        return ret;
+}
+#else
+static inline int ct_show_secctx(struct seq_file *s, const struct nf_conn *ct)
+{
+        return 0;
+}
+#endif
+
 /* return 0 on success, 1 in case of error */
 static int ct_seq_show(struct seq_file *s, void *v)
 {
@@ -168,10 +192,8 @@ static int ct_seq_show(struct seq_file *s, void *v)
                 goto release;
 #endif
 
-#ifdef CONFIG_NF_CONNTRACK_SECMARK
-        if (seq_printf(s, "secmark=%u ", ct->secmark))
+        if (ct_show_secctx(s, ct))
                 goto release;
-#endif
 
 #ifdef CONFIG_NF_CONNTRACK_ZONES
         if (seq_printf(s, "zone=%u ", nf_ct_zone(ct)))
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index 7df37fd786bc..b07393eab88e 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -16,7 +16,7 @@
 #define NF_LOG_PREFIXLEN                128
 #define NFLOGGER_NAME_LEN               64
 
-static const struct nf_logger *nf_loggers[NFPROTO_NUMPROTO] __read_mostly;
+static const struct nf_logger __rcu *nf_loggers[NFPROTO_NUMPROTO] __read_mostly;
 static struct list_head nf_loggers_l[NFPROTO_NUMPROTO] __read_mostly;
 static DEFINE_MUTEX(nf_log_mutex);
 
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 78b3cf9c519c..74aebed5bd28 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -18,7 +18,7 @@
  * long term mutex.  The handler must provide an an outfn() to accept packets
  * for queueing and must reinject all packets it receives, no matter what.
  */
-static const struct nf_queue_handler *queue_handler[NFPROTO_NUMPROTO] __read_mostly;
+static const struct nf_queue_handler __rcu *queue_handler[NFPROTO_NUMPROTO] __read_mostly;
 
 static DEFINE_MUTEX(queue_handler_mutex);
 
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index 0cb6053f02fd..782e51986a6f 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -9,7 +9,6 @@
 #include <linux/module.h>
 #include <linux/gfp.h>
 #include <linux/skbuff.h>
-#include <linux/selinux.h>
 #include <linux/netfilter_ipv4/ip_tables.h>
 #include <linux/netfilter_ipv6/ip6_tables.h>
 #include <linux/netfilter/x_tables.h>
diff --git a/net/netfilter/xt_SECMARK.c b/net/netfilter/xt_SECMARK.c
index 23b2d6c486b5..9faf5e050b79 100644
--- a/net/netfilter/xt_SECMARK.c
+++ b/net/netfilter/xt_SECMARK.c
@@ -14,8 +14,8 @@
  */
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 #include <linux/module.h>
+#include <linux/security.h>
 #include <linux/skbuff.h>
-#include <linux/selinux.h>
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter/xt_SECMARK.h>
 
@@ -39,9 +39,8 @@ secmark_tg(struct sk_buff *skb, const struct xt_action_param *par)
 
         switch (mode) {
         case SECMARK_MODE_SEL:
-                secmark = info->u.sel.selsid;
+                secmark = info->secid;
                 break;
-
         default:
                 BUG();
         }
@@ -50,33 +49,33 @@ secmark_tg(struct sk_buff *skb, const struct xt_action_param *par)
         return XT_CONTINUE;
 }
 
-static int checkentry_selinux(struct xt_secmark_target_info *info)
+static int checkentry_lsm(struct xt_secmark_target_info *info)
 {
         int err;
-        struct xt_secmark_target_selinux_info *sel = &info->u.sel;
 
-        sel->selctx[SECMARK_SELCTX_MAX - 1] = '\0';
+        info->secctx[SECMARK_SECCTX_MAX - 1] = '\0';
+        info->secid = 0;
 
-        err = selinux_string_to_sid(sel->selctx, &sel->selsid);
+        err = security_secctx_to_secid(info->secctx, strlen(info->secctx),
+                                       &info->secid);
         if (err) {
                 if (err == -EINVAL)
-                        pr_info("invalid SELinux context \'%s\'\n",
-                                sel->selctx);
+                        pr_info("invalid security context \'%s\'\n", info->secctx);
                 return err;
         }
 
-        if (!sel->selsid) {
-                pr_info("unable to map SELinux context \'%s\'\n", sel->selctx);
+        if (!info->secid) {
+                pr_info("unable to map security context \'%s\'\n", info->secctx);
                 return -ENOENT;
         }
 
-        err = selinux_secmark_relabel_packet_permission(sel->selsid);
+        err = security_secmark_relabel_packet(info->secid);
         if (err) {
                 pr_info("unable to obtain relabeling permission\n");
                 return err;
         }
 
-        selinux_secmark_refcount_inc();
+        security_secmark_refcount_inc();
         return 0;
 }
 
@@ -100,16 +99,16 @@ static int secmark_tg_check(const struct xt_tgchk_param *par)
 
         switch (info->mode) {
         case SECMARK_MODE_SEL:
-                err = checkentry_selinux(info);
-                if (err <= 0)
-                        return err;
                 break;
-
         default:
                 pr_info("invalid mode: %hu\n", info->mode);
                 return -EINVAL;
         }
 
+        err = checkentry_lsm(info);
+        if (err)
+                return err;
+
         if (!mode)
                 mode = info->mode;
         return 0;
@@ -119,7 +118,7 @@ static void secmark_tg_destroy(const struct xt_tgdtor_param *par)
 {
         switch (mode) {
         case SECMARK_MODE_SEL:
-                selinux_secmark_refcount_dec();
+                security_secmark_refcount_dec();
         }
 }
 
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index 78ef2c5e130b..37dff78e9cb1 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -123,7 +123,7 @@ static int cls_cgroup_classify(struct sk_buff *skb, struct tcf_proto *tp,
          * calls by looking at the number of nested bh disable calls because
          * softirqs always disables bh.
          */
-        if (softirq_count() != SOFTIRQ_OFFSET) {
+        if (in_serving_softirq()) {
                 /* If there is an sk_classid we'll use that. */
                 if (!skb->sk)
                         return -1;
diff --git a/security/apparmor/.gitignore b/security/apparmor/.gitignore
index 0a0a99f3b083..4d995aeaebc0 100644
--- a/security/apparmor/.gitignore
+++ b/security/apparmor/.gitignore
@@ -3,3 +3,4 @@
 #
 af_names.h
 capability_names.h
+rlim_names.h
diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c
index 7320331b44ab..544ff5837cb6 100644
--- a/security/apparmor/apparmorfs.c
+++ b/security/apparmor/apparmorfs.c
@@ -29,7 +29,7 @@
  * aa_simple_write_to_buffer - common routine for getting policy from user
  * @op: operation doing the user buffer copy
  * @userbuf: user buffer to copy data from  (NOT NULL)
- * @alloc_size: size of user buffer
+ * @alloc_size: size of user buffer (REQUIRES: @alloc_size >= @copy_size)
  * @copy_size: size of data to copy from user buffer
  * @pos: position write is at in the file (NOT NULL)
  *
@@ -42,6 +42,8 @@ static char *aa_simple_write_to_buffer(int op, const char __user *userbuf,
 {
         char *data;
 
+        BUG_ON(copy_size > alloc_size);
+
         if (*pos != 0)
                 /* only writes from pos 0, that is complete writes */
                 return ERR_PTR(-ESPIPE);
diff --git a/security/capability.c b/security/capability.c
index 95a6599a37bb..30ae00fbecd5 100644
--- a/security/capability.c
+++ b/security/capability.c
@@ -677,7 +677,18 @@ static void cap_inet_conn_established(struct sock *sk, struct sk_buff *skb)
 {
 }
 
+static int cap_secmark_relabel_packet(u32 secid)
+{
+        return 0;
+}
 
+static void cap_secmark_refcount_inc(void)
+{
+}
+
+static void cap_secmark_refcount_dec(void)
+{
+}
 
 static void cap_req_classify_flow(const struct request_sock *req,
                                   struct flowi *fl)
@@ -777,7 +788,8 @@ static int cap_secid_to_secctx(u32 secid, char **secdata, u32 *seclen)
 
 static int cap_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid)
 {
-        return -EOPNOTSUPP;
+        *secid = 0;
+        return 0;
 }
 
 static void cap_release_secctx(char *secdata, u32 seclen)
@@ -1018,6 +1030,9 @@ void __init security_fixup_ops(struct security_operations *ops)
         set_to_cap_if_null(ops, inet_conn_request);
         set_to_cap_if_null(ops, inet_csk_clone);
         set_to_cap_if_null(ops, inet_conn_established);
+        set_to_cap_if_null(ops, secmark_relabel_packet);
+        set_to_cap_if_null(ops, secmark_refcount_inc);
+        set_to_cap_if_null(ops, secmark_refcount_dec);
         set_to_cap_if_null(ops, req_classify_flow);
         set_to_cap_if_null(ops, tun_dev_create);
         set_to_cap_if_null(ops, tun_dev_post_create);
diff --git a/security/commoncap.c b/security/commoncap.c
index 9d172e6e330c..5e632b4857e4 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -719,14 +719,11 @@ static int cap_safe_nice(struct task_struct *p)
 /**
  * cap_task_setscheduler - Detemine if scheduler policy change is permitted
  * @p: The task to affect
- * @policy: The policy to effect
- * @lp: The parameters to the scheduling policy
  *
  * Detemine if the requested scheduler policy change is permitted for the
  * specified task, returning 0 if permission is granted, -ve if denied.
  */
-int cap_task_setscheduler(struct task_struct *p, int policy,
-                           struct sched_param *lp)
+int cap_task_setscheduler(struct task_struct *p)
 {
         return cap_safe_nice(p);
 }
diff --git a/security/security.c b/security/security.c
index c53949f17d9e..b50f472061a4 100644
--- a/security/security.c
+++ b/security/security.c
@@ -89,20 +89,12 @@ __setup("security=", choose_lsm);
  * Return true if:
  *      -The passed LSM is the one chosen by user at boot time,
  *      -or the passed LSM is configured as the default and the user did not
- *       choose an alternate LSM at boot time,
- *      -or there is no default LSM set and the user didn't specify a
- *       specific LSM and we're the first to ask for registration permission,
- *      -or the passed LSM is currently loaded.
+ *       choose an alternate LSM at boot time.
  * Otherwise, return false.
  */
 int __init security_module_enable(struct security_operations *ops)
 {
-        if (!*chosen_lsm)
-                strncpy(chosen_lsm, ops->name, SECURITY_NAME_MAX);
-        else if (strncmp(ops->name, chosen_lsm, SECURITY_NAME_MAX))
-                return 0;
-
-        return 1;
+        return !strcmp(ops->name, chosen_lsm);
 }
 
 /**
@@ -786,10 +778,9 @@ int security_task_setrlimit(struct task_struct *p, unsigned int resource,
         return security_ops->task_setrlimit(p, resource, new_rlim);
 }
 
-int security_task_setscheduler(struct task_struct *p,
-                                int policy, struct sched_param *lp)
+int security_task_setscheduler(struct task_struct *p)
 {
-        return security_ops->task_setscheduler(p, policy, lp);
+        return security_ops->task_setscheduler(p);
 }
 
 int security_task_getscheduler(struct task_struct *p)
@@ -1145,6 +1136,24 @@ void security_inet_conn_established(struct sock *sk,
         security_ops->inet_conn_established(sk, skb);
 }
 
+int security_secmark_relabel_packet(u32 secid)
+{
+        return security_ops->secmark_relabel_packet(secid);
+}
+EXPORT_SYMBOL(security_secmark_relabel_packet);
+
+void security_secmark_refcount_inc(void)
+{
+        security_ops->secmark_refcount_inc();
+}
+EXPORT_SYMBOL(security_secmark_refcount_inc);
+
+void security_secmark_refcount_dec(void)
+{
+        security_ops->secmark_refcount_dec();
+}
+EXPORT_SYMBOL(security_secmark_refcount_dec);
+
 int security_tun_dev_create(void)
 {
         return security_ops->tun_dev_create();
diff --git a/security/selinux/Makefile b/security/selinux/Makefile
index 58d80f3bd6f6..ad5cd76ec231 100644
--- a/security/selinux/Makefile
+++ b/security/selinux/Makefile
@@ -2,25 +2,20 @@
 # Makefile for building the SELinux module as part of the kernel tree.
 #
 
-obj-$(CONFIG_SECURITY_SELINUX) := selinux.o ss/
-
-selinux-y := avc.o \
-             hooks.o \
-             selinuxfs.o \
-             netlink.o \
-             nlmsgtab.o \
-             netif.o \
-             netnode.o \
-             netport.o \
-             exports.o
+obj-$(CONFIG_SECURITY_SELINUX) := selinux.o
+
+selinux-y := avc.o hooks.o selinuxfs.o netlink.o nlmsgtab.o netif.o \
+             netnode.o netport.o exports.o \
+             ss/ebitmap.o ss/hashtab.o ss/symtab.o ss/sidtab.o ss/avtab.o \
+             ss/policydb.o ss/services.o ss/conditional.o ss/mls.o ss/status.o
 
 selinux-$(CONFIG_SECURITY_NETWORK_XFRM) += xfrm.o
 
 selinux-$(CONFIG_NETLABEL) += netlabel.o
 
-EXTRA_CFLAGS += -Isecurity/selinux -Isecurity/selinux/include
+ccflags-y := -Isecurity/selinux -Isecurity/selinux/include
 
-$(obj)/avc.o: $(obj)/flask.h
+$(addprefix $(obj)/,$(selinux-y)): $(obj)/flask.h
 
 quiet_cmd_flask = GEN     $(obj)/flask.h $(obj)/av_permissions.h
       cmd_flask = scripts/selinux/genheaders/genheaders $(obj)/flask.h $(obj)/av_permissions.h
diff --git a/security/selinux/exports.c b/security/selinux/exports.c
index c0a454aee1e0..90664385dead 100644
--- a/security/selinux/exports.c
+++ b/security/selinux/exports.c
@@ -11,58 +11,9 @@
  * it under the terms of the GNU General Public License version 2,
  * as published by the Free Software Foundation.
  */
-#include <linux/types.h>
-#include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/selinux.h>
-#include <linux/fs.h>
-#include <linux/ipc.h>
-#include <asm/atomic.h>
 
 #include "security.h"
-#include "objsec.h"
-
-/* SECMARK reference count */
-extern atomic_t selinux_secmark_refcount;
-
-int selinux_string_to_sid(char *str, u32 *sid)
-{
-        if (selinux_enabled)
-                return security_context_to_sid(str, strlen(str), sid);
-        else {
-                *sid = 0;
-                return 0;
-        }
-}
-EXPORT_SYMBOL_GPL(selinux_string_to_sid);
-
-int selinux_secmark_relabel_packet_permission(u32 sid)
-{
-        if (selinux_enabled) {
-                const struct task_security_struct *__tsec;
-                u32 tsid;
-
-                __tsec = current_security();
-                tsid = __tsec->sid;
-
-                return avc_has_perm(tsid, sid, SECCLASS_PACKET,
-                                    PACKET__RELABELTO, NULL);
-        }
-        return 0;
-}
-EXPORT_SYMBOL_GPL(selinux_secmark_relabel_packet_permission);
-
-void selinux_secmark_refcount_inc(void)
-{
-        atomic_inc(&selinux_secmark_refcount);
-}
-EXPORT_SYMBOL_GPL(selinux_secmark_refcount_inc);
-
-void selinux_secmark_refcount_dec(void)
-{
-        atomic_dec(&selinux_secmark_refcount);
-}
-EXPORT_SYMBOL_GPL(selinux_secmark_refcount_dec);
 
 bool selinux_is_enabled(void)
 {
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 4796ddd4e721..d9154cf90ae1 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -3354,11 +3354,11 @@ static int selinux_task_setrlimit(struct task_struct *p, unsigned int resource,
         return 0;
 }
 
-static int selinux_task_setscheduler(struct task_struct *p, int policy, struct sched_param *lp)
+static int selinux_task_setscheduler(struct task_struct *p)
 {
         int rc;
 
-        rc = cap_task_setscheduler(p, policy, lp);
+        rc = cap_task_setscheduler(p);
         if (rc)
                 return rc;
 
@@ -4279,6 +4279,27 @@ static void selinux_inet_conn_established(struct sock *sk, struct sk_buff *skb)
         selinux_skb_peerlbl_sid(skb, family, &sksec->peer_sid);
 }
 
+static int selinux_secmark_relabel_packet(u32 sid)
+{
+        const struct task_security_struct *__tsec;
+        u32 tsid;
+
+        __tsec = current_security();
+        tsid = __tsec->sid;
+
+        return avc_has_perm(tsid, sid, SECCLASS_PACKET, PACKET__RELABELTO, NULL);
+}
+
+static void selinux_secmark_refcount_inc(void)
+{
+        atomic_inc(&selinux_secmark_refcount);
+}
+
+static void selinux_secmark_refcount_dec(void)
+{
+        atomic_dec(&selinux_secmark_refcount);
+}
+
 static void selinux_req_classify_flow(const struct request_sock *req,
                                       struct flowi *fl)
 {
@@ -5533,6 +5554,9 @@ static struct security_operations selinux_ops = {
         .inet_conn_request =            selinux_inet_conn_request,
         .inet_csk_clone =               selinux_inet_csk_clone,
         .inet_conn_established =        selinux_inet_conn_established,
+        .secmark_relabel_packet =       selinux_secmark_relabel_packet,
+        .secmark_refcount_inc =         selinux_secmark_refcount_inc,
+        .secmark_refcount_dec =         selinux_secmark_refcount_dec,
         .req_classify_flow =            selinux_req_classify_flow,
         .tun_dev_create =               selinux_tun_dev_create,
         .tun_dev_post_create =          selinux_tun_dev_post_create,
diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h
index b4c9eb4bd6f9..8858d2b2d4b6 100644
--- a/security/selinux/include/classmap.h
+++ b/security/selinux/include/classmap.h
@@ -17,7 +17,7 @@ struct security_class_mapping secclass_map[] = {
           { "compute_av", "compute_create", "compute_member",
             "check_context", "load_policy", "compute_relabel",
             "compute_user", "setenforce", "setbool", "setsecparam",
-            "setcheckreqprot", NULL } },
+            "setcheckreqprot", "read_policy", NULL } },
         { "process",
           { "fork", "transition", "sigchld", "sigkill",
             "sigstop", "signull", "signal", "ptrace", "getsched", "setsched",
diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h
index 1f7c2491d3dc..671273eb1115 100644
--- a/security/selinux/include/security.h
+++ b/security/selinux/include/security.h
@@ -9,6 +9,7 @@
 #define _SELINUX_SECURITY_H_
 
 #include <linux/magic.h>
+#include <linux/types.h>
 #include "flask.h"
 
 #define SECSID_NULL                     0x00000000 /* unspecified SID */
@@ -82,6 +83,8 @@ extern int selinux_policycap_openperm;
 int security_mls_enabled(void);
 
 int security_load_policy(void *data, size_t len);
+int security_read_policy(void **data, ssize_t *len);
+size_t security_policydb_len(void);
 
 int security_policycap_supported(unsigned int req_cap);
 
@@ -191,5 +194,25 @@ static inline int security_netlbl_sid_to_secattr(u32 sid,
 
 const char *security_get_initial_sid_context(u32 sid);
 
+/*
+ * status notifier using mmap interface
+ */
+extern struct page *selinux_kernel_status_page(void);
+
+#define SELINUX_KERNEL_STATUS_VERSION   1
+struct selinux_kernel_status {
+        u32     version;        /* version number of thie structure */
+        u32     sequence;       /* sequence number of seqlock logic */
+        u32     enforcing;      /* current setting of enforcing mode */
+        u32     policyload;     /* times of policy reloaded */
+        u32     deny_unknown;   /* current setting of deny_unknown */
+        /*
+         * The version > 0 supports above members.
+         */
+} __attribute__((packed));
+
+extern void selinux_status_update_setenforce(int enforcing);
+extern void selinux_status_update_policyload(int seqno);
+
 #endif /* _SELINUX_SECURITY_H_ */
 
diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c
index 79a1bb635662..87e0556bae70 100644
--- a/security/selinux/selinuxfs.c
+++ b/security/selinux/selinuxfs.c
@@ -68,6 +68,8 @@ static int *bool_pending_values;
 static struct dentry *class_dir;
 static unsigned long last_class_ino;
 
+static char policy_opened;
+
 /* global data for policy capabilities */
 static struct dentry *policycap_dir;
 
@@ -110,6 +112,8 @@ enum sel_inos {
         SEL_COMPAT_NET, /* whether to use old compat network packet controls */
         SEL_REJECT_UNKNOWN, /* export unknown reject handling to userspace */
         SEL_DENY_UNKNOWN, /* export unknown deny handling to userspace */
+        SEL_STATUS,     /* export current status using mmap() */
+        SEL_POLICY,     /* allow userspace to read the in kernel policy */
         SEL_INO_NEXT,   /* The next inode number to use */
 };
 
@@ -171,6 +175,7 @@ static ssize_t sel_write_enforce(struct file *file, const char __user *buf,
                 if (selinux_enforcing)
                         avc_ss_reset(0);
                 selnl_notify_setenforce(selinux_enforcing);
+                selinux_status_update_setenforce(selinux_enforcing);
         }
         length = count;
 out:
@@ -205,6 +210,59 @@ static const struct file_operations sel_handle_unknown_ops = {
         .llseek         = generic_file_llseek,
 };
 
+static int sel_open_handle_status(struct inode *inode, struct file *filp)
+{
+        struct page    *status = selinux_kernel_status_page();
+
+        if (!status)
+                return -ENOMEM;
+
+        filp->private_data = status;
+
+        return 0;
+}
+
+static ssize_t sel_read_handle_status(struct file *filp, char __user *buf,
+                                      size_t count, loff_t *ppos)
+{
+        struct page    *status = filp->private_data;
+
+        BUG_ON(!status);
+
+        return simple_read_from_buffer(buf, count, ppos,
+                                       page_address(status),
+                                       sizeof(struct selinux_kernel_status));
+}
+
+static int sel_mmap_handle_status(struct file *filp,
+                                  struct vm_area_struct *vma)
+{
+        struct page    *status = filp->private_data;
+        unsigned long   size = vma->vm_end - vma->vm_start;
+
+        BUG_ON(!status);
+
+        /* only allows one page from the head */
+        if (vma->vm_pgoff > 0 || size != PAGE_SIZE)
+                return -EIO;
+        /* disallow writable mapping */
+        if (vma->vm_flags & VM_WRITE)
+                return -EPERM;
+        /* disallow mprotect() turns it into writable */
+        vma->vm_flags &= ~VM_MAYWRITE;
+
+        return remap_pfn_range(vma, vma->vm_start,
+                               page_to_pfn(status),
+                               size, vma->vm_page_prot);
+}
+
+static const struct file_operations sel_handle_status_ops = {
+        .open           = sel_open_handle_status,
+        .read           = sel_read_handle_status,
+        .mmap           = sel_mmap_handle_status,
+        .llseek         = generic_file_llseek,
+};
+
 #ifdef CONFIG_SECURITY_SELINUX_DISABLE
 static ssize_t sel_write_disable(struct file *file, const char __user *buf,
                                  size_t count, loff_t *ppos)
@@ -296,6 +354,141 @@ static const struct file_operations sel_mls_ops = {
         .llseek         = generic_file_llseek,
 };
 
+struct policy_load_memory {
+        size_t len;
+        void *data;
+};
+
+static int sel_open_policy(struct inode *inode, struct file *filp)
+{
+        struct policy_load_memory *plm = NULL;
+        int rc;
+
+        BUG_ON(filp->private_data);
+
+        mutex_lock(&sel_mutex);
+
+        rc = task_has_security(current, SECURITY__READ_POLICY);
+        if (rc)
+                goto err;
+
+        rc = -EBUSY;
+        if (policy_opened)
+                goto err;
+
+        rc = -ENOMEM;
+        plm = kzalloc(sizeof(*plm), GFP_KERNEL);
+        if (!plm)
+                goto err;
+
+        if (i_size_read(inode) != security_policydb_len()) {
+                mutex_lock(&inode->i_mutex);
+                i_size_write(inode, security_policydb_len());
+                mutex_unlock(&inode->i_mutex);
+        }
+
+        rc = security_read_policy(&plm->data, &plm->len);
+        if (rc)
+                goto err;
+
+        policy_opened = 1;
+
+        filp->private_data = plm;
+
+        mutex_unlock(&sel_mutex);
+
+        return 0;
+err:
+        mutex_unlock(&sel_mutex);
+
+        if (plm)
+                vfree(plm->data);
+        kfree(plm);
+        return rc;
+}
+
+static int sel_release_policy(struct inode *inode, struct file *filp)
+{
+        struct policy_load_memory *plm = filp->private_data;
+
+        BUG_ON(!plm);
+
+        policy_opened = 0;
+
+        vfree(plm->data);
+        kfree(plm);
+
+        return 0;
+}
+
+static ssize_t sel_read_policy(struct file *filp, char __user *buf,
+                               size_t count, loff_t *ppos)
+{
+        struct policy_load_memory *plm = filp->private_data;
+        int ret;
+
+        mutex_lock(&sel_mutex);
+
+        ret = task_has_security(current, SECURITY__READ_POLICY);
+        if (ret)
+                goto out;
+
+        ret = simple_read_from_buffer(buf, count, ppos, plm->data, plm->len);
+out:
+        mutex_unlock(&sel_mutex);
+        return ret;
+}
+
+static int sel_mmap_policy_fault(struct vm_area_struct *vma,
+                                 struct vm_fault *vmf)
+{
+        struct policy_load_memory *plm = vma->vm_file->private_data;
+        unsigned long offset;
+        struct page *page;
+
+        if (vmf->flags & (FAULT_FLAG_MKWRITE | FAULT_FLAG_WRITE))
+                return VM_FAULT_SIGBUS;
+
+        offset = vmf->pgoff << PAGE_SHIFT;
+        if (offset >= roundup(plm->len, PAGE_SIZE))
+                return VM_FAULT_SIGBUS;
+
+        page = vmalloc_to_page(plm->data + offset);
+        get_page(page);
+
+        vmf->page = page;
+
+        return 0;
+}
+
+static struct vm_operations_struct sel_mmap_policy_ops = {
+        .fault = sel_mmap_policy_fault,
+        .page_mkwrite = sel_mmap_policy_fault,
+};
+
+int sel_mmap_policy(struct file *filp, struct vm_area_struct *vma)
+{
+        if (vma->vm_flags & VM_SHARED) {
+                /* do not allow mprotect to make mapping writable */
+                vma->vm_flags &= ~VM_MAYWRITE;
+
+                if (vma->vm_flags & VM_WRITE)
+                        return -EACCES;
+        }
+
+        vma->vm_flags |= VM_RESERVED;
+        vma->vm_ops = &sel_mmap_policy_ops;
+
+        return 0;
+}
+
+static const struct file_operations sel_policy_ops = {
+        .open           = sel_open_policy,
+        .read           = sel_read_policy,
+        .mmap           = sel_mmap_policy,
+        .release        = sel_release_policy,
+};
+
 static ssize_t sel_write_load(struct file *file, const char __user *buf,
                               size_t count, loff_t *ppos)
 
@@ -1612,6 +1805,8 @@ static int sel_fill_super(struct super_block *sb, void *data, int silent)
                 [SEL_CHECKREQPROT] = {"checkreqprot", &sel_checkreqprot_ops, S_IRUGO|S_IWUSR},
                 [SEL_REJECT_UNKNOWN] = {"reject_unknown", &sel_handle_unknown_ops, S_IRUGO},
                 [SEL_DENY_UNKNOWN] = {"deny_unknown", &sel_handle_unknown_ops, S_IRUGO},
+                [SEL_STATUS] = {"status", &sel_handle_status_ops, S_IRUGO},
+                [SEL_POLICY] = {"policy", &sel_policy_ops, S_IRUSR},
                 /* last one */ {""}
         };
         ret = simple_fill_super(sb, SELINUX_MAGIC, selinux_files);
diff --git a/security/selinux/ss/Makefile b/security/selinux/ss/Makefile
deleted file mode 100644
index 15d4e62917de..000000000000
--- a/security/selinux/ss/Makefile
+++ /dev/null
@@ -1,9 +0,0 @@
-#
-# Makefile for building the SELinux security server as part of the kernel tree.
-#
-
-EXTRA_CFLAGS += -Isecurity/selinux -Isecurity/selinux/include
-obj-y := ss.o
-
-ss-y := ebitmap.o hashtab.o symtab.o sidtab.o avtab.o policydb.o services.o conditional.o mls.o
-
diff --git a/security/selinux/ss/avtab.c b/security/selinux/ss/avtab.c
index 929480c6c430..a3dd9faa19c0 100644
--- a/security/selinux/ss/avtab.c
+++ b/security/selinux/ss/avtab.c
@@ -266,8 +266,8 @@ int avtab_alloc(struct avtab *h, u32 nrules)
         if (shift > 2)
                 shift = shift - 2;
         nslot = 1 << shift;
-        if (nslot > MAX_AVTAB_SIZE)
-                nslot = MAX_AVTAB_SIZE;
+        if (nslot > MAX_AVTAB_HASH_BUCKETS)
+                nslot = MAX_AVTAB_HASH_BUCKETS;
         mask = nslot - 1;
 
         h->htable = kcalloc(nslot, sizeof(*(h->htable)), GFP_KERNEL);
@@ -501,6 +501,48 @@ bad:
         goto out;
 }
 
+int avtab_write_item(struct policydb *p, struct avtab_node *cur, void *fp)
+{
+        __le16 buf16[4];
+        __le32 buf32[1];
+        int rc;
+
+        buf16[0] = cpu_to_le16(cur->key.source_type);
+        buf16[1] = cpu_to_le16(cur->key.target_type);
+        buf16[2] = cpu_to_le16(cur->key.target_class);
+        buf16[3] = cpu_to_le16(cur->key.specified);
+        rc = put_entry(buf16, sizeof(u16), 4, fp);
+        if (rc)
+                return rc;
+        buf32[0] = cpu_to_le32(cur->datum.data);
+        rc = put_entry(buf32, sizeof(u32), 1, fp);
+        if (rc)
+                return rc;
+        return 0;
+}
+
+int avtab_write(struct policydb *p, struct avtab *a, void *fp)
+{
+        unsigned int i;
+        int rc = 0;
+        struct avtab_node *cur;
+        __le32 buf[1];
+
+        buf[0] = cpu_to_le32(a->nel);
+        rc = put_entry(buf, sizeof(u32), 1, fp);
+        if (rc)
+                return rc;
+
+        for (i = 0; i < a->nslot; i++) {
+                for (cur = a->htable[i]; cur; cur = cur->next) {
+                        rc = avtab_write_item(p, cur, fp);
+                        if (rc)
+                                return rc;
+                }
+        }
+
+        return rc;
+}
 void avtab_cache_init(void)
 {
         avtab_node_cachep = kmem_cache_create("avtab_node",
diff --git a/security/selinux/ss/avtab.h b/security/selinux/ss/avtab.h
index cd4f734e2749..dff0c75345c1 100644
--- a/security/selinux/ss/avtab.h
+++ b/security/selinux/ss/avtab.h
@@ -71,6 +71,8 @@ int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol,
                     void *p);
 
 int avtab_read(struct avtab *a, void *fp, struct policydb *pol);
+int avtab_write_item(struct policydb *p, struct avtab_node *cur, void *fp);
+int avtab_write(struct policydb *p, struct avtab *a, void *fp);
 
 struct avtab_node *avtab_insert_nonunique(struct avtab *h, struct avtab_key *key,
                                           struct avtab_datum *datum);
@@ -85,7 +87,6 @@ void avtab_cache_destroy(void);
 #define MAX_AVTAB_HASH_BITS 11
 #define MAX_AVTAB_HASH_BUCKETS (1 << MAX_AVTAB_HASH_BITS)
 #define MAX_AVTAB_HASH_MASK (MAX_AVTAB_HASH_BUCKETS-1)
-#define MAX_AVTAB_SIZE MAX_AVTAB_HASH_BUCKETS
 
 #endif  /* _SS_AVTAB_H_ */
 
diff --git a/security/selinux/ss/conditional.c b/security/selinux/ss/conditional.c
index c91e150c3087..655fe1c6cc69 100644
--- a/security/selinux/ss/conditional.c
+++ b/security/selinux/ss/conditional.c
@@ -490,6 +490,129 @@ err:
         return rc;
 }
 
+int cond_write_bool(void *vkey, void *datum, void *ptr)
+{
+        char *key = vkey;
+        struct cond_bool_datum *booldatum = datum;
+        struct policy_data *pd = ptr;
+        void *fp = pd->fp;
+        __le32 buf[3];
+        u32 len;
+        int rc;
+
+        len = strlen(key);
+        buf[0] = cpu_to_le32(booldatum->value);
+        buf[1] = cpu_to_le32(booldatum->state);
+        buf[2] = cpu_to_le32(len);
+        rc = put_entry(buf, sizeof(u32), 3, fp);
+        if (rc)
+                return rc;
+        rc = put_entry(key, 1, len, fp);
+        if (rc)
+                return rc;
+        return 0;
+}
+
+/*
+ * cond_write_cond_av_list doesn't write out the av_list nodes.
+ * Instead it writes out the key/value pairs from the avtab. This
+ * is necessary because there is no way to uniquely identifying rules
+ * in the avtab so it is not possible to associate individual rules
+ * in the avtab with a conditional without saving them as part of
+ * the conditional. This means that the avtab with the conditional
+ * rules will not be saved but will be rebuilt on policy load.
+ */
+static int cond_write_av_list(struct policydb *p,
+                              struct cond_av_list *list, struct policy_file *fp)
+{
+        __le32 buf[1];
+        struct cond_av_list *cur_list;
+        u32 len;
+        int rc;
+
+        len = 0;
+        for (cur_list = list; cur_list != NULL; cur_list = cur_list->next)
+                len++;
+
+        buf[0] = cpu_to_le32(len);
+        rc = put_entry(buf, sizeof(u32), 1, fp);
+        if (rc)
+                return rc;
+
+        if (len == 0)
+                return 0;
+
+        for (cur_list = list; cur_list != NULL; cur_list = cur_list->next) {
+                rc = avtab_write_item(p, cur_list->node, fp);
+                if (rc)
+                        return rc;
+        }
+
+        return 0;
+}
+
+int cond_write_node(struct policydb *p, struct cond_node *node,
+                    struct policy_file *fp)
+{
+        struct cond_expr *cur_expr;
+        __le32 buf[2];
+        int rc;
+        u32 len = 0;
+
+        buf[0] = cpu_to_le32(node->cur_state);
+        rc = put_entry(buf, sizeof(u32), 1, fp);
+        if (rc)
+                return rc;
+
+        for (cur_expr = node->expr; cur_expr != NULL; cur_expr = cur_expr->next)
+                len++;
+
+        buf[0] = cpu_to_le32(len);
+        rc = put_entry(buf, sizeof(u32), 1, fp);
+        if (rc)
+                return rc;
+
+        for (cur_expr = node->expr; cur_expr != NULL; cur_expr = cur_expr->next) {
+                buf[0] = cpu_to_le32(cur_expr->expr_type);
+                buf[1] = cpu_to_le32(cur_expr->bool);
+                rc = put_entry(buf, sizeof(u32), 2, fp);
+                if (rc)
+                        return rc;
+        }
+
+        rc = cond_write_av_list(p, node->true_list, fp);
+        if (rc)
+                return rc;
+        rc = cond_write_av_list(p, node->false_list, fp);
+        if (rc)
+                return rc;
+
+        return 0;
+}
+
+int cond_write_list(struct policydb *p, struct cond_node *list, void *fp)
+{
+        struct cond_node *cur;
+        u32 len;
+        __le32 buf[1];
+        int rc;
+
+        len = 0;
+        for (cur = list; cur != NULL; cur = cur->next)
+                len++;
+        buf[0] = cpu_to_le32(len);
+        rc = put_entry(buf, sizeof(u32), 1, fp);
+        if (rc)
+                return rc;
+
+        for (cur = list; cur != NULL; cur = cur->next) {
+                rc = cond_write_node(p, cur, fp);
+                if (rc)
+                        return rc;
+        }
+
+        return 0;
+}
 /* Determine whether additional permissions are granted by the conditional
  * av table, and if so, add them to the result
  */
diff --git a/security/selinux/ss/conditional.h b/security/selinux/ss/conditional.h
index 53ddb013ae57..3f209c635295 100644
--- a/security/selinux/ss/conditional.h
+++ b/security/selinux/ss/conditional.h
@@ -69,6 +69,8 @@ int cond_index_bool(void *key, void *datum, void *datap);
 
 int cond_read_bool(struct policydb *p, struct hashtab *h, void *fp);
 int cond_read_list(struct policydb *p, void *fp);
+int cond_write_bool(void *key, void *datum, void *ptr);
+int cond_write_list(struct policydb *p, struct cond_node *list, void *fp);
 
 void cond_compute_av(struct avtab *ctab, struct avtab_key *key, struct av_decision *avd);
 
diff --git a/security/selinux/ss/ebitmap.c b/security/selinux/ss/ebitmap.c
index 04b6145d767f..d42951fcbe87 100644
--- a/security/selinux/ss/ebitmap.c
+++ b/security/selinux/ss/ebitmap.c
@@ -22,6 +22,8 @@
 #include "ebitmap.h"
 #include "policydb.h"
 
+#define BITS_PER_U64    (sizeof(u64) * 8)
+
 int ebitmap_cmp(struct ebitmap *e1, struct ebitmap *e2)
 {
         struct ebitmap_node *n1, *n2;
@@ -363,10 +365,10 @@ int ebitmap_read(struct ebitmap *e, void *fp)
         e->highbit = le32_to_cpu(buf[1]);
         count = le32_to_cpu(buf[2]);
 
-        if (mapunit != sizeof(u64) * 8) {
+        if (mapunit != BITS_PER_U64) {
                 printk(KERN_ERR "SELinux: ebitmap: map size %u does not "
                        "match my size %Zd (high bit was %d)\n",
-                       mapunit, sizeof(u64) * 8, e->highbit);
+                       mapunit, BITS_PER_U64, e->highbit);
                 goto bad;
         }
 
@@ -446,3 +448,78 @@ bad:
         ebitmap_destroy(e);
         goto out;
 }
+
+int ebitmap_write(struct ebitmap *e, void *fp)
+{
+        struct ebitmap_node *n;
+        u32 count;
+        __le32 buf[3];
+        u64 map;
+        int bit, last_bit, last_startbit, rc;
+
+        buf[0] = cpu_to_le32(BITS_PER_U64);
+
+        count = 0;
+        last_bit = 0;
+        last_startbit = -1;
+        ebitmap_for_each_positive_bit(e, n, bit) {
+                if (rounddown(bit, (int)BITS_PER_U64) > last_startbit) {
+                        count++;
+                        last_startbit = rounddown(bit, BITS_PER_U64);
+                }
+                last_bit = roundup(bit + 1, BITS_PER_U64);
+        }
+        buf[1] = cpu_to_le32(last_bit);
+        buf[2] = cpu_to_le32(count);
+
+        rc = put_entry(buf, sizeof(u32), 3, fp);
+        if (rc)
+                return rc;
+
+        map = 0;
+        last_startbit = INT_MIN;
+        ebitmap_for_each_positive_bit(e, n, bit) {
+                if (rounddown(bit, (int)BITS_PER_U64) > last_startbit) {
+                        __le64 buf64[1];
+
+                        /* this is the very first bit */
+                        if (!map) {
+                                last_startbit = rounddown(bit, BITS_PER_U64);
+                                map = (u64)1 << (bit - last_startbit);
+                                continue;
+                        }
+
+                        /* write the last node */
+                        buf[0] = cpu_to_le32(last_startbit);
+                        rc = put_entry(buf, sizeof(u32), 1, fp);
+                        if (rc)
+                                return rc;
+
+                        buf64[0] = cpu_to_le64(map);
+                        rc = put_entry(buf64, sizeof(u64), 1, fp);
+                        if (rc)
+                                return rc;
+
+                        /* set up for the next node */
+                        map = 0;
+                        last_startbit = rounddown(bit, BITS_PER_U64);
+                }
+                map |= (u64)1 << (bit - last_startbit);
+        }
+        /* write the last node */
+        if (map) {
+                __le64 buf64[1];
+
+                /* write the last node */
+                buf[0] = cpu_to_le32(last_startbit);
+                rc = put_entry(buf, sizeof(u32), 1, fp);
+                if (rc)
+                        return rc;
+
+                buf64[0] = cpu_to_le64(map);
+                rc = put_entry(buf64, sizeof(u64), 1, fp);
+                if (rc)
+                        return rc;
+        }
+        return 0;
+}
diff --git a/security/selinux/ss/ebitmap.h b/security/selinux/ss/ebitmap.h
index f283b4367f54..1f4e93c2ae86 100644
--- a/security/selinux/ss/ebitmap.h
+++ b/security/selinux/ss/ebitmap.h
@@ -123,6 +123,7 @@ int ebitmap_get_bit(struct ebitmap *e, unsigned long bit);
 int ebitmap_set_bit(struct ebitmap *e, unsigned long bit, int value);
 void ebitmap_destroy(struct ebitmap *e);
 int ebitmap_read(struct ebitmap *e, void *fp);
+int ebitmap_write(struct ebitmap *e, void *fp);
 
 #ifdef CONFIG_NETLABEL
 int ebitmap_netlbl_export(struct ebitmap *ebmap,
diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c
index 3a29704be8ce..94f630d93a5c 100644
--- a/security/selinux/ss/policydb.c
+++ b/security/selinux/ss/policydb.c
@@ -37,6 +37,7 @@
 #include "policydb.h"
 #include "conditional.h"
 #include "mls.h"
+#include "services.h"
 
 #define _DEBUG_HASHES
 
@@ -185,9 +186,19 @@ static u32 rangetr_hash(struct hashtab *h, const void *k)
 static int rangetr_cmp(struct hashtab *h, const void *k1, const void *k2)
 {
         const struct range_trans *key1 = k1, *key2 = k2;
-        return (key1->source_type != key2->source_type ||
-                key1->target_type != key2->target_type ||
-                key1->target_class != key2->target_class);
+        int v;
+
+        v = key1->source_type - key2->source_type;
+        if (v)
+                return v;
+
+        v = key1->target_type - key2->target_type;
+        if (v)
+                return v;
+
+        v = key1->target_class - key2->target_class;
+
+        return v;
 }
 
 /*
@@ -1624,11 +1635,11 @@ static int role_bounds_sanity_check(void *key, void *datum, void *datap)
 
 static int type_bounds_sanity_check(void *key, void *datum, void *datap)
 {
-        struct type_datum *upper, *type;
+        struct type_datum *upper;
         struct policydb *p = datap;
         int depth = 0;
 
-        upper = type = datum;
+        upper = datum;
         while (upper->bounds) {
                 if (++depth == POLICYDB_BOUNDS_MAXDEPTH) {
                         printk(KERN_ERR "SELinux: type %s: "
@@ -2306,3 +2317,843 @@ bad:
         policydb_destroy(p);
         goto out;
 }
+
+/*
+ * Write a MLS level structure to a policydb binary
+ * representation file.
+ */
+static int mls_write_level(struct mls_level *l, void *fp)
+{
+        __le32 buf[1];
+        int rc;
+
+        buf[0] = cpu_to_le32(l->sens);
+        rc = put_entry(buf, sizeof(u32), 1, fp);
+        if (rc)
+                return rc;
+
+        rc = ebitmap_write(&l->cat, fp);
+        if (rc)
+                return rc;
+
+        return 0;
+}
+
+/*
+ * Write a MLS range structure to a policydb binary
+ * representation file.
+ */
+static int mls_write_range_helper(struct mls_range *r, void *fp)
+{
+        __le32 buf[3];
+        size_t items;
+        int rc, eq;
+
+        eq = mls_level_eq(&r->level[1], &r->level[0]);
+
+        if (eq)
+                items = 2;
+        else
+                items = 3;
+        buf[0] = cpu_to_le32(items-1);
+        buf[1] = cpu_to_le32(r->level[0].sens);
+        if (!eq)
+                buf[2] = cpu_to_le32(r->level[1].sens);
+
+        BUG_ON(items > (sizeof(buf)/sizeof(buf[0])));
+
+        rc = put_entry(buf, sizeof(u32), items, fp);
+        if (rc)
+                return rc;
+
+        rc = ebitmap_write(&r->level[0].cat, fp);
+        if (rc)
+                return rc;
+        if (!eq) {
+                rc = ebitmap_write(&r->level[1].cat, fp);
+                if (rc)
+                        return rc;
+        }
+
+        return 0;
+}
+
+static int sens_write(void *vkey, void *datum, void *ptr)
+{
+        char *key = vkey;
+        struct level_datum *levdatum = datum;
+        struct policy_data *pd = ptr;
+        void *fp = pd->fp;
+        __le32 buf[2];
+        size_t len;
+        int rc;
+
+        len = strlen(key);
+        buf[0] = cpu_to_le32(len);
+        buf[1] = cpu_to_le32(levdatum->isalias);
+        rc = put_entry(buf, sizeof(u32), 2, fp);
+        if (rc)
+                return rc;
+
+        rc = put_entry(key, 1, len, fp);
+        if (rc)
+                return rc;
+
+        rc = mls_write_level(levdatum->level, fp);
+        if (rc)
+                return rc;
+
+        return 0;
+}
+
+static int cat_write(void *vkey, void *datum, void *ptr)
+{
+        char *key = vkey;
+        struct cat_datum *catdatum = datum;
+        struct policy_data *pd = ptr;
+        void *fp = pd->fp;
+        __le32 buf[3];
+        size_t len;
+        int rc;
+
+        len = strlen(key);
+        buf[0] = cpu_to_le32(len);
+        buf[1] = cpu_to_le32(catdatum->value);
+        buf[2] = cpu_to_le32(catdatum->isalias);
+        rc = put_entry(buf, sizeof(u32), 3, fp);
+        if (rc)
+                return rc;
+
+        rc = put_entry(key, 1, len, fp);
+        if (rc)
+                return rc;
+
+        return 0;
+}
+
+static int role_trans_write(struct role_trans *r, void *fp)
+{
+        struct role_trans *tr;
+        u32 buf[3];
+        size_t nel;
+        int rc;
+
+        nel = 0;
+        for (tr = r; tr; tr = tr->next)
+                nel++;
+        buf[0] = cpu_to_le32(nel);
+        rc = put_entry(buf, sizeof(u32), 1, fp);
+        if (rc)
+                return rc;
+        for (tr = r; tr; tr = tr->next) {
+                buf[0] = cpu_to_le32(tr->role);
+                buf[1] = cpu_to_le32(tr->type);
+                buf[2] = cpu_to_le32(tr->new_role);
+                rc = put_entry(buf, sizeof(u32), 3, fp);
+                if (rc)
+                        return rc;
+        }
+
+        return 0;
+}
+
+static int role_allow_write(struct role_allow *r, void *fp)
+{
+        struct role_allow *ra;
+        u32 buf[2];
+        size_t nel;
+        int rc;
+
+        nel = 0;
+        for (ra = r; ra; ra = ra->next)
+                nel++;
+        buf[0] = cpu_to_le32(nel);
+        rc = put_entry(buf, sizeof(u32), 1, fp);
+        if (rc)
+                return rc;
+        for (ra = r; ra; ra = ra->next) {
+                buf[0] = cpu_to_le32(ra->role);
+                buf[1] = cpu_to_le32(ra->new_role);
+                rc = put_entry(buf, sizeof(u32), 2, fp);
+                if (rc)
+                        return rc;
+        }
+        return 0;
+}
+
+/*
+ * Write a security context structure
+ * to a policydb binary representation file.
+ */
+static int context_write(struct policydb *p, struct context *c,
+                         void *fp)
+{
+        int rc;
+        __le32 buf[3];
+
+        buf[0] = cpu_to_le32(c->user);
+        buf[1] = cpu_to_le32(c->role);
+        buf[2] = cpu_to_le32(c->type);
+
+        rc = put_entry(buf, sizeof(u32), 3, fp);
+        if (rc)
+                return rc;
+
+        rc = mls_write_range_helper(&c->range, fp);
+        if (rc)
+                return rc;
+
+        return 0;
+}
+
+/*
+ * The following *_write functions are used to
+ * write the symbol data to a policy database
+ * binary representation file.
+ */
+
+static int perm_write(void *vkey, void *datum, void *fp)
+{
+        char *key = vkey;
+        struct perm_datum *perdatum = datum;
+        __le32 buf[2];
+        size_t len;
+        int rc;
+
+        len = strlen(key);
+        buf[0] = cpu_to_le32(len);
+        buf[1] = cpu_to_le32(perdatum->value);
+        rc = put_entry(buf, sizeof(u32), 2, fp);
+        if (rc)
+                return rc;
+
+        rc = put_entry(key, 1, len, fp);
+        if (rc)
+                return rc;
+
+        return 0;
+}
+
+static int common_write(void *vkey, void *datum, void *ptr)
+{
+        char *key = vkey;
+        struct common_datum *comdatum = datum;
+        struct policy_data *pd = ptr;
+        void *fp = pd->fp;
+        __le32 buf[4];
+        size_t len;
+        int rc;
+
+        len = strlen(key);
+        buf[0] = cpu_to_le32(len);
+        buf[1] = cpu_to_le32(comdatum->value);
+        buf[2] = cpu_to_le32(comdatum->permissions.nprim);
+        buf[3] = cpu_to_le32(comdatum->permissions.table->nel);
+        rc = put_entry(buf, sizeof(u32), 4, fp);
+        if (rc)
+                return rc;
+
+        rc = put_entry(key, 1, len, fp);
+        if (rc)
+                return rc;
+
+        rc = hashtab_map(comdatum->permissions.table, perm_write, fp);
+        if (rc)
+                return rc;
+
+        return 0;
+}
+
+static int write_cons_helper(struct policydb *p, struct constraint_node *node,
+                             void *fp)
+{
+        struct constraint_node *c;
+        struct constraint_expr *e;
+        __le32 buf[3];
+        u32 nel;
+        int rc;
+
+        for (c = node; c; c = c->next) {
+                nel = 0;
+                for (e = c->expr; e; e = e->next)
+                        nel++;
+                buf[0] = cpu_to_le32(c->permissions);
+                buf[1] = cpu_to_le32(nel);
+                rc = put_entry(buf, sizeof(u32), 2, fp);
+                if (rc)
+                        return rc;
+                for (e = c->expr; e; e = e->next) {
+                        buf[0] = cpu_to_le32(e->expr_type);
+                        buf[1] = cpu_to_le32(e->attr);
+                        buf[2] = cpu_to_le32(e->op);
+                        rc = put_entry(buf, sizeof(u32), 3, fp);
+                        if (rc)
+                                return rc;
+
+                        switch (e->expr_type) {
+                        case CEXPR_NAMES:
+                                rc = ebitmap_write(&e->names, fp);
+                                if (rc)
+                                        return rc;
+                                break;
+                        default:
+                                break;
+                        }
+                }
+        }
+
+        return 0;
+}
+
+static int class_write(void *vkey, void *datum, void *ptr)
+{
+        char *key = vkey;
+        struct class_datum *cladatum = datum;
+        struct policy_data *pd = ptr;
+        void *fp = pd->fp;
+        struct policydb *p = pd->p;
+        struct constraint_node *c;
+        __le32 buf[6];
+        u32 ncons;
+        size_t len, len2;
+        int rc;
+
+        len = strlen(key);
+        if (cladatum->comkey)
+                len2 = strlen(cladatum->comkey);
+        else
+                len2 = 0;
+
+        ncons = 0;
+        for (c = cladatum->constraints; c; c = c->next)
+                ncons++;
+
+        buf[0] = cpu_to_le32(len);
+        buf[1] = cpu_to_le32(len2);
+        buf[2] = cpu_to_le32(cladatum->value);
+        buf[3] = cpu_to_le32(cladatum->permissions.nprim);
+        if (cladatum->permissions.table)
+                buf[4] = cpu_to_le32(cladatum->permissions.table->nel);
+        else
+                buf[4] = 0;
+        buf[5] = cpu_to_le32(ncons);
+        rc = put_entry(buf, sizeof(u32), 6, fp);
+        if (rc)
+                return rc;
+
+        rc = put_entry(key, 1, len, fp);
+        if (rc)
+                return rc;
+
+        if (cladatum->comkey) {
+                rc = put_entry(cladatum->comkey, 1, len2, fp);
+                if (rc)
+                        return rc;
+        }
+
+        rc = hashtab_map(cladatum->permissions.table, perm_write, fp);
+        if (rc)
+                return rc;
+
+        rc = write_cons_helper(p, cladatum->constraints, fp);
+        if (rc)
+                return rc;
+
+        /* write out the validatetrans rule */
+        ncons = 0;
+        for (c = cladatum->validatetrans; c; c = c->next)
+                ncons++;
+
+        buf[0] = cpu_to_le32(ncons);
+        rc = put_entry(buf, sizeof(u32), 1, fp);
+        if (rc)
+                return rc;
+
+        rc = write_cons_helper(p, cladatum->validatetrans, fp);
+        if (rc)
+                return rc;
+
+        return 0;
+}
+
+static int role_write(void *vkey, void *datum, void *ptr)
+{
+        char *key = vkey;
+        struct role_datum *role = datum;
+        struct policy_data *pd = ptr;
+        void *fp = pd->fp;
+        struct policydb *p = pd->p;
+        __le32 buf[3];
+        size_t items, len;
+        int rc;
+
+        len = strlen(key);
+        items = 0;
+        buf[items++] = cpu_to_le32(len);
+        buf[items++] = cpu_to_le32(role->value);
+        if (p->policyvers >= POLICYDB_VERSION_BOUNDARY)
+                buf[items++] = cpu_to_le32(role->bounds);
+
+        BUG_ON(items > (sizeof(buf)/sizeof(buf[0])));
+
+        rc = put_entry(buf, sizeof(u32), items, fp);
+        if (rc)
+                return rc;
+
+        rc = put_entry(key, 1, len, fp);
+        if (rc)
+                return rc;
+
+        rc = ebitmap_write(&role->dominates, fp);
+        if (rc)
+                return rc;
+
+        rc = ebitmap_write(&role->types, fp);
+        if (rc)
+                return rc;
+
+        return 0;
+}
+
+static int type_write(void *vkey, void *datum, void *ptr)
+{
+        char *key = vkey;
+        struct type_datum *typdatum = datum;
+        struct policy_data *pd = ptr;
+        struct policydb *p = pd->p;
+        void *fp = pd->fp;
+        __le32 buf[4];
+        int rc;
+        size_t items, len;
+
+        len = strlen(key);
+        items = 0;
+        buf[items++] = cpu_to_le32(len);
+        buf[items++] = cpu_to_le32(typdatum->value);
+        if (p->policyvers >= POLICYDB_VERSION_BOUNDARY) {
+                u32 properties = 0;
+
+                if (typdatum->primary)
+                        properties |= TYPEDATUM_PROPERTY_PRIMARY;
+
+                if (typdatum->attribute)
+                        properties |= TYPEDATUM_PROPERTY_ATTRIBUTE;
+
+                buf[items++] = cpu_to_le32(properties);
+                buf[items++] = cpu_to_le32(typdatum->bounds);
+        } else {
+                buf[items++] = cpu_to_le32(typdatum->primary);
+        }
+        BUG_ON(items > (sizeof(buf) / sizeof(buf[0])));
+        rc = put_entry(buf, sizeof(u32), items, fp);
+        if (rc)
+                return rc;
+
+        rc = put_entry(key, 1, len, fp);
+        if (rc)
+                return rc;
+
+        return 0;
+}
+
+static int user_write(void *vkey, void *datum, void *ptr)
+{
+        char *key = vkey;
+        struct user_datum *usrdatum = datum;
+        struct policy_data *pd = ptr;
+        struct policydb *p = pd->p;
+        void *fp = pd->fp;
+        __le32 buf[3];
+        size_t items, len;
+        int rc;
+
+        len = strlen(key);
+        items = 0;
+        buf[items++] = cpu_to_le32(len);
+        buf[items++] = cpu_to_le32(usrdatum->value);
+        if (p->policyvers >= POLICYDB_VERSION_BOUNDARY)
+                buf[items++] = cpu_to_le32(usrdatum->bounds);
+        BUG_ON(items > (sizeof(buf) / sizeof(buf[0])));
+        rc = put_entry(buf, sizeof(u32), items, fp);
+        if (rc)
+                return rc;
+
+        rc = put_entry(key, 1, len, fp);
+        if (rc)
+                return rc;
+
+        rc = ebitmap_write(&usrdatum->roles, fp);
+        if (rc)
+                return rc;
+
+        rc = mls_write_range_helper(&usrdatum->range, fp);
+        if (rc)
+                return rc;
+
+        rc = mls_write_level(&usrdatum->dfltlevel, fp);
+        if (rc)
+                return rc;
+
+        return 0;
+}
+
+static int (*write_f[SYM_NUM]) (void *key, void *datum,
+                                void *datap) =
+{
+        common_write,
+        class_write,
+        role_write,
+        type_write,
+        user_write,
+        cond_write_bool,
+        sens_write,
+        cat_write,
+};
+
+static int ocontext_write(struct policydb *p, struct policydb_compat_info *info,
+                          void *fp)
+{
+        unsigned int i, j, rc;
+        size_t nel, len;
+        __le32 buf[3];
+        u32 nodebuf[8];
+        struct ocontext *c;
+        for (i = 0; i < info->ocon_num; i++) {
+                nel = 0;
+                for (c = p->ocontexts[i]; c; c = c->next)
+                        nel++;
+                buf[0] = cpu_to_le32(nel);
+                rc = put_entry(buf, sizeof(u32), 1, fp);
+                if (rc)
+                        return rc;
+                for (c = p->ocontexts[i]; c; c = c->next) {
+                        switch (i) {
+                        case OCON_ISID:
+                                buf[0] = cpu_to_le32(c->sid[0]);
+                                rc = put_entry(buf, sizeof(u32), 1, fp);
+                                if (rc)
+                                        return rc;
+                                rc = context_write(p, &c->context[0], fp);
+                                if (rc)
+                                        return rc;
+                                break;
+                        case OCON_FS:
+                        case OCON_NETIF:
+                                len = strlen(c->u.name);
+                                buf[0] = cpu_to_le32(len);
+                                rc = put_entry(buf, sizeof(u32), 1, fp);
+                                if (rc)
+                                        return rc;
+                                rc = put_entry(c->u.name, 1, len, fp);
+                                if (rc)
+                                        return rc;
+                                rc = context_write(p, &c->context[0], fp);
+                                if (rc)
+                                        return rc;
+                                rc = context_write(p, &c->context[1], fp);
+                                if (rc)
+                                        return rc;
+                                break;
+                        case OCON_PORT:
+                                buf[0] = cpu_to_le32(c->u.port.protocol);
+                                buf[1] = cpu_to_le32(c->u.port.low_port);
+                                buf[2] = cpu_to_le32(c->u.port.high_port);
+                                rc = put_entry(buf, sizeof(u32), 3, fp);
+                                if (rc)
+                                        return rc;
+                                rc = context_write(p, &c->context[0], fp);
+                                if (rc)
+                                        return rc;
+                                break;
+                        case OCON_NODE:
+                                nodebuf[0] = c->u.node.addr; /* network order */
+                                nodebuf[1] = c->u.node.mask; /* network order */
+                                rc = put_entry(nodebuf, sizeof(u32), 2, fp);
+                                if (rc)
+                                        return rc;
+                                rc = context_write(p, &c->context[0], fp);
+                                if (rc)
+                                        return rc;
+                                break;
+                        case OCON_FSUSE:
+                                buf[0] = cpu_to_le32(c->v.behavior);
+                                len = strlen(c->u.name);
+                                buf[1] = cpu_to_le32(len);
+                                rc = put_entry(buf, sizeof(u32), 2, fp);
+                                if (rc)
+                                        return rc;
+                                rc = put_entry(c->u.name, 1, len, fp);
+                                if (rc)
+                                        return rc;
+                                rc = context_write(p, &c->context[0], fp);
+                                if (rc)
+                                        return rc;
+                                break;
+                        case OCON_NODE6:
+                                for (j = 0; j < 4; j++)
+                                        nodebuf[j] = c->u.node6.addr[j]; /* network order */
+                                for (j = 0; j < 4; j++)
+                                        nodebuf[j + 4] = c->u.node6.mask[j]; /* network order */
+                                rc = put_entry(nodebuf, sizeof(u32), 8, fp);
+                                if (rc)
+                                        return rc;
+                                rc = context_write(p, &c->context[0], fp);
+                                if (rc)
+                                        return rc;
+                                break;
+                        }
+                }
+        }
+        return 0;
+}
+
+static int genfs_write(struct policydb *p, void *fp)
+{
+        struct genfs *genfs;
+        struct ocontext *c;
+        size_t len;
+        __le32 buf[1];
+        int rc;
+
+        len = 0;
+        for (genfs = p->genfs; genfs; genfs = genfs->next)
+                len++;
+        buf[0] = cpu_to_le32(len);
+        rc = put_entry(buf, sizeof(u32), 1, fp);
+        if (rc)
+                return rc;
+        for (genfs = p->genfs; genfs; genfs = genfs->next) {
+                len = strlen(genfs->fstype);
+                buf[0] = cpu_to_le32(len);
+                rc = put_entry(buf, sizeof(u32), 1, fp);
+                if (rc)
+                        return rc;
+                rc = put_entry(genfs->fstype, 1, len, fp);
+                if (rc)
+                        return rc;
+                len = 0;
+                for (c = genfs->head; c; c = c->next)
+                        len++;
+                buf[0] = cpu_to_le32(len);
+                rc = put_entry(buf, sizeof(u32), 1, fp);
+                if (rc)
+                        return rc;
+                for (c = genfs->head; c; c = c->next) {
+                        len = strlen(c->u.name);
+                        buf[0] = cpu_to_le32(len);
+                        rc = put_entry(buf, sizeof(u32), 1, fp);
+                        if (rc)
+                                return rc;
+                        rc = put_entry(c->u.name, 1, len, fp);
+                        if (rc)
+                                return rc;
+                        buf[0] = cpu_to_le32(c->v.sclass);
+                        rc = put_entry(buf, sizeof(u32), 1, fp);
+                        if (rc)
+                                return rc;
+                        rc = context_write(p, &c->context[0], fp);
+                        if (rc)
+                                return rc;
+                }
+        }
+        return 0;
+}
+
+static int range_count(void *key, void *data, void *ptr)
+{
+        int *cnt = ptr;
+        *cnt = *cnt + 1;
+
+        return 0;
+}
+
+static int range_write_helper(void *key, void *data, void *ptr)
+{
+        __le32 buf[2];
+        struct range_trans *rt = key;
+        struct mls_range *r = data;
+        struct policy_data *pd = ptr;
+        void *fp = pd->fp;
+        struct policydb *p = pd->p;
+        int rc;
+
+        buf[0] = cpu_to_le32(rt->source_type);
+        buf[1] = cpu_to_le32(rt->target_type);
+        rc = put_entry(buf, sizeof(u32), 2, fp);
+        if (rc)
+                return rc;
+        if (p->policyvers >= POLICYDB_VERSION_RANGETRANS) {
+                buf[0] = cpu_to_le32(rt->target_class);
+                rc = put_entry(buf, sizeof(u32), 1, fp);
+                if (rc)
+                        return rc;
+        }
+        rc = mls_write_range_helper(r, fp);
+        if (rc)
+                return rc;
+
+        return 0;
+}
+
+static int range_write(struct policydb *p, void *fp)
+{
+        size_t nel;
+        __le32 buf[1];
+        int rc;
+        struct policy_data pd;
+
+        pd.p = p;
+        pd.fp = fp;
+
+        /* count the number of entries in the hashtab */
+        nel = 0;
+        rc = hashtab_map(p->range_tr, range_count, &nel);
+        if (rc)
+                return rc;
+
+        buf[0] = cpu_to_le32(nel);
+        rc = put_entry(buf, sizeof(u32), 1, fp);
+        if (rc)
+                return rc;
+
+        /* actually write all of the entries */
+        rc = hashtab_map(p->range_tr, range_write_helper, &pd);
+        if (rc)
+                return rc;
+
+        return 0;
+}
+
+/*
+ * Write the configuration data in a policy database
+ * structure to a policy database binary representation
+ * file.
+ */
+int policydb_write(struct policydb *p, void *fp)
+{
+        unsigned int i, num_syms;
+        int rc;
+        __le32 buf[4];
+        u32 config;
+        size_t len;
+        struct policydb_compat_info *info;
+
+        /*
+         * refuse to write policy older than compressed avtab
+         * to simplify the writer.  There are other tests dropped
+         * since we assume this throughout the writer code.  Be
+         * careful if you ever try to remove this restriction
+         */
+        if (p->policyvers < POLICYDB_VERSION_AVTAB) {
+                printk(KERN_ERR "SELinux: refusing to write policy version %d."
+                       "  Because it is less than version %d\n", p->policyvers,
+                       POLICYDB_VERSION_AVTAB);
+                return -EINVAL;
+        }
+
+        config = 0;
+        if (p->mls_enabled)
+                config |= POLICYDB_CONFIG_MLS;
+
+        if (p->reject_unknown)
+                config |= REJECT_UNKNOWN;
+        if (p->allow_unknown)
+                config |= ALLOW_UNKNOWN;
+
+        /* Write the magic number and string identifiers. */
+        buf[0] = cpu_to_le32(POLICYDB_MAGIC);
+        len = strlen(POLICYDB_STRING);
+        buf[1] = cpu_to_le32(len);
+        rc = put_entry(buf, sizeof(u32), 2, fp);
+        if (rc)
+                return rc;
+        rc = put_entry(POLICYDB_STRING, 1, len, fp);
+        if (rc)
+                return rc;
+
+        /* Write the version, config, and table sizes. */
+        info = policydb_lookup_compat(p->policyvers);
+        if (!info) {
+                printk(KERN_ERR "SELinux: compatibility lookup failed for policy "
+                    "version %d", p->policyvers);
+                return rc;
+        }
+
+        buf[0] = cpu_to_le32(p->policyvers);
+        buf[1] = cpu_to_le32(config);
+        buf[2] = cpu_to_le32(info->sym_num);
+        buf[3] = cpu_to_le32(info->ocon_num);
+
+        rc = put_entry(buf, sizeof(u32), 4, fp);
+        if (rc)
+                return rc;
+
+        if (p->policyvers >= POLICYDB_VERSION_POLCAP) {
+                rc = ebitmap_write(&p->policycaps, fp);
+                if (rc)
+                        return rc;
+        }
+
+        if (p->policyvers >= POLICYDB_VERSION_PERMISSIVE) {
+                rc = ebitmap_write(&p->permissive_map, fp);
+                if (rc)
+                        return rc;
+        }
+
+        num_syms = info->sym_num;
+        for (i = 0; i < num_syms; i++) {
+                struct policy_data pd;
+
+                pd.fp = fp;
+                pd.p = p;
+
+                buf[0] = cpu_to_le32(p->symtab[i].nprim);
+                buf[1] = cpu_to_le32(p->symtab[i].table->nel);
+
+                rc = put_entry(buf, sizeof(u32), 2, fp);
+                if (rc)
+                        return rc;
+                rc = hashtab_map(p->symtab[i].table, write_f[i], &pd);
+                if (rc)
+                        return rc;
+        }
+
+        rc = avtab_write(p, &p->te_avtab, fp);
+        if (rc)
+                return rc;
+
+        rc = cond_write_list(p, p->cond_list, fp);
+        if (rc)
+                return rc;
+
+        rc = role_trans_write(p->role_tr, fp);
+        if (rc)
+                return rc;
+
+        rc = role_allow_write(p->role_allow, fp);
+        if (rc)
+                return rc;
+
+        rc = ocontext_write(p, info, fp);
+        if (rc)
+                return rc;
+
+        rc = genfs_write(p, fp);
+        if (rc)
+                return rc;
+
+        rc = range_write(p, fp);
+        if (rc)
+                return rc;
+
+        for (i = 0; i < p->p_types.nprim; i++) {
+                struct ebitmap *e = flex_array_get(p->type_attr_map_array, i);
+
+                BUG_ON(!e);
+                rc = ebitmap_write(e, fp);
+                if (rc)
+                        return rc;
+        }
+
+        return 0;
+}
diff --git a/security/selinux/ss/policydb.h b/security/selinux/ss/policydb.h
index 310e94442cb8..95d3d7de361e 100644
--- a/security/selinux/ss/policydb.h
+++ b/security/selinux/ss/policydb.h
@@ -254,6 +254,9 @@ struct policydb {
 
         struct ebitmap permissive_map;
 
+        /* length of this policy when it was loaded */
+        size_t len;
+
         unsigned int policyvers;
 
         unsigned int reject_unknown : 1;
@@ -270,6 +273,7 @@ extern int policydb_class_isvalid(struct policydb *p, unsigned int class);
 extern int policydb_type_isvalid(struct policydb *p, unsigned int type);
 extern int policydb_role_isvalid(struct policydb *p, unsigned int role);
 extern int policydb_read(struct policydb *p, void *fp);
+extern int policydb_write(struct policydb *p, void *fp);
 
 #define PERM_SYMTAB_SIZE 32
 
@@ -290,6 +294,11 @@ struct policy_file {
         size_t len;
 };
 
+struct policy_data {
+        struct policydb *p;
+        void *fp;
+};
+
 static inline int next_entry(void *buf, struct policy_file *fp, size_t bytes)
 {
         if (bytes > fp->len)
@@ -301,6 +310,17 @@ static inline int next_entry(void *buf, struct policy_file *fp, size_t bytes)
         return 0;
 }
 
+static inline int put_entry(void *buf, size_t bytes, int num, struct policy_file *fp)
+{
+        size_t len = bytes * num;
+
+        memcpy(fp->data, buf, len);
+        fp->data += len;
+        fp->len -= len;
+
+        return 0;
+}
+
 extern u16 string_to_security_class(struct policydb *p, const char *name);
 extern u32 string_to_av_perm(struct policydb *p, u16 tclass, const char *name);
 
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index 9ea2feca3cd4..223c1ff6ef23 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -51,6 +51,7 @@
 #include <linux/mutex.h>
 #include <linux/selinux.h>
 #include <linux/flex_array.h>
+#include <linux/vmalloc.h>
 #include <net/netlabel.h>
 
 #include "flask.h"
@@ -991,7 +992,8 @@ static int context_struct_to_string(struct context *context, char **scontext, u3
 {
         char *scontextp;
 
-        *scontext = NULL;
+        if (scontext)
+                *scontext = NULL;
         *scontext_len = 0;
 
         if (context->len) {
@@ -1008,6 +1010,9 @@ static int context_struct_to_string(struct context *context, char **scontext, u3
         *scontext_len += strlen(policydb.p_type_val_to_name[context->type - 1]) + 1;
         *scontext_len += mls_compute_context_len(context);
 
+        if (!scontext)
+                return 0;
+
         /* Allocate space for the context; caller must free this space. */
         scontextp = kmalloc(*scontext_len, GFP_ATOMIC);
         if (!scontextp)
@@ -1047,7 +1052,8 @@ static int security_sid_to_context_core(u32 sid, char **scontext,
         struct context *context;
         int rc = 0;
 
-        *scontext = NULL;
+        if (scontext)
+                *scontext = NULL;
         *scontext_len  = 0;
 
         if (!ss_initialized) {
@@ -1055,6 +1061,8 @@ static int security_sid_to_context_core(u32 sid, char **scontext,
                         char *scontextp;
 
                         *scontext_len = strlen(initial_sid_to_string[sid]) + 1;
+                        if (!scontext)
+                                goto out;
                         scontextp = kmalloc(*scontext_len, GFP_ATOMIC);
                         if (!scontextp) {
                                 rc = -ENOMEM;
@@ -1769,6 +1777,7 @@ int security_load_policy(void *data, size_t len)
                         return rc;
                 }
 
+                policydb.len = len;
                 rc = selinux_set_mapping(&policydb, secclass_map,
                                          &current_mapping,
                                          &current_mapping_size);
@@ -1791,6 +1800,7 @@ int security_load_policy(void *data, size_t len)
                 selinux_complete_init();
                 avc_ss_reset(seqno);
                 selnl_notify_policyload(seqno);
+                selinux_status_update_policyload(seqno);
                 selinux_netlbl_cache_invalidate();
                 selinux_xfrm_notify_policyload();
                 return 0;
@@ -1804,6 +1814,7 @@ int security_load_policy(void *data, size_t len)
         if (rc)
                 return rc;
 
+        newpolicydb.len = len;
         /* If switching between different policy types, log MLS status */
         if (policydb.mls_enabled && !newpolicydb.mls_enabled)
                 printk(KERN_INFO "SELinux: Disabling MLS support...\n");
@@ -1870,6 +1881,7 @@ int security_load_policy(void *data, size_t len)
 
         avc_ss_reset(seqno);
         selnl_notify_policyload(seqno);
+        selinux_status_update_policyload(seqno);
         selinux_netlbl_cache_invalidate();
         selinux_xfrm_notify_policyload();
 
@@ -1883,6 +1895,17 @@ err:
 
 }
 
+size_t security_policydb_len(void)
+{
+        size_t len;
+
+        read_lock(&policy_rwlock);
+        len = policydb.len;
+        read_unlock(&policy_rwlock);
+
+        return len;
+}
+
 /**
  * security_port_sid - Obtain the SID for a port.
  * @protocol: protocol number
@@ -2374,6 +2397,7 @@ out:
         if (!rc) {
                 avc_ss_reset(seqno);
                 selnl_notify_policyload(seqno);
+                selinux_status_update_policyload(seqno);
                 selinux_xfrm_notify_policyload();
         }
         return rc;
@@ -3129,3 +3153,38 @@ netlbl_sid_to_secattr_failure:
         return rc;
 }
 #endif /* CONFIG_NETLABEL */
+
+/**
+ * security_read_policy - read the policy.
+ * @data: binary policy data
+ * @len: length of data in bytes
+ *
+ */
+int security_read_policy(void **data, ssize_t *len)
+{
+        int rc;
+        struct policy_file fp;
+
+        if (!ss_initialized)
+                return -EINVAL;
+
+        *len = security_policydb_len();
+
+        *data = vmalloc_user(*len);
+        if (!*data)
+                return -ENOMEM;
+
+        fp.data = *data;
+        fp.len = *len;
+
+        read_lock(&policy_rwlock);
+        rc = policydb_write(&policydb, &fp);
+        read_unlock(&policy_rwlock);
+
+        if (rc)
+                return rc;
+
+        *len = (unsigned long)fp.data - (unsigned long)*data;
+        return 0;
+
+}
diff --git a/security/selinux/ss/status.c b/security/selinux/ss/status.c
new file mode 100644
index 000000000000..d982365f9d1a
--- /dev/null
+++ b/security/selinux/ss/status.c
@@ -0,0 +1,126 @@
+/*
+ * mmap based event notifications for SELinux
+ *
+ * Author: KaiGai Kohei <kaigai@ak.jp.nec.com>
+ *
+ * Copyright (C) 2010 NEC corporation
+ *
+ * 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 published by the Free Software Foundation.
+ */
+#include <linux/kernel.h>
+#include <linux/gfp.h>
+#include <linux/mm.h>
+#include <linux/mutex.h>
+#include "avc.h"
+#include "services.h"
+
+/*
+ * The selinux_status_page shall be exposed to userspace applications
+ * using mmap interface on /selinux/status.
+ * It enables to notify applications a few events that will cause reset
+ * of userspace access vector without context switching.
+ *
+ * The selinux_kernel_status structure on the head of status page is
+ * protected from concurrent accesses using seqlock logic, so userspace
+ * application should reference the status page according to the seqlock
+ * logic.
+ *
+ * Typically, application checks status->sequence at the head of access
+ * control routine. If it is odd-number, kernel is updating the status,
+ * so please wait for a moment. If it is changed from the last sequence
+ * number, it means something happen, so application will reset userspace
+ * avc, if needed.
+ * In most cases, application shall confirm the kernel status is not
+ * changed without any system call invocations.
+ */
+static struct page *selinux_status_page;
+static DEFINE_MUTEX(selinux_status_lock);
+
+/*
+ * selinux_kernel_status_page
+ *
+ * It returns a reference to selinux_status_page. If the status page is
+ * not allocated yet, it also tries to allocate it at the first time.
+ */
+struct page *selinux_kernel_status_page(void)
+{
+        struct selinux_kernel_status   *status;
+        struct page                    *result = NULL;
+
+        mutex_lock(&selinux_status_lock);
+        if (!selinux_status_page) {
+                selinux_status_page = alloc_page(GFP_KERNEL|__GFP_ZERO);
+
+                if (selinux_status_page) {
+                        status = page_address(selinux_status_page);
+
+                        status->version = SELINUX_KERNEL_STATUS_VERSION;
+                        status->sequence = 0;
+                        status->enforcing = selinux_enforcing;
+                        /*
+                         * NOTE: the next policyload event shall set
+                         * a positive value on the status->policyload,
+                         * although it may not be 1, but never zero.
+                         * So, application can know it was updated.
+                         */
+                        status->policyload = 0;
+                        status->deny_unknown = !security_get_allow_unknown();
+                }
+        }
+        result = selinux_status_page;
+        mutex_unlock(&selinux_status_lock);
+
+        return result;
+}
+
+/*
+ * selinux_status_update_setenforce
+ *
+ * It updates status of the current enforcing/permissive mode.
+ */
+void selinux_status_update_setenforce(int enforcing)
+{
+        struct selinux_kernel_status   *status;
+
+        mutex_lock(&selinux_status_lock);
+        if (selinux_status_page) {
+                status = page_address(selinux_status_page);
+
+                status->sequence++;
+                smp_wmb();
+
+                status->enforcing = enforcing;
+
+                smp_wmb();
+                status->sequence++;
+        }
+        mutex_unlock(&selinux_status_lock);
+}
+
+/*
+ * selinux_status_update_policyload
+ *
+ * It updates status of the times of policy reloaded, and current
+ * setting of deny_unknown.
+ */
+void selinux_status_update_policyload(int seqno)
+{
+        struct selinux_kernel_status   *status;
+
+        mutex_lock(&selinux_status_lock);
+        if (selinux_status_page) {
+                status = page_address(selinux_status_page);
+
+                status->sequence++;
+                smp_wmb();
+
+                status->policyload = seqno;
+                status->deny_unknown = !security_get_allow_unknown();
+
+                smp_wmb();
+                status->sequence++;
+        }
+        mutex_unlock(&selinux_status_lock);
+}
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index c448d57ae2b7..bc39f4067af6 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -1281,12 +1281,11 @@ static int smack_task_getioprio(struct task_struct *p)
  *
  * Return 0 if read access is permitted
  */
-static int smack_task_setscheduler(struct task_struct *p, int policy,
-                                   struct sched_param *lp)
+static int smack_task_setscheduler(struct task_struct *p)
 {
         int rc;
 
-        rc = cap_task_setscheduler(p, policy, lp);
+        rc = cap_task_setscheduler(p);
         if (rc == 0)
                 rc = smk_curacc_on_task(p, MAY_WRITE);
         return rc;
@@ -3005,7 +3004,8 @@ static int smack_secid_to_secctx(u32 secid, char **secdata, u32 *seclen)
 {
         char *sp = smack_from_secid(secid);
 
-        *secdata = sp;
+        if (secdata)
+                *secdata = sp;
         *seclen = strlen(sp);
         return 0;
 }
diff --git a/security/tomoyo/common.c b/security/tomoyo/common.c
index c668b447c725..7556315c1978 100644
--- a/security/tomoyo/common.c
+++ b/security/tomoyo/common.c
@@ -768,8 +768,10 @@ static bool tomoyo_select_one(struct tomoyo_io_buffer *head, const char *data)
                 return true; /* Do nothing if open(O_WRONLY). */
         memset(&head->r, 0, sizeof(head->r));
         head->r.print_this_domain_only = true;
-        head->r.eof = !domain;
-        head->r.domain = &domain->list;
+        if (domain)
+                head->r.domain = &domain->list;
+        else
+                head->r.eof = 1;
         tomoyo_io_printf(head, "# select %s\n", data);
         if (domain && domain->is_deleted)
                 tomoyo_io_printf(head, "# This is a deleted domain.\n");
@@ -2051,13 +2053,22 @@ void tomoyo_check_profile(void)
                 const u8 profile = domain->profile;
                 if (tomoyo_profile_ptr[profile])
                         continue;
+                printk(KERN_ERR "You need to define profile %u before using it.\n",
+                       profile);
+                printk(KERN_ERR "Please see http://tomoyo.sourceforge.jp/2.3/ "
+                       "for more information.\n");
                 panic("Profile %u (used by '%s') not defined.\n",
                       profile, domain->domainname->name);
         }
         tomoyo_read_unlock(idx);
-        if (tomoyo_profile_version != 20090903)
+        if (tomoyo_profile_version != 20090903) {
+                printk(KERN_ERR "You need to install userland programs for "
+                       "TOMOYO 2.3 and initialize policy configuration.\n");
+                printk(KERN_ERR "Please see http://tomoyo.sourceforge.jp/2.3/ "
+                       "for more information.\n");
                 panic("Profile version %u is not supported.\n",
                       tomoyo_profile_version);
+        }
         printk(KERN_INFO "TOMOYO: 2.3.0\n");
         printk(KERN_INFO "Mandatory Access Control activated.\n");
 }