25 files changed, 110 insertions, 85 deletions

diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX
index c17cd4bb2290..1b777b960492 100644
--- a/Documentation/00-INDEX
+++ b/Documentation/00-INDEX
@@ -328,8 +328,6 @@ sysrq.txt
 	- info on the magic SysRq key.
 telephony/
 	- directory with info on telephony (e.g. voice over IP) support.
-uml/
-	- directory with information about User Mode Linux.
 unicode.txt
 	- info on the Unicode character/font mapping used in Linux.
 unshare.txt
diff --git a/Documentation/ABI/testing/sysfs-power b/Documentation/ABI/testing/sysfs-power
index 194ca446ac28..b464d12761ba 100644
--- a/Documentation/ABI/testing/sysfs-power
+++ b/Documentation/ABI/testing/sysfs-power
@@ -158,3 +158,17 @@ Description:
 		successful, will make the kernel abort a subsequent transition
 		to a sleep state if any wakeup events are reported after the
 		write has returned.
+
+What:		/sys/power/reserved_size
+Date:		May 2011
+Contact:	Rafael J. Wysocki <rjw@sisk.pl>
+Description:
+		The /sys/power/reserved_size file allows user space to control
+		the amount of memory reserved for allocations made by device
+		drivers during the "device freeze" stage of hibernation.  It can
+		be written a string representing a non-negative integer that
+		will be used as the amount of memory to reserve for allocations
+		made by device drivers' "freeze" callbacks, in bytes.
+
+		Reading from this file will display the current value, which is
+		set to 1 MB by default.
diff --git a/Documentation/DocBook/genericirq.tmpl b/Documentation/DocBook/genericirq.tmpl
index fb10fd08c05c..b3422341d65c 100644
--- a/Documentation/DocBook/genericirq.tmpl
+++ b/Documentation/DocBook/genericirq.tmpl
@@ -191,8 +191,8 @@
 	<para>
 	Whenever an interrupt triggers, the lowlevel arch code calls into
 	the generic interrupt code by calling desc->handle_irq().
-	This highlevel IRQ handling function only uses desc->chip primitives
-	referenced by the assigned chip descriptor structure.
+	This highlevel IRQ handling function only uses desc->irq_data.chip
+	primitives referenced by the assigned chip descriptor structure.
 	</para>
     </sect1>
     <sect1 id="Highlevel_Driver_API">
@@ -206,11 +206,11 @@
 	  <listitem><para>enable_irq()</para></listitem>
 	  <listitem><para>disable_irq_nosync() (SMP only)</para></listitem>
 	  <listitem><para>synchronize_irq() (SMP only)</para></listitem>
-	  <listitem><para>set_irq_type()</para></listitem>
-	  <listitem><para>set_irq_wake()</para></listitem>
-	  <listitem><para>set_irq_data()</para></listitem>
-	  <listitem><para>set_irq_chip()</para></listitem>
-	  <listitem><para>set_irq_chip_data()</para></listitem>
+	  <listitem><para>irq_set_irq_type()</para></listitem>
+	  <listitem><para>irq_set_irq_wake()</para></listitem>
+	  <listitem><para>irq_set_handler_data()</para></listitem>
+	  <listitem><para>irq_set_chip()</para></listitem>
+	  <listitem><para>irq_set_chip_data()</para></listitem>
           </itemizedlist>
 	  See the autogenerated function documentation for details.
 	</para>
@@ -225,6 +225,8 @@
 	  <listitem><para>handle_fasteoi_irq</para></listitem>
 	  <listitem><para>handle_simple_irq</para></listitem>
 	  <listitem><para>handle_percpu_irq</para></listitem>
+	  <listitem><para>handle_edge_eoi_irq</para></listitem>
+	  <listitem><para>handle_bad_irq</para></listitem>
 	  </itemizedlist>
 	  The interrupt flow handlers (either predefined or architecture
 	  specific) are assigned to specific interrupts by the architecture
@@ -241,13 +243,13 @@
 		<programlisting>
 default_enable(struct irq_data *data)
 {
-	desc->chip->irq_unmask(data);
+	desc->irq_data.chip->irq_unmask(data);
 }
 
 default_disable(struct irq_data *data)
 {
 	if (!delay_disable(data))
-		desc->chip->irq_mask(data);
+		desc->irq_data.chip->irq_mask(data);
 }
 
 default_ack(struct irq_data *data)
@@ -284,9 +286,9 @@ noop(struct irq_data *data))
 		<para>
 		The following control flow is implemented (simplified excerpt):
 		<programlisting>
-desc->chip->irq_mask();
-handle_IRQ_event(desc->action);
-desc->chip->irq_unmask();
+desc->irq_data.chip->irq_mask_ack();
+handle_irq_event(desc->action);
+desc->irq_data.chip->irq_unmask();
 		</programlisting>
 		</para>
 	    </sect3>
@@ -300,8 +302,8 @@ desc->chip->irq_unmask();
 		<para>
 		The following control flow is implemented (simplified excerpt):
 		<programlisting>
-handle_IRQ_event(desc->action);
-desc->chip->irq_eoi();
+handle_irq_event(desc->action);
+desc->irq_data.chip->irq_eoi();
 		</programlisting>
 		</para>
 	    </sect3>
@@ -315,17 +317,17 @@ desc->chip->irq_eoi();
 		The following control flow is implemented (simplified excerpt):
 		<programlisting>
 if (desc->status &amp; running) {
-	desc->chip->irq_mask();
+	desc->irq_data.chip->irq_mask_ack();
 	desc->status |= pending | masked;
 	return;
 }
-desc->chip->irq_ack();
+desc->irq_data.chip->irq_ack();
 desc->status |= running;
 do {
 	if (desc->status &amp; masked)
-		desc->chip->irq_unmask();
+		desc->irq_data.chip->irq_unmask();
 	desc->status &amp;= ~pending;
-	handle_IRQ_event(desc->action);
+	handle_irq_event(desc->action);
 } while (status &amp; pending);
 desc->status &amp;= ~running;
 		</programlisting>
@@ -344,7 +346,7 @@ desc->status &amp;= ~running;
 		<para>
 		The following control flow is implemented (simplified excerpt):
 		<programlisting>
-handle_IRQ_event(desc->action);
+handle_irq_event(desc->action);
 		</programlisting>
 		</para>
    	    </sect3>
@@ -362,12 +364,29 @@ handle_IRQ_event(desc->action);
 		<para>
 		The following control flow is implemented (simplified excerpt):
 		<programlisting>
-handle_IRQ_event(desc->action);
-if (desc->chip->irq_eoi)
-        desc->chip->irq_eoi();
+if (desc->irq_data.chip->irq_ack)
+	desc->irq_data.chip->irq_ack();
+handle_irq_event(desc->action);
+if (desc->irq_data.chip->irq_eoi)
+        desc->irq_data.chip->irq_eoi();
 		</programlisting>
 		</para>
    	    </sect3>
+	    <sect3 id="EOI_Edge_IRQ_flow_handler">
+	 	<title>EOI Edge IRQ flow handler</title>
+		<para>
+		handle_edge_eoi_irq provides an abnomination of the edge
+		handler which is solely used to tame a badly wreckaged
+		irq controller on powerpc/cell.
+		</para>
+   	    </sect3>
+	    <sect3 id="BAD_IRQ_flow_handler">
+	 	<title>Bad IRQ flow handler</title>
+		<para>
+		handle_bad_irq is used for spurious interrupts which
+		have no real handler assigned..
+		</para>
+   	    </sect3>
 	</sect2>
 	<sect2 id="Quirks_and_optimizations">
 	<title>Quirks and optimizations</title>
@@ -410,6 +429,7 @@ if (desc->chip->irq_eoi)
 	  <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_eoi() - Optional, required for eoi flow handlers</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>
@@ -424,32 +444,24 @@ if (desc->chip->irq_eoi)
   <chapter id="doirq">
      <title>__do_IRQ entry point</title>
      <para>
- 	The original implementation __do_IRQ() is an alternative entry
-	point for all types of interrupts.
+	The original implementation __do_IRQ() was an alternative entry
+	point for all types of interrupts. It not longer exists.
      </para>
      <para>
 	This handler turned out to be not suitable for all
 	interrupt hardware and was therefore reimplemented with split
-	functionality for egde/level/simple/percpu interrupts. This is not
+	functionality for edge/level/simple/percpu interrupts. This is not
 	only a functional optimization. It also shortens code paths for
 	interrupts.
       </para>
-      <para>
-	To make use of the split implementation, replace the call to
-	__do_IRQ by a call to desc->handle_irq() and associate
-        the appropriate handler function to desc->handle_irq().
-	In most cases the generic handler implementations should
-	be sufficient.
-     </para>
   </chapter>
 
   <chapter id="locking">
      <title>Locking on SMP</title>
      <para>
 	The locking of chip registers is up to the architecture that
-	defines the chip primitives. There is a chip->lock field that can be used
-	for serialization, but the generic layer does not touch it. The per-irq
-	structure is protected via desc->lock, by the generic layer.
+	defines the chip primitives. The per-irq structure is
+	protected via desc->lock, by the generic layer.
      </para>
   </chapter>
   <chapter id="structs">
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index 492e81df2968..f6a24e8aa11e 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -460,14 +460,6 @@ Who:	Thomas Gleixner <tglx@linutronix.de>
 
 ----------------------------
 
-What:	The acpi_sleep=s4_nonvs command line option
-When:	2.6.37
-Files:	arch/x86/kernel/acpi/sleep.c
-Why:	superseded by acpi_sleep=nonvs
-Who:	Rafael J. Wysocki <rjw@sisk.pl>
-
-----------------------------
-
 What: 	PCI DMA unmap state API
 When:	August 2012
 Why:	PCI DMA unmap state API (include/linux/pci-dma.h) was replaced
diff --git a/Documentation/flexible-arrays.txt b/Documentation/flexible-arrays.txt
index cb8a3a00cc92..df904aec9904 100644
--- a/Documentation/flexible-arrays.txt
+++ b/Documentation/flexible-arrays.txt
@@ -66,10 +66,10 @@ trick is to ensure that any needed memory allocations are done before
 entering atomic context, using:
 
     int flex_array_prealloc(struct flex_array *array, unsigned int start,
-			    unsigned int end, gfp_t flags);
+			    unsigned int nr_elements, gfp_t flags);
 
 This function will ensure that memory for the elements indexed in the range
-defined by start and end has been allocated.  Thereafter, a
+defined by start and nr_elements has been allocated.  Thereafter, a
 flex_array_put() call on an element in that range is guaranteed not to
 block.
 
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index cc85a9278190..259037b873b7 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -245,7 +245,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	acpi_sleep=	[HW,ACPI] Sleep options
 			Format: { s3_bios, s3_mode, s3_beep, s4_nohwsig,
-				  old_ordering, s4_nonvs, sci_force_enable }
+				  old_ordering, nonvs, sci_force_enable }
 			See Documentation/power/video.txt for information on
 			s3_bios and s3_mode.
 			s3_beep is for debugging; it makes the PC's speaker beep
diff --git a/Documentation/power/devices.txt b/Documentation/power/devices.txt
index 1971bcf48a60..88880839ece4 100644
--- a/Documentation/power/devices.txt
+++ b/Documentation/power/devices.txt
@@ -279,11 +279,15 @@ When the system goes into the standby or memory sleep state, the phases are:
 	time.)  Unlike the other suspend-related phases, during the prepare
 	phase the device tree is traversed top-down.
 
-	The prepare phase uses only a bus callback.  After the callback method
-	returns, no new children may be registered below the device.  The method
-	may also prepare the device or driver in some way for the upcoming
-	system power transition, but it should not put the device into a
-	low-power state.
+	In addition to that, if device drivers need to allocate additional
+	memory to be able to hadle device suspend correctly, that should be
+	done in the prepare phase.
+
+	After the prepare callback method returns, no new children may be
+	registered below the device.  The method may also prepare the device or
+	driver in some way for the upcoming system power transition (for
+	example, by allocating additional memory required for this purpose), but
+	it should not put the device into a low-power state.
 
     2.	The suspend methods should quiesce the device to stop it from performing
 	I/O.  They also may save the device registers and put it into the
diff --git a/Documentation/power/notifiers.txt b/Documentation/power/notifiers.txt
index cf980709122a..c2a4a346c0d9 100644
--- a/Documentation/power/notifiers.txt
+++ b/Documentation/power/notifiers.txt
@@ -1,46 +1,41 @@
 Suspend notifiers
-	(C) 2007 Rafael J. Wysocki <rjw@sisk.pl>, GPL
-
-There are some operations that device drivers may want to carry out in their
-.suspend() routines, but shouldn't, because they can cause the hibernation or
-suspend to fail. For example, a driver may want to allocate a substantial amount
-of memory (like 50 MB) in .suspend(), but that shouldn't be done after the
-swsusp's memory shrinker has run.
-
-Also, there may be some operations, that subsystems want to carry out before a
-hibernation/suspend or after a restore/resume, requiring the system to be fully
-functional, so the drivers' .suspend() and .resume() routines are not suitable
-for this purpose.  For example, device drivers may want to upload firmware to
-their devices after a restore from a hibernation image, but they cannot do it by
-calling request_firmware() from their .resume() routines (user land processes
-are frozen at this point).  The solution may be to load the firmware into
-memory before processes are frozen and upload it from there in the .resume()
-routine.  Of course, a hibernation notifier may be used for this purpose.
-
-The subsystems that have such needs can register suspend notifiers that will be
-called upon the following events by the suspend core:
+	(C) 2007-2011 Rafael J. Wysocki <rjw@sisk.pl>, GPL
+
+There are some operations that subsystems or drivers may want to carry out
+before hibernation/suspend or after restore/resume, but they require the system
+to be fully functional, so the drivers' and subsystems' .suspend() and .resume()
+or even .prepare() and .complete() callbacks are not suitable for this purpose.
+For example, device drivers may want to upload firmware to their devices after
+resume/restore, but they cannot do it by calling request_firmware() from their
+.resume() or .complete() routines (user land processes are frozen at these
+points).  The solution may be to load the firmware into memory before processes
+are frozen and upload it from there in the .resume() routine.
+A suspend/hibernation notifier may be used for this purpose.
+
+The subsystems or drivers having such needs can register suspend notifiers that
+will be called upon the following events by the PM core:
 
 PM_HIBERNATION_PREPARE	The system is going to hibernate or suspend, tasks will
 			be frozen immediately.
 
 PM_POST_HIBERNATION	The system memory state has been restored from a
-			hibernation image or an error occurred during the
-			hibernation.  Device drivers' .resume() callbacks have
+			hibernation image or an error occurred during
+			hibernation.  Device drivers' restore callbacks have
 			been executed and tasks have been thawed.
 
 PM_RESTORE_PREPARE	The system is going to restore a hibernation image.
-			If all goes well the restored kernel will issue a
+			If all goes well, the restored kernel will issue a
 			PM_POST_HIBERNATION notification.
 
-PM_POST_RESTORE		An error occurred during the hibernation restore.
-			Device drivers' .resume() callbacks have been executed
+PM_POST_RESTORE		An error occurred during restore from hibernation.
+			Device drivers' restore callbacks have been executed
 			and tasks have been thawed.
 
-PM_SUSPEND_PREPARE	The system is preparing for a suspend.
+PM_SUSPEND_PREPARE	The system is preparing for suspend.
 
 PM_POST_SUSPEND		The system has just resumed or an error occurred during
-			the suspend.	Device drivers' .resume() callbacks have
-			been executed and tasks have been thawed.
+			suspend.  Device drivers' resume callbacks have been
+			executed and tasks have been thawed.
 
 It is generally assumed that whatever the notifiers do for
 PM_HIBERNATION_PREPARE, should be undone for PM_POST_HIBERNATION.  Analogously,
diff --git a/Documentation/trace/kprobetrace.txt b/Documentation/trace/kprobetrace.txt
index 6d27ab8d6e9f..c83bd6b4e6e8 100644
--- a/Documentation/trace/kprobetrace.txt
+++ b/Documentation/trace/kprobetrace.txt
@@ -120,7 +120,6 @@ format:
         field:unsigned char common_flags;       offset:2;       size:1; signed:0;
         field:unsigned char common_preempt_count;       offset:3; size:1;signed:0;
         field:int common_pid;   offset:4;       size:4; signed:1;
-        field:int common_lock_depth;    offset:8;       size:4; signed:1;
 
         field:unsigned long __probe_ip; offset:12;      size:4; signed:0;
         field:int __probe_nargs;        offset:16;      size:4; signed:1;
diff --git a/Documentation/virtual/00-INDEX b/Documentation/virtual/00-INDEX
new file mode 100644
index 000000000000..fe0251c4cfb7
--- /dev/null
+++ b/Documentation/virtual/00-INDEX
@@ -0,0 +1,10 @@
+Virtualization support in the Linux kernel.
+
+00-INDEX
+	- this file.
+kvm/
+	- Kernel Virtual Machine.  See also http://linux-kvm.org
+lguest/
+	- Extremely simple hypervisor for experimental/educational use.
+uml/
+	- User Mode Linux, builds/runs Linux kernel as a userspace program.
diff --git a/Documentation/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 9bef4e4cec50..9bef4e4cec50 100644
--- a/Documentation/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
diff --git a/Documentation/kvm/cpuid.txt b/Documentation/virtual/kvm/cpuid.txt
index 882068538c9c..882068538c9c 100644
--- a/Documentation/kvm/cpuid.txt
+++ b/Documentation/virtual/kvm/cpuid.txt
diff --git a/Documentation/kvm/locking.txt b/Documentation/virtual/kvm/locking.txt
index 3b4cd3bf5631..3b4cd3bf5631 100644
--- a/Documentation/kvm/locking.txt
+++ b/Documentation/virtual/kvm/locking.txt
diff --git a/Documentation/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt
index f46aa58389ca..f46aa58389ca 100644
--- a/Documentation/kvm/mmu.txt
+++ b/Documentation/virtual/kvm/mmu.txt
diff --git a/Documentation/kvm/msr.txt b/Documentation/virtual/kvm/msr.txt
index d079aed27e03..d079aed27e03 100644
--- a/Documentation/kvm/msr.txt
+++ b/Documentation/virtual/kvm/msr.txt
diff --git a/Documentation/kvm/ppc-pv.txt b/Documentation/virtual/kvm/ppc-pv.txt
index 3ab969c59046..3ab969c59046 100644
--- a/Documentation/kvm/ppc-pv.txt
+++ b/Documentation/virtual/kvm/ppc-pv.txt
diff --git a/Documentation/kvm/review-checklist.txt b/Documentation/virtual/kvm/review-checklist.txt
index 730475ae1b8d..a850986ed684 100644
--- a/Documentation/kvm/review-checklist.txt
+++ b/Documentation/virtual/kvm/review-checklist.txt
@@ -7,7 +7,7 @@ Review checklist for kvm patches
 2.  Patches should be against kvm.git master branch.
 
 3.  If the patch introduces or modifies a new userspace API:
-    - the API must be documented in Documentation/kvm/api.txt
+    - the API must be documented in Documentation/virtual/kvm/api.txt
     - the API must be discoverable using KVM_CHECK_EXTENSION
 
 4.  New state must include support for save/restore.
diff --git a/Documentation/kvm/timekeeping.txt b/Documentation/virtual/kvm/timekeeping.txt
index df8946377cb6..df8946377cb6 100644
--- a/Documentation/kvm/timekeeping.txt
+++ b/Documentation/virtual/kvm/timekeeping.txt
diff --git a/Documentation/lguest/.gitignore b/Documentation/virtual/lguest/.gitignore
index 115587fd5f65..115587fd5f65 100644
--- a/Documentation/lguest/.gitignore
+++ b/Documentation/virtual/lguest/.gitignore
diff --git a/Documentation/lguest/Makefile b/Documentation/virtual/lguest/Makefile
index bebac6b4f332..bebac6b4f332 100644
--- a/Documentation/lguest/Makefile
+++ b/Documentation/virtual/lguest/Makefile
diff --git a/Documentation/lguest/extract b/Documentation/virtual/lguest/extract
index 7730bb6e4b94..7730bb6e4b94 100644
--- a/Documentation/lguest/extract
+++ b/Documentation/virtual/lguest/extract
diff --git a/Documentation/lguest/lguest.c b/Documentation/virtual/lguest/lguest.c
index d9da7e148538..d9da7e148538 100644
--- a/Documentation/lguest/lguest.c
+++ b/Documentation/virtual/lguest/lguest.c
diff --git a/Documentation/lguest/lguest.txt b/Documentation/virtual/lguest/lguest.txt
index dad99978a6a8..bff0c554485d 100644
--- a/Documentation/lguest/lguest.txt
+++ b/Documentation/virtual/lguest/lguest.txt
@@ -74,7 +74,8 @@ Running Lguest:
 
 - Run an lguest as root:
 
-      Documentation/lguest/lguest 64 vmlinux --tunnet=192.168.19.1 --block=rootfile root=/dev/vda
+      Documentation/virtual/lguest/lguest 64 vmlinux --tunnet=192.168.19.1 \
+        --block=rootfile root=/dev/vda
 
    Explanation:
     64: the amount of memory to use, in MB.
diff --git a/Documentation/uml/UserModeLinux-HOWTO.txt b/Documentation/virtual/uml/UserModeLinux-HOWTO.txt
index 9b7e1904db1c..9b7e1904db1c 100644
--- a/Documentation/uml/UserModeLinux-HOWTO.txt
+++ b/Documentation/virtual/uml/UserModeLinux-HOWTO.txt
diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
index 092e596a1301..c54b4f503e2a 100644
--- a/Documentation/x86/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
@@ -206,7 +206,7 @@ IOMMU (input/output memory management unit)
       (e.g. because you have < 3 GB memory).
       Kernel boot message: "PCI-DMA: Disabling IOMMU"
 
-   2. <arch/x86_64/kernel/pci-gart.c>: AMD GART based hardware IOMMU.
+   2. <arch/x86/kernel/amd_gart_64.c>: AMD GART based hardware IOMMU.
       Kernel boot message: "PCI-DMA: using GART IOMMU"
 
    3. <arch/x86_64/kernel/pci-swiotlb.c> : Software IOMMU implementation. Used