Merge branch 'docs-next' of git://git.lwn.net/linux

Pull documentation updates from Jonathan Corbet:
 "After a fair amount of churn in the last couple of cycles, docs are
  taking it easier this time around. Lots of fixes and some new
  documentation, but nothing all that radical. Perhaps the most
  interesting change for many is the scripts/sphinx-pre-install tool
  from Mauro; it will tell you exactly which packages you need to
  install to get a working docs toolchain on your system.

  There are two little patches reaching outside of Documentation/; both
  just tweak kerneldoc comments to eliminate warnings and fix some
  dangling doc pointers"

* 'docs-next' of git://git.lwn.net/linux: (52 commits)
  Documentation/sphinx: fix kernel-doc decode for non-utf-8 locale
  genalloc: Fix an incorrect kerneldoc comment
  doc: Add documentation for the genalloc subsystem
  assoc_array: fix path to assoc_array documentation
  kernel-doc parser mishandles declarations split into lines
  docs: ReSTify table of contents in core.rst
  docs: process: drop git snapshots from applying-patches.rst
  Documentation:input: fix typo
  swap: Remove obsolete sentence
  sphinx.rst: Allow Sphinx version 1.6 at the docs
  docs-rst: fix verbatim font size on tables
  Documentation: stable-kernel-rules: fix broken git urls
  rtmutex: update rt-mutex
  rtmutex: update rt-mutex-design
  docs: fix minimal sphinx version in conf.py
  docs: fix nested numbering in the TOC
  NVMEM documentation fix: A minor typo
  docs-rst: pdf: use same vertical margin on all Sphinx versions
  doc: Makefile: if sphinx is not found, run a check script
  docs: Fix paths in security/keys
  ...

34 files changed, 454 insertions, 493 deletions

diff --git a/Documentation/Makefile b/Documentation/Makefile
index a42320385df3..85f7856f0092 100644
--- a/Documentation/Makefile
+++ b/Documentation/Makefile
@@ -22,6 +22,8 @@ ifeq ($(HAVE_SPHINX),0)
 
 .DEFAULT:
 	$(warning The '$(SPHINXBUILD)' command was not found. Make sure you have Sphinx installed and in PATH, or set the SPHINXBUILD make variable to point to the full path of the '$(SPHINXBUILD)' executable.)
+	@echo
+	@./scripts/sphinx-pre-install
 	@echo "  SKIP    Sphinx $@ target."
 
 else # HAVE_SPHINX
@@ -95,16 +97,6 @@ endif # HAVE_SPHINX
 # The following targets are independent of HAVE_SPHINX, and the rules should
 # work or silently pass without Sphinx.
 
-# no-ops for the Sphinx toolchain
-sgmldocs:
-	@:
-psdocs:
-	@:
-mandocs:
-	@:
-installmandocs:
-	@:
-
 cleandocs:
 	$(Q)rm -rf $(BUILDDIR)
 	$(Q)$(MAKE) BUILDDIR=$(abspath $(BUILDDIR)) $(build)=Documentation/media clean
diff --git a/Documentation/arm/firmware.txt b/Documentation/arm/firmware.txt
index da6713adac8a..7f175dbb427e 100644
--- a/Documentation/arm/firmware.txt
+++ b/Documentation/arm/firmware.txt
@@ -60,7 +60,7 @@ Example of using a firmware operation:
 
 	/* some platform code, e.g. SMP initialization */
 
-	__raw_writel(virt_to_phys(exynos4_secondary_startup),
+	__raw_writel(__pa_symbol(exynos4_secondary_startup),
 		CPU1_BOOT_REG);
 
 	/* Call Exynos specific smc call */
diff --git a/Documentation/conf.py b/Documentation/conf.py
index 71b032bb44fd..f9054ab60cb1 100644
--- a/Documentation/conf.py
+++ b/Documentation/conf.py
@@ -29,7 +29,7 @@ from load_config import loadConfig
 # -- General configuration ------------------------------------------------
 
 # If your documentation needs a minimal Sphinx version, state it here.
-needs_sphinx = '1.2'
+needs_sphinx = '1.3'
 
 # Add any Sphinx extension module names here, as strings. They can be
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
@@ -344,8 +344,8 @@ if major == 1 and minor > 3:
 if major == 1 and minor <= 4:
     latex_elements['preamble']  += '\\usepackage[margin=0.5in, top=1in, bottom=1in]{geometry}'
 elif major == 1 and (minor > 5 or (minor == 5 and patch >= 3)):
-    latex_elements['sphinxsetup'] = 'hmargin=0.5in, vmargin=0.5in'
-
+    latex_elements['sphinxsetup'] = 'hmargin=0.5in, vmargin=1in'
+    latex_elements['preamble']  += '\\fvset{fontsize=auto}\n'
 
 # Grouping the document tree into LaTeX files. List of tuples
 # (source start file, target name, title,
diff --git a/Documentation/core-api/genalloc.rst b/Documentation/core-api/genalloc.rst
new file mode 100644
index 000000000000..6b38a39fab24
--- /dev/null
+++ b/Documentation/core-api/genalloc.rst
@@ -0,0 +1,144 @@
+The genalloc/genpool subsystem
+==============================
+
+There are a number of memory-allocation subsystems in the kernel, each
+aimed at a specific need.  Sometimes, however, a kernel developer needs to
+implement a new allocator for a specific range of special-purpose memory;
+often that memory is located on a device somewhere.  The author of the
+driver for that device can certainly write a little allocator to get the
+job done, but that is the way to fill the kernel with dozens of poorly
+tested allocators.  Back in 2005, Jes Sorensen lifted one of those
+allocators from the sym53c8xx_2 driver and posted_ it as a generic module
+for the creation of ad hoc memory allocators.  This code was merged
+for the 2.6.13 release; it has been modified considerably since then.
+
+.. _posted: https://lwn.net/Articles/125842/
+
+Code using this allocator should include <linux/genalloc.h>.  The action
+begins with the creation of a pool using one of:
+
+.. kernel-doc:: lib/genalloc.c
+   :functions: gen_pool_create		
+
+.. kernel-doc:: lib/genalloc.c
+   :functions: devm_gen_pool_create
+
+A call to :c:func:`gen_pool_create` will create a pool.  The granularity of
+allocations is set with min_alloc_order; it is a log-base-2 number like
+those used by the page allocator, but it refers to bytes rather than pages.
+So, if min_alloc_order is passed as 3, then all allocations will be a
+multiple of eight bytes.  Increasing min_alloc_order decreases the memory
+required to track the memory in the pool.  The nid parameter specifies
+which NUMA node should be used for the allocation of the housekeeping
+structures; it can be -1 if the caller doesn't care.
+
+The "managed" interface :c:func:`devm_gen_pool_create` ties the pool to a
+specific device.  Among other things, it will automatically clean up the
+pool when the given device is destroyed.
+
+A pool is shut down with:
+
+.. kernel-doc:: lib/genalloc.c
+   :functions: gen_pool_destroy
+
+It's worth noting that, if there are still allocations outstanding from the
+given pool, this function will take the rather extreme step of invoking
+BUG(), crashing the entire system.  You have been warned.
+
+A freshly created pool has no memory to allocate.  It is fairly useless in
+that state, so one of the first orders of business is usually to add memory
+to the pool.  That can be done with one of:
+
+.. kernel-doc:: include/linux/genalloc.h
+   :functions: gen_pool_add
+
+.. kernel-doc:: lib/genalloc.c
+   :functions: gen_pool_add_virt
+
+A call to :c:func:`gen_pool_add` will place the size bytes of memory
+starting at addr (in the kernel's virtual address space) into the given
+pool, once again using nid as the node ID for ancillary memory allocations.
+The :c:func:`gen_pool_add_virt` variant associates an explicit physical
+address with the memory; this is only necessary if the pool will be used
+for DMA allocations.
+
+The functions for allocating memory from the pool (and putting it back)
+are:
+
+.. kernel-doc:: lib/genalloc.c
+   :functions: gen_pool_alloc
+
+.. kernel-doc:: lib/genalloc.c
+   :functions: gen_pool_dma_alloc
+
+.. kernel-doc:: lib/genalloc.c
+   :functions: gen_pool_free
+
+As one would expect, :c:func:`gen_pool_alloc` will allocate size< bytes
+from the given pool.  The :c:func:`gen_pool_dma_alloc` variant allocates
+memory for use with DMA operations, returning the associated physical
+address in the space pointed to by dma.  This will only work if the memory
+was added with :c:func:`gen_pool_add_virt`.  Note that this function
+departs from the usual genpool pattern of using unsigned long values to
+represent kernel addresses; it returns a void * instead.
+
+That all seems relatively simple; indeed, some developers clearly found it
+to be too simple.  After all, the interface above provides no control over
+how the allocation functions choose which specific piece of memory to
+return.  If that sort of control is needed, the following functions will be
+of interest:
+
+.. kernel-doc:: lib/genalloc.c
+   :functions: gen_pool_alloc_algo
+
+.. kernel-doc:: lib/genalloc.c
+   :functions: gen_pool_set_algo
+
+Allocations with :c:func:`gen_pool_alloc_algo` specify an algorithm to be
+used to choose the memory to be allocated; the default algorithm can be set
+with :c:func:`gen_pool_set_algo`.  The data value is passed to the
+algorithm; most ignore it, but it is occasionally needed.  One can,
+naturally, write a special-purpose algorithm, but there is a fair set
+already available:
+
+- gen_pool_first_fit is a simple first-fit allocator; this is the default
+  algorithm if none other has been specified.
+
+- gen_pool_first_fit_align forces the allocation to have a specific
+  alignment (passed via data in a genpool_data_align structure).
+
+- gen_pool_first_fit_order_align aligns the allocation to the order of the
+  size.  A 60-byte allocation will thus be 64-byte aligned, for example.
+
+- gen_pool_best_fit, as one would expect, is a simple best-fit allocator.
+
+- gen_pool_fixed_alloc allocates at a specific offset (passed in a
+  genpool_data_fixed structure via the data parameter) within the pool.
+  If the indicated memory is not available the allocation fails.
+
+There is a handful of other functions, mostly for purposes like querying
+the space available in the pool or iterating through chunks of memory.
+Most users, however, should not need much beyond what has been described
+above.  With luck, wider awareness of this module will help to prevent the
+writing of special-purpose memory allocators in the future.
+
+.. kernel-doc:: lib/genalloc.c
+   :functions: gen_pool_virt_to_phys
+
+.. kernel-doc:: lib/genalloc.c
+   :functions: gen_pool_for_each_chunk
+
+.. kernel-doc:: lib/genalloc.c
+   :functions: addr_in_gen_pool
+
+.. kernel-doc:: lib/genalloc.c
+   :functions: gen_pool_avail
+
+.. kernel-doc:: lib/genalloc.c
+   :functions: gen_pool_size
+
+.. kernel-doc:: lib/genalloc.c
+   :functions: gen_pool_get
+
+.. kernel-doc:: lib/genalloc.c
+   :functions: of_gen_pool_get
diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst
index 0606be3a3111..d5bbe035316d 100644
--- a/Documentation/core-api/index.rst
+++ b/Documentation/core-api/index.rst
@@ -20,6 +20,7 @@ Core utilities
    genericirq
    flexible-arrays
    librs
+   genalloc
 
 Interfaces for kernel debugging
 ===============================
diff --git a/Documentation/dev-tools/gdb-kernel-debugging.rst b/Documentation/dev-tools/gdb-kernel-debugging.rst
index 5e93c9bc6619..19df79286f00 100644
--- a/Documentation/dev-tools/gdb-kernel-debugging.rst
+++ b/Documentation/dev-tools/gdb-kernel-debugging.rst
@@ -31,11 +31,13 @@ Setup
   CONFIG_DEBUG_INFO_REDUCED off. If your architecture supports
   CONFIG_FRAME_POINTER, keep it enabled.
 
-- Install that kernel on the guest.
+- Install that kernel on the guest, turn off KASLR if necessary by adding
+  "nokaslr" to the kernel command line.
   Alternatively, QEMU allows to boot the kernel directly using -kernel,
   -append, -initrd command line switches. This is generally only useful if
   you do not depend on modules. See QEMU documentation for more details on
-  this mode.
+  this mode. In this case, you should build the kernel with
+  CONFIG_RANDOMIZE_BASE disabled if the architecture supports KASLR.
 
 - Enable the gdb stub of QEMU/KVM, either
 
diff --git a/Documentation/dev-tools/kgdb.rst b/Documentation/dev-tools/kgdb.rst
index 75273203a35a..d38be58f872a 100644
--- a/Documentation/dev-tools/kgdb.rst
+++ b/Documentation/dev-tools/kgdb.rst
@@ -348,6 +348,15 @@ default behavior is always set to 0.
     - ``echo 1 > /sys/module/debug_core/parameters/kgdbreboot``
     - Enter the debugger on reboot notify.
 
+Kernel parameter: ``nokaslr``
+-----------------------------
+
+If the architecture that you are using enable KASLR by default,
+you should consider turning it off.  KASLR randomizes the
+virtual address where the kernel image is mapped and confuse
+gdb which resolve kernel symbol address from symbol table
+of vmlinux.
+
 Using kdb
 =========
 
@@ -358,7 +367,7 @@ This is a quick example of how to use kdb.
 
 1. Configure kgdboc at boot using kernel parameters::
 
-	console=ttyS0,115200 kgdboc=ttyS0,115200
+	console=ttyS0,115200 kgdboc=ttyS0,115200 nokaslr
 
    OR
 
diff --git a/Documentation/doc-guide/sphinx.rst b/Documentation/doc-guide/sphinx.rst
index 84e8e8a9cbdb..a2417633fdd8 100644
--- a/Documentation/doc-guide/sphinx.rst
+++ b/Documentation/doc-guide/sphinx.rst
@@ -19,6 +19,110 @@ Finally, there are thousands of plain text documentation files scattered around
 ``Documentation``. Some of these will likely be converted to reStructuredText
 over time, but the bulk of them will remain in plain text.
 
+.. _sphinx_install:
+
+Sphinx Install
+==============
+
+The ReST markups currently used by the Documentation/ files are meant to be
+built with ``Sphinx`` version 1.3 or upper. If you're desiring to build
+PDF outputs, it is recommended to use version 1.4.6 or upper.
+
+There's a script that checks for the Spinx requirements. Please see
+:ref:`sphinx-pre-install` for further details.
+
+Most distributions are shipped with Sphinx, but its toolchain is fragile,
+and it is not uncommon that upgrading it or some other Python packages
+on your machine would cause the documentation build to break.
+
+A way to get rid of that is to use a different version than the one shipped
+on your distributions. In order to do that, it is recommended to install
+Sphinx inside a virtual environment, using ``virtualenv-3``
+or ``virtualenv``, depending on how your distribution packaged Python 3.
+
+.. note::
+
+   #) Sphinx versions below 1.5 don't work properly with Python's
+      docutils version 0.13.1 or upper. So, if you're willing to use
+      those versions, you should run ``pip install 'docutils==0.12'``.
+
+   #) It is recommended to use the RTD theme for html output. Depending
+      on the Sphinx version, it should be installed  in separate,
+      with ``pip install sphinx_rtd_theme``.
+
+   #) Some ReST pages contain math expressions. Due to the way Sphinx work,
+      those expressions are written using LaTeX notation. It needs texlive
+      installed with amdfonts and amsmath in order to evaluate them.
+
+In summary, if you want to install Sphinx version 1.4.9, you should do::
+
+       $ virtualenv sphinx_1.4
+       $ . sphinx_1.4/bin/activate
+       (sphinx_1.4) $ pip install -r Documentation/sphinx/requirements.txt
+
+After running ``. sphinx_1.4/bin/activate``, the prompt will change,
+in order to indicate that you're using the new environment. If you
+open a new shell, you need to rerun this command to enter again at
+the virtual environment before building the documentation.
+
+Image output
+------------
+
+The kernel documentation build system contains an extension that
+handles images on both GraphViz and SVG formats (see
+:ref:`sphinx_kfigure`).
+
+For it to work, you need to install both GraphViz and ImageMagick
+packages. If those packages are not installed, the build system will
+still build the documentation, but won't include any images at the
+output.
+
+PDF and LaTeX builds
+--------------------
+
+Such builds are currently supported only with Sphinx versions 1.4 and upper.
+
+For PDF and LaTeX output, you'll also need ``XeLaTeX`` version 3.14159265.
+
+Depending on the distribution, you may also need to install a series of
+``texlive`` packages that provide the minimal set of functionalities
+required for ``XeLaTeX`` to work.
+
+.. _sphinx-pre-install:
+
+Checking for Sphinx dependencies
+--------------------------------
+
+There's a script that automatically check for Sphinx dependencies. If it can
+recognize your distribution, it will also give a hint about the install
+command line options for your distro::
+
+	$ ./scripts/sphinx-pre-install
+	Checking if the needed tools for Fedora release 26 (Twenty Six) are available
+	Warning: better to also install "texlive-luatex85".
+	You should run:
+
+		sudo dnf install -y texlive-luatex85
+		/usr/bin/virtualenv sphinx_1.4
+		. sphinx_1.4/bin/activate
+		pip install -r Documentation/sphinx/requirements.txt
+
+	Can't build as 1 mandatory dependency is missing at ./scripts/sphinx-pre-install line 468.
+
+By default, it checks all the requirements for both html and PDF, including
+the requirements for images, math expressions and LaTeX build, and assumes
+that a virtual Python environment will be used. The ones needed for html
+builds are assumed to be mandatory; the others to be optional.
+
+It supports two optional parameters:
+
+``--no-pdf``
+	Disable checks for PDF;
+
+``--no-virtualenv``
+	Use OS packaging for Sphinx instead of Python virtual environment.
+
+
 Sphinx Build
 ============
 
@@ -118,7 +222,7 @@ Here are some specific guidelines for the kernel documentation:
 the C domain
 ------------
 
-The `Sphinx C Domain`_ (name c) is suited for documentation of C API. E.g. a
+The **Sphinx C Domain** (name c) is suited for documentation of C API. E.g. a
 function prototype:
 
 .. code-block:: rst
@@ -229,6 +333,7 @@ Rendered as:
 
         - column 3
 
+.. _sphinx_kfigure:
 
 Figures & Images
 ================
diff --git a/Documentation/driver-api/basics.rst b/Documentation/driver-api/basics.rst
index ab82250c7727..73fa7d42bbba 100644
--- a/Documentation/driver-api/basics.rst
+++ b/Documentation/driver-api/basics.rst
@@ -4,7 +4,7 @@ Driver Basics
 Driver Entry and Exit points
 ----------------------------
 
-.. kernel-doc:: include/linux/init.h
+.. kernel-doc:: include/linux/module.h
    :internal:
 
 Driver device table
@@ -103,9 +103,6 @@ Kernel utility functions
 .. kernel-doc:: kernel/panic.c
    :export:
 
-.. kernel-doc:: kernel/sys.c
-   :export:
-
 .. kernel-doc:: kernel/rcu/tree.c
    :export:
 
diff --git a/Documentation/driver-api/dma-buf.rst b/Documentation/driver-api/dma-buf.rst
index 31671b469627..dc384f2f7f34 100644
--- a/Documentation/driver-api/dma-buf.rst
+++ b/Documentation/driver-api/dma-buf.rst
@@ -139,9 +139,6 @@ DMA Fences
 Seqno Hardware Fences
 ~~~~~~~~~~~~~~~~~~~~~
 
-.. kernel-doc:: drivers/dma-buf/seqno-fence.c
-   :export:
-
 .. kernel-doc:: include/linux/seqno-fence.h
    :internal:
 
diff --git a/Documentation/driver-api/miscellaneous.rst b/Documentation/driver-api/miscellaneous.rst
index 8da7d115bafc..304ffb146cf9 100644
--- a/Documentation/driver-api/miscellaneous.rst
+++ b/Documentation/driver-api/miscellaneous.rst
@@ -47,4 +47,3 @@ used by one consumer at a time.
 
 .. kernel-doc:: drivers/pwm/core.c
    :export:
-   
diff --git a/Documentation/driver-api/s390-drivers.rst b/Documentation/driver-api/s390-drivers.rst
index 7060da136095..ecf8851d3565 100644
--- a/Documentation/driver-api/s390-drivers.rst
+++ b/Documentation/driver-api/s390-drivers.rst
@@ -75,7 +75,7 @@ The channel-measurement facility provides a means to collect measurement
 data which is made available by the channel subsystem for each channel
 attached device.
 
-.. kernel-doc:: arch/s390/include/asm/cmb.h
+.. kernel-doc:: arch/s390/include/uapi/asm/cmb.h
    :internal:
 
 .. kernel-doc:: drivers/s390/cio/cmf.c
diff --git a/Documentation/driver-api/scsi.rst b/Documentation/driver-api/scsi.rst
index 859fb672319f..5a2aa7a377d9 100644
--- a/Documentation/driver-api/scsi.rst
+++ b/Documentation/driver-api/scsi.rst
@@ -224,14 +224,6 @@ mid to lowlevel SCSI driver interface
 .. kernel-doc:: drivers/scsi/hosts.c
    :export:
 
-drivers/scsi/constants.c
-~~~~~~~~~~~~~~~~~~~~~~~~
-
-mid to lowlevel SCSI driver interface
-
-.. kernel-doc:: drivers/scsi/constants.c
-   :export:
-
 Transport classes
 -----------------
 
diff --git a/Documentation/features/core/tracehook/arch-support.txt b/Documentation/features/core/tracehook/arch-support.txt
index 5e97a89420ef..dfb638c2f842 100644
--- a/Documentation/features/core/tracehook/arch-support.txt
+++ b/Documentation/features/core/tracehook/arch-support.txt
@@ -25,7 +25,7 @@
     |     mn10300: |  ok  |
     |       nios2: |  ok  |
     |    openrisc: |  ok  |
-    |      parisc: | TODO |
+    |      parisc: |  ok  |
     |     powerpc: |  ok  |
     |        s390: |  ok  |
     |       score: | TODO |
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 73e7d91f03dc..405a3df759b3 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -829,9 +829,7 @@ struct address_space_operations {
   swap_activate: Called when swapon is used on a file to allocate
 	space if necessary and pin the block lookup information in
 	memory. A return value of zero indicates success,
-	in which case this file can be used to back swapspace. The
-	swapspace operations will be proxied to this address space's
-	->swap_{out,in} methods.
+	in which case this file can be used to back swapspace.
 
   swap_deactivate: Called during swapoff on files where swap_activate
 	was successful.
diff --git a/Documentation/input/input.rst b/Documentation/input/input.rst
index 3b3a22975106..47f86a4bf16c 100644
--- a/Documentation/input/input.rst
+++ b/Documentation/input/input.rst
@@ -109,7 +109,7 @@ evdev nodes are created with minors starting with 256.
 keyboard
 ~~~~~~~~
 
-``keyboard`` is in-kernel input handler ad is a part of VT code. It
+``keyboard`` is in-kernel input handler and is a part of VT code. It
 consumes keyboard keystrokes and handles user input for VT consoles.
 
 mousedev
diff --git a/Documentation/input/joydev/index.rst b/Documentation/input/joydev/index.rst
index 8d9666c7561c..ebcff43056e2 100644
--- a/Documentation/input/joydev/index.rst
+++ b/Documentation/input/joydev/index.rst
@@ -12,7 +12,6 @@ Linux Joystick support
 
 .. toctree::
 	:maxdepth: 3
-	:numbered:
 
 	joystick
 	joystick-api
diff --git a/Documentation/kbuild/makefiles.txt b/Documentation/kbuild/makefiles.txt
index 7003141a6d4f..329e740adea7 100644
--- a/Documentation/kbuild/makefiles.txt
+++ b/Documentation/kbuild/makefiles.txt
@@ -297,9 +297,9 @@ more details, with real examples.
 	ccflags-y specifies options for compiling with $(CC).
 
 	Example:
-		# drivers/acpi/Makefile
-		ccflags-y := -Os
-		ccflags-$(CONFIG_ACPI_DEBUG) += -DACPI_DEBUG_OUTPUT
+		# drivers/acpi/acpica/Makefile
+		ccflags-y			:= -Os -D_LINUX -DBUILDING_ACPICA
+		ccflags-$(CONFIG_ACPI_DEBUG)	+= -DACPI_DEBUG_OUTPUT
 
 	This variable is necessary because the top Makefile owns the
 	variable $(KBUILD_CFLAGS) and uses it for compilation flags for the
diff --git a/Documentation/locking/rt-mutex-design.txt b/Documentation/locking/rt-mutex-design.txt
index 8666070d3189..6c6e8c2410de 100644
--- a/Documentation/locking/rt-mutex-design.txt
+++ b/Documentation/locking/rt-mutex-design.txt
@@ -97,9 +97,9 @@ waiter   - A waiter is a struct that is stored on the stack of a blocked
            a process being blocked on the mutex, it is fine to allocate
            the waiter on the process's stack (local variable).  This
            structure holds a pointer to the task, as well as the mutex that
-           the task is blocked on.  It also has the plist node structures to
-           place the task in the waiter_list of a mutex as well as the
-           pi_list of a mutex owner task (described below).
+           the task is blocked on.  It also has rbtree node structures to
+           place the task in the waiters rbtree of a mutex as well as the
+           pi_waiters rbtree of a mutex owner task (described below).
 
            waiter is sometimes used in reference to the task that is waiting
            on a mutex. This is the same as waiter->task.
@@ -179,53 +179,34 @@ again.
                          |
                    F->L5-+
 
+If process G has the highest priority in the chain, then all the tasks up
+the chain (A and B in this example), must have their priorities increased
+to that of G.
 
-Plist
------
-
-Before I go further and talk about how the PI chain is stored through lists
-on both mutexes and processes, I'll explain the plist.  This is similar to
-the struct list_head functionality that is already in the kernel.
-The implementation of plist is out of scope for this document, but it is
-very important to understand what it does.
-
-There are a few differences between plist and list, the most important one
-being that plist is a priority sorted linked list.  This means that the
-priorities of the plist are sorted, such that it takes O(1) to retrieve the
-highest priority item in the list.  Obviously this is useful to store processes
-based on their priorities.
-
-Another difference, which is important for implementation, is that, unlike
-list, the head of the list is a different element than the nodes of a list.
-So the head of the list is declared as struct plist_head and nodes that will
-be added to the list are declared as struct plist_node.
-
-
-Mutex Waiter List
+Mutex Waiters Tree
 -----------------
 
-Every mutex keeps track of all the waiters that are blocked on itself. The mutex
-has a plist to store these waiters by priority.  This list is protected by
-a spin lock that is located in the struct of the mutex. This lock is called
-wait_lock.  Since the modification of the waiter list is never done in
-interrupt context, the wait_lock can be taken without disabling interrupts.
+Every mutex keeps track of all the waiters that are blocked on itself. The
+mutex has a rbtree to store these waiters by priority.  This tree is protected
+by a spin lock that is located in the struct of the mutex. This lock is called
+wait_lock.
 
 
-Task PI List
+Task PI Tree
 ------------
 
-To keep track of the PI chains, each process has its own PI list.  This is
-a list of all top waiters of the mutexes that are owned by the process.
-Note that this list only holds the top waiters and not all waiters that are
+To keep track of the PI chains, each process has its own PI rbtree.  This is
+a tree of all top waiters of the mutexes that are owned by the process.
+Note that this tree only holds the top waiters and not all waiters that are
 blocked on mutexes owned by the process.
 
-The top of the task's PI list is always the highest priority task that
+The top of the task's PI tree is always the highest priority task that
 is waiting on a mutex that is owned by the task.  So if the task has
 inherited a priority, it will always be the priority of the task that is
-at the top of this list.
+at the top of this tree.
 
-This list is stored in the task structure of a process as a plist called
-pi_list.  This list is protected by a spin lock also in the task structure,
+This tree is stored in the task structure of a process as a rbtree called
+pi_waiters.  It is protected by a spin lock also in the task structure,
 called pi_lock.  This lock may also be taken in interrupt context, so when
 locking the pi_lock, interrupts must be disabled.
 
@@ -312,15 +293,12 @@ Mutex owner and flags
 
 The mutex structure contains a pointer to the owner of the mutex.  If the
 mutex is not owned, this owner is set to NULL.  Since all architectures
-have the task structure on at least a four byte alignment (and if this is
-not true, the rtmutex.c code will be broken!), this allows for the two
-least significant bits to be used as flags.  This part is also described
-in Documentation/rt-mutex.txt, but will also be briefly described here.
-
-Bit 0 is used as the "Pending Owner" flag.  This is described later.
-Bit 1 is used as the "Has Waiters" flags.  This is also described later
-  in more detail, but is set whenever there are waiters on a mutex.
+have the task structure on at least a two byte alignment (and if this is
+not true, the rtmutex.c code will be broken!), this allows for the least
+significant bit to be used as a flag.  Bit 0 is used as the "Has Waiters"
+flag. It's set whenever there are waiters on a mutex.
 
+See Documentation/locking/rt-mutex.txt for further details.
 
 cmpxchg Tricks
 --------------
@@ -359,40 +337,31 @@ Priority adjustments
 --------------------
 
 The implementation of the PI code in rtmutex.c has several places that a
-process must adjust its priority.  With the help of the pi_list of a
+process must adjust its priority.  With the help of the pi_waiters of a
 process this is rather easy to know what needs to be adjusted.
 
-The functions implementing the task adjustments are rt_mutex_adjust_prio,
-__rt_mutex_adjust_prio (same as the former, but expects the task pi_lock
-to already be taken), rt_mutex_getprio, and rt_mutex_setprio.
+The functions implementing the task adjustments are rt_mutex_adjust_prio
+and rt_mutex_setprio. rt_mutex_setprio is only used in rt_mutex_adjust_prio.
 
-rt_mutex_getprio and rt_mutex_setprio are only used in __rt_mutex_adjust_prio.
+rt_mutex_adjust_prio examines the priority of the task, and the highest
+priority process that is waiting any of mutexes owned by the task. Since
+the pi_waiters of a task holds an order by priority of all the top waiters
+of all the mutexes that the task owns, we simply need to compare the top
+pi waiter to its own normal/deadline priority and take the higher one.
+Then rt_mutex_setprio is called to adjust the priority of the task to the
+new priority. Note that rt_mutex_setprio is defined in kernel/sched/core.c
+to implement the actual change in priority.
 
-rt_mutex_getprio returns the priority that the task should have.  Either the
-task's own normal priority, or if a process of a higher priority is waiting on
-a mutex owned by the task, then that higher priority should be returned.
-Since the pi_list of a task holds an order by priority list of all the top
-waiters of all the mutexes that the task owns, rt_mutex_getprio simply needs
-to compare the top pi waiter to its own normal priority, and return the higher
-priority back.
+(Note:  For the "prio" field in task_struct, the lower the number, the
+	higher the priority. A "prio" of 5 is of higher priority than a
+	"prio" of 10.)
 
-(Note:  if looking at the code, you will notice that the lower number of
-        prio is returned.  This is because the prio field in the task structure
-        is an inverse order of the actual priority.  So a "prio" of 5 is
-        of higher priority than a "prio" of 10.)
-
-__rt_mutex_adjust_prio examines the result of rt_mutex_getprio, and if the
-result does not equal the task's current priority, then rt_mutex_setprio
-is called to adjust the priority of the task to the new priority.
-Note that rt_mutex_setprio is defined in kernel/sched/core.c to implement the
-actual change in priority.
-
-It is interesting to note that __rt_mutex_adjust_prio can either increase
+It is interesting to note that rt_mutex_adjust_prio can either increase
 or decrease the priority of the task.  In the case that a higher priority
-process has just blocked on a mutex owned by the task, __rt_mutex_adjust_prio
+process has just blocked on a mutex owned by the task, rt_mutex_adjust_prio
 would increase/boost the task's priority.  But if a higher priority task
 were for some reason to leave the mutex (timeout or signal), this same function
-would decrease/unboost the priority of the task.  That is because the pi_list
+would decrease/unboost the priority of the task.  That is because the pi_waiters
 always contains the highest priority task that is waiting on a mutex owned
 by the task, so we only need to compare the priority of that top pi waiter
 to the normal priority of the given task.
@@ -412,9 +381,10 @@ priorities.
 
 rt_mutex_adjust_prio_chain is called with a task to be checked for PI
 (de)boosting (the owner of a mutex that a process is blocking on), a flag to
-check for deadlocking, the mutex that the task owns, and a pointer to a waiter
+check for deadlocking, the mutex that the task owns, a pointer to a waiter
 that is the process's waiter struct that is blocked on the mutex (although this
-parameter may be NULL for deboosting).
+parameter may be NULL for deboosting), a pointer to the mutex on which the task
+is blocked, and a top_task as the top waiter of the mutex.
 
 For this explanation, I will not mention deadlock detection. This explanation
 will try to stay at a high level.
@@ -424,133 +394,14 @@ that the state of the owner and lock can change when entered into this function.
 
 Before this function is called, the task has already had rt_mutex_adjust_prio
 performed on it.  This means that the task is set to the priority that it
-should be at, but the plist nodes of the task's waiter have not been updated
-with the new priorities, and that this task may not be in the proper locations
-in the pi_lists and wait_lists that the task is blocked on.  This function
+should be at, but the rbtree nodes of the task's waiter have not been updated
+with the new priorities, and this task may not be in the proper locations
+in the pi_waiters and waiters trees that the task is blocked on. This function
 solves all that.
 
-A loop is entered, where task is the owner to be checked for PI changes that
-was passed by parameter (for the first iteration).  The pi_lock of this task is
-taken to prevent any more changes to the pi_list of the task.  This also
-prevents new tasks from completing the blocking on a mutex that is owned by this
-task.
-
-If the task is not blocked on a mutex then the loop is exited.  We are at
-the top of the PI chain.
-
-A check is now done to see if the original waiter (the process that is blocked
-on the current mutex) is the top pi waiter of the task.  That is, is this
-waiter on the top of the task's pi_list.  If it is not, it either means that
-there is another process higher in priority that is blocked on one of the
-mutexes that the task owns, or that the waiter has just woken up via a signal
-or timeout and has left the PI chain.  In either case, the loop is exited, since
-we don't need to do any more changes to the priority of the current task, or any
-task that owns a mutex that this current task is waiting on.  A priority chain
-walk is only needed when a new top pi waiter is made to a task.
-
-The next check sees if the task's waiter plist node has the priority equal to
-the priority the task is set at.  If they are equal, then we are done with
-the loop.  Remember that the function started with the priority of the
-task adjusted, but the plist nodes that hold the task in other processes
-pi_lists have not been adjusted.
-
-Next, we look at the mutex that the task is blocked on. The mutex's wait_lock
-is taken.  This is done by a spin_trylock, because the locking order of the
-pi_lock and wait_lock goes in the opposite direction. If we fail to grab the
-lock, the pi_lock is released, and we restart the loop.
-
-Now that we have both the pi_lock of the task as well as the wait_lock of
-the mutex the task is blocked on, we update the task's waiter's plist node
-that is located on the mutex's wait_list.
-
-Now we release the pi_lock of the task.
-
-Next the owner of the mutex has its pi_lock taken, so we can update the
-task's entry in the owner's pi_list.  If the task is the highest priority
-process on the mutex's wait_list, then we remove the previous top waiter
-from the owner's pi_list, and replace it with the task.
-
-Note: It is possible that the task was the current top waiter on the mutex,
-      in which case the task is not yet on the pi_list of the waiter.  This
-      is OK, since plist_del does nothing if the plist node is not on any
-      list.
-
-If the task was not the top waiter of the mutex, but it was before we
-did the priority updates, that means we are deboosting/lowering the
-task.  In this case, the task is removed from the pi_list of the owner,
-and the new top waiter is added.
-
-Lastly, we unlock both the pi_lock of the task, as well as the mutex's
-wait_lock, and continue the loop again.  On the next iteration of the
-loop, the previous owner of the mutex will be the task that will be
-processed.
-
-Note: One might think that the owner of this mutex might have changed
-      since we just grab the mutex's wait_lock. And one could be right.
-      The important thing to remember is that the owner could not have
-      become the task that is being processed in the PI chain, since
-      we have taken that task's pi_lock at the beginning of the loop.
-      So as long as there is an owner of this mutex that is not the same
-      process as the tasked being worked on, we are OK.
-
-      Looking closely at the code, one might be confused.  The check for the
-      end of the PI chain is when the task isn't blocked on anything or the
-      task's waiter structure "task" element is NULL.  This check is
-      protected only by the task's pi_lock.  But the code to unlock the mutex
-      sets the task's waiter structure "task" element to NULL with only
-      the protection of the mutex's wait_lock, which was not taken yet.
-      Isn't this a race condition if the task becomes the new owner?
-
-      The answer is No!  The trick is the spin_trylock of the mutex's
-      wait_lock.  If we fail that lock, we release the pi_lock of the
-      task and continue the loop, doing the end of PI chain check again.
-
-      In the code to release the lock, the wait_lock of the mutex is held
-      the entire time, and it is not let go when we grab the pi_lock of the
-      new owner of the mutex.  So if the switch of a new owner were to happen
-      after the check for end of the PI chain and the grabbing of the
-      wait_lock, the unlocking code would spin on the new owner's pi_lock
-      but never give up the wait_lock.  So the PI chain loop is guaranteed to
-      fail the spin_trylock on the wait_lock, release the pi_lock, and
-      try again.
-
-      If you don't quite understand the above, that's OK. You don't have to,
-      unless you really want to make a proof out of it ;)
-
-
-Pending Owners and Lock stealing
---------------------------------
-
-One of the flags in the owner field of the mutex structure is "Pending Owner".
-What this means is that an owner was chosen by the process releasing the
-mutex, but that owner has yet to wake up and actually take the mutex.
-
-Why is this important?  Why can't we just give the mutex to another process
-and be done with it?
-
-The PI code is to help with real-time processes, and to let the highest
-priority process run as long as possible with little latencies and delays.
-If a high priority process owns a mutex that a lower priority process is
-blocked on, when the mutex is released it would be given to the lower priority
-process.  What if the higher priority process wants to take that mutex again.
-The high priority process would fail to take that mutex that it just gave up
-and it would need to boost the lower priority process to run with full
-latency of that critical section (since the low priority process just entered
-it).
-
-There's no reason a high priority process that gives up a mutex should be
-penalized if it tries to take that mutex again.  If the new owner of the
-mutex has not woken up yet, there's no reason that the higher priority process
-could not take that mutex away.
-
-To solve this, we introduced Pending Ownership and Lock Stealing.  When a
-new process is given a mutex that it was blocked on, it is only given
-pending ownership.  This means that it's the new owner, unless a higher
-priority process comes in and tries to grab that mutex.  If a higher priority
-process does come along and wants that mutex, we let the higher priority
-process "steal" the mutex from the pending owner (only if it is still pending)
-and continue with the mutex.
-
+The main operation of this function is summarized by Thomas Gleixner in
+rtmutex.c. See the 'Chain walk basics and protection scope' comment for further
+details.
 
 Taking of a mutex (The walk through)
 ------------------------------------
@@ -563,14 +414,14 @@ done when we have CMPXCHG enabled (otherwise the fast taking automatically
 fails).  Only when the owner field of the mutex is NULL can the lock be
 taken with the CMPXCHG and nothing else needs to be done.
 
-If there is contention on the lock, whether it is owned or pending owner
-we go about the slow path (rt_mutex_slowlock).
+If there is contention on the lock, we go about the slow path
+(rt_mutex_slowlock).
 
 The slow path function is where the task's waiter structure is created on
 the stack.  This is because the waiter structure is only needed for the
 scope of this function.  The waiter structure holds the nodes to store
-the task on the wait_list of the mutex, and if need be, the pi_list of
-the owner.
+the task on the waiters tree of the mutex, and if need be, the pi_waiters
+tree of the owner.
 
 The wait_lock of the mutex is taken since the slow path of unlocking the
 mutex also takes this lock.
@@ -581,102 +432,45 @@ contention).
 
 try_to_take_rt_mutex is used every time the task tries to grab a mutex in the
 slow path.  The first thing that is done here is an atomic setting of
-the "Has Waiters" flag of the mutex's owner field.  Yes, this could really
-be false, because if the mutex has no owner, there are no waiters and
-the current task also won't have any waiters.  But we don't have the lock
-yet, so we assume we are going to be a waiter.  The reason for this is to
-play nice for those architectures that do have CMPXCHG.  By setting this flag
-now, the owner of the mutex can't release the mutex without going into the
-slow unlock path, and it would then need to grab the wait_lock, which this
-code currently holds.  So setting the "Has Waiters" flag forces the owner
-to synchronize with this code.
-
-Now that we know that we can't have any races with the owner releasing the
-mutex, we check to see if we can take the ownership.  This is done if the
-mutex doesn't have a owner, or if we can steal the mutex from a pending
-owner.  Let's look at the situations we have here.
-
-  1) Has owner that is pending
-  ----------------------------
-
-  The mutex has a owner, but it hasn't woken up and the mutex flag
-  "Pending Owner" is set.  The first check is to see if the owner isn't the
-  current task.  This is because this function is also used for the pending
-  owner to grab the mutex.  When a pending owner wakes up, it checks to see
-  if it can take the mutex, and this is done if the owner is already set to
-  itself.  If so, we succeed and leave the function, clearing the "Pending
-  Owner" bit.
-
-  If the pending owner is not current, we check to see if the current priority is
-  higher than the pending owner.  If not, we fail the function and return.
-
-  There's also something special about a pending owner.  That is a pending owner
-  is never blocked on a mutex.  So there is no PI chain to worry about.  It also
-  means that if the mutex doesn't have any waiters, there's no accounting needed
-  to update the pending owner's pi_list, since we only worry about processes
-  blocked on the current mutex.
-
-  If there are waiters on this mutex, and we just stole the ownership, we need
-  to take the top waiter, remove it from the pi_list of the pending owner, and
-  add it to the current pi_list.  Note that at this moment, the pending owner
-  is no longer on the list of waiters.  This is fine, since the pending owner
-  would add itself back when it realizes that it had the ownership stolen
-  from itself.  When the pending owner tries to grab the mutex, it will fail
-  in try_to_take_rt_mutex if the owner field points to another process.
-
-  2) No owner
-  -----------
-
-  If there is no owner (or we successfully stole the lock), we set the owner
-  of the mutex to current, and set the flag of "Has Waiters" if the current
-  mutex actually has waiters, or we clear the flag if it doesn't.  See, it was
-  OK that we set that flag early, since now it is cleared.
-
-  3) Failed to grab ownership
-  ---------------------------
-
-  The most interesting case is when we fail to take ownership. This means that
-  there exists an owner, or there's a pending owner with equal or higher
-  priority than the current task.
-
-We'll continue on the failed case.
-
-If the mutex has a timeout, we set up a timer to go off to break us out
-of this mutex if we failed to get it after a specified amount of time.
-
-Now we enter a loop that will continue to try to take ownership of the mutex, or
-fail from a timeout or signal.
-
-Once again we try to take the mutex.  This will usually fail the first time
-in the loop, since it had just failed to get the mutex.  But the second time
-in the loop, this would likely succeed, since the task would likely be
-the pending owner.
-
-If the mutex is TASK_INTERRUPTIBLE a check for signals and timeout is done
-here.
-
-The waiter structure has a "task" field that points to the task that is blocked
-on the mutex.  This field can be NULL the first time it goes through the loop
-or if the task is a pending owner and had its mutex stolen.  If the "task"
-field is NULL then we need to set up the accounting for it.
+the "Has Waiters" flag of the mutex's owner field. By setting this flag
+now, the current owner of the mutex being contended for can't release the mutex
+without going into the slow unlock path, and it would then need to grab the
+wait_lock, which this code currently holds. So setting the "Has Waiters" flag
+forces the current owner to synchronize with this code.
+
+The lock is taken if the following are true:
+   1) The lock has no owner
+   2) The current task is the highest priority against all other
+      waiters of the lock
+
+If the task succeeds to acquire the lock, then the task is set as the
+owner of the lock, and if the lock still has waiters, the top_waiter
+(highest priority task waiting on the lock) is added to this task's
+pi_waiters tree.
+
+If the lock is not taken by try_to_take_rt_mutex(), then the
+task_blocks_on_rt_mutex() function is called. This will add the task to
+the lock's waiter tree and propagate the pi chain of the lock as well
+as the lock's owner's pi_waiters tree. This is described in the next
+section.
 
 Task blocks on mutex
 --------------------
 
 The accounting of a mutex and process is done with the waiter structure of
 the process.  The "task" field is set to the process, and the "lock" field
-to the mutex.  The plist nodes are initialized to the processes current
-priority.
+to the mutex.  The rbtree node of waiter are initialized to the processes
+current priority.
 
 Since the wait_lock was taken at the entry of the slow lock, we can safely
-add the waiter to the wait_list.  If the current process is the highest
-priority process currently waiting on this mutex, then we remove the
-previous top waiter process (if it exists) from the pi_list of the owner,
-and add the current process to that list.  Since the pi_list of the owner
+add the waiter to the task waiter tree.  If the current process is the
+highest priority process currently waiting on this mutex, then we remove the
+previous top waiter process (if it exists) from the pi_waiters of the owner,
+and add the current process to that tree.  Since the pi_waiter of the owner
 has changed, we call rt_mutex_adjust_prio on the owner to see if the owner
 should adjust its priority accordingly.
 
-If the owner is also blocked on a lock, and had its pi_list changed
+If the owner is also blocked on a lock, and had its pi_waiters changed
 (or deadlock checking is on), we unlock the wait_lock of the mutex and go ahead
 and run rt_mutex_adjust_prio_chain on the owner, as described earlier.
 
@@ -686,30 +480,23 @@ mutex (waiter "task" field is not NULL), then we go to sleep (call schedule).
 Waking up in the loop
 ---------------------
 
-The schedule can then wake up for a few reasons.
-  1) we were given pending ownership of the mutex.
-  2) we received a signal and was TASK_INTERRUPTIBLE
-  3) we had a timeout and was TASK_INTERRUPTIBLE
+The task can then wake up for a couple of reasons:
+  1) The previous lock owner released the lock, and the task now is top_waiter
+  2) we received a signal or timeout
 
-In any of these cases, we continue the loop and once again try to grab the
-ownership of the mutex.  If we succeed, we exit the loop, otherwise we continue
-and on signal and timeout, will exit the loop, or if we had the mutex stolen
-we just simply add ourselves back on the lists and go back to sleep.
+In both cases, the task will try again to acquire the lock. If it
+does, then it will take itself off the waiters tree and set itself back
+to the TASK_RUNNING state.
 
-Note: For various reasons, because of timeout and signals, the steal mutex
-      algorithm needs to be careful. This is because the current process is
-      still on the wait_list. And because of dynamic changing of priorities,
-      especially on SCHED_OTHER tasks, the current process can be the
-      highest priority task on the wait_list.
-
-Failed to get mutex on Timeout or Signal
-----------------------------------------
+In first case, if the lock was acquired by another task before this task
+could get the lock, then it will go back to sleep and wait to be woken again.
 
-If a timeout or signal occurred, the waiter's "task" field would not be
-NULL and the task needs to be taken off the wait_list of the mutex and perhaps
-pi_list of the owner.  If this process was a high priority process, then
-the rt_mutex_adjust_prio_chain needs to be executed again on the owner,
-but this time it will be lowering the priorities.
+The second case is only applicable for tasks that are grabbing a mutex
+that can wake up before getting the lock, either due to a signal or
+a timeout (i.e. rt_mutex_timed_futex_lock()). When woken, it will try to
+take the lock again, if it succeeds, then the task will return with the
+lock held, otherwise it will return with -EINTR if the task was woken
+by a signal, or -ETIMEDOUT if it timed out.
 
 
 Unlocking the Mutex
@@ -739,25 +526,12 @@ owner still needs to make this check. If there are no waiters then the mutex
 owner field is set to NULL, the wait_lock is released and nothing more is
 needed.
 
-If there are waiters, then we need to wake one up and give that waiter
-pending ownership.
+If there are waiters, then we need to wake one up.
 
 On the wake up code, the pi_lock of the current owner is taken.  The top
-waiter of the lock is found and removed from the wait_list of the mutex
-as well as the pi_list of the current owner.  The task field of the new
-pending owner's waiter structure is set to NULL, and the owner field of the
-mutex is set to the new owner with the "Pending Owner" bit set, as well
-as the "Has Waiters" bit if there still are other processes blocked on the
-mutex.
-
-The pi_lock of the previous owner is released, and the new pending owner's
-pi_lock is taken.  Remember that this is the trick to prevent the race
-condition in rt_mutex_adjust_prio_chain from adding itself as a waiter
-on the mutex.
-
-We now clear the "pi_blocked_on" field of the new pending owner, and if
-the mutex still has waiters pending, we add the new top waiter to the pi_list
-of the pending owner.
+waiter of the lock is found and removed from the waiters tree of the mutex
+as well as the pi_waiters tree of the current owner. The "Has Waiters" bit is
+marked to prevent lower priority tasks from stealing the lock.
 
 Finally we unlock the pi_lock of the pending owner and wake it up.
 
@@ -772,10 +546,14 @@ Credits
 -------
 
 Author:  Steven Rostedt <rostedt@goodmis.org>
+Updated: Alex Shi <alex.shi@linaro.org>	- 7/6/2017
 
-Reviewers:  Ingo Molnar, Thomas Gleixner, Thomas Duetsch, and Randy Dunlap
+Original Reviewers:  Ingo Molnar, Thomas Gleixner, Thomas Duetsch, and
+		     Randy Dunlap
+Update (7/6/2017) Reviewers: Steven Rostedt and Sebastian Siewior
 
 Updates
 -------
 
 This document was originally written for 2.6.17-rc3-mm1
+was updated on 4.12
diff --git a/Documentation/locking/rt-mutex.txt b/Documentation/locking/rt-mutex.txt
index 243393d882ee..35793e003041 100644
--- a/Documentation/locking/rt-mutex.txt
+++ b/Documentation/locking/rt-mutex.txt
@@ -28,14 +28,13 @@ magic bullet for poorly designed applications, but it allows
 well-designed applications to use userspace locks in critical parts of
 an high priority thread, without losing determinism.
 
-The enqueueing of the waiters into the rtmutex waiter list is done in
+The enqueueing of the waiters into the rtmutex waiter tree is done in
 priority order. For same priorities FIFO order is chosen. For each
 rtmutex, only the top priority waiter is enqueued into the owner's
-priority waiters list. This list too queues in priority order. Whenever
+priority waiters tree. This tree too queues in priority order. Whenever
 the top priority waiter of a task changes (for example it timed out or
-got a signal), the priority of the owner task is readjusted. [The
-priority enqueueing is handled by "plists", see include/linux/plist.h
-for more details.]
+got a signal), the priority of the owner task is readjusted. The
+priority enqueueing is handled by "pi_waiters".
 
 RT-mutexes are optimized for fastpath operations and have no internal
 locking overhead when locking an uncontended mutex or unlocking a mutex
@@ -46,34 +45,29 @@ is used]
 The state of the rt-mutex is tracked via the owner field of the rt-mutex
 structure:
 
-rt_mutex->owner holds the task_struct pointer of the owner. Bit 0 and 1
-are used to keep track of the "owner is pending" and "rtmutex has
-waiters" state.
+lock->owner holds the task_struct pointer of the owner. Bit 0 is used to
+keep track of the "lock has waiters" state.
 
- owner		bit1	bit0
- NULL		0	0	mutex is free (fast acquire possible)
- NULL		0	1	invalid state
- NULL		1	0	Transitional state*
- NULL		1	1	invalid state
- taskpointer	0	0	mutex is held (fast release possible)
- taskpointer	0	1	task is pending owner
- taskpointer	1	0	mutex is held and has waiters
- taskpointer	1	1	task is pending owner and mutex has waiters
+ owner        bit0
+ NULL         0       lock is free (fast acquire possible)
+ NULL         1       lock is free and has waiters and the top waiter
+			is going to take the lock*
+ taskpointer  0       lock is held (fast release possible)
+ taskpointer  1       lock is held and has waiters**
 
-Pending-ownership handling is a performance optimization:
-pending-ownership is assigned to the first (highest priority) waiter of
-the mutex, when the mutex is released. The thread is woken up and once
-it starts executing it can acquire the mutex. Until the mutex is taken
-by it (bit 0 is cleared) a competing higher priority thread can "steal"
-the mutex which puts the woken up thread back on the waiters list.
+The fast atomic compare exchange based acquire and release is only
+possible when bit 0 of lock->owner is 0.
 
-The pending-ownership optimization is especially important for the
-uninterrupted workflow of high-prio tasks which repeatedly
-takes/releases locks that have lower-prio waiters. Without this
-optimization the higher-prio thread would ping-pong to the lower-prio
-task [because at unlock time we always assign a new owner].
+(*) It also can be a transitional state when grabbing the lock
+with ->wait_lock is held. To prevent any fast path cmpxchg to the lock,
+we need to set the bit0 before looking at the lock, and the owner may be
+NULL in this small time, hence this can be a transitional state.
 
-(*) The "mutex has waiters" bit gets set to take the lock. If the lock
-doesn't already have an owner, this bit is quickly cleared if there are
-no waiters.  So this is a transitional state to synchronize with looking
-at the owner field of the mutex and the mutex owner releasing the lock.
+(**) There is a small time when bit 0 is set but there are no
+waiters. This can happen when grabbing the lock in the slow path.
+To prevent a cmpxchg of the owner releasing the lock, we need to
+set this bit before looking at the lock.
+
+BTW, there is still technically a "Pending Owner", it's just not called
+that anymore. The pending owner happens to be the top_waiter of a lock
+that has no owner and has been woken up to grab the lock.
diff --git a/Documentation/media/uapi/cec/cec-funcs.rst b/Documentation/media/uapi/cec/cec-funcs.rst
index 5b7630f2e076..6d696cead5cb 100644
--- a/Documentation/media/uapi/cec/cec-funcs.rst
+++ b/Documentation/media/uapi/cec/cec-funcs.rst
@@ -7,7 +7,6 @@ Function Reference
 
 .. toctree::
     :maxdepth: 1
-    :numbered:
 
     cec-func-open
     cec-func-close
diff --git a/Documentation/networking/ieee802154.txt b/Documentation/networking/ieee802154.txt
index c4114346f054..057e9fdbfac9 100644
--- a/Documentation/networking/ieee802154.txt
+++ b/Documentation/networking/ieee802154.txt
@@ -84,17 +84,17 @@ Device drivers API
 ==================
 
 The include/net/mac802154.h defines following functions:
- - struct ieee802154_dev *ieee802154_alloc_device
-   (size_t priv_size, struct ieee802154_ops *ops):
-   allocation of IEEE 802.15.4 compatible device
+ - struct ieee802154_hw *
+   ieee802154_alloc_hw(size_t priv_data_len, const struct ieee802154_ops *ops):
+   allocation of IEEE 802.15.4 compatible hardware device
 
- - void ieee802154_free_device(struct ieee802154_dev *dev):
-   freeing allocated device
+ - void ieee802154_free_hw(struct ieee802154_hw *hw):
+   freeing allocated hardware device
 
- - int ieee802154_register_device(struct ieee802154_dev *dev):
-   register PHY in the system
+ - int ieee802154_register_hw(struct ieee802154_hw *hw):
+   register PHY which is the allocated hardware device, in the system
 
- - void ieee802154_unregister_device(struct ieee802154_dev *dev):
+ - void ieee802154_unregister_hw(struct ieee802154_hw *hw):
    freeing registered PHY
 
 Moreover IEEE 802.15.4 device operations structure should be filled.
diff --git a/Documentation/nvmem/nvmem.txt b/Documentation/nvmem/nvmem.txt
index dbd40d879239..8d8d8f58f96f 100644
--- a/Documentation/nvmem/nvmem.txt
+++ b/Documentation/nvmem/nvmem.txt
@@ -112,7 +112,7 @@ take nvmem_device as parameter.
 5. Releasing a reference to the NVMEM
 =====================================
 
-When a consumers no longer needs the NVMEM, it has to release the reference
+When a consumer no longer needs the NVMEM, it has to release the reference
 to the NVMEM it has obtained using the APIs mentioned in the above section.
 The NVMEM framework provides 2 APIs to release a reference to the NVMEM.
 
diff --git a/Documentation/process/applying-patches.rst b/Documentation/process/applying-patches.rst
index a0d058cc6d25..dc2ddc345044 100644
--- a/Documentation/process/applying-patches.rst
+++ b/Documentation/process/applying-patches.rst
@@ -6,9 +6,6 @@ Applying Patches To The Linux Kernel
 Original by:
 	Jesper Juhl, August 2005
 
-Last update:
-	2016-09-14
-
 .. note::
 
    This document is obsolete.  In most cases, rather than using ``patch``
@@ -344,7 +341,7 @@ possible.
 
 This is a good branch to run for people who want to help out testing
 development kernels but do not want to run some of the really experimental
-stuff (such people should see the sections about -git and -mm kernels below).
+stuff (such people should see the sections about -next and -mm kernels below).
 
 The -rc patches are not incremental, they apply to a base 4.x kernel, just
 like the 4.x.y patches described above. The kernel version before the -rcN
@@ -380,44 +377,6 @@ Here are 3 examples of how to apply these patches::
 	$ mv linux-4.7.3 linux-4.8-rc5		# rename the kernel source dir
 
 
-The -git kernels
-================
-
-These are daily snapshots of Linus' kernel tree (managed in a git
-repository, hence the name).
-
-These patches are usually released daily and represent the current state of
-Linus's tree. They are more experimental than -rc kernels since they are
-generated automatically without even a cursory glance to see if they are
-sane.
-
--git patches are not incremental and apply either to a base 4.x kernel or
-a base 4.x-rc kernel -- you can see which from their name.
-A patch named 4.7-git1 applies to the 4.7 kernel source and a patch
-named 4.8-rc3-git2 applies to the source of the 4.8-rc3 kernel.
-
-Here are some examples of how to apply these patches::
-
-	# moving from 4.7 to 4.7-git1
-
-	$ cd ~/linux-4.7			# change to the kernel source dir
-	$ patch -p1 < ../patch-4.7-git1		# apply the 4.7-git1 patch
-	$ cd ..
-	$ mv linux-4.7 linux-4.7-git1		# rename the kernel source dir
-
-	# moving from 4.7-git1 to 4.8-rc2-git3
-
-	$ cd ~/linux-4.7-git1			# change to the kernel source dir
-	$ patch -p1 -R < ../patch-4.7-git1	# revert the 4.7-git1 patch
-						# we now have a 4.7 kernel
-	$ patch -p1 < ../patch-4.8-rc2		# apply the 4.8-rc2 patch
-						# the kernel is now 4.8-rc2
-	$ patch -p1 < ../patch-4.8-rc2-git3	# apply the 4.8-rc2-git3 patch
-						# the kernel is now 4.8-rc2-git3
-	$ cd ..
-	$ mv linux-4.7-git1 linux-4.8-rc2-git3	# rename source dir
-
-
 The -mm patches and the linux-next tree
 =======================================
 
diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst
index adbb50ae5246..560beaef5a7c 100644
--- a/Documentation/process/changes.rst
+++ b/Documentation/process/changes.rst
@@ -53,7 +53,7 @@ mcelog                 0.6              mcelog --version
 iptables               1.4.2            iptables -V
 openssl & libcrypto    1.0.0            openssl version
 bc                     1.06.95          bc --version
-Sphinx\ [#f1]_	       1.2		sphinx-build --version
+Sphinx\ [#f1]_	       1.3		sphinx-build --version
 ====================== ===============  ========================================
 
 .. [#f1] Sphinx is needed only to build the Kernel documentation
@@ -309,18 +309,8 @@ Kernel documentation
 Sphinx
 ------
 
-The ReST markups currently used by the Documentation/ files are meant to be
-built with ``Sphinx`` version 1.2 or upper. If you're desiring to build
-PDF outputs, it is recommended to use version 1.4.6.
-
-.. note::
-
-  Please notice that, for PDF and LaTeX output, you'll also need ``XeLaTeX``
-  version 3.14159265. Depending on the distribution, you may also need to
-  install a series of ``texlive`` packages that provide the minimal set of
-  functionalities required for ``XeLaTex`` to work. For PDF output you'll also
-  need ``convert(1)`` from ImageMagick (https://www.imagemagick.org).
-
+Please see :ref:`sphinx_install` in ``Documentation/doc-guide/sphinx.rst``
+for details about Sphinx requirements.
 
 Getting updated software
 ========================
diff --git a/Documentation/process/stable-kernel-rules.rst b/Documentation/process/stable-kernel-rules.rst
index 61e9c78bd6d1..36a2dded525b 100644
--- a/Documentation/process/stable-kernel-rules.rst
+++ b/Documentation/process/stable-kernel-rules.rst
@@ -166,12 +166,12 @@ Trees
  - The queues of patches, for both completed versions and in progress
    versions can be found at:
 
-	http://git.kernel.org/?p=linux/kernel/git/stable/stable-queue.git
+	https://git.kernel.org/pub/scm/linux/kernel/git/stable/stable-queue.git
 
  - The finalized and tagged releases of all stable kernels can be found
    in separate branches per version at:
 
-	http://git.kernel.org/?p=linux/kernel/git/stable/linux-stable.git
+	https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable.git
 
 
 Review committee
diff --git a/Documentation/process/submitting-patches.rst b/Documentation/process/submitting-patches.rst
index 3e10719fee35..733478ade91b 100644
--- a/Documentation/process/submitting-patches.rst
+++ b/Documentation/process/submitting-patches.rst
@@ -413,7 +413,7 @@ e-mail discussions.
 
 
 
-11) Sign your work — the Developer's Certificate of Origin
+11) Sign your work - the Developer's Certificate of Origin
 ----------------------------------------------------------
 
 To improve tracking of who did what, especially with patches that can
diff --git a/Documentation/security/keys/core.rst b/Documentation/security/keys/core.rst
index 1648fa80b3bf..1266eeae45f6 100644
--- a/Documentation/security/keys/core.rst
+++ b/Documentation/security/keys/core.rst
@@ -16,17 +16,7 @@ The key service can be configured on by enabling:
 
 This document has the following sections:
 
-	- Key overview
-	- Key service overview
-	- Key access permissions
-	- SELinux support
-	- New procfs files
-	- Userspace system call interface
-	- Kernel services
-	- Notes on accessing payload contents
-	- Defining a key type
-	- Request-key callback service
-	- Garbage collection
+.. contents:: :local:
 
 
 Key Overview
@@ -443,7 +433,7 @@ The main syscalls are:
      /sbin/request-key will be invoked in an attempt to obtain a key. The
      callout_info string will be passed as an argument to the program.
 
-     See also Documentation/security/keys-request-key.txt.
+     See also Documentation/security/keys/request-key.rst.
 
 
 The keyctl syscall functions are:
@@ -973,7 +963,7 @@ payload contents" for more information.
     If successful, the key will have been attached to the default keyring for
     implicitly obtained request-key keys, as set by KEYCTL_SET_REQKEY_KEYRING.
 
-    See also Documentation/security/keys-request-key.txt.
+    See also Documentation/security/keys/request-key.rst.
 
 
  *  To search for a key, passing auxiliary data to the upcaller, call::
diff --git a/Documentation/security/keys/request-key.rst b/Documentation/security/keys/request-key.rst
index aba32784174c..b2d16abaa9e9 100644
--- a/Documentation/security/keys/request-key.rst
+++ b/Documentation/security/keys/request-key.rst
@@ -3,7 +3,7 @@ Key Request Service
 ===================
 
 The key request service is part of the key retention service (refer to
-Documentation/security/keys.txt).  This document explains more fully how
+Documentation/security/core.rst).  This document explains more fully how
 the requesting algorithm works.
 
 The process starts by either the kernel requesting a service by calling
diff --git a/Documentation/security/keys/trusted-encrypted.rst b/Documentation/security/keys/trusted-encrypted.rst
index 7b503831bdea..3bb24e09a332 100644
--- a/Documentation/security/keys/trusted-encrypted.rst
+++ b/Documentation/security/keys/trusted-encrypted.rst
@@ -172,4 +172,4 @@ Other uses for trusted and encrypted keys, such as for disk and file encryption
 are anticipated.  In particular the new format 'ecryptfs' has been defined in
 in order to use encrypted keys to mount an eCryptfs filesystem.  More details
 about the usage can be found in the file
-``Documentation/security/keys-ecryptfs.txt``.
+``Documentation/security/keys/ecryptfs.rst``.
diff --git a/Documentation/sphinx-static/theme_overrides.css b/Documentation/sphinx-static/theme_overrides.css
index d5764a4de5a2..522b6d4c49d4 100644
--- a/Documentation/sphinx-static/theme_overrides.css
+++ b/Documentation/sphinx-static/theme_overrides.css
@@ -4,6 +4,17 @@
  *
  */
 
+/* Interim: Code-blocks with line nos - lines and line numbers don't line up.
+ * see: https://github.com/rtfd/sphinx_rtd_theme/issues/419
+ */
+
+div[class^="highlight"] pre {
+    line-height: normal;
+}
+.rst-content .highlight > pre {
+    line-height: normal;
+}
+
 @media screen {
 
     /* content column
@@ -56,6 +67,12 @@
 	font-family: "Courier New", Courier, monospace
     }
 
+    /* fix bottom margin of lists items */
+
+    .rst-content .section ul li:last-child, .rst-content .section ul li p:last-child {
+          margin-bottom: 12px;
+    }
+
     /* inline literal: drop the borderbox, padding and red color */
 
     code, .rst-content tt, .rst-content code {
diff --git a/Documentation/sphinx/kerneldoc.py b/Documentation/sphinx/kerneldoc.py
index d15e07f36881..39aa9e8697cc 100644
--- a/Documentation/sphinx/kerneldoc.py
+++ b/Documentation/sphinx/kerneldoc.py
@@ -27,6 +27,7 @@
 # Please make sure this works on both python2 and python3.
 #
 
+import codecs
 import os
 import subprocess
 import sys
@@ -88,13 +89,10 @@ class KernelDocDirective(Directive):
         try:
             env.app.verbose('calling kernel-doc \'%s\'' % (" ".join(cmd)))
 
-            p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, universal_newlines=True)
+            p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
             out, err = p.communicate()
 
-            # python2 needs conversion to unicode.
-            # python3 with universal_newlines=True returns strings.
-            if sys.version_info.major < 3:
-                out, err = unicode(out, 'utf-8'), unicode(err, 'utf-8')
+            out, err = codecs.decode(out, 'utf-8'), codecs.decode(err, 'utf-8')
 
             if p.returncode != 0:
                 sys.stderr.write(err)
diff --git a/Documentation/sphinx/requirements.txt b/Documentation/sphinx/requirements.txt
new file mode 100644
index 000000000000..742be3e12619
--- /dev/null
+++ b/Documentation/sphinx/requirements.txt
@@ -0,0 +1,3 @@
+docutils==0.12
+Sphinx==1.4.9
+sphinx_rtd_theme
diff --git a/Documentation/translations/zh_CN/HOWTO b/Documentation/translations/zh_CN/HOWTO
index 11be075ba5fa..5f6d09edc9ac 100644
--- a/Documentation/translations/zh_CN/HOWTO
+++ b/Documentation/translations/zh_CN/HOWTO
@@ -149,9 +149,7 @@ Linux内核代码中包含有大量的文档。这些文档对于学习如何与
 核源码的主目录中使用以下不同命令将会分别生成PDF、Postscript、HTML和手册
 页等不同格式的文档：
     make pdfdocs
-    make psdocs
     make htmldocs
-    make mandocs
 
 
 如何成为内核开发者