diff --git a/Documentation/DMA-API-HOWTO.txt b/Documentation/DMA-API-HOWTO.txt
index 4ed3883..f0cc3f7 100644
--- a/Documentation/DMA-API-HOWTO.txt
+++ b/Documentation/DMA-API-HOWTO.txt
@@ -1,22 +1,24 @@
-		     Dynamic DMA mapping Guide
-		     =========================
+=========================
+Dynamic DMA mapping Guide
+=========================
 
-		 David S. Miller <davem@redhat.com>
-		 Richard Henderson <rth@cygnus.com>
-		  Jakub Jelinek <jakub@redhat.com>
+:Author: David S. Miller <davem@redhat.com>
+:Author: Richard Henderson <rth@cygnus.com>
+:Author: Jakub Jelinek <jakub@redhat.com>
 
 This is a guide to device driver writers on how to use the DMA API
 with example pseudo-code.  For a concise description of the API, see
 DMA-API.txt.
 
-                       CPU and DMA addresses
+CPU and DMA addresses
+=====================
 
 There are several kinds of addresses involved in the DMA API, and it's
 important to understand the differences.
 
 The kernel normally uses virtual addresses.  Any address returned by
 kmalloc(), vmalloc(), and similar interfaces is a virtual address and can
-be stored in a "void *".
+be stored in a ``void *``.
 
 The virtual memory system (TLB, page tables, etc.) translates virtual
 addresses to CPU physical addresses, which are stored as "phys_addr_t" or
@@ -37,7 +39,7 @@
 supports 64-bit addresses for main memory and PCI BARs, it may use an IOMMU
 so devices only need to use 32-bit DMA addresses.
 
-Here's a picture and some examples:
+Here's a picture and some examples::
 
                CPU                  CPU                  Bus
              Virtual              Physical             Address
@@ -98,15 +100,16 @@
 bus-specific DMA API, i.e., use the dma_map_*() interfaces rather than the
 pci_map_*() interfaces.
 
-First of all, you should make sure
+First of all, you should make sure::
 
-#include <linux/dma-mapping.h>
+	#include <linux/dma-mapping.h>
 
 is in your driver, which provides the definition of dma_addr_t.  This type
 can hold any valid DMA address for the platform and should be used
 everywhere you hold a DMA address returned from the DMA mapping functions.
 
-			 What memory is DMA'able?
+What memory is DMA'able?
+========================
 
 The first piece of information you must know is what kernel memory can
 be used with the DMA mapping facilities.  There has been an unwritten
@@ -143,7 +146,8 @@
 networking subsystems make sure that the buffers they use are valid
 for you to DMA from/to.
 
-			DMA addressing limitations
+DMA addressing limitations
+==========================
 
 Does your device have any DMA addressing limitations?  For example, is
 your device only capable of driving the low order 24-bits of address?
@@ -166,7 +170,7 @@
 because this shows that you did think about these issues wrt. your
 device.
 
-The query is performed via a call to dma_set_mask_and_coherent():
+The query is performed via a call to dma_set_mask_and_coherent()::
 
 	int dma_set_mask_and_coherent(struct device *dev, u64 mask);
 
@@ -175,12 +179,12 @@
 queries can be used instead:
 
 	The query for streaming mappings is performed via a call to
-	dma_set_mask():
+	dma_set_mask()::
 
 		int dma_set_mask(struct device *dev, u64 mask);
 
 	The query for consistent allocations is performed via a call
-	to dma_set_coherent_mask():
+	to dma_set_coherent_mask()::
 
 		int dma_set_coherent_mask(struct device *dev, u64 mask);
 
@@ -209,7 +213,7 @@
 even detected, you can ask them for the kernel messages to find out
 exactly why.
 
-The standard 32-bit addressing device would do something like this:
+The standard 32-bit addressing device would do something like this::
 
 	if (dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32))) {
 		dev_warn(dev, "mydev: No suitable DMA available\n");
@@ -225,7 +229,7 @@
 more efficient than DAC addressing.
 
 Here is how you would handle a 64-bit capable device which can drive
-all 64-bits when accessing streaming DMA:
+all 64-bits when accessing streaming DMA::
 
 	int using_dac;
 
@@ -239,7 +243,7 @@
 	}
 
 If a card is capable of using 64-bit consistent allocations as well,
-the case would look like this:
+the case would look like this::
 
 	int using_dac, consistent_using_dac;
 
@@ -260,7 +264,7 @@
 dma_set_coherent_mask().
 
 Finally, if your device can only drive the low 24-bits of
-address you might do something like:
+address you might do something like::
 
 	if (dma_set_mask(dev, DMA_BIT_MASK(24))) {
 		dev_warn(dev, "mydev: 24-bit DMA addressing not available\n");
@@ -280,7 +284,7 @@
 is important that the last call to dma_set_mask() be for the
 most specific mask.
 
-Here is pseudo-code showing how this might be done:
+Here is pseudo-code showing how this might be done::
 
 	#define PLAYBACK_ADDRESS_BITS	DMA_BIT_MASK(32)
 	#define RECORD_ADDRESS_BITS	DMA_BIT_MASK(24)
@@ -308,7 +312,8 @@
 devices seems to be littered with ISA chips given a PCI front end,
 and thus retaining the 16MB DMA addressing limitations of ISA.
 
-			Types of DMA mappings
+Types of DMA mappings
+=====================
 
 There are two types of DMA mappings:
 
@@ -336,12 +341,14 @@
   to memory is immediately visible to the device, and vice
   versa.  Consistent mappings guarantee this.
 
-  IMPORTANT: Consistent DMA memory does not preclude the usage of
-             proper memory barriers.  The CPU may reorder stores to
+  .. important::
+
+	     Consistent DMA memory does not preclude the usage of
+	     proper memory barriers.  The CPU may reorder stores to
 	     consistent memory just as it may normal memory.  Example:
 	     if it is important for the device to see the first word
 	     of a descriptor updated before the second, you must do
-	     something like:
+	     something like::
 
 		desc->word0 = address;
 		wmb();
@@ -377,16 +384,17 @@
 when the underlying buffers don't share cache lines with other data.
 
 
-		 Using Consistent DMA mappings.
+Using Consistent DMA mappings
+=============================
 
 To allocate and map large (PAGE_SIZE or so) consistent DMA regions,
-you should do:
+you should do::
 
 	dma_addr_t dma_handle;
 
 	cpu_addr = dma_alloc_coherent(dev, size, &dma_handle, gfp);
 
-where device is a struct device *. This may be called in interrupt
+where device is a ``struct device *``. This may be called in interrupt
 context with the GFP_ATOMIC flag.
 
 Size is the length of the region you want to allocate, in bytes.
@@ -415,7 +423,7 @@
 which is smaller than or equal to 64 kilobytes, the extent of the
 buffer you receive will not cross a 64K boundary.
 
-To unmap and free such a DMA region, you call:
+To unmap and free such a DMA region, you call::
 
 	dma_free_coherent(dev, size, cpu_addr, dma_handle);
 
@@ -430,7 +438,7 @@
 Also, it understands common hardware constraints for alignment,
 like queue heads needing to be aligned on N byte boundaries.
 
-Create a dma_pool like this:
+Create a dma_pool like this::
 
 	struct dma_pool *pool;
 
@@ -444,7 +452,7 @@
 must not cross 4KByte boundaries (but at that time it may be better to
 use dma_alloc_coherent() directly instead).
 
-Allocate memory from a DMA pool like this:
+Allocate memory from a DMA pool like this::
 
 	cpu_addr = dma_pool_alloc(pool, flags, &dma_handle);
 
@@ -452,7 +460,7 @@
 holding SMP locks), GFP_ATOMIC otherwise.  Like dma_alloc_coherent(),
 this returns two values, cpu_addr and dma_handle.
 
-Free memory that was allocated from a dma_pool like this:
+Free memory that was allocated from a dma_pool like this::
 
 	dma_pool_free(pool, cpu_addr, dma_handle);
 
@@ -460,7 +468,7 @@
 dma_handle are the values dma_pool_alloc() returned. This function
 may be called in interrupt context.
 
-Destroy a dma_pool by calling:
+Destroy a dma_pool by calling::
 
 	dma_pool_destroy(pool);
 
@@ -468,11 +476,12 @@
 from a pool before you destroy the pool. This function may not
 be called in interrupt context.
 
-			DMA Direction
+DMA Direction
+=============
 
 The interfaces described in subsequent portions of this document
 take a DMA direction argument, which is an integer and takes on
-one of the following values:
+one of the following values::
 
  DMA_BIDIRECTIONAL
  DMA_TO_DEVICE
@@ -521,14 +530,15 @@
 specifier.  For receive packets, just the opposite, map/unmap them
 with the DMA_FROM_DEVICE direction specifier.
 
-		  Using Streaming DMA mappings
+Using Streaming DMA mappings
+============================
 
 The streaming DMA mapping routines can be called from interrupt
 context.  There are two versions of each map/unmap, one which will
 map/unmap a single memory region, and one which will map/unmap a
 scatterlist.
 
-To map a single region, you do:
+To map a single region, you do::
 
 	struct device *dev = &my_dev->dev;
 	dma_addr_t dma_handle;
@@ -545,7 +555,7 @@
 		goto map_error_handling;
 	}
 
-and to unmap it:
+and to unmap it::
 
 	dma_unmap_single(dev, dma_handle, size, direction);
 
@@ -563,7 +573,7 @@
 you cannot reference HIGHMEM memory in this way.  Thus, there is a
 map/unmap interface pair akin to dma_{map,unmap}_single().  These
 interfaces deal with page/offset pairs instead of CPU pointers.
-Specifically:
+Specifically::
 
 	struct device *dev = &my_dev->dev;
 	dma_addr_t dma_handle;
@@ -593,7 +603,7 @@
 You should call dma_unmap_page() when the DMA activity is finished, e.g.,
 from the interrupt which told you that the DMA transfer is done.
 
-With scatterlists, you map a region gathered from several regions by:
+With scatterlists, you map a region gathered from several regions by::
 
 	int i, count = dma_map_sg(dev, sglist, nents, direction);
 	struct scatterlist *sg;
@@ -617,16 +627,18 @@
 and use sg_dma_address() and sg_dma_len() macros where you previously
 accessed sg->address and sg->length as shown above.
 
-To unmap a scatterlist, just call:
+To unmap a scatterlist, just call::
 
 	dma_unmap_sg(dev, sglist, nents, direction);
 
 Again, make sure DMA activity has already finished.
 
-PLEASE NOTE:  The 'nents' argument to the dma_unmap_sg call must be
-              the _same_ one you passed into the dma_map_sg call,
-	      it should _NOT_ be the 'count' value _returned_ from the
-              dma_map_sg call.
+.. note::
+
+	The 'nents' argument to the dma_unmap_sg call must be
+	the _same_ one you passed into the dma_map_sg call,
+	it should _NOT_ be the 'count' value _returned_ from the
+	dma_map_sg call.
 
 Every dma_map_{single,sg}() call should have its dma_unmap_{single,sg}()
 counterpart, because the DMA address space is a shared resource and
@@ -638,11 +650,11 @@
 correct copy of the DMA buffer.
 
 So, firstly, just map it with dma_map_{single,sg}(), and after each DMA
-transfer call either:
+transfer call either::
 
 	dma_sync_single_for_cpu(dev, dma_handle, size, direction);
 
-or:
+or::
 
 	dma_sync_sg_for_cpu(dev, sglist, nents, direction);
 
@@ -650,17 +662,19 @@
 
 Then, if you wish to let the device get at the DMA area again,
 finish accessing the data with the CPU, and then before actually
-giving the buffer to the hardware call either:
+giving the buffer to the hardware call either::
 
 	dma_sync_single_for_device(dev, dma_handle, size, direction);
 
-or:
+or::
 
 	dma_sync_sg_for_device(dev, sglist, nents, direction);
 
 as appropriate.
 
-PLEASE NOTE:  The 'nents' argument to dma_sync_sg_for_cpu() and
+.. note::
+
+	      The 'nents' argument to dma_sync_sg_for_cpu() and
 	      dma_sync_sg_for_device() must be the same passed to
 	      dma_map_sg(). It is _NOT_ the count returned by
 	      dma_map_sg().
@@ -671,7 +685,7 @@
 dma_sync_*() routines at all.
 
 Here is pseudo code which shows a situation in which you would need
-to use the dma_sync_*() interfaces.
+to use the dma_sync_*() interfaces::
 
 	my_card_setup_receive_buffer(struct my_card *cp, char *buffer, int len)
 	{
@@ -747,7 +761,8 @@
 they are entirely deprecated.  Some ports already do not provide these
 as it is impossible to correctly support them.
 
-			Handling Errors
+Handling Errors
+===============
 
 DMA address space is limited on some architectures and an allocation
 failure can be determined by:
@@ -755,7 +770,7 @@
 - checking if dma_alloc_coherent() returns NULL or dma_map_sg returns 0
 
 - checking the dma_addr_t returned from dma_map_single() and dma_map_page()
-  by using dma_mapping_error():
+  by using dma_mapping_error()::
 
 	dma_addr_t dma_handle;
 
@@ -773,7 +788,8 @@
   of a multiple page mapping attempt. These example are applicable to
   dma_map_page() as well.
 
-Example 1:
+Example 1::
+
 	dma_addr_t dma_handle1;
 	dma_addr_t dma_handle2;
 
@@ -802,8 +818,12 @@
 		dma_unmap_single(dma_handle1);
 	map_error_handling1:
 
-Example 2: (if buffers are allocated in a loop, unmap all mapped buffers when
-	    mapping error is detected in the middle)
+Example 2::
+
+	/*
+	 * if buffers are allocated in a loop, unmap all mapped buffers when
+	 * mapping error is detected in the middle
+	 */
 
 	dma_addr_t dma_addr;
 	dma_addr_t array[DMA_BUFFERS];
@@ -846,7 +866,8 @@
 fails in the queuecommand hook. This means that the SCSI subsystem
 passes the command to the driver again later.
 
-		Optimizing Unmap State Space Consumption
+Optimizing Unmap State Space Consumption
+========================================
 
 On many platforms, dma_unmap_{single,page}() is simply a nop.
 Therefore, keeping track of the mapping address and length is a waste
@@ -858,7 +879,7 @@
 transform some example code.
 
 1) Use DEFINE_DMA_UNMAP_{ADDR,LEN} in state saving structures.
-   Example, before:
+   Example, before::
 
 	struct ring_state {
 		struct sk_buff *skb;
@@ -866,7 +887,7 @@
 		__u32 len;
 	};
 
-   after:
+   after::
 
 	struct ring_state {
 		struct sk_buff *skb;
@@ -875,23 +896,23 @@
 	};
 
 2) Use dma_unmap_{addr,len}_set() to set these values.
-   Example, before:
+   Example, before::
 
 	ringp->mapping = FOO;
 	ringp->len = BAR;
 
-   after:
+   after::
 
 	dma_unmap_addr_set(ringp, mapping, FOO);
 	dma_unmap_len_set(ringp, len, BAR);
 
 3) Use dma_unmap_{addr,len}() to access these values.
-   Example, before:
+   Example, before::
 
 	dma_unmap_single(dev, ringp->mapping, ringp->len,
 			 DMA_FROM_DEVICE);
 
-   after:
+   after::
 
 	dma_unmap_single(dev,
 			 dma_unmap_addr(ringp, mapping),
@@ -902,7 +923,8 @@
 separately, because it is possible for an implementation to only
 need the address in order to perform the unmap operation.
 
-			Platform Issues
+Platform Issues
+===============
 
 If you are just writing drivers for Linux and do not maintain
 an architecture port for the kernel, you can safely skip down
@@ -928,12 +950,13 @@
    alignment constraints (e.g. the alignment constraints about 64-bit
    objects).
 
-			   Closing
+Closing
+=======
 
 This document, and the API itself, would not be in its current
 form without the feedback and suggestions from numerous individuals.
 We would like to specifically mention, in no particular order, the
-following people:
+following people::
 
 	Russell King <rmk@arm.linux.org.uk>
 	Leo Dagum <dagum@barrel.engr.sgi.com>
diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt
index 71200df..45b2932 100644
--- a/Documentation/DMA-API.txt
+++ b/Documentation/DMA-API.txt
@@ -1,7 +1,8 @@
-               Dynamic DMA mapping using the generic device
-               ============================================
+============================================
+Dynamic DMA mapping using the generic device
+============================================
 
-        James E.J. Bottomley <James.Bottomley@HansenPartnership.com>
+:Author: James E.J. Bottomley <James.Bottomley@HansenPartnership.com>
 
 This document describes the DMA API.  For a more gentle introduction
 of the API (and actual examples), see Documentation/DMA-API-HOWTO.txt.
@@ -12,10 +13,10 @@
 non-consistent platforms (this is usually only legacy platforms) you
 should only use the API described in part I.
 
-Part I - dma_ API
--------------------------------------
+Part I - dma_API
+----------------
 
-To get the dma_ API, you must #include <linux/dma-mapping.h>.  This
+To get the dma_API, you must #include <linux/dma-mapping.h>.  This
 provides dma_addr_t and the interfaces described below.
 
 A dma_addr_t can hold any valid DMA address for the platform.  It can be
@@ -26,9 +27,11 @@
 Part Ia - Using large DMA-coherent buffers
 ------------------------------------------
 
-void *
-dma_alloc_coherent(struct device *dev, size_t size,
-			     dma_addr_t *dma_handle, gfp_t flag)
+::
+
+	void *
+	dma_alloc_coherent(struct device *dev, size_t size,
+			   dma_addr_t *dma_handle, gfp_t flag)
 
 Consistent memory is memory for which a write by either the device or
 the processor can immediately be read by the processor or device
@@ -51,20 +54,24 @@
 The simplest way to do that is to use the dma_pool calls (see below).
 
 The flag parameter (dma_alloc_coherent() only) allows the caller to
-specify the GFP_ flags (see kmalloc()) for the allocation (the
+specify the ``GFP_`` flags (see kmalloc()) for the allocation (the
 implementation may choose to ignore flags that affect the location of
 the returned memory, like GFP_DMA).
 
-void *
-dma_zalloc_coherent(struct device *dev, size_t size,
-			     dma_addr_t *dma_handle, gfp_t flag)
+::
+
+	void *
+	dma_zalloc_coherent(struct device *dev, size_t size,
+			    dma_addr_t *dma_handle, gfp_t flag)
 
 Wraps dma_alloc_coherent() and also zeroes the returned memory if the
 allocation attempt succeeded.
 
-void
-dma_free_coherent(struct device *dev, size_t size, void *cpu_addr,
-			   dma_addr_t dma_handle)
+::
+
+	void
+	dma_free_coherent(struct device *dev, size_t size, void *cpu_addr,
+			  dma_addr_t dma_handle)
 
 Free a region of consistent memory you previously allocated.  dev,
 size and dma_handle must all be the same as those passed into
@@ -78,7 +85,7 @@
 Part Ib - Using small DMA-coherent buffers
 ------------------------------------------
 
-To get this part of the dma_ API, you must #include <linux/dmapool.h>
+To get this part of the dma_API, you must #include <linux/dmapool.h>
 
 Many drivers need lots of small DMA-coherent memory regions for DMA
 descriptors or I/O buffers.  Rather than allocating in units of a page
@@ -88,6 +95,8 @@
 for alignment, like queue heads needing to be aligned on N-byte boundaries.
 
 
+::
+
 	struct dma_pool *
 	dma_pool_create(const char *name, struct device *dev,
 			size_t size, size_t align, size_t alloc);
@@ -103,16 +112,21 @@
 crossing restrictions, pass 0 for alloc; passing 4096 says memory allocated
 from this pool must not cross 4KByte boundaries.
 
+::
 
-	void *dma_pool_zalloc(struct dma_pool *pool, gfp_t mem_flags,
-			      dma_addr_t *handle)
+	void *
+	dma_pool_zalloc(struct dma_pool *pool, gfp_t mem_flags,
+		        dma_addr_t *handle)
 
 Wraps dma_pool_alloc() and also zeroes the returned memory if the
 allocation attempt succeeded.
 
 
-	void *dma_pool_alloc(struct dma_pool *pool, gfp_t gfp_flags,
-			dma_addr_t *dma_handle);
+::
+
+	void *
+	dma_pool_alloc(struct dma_pool *pool, gfp_t gfp_flags,
+		       dma_addr_t *dma_handle);
 
 This allocates memory from the pool; the returned memory will meet the
 size and alignment requirements specified at creation time.  Pass
@@ -122,16 +136,20 @@
 address usable by the CPU, and the DMA address usable by the pool's
 device.
 
+::
 
-	void dma_pool_free(struct dma_pool *pool, void *vaddr,
-			dma_addr_t addr);
+	void
+	dma_pool_free(struct dma_pool *pool, void *vaddr,
+		      dma_addr_t addr);
 
 This puts memory back into the pool.  The pool is what was passed to
 dma_pool_alloc(); the CPU (vaddr) and DMA addresses are what
 were returned when that routine allocated the memory being freed.
 
+::
 
-	void dma_pool_destroy(struct dma_pool *pool);
+	void
+	dma_pool_destroy(struct dma_pool *pool);
 
 dma_pool_destroy() frees the resources of the pool.  It must be
 called in a context which can sleep.  Make sure you've freed all allocated
@@ -141,32 +159,40 @@
 Part Ic - DMA addressing limitations
 ------------------------------------
 
-int
-dma_set_mask_and_coherent(struct device *dev, u64 mask)
+::
+
+	int
+	dma_set_mask_and_coherent(struct device *dev, u64 mask)
 
 Checks to see if the mask is possible and updates the device
 streaming and coherent DMA mask parameters if it is.
 
 Returns: 0 if successful and a negative error if not.
 
-int
-dma_set_mask(struct device *dev, u64 mask)
+::
+
+	int
+	dma_set_mask(struct device *dev, u64 mask)
 
 Checks to see if the mask is possible and updates the device
 parameters if it is.
 
 Returns: 0 if successful and a negative error if not.
 
-int
-dma_set_coherent_mask(struct device *dev, u64 mask)
+::
+
+	int
+	dma_set_coherent_mask(struct device *dev, u64 mask)
 
 Checks to see if the mask is possible and updates the device
 parameters if it is.
 
 Returns: 0 if successful and a negative error if not.
 
-u64
-dma_get_required_mask(struct device *dev)
+::
+
+	u64
+	dma_get_required_mask(struct device *dev)
 
 This API returns the mask that the platform requires to
 operate efficiently.  Usually this means the returned mask
@@ -182,94 +208,107 @@
 Part Id - Streaming DMA mappings
 --------------------------------
 
-dma_addr_t
-dma_map_single(struct device *dev, void *cpu_addr, size_t size,
-		      enum dma_data_direction direction)
+::
+
+	dma_addr_t
+	dma_map_single(struct device *dev, void *cpu_addr, size_t size,
+		       enum dma_data_direction direction)
 
 Maps a piece of processor virtual memory so it can be accessed by the
 device and returns the DMA address of the memory.
 
 The direction for both APIs may be converted freely by casting.
-However the dma_ API uses a strongly typed enumerator for its
+However the dma_API uses a strongly typed enumerator for its
 direction:
 
+======================= =============================================
 DMA_NONE		no direction (used for debugging)
 DMA_TO_DEVICE		data is going from the memory to the device
 DMA_FROM_DEVICE		data is coming from the device to the memory
 DMA_BIDIRECTIONAL	direction isn't known
+======================= =============================================
 
-Notes:  Not all memory regions in a machine can be mapped by this API.
-Further, contiguous kernel virtual space may not be contiguous as
-physical memory.  Since this API does not provide any scatter/gather
-capability, it will fail if the user tries to map a non-physically
-contiguous piece of memory.  For this reason, memory to be mapped by
-this API should be obtained from sources which guarantee it to be
-physically contiguous (like kmalloc).
+.. note::
 
-Further, the DMA address of the memory must be within the
-dma_mask of the device (the dma_mask is a bit mask of the
-addressable region for the device, i.e., if the DMA address of
-the memory ANDed with the dma_mask is still equal to the DMA
-address, then the device can perform DMA to the memory).  To
-ensure that the memory allocated by kmalloc is within the dma_mask,
-the driver may specify various platform-dependent flags to restrict
-the DMA address range of the allocation (e.g., on x86, GFP_DMA
-guarantees to be within the first 16MB of available DMA addresses,
-as required by ISA devices).
+	Not all memory regions in a machine can be mapped by this API.
+	Further, contiguous kernel virtual space may not be contiguous as
+	physical memory.  Since this API does not provide any scatter/gather
+	capability, it will fail if the user tries to map a non-physically
+	contiguous piece of memory.  For this reason, memory to be mapped by
+	this API should be obtained from sources which guarantee it to be
+	physically contiguous (like kmalloc).
 
-Note also that the above constraints on physical contiguity and
-dma_mask may not apply if the platform has an IOMMU (a device which
-maps an I/O DMA address to a physical memory address).  However, to be
-portable, device driver writers may *not* assume that such an IOMMU
-exists.
+	Further, the DMA address of the memory must be within the
+	dma_mask of the device (the dma_mask is a bit mask of the
+	addressable region for the device, i.e., if the DMA address of
+	the memory ANDed with the dma_mask is still equal to the DMA
+	address, then the device can perform DMA to the memory).  To
+	ensure that the memory allocated by kmalloc is within the dma_mask,
+	the driver may specify various platform-dependent flags to restrict
+	the DMA address range of the allocation (e.g., on x86, GFP_DMA
+	guarantees to be within the first 16MB of available DMA addresses,
+	as required by ISA devices).
 
-Warnings:  Memory coherency operates at a granularity called the cache
-line width.  In order for memory mapped by this API to operate
-correctly, the mapped region must begin exactly on a cache line
-boundary and end exactly on one (to prevent two separately mapped
-regions from sharing a single cache line).  Since the cache line size
-may not be known at compile time, the API will not enforce this
-requirement.  Therefore, it is recommended that driver writers who
-don't take special care to determine the cache line size at run time
-only map virtual regions that begin and end on page boundaries (which
-are guaranteed also to be cache line boundaries).
+	Note also that the above constraints on physical contiguity and
+	dma_mask may not apply if the platform has an IOMMU (a device which
+	maps an I/O DMA address to a physical memory address).  However, to be
+	portable, device driver writers may *not* assume that such an IOMMU
+	exists.
 
-DMA_TO_DEVICE synchronisation must be done after the last modification
-of the memory region by the software and before it is handed off to
-the device.  Once this primitive is used, memory covered by this
-primitive should be treated as read-only by the device.  If the device
-may write to it at any point, it should be DMA_BIDIRECTIONAL (see
-below).
+.. warning::
 
-DMA_FROM_DEVICE synchronisation must be done before the driver
-accesses data that may be changed by the device.  This memory should
-be treated as read-only by the driver.  If the driver needs to write
-to it at any point, it should be DMA_BIDIRECTIONAL (see below).
+	Memory coherency operates at a granularity called the cache
+	line width.  In order for memory mapped by this API to operate
+	correctly, the mapped region must begin exactly on a cache line
+	boundary and end exactly on one (to prevent two separately mapped
+	regions from sharing a single cache line).  Since the cache line size
+	may not be known at compile time, the API will not enforce this
+	requirement.  Therefore, it is recommended that driver writers who
+	don't take special care to determine the cache line size at run time
+	only map virtual regions that begin and end on page boundaries (which
+	are guaranteed also to be cache line boundaries).
 
-DMA_BIDIRECTIONAL requires special handling: it means that the driver
-isn't sure if the memory was modified before being handed off to the
-device and also isn't sure if the device will also modify it.  Thus,
-you must always sync bidirectional memory twice: once before the
-memory is handed off to the device (to make sure all memory changes
-are flushed from the processor) and once before the data may be
-accessed after being used by the device (to make sure any processor
-cache lines are updated with data that the device may have changed).
+	DMA_TO_DEVICE synchronisation must be done after the last modification
+	of the memory region by the software and before it is handed off to
+	the device.  Once this primitive is used, memory covered by this
+	primitive should be treated as read-only by the device.  If the device
+	may write to it at any point, it should be DMA_BIDIRECTIONAL (see
+	below).
 
-void
-dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
-		 enum dma_data_direction direction)
+	DMA_FROM_DEVICE synchronisation must be done before the driver
+	accesses data that may be changed by the device.  This memory should
+	be treated as read-only by the driver.  If the driver needs to write
+	to it at any point, it should be DMA_BIDIRECTIONAL (see below).
+
+	DMA_BIDIRECTIONAL requires special handling: it means that the driver
+	isn't sure if the memory was modified before being handed off to the
+	device and also isn't sure if the device will also modify it.  Thus,
+	you must always sync bidirectional memory twice: once before the
+	memory is handed off to the device (to make sure all memory changes
+	are flushed from the processor) and once before the data may be
+	accessed after being used by the device (to make sure any processor
+	cache lines are updated with data that the device may have changed).
+
+::
+
+	void
+	dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
+			 enum dma_data_direction direction)
 
 Unmaps the region previously mapped.  All the parameters passed in
 must be identical to those passed in (and returned) by the mapping
 API.
 
-dma_addr_t
-dma_map_page(struct device *dev, struct page *page,
-		    unsigned long offset, size_t size,
-		    enum dma_data_direction direction)
-void
-dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size,
-	       enum dma_data_direction direction)
+::
+
+	dma_addr_t
+	dma_map_page(struct device *dev, struct page *page,
+		     unsigned long offset, size_t size,
+		     enum dma_data_direction direction)
+
+	void
+	dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size,
+		       enum dma_data_direction direction)
 
 API for mapping and unmapping for pages.  All the notes and warnings
 for the other mapping APIs apply here.  Also, although the <offset>
@@ -277,20 +316,24 @@
 recommended that you never use these unless you really know what the
 cache width is.
 
-dma_addr_t
-dma_map_resource(struct device *dev, phys_addr_t phys_addr, size_t size,
-		 enum dma_data_direction dir, unsigned long attrs)
+::
 
-void
-dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size,
-		   enum dma_data_direction dir, unsigned long attrs)
+	dma_addr_t
+	dma_map_resource(struct device *dev, phys_addr_t phys_addr, size_t size,
+			 enum dma_data_direction dir, unsigned long attrs)
+
+	void
+	dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size,
+			   enum dma_data_direction dir, unsigned long attrs)
 
 API for mapping and unmapping for MMIO resources. All the notes and
 warnings for the other mapping APIs apply here. The API should only be
 used to map device MMIO resources, mapping of RAM is not permitted.
 
-int
-dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
+::
+
+	int
+	dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 
 In some circumstances dma_map_single(), dma_map_page() and dma_map_resource()
 will fail to create a mapping. A driver can check for these errors by testing
@@ -298,9 +341,11 @@
 means the mapping could not be created and the driver should take appropriate
 action (e.g. reduce current DMA mapping usage or delay and try again later).
 
+::
+
 	int
 	dma_map_sg(struct device *dev, struct scatterlist *sg,
-		int nents, enum dma_data_direction direction)
+		   int nents, enum dma_data_direction direction)
 
 Returns: the number of DMA address segments mapped (this may be shorter
 than <nents> passed in if some elements of the scatter/gather list are
@@ -316,7 +361,7 @@
 aborting the request or even oopsing is better than doing nothing and
 corrupting the filesystem.
 
-With scatterlists, you use the resulting mapping like this:
+With scatterlists, you use the resulting mapping like this::
 
 	int i, count = dma_map_sg(dev, sglist, nents, direction);
 	struct scatterlist *sg;
@@ -337,9 +382,11 @@
 and use sg_dma_address() and sg_dma_len() macros where you previously
 accessed sg->address and sg->length as shown above.
 
+::
+
 	void
 	dma_unmap_sg(struct device *dev, struct scatterlist *sg,
-		int nents, enum dma_data_direction direction)
+		     int nents, enum dma_data_direction direction)
 
 Unmap the previously mapped scatter/gather list.  All the parameters
 must be the same as those and passed in to the scatter/gather mapping
@@ -348,18 +395,27 @@
 Note: <nents> must be the number you passed in, *not* the number of
 DMA address entries returned.
 
-void
-dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size,
-			enum dma_data_direction direction)
-void
-dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, size_t size,
-			   enum dma_data_direction direction)
-void
-dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nents,
-		    enum dma_data_direction direction)
-void
-dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nents,
-		       enum dma_data_direction direction)
+::
+
+	void
+	dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
+				size_t size,
+				enum dma_data_direction direction)
+
+	void
+	dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle,
+				   size_t size,
+				   enum dma_data_direction direction)
+
+	void
+	dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
+			    int nents,
+			    enum dma_data_direction direction)
+
+	void
+	dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
+			       int nents,
+			       enum dma_data_direction direction)
 
 Synchronise a single contiguous or scatter/gather mapping for the CPU
 and device. With the sync_sg API, all the parameters must be the same
@@ -367,36 +423,41 @@
 you can use dma_handle and size parameters that aren't identical to
 those passed into the single mapping API to do a partial sync.
 
-Notes:  You must do this:
 
-- Before reading values that have been written by DMA from the device
-  (use the DMA_FROM_DEVICE direction)
-- After writing values that will be written to the device using DMA
-  (use the DMA_TO_DEVICE) direction
-- before *and* after handing memory to the device if the memory is
-  DMA_BIDIRECTIONAL
+.. note::
+
+   You must do this:
+
+   - Before reading values that have been written by DMA from the device
+     (use the DMA_FROM_DEVICE direction)
+   - After writing values that will be written to the device using DMA
+     (use the DMA_TO_DEVICE) direction
+   - before *and* after handing memory to the device if the memory is
+     DMA_BIDIRECTIONAL
 
 See also dma_map_single().
 
-dma_addr_t
-dma_map_single_attrs(struct device *dev, void *cpu_addr, size_t size,
-		     enum dma_data_direction dir,
-		     unsigned long attrs)
+::
 
-void
-dma_unmap_single_attrs(struct device *dev, dma_addr_t dma_addr,
-		       size_t size, enum dma_data_direction dir,
-		       unsigned long attrs)
+	dma_addr_t
+	dma_map_single_attrs(struct device *dev, void *cpu_addr, size_t size,
+			     enum dma_data_direction dir,
+			     unsigned long attrs)
 
-int
-dma_map_sg_attrs(struct device *dev, struct scatterlist *sgl,
-		 int nents, enum dma_data_direction dir,
-		 unsigned long attrs)
+	void
+	dma_unmap_single_attrs(struct device *dev, dma_addr_t dma_addr,
+			       size_t size, enum dma_data_direction dir,
+			       unsigned long attrs)
 
-void
-dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sgl,
-		   int nents, enum dma_data_direction dir,
-		   unsigned long attrs)
+	int
+	dma_map_sg_attrs(struct device *dev, struct scatterlist *sgl,
+			 int nents, enum dma_data_direction dir,
+			 unsigned long attrs)
+
+	void
+	dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sgl,
+			   int nents, enum dma_data_direction dir,
+			   unsigned long attrs)
 
 The four functions above are just like the counterpart functions
 without the _attrs suffixes, except that they pass an optional
@@ -410,37 +471,38 @@
 without the _attrs suffix. As a result dma_map_single_attrs()
 can generally replace dma_map_single(), etc.
 
-As an example of the use of the *_attrs functions, here's how
+As an example of the use of the ``*_attrs`` functions, here's how
 you could pass an attribute DMA_ATTR_FOO when mapping memory
-for DMA:
+for DMA::
 
-#include <linux/dma-mapping.h>
-/* DMA_ATTR_FOO should be defined in linux/dma-mapping.h and
- * documented in Documentation/DMA-attributes.txt */
-...
+	#include <linux/dma-mapping.h>
+	/* DMA_ATTR_FOO should be defined in linux/dma-mapping.h and
+	* documented in Documentation/DMA-attributes.txt */
+	...
 
-	unsigned long attr;
-	attr |= DMA_ATTR_FOO;
-	....
-	n = dma_map_sg_attrs(dev, sg, nents, DMA_TO_DEVICE, attr);
-	....
+		unsigned long attr;
+		attr |= DMA_ATTR_FOO;
+		....
+		n = dma_map_sg_attrs(dev, sg, nents, DMA_TO_DEVICE, attr);
+		....
 
 Architectures that care about DMA_ATTR_FOO would check for its
 presence in their implementations of the mapping and unmapping
-routines, e.g.:
+routines, e.g.:::
 
-void whizco_dma_map_sg_attrs(struct device *dev, dma_addr_t dma_addr,
-			     size_t size, enum dma_data_direction dir,
-			     unsigned long attrs)
-{
-	....
-	if (attrs & DMA_ATTR_FOO)
-		/* twizzle the frobnozzle */
-	....
+	void whizco_dma_map_sg_attrs(struct device *dev, dma_addr_t dma_addr,
+				     size_t size, enum dma_data_direction dir,
+				     unsigned long attrs)
+	{
+		....
+		if (attrs & DMA_ATTR_FOO)
+			/* twizzle the frobnozzle */
+		....
+	}
 
 
-Part II - Advanced dma_ usage
------------------------------
+Part II - Advanced dma usage
+----------------------------
 
 Warning: These pieces of the DMA API should not be used in the
 majority of cases, since they cater for unlikely corner cases that
@@ -450,9 +512,11 @@
 processor and an I/O device, you should not be using this part of the
 API at all.
 
-void *
-dma_alloc_noncoherent(struct device *dev, size_t size,
-			       dma_addr_t *dma_handle, gfp_t flag)
+::
+
+	void *
+	dma_alloc_noncoherent(struct device *dev, size_t size,
+			      dma_addr_t *dma_handle, gfp_t flag)
 
 Identical to dma_alloc_coherent() except that the platform will
 choose to return either consistent or non-consistent memory as it sees
@@ -468,39 +532,49 @@
 required to work on one of the rare (usually non-PCI) architectures
 that simply cannot make consistent memory.
 
-void
-dma_free_noncoherent(struct device *dev, size_t size, void *cpu_addr,
-			      dma_addr_t dma_handle)
+::
+
+	void
+	dma_free_noncoherent(struct device *dev, size_t size, void *cpu_addr,
+			     dma_addr_t dma_handle)
 
 Free memory allocated by the nonconsistent API.  All parameters must
 be identical to those passed in (and returned by
 dma_alloc_noncoherent()).
 
-int
-dma_get_cache_alignment(void)
+::
+
+	int
+	dma_get_cache_alignment(void)
 
 Returns the processor cache alignment.  This is the absolute minimum
 alignment *and* width that you must observe when either mapping
 memory or doing partial flushes.
 
-Notes: This API may return a number *larger* than the actual cache
-line, but it will guarantee that one or more cache lines fit exactly
-into the width returned by this call.  It will also always be a power
-of two for easy alignment.
+.. note::
 
-void
-dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-	       enum dma_data_direction direction)
+	This API may return a number *larger* than the actual cache
+	line, but it will guarantee that one or more cache lines fit exactly
+	into the width returned by this call.  It will also always be a power
+	of two for easy alignment.
+
+::
+
+	void
+	dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+		       enum dma_data_direction direction)
 
 Do a partial sync of memory that was allocated by
 dma_alloc_noncoherent(), starting at virtual address vaddr and
 continuing on for size.  Again, you *must* observe the cache line
 boundaries when doing this.
 
-int
-dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
-			    dma_addr_t device_addr, size_t size, int
-			    flags)
+::
+
+	int
+	dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
+				    dma_addr_t device_addr, size_t size, int
+				    flags)
 
 Declare region of memory to be handed out by dma_alloc_coherent() when
 it's asked for coherent memory for this device.
@@ -516,21 +590,21 @@
 
 flags can be ORed together and are:
 
-DMA_MEMORY_MAP - request that the memory returned from
-dma_alloc_coherent() be directly writable.
+- DMA_MEMORY_MAP - request that the memory returned from
+  dma_alloc_coherent() be directly writable.
 
-DMA_MEMORY_IO - request that the memory returned from
-dma_alloc_coherent() be addressable using read()/write()/memcpy_toio() etc.
+- DMA_MEMORY_IO - request that the memory returned from
+  dma_alloc_coherent() be addressable using read()/write()/memcpy_toio() etc.
 
 One or both of these flags must be present.
 
-DMA_MEMORY_INCLUDES_CHILDREN - make the declared memory be allocated by
-dma_alloc_coherent of any child devices of this one (for memory residing
-on a bridge).
+- DMA_MEMORY_INCLUDES_CHILDREN - make the declared memory be allocated by
+  dma_alloc_coherent of any child devices of this one (for memory residing
+  on a bridge).
 
-DMA_MEMORY_EXCLUSIVE - only allocate memory from the declared regions. 
-Do not allow dma_alloc_coherent() to fall back to system memory when
-it's out of memory in the declared region.
+- DMA_MEMORY_EXCLUSIVE - only allocate memory from the declared regions.
+  Do not allow dma_alloc_coherent() to fall back to system memory when
+  it's out of memory in the declared region.
 
 The return value will be either DMA_MEMORY_MAP or DMA_MEMORY_IO and
 must correspond to a passed in flag (i.e. no returning DMA_MEMORY_IO
@@ -543,15 +617,17 @@
 isn't prepared to handle this contingency, it should not specify
 DMA_MEMORY_IO in the input flags.
 
-As a simplification for the platforms, only *one* such region of
+As a simplification for the platforms, only **one** such region of
 memory may be declared per device.
 
 For reasons of efficiency, most platforms choose to track the declared
 region only at the granularity of a page.  For smaller allocations,
 you should use the dma_pool() API.
 
-void
-dma_release_declared_memory(struct device *dev)
+::
+
+	void
+	dma_release_declared_memory(struct device *dev)
 
 Remove the memory region previously declared from the system.  This
 API performs *no* in-use checking for this region and will return
@@ -559,9 +635,11 @@
 driver's job to ensure that no parts of this memory region are
 currently in use.
 
-void *
-dma_mark_declared_memory_occupied(struct device *dev,
-				  dma_addr_t device_addr, size_t size)
+::
+
+	void *
+	dma_mark_declared_memory_occupied(struct device *dev,
+					  dma_addr_t device_addr, size_t size)
 
 This is used to occupy specific regions of the declared space
 (dma_alloc_coherent() will hand out the first free region it finds).
@@ -592,38 +670,37 @@
 If you boot the resulting kernel will contain code which does some bookkeeping
 about what DMA memory was allocated for which device. If this code detects an
 error it prints a warning message with some details into your kernel log. An
-example warning message may look like this:
+example warning message may look like this::
 
-------------[ cut here ]------------
-WARNING: at /data2/repos/linux-2.6-iommu/lib/dma-debug.c:448
-	check_unmap+0x203/0x490()
-Hardware name:
-forcedeth 0000:00:08.0: DMA-API: device driver frees DMA memory with wrong
-	function [device address=0x00000000640444be] [size=66 bytes] [mapped as
-single] [unmapped as page]
-Modules linked in: nfsd exportfs bridge stp llc r8169
-Pid: 0, comm: swapper Tainted: G        W  2.6.28-dmatest-09289-g8bb99c0 #1
-Call Trace:
- <IRQ>  [<ffffffff80240b22>] warn_slowpath+0xf2/0x130
- [<ffffffff80647b70>] _spin_unlock+0x10/0x30
- [<ffffffff80537e75>] usb_hcd_link_urb_to_ep+0x75/0xc0
- [<ffffffff80647c22>] _spin_unlock_irqrestore+0x12/0x40
- [<ffffffff8055347f>] ohci_urb_enqueue+0x19f/0x7c0
- [<ffffffff80252f96>] queue_work+0x56/0x60
- [<ffffffff80237e10>] enqueue_task_fair+0x20/0x50
- [<ffffffff80539279>] usb_hcd_submit_urb+0x379/0xbc0
- [<ffffffff803b78c3>] cpumask_next_and+0x23/0x40
- [<ffffffff80235177>] find_busiest_group+0x207/0x8a0
- [<ffffffff8064784f>] _spin_lock_irqsave+0x1f/0x50
- [<ffffffff803c7ea3>] check_unmap+0x203/0x490
- [<ffffffff803c8259>] debug_dma_unmap_page+0x49/0x50
- [<ffffffff80485f26>] nv_tx_done_optimized+0xc6/0x2c0
- [<ffffffff80486c13>] nv_nic_irq_optimized+0x73/0x2b0
- [<ffffffff8026df84>] handle_IRQ_event+0x34/0x70
- [<ffffffff8026ffe9>] handle_edge_irq+0xc9/0x150
- [<ffffffff8020e3ab>] do_IRQ+0xcb/0x1c0
- [<ffffffff8020c093>] ret_from_intr+0x0/0xa
- <EOI> <4>---[ end trace f6435a98e2a38c0e ]---
+	WARNING: at /data2/repos/linux-2.6-iommu/lib/dma-debug.c:448
+		check_unmap+0x203/0x490()
+	Hardware name:
+	forcedeth 0000:00:08.0: DMA-API: device driver frees DMA memory with wrong
+		function [device address=0x00000000640444be] [size=66 bytes] [mapped as
+	single] [unmapped as page]
+	Modules linked in: nfsd exportfs bridge stp llc r8169
+	Pid: 0, comm: swapper Tainted: G        W  2.6.28-dmatest-09289-g8bb99c0 #1
+	Call Trace:
+	<IRQ>  [<ffffffff80240b22>] warn_slowpath+0xf2/0x130
+	[<ffffffff80647b70>] _spin_unlock+0x10/0x30
+	[<ffffffff80537e75>] usb_hcd_link_urb_to_ep+0x75/0xc0
+	[<ffffffff80647c22>] _spin_unlock_irqrestore+0x12/0x40
+	[<ffffffff8055347f>] ohci_urb_enqueue+0x19f/0x7c0
+	[<ffffffff80252f96>] queue_work+0x56/0x60
+	[<ffffffff80237e10>] enqueue_task_fair+0x20/0x50
+	[<ffffffff80539279>] usb_hcd_submit_urb+0x379/0xbc0
+	[<ffffffff803b78c3>] cpumask_next_and+0x23/0x40
+	[<ffffffff80235177>] find_busiest_group+0x207/0x8a0
+	[<ffffffff8064784f>] _spin_lock_irqsave+0x1f/0x50
+	[<ffffffff803c7ea3>] check_unmap+0x203/0x490
+	[<ffffffff803c8259>] debug_dma_unmap_page+0x49/0x50
+	[<ffffffff80485f26>] nv_tx_done_optimized+0xc6/0x2c0
+	[<ffffffff80486c13>] nv_nic_irq_optimized+0x73/0x2b0
+	[<ffffffff8026df84>] handle_IRQ_event+0x34/0x70
+	[<ffffffff8026ffe9>] handle_edge_irq+0xc9/0x150
+	[<ffffffff8020e3ab>] do_IRQ+0xcb/0x1c0
+	[<ffffffff8020c093>] ret_from_intr+0x0/0xa
+	<EOI> <4>---[ end trace f6435a98e2a38c0e ]---
 
 The driver developer can find the driver and the device including a stacktrace
 of the DMA-API call which caused this warning.
@@ -637,43 +714,42 @@
 The debugfs directory for the DMA-API debugging code is called dma-api/. In
 this directory the following files can currently be found:
 
-	dma-api/all_errors	This file contains a numeric value. If this
+=============================== ===============================================
+dma-api/all_errors		This file contains a numeric value. If this
 				value is not equal to zero the debugging code
 				will print a warning for every error it finds
 				into the kernel log. Be careful with this
 				option, as it can easily flood your logs.
 
-	dma-api/disabled	This read-only file contains the character 'Y'
+dma-api/disabled		This read-only file contains the character 'Y'
 				if the debugging code is disabled. This can
 				happen when it runs out of memory or if it was
 				disabled at boot time
 
-	dma-api/error_count	This file is read-only and shows the total
+dma-api/error_count		This file is read-only and shows the total
 				numbers of errors found.
 
-	dma-api/num_errors	The number in this file shows how many
+dma-api/num_errors		The number in this file shows how many
 				warnings will be printed to the kernel log
 				before it stops. This number is initialized to
 				one at system boot and be set by writing into
 				this file
 
-	dma-api/min_free_entries
-				This read-only file can be read to get the
+dma-api/min_free_entries	This read-only file can be read to get the
 				minimum number of free dma_debug_entries the
 				allocator has ever seen. If this value goes
 				down to zero the code will disable itself
 				because it is not longer reliable.
 
-	dma-api/num_free_entries
-				The current number of free dma_debug_entries
+dma-api/num_free_entries	The current number of free dma_debug_entries
 				in the allocator.
 
-	dma-api/driver-filter
-				You can write a name of a driver into this file
+dma-api/driver-filter		You can write a name of a driver into this file
 				to limit the debug output to requests from that
 				particular driver. Write an empty string to
 				that file to disable the filter and see
 				all errors again.
+=============================== ===============================================
 
 If you have this code compiled into your kernel it will be enabled by default.
 If you want to boot without the bookkeeping anyway you can provide
@@ -692,7 +768,10 @@
 boot with 'dma_debug_entries=<your_desired_number>' to overwrite the
 architectural default.
 
-void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr);
+::
+
+	void
+	debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr);
 
 dma-debug interface debug_dma_mapping_error() to debug drivers that fail
 to check DMA mapping errors on addresses returned by dma_map_single() and
@@ -702,4 +781,3 @@
 this flag is still set, prints warning message that includes call trace that
 leads up to the unmap. This interface can be called from dma_mapping_error()
 routines to enable DMA mapping error check debugging.
-
diff --git a/Documentation/DMA-ISA-LPC.txt b/Documentation/DMA-ISA-LPC.txt
index 7a065ac..8c2b8be 100644
--- a/Documentation/DMA-ISA-LPC.txt
+++ b/Documentation/DMA-ISA-LPC.txt
@@ -1,19 +1,20 @@
-                        DMA with ISA and LPC devices
-                        ============================
+============================
+DMA with ISA and LPC devices
+============================
 
-                      Pierre Ossman <drzeus@drzeus.cx>
+:Author: Pierre Ossman <drzeus@drzeus.cx>
 
 This document describes how to do DMA transfers using the old ISA DMA
 controller. Even though ISA is more or less dead today the LPC bus
 uses the same DMA system so it will be around for quite some time.
 
-Part I - Headers and dependencies
----------------------------------
+Headers and dependencies
+------------------------
 
-To do ISA style DMA you need to include two headers:
+To do ISA style DMA you need to include two headers::
 
-#include <linux/dma-mapping.h>
-#include <asm/dma.h>
+	#include <linux/dma-mapping.h>
+	#include <asm/dma.h>
 
 The first is the generic DMA API used to convert virtual addresses to
 bus addresses (see Documentation/DMA-API.txt for details).
@@ -23,8 +24,8 @@
 Kconfig to be dependent on ISA_DMA_API (not ISA) so that nobody tries
 to build your driver on unsupported platforms.
 
-Part II - Buffer allocation
----------------------------
+Buffer allocation
+-----------------
 
 The ISA DMA controller has some very strict requirements on which
 memory it can access so extra care must be taken when allocating
@@ -47,8 +48,8 @@
 (This scarcity also means that you should allocate the buffer as
 early as possible and not release it until the driver is unloaded.)
 
-Part III - Address translation
-------------------------------
+Address translation
+-------------------
 
 To translate the virtual address to a bus address, use the normal DMA
 API. Do _not_ use isa_virt_to_phys() even though it does the same
@@ -61,8 +62,8 @@
 been fixed. If your arch has problems then fix the DMA API instead of
 reverting to the ISA functions.
 
-Part IV - Channels
-------------------
+Channels
+--------
 
 A normal ISA DMA controller has 8 channels. The lower four are for
 8-bit transfers and the upper four are for 16-bit transfers.
@@ -80,8 +81,8 @@
 driver author but depends on what the hardware supports. Check your
 specs or test different channels.
 
-Part V - Transfer data
-----------------------
+Transfer data
+-------------
 
 Now for the good stuff, the actual DMA transfer. :)
 
@@ -112,37 +113,37 @@
 the channel again. You should also check get_dma_residue() to make
 sure that all data has been transferred.
 
-Example:
+Example::
 
-int flags, residue;
+	int flags, residue;
 
-flags = claim_dma_lock();
+	flags = claim_dma_lock();
 
-clear_dma_ff();
+	clear_dma_ff();
 
-set_dma_mode(channel, DMA_MODE_WRITE);
-set_dma_addr(channel, phys_addr);
-set_dma_count(channel, num_bytes);
+	set_dma_mode(channel, DMA_MODE_WRITE);
+	set_dma_addr(channel, phys_addr);
+	set_dma_count(channel, num_bytes);
 
-dma_enable(channel);
+	dma_enable(channel);
 
-release_dma_lock(flags);
+	release_dma_lock(flags);
 
-while (!device_done());
+	while (!device_done());
 
-flags = claim_dma_lock();
+	flags = claim_dma_lock();
 
-dma_disable(channel);
+	dma_disable(channel);
 
-residue = dma_get_residue(channel);
-if (residue != 0)
-	printk(KERN_ERR "driver: Incomplete DMA transfer!"
-		" %d bytes left!\n", residue);
+	residue = dma_get_residue(channel);
+	if (residue != 0)
+		printk(KERN_ERR "driver: Incomplete DMA transfer!"
+			" %d bytes left!\n", residue);
 
-release_dma_lock(flags);
+	release_dma_lock(flags);
 
-Part VI - Suspend/resume
-------------------------
+Suspend/resume
+--------------
 
 It is the driver's responsibility to make sure that the machine isn't
 suspended while a DMA transfer is in progress. Also, all DMA settings
diff --git a/Documentation/DMA-attributes.txt b/Documentation/DMA-attributes.txt
index 44c6bc4..8f8d97f 100644
--- a/Documentation/DMA-attributes.txt
+++ b/Documentation/DMA-attributes.txt
@@ -1,5 +1,6 @@
-			DMA attributes
-			==============
+==============
+DMA attributes
+==============
 
 This document describes the semantics of the DMA attributes that are
 defined in linux/dma-mapping.h.
@@ -108,6 +109,7 @@
 the time to try to allocate memory to in a way that gives better TLB
 efficiency (AKA it's not worth trying to build the mapping out of larger
 pages).  You might want to specify this if:
+
 - You know that the accesses to this memory won't thrash the TLB.
   You might know that the accesses are likely to be sequential or
   that they aren't sequential but it's unlikely you'll ping-pong
@@ -121,11 +123,12 @@
   the mapping to have a short lifetime then it may be worth it to
   optimize allocation (avoid coming up with large pages) instead of
   getting the slight performance win of larger pages.
+
 Setting this hint doesn't guarantee that you won't get huge pages, but it
 means that we won't try quite as hard to get them.
 
-NOTE: At the moment DMA_ATTR_ALLOC_SINGLE_PAGES is only implemented on ARM,
-though ARM64 patches will likely be posted soon.
+.. note:: At the moment DMA_ATTR_ALLOC_SINGLE_PAGES is only implemented on ARM,
+	  though ARM64 patches will likely be posted soon.
 
 DMA_ATTR_NO_WARN
 ----------------
@@ -142,10 +145,10 @@
 So, this provides a way for drivers to avoid those error messages on calls
 where allocation failures are not a problem, and shouldn't bother the logs.
 
-NOTE: At the moment DMA_ATTR_NO_WARN is only implemented on PowerPC.
+.. note:: At the moment DMA_ATTR_NO_WARN is only implemented on PowerPC.
 
 DMA_ATTR_PRIVILEGED
-------------------------------
+-------------------
 
 Some advanced peripherals such as remote processors and GPUs perform
 accesses to DMA buffers in both privileged "supervisor" and unprivileged
diff --git a/Documentation/IPMI.txt b/Documentation/IPMI.txt
index 6962cab..aa77a25 100644
--- a/Documentation/IPMI.txt
+++ b/Documentation/IPMI.txt
@@ -1,9 +1,8 @@
+=====================
+The Linux IPMI Driver
+=====================
 
-                          The Linux IPMI Driver
-			  ---------------------
-			      Corey Minyard
-			  <minyard@mvista.com>
-			    <minyard@acm.org>
+:Author: Corey Minyard <minyard@mvista.com> / <minyard@acm.org>
 
 The Intelligent Platform Management Interface, or IPMI, is a
 standard for controlling intelligent devices that monitor a system.
@@ -141,7 +140,7 @@
 ----------
 
 The IPMI addressing works much like IP addresses, you have an overlay
-to handle the different address types.  The overlay is:
+to handle the different address types.  The overlay is::
 
   struct ipmi_addr
   {
@@ -153,7 +152,7 @@
 The addr_type determines what the address really is.  The driver
 currently understands two different types of addresses.
 
-"System Interface" addresses are defined as:
+"System Interface" addresses are defined as::
 
   struct ipmi_system_interface_addr
   {
@@ -166,7 +165,7 @@
 IPMI_BMC_CHANNEL.
 
 Messages that are destined to go out on the IPMB bus use the
-IPMI_IPMB_ADDR_TYPE address type.  The format is
+IPMI_IPMB_ADDR_TYPE address type.  The format is::
 
   struct ipmi_ipmb_addr
   {
@@ -184,16 +183,16 @@
 Messages
 --------
 
-Messages are defined as:
+Messages are defined as::
 
-struct ipmi_msg
-{
+  struct ipmi_msg
+  {
 	unsigned char netfn;
 	unsigned char lun;
 	unsigned char cmd;
 	unsigned char *data;
 	int           data_len;
-};
+  };
 
 The driver takes care of adding/stripping the header information.  The
 data portion is just the data to be send (do NOT put addressing info
@@ -208,7 +207,7 @@
 will have no place to put the message.
 
 Messages coming up from the message handler in kernelland will come in
-as:
+as::
 
   struct ipmi_recv_msg
   {
@@ -246,6 +245,7 @@
 
 
 Watching For Interfaces
+^^^^^^^^^^^^^^^^^^^^^^^
 
 When your code comes up, the IPMI driver may or may not have detected
 if IPMI devices exist.  So you might have to defer your setup until
@@ -256,6 +256,7 @@
 
 
 Creating the User
+^^^^^^^^^^^^^^^^^
 
 To use the message handler, you must first create a user using
 ipmi_create_user.  The interface number specifies which SMI you want
@@ -272,6 +273,7 @@
 
 
 Messaging
+^^^^^^^^^
 
 To send a message from kernel-land, the ipmi_request_settime() call does
 pretty much all message handling.  Most of the parameter are
@@ -321,6 +323,7 @@
 
 
 Events and Incoming Commands
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 The driver takes care of polling for IPMI events and receiving
 commands (commands are messages that are not responses, they are
@@ -367,7 +370,7 @@
 methods, depending on the system.
 
 You can specify up to four interfaces on the module load line and
-control some module parameters:
+control some module parameters::
 
   modprobe ipmi_si.o type=<type1>,<type2>....
        ports=<port1>,<port2>... addrs=<addr1>,<addr2>...
@@ -437,7 +440,7 @@
 obviously only useful for modules.
 
 When compiled into the kernel, the parameters can be specified on the
-kernel command line as:
+kernel command line as::
 
   ipmi_si.type=<type1>,<type2>...
        ipmi_si.ports=<port1>,<port2>... ipmi_si.addrs=<addr1>,<addr2>...
@@ -474,16 +477,22 @@
 interfaces can be added or removed after the kernel is up and running.
 This is done using /sys/modules/ipmi_si/parameters/hotmod, which is a
 write-only parameter.  You write a string to this interface.  The string
-has the format:
+has the format::
+
    <op1>[:op2[:op3...]]
-The "op"s are:
+
+The "op"s are::
+
    add|remove,kcs|bt|smic,mem|i/o,<address>[,<opt1>[,<opt2>[,...]]]
-You can specify more than one interface on the line.  The "opt"s are:
+
+You can specify more than one interface on the line.  The "opt"s are::
+
    rsp=<regspacing>
    rsi=<regsize>
    rsh=<regshift>
    irq=<irq>
    ipmb=<ipmb slave addr>
+
 and these have the same meanings as discussed above.  Note that you
 can also use this on the kernel command line for a more compact format
 for specifying an interface.  Note that when removing an interface,
@@ -496,7 +505,7 @@
 The SMBus driver allows up to 4 SMBus devices to be configured in the
 system.  By default, the driver will only register with something it
 finds in DMI or ACPI tables.  You can change this
-at module load time (for a module) with:
+at module load time (for a module) with::
 
   modprobe ipmi_ssif.o
 	addr=<i2caddr1>[,<i2caddr2>[,...]]
@@ -535,7 +544,7 @@
 driver what to use.
 
 When compiled into the kernel, the addresses can be specified on the
-kernel command line as:
+kernel command line as::
 
   ipmb_ssif.addr=<i2caddr1>[,<i2caddr2>[...]]
 	ipmi_ssif.adapter=<adapter1>[,<adapter2>[...]]
@@ -565,9 +574,9 @@
 the address came from or the raw base device for the IPMI interface.
 You can use the IPMI smi_watcher to catch the IPMI interfaces as they
 come or go, and to grab the information, you can use the function
-ipmi_get_smi_info(), which returns the following structure:
+ipmi_get_smi_info(), which returns the following structure::
 
-struct ipmi_smi_info {
+  struct ipmi_smi_info {
 	enum ipmi_addr_src addr_src;
 	struct device *dev;
 	union {
@@ -575,7 +584,7 @@
 			void *acpi_handle;
 		} acpi_info;
 	} addr_info;
-};
+  };
 
 Currently special info for only for SI_ACPI address sources is
 returned.  Others may be added as necessary.
@@ -590,7 +599,7 @@
 
 A watchdog timer is provided that implements the Linux-standard
 watchdog timer interface.  It has three module parameters that can be
-used to control it:
+used to control it::
 
   modprobe ipmi_watchdog timeout=<t> pretimeout=<t> action=<action type>
       preaction=<preaction type> preop=<preop type> start_now=x
@@ -635,7 +644,7 @@
 if the CONFIG_WATCHDOG_NOWAYOUT option is enabled, or false if not.
 
 When compiled into the kernel, the kernel command line is available
-for configuring the watchdog:
+for configuring the watchdog::
 
   ipmi_watchdog.timeout=<t> ipmi_watchdog.pretimeout=<t>
 	ipmi_watchdog.action=<action type>
@@ -675,6 +684,7 @@
 
 
 The field settings of the events are:
+
 * Generator ID: 0x21 (kernel)
 * EvM Rev: 0x03 (this event is formatting in IPMI 1.0 format)
 * Sensor Type: 0x20 (OS critical stop sensor)
@@ -683,18 +693,20 @@
 * Event Data 1: 0xa1 (Runtime stop in OEM bytes 2 and 3)
 * Event data 2: second byte of panic string
 * Event data 3: third byte of panic string
+
 See the IPMI spec for the details of the event layout.  This event is
 always sent to the local management controller.  It will handle routing
 the message to the right place
 
 Other OEM events have the following format:
-Record ID (bytes 0-1): Set by the SEL.
-Record type (byte 2): 0xf0 (OEM non-timestamped)
-byte 3: The slave address of the card saving the panic
-byte 4: A sequence number (starting at zero)
-The rest of the bytes (11 bytes) are the panic string.  If the panic string
-is longer than 11 bytes, multiple messages will be sent with increasing
-sequence numbers.
+
+* Record ID (bytes 0-1): Set by the SEL.
+* Record type (byte 2): 0xf0 (OEM non-timestamped)
+* byte 3: The slave address of the card saving the panic
+* byte 4: A sequence number (starting at zero)
+  The rest of the bytes (11 bytes) are the panic string.  If the panic string
+  is longer than 11 bytes, multiple messages will be sent with increasing
+  sequence numbers.
 
 Because you cannot send OEM events using the standard interface, this
 function will attempt to find an SEL and add the events there.  It
diff --git a/Documentation/IRQ-affinity.txt b/Documentation/IRQ-affinity.txt
index 01a6751..29da500 100644
--- a/Documentation/IRQ-affinity.txt
+++ b/Documentation/IRQ-affinity.txt
@@ -1,8 +1,11 @@
-ChangeLog:
-	Started by Ingo Molnar <mingo@redhat.com>
-	Update by Max Krasnyansky <maxk@qualcomm.com>
-
+================
 SMP IRQ affinity
+================
+
+ChangeLog:
+	- Started by Ingo Molnar <mingo@redhat.com>
+	- Update by Max Krasnyansky <maxk@qualcomm.com>
+
 
 /proc/irq/IRQ#/smp_affinity and /proc/irq/IRQ#/smp_affinity_list specify
 which target CPUs are permitted for a given IRQ source.  It's a bitmask
@@ -16,50 +19,52 @@
 Default mask is 0xffffffff.
 
 Here is an example of restricting IRQ44 (eth1) to CPU0-3 then restricting
-it to CPU4-7 (this is an 8-CPU SMP box):
+it to CPU4-7 (this is an 8-CPU SMP box)::
 
-[root@moon 44]# cd /proc/irq/44
-[root@moon 44]# cat smp_affinity
-ffffffff
+	[root@moon 44]# cd /proc/irq/44
+	[root@moon 44]# cat smp_affinity
+	ffffffff
 
-[root@moon 44]# echo 0f > smp_affinity
-[root@moon 44]# cat smp_affinity
-0000000f
-[root@moon 44]# ping -f h
-PING hell (195.4.7.3): 56 data bytes
-...
---- hell ping statistics ---
-6029 packets transmitted, 6027 packets received, 0% packet loss
-round-trip min/avg/max = 0.1/0.1/0.4 ms
-[root@moon 44]# cat /proc/interrupts | grep 'CPU\|44:'
-           CPU0       CPU1       CPU2       CPU3      CPU4       CPU5        CPU6       CPU7
- 44:       1068       1785       1785       1783         0          0           0         0    IO-APIC-level  eth1
+	[root@moon 44]# echo 0f > smp_affinity
+	[root@moon 44]# cat smp_affinity
+	0000000f
+	[root@moon 44]# ping -f h
+	PING hell (195.4.7.3): 56 data bytes
+	...
+	--- hell ping statistics ---
+	6029 packets transmitted, 6027 packets received, 0% packet loss
+	round-trip min/avg/max = 0.1/0.1/0.4 ms
+	[root@moon 44]# cat /proc/interrupts | grep 'CPU\|44:'
+		CPU0       CPU1       CPU2       CPU3      CPU4       CPU5        CPU6       CPU7
+	44:       1068       1785       1785       1783         0          0           0         0    IO-APIC-level  eth1
 
 As can be seen from the line above IRQ44 was delivered only to the first four
 processors (0-3).
 Now lets restrict that IRQ to CPU(4-7).
 
-[root@moon 44]# echo f0 > smp_affinity
-[root@moon 44]# cat smp_affinity
-000000f0
-[root@moon 44]# ping -f h
-PING hell (195.4.7.3): 56 data bytes
-..
---- hell ping statistics ---
-2779 packets transmitted, 2777 packets received, 0% packet loss
-round-trip min/avg/max = 0.1/0.5/585.4 ms
-[root@moon 44]# cat /proc/interrupts |  'CPU\|44:'
-           CPU0       CPU1       CPU2       CPU3      CPU4       CPU5        CPU6       CPU7
- 44:       1068       1785       1785       1783      1784       1069        1070       1069   IO-APIC-level  eth1
+::
+
+	[root@moon 44]# echo f0 > smp_affinity
+	[root@moon 44]# cat smp_affinity
+	000000f0
+	[root@moon 44]# ping -f h
+	PING hell (195.4.7.3): 56 data bytes
+	..
+	--- hell ping statistics ---
+	2779 packets transmitted, 2777 packets received, 0% packet loss
+	round-trip min/avg/max = 0.1/0.5/585.4 ms
+	[root@moon 44]# cat /proc/interrupts |  'CPU\|44:'
+		CPU0       CPU1       CPU2       CPU3      CPU4       CPU5        CPU6       CPU7
+	44:       1068       1785       1785       1783      1784       1069        1070       1069   IO-APIC-level  eth1
 
 This time around IRQ44 was delivered only to the last four processors.
 i.e counters for the CPU0-3 did not change.
 
-Here is an example of limiting that same irq (44) to cpus 1024 to 1031:
+Here is an example of limiting that same irq (44) to cpus 1024 to 1031::
 
-[root@moon 44]# echo 1024-1031 > smp_affinity_list
-[root@moon 44]# cat smp_affinity_list
-1024-1031
+	[root@moon 44]# echo 1024-1031 > smp_affinity_list
+	[root@moon 44]# cat smp_affinity_list
+	1024-1031
 
 Note that to do this with a bitmask would require 32 bitmasks of zero
 to follow the pertinent one.
diff --git a/Documentation/IRQ-domain.txt b/Documentation/IRQ-domain.txt
index 1f246eb..4a1cd76 100644
--- a/Documentation/IRQ-domain.txt
+++ b/Documentation/IRQ-domain.txt
@@ -1,4 +1,6 @@
-irq_domain interrupt number mapping library
+===============================================
+The irq_domain interrupt number mapping library
+===============================================
 
 The current design of the Linux kernel uses a single large number
 space where each separate IRQ source is assigned a different number.
@@ -36,7 +38,9 @@
 structure to hwirq numbers (Device Tree and ACPI GSI so far), and can
 be easily extended to support other IRQ topology data sources.
 
-=== irq_domain usage ===
+irq_domain usage
+================
+
 An interrupt controller driver creates and registers an irq_domain by
 calling one of the irq_domain_add_*() functions (each mapping method
 has a different allocator function, more on that later).  The function
@@ -62,15 +66,21 @@
 needs to know the associated hwirq number (such as in the irq_chip
 callbacks) then it can be directly obtained from irq_data->hwirq.
 
-=== Types of irq_domain mappings ===
+Types of irq_domain mappings
+============================
+
 There are several mechanisms available for reverse mapping from hwirq
 to Linux irq, and each mechanism uses a different allocation function.
 Which reverse map type should be used depends on the use case.  Each
 of the reverse map types are described below:
 
-==== Linear ====
-irq_domain_add_linear()
-irq_domain_create_linear()
+Linear
+------
+
+::
+
+	irq_domain_add_linear()
+	irq_domain_create_linear()
 
 The linear reverse map maintains a fixed size table indexed by the
 hwirq number.  When a hwirq is mapped, an irq_desc is allocated for
@@ -89,9 +99,13 @@
 
 The majority of drivers should use the linear map.
 
-==== Tree ====
-irq_domain_add_tree()
-irq_domain_create_tree()
+Tree
+----
+
+::
+
+	irq_domain_add_tree()
+	irq_domain_create_tree()
 
 The irq_domain maintains a radix tree map from hwirq numbers to Linux
 IRQs.  When an hwirq is mapped, an irq_desc is allocated and the
@@ -109,8 +123,12 @@
 
 Very few drivers should need this mapping.
 
-==== No Map ===-
-irq_domain_add_nomap()
+No Map
+------
+
+::
+
+	irq_domain_add_nomap()
 
 The No Map mapping is to be used when the hwirq number is
 programmable in the hardware.  In this case it is best to program the
@@ -121,10 +139,14 @@
 
 Most drivers cannot use this mapping.
 
-==== Legacy ====
-irq_domain_add_simple()
-irq_domain_add_legacy()
-irq_domain_add_legacy_isa()
+Legacy
+------
+
+::
+
+	irq_domain_add_simple()
+	irq_domain_add_legacy()
+	irq_domain_add_legacy_isa()
 
 The Legacy mapping is a special case for drivers that already have a
 range of irq_descs allocated for the hwirqs.  It is used when the
@@ -163,14 +185,17 @@
 before any irq_find_mapping() since the latter will actually work
 for the static IRQ assignment case.
 
-==== Hierarchy IRQ domain ====
+Hierarchy IRQ domain
+--------------------
+
 On some architectures, there may be multiple interrupt controllers
 involved in delivering an interrupt from the device to the target CPU.
-Let's look at a typical interrupt delivering path on x86 platforms:
+Let's look at a typical interrupt delivering path on x86 platforms::
 
-Device --> IOAPIC -> Interrupt remapping Controller -> Local APIC -> CPU
+  Device --> IOAPIC -> Interrupt remapping Controller -> Local APIC -> CPU
 
 There are three interrupt controllers involved:
+
 1) IOAPIC controller
 2) Interrupt remapping controller
 3) Local APIC controller
@@ -180,7 +205,8 @@
 interrupt controller and those irq_domains are organized into hierarchy.
 When building irq_domain hierarchy, the irq_domain near to the device is
 child and the irq_domain near to CPU is parent. So a hierarchy structure
-as below will be built for the example above.
+as below will be built for the example above::
+
 	CPU Vector irq_domain (root irq_domain to manage CPU vectors)
 		^
 		|
@@ -190,6 +216,7 @@
 	IOAPIC irq_domain (manage IOAPIC delivery entries/pins)
 
 There are four major interfaces to use hierarchy irq_domain:
+
 1) irq_domain_alloc_irqs(): allocate IRQ descriptors and interrupt
    controller related resources to deliver these interrupts.
 2) irq_domain_free_irqs(): free IRQ descriptors and interrupt controller
@@ -199,7 +226,8 @@
 4) irq_domain_deactivate_irq(): deactivate interrupt controller hardware
    to stop delivering the interrupt.
 
-Following changes are needed to support hierarchy irq_domain.
+Following changes are needed to support hierarchy irq_domain:
+
 1) a new field 'parent' is added to struct irq_domain; it's used to
    maintain irq_domain hierarchy information.
 2) a new field 'parent_data' is added to struct irq_data; it's used to
@@ -223,6 +251,7 @@
 
 For an interrupt controller driver to support hierarchy irq_domain, it
 needs to:
+
 1) Implement irq_domain_ops.alloc and irq_domain_ops.free
 2) Optionally implement irq_domain_ops.activate and
    irq_domain_ops.deactivate.
diff --git a/Documentation/IRQ.txt b/Documentation/IRQ.txt
index 1011e71..4273806 100644
--- a/Documentation/IRQ.txt
+++ b/Documentation/IRQ.txt
@@ -1,4 +1,6 @@
+===============
 What is an IRQ?
+===============
 
 An IRQ is an interrupt request from a device.
 Currently they can come in over a pin, or over a packet.
diff --git a/Documentation/Intel-IOMMU.txt b/Documentation/Intel-IOMMU.txt
index 49585b6..9dae6b4 100644
--- a/Documentation/Intel-IOMMU.txt
+++ b/Documentation/Intel-IOMMU.txt
@@ -1,3 +1,4 @@
+===================
 Linux IOMMU Support
 ===================
 
@@ -9,11 +10,11 @@
 
 Some Keywords
 
-DMAR - DMA remapping
-DRHD - DMA Remapping Hardware Unit Definition
-RMRR - Reserved memory Region Reporting Structure
-ZLR  - Zero length reads from PCI devices
-IOVA - IO Virtual address.
+- DMAR - DMA remapping
+- DRHD - DMA Remapping Hardware Unit Definition
+- RMRR - Reserved memory Region Reporting Structure
+- ZLR  - Zero length reads from PCI devices
+- IOVA - IO Virtual address.
 
 Basic stuff
 -----------
@@ -33,7 +34,7 @@
 unity mappings for these regions for these devices to access these regions.
 
 How is IOVA generated?
----------------------
+----------------------
 
 Well behaved drivers call pci_map_*() calls before sending command to device
 that needs to perform DMA. Once DMA is completed and mapping is no longer
@@ -82,14 +83,14 @@
 ACPI: DMAR (v001 A M I  OEMDMAR  0x00000001 MSFT 0x00000097) @ 0x000000007f5b5ef0
 
 When DMAR is being processed and initialized by ACPI, prints DMAR locations
-and any RMRR's processed.
+and any RMRR's processed::
 
-ACPI DMAR:Host address width 36
-ACPI DMAR:DRHD (flags: 0x00000000)base: 0x00000000fed90000
-ACPI DMAR:DRHD (flags: 0x00000000)base: 0x00000000fed91000
-ACPI DMAR:DRHD (flags: 0x00000001)base: 0x00000000fed93000
-ACPI DMAR:RMRR base: 0x00000000000ed000 end: 0x00000000000effff
-ACPI DMAR:RMRR base: 0x000000007f600000 end: 0x000000007fffffff
+	ACPI DMAR:Host address width 36
+	ACPI DMAR:DRHD (flags: 0x00000000)base: 0x00000000fed90000
+	ACPI DMAR:DRHD (flags: 0x00000000)base: 0x00000000fed91000
+	ACPI DMAR:DRHD (flags: 0x00000001)base: 0x00000000fed93000
+	ACPI DMAR:RMRR base: 0x00000000000ed000 end: 0x00000000000effff
+	ACPI DMAR:RMRR base: 0x000000007f600000 end: 0x000000007fffffff
 
 When DMAR is enabled for use, you will notice..
 
@@ -98,10 +99,12 @@
 Fault reporting
 ---------------
 
-DMAR:[DMA Write] Request device [00:02.0] fault addr 6df084000
-DMAR:[fault reason 05] PTE Write access is not set
-DMAR:[DMA Write] Request device [00:02.0] fault addr 6df084000
-DMAR:[fault reason 05] PTE Write access is not set
+::
+
+	DMAR:[DMA Write] Request device [00:02.0] fault addr 6df084000
+	DMAR:[fault reason 05] PTE Write access is not set
+	DMAR:[DMA Write] Request device [00:02.0] fault addr 6df084000
+	DMAR:[fault reason 05] PTE Write access is not set
 
 TBD
 ----
diff --git a/Documentation/SAK.txt b/Documentation/SAK.txt
index 74be146..260e1d3 100644
--- a/Documentation/SAK.txt
+++ b/Documentation/SAK.txt
@@ -1,5 +1,9 @@
-Linux 2.4.2 Secure Attention Key (SAK) handling
-18 March 2001, Andrew Morton
+=========================================
+Linux Secure Attention Key (SAK) handling
+=========================================
+
+:Date: 18 March 2001
+:Author: Andrew Morton
 
 An operating system's Secure Attention Key is a security tool which is
 provided as protection against trojan password capturing programs.  It
@@ -13,7 +17,7 @@
 sysrq support.
 
 The proper way of generating a SAK is to define the key sequence using
-`loadkeys'.  This will work whether or not sysrq support is compiled
+``loadkeys``.  This will work whether or not sysrq support is compiled
 into the kernel.
 
 SAK works correctly when the keyboard is in raw mode.  This means that
@@ -25,64 +29,63 @@
 the machine.  CTRL-ALT-BACKSPACE is magical to the X server.  We'll
 choose CTRL-ALT-PAUSE.
 
-In your rc.sysinit (or rc.local) file, add the command
+In your rc.sysinit (or rc.local) file, add the command::
 
 	echo "control alt keycode 101 = SAK" | /bin/loadkeys
 
 And that's it!  Only the superuser may reprogram the SAK key.
 
 
-NOTES
-=====
+.. note::
 
-1: Linux SAK is said to be not a "true SAK" as is required by
-   systems which implement C2 level security.  This author does not
-   know why.
+  1. Linux SAK is said to be not a "true SAK" as is required by
+     systems which implement C2 level security.  This author does not
+     know why.
 
 
-2: On the PC keyboard, SAK kills all applications which have
-   /dev/console opened.
+  2. On the PC keyboard, SAK kills all applications which have
+     /dev/console opened.
 
-   Unfortunately this includes a number of things which you don't
-   actually want killed.  This is because these applications are
-   incorrectly holding /dev/console open.  Be sure to complain to your
-   Linux distributor about this!
+     Unfortunately this includes a number of things which you don't
+     actually want killed.  This is because these applications are
+     incorrectly holding /dev/console open.  Be sure to complain to your
+     Linux distributor about this!
 
-   You can identify processes which will be killed by SAK with the
-   command
+     You can identify processes which will be killed by SAK with the
+     command::
 
 	# ls -l /proc/[0-9]*/fd/* | grep console
 	l-wx------    1 root     root           64 Mar 18 00:46 /proc/579/fd/0 -> /dev/console
 
-   Then:
+     Then::
 
 	# ps aux|grep 579
 	root       579  0.0  0.1  1088  436 ?        S    00:43   0:00 gpm -t ps/2
 
-   So `gpm' will be killed by SAK.  This is a bug in gpm.  It should
-   be closing standard input.  You can work around this by finding the
-   initscript which launches gpm and changing it thusly:
+     So ``gpm`` will be killed by SAK.  This is a bug in gpm.  It should
+     be closing standard input.  You can work around this by finding the
+     initscript which launches gpm and changing it thusly:
 
-   Old:
+     Old::
 
 	daemon gpm
 
-   New:
+     New::
 
 	daemon gpm < /dev/null
 
-   Vixie cron also seems to have this problem, and needs the same treatment.
+     Vixie cron also seems to have this problem, and needs the same treatment.
 
-   Also, one prominent Linux distribution has the following three
-   lines in its rc.sysinit and rc scripts:
+     Also, one prominent Linux distribution has the following three
+     lines in its rc.sysinit and rc scripts::
 
 	exec 3<&0
 	exec 4>&1
 	exec 5>&2
 
-   These commands cause *all* daemons which are launched by the
-   initscripts to have file descriptors 3, 4 and 5 attached to
-   /dev/console.  So SAK kills them all.  A workaround is to simply
-   delete these lines, but this may cause system management
-   applications to malfunction - test everything well.
+     These commands cause **all** daemons which are launched by the
+     initscripts to have file descriptors 3, 4 and 5 attached to
+     /dev/console.  So SAK kills them all.  A workaround is to simply
+     delete these lines, but this may cause system management
+     applications to malfunction - test everything well.
 
diff --git a/Documentation/SM501.txt b/Documentation/SM501.txt
index 561826f..8825074 100644
--- a/Documentation/SM501.txt
+++ b/Documentation/SM501.txt
@@ -1,7 +1,10 @@
-			SM501 Driver
-			============
+.. include:: <isonum.txt>
 
-Copyright 2006, 2007 Simtec Electronics
+============
+SM501 Driver
+============
+
+:Copyright: |copy| 2006, 2007 Simtec Electronics
 
 The Silicon Motion SM501 multimedia companion chip is a multifunction device
 which may provide numerous interfaces including USB host controller USB gadget,
diff --git a/Documentation/bcache.txt b/Documentation/bcache.txt
index a9259b5..c0ce64d 100644
--- a/Documentation/bcache.txt
+++ b/Documentation/bcache.txt
@@ -1,10 +1,15 @@
+============================
+A block layer cache (bcache)
+============================
+
 Say you've got a big slow raid 6, and an ssd or three. Wouldn't it be
 nice if you could use them as cache... Hence bcache.
 
 Wiki and git repositories are at:
-  http://bcache.evilpiepirate.org
-  http://evilpiepirate.org/git/linux-bcache.git
-  http://evilpiepirate.org/git/bcache-tools.git
+
+  - http://bcache.evilpiepirate.org
+  - http://evilpiepirate.org/git/linux-bcache.git
+  - http://evilpiepirate.org/git/bcache-tools.git
 
 It's designed around the performance characteristics of SSDs - it only allocates
 in erase block sized buckets, and it uses a hybrid btree/log to track cached
@@ -37,17 +42,19 @@
 
 Getting started:
 You'll need make-bcache from the bcache-tools repository. Both the cache device
-and backing device must be formatted before use.
+and backing device must be formatted before use::
+
   make-bcache -B /dev/sdb
   make-bcache -C /dev/sdc
 
 make-bcache has the ability to format multiple devices at the same time - if
 you format your backing devices and cache device at the same time, you won't
-have to manually attach:
+have to manually attach::
+
   make-bcache -B /dev/sda /dev/sdb -C /dev/sdc
 
 bcache-tools now ships udev rules, and bcache devices are known to the kernel
-immediately.  Without udev, you can manually register devices like this:
+immediately.  Without udev, you can manually register devices like this::
 
   echo /dev/sdb > /sys/fs/bcache/register
   echo /dev/sdc > /sys/fs/bcache/register
@@ -60,16 +67,16 @@
 a caching device later.
 See 'ATTACHING' section below.
 
-The devices show up as:
+The devices show up as::
 
   /dev/bcache<N>
 
-As well as (with udev):
+As well as (with udev)::
 
   /dev/bcache/by-uuid/<uuid>
   /dev/bcache/by-label/<label>
 
-To get started:
+To get started::
 
   mkfs.ext4 /dev/bcache0
   mount /dev/bcache0 /mnt
@@ -81,13 +88,13 @@
 but will allow for mirroring of metadata and dirty data in the future. Your new
 cache set shows up as /sys/fs/bcache/<UUID>
 
-ATTACHING
+Attaching
 ---------
 
 After your cache device and backing device are registered, the backing device
 must be attached to your cache set to enable caching. Attaching a backing
 device to a cache set is done thusly, with the UUID of the cache set in
-/sys/fs/bcache:
+/sys/fs/bcache::
 
   echo <CSET-UUID> > /sys/block/bcache0/bcache/attach
 
@@ -97,7 +104,7 @@
 important if you have writeback caching turned on.
 
 If you're booting up and your cache device is gone and never coming back, you
-can force run the backing device:
+can force run the backing device::
 
   echo 1 > /sys/block/sdb/bcache/running
 
@@ -110,7 +117,7 @@
 cache, don't expect the filesystem to be recoverable - you will have massive
 filesystem corruption, though ext4's fsck does work miracles.
 
-ERROR HANDLING
+Error Handling
 --------------
 
 Bcache tries to transparently handle IO errors to/from the cache device without
@@ -134,25 +141,27 @@
    read some of the dirty data, though.
 
 
-HOWTO/COOKBOOK
+Howto/cookbook
 --------------
 
 A) Starting a bcache with a missing caching device
 
 If registering the backing device doesn't help, it's already there, you just need
-to force it to run without the cache:
+to force it to run without the cache::
+
 	host:~# echo /dev/sdb1 > /sys/fs/bcache/register
 	[  119.844831] bcache: register_bcache() error opening /dev/sdb1: device already registered
 
 Next, you try to register your caching device if it's present. However
 if it's absent, or registration fails for some reason, you can still
-start your bcache without its cache, like so:
+start your bcache without its cache, like so::
+
 	host:/sys/block/sdb/sdb1/bcache# echo 1 > running
 
 Note that this may cause data loss if you were running in writeback mode.
 
 
-B) Bcache does not find its cache
+B) Bcache does not find its cache::
 
 	host:/sys/block/md5/bcache# echo 0226553a-37cf-41d5-b3ce-8b1e944543a8 > attach
 	[ 1933.455082] bcache: bch_cached_dev_attach() Couldn't find uuid for md5 in set
@@ -160,7 +169,8 @@
 	[ 1933.478179] : cache set not found
 
 In this case, the caching device was simply not registered at boot
-or disappeared and came back, and needs to be (re-)registered:
+or disappeared and came back, and needs to be (re-)registered::
+
 	host:/sys/block/md5/bcache# echo /dev/sdh2 > /sys/fs/bcache/register
 
 
@@ -180,7 +190,8 @@
 of the backing device created with --offset 8K, or any value defined by
 --data-offset when you originally formatted bcache with `make-bcache`.
 
-For example:
+For example::
+
 	losetup -o 8192 /dev/loop0 /dev/your_bcache_backing_dev
 
 This should present your unmodified backing device data in /dev/loop0
@@ -191,33 +202,38 @@
 
 E) Wiping a cache device
 
-host:~# wipefs -a /dev/sdh2
-16 bytes were erased at offset 0x1018 (bcache)
-they were: c6 85 73 f6 4e 1a 45 ca 82 65 f5 7f 48 ba 6d 81
+::
 
-After you boot back with bcache enabled, you recreate the cache and attach it:
-host:~# make-bcache -C /dev/sdh2
-UUID:                   7be7e175-8f4c-4f99-94b2-9c904d227045
-Set UUID:               5bc072a8-ab17-446d-9744-e247949913c1
-version:                0
-nbuckets:               106874
-block_size:             1
-bucket_size:            1024
-nr_in_set:              1
-nr_this_dev:            0
-first_bucket:           1
-[  650.511912] bcache: run_cache_set() invalidating existing data
-[  650.549228] bcache: register_cache() registered cache device sdh2
+	host:~# wipefs -a /dev/sdh2
+	16 bytes were erased at offset 0x1018 (bcache)
+	they were: c6 85 73 f6 4e 1a 45 ca 82 65 f5 7f 48 ba 6d 81
 
-start backing device with missing cache:
-host:/sys/block/md5/bcache# echo 1 > running
+After you boot back with bcache enabled, you recreate the cache and attach it::
 
-attach new cache:
-host:/sys/block/md5/bcache# echo 5bc072a8-ab17-446d-9744-e247949913c1 > attach
-[  865.276616] bcache: bch_cached_dev_attach() Caching md5 as bcache0 on set 5bc072a8-ab17-446d-9744-e247949913c1
+	host:~# make-bcache -C /dev/sdh2
+	UUID:                   7be7e175-8f4c-4f99-94b2-9c904d227045
+	Set UUID:               5bc072a8-ab17-446d-9744-e247949913c1
+	version:                0
+	nbuckets:               106874
+	block_size:             1
+	bucket_size:            1024
+	nr_in_set:              1
+	nr_this_dev:            0
+	first_bucket:           1
+	[  650.511912] bcache: run_cache_set() invalidating existing data
+	[  650.549228] bcache: register_cache() registered cache device sdh2
+
+start backing device with missing cache::
+
+	host:/sys/block/md5/bcache# echo 1 > running
+
+attach new cache::
+
+	host:/sys/block/md5/bcache# echo 5bc072a8-ab17-446d-9744-e247949913c1 > attach
+	[  865.276616] bcache: bch_cached_dev_attach() Caching md5 as bcache0 on set 5bc072a8-ab17-446d-9744-e247949913c1
 
 
-F) Remove or replace a caching device
+F) Remove or replace a caching device::
 
 	host:/sys/block/sda/sda7/bcache# echo 1 > detach
 	[  695.872542] bcache: cached_dev_detach_finish() Caching disabled for sda7
@@ -226,13 +242,15 @@
 	wipefs: error: /dev/nvme0n1p4: probing initialization failed: Device or resource busy
 	Ooops, it's disabled, but not unregistered, so it's still protected
 
-We need to go and unregister it:
+We need to go and unregister it::
+
 	host:/sys/fs/bcache/b7ba27a1-2398-4649-8ae3-0959f57ba128# ls -l cache0
 	lrwxrwxrwx 1 root root 0 Feb 25 18:33 cache0 -> ../../../devices/pci0000:00/0000:00:1d.0/0000:70:00.0/nvme/nvme0/nvme0n1/nvme0n1p4/bcache/
 	host:/sys/fs/bcache/b7ba27a1-2398-4649-8ae3-0959f57ba128# echo 1 > stop
 	kernel: [  917.041908] bcache: cache_set_free() Cache set b7ba27a1-2398-4649-8ae3-0959f57ba128 unregistered
 
-Now we can wipe it:
+Now we can wipe it::
+
 	host:~# wipefs -a /dev/nvme0n1p4
 	/dev/nvme0n1p4: 16 bytes were erased at offset 0x00001018 (bcache): c6 85 73 f6 4e 1a 45 ca 82 65 f5 7f 48 ba 6d 81
 
@@ -252,40 +270,44 @@
 
 1) Is it present in /dev/bcache* ? (there are times where it won't be)
 
-If so, it's easy:
+   If so, it's easy::
+
 	host:/sys/block/bcache0/bcache# echo 1 > stop
 
-2) But if your backing device is gone, this won't work:
+2) But if your backing device is gone, this won't work::
+
 	host:/sys/block/bcache0# cd bcache
 	bash: cd: bcache: No such file or directory
 
-In this case, you may have to unregister the dmcrypt block device that
-references this bcache to free it up:
+   In this case, you may have to unregister the dmcrypt block device that
+   references this bcache to free it up::
+
 	host:~# dmsetup remove oldds1
 	bcache: bcache_device_free() bcache0 stopped
 	bcache: cache_set_free() Cache set 5bc072a8-ab17-446d-9744-e247949913c1 unregistered
 
-This causes the backing bcache to be removed from /sys/fs/bcache and
-then it can be reused.  This would be true of any block device stacking
-where bcache is a lower device.
+   This causes the backing bcache to be removed from /sys/fs/bcache and
+   then it can be reused.  This would be true of any block device stacking
+   where bcache is a lower device.
 
-3) In other cases, you can also look in /sys/fs/bcache/:
+3) In other cases, you can also look in /sys/fs/bcache/::
 
-host:/sys/fs/bcache# ls -l */{cache?,bdev?}
-lrwxrwxrwx 1 root root 0 Mar  5 09:39 0226553a-37cf-41d5-b3ce-8b1e944543a8/bdev1 -> ../../../devices/virtual/block/dm-1/bcache/
-lrwxrwxrwx 1 root root 0 Mar  5 09:39 0226553a-37cf-41d5-b3ce-8b1e944543a8/cache0 -> ../../../devices/virtual/block/dm-4/bcache/
-lrwxrwxrwx 1 root root 0 Mar  5 09:39 5bc072a8-ab17-446d-9744-e247949913c1/cache0 -> ../../../devices/pci0000:00/0000:00:01.0/0000:01:00.0/ata10/host9/target9:0:0/9:0:0:0/block/sdl/sdl2/bcache/
+	host:/sys/fs/bcache# ls -l */{cache?,bdev?}
+	lrwxrwxrwx 1 root root 0 Mar  5 09:39 0226553a-37cf-41d5-b3ce-8b1e944543a8/bdev1 -> ../../../devices/virtual/block/dm-1/bcache/
+	lrwxrwxrwx 1 root root 0 Mar  5 09:39 0226553a-37cf-41d5-b3ce-8b1e944543a8/cache0 -> ../../../devices/virtual/block/dm-4/bcache/
+	lrwxrwxrwx 1 root root 0 Mar  5 09:39 5bc072a8-ab17-446d-9744-e247949913c1/cache0 -> ../../../devices/pci0000:00/0000:00:01.0/0000:01:00.0/ata10/host9/target9:0:0/9:0:0:0/block/sdl/sdl2/bcache/
 
-The device names will show which UUID is relevant, cd in that directory
-and stop the cache:
+   The device names will show which UUID is relevant, cd in that directory
+   and stop the cache::
+
 	host:/sys/fs/bcache/5bc072a8-ab17-446d-9744-e247949913c1# echo 1 > stop
 
-This will free up bcache references and let you reuse the partition for
-other purposes.
+   This will free up bcache references and let you reuse the partition for
+   other purposes.
 
 
 
-TROUBLESHOOTING PERFORMANCE
+Troubleshooting performance
 ---------------------------
 
 Bcache has a bunch of config options and tunables. The defaults are intended to
@@ -301,11 +323,13 @@
    raid stripe size to get the disk multiples that you would like.
 
    For example:  If you have a 64k stripe size, then the following offset
-   would provide alignment for many common RAID5 data spindle counts:
+   would provide alignment for many common RAID5 data spindle counts::
+
 	64k * 2*2*2*3*3*5*7 bytes = 161280k
 
    That space is wasted, but for only 157.5MB you can grow your RAID 5
-   volume to the following data-spindle counts without re-aligning:
+   volume to the following data-spindle counts without re-aligning::
+
 	3,4,5,6,7,8,9,10,12,14,15,18,20,21 ...
 
  - Bad write performance
@@ -313,9 +337,9 @@
    If write performance is not what you expected, you probably wanted to be
    running in writeback mode, which isn't the default (not due to a lack of
    maturity, but simply because in writeback mode you'll lose data if something
-   happens to your SSD)
+   happens to your SSD)::
 
-   # echo writeback > /sys/block/bcache0/bcache/cache_mode
+	# echo writeback > /sys/block/bcache0/bcache/cache_mode
 
  - Bad performance, or traffic not going to the SSD that you'd expect
 
@@ -325,13 +349,13 @@
    accessed data out of your cache.
 
    But if you want to benchmark reads from cache, and you start out with fio
-   writing an 8 gigabyte test file - so you want to disable that.
+   writing an 8 gigabyte test file - so you want to disable that::
 
-   # echo 0 > /sys/block/bcache0/bcache/sequential_cutoff
+	# echo 0 > /sys/block/bcache0/bcache/sequential_cutoff
 
-   To set it back to the default (4 mb), do
+   To set it back to the default (4 mb), do::
 
-   # echo 4M > /sys/block/bcache0/bcache/sequential_cutoff
+	# echo 4M > /sys/block/bcache0/bcache/sequential_cutoff
 
  - Traffic's still going to the spindle/still getting cache misses
 
@@ -344,10 +368,10 @@
    throttles traffic if the latency exceeds a threshold (it does this by
    cranking down the sequential bypass).
 
-   You can disable this if you need to by setting the thresholds to 0:
+   You can disable this if you need to by setting the thresholds to 0::
 
-   # echo 0 > /sys/fs/bcache/<cache set>/congested_read_threshold_us
-   # echo 0 > /sys/fs/bcache/<cache set>/congested_write_threshold_us
+	# echo 0 > /sys/fs/bcache/<cache set>/congested_read_threshold_us
+	# echo 0 > /sys/fs/bcache/<cache set>/congested_write_threshold_us
 
    The default is 2000 us (2 milliseconds) for reads, and 20000 for writes.
 
@@ -369,7 +393,7 @@
    a fix for the issue there).
 
 
-SYSFS - BACKING DEVICE
+Sysfs - backing device
 ----------------------
 
 Available at /sys/block/<bdev>/bcache, /sys/block/bcache*/bcache and
@@ -454,7 +478,8 @@
   still be added to the cache until it is mostly full; only meant for
   benchmarking. Defaults to on.
 
-SYSFS - BACKING DEVICE STATS:
+Sysfs - backing device stats
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 There are directories with these numbers for a running total, as well as
 versions that decay over the past day, hour and 5 minutes; they're also
@@ -463,14 +488,11 @@
 bypassed
   Amount of IO (both reads and writes) that has bypassed the cache
 
-cache_hits
-cache_misses
-cache_hit_ratio
+cache_hits, cache_misses, cache_hit_ratio
   Hits and misses are counted per individual IO as bcache sees them; a
   partial hit is counted as a miss.
 
-cache_bypass_hits
-cache_bypass_misses
+cache_bypass_hits, cache_bypass_misses
   Hits and misses for IO that is intended to skip the cache are still counted,
   but broken out here.
 
@@ -482,7 +504,8 @@
 cache_readaheads
   Count of times readahead occurred.
 
-SYSFS - CACHE SET:
+Sysfs - cache set
+~~~~~~~~~~~~~~~~~
 
 Available at /sys/fs/bcache/<cset-uuid>
 
@@ -520,8 +543,7 @@
   Echoing a size to this file (in human readable units, k/M/G) creates a thinly
   provisioned volume backed by the cache set.
 
-io_error_halflife
-io_error_limit
+io_error_halflife, io_error_limit
   These determines how many errors we accept before disabling the cache.
   Each error is decayed by the half life (in # ios).  If the decaying count
   reaches io_error_limit dirty data is written out and the cache is disabled.
@@ -545,7 +567,8 @@
   Detaches all backing devices and closes the cache devices; if dirty data is
   present it will disable writeback caching and wait for it to be flushed.
 
-SYSFS - CACHE SET INTERNAL:
+Sysfs - cache set internal
+~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 This directory also exposes timings for a number of internal operations, with
 separate files for average duration, average frequency, last occurrence and max
@@ -574,7 +597,8 @@
 trigger_gc
   Writing to this file forces garbage collection to run.
 
-SYSFS - CACHE DEVICE:
+Sysfs - Cache device
+~~~~~~~~~~~~~~~~~~~~
 
 Available at /sys/block/<cdev>/bcache
 
diff --git a/Documentation/bt8xxgpio.txt b/Documentation/bt8xxgpio.txt
index d8297e4..a845feb 100644
--- a/Documentation/bt8xxgpio.txt
+++ b/Documentation/bt8xxgpio.txt
@@ -1,12 +1,8 @@
-===============================================================
-==  BT8XXGPIO driver                                         ==
-==                                                           ==
-==  A driver for a selfmade cheap BT8xx based PCI GPIO-card  ==
-==                                                           ==
-==  For advanced documentation, see                          ==
-==  http://www.bu3sch.de/btgpio.php                          ==
-===============================================================
+===================================================================
+A driver for a selfmade cheap BT8xx based PCI GPIO-card (bt8xxgpio)
+===================================================================
 
+For advanced documentation, see http://www.bu3sch.de/btgpio.php
 
 A generic digital 24-port PCI GPIO card can be built out of an ordinary
 Brooktree bt848, bt849, bt878 or bt879 based analog TV tuner card. The
@@ -17,9 +13,8 @@
 These ports are accessible via 24 pins on the SMD chip package.
 
 
-==============================================
-==  How to physically access the GPIO pins  ==
-==============================================
+How to physically access the GPIO pins
+======================================
 
 The are several ways to access these pins. One might unsolder the whole chip
 and put it on a custom PCI board, or one might only unsolder each individual
@@ -27,7 +22,7 @@
 there are some advanced soldering skills needed in any case.
 
 The physical pinouts are drawn in the following ASCII art.
-The GPIO pins are marked with G00-G23
+The GPIO pins are marked with G00-G23::
 
                                            G G G G G G G G G G G G     G G G G G G
                                            0 0 0 0 0 0 0 0 0 0 1 1     1 1 1 1 1 1
diff --git a/Documentation/btmrvl.txt b/Documentation/btmrvl.txt
index 34916a4..ec57740 100644
--- a/Documentation/btmrvl.txt
+++ b/Documentation/btmrvl.txt
@@ -1,18 +1,16 @@
-=======================================================================
-		README for btmrvl driver
-=======================================================================
-
+=============
+btmrvl driver
+=============
 
 All commands are used via debugfs interface.
 
-=====================
-Set/get driver configurations:
+Set/get driver configurations
+=============================
 
 Path:	/debug/btmrvl/config/
 
-gpiogap=[n]
-hscfgcmd
-	These commands are used to configure the host sleep parameters.
+gpiogap=[n], hscfgcmd
+	These commands are used to configure the host sleep parameters::
 	bit 8:0  -- Gap
 	bit 16:8 -- GPIO
 
@@ -23,7 +21,8 @@
 	where Gap is the gap in milli seconds between wakeup signal and
 	wakeup event, or 0xff for special host sleep setting.
 
-	Usage:
+	Usage::
+
 		# Use SDIO interface to wake up the host and set GAP to 0x80:
 		echo 0xff80 > /debug/btmrvl/config/gpiogap
 		echo 1 > /debug/btmrvl/config/hscfgcmd
@@ -32,15 +31,16 @@
 		echo 0x03ff >  /debug/btmrvl/config/gpiogap
 		echo 1 > /debug/btmrvl/config/hscfgcmd
 
-psmode=[n]
-pscmd
+psmode=[n], pscmd
 	These commands are used to enable/disable auto sleep mode
 
-	where the option is:
+	where the option is::
+
 			1 	-- Enable auto sleep mode
 			0 	-- Disable auto sleep mode
 
-	Usage:
+	Usage::
+
 		# Enable auto sleep mode
 		echo 1 > /debug/btmrvl/config/psmode
 		echo 1 > /debug/btmrvl/config/pscmd
@@ -50,15 +50,16 @@
 		echo 1 > /debug/btmrvl/config/pscmd
 
 
-hsmode=[n]
-hscmd
+hsmode=[n], hscmd
 	These commands are used to enable host sleep or wake up firmware
 
-	where the option is:
+	where the option is::
+
 			1	-- Enable host sleep
 			0	-- Wake up firmware
 
-	Usage:
+	Usage::
+
 		# Enable host sleep
 		echo 1 > /debug/btmrvl/config/hsmode
 		echo 1 > /debug/btmrvl/config/hscmd
@@ -68,12 +69,13 @@
 		echo 1 > /debug/btmrvl/config/hscmd
 
 
-======================
-Get driver status:
+Get driver status
+=================
 
 Path:	/debug/btmrvl/status/
 
-Usage:
+Usage::
+
 	cat /debug/btmrvl/status/<args>
 
 where the args are:
@@ -90,14 +92,17 @@
 txdnldrdy
 	This command displays the value of Tx download ready flag.
 
-
-=====================
+Issuing a raw hci command
+=========================
 
 Use hcitool to issue raw hci command, refer to hcitool manual
 
-	Usage: Hcitool cmd <ogf> <ocf> [Parameters]
+Usage::
 
-	Interface Control Command
+	Hcitool cmd <ogf> <ocf> [Parameters]
+
+Interface Control Command::
+
 	hcitool cmd 0x3f 0x5b 0xf5 0x01 0x00    --Enable All interface
 	hcitool cmd 0x3f 0x5b 0xf5 0x01 0x01    --Enable Wlan interface
 	hcitool cmd 0x3f 0x5b 0xf5 0x01 0x02    --Enable BT interface
@@ -105,13 +110,13 @@
 	hcitool cmd 0x3f 0x5b 0xf5 0x00 0x01    --Disable Wlan interface
 	hcitool cmd 0x3f 0x5b 0xf5 0x00 0x02    --Disable BT interface
 
-=======================================================================
+SD8688 firmware
+===============
 
+Images:
 
-SD8688 firmware:
-
-/lib/firmware/sd8688_helper.bin
-/lib/firmware/sd8688.bin
+- /lib/firmware/sd8688_helper.bin
+- /lib/firmware/sd8688.bin
 
 
 The images can be downloaded from:
diff --git a/Documentation/bus-virt-phys-mapping.txt b/Documentation/bus-virt-phys-mapping.txt
index 2bc55ff..4bb07c2 100644
--- a/Documentation/bus-virt-phys-mapping.txt
+++ b/Documentation/bus-virt-phys-mapping.txt
@@ -1,17 +1,27 @@
-[ NOTE: The virt_to_bus() and bus_to_virt() functions have been
+==========================================================
+How to access I/O mapped memory from within device drivers
+==========================================================
+
+:Author: Linus
+
+.. warning::
+
+	The virt_to_bus() and bus_to_virt() functions have been
 	superseded by the functionality provided by the PCI DMA interface
 	(see Documentation/DMA-API-HOWTO.txt).  They continue
 	to be documented below for historical purposes, but new code
-	must not use them. --davidm 00/12/12 ]
+	must not use them. --davidm 00/12/12
 
-[ This is a mail message in response to a query on IO mapping, thus the
-  strange format for a "document" ]
+::
+
+  [ This is a mail message in response to a query on IO mapping, thus the
+    strange format for a "document" ]
 
 The AHA-1542 is a bus-master device, and your patch makes the driver give the
 controller the physical address of the buffers, which is correct on x86
 (because all bus master devices see the physical memory mappings directly). 
 
-However, on many setups, there are actually _three_ different ways of looking
+However, on many setups, there are actually **three** different ways of looking
 at memory addresses, and in this case we actually want the third, the
 so-called "bus address". 
 
@@ -38,7 +48,7 @@
 not generally necessarily true on other PCI/ISA setups. 
 
 Now, just as an example, on the PReP (PowerPC Reference Platform), the 
-CPU sees a memory map something like this (this is from memory):
+CPU sees a memory map something like this (this is from memory)::
 
 	0-2 GB		"real memory"
 	2 GB-3 GB	"system IO" (inb/out and similar accesses on x86)
@@ -52,7 +62,7 @@
 has to give the master address 0x80000000 as the memory address.
 
 So, for example, depending on how the kernel is actually mapped on the 
-PPC, you can end up with a setup like this:
+PPC, you can end up with a setup like this::
 
  physical address:	0
  virtual address:	0xC0000000
@@ -61,7 +71,7 @@
 where all the addresses actually point to the same thing.  It's just seen 
 through different translations..
 
-Similarly, on the Alpha, the normal translation is
+Similarly, on the Alpha, the normal translation is::
 
  physical address:	0
  virtual address:	0xfffffc0000000000
@@ -70,7 +80,7 @@
 (but there are also Alphas where the physical address and the bus address
 are the same). 
 
-Anyway, the way to look up all these translations, you do
+Anyway, the way to look up all these translations, you do::
 
 	#include <asm/io.h>
 
@@ -81,8 +91,8 @@
 
 Now, when do you need these?
 
-You want the _virtual_ address when you are actually going to access that 
-pointer from the kernel. So you can have something like this:
+You want the **virtual** address when you are actually going to access that
+pointer from the kernel. So you can have something like this::
 
 	/*
 	 * this is the hardware "mailbox" we use to communicate with
@@ -104,7 +114,7 @@
 				...
 
 on the other hand, you want the bus address when you have a buffer that 
-you want to give to the controller:
+you want to give to the controller::
 
 	/* ask the controller to read the sense status into "sense_buffer" */
 	mbox.bufstart = virt_to_bus(&sense_buffer);
@@ -112,7 +122,7 @@
 	mbox.status = 0;
 	notify_controller(&mbox);
 
-And you generally _never_ want to use the physical address, because you can't
+And you generally **never** want to use the physical address, because you can't
 use that from the CPU (the CPU only uses translated virtual addresses), and
 you can't use it from the bus master. 
 
@@ -124,8 +134,10 @@
 management layer doesn't know about devices outside the CPU, so it
 shouldn't need to know about "bus addresses" etc).
 
-NOTE NOTE NOTE! The above is only one part of the whole equation. The above
-only talks about "real memory", that is, CPU memory (RAM). 
+.. note::
+
+	The above is only one part of the whole equation. The above
+	only talks about "real memory", that is, CPU memory (RAM).
 
 There is a completely different type of memory too, and that's the "shared
 memory" on the PCI or ISA bus. That's generally not RAM (although in the case
@@ -137,20 +149,22 @@
 related functions. You should never take the address of such memory, because
 there is really nothing you can do with such an address: it's not
 conceptually in the same memory space as "real memory" at all, so you cannot
-just dereference a pointer. (Sadly, on x86 it _is_ in the same memory space,
+just dereference a pointer. (Sadly, on x86 it **is** in the same memory space,
 so on x86 it actually works to just deference a pointer, but it's not
 portable). 
 
-For such memory, you can do things like
+For such memory, you can do things like:
 
- - reading:
+ - reading::
+
 	/*
 	 * read first 32 bits from ISA memory at 0xC0000, aka
 	 * C000:0000 in DOS terms
 	 */
 	unsigned int signature = isa_readl(0xC0000);
 
- - remapping and writing:
+ - remapping and writing::
+
 	/*
 	 * remap framebuffer PCI memory area at 0xFC000000,
 	 * size 1MB, so that we can access it: We can directly
@@ -165,7 +179,8 @@
 	/* unmap when we unload the driver */
 	iounmap(baseptr);
 
- - copying and clearing:
+ - copying and clearing::
+
 	/* get the 6-byte Ethernet address at ISA address E000:0040 */
 	memcpy_fromio(kernel_buffer, 0xE0040, 6);
 	/* write a packet to the driver */
@@ -181,10 +196,10 @@
 Note that kernel versions 2.0.x (and earlier) mistakenly called the
 ioremap() function "vremap()".  ioremap() is the proper name, but I
 didn't think straight when I wrote it originally.  People who have to
-support both can do something like:
+support both can do something like::
  
 	/* support old naming silliness */
-	#if LINUX_VERSION_CODE < 0x020100                                     
+	#if LINUX_VERSION_CODE < 0x020100
 	#define ioremap vremap
 	#define iounmap vfree                                                     
 	#endif
@@ -196,13 +211,10 @@
 don't do all that complex things (or rather: the complexity is not so
 much in the actual IO accesses as in error handling and timeouts etc). 
 It's generally not hard to fix drivers, and in many cases the code
-actually looks better afterwards:
+actually looks better afterwards::
 
 	unsigned long signature = *(unsigned int *) 0xC0000;
 		vs
 	unsigned long signature = readl(0xC0000);
 
 I think the second version actually is more readable, no?
-
-		Linus
-
diff --git a/Documentation/cachetlb.txt b/Documentation/cachetlb.txt
index 3f9f808..6eb9d3f 100644
--- a/Documentation/cachetlb.txt
+++ b/Documentation/cachetlb.txt
@@ -1,7 +1,8 @@
-		Cache and TLB Flushing
-		     Under Linux
+==================================
+Cache and TLB Flushing Under Linux
+==================================
 
-	    David S. Miller <davem@redhat.com>
+:Author: David S. Miller <davem@redhat.com>
 
 This document describes the cache/tlb flushing interfaces called
 by the Linux VM subsystem.  It enumerates over each interface,
@@ -28,7 +29,7 @@
 invoke one of the following flush methods _after_ the page table
 changes occur:
 
-1) void flush_tlb_all(void)
+1) ``void flush_tlb_all(void)``
 
 	The most severe flush of all.  After this interface runs,
 	any previous page table modification whatsoever will be
@@ -37,7 +38,7 @@
 	This is usually invoked when the kernel page tables are
 	changed, since such translations are "global" in nature.
 
-2) void flush_tlb_mm(struct mm_struct *mm)
+2) ``void flush_tlb_mm(struct mm_struct *mm)``
 
 	This interface flushes an entire user address space from
 	the TLB.  After running, this interface must make sure that
@@ -49,8 +50,8 @@
 	page table operations such as what happens during
 	fork, and exec.
 
-3) void flush_tlb_range(struct vm_area_struct *vma,
-			unsigned long start, unsigned long end)
+3) ``void flush_tlb_range(struct vm_area_struct *vma,
+   unsigned long start, unsigned long end)``
 
 	Here we are flushing a specific range of (user) virtual
 	address translations from the TLB.  After running, this
@@ -69,7 +70,7 @@
 	call flush_tlb_page (see below) for each entry which may be
 	modified.
 
-4) void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
+4) ``void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)``
 
 	This time we need to remove the PAGE_SIZE sized translation
 	from the TLB.  The 'vma' is the backing structure used by
@@ -87,8 +88,8 @@
 
 	This is used primarily during fault processing.
 
-5) void update_mmu_cache(struct vm_area_struct *vma,
-			 unsigned long address, pte_t *ptep)
+5) ``void update_mmu_cache(struct vm_area_struct *vma,
+   unsigned long address, pte_t *ptep)``
 
 	At the end of every page fault, this routine is invoked to
 	tell the architecture specific code that a translation
@@ -100,7 +101,7 @@
 	translations for software managed TLB configurations.
 	The sparc64 port currently does this.
 
-6) void tlb_migrate_finish(struct mm_struct *mm)
+6) ``void tlb_migrate_finish(struct mm_struct *mm)``
 
 	This interface is called at the end of an explicit
 	process migration. This interface provides a hook
@@ -112,7 +113,7 @@
 
 Next, we have the cache flushing interfaces.  In general, when Linux
 is changing an existing virtual-->physical mapping to a new value,
-the sequence will be in one of the following forms:
+the sequence will be in one of the following forms::
 
 	1) flush_cache_mm(mm);
 	   change_all_page_tables_of(mm);
@@ -143,7 +144,7 @@
 
 Here are the routines, one by one:
 
-1) void flush_cache_mm(struct mm_struct *mm)
+1) ``void flush_cache_mm(struct mm_struct *mm)``
 
 	This interface flushes an entire user address space from
 	the caches.  That is, after running, there will be no cache
@@ -152,7 +153,7 @@
 	This interface is used to handle whole address space
 	page table operations such as what happens during exit and exec.
 
-2) void flush_cache_dup_mm(struct mm_struct *mm)
+2) ``void flush_cache_dup_mm(struct mm_struct *mm)``
 
 	This interface flushes an entire user address space from
 	the caches.  That is, after running, there will be no cache
@@ -164,8 +165,8 @@
 	This option is separate from flush_cache_mm to allow some
 	optimizations for VIPT caches.
 
-3) void flush_cache_range(struct vm_area_struct *vma,
-			  unsigned long start, unsigned long end)
+3) ``void flush_cache_range(struct vm_area_struct *vma,
+   unsigned long start, unsigned long end)``
 
 	Here we are flushing a specific range of (user) virtual
 	addresses from the cache.  After running, there will be no
@@ -181,7 +182,7 @@
 	call flush_cache_page (see below) for each entry which may be
 	modified.
 
-4) void flush_cache_page(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn)
+4) ``void flush_cache_page(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn)``
 
 	This time we need to remove a PAGE_SIZE sized range
 	from the cache.  The 'vma' is the backing structure used by
@@ -202,7 +203,7 @@
 
 	This is used primarily during fault processing.
 
-5) void flush_cache_kmaps(void)
+5) ``void flush_cache_kmaps(void)``
 
 	This routine need only be implemented if the platform utilizes
 	highmem.  It will be called right before all of the kmaps
@@ -214,8 +215,8 @@
 
 	This routing should be implemented in asm/highmem.h
 
-6) void flush_cache_vmap(unsigned long start, unsigned long end)
-   void flush_cache_vunmap(unsigned long start, unsigned long end)
+6) ``void flush_cache_vmap(unsigned long start, unsigned long end)``
+   ``void flush_cache_vunmap(unsigned long start, unsigned long end)``
 
 	Here in these two interfaces we are flushing a specific range
 	of (kernel) virtual addresses from the cache.  After running,
@@ -243,8 +244,10 @@
 processes to mmap shared memory at address which are a multiple of
 this value.
 
-NOTE: This does not fix shared mmaps, check out the sparc64 port for
-one way to solve this (in particular SPARC_FLAG_MMAPSHARED).
+.. note::
+
+  This does not fix shared mmaps, check out the sparc64 port for
+  one way to solve this (in particular SPARC_FLAG_MMAPSHARED).
 
 Next, you have to solve the D-cache aliasing issue for all
 other cases.  Please keep in mind that fact that, for a given page
@@ -255,8 +258,8 @@
 aliasing problem has the potential to exist since the kernel already
 maps this page at its virtual address.
 
-  void copy_user_page(void *to, void *from, unsigned long addr, struct page *page)
-  void clear_user_page(void *to, unsigned long addr, struct page *page)
+  ``void copy_user_page(void *to, void *from, unsigned long addr, struct page *page)``
+  ``void clear_user_page(void *to, unsigned long addr, struct page *page)``
 
 	These two routines store data in user anonymous or COW
 	pages.  It allows a port to efficiently avoid D-cache alias
@@ -276,14 +279,16 @@
 	If D-cache aliasing is not an issue, these two routines may
 	simply call memcpy/memset directly and do nothing more.
 
-  void flush_dcache_page(struct page *page)
+  ``void flush_dcache_page(struct page *page)``
 
 	Any time the kernel writes to a page cache page, _OR_
 	the kernel is about to read from a page cache page and
 	user space shared/writable mappings of this page potentially
 	exist, this routine is called.
 
-	NOTE: This routine need only be called for page cache pages
+	.. note::
+
+	      This routine need only be called for page cache pages
 	      which can potentially ever be mapped into the address
 	      space of a user process.  So for example, VFS layer code
 	      handling vfs symlinks in the page cache need not call
@@ -322,18 +327,19 @@
 	made of this flag bit, and if set the flush is done and the flag
 	bit is cleared.
 
-	IMPORTANT NOTE: It is often important, if you defer the flush,
+	.. important::
+
+			It is often important, if you defer the flush,
 			that the actual flush occurs on the same CPU
 			as did the cpu stores into the page to make it
 			dirty.  Again, see sparc64 for examples of how
 			to deal with this.
 
-  void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
-                         unsigned long user_vaddr,
-                         void *dst, void *src, int len)
-  void copy_from_user_page(struct vm_area_struct *vma, struct page *page,
-                           unsigned long user_vaddr,
-                           void *dst, void *src, int len)
+  ``void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
+  unsigned long user_vaddr, void *dst, void *src, int len)``
+  ``void copy_from_user_page(struct vm_area_struct *vma, struct page *page,
+  unsigned long user_vaddr, void *dst, void *src, int len)``
+
 	When the kernel needs to copy arbitrary data in and out
 	of arbitrary user pages (f.e. for ptrace()) it will use
 	these two routines.
@@ -344,8 +350,9 @@
 	likely that you will need to flush the instruction cache
 	for copy_to_user_page().
 
-  void flush_anon_page(struct vm_area_struct *vma, struct page *page,
-                       unsigned long vmaddr)
+  ``void flush_anon_page(struct vm_area_struct *vma, struct page *page,
+  unsigned long vmaddr)``
+
   	When the kernel needs to access the contents of an anonymous
 	page, it calls this function (currently only
 	get_user_pages()).  Note: flush_dcache_page() deliberately
@@ -354,7 +361,8 @@
 	architectures).  For incoherent architectures, it should flush
 	the cache of the page at vmaddr.
 
-  void flush_kernel_dcache_page(struct page *page)
+  ``void flush_kernel_dcache_page(struct page *page)``
+
 	When the kernel needs to modify a user page is has obtained
 	with kmap, it calls this function after all modifications are
 	complete (but before kunmapping it) to bring the underlying
@@ -366,14 +374,16 @@
 	the kernel cache for page (using page_address(page)).
 
 
-  void flush_icache_range(unsigned long start, unsigned long end)
+  ``void flush_icache_range(unsigned long start, unsigned long end)``
+
   	When the kernel stores into addresses that it will execute
 	out of (eg when loading modules), this function is called.
 
 	If the icache does not snoop stores then this routine will need
 	to flush it.
 
-  void flush_icache_page(struct vm_area_struct *vma, struct page *page)
+  ``void flush_icache_page(struct vm_area_struct *vma, struct page *page)``
+
 	All the functionality of flush_icache_page can be implemented in
 	flush_dcache_page and update_mmu_cache. In the future, the hope
 	is to remove this interface completely.
@@ -387,7 +397,8 @@
 coherency.  It must do this by flushing the vmap range before doing
 I/O and invalidating it after the I/O returns.
 
-  void flush_kernel_vmap_range(void *vaddr, int size)
+  ``void flush_kernel_vmap_range(void *vaddr, int size)``
+
        flushes the kernel cache for a given virtual address range in
        the vmap area.  This is to make sure that any data the kernel
        modified in the vmap range is made visible to the physical
@@ -395,7 +406,8 @@
        Note that this API does *not* also flush the offset map alias
        of the area.
 
-  void invalidate_kernel_vmap_range(void *vaddr, int size) invalidates
+  ``void invalidate_kernel_vmap_range(void *vaddr, int size) invalidates``
+
        the cache for a given virtual address range in the vmap area
        which prevents the processor from making the cache stale by
        speculatively reading data while the I/O was occurring to the
diff --git a/Documentation/cgroup-v2.txt b/Documentation/cgroup-v2.txt
index e610197..bde1771 100644
--- a/Documentation/cgroup-v2.txt
+++ b/Documentation/cgroup-v2.txt
@@ -1,7 +1,9 @@
-
+================
 Control Group v2
+================
 
-October, 2015		Tejun Heo <tj@kernel.org>
+:Date: October, 2015
+:Author: Tejun Heo <tj@kernel.org>
 
 This is the authoritative documentation on the design, interface and
 conventions of cgroup v2.  It describes all userland-visible aspects
@@ -9,70 +11,72 @@
 future changes must be reflected in this document.  Documentation for
 v1 is available under Documentation/cgroup-v1/.
 
-CONTENTS
+.. CONTENTS
 
-1. Introduction
-  1-1. Terminology
-  1-2. What is cgroup?
-2. Basic Operations
-  2-1. Mounting
-  2-2. Organizing Processes
-  2-3. [Un]populated Notification
-  2-4. Controlling Controllers
-    2-4-1. Enabling and Disabling
-    2-4-2. Top-down Constraint
-    2-4-3. No Internal Process Constraint
-  2-5. Delegation
-    2-5-1. Model of Delegation
-    2-5-2. Delegation Containment
-  2-6. Guidelines
-    2-6-1. Organize Once and Control
-    2-6-2. Avoid Name Collisions
-3. Resource Distribution Models
-  3-1. Weights
-  3-2. Limits
-  3-3. Protections
-  3-4. Allocations
-4. Interface Files
-  4-1. Format
-  4-2. Conventions
-  4-3. Core Interface Files
-5. Controllers
-  5-1. CPU
-    5-1-1. CPU Interface Files
-  5-2. Memory
-    5-2-1. Memory Interface Files
-    5-2-2. Usage Guidelines
-    5-2-3. Memory Ownership
-  5-3. IO
-    5-3-1. IO Interface Files
-    5-3-2. Writeback
-  5-4. PID
-    5-4-1. PID Interface Files
-  5-5. RDMA
-    5-5-1. RDMA Interface Files
-  5-6. Misc
-    5-6-1. perf_event
-6. Namespace
-  6-1. Basics
-  6-2. The Root and Views
-  6-3. Migration and setns(2)
-  6-4. Interaction with Other Namespaces
-P. Information on Kernel Programming
-  P-1. Filesystem Support for Writeback
-D. Deprecated v1 Core Features
-R. Issues with v1 and Rationales for v2
-  R-1. Multiple Hierarchies
-  R-2. Thread Granularity
-  R-3. Competition Between Inner Nodes and Threads
-  R-4. Other Interface Issues
-  R-5. Controller Issues and Remedies
-    R-5-1. Memory
+   1. Introduction
+     1-1. Terminology
+     1-2. What is cgroup?
+   2. Basic Operations
+     2-1. Mounting
+     2-2. Organizing Processes
+     2-3. [Un]populated Notification
+     2-4. Controlling Controllers
+       2-4-1. Enabling and Disabling
+       2-4-2. Top-down Constraint
+       2-4-3. No Internal Process Constraint
+     2-5. Delegation
+       2-5-1. Model of Delegation
+       2-5-2. Delegation Containment
+     2-6. Guidelines
+       2-6-1. Organize Once and Control
+       2-6-2. Avoid Name Collisions
+   3. Resource Distribution Models
+     3-1. Weights
+     3-2. Limits
+     3-3. Protections
+     3-4. Allocations
+   4. Interface Files
+     4-1. Format
+     4-2. Conventions
+     4-3. Core Interface Files
+   5. Controllers
+     5-1. CPU
+       5-1-1. CPU Interface Files
+     5-2. Memory
+       5-2-1. Memory Interface Files
+       5-2-2. Usage Guidelines
+       5-2-3. Memory Ownership
+     5-3. IO
+       5-3-1. IO Interface Files
+       5-3-2. Writeback
+     5-4. PID
+       5-4-1. PID Interface Files
+     5-5. RDMA
+       5-5-1. RDMA Interface Files
+     5-6. Misc
+       5-6-1. perf_event
+   6. Namespace
+     6-1. Basics
+     6-2. The Root and Views
+     6-3. Migration and setns(2)
+     6-4. Interaction with Other Namespaces
+   P. Information on Kernel Programming
+     P-1. Filesystem Support for Writeback
+   D. Deprecated v1 Core Features
+   R. Issues with v1 and Rationales for v2
+     R-1. Multiple Hierarchies
+     R-2. Thread Granularity
+     R-3. Competition Between Inner Nodes and Threads
+     R-4. Other Interface Issues
+     R-5. Controller Issues and Remedies
+       R-5-1. Memory
 
 
-1. Introduction
+Introduction
+============
 
-1-1. Terminology
+Terminology
+-----------
 
 "cgroup" stands for "control group" and is never capitalized.  The
 singular form is used to designate the whole feature and also as a
@@ -80,7 +84,8 @@
 multiple individual control groups, the plural form "cgroups" is used.
 
 
-1-2. What is cgroup?
+What is cgroup?
+---------------
 
 cgroup is a mechanism to organize processes hierarchically and
 distribute system resources along the hierarchy in a controlled and
@@ -110,12 +115,14 @@
 overridden from further away.
 
 
-2. Basic Operations
+Basic Operations
+================
 
-2-1. Mounting
+Mounting
+--------
 
 Unlike v1, cgroup v2 has only single hierarchy.  The cgroup v2
-hierarchy can be mounted with the following mount command.
+hierarchy can be mounted with the following mount command::
 
   # mount -t cgroup2 none $MOUNT_POINT
 
@@ -160,10 +167,11 @@
 	Delegation section for details.
 
 
-2-2. Organizing Processes
+Organizing Processes
+--------------------
 
 Initially, only the root cgroup exists to which all processes belong.
-A child cgroup can be created by creating a sub-directory.
+A child cgroup can be created by creating a sub-directory::
 
   # mkdir $CGROUP_NAME
 
@@ -190,28 +198,29 @@
 A cgroup which doesn't have any children or live processes can be
 destroyed by removing the directory.  Note that a cgroup which doesn't
 have any children and is associated only with zombie processes is
-considered empty and can be removed.
+considered empty and can be removed::
 
   # rmdir $CGROUP_NAME
 
 "/proc/$PID/cgroup" lists a process's cgroup membership.  If legacy
 cgroup is in use in the system, this file may contain multiple lines,
 one for each hierarchy.  The entry for cgroup v2 is always in the
-format "0::$PATH".
+format "0::$PATH"::
 
   # cat /proc/842/cgroup
   ...
   0::/test-cgroup/test-cgroup-nested
 
 If the process becomes a zombie and the cgroup it was associated with
-is removed subsequently, " (deleted)" is appended to the path.
+is removed subsequently, " (deleted)" is appended to the path::
 
   # cat /proc/842/cgroup
   ...
   0::/test-cgroup/test-cgroup-nested (deleted)
 
 
-2-3. [Un]populated Notification
+[Un]populated Notification
+--------------------------
 
 Each non-root cgroup has a "cgroup.events" file which contains
 "populated" field indicating whether the cgroup's sub-hierarchy has
@@ -222,7 +231,7 @@
 sub-hierarchy have exited.  The populated state updates and
 notifications are recursive.  Consider the following sub-hierarchy
 where the numbers in the parentheses represent the numbers of processes
-in each cgroup.
+in each cgroup::
 
   A(4) - B(0) - C(1)
               \ D(0)
@@ -233,18 +242,20 @@
 both cgroups.
 
 
-2-4. Controlling Controllers
+Controlling Controllers
+-----------------------
 
-2-4-1. Enabling and Disabling
+Enabling and Disabling
+~~~~~~~~~~~~~~~~~~~~~~
 
 Each cgroup has a "cgroup.controllers" file which lists all
-controllers available for the cgroup to enable.
+controllers available for the cgroup to enable::
 
   # cat cgroup.controllers
   cpu io memory
 
 No controller is enabled by default.  Controllers can be enabled and
-disabled by writing to the "cgroup.subtree_control" file.
+disabled by writing to the "cgroup.subtree_control" file::
 
   # echo "+cpu +memory -io" > cgroup.subtree_control
 
@@ -256,7 +267,7 @@
 Enabling a controller in a cgroup indicates that the distribution of
 the target resource across its immediate children will be controlled.
 Consider the following sub-hierarchy.  The enabled controllers are
-listed in parentheses.
+listed in parentheses::
 
   A(cpu,memory) - B(memory) - C()
                             \ D()
@@ -276,7 +287,8 @@
 "cgroup." are owned by the parent rather than the cgroup itself.
 
 
-2-4-2. Top-down Constraint
+Top-down Constraint
+~~~~~~~~~~~~~~~~~~~
 
 Resources are distributed top-down and a cgroup can further distribute
 a resource only if the resource has been distributed to it from the
@@ -287,7 +299,8 @@
 disabled if one or more children have it enabled.
 
 
-2-4-3. No Internal Process Constraint
+No Internal Process Constraint
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 Non-root cgroups can only distribute resources to their children when
 they don't have any processes of their own.  In other words, only
@@ -314,9 +327,11 @@
 file.
 
 
-2-5. Delegation
+Delegation
+----------
 
-2-5-1. Model of Delegation
+Model of Delegation
+~~~~~~~~~~~~~~~~~~~
 
 A cgroup can be delegated in two ways.  First, to a less privileged
 user by granting write access of the directory and its "cgroup.procs"
@@ -345,7 +360,8 @@
 this may be limited explicitly in the future.
 
 
-2-5-2. Delegation Containment
+Delegation Containment
+~~~~~~~~~~~~~~~~~~~~~~
 
 A delegated sub-hierarchy is contained in the sense that processes
 can't be moved into or out of the sub-hierarchy by the delegatee.
@@ -366,7 +382,7 @@
 
 For an example, let's assume cgroups C0 and C1 have been delegated to
 user U0 who created C00, C01 under C0 and C10 under C1 as follows and
-all processes under C0 and C1 belong to U0.
+all processes under C0 and C1 belong to U0::
 
   ~~~~~~~~~~~~~ - C0 - C00
   ~ cgroup    ~      \ C01
@@ -386,9 +402,11 @@
 is not reachable, the migration is rejected with -ENOENT.
 
 
-2-6. Guidelines
+Guidelines
+----------
 
-2-6-1. Organize Once and Control
+Organize Once and Control
+~~~~~~~~~~~~~~~~~~~~~~~~~
 
 Migrating a process across cgroups is a relatively expensive operation
 and stateful resources such as memory are not moved together with the
@@ -404,7 +422,8 @@
 the interface files.
 
 
-2-6-2. Avoid Name Collisions
+Avoid Name Collisions
+~~~~~~~~~~~~~~~~~~~~~
 
 Interface files for a cgroup and its children cgroups occupy the same
 directory and it is possible to create children cgroups which collide
@@ -422,14 +441,16 @@
 user's responsibility to avoid them.
 
 
-3. Resource Distribution Models
+Resource Distribution Models
+============================
 
 cgroup controllers implement several resource distribution schemes
 depending on the resource type and expected use cases.  This section
 describes major schemes in use along with their expected behaviors.
 
 
-3-1. Weights
+Weights
+-------
 
 A parent's resource is distributed by adding up the weights of all
 active children and giving each the fraction matching the ratio of its
@@ -450,7 +471,8 @@
 and is an example of this type.
 
 
-3-2. Limits
+Limits
+------
 
 A child can only consume upto the configured amount of the resource.
 Limits can be over-committed - the sum of the limits of children can
@@ -466,7 +488,8 @@
 on an IO device and is an example of this type.
 
 
-3-3. Protections
+Protections
+-----------
 
 A cgroup is protected to be allocated upto the configured amount of
 the resource if the usages of all its ancestors are under their
@@ -486,7 +509,8 @@
 example of this type.
 
 
-3-4. Allocations
+Allocations
+-----------
 
 A cgroup is exclusively allocated a certain amount of a finite
 resource.  Allocations can't be over-committed - the sum of the
@@ -505,12 +529,14 @@
 type.
 
 
-4. Interface Files
+Interface Files
+===============
 
-4-1. Format
+Format
+------
 
 All interface files should be in one of the following formats whenever
-possible.
+possible::
 
   New-line separated values
   (when only one value can be written at once)
@@ -545,7 +571,8 @@
 may be specified in any order and not all pairs have to be specified.
 
 
-4-2. Conventions
+Conventions
+-----------
 
 - Settings for a single feature should be contained in a single file.
 
@@ -581,25 +608,25 @@
   with "default" as the value must not appear when read.
 
   For example, a setting which is keyed by major:minor device numbers
-  with integer values may look like the following.
+  with integer values may look like the following::
 
     # cat cgroup-example-interface-file
     default 150
     8:0 300
 
-  The default value can be updated by
+  The default value can be updated by::
 
     # echo 125 > cgroup-example-interface-file
 
-  or
+  or::
 
     # echo "default 125" > cgroup-example-interface-file
 
-  An override can be set by
+  An override can be set by::
 
     # echo "8:16 170" > cgroup-example-interface-file
 
-  and cleared by
+  and cleared by::
 
     # echo "8:0 default" > cgroup-example-interface-file
     # cat cgroup-example-interface-file
@@ -612,12 +639,12 @@
   generated on the file.
 
 
-4-3. Core Interface Files
+Core Interface Files
+--------------------
 
 All cgroup core files are prefixed with "cgroup."
 
   cgroup.procs
-
 	A read-write new-line separated values file which exists on
 	all cgroups.
 
@@ -643,7 +670,6 @@
 	should be granted along with the containing directory.
 
   cgroup.controllers
-
 	A read-only space separated values file which exists on all
 	cgroups.
 
@@ -651,7 +677,6 @@
 	the cgroup.  The controllers are not ordered.
 
   cgroup.subtree_control
-
 	A read-write space separated values file which exists on all
 	cgroups.  Starts out empty.
 
@@ -667,23 +692,25 @@
 	operations are specified, either all succeed or all fail.
 
   cgroup.events
-
 	A read-only flat-keyed file which exists on non-root cgroups.
 	The following entries are defined.  Unless specified
 	otherwise, a value change in this file generates a file
 	modified event.
 
 	  populated
-
 		1 if the cgroup or its descendants contains any live
 		processes; otherwise, 0.
 
 
-5. Controllers
+Controllers
+===========
 
-5-1. CPU
+CPU
+---
 
-[NOTE: The interface for the cpu controller hasn't been merged yet]
+.. note::
+
+	The interface for the cpu controller hasn't been merged yet
 
 The "cpu" controllers regulates distribution of CPU cycles.  This
 controller implements weight and absolute bandwidth limit models for
@@ -691,36 +718,34 @@
 realtime scheduling policy.
 
 
-5-1-1. CPU Interface Files
+CPU Interface Files
+~~~~~~~~~~~~~~~~~~~
 
 All time durations are in microseconds.
 
   cpu.stat
-
 	A read-only flat-keyed file which exists on non-root cgroups.
 
-	It reports the following six stats.
+	It reports the following six stats:
 
-	  usage_usec
-	  user_usec
-	  system_usec
-	  nr_periods
-	  nr_throttled
-	  throttled_usec
+	- usage_usec
+	- user_usec
+	- system_usec
+	- nr_periods
+	- nr_throttled
+	- throttled_usec
 
   cpu.weight
-
 	A read-write single value file which exists on non-root
 	cgroups.  The default is "100".
 
 	The weight in the range [1, 10000].
 
   cpu.max
-
 	A read-write two value file which exists on non-root cgroups.
 	The default is "max 100000".
 
-	The maximum bandwidth limit.  It's in the following format.
+	The maximum bandwidth limit.  It's in the following format::
 
 	  $MAX $PERIOD
 
@@ -729,9 +754,10 @@
 	one number is written, $MAX is updated.
 
   cpu.rt.max
+	.. note::
 
-  [NOTE: The semantics of this file is still under discussion and the
-   interface hasn't been merged yet]
+	   The semantics of this file is still under discussion and the
+	   interface hasn't been merged yet
 
 	A read-write two value file which exists on all cgroups.
 	The default is "0 100000".
@@ -739,7 +765,7 @@
 	The maximum realtime runtime allocation.  Over-committing
 	configurations are disallowed and process migrations are
 	rejected if not enough bandwidth is available.  It's in the
-	following format.
+	following format::
 
 	  $MAX $PERIOD
 
@@ -748,7 +774,8 @@
 	updated.
 
 
-5-2. Memory
+Memory
+------
 
 The "memory" controller regulates distribution of memory.  Memory is
 stateful and implements both limit and protection models.  Due to the
@@ -770,14 +797,14 @@
 The above list may expand in the future for better coverage.
 
 
-5-2-1. Memory Interface Files
+Memory Interface Files
+~~~~~~~~~~~~~~~~~~~~~~
 
 All memory amounts are in bytes.  If a value which is not aligned to
 PAGE_SIZE is written, the value may be rounded up to the closest
 PAGE_SIZE multiple when read back.
 
   memory.current
-
 	A read-only single value file which exists on non-root
 	cgroups.
 
@@ -785,7 +812,6 @@
 	and its descendants.
 
   memory.low
-
 	A read-write single value file which exists on non-root
 	cgroups.  The default is "0".
 
@@ -798,7 +824,6 @@
 	protection is discouraged.
 
   memory.high
-
 	A read-write single value file which exists on non-root
 	cgroups.  The default is "max".
 
@@ -811,7 +836,6 @@
 	under extreme conditions the limit may be breached.
 
   memory.max
-
 	A read-write single value file which exists on non-root
 	cgroups.  The default is "max".
 
@@ -826,21 +850,18 @@
 	utility is limited to providing the final safety net.
 
   memory.events
-
 	A read-only flat-keyed file which exists on non-root cgroups.
 	The following entries are defined.  Unless specified
 	otherwise, a value change in this file generates a file
 	modified event.
 
 	  low
-
 		The number of times the cgroup is reclaimed due to
 		high memory pressure even though its usage is under
 		the low boundary.  This usually indicates that the low
 		boundary is over-committed.
 
 	  high
-
 		The number of times processes of the cgroup are
 		throttled and routed to perform direct memory reclaim
 		because the high memory boundary was exceeded.  For a
@@ -849,13 +870,11 @@
 		occurrences are expected.
 
 	  max
-
 		The number of times the cgroup's memory usage was
 		about to go over the max boundary.  If direct reclaim
 		fails to bring it down, the cgroup goes to OOM state.
 
 	  oom
-
 		The number of time the cgroup's memory usage was
 		reached the limit and allocation was about to fail.
 
@@ -864,16 +883,14 @@
 
 		Failed allocation in its turn could be returned into
 		userspace as -ENOMEM or siletly ignored in cases like
-		disk readahead.	 For now OOM in memory cgroup kills
+		disk readahead.  For now OOM in memory cgroup kills
 		tasks iff shortage has happened inside page fault.
 
 	  oom_kill
-
 		The number of processes belonging to this cgroup
 		killed by any kind of OOM killer.
 
   memory.stat
-
 	A read-only flat-keyed file which exists on non-root cgroups.
 
 	This breaks down the cgroup's memory footprint into different
@@ -887,73 +904,55 @@
 	fixed position; use the keys to look up specific values!
 
 	  anon
-
 		Amount of memory used in anonymous mappings such as
 		brk(), sbrk(), and mmap(MAP_ANONYMOUS)
 
 	  file
-
 		Amount of memory used to cache filesystem data,
 		including tmpfs and shared memory.
 
 	  kernel_stack
-
 		Amount of memory allocated to kernel stacks.
 
 	  slab
-
 		Amount of memory used for storing in-kernel data
 		structures.
 
 	  sock
-
 		Amount of memory used in network transmission buffers
 
 	  shmem
-
 		Amount of cached filesystem data that is swap-backed,
 		such as tmpfs, shm segments, shared anonymous mmap()s
 
 	  file_mapped
-
 		Amount of cached filesystem data mapped with mmap()
 
 	  file_dirty
-
 		Amount of cached filesystem data that was modified but
 		not yet written back to disk
 
 	  file_writeback
-
 		Amount of cached filesystem data that was modified and
 		is currently being written back to disk
 
-	  inactive_anon
-	  active_anon
-	  inactive_file
-	  active_file
-	  unevictable
-
+	  inactive_anon, active_anon, inactive_file, active_file, unevictable
 		Amount of memory, swap-backed and filesystem-backed,
 		on the internal memory management lists used by the
 		page reclaim algorithm
 
 	  slab_reclaimable
-
 		Part of "slab" that might be reclaimed, such as
 		dentries and inodes.
 
 	  slab_unreclaimable
-
 		Part of "slab" that cannot be reclaimed on memory
 		pressure.
 
 	  pgfault
-
 		Total number of page faults incurred
 
 	  pgmajfault
-
 		Number of major page faults incurred
 
 	  workingset_refault
@@ -997,7 +996,6 @@
 		Amount of reclaimed lazyfree pages
 
   memory.swap.current
-
 	A read-only single value file which exists on non-root
 	cgroups.
 
@@ -1005,7 +1003,6 @@
 	and its descendants.
 
   memory.swap.max
-
 	A read-write single value file which exists on non-root
 	cgroups.  The default is "max".
 
@@ -1013,7 +1010,8 @@
 	limit, anonymous meomry of the cgroup will not be swapped out.
 
 
-5-2-2. Usage Guidelines
+Usage Guidelines
+~~~~~~~~~~~~~~~~
 
 "memory.high" is the main mechanism to control memory usage.
 Over-committing on high limit (sum of high limits > available memory)
@@ -1036,7 +1034,8 @@
 implemented yet.
 
 
-5-2-3. Memory Ownership
+Memory Ownership
+~~~~~~~~~~~~~~~~
 
 A memory area is charged to the cgroup which instantiated it and stays
 charged to the cgroup until the area is released.  Migrating a process
@@ -1054,7 +1053,8 @@
 belonging to the affected files to ensure correct memory ownership.
 
 
-5-3. IO
+IO
+--
 
 The "io" controller regulates the distribution of IO resources.  This
 controller implements both weight based and absolute bandwidth or IOPS
@@ -1063,28 +1063,29 @@
 blk-mq devices.
 
 
-5-3-1. IO Interface Files
+IO Interface Files
+~~~~~~~~~~~~~~~~~~
 
   io.stat
-
 	A read-only nested-keyed file which exists on non-root
 	cgroups.
 
 	Lines are keyed by $MAJ:$MIN device numbers and not ordered.
 	The following nested keys are defined.
 
+	  ======	===================
 	  rbytes	Bytes read
 	  wbytes	Bytes written
 	  rios		Number of read IOs
 	  wios		Number of write IOs
+	  ======	===================
 
-	An example read output follows.
+	An example read output follows:
 
 	  8:16 rbytes=1459200 wbytes=314773504 rios=192 wios=353
 	  8:0 rbytes=90430464 wbytes=299008000 rios=8950 wios=1252
 
   io.weight
-
 	A read-write flat-keyed file which exists on non-root cgroups.
 	The default is "default 100".
 
@@ -1098,14 +1099,13 @@
 	$WEIGHT" or simply "$WEIGHT".  Overrides can be set by writing
 	"$MAJ:$MIN $WEIGHT" and unset by writing "$MAJ:$MIN default".
 
-	An example read output follows.
+	An example read output follows::
 
 	  default 100
 	  8:16 200
 	  8:0 50
 
   io.max
-
 	A read-write nested-keyed file which exists on non-root
 	cgroups.
 
@@ -1113,10 +1113,12 @@
 	device numbers and not ordered.  The following nested keys are
 	defined.
 
+	  =====		==================================
 	  rbps		Max read bytes per second
 	  wbps		Max write bytes per second
 	  riops		Max read IO operations per second
 	  wiops		Max write IO operations per second
+	  =====		==================================
 
 	When writing, any number of nested key-value pairs can be
 	specified in any order.  "max" can be specified as the value
@@ -1126,24 +1128,25 @@
 	BPS and IOPS are measured in each IO direction and IOs are
 	delayed if limit is reached.  Temporary bursts are allowed.
 
-	Setting read limit at 2M BPS and write at 120 IOPS for 8:16.
+	Setting read limit at 2M BPS and write at 120 IOPS for 8:16::
 
 	  echo "8:16 rbps=2097152 wiops=120" > io.max
 
-	Reading returns the following.
+	Reading returns the following::
 
 	  8:16 rbps=2097152 wbps=max riops=max wiops=120
 
-	Write IOPS limit can be removed by writing the following.
+	Write IOPS limit can be removed by writing the following::
 
 	  echo "8:16 wiops=max" > io.max
 
-	Reading now returns the following.
+	Reading now returns the following::
 
 	  8:16 rbps=2097152 wbps=max riops=max wiops=max
 
 
-5-3-2. Writeback
+Writeback
+~~~~~~~~~
 
 Page cache is dirtied through buffered writes and shared mmaps and
 written asynchronously to the backing filesystem by the writeback
@@ -1191,22 +1194,19 @@
 The sysctl knobs which affect writeback behavior are applied to cgroup
 writeback as follows.
 
-  vm.dirty_background_ratio
-  vm.dirty_ratio
-
+  vm.dirty_background_ratio, vm.dirty_ratio
 	These ratios apply the same to cgroup writeback with the
 	amount of available memory capped by limits imposed by the
 	memory controller and system-wide clean memory.
 
-  vm.dirty_background_bytes
-  vm.dirty_bytes
-
+  vm.dirty_background_bytes, vm.dirty_bytes
 	For cgroup writeback, this is calculated into ratio against
 	total available memory and applied the same way as
 	vm.dirty[_background]_ratio.
 
 
-5-4. PID
+PID
+---
 
 The process number controller is used to allow a cgroup to stop any
 new tasks from being fork()'d or clone()'d after a specified limit is
@@ -1221,17 +1221,16 @@
 used by the kernel.
 
 
-5-4-1. PID Interface Files
+PID Interface Files
+~~~~~~~~~~~~~~~~~~~
 
   pids.max
-
 	A read-write single value file which exists on non-root
 	cgroups.  The default is "max".
 
 	Hard limit of number of processes.
 
   pids.current
-
 	A read-only single value file which exists on all cgroups.
 
 	The number of processes currently in the cgroup and its
@@ -1246,12 +1245,14 @@
 of a new process would cause a cgroup policy to be violated.
 
 
-5-5. RDMA
+RDMA
+----
 
 The "rdma" controller regulates the distribution and accounting of
 of RDMA resources.
 
-5-5-1. RDMA Interface Files
+RDMA Interface Files
+~~~~~~~~~~~~~~~~~~~~
 
   rdma.max
 	A readwrite nested-keyed file that exists for all the cgroups
@@ -1264,10 +1265,12 @@
 
 	The following nested keys are defined.
 
+	  ==========	=============================
 	  hca_handle	Maximum number of HCA Handles
 	  hca_object 	Maximum number of HCA Objects
+	  ==========	=============================
 
-	An example for mlx4 and ocrdma device follows.
+	An example for mlx4 and ocrdma device follows::
 
 	  mlx4_0 hca_handle=2 hca_object=2000
 	  ocrdma1 hca_handle=3 hca_object=max
@@ -1276,15 +1279,17 @@
 	A read-only file that describes current resource usage.
 	It exists for all the cgroup except root.
 
-	An example for mlx4 and ocrdma device follows.
+	An example for mlx4 and ocrdma device follows::
 
 	  mlx4_0 hca_handle=1 hca_object=20
 	  ocrdma1 hca_handle=1 hca_object=23
 
 
-5-6. Misc
+Misc
+----
 
-5-6-1. perf_event
+perf_event
+~~~~~~~~~~
 
 perf_event controller, if not mounted on a legacy hierarchy, is
 automatically enabled on the v2 hierarchy so that perf events can
@@ -1292,9 +1297,11 @@
 moved to a legacy hierarchy after v2 hierarchy is populated.
 
 
-6. Namespace
+Namespace
+=========
 
-6-1. Basics
+Basics
+------
 
 cgroup namespace provides a mechanism to virtualize the view of the
 "/proc/$PID/cgroup" file and cgroup mounts.  The CLONE_NEWCGROUP clone
@@ -1308,7 +1315,7 @@
 complete path of the cgroup of a process.  In a container setup where
 a set of cgroups and namespaces are intended to isolate processes the
 "/proc/$PID/cgroup" file may leak potential system level information
-to the isolated processes.  For Example:
+to the isolated processes.  For Example::
 
   # cat /proc/self/cgroup
   0::/batchjobs/container_id1
@@ -1316,14 +1323,14 @@
 The path '/batchjobs/container_id1' can be considered as system-data
 and undesirable to expose to the isolated processes.  cgroup namespace
 can be used to restrict visibility of this path.  For example, before
-creating a cgroup namespace, one would see:
+creating a cgroup namespace, one would see::
 
   # ls -l /proc/self/ns/cgroup
   lrwxrwxrwx 1 root root 0 2014-07-15 10:37 /proc/self/ns/cgroup -> cgroup:[4026531835]
   # cat /proc/self/cgroup
   0::/batchjobs/container_id1
 
-After unsharing a new namespace, the view changes.
+After unsharing a new namespace, the view changes::
 
   # ls -l /proc/self/ns/cgroup
   lrwxrwxrwx 1 root root 0 2014-07-15 10:35 /proc/self/ns/cgroup -> cgroup:[4026532183]
@@ -1341,7 +1348,8 @@
 remain.
 
 
-6-2. The Root and Views
+The Root and Views
+------------------
 
 The 'cgroupns root' for a cgroup namespace is the cgroup in which the
 process calling unshare(2) is running.  For example, if a process in
@@ -1350,7 +1358,7 @@
 init_cgroup_ns, this is the real root ('/') cgroup.
 
 The cgroupns root cgroup does not change even if the namespace creator
-process later moves to a different cgroup.
+process later moves to a different cgroup::
 
   # ~/unshare -c # unshare cgroupns in some cgroup
   # cat /proc/self/cgroup
@@ -1364,7 +1372,7 @@
 
 Processes running inside the cgroup namespace will be able to see
 cgroup paths (in /proc/self/cgroup) only inside their root cgroup.
-From within an unshared cgroupns:
+From within an unshared cgroupns::
 
   # sleep 100000 &
   [1] 7353
@@ -1373,7 +1381,7 @@
   0::/sub_cgrp_1
 
 From the initial cgroup namespace, the real cgroup path will be
-visible:
+visible::
 
   $ cat /proc/7353/cgroup
   0::/batchjobs/container_id1/sub_cgrp_1
@@ -1381,7 +1389,7 @@
 From a sibling cgroup namespace (that is, a namespace rooted at a
 different cgroup), the cgroup path relative to its own cgroup
 namespace root will be shown.  For instance, if PID 7353's cgroup
-namespace root is at '/batchjobs/container_id2', then it will see
+namespace root is at '/batchjobs/container_id2', then it will see::
 
   # cat /proc/7353/cgroup
   0::/../container_id2/sub_cgrp_1
@@ -1390,13 +1398,14 @@
 its relative to the cgroup namespace root of the caller.
 
 
-6-3. Migration and setns(2)
+Migration and setns(2)
+----------------------
 
 Processes inside a cgroup namespace can move into and out of the
 namespace root if they have proper access to external cgroups.  For
 example, from inside a namespace with cgroupns root at
 /batchjobs/container_id1, and assuming that the global hierarchy is
-still accessible inside cgroupns:
+still accessible inside cgroupns::
 
   # cat /proc/7353/cgroup
   0::/sub_cgrp_1
@@ -1418,10 +1427,11 @@
 process under the target cgroup namespace root.
 
 
-6-4. Interaction with Other Namespaces
+Interaction with Other Namespaces
+---------------------------------
 
 Namespace specific cgroup hierarchy can be mounted by a process
-running inside a non-init cgroup namespace.
+running inside a non-init cgroup namespace::
 
   # mount -t cgroup2 none $MOUNT_POINT
 
@@ -1434,27 +1444,27 @@
 provides a properly isolated cgroup view inside the container.
 
 
-P. Information on Kernel Programming
+Information on Kernel Programming
+=================================
 
 This section contains kernel programming information in the areas
 where interacting with cgroup is necessary.  cgroup core and
 controllers are not covered.
 
 
-P-1. Filesystem Support for Writeback
+Filesystem Support for Writeback
+--------------------------------
 
 A filesystem can support cgroup writeback by updating
 address_space_operations->writepage[s]() to annotate bio's using the
 following two functions.
 
   wbc_init_bio(@wbc, @bio)
-
 	Should be called for each bio carrying writeback data and
 	associates the bio with the inode's owner cgroup.  Can be
 	called anytime between bio allocation and submission.
 
   wbc_account_io(@wbc, @page, @bytes)
-
 	Should be called for each data segment being written out.
 	While this function doesn't care exactly when it's called
 	during the writeback session, it's the easiest and most
@@ -1475,7 +1485,8 @@
 directly.
 
 
-D. Deprecated v1 Core Features
+Deprecated v1 Core Features
+===========================
 
 - Multiple hierarchies including named ones are not supported.
 
@@ -1489,9 +1500,11 @@
   at the root instead.
 
 
-R. Issues with v1 and Rationales for v2
+Issues with v1 and Rationales for v2
+====================================
 
-R-1. Multiple Hierarchies
+Multiple Hierarchies
+--------------------
 
 cgroup v1 allowed an arbitrary number of hierarchies and each
 hierarchy could host any number of controllers.  While this seemed to
@@ -1543,7 +1556,8 @@
 to control how CPU cycles are distributed.
 
 
-R-2. Thread Granularity
+Thread Granularity
+------------------
 
 cgroup v1 allowed threads of a process to belong to different cgroups.
 This didn't make sense for some controllers and those controllers
@@ -1586,7 +1600,8 @@
 locked into constructs inadvertently.
 
 
-R-3. Competition Between Inner Nodes and Threads
+Competition Between Inner Nodes and Threads
+-------------------------------------------
 
 cgroup v1 allowed threads to be in any cgroups which created an
 interesting problem where threads belonging to a parent cgroup and its
@@ -1605,7 +1620,7 @@
 
 The io controller implicitly created a hidden leaf node for each
 cgroup to host the threads.  The hidden leaf had its own copies of all
-the knobs with "leaf_" prefixed.  While this allowed equivalent
+the knobs with ``leaf_`` prefixed.  While this allowed equivalent
 control over internal threads, it was with serious drawbacks.  It
 always added an extra layer of nesting which wouldn't be necessary
 otherwise, made the interface messy and significantly complicated the
@@ -1626,7 +1641,8 @@
 in a uniform way.
 
 
-R-4. Other Interface Issues
+Other Interface Issues
+----------------------
 
 cgroup v1 grew without oversight and developed a large number of
 idiosyncrasies and inconsistencies.  One issue on the cgroup core side
@@ -1654,9 +1670,11 @@
 controllers so that they expose minimal and consistent interfaces.
 
 
-R-5. Controller Issues and Remedies
+Controller Issues and Remedies
+------------------------------
 
-R-5-1. Memory
+Memory
+~~~~~~
 
 The original lower boundary, the soft limit, is defined as a limit
 that is per default unset.  As a result, the set of cgroups that
diff --git a/Documentation/circular-buffers.txt b/Documentation/circular-buffers.txt
index 4a824d2..d462817 100644
--- a/Documentation/circular-buffers.txt
+++ b/Documentation/circular-buffers.txt
@@ -1,9 +1,9 @@
-			       ================
-			       CIRCULAR BUFFERS
-			       ================
+================
+Circular Buffers
+================
 
-By: David Howells <dhowells@redhat.com>
-    Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+:Author: David Howells <dhowells@redhat.com>
+:Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 
 
 Linux provides a number of features that can be used to implement circular
@@ -20,7 +20,7 @@
 serialising them, and to handle multiple consumers by serialising them.
 
 
-Contents:
+.. Contents:
 
  (*) What is a circular buffer?
 
@@ -31,8 +31,8 @@
      - The consumer.
 
 
-==========================
-WHAT IS A CIRCULAR BUFFER?
+
+What is a circular buffer?
 ==========================
 
 First of all, what is a circular buffer?  A circular buffer is a buffer of
@@ -60,9 +60,7 @@
 be careful, however, as a region more than one unit in size may wrap the end of
 the buffer and be broken into two segments.
 
-
-============================
-MEASURING POWER-OF-2 BUFFERS
+Measuring power-of-2 buffers
 ============================
 
 Calculation of the occupancy or the remaining capacity of an arbitrarily sized
@@ -71,13 +69,13 @@
 then a much quicker bitwise-AND instruction can be used instead.
 
 Linux provides a set of macros for handling power-of-2 circular buffers.  These
-can be made use of by:
+can be made use of by::
 
 	#include <linux/circ_buf.h>
 
 The macros are:
 
- (*) Measure the remaining capacity of a buffer:
+ (#) Measure the remaining capacity of a buffer::
 
 	CIRC_SPACE(head_index, tail_index, buffer_size);
 
@@ -85,7 +83,7 @@
      can be inserted.
 
 
- (*) Measure the maximum consecutive immediate space in a buffer:
+ (#) Measure the maximum consecutive immediate space in a buffer::
 
 	CIRC_SPACE_TO_END(head_index, tail_index, buffer_size);
 
@@ -94,14 +92,14 @@
      beginning of the buffer.
 
 
- (*) Measure the occupancy of a buffer:
+ (#) Measure the occupancy of a buffer::
 
 	CIRC_CNT(head_index, tail_index, buffer_size);
 
      This returns the number of items currently occupying a buffer[2].
 
 
- (*) Measure the non-wrapping occupancy of a buffer:
+ (#) Measure the non-wrapping occupancy of a buffer::
 
 	CIRC_CNT_TO_END(head_index, tail_index, buffer_size);
 
@@ -112,7 +110,7 @@
 Each of these macros will nominally return a value between 0 and buffer_size-1,
 however:
 
- [1] CIRC_SPACE*() are intended to be used in the producer.  To the producer
+ (1) CIRC_SPACE*() are intended to be used in the producer.  To the producer
      they will return a lower bound as the producer controls the head index,
      but the consumer may still be depleting the buffer on another CPU and
      moving the tail index.
@@ -120,7 +118,7 @@
      To the consumer it will show an upper bound as the producer may be busy
      depleting the space.
 
- [2] CIRC_CNT*() are intended to be used in the consumer.  To the consumer they
+ (2) CIRC_CNT*() are intended to be used in the consumer.  To the consumer they
      will return a lower bound as the consumer controls the tail index, but the
      producer may still be filling the buffer on another CPU and moving the
      head index.
@@ -128,14 +126,12 @@
      To the producer it will show an upper bound as the consumer may be busy
      emptying the buffer.
 
- [3] To a third party, the order in which the writes to the indices by the
+ (3) To a third party, the order in which the writes to the indices by the
      producer and consumer become visible cannot be guaranteed as they are
      independent and may be made on different CPUs - so the result in such a
      situation will merely be a guess, and may even be negative.
 
-
-===========================================
-USING MEMORY BARRIERS WITH CIRCULAR BUFFERS
+Using memory barriers with circular buffers
 ===========================================
 
 By using memory barriers in conjunction with circular buffers, you can avoid
@@ -152,10 +148,10 @@
 two sides can operate simultaneously.
 
 
-THE PRODUCER
+The producer
 ------------
 
-The producer will look something like this:
+The producer will look something like this::
 
 	spin_lock(&producer_lock);
 
@@ -193,10 +189,10 @@
 vacated a given element and the write by the producer to that same element.
 
 
-THE CONSUMER
+The Consumer
 ------------
 
-The consumer will look something like this:
+The consumer will look something like this::
 
 	spin_lock(&consumer_lock);
 
@@ -235,8 +231,7 @@
 against previous accesses.
 
 
-===============
-FURTHER READING
+Further reading
 ===============
 
 See also Documentation/memory-barriers.txt for a description of Linux's memory
diff --git a/Documentation/clk.txt b/Documentation/clk.txt
index 22f026a..be909ed 100644
--- a/Documentation/clk.txt
+++ b/Documentation/clk.txt
@@ -1,12 +1,16 @@
-		The Common Clk Framework
-		Mike Turquette <mturquette@ti.com>
+========================
+The Common Clk Framework
+========================
+
+:Author: Mike Turquette <mturquette@ti.com>
 
 This document endeavours to explain the common clk framework details,
 and how to port a platform over to this framework.  It is not yet a
 detailed explanation of the clock api in include/linux/clk.h, but
 perhaps someday it will include that information.
 
-	Part 1 - introduction and interface split
+Introduction and interface split
+================================
 
 The common clk framework is an interface to control the clock nodes
 available on various devices today.  This may come in the form of clock
@@ -35,10 +39,11 @@
 allows for easy navigation between the two discrete halves of the common
 clock interface.
 
-	Part 2 - common data structures and api
+Common data structures and api
+==============================
 
 Below is the common struct clk_core definition from
-drivers/clk/clk.c, modified for brevity:
+drivers/clk/clk.c, modified for brevity::
 
 	struct clk_core {
 		const char		*name;
@@ -59,7 +64,7 @@
 
 Platforms and devices utilizing the common struct clk_core use the struct
 clk_ops pointer in struct clk_core to perform the hardware-specific parts of
-the operations defined in clk-provider.h:
+the operations defined in clk-provider.h::
 
 	struct clk_ops {
 		int		(*prepare)(struct clk_hw *hw);
@@ -95,19 +100,20 @@
 					      struct dentry *dentry);
 	};
 
-	Part 3 - hardware clk implementations
+Hardware clk implementations
+============================
 
 The strength of the common struct clk_core comes from its .ops and .hw pointers
 which abstract the details of struct clk from the hardware-specific bits, and
 vice versa.  To illustrate consider the simple gateable clk implementation in
-drivers/clk/clk-gate.c:
+drivers/clk/clk-gate.c::
 
-struct clk_gate {
-	struct clk_hw	hw;
-	void __iomem    *reg;
-	u8              bit_idx;
-	...
-};
+	struct clk_gate {
+		struct clk_hw	hw;
+		void __iomem    *reg;
+		u8              bit_idx;
+		...
+	};
 
 struct clk_gate contains struct clk_hw hw as well as hardware-specific
 knowledge about which register and bit controls this clk's gating.
@@ -115,7 +121,7 @@
 notifier_count, is needed here.  That is all handled by the common
 framework code and struct clk_core.
 
-Let's walk through enabling this clk from driver code:
+Let's walk through enabling this clk from driver code::
 
 	struct clk *clk;
 	clk = clk_get(NULL, "my_gateable_clk");
@@ -123,70 +129,71 @@
 	clk_prepare(clk);
 	clk_enable(clk);
 
-The call graph for clk_enable is very simple:
+The call graph for clk_enable is very simple::
 
-clk_enable(clk);
-	clk->ops->enable(clk->hw);
-	[resolves to...]
-		clk_gate_enable(hw);
-		[resolves struct clk gate with to_clk_gate(hw)]
-			clk_gate_set_bit(gate);
+	clk_enable(clk);
+		clk->ops->enable(clk->hw);
+		[resolves to...]
+			clk_gate_enable(hw);
+			[resolves struct clk gate with to_clk_gate(hw)]
+				clk_gate_set_bit(gate);
 
-And the definition of clk_gate_set_bit:
+And the definition of clk_gate_set_bit::
 
-static void clk_gate_set_bit(struct clk_gate *gate)
-{
-	u32 reg;
+	static void clk_gate_set_bit(struct clk_gate *gate)
+	{
+		u32 reg;
 
-	reg = __raw_readl(gate->reg);
-	reg |= BIT(gate->bit_idx);
-	writel(reg, gate->reg);
-}
+		reg = __raw_readl(gate->reg);
+		reg |= BIT(gate->bit_idx);
+		writel(reg, gate->reg);
+	}
 
-Note that to_clk_gate is defined as:
+Note that to_clk_gate is defined as::
 
-#define to_clk_gate(_hw) container_of(_hw, struct clk_gate, hw)
+	#define to_clk_gate(_hw) container_of(_hw, struct clk_gate, hw)
 
 This pattern of abstraction is used for every clock hardware
 representation.
 
-	Part 4 - supporting your own clk hardware
+Supporting your own clk hardware
+================================
 
 When implementing support for a new type of clock it is only necessary to
-include the following header:
+include the following header::
 
-#include <linux/clk-provider.h>
+	#include <linux/clk-provider.h>
 
 To construct a clk hardware structure for your platform you must define
-the following:
+the following::
 
-struct clk_foo {
-	struct clk_hw hw;
-	... hardware specific data goes here ...
-};
+	struct clk_foo {
+		struct clk_hw hw;
+		... hardware specific data goes here ...
+	};
 
 To take advantage of your data you'll need to support valid operations
-for your clk:
+for your clk::
 
-struct clk_ops clk_foo_ops {
-	.enable		= &clk_foo_enable;
-	.disable	= &clk_foo_disable;
-};
+	struct clk_ops clk_foo_ops {
+		.enable		= &clk_foo_enable;
+		.disable	= &clk_foo_disable;
+	};
 
-Implement the above functions using container_of:
+Implement the above functions using container_of::
 
-#define to_clk_foo(_hw) container_of(_hw, struct clk_foo, hw)
+	#define to_clk_foo(_hw) container_of(_hw, struct clk_foo, hw)
 
-int clk_foo_enable(struct clk_hw *hw)
-{
-	struct clk_foo *foo;
+	int clk_foo_enable(struct clk_hw *hw)
+	{
+		struct clk_foo *foo;
 
-	foo = to_clk_foo(hw);
+		foo = to_clk_foo(hw);
 
-	... perform magic on foo ...
+		... perform magic on foo ...
 
-	return 0;
-};
+		return 0;
+	};
 
 Below is a matrix detailing which clk_ops are mandatory based upon the
 hardware capabilities of that clock.  A cell marked as "y" means
@@ -194,41 +201,56 @@
 callback is invalid or otherwise unnecessary.  Empty cells are either
 optional or must be evaluated on a case-by-case basis.
 
-                              clock hardware characteristics
-                -----------------------------------------------------------
-                | gate | change rate | single parent | multiplexer | root |
-                |------|-------------|---------------|-------------|------|
-.prepare        |      |             |               |             |      |
-.unprepare      |      |             |               |             |      |
-                |      |             |               |             |      |
-.enable         | y    |             |               |             |      |
-.disable        | y    |             |               |             |      |
-.is_enabled     | y    |             |               |             |      |
-                |      |             |               |             |      |
-.recalc_rate    |      | y           |               |             |      |
-.round_rate     |      | y [1]       |               |             |      |
-.determine_rate |      | y [1]       |               |             |      |
-.set_rate       |      | y           |               |             |      |
-                |      |             |               |             |      |
-.set_parent     |      |             | n             | y           | n    |
-.get_parent     |      |             | n             | y           | n    |
-                |      |             |               |             |      |
-.recalc_accuracy|      |             |               |             |      |
-                |      |             |               |             |      |
-.init           |      |             |               |             |      |
-                -----------------------------------------------------------
-[1] either one of round_rate or determine_rate is required.
+.. table:: clock hardware characteristics
+
+   +----------------+------+-------------+---------------+-------------+------+
+   |                | gate | change rate | single parent | multiplexer | root |
+   +================+======+=============+===============+=============+======+
+   |.prepare        |      |             |               |             |      |
+   +----------------+------+-------------+---------------+-------------+------+
+   |.unprepare      |      |             |               |             |      |
+   +----------------+------+-------------+---------------+-------------+------+
+   +----------------+------+-------------+---------------+-------------+------+
+   |.enable         | y    |             |               |             |      |
+   +----------------+------+-------------+---------------+-------------+------+
+   |.disable        | y    |             |               |             |      |
+   +----------------+------+-------------+---------------+-------------+------+
+   |.is_enabled     | y    |             |               |             |      |
+   +----------------+------+-------------+---------------+-------------+------+
+   +----------------+------+-------------+---------------+-------------+------+
+   |.recalc_rate    |      | y           |               |             |      |
+   +----------------+------+-------------+---------------+-------------+------+
+   |.round_rate     |      | y [1]_      |               |             |      |
+   +----------------+------+-------------+---------------+-------------+------+
+   |.determine_rate |      | y [1]_      |               |             |      |
+   +----------------+------+-------------+---------------+-------------+------+
+   |.set_rate       |      | y           |               |             |      |
+   +----------------+------+-------------+---------------+-------------+------+
+   +----------------+------+-------------+---------------+-------------+------+
+   |.set_parent     |      |             | n             | y           | n    |
+   +----------------+------+-------------+---------------+-------------+------+
+   |.get_parent     |      |             | n             | y           | n    |
+   +----------------+------+-------------+---------------+-------------+------+
+   +----------------+------+-------------+---------------+-------------+------+
+   |.recalc_accuracy|      |             |               |             |      |
+   +----------------+------+-------------+---------------+-------------+------+
+   +----------------+------+-------------+---------------+-------------+------+
+   |.init           |      |             |               |             |      |
+   +----------------+------+-------------+---------------+-------------+------+
+
+.. [1] either one of round_rate or determine_rate is required.
 
 Finally, register your clock at run-time with a hardware-specific
 registration function.  This function simply populates struct clk_foo's
 data and then passes the common struct clk parameters to the framework
-with a call to:
+with a call to::
 
-clk_register(...)
+	clk_register(...)
 
-See the basic clock types in drivers/clk/clk-*.c for examples.
+See the basic clock types in ``drivers/clk/clk-*.c`` for examples.
 
-	Part 5 - Disabling clock gating of unused clocks
+Disabling clock gating of unused clocks
+=======================================
 
 Sometimes during development it can be useful to be able to bypass the
 default disabling of unused clocks. For example, if drivers aren't enabling
@@ -239,7 +261,8 @@
 To bypass this disabling, include "clk_ignore_unused" in the bootargs to the
 kernel.
 
-	Part 6 - Locking
+Locking
+=======
 
 The common clock framework uses two global locks, the prepare lock and the
 enable lock.
diff --git a/Documentation/cpu-load.txt b/Documentation/cpu-load.txt
index 287224e..2d01ce4 100644
--- a/Documentation/cpu-load.txt
+++ b/Documentation/cpu-load.txt
@@ -1,9 +1,10 @@
+========
 CPU load
---------
+========
 
-Linux exports various bits of information via `/proc/stat' and
-`/proc/uptime' that userland tools, such as top(1), use to calculate
-the average time system spent in a particular state, for example:
+Linux exports various bits of information via ``/proc/stat`` and
+``/proc/uptime`` that userland tools, such as top(1), use to calculate
+the average time system spent in a particular state, for example::
 
     $ iostat
     Linux 2.6.18.3-exp (linmac)     02/20/2007
@@ -17,7 +18,7 @@
 system spent 10.01% of the time doing work in user space, 2.92% in the
 kernel, and was overall 81.63% of the time idle.
 
-In most cases the `/proc/stat' information reflects the reality quite
+In most cases the ``/proc/stat``	 information reflects the reality quite
 closely, however due to the nature of how/when the kernel collects
 this data sometimes it can not be trusted at all.
 
@@ -33,78 +34,78 @@
 -------
 
 If we imagine the system with one task that periodically burns cycles
-in the following manner:
+in the following manner::
 
- time line between two timer interrupts
-|--------------------------------------|
- ^                                    ^
- |_ something begins working          |
-                                      |_ something goes to sleep
-                                     (only to be awaken quite soon)
+     time line between two timer interrupts
+    |--------------------------------------|
+     ^                                    ^
+     |_ something begins working          |
+                                          |_ something goes to sleep
+                                         (only to be awaken quite soon)
 
 In the above situation the system will be 0% loaded according to the
-`/proc/stat' (since the timer interrupt will always happen when the
+``/proc/stat`` (since the timer interrupt will always happen when the
 system is executing the idle handler), but in reality the load is
 closer to 99%.
 
 One can imagine many more situations where this behavior of the kernel
-will lead to quite erratic information inside `/proc/stat'.
+will lead to quite erratic information inside ``/proc/stat``::
 
 
-/* gcc -o hog smallhog.c */
-#include <time.h>
-#include <limits.h>
-#include <signal.h>
-#include <sys/time.h>
-#define HIST 10
+	/* gcc -o hog smallhog.c */
+	#include <time.h>
+	#include <limits.h>
+	#include <signal.h>
+	#include <sys/time.h>
+	#define HIST 10
 
-static volatile sig_atomic_t stop;
+	static volatile sig_atomic_t stop;
 
-static void sighandler (int signr)
-{
-     (void) signr;
-     stop = 1;
-}
-static unsigned long hog (unsigned long niters)
-{
-     stop = 0;
-     while (!stop && --niters);
-     return niters;
-}
-int main (void)
-{
-     int i;
-     struct itimerval it = { .it_interval = { .tv_sec = 0, .tv_usec = 1 },
-                             .it_value = { .tv_sec = 0, .tv_usec = 1 } };
-     sigset_t set;
-     unsigned long v[HIST];
-     double tmp = 0.0;
-     unsigned long n;
-     signal (SIGALRM, &sighandler);
-     setitimer (ITIMER_REAL, &it, NULL);
+	static void sighandler (int signr)
+	{
+	(void) signr;
+	stop = 1;
+	}
+	static unsigned long hog (unsigned long niters)
+	{
+	stop = 0;
+	while (!stop && --niters);
+	return niters;
+	}
+	int main (void)
+	{
+	int i;
+	struct itimerval it = { .it_interval = { .tv_sec = 0, .tv_usec = 1 },
+				.it_value = { .tv_sec = 0, .tv_usec = 1 } };
+	sigset_t set;
+	unsigned long v[HIST];
+	double tmp = 0.0;
+	unsigned long n;
+	signal (SIGALRM, &sighandler);
+	setitimer (ITIMER_REAL, &it, NULL);
 
-     hog (ULONG_MAX);
-     for (i = 0; i < HIST; ++i) v[i] = ULONG_MAX - hog (ULONG_MAX);
-     for (i = 0; i < HIST; ++i) tmp += v[i];
-     tmp /= HIST;
-     n = tmp - (tmp / 3.0);
+	hog (ULONG_MAX);
+	for (i = 0; i < HIST; ++i) v[i] = ULONG_MAX - hog (ULONG_MAX);
+	for (i = 0; i < HIST; ++i) tmp += v[i];
+	tmp /= HIST;
+	n = tmp - (tmp / 3.0);
 
-     sigemptyset (&set);
-     sigaddset (&set, SIGALRM);
+	sigemptyset (&set);
+	sigaddset (&set, SIGALRM);
 
-     for (;;) {
-         hog (n);
-         sigwait (&set, &i);
-     }
-     return 0;
-}
+	for (;;) {
+		hog (n);
+		sigwait (&set, &i);
+	}
+	return 0;
+	}
 
 
 References
 ----------
 
-http://lkml.org/lkml/2007/2/12/6
-Documentation/filesystems/proc.txt (1.8)
+- http://lkml.org/lkml/2007/2/12/6
+- Documentation/filesystems/proc.txt (1.8)
 
 
 Thanks
diff --git a/Documentation/cputopology.txt b/Documentation/cputopology.txt
index 127c9d8..c6e7e91 100644
--- a/Documentation/cputopology.txt
+++ b/Documentation/cputopology.txt
@@ -1,3 +1,6 @@
+===========================================
+How CPU topology info is exported via sysfs
+===========================================
 
 Export CPU topology info via sysfs. Items (attributes) are similar
 to /proc/cpuinfo output of some architectures:
@@ -75,24 +78,26 @@
 they reflect the cpu and cache hierarchy.
 
 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_drawer_id(cpu)
-#define topology_sibling_cpumask(cpu)
-#define topology_core_cpumask(cpu)
-#define topology_book_cpumask(cpu)
-#define topology_drawer_cpumask(cpu)
+these macros in include/asm-XXX/topology.h::
 
-The type of **_id macros is int.
-The type of **_cpumask macros is (const) struct cpumask *. The latter
-correspond with appropriate **_siblings sysfs attributes (except for
+	#define topology_physical_package_id(cpu)
+	#define topology_core_id(cpu)
+	#define topology_book_id(cpu)
+	#define topology_drawer_id(cpu)
+	#define topology_sibling_cpumask(cpu)
+	#define topology_core_cpumask(cpu)
+	#define topology_book_cpumask(cpu)
+	#define topology_drawer_cpumask(cpu)
+
+The type of ``**_id macros`` is int.
+The type of ``**_cpumask macros`` is ``(const) struct cpumask *``. The latter
+correspond with appropriate ``**_siblings`` sysfs attributes (except for
 topology_sibling_cpumask() which corresponds with thread_siblings).
 
 To be consistent on all architectures, include/linux/topology.h
 provides default definitions for any of the above macros that are
 not defined by include/asm-XXX/topology.h:
+
 1) physical_package_id: -1
 2) core_id: 0
 3) sibling_cpumask: just the given CPU
@@ -107,6 +112,7 @@
 /sys/devices/system/cpu and includes these files.  The internal
 source for the output is in brackets ("[]").
 
+    =========== ==========================================================
     kernel_max: the maximum CPU index allowed by the kernel configuration.
 		[NR_CPUS-1]
 
@@ -122,6 +128,7 @@
 
     present:	CPUs that have been identified as being present in the
 		system. [cpu_present_mask]
+    =========== ==========================================================
 
 The format for the above output is compatible with cpulist_parse()
 [see <linux/cpumask.h>].  Some examples follow.
@@ -129,7 +136,7 @@
 In this example, there are 64 CPUs in the system but cpus 32-63 exceed
 the kernel max which is limited to 0..31 by the NR_CPUS config option
 being 32.  Note also that CPUs 2 and 4-31 are not online but could be
-brought online as they are both present and possible.
+brought online as they are both present and possible::
 
      kernel_max: 31
         offline: 2,4-31,32-63
@@ -140,7 +147,7 @@
 In this example, the NR_CPUS config option is 128, but the kernel was
 started with possible_cpus=144.  There are 4 CPUs in the system and cpu2
 was manually taken offline (and is the only CPU that can be brought
-online.)
+online.)::
 
      kernel_max: 127
         offline: 2,4-127,128-143
diff --git a/Documentation/crc32.txt b/Documentation/crc32.txt
index a08a7dd..8a6860f 100644
--- a/Documentation/crc32.txt
+++ b/Documentation/crc32.txt
@@ -1,4 +1,6 @@
-A brief CRC tutorial.
+=================================
+brief tutorial on CRC computation
+=================================
 
 A CRC is a long-division remainder.  You add the CRC to the message,
 and the whole thing (message+CRC) is a multiple of the given
@@ -8,7 +10,8 @@
 is used by a lot of hardware implementations, and is why so many
 protocols put the end-of-frame flag after the CRC.
 
-It's actually the same long division you learned in school, except that
+It's actually the same long division you learned in school, except that:
+
 - We're working in binary, so the digits are only 0 and 1, and
 - When dividing polynomials, there are no carries.  Rather than add and
   subtract, we just xor.  Thus, we tend to get a bit sloppy about
@@ -40,11 +43,12 @@
 the polynomial from the remainder and we're back to where we started,
 ready to process the next bit.
 
-A big-endian CRC written this way would be coded like:
-for (i = 0; i < input_bits; i++) {
-	multiple = remainder & 0x80000000 ? CRCPOLY : 0;
-	remainder = (remainder << 1 | next_input_bit()) ^ multiple;
-}
+A big-endian CRC written this way would be coded like::
+
+	for (i = 0; i < input_bits; i++) {
+		multiple = remainder & 0x80000000 ? CRCPOLY : 0;
+		remainder = (remainder << 1 | next_input_bit()) ^ multiple;
+	}
 
 Notice how, to get at bit 32 of the shifted remainder, we look
 at bit 31 of the remainder *before* shifting it.
@@ -54,25 +58,26 @@
 32 bits later.  Thus, the first 32 cycles of this are pretty boring.
 Also, to add the CRC to a message, we need a 32-bit-long hole for it at
 the end, so we have to add 32 extra cycles shifting in zeros at the
-end of every message,
+end of every message.
 
 These details lead to a standard trick: rearrange merging in the
 next_input_bit() until the moment it's needed.  Then the first 32 cycles
 can be precomputed, and merging in the final 32 zero bits to make room
-for the CRC can be skipped entirely.  This changes the code to:
+for the CRC can be skipped entirely.  This changes the code to::
 
-for (i = 0; i < input_bits; i++) {
-	remainder ^= next_input_bit() << 31;
-	multiple = (remainder & 0x80000000) ? CRCPOLY : 0;
-	remainder = (remainder << 1) ^ multiple;
-}
+	for (i = 0; i < input_bits; i++) {
+		remainder ^= next_input_bit() << 31;
+		multiple = (remainder & 0x80000000) ? CRCPOLY : 0;
+		remainder = (remainder << 1) ^ multiple;
+	}
 
-With this optimization, the little-endian code is particularly simple:
-for (i = 0; i < input_bits; i++) {
-	remainder ^= next_input_bit();
-	multiple = (remainder & 1) ? CRCPOLY : 0;
-	remainder = (remainder >> 1) ^ multiple;
-}
+With this optimization, the little-endian code is particularly simple::
+
+	for (i = 0; i < input_bits; i++) {
+		remainder ^= next_input_bit();
+		multiple = (remainder & 1) ? CRCPOLY : 0;
+		remainder = (remainder >> 1) ^ multiple;
+	}
 
 The most significant coefficient of the remainder polynomial is stored
 in the least significant bit of the binary "remainder" variable.
@@ -81,23 +86,25 @@
 
 As long as next_input_bit is returning the bits in a sensible order, we don't
 *have* to wait until the last possible moment to merge in additional bits.
-We can do it 8 bits at a time rather than 1 bit at a time:
-for (i = 0; i < input_bytes; i++) {
-	remainder ^= next_input_byte() << 24;
-	for (j = 0; j < 8; j++) {
-		multiple = (remainder & 0x80000000) ? CRCPOLY : 0;
-		remainder = (remainder << 1) ^ multiple;
-	}
-}
+We can do it 8 bits at a time rather than 1 bit at a time::
 
-Or in little-endian:
-for (i = 0; i < input_bytes; i++) {
-	remainder ^= next_input_byte();
-	for (j = 0; j < 8; j++) {
-		multiple = (remainder & 1) ? CRCPOLY : 0;
-		remainder = (remainder >> 1) ^ multiple;
+	for (i = 0; i < input_bytes; i++) {
+		remainder ^= next_input_byte() << 24;
+		for (j = 0; j < 8; j++) {
+			multiple = (remainder & 0x80000000) ? CRCPOLY : 0;
+			remainder = (remainder << 1) ^ multiple;
+		}
 	}
-}
+
+Or in little-endian::
+
+	for (i = 0; i < input_bytes; i++) {
+		remainder ^= next_input_byte();
+		for (j = 0; j < 8; j++) {
+			multiple = (remainder & 1) ? CRCPOLY : 0;
+			remainder = (remainder >> 1) ^ multiple;
+		}
+	}
 
 If the input is a multiple of 32 bits, you can even XOR in a 32-bit
 word at a time and increase the inner loop count to 32.
diff --git a/Documentation/dcdbas.txt b/Documentation/dcdbas.txt
index e1c52e2..309cc57 100644
--- a/Documentation/dcdbas.txt
+++ b/Documentation/dcdbas.txt
@@ -1,4 +1,9 @@
+===================================
+Dell Systems Management Base Driver
+===================================
+
 Overview
+========
 
 The Dell Systems Management Base Driver provides a sysfs interface for
 systems management software such as Dell OpenManage to perform system
@@ -17,6 +22,7 @@
 
 
 System Management Interrupt
+===========================
 
 On some Dell systems, systems management software must access certain
 management information via a system management interrupt (SMI).  The SMI data
@@ -24,12 +30,12 @@
 buffer is required for the SMI.  The driver maintains the memory required for
 the SMI and provides a way for the application to generate the SMI.
 The driver creates the following sysfs entries for systems management
-software to perform these system management interrupts:
+software to perform these system management interrupts::
 
-/sys/devices/platform/dcdbas/smi_data
-/sys/devices/platform/dcdbas/smi_data_buf_phys_addr
-/sys/devices/platform/dcdbas/smi_data_buf_size
-/sys/devices/platform/dcdbas/smi_request
+	/sys/devices/platform/dcdbas/smi_data
+	/sys/devices/platform/dcdbas/smi_data_buf_phys_addr
+	/sys/devices/platform/dcdbas/smi_data_buf_size
+	/sys/devices/platform/dcdbas/smi_request
 
 Systems management software must perform the following steps to execute
 a SMI using this driver:
@@ -43,6 +49,7 @@
 
 
 Host Control Action
+===================
 
 Dell OpenManage supports a host control feature that allows the administrator
 to perform a power cycle or power off of the system after the OS has finished
@@ -69,12 +76,14 @@
 
 
 Host Control SMI Type
+=====================
 
 The following table shows the value to write to host_control_smi_type to
 perform a power cycle or power off host control action:
 
+=================== =====================
 PowerEdge System    Host Control SMI Type
-----------------    ---------------------
+=================== =====================
       300             HC_SMITYPE_TYPE1
      1300             HC_SMITYPE_TYPE1
      1400             HC_SMITYPE_TYPE2
@@ -87,5 +96,4 @@
      1655MC           HC_SMITYPE_TYPE2
       700             HC_SMITYPE_TYPE3
       750             HC_SMITYPE_TYPE3
-
-
+=================== =====================
diff --git a/Documentation/debugging-via-ohci1394.txt b/Documentation/debugging-via-ohci1394.txt
index 9ff026d..981ad4f 100644
--- a/Documentation/debugging-via-ohci1394.txt
+++ b/Documentation/debugging-via-ohci1394.txt
@@ -1,6 +1,6 @@
-
-  Using physical DMA provided by OHCI-1394 FireWire controllers for debugging
-  ---------------------------------------------------------------------------
+===========================================================================
+Using physical DMA provided by OHCI-1394 FireWire controllers for debugging
+===========================================================================
 
 Introduction
 ------------
@@ -91,10 +91,10 @@
 1) Verify that your hardware is supported:
 
    Load the firewire-ohci module and check your kernel logs.
-   You should see a line similar to
+   You should see a line similar to::
 
-   firewire_ohci 0000:15:00.1: added OHCI v1.0 device as card 2, 4 IR + 4 IT
-   ... contexts, quirks 0x11
+     firewire_ohci 0000:15:00.1: added OHCI v1.0 device as card 2, 4 IR + 4 IT
+     ... contexts, quirks 0x11
 
    when loading the driver. If you have no supported controller, many PCI,
    CardBus and even some Express cards which are fully compliant to OHCI-1394
@@ -113,9 +113,9 @@
    stable connection and has matching connectors (there are small 4-pin and
    large 6-pin FireWire ports) will do.
 
-   If an driver is running on both machines you should see a line like
+   If an driver is running on both machines you should see a line like::
 
-   firewire_core 0000:15:00.1: created device fw1: GUID 00061b0020105917, S400
+     firewire_core 0000:15:00.1: created device fw1: GUID 00061b0020105917, S400
 
    on both machines in the kernel log when the cable is plugged in
    and connects the two machines.
@@ -123,7 +123,7 @@
 3) Test physical DMA using firescope:
 
    On the debug host, make sure that /dev/fw* is accessible,
-   then start firescope:
+   then start firescope::
 
 	$ firescope
 	Port 0 (/dev/fw1) opened, 2 nodes detected
@@ -163,7 +163,7 @@
    host loaded, reboot the debugged machine, booting the kernel which has
    CONFIG_PROVIDE_OHCI1394_DMA_INIT enabled, with the option ohci1394_dma=early.
 
-   Then, on the debugging host, run firescope, for example by using -A:
+   Then, on the debugging host, run firescope, for example by using -A::
 
 	firescope -A System.map-of-debug-target-kernel
 
@@ -178,6 +178,7 @@
 
 Notes
 -----
+
 Documentation and specifications: http://halobates.de/firewire/
 
 FireWire is a trademark of Apple Inc. - for more information please refer to:
diff --git a/Documentation/dell_rbu.txt b/Documentation/dell_rbu.txt
index d262e22..0fdb6aa 100644
--- a/Documentation/dell_rbu.txt
+++ b/Documentation/dell_rbu.txt
@@ -1,18 +1,30 @@
-Purpose:
-Demonstrate the usage of the new open sourced rbu (Remote BIOS Update) driver
+=============================================================
+Usage of the new open sourced rbu (Remote BIOS Update) driver
+=============================================================
+
+Purpose
+=======
+
+Document demonstrating the use of the Dell Remote BIOS Update driver.
 for updating BIOS images on Dell servers and desktops.
 
-Scope:
+Scope
+=====
+
 This document discusses the functionality of the rbu driver only.
 It does not cover the support needed from applications to enable the BIOS to
 update itself with the image downloaded in to the memory.
 
-Overview:
+Overview
+========
+
 This driver works with Dell OpenManage or Dell Update Packages for updating
 the BIOS on Dell servers (starting from servers sold since 1999), desktops
 and notebooks (starting from those sold in 2005).
+
 Please go to  http://support.dell.com register and you can find info on
 OpenManage and Dell Update packages (DUP).
+
 Libsmbios can also be used to update BIOS on Dell systems go to
 http://linux.dell.com/libsmbios/ for details.
 
@@ -22,6 +34,7 @@
 using the driver breaks the image in to packets of fixed sizes and the driver
 would place each packet in contiguous physical memory. The driver also
 maintains a link list of packets for reading them back.
+
 If the dell_rbu driver is unloaded all the allocated memory is freed.
 
 The rbu driver needs to have an application (as mentioned above)which will
@@ -30,28 +43,33 @@
 The user should not unload the rbu driver after downloading the BIOS image
 or updating.
 
-The driver load creates the following directories under the /sys file system.
-/sys/class/firmware/dell_rbu/loading
-/sys/class/firmware/dell_rbu/data
-/sys/devices/platform/dell_rbu/image_type
-/sys/devices/platform/dell_rbu/data
-/sys/devices/platform/dell_rbu/packet_size
+The driver load creates the following directories under the /sys file system::
+
+	/sys/class/firmware/dell_rbu/loading
+	/sys/class/firmware/dell_rbu/data
+	/sys/devices/platform/dell_rbu/image_type
+	/sys/devices/platform/dell_rbu/data
+	/sys/devices/platform/dell_rbu/packet_size
 
 The driver supports two types of update mechanism; monolithic and packetized.
 These update mechanism depends upon the BIOS currently running on the system.
 Most of the Dell systems support a monolithic update where the BIOS image is
 copied to a single contiguous block of physical memory.
+
 In case of packet mechanism the single memory can be broken in smaller chunks
 of contiguous memory and the BIOS image is scattered in these packets.
 
 By default the driver uses monolithic memory for the update type. This can be
 changed to packets during the driver load time by specifying the load
-parameter image_type=packet.  This can also be changed later as below
-echo packet > /sys/devices/platform/dell_rbu/image_type
+parameter image_type=packet.  This can also be changed later as below::
+
+	echo packet > /sys/devices/platform/dell_rbu/image_type
 
 In packet update mode the packet size has to be given before any packets can
-be downloaded. It is done as below
-echo XXXX > /sys/devices/platform/dell_rbu/packet_size
+be downloaded. It is done as below::
+
+	echo XXXX > /sys/devices/platform/dell_rbu/packet_size
+
 In the packet update mechanism, the user needs to create a new file having
 packets of data arranged back to back. It can be done as follows
 The user creates packets header, gets the chunk of the BIOS image and
@@ -60,41 +78,54 @@
 packet, the user needs to create more such packets out of the entire BIOS
 image file and then arrange all these packets back to back in to one single
 file.
+
 This file is then copied to /sys/class/firmware/dell_rbu/data.
 Once this file gets to the driver, the driver extracts packet_size data from
 the file and spreads it across the physical memory in contiguous packet_sized
 space.
+
 This method makes sure that all the packets get to the driver in a single operation.
 
 In monolithic update the user simply get the BIOS image (.hdr file) and copies
 to the data file as is without any change to the BIOS image itself.
 
 Do the steps below to download the BIOS image.
+
 1) echo 1 > /sys/class/firmware/dell_rbu/loading
 2) cp bios_image.hdr /sys/class/firmware/dell_rbu/data
 3) echo 0 > /sys/class/firmware/dell_rbu/loading
 
 The /sys/class/firmware/dell_rbu/ entries will remain till the following is
 done.
-echo -1 > /sys/class/firmware/dell_rbu/loading
+
+::
+
+	echo -1 > /sys/class/firmware/dell_rbu/loading
+
 Until this step is completed the driver cannot be unloaded.
+
 Also echoing either mono, packet or init in to image_type will free up the
 memory allocated by the driver.
 
 If a user by accident executes steps 1 and 3 above without executing step 2;
 it will make the /sys/class/firmware/dell_rbu/ entries disappear.
-The entries can be recreated by doing the following
-echo init > /sys/devices/platform/dell_rbu/image_type
-NOTE: echoing init in image_type does not change it original value.
+
+The entries can be recreated by doing the following::
+
+	echo init > /sys/devices/platform/dell_rbu/image_type
+
+.. note:: echoing init in image_type does not change it original value.
 
 Also the driver provides /sys/devices/platform/dell_rbu/data readonly file to
 read back the image downloaded.
 
-NOTE:
-This driver requires a patch for firmware_class.c which has the modified
-request_firmware_nowait function.
-Also after updating the BIOS image a user mode application needs to execute
-code which sends the BIOS update request to the BIOS. So on the next reboot
-the BIOS knows about the new image downloaded and it updates itself.
-Also don't unload the rbu driver if the image has to be updated.
+.. note::
+
+   This driver requires a patch for firmware_class.c which has the modified
+   request_firmware_nowait function.
+
+   Also after updating the BIOS image a user mode application needs to execute
+   code which sends the BIOS update request to the BIOS. So on the next reboot
+   the BIOS knows about the new image downloaded and it updates itself.
+   Also don't unload the rbu driver if the image has to be updated.
 
diff --git a/Documentation/digsig.txt b/Documentation/digsig.txt
index 3f68288..f6a8902 100644
--- a/Documentation/digsig.txt
+++ b/Documentation/digsig.txt
@@ -1,13 +1,20 @@
+==================================
 Digital Signature Verification API
+==================================
 
-CONTENTS
-
-1. Introduction
-2. API
-3. User-space utilities
+:Author: Dmitry Kasatkin
+:Date: 06.10.2011
 
 
-1. Introduction
+.. CONTENTS
+
+   1. Introduction
+   2. API
+   3. User-space utilities
+
+
+Introduction
+============
 
 Digital signature verification API provides a method to verify digital signature.
 Currently digital signatures are used by the IMA/EVM integrity protection subsystem.
@@ -17,25 +24,25 @@
 memory allocation errors handling, has been refactored according to kernel
 coding style, and checkpatch.pl reported errors and warnings have been fixed.
 
-Public key and signature consist of header and MPIs.
+Public key and signature consist of header and MPIs::
 
-struct pubkey_hdr {
-	uint8_t		version;	/* key format version */
-	time_t		timestamp;	/* key made, always 0 for now */
-	uint8_t		algo;
-	uint8_t		nmpi;
-	char		mpi[0];
-} __packed;
+	struct pubkey_hdr {
+		uint8_t		version;	/* key format version */
+		time_t		timestamp;	/* key made, always 0 for now */
+		uint8_t		algo;
+		uint8_t		nmpi;
+		char		mpi[0];
+	} __packed;
 
-struct signature_hdr {
-	uint8_t		version;	/* signature format version */
-	time_t		timestamp;	/* signature made */
-	uint8_t		algo;
-	uint8_t		hash;
-	uint8_t		keyid[8];
-	uint8_t		nmpi;
-	char		mpi[0];
-} __packed;
+	struct signature_hdr {
+		uint8_t		version;	/* signature format version */
+		time_t		timestamp;	/* signature made */
+		uint8_t		algo;
+		uint8_t		hash;
+		uint8_t		keyid[8];
+		uint8_t		nmpi;
+		char		mpi[0];
+	} __packed;
 
 keyid equals to SHA1[12-19] over the total key content.
 Signature header is used as an input to generate a signature.
@@ -43,31 +50,33 @@
 It protects timestamp from been changed and can be used for rollback
 protection.
 
-2. API
+API
+===
 
-API currently includes only 1 function:
+API currently includes only 1 function::
 
 	digsig_verify() - digital signature verification with public key
 
 
-/**
- * digsig_verify() - digital signature verification with public key
- * @keyring:	keyring to search key in
- * @sig:	digital signature
- * @sigen:	length of the signature
- * @data:	data
- * @datalen:	length of the data
- * @return:	0 on success, -EINVAL otherwise
- *
- * Verifies data integrity against digital signature.
- * Currently only RSA is supported.
- * Normally hash of the content is used as a data for this function.
- *
- */
-int digsig_verify(struct key *keyring, const char *sig, int siglen,
-						const char *data, int datalen);
+	/**
+	* digsig_verify() - digital signature verification with public key
+	* @keyring:	keyring to search key in
+	* @sig:	digital signature
+	* @sigen:	length of the signature
+	* @data:	data
+	* @datalen:	length of the data
+	* @return:	0 on success, -EINVAL otherwise
+	*
+	* Verifies data integrity against digital signature.
+	* Currently only RSA is supported.
+	* Normally hash of the content is used as a data for this function.
+	*
+	*/
+	int digsig_verify(struct key *keyring, const char *sig, int siglen,
+			  const char *data, int datalen);
 
-3. User-space utilities
+User-space utilities
+====================
 
 The signing and key management utilities evm-utils provide functionality
 to generate signatures, to load keys into the kernel keyring.
@@ -75,22 +84,18 @@
 When the key is added to the kernel keyring, the keyid defines the name
 of the key: 5D2B05FC633EE3E8 in the example bellow.
 
-Here is example output of the keyctl utility.
+Here is example output of the keyctl utility::
 
-$ keyctl show
-Session Keyring
-       -3 --alswrv      0     0  keyring: _ses
-603976250 --alswrv      0    -1   \_ keyring: _uid.0
-817777377 --alswrv      0     0       \_ user: kmk
-891974900 --alswrv      0     0       \_ encrypted: evm-key
-170323636 --alswrv      0     0       \_ keyring: _module
-548221616 --alswrv      0     0       \_ keyring: _ima
-128198054 --alswrv      0     0       \_ keyring: _evm
+	$ keyctl show
+	Session Keyring
+	-3 --alswrv      0     0  keyring: _ses
+	603976250 --alswrv      0    -1   \_ keyring: _uid.0
+	817777377 --alswrv      0     0       \_ user: kmk
+	891974900 --alswrv      0     0       \_ encrypted: evm-key
+	170323636 --alswrv      0     0       \_ keyring: _module
+	548221616 --alswrv      0     0       \_ keyring: _ima
+	128198054 --alswrv      0     0       \_ keyring: _evm
 
-$ keyctl list 128198054
-1 key in keyring:
-620789745: --alswrv     0     0 user: 5D2B05FC633EE3E8
-
-
-Dmitry Kasatkin
-06.10.2011
+	$ keyctl list 128198054
+	1 key in keyring:
+	620789745: --alswrv     0     0 user: 5D2B05FC633EE3E8
diff --git a/Documentation/efi-stub.txt b/Documentation/efi-stub.txt
index e157469..41df801 100644
--- a/Documentation/efi-stub.txt
+++ b/Documentation/efi-stub.txt
@@ -1,5 +1,6 @@
-			  The EFI Boot Stub
-		     ---------------------------
+=================
+The EFI Boot Stub
+=================
 
 On the x86 and ARM platforms, a kernel zImage/bzImage can masquerade
 as a PE/COFF image, thereby convincing EFI firmware loaders to load
@@ -25,7 +26,8 @@
 The EFI boot stub is enabled with the CONFIG_EFI_STUB kernel option.
 
 
-**** How to install bzImage.efi
+How to install bzImage.efi
+--------------------------
 
 The bzImage located in arch/x86/boot/bzImage must be copied to the EFI
 System Partition (ESP) and renamed with the extension ".efi". Without
@@ -37,14 +39,16 @@
 should be copied but not necessarily renamed.
 
 
-**** Passing kernel parameters from the EFI shell
+Passing kernel parameters from the EFI shell
+--------------------------------------------
 
-Arguments to the kernel can be passed after bzImage.efi, e.g.
+Arguments to the kernel can be passed after bzImage.efi, e.g.::
 
 	fs0:> bzImage.efi console=ttyS0 root=/dev/sda4
 
 
-**** The "initrd=" option
+The "initrd=" option
+--------------------
 
 Like most boot loaders, the EFI stub allows the user to specify
 multiple initrd files using the "initrd=" option. This is the only EFI
@@ -54,9 +58,9 @@
 The path to the initrd file must be an absolute path from the
 beginning of the ESP, relative path names do not work. Also, the path
 is an EFI-style path and directory elements must be separated with
-backslashes (\). For example, given the following directory layout,
+backslashes (\). For example, given the following directory layout::
 
-fs0:>
+  fs0:>
 	Kernels\
 			bzImage.efi
 			initrd-large.img
@@ -66,7 +70,7 @@
 			initrd-medium.img
 
 to boot with the initrd-large.img file if the current working
-directory is fs0:\Kernels, the following command must be used,
+directory is fs0:\Kernels, the following command must be used::
 
 	fs0:\Kernels> bzImage.efi initrd=\Kernels\initrd-large.img
 
@@ -76,7 +80,8 @@
 is passed to bzImage.efi.
 
 
-**** The "dtb=" option
+The "dtb=" option
+-----------------
 
 For the ARM and arm64 architectures, we also need to be able to provide a
 device tree to the kernel. This is done with the "dtb=" command line option,
diff --git a/Documentation/eisa.txt b/Documentation/eisa.txt
index a55e491..2806e55 100644
--- a/Documentation/eisa.txt
+++ b/Documentation/eisa.txt
@@ -1,4 +1,8 @@
-EISA bus support (Marc Zyngier <maz@wild-wind.fr.eu.org>)
+================
+EISA bus support
+================
+
+:Author: Marc Zyngier <maz@wild-wind.fr.eu.org>
 
 This document groups random notes about porting EISA drivers to the
 new EISA/sysfs API.
@@ -14,168 +18,189 @@
 most EISA drivers are among the oldest Linux drivers so, as you can
 imagine, some dust has settled here over the years.
 
-The EISA infrastructure is made up of three parts :
+The EISA infrastructure is made up of three parts:
 
     - The bus code implements most of the generic code. It is shared
-    among all the architectures that the EISA code runs on. It
-    implements bus probing (detecting EISA cards available on the bus),
-    allocates I/O resources, allows fancy naming through sysfs, and
-    offers interfaces for driver to register.
+      among all the architectures that the EISA code runs on. It
+      implements bus probing (detecting EISA cards available on the bus),
+      allocates I/O resources, allows fancy naming through sysfs, and
+      offers interfaces for driver to register.
 
     - The bus root driver implements the glue between the bus hardware
-    and the generic bus code. It is responsible for discovering the
-    device implementing the bus, and setting it up to be latter probed
-    by the bus code. This can go from something as simple as reserving
-    an I/O region on x86, to the rather more complex, like the hppa
-    EISA code. This is the part to implement in order to have EISA
-    running on an "new" platform.
+      and the generic bus code. It is responsible for discovering the
+      device implementing the bus, and setting it up to be latter probed
+      by the bus code. This can go from something as simple as reserving
+      an I/O region on x86, to the rather more complex, like the hppa
+      EISA code. This is the part to implement in order to have EISA
+      running on an "new" platform.
 
     - The driver offers the bus a list of devices that it manages, and
-    implements the necessary callbacks to probe and release devices
-    whenever told to.
+      implements the necessary callbacks to probe and release devices
+      whenever told to.
 
 Every function/structure below lives in <linux/eisa.h>, which depends
 heavily on <linux/device.h>.
 
-** Bus root driver :
+Bus root driver
+===============
 
-int eisa_root_register (struct eisa_root_device *root);
+::
+
+	int eisa_root_register (struct eisa_root_device *root);
 
 The eisa_root_register function is used to declare a device as the
 root of an EISA bus. The eisa_root_device structure holds a reference
-to this device, as well as some parameters for probing purposes.
+to this device, as well as some parameters for probing purposes::
 
-struct eisa_root_device {
-	struct device   *dev;	 /* Pointer to bridge device */
-	struct resource *res;
-	unsigned long    bus_base_addr;
-	int		 slots;  /* Max slot number */
-	int		 force_probe; /* Probe even when no slot 0 */
-	u64		 dma_mask; /* from bridge device */
-	int              bus_nr; /* Set by eisa_root_register */
-	struct resource  eisa_root_res;	/* ditto */
-};
+	struct eisa_root_device {
+		struct device   *dev;	 /* Pointer to bridge device */
+		struct resource *res;
+		unsigned long    bus_base_addr;
+		int		 slots;  /* Max slot number */
+		int		 force_probe; /* Probe even when no slot 0 */
+		u64		 dma_mask; /* from bridge device */
+		int              bus_nr; /* Set by eisa_root_register */
+		struct resource  eisa_root_res;	/* ditto */
+	};
 
-node          : used for eisa_root_register internal purpose
-dev           : pointer to the root device
-res           : root device I/O resource
-bus_base_addr : slot 0 address on this bus
-slots	      : max slot number to probe
-force_probe   : Probe even when slot 0 is empty (no EISA mainboard)
-dma_mask      : Default DMA mask. Usually the bridge device dma_mask.
-bus_nr	      : unique bus id, set by eisa_root_register
+============= ======================================================
+node          used for eisa_root_register internal purpose
+dev           pointer to the root device
+res           root device I/O resource
+bus_base_addr slot 0 address on this bus
+slots	      max slot number to probe
+force_probe   Probe even when slot 0 is empty (no EISA mainboard)
+dma_mask      Default DMA mask. Usually the bridge device dma_mask.
+bus_nr	      unique bus id, set by eisa_root_register
+============= ======================================================
 
-** Driver :
+Driver
+======
 
-int eisa_driver_register (struct eisa_driver *edrv);
-void eisa_driver_unregister (struct eisa_driver *edrv);
+::
+
+	int eisa_driver_register (struct eisa_driver *edrv);
+	void eisa_driver_unregister (struct eisa_driver *edrv);
 
 Clear enough ?
 
-struct eisa_device_id {
-        char sig[EISA_SIG_LEN];
-	unsigned long driver_data;
-};
+::
 
-struct eisa_driver {
-        const struct eisa_device_id *id_table;
-        struct device_driver         driver;
-};
+	struct eisa_device_id {
+		char sig[EISA_SIG_LEN];
+		unsigned long driver_data;
+	};
 
-id_table	: an array of NULL terminated EISA id strings,
-		  followed by an empty string. Each string can
-		  optionally be paired with a driver-dependent value
-		  (driver_data).
+	struct eisa_driver {
+		const struct eisa_device_id *id_table;
+		struct device_driver         driver;
+	};
 
-driver		: a generic driver, such as described in
-		  Documentation/driver-model/driver.txt. Only .name,
-		  .probe and .remove members are mandatory.
+=============== ====================================================
+id_table	an array of NULL terminated EISA id strings,
+		followed by an empty string. Each string can
+		optionally be paired with a driver-dependent value
+		(driver_data).
 
-An example is the 3c59x driver :
+driver		a generic driver, such as described in
+		Documentation/driver-model/driver.txt. Only .name,
+		.probe and .remove members are mandatory.
+=============== ====================================================
 
-static struct eisa_device_id vortex_eisa_ids[] = {
-	{ "TCM5920", EISA_3C592_OFFSET },
-	{ "TCM5970", EISA_3C597_OFFSET },
-	{ "" }
-};
+An example is the 3c59x driver::
 
-static struct eisa_driver vortex_eisa_driver = {
-	.id_table = vortex_eisa_ids,
-	.driver   = {
-		.name    = "3c59x",
-		.probe   = vortex_eisa_probe,
-		.remove  = vortex_eisa_remove
-	}
-};
+	static struct eisa_device_id vortex_eisa_ids[] = {
+		{ "TCM5920", EISA_3C592_OFFSET },
+		{ "TCM5970", EISA_3C597_OFFSET },
+		{ "" }
+	};
 
-** Device :
+	static struct eisa_driver vortex_eisa_driver = {
+		.id_table = vortex_eisa_ids,
+		.driver   = {
+			.name    = "3c59x",
+			.probe   = vortex_eisa_probe,
+			.remove  = vortex_eisa_remove
+		}
+	};
+
+Device
+======
 
 The sysfs framework calls .probe and .remove functions upon device
 discovery and removal (note that the .remove function is only called
 when driver is built as a module).
 
 Both functions are passed a pointer to a 'struct device', which is
-encapsulated in a 'struct eisa_device' described as follows :
+encapsulated in a 'struct eisa_device' described as follows::
 
-struct eisa_device {
-        struct eisa_device_id id;
-        int                   slot;
-	int                   state;
-	unsigned long         base_addr;
-	struct resource       res[EISA_MAX_RESOURCES];
-	u64                   dma_mask;
-        struct device         dev; /* generic device */
-};
+	struct eisa_device {
+		struct eisa_device_id id;
+		int                   slot;
+		int                   state;
+		unsigned long         base_addr;
+		struct resource       res[EISA_MAX_RESOURCES];
+		u64                   dma_mask;
+		struct device         dev; /* generic device */
+	};
 
-id	: EISA id, as read from device. id.driver_data is set from the
-	  matching driver EISA id.
-slot	: slot number which the device was detected on
-state   : set of flags indicating the state of the device. Current
-	  flags are EISA_CONFIG_ENABLED and EISA_CONFIG_FORCED.
-res	: set of four 256 bytes I/O regions allocated to this device
-dma_mask: DMA mask set from the parent device.
-dev	: generic device (see Documentation/driver-model/device.txt)
+======== ============================================================
+id	 EISA id, as read from device. id.driver_data is set from the
+	 matching driver EISA id.
+slot	 slot number which the device was detected on
+state    set of flags indicating the state of the device. Current
+	 flags are EISA_CONFIG_ENABLED and EISA_CONFIG_FORCED.
+res	 set of four 256 bytes I/O regions allocated to this device
+dma_mask DMA mask set from the parent device.
+dev	 generic device (see Documentation/driver-model/device.txt)
+======== ============================================================
 
 You can get the 'struct eisa_device' from 'struct device' using the
 'to_eisa_device' macro.
 
-** Misc stuff :
+Misc stuff
+==========
 
-void eisa_set_drvdata (struct eisa_device *edev, void *data);
+::
+
+	void eisa_set_drvdata (struct eisa_device *edev, void *data);
 
 Stores data into the device's driver_data area.
 
-void *eisa_get_drvdata (struct eisa_device *edev):
+::
+
+	void *eisa_get_drvdata (struct eisa_device *edev):
 
 Gets the pointer previously stored into the device's driver_data area.
 
-int eisa_get_region_index (void *addr);
+::
+
+	int eisa_get_region_index (void *addr);
 
 Returns the region number (0 <= x < EISA_MAX_RESOURCES) of a given
 address.
 
-** Kernel parameters :
+Kernel parameters
+=================
 
-eisa_bus.enable_dev :
+eisa_bus.enable_dev
+	A comma-separated list of slots to be enabled, even if the firmware
+	set the card as disabled. The driver must be able to properly
+	initialize the device in such conditions.
 
-A comma-separated list of slots to be enabled, even if the firmware
-set the card as disabled. The driver must be able to properly
-initialize the device in such conditions.
+eisa_bus.disable_dev
+	A comma-separated list of slots to be enabled, even if the firmware
+	set the card as enabled. The driver won't be called to handle this
+	device.
 
-eisa_bus.disable_dev :
+virtual_root.force_probe
+	Force the probing code to probe EISA slots even when it cannot find an
+	EISA compliant mainboard (nothing appears on slot 0). Defaults to 0
+	(don't force), and set to 1 (force probing) when either
+	CONFIG_ALPHA_JENSEN or CONFIG_EISA_VLB_PRIMING are set.
 
-A comma-separated list of slots to be enabled, even if the firmware
-set the card as enabled. The driver won't be called to handle this
-device.
-
-virtual_root.force_probe :
-
-Force the probing code to probe EISA slots even when it cannot find an
-EISA compliant mainboard (nothing appears on slot 0). Defaults to 0
-(don't force), and set to 1 (force probing) when either
-CONFIG_ALPHA_JENSEN or CONFIG_EISA_VLB_PRIMING are set.
-
-** Random notes :
+Random notes
+============
 
 Converting an EISA driver to the new API mostly involves *deleting*
 code (since probing is now in the core EISA code). Unfortunately, most
@@ -194,9 +219,11 @@
 For example, switching your favorite EISA SCSI card to the "hotplug"
 model is "the right thing"(tm).
 
-** Thanks :
+Thanks
+======
 
-I'd like to thank the following people for their help :
+I'd like to thank the following people for their help:
+
 - Xavier Benigni for lending me a wonderful Alpha Jensen,
 - James Bottomley, Jeff Garzik for getting this stuff into the kernel,
 - Andries Brouwer for contributing numerous EISA ids,
diff --git a/Documentation/flexible-arrays.txt b/Documentation/flexible-arrays.txt
index df904ae..a0f2989 100644
--- a/Documentation/flexible-arrays.txt
+++ b/Documentation/flexible-arrays.txt
@@ -1,6 +1,9 @@
+===================================
 Using flexible arrays in the kernel
-Last updated for 2.6.32
-Jonathan Corbet <corbet@lwn.net>
+===================================
+
+:Updated: Last updated for 2.6.32
+:Author: Jonathan Corbet <corbet@lwn.net>
 
 Large contiguous memory allocations can be unreliable in the Linux kernel.
 Kernel programmers will sometimes respond to this problem by allocating
@@ -26,7 +29,7 @@
 locking at all; if concurrent access to an array is possible, then the
 caller must arrange for appropriate mutual exclusion.
 
-The creation of a flexible array is done with:
+The creation of a flexible array is done with::
 
     #include <linux/flex_array.h>
 
@@ -40,14 +43,14 @@
 the current code, using flags to ask for high memory is likely to lead to
 notably unpleasant side effects.
 
-It is also possible to define flexible arrays at compile time with:
+It is also possible to define flexible arrays at compile time with::
 
     DEFINE_FLEX_ARRAY(name, element_size, total);
 
 This macro will result in a definition of an array with the given name; the
 element size and total will be checked for validity at compile time.
 
-Storing data into a flexible array is accomplished with a call to:
+Storing data into a flexible array is accomplished with a call to::
 
     int flex_array_put(struct flex_array *array, unsigned int element_nr,
     		       void *src, gfp_t flags);
@@ -63,7 +66,7 @@
 memory allocator would be a bad thing.  That can be avoided by using
 GFP_ATOMIC for the flags value, but, often, there is a better way.  The
 trick is to ensure that any needed memory allocations are done before
-entering atomic context, using:
+entering atomic context, using::
 
     int flex_array_prealloc(struct flex_array *array, unsigned int start,
 			    unsigned int nr_elements, gfp_t flags);
@@ -73,7 +76,7 @@
 flex_array_put() call on an element in that range is guaranteed not to
 block.
 
-Getting data back out of the array is done with:
+Getting data back out of the array is done with::
 
     void *flex_array_get(struct flex_array *fa, unsigned int element_nr);
 
@@ -89,7 +92,7 @@
 Note that, if array elements are allocated with __GFP_ZERO, they will be
 initialized to zero and this poisoning will not happen.
 
-Individual elements in the array can be cleared with:
+Individual elements in the array can be cleared with::
 
     int flex_array_clear(struct flex_array *array, unsigned int element_nr);
 
@@ -97,7 +100,7 @@
 zero.  If storage for the indicated element is not allocated for the array,
 flex_array_clear() will return -EINVAL instead.  Note that clearing an
 element does not release the storage associated with it; to reduce the
-allocated size of an array, call:
+allocated size of an array, call::
 
     int flex_array_shrink(struct flex_array *array);
 
@@ -106,12 +109,12 @@
 FLEX_ARRAY_FREE bytes, so (1) it can be expensive, and (2) it will not work
 if the array's pages are allocated with __GFP_ZERO.
 
-It is possible to remove all elements of an array with a call to:
+It is possible to remove all elements of an array with a call to::
 
     void flex_array_free_parts(struct flex_array *array);
 
 This call frees all elements, but leaves the array itself in place.
-Freeing the entire array is done with:
+Freeing the entire array is done with::
 
     void flex_array_free(struct flex_array *array);
 
diff --git a/Documentation/futex-requeue-pi.txt b/Documentation/futex-requeue-pi.txt
index 77b36f5..14ab578 100644
--- a/Documentation/futex-requeue-pi.txt
+++ b/Documentation/futex-requeue-pi.txt
@@ -1,5 +1,6 @@
+================
 Futex Requeue PI
-----------------
+================
 
 Requeueing of tasks from a non-PI futex to a PI futex requires
 special handling in order to ensure the underlying rt_mutex is never
@@ -20,28 +21,28 @@
 rest to the natural wakeup inherent in unlocking the mutex
 associated with the condvar.
 
-Consider the simplified glibc calls:
+Consider the simplified glibc calls::
 
-/* caller must lock mutex */
-pthread_cond_wait(cond, mutex)
-{
-	lock(cond->__data.__lock);
-	unlock(mutex);
-	do {
-	   unlock(cond->__data.__lock);
-	   futex_wait(cond->__data.__futex);
-	   lock(cond->__data.__lock);
-	} while(...)
-	unlock(cond->__data.__lock);
-	lock(mutex);
-}
+	/* caller must lock mutex */
+	pthread_cond_wait(cond, mutex)
+	{
+		lock(cond->__data.__lock);
+		unlock(mutex);
+		do {
+		unlock(cond->__data.__lock);
+		futex_wait(cond->__data.__futex);
+		lock(cond->__data.__lock);
+		} while(...)
+		unlock(cond->__data.__lock);
+		lock(mutex);
+	}
 
-pthread_cond_broadcast(cond)
-{
-	lock(cond->__data.__lock);
-	unlock(cond->__data.__lock);
-	futex_requeue(cond->data.__futex, cond->mutex);
-}
+	pthread_cond_broadcast(cond)
+	{
+		lock(cond->__data.__lock);
+		unlock(cond->__data.__lock);
+		futex_requeue(cond->data.__futex, cond->mutex);
+	}
 
 Once pthread_cond_broadcast() requeues the tasks, the cond->mutex
 has waiters. Note that pthread_cond_wait() attempts to lock the
@@ -53,29 +54,29 @@
 be able to requeue tasks to PI futexes.  This support implies that
 upon a successful futex_wait system call, the caller would return to
 user space already holding the PI futex.  The glibc implementation
-would be modified as follows:
+would be modified as follows::
 
 
-/* caller must lock mutex */
-pthread_cond_wait_pi(cond, mutex)
-{
-	lock(cond->__data.__lock);
-	unlock(mutex);
-	do {
-	   unlock(cond->__data.__lock);
-	   futex_wait_requeue_pi(cond->__data.__futex);
-	   lock(cond->__data.__lock);
-	} while(...)
-	unlock(cond->__data.__lock);
-        /* the kernel acquired the mutex for us */
-}
+	/* caller must lock mutex */
+	pthread_cond_wait_pi(cond, mutex)
+	{
+		lock(cond->__data.__lock);
+		unlock(mutex);
+		do {
+		unlock(cond->__data.__lock);
+		futex_wait_requeue_pi(cond->__data.__futex);
+		lock(cond->__data.__lock);
+		} while(...)
+		unlock(cond->__data.__lock);
+		/* the kernel acquired the mutex for us */
+	}
 
-pthread_cond_broadcast_pi(cond)
-{
-	lock(cond->__data.__lock);
-	unlock(cond->__data.__lock);
-	futex_requeue_pi(cond->data.__futex, cond->mutex);
-}
+	pthread_cond_broadcast_pi(cond)
+	{
+		lock(cond->__data.__lock);
+		unlock(cond->__data.__lock);
+		futex_requeue_pi(cond->data.__futex, cond->mutex);
+	}
 
 The actual glibc implementation will likely test for PI and make the
 necessary changes inside the existing calls rather than creating new
diff --git a/Documentation/gcc-plugins.txt b/Documentation/gcc-plugins.txt
index 433eaef..8502f24 100644
--- a/Documentation/gcc-plugins.txt
+++ b/Documentation/gcc-plugins.txt
@@ -1,14 +1,15 @@
+=========================
 GCC plugin infrastructure
 =========================
 
 
-1. Introduction
-===============
+Introduction
+============
 
 GCC plugins are loadable modules that provide extra features to the
-compiler [1]. They are useful for runtime instrumentation and static analysis.
+compiler [1]_. They are useful for runtime instrumentation and static analysis.
 We can analyse, change and add further code during compilation via
-callbacks [2], GIMPLE [3], IPA [4] and RTL passes [5].
+callbacks [2]_, GIMPLE [3]_, IPA [4]_ and RTL passes [5]_.
 
 The GCC plugin infrastructure of the kernel supports all gcc versions from
 4.5 to 6.0, building out-of-tree modules, cross-compilation and building in a
@@ -21,56 +22,61 @@
 Currently the GCC plugin infrastructure supports only the x86, arm, arm64 and
 powerpc architectures.
 
-This infrastructure was ported from grsecurity [6] and PaX [7].
+This infrastructure was ported from grsecurity [6]_ and PaX [7]_.
 
 --
-[1] https://gcc.gnu.org/onlinedocs/gccint/Plugins.html
-[2] https://gcc.gnu.org/onlinedocs/gccint/Plugin-API.html#Plugin-API
-[3] https://gcc.gnu.org/onlinedocs/gccint/GIMPLE.html
-[4] https://gcc.gnu.org/onlinedocs/gccint/IPA.html
-[5] https://gcc.gnu.org/onlinedocs/gccint/RTL.html
-[6] https://grsecurity.net/
-[7] https://pax.grsecurity.net/
+
+.. [1] https://gcc.gnu.org/onlinedocs/gccint/Plugins.html
+.. [2] https://gcc.gnu.org/onlinedocs/gccint/Plugin-API.html#Plugin-API
+.. [3] https://gcc.gnu.org/onlinedocs/gccint/GIMPLE.html
+.. [4] https://gcc.gnu.org/onlinedocs/gccint/IPA.html
+.. [5] https://gcc.gnu.org/onlinedocs/gccint/RTL.html
+.. [6] https://grsecurity.net/
+.. [7] https://pax.grsecurity.net/
 
 
-2. Files
-========
+Files
+=====
 
-$(src)/scripts/gcc-plugins
+**$(src)/scripts/gcc-plugins**
+
 	This is the directory of the GCC plugins.
 
-$(src)/scripts/gcc-plugins/gcc-common.h
+**$(src)/scripts/gcc-plugins/gcc-common.h**
+
 	This is a compatibility header for GCC plugins.
 	It should be always included instead of individual gcc headers.
 
-$(src)/scripts/gcc-plugin.sh
+**$(src)/scripts/gcc-plugin.sh**
+
 	This script checks the availability of the included headers in
 	gcc-common.h and chooses the proper host compiler to build the plugins
 	(gcc-4.7 can be built by either gcc or g++).
 
-$(src)/scripts/gcc-plugins/gcc-generate-gimple-pass.h
-$(src)/scripts/gcc-plugins/gcc-generate-ipa-pass.h
-$(src)/scripts/gcc-plugins/gcc-generate-simple_ipa-pass.h
-$(src)/scripts/gcc-plugins/gcc-generate-rtl-pass.h
+**$(src)/scripts/gcc-plugins/gcc-generate-gimple-pass.h,
+$(src)/scripts/gcc-plugins/gcc-generate-ipa-pass.h,
+$(src)/scripts/gcc-plugins/gcc-generate-simple_ipa-pass.h,
+$(src)/scripts/gcc-plugins/gcc-generate-rtl-pass.h**
+
 	These headers automatically generate the registration structures for
 	GIMPLE, SIMPLE_IPA, IPA and RTL passes. They support all gcc versions
 	from 4.5 to 6.0.
 	They should be preferred to creating the structures by hand.
 
 
-3. Usage
-========
+Usage
+=====
 
 You must install the gcc plugin headers for your gcc version,
-e.g., on Ubuntu for gcc-4.9:
+e.g., on Ubuntu for gcc-4.9::
 
 	apt-get install gcc-4.9-plugin-dev
 
-Enable a GCC plugin based feature in the kernel config:
+Enable a GCC plugin based feature in the kernel config::
 
 	CONFIG_GCC_PLUGIN_CYC_COMPLEXITY = y
 
-To compile only the plugin(s):
+To compile only the plugin(s)::
 
 	make gcc-plugins
 
diff --git a/Documentation/highuid.txt b/Documentation/highuid.txt
index 6bad6f1..6ee7046 100644
--- a/Documentation/highuid.txt
+++ b/Documentation/highuid.txt
@@ -1,4 +1,9 @@
-Notes on the change from 16-bit UIDs to 32-bit UIDs:
+===================================================
+Notes on the change from 16-bit UIDs to 32-bit UIDs
+===================================================
+
+:Author: Chris Wing <wingc@umich.edu>
+:Last updated: January 11, 2000
 
 - kernel code MUST take into account __kernel_uid_t and __kernel_uid32_t
   when communicating between user and kernel space in an ioctl or data
@@ -28,30 +33,34 @@
   uses the 32-bit UID system calls properly otherwise.
 
   This affects at least:
-	iBCS on Intel
 
-	sparc32 emulation on sparc64
-	(need to support whatever new 32-bit UID system calls are added to
-	sparc32)
+	- iBCS on Intel
+
+	- sparc32 emulation on sparc64
+	  (need to support whatever new 32-bit UID system calls are added to
+	  sparc32)
 
 - Validate that all filesystems behave properly.
 
   At present, 32-bit UIDs _should_ work for:
-	ext2
-	ufs
-	isofs
-	nfs
-	coda
-	udf
+
+	- ext2
+	- ufs
+	- isofs
+	- nfs
+	- coda
+	- udf
 
   Ioctl() fixups have been made for:
-	ncpfs
-	smbfs
+
+	- ncpfs
+	- smbfs
 
   Filesystems with simple fixups to prevent 16-bit UID wraparound:
-	minix
-	sysv
-	qnx4
+
+	- minix
+	- sysv
+	- qnx4
 
   Other filesystems have not been checked yet.
 
@@ -69,9 +78,3 @@
 - make sure that the UID mapping feature of AX25 networking works properly
   (it should be safe because it's always used a 32-bit integer to
   communicate between user and kernel)
-
-
-Chris Wing
-wingc@umich.edu
-
-last updated: January 11, 2000
diff --git a/Documentation/hw_random.txt b/Documentation/hw_random.txt
index fce1634..121de96 100644
--- a/Documentation/hw_random.txt
+++ b/Documentation/hw_random.txt
@@ -1,90 +1,105 @@
-Introduction:
+==========================================================
+Linux support for random number generator in i8xx chipsets
+==========================================================
 
-	The hw_random framework is software that makes use of a
-	special hardware feature on your CPU or motherboard,
-	a Random Number Generator (RNG).  The software has two parts:
-	a core providing the /dev/hwrng character device and its
-	sysfs support, plus a hardware-specific driver that plugs
-	into that core.
+Introduction
+============
 
-	To make the most effective use of these mechanisms, you
-	should download the support software as well.  Download the
-	latest version of the "rng-tools" package from the
-	hw_random driver's official Web site:
+The hw_random framework is software that makes use of a
+special hardware feature on your CPU or motherboard,
+a Random Number Generator (RNG).  The software has two parts:
+a core providing the /dev/hwrng character device and its
+sysfs support, plus a hardware-specific driver that plugs
+into that core.
 
-		http://sourceforge.net/projects/gkernel/
+To make the most effective use of these mechanisms, you
+should download the support software as well.  Download the
+latest version of the "rng-tools" package from the
+hw_random driver's official Web site:
 
-	Those tools use /dev/hwrng to fill the kernel entropy pool,
-	which is used internally and exported by the /dev/urandom and
-	/dev/random special files.
+	http://sourceforge.net/projects/gkernel/
 
-Theory of operation:
+Those tools use /dev/hwrng to fill the kernel entropy pool,
+which is used internally and exported by the /dev/urandom and
+/dev/random special files.
 
-	CHARACTER DEVICE.  Using the standard open()
-	and read() system calls, you can read random data from
-	the hardware RNG device.  This data is NOT CHECKED by any
-	fitness tests, and could potentially be bogus (if the
-	hardware is faulty or has been tampered with).  Data is only
-	output if the hardware "has-data" flag is set, but nevertheless
-	a security-conscious person would run fitness tests on the
-	data before assuming it is truly random.
+Theory of operation
+===================
 
-	The rng-tools package uses such tests in "rngd", and lets you
-	run them by hand with a "rngtest" utility.
+CHARACTER DEVICE.  Using the standard open()
+and read() system calls, you can read random data from
+the hardware RNG device.  This data is NOT CHECKED by any
+fitness tests, and could potentially be bogus (if the
+hardware is faulty or has been tampered with).  Data is only
+output if the hardware "has-data" flag is set, but nevertheless
+a security-conscious person would run fitness tests on the
+data before assuming it is truly random.
 
-	/dev/hwrng is char device major 10, minor 183.
+The rng-tools package uses such tests in "rngd", and lets you
+run them by hand with a "rngtest" utility.
 
-	CLASS DEVICE.  There is a /sys/class/misc/hw_random node with
-	two unique attributes, "rng_available" and "rng_current".  The
-	"rng_available" attribute lists the hardware-specific drivers
-	available, while "rng_current" lists the one which is currently
-	connected to /dev/hwrng.  If your system has more than one
-	RNG available, you may change the one used by writing a name from
-	the list in "rng_available" into "rng_current".
+/dev/hwrng is char device major 10, minor 183.
+
+CLASS DEVICE.  There is a /sys/class/misc/hw_random node with
+two unique attributes, "rng_available" and "rng_current".  The
+"rng_available" attribute lists the hardware-specific drivers
+available, while "rng_current" lists the one which is currently
+connected to /dev/hwrng.  If your system has more than one
+RNG available, you may change the one used by writing a name from
+the list in "rng_available" into "rng_current".
 
 ==========================================================================
 
-	Hardware driver for Intel/AMD/VIA Random Number Generators (RNG)
-	Copyright 2000,2001 Jeff Garzik <jgarzik@pobox.com>
-	Copyright 2000,2001 Philipp Rumpf <prumpf@mandrakesoft.com>
+
+Hardware driver for Intel/AMD/VIA Random Number Generators (RNG)
+	- Copyright 2000,2001 Jeff Garzik <jgarzik@pobox.com>
+	- Copyright 2000,2001 Philipp Rumpf <prumpf@mandrakesoft.com>
 
 
-About the Intel RNG hardware, from the firmware hub datasheet:
+About the Intel RNG hardware, from the firmware hub datasheet
+=============================================================
 
-	The Firmware Hub integrates a Random Number Generator (RNG)
-	using thermal noise generated from inherently random quantum
-	mechanical properties of silicon. When not generating new random
-	bits the RNG circuitry will enter a low power state. Intel will
-	provide a binary software driver to give third party software
-	access to our RNG for use as a security feature. At this time,
-	the RNG is only to be used with a system in an OS-present state.
+The Firmware Hub integrates a Random Number Generator (RNG)
+using thermal noise generated from inherently random quantum
+mechanical properties of silicon. When not generating new random
+bits the RNG circuitry will enter a low power state. Intel will
+provide a binary software driver to give third party software
+access to our RNG for use as a security feature. At this time,
+the RNG is only to be used with a system in an OS-present state.
 
-Intel RNG Driver notes:
+Intel RNG Driver notes
+======================
 
-	* FIXME: support poll(2)
+FIXME: support poll(2)
 
-	NOTE: request_mem_region was removed, for three reasons:
-	1) Only one RNG is supported by this driver, 2) The location
-	used by the RNG is a fixed location in MMIO-addressable memory,
+.. note::
+
+	request_mem_region was removed, for three reasons:
+
+	1) Only one RNG is supported by this driver;
+	2) The location used by the RNG is a fixed location in
+	   MMIO-addressable memory;
 	3) users with properly working BIOS e820 handling will always
-	have the region in which the RNG is located reserved, so
-	request_mem_region calls always fail for proper setups.
-	However, for people who use mem=XX, BIOS e820 information is
-	-not- in /proc/iomem, and request_mem_region(RNG_ADDR) can
-	succeed.
+	   have the region in which the RNG is located reserved, so
+	   request_mem_region calls always fail for proper setups.
+	   However, for people who use mem=XX, BIOS e820 information is
+	   **not** in /proc/iomem, and request_mem_region(RNG_ADDR) can
+	   succeed.
 
-Driver details:
+Driver details
+==============
 
-	Based on:
+Based on:
 	Intel 82802AB/82802AC Firmware Hub (FWH) Datasheet
-		May 1999 Order Number: 290658-002 R
+	May 1999 Order Number: 290658-002 R
 
-	Intel 82802 Firmware Hub: Random Number Generator
+Intel 82802 Firmware Hub:
+	Random Number Generator
 	Programmer's Reference Manual
-		December 1999 Order Number: 298029-001 R
+	December 1999 Order Number: 298029-001 R
 
-	Intel 82802 Firmware HUB Random Number Generator Driver
+Intel 82802 Firmware HUB Random Number Generator Driver
 	Copyright (c) 2000 Matt Sottek <msottek@quiknet.com>
 
-	Special thanks to Matt Sottek.  I did the "guts", he
-	did the "brains" and all the testing.
+Special thanks to Matt Sottek.  I did the "guts", he
+did the "brains" and all the testing.
diff --git a/Documentation/hwspinlock.txt b/Documentation/hwspinlock.txt
index 61c1ee9..ed640a2 100644
--- a/Documentation/hwspinlock.txt
+++ b/Documentation/hwspinlock.txt
@@ -1,6 +1,9 @@
+===========================
 Hardware Spinlock Framework
+===========================
 
-1. Introduction
+Introduction
+============
 
 Hardware spinlock modules provide hardware assistance for synchronization
 and mutual exclusion between heterogeneous processors and those not operating
@@ -32,286 +35,370 @@
 A common hwspinlock interface makes it possible to have generic, platform-
 independent, drivers.
 
-2. User API
+User API
+========
+
+::
 
   struct hwspinlock *hwspin_lock_request(void);
-   - dynamically assign an hwspinlock and return its address, or NULL
-     in case an unused hwspinlock isn't available. Users of this
-     API will usually want to communicate the lock's id to the remote core
-     before it can be used to achieve synchronization.
-     Should be called from a process context (might sleep).
+
+Dynamically assign an hwspinlock and return its address, or NULL
+in case an unused hwspinlock isn't available. Users of this
+API will usually want to communicate the lock's id to the remote core
+before it can be used to achieve synchronization.
+
+Should be called from a process context (might sleep).
+
+::
 
   struct hwspinlock *hwspin_lock_request_specific(unsigned int id);
-   - assign a specific hwspinlock id and return its address, or NULL
-     if that hwspinlock is already in use. Usually board code will
-     be calling this function in order to reserve specific hwspinlock
-     ids for predefined purposes.
-     Should be called from a process context (might sleep).
+
+Assign a specific hwspinlock id and return its address, or NULL
+if that hwspinlock is already in use. Usually board code will
+be calling this function in order to reserve specific hwspinlock
+ids for predefined purposes.
+
+Should be called from a process context (might sleep).
+
+::
 
   int of_hwspin_lock_get_id(struct device_node *np, int index);
-   - retrieve the global lock id for an OF phandle-based specific lock.
-     This function provides a means for DT users of a hwspinlock module
-     to get the global lock id of a specific hwspinlock, so that it can
-     be requested using the normal hwspin_lock_request_specific() API.
-     The function returns a lock id number on success, -EPROBE_DEFER if
-     the hwspinlock device is not yet registered with the core, or other
-     error values.
-     Should be called from a process context (might sleep).
+
+Retrieve the global lock id for an OF phandle-based specific lock.
+This function provides a means for DT users of a hwspinlock module
+to get the global lock id of a specific hwspinlock, so that it can
+be requested using the normal hwspin_lock_request_specific() API.
+
+The function returns a lock id number on success, -EPROBE_DEFER if
+the hwspinlock device is not yet registered with the core, or other
+error values.
+
+Should be called from a process context (might sleep).
+
+::
 
   int hwspin_lock_free(struct hwspinlock *hwlock);
-   - free a previously-assigned hwspinlock; returns 0 on success, or an
-     appropriate error code on failure (e.g. -EINVAL if the hwspinlock
-     is already free).
-     Should be called from a process context (might sleep).
+
+Free a previously-assigned hwspinlock; returns 0 on success, or an
+appropriate error code on failure (e.g. -EINVAL if the hwspinlock
+is already free).
+
+Should be called from a process context (might sleep).
+
+::
 
   int hwspin_lock_timeout(struct hwspinlock *hwlock, unsigned int timeout);
-   - lock a previously-assigned hwspinlock with a timeout limit (specified in
-     msecs). If the hwspinlock is already taken, the function will busy loop
-     waiting for it to be released, but give up when the timeout elapses.
-     Upon a successful return from this function, preemption is disabled so
-     the caller must not sleep, and is advised to release the hwspinlock as
-     soon as possible, in order to minimize remote cores polling on the
-     hardware interconnect.
-     Returns 0 when successful and an appropriate error code otherwise (most
-     notably -ETIMEDOUT if the hwspinlock is still busy after timeout msecs).
-     The function will never sleep.
+
+Lock a previously-assigned hwspinlock with a timeout limit (specified in
+msecs). If the hwspinlock is already taken, the function will busy loop
+waiting for it to be released, but give up when the timeout elapses.
+Upon a successful return from this function, preemption is disabled so
+the caller must not sleep, and is advised to release the hwspinlock as
+soon as possible, in order to minimize remote cores polling on the
+hardware interconnect.
+
+Returns 0 when successful and an appropriate error code otherwise (most
+notably -ETIMEDOUT if the hwspinlock is still busy after timeout msecs).
+The function will never sleep.
+
+::
 
   int hwspin_lock_timeout_irq(struct hwspinlock *hwlock, unsigned int timeout);
-   - lock a previously-assigned hwspinlock with a timeout limit (specified in
-     msecs). If the hwspinlock is already taken, the function will busy loop
-     waiting for it to be released, but give up when the timeout elapses.
-     Upon a successful return from this function, preemption and the local
-     interrupts are disabled, so the caller must not sleep, and is advised to
-     release the hwspinlock as soon as possible.
-     Returns 0 when successful and an appropriate error code otherwise (most
-     notably -ETIMEDOUT if the hwspinlock is still busy after timeout msecs).
-     The function will never sleep.
+
+Lock a previously-assigned hwspinlock with a timeout limit (specified in
+msecs). If the hwspinlock is already taken, the function will busy loop
+waiting for it to be released, but give up when the timeout elapses.
+Upon a successful return from this function, preemption and the local
+interrupts are disabled, so the caller must not sleep, and is advised to
+release the hwspinlock as soon as possible.
+
+Returns 0 when successful and an appropriate error code otherwise (most
+notably -ETIMEDOUT if the hwspinlock is still busy after timeout msecs).
+The function will never sleep.
+
+::
 
   int hwspin_lock_timeout_irqsave(struct hwspinlock *hwlock, unsigned int to,
-							unsigned long *flags);
-   - lock a previously-assigned hwspinlock with a timeout limit (specified in
-     msecs). If the hwspinlock is already taken, the function will busy loop
-     waiting for it to be released, but give up when the timeout elapses.
-     Upon a successful return from this function, preemption is disabled,
-     local interrupts are disabled and their previous state is saved at the
-     given flags placeholder. The caller must not sleep, and is advised to
-     release the hwspinlock as soon as possible.
-     Returns 0 when successful and an appropriate error code otherwise (most
-     notably -ETIMEDOUT if the hwspinlock is still busy after timeout msecs).
-     The function will never sleep.
+				  unsigned long *flags);
+
+Lock a previously-assigned hwspinlock with a timeout limit (specified in
+msecs). If the hwspinlock is already taken, the function will busy loop
+waiting for it to be released, but give up when the timeout elapses.
+Upon a successful return from this function, preemption is disabled,
+local interrupts are disabled and their previous state is saved at the
+given flags placeholder. The caller must not sleep, and is advised to
+release the hwspinlock as soon as possible.
+
+Returns 0 when successful and an appropriate error code otherwise (most
+notably -ETIMEDOUT if the hwspinlock is still busy after timeout msecs).
+
+The function will never sleep.
+
+::
 
   int hwspin_trylock(struct hwspinlock *hwlock);
-   - attempt to lock a previously-assigned hwspinlock, but immediately fail if
-     it is already taken.
-     Upon a successful return from this function, preemption is disabled so
-     caller must not sleep, and is advised to release the hwspinlock as soon as
-     possible, in order to minimize remote cores polling on the hardware
-     interconnect.
-     Returns 0 on success and an appropriate error code otherwise (most
-     notably -EBUSY if the hwspinlock was already taken).
-     The function will never sleep.
+
+
+Attempt to lock a previously-assigned hwspinlock, but immediately fail if
+it is already taken.
+
+Upon a successful return from this function, preemption is disabled so
+caller must not sleep, and is advised to release the hwspinlock as soon as
+possible, in order to minimize remote cores polling on the hardware
+interconnect.
+
+Returns 0 on success and an appropriate error code otherwise (most
+notably -EBUSY if the hwspinlock was already taken).
+The function will never sleep.
+
+::
 
   int hwspin_trylock_irq(struct hwspinlock *hwlock);
-   - attempt to lock a previously-assigned hwspinlock, but immediately fail if
-     it is already taken.
-     Upon a successful return from this function, preemption and the local
-     interrupts are disabled so caller must not sleep, and is advised to
-     release the hwspinlock as soon as possible.
-     Returns 0 on success and an appropriate error code otherwise (most
-     notably -EBUSY if the hwspinlock was already taken).
-     The function will never sleep.
+
+
+Attempt to lock a previously-assigned hwspinlock, but immediately fail if
+it is already taken.
+
+Upon a successful return from this function, preemption and the local
+interrupts are disabled so caller must not sleep, and is advised to
+release the hwspinlock as soon as possible.
+
+Returns 0 on success and an appropriate error code otherwise (most
+notably -EBUSY if the hwspinlock was already taken).
+
+The function will never sleep.
+
+::
 
   int hwspin_trylock_irqsave(struct hwspinlock *hwlock, unsigned long *flags);
-   - attempt to lock a previously-assigned hwspinlock, but immediately fail if
-     it is already taken.
-     Upon a successful return from this function, preemption is disabled,
-     the local interrupts are disabled and their previous state is saved
-     at the given flags placeholder. The caller must not sleep, and is advised
-     to release the hwspinlock as soon as possible.
-     Returns 0 on success and an appropriate error code otherwise (most
-     notably -EBUSY if the hwspinlock was already taken).
-     The function will never sleep.
+
+Attempt to lock a previously-assigned hwspinlock, but immediately fail if
+it is already taken.
+
+Upon a successful return from this function, preemption is disabled,
+the local interrupts are disabled and their previous state is saved
+at the given flags placeholder. The caller must not sleep, and is advised
+to release the hwspinlock as soon as possible.
+
+Returns 0 on success and an appropriate error code otherwise (most
+notably -EBUSY if the hwspinlock was already taken).
+The function will never sleep.
+
+::
 
   void hwspin_unlock(struct hwspinlock *hwlock);
-   - unlock a previously-locked hwspinlock. Always succeed, and can be called
-     from any context (the function never sleeps). Note: code should _never_
-     unlock an hwspinlock which is already unlocked (there is no protection
-     against this).
+
+Unlock a previously-locked hwspinlock. Always succeed, and can be called
+from any context (the function never sleeps).
+
+.. note::
+
+  code should **never** unlock an hwspinlock which is already unlocked
+  (there is no protection against this).
+
+::
 
   void hwspin_unlock_irq(struct hwspinlock *hwlock);
-   - unlock a previously-locked hwspinlock and enable local interrupts.
-     The caller should _never_ unlock an hwspinlock which is already unlocked.
-     Doing so is considered a bug (there is no protection against this).
-     Upon a successful return from this function, preemption and local
-     interrupts are enabled. This function will never sleep.
+
+Unlock a previously-locked hwspinlock and enable local interrupts.
+The caller should **never** unlock an hwspinlock which is already unlocked.
+
+Doing so is considered a bug (there is no protection against this).
+Upon a successful return from this function, preemption and local
+interrupts are enabled. This function will never sleep.
+
+::
 
   void
   hwspin_unlock_irqrestore(struct hwspinlock *hwlock, unsigned long *flags);
-   - unlock a previously-locked hwspinlock.
-     The caller should _never_ unlock an hwspinlock which is already unlocked.
-     Doing so is considered a bug (there is no protection against this).
-     Upon a successful return from this function, preemption is reenabled,
-     and the state of the local interrupts is restored to the state saved at
-     the given flags. This function will never sleep.
+
+Unlock a previously-locked hwspinlock.
+
+The caller should **never** unlock an hwspinlock which is already unlocked.
+Doing so is considered a bug (there is no protection against this).
+Upon a successful return from this function, preemption is reenabled,
+and the state of the local interrupts is restored to the state saved at
+the given flags. This function will never sleep.
+
+::
 
   int hwspin_lock_get_id(struct hwspinlock *hwlock);
-   - retrieve id number of a given hwspinlock. This is needed when an
-     hwspinlock is dynamically assigned: before it can be used to achieve
-     mutual exclusion with a remote cpu, the id number should be communicated
-     to the remote task with which we want to synchronize.
-     Returns the hwspinlock id number, or -EINVAL if hwlock is null.
 
-3. Typical usage
+Retrieve id number of a given hwspinlock. This is needed when an
+hwspinlock is dynamically assigned: before it can be used to achieve
+mutual exclusion with a remote cpu, the id number should be communicated
+to the remote task with which we want to synchronize.
 
-#include <linux/hwspinlock.h>
-#include <linux/err.h>
+Returns the hwspinlock id number, or -EINVAL if hwlock is null.
 
-int hwspinlock_example1(void)
-{
-	struct hwspinlock *hwlock;
-	int ret;
+Typical usage
+=============
 
-	/* dynamically assign a hwspinlock */
-	hwlock = hwspin_lock_request();
-	if (!hwlock)
-		...
+::
 
-	id = hwspin_lock_get_id(hwlock);
-	/* probably need to communicate id to a remote processor now */
+	#include <linux/hwspinlock.h>
+	#include <linux/err.h>
 
-	/* take the lock, spin for 1 sec if it's already taken */
-	ret = hwspin_lock_timeout(hwlock, 1000);
-	if (ret)
-		...
+	int hwspinlock_example1(void)
+	{
+		struct hwspinlock *hwlock;
+		int ret;
 
-	/*
-	 * we took the lock, do our thing now, but do NOT sleep
-	 */
+		/* dynamically assign a hwspinlock */
+		hwlock = hwspin_lock_request();
+		if (!hwlock)
+			...
 
-	/* release the lock */
-	hwspin_unlock(hwlock);
+		id = hwspin_lock_get_id(hwlock);
+		/* probably need to communicate id to a remote processor now */
 
-	/* free the lock */
-	ret = hwspin_lock_free(hwlock);
-	if (ret)
-		...
+		/* take the lock, spin for 1 sec if it's already taken */
+		ret = hwspin_lock_timeout(hwlock, 1000);
+		if (ret)
+			...
 
-	return ret;
-}
+		/*
+		* we took the lock, do our thing now, but do NOT sleep
+		*/
 
-int hwspinlock_example2(void)
-{
-	struct hwspinlock *hwlock;
-	int ret;
+		/* release the lock */
+		hwspin_unlock(hwlock);
 
-	/*
-	 * assign a specific hwspinlock id - this should be called early
-	 * by board init code.
-	 */
-	hwlock = hwspin_lock_request_specific(PREDEFINED_LOCK_ID);
-	if (!hwlock)
-		...
+		/* free the lock */
+		ret = hwspin_lock_free(hwlock);
+		if (ret)
+			...
 
-	/* try to take it, but don't spin on it */
-	ret = hwspin_trylock(hwlock);
-	if (!ret) {
-		pr_info("lock is already taken\n");
-		return -EBUSY;
+		return ret;
 	}
 
-	/*
-	 * we took the lock, do our thing now, but do NOT sleep
-	 */
+	int hwspinlock_example2(void)
+	{
+		struct hwspinlock *hwlock;
+		int ret;
 
-	/* release the lock */
-	hwspin_unlock(hwlock);
+		/*
+		* assign a specific hwspinlock id - this should be called early
+		* by board init code.
+		*/
+		hwlock = hwspin_lock_request_specific(PREDEFINED_LOCK_ID);
+		if (!hwlock)
+			...
 
-	/* free the lock */
-	ret = hwspin_lock_free(hwlock);
-	if (ret)
-		...
+		/* try to take it, but don't spin on it */
+		ret = hwspin_trylock(hwlock);
+		if (!ret) {
+			pr_info("lock is already taken\n");
+			return -EBUSY;
+		}
 
-	return ret;
-}
+		/*
+		* we took the lock, do our thing now, but do NOT sleep
+		*/
+
+		/* release the lock */
+		hwspin_unlock(hwlock);
+
+		/* free the lock */
+		ret = hwspin_lock_free(hwlock);
+		if (ret)
+			...
+
+		return ret;
+	}
 
 
-4. API for implementors
+API for implementors
+====================
+
+::
 
   int hwspin_lock_register(struct hwspinlock_device *bank, struct device *dev,
 		const struct hwspinlock_ops *ops, int base_id, int num_locks);
-   - to be called from the underlying platform-specific implementation, in
-     order to register a new hwspinlock device (which is usually a bank of
-     numerous locks). Should be called from a process context (this function
-     might sleep).
-     Returns 0 on success, or appropriate error code on failure.
+
+To be called from the underlying platform-specific implementation, in
+order to register a new hwspinlock device (which is usually a bank of
+numerous locks). Should be called from a process context (this function
+might sleep).
+
+Returns 0 on success, or appropriate error code on failure.
+
+::
 
   int hwspin_lock_unregister(struct hwspinlock_device *bank);
-   - to be called from the underlying vendor-specific implementation, in order
-     to unregister an hwspinlock device (which is usually a bank of numerous
-     locks).
-     Should be called from a process context (this function might sleep).
-     Returns the address of hwspinlock on success, or NULL on error (e.g.
-     if the hwspinlock is still in use).
 
-5. Important structs
+To be called from the underlying vendor-specific implementation, in order
+to unregister an hwspinlock device (which is usually a bank of numerous
+locks).
+
+Should be called from a process context (this function might sleep).
+
+Returns the address of hwspinlock on success, or NULL on error (e.g.
+if the hwspinlock is still in use).
+
+Important structs
+=================
 
 struct hwspinlock_device is a device which usually contains a bank
 of hardware locks. It is registered by the underlying hwspinlock
 implementation using the hwspin_lock_register() API.
 
-/**
- * struct hwspinlock_device - a device which usually spans numerous hwspinlocks
- * @dev: underlying device, will be used to invoke runtime PM api
- * @ops: platform-specific hwspinlock handlers
- * @base_id: id index of the first lock in this device
- * @num_locks: number of locks in this device
- * @lock: dynamically allocated array of 'struct hwspinlock'
- */
-struct hwspinlock_device {
-	struct device *dev;
-	const struct hwspinlock_ops *ops;
-	int base_id;
-	int num_locks;
-	struct hwspinlock lock[0];
-};
+::
+
+	/**
+	* struct hwspinlock_device - a device which usually spans numerous hwspinlocks
+	* @dev: underlying device, will be used to invoke runtime PM api
+	* @ops: platform-specific hwspinlock handlers
+	* @base_id: id index of the first lock in this device
+	* @num_locks: number of locks in this device
+	* @lock: dynamically allocated array of 'struct hwspinlock'
+	*/
+	struct hwspinlock_device {
+		struct device *dev;
+		const struct hwspinlock_ops *ops;
+		int base_id;
+		int num_locks;
+		struct hwspinlock lock[0];
+	};
 
 struct hwspinlock_device contains an array of hwspinlock structs, each
-of which represents a single hardware lock:
+of which represents a single hardware lock::
 
-/**
- * struct hwspinlock - this struct represents a single hwspinlock instance
- * @bank: the hwspinlock_device structure which owns this lock
- * @lock: initialized and used by hwspinlock core
- * @priv: private data, owned by the underlying platform-specific hwspinlock drv
- */
-struct hwspinlock {
-	struct hwspinlock_device *bank;
-	spinlock_t lock;
-	void *priv;
-};
+	/**
+	* struct hwspinlock - this struct represents a single hwspinlock instance
+	* @bank: the hwspinlock_device structure which owns this lock
+	* @lock: initialized and used by hwspinlock core
+	* @priv: private data, owned by the underlying platform-specific hwspinlock drv
+	*/
+	struct hwspinlock {
+		struct hwspinlock_device *bank;
+		spinlock_t lock;
+		void *priv;
+	};
 
 When registering a bank of locks, the hwspinlock driver only needs to
 set the priv members of the locks. The rest of the members are set and
 initialized by the hwspinlock core itself.
 
-6. Implementation callbacks
+Implementation callbacks
+========================
 
-There are three possible callbacks defined in 'struct hwspinlock_ops':
+There are three possible callbacks defined in 'struct hwspinlock_ops'::
 
-struct hwspinlock_ops {
-	int (*trylock)(struct hwspinlock *lock);
-	void (*unlock)(struct hwspinlock *lock);
-	void (*relax)(struct hwspinlock *lock);
-};
+	struct hwspinlock_ops {
+		int (*trylock)(struct hwspinlock *lock);
+		void (*unlock)(struct hwspinlock *lock);
+		void (*relax)(struct hwspinlock *lock);
+	};
 
 The first two callbacks are mandatory:
 
 The ->trylock() callback should make a single attempt to take the lock, and
-return 0 on failure and 1 on success. This callback may _not_ sleep.
+return 0 on failure and 1 on success. This callback may **not** sleep.
 
 The ->unlock() callback releases the lock. It always succeed, and it, too,
-may _not_ sleep.
+may **not** sleep.
 
 The ->relax() callback is optional. It is called by hwspinlock core while
 spinning on a lock, and can be used by the underlying implementation to force
-a delay between two successive invocations of ->trylock(). It may _not_ sleep.
+a delay between two successive invocations of ->trylock(). It may **not** sleep.
diff --git a/Documentation/intel_txt.txt b/Documentation/intel_txt.txt
index 91d89c5..d83c1a2 100644
--- a/Documentation/intel_txt.txt
+++ b/Documentation/intel_txt.txt
@@ -1,4 +1,5 @@
-Intel(R) TXT Overview:
+=====================
+Intel(R) TXT Overview
 =====================
 
 Intel's technology for safer computing, Intel(R) Trusted Execution
@@ -8,9 +9,10 @@
 Intel TXT was formerly known by the code name LaGrande Technology (LT).
 
 Intel TXT in Brief:
-o  Provides dynamic root of trust for measurement (DRTM)
-o  Data protection in case of improper shutdown
-o  Measurement and verification of launched environment
+
+-  Provides dynamic root of trust for measurement (DRTM)
+-  Data protection in case of improper shutdown
+-  Measurement and verification of launched environment
 
 Intel TXT is part of the vPro(TM) brand and is also available some
 non-vPro systems.  It is currently available on desktop systems
@@ -24,16 +26,21 @@
 
 Intel TXT has been presented at various events over the past few
 years, some of which are:
-      LinuxTAG 2008:
+
+      - LinuxTAG 2008:
           http://www.linuxtag.org/2008/en/conf/events/vp-donnerstag.html
-      TRUST2008:
+
+      - TRUST2008:
           http://www.trust-conference.eu/downloads/Keynote-Speakers/
           3_David-Grawrock_The-Front-Door-of-Trusted-Computing.pdf
-      IDF, Shanghai:
-          http://www.prcidf.com.cn/index_en.html
-      IDFs 2006, 2007 (I'm not sure if/where they are online)
 
-Trusted Boot Project Overview:
+      - IDF, Shanghai:
+          http://www.prcidf.com.cn/index_en.html
+
+      - IDFs 2006, 2007
+	  (I'm not sure if/where they are online)
+
+Trusted Boot Project Overview
 =============================
 
 Trusted Boot (tboot) is an open source, pre-kernel/VMM module that
@@ -87,11 +94,12 @@
 How Does it Work?
 =================
 
-o  Tboot is an executable that is launched by the bootloader as
+-  Tboot is an executable that is launched by the bootloader as
    the "kernel" (the binary the bootloader executes).
-o  It performs all of the work necessary to determine if the
+-  It performs all of the work necessary to determine if the
    platform supports Intel TXT and, if so, executes the GETSEC[SENTER]
    processor instruction that initiates the dynamic root of trust.
+
    -  If tboot determines that the system does not support Intel TXT
       or is not configured correctly (e.g. the SINIT AC Module was
       incorrect), it will directly launch the kernel with no changes
@@ -99,12 +107,14 @@
    -  Tboot will output various information about its progress to the
       terminal, serial port, and/or an in-memory log; the output
       locations can be configured with a command line switch.
-o  The GETSEC[SENTER] instruction will return control to tboot and
+
+-  The GETSEC[SENTER] instruction will return control to tboot and
    tboot then verifies certain aspects of the environment (e.g. TPM NV
    lock, e820 table does not have invalid entries, etc.).
-o  It will wake the APs from the special sleep state the GETSEC[SENTER]
+-  It will wake the APs from the special sleep state the GETSEC[SENTER]
    instruction had put them in and place them into a wait-for-SIPI
    state.
+
    -  Because the processors will not respond to an INIT or SIPI when
       in the TXT environment, it is necessary to create a small VT-x
       guest for the APs.  When they run in this guest, they will
@@ -112,8 +122,10 @@
       VMEXITs, and then disable VT and jump to the SIPI vector.  This
       approach seemed like a better choice than having to insert
       special code into the kernel's MP wakeup sequence.
-o  Tboot then applies an (optional) user-defined launch policy to
+
+-  Tboot then applies an (optional) user-defined launch policy to
    verify the kernel and initrd.
+
    -  This policy is rooted in TPM NV and is described in the tboot
       project.  The tboot project also contains code for tools to
       create and provision the policy.
@@ -121,30 +133,34 @@
       then any kernel will be launched.
    -  Policy action is flexible and can include halting on failures
       or simply logging them and continuing.
-o  Tboot adjusts the e820 table provided by the bootloader to reserve
+
+-  Tboot adjusts the e820 table provided by the bootloader to reserve
    its own location in memory as well as to reserve certain other
    TXT-related regions.
-o  As part of its launch, tboot DMA protects all of RAM (using the
+-  As part of its launch, tboot DMA protects all of RAM (using the
    VT-d PMRs).  Thus, the kernel must be booted with 'intel_iommu=on'
    in order to remove this blanket protection and use VT-d's
    page-level protection.
-o  Tboot will populate a shared page with some data about itself and
+-  Tboot will populate a shared page with some data about itself and
    pass this to the Linux kernel as it transfers control.
+
    -  The location of the shared page is passed via the boot_params
       struct as a physical address.
-o  The kernel will look for the tboot shared page address and, if it
+
+-  The kernel will look for the tboot shared page address and, if it
    exists, map it.
-o  As one of the checks/protections provided by TXT, it makes a copy
+-  As one of the checks/protections provided by TXT, it makes a copy
    of the VT-d DMARs in a DMA-protected region of memory and verifies
    them for correctness.  The VT-d code will detect if the kernel was
    launched with tboot and use this copy instead of the one in the
    ACPI table.
-o  At this point, tboot and TXT are out of the picture until a
+-  At this point, tboot and TXT are out of the picture until a
    shutdown (S<n>)
-o  In order to put a system into any of the sleep states after a TXT
+-  In order to put a system into any of the sleep states after a TXT
    launch, TXT must first be exited.  This is to prevent attacks that
    attempt to crash the system to gain control on reboot and steal
    data left in memory.
+
    -  The kernel will perform all of its sleep preparation and
       populate the shared page with the ACPI data needed to put the
       platform in the desired sleep state.
@@ -172,7 +188,7 @@
 That's pretty much it for TXT support.
 
 
-Configuring the System:
+Configuring the System
 ======================
 
 This code works with 32bit, 32bit PAE, and 64bit (x86_64) kernels.
@@ -181,7 +197,8 @@
 allow these to be individually enabled/disabled and the screens in
 which to find them are BIOS-specific.
 
-grub.conf needs to be modified as follows:
+grub.conf needs to be modified as follows::
+
         title Linux 2.6.29-tip w/ tboot
           root (hd0,0)
                 kernel /tboot.gz logging=serial,vga,memory
diff --git a/Documentation/io-mapping.txt b/Documentation/io-mapping.txt
index 5ca7842..a966239 100644
--- a/Documentation/io-mapping.txt
+++ b/Documentation/io-mapping.txt
@@ -1,66 +1,81 @@
+========================
+The io_mapping functions
+========================
+
+API
+===
+
 The io_mapping functions in linux/io-mapping.h provide an abstraction for
 efficiently mapping small regions of an I/O device to the CPU. The initial
 usage is to support the large graphics aperture on 32-bit processors where
 ioremap_wc cannot be used to statically map the entire aperture to the CPU
 as it would consume too much of the kernel address space.
 
-A mapping object is created during driver initialization using
+A mapping object is created during driver initialization using::
 
 	struct io_mapping *io_mapping_create_wc(unsigned long base,
 						unsigned long size)
 
-		'base' is the bus address of the region to be made
-		mappable, while 'size' indicates how large a mapping region to
-		enable. Both are in bytes.
+'base' is the bus address of the region to be made
+mappable, while 'size' indicates how large a mapping region to
+enable. Both are in bytes.
 
-		This _wc variant provides a mapping which may only be used
-		with the io_mapping_map_atomic_wc or io_mapping_map_wc.
+This _wc variant provides a mapping which may only be used
+with the io_mapping_map_atomic_wc or io_mapping_map_wc.
 
 With this mapping object, individual pages can be mapped either atomically
 or not, depending on the necessary scheduling environment. Of course, atomic
-maps are more efficient:
+maps are more efficient::
 
 	void *io_mapping_map_atomic_wc(struct io_mapping *mapping,
 				       unsigned long offset)
 
-		'offset' is the offset within the defined mapping region.
-		Accessing addresses beyond the region specified in the
-		creation function yields undefined results. Using an offset
-		which is not page aligned yields an undefined result. The
-		return value points to a single page in CPU address space.
+'offset' is the offset within the defined mapping region.
+Accessing addresses beyond the region specified in the
+creation function yields undefined results. Using an offset
+which is not page aligned yields an undefined result. The
+return value points to a single page in CPU address space.
 
-		This _wc variant returns a write-combining map to the
-		page and may only be used with mappings created by
-		io_mapping_create_wc
+This _wc variant returns a write-combining map to the
+page and may only be used with mappings created by
+io_mapping_create_wc
 
-		Note that the task may not sleep while holding this page
-		mapped.
+Note that the task may not sleep while holding this page
+mapped.
+
+::
 
 	void io_mapping_unmap_atomic(void *vaddr)
 
-		'vaddr' must be the value returned by the last
-		io_mapping_map_atomic_wc call. This unmaps the specified
-		page and allows the task to sleep once again.
+'vaddr' must be the value returned by the last
+io_mapping_map_atomic_wc call. This unmaps the specified
+page and allows the task to sleep once again.
 
 If you need to sleep while holding the lock, you can use the non-atomic
 variant, although they may be significantly slower.
 
+::
+
 	void *io_mapping_map_wc(struct io_mapping *mapping,
 				unsigned long offset)
 
-		This works like io_mapping_map_atomic_wc except it allows
-		the task to sleep while holding the page mapped.
+This works like io_mapping_map_atomic_wc except it allows
+the task to sleep while holding the page mapped.
+
+
+::
 
 	void io_mapping_unmap(void *vaddr)
 
-		This works like io_mapping_unmap_atomic, except it is used
-		for pages mapped with io_mapping_map_wc.
+This works like io_mapping_unmap_atomic, except it is used
+for pages mapped with io_mapping_map_wc.
 
-At driver close time, the io_mapping object must be freed:
+At driver close time, the io_mapping object must be freed::
 
 	void io_mapping_free(struct io_mapping *mapping)
 
-Current Implementation:
+Current Implementation
+======================
 
 The initial implementation of these functions uses existing mapping
 mechanisms and so provides only an abstraction layer and no new
diff --git a/Documentation/io_ordering.txt b/Documentation/io_ordering.txt
index 9faae6f..2ab303c 100644
--- a/Documentation/io_ordering.txt
+++ b/Documentation/io_ordering.txt
@@ -1,3 +1,7 @@
+==============================================
+Ordering I/O writes to memory-mapped addresses
+==============================================
+
 On some platforms, so-called memory-mapped I/O is weakly ordered.  On such
 platforms, driver writers are responsible for ensuring that I/O writes to
 memory-mapped addresses on their device arrive in the order intended.  This is
@@ -8,39 +12,39 @@
 subsequent writes to I/O space arrived only after all prior writes (much like a
 memory barrier op, mb(), only with respect to I/O).
 
-A more concrete example from a hypothetical device driver:
+A more concrete example from a hypothetical device driver::
 
-        ...
-CPU A:  spin_lock_irqsave(&dev_lock, flags)
-CPU A:  val = readl(my_status);
-CPU A:  ...
-CPU A:  writel(newval, ring_ptr);
-CPU A:  spin_unlock_irqrestore(&dev_lock, flags)
-        ...
-CPU B:  spin_lock_irqsave(&dev_lock, flags)
-CPU B:  val = readl(my_status);
-CPU B:  ...
-CPU B:  writel(newval2, ring_ptr);
-CPU B:  spin_unlock_irqrestore(&dev_lock, flags)
-        ...
+		...
+	CPU A:  spin_lock_irqsave(&dev_lock, flags)
+	CPU A:  val = readl(my_status);
+	CPU A:  ...
+	CPU A:  writel(newval, ring_ptr);
+	CPU A:  spin_unlock_irqrestore(&dev_lock, flags)
+		...
+	CPU B:  spin_lock_irqsave(&dev_lock, flags)
+	CPU B:  val = readl(my_status);
+	CPU B:  ...
+	CPU B:  writel(newval2, ring_ptr);
+	CPU B:  spin_unlock_irqrestore(&dev_lock, flags)
+		...
 
 In the case above, the device may receive newval2 before it receives newval,
-which could cause problems.  Fixing it is easy enough though:
+which could cause problems.  Fixing it is easy enough though::
 
-        ...
-CPU A:  spin_lock_irqsave(&dev_lock, flags)
-CPU A:  val = readl(my_status);
-CPU A:  ...
-CPU A:  writel(newval, ring_ptr);
-CPU A:  (void)readl(safe_register); /* maybe a config register? */
-CPU A:  spin_unlock_irqrestore(&dev_lock, flags)
-        ...
-CPU B:  spin_lock_irqsave(&dev_lock, flags)
-CPU B:  val = readl(my_status);
-CPU B:  ...
-CPU B:  writel(newval2, ring_ptr);
-CPU B:  (void)readl(safe_register); /* maybe a config register? */
-CPU B:  spin_unlock_irqrestore(&dev_lock, flags)
+		...
+	CPU A:  spin_lock_irqsave(&dev_lock, flags)
+	CPU A:  val = readl(my_status);
+	CPU A:  ...
+	CPU A:  writel(newval, ring_ptr);
+	CPU A:  (void)readl(safe_register); /* maybe a config register? */
+	CPU A:  spin_unlock_irqrestore(&dev_lock, flags)
+		...
+	CPU B:  spin_lock_irqsave(&dev_lock, flags)
+	CPU B:  val = readl(my_status);
+	CPU B:  ...
+	CPU B:  writel(newval2, ring_ptr);
+	CPU B:  (void)readl(safe_register); /* maybe a config register? */
+	CPU B:  spin_unlock_irqrestore(&dev_lock, flags)
 
 Here, the reads from safe_register will cause the I/O chipset to flush any
 pending writes before actually posting the read to the chipset, preventing
diff --git a/Documentation/iostats.txt b/Documentation/iostats.txt
index 65f694f..04d394a 100644
--- a/Documentation/iostats.txt
+++ b/Documentation/iostats.txt
@@ -1,49 +1,50 @@
+=====================
 I/O statistics fields
----------------
+=====================
 
 Since 2.4.20 (and some versions before, with patches), and 2.5.45,
 more extensive disk statistics have been introduced to help measure disk
-activity. Tools such as sar and iostat typically interpret these and do
+activity. Tools such as ``sar`` and ``iostat`` typically interpret these and do
 the work for you, but in case you are interested in creating your own
 tools, the fields are explained here.
 
 In 2.4 now, the information is found as additional fields in
-/proc/partitions.  In 2.6, the same information is found in two
-places: one is in the file /proc/diskstats, and the other is within
+``/proc/partitions``.  In 2.6 and upper, the same information is found in two
+places: one is in the file ``/proc/diskstats``, and the other is within
 the sysfs file system, which must be mounted in order to obtain
 the information. Throughout this document we'll assume that sysfs
-is mounted on /sys, although of course it may be mounted anywhere.
-Both /proc/diskstats and sysfs use the same source for the information
+is mounted on ``/sys``, although of course it may be mounted anywhere.
+Both ``/proc/diskstats`` and sysfs use the same source for the information
 and so should not differ.
 
-Here are examples of these different formats:
+Here are examples of these different formats::
 
-2.4:
-   3     0   39082680 hda 446216 784926 9550688 4382310 424847 312726 5922052 19310380 0 3376340 23705160
-   3     1    9221278 hda1 35486 0 35496 38030 0 0 0 0 0 38030 38030
+   2.4:
+      3     0   39082680 hda 446216 784926 9550688 4382310 424847 312726 5922052 19310380 0 3376340 23705160
+      3     1    9221278 hda1 35486 0 35496 38030 0 0 0 0 0 38030 38030
 
+   2.6+ sysfs:
+      446216 784926 9550688 4382310 424847 312726 5922052 19310380 0 3376340 23705160
+      35486    38030    38030    38030
 
-2.6 sysfs:
-   446216 784926 9550688 4382310 424847 312726 5922052 19310380 0 3376340 23705160
-   35486    38030    38030    38030
+   2.6+ diskstats:
+      3    0   hda 446216 784926 9550688 4382310 424847 312726 5922052 19310380 0 3376340 23705160
+      3    1   hda1 35486 38030 38030 38030
 
-2.6 diskstats:
-   3    0   hda 446216 784926 9550688 4382310 424847 312726 5922052 19310380 0 3376340 23705160
-   3    1   hda1 35486 38030 38030 38030
+On 2.4 you might execute ``grep 'hda ' /proc/partitions``. On 2.6+, you have
+a choice of ``cat /sys/block/hda/stat`` or ``grep 'hda ' /proc/diskstats``.
 
-On 2.4 you might execute "grep 'hda ' /proc/partitions". On 2.6, you have
-a choice of "cat /sys/block/hda/stat" or "grep 'hda ' /proc/diskstats".
 The advantage of one over the other is that the sysfs choice works well
-if you are watching a known, small set of disks.  /proc/diskstats may
+if you are watching a known, small set of disks.  ``/proc/diskstats`` may
 be a better choice if you are watching a large number of disks because
 you'll avoid the overhead of 50, 100, or 500 or more opens/closes with
 each snapshot of your disk statistics.
 
 In 2.4, the statistics fields are those after the device name. In
 the above example, the first field of statistics would be 446216.
-By contrast, in 2.6 if you look at /sys/block/hda/stat, you'll
+By contrast, in 2.6+ if you look at ``/sys/block/hda/stat``, you'll
 find just the eleven fields, beginning with 446216.  If you look at
-/proc/diskstats, the eleven fields will be preceded by the major and
+``/proc/diskstats``, the eleven fields will be preceded by the major and
 minor device numbers, and device name.  Each of these formats provides
 eleven fields of statistics, each meaning exactly the same things.
 All fields except field 9 are cumulative since boot.  Field 9 should
@@ -59,30 +60,40 @@
 
 Field  1 -- # of reads completed
     This is the total number of reads completed successfully.
+
 Field  2 -- # of reads merged, field 6 -- # of writes merged
     Reads and writes which are adjacent to each other may be merged for
     efficiency.  Thus two 4K reads may become one 8K read before it is
     ultimately handed to the disk, and so it will be counted (and queued)
     as only one I/O.  This field lets you know how often this was done.
+
 Field  3 -- # of sectors read
     This is the total number of sectors read successfully.
+
 Field  4 -- # of milliseconds spent reading
     This is the total number of milliseconds spent by all reads (as
     measured from __make_request() to end_that_request_last()).
+
 Field  5 -- # of writes completed
     This is the total number of writes completed successfully.
+
 Field  6 -- # of writes merged
     See the description of field 2.
+
 Field  7 -- # of sectors written
     This is the total number of sectors written successfully.
+
 Field  8 -- # of milliseconds spent writing
     This is the total number of milliseconds spent by all writes (as
     measured from __make_request() to end_that_request_last()).
+
 Field  9 -- # of I/Os currently in progress
     The only field that should go to zero. Incremented as requests are
     given to appropriate struct request_queue and decremented as they finish.
+
 Field 10 -- # of milliseconds spent doing I/Os
     This field increases so long as field 9 is nonzero.
+
 Field 11 -- weighted # of milliseconds spent doing I/Os
     This field is incremented at each I/O start, I/O completion, I/O
     merge, or read of these stats by the number of I/Os in progress
@@ -97,7 +108,7 @@
 read I/Os issued per partition should equal those made to the disks ...
 but due to the lack of locking it may only be very close.
 
-In 2.6, there are counters for each CPU, which make the lack of locking
+In 2.6+, there are counters for each CPU, which make the lack of locking
 almost a non-issue.  When the statistics are read, the per-CPU counters
 are summed (possibly overflowing the unsigned long variable they are
 summed to) and the result given to the user.  There is no convenient
@@ -106,22 +117,25 @@
 Disks vs Partitions
 -------------------
 
-There were significant changes between 2.4 and 2.6 in the I/O subsystem.
+There were significant changes between 2.4 and 2.6+ in the I/O subsystem.
 As a result, some statistic information disappeared. The translation from
 a disk address relative to a partition to the disk address relative to
 the host disk happens much earlier.  All merges and timings now happen
 at the disk level rather than at both the disk and partition level as
-in 2.4.  Consequently, you'll see a different statistics output on 2.6 for
+in 2.4.  Consequently, you'll see a different statistics output on 2.6+ for
 partitions from that for disks.  There are only *four* fields available
-for partitions on 2.6 machines.  This is reflected in the examples above.
+for partitions on 2.6+ machines.  This is reflected in the examples above.
 
 Field  1 -- # of reads issued
     This is the total number of reads issued to this partition.
+
 Field  2 -- # of sectors read
     This is the total number of sectors requested to be read from this
     partition.
+
 Field  3 -- # of writes issued
     This is the total number of writes issued to this partition.
+
 Field  4 -- # of sectors written
     This is the total number of sectors requested to be written to
     this partition.
@@ -149,16 +163,16 @@
 Additional notes
 ----------------
 
-In 2.6, sysfs is not mounted by default.  If your distribution of
+In 2.6+, sysfs is not mounted by default.  If your distribution of
 Linux hasn't added it already, here's the line you'll want to add to
-your /etc/fstab:
+your ``/etc/fstab``::
 
-none /sys sysfs defaults 0 0
+	none /sys sysfs defaults 0 0
 
 
-In 2.6, all disk statistics were removed from /proc/stat.  In 2.4, they
-appear in both /proc/partitions and /proc/stat, although the ones in
-/proc/stat take a very different format from those in /proc/partitions
+In 2.6+, all disk statistics were removed from ``/proc/stat``.  In 2.4, they
+appear in both ``/proc/partitions`` and ``/proc/stat``, although the ones in
+``/proc/stat`` take a very different format from those in ``/proc/partitions``
 (see proc(5), if your system has it.)
 
 -- ricklind@us.ibm.com
diff --git a/Documentation/irqflags-tracing.txt b/Documentation/irqflags-tracing.txt
index f6da056..bdd2082 100644
--- a/Documentation/irqflags-tracing.txt
+++ b/Documentation/irqflags-tracing.txt
@@ -1,8 +1,10 @@
+=======================
 IRQ-flags state tracing
+=======================
 
-started by Ingo Molnar <mingo@redhat.com>
+:Author: started by Ingo Molnar <mingo@redhat.com>
 
-the "irq-flags tracing" feature "traces" hardirq and softirq state, in
+The "irq-flags tracing" feature "traces" hardirq and softirq state, in
 that it gives interested subsystems an opportunity to be notified of
 every hardirqs-off/hardirqs-on, softirqs-off/softirqs-on event that
 happens in the kernel.
@@ -14,7 +16,7 @@
 are locking APIs that are not used in IRQ context. (the one exception
 for rwsems is worked around)
 
-architecture support for this is certainly not in the "trivial"
+Architecture support for this is certainly not in the "trivial"
 category, because lots of lowlevel assembly code deal with irq-flags
 state changes. But an architecture can be irq-flags-tracing enabled in a
 rather straightforward and risk-free manner.
@@ -41,7 +43,7 @@
   excluded from the irq-tracing [and lock validation] mechanism via
   lockdep_off()/lockdep_on().
 
-in general there is no risk from having an incomplete irq-flags-tracing
+In general there is no risk from having an incomplete irq-flags-tracing
 implementation in an architecture: lockdep will detect that and will
 turn itself off. I.e. the lock validator will still be reliable. There
 should be no crashes due to irq-tracing bugs. (except if the assembly
diff --git a/Documentation/isa.txt b/Documentation/isa.txt
index f232c26..def4a7b6 100644
--- a/Documentation/isa.txt
+++ b/Documentation/isa.txt
@@ -1,5 +1,6 @@
+===========
 ISA Drivers
------------
+===========
 
 The following text is adapted from the commit message of the initial
 commit of the ISA bus driver authored by Rene Herman.
@@ -23,17 +24,17 @@
 
 The usage model this provides is nice, and has been acked from the ALSA
 side by Takashi Iwai and Jaroslav Kysela. The ALSA driver module_init's
-now (for oldisa-only drivers) become:
+now (for oldisa-only drivers) become::
 
-static int __init alsa_card_foo_init(void)
-{
-	return isa_register_driver(&snd_foo_isa_driver, SNDRV_CARDS);
-}
+	static int __init alsa_card_foo_init(void)
+	{
+		return isa_register_driver(&snd_foo_isa_driver, SNDRV_CARDS);
+	}
 
-static void __exit alsa_card_foo_exit(void)
-{
-	isa_unregister_driver(&snd_foo_isa_driver);
-}
+	static void __exit alsa_card_foo_exit(void)
+	{
+		isa_unregister_driver(&snd_foo_isa_driver);
+	}
 
 Quite like the other bus models therefore. This removes a lot of
 duplicated init code from the ALSA ISA drivers.
@@ -47,11 +48,11 @@
 with.
 
 The platform_driver callbacks are called with a platform_device param;
-the isa_driver callbacks are being called with a "struct device *dev,
-unsigned int id" pair directly -- with the device creation completely
+the isa_driver callbacks are being called with a ``struct device *dev,
+unsigned int id`` pair directly -- with the device creation completely
 internal to the bus it's much cleaner to not leak isa_dev's by passing
 them in at all. The id is the only thing we ever want other then the
-struct device * anyways, and it makes for nicer code in the callbacks as
+struct device anyways, and it makes for nicer code in the callbacks as
 well.
 
 With this additional .match() callback ISA drivers have all options. If
@@ -75,20 +76,20 @@
 
 isa_register_driver() register's the struct device_driver, and then
 loops over the passed in ndev creating devices and registering them.
-This causes the bus match method to be called for them, which is:
+This causes the bus match method to be called for them, which is::
 
-int isa_bus_match(struct device *dev, struct device_driver *driver)
-{
-          struct isa_driver *isa_driver = to_isa_driver(driver);
+	int isa_bus_match(struct device *dev, struct device_driver *driver)
+	{
+		struct isa_driver *isa_driver = to_isa_driver(driver);
 
-          if (dev->platform_data == isa_driver) {
-                  if (!isa_driver->match ||
-                          isa_driver->match(dev, to_isa_dev(dev)->id))
-                          return 1;
-                  dev->platform_data = NULL;
-          }
-          return 0;
-}
+		if (dev->platform_data == isa_driver) {
+			if (!isa_driver->match ||
+				isa_driver->match(dev, to_isa_dev(dev)->id))
+				return 1;
+			dev->platform_data = NULL;
+		}
+		return 0;
+	}
 
 The first thing this does is check if this device is in fact one of this
 driver's devices by seeing if the device's platform_data pointer is set
@@ -102,7 +103,7 @@
 Then, if the the driver did not provide a .match, it matches. If it did,
 the driver match() method is called to determine a match.
 
-If it did _not_ match, dev->platform_data is reset to indicate this to
+If it did **not** match, dev->platform_data is reset to indicate this to
 isa_register_driver which can then unregister the device again.
 
 If during all this, there's any error, or no devices matched at all
diff --git a/Documentation/isapnp.txt b/Documentation/isapnp.txt
index 400d1b5..8d0840a 100644
--- a/Documentation/isapnp.txt
+++ b/Documentation/isapnp.txt
@@ -1,3 +1,4 @@
+==========================================================
 ISA Plug & Play support by Jaroslav Kysela <perex@suse.cz>
 ==========================================================
 
diff --git a/Documentation/kernel-per-CPU-kthreads.txt b/Documentation/kernel-per-CPU-kthreads.txt
index 2cb7dc5..0f00f9c 100644
--- a/Documentation/kernel-per-CPU-kthreads.txt
+++ b/Documentation/kernel-per-CPU-kthreads.txt
@@ -1,27 +1,29 @@
-REDUCING OS JITTER DUE TO PER-CPU KTHREADS
+==========================================
+Reducing OS jitter due to per-cpu kthreads
+==========================================
 
 This document lists per-CPU kthreads in the Linux kernel and presents
 options to control their OS jitter.  Note that non-per-CPU kthreads are
 not listed here.  To reduce OS jitter from non-per-CPU kthreads, bind
 them to a "housekeeping" CPU dedicated to such work.
 
+References
+==========
 
-REFERENCES
+-	Documentation/IRQ-affinity.txt:  Binding interrupts to sets of CPUs.
 
-o	Documentation/IRQ-affinity.txt:  Binding interrupts to sets of CPUs.
+-	Documentation/cgroup-v1:  Using cgroups to bind tasks to sets of CPUs.
 
-o	Documentation/cgroup-v1:  Using cgroups to bind tasks to sets of CPUs.
-
-o	man taskset:  Using the taskset command to bind tasks to sets
+-	man taskset:  Using the taskset command to bind tasks to sets
 	of CPUs.
 
-o	man sched_setaffinity:  Using the sched_setaffinity() system
+-	man sched_setaffinity:  Using the sched_setaffinity() system
 	call to bind tasks to sets of CPUs.
 
-o	/sys/devices/system/cpu/cpuN/online:  Control CPU N's hotplug state,
+-	/sys/devices/system/cpu/cpuN/online:  Control CPU N's hotplug state,
 	writing "0" to offline and "1" to online.
 
-o	In order to locate kernel-generated OS jitter on CPU N:
+-	In order to locate kernel-generated OS jitter on CPU N:
 
 		cd /sys/kernel/debug/tracing
 		echo 1 > max_graph_depth # Increase the "1" for more detail
@@ -29,12 +31,17 @@
 		# run workload
 		cat per_cpu/cpuN/trace
 
+kthreads
+========
 
-KTHREADS
+Name:
+  ehca_comp/%u
 
-Name: ehca_comp/%u
-Purpose: Periodically process Infiniband-related work.
+Purpose:
+  Periodically process Infiniband-related work.
+
 To reduce its OS jitter, do any of the following:
+
 1.	Don't use eHCA Infiniband hardware, instead choosing hardware
 	that does not require per-CPU kthreads.  This will prevent these
 	kthreads from being created in the first place.  (This will
@@ -46,26 +53,45 @@
 	provisioned only on selected CPUs.
 
 
-Name: irq/%d-%s
-Purpose: Handle threaded interrupts.
+Name:
+  irq/%d-%s
+
+Purpose:
+  Handle threaded interrupts.
+
 To reduce its OS jitter, do the following:
+
 1.	Use irq affinity to force the irq threads to execute on
 	some other CPU.
 
-Name: kcmtpd_ctr_%d
-Purpose: Handle Bluetooth work.
+Name:
+  kcmtpd_ctr_%d
+
+Purpose:
+  Handle Bluetooth work.
+
 To reduce its OS jitter, do one of the following:
+
 1.	Don't use Bluetooth, in which case these kthreads won't be
 	created in the first place.
 2.	Use irq affinity to force Bluetooth-related interrupts to
 	occur on some other CPU and furthermore initiate all
 	Bluetooth activity on some other CPU.
 
-Name: ksoftirqd/%u
-Purpose: Execute softirq handlers when threaded or when under heavy load.
+Name:
+  ksoftirqd/%u
+
+Purpose:
+  Execute softirq handlers when threaded or when under heavy load.
+
 To reduce its OS jitter, each softirq vector must be handled
 separately as follows:
-TIMER_SOFTIRQ:  Do all of the following:
+
+TIMER_SOFTIRQ
+-------------
+
+Do all of the following:
+
 1.	To the extent possible, keep the CPU out of the kernel when it
 	is non-idle, for example, by avoiding system calls and by forcing
 	both kernel threads and interrupts to execute elsewhere.
@@ -76,34 +102,59 @@
 	first one back online.  Once you have onlined the CPUs in question,
 	do not offline any other CPUs, because doing so could force the
 	timer back onto one of the CPUs in question.
-NET_TX_SOFTIRQ and NET_RX_SOFTIRQ:  Do all of the following:
+
+NET_TX_SOFTIRQ and NET_RX_SOFTIRQ
+---------------------------------
+
+Do all of the following:
+
 1.	Force networking interrupts onto other CPUs.
 2.	Initiate any network I/O on other CPUs.
 3.	Once your application has started, prevent CPU-hotplug operations
 	from being initiated from tasks that might run on the CPU to
 	be de-jittered.  (It is OK to force this CPU offline and then
 	bring it back online before you start your application.)
-BLOCK_SOFTIRQ:  Do all of the following:
+
+BLOCK_SOFTIRQ
+-------------
+
+Do all of the following:
+
 1.	Force block-device interrupts onto some other CPU.
 2.	Initiate any block I/O on other CPUs.
 3.	Once your application has started, prevent CPU-hotplug operations
 	from being initiated from tasks that might run on the CPU to
 	be de-jittered.  (It is OK to force this CPU offline and then
 	bring it back online before you start your application.)
-IRQ_POLL_SOFTIRQ:  Do all of the following:
+
+IRQ_POLL_SOFTIRQ
+----------------
+
+Do all of the following:
+
 1.	Force block-device interrupts onto some other CPU.
 2.	Initiate any block I/O and block-I/O polling on other CPUs.
 3.	Once your application has started, prevent CPU-hotplug operations
 	from being initiated from tasks that might run on the CPU to
 	be de-jittered.  (It is OK to force this CPU offline and then
 	bring it back online before you start your application.)
-TASKLET_SOFTIRQ: Do one or more of the following:
+
+TASKLET_SOFTIRQ
+---------------
+
+Do one or more of the following:
+
 1.	Avoid use of drivers that use tasklets.  (Such drivers will contain
 	calls to things like tasklet_schedule().)
 2.	Convert all drivers that you must use from tasklets to workqueues.
 3.	Force interrupts for drivers using tasklets onto other CPUs,
 	and also do I/O involving these drivers on other CPUs.
-SCHED_SOFTIRQ: Do all of the following:
+
+SCHED_SOFTIRQ
+-------------
+
+Do all of the following:
+
 1.	Avoid sending scheduler IPIs to the CPU to be de-jittered,
 	for example, ensure that at most one runnable kthread is present
 	on that CPU.  If a thread that expects to run on the de-jittered
@@ -120,7 +171,12 @@
 	forcing both kernel threads and interrupts to execute elsewhere.
 	This further reduces the number of scheduler-clock interrupts
 	received by the de-jittered CPU.
-HRTIMER_SOFTIRQ:  Do all of the following:
+
+HRTIMER_SOFTIRQ
+---------------
+
+Do all of the following:
+
 1.	To the extent possible, keep the CPU out of the kernel when it
 	is non-idle.  For example, avoid system calls and force both
 	kernel threads and interrupts to execute elsewhere.
@@ -131,9 +187,15 @@
 	back online.  Once you have onlined the CPUs in question, do not
 	offline any other CPUs, because doing so could force the timer
 	back onto one of the CPUs in question.
-RCU_SOFTIRQ:  Do at least one of the following:
+
+RCU_SOFTIRQ
+-----------
+
+Do at least one of the following:
+
 1.	Offload callbacks and keep the CPU in either dyntick-idle or
 	adaptive-ticks state by doing all of the following:
+
 	a.	CONFIG_NO_HZ_FULL=y and ensure that the CPU to be
 		de-jittered is marked as an adaptive-ticks CPU using the
 		"nohz_full=" boot parameter.  Bind the rcuo kthreads to
@@ -142,8 +204,10 @@
 		when it is non-idle, for example, by avoiding system
 		calls and by forcing both kernel threads and interrupts
 		to execute elsewhere.
+
 2.	Enable RCU to do its processing remotely via dyntick-idle by
 	doing all of the following:
+
 	a.	Build with CONFIG_NO_HZ=y and CONFIG_RCU_FAST_NO_HZ=y.
 	b.	Ensure that the CPU goes idle frequently, allowing other
 		CPUs to detect that it has passed through an RCU quiescent
@@ -155,15 +219,20 @@
 		calls and by forcing both kernel threads and interrupts
 		to execute elsewhere.
 
-Name: kworker/%u:%d%s (cpu, id, priority)
-Purpose: Execute workqueue requests
+Name:
+  kworker/%u:%d%s (cpu, id, priority)
+
+Purpose:
+  Execute workqueue requests
+
 To reduce its OS jitter, do any of the following:
+
 1.	Run your workload at a real-time priority, which will allow
 	preempting the kworker daemons.
 2.	A given workqueue can be made visible in the sysfs filesystem
 	by passing the WQ_SYSFS to that workqueue's alloc_workqueue().
 	Such a workqueue can be confined to a given subset of the
-	CPUs using the /sys/devices/virtual/workqueue/*/cpumask sysfs
+	CPUs using the ``/sys/devices/virtual/workqueue/*/cpumask`` sysfs
 	files.	The set of WQ_SYSFS workqueues can be displayed using
 	"ls sys/devices/virtual/workqueue".  That said, the workqueues
 	maintainer would like to caution people against indiscriminately
@@ -173,6 +242,7 @@
 	to remove it, even if its addition was a mistake.
 3.	Do any of the following needed to avoid jitter that your
 	application cannot tolerate:
+
 	a.	Build your kernel with CONFIG_SLUB=y rather than
 		CONFIG_SLAB=y, thus avoiding the slab allocator's periodic
 		use of each CPU's workqueues to run its cache_reap()
@@ -186,6 +256,7 @@
 		be able to build your kernel with CONFIG_CPU_FREQ=n to
 		avoid the CPU-frequency governor periodically running
 		on each CPU, including cs_dbs_timer() and od_dbs_timer().
+
 		WARNING:  Please check your CPU specifications to
 		make sure that this is safe on your particular system.
 	d.	As of v3.18, Christoph Lameter's on-demand vmstat workers
@@ -222,9 +293,14 @@
 		CONFIG_PMAC_RACKMETER=n to disable the CPU-meter,
 		avoiding OS jitter from rackmeter_do_timer().
 
-Name: rcuc/%u
-Purpose: Execute RCU callbacks in CONFIG_RCU_BOOST=y kernels.
+Name:
+  rcuc/%u
+
+Purpose:
+  Execute RCU callbacks in CONFIG_RCU_BOOST=y kernels.
+
 To reduce its OS jitter, do at least one of the following:
+
 1.	Build the kernel with CONFIG_PREEMPT=n.  This prevents these
 	kthreads from being created in the first place, and also obviates
 	the need for RCU priority boosting.  This approach is feasible
@@ -244,9 +320,14 @@
 	CPU, again preventing the rcuc/%u kthreads from having any work
 	to do.
 
-Name: rcuob/%d, rcuop/%d, and rcuos/%d
-Purpose: Offload RCU callbacks from the corresponding CPU.
+Name:
+  rcuob/%d, rcuop/%d, and rcuos/%d
+
+Purpose:
+  Offload RCU callbacks from the corresponding CPU.
+
 To reduce its OS jitter, do at least one of the following:
+
 1.	Use affinity, cgroups, or other mechanism to force these kthreads
 	to execute on some other CPU.
 2.	Build with CONFIG_RCU_NOCB_CPU=n, which will prevent these
@@ -254,9 +335,14 @@
 	note that this will not eliminate OS jitter, but will instead
 	shift it to RCU_SOFTIRQ.
 
-Name: watchdog/%u
-Purpose: Detect software lockups on each CPU.
+Name:
+  watchdog/%u
+
+Purpose:
+  Detect software lockups on each CPU.
+
 To reduce its OS jitter, do at least one of the following:
+
 1.	Build with CONFIG_LOCKUP_DETECTOR=n, which will prevent these
 	kthreads from being created in the first place.
 2.	Boot with "nosoftlockup=0", which will also prevent these kthreads
diff --git a/Documentation/kobject.txt b/Documentation/kobject.txt
index 1be59a3..fc9485d 100644
--- a/Documentation/kobject.txt
+++ b/Documentation/kobject.txt
@@ -1,13 +1,13 @@
+=====================================================================
 Everything you never wanted to know about kobjects, ksets, and ktypes
+=====================================================================
 
-Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+:Author: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+:Last updated: December 19, 2007
 
 Based on an original article by Jon Corbet for lwn.net written October 1,
 2003 and located at http://lwn.net/Articles/51437/
 
-Last updated December 19, 2007
-
-
 Part of the difficulty in understanding the driver model - and the kobject
 abstraction upon which it is built - is that there is no obvious starting
 place. Dealing with kobjects requires understanding a few different types,
@@ -47,6 +47,7 @@
 
 
 Embedding kobjects
+==================
 
 It is rare for kernel code to create a standalone kobject, with one major
 exception explained below.  Instead, kobjects are used to control access to
@@ -65,7 +66,7 @@
 interest.)
 
 So, for example, the UIO code in drivers/uio/uio.c has a structure that
-defines the memory region associated with a uio device:
+defines the memory region associated with a uio device::
 
     struct uio_map {
 	struct kobject kobj;
@@ -77,7 +78,7 @@
 often have the opposite problem, however: given a struct kobject pointer,
 what is the pointer to the containing structure?  You must avoid tricks
 (such as assuming that the kobject is at the beginning of the structure)
-and, instead, use the container_of() macro, found in <linux/kernel.h>:
+and, instead, use the container_of() macro, found in <linux/kernel.h>::
 
     container_of(pointer, type, member)
 
@@ -90,13 +91,13 @@
 The return value from container_of() is a pointer to the corresponding
 container type. So, for example, a pointer "kp" to a struct kobject
 embedded *within* a struct uio_map could be converted to a pointer to the
-*containing* uio_map structure with:
+*containing* uio_map structure with::
 
     struct uio_map *u_map = container_of(kp, struct uio_map, kobj);
 
 For convenience, programmers often define a simple macro for "back-casting"
 kobject pointers to the containing type.  Exactly this happens in the
-earlier drivers/uio/uio.c, as you can see here:
+earlier drivers/uio/uio.c, as you can see here::
 
     struct uio_map {
         struct kobject kobj;
@@ -106,23 +107,25 @@
     #define to_map(map) container_of(map, struct uio_map, kobj)
 
 where the macro argument "map" is a pointer to the struct kobject in
-question.  That macro is subsequently invoked with:
+question.  That macro is subsequently invoked with::
 
     struct uio_map *map = to_map(kobj);
 
 
 Initialization of kobjects
+==========================
 
 Code which creates a kobject must, of course, initialize that object. Some
-of the internal fields are setup with a (mandatory) call to kobject_init():
+of the internal fields are setup with a (mandatory) call to kobject_init()::
 
     void kobject_init(struct kobject *kobj, struct kobj_type *ktype);
 
 The ktype is required for a kobject to be created properly, as every kobject
 must have an associated kobj_type.  After calling kobject_init(), to
-register the kobject with sysfs, the function kobject_add() must be called:
+register the kobject with sysfs, the function kobject_add() must be called::
 
-    int kobject_add(struct kobject *kobj, struct kobject *parent, const char *fmt, ...);
+    int kobject_add(struct kobject *kobj, struct kobject *parent,
+		    const char *fmt, ...);
 
 This sets up the parent of the kobject and the name for the kobject
 properly.  If the kobject is to be associated with a specific kset,
@@ -133,7 +136,7 @@
 
 As the name of the kobject is set when it is added to the kernel, the name
 of the kobject should never be manipulated directly.  If you must change
-the name of the kobject, call kobject_rename():
+the name of the kobject, call kobject_rename()::
 
     int kobject_rename(struct kobject *kobj, const char *new_name);
 
@@ -146,12 +149,12 @@
 incorrect and needs to be fixed.
 
 To properly access the name of the kobject, use the function
-kobject_name():
+kobject_name()::
 
     const char *kobject_name(const struct kobject * kobj);
 
 There is a helper function to both initialize and add the kobject to the
-kernel at the same time, called surprisingly enough kobject_init_and_add():
+kernel at the same time, called surprisingly enough kobject_init_and_add()::
 
     int kobject_init_and_add(struct kobject *kobj, struct kobj_type *ktype,
                              struct kobject *parent, const char *fmt, ...);
@@ -161,10 +164,11 @@
 
 
 Uevents
+=======
 
 After a kobject has been registered with the kobject core, you need to
 announce to the world that it has been created.  This can be done with a
-call to kobject_uevent():
+call to kobject_uevent()::
 
     int kobject_uevent(struct kobject *kobj, enum kobject_action action);
 
@@ -180,11 +184,12 @@
 
 
 Reference counts
+================
 
 One of the key functions of a kobject is to serve as a reference counter
 for the object in which it is embedded. As long as references to the object
 exist, the object (and the code which supports it) must continue to exist.
-The low-level functions for manipulating a kobject's reference counts are:
+The low-level functions for manipulating a kobject's reference counts are::
 
     struct kobject *kobject_get(struct kobject *kobj);
     void kobject_put(struct kobject *kobj);
@@ -209,21 +214,24 @@
 
 
 Creating "simple" kobjects
+==========================
 
 Sometimes all that a developer wants is a way to create a simple directory
 in the sysfs hierarchy, and not have to mess with the whole complication of
 ksets, show and store functions, and other details.  This is the one
 exception where a single kobject should be created.  To create such an
-entry, use the function:
+entry, use the function::
 
     struct kobject *kobject_create_and_add(char *name, struct kobject *parent);
 
 This function will create a kobject and place it in sysfs in the location
 underneath the specified parent kobject.  To create simple attributes
-associated with this kobject, use:
+associated with this kobject, use::
 
     int sysfs_create_file(struct kobject *kobj, struct attribute *attr);
-or
+
+or::
+
     int sysfs_create_group(struct kobject *kobj, struct attribute_group *grp);
 
 Both types of attributes used here, with a kobject that has been created
@@ -236,6 +244,7 @@
 
 
 ktypes and release methods
+==========================
 
 One important thing still missing from the discussion is what happens to a
 kobject when its reference count reaches zero. The code which created the
@@ -257,7 +266,7 @@
 errors creeping in.
 
 This notification is done through a kobject's release() method. Usually
-such a method has a form like:
+such a method has a form like::
 
     void my_object_release(struct kobject *kobj)
     {
@@ -281,7 +290,7 @@
 
 Interestingly, the release() method is not stored in the kobject itself;
 instead, it is associated with the ktype. So let us introduce struct
-kobj_type:
+kobj_type::
 
     struct kobj_type {
 	    void (*release)(struct kobject *kobj);
@@ -306,6 +315,7 @@
 
 
 ksets
+=====
 
 A kset is merely a collection of kobjects that want to be associated with
 each other.  There is no restriction that they be of the same ktype, but be
@@ -335,13 +345,16 @@
 
 As a kset contains a kobject within it, it should always be dynamically
 created and never declared statically or on the stack.  To create a new
-kset use:
+kset use::
+
   struct kset *kset_create_and_add(const char *name,
 				   struct kset_uevent_ops *u,
 				   struct kobject *parent);
 
-When you are finished with the kset, call:
+When you are finished with the kset, call::
+
   void kset_unregister(struct kset *kset);
+
 to destroy it.  This removes the kset from sysfs and decrements its reference
 count.  When the reference count goes to zero, the kset will be released.
 Because other references to the kset may still exist, the release may happen
@@ -351,14 +364,14 @@
 samples/kobject/kset-example.c file in the kernel tree.
 
 If a kset wishes to control the uevent operations of the kobjects
-associated with it, it can use the struct kset_uevent_ops to handle it:
+associated with it, it can use the struct kset_uevent_ops to handle it::
 
-struct kset_uevent_ops {
+  struct kset_uevent_ops {
         int (*filter)(struct kset *kset, struct kobject *kobj);
         const char *(*name)(struct kset *kset, struct kobject *kobj);
         int (*uevent)(struct kset *kset, struct kobject *kobj,
                       struct kobj_uevent_env *env);
-};
+  };
 
 
 The filter function allows a kset to prevent a uevent from being emitted to
@@ -386,6 +399,7 @@
 
 
 Kobject removal
+===============
 
 After a kobject has been registered with the kobject core successfully, it
 must be cleaned up when the code is finished with it.  To do that, call
@@ -409,6 +423,7 @@
 
 
 Example code to copy from
+=========================
 
 For a more complete example of using ksets and kobjects properly, see the
 example programs samples/kobject/{kobject-example.c,kset-example.c},
diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt
index 1f6d45a..2335715 100644
--- a/Documentation/kprobes.txt
+++ b/Documentation/kprobes.txt
@@ -1,30 +1,36 @@
-Title	: Kernel Probes (Kprobes)
-Authors	: Jim Keniston <jkenisto@us.ibm.com>
-	: Prasanna S Panchamukhi <prasanna.panchamukhi@gmail.com>
-	: Masami Hiramatsu <mhiramat@redhat.com>
+=======================
+Kernel Probes (Kprobes)
+=======================
 
-CONTENTS
+:Author: Jim Keniston <jkenisto@us.ibm.com>
+:Author: Prasanna S Panchamukhi <prasanna.panchamukhi@gmail.com>
+:Author: Masami Hiramatsu <mhiramat@redhat.com>
 
-1. Concepts: Kprobes, Jprobes, Return Probes
-2. Architectures Supported
-3. Configuring Kprobes
-4. API Reference
-5. Kprobes Features and Limitations
-6. Probe Overhead
-7. TODO
-8. Kprobes Example
-9. Jprobes Example
-10. Kretprobes Example
-Appendix A: The kprobes debugfs interface
-Appendix B: The kprobes sysctl interface
+.. CONTENTS
 
-1. Concepts: Kprobes, Jprobes, Return Probes
+  1. Concepts: Kprobes, Jprobes, Return Probes
+  2. Architectures Supported
+  3. Configuring Kprobes
+  4. API Reference
+  5. Kprobes Features and Limitations
+  6. Probe Overhead
+  7. TODO
+  8. Kprobes Example
+  9. Jprobes Example
+  10. Kretprobes Example
+  Appendix A: The kprobes debugfs interface
+  Appendix B: The kprobes sysctl interface
+
+Concepts: Kprobes, Jprobes, Return Probes
+=========================================
 
 Kprobes enables you to dynamically break into any kernel routine and
 collect debugging and performance information non-disruptively. You
-can trap at almost any kernel code address(*), specifying a handler
+can trap at almost any kernel code address [1]_, specifying a handler
 routine to be invoked when the breakpoint is hit.
-(*: some parts of the kernel code can not be trapped, see 1.5 Blacklist)
+
+.. [1] some parts of the kernel code can not be trapped, see
+       :ref:`kprobes_blacklist`)
 
 There are currently three types of probes: kprobes, jprobes, and
 kretprobes (also called return probes).  A kprobe can be inserted
@@ -40,8 +46,8 @@
 the probe is to be inserted and what handler is to be called when
 the probe is hit.
 
-There are also register_/unregister_*probes() functions for batch
-registration/unregistration of a group of *probes. These functions
+There are also ``register_/unregister_*probes()`` functions for batch
+registration/unregistration of a group of ``*probes``. These functions
 can speed up unregistration process when you have to unregister
 a lot of probes at once.
 
@@ -51,9 +57,10 @@
 Kprobes -- e.g., the difference between a pre_handler and
 a post_handler, and how to use the maxactive and nmissed fields of
 a kretprobe.  But if you're in a hurry to start using Kprobes, you
-can skip ahead to section 2.
+can skip ahead to :ref:`kprobes_archs_supported`.
 
-1.1 How Does a Kprobe Work?
+How Does a Kprobe Work?
+-----------------------
 
 When a kprobe is registered, Kprobes makes a copy of the probed
 instruction and replaces the first byte(s) of the probed instruction
@@ -75,7 +82,8 @@
 "post_handler," if any, that is associated with the kprobe.
 Execution then continues with the instruction following the probepoint.
 
-1.2 How Does a Jprobe Work?
+How Does a Jprobe Work?
+-----------------------
 
 A jprobe is implemented using a kprobe that is placed on a function's
 entry point.  It employs a simple mirroring principle to allow
@@ -113,9 +121,11 @@
 bytes, or more than 64 bytes of argument data, depending on
 architecture).
 
-1.3 Return Probes
+Return Probes
+-------------
 
-1.3.1 How Does a Return Probe Work?
+How Does a Return Probe Work?
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 When you call register_kretprobe(), Kprobes establishes a kprobe at
 the entry to the function.  When the probed function is called and this
@@ -150,7 +160,8 @@
 time the probed function is entered but there is no kretprobe_instance
 object available for establishing the return probe.
 
-1.3.2 Kretprobe entry-handler
+Kretprobe entry-handler
+^^^^^^^^^^^^^^^^^^^^^^^
 
 Kretprobes also provides an optional user-specified handler which runs
 on function entry. This handler is specified by setting the entry_handler
@@ -174,7 +185,10 @@
 object available, then in addition to incrementing the nmissed count,
 the user entry_handler invocation is also skipped.
 
-1.4 How Does Jump Optimization Work?
+.. _kprobes_jump_optimization:
+
+How Does Jump Optimization Work?
+--------------------------------
 
 If your kernel is built with CONFIG_OPTPROBES=y (currently this flag
 is automatically set 'y' on x86/x86-64, non-preemptive kernel) and
@@ -182,53 +196,60 @@
 sysctl(8)), Kprobes tries to reduce probe-hit overhead by using a jump
 instruction instead of a breakpoint instruction at each probepoint.
 
-1.4.1 Init a Kprobe
+Init a Kprobe
+^^^^^^^^^^^^^
 
 When a probe is registered, before attempting this optimization,
 Kprobes inserts an ordinary, breakpoint-based kprobe at the specified
 address. So, even if it's not possible to optimize this particular
 probepoint, there'll be a probe there.
 
-1.4.2 Safety Check
+Safety Check
+^^^^^^^^^^^^
 
 Before optimizing a probe, Kprobes performs the following safety checks:
 
 - Kprobes verifies that the region that will be replaced by the jump
-instruction (the "optimized region") lies entirely within one function.
-(A jump instruction is multiple bytes, and so may overlay multiple
-instructions.)
+  instruction (the "optimized region") lies entirely within one function.
+  (A jump instruction is multiple bytes, and so may overlay multiple
+  instructions.)
 
 - Kprobes analyzes the entire function and verifies that there is no
-jump into the optimized region.  Specifically:
+  jump into the optimized region.  Specifically:
+
   - the function contains no indirect jump;
   - the function contains no instruction that causes an exception (since
-  the fixup code triggered by the exception could jump back into the
-  optimized region -- Kprobes checks the exception tables to verify this);
-  and
+    the fixup code triggered by the exception could jump back into the
+    optimized region -- Kprobes checks the exception tables to verify this);
   - there is no near jump to the optimized region (other than to the first
-  byte).
+    byte).
 
 - For each instruction in the optimized region, Kprobes verifies that
-the instruction can be executed out of line.
+  the instruction can be executed out of line.
 
-1.4.3 Preparing Detour Buffer
+Preparing Detour Buffer
+^^^^^^^^^^^^^^^^^^^^^^^
 
 Next, Kprobes prepares a "detour" buffer, which contains the following
 instruction sequence:
+
 - code to push the CPU's registers (emulating a breakpoint trap)
 - a call to the trampoline code which calls user's probe handlers.
 - code to restore registers
 - the instructions from the optimized region
 - a jump back to the original execution path.
 
-1.4.4 Pre-optimization
+Pre-optimization
+^^^^^^^^^^^^^^^^
 
 After preparing the detour buffer, Kprobes verifies that none of the
 following situations exist:
+
 - The probe has either a break_handler (i.e., it's a jprobe) or a
-post_handler.
+  post_handler.
 - Other instructions in the optimized region are probed.
 - The probe is disabled.
+
 In any of the above cases, Kprobes won't start optimizing the probe.
 Since these are temporary situations, Kprobes tries to start
 optimizing it again if the situation is changed.
@@ -240,21 +261,23 @@
 the CPU's instruction pointer to the copied code in the detour buffer
 -- thus at least avoiding the single-step.
 
-1.4.5 Optimization
+Optimization
+^^^^^^^^^^^^
 
 The Kprobe-optimizer doesn't insert the jump instruction immediately;
 rather, it calls synchronize_sched() for safety first, because it's
 possible for a CPU to be interrupted in the middle of executing the
-optimized region(*).  As you know, synchronize_sched() can ensure
+optimized region [3]_.  As you know, synchronize_sched() can ensure
 that all interruptions that were active when synchronize_sched()
 was called are done, but only if CONFIG_PREEMPT=n.  So, this version
-of kprobe optimization supports only kernels with CONFIG_PREEMPT=n.(**)
+of kprobe optimization supports only kernels with CONFIG_PREEMPT=n [4]_.
 
 After that, the Kprobe-optimizer calls stop_machine() to replace
 the optimized region with a jump instruction to the detour buffer,
 using text_poke_smp().
 
-1.4.6 Unoptimization
+Unoptimization
+^^^^^^^^^^^^^^
 
 When an optimized kprobe is unregistered, disabled, or blocked by
 another kprobe, it will be unoptimized.  If this happens before
@@ -263,15 +286,15 @@
 replaced with the original code (except for an int3 breakpoint in
 the first byte) by using text_poke_smp().
 
-(*)Please imagine that the 2nd instruction is interrupted and then
-the optimizer replaces the 2nd instruction with the jump *address*
-while the interrupt handler is running. When the interrupt
-returns to original address, there is no valid instruction,
-and it causes an unexpected result.
+.. [3] Please imagine that the 2nd instruction is interrupted and then
+   the optimizer replaces the 2nd instruction with the jump *address*
+   while the interrupt handler is running. When the interrupt
+   returns to original address, there is no valid instruction,
+   and it causes an unexpected result.
 
-(**)This optimization-safety checking may be replaced with the
-stop-machine method that ksplice uses for supporting a CONFIG_PREEMPT=y
-kernel.
+.. [4] This optimization-safety checking may be replaced with the
+   stop-machine method that ksplice uses for supporting a CONFIG_PREEMPT=y
+   kernel.
 
 NOTE for geeks:
 The jump optimization changes the kprobe's pre_handler behavior.
@@ -280,11 +303,17 @@
 is optimized, that modification is ignored.  Thus, if you want to
 tweak the kernel's execution path, you need to suppress optimization,
 using one of the following techniques:
+
 - Specify an empty function for the kprobe's post_handler or break_handler.
- or
+
+or
+
 - Execute 'sysctl -w debug.kprobes_optimization=n'
 
-1.5 Blacklist
+.. _kprobes_blacklist:
+
+Blacklist
+---------
 
 Kprobes can probe most of the kernel except itself. This means
 that there are some functions where kprobes cannot probe. Probing
@@ -297,7 +326,10 @@
 Kprobes checks the given probe address against the blacklist and
 rejects registering it, if the given address is in the blacklist.
 
-2. Architectures Supported
+.. _kprobes_archs_supported:
+
+Architectures Supported
+=======================
 
 Kprobes, jprobes, and return probes are implemented on the following
 architectures:
@@ -312,7 +344,8 @@
 - mips
 - s390
 
-3. Configuring Kprobes
+Configuring Kprobes
+===================
 
 When configuring the kernel using make menuconfig/xconfig/oldconfig,
 ensure that CONFIG_KPROBES is set to "y". Under "General setup", look
@@ -331,7 +364,8 @@
 so you can use "objdump -d -l vmlinux" to see the source-to-object
 code mapping.
 
-4. API Reference
+API Reference
+=============
 
 The Kprobes API includes a "register" function and an "unregister"
 function for each type of probe. The API also includes "register_*probes"
@@ -340,10 +374,13 @@
 the associated probe handlers that you'll write. See the files in the
 samples/kprobes/ sub-directory for examples.
 
-4.1 register_kprobe
+register_kprobe
+---------------
 
-#include <linux/kprobes.h>
-int register_kprobe(struct kprobe *kp);
+::
+
+	#include <linux/kprobes.h>
+	int register_kprobe(struct kprobe *kp);
 
 Sets a breakpoint at the address kp->addr.  When the breakpoint is
 hit, Kprobes calls kp->pre_handler.  After the probed instruction
@@ -354,61 +391,68 @@
 is set KPROBE_FLAG_DISABLED, that kp will be registered but disabled,
 so, its handlers aren't hit until calling enable_kprobe(kp).
 
-NOTE:
-1. With the introduction of the "symbol_name" field to struct kprobe,
-the probepoint address resolution will now be taken care of by the kernel.
-The following will now work:
+.. note::
+
+   1. With the introduction of the "symbol_name" field to struct kprobe,
+      the probepoint address resolution will now be taken care of by the kernel.
+      The following will now work::
 
 	kp.symbol_name = "symbol_name";
 
-(64-bit powerpc intricacies such as function descriptors are handled
-transparently)
+      (64-bit powerpc intricacies such as function descriptors are handled
+      transparently)
 
-2. Use the "offset" field of struct kprobe if the offset into the symbol
-to install a probepoint is known. This field is used to calculate the
-probepoint.
+   2. Use the "offset" field of struct kprobe if the offset into the symbol
+      to install a probepoint is known. This field is used to calculate the
+      probepoint.
 
-3. Specify either the kprobe "symbol_name" OR the "addr". If both are
-specified, kprobe registration will fail with -EINVAL.
+   3. Specify either the kprobe "symbol_name" OR the "addr". If both are
+      specified, kprobe registration will fail with -EINVAL.
 
-4. With CISC architectures (such as i386 and x86_64), the kprobes code
-does not validate if the kprobe.addr is at an instruction boundary.
-Use "offset" with caution.
+   4. With CISC architectures (such as i386 and x86_64), the kprobes code
+      does not validate if the kprobe.addr is at an instruction boundary.
+      Use "offset" with caution.
 
 register_kprobe() returns 0 on success, or a negative errno otherwise.
 
-User's pre-handler (kp->pre_handler):
-#include <linux/kprobes.h>
-#include <linux/ptrace.h>
-int pre_handler(struct kprobe *p, struct pt_regs *regs);
+User's pre-handler (kp->pre_handler)::
+
+	#include <linux/kprobes.h>
+	#include <linux/ptrace.h>
+	int pre_handler(struct kprobe *p, struct pt_regs *regs);
 
 Called with p pointing to the kprobe associated with the breakpoint,
 and regs pointing to the struct containing the registers saved when
 the breakpoint was hit.  Return 0 here unless you're a Kprobes geek.
 
-User's post-handler (kp->post_handler):
-#include <linux/kprobes.h>
-#include <linux/ptrace.h>
-void post_handler(struct kprobe *p, struct pt_regs *regs,
-	unsigned long flags);
+User's post-handler (kp->post_handler)::
+
+	#include <linux/kprobes.h>
+	#include <linux/ptrace.h>
+	void post_handler(struct kprobe *p, struct pt_regs *regs,
+			  unsigned long flags);
 
 p and regs are as described for the pre_handler.  flags always seems
 to be zero.
 
-User's fault-handler (kp->fault_handler):
-#include <linux/kprobes.h>
-#include <linux/ptrace.h>
-int fault_handler(struct kprobe *p, struct pt_regs *regs, int trapnr);
+User's fault-handler (kp->fault_handler)::
+
+	#include <linux/kprobes.h>
+	#include <linux/ptrace.h>
+	int fault_handler(struct kprobe *p, struct pt_regs *regs, int trapnr);
 
 p and regs are as described for the pre_handler.  trapnr is the
 architecture-specific trap number associated with the fault (e.g.,
 on i386, 13 for a general protection fault or 14 for a page fault).
 Returns 1 if it successfully handled the exception.
 
-4.2 register_jprobe
+register_jprobe
+---------------
 
-#include <linux/kprobes.h>
-int register_jprobe(struct jprobe *jp)
+::
+
+	#include <linux/kprobes.h>
+	int register_jprobe(struct jprobe *jp)
 
 Sets a breakpoint at the address jp->kp.addr, which must be the address
 of the first instruction of a function.  When the breakpoint is hit,
@@ -423,10 +467,13 @@
 
 register_jprobe() returns 0 on success, or a negative errno otherwise.
 
-4.3 register_kretprobe
+register_kretprobe
+------------------
 
-#include <linux/kprobes.h>
-int register_kretprobe(struct kretprobe *rp);
+::
+
+	#include <linux/kprobes.h>
+	int register_kretprobe(struct kretprobe *rp);
 
 Establishes a return probe for the function whose address is
 rp->kp.addr.  When that function returns, Kprobes calls rp->handler.
@@ -436,14 +483,17 @@
 register_kretprobe() returns 0 on success, or a negative errno
 otherwise.
 
-User's return-probe handler (rp->handler):
-#include <linux/kprobes.h>
-#include <linux/ptrace.h>
-int kretprobe_handler(struct kretprobe_instance *ri, struct pt_regs *regs);
+User's return-probe handler (rp->handler)::
+
+	#include <linux/kprobes.h>
+	#include <linux/ptrace.h>
+	int kretprobe_handler(struct kretprobe_instance *ri,
+			      struct pt_regs *regs);
 
 regs is as described for kprobe.pre_handler.  ri points to the
 kretprobe_instance object, of which the following fields may be
 of interest:
+
 - ret_addr: the return address
 - rp: points to the corresponding kretprobe object
 - task: points to the corresponding task struct
@@ -456,74 +506,94 @@
 
 The handler's return value is currently ignored.
 
-4.4 unregister_*probe
+unregister_*probe
+------------------
 
-#include <linux/kprobes.h>
-void unregister_kprobe(struct kprobe *kp);
-void unregister_jprobe(struct jprobe *jp);
-void unregister_kretprobe(struct kretprobe *rp);
+::
+
+	#include <linux/kprobes.h>
+	void unregister_kprobe(struct kprobe *kp);
+	void unregister_jprobe(struct jprobe *jp);
+	void unregister_kretprobe(struct kretprobe *rp);
 
 Removes the specified probe.  The unregister function can be called
 at any time after the probe has been registered.
 
-NOTE:
-If the functions find an incorrect probe (ex. an unregistered probe),
-they clear the addr field of the probe.
+.. note::
 
-4.5 register_*probes
+   If the functions find an incorrect probe (ex. an unregistered probe),
+   they clear the addr field of the probe.
 
-#include <linux/kprobes.h>
-int register_kprobes(struct kprobe **kps, int num);
-int register_kretprobes(struct kretprobe **rps, int num);
-int register_jprobes(struct jprobe **jps, int num);
+register_*probes
+----------------
+
+::
+
+	#include <linux/kprobes.h>
+	int register_kprobes(struct kprobe **kps, int num);
+	int register_kretprobes(struct kretprobe **rps, int num);
+	int register_jprobes(struct jprobe **jps, int num);
 
 Registers each of the num probes in the specified array.  If any
 error occurs during registration, all probes in the array, up to
 the bad probe, are safely unregistered before the register_*probes
 function returns.
-- kps/rps/jps: an array of pointers to *probe data structures
+
+- kps/rps/jps: an array of pointers to ``*probe`` data structures
 - num: the number of the array entries.
 
-NOTE:
-You have to allocate(or define) an array of pointers and set all
-of the array entries before using these functions.
+.. note::
 
-4.6 unregister_*probes
+   You have to allocate(or define) an array of pointers and set all
+   of the array entries before using these functions.
 
-#include <linux/kprobes.h>
-void unregister_kprobes(struct kprobe **kps, int num);
-void unregister_kretprobes(struct kretprobe **rps, int num);
-void unregister_jprobes(struct jprobe **jps, int num);
+unregister_*probes
+------------------
+
+::
+
+	#include <linux/kprobes.h>
+	void unregister_kprobes(struct kprobe **kps, int num);
+	void unregister_kretprobes(struct kretprobe **rps, int num);
+	void unregister_jprobes(struct jprobe **jps, int num);
 
 Removes each of the num probes in the specified array at once.
 
-NOTE:
-If the functions find some incorrect probes (ex. unregistered
-probes) in the specified array, they clear the addr field of those
-incorrect probes. However, other probes in the array are
-unregistered correctly.
+.. note::
 
-4.7 disable_*probe
+   If the functions find some incorrect probes (ex. unregistered
+   probes) in the specified array, they clear the addr field of those
+   incorrect probes. However, other probes in the array are
+   unregistered correctly.
 
-#include <linux/kprobes.h>
-int disable_kprobe(struct kprobe *kp);
-int disable_kretprobe(struct kretprobe *rp);
-int disable_jprobe(struct jprobe *jp);
+disable_*probe
+--------------
 
-Temporarily disables the specified *probe. You can enable it again by using
+::
+
+	#include <linux/kprobes.h>
+	int disable_kprobe(struct kprobe *kp);
+	int disable_kretprobe(struct kretprobe *rp);
+	int disable_jprobe(struct jprobe *jp);
+
+Temporarily disables the specified ``*probe``. You can enable it again by using
 enable_*probe(). You must specify the probe which has been registered.
 
-4.8 enable_*probe
+enable_*probe
+-------------
 
-#include <linux/kprobes.h>
-int enable_kprobe(struct kprobe *kp);
-int enable_kretprobe(struct kretprobe *rp);
-int enable_jprobe(struct jprobe *jp);
+::
 
-Enables *probe which has been disabled by disable_*probe(). You must specify
+	#include <linux/kprobes.h>
+	int enable_kprobe(struct kprobe *kp);
+	int enable_kretprobe(struct kretprobe *rp);
+	int enable_jprobe(struct jprobe *jp);
+
+Enables ``*probe`` which has been disabled by disable_*probe(). You must specify
 the probe which has been registered.
 
-5. Kprobes Features and Limitations
+Kprobes Features and Limitations
+================================
 
 Kprobes allows multiple probes at the same address.  Currently,
 however, there cannot be multiple jprobes on the same function at
@@ -538,7 +608,7 @@
 
 The register_*probe functions will return -EINVAL if you attempt
 to install a probe in the code that implements Kprobes (mostly
-kernel/kprobes.c and arch/*/kernel/kprobes.c, but also functions such
+kernel/kprobes.c and ``arch/*/kernel/kprobes.c``, but also functions such
 as do_page_fault and notifier_call_chain).
 
 If you install a probe in an inline-able function, Kprobes makes
@@ -602,19 +672,21 @@
 sequence consisting of a two 2-byte instructions and one 3-byte
 instruction.
 
-        IA
-         |
-[-2][-1][0][1][2][3][4][5][6][7]
-        [ins1][ins2][  ins3 ]
-	[<-     DCR       ->]
-	   [<- JTPR ->]
+::
 
-ins1: 1st Instruction
-ins2: 2nd Instruction
-ins3: 3rd Instruction
-IA:  Insertion Address
-JTPR: Jump Target Prohibition Region
-DCR: Detoured Code Region
+		IA
+		|
+	[-2][-1][0][1][2][3][4][5][6][7]
+		[ins1][ins2][  ins3 ]
+		[<-     DCR       ->]
+		[<- JTPR ->]
+
+	ins1: 1st Instruction
+	ins2: 2nd Instruction
+	ins3: 3rd Instruction
+	IA:  Insertion Address
+	JTPR: Jump Target Prohibition Region
+	DCR: Detoured Code Region
 
 The instructions in DCR are copied to the out-of-line buffer
 of the kprobe, because the bytes in DCR are replaced by
@@ -628,7 +700,8 @@
 Anyway, these limitations are checked by the in-kernel instruction
 decoder, so you don't need to worry about that.
 
-6. Probe Overhead
+Probe Overhead
+==============
 
 On a typical CPU in use in 2005, a kprobe hit takes 0.5 to 1.0
 microseconds to process.  Specifically, a benchmark that hits the same
@@ -638,70 +711,80 @@
 When you have a return probe set on a function, adding a kprobe at
 the entry to that function adds essentially no overhead.
 
-Here are sample overhead figures (in usec) for different architectures.
-k = kprobe; j = jprobe; r = return probe; kr = kprobe + return probe
-on same function; jr = jprobe + return probe on same function
+Here are sample overhead figures (in usec) for different architectures::
 
-i386: Intel Pentium M, 1495 MHz, 2957.31 bogomips
-k = 0.57 usec; j = 1.00; r = 0.92; kr = 0.99; jr = 1.40
+  k = kprobe; j = jprobe; r = return probe; kr = kprobe + return probe
+  on same function; jr = jprobe + return probe on same function::
 
-x86_64: AMD Opteron 246, 1994 MHz, 3971.48 bogomips
-k = 0.49 usec; j = 0.76; r = 0.80; kr = 0.82; jr = 1.07
+  i386: Intel Pentium M, 1495 MHz, 2957.31 bogomips
+  k = 0.57 usec; j = 1.00; r = 0.92; kr = 0.99; jr = 1.40
 
-ppc64: POWER5 (gr), 1656 MHz (SMT disabled, 1 virtual CPU per physical CPU)
-k = 0.77 usec; j = 1.31; r = 1.26; kr = 1.45; jr = 1.99
+  x86_64: AMD Opteron 246, 1994 MHz, 3971.48 bogomips
+  k = 0.49 usec; j = 0.76; r = 0.80; kr = 0.82; jr = 1.07
 
-6.1 Optimized Probe Overhead
+  ppc64: POWER5 (gr), 1656 MHz (SMT disabled, 1 virtual CPU per physical CPU)
+  k = 0.77 usec; j = 1.31; r = 1.26; kr = 1.45; jr = 1.99
+
+Optimized Probe Overhead
+------------------------
 
 Typically, an optimized kprobe hit takes 0.07 to 0.1 microseconds to
-process. Here are sample overhead figures (in usec) for x86 architectures.
-k = unoptimized kprobe, b = boosted (single-step skipped), o = optimized kprobe,
-r = unoptimized kretprobe, rb = boosted kretprobe, ro = optimized kretprobe.
+process. Here are sample overhead figures (in usec) for x86 architectures::
 
-i386: Intel(R) Xeon(R) E5410, 2.33GHz, 4656.90 bogomips
-k = 0.80 usec; b = 0.33; o = 0.05; r = 1.10; rb = 0.61; ro = 0.33
+  k = unoptimized kprobe, b = boosted (single-step skipped), o = optimized kprobe,
+  r = unoptimized kretprobe, rb = boosted kretprobe, ro = optimized kretprobe.
 
-x86-64: Intel(R) Xeon(R) E5410, 2.33GHz, 4656.90 bogomips
-k = 0.99 usec; b = 0.43; o = 0.06; r = 1.24; rb = 0.68; ro = 0.30
+  i386: Intel(R) Xeon(R) E5410, 2.33GHz, 4656.90 bogomips
+  k = 0.80 usec; b = 0.33; o = 0.05; r = 1.10; rb = 0.61; ro = 0.33
 
-7. TODO
+  x86-64: Intel(R) Xeon(R) E5410, 2.33GHz, 4656.90 bogomips
+  k = 0.99 usec; b = 0.43; o = 0.06; r = 1.24; rb = 0.68; ro = 0.30
+
+TODO
+====
 
 a. SystemTap (http://sourceware.org/systemtap): Provides a simplified
-programming interface for probe-based instrumentation.  Try it out.
+   programming interface for probe-based instrumentation.  Try it out.
 b. Kernel return probes for sparc64.
 c. Support for other architectures.
 d. User-space probes.
 e. Watchpoint probes (which fire on data references).
 
-8. Kprobes Example
+Kprobes Example
+===============
 
 See samples/kprobes/kprobe_example.c
 
-9. Jprobes Example
+Jprobes Example
+===============
 
 See samples/kprobes/jprobe_example.c
 
-10. Kretprobes Example
+Kretprobes Example
+==================
 
 See samples/kprobes/kretprobe_example.c
 
 For additional information on Kprobes, refer to the following URLs:
-http://www-106.ibm.com/developerworks/library/l-kprobes.html?ca=dgr-lnxw42Kprobe
-http://www.redhat.com/magazine/005mar05/features/kprobes/
-http://www-users.cs.umn.edu/~boutcher/kprobes/
-http://www.linuxsymposium.org/2006/linuxsymposium_procv2.pdf (pages 101-115)
+
+- http://www-106.ibm.com/developerworks/library/l-kprobes.html?ca=dgr-lnxw42Kprobe
+- http://www.redhat.com/magazine/005mar05/features/kprobes/
+- http://www-users.cs.umn.edu/~boutcher/kprobes/
+- http://www.linuxsymposium.org/2006/linuxsymposium_procv2.pdf (pages 101-115)
 
 
-Appendix A: The kprobes debugfs interface
+The kprobes debugfs interface
+=============================
+
 
 With recent kernels (> 2.6.20) the list of registered kprobes is visible
 under the /sys/kernel/debug/kprobes/ directory (assuming debugfs is mounted at //sys/kernel/debug).
 
-/sys/kernel/debug/kprobes/list: Lists all registered probes on the system
+/sys/kernel/debug/kprobes/list: Lists all registered probes on the system::
 
-c015d71a  k  vfs_read+0x0
-c011a316  j  do_fork+0x0
-c03dedc5  r  tcp_v4_rcv+0x0
+	c015d71a  k  vfs_read+0x0
+	c011a316  j  do_fork+0x0
+	c03dedc5  r  tcp_v4_rcv+0x0
 
 The first column provides the kernel address where the probe is inserted.
 The second column identifies the type of probe (k - kprobe, r - kretprobe
@@ -725,17 +808,19 @@
 [DISABLED]) will be not enabled if you turn ON all kprobes by this knob.
 
 
-Appendix B: The kprobes sysctl interface
+The kprobes sysctl interface
+============================
 
 /proc/sys/debug/kprobes-optimization: Turn kprobes optimization ON/OFF.
 
 When CONFIG_OPTPROBES=y, this sysctl interface appears and it provides
 a knob to globally and forcibly turn jump optimization (see section
-1.4) ON or OFF. By default, jump optimization is allowed (ON).
-If you echo "0" to this file or set "debug.kprobes_optimization" to
-0 via sysctl, all optimized probes will be unoptimized, and any new
-probes registered after that will not be optimized.  Note that this
-knob *changes* the optimized state. This means that optimized probes
-(marked [OPTIMIZED]) will be unoptimized ([OPTIMIZED] tag will be
+:ref:`kprobes_jump_optimization`) ON or OFF. By default, jump optimization
+is allowed (ON). If you echo "0" to this file or set
+"debug.kprobes_optimization" to 0 via sysctl, all optimized probes will be
+unoptimized, and any new probes registered after that will not be optimized.
+
+Note that this knob *changes* the optimized state. This means that optimized
+probes (marked [OPTIMIZED]) will be unoptimized ([OPTIMIZED] tag will be
 removed). If the knob is turned on, they will be optimized again.
 
diff --git a/Documentation/kref.txt b/Documentation/kref.txt
index d26a27c..3af3841 100644
--- a/Documentation/kref.txt
+++ b/Documentation/kref.txt
@@ -1,24 +1,42 @@
+===================================================
+Adding reference counters (krefs) to kernel objects
+===================================================
+
+:Author: Corey Minyard <minyard@acm.org>
+:Author: Thomas Hellstrom <thellstrom@vmware.com>
+
+A lot of this was lifted from Greg Kroah-Hartman's 2004 OLS paper and
+presentation on krefs, which can be found at:
+
+  - http://www.kroah.com/linux/talks/ols_2004_kref_paper/Reprint-Kroah-Hartman-OLS2004.pdf
+  - http://www.kroah.com/linux/talks/ols_2004_kref_talk/
+
+Introduction
+============
 
 krefs allow you to add reference counters to your objects.  If you
 have objects that are used in multiple places and passed around, and
 you don't have refcounts, your code is almost certainly broken.  If
 you want refcounts, krefs are the way to go.
 
-To use a kref, add one to your data structures like:
+To use a kref, add one to your data structures like::
 
-struct my_data
-{
+    struct my_data
+    {
 	.
 	.
 	struct kref refcount;
 	.
 	.
-};
+    };
 
 The kref can occur anywhere within the data structure.
 
+Initialization
+==============
+
 You must initialize the kref after you allocate it.  To do this, call
-kref_init as so:
+kref_init as so::
 
      struct my_data *data;
 
@@ -29,18 +47,25 @@
 
 This sets the refcount in the kref to 1.
 
+Kref rules
+==========
+
 Once you have an initialized kref, you must follow the following
 rules:
 
 1) If you make a non-temporary copy of a pointer, especially if
    it can be passed to another thread of execution, you must
-   increment the refcount with kref_get() before passing it off:
+   increment the refcount with kref_get() before passing it off::
+
        kref_get(&data->refcount);
+
    If you already have a valid pointer to a kref-ed structure (the
    refcount cannot go to zero) you may do this without a lock.
 
-2) When you are done with a pointer, you must call kref_put():
+2) When you are done with a pointer, you must call kref_put()::
+
        kref_put(&data->refcount, data_release);
+
    If this is the last reference to the pointer, the release
    routine will be called.  If the code never tries to get
    a valid pointer to a kref-ed structure without already
@@ -53,25 +78,25 @@
    structure must remain valid during the kref_get().
 
 For example, if you allocate some data and then pass it to another
-thread to process:
+thread to process::
 
-void data_release(struct kref *ref)
-{
+    void data_release(struct kref *ref)
+    {
 	struct my_data *data = container_of(ref, struct my_data, refcount);
 	kfree(data);
-}
+    }
 
-void more_data_handling(void *cb_data)
-{
+    void more_data_handling(void *cb_data)
+    {
 	struct my_data *data = cb_data;
 	.
 	. do stuff with data here
 	.
 	kref_put(&data->refcount, data_release);
-}
+    }
 
-int my_data_handler(void)
-{
+    int my_data_handler(void)
+    {
 	int rv = 0;
 	struct my_data *data;
 	struct task_struct *task;
@@ -91,10 +116,10 @@
 	.
 	. do stuff with data here
 	.
- out:
+    out:
 	kref_put(&data->refcount, data_release);
 	return rv;
-}
+    }
 
 This way, it doesn't matter what order the two threads handle the
 data, the kref_put() handles knowing when the data is not referenced
@@ -104,7 +129,7 @@
 already holding a pointer.
 
 Note that the "before" in rule 1 is very important.  You should never
-do something like:
+do something like::
 
 	task = kthread_run(more_data_handling, data, "more_data_handling");
 	if (task == ERR_PTR(-ENOMEM)) {
@@ -124,14 +149,14 @@
 There are some situations where you can optimize the gets and puts.
 For instance, if you are done with an object and enqueuing it for
 something else or passing it off to something else, there is no reason
-to do a get then a put:
+to do a get then a put::
 
 	/* Silly extra get and put */
 	kref_get(&obj->ref);
 	enqueue(obj);
 	kref_put(&obj->ref, obj_cleanup);
 
-Just do the enqueue.  A comment about this is always welcome:
+Just do the enqueue.  A comment about this is always welcome::
 
 	enqueue(obj);
 	/* We are done with obj, so we pass our refcount off
@@ -142,109 +167,99 @@
 to get the first one.  You can't just pull the first item off the list
 and kref_get() it.  That violates rule 3 because you are not already
 holding a valid pointer.  You must add a mutex (or some other lock).
-For instance:
+For instance::
 
-static DEFINE_MUTEX(mutex);
-static LIST_HEAD(q);
-struct my_data
-{
-	struct kref      refcount;
-	struct list_head link;
-};
+	static DEFINE_MUTEX(mutex);
+	static LIST_HEAD(q);
+	struct my_data
+	{
+		struct kref      refcount;
+		struct list_head link;
+	};
 
-static struct my_data *get_entry()
-{
-	struct my_data *entry = NULL;
-	mutex_lock(&mutex);
-	if (!list_empty(&q)) {
-		entry = container_of(q.next, struct my_data, link);
-		kref_get(&entry->refcount);
+	static struct my_data *get_entry()
+	{
+		struct my_data *entry = NULL;
+		mutex_lock(&mutex);
+		if (!list_empty(&q)) {
+			entry = container_of(q.next, struct my_data, link);
+			kref_get(&entry->refcount);
+		}
+		mutex_unlock(&mutex);
+		return entry;
 	}
-	mutex_unlock(&mutex);
-	return entry;
-}
 
-static void release_entry(struct kref *ref)
-{
-	struct my_data *entry = container_of(ref, struct my_data, refcount);
+	static void release_entry(struct kref *ref)
+	{
+		struct my_data *entry = container_of(ref, struct my_data, refcount);
 
-	list_del(&entry->link);
-	kfree(entry);
-}
+		list_del(&entry->link);
+		kfree(entry);
+	}
 
-static void put_entry(struct my_data *entry)
-{
-	mutex_lock(&mutex);
-	kref_put(&entry->refcount, release_entry);
-	mutex_unlock(&mutex);
-}
+	static void put_entry(struct my_data *entry)
+	{
+		mutex_lock(&mutex);
+		kref_put(&entry->refcount, release_entry);
+		mutex_unlock(&mutex);
+	}
 
 The kref_put() return value is useful if you do not want to hold the
 lock during the whole release operation.  Say you didn't want to call
 kfree() with the lock held in the example above (since it is kind of
-pointless to do so).  You could use kref_put() as follows:
+pointless to do so).  You could use kref_put() as follows::
 
-static void release_entry(struct kref *ref)
-{
-	/* All work is done after the return from kref_put(). */
-}
+	static void release_entry(struct kref *ref)
+	{
+		/* All work is done after the return from kref_put(). */
+	}
 
-static void put_entry(struct my_data *entry)
-{
-	mutex_lock(&mutex);
-	if (kref_put(&entry->refcount, release_entry)) {
-		list_del(&entry->link);
-		mutex_unlock(&mutex);
-		kfree(entry);
-	} else
-		mutex_unlock(&mutex);
-}
+	static void put_entry(struct my_data *entry)
+	{
+		mutex_lock(&mutex);
+		if (kref_put(&entry->refcount, release_entry)) {
+			list_del(&entry->link);
+			mutex_unlock(&mutex);
+			kfree(entry);
+		} else
+			mutex_unlock(&mutex);
+	}
 
 This is really more useful if you have to call other routines as part
 of the free operations that could take a long time or might claim the
 same lock.  Note that doing everything in the release routine is still
 preferred as it is a little neater.
 
-
-Corey Minyard <minyard@acm.org>
-
-A lot of this was lifted from Greg Kroah-Hartman's 2004 OLS paper and
-presentation on krefs, which can be found at:
-  http://www.kroah.com/linux/talks/ols_2004_kref_paper/Reprint-Kroah-Hartman-OLS2004.pdf
-and:
-  http://www.kroah.com/linux/talks/ols_2004_kref_talk/
-
-
 The above example could also be optimized using kref_get_unless_zero() in
-the following way:
+the following way::
 
-static struct my_data *get_entry()
-{
-	struct my_data *entry = NULL;
-	mutex_lock(&mutex);
-	if (!list_empty(&q)) {
-		entry = container_of(q.next, struct my_data, link);
-		if (!kref_get_unless_zero(&entry->refcount))
-			entry = NULL;
+	static struct my_data *get_entry()
+	{
+		struct my_data *entry = NULL;
+		mutex_lock(&mutex);
+		if (!list_empty(&q)) {
+			entry = container_of(q.next, struct my_data, link);
+			if (!kref_get_unless_zero(&entry->refcount))
+				entry = NULL;
+		}
+		mutex_unlock(&mutex);
+		return entry;
 	}
-	mutex_unlock(&mutex);
-	return entry;
-}
 
-static void release_entry(struct kref *ref)
-{
-	struct my_data *entry = container_of(ref, struct my_data, refcount);
+	static void release_entry(struct kref *ref)
+	{
+		struct my_data *entry = container_of(ref, struct my_data, refcount);
 
-	mutex_lock(&mutex);
-	list_del(&entry->link);
-	mutex_unlock(&mutex);
-	kfree(entry);
-}
+		mutex_lock(&mutex);
+		list_del(&entry->link);
+		mutex_unlock(&mutex);
+		kfree(entry);
+	}
 
-static void put_entry(struct my_data *entry)
-{
-	kref_put(&entry->refcount, release_entry);
-}
+	static void put_entry(struct my_data *entry)
+	{
+		kref_put(&entry->refcount, release_entry);
+	}
 
 Which is useful to remove the mutex lock around kref_put() in put_entry(), but
 it's important that kref_get_unless_zero is enclosed in the same critical
@@ -254,51 +269,51 @@
 return value. If you are sure (by already having a valid pointer) that
 kref_get_unless_zero() will return true, then use kref_get() instead.
 
+Krefs and RCU
+=============
+
 The function kref_get_unless_zero also makes it possible to use rcu
-locking for lookups in the above example:
+locking for lookups in the above example::
 
-struct my_data
-{
-	struct rcu_head rhead;
-	.
-	struct kref refcount;
-	.
-	.
-};
+	struct my_data
+	{
+		struct rcu_head rhead;
+		.
+		struct kref refcount;
+		.
+		.
+	};
 
-static struct my_data *get_entry_rcu()
-{
-	struct my_data *entry = NULL;
-	rcu_read_lock();
-	if (!list_empty(&q)) {
-		entry = container_of(q.next, struct my_data, link);
-		if (!kref_get_unless_zero(&entry->refcount))
-			entry = NULL;
+	static struct my_data *get_entry_rcu()
+	{
+		struct my_data *entry = NULL;
+		rcu_read_lock();
+		if (!list_empty(&q)) {
+			entry = container_of(q.next, struct my_data, link);
+			if (!kref_get_unless_zero(&entry->refcount))
+				entry = NULL;
+		}
+		rcu_read_unlock();
+		return entry;
 	}
-	rcu_read_unlock();
-	return entry;
-}
 
-static void release_entry_rcu(struct kref *ref)
-{
-	struct my_data *entry = container_of(ref, struct my_data, refcount);
+	static void release_entry_rcu(struct kref *ref)
+	{
+		struct my_data *entry = container_of(ref, struct my_data, refcount);
 
-	mutex_lock(&mutex);
-	list_del_rcu(&entry->link);
-	mutex_unlock(&mutex);
-	kfree_rcu(entry, rhead);
-}
+		mutex_lock(&mutex);
+		list_del_rcu(&entry->link);
+		mutex_unlock(&mutex);
+		kfree_rcu(entry, rhead);
+	}
 
-static void put_entry(struct my_data *entry)
-{
-	kref_put(&entry->refcount, release_entry_rcu);
-}
+	static void put_entry(struct my_data *entry)
+	{
+		kref_put(&entry->refcount, release_entry_rcu);
+	}
 
 But note that the struct kref member needs to remain in valid memory for a
 rcu grace period after release_entry_rcu was called. That can be accomplished
 by using kfree_rcu(entry, rhead) as done above, or by calling synchronize_rcu()
 before using kfree, but note that synchronize_rcu() may sleep for a
 substantial amount of time.
-
-
-Thomas Hellstrom <thellstrom@vmware.com>
diff --git a/Documentation/ldm.txt b/Documentation/ldm.txt
index 4f80edd..12c5713 100644
--- a/Documentation/ldm.txt
+++ b/Documentation/ldm.txt
@@ -1,9 +1,9 @@
+==========================================
+LDM - Logical Disk Manager (Dynamic Disks)
+==========================================
 
-            LDM - Logical Disk Manager (Dynamic Disks)
-            ------------------------------------------
-
-Originally Written by FlatCap - Richard Russon <ldm@flatcap.org>.
-Last Updated by Anton Altaparmakov on 30 March 2007 for Windows Vista.
+:Author: Originally Written by FlatCap - Richard Russon <ldm@flatcap.org>.
+:Last Updated: Anton Altaparmakov on 30 March 2007 for Windows Vista.
 
 Overview
 --------
@@ -37,24 +37,36 @@
 -------
 
 Below we have a 50MiB disk, divided into seven partitions.
-N.B.  The missing 1MiB at the end of the disk is where the LDM database is
-      stored.
 
-  Device | Offset Bytes  Sectors  MiB | Size   Bytes  Sectors  MiB
-  -------+----------------------------+---------------------------
-  hda    |            0        0    0 |     52428800   102400   50
-  hda1   |     51380224   100352   49 |      1048576     2048    1
-  hda2   |        16384       32    0 |      6979584    13632    6
-  hda3   |      6995968    13664    6 |     10485760    20480   10
-  hda4   |     17481728    34144   16 |      4194304     8192    4
-  hda5   |     21676032    42336   20 |      5242880    10240    5
-  hda6   |     26918912    52576   25 |     10485760    20480   10
-  hda7   |     37404672    73056   35 |     13959168    27264   13
+.. note::
+
+   The missing 1MiB at the end of the disk is where the LDM database is
+   stored.
+
++-------++--------------+---------+-----++--------------+---------+----+
+|Device || Offset Bytes | Sectors | MiB || Size   Bytes | Sectors | MiB|
++=======++==============+=========+=====++==============+=========+====+
+|hda    ||            0 |       0 |   0 ||     52428800 |  102400 |  50|
++-------++--------------+---------+-----++--------------+---------+----+
+|hda1   ||     51380224 |  100352 |  49 ||      1048576 |    2048 |   1|
++-------++--------------+---------+-----++--------------+---------+----+
+|hda2   ||        16384 |      32 |   0 ||      6979584 |   13632 |   6|
++-------++--------------+---------+-----++--------------+---------+----+
+|hda3   ||      6995968 |   13664 |   6 ||     10485760 |   20480 |  10|
++-------++--------------+---------+-----++--------------+---------+----+
+|hda4   ||     17481728 |   34144 |  16 ||      4194304 |    8192 |   4|
++-------++--------------+---------+-----++--------------+---------+----+
+|hda5   ||     21676032 |   42336 |  20 ||      5242880 |   10240 |   5|
++-------++--------------+---------+-----++--------------+---------+----+
+|hda6   ||     26918912 |   52576 |  25 ||     10485760 |   20480 |  10|
++-------++--------------+---------+-----++--------------+---------+----+
+|hda7   ||     37404672 |   73056 |  35 ||     13959168 |   27264 |  13|
++-------++--------------+---------+-----++--------------+---------+----+
 
 The LDM Database may not store the partitions in the order that they appear on
 disk, but the driver will sort them.
 
-When Linux boots, you will see something like:
+When Linux boots, you will see something like::
 
   hda: 102400 sectors w/32KiB Cache, CHS=50/64/32
   hda: [LDM] hda1 hda2 hda3 hda4 hda5 hda6 hda7
@@ -65,13 +77,13 @@
 
 To enable LDM, choose the following two options: 
 
-  "Advanced partition selection" CONFIG_PARTITION_ADVANCED
-  "Windows Logical Disk Manager (Dynamic Disk) support" CONFIG_LDM_PARTITION
+  - "Advanced partition selection" CONFIG_PARTITION_ADVANCED
+  - "Windows Logical Disk Manager (Dynamic Disk) support" CONFIG_LDM_PARTITION
 
 If you believe the driver isn't working as it should, you can enable the extra
 debugging code.  This will produce a LOT of output.  The option is:
 
-  "Windows LDM extra logging" CONFIG_LDM_DEBUG
+  - "Windows LDM extra logging" CONFIG_LDM_DEBUG
 
 N.B. The partition code cannot be compiled as a module.
 
diff --git a/Documentation/lockup-watchdogs.txt b/Documentation/lockup-watchdogs.txt
index c8b8378..290840c 100644
--- a/Documentation/lockup-watchdogs.txt
+++ b/Documentation/lockup-watchdogs.txt
@@ -30,7 +30,8 @@
 to cause the system to reboot automatically after a specified amount
 of time.
 
-=== Implementation ===
+Implementation
+==============
 
 The soft and hard lockup detectors are built on top of the hrtimer and
 perf subsystems, respectively. A direct consequence of this is that,
diff --git a/Documentation/lzo.txt b/Documentation/lzo.txt
index 285c54f..6fa6a93 100644
--- a/Documentation/lzo.txt
+++ b/Documentation/lzo.txt
@@ -1,8 +1,9 @@
-
+===========================================================
 LZO stream format as understood by Linux's LZO decompressor
 ===========================================================
 
 Introduction
+============
 
   This is not a specification. No specification seems to be publicly available
   for the LZO stream format. This document describes what input format the LZO
@@ -14,12 +15,13 @@
   for future bug reports.
 
 Description
+===========
 
   The stream is composed of a series of instructions, operands, and data. The
   instructions consist in a few bits representing an opcode, and bits forming
   the operands for the instruction, whose size and position depend on the
   opcode and on the number of literals copied by previous instruction. The
-  operands are used to indicate :
+  operands are used to indicate:
 
     - a distance when copying data from the dictionary (past output buffer)
     - a length (number of bytes to copy from dictionary)
@@ -38,7 +40,7 @@
   of bits in the operand. If the number of bits isn't enough to represent the
   length, up to 255 may be added in increments by consuming more bytes with a
   rate of at most 255 per extra byte (thus the compression ratio cannot exceed
-  around 255:1). The variable length encoding using #bits is always the same :
+  around 255:1). The variable length encoding using #bits is always the same::
 
        length = byte & ((1 << #bits) - 1)
        if (!length) {
@@ -67,15 +69,19 @@
   instruction may encode this distance (0001HLLL), it takes one LE16 operand
   for the distance, thus requiring 3 bytes.
 
-  IMPORTANT NOTE : in the code some length checks are missing because certain
-  instructions are called under the assumption that a certain number of bytes
-  follow because it has already been guaranteed before parsing the instructions.
-  They just have to "refill" this credit if they consume extra bytes. This is
-  an implementation design choice independent on the algorithm or encoding.
+  .. important::
+
+     In the code some length checks are missing because certain instructions
+     are called under the assumption that a certain number of bytes follow
+     because it has already been guaranteed before parsing the instructions.
+     They just have to "refill" this credit if they consume extra bytes. This
+     is an implementation design choice independent on the algorithm or
+     encoding.
 
 Byte sequences
+==============
 
-  First byte encoding :
+  First byte encoding::
 
       0..17   : follow regular instruction encoding, see below. It is worth
                 noting that codes 16 and 17 will represent a block copy from
@@ -91,7 +97,7 @@
                 state = 4 [ don't copy extra literals ]
                 skip byte
 
-  Instruction encoding :
+  Instruction encoding::
 
       0 0 0 0 X X X X  (0..15)
         Depends on the number of literals copied by the last instruction.
@@ -156,6 +162,7 @@
            distance = (H << 3) + D + 1
 
 Authors
+=======
 
   This document was written by Willy Tarreau <w@1wt.eu> on 2014/07/19 during an
   analysis of the decompression code available in Linux 3.16-rc5. The code is
diff --git a/Documentation/mailbox.txt b/Documentation/mailbox.txt
index 7ed371c..0ed9500 100644
--- a/Documentation/mailbox.txt
+++ b/Documentation/mailbox.txt
@@ -1,7 +1,10 @@
-		The Common Mailbox Framework
-		Jassi Brar <jaswinder.singh@linaro.org>
+============================
+The Common Mailbox Framework
+============================
 
- This document aims to help developers write client and controller
+:Author: Jassi Brar <jaswinder.singh@linaro.org>
+
+This document aims to help developers write client and controller
 drivers for the API. But before we start, let us note that the
 client (especially) and controller drivers are likely going to be
 very platform specific because the remote firmware is likely to be
@@ -13,14 +16,17 @@
 nothing prevents the remote f/w to also be Linux based and use the
 same api there. However none of that helps us locally because we only
 ever deal at client's protocol level.
- Some of the choices made during implementation are the result of this
+
+Some of the choices made during implementation are the result of this
 peculiarity of this "common" framework.
 
 
 
-	Part 1 - Controller Driver (See include/linux/mailbox_controller.h)
+Controller Driver (See include/linux/mailbox_controller.h)
+==========================================================
 
- Allocate mbox_controller and the array of mbox_chan.
+
+Allocate mbox_controller and the array of mbox_chan.
 Populate mbox_chan_ops, except peek_data() all are mandatory.
 The controller driver might know a message has been consumed
 by the remote by getting an IRQ or polling some hardware flag
@@ -30,91 +36,94 @@
 or neither.
 
 
-	Part 2 - Client Driver (See include/linux/mailbox_client.h)
+Client Driver (See include/linux/mailbox_client.h)
+==================================================
 
- The client might want to operate in blocking mode (synchronously
+
+The client might want to operate in blocking mode (synchronously
 send a message through before returning) or non-blocking/async mode (submit
 a message and a callback function to the API and return immediately).
 
+::
 
-struct demo_client {
-	struct mbox_client cl;
-	struct mbox_chan *mbox;
-	struct completion c;
-	bool async;
-	/* ... */
-};
+	struct demo_client {
+		struct mbox_client cl;
+		struct mbox_chan *mbox;
+		struct completion c;
+		bool async;
+		/* ... */
+	};
 
-/*
- * This is the handler for data received from remote. The behaviour is purely
- * dependent upon the protocol. This is just an example.
- */
-static void message_from_remote(struct mbox_client *cl, void *mssg)
-{
-	struct demo_client *dc = container_of(cl, struct demo_client, cl);
-	if (dc->async) {
-		if (is_an_ack(mssg)) {
-			/* An ACK to our last sample sent */
-			return; /* Or do something else here */
-		} else { /* A new message from remote */
-			queue_req(mssg);
+	/*
+	* This is the handler for data received from remote. The behaviour is purely
+	* dependent upon the protocol. This is just an example.
+	*/
+	static void message_from_remote(struct mbox_client *cl, void *mssg)
+	{
+		struct demo_client *dc = container_of(cl, struct demo_client, cl);
+		if (dc->async) {
+			if (is_an_ack(mssg)) {
+				/* An ACK to our last sample sent */
+				return; /* Or do something else here */
+			} else { /* A new message from remote */
+				queue_req(mssg);
+			}
+		} else {
+			/* Remote f/w sends only ACK packets on this channel */
+			return;
 		}
-	} else {
-		/* Remote f/w sends only ACK packets on this channel */
-		return;
 	}
-}
 
-static void sample_sent(struct mbox_client *cl, void *mssg, int r)
-{
-	struct demo_client *dc = container_of(cl, struct demo_client, cl);
-	complete(&dc->c);
-}
+	static void sample_sent(struct mbox_client *cl, void *mssg, int r)
+	{
+		struct demo_client *dc = container_of(cl, struct demo_client, cl);
+		complete(&dc->c);
+	}
 
-static void client_demo(struct platform_device *pdev)
-{
-	struct demo_client *dc_sync, *dc_async;
-	/* The controller already knows async_pkt and sync_pkt */
-	struct async_pkt ap;
-	struct sync_pkt sp;
+	static void client_demo(struct platform_device *pdev)
+	{
+		struct demo_client *dc_sync, *dc_async;
+		/* The controller already knows async_pkt and sync_pkt */
+		struct async_pkt ap;
+		struct sync_pkt sp;
 
-	dc_sync = kzalloc(sizeof(*dc_sync), GFP_KERNEL);
-	dc_async = kzalloc(sizeof(*dc_async), GFP_KERNEL);
+		dc_sync = kzalloc(sizeof(*dc_sync), GFP_KERNEL);
+		dc_async = kzalloc(sizeof(*dc_async), GFP_KERNEL);
 
-	/* Populate non-blocking mode client */
-	dc_async->cl.dev = &pdev->dev;
-	dc_async->cl.rx_callback = message_from_remote;
-	dc_async->cl.tx_done = sample_sent;
-	dc_async->cl.tx_block = false;
-	dc_async->cl.tx_tout = 0; /* doesn't matter here */
-	dc_async->cl.knows_txdone = false; /* depending upon protocol */
-	dc_async->async = true;
-	init_completion(&dc_async->c);
+		/* Populate non-blocking mode client */
+		dc_async->cl.dev = &pdev->dev;
+		dc_async->cl.rx_callback = message_from_remote;
+		dc_async->cl.tx_done = sample_sent;
+		dc_async->cl.tx_block = false;
+		dc_async->cl.tx_tout = 0; /* doesn't matter here */
+		dc_async->cl.knows_txdone = false; /* depending upon protocol */
+		dc_async->async = true;
+		init_completion(&dc_async->c);
 
-	/* Populate blocking mode client */
-	dc_sync->cl.dev = &pdev->dev;
-	dc_sync->cl.rx_callback = message_from_remote;
-	dc_sync->cl.tx_done = NULL; /* operate in blocking mode */
-	dc_sync->cl.tx_block = true;
-	dc_sync->cl.tx_tout = 500; /* by half a second */
-	dc_sync->cl.knows_txdone = false; /* depending upon protocol */
-	dc_sync->async = false;
+		/* Populate blocking mode client */
+		dc_sync->cl.dev = &pdev->dev;
+		dc_sync->cl.rx_callback = message_from_remote;
+		dc_sync->cl.tx_done = NULL; /* operate in blocking mode */
+		dc_sync->cl.tx_block = true;
+		dc_sync->cl.tx_tout = 500; /* by half a second */
+		dc_sync->cl.knows_txdone = false; /* depending upon protocol */
+		dc_sync->async = false;
 
-	/* ASync mailbox is listed second in 'mboxes' property */
-	dc_async->mbox = mbox_request_channel(&dc_async->cl, 1);
-	/* Populate data packet */
-	/* ap.xxx = 123; etc */
-	/* Send async message to remote */
-	mbox_send_message(dc_async->mbox, &ap);
+		/* ASync mailbox is listed second in 'mboxes' property */
+		dc_async->mbox = mbox_request_channel(&dc_async->cl, 1);
+		/* Populate data packet */
+		/* ap.xxx = 123; etc */
+		/* Send async message to remote */
+		mbox_send_message(dc_async->mbox, &ap);
 
-	/* Sync mailbox is listed first in 'mboxes' property */
-	dc_sync->mbox = mbox_request_channel(&dc_sync->cl, 0);
-	/* Populate data packet */
-	/* sp.abc = 123; etc */
-	/* Send message to remote in blocking mode */
-	mbox_send_message(dc_sync->mbox, &sp);
-	/* At this point 'sp' has been sent */
+		/* Sync mailbox is listed first in 'mboxes' property */
+		dc_sync->mbox = mbox_request_channel(&dc_sync->cl, 0);
+		/* Populate data packet */
+		/* sp.abc = 123; etc */
+		/* Send message to remote in blocking mode */
+		mbox_send_message(dc_sync->mbox, &sp);
+		/* At this point 'sp' has been sent */
 
-	/* Now wait for async chan to be done */
-	wait_for_completion(&dc_async->c);
-}
+		/* Now wait for async chan to be done */
+		wait_for_completion(&dc_async->c);
+	}
diff --git a/Documentation/memory-hotplug.txt b/Documentation/memory-hotplug.txt
index 5c628e1..7f49ebf 100644
--- a/Documentation/memory-hotplug.txt
+++ b/Documentation/memory-hotplug.txt
@@ -2,43 +2,48 @@
 Memory Hotplug
 ==============
 
-Created:					Jul 28 2007
-Add description of notifier of memory hotplug	Oct 11 2007
+:Created:							Jul 28 2007
+:Updated: Add description of notifier of memory hotplug:	Oct 11 2007
 
 This document is about memory hotplug including how-to-use and current status.
 Because Memory Hotplug is still under development, contents of this text will
 be changed often.
 
-1. Introduction
-  1.1 purpose of memory hotplug
-  1.2. Phases of memory hotplug
-  1.3. Unit of Memory online/offline operation
-2. Kernel Configuration
-3. sysfs files for memory hotplug
-4. Physical memory hot-add phase
-  4.1 Hardware(Firmware) Support
-  4.2 Notify memory hot-add event by hand
-5. Logical Memory hot-add phase
-  5.1. State of memory
-  5.2. How to online memory
-6. Logical memory remove
-  6.1 Memory offline and ZONE_MOVABLE
-  6.2. How to offline memory
-7. Physical memory remove
-8. Memory hotplug event notifier
-9. Future Work List
+.. CONTENTS
 
-Note(1): x86_64's has special implementation for memory hotplug.
-         This text does not describe it.
-Note(2): This text assumes that sysfs is mounted at /sys.
+  1. Introduction
+    1.1 purpose of memory hotplug
+    1.2. Phases of memory hotplug
+    1.3. Unit of Memory online/offline operation
+  2. Kernel Configuration
+  3. sysfs files for memory hotplug
+  4. Physical memory hot-add phase
+    4.1 Hardware(Firmware) Support
+    4.2 Notify memory hot-add event by hand
+  5. Logical Memory hot-add phase
+    5.1. State of memory
+    5.2. How to online memory
+  6. Logical memory remove
+    6.1 Memory offline and ZONE_MOVABLE
+    6.2. How to offline memory
+  7. Physical memory remove
+  8. Memory hotplug event notifier
+  9. Future Work List
 
 
----------------
-1. Introduction
----------------
+.. note::
 
-1.1 purpose of memory hotplug
-------------
+    (1) x86_64's has special implementation for memory hotplug.
+        This text does not describe it.
+    (2) This text assumes that sysfs is mounted at /sys.
+
+
+Introduction
+============
+
+purpose of memory hotplug
+-------------------------
+
 Memory Hotplug allows users to increase/decrease the amount of memory.
 Generally, there are two purposes.
 
@@ -53,9 +58,11 @@
 Linux memory hotplug is designed for both purpose.
 
 
-1.2. Phases of memory hotplug
----------------
-There are 2 phases in Memory Hotplug.
+Phases of memory hotplug
+------------------------
+
+There are 2 phases in Memory Hotplug:
+
   1) Physical Memory Hotplug phase
   2) Logical Memory Hotplug phase.
 
@@ -70,7 +77,7 @@
 If firmware supports notification of connection of new memory to OS,
 this phase is triggered automatically. ACPI can notify this event. If not,
 "probe" operation by system administration is used instead.
-(see Section 4.).
+(see :ref:`memory_hotplug_physical_mem`).
 
 Logical Memory Hotplug phase is to change memory state into
 available/unavailable for users. Amount of memory from user's view is
@@ -83,11 +90,12 @@
 administrator. For the hot-add case, it must be executed after Physical Hotplug
 phase by hand.
 (However, if you writes udev's hotplug scripts for memory hotplug, these
- phases can be execute in seamless way.)
+phases can be execute in seamless way.)
 
 
-1.3. Unit of Memory online/offline operation
-------------
+Unit of Memory online/offline operation
+---------------------------------------
+
 Memory hotplug uses SPARSEMEM memory model which allows memory to be divided
 into chunks of the same size. These chunks are called "sections". The size of
 a memory section is architecture dependent. For example, power uses 16MiB, ia64
@@ -97,46 +105,50 @@
 size of a memory block is architecture dependent and represents the logical
 unit upon which memory online/offline operations are to be performed. The
 default size of a memory block is the same as memory section size unless an
-architecture specifies otherwise. (see Section 3.)
+architecture specifies otherwise. (see :ref:`memory_hotplug_sysfs_files`.)
 
 To determine the size (in bytes) of a memory block please read this file:
 
 /sys/devices/system/memory/block_size_bytes
 
 
------------------------
-2. Kernel Configuration
------------------------
+Kernel Configuration
+====================
+
 To use memory hotplug feature, kernel must be compiled with following
 config options.
 
-- For all memory hotplug
-    Memory model -> Sparse Memory  (CONFIG_SPARSEMEM)
-    Allow for memory hot-add       (CONFIG_MEMORY_HOTPLUG)
+- For all memory hotplug:
+    - Memory model -> Sparse Memory  (CONFIG_SPARSEMEM)
+    - Allow for memory hot-add       (CONFIG_MEMORY_HOTPLUG)
 
-- To enable memory removal, the following are also necessary
-    Allow for memory hot remove    (CONFIG_MEMORY_HOTREMOVE)
-    Page Migration                 (CONFIG_MIGRATION)
+- To enable memory removal, the following are also necessary:
+    - Allow for memory hot remove    (CONFIG_MEMORY_HOTREMOVE)
+    - Page Migration                 (CONFIG_MIGRATION)
 
-- For ACPI memory hotplug, the following are also necessary
-    Memory hotplug (under ACPI Support menu) (CONFIG_ACPI_HOTPLUG_MEMORY)
-    This option can be kernel module.
+- For ACPI memory hotplug, the following are also necessary:
+    - Memory hotplug (under ACPI Support menu) (CONFIG_ACPI_HOTPLUG_MEMORY)
+    - This option can be kernel module.
 
 - As a related configuration, if your box has a feature of NUMA-node hotplug
   via ACPI, then this option is necessary too.
-    ACPI0004,PNP0A05 and PNP0A06 Container Driver (under ACPI Support menu)
-    (CONFIG_ACPI_CONTAINER).
-    This option can be kernel module too.
+
+    - ACPI0004,PNP0A05 and PNP0A06 Container Driver (under ACPI Support menu)
+      (CONFIG_ACPI_CONTAINER).
+
+     This option can be kernel module too.
 
 
---------------------------------
-3 sysfs files for memory hotplug
---------------------------------
+.. _memory_hotplug_sysfs_files:
+
+sysfs files for memory hotplug
+==============================
+
 All memory blocks have their device information in sysfs.  Each memory block
-is described under /sys/devices/system/memory as
+is described under /sys/devices/system/memory as:
 
-/sys/devices/system/memory/memoryXXX
-(XXX is the memory block id.)
+	/sys/devices/system/memory/memoryXXX
+	(XXX is the memory block id.)
 
 For the memory block covered by the sysfs directory.  It is expected that all
 memory sections in this range are present and no memory holes exist in the
@@ -145,43 +157,53 @@
 block.
 
 For example, assume 1GiB memory block size. A device for a memory starting at
-0x100000000 is /sys/device/system/memory/memory4
-(0x100000000 / 1Gib = 4)
+0x100000000 is /sys/device/system/memory/memory4::
+
+	(0x100000000 / 1Gib = 4)
+
 This device covers address range [0x100000000 ... 0x140000000)
 
 Under each memory block, you can see 5 files:
 
-/sys/devices/system/memory/memoryXXX/phys_index
-/sys/devices/system/memory/memoryXXX/phys_device
-/sys/devices/system/memory/memoryXXX/state
-/sys/devices/system/memory/memoryXXX/removable
-/sys/devices/system/memory/memoryXXX/valid_zones
+- /sys/devices/system/memory/memoryXXX/phys_index
+- /sys/devices/system/memory/memoryXXX/phys_device
+- /sys/devices/system/memory/memoryXXX/state
+- /sys/devices/system/memory/memoryXXX/removable
+- /sys/devices/system/memory/memoryXXX/valid_zones
 
-'phys_index'      : read-only and contains memory block id, same as XXX.
-'state'           : read-write
-                    at read:  contains online/offline state of memory.
-                    at write: user can specify "online_kernel",
+=================== ============================================================
+``phys_index``      read-only and contains memory block id, same as XXX.
+``state``           read-write
+
+                    - at read:  contains online/offline state of memory.
+                    - at write: user can specify "online_kernel",
+
                     "online_movable", "online", "offline" command
                     which will be performed on all sections in the block.
-'phys_device'     : read-only: designed to show the name of physical memory
+``phys_device``     read-only: designed to show the name of physical memory
                     device.  This is not well implemented now.
-'removable'       : read-only: contains an integer value indicating
+``removable``       read-only: contains an integer value indicating
                     whether the memory block is removable or not
                     removable.  A value of 1 indicates that the memory
                     block is removable and a value of 0 indicates that
                     it is not removable. A memory block is removable only if
                     every section in the block is removable.
-'valid_zones'     : read-only: designed to show which zones this memory block
+``valid_zones``     read-only: designed to show which zones this memory block
 		    can be onlined to.
-		    The first column shows it's default zone.
+
+		    The first column shows it`s default zone.
+
 		    "memory6/valid_zones: Normal Movable" shows this memoryblock
 		    can be onlined to ZONE_NORMAL by default and to ZONE_MOVABLE
 		    by online_movable.
+
 		    "memory7/valid_zones: Movable Normal" shows this memoryblock
 		    can be onlined to ZONE_MOVABLE by default and to ZONE_NORMAL
 		    by online_kernel.
+=================== ============================================================
 
-NOTE:
+.. note::
+
   These directories/files appear after physical memory hotplug phase.
 
 If CONFIG_NUMA is enabled the memoryXXX/ directories can also be accessed
@@ -193,13 +215,14 @@
 A backlink will also be created:
 /sys/devices/system/memory/memory9/node0 -> ../../node/node0
 
+.. _memory_hotplug_physical_mem:
 
---------------------------------
-4. Physical memory hot-add phase
---------------------------------
+Physical memory hot-add phase
+=============================
 
-4.1 Hardware(Firmware) Support
-------------
+Hardware(Firmware) Support
+--------------------------
+
 On x86_64/ia64 platform, memory hotplug by ACPI is supported.
 
 In general, the firmware (ACPI) which supports memory hotplug defines
@@ -209,7 +232,8 @@
 
 But scripts for memory hotplug are not contained in generic udev package(now).
 You may have to write it by yourself or online/offline memory by hand.
-Please see "How to online memory", "How to offline memory" in this text.
+Please see :ref:`memory_hotplug_how_to_online_memory` and
+:ref:`memory_hotplug_how_to_offline_memory`.
 
 If firmware supports NUMA-node hotplug, and defines an object _HID "ACPI0004",
 "PNP0A05", or "PNP0A06", notification is asserted to it, and ACPI handler
@@ -217,8 +241,9 @@
 If memory device is found, memory hotplug code will be called.
 
 
-4.2 Notify memory hot-add event by hand
-------------
+Notify memory hot-add event by hand
+-----------------------------------
+
 On some architectures, the firmware may not notify the kernel of a memory
 hotplug event.  Therefore, the memory "probe" interface is supported to
 explicitly notify the kernel.  This interface depends on
@@ -229,45 +254,48 @@
 Probe interface is located at
 /sys/devices/system/memory/probe
 
-You can tell the physical address of new memory to the kernel by
+You can tell the physical address of new memory to the kernel by::
 
-% echo start_address_of_new_memory > /sys/devices/system/memory/probe
+	% echo start_address_of_new_memory > /sys/devices/system/memory/probe
 
 Then, [start_address_of_new_memory, start_address_of_new_memory +
 memory_block_size] memory range is hot-added. In this case, hotplug script is
 not called (in current implementation). You'll have to online memory by
-yourself.  Please see "How to online memory" in this text.
+yourself.  Please see :ref:`memory_hotplug_how_to_online_memory`.
 
 
-------------------------------
-5. Logical Memory hot-add phase
-------------------------------
+Logical Memory hot-add phase
+============================
 
-5.1. State of memory
-------------
-To see (online/offline) state of a memory block, read 'state' file.
+State of memory
+---------------
 
-% cat /sys/device/system/memory/memoryXXX/state
+To see (online/offline) state of a memory block, read 'state' file::
+
+	% cat /sys/device/system/memory/memoryXXX/state
 
 
-If the memory block is online, you'll read "online".
-If the memory block is offline, you'll read "offline".
+- If the memory block is online, you'll read "online".
+- If the memory block is offline, you'll read "offline".
 
 
-5.2. How to online memory
-------------
+.. _memory_hotplug_how_to_online_memory:
+
+How to online memory
+--------------------
+
 When the memory is hot-added, the kernel decides whether or not to "online"
-it according to the policy which can be read from "auto_online_blocks" file:
+it according to the policy which can be read from "auto_online_blocks" file::
 
-% cat /sys/devices/system/memory/auto_online_blocks
+	% cat /sys/devices/system/memory/auto_online_blocks
 
 The default depends on the CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE kernel config
 option. If it is disabled the default is "offline" which means the newly added
 memory is not in a ready-to-use state and you have to "online" the newly added
 memory blocks manually. Automatic onlining can be requested by writing "online"
-to "auto_online_blocks" file:
+to "auto_online_blocks" file::
 
-% echo online > /sys/devices/system/memory/auto_online_blocks
+	% echo online > /sys/devices/system/memory/auto_online_blocks
 
 This sets a global policy and impacts all memory blocks that will subsequently
 be hotplugged. Currently offline blocks keep their state. It is possible, under
@@ -277,24 +305,26 @@
 
 If the automatic onlining wasn't requested, failed, or some memory block was
 offlined it is possible to change the individual block's state by writing to the
-"state" file:
+"state" file::
 
-% echo online > /sys/devices/system/memory/memoryXXX/state
+	% echo online > /sys/devices/system/memory/memoryXXX/state
 
 This onlining will not change the ZONE type of the target memory block,
 If the memory block doesn't belong to any zone an appropriate kernel zone
 (usually ZONE_NORMAL) will be used unless movable_node kernel command line
 option is specified when ZONE_MOVABLE will be used.
 
-You can explicitly request to associate it with ZONE_MOVABLE by
+You can explicitly request to associate it with ZONE_MOVABLE by::
 
-% echo online_movable > /sys/devices/system/memory/memoryXXX/state
-(NOTE: current limit: this memory block must be adjacent to ZONE_MOVABLE)
+	% echo online_movable > /sys/devices/system/memory/memoryXXX/state
 
-Or you can explicitly request a kernel zone (usually ZONE_NORMAL) by:
+.. note:: current limit: this memory block must be adjacent to ZONE_MOVABLE
 
-% echo online_kernel > /sys/devices/system/memory/memoryXXX/state
-(NOTE: current limit: this memory block must be adjacent to ZONE_NORMAL)
+Or you can explicitly request a kernel zone (usually ZONE_NORMAL) by::
+
+	% echo online_kernel > /sys/devices/system/memory/memoryXXX/state
+
+.. note:: current limit: this memory block must be adjacent to ZONE_NORMAL
 
 An explicit zone onlining can fail (e.g. when the range is already within
 and existing and incompatible zone already).
@@ -306,12 +336,12 @@
 
 
 
-------------------------
-6. Logical memory remove
-------------------------
+Logical memory remove
+=====================
 
-6.1 Memory offline and ZONE_MOVABLE
-------------
+Memory offline and ZONE_MOVABLE
+-------------------------------
+
 Memory offlining is more complicated than memory online. Because memory offline
 has to make the whole memory block be unused, memory offline can fail if
 the memory block includes memory which cannot be freed.
@@ -336,24 +366,27 @@
 creates ZONE_MOVABLE as following.
 
 1) When kernelcore=YYYY boot option is used,
-  Size of memory not for movable pages (not for offline) is YYYY.
-  Size of memory for movable pages (for offline) is TOTAL-YYYY.
+   Size of memory not for movable pages (not for offline) is YYYY.
+   Size of memory for movable pages (for offline) is TOTAL-YYYY.
 
 2) When movablecore=ZZZZ boot option is used,
-  Size of memory not for movable pages (not for offline) is TOTAL - ZZZZ.
-  Size of memory for movable pages (for offline) is ZZZZ.
+   Size of memory not for movable pages (not for offline) is TOTAL - ZZZZ.
+   Size of memory for movable pages (for offline) is ZZZZ.
 
+.. note::
 
-Note: Unfortunately, there is no information to show which memory block belongs
-to ZONE_MOVABLE. This is TBD.
+   Unfortunately, there is no information to show which memory block belongs
+   to ZONE_MOVABLE. This is TBD.
 
+.. _memory_hotplug_how_to_offline_memory:
 
-6.2. How to offline memory
-------------
+How to offline memory
+---------------------
+
 You can offline a memory block by using the same sysfs interface that was used
-in memory onlining.
+in memory onlining::
 
-% echo offline > /sys/devices/system/memory/memoryXXX/state
+	% echo offline > /sys/devices/system/memory/memoryXXX/state
 
 If offline succeeds, the state of the memory block is changed to be "offline".
 If it fails, some error core (like -EBUSY) will be returned by the kernel.
@@ -367,22 +400,22 @@
 internal call and released soon.)
 
 Consideration:
-Memory hotplug's design direction is to make the possibility of memory offlining
-higher and to guarantee unplugging memory under any situation. But it needs
-more work. Returning -EBUSY under some situation may be good because the user
-can decide to retry more or not by himself. Currently, memory offlining code
-does some amount of retry with 120 seconds timeout.
+  Memory hotplug's design direction is to make the possibility of memory
+  offlining higher and to guarantee unplugging memory under any situation. But
+  it needs more work. Returning -EBUSY under some situation may be good because
+  the user can decide to retry more or not by himself. Currently, memory
+  offlining code does some amount of retry with 120 seconds timeout.
 
--------------------------
-7. Physical memory remove
--------------------------
+Physical memory remove
+======================
+
 Need more implementation yet....
  - Notification completion of remove works by OS to firmware.
  - Guard from remove if not yet.
 
---------------------------------
-8. Memory hotplug event notifier
---------------------------------
+Memory hotplug event notifier
+=============================
+
 Hotplugging events are sent to a notification queue.
 
 There are six types of notification defined in include/linux/memory.h:
@@ -412,14 +445,14 @@
 MEM_OFFLINE
   Generated after offlining memory is complete.
 
-A callback routine can be registered by calling
+A callback routine can be registered by calling::
 
   hotplug_memory_notifier(callback_func, priority)
 
 Callback functions with higher values of priority are called before callback
 functions with lower values.
 
-A callback function must have the following prototype:
+A callback function must have the following prototype::
 
   int callback_func(
     struct notifier_block *self, unsigned long action, void *arg);
@@ -427,27 +460,28 @@
 The first argument of the callback function (self) is a pointer to the block
 of the notifier chain that points to the callback function itself.
 The second argument (action) is one of the event types described above.
-The third argument (arg) passes a pointer of struct memory_notify.
+The third argument (arg) passes a pointer of struct memory_notify::
 
-struct memory_notify {
-       unsigned long start_pfn;
-       unsigned long nr_pages;
-       int status_change_nid_normal;
-       int status_change_nid_high;
-       int status_change_nid;
-}
+	struct memory_notify {
+		unsigned long start_pfn;
+		unsigned long nr_pages;
+		int status_change_nid_normal;
+		int status_change_nid_high;
+		int status_change_nid;
+	}
 
-start_pfn is start_pfn of online/offline memory.
-nr_pages is # of pages of online/offline memory.
-status_change_nid_normal is set node id when N_NORMAL_MEMORY of nodemask
-is (will be) set/clear, if this is -1, then nodemask status is not changed.
-status_change_nid_high is set node id when N_HIGH_MEMORY of nodemask
-is (will be) set/clear, if this is -1, then nodemask status is not changed.
-status_change_nid is set node id when N_MEMORY of nodemask is (will be)
-set/clear. It means a new(memoryless) node gets new memory by online and a
-node loses all memory. If this is -1, then nodemask status is not changed.
-If status_changed_nid* >= 0, callback should create/discard structures for the
-node if necessary.
+- start_pfn is start_pfn of online/offline memory.
+- nr_pages is # of pages of online/offline memory.
+- status_change_nid_normal is set node id when N_NORMAL_MEMORY of nodemask
+  is (will be) set/clear, if this is -1, then nodemask status is not changed.
+- status_change_nid_high is set node id when N_HIGH_MEMORY of nodemask
+  is (will be) set/clear, if this is -1, then nodemask status is not changed.
+- status_change_nid is set node id when N_MEMORY of nodemask is (will be)
+  set/clear. It means a new(memoryless) node gets new memory by online and a
+  node loses all memory. If this is -1, then nodemask status is not changed.
+
+  If status_changed_nid* >= 0, callback should create/discard structures for the
+  node if necessary.
 
 The callback routine shall return one of the values
 NOTIFY_DONE, NOTIFY_OK, NOTIFY_BAD, NOTIFY_STOP
@@ -461,9 +495,9 @@
 
 NOTIFY_STOP stops further processing of the notification queue.
 
---------------
-9. Future Work
---------------
+Future Work
+===========
+
   - allowing memory hot-add to ZONE_MOVABLE. maybe we need some switch like
     sysctl or new control file.
   - showing memory block and physical device relationship.
@@ -471,4 +505,3 @@
   - support HugeTLB page migration and offlining.
   - memmap removing at memory offline.
   - physical remove memory.
-
diff --git a/Documentation/men-chameleon-bus.txt b/Documentation/men-chameleon-bus.txt
index 30ded73..1b1f048 100644
--- a/Documentation/men-chameleon-bus.txt
+++ b/Documentation/men-chameleon-bus.txt
@@ -1,163 +1,175 @@
-                               MEN Chameleon Bus
-                               =================
-
-Table of Contents
 =================
-1 Introduction
-    1.1 Scope of this Document
-    1.2 Limitations of the current implementation
-2 Architecture
-    2.1 MEN Chameleon Bus
-    2.2 Carrier Devices
-    2.3 Parser
-3 Resource handling
-    3.1 Memory Resources
-    3.2 IRQs
-4 Writing an MCB driver
-    4.1 The driver structure
-    4.2 Probing and attaching
-    4.3 Initializing the driver
+MEN Chameleon Bus
+=================
+
+.. Table of Contents
+   =================
+   1 Introduction
+       1.1 Scope of this Document
+       1.2 Limitations of the current implementation
+   2 Architecture
+       2.1 MEN Chameleon Bus
+       2.2 Carrier Devices
+       2.3 Parser
+   3 Resource handling
+       3.1 Memory Resources
+       3.2 IRQs
+   4 Writing an MCB driver
+       4.1 The driver structure
+       4.2 Probing and attaching
+       4.3 Initializing the driver
 
 
-1 Introduction
-===============
-  This document describes the architecture and implementation of the MEN
-  Chameleon Bus (called MCB throughout this document).
+Introduction
+============
 
-1.1 Scope of this Document
----------------------------
-  This document is intended to be a short overview of the current
-  implementation and does by no means describe the complete possibilities of MCB
-  based devices.
+This document describes the architecture and implementation of the MEN
+Chameleon Bus (called MCB throughout this document).
 
-1.2 Limitations of the current implementation
-----------------------------------------------
-  The current implementation is limited to PCI and PCIe based carrier devices
-  that only use a single memory resource and share the PCI legacy IRQ.  Not
-  implemented are:
-  - Multi-resource MCB devices like the VME Controller or M-Module carrier.
-  - MCB devices that need another MCB device, like SRAM for a DMA Controller's
-    buffer descriptors or a video controller's video memory.
-  - A per-carrier IRQ domain for carrier devices that have one (or more) IRQs
-    per MCB device like PCIe based carriers with MSI or MSI-X support.
-
-2 Architecture
-===============
-  MCB is divided into 3 functional blocks:
-  - The MEN Chameleon Bus itself,
-  - drivers for MCB Carrier Devices and
-  - the parser for the Chameleon table.
-
-2.1 MEN Chameleon Bus
+Scope of this Document
 ----------------------
-   The MEN Chameleon Bus is an artificial bus system that attaches to a so
-   called Chameleon FPGA device found on some hardware produced my MEN Mikro
-   Elektronik GmbH. These devices are multi-function devices implemented in a
-   single FPGA and usually attached via some sort of PCI or PCIe link. Each
-   FPGA contains a header section describing the content of the FPGA. The
-   header lists the device id, PCI BAR, offset from the beginning of the PCI
-   BAR, size in the FPGA, interrupt number and some other properties currently
-   not handled by the MCB implementation.
 
-2.2 Carrier Devices
+This document is intended to be a short overview of the current
+implementation and does by no means describe the complete possibilities of MCB
+based devices.
+
+Limitations of the current implementation
+-----------------------------------------
+
+The current implementation is limited to PCI and PCIe based carrier devices
+that only use a single memory resource and share the PCI legacy IRQ.  Not
+implemented are:
+
+- Multi-resource MCB devices like the VME Controller or M-Module carrier.
+- MCB devices that need another MCB device, like SRAM for a DMA Controller's
+  buffer descriptors or a video controller's video memory.
+- A per-carrier IRQ domain for carrier devices that have one (or more) IRQs
+  per MCB device like PCIe based carriers with MSI or MSI-X support.
+
+Architecture
+============
+
+MCB is divided into 3 functional blocks:
+
+- The MEN Chameleon Bus itself,
+- drivers for MCB Carrier Devices and
+- the parser for the Chameleon table.
+
+MEN Chameleon Bus
+-----------------
+
+The MEN Chameleon Bus is an artificial bus system that attaches to a so
+called Chameleon FPGA device found on some hardware produced my MEN Mikro
+Elektronik GmbH. These devices are multi-function devices implemented in a
+single FPGA and usually attached via some sort of PCI or PCIe link. Each
+FPGA contains a header section describing the content of the FPGA. The
+header lists the device id, PCI BAR, offset from the beginning of the PCI
+BAR, size in the FPGA, interrupt number and some other properties currently
+not handled by the MCB implementation.
+
+Carrier Devices
+---------------
+
+A carrier device is just an abstraction for the real world physical bus the
+Chameleon FPGA is attached to. Some IP Core drivers may need to interact with
+properties of the carrier device (like querying the IRQ number of a PCI
+device). To provide abstraction from the real hardware bus, an MCB carrier
+device provides callback methods to translate the driver's MCB function calls
+to hardware related function calls. For example a carrier device may
+implement the get_irq() method which can be translated into a hardware bus
+query for the IRQ number the device should use.
+
+Parser
+------
+
+The parser reads the first 512 bytes of a Chameleon device and parses the
+Chameleon table. Currently the parser only supports the Chameleon v2 variant
+of the Chameleon table but can easily be adopted to support an older or
+possible future variant. While parsing the table's entries new MCB devices
+are allocated and their resources are assigned according to the resource
+assignment in the Chameleon table. After resource assignment is finished, the
+MCB devices are registered at the MCB and thus at the driver core of the
+Linux kernel.
+
+Resource handling
+=================
+
+The current implementation assigns exactly one memory and one IRQ resource
+per MCB device. But this is likely going to change in the future.
+
+Memory Resources
+----------------
+
+Each MCB device has exactly one memory resource, which can be requested from
+the MCB bus. This memory resource is the physical address of the MCB device
+inside the carrier and is intended to be passed to ioremap() and friends. It
+is already requested from the kernel by calling request_mem_region().
+
+IRQs
+----
+
+Each MCB device has exactly one IRQ resource, which can be requested from the
+MCB bus. If a carrier device driver implements the ->get_irq() callback
+method, the IRQ number assigned by the carrier device will be returned,
+otherwise the IRQ number inside the Chameleon table will be returned. This
+number is suitable to be passed to request_irq().
+
+Writing an MCB driver
+=====================
+
+The driver structure
 --------------------
-   A carrier device is just an abstraction for the real world physical bus the
-   Chameleon FPGA is attached to. Some IP Core drivers may need to interact with
-   properties of the carrier device (like querying the IRQ number of a PCI
-   device). To provide abstraction from the real hardware bus, an MCB carrier
-   device provides callback methods to translate the driver's MCB function calls
-   to hardware related function calls. For example a carrier device may
-   implement the get_irq() method which can be translated into a hardware bus
-   query for the IRQ number the device should use.
 
-2.3 Parser
------------
-   The parser reads the first 512 bytes of a Chameleon device and parses the
-   Chameleon table. Currently the parser only supports the Chameleon v2 variant
-   of the Chameleon table but can easily be adopted to support an older or
-   possible future variant. While parsing the table's entries new MCB devices
-   are allocated and their resources are assigned according to the resource
-   assignment in the Chameleon table. After resource assignment is finished, the
-   MCB devices are registered at the MCB and thus at the driver core of the
-   Linux kernel.
+Each MCB driver has a structure to identify the device driver as well as
+device ids which identify the IP Core inside the FPGA. The driver structure
+also contains callback methods which get executed on driver probe and
+removal from the system::
 
-3 Resource handling
-====================
-  The current implementation assigns exactly one memory and one IRQ resource
-  per MCB device. But this is likely going to change in the future.
+	static const struct mcb_device_id foo_ids[] = {
+		{ .device = 0x123 },
+		{ }
+	};
+	MODULE_DEVICE_TABLE(mcb, foo_ids);
 
-3.1 Memory Resources
+	static struct mcb_driver foo_driver = {
+	driver = {
+		.name = "foo-bar",
+		.owner = THIS_MODULE,
+	},
+		.probe = foo_probe,
+		.remove = foo_remove,
+		.id_table = foo_ids,
+	};
+
+Probing and attaching
 ---------------------
-   Each MCB device has exactly one memory resource, which can be requested from
-   the MCB bus. This memory resource is the physical address of the MCB device
-   inside the carrier and is intended to be passed to ioremap() and friends. It
-   is already requested from the kernel by calling request_mem_region().
 
-3.2 IRQs
----------
-   Each MCB device has exactly one IRQ resource, which can be requested from the
-   MCB bus. If a carrier device driver implements the ->get_irq() callback
-   method, the IRQ number assigned by the carrier device will be returned,
-   otherwise the IRQ number inside the Chameleon table will be returned. This
-   number is suitable to be passed to request_irq().
+When a driver is loaded and the MCB devices it services are found, the MCB
+core will call the driver's probe callback method. When the driver is removed
+from the system, the MCB core will call the driver's remove callback method::
 
-4 Writing an MCB driver
-=======================
+	static init foo_probe(struct mcb_device *mdev, const struct mcb_device_id *id);
+	static void foo_remove(struct mcb_device *mdev);
 
-4.1 The driver structure
--------------------------
-    Each MCB driver has a structure to identify the device driver as well as
-    device ids which identify the IP Core inside the FPGA. The driver structure
-    also contains callback methods which get executed on driver probe and
-    removal from the system.
+Initializing the driver
+-----------------------
 
+When the kernel is booted or your foo driver module is inserted, you have to
+perform driver initialization. Usually it is enough to register your driver
+module at the MCB core::
 
-  static const struct mcb_device_id foo_ids[] = {
-          { .device = 0x123 },
-          { }
-  };
-  MODULE_DEVICE_TABLE(mcb, foo_ids);
+	static int __init foo_init(void)
+	{
+		return mcb_register_driver(&foo_driver);
+	}
+	module_init(foo_init);
 
-  static struct mcb_driver foo_driver = {
-          driver = {
-                  .name = "foo-bar",
-                  .owner = THIS_MODULE,
-          },
-          .probe = foo_probe,
-          .remove = foo_remove,
-          .id_table = foo_ids,
-  };
+	static void __exit foo_exit(void)
+	{
+		mcb_unregister_driver(&foo_driver);
+	}
+	module_exit(foo_exit);
 
-4.2 Probing and attaching
---------------------------
-   When a driver is loaded and the MCB devices it services are found, the MCB
-   core will call the driver's probe callback method. When the driver is removed
-   from the system, the MCB core will call the driver's remove callback method.
+The module_mcb_driver() macro can be used to reduce the above code::
 
-
-  static init foo_probe(struct mcb_device *mdev, const struct mcb_device_id *id);
-  static void foo_remove(struct mcb_device *mdev);
-
-4.3 Initializing the driver
-----------------------------
-   When the kernel is booted or your foo driver module is inserted, you have to
-   perform driver initialization. Usually it is enough to register your driver
-   module at the MCB core.
-
-
-  static int __init foo_init(void)
-  {
-          return mcb_register_driver(&foo_driver);
-  }
-  module_init(foo_init);
-
-  static void __exit foo_exit(void)
-  {
-          mcb_unregister_driver(&foo_driver);
-  }
-  module_exit(foo_exit);
-
-   The module_mcb_driver() macro can be used to reduce the above code.
-
-
-  module_mcb_driver(foo_driver);
+	module_mcb_driver(foo_driver);
diff --git a/Documentation/nommu-mmap.txt b/Documentation/nommu-mmap.txt
index ae57b9e..69556f0 100644
--- a/Documentation/nommu-mmap.txt
+++ b/Documentation/nommu-mmap.txt
@@ -1,6 +1,6 @@
-			 =============================
-			 NO-MMU MEMORY MAPPING SUPPORT
-			 =============================
+=============================
+No-MMU memory mapping support
+=============================
 
 The kernel has limited support for memory mapping under no-MMU conditions, such
 as are used in uClinux environments. From the userspace point of view, memory
@@ -16,7 +16,7 @@
 The behaviour is similar between the MMU and no-MMU cases, but not identical;
 and it's also much more restricted in the latter case:
 
- (*) Anonymous mapping, MAP_PRIVATE
+ (#) Anonymous mapping, MAP_PRIVATE
 
 	In the MMU case: VM regions backed by arbitrary pages; copy-on-write
 	across fork.
@@ -24,14 +24,14 @@
 	In the no-MMU case: VM regions backed by arbitrary contiguous runs of
 	pages.
 
- (*) Anonymous mapping, MAP_SHARED
+ (#) Anonymous mapping, MAP_SHARED
 
 	These behave very much like private mappings, except that they're
 	shared across fork() or clone() without CLONE_VM in the MMU case. Since
 	the no-MMU case doesn't support these, behaviour is identical to
 	MAP_PRIVATE there.
 
- (*) File, MAP_PRIVATE, PROT_READ / PROT_EXEC, !PROT_WRITE
+ (#) File, MAP_PRIVATE, PROT_READ / PROT_EXEC, !PROT_WRITE
 
 	In the MMU case: VM regions backed by pages read from file; changes to
 	the underlying file are reflected in the mapping; copied across fork.
@@ -56,7 +56,7 @@
 	   are visible in other processes (no MMU protection), but should not
 	   happen.
 
- (*) File, MAP_PRIVATE, PROT_READ / PROT_EXEC, PROT_WRITE
+ (#) File, MAP_PRIVATE, PROT_READ / PROT_EXEC, PROT_WRITE
 
 	In the MMU case: like the non-PROT_WRITE case, except that the pages in
 	question get copied before the write actually happens. From that point
@@ -66,7 +66,7 @@
 	In the no-MMU case: works much like the non-PROT_WRITE case, except
 	that a copy is always taken and never shared.
 
- (*) Regular file / blockdev, MAP_SHARED, PROT_READ / PROT_EXEC / PROT_WRITE
+ (#) Regular file / blockdev, MAP_SHARED, PROT_READ / PROT_EXEC / PROT_WRITE
 
 	In the MMU case: VM regions backed by pages read from file; changes to
 	pages written back to file; writes to file reflected into pages backing
@@ -74,7 +74,7 @@
 
 	In the no-MMU case: not supported.
 
- (*) Memory backed regular file, MAP_SHARED, PROT_READ / PROT_EXEC / PROT_WRITE
+ (#) Memory backed regular file, MAP_SHARED, PROT_READ / PROT_EXEC / PROT_WRITE
 
 	In the MMU case: As for ordinary regular files.
 
@@ -85,7 +85,7 @@
 	as for the MMU case. If the filesystem does not provide any such
 	support, then the mapping request will be denied.
 
- (*) Memory backed blockdev, MAP_SHARED, PROT_READ / PROT_EXEC / PROT_WRITE
+ (#) Memory backed blockdev, MAP_SHARED, PROT_READ / PROT_EXEC / PROT_WRITE
 
 	In the MMU case: As for ordinary regular files.
 
@@ -94,7 +94,7 @@
 	truncate being called. The ramdisk driver could do this if it allocated
 	all its memory as a contiguous array upfront.
 
- (*) Memory backed chardev, MAP_SHARED, PROT_READ / PROT_EXEC / PROT_WRITE
+ (#) Memory backed chardev, MAP_SHARED, PROT_READ / PROT_EXEC / PROT_WRITE
 
 	In the MMU case: As for ordinary regular files.
 
@@ -105,21 +105,20 @@
 	provide any such support, then the mapping request will be denied.
 
 
-============================
-FURTHER NOTES ON NO-MMU MMAP
+Further notes on no-MMU MMAP
 ============================
 
- (*) A request for a private mapping of a file may return a buffer that is not
+ (#) A request for a private mapping of a file may return a buffer that is not
      page-aligned.  This is because XIP may take place, and the data may not be
      paged aligned in the backing store.
 
- (*) A request for an anonymous mapping will always be page aligned.  If
+ (#) A request for an anonymous mapping will always be page aligned.  If
      possible the size of the request should be a power of two otherwise some
      of the space may be wasted as the kernel must allocate a power-of-2
      granule but will only discard the excess if appropriately configured as
      this has an effect on fragmentation.
 
- (*) The memory allocated by a request for an anonymous mapping will normally
+ (#) The memory allocated by a request for an anonymous mapping will normally
      be cleared by the kernel before being returned in accordance with the
      Linux man pages (ver 2.22 or later).
 
@@ -145,24 +144,23 @@
      uClibc uses this to speed up malloc(), and the ELF-FDPIC binfmt uses this
      to allocate the brk and stack region.
 
- (*) A list of all the private copy and anonymous mappings on the system is
+ (#) A list of all the private copy and anonymous mappings on the system is
      visible through /proc/maps in no-MMU mode.
 
- (*) A list of all the mappings in use by a process is visible through
+ (#) A list of all the mappings in use by a process is visible through
      /proc/<pid>/maps in no-MMU mode.
 
- (*) Supplying MAP_FIXED or a requesting a particular mapping address will
+ (#) Supplying MAP_FIXED or a requesting a particular mapping address will
      result in an error.
 
- (*) Files mapped privately usually have to have a read method provided by the
+ (#) Files mapped privately usually have to have a read method provided by the
      driver or filesystem so that the contents can be read into the memory
      allocated if mmap() chooses not to map the backing device directly. An
      error will result if they don't. This is most likely to be encountered
      with character device files, pipes, fifos and sockets.
 
 
-==========================
-INTERPROCESS SHARED MEMORY
+Interprocess shared memory
 ==========================
 
 Both SYSV IPC SHM shared memory and POSIX shared memory is supported in NOMMU
@@ -170,8 +168,7 @@
 on ramfs or tmpfs mounts.
 
 
-=======
-FUTEXES
+Futexes
 =======
 
 Futexes are supported in NOMMU mode if the arch supports them.  An error will
@@ -180,12 +177,11 @@
 support futexes (such as an I/O chardev mapping).
 
 
-=============
-NO-MMU MREMAP
+No-MMU mremap
 =============
 
 The mremap() function is partially supported.  It may change the size of a
-mapping, and may move it[*] if MREMAP_MAYMOVE is specified and if the new size
+mapping, and may move it [#]_ if MREMAP_MAYMOVE is specified and if the new size
 of the mapping exceeds the size of the slab object currently occupied by the
 memory to which the mapping refers, or if a smaller slab object could be used.
 
@@ -200,11 +196,10 @@
 mappings, move parts of existing mappings or resize parts of mappings.  It must
 act on a complete mapping.
 
-[*] Not currently supported.
+.. [#] Not currently supported.
 
 
-============================================
-PROVIDING SHAREABLE CHARACTER DEVICE SUPPORT
+Providing shareable character device support
 ============================================
 
 To provide shareable character device support, a driver must provide a
@@ -235,7 +230,7 @@
 mapping request will be rejected if NOMMU_MAP_COPY is not specified, and a
 copy mapped otherwise.
 
-IMPORTANT NOTE:
+.. important::
 
 	Some types of device may present a different appearance to anyone
 	looking at them in certain modes. Flash chips can be like this; for
@@ -249,8 +244,7 @@
 	circumstances!
 
 
-==============================================
-PROVIDING SHAREABLE MEMORY-BACKED FILE SUPPORT
+Providing shareable memory-backed file support
 ==============================================
 
 Provision of shared mappings on memory backed files is similar to the provision
@@ -267,8 +261,7 @@
 the memory_backed flag set.
 
 
-========================================
-PROVIDING SHAREABLE BLOCK DEVICE SUPPORT
+Providing shareable block device support
 ========================================
 
 Provision of shared mappings on block device files is exactly the same as for
@@ -276,8 +269,7 @@
 should allocate sufficient contiguous memory to honour any supported mapping.
 
 
-=================================
-ADJUSTING PAGE TRIMMING BEHAVIOUR
+Adjusting page trimming behaviour
 =================================
 
 NOMMU mmap automatically rounds up to the nearest power-of-2 number of pages
@@ -288,4 +280,4 @@
 behaviour can either be disabled completely, or bumped up to a higher page
 watermark where trimming begins.
 
-Page trimming behaviour is configurable via the sysctl `vm.nr_trim_pages'.
+Page trimming behaviour is configurable via the sysctl ``vm.nr_trim_pages``.
diff --git a/Documentation/ntb.txt b/Documentation/ntb.txt
index a5af4f0..a043854 100644
--- a/Documentation/ntb.txt
+++ b/Documentation/ntb.txt
@@ -1,4 +1,6 @@
-# NTB Drivers
+===========
+NTB Drivers
+===========
 
 NTB (Non-Transparent Bridge) is a type of PCI-Express bridge chip that connects
 the separate memory systems of two or more computers to the same PCI-Express
@@ -12,7 +14,8 @@
 peer. Doorbell registers provide a way for peers to send interrupt events.
 Memory windows allow translated read and write access to the peer memory.
 
-## NTB Core Driver (ntb)
+NTB Core Driver (ntb)
+=====================
 
 The NTB core driver defines an api wrapping the common feature set, and allows
 clients interested in NTB features to discover NTB the devices supported by
@@ -20,7 +23,8 @@
 component making use of the NTB api.  The term "driver," or "hardware driver,"
 is used here to mean a driver for a specific vendor and model of NTB hardware.
 
-## NTB Client Drivers
+NTB Client Drivers
+==================
 
 NTB client drivers should register with the NTB core driver.  After
 registering, the client probe and remove functions will be called appropriately
@@ -28,7 +32,8 @@
 registration uses the Linux Device framework, so it should feel familiar to
 anyone who has written a pci driver.
 
-### NTB Typical client driver implementation
+NTB Typical client driver implementation
+----------------------------------------
 
 Primary purpose of NTB is to share some peace of memory between at least two
 systems. So the NTB device features like Scratchpad/Message registers are
@@ -109,7 +114,8 @@
 Also it is worth to note, that method ntb_mw_count(pidx) should return the
 same value as ntb_peer_mw_count() on the peer with port index - pidx.
 
-### NTB Transport Client (ntb\_transport) and NTB Netdev (ntb\_netdev)
+NTB Transport Client (ntb\_transport) and NTB Netdev (ntb\_netdev)
+------------------------------------------------------------------
 
 The primary client for NTB is the Transport client, used in tandem with NTB
 Netdev.  These drivers function together to create a logical link to the peer,
@@ -120,7 +126,8 @@
 Transport queue pair buffer.  The Transport client may be used for other things
 besides Netdev, however no other applications have yet been written.
 
-### NTB Ping Pong Test Client (ntb\_pingpong)
+NTB Ping Pong Test Client (ntb\_pingpong)
+-----------------------------------------
 
 The Ping Pong test client serves as a demonstration to exercise the doorbell
 and scratchpad registers of NTB hardware, and as an example simple NTB client.
@@ -147,7 +154,8 @@
 * dyndbg - It is suggested to specify dyndbg=+p when loading this module, and
 	then to observe debugging output on the console.
 
-### NTB Tool Test Client (ntb\_tool)
+NTB Tool Test Client (ntb\_tool)
+--------------------------------
 
 The Tool test client serves for debugging, primarily, ntb hardware and drivers.
 The Tool provides access through debugfs for reading, setting, and clearing the
@@ -157,48 +165,60 @@
 
 Debugfs Files:
 
-* *debugfs*/ntb\_tool/*hw*/ - A directory in debugfs will be created for each
+* *debugfs*/ntb\_tool/*hw*/
+	A directory in debugfs will be created for each
 	NTB device probed by the tool.  This directory is shortened to *hw*
 	below.
-* *hw*/db - This file is used to read, set, and clear the local doorbell.  Not
+* *hw*/db
+	This file is used to read, set, and clear the local doorbell.  Not
 	all operations may be supported by all hardware.  To read the doorbell,
 	read the file.  To set the doorbell, write `s` followed by the bits to
 	set (eg: `echo 's 0x0101' > db`).  To clear the doorbell, write `c`
 	followed by the bits to clear.
-* *hw*/mask - This file is used to read, set, and clear the local doorbell mask.
+* *hw*/mask
+	This file is used to read, set, and clear the local doorbell mask.
 	See *db* for details.
-* *hw*/peer\_db - This file is used to read, set, and clear the peer doorbell.
+* *hw*/peer\_db
+	This file is used to read, set, and clear the peer doorbell.
 	See *db* for details.
-* *hw*/peer\_mask - This file is used to read, set, and clear the peer doorbell
+* *hw*/peer\_mask
+	This file is used to read, set, and clear the peer doorbell
 	mask.  See *db* for details.
-* *hw*/spad - This file is used to read and write local scratchpads.  To read
+* *hw*/spad
+	This file is used to read and write local scratchpads.  To read
 	the values of all scratchpads, read the file.  To write values, write a
 	series of pairs of scratchpad number and value
 	(eg: `echo '4 0x123 7 0xabc' > spad`
 	# to set scratchpads `4` and `7` to `0x123` and `0xabc`, respectively).
-* *hw*/peer\_spad - This file is used to read and write peer scratchpads.  See
+* *hw*/peer\_spad
+	This file is used to read and write peer scratchpads.  See
 	*spad* for details.
 
-## NTB Hardware Drivers
+NTB Hardware Drivers
+====================
 
 NTB hardware drivers should register devices with the NTB core driver.  After
 registering, clients probe and remove functions will be called.
 
-### NTB Intel Hardware Driver (ntb\_hw\_intel)
+NTB Intel Hardware Driver (ntb\_hw\_intel)
+------------------------------------------
 
 The Intel hardware driver supports NTB on Xeon and Atom CPUs.
 
 Module Parameters:
 
-* b2b\_mw\_idx - If the peer ntb is to be accessed via a memory window, then use
+* b2b\_mw\_idx
+	If the peer ntb is to be accessed via a memory window, then use
 	this memory window to access the peer ntb.  A value of zero or positive
 	starts from the first mw idx, and a negative value starts from the last
 	mw idx.  Both sides MUST set the same value here!  The default value is
 	`-1`.
-* b2b\_mw\_share - If the peer ntb is to be accessed via a memory window, and if
+* b2b\_mw\_share
+	If the peer ntb is to be accessed via a memory window, and if
 	the memory window is large enough, still allow the client to use the
 	second half of the memory window for address translation to the peer.
-* xeon\_b2b\_usd\_bar2\_addr64 - If using B2B topology on Xeon hardware, use
+* xeon\_b2b\_usd\_bar2\_addr64
+	If using B2B topology on Xeon hardware, use
 	this 64 bit address on the bus between the NTB devices for the window
 	at BAR2, on the upstream side of the link.
 * xeon\_b2b\_usd\_bar4\_addr64 - See *xeon\_b2b\_bar2\_addr64*.
diff --git a/Documentation/numastat.txt b/Documentation/numastat.txt
index 5203277..aaf1667 100644
--- a/Documentation/numastat.txt
+++ b/Documentation/numastat.txt
@@ -1,10 +1,12 @@
-
+===============================
 Numa policy hit/miss statistics
+===============================
 
 /sys/devices/system/node/node*/numastat
 
 All units are pages. Hugepages have separate counters.
 
+=============== ============================================================
 numa_hit	A process wanted to allocate memory from this node,
 		and succeeded.
 
@@ -20,6 +22,7 @@
 
 interleave_hit 	Interleaving wanted to allocate from this node
 		and succeeded.
+=============== ============================================================
 
 For easier reading you can use the numastat utility from the numactl package
 (http://oss.sgi.com/projects/libnuma/). Note that it only works
diff --git a/Documentation/padata.txt b/Documentation/padata.txt
index 7ddfe21..b103d0c 100644
--- a/Documentation/padata.txt
+++ b/Documentation/padata.txt
@@ -1,5 +1,8 @@
+=======================================
 The padata parallel execution mechanism
-Last updated for 2.6.36
+=======================================
+
+:Last updated: for 2.6.36
 
 Padata is a mechanism by which the kernel can farm work out to be done in
 parallel on multiple CPUs while retaining the ordering of tasks.  It was
@@ -9,7 +12,7 @@
 sufficiently general fashion that it could be put to other uses as well.
 
 The first step in using padata is to set up a padata_instance structure for
-overall control of how tasks are to be run:
+overall control of how tasks are to be run::
 
     #include <linux/padata.h>
 
@@ -24,7 +27,7 @@
 a multithreaded queue, naturally.
 
 To allocate a padata instance with the cpu_possible_mask for both
-cpumasks this helper function can be used:
+cpumasks this helper function can be used::
 
     struct padata_instance *padata_alloc_possible(struct workqueue_struct *wq);
 
@@ -36,7 +39,7 @@
 Once an offline CPU in the user supplied cpumask comes online, padata
 is going to use it.
 
-There are functions for enabling and disabling the instance:
+There are functions for enabling and disabling the instance::
 
     int padata_start(struct padata_instance *pinst);
     void padata_stop(struct padata_instance *pinst);
@@ -48,7 +51,7 @@
 padata_stop clears the flag and blocks until the padata instance
 is unused.
 
-The list of CPUs to be used can be adjusted with these functions:
+The list of CPUs to be used can be adjusted with these functions::
 
     int padata_set_cpumasks(struct padata_instance *pinst,
 			    cpumask_var_t pcpumask,
@@ -71,12 +74,12 @@
 remove and mask is one of PADATA_CPU_SERIAL, PADATA_CPU_PARALLEL.
 
 If a user is interested in padata cpumask changes, he can register to
-the padata cpumask change notifier:
+the padata cpumask change notifier::
 
     int padata_register_cpumask_notifier(struct padata_instance *pinst,
 					 struct notifier_block *nblock);
 
-To unregister from that notifier:
+To unregister from that notifier::
 
     int padata_unregister_cpumask_notifier(struct padata_instance *pinst,
 					   struct notifier_block *nblock);
@@ -84,7 +87,7 @@
 The padata cpumask change notifier notifies about changes of the usable
 cpumasks, i.e. the subset of active CPUs in the user supplied cpumask.
 
-Padata calls the notifier chain with:
+Padata calls the notifier chain with::
 
     blocking_notifier_call_chain(&pinst->cpumask_change_notifier,
 				 notification_mask,
@@ -95,7 +98,7 @@
 to a struct padata_cpumask that contains the new cpumask information.
 
 Actually submitting work to the padata instance requires the creation of a
-padata_priv structure:
+padata_priv structure::
 
     struct padata_priv {
         /* Other stuff here... */
@@ -110,7 +113,7 @@
 be called in the process of getting the work done as we will see
 momentarily.
 
-The submission of work is done with:
+The submission of work is done with::
 
     int padata_do_parallel(struct padata_instance *pinst,
 		           struct padata_priv *padata, int cb_cpu);
@@ -138,7 +141,7 @@
 outstanding, it should be prepared to be called again with a new job before
 the previous one completes.  When a task does complete, parallel() (or
 whatever function actually finishes the job) should inform padata of the
-fact with a call to:
+fact with a call to::
 
     void padata_do_serial(struct padata_priv *padata);
 
@@ -151,7 +154,7 @@
 submitted.
 
 The one remaining function in the padata API should be called to clean up
-when a padata instance is no longer needed:
+when a padata instance is no longer needed::
 
     void padata_free(struct padata_instance *pinst);
 
diff --git a/Documentation/parport-lowlevel.txt b/Documentation/parport-lowlevel.txt
index 120eb20..0633d70 100644
--- a/Documentation/parport-lowlevel.txt
+++ b/Documentation/parport-lowlevel.txt
@@ -1,11 +1,12 @@
+===============================
 PARPORT interface documentation
--------------------------------
+===============================
 
-Time-stamp: <2000-02-24 13:30:20 twaugh>
+:Time-stamp: <2000-02-24 13:30:20 twaugh>
 
 Described here are the following functions:
 
-Global functions:
+Global functions::
   parport_register_driver
   parport_unregister_driver
   parport_enumerate
@@ -31,7 +32,8 @@
   parport_set_timeout
 
 Port functions (can be overridden by low-level drivers):
-  SPP:
+
+  SPP::
     port->ops->read_data
     port->ops->write_data
     port->ops->read_status
@@ -43,23 +45,23 @@
     port->ops->data_forward
     port->ops->data_reverse
 
-  EPP:
+  EPP::
     port->ops->epp_write_data
     port->ops->epp_read_data
     port->ops->epp_write_addr
     port->ops->epp_read_addr
 
-  ECP:
+  ECP::
     port->ops->ecp_write_data
     port->ops->ecp_read_data
     port->ops->ecp_write_addr
 
-  Other:
+  Other::
     port->ops->nibble_read_data
     port->ops->byte_read_data
     port->ops->compat_write_data
 
-The parport subsystem comprises 'parport' (the core port-sharing
+The parport subsystem comprises ``parport`` (the core port-sharing
 code), and a variety of low-level drivers that actually do the port
 accesses.  Each low-level driver handles a particular style of port
 (PC, Amiga, and so on).
@@ -70,14 +72,14 @@
 The global functions are mostly for communicating between the device
 driver and the parport subsystem: acquiring a list of available ports,
 claiming a port for exclusive use, and so on.  They also include
-'generic' functions for doing standard things that will work on any
+``generic`` functions for doing standard things that will work on any
 IEEE 1284-capable architecture.
 
 The port functions are provided by the low-level drivers, although the
-core parport module provides generic 'defaults' for some routines.
+core parport module provides generic ``defaults`` for some routines.
 The port functions can be split into three groups: SPP, EPP, and ECP.
 
-SPP (Standard Parallel Port) functions modify so-called 'SPP'
+SPP (Standard Parallel Port) functions modify so-called ``SPP``
 registers: data, status, and control.  The hardware may not actually
 have registers exactly like that, but the PC does and this interface is
 modelled after common PC implementations.  Other low-level drivers may
@@ -95,58 +97,63 @@
 low-level driver specific function is provided, for altering 'fudge
 factors'.
 
-GLOBAL FUNCTIONS
-----------------
+Global functions
+================
 
 parport_register_driver - register a device driver with parport
------------------------
+---------------------------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-struct parport_driver {
-	const char *name;
-	void (*attach) (struct parport *);
-	void (*detach) (struct parport *);
-	struct parport_driver *next;
-};
-int parport_register_driver (struct parport_driver *driver);
+	#include <linux/parport.h>
+
+	struct parport_driver {
+		const char *name;
+		void (*attach) (struct parport *);
+		void (*detach) (struct parport *);
+		struct parport_driver *next;
+	};
+	int parport_register_driver (struct parport_driver *driver);
 
 DESCRIPTION
+^^^^^^^^^^^
 
 In order to be notified about parallel ports when they are detected,
 parport_register_driver should be called.  Your driver will
 immediately be notified of all ports that have already been detected,
 and of each new port as low-level drivers are loaded.
 
-A 'struct parport_driver' contains the textual name of your driver,
+A ``struct parport_driver`` contains the textual name of your driver,
 a pointer to a function to handle new ports, and a pointer to a
 function to handle ports going away due to a low-level driver
 unloading.  Ports will only be detached if they are not being used
 (i.e. there are no devices registered on them).
 
-The visible parts of the 'struct parport *' argument given to
-attach/detach are:
+The visible parts of the ``struct parport *`` argument given to
+attach/detach are::
 
-struct parport
-{
-	struct parport *next; /* next parport in list */
-	const char *name;     /* port's name */
-	unsigned int modes;   /* bitfield of hardware modes */
-	struct parport_device_info probe_info;
-			      /* IEEE1284 info */
-	int number;           /* parport index */
-	struct parport_operations *ops;
-	...
-};
+	struct parport
+	{
+		struct parport *next; /* next parport in list */
+		const char *name;     /* port's name */
+		unsigned int modes;   /* bitfield of hardware modes */
+		struct parport_device_info probe_info;
+				/* IEEE1284 info */
+		int number;           /* parport index */
+		struct parport_operations *ops;
+		...
+	};
 
 There are other members of the structure, but they should not be
 touched.
 
-The 'modes' member summarises the capabilities of the underlying
+The ``modes`` member summarises the capabilities of the underlying
 hardware.  It consists of flags which may be bitwise-ored together:
 
+  ============================= ===============================================
   PARPORT_MODE_PCSPP		IBM PC registers are available,
 				i.e. functions that act on data,
 				control and status registers are
@@ -169,297 +176,351 @@
 				GFP_DMA flag with kmalloc) to the
 				low-level driver in order to take
 				advantage of it.
+  ============================= ===============================================
 
-There may be other flags in 'modes' as well.
+There may be other flags in ``modes`` as well.
 
-The contents of 'modes' is advisory only.  For example, if the
-hardware is capable of DMA, and PARPORT_MODE_DMA is in 'modes', it
+The contents of ``modes`` is advisory only.  For example, if the
+hardware is capable of DMA, and PARPORT_MODE_DMA is in ``modes``, it
 doesn't necessarily mean that DMA will always be used when possible.
 Similarly, hardware that is capable of assisting ECP transfers won't
 necessarily be used.
 
 RETURN VALUE
+^^^^^^^^^^^^
 
 Zero on success, otherwise an error code.
 
 ERRORS
+^^^^^^
 
 None. (Can it fail? Why return int?)
 
 EXAMPLE
+^^^^^^^
 
-static void lp_attach (struct parport *port)
-{
-	...
-	private = kmalloc (...);
-	dev[count++] = parport_register_device (...);
-	...
-}
+::
 
-static void lp_detach (struct parport *port)
-{
-	...
-}
-
-static struct parport_driver lp_driver = {
-	"lp",
-	lp_attach,
-	lp_detach,
-	NULL /* always put NULL here */
-};
-
-int lp_init (void)
-{
-	...
-	if (parport_register_driver (&lp_driver)) {
-		/* Failed; nothing we can do. */
-		return -EIO;
+	static void lp_attach (struct parport *port)
+	{
+		...
+		private = kmalloc (...);
+		dev[count++] = parport_register_device (...);
+		...
 	}
-	...
-}
+
+	static void lp_detach (struct parport *port)
+	{
+		...
+	}
+
+	static struct parport_driver lp_driver = {
+		"lp",
+		lp_attach,
+		lp_detach,
+		NULL /* always put NULL here */
+	};
+
+	int lp_init (void)
+	{
+		...
+		if (parport_register_driver (&lp_driver)) {
+			/* Failed; nothing we can do. */
+			return -EIO;
+		}
+		...
+	}
+
 
 SEE ALSO
+^^^^^^^^
 
 parport_unregister_driver, parport_register_device, parport_enumerate
-
+
+
+
 parport_unregister_driver - tell parport to forget about this driver
--------------------------
+--------------------------------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-struct parport_driver {
-	const char *name;
-	void (*attach) (struct parport *);
-	void (*detach) (struct parport *);
-	struct parport_driver *next;
-};
-void parport_unregister_driver (struct parport_driver *driver);
+	#include <linux/parport.h>
+
+	struct parport_driver {
+		const char *name;
+		void (*attach) (struct parport *);
+		void (*detach) (struct parport *);
+		struct parport_driver *next;
+	};
+	void parport_unregister_driver (struct parport_driver *driver);
 
 DESCRIPTION
+^^^^^^^^^^^
 
 This tells parport not to notify the device driver of new ports or of
 ports going away.  Registered devices belonging to that driver are NOT
 unregistered: parport_unregister_device must be used for each one.
 
 EXAMPLE
+^^^^^^^
 
-void cleanup_module (void)
-{
-	...
-	/* Stop notifications. */
-	parport_unregister_driver (&lp_driver);
+::
 
-	/* Unregister devices. */
-	for (i = 0; i < NUM_DEVS; i++)
-		parport_unregister_device (dev[i]);
-	...
-}
+	void cleanup_module (void)
+	{
+		...
+		/* Stop notifications. */
+		parport_unregister_driver (&lp_driver);
+
+		/* Unregister devices. */
+		for (i = 0; i < NUM_DEVS; i++)
+			parport_unregister_device (dev[i]);
+		...
+	}
 
 SEE ALSO
+^^^^^^^^
 
 parport_register_driver, parport_enumerate
-
+
+
+
 parport_enumerate - retrieve a list of parallel ports (DEPRECATED)
------------------
+------------------------------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-struct parport *parport_enumerate (void);
+	#include <linux/parport.h>
+
+	struct parport *parport_enumerate (void);
 
 DESCRIPTION
+^^^^^^^^^^^
 
 Retrieve the first of a list of valid parallel ports for this machine.
-Successive parallel ports can be found using the 'struct parport
-*next' element of the 'struct parport *' that is returned.  If 'next'
+Successive parallel ports can be found using the ``struct parport
+*next`` element of the ``struct parport *`` that is returned.  If ``next``
 is NULL, there are no more parallel ports in the list.  The number of
 ports in the list will not exceed PARPORT_MAX.
 
 RETURN VALUE
+^^^^^^^^^^^^
 
-A 'struct parport *' describing a valid parallel port for the machine,
+A ``struct parport *`` describing a valid parallel port for the machine,
 or NULL if there are none.
 
 ERRORS
+^^^^^^
 
 This function can return NULL to indicate that there are no parallel
 ports to use.
 
 EXAMPLE
+^^^^^^^
 
-int detect_device (void)
-{
-	struct parport *port;
+::
 
-	for (port = parport_enumerate ();
-	     port != NULL;
-	     port = port->next) {
-		/* Try to detect a device on the port... */
+	int detect_device (void)
+	{
+		struct parport *port;
+
+		for (port = parport_enumerate ();
+		port != NULL;
+		port = port->next) {
+			/* Try to detect a device on the port... */
+			...
+		}
+		}
+
 		...
-             }
 	}
 
-	...
-}
-
 NOTES
+^^^^^
 
 parport_enumerate is deprecated; parport_register_driver should be
 used instead.
 
 SEE ALSO
+^^^^^^^^
 
 parport_register_driver, parport_unregister_driver
-
+
+
+
 parport_register_device - register to use a port
------------------------
+------------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-typedef int (*preempt_func) (void *handle);
-typedef void (*wakeup_func) (void *handle);
-typedef int (*irq_func) (int irq, void *handle, struct pt_regs *);
+	#include <linux/parport.h>
 
-struct pardevice *parport_register_device(struct parport *port,
-                                          const char *name,
-                                          preempt_func preempt,
-                                          wakeup_func wakeup,
-                                          irq_func irq,
-                                          int flags,
-                                          void *handle);
+	typedef int (*preempt_func) (void *handle);
+	typedef void (*wakeup_func) (void *handle);
+	typedef int (*irq_func) (int irq, void *handle, struct pt_regs *);
+
+	struct pardevice *parport_register_device(struct parport *port,
+						  const char *name,
+						  preempt_func preempt,
+						  wakeup_func wakeup,
+						  irq_func irq,
+						  int flags,
+						  void *handle);
 
 DESCRIPTION
+^^^^^^^^^^^
 
 Use this function to register your device driver on a parallel port
-('port').  Once you have done that, you will be able to use
+(``port``).  Once you have done that, you will be able to use
 parport_claim and parport_release in order to use the port.
 
-The ('name') argument is the name of the device that appears in /proc
+The (``name``) argument is the name of the device that appears in /proc
 filesystem. The string must be valid for the whole lifetime of the
 device (until parport_unregister_device is called).
 
 This function will register three callbacks into your driver:
-'preempt', 'wakeup' and 'irq'.  Each of these may be NULL in order to
+``preempt``, ``wakeup`` and ``irq``.  Each of these may be NULL in order to
 indicate that you do not want a callback.
 
-When the 'preempt' function is called, it is because another driver
-wishes to use the parallel port.  The 'preempt' function should return
+When the ``preempt`` function is called, it is because another driver
+wishes to use the parallel port.  The ``preempt`` function should return
 non-zero if the parallel port cannot be released yet -- if zero is
 returned, the port is lost to another driver and the port must be
 re-claimed before use.
 
-The 'wakeup' function is called once another driver has released the
+The ``wakeup`` function is called once another driver has released the
 port and no other driver has yet claimed it.  You can claim the
-parallel port from within the 'wakeup' function (in which case the
+parallel port from within the ``wakeup`` function (in which case the
 claim is guaranteed to succeed), or choose not to if you don't need it
 now.
 
 If an interrupt occurs on the parallel port your driver has claimed,
-the 'irq' function will be called. (Write something about shared
+the ``irq`` function will be called. (Write something about shared
 interrupts here.)
 
-The 'handle' is a pointer to driver-specific data, and is passed to
+The ``handle`` is a pointer to driver-specific data, and is passed to
 the callback functions.
 
-'flags' may be a bitwise combination of the following flags:
+``flags`` may be a bitwise combination of the following flags:
 
+  ===================== =================================================
         Flag            Meaning
+  ===================== =================================================
   PARPORT_DEV_EXCL	The device cannot share the parallel port at all.
 			Use this only when absolutely necessary.
+  ===================== =================================================
 
 The typedefs are not actually defined -- they are only shown in order
 to make the function prototype more readable.
 
-The visible parts of the returned 'struct pardevice' are:
+The visible parts of the returned ``struct pardevice`` are::
 
-struct pardevice {
-	struct parport *port;	/* Associated port */
-	void *private;		/* Device driver's 'handle' */
-	...
-};
+	struct pardevice {
+		struct parport *port;	/* Associated port */
+		void *private;		/* Device driver's 'handle' */
+		...
+	};
 
 RETURN VALUE
+^^^^^^^^^^^^
 
-A 'struct pardevice *': a handle to the registered parallel port
+A ``struct pardevice *``: a handle to the registered parallel port
 device that can be used for parport_claim, parport_release, etc.
 
 ERRORS
+^^^^^^
 
 A return value of NULL indicates that there was a problem registering
 a device on that port.
 
 EXAMPLE
+^^^^^^^
 
-static int preempt (void *handle)
-{
-	if (busy_right_now)
-		return 1;
+::
 
-	must_reclaim_port = 1;
-	return 0;
-}
+	static int preempt (void *handle)
+	{
+		if (busy_right_now)
+			return 1;
 
-static void wakeup (void *handle)
-{
-	struct toaster *private = handle;
-	struct pardevice *dev = private->dev;
-	if (!dev) return; /* avoid races */
-
-	if (want_port)
-		parport_claim (dev);
-}
-
-static int toaster_detect (struct toaster *private, struct parport *port)
-{
-	private->dev = parport_register_device (port, "toaster", preempt,
-					        wakeup, NULL, 0,
-						private);
-	if (!private->dev)
-		/* Couldn't register with parport. */
-		return -EIO;
-
-	must_reclaim_port = 0;
-	busy_right_now = 1;
-	parport_claim_or_block (private->dev);
-	...
-	/* Don't need the port while the toaster warms up. */
-	busy_right_now = 0;
-	...
-	busy_right_now = 1;
-	if (must_reclaim_port) {
-		parport_claim_or_block (private->dev);
-		must_reclaim_port = 0;
+		must_reclaim_port = 1;
+		return 0;
 	}
-	...
-}
+
+	static void wakeup (void *handle)
+	{
+		struct toaster *private = handle;
+		struct pardevice *dev = private->dev;
+		if (!dev) return; /* avoid races */
+
+		if (want_port)
+			parport_claim (dev);
+	}
+
+	static int toaster_detect (struct toaster *private, struct parport *port)
+	{
+		private->dev = parport_register_device (port, "toaster", preempt,
+							wakeup, NULL, 0,
+							private);
+		if (!private->dev)
+			/* Couldn't register with parport. */
+			return -EIO;
+
+		must_reclaim_port = 0;
+		busy_right_now = 1;
+		parport_claim_or_block (private->dev);
+		...
+		/* Don't need the port while the toaster warms up. */
+		busy_right_now = 0;
+		...
+		busy_right_now = 1;
+		if (must_reclaim_port) {
+			parport_claim_or_block (private->dev);
+			must_reclaim_port = 0;
+		}
+		...
+	}
 
 SEE ALSO
+^^^^^^^^
 
 parport_unregister_device, parport_claim
+
+
 
 parport_unregister_device - finish using a port
--------------------------
+-----------------------------------------------
 
 SYNPOPSIS
 
-#include <linux/parport.h>
+::
 
-void parport_unregister_device (struct pardevice *dev);
+	#include <linux/parport.h>
+
+	void parport_unregister_device (struct pardevice *dev);
 
 DESCRIPTION
+^^^^^^^^^^^
 
 This function is the opposite of parport_register_device.  After using
-parport_unregister_device, 'dev' is no longer a valid device handle.
+parport_unregister_device, ``dev`` is no longer a valid device handle.
 
 You should not unregister a device that is currently claimed, although
 if you do it will be released automatically.
 
 EXAMPLE
+^^^^^^^
+
+::
 
 	...
 	kfree (dev->private); /* before we lose the pointer */
@@ -467,460 +528,602 @@
 	...
 
 SEE ALSO
+^^^^^^^^
+
 
 parport_unregister_driver
 
 parport_claim, parport_claim_or_block - claim the parallel port for a device
--------------------------------------
+----------------------------------------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-int parport_claim (struct pardevice *dev);
-int parport_claim_or_block (struct pardevice *dev);
+	#include <linux/parport.h>
+
+	int parport_claim (struct pardevice *dev);
+	int parport_claim_or_block (struct pardevice *dev);
 
 DESCRIPTION
+^^^^^^^^^^^
 
 These functions attempt to gain control of the parallel port on which
-'dev' is registered.  'parport_claim' does not block, but
-'parport_claim_or_block' may do. (Put something here about blocking
+``dev`` is registered.  ``parport_claim`` does not block, but
+``parport_claim_or_block`` may do. (Put something here about blocking
 interruptibly or non-interruptibly.)
 
 You should not try to claim a port that you have already claimed.
 
 RETURN VALUE
+^^^^^^^^^^^^
 
 A return value of zero indicates that the port was successfully
 claimed, and the caller now has possession of the parallel port.
 
-If 'parport_claim_or_block' blocks before returning successfully, the
+If ``parport_claim_or_block`` blocks before returning successfully, the
 return value is positive.
 
 ERRORS
+^^^^^^
 
+========== ==========================================================
   -EAGAIN  The port is unavailable at the moment, but another attempt
            to claim it may succeed.
+========== ==========================================================
 
 SEE ALSO
+^^^^^^^^
+
 
 parport_release
 
 parport_release - release the parallel port
----------------
+-------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-void parport_release (struct pardevice *dev);
+	#include <linux/parport.h>
+
+	void parport_release (struct pardevice *dev);
 
 DESCRIPTION
+^^^^^^^^^^^
 
 Once a parallel port device has been claimed, it can be released using
-'parport_release'.  It cannot fail, but you should not release a
+``parport_release``.  It cannot fail, but you should not release a
 device that you do not have possession of.
 
 EXAMPLE
+^^^^^^^
 
-static size_t write (struct pardevice *dev, const void *buf,
-		     size_t len)
-{
-	...
-	written = dev->port->ops->write_ecp_data (dev->port, buf,
-						  len);
-	parport_release (dev);
-	...
-}
+::
+
+	static size_t write (struct pardevice *dev, const void *buf,
+			size_t len)
+	{
+		...
+		written = dev->port->ops->write_ecp_data (dev->port, buf,
+							len);
+		parport_release (dev);
+		...
+	}
 
 
 SEE ALSO
+^^^^^^^^
 
 change_mode, parport_claim, parport_claim_or_block, parport_yield
-
+
+
+
 parport_yield, parport_yield_blocking - temporarily release a parallel port
--------------------------------------
+---------------------------------------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-int parport_yield (struct pardevice *dev)
-int parport_yield_blocking (struct pardevice *dev);
+	#include <linux/parport.h>
+
+	int parport_yield (struct pardevice *dev)
+	int parport_yield_blocking (struct pardevice *dev);
 
 DESCRIPTION
+^^^^^^^^^^^
 
 When a driver has control of a parallel port, it may allow another
-driver to temporarily 'borrow' it.  'parport_yield' does not block;
-'parport_yield_blocking' may do.
+driver to temporarily ``borrow`` it.  ``parport_yield`` does not block;
+``parport_yield_blocking`` may do.
 
 RETURN VALUE
+^^^^^^^^^^^^
 
 A return value of zero indicates that the caller still owns the port
 and the call did not block.
 
-A positive return value from 'parport_yield_blocking' indicates that
+A positive return value from ``parport_yield_blocking`` indicates that
 the caller still owns the port and the call blocked.
 
 A return value of -EAGAIN indicates that the caller no longer owns the
 port, and it must be re-claimed before use.
 
 ERRORS
+^^^^^^
 
+========= ==========================================================
   -EAGAIN  Ownership of the parallel port was given away.
+========= ==========================================================
 
 SEE ALSO
+^^^^^^^^
 
 parport_release
+
+
 
 parport_wait_peripheral - wait for status lines, up to 35ms
------------------------
+-----------------------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-int parport_wait_peripheral (struct parport *port,
-			     unsigned char mask,
-			     unsigned char val);
+	#include <linux/parport.h>
+
+	int parport_wait_peripheral (struct parport *port,
+				     unsigned char mask,
+				     unsigned char val);
 
 DESCRIPTION
+^^^^^^^^^^^
 
 Wait for the status lines in mask to match the values in val.
 
 RETURN VALUE
+^^^^^^^^^^^^
 
+======== ==========================================================
  -EINTR  a signal is pending
       0  the status lines in mask have values in val
       1  timed out while waiting (35ms elapsed)
+======== ==========================================================
 
 SEE ALSO
+^^^^^^^^
 
 parport_poll_peripheral
+
+
 
 parport_poll_peripheral - wait for status lines, in usec
------------------------
+--------------------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-int parport_poll_peripheral (struct parport *port,
-			     unsigned char mask,
-			     unsigned char val,
-			     int usec);
+	#include <linux/parport.h>
+
+	int parport_poll_peripheral (struct parport *port,
+				     unsigned char mask,
+				     unsigned char val,
+				     int usec);
 
 DESCRIPTION
+^^^^^^^^^^^
 
 Wait for the status lines in mask to match the values in val.
 
 RETURN VALUE
+^^^^^^^^^^^^
 
+======== ==========================================================
  -EINTR  a signal is pending
       0  the status lines in mask have values in val
       1  timed out while waiting (usec microseconds have elapsed)
+======== ==========================================================
 
 SEE ALSO
+^^^^^^^^
 
 parport_wait_peripheral
-
+
+
+
 parport_wait_event - wait for an event on a port
-------------------
+------------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-int parport_wait_event (struct parport *port, signed long timeout)
+	#include <linux/parport.h>
+
+	int parport_wait_event (struct parport *port, signed long timeout)
 
 DESCRIPTION
+^^^^^^^^^^^
 
 Wait for an event (e.g. interrupt) on a port.  The timeout is in
 jiffies.
 
 RETURN VALUE
+^^^^^^^^^^^^
 
+======= ==========================================================
       0  success
      <0  error (exit as soon as possible)
      >0  timed out
-
+======= ==========================================================
+
 parport_negotiate - perform IEEE 1284 negotiation
------------------
+-------------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-int parport_negotiate (struct parport *, int mode);
+	#include <linux/parport.h>
+
+	int parport_negotiate (struct parport *, int mode);
 
 DESCRIPTION
+^^^^^^^^^^^
 
 Perform IEEE 1284 negotiation.
 
 RETURN VALUE
+^^^^^^^^^^^^
 
+======= ==========================================================
      0  handshake OK; IEEE 1284 peripheral and mode available
     -1  handshake failed; peripheral not compliant (or none present)
      1  handshake OK; IEEE 1284 peripheral present but mode not
         available
+======= ==========================================================
 
 SEE ALSO
+^^^^^^^^
 
 parport_read, parport_write
-
+
+
+
 parport_read - read data from device
-------------
+------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-ssize_t parport_read (struct parport *, void *buf, size_t len);
+	#include <linux/parport.h>
+
+	ssize_t parport_read (struct parport *, void *buf, size_t len);
 
 DESCRIPTION
+^^^^^^^^^^^
 
 Read data from device in current IEEE 1284 transfer mode.  This only
 works for modes that support reverse data transfer.
 
 RETURN VALUE
+^^^^^^^^^^^^
 
 If negative, an error code; otherwise the number of bytes transferred.
 
 SEE ALSO
+^^^^^^^^
 
 parport_write, parport_negotiate
-
+
+
+
 parport_write - write data to device
--------------
+------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-ssize_t parport_write (struct parport *, const void *buf, size_t len);
+	#include <linux/parport.h>
+
+	ssize_t parport_write (struct parport *, const void *buf, size_t len);
 
 DESCRIPTION
+^^^^^^^^^^^
 
 Write data to device in current IEEE 1284 transfer mode.  This only
 works for modes that support forward data transfer.
 
 RETURN VALUE
+^^^^^^^^^^^^
 
 If negative, an error code; otherwise the number of bytes transferred.
 
 SEE ALSO
+^^^^^^^^
 
 parport_read, parport_negotiate
+
+
 
 parport_open - register device for particular device number
-------------
+-----------------------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-struct pardevice *parport_open (int devnum, const char *name,
-			        int (*pf) (void *),
-				void (*kf) (void *),
-				void (*irqf) (int, void *,
-					      struct pt_regs *),
-				int flags, void *handle);
+	#include <linux/parport.h>
+
+	struct pardevice *parport_open (int devnum, const char *name,
+				        int (*pf) (void *),
+					void (*kf) (void *),
+					void (*irqf) (int, void *,
+						      struct pt_regs *),
+					int flags, void *handle);
 
 DESCRIPTION
+^^^^^^^^^^^
 
 This is like parport_register_device but takes a device number instead
 of a pointer to a struct parport.
 
 RETURN VALUE
+^^^^^^^^^^^^
 
 See parport_register_device.  If no device is associated with devnum,
 NULL is returned.
 
 SEE ALSO
+^^^^^^^^
 
 parport_register_device
-
+
+
+
 parport_close - unregister device for particular device number
--------------
+--------------------------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-void parport_close (struct pardevice *dev);
+	#include <linux/parport.h>
+
+	void parport_close (struct pardevice *dev);
 
 DESCRIPTION
+^^^^^^^^^^^
 
 This is the equivalent of parport_unregister_device for parport_open.
 
 SEE ALSO
+^^^^^^^^
 
 parport_unregister_device, parport_open
-
+
+
+
 parport_device_id - obtain IEEE 1284 Device ID
------------------
+----------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-ssize_t parport_device_id (int devnum, char *buffer, size_t len);
+	#include <linux/parport.h>
+
+	ssize_t parport_device_id (int devnum, char *buffer, size_t len);
 
 DESCRIPTION
+^^^^^^^^^^^
 
 Obtains the IEEE 1284 Device ID associated with a given device.
 
 RETURN VALUE
+^^^^^^^^^^^^
 
 If negative, an error code; otherwise, the number of bytes of buffer
 that contain the device ID.  The format of the device ID is as
-follows:
+follows::
 
-[length][ID]
+	[length][ID]
 
 The first two bytes indicate the inclusive length of the entire Device
 ID, and are in big-endian order.  The ID is a sequence of pairs of the
-form:
+form::
 
-key:value;
+	key:value;
 
 NOTES
+^^^^^
 
 Many devices have ill-formed IEEE 1284 Device IDs.
 
 SEE ALSO
+^^^^^^^^
 
 parport_find_class, parport_find_device
-
+
+
+
 parport_device_coords - convert device number to device coordinates
-------------------
+-------------------------------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-int parport_device_coords (int devnum, int *parport, int *mux,
-			   int *daisy);
+	#include <linux/parport.h>
+
+	int parport_device_coords (int devnum, int *parport, int *mux,
+				   int *daisy);
 
 DESCRIPTION
+^^^^^^^^^^^
 
 Convert between device number (zero-based) and device coordinates
 (port, multiplexor, daisy chain address).
 
 RETURN VALUE
+^^^^^^^^^^^^
 
-Zero on success, in which case the coordinates are (*parport, *mux,
-*daisy).
+Zero on success, in which case the coordinates are (``*parport``, ``*mux``,
+``*daisy``).
 
 SEE ALSO
+^^^^^^^^
 
 parport_open, parport_device_id
-
+
+
+
 parport_find_class - find a device by its class
-------------------
+-----------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-typedef enum {
-	PARPORT_CLASS_LEGACY = 0,       /* Non-IEEE1284 device */
-	PARPORT_CLASS_PRINTER,
-	PARPORT_CLASS_MODEM,
-	PARPORT_CLASS_NET,
-	PARPORT_CLASS_HDC,              /* Hard disk controller */
-	PARPORT_CLASS_PCMCIA,
-	PARPORT_CLASS_MEDIA,            /* Multimedia device */
-	PARPORT_CLASS_FDC,              /* Floppy disk controller */
-	PARPORT_CLASS_PORTS,
-	PARPORT_CLASS_SCANNER,
-	PARPORT_CLASS_DIGCAM,
-	PARPORT_CLASS_OTHER,            /* Anything else */
-	PARPORT_CLASS_UNSPEC,           /* No CLS field in ID */
-	PARPORT_CLASS_SCSIADAPTER
-} parport_device_class;
+	#include <linux/parport.h>
 
-int parport_find_class (parport_device_class cls, int from);
+	typedef enum {
+		PARPORT_CLASS_LEGACY = 0,       /* Non-IEEE1284 device */
+		PARPORT_CLASS_PRINTER,
+		PARPORT_CLASS_MODEM,
+		PARPORT_CLASS_NET,
+		PARPORT_CLASS_HDC,              /* Hard disk controller */
+		PARPORT_CLASS_PCMCIA,
+		PARPORT_CLASS_MEDIA,            /* Multimedia device */
+		PARPORT_CLASS_FDC,              /* Floppy disk controller */
+		PARPORT_CLASS_PORTS,
+		PARPORT_CLASS_SCANNER,
+		PARPORT_CLASS_DIGCAM,
+		PARPORT_CLASS_OTHER,            /* Anything else */
+		PARPORT_CLASS_UNSPEC,           /* No CLS field in ID */
+		PARPORT_CLASS_SCSIADAPTER
+	} parport_device_class;
+
+	int parport_find_class (parport_device_class cls, int from);
 
 DESCRIPTION
+^^^^^^^^^^^
 
 Find a device by class.  The search starts from device number from+1.
 
 RETURN VALUE
+^^^^^^^^^^^^
 
 The device number of the next device in that class, or -1 if no such
 device exists.
 
 NOTES
+^^^^^
 
-Example usage:
+Example usage::
 
-int devnum = -1;
-while ((devnum = parport_find_class (PARPORT_CLASS_DIGCAM, devnum)) != -1) {
-    struct pardevice *dev = parport_open (devnum, ...);
-    ...
-}
+	int devnum = -1;
+	while ((devnum = parport_find_class (PARPORT_CLASS_DIGCAM, devnum)) != -1) {
+		struct pardevice *dev = parport_open (devnum, ...);
+		...
+	}
 
 SEE ALSO
+^^^^^^^^
 
 parport_find_device, parport_open, parport_device_id
-
+
+
+
 parport_find_device - find a device by its class
-------------------
+------------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-int parport_find_device (const char *mfg, const char *mdl, int from);
+	#include <linux/parport.h>
+
+	int parport_find_device (const char *mfg, const char *mdl, int from);
 
 DESCRIPTION
+^^^^^^^^^^^
 
 Find a device by vendor and model.  The search starts from device
 number from+1.
 
 RETURN VALUE
+^^^^^^^^^^^^
 
 The device number of the next device matching the specifications, or
 -1 if no such device exists.
 
 NOTES
+^^^^^
 
-Example usage:
+Example usage::
 
-int devnum = -1;
-while ((devnum = parport_find_device ("IOMEGA", "ZIP+", devnum)) != -1) {
-    struct pardevice *dev = parport_open (devnum, ...);
-    ...
-}
+	int devnum = -1;
+	while ((devnum = parport_find_device ("IOMEGA", "ZIP+", devnum)) != -1) {
+		struct pardevice *dev = parport_open (devnum, ...);
+		...
+	}
 
 SEE ALSO
+^^^^^^^^
 
 parport_find_class, parport_open, parport_device_id
+
+
 
 parport_set_timeout - set the inactivity timeout
--------------------
+------------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-long parport_set_timeout (struct pardevice *dev, long inactivity);
+	#include <linux/parport.h>
+
+	long parport_set_timeout (struct pardevice *dev, long inactivity);
 
 DESCRIPTION
+^^^^^^^^^^^
 
 Set the inactivity timeout, in jiffies, for a registered device.  The
 previous timeout is returned.
 
 RETURN VALUE
+^^^^^^^^^^^^
 
 The previous timeout, in jiffies.
 
 NOTES
+^^^^^
 
 Some of the port->ops functions for a parport may take time, owing to
 delays at the peripheral.  After the peripheral has not responded for
-'inactivity' jiffies, a timeout will occur and the blocking function
+``inactivity`` jiffies, a timeout will occur and the blocking function
 will return.
 
 A timeout of 0 jiffies is a special case: the function must do as much
@@ -932,29 +1135,37 @@
 value until set again.
 
 SEE ALSO
+^^^^^^^^
 
 port->ops->xxx_read/write_yyy
-
+
+
+
+
 PORT FUNCTIONS
---------------
+==============
 
 The functions in the port->ops structure (struct parport_operations)
 are provided by the low-level driver responsible for that port.
 
 port->ops->read_data - read the data register
---------------------
+---------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-struct parport_operations {
-	...
-	unsigned char (*read_data) (struct parport *port);
-	...
-};
+	#include <linux/parport.h>
+
+	struct parport_operations {
+		...
+		unsigned char (*read_data) (struct parport *port);
+		...
+	};
 
 DESCRIPTION
+^^^^^^^^^^^
 
 If port->modes contains the PARPORT_MODE_TRISTATE flag and the
 PARPORT_CONTROL_DIRECTION bit in the control register is set, this
@@ -964,45 +1175,59 @@
 register.  Otherwise the return value is undefined.
 
 SEE ALSO
+^^^^^^^^
 
 write_data, read_status, write_control
+
+
 
 port->ops->write_data - write the data register
----------------------
+-----------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-struct parport_operations {
-	...
-	void (*write_data) (struct parport *port, unsigned char d);
-	...
-};
+	#include <linux/parport.h>
+
+	struct parport_operations {
+		...
+		void (*write_data) (struct parport *port, unsigned char d);
+		...
+	};
 
 DESCRIPTION
+^^^^^^^^^^^
 
 Writes to the data register.  May have side-effects (a STROBE pulse,
 for instance).
 
 SEE ALSO
+^^^^^^^^
 
 read_data, read_status, write_control
+
+
 
 port->ops->read_status - read the status register
-----------------------
+-------------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-struct parport_operations {
-	...
-	unsigned char (*read_status) (struct parport *port);
-	...
-};
+	#include <linux/parport.h>
+
+	struct parport_operations {
+		...
+		unsigned char (*read_status) (struct parport *port);
+		...
+	};
 
 DESCRIPTION
+^^^^^^^^^^^
 
 Reads from the status register.  This is a bitmask:
 
@@ -1015,76 +1240,98 @@
 There may be other bits set.
 
 SEE ALSO
+^^^^^^^^
 
 read_data, write_data, write_control
+
+
 
 port->ops->read_control - read the control register
------------------------
+---------------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-struct parport_operations {
-	...
-	unsigned char (*read_control) (struct parport *port);
-	...
-};
+	#include <linux/parport.h>
+
+	struct parport_operations {
+		...
+		unsigned char (*read_control) (struct parport *port);
+		...
+	};
 
 DESCRIPTION
+^^^^^^^^^^^
 
 Returns the last value written to the control register (either from
 write_control or frob_control).  No port access is performed.
 
 SEE ALSO
+^^^^^^^^
 
 read_data, write_data, read_status, write_control
+
+
 
 port->ops->write_control - write the control register
-------------------------
+-----------------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-struct parport_operations {
-	...
-	void (*write_control) (struct parport *port, unsigned char s);
-	...
-};
+	#include <linux/parport.h>
+
+	struct parport_operations {
+		...
+		void (*write_control) (struct parport *port, unsigned char s);
+		...
+	};
 
 DESCRIPTION
+^^^^^^^^^^^
 
-Writes to the control register. This is a bitmask:
-                          _______
-- PARPORT_CONTROL_STROBE (nStrobe)
-                          _______
-- PARPORT_CONTROL_AUTOFD (nAutoFd)
-                        _____
-- PARPORT_CONTROL_INIT (nInit)
-                          _________
-- PARPORT_CONTROL_SELECT (nSelectIn)
+Writes to the control register. This is a bitmask::
+
+				  _______
+	- PARPORT_CONTROL_STROBE (nStrobe)
+				  _______
+	- PARPORT_CONTROL_AUTOFD (nAutoFd)
+				_____
+	- PARPORT_CONTROL_INIT (nInit)
+				  _________
+	- PARPORT_CONTROL_SELECT (nSelectIn)
 
 SEE ALSO
+^^^^^^^^
 
 read_data, write_data, read_status, frob_control
+
+
 
 port->ops->frob_control - write control register bits
------------------------
+-----------------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-struct parport_operations {
-	...
-	unsigned char (*frob_control) (struct parport *port,
-				       unsigned char mask,
-				       unsigned char val);
-	...
-};
+	#include <linux/parport.h>
+
+	struct parport_operations {
+		...
+		unsigned char (*frob_control) (struct parport *port,
+					unsigned char mask,
+					unsigned char val);
+		...
+	};
 
 DESCRIPTION
+^^^^^^^^^^^
 
 This is equivalent to reading from the control register, masking out
 the bits in mask, exclusive-or'ing with the bits in val, and writing
@@ -1095,23 +1342,30 @@
 port access.
 
 SEE ALSO
+^^^^^^^^
 
 read_data, write_data, read_status, write_control
+
+
 
 port->ops->enable_irq - enable interrupt generation
----------------------
+---------------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-struct parport_operations {
-	...
-	void (*enable_irq) (struct parport *port);
-	...
-};
+	#include <linux/parport.h>
+
+	struct parport_operations {
+		...
+		void (*enable_irq) (struct parport *port);
+		...
+	};
 
 DESCRIPTION
+^^^^^^^^^^^
 
 The parallel port hardware is instructed to generate interrupts at
 appropriate moments, although those moments are
@@ -1119,353 +1373,460 @@
 commonly generated on the rising edge of nAck.
 
 SEE ALSO
+^^^^^^^^
 
 disable_irq
+
+
 
 port->ops->disable_irq - disable interrupt generation
-----------------------
+-----------------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-struct parport_operations {
-	...
-	void (*disable_irq) (struct parport *port);
-	...
-};
+	#include <linux/parport.h>
+
+	struct parport_operations {
+		...
+		void (*disable_irq) (struct parport *port);
+		...
+	};
 
 DESCRIPTION
+^^^^^^^^^^^
 
 The parallel port hardware is instructed not to generate interrupts.
 The interrupt itself is not masked.
 
 SEE ALSO
+^^^^^^^^
 
 enable_irq
 
+
+
 port->ops->data_forward - enable data drivers
------------------------
+---------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-struct parport_operations {
-	...
-	void (*data_forward) (struct parport *port);
-	...
-};
+	#include <linux/parport.h>
+
+	struct parport_operations {
+		...
+		void (*data_forward) (struct parport *port);
+		...
+	};
 
 DESCRIPTION
+^^^^^^^^^^^
 
 Enables the data line drivers, for 8-bit host-to-peripheral
 communications.
 
 SEE ALSO
+^^^^^^^^
 
 data_reverse
+
+
 
 port->ops->data_reverse - tristate the buffer
------------------------
+---------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-struct parport_operations {
-	...
-	void (*data_reverse) (struct parport *port);
-	...
-};
+	#include <linux/parport.h>
+
+	struct parport_operations {
+		...
+		void (*data_reverse) (struct parport *port);
+		...
+	};
 
 DESCRIPTION
+^^^^^^^^^^^
 
 Places the data bus in a high impedance state, if port->modes has the
 PARPORT_MODE_TRISTATE bit set.
 
 SEE ALSO
+^^^^^^^^
 
 data_forward
-
+
+
+
 port->ops->epp_write_data - write EPP data
--------------------------
+------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-struct parport_operations {
-	...
-	size_t (*epp_write_data) (struct parport *port, const void *buf,
-				  size_t len, int flags);
-	...
-};
+	#include <linux/parport.h>
+
+	struct parport_operations {
+		...
+		size_t (*epp_write_data) (struct parport *port, const void *buf,
+					size_t len, int flags);
+		...
+	};
 
 DESCRIPTION
+^^^^^^^^^^^
 
 Writes data in EPP mode, and returns the number of bytes written.
 
-The 'flags' parameter may be one or more of the following,
+The ``flags`` parameter may be one or more of the following,
 bitwise-or'ed together:
 
+======================= =================================================
 PARPORT_EPP_FAST	Use fast transfers. Some chips provide 16-bit and
 			32-bit registers.  However, if a transfer
 			times out, the return value may be unreliable.
+======================= =================================================
 
 SEE ALSO
+^^^^^^^^
 
 epp_read_data, epp_write_addr, epp_read_addr
+
+
 
 port->ops->epp_read_data - read EPP data
-------------------------
+----------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-struct parport_operations {
-	...
-	size_t (*epp_read_data) (struct parport *port, void *buf,
-				 size_t len, int flags);
-	...
-};
+	#include <linux/parport.h>
+
+	struct parport_operations {
+		...
+		size_t (*epp_read_data) (struct parport *port, void *buf,
+					size_t len, int flags);
+		...
+	};
 
 DESCRIPTION
+^^^^^^^^^^^
 
 Reads data in EPP mode, and returns the number of bytes read.
 
-The 'flags' parameter may be one or more of the following,
+The ``flags`` parameter may be one or more of the following,
 bitwise-or'ed together:
 
+======================= =================================================
 PARPORT_EPP_FAST	Use fast transfers. Some chips provide 16-bit and
 			32-bit registers.  However, if a transfer
 			times out, the return value may be unreliable.
+======================= =================================================
 
 SEE ALSO
+^^^^^^^^
 
 epp_write_data, epp_write_addr, epp_read_addr
-
+
+
+
 port->ops->epp_write_addr - write EPP address
--------------------------
+---------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-struct parport_operations {
-	...
-	size_t (*epp_write_addr) (struct parport *port,
-				  const void *buf, size_t len, int flags);
-	...
-};
+	#include <linux/parport.h>
+
+	struct parport_operations {
+		...
+		size_t (*epp_write_addr) (struct parport *port,
+					const void *buf, size_t len, int flags);
+		...
+	};
 
 DESCRIPTION
+^^^^^^^^^^^
 
 Writes EPP addresses (8 bits each), and returns the number written.
 
-The 'flags' parameter may be one or more of the following,
+The ``flags`` parameter may be one or more of the following,
 bitwise-or'ed together:
 
+======================= =================================================
 PARPORT_EPP_FAST	Use fast transfers. Some chips provide 16-bit and
 			32-bit registers.  However, if a transfer
 			times out, the return value may be unreliable.
+======================= =================================================
 
 (Does PARPORT_EPP_FAST make sense for this function?)
 
 SEE ALSO
+^^^^^^^^
 
 epp_write_data, epp_read_data, epp_read_addr
+
+
 
 port->ops->epp_read_addr - read EPP address
-------------------------
+-------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-struct parport_operations {
-	...
-	size_t (*epp_read_addr) (struct parport *port, void *buf,
-				 size_t len, int flags);
-	...
-};
+	#include <linux/parport.h>
+
+	struct parport_operations {
+		...
+		size_t (*epp_read_addr) (struct parport *port, void *buf,
+					size_t len, int flags);
+		...
+	};
 
 DESCRIPTION
+^^^^^^^^^^^
 
 Reads EPP addresses (8 bits each), and returns the number read.
 
-The 'flags' parameter may be one or more of the following,
+The ``flags`` parameter may be one or more of the following,
 bitwise-or'ed together:
 
+======================= =================================================
 PARPORT_EPP_FAST	Use fast transfers. Some chips provide 16-bit and
 			32-bit registers.  However, if a transfer
 			times out, the return value may be unreliable.
+======================= =================================================
 
 (Does PARPORT_EPP_FAST make sense for this function?)
 
 SEE ALSO
+^^^^^^^^
 
 epp_write_data, epp_read_data, epp_write_addr
+
+
 
 port->ops->ecp_write_data - write a block of ECP data
--------------------------
+-----------------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-struct parport_operations {
-	...
-	size_t (*ecp_write_data) (struct parport *port,
-				  const void *buf, size_t len, int flags);
-	...
-};
+	#include <linux/parport.h>
+
+	struct parport_operations {
+		...
+		size_t (*ecp_write_data) (struct parport *port,
+					const void *buf, size_t len, int flags);
+		...
+	};
 
 DESCRIPTION
+^^^^^^^^^^^
 
-Writes a block of ECP data.  The 'flags' parameter is ignored.
+Writes a block of ECP data.  The ``flags`` parameter is ignored.
 
 RETURN VALUE
+^^^^^^^^^^^^
 
 The number of bytes written.
 
 SEE ALSO
+^^^^^^^^
 
 ecp_read_data, ecp_write_addr
 
+
+
 port->ops->ecp_read_data - read a block of ECP data
-------------------------
+---------------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-struct parport_operations {
-	...
-	size_t (*ecp_read_data) (struct parport *port,
-				 void *buf, size_t len, int flags);
-	...
-};
+	#include <linux/parport.h>
+
+	struct parport_operations {
+		...
+		size_t (*ecp_read_data) (struct parport *port,
+					void *buf, size_t len, int flags);
+		...
+	};
 
 DESCRIPTION
+^^^^^^^^^^^
 
-Reads a block of ECP data.  The 'flags' parameter is ignored.
+Reads a block of ECP data.  The ``flags`` parameter is ignored.
 
 RETURN VALUE
+^^^^^^^^^^^^
 
 The number of bytes read.  NB. There may be more unread data in a
 FIFO.  Is there a way of stunning the FIFO to prevent this?
 
 SEE ALSO
+^^^^^^^^
 
 ecp_write_block, ecp_write_addr
-
+
+
+
 port->ops->ecp_write_addr - write a block of ECP addresses
--------------------------
+----------------------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-struct parport_operations {
-	...
-	size_t (*ecp_write_addr) (struct parport *port,
-				  const void *buf, size_t len, int flags);
-	...
-};
+	#include <linux/parport.h>
+
+	struct parport_operations {
+		...
+		size_t (*ecp_write_addr) (struct parport *port,
+					const void *buf, size_t len, int flags);
+		...
+	};
 
 DESCRIPTION
+^^^^^^^^^^^
 
-Writes a block of ECP addresses.  The 'flags' parameter is ignored.
+Writes a block of ECP addresses.  The ``flags`` parameter is ignored.
 
 RETURN VALUE
+^^^^^^^^^^^^
 
 The number of bytes written.
 
 NOTES
+^^^^^
 
 This may use a FIFO, and if so shall not return until the FIFO is empty.
 
 SEE ALSO
+^^^^^^^^
 
 ecp_read_data, ecp_write_data
-
+
+
+
 port->ops->nibble_read_data - read a block of data in nibble mode
----------------------------
+-----------------------------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-struct parport_operations {
-	...
-	size_t (*nibble_read_data) (struct parport *port,
-				    void *buf, size_t len, int flags);
-	...
-};
+	#include <linux/parport.h>
+
+	struct parport_operations {
+		...
+		size_t (*nibble_read_data) (struct parport *port,
+					void *buf, size_t len, int flags);
+		...
+	};
 
 DESCRIPTION
+^^^^^^^^^^^
 
-Reads a block of data in nibble mode.  The 'flags' parameter is ignored.
+Reads a block of data in nibble mode.  The ``flags`` parameter is ignored.
 
 RETURN VALUE
+^^^^^^^^^^^^
 
 The number of whole bytes read.
 
 SEE ALSO
+^^^^^^^^
 
 byte_read_data, compat_write_data
+
+
 
 port->ops->byte_read_data - read a block of data in byte mode
--------------------------
+-------------------------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-struct parport_operations {
-	...
-	size_t (*byte_read_data) (struct parport *port,
-				  void *buf, size_t len, int flags);
-	...
-};
+	#include <linux/parport.h>
+
+	struct parport_operations {
+		...
+		size_t (*byte_read_data) (struct parport *port,
+					void *buf, size_t len, int flags);
+		...
+	};
 
 DESCRIPTION
+^^^^^^^^^^^
 
-Reads a block of data in byte mode.  The 'flags' parameter is ignored.
+Reads a block of data in byte mode.  The ``flags`` parameter is ignored.
 
 RETURN VALUE
+^^^^^^^^^^^^
 
 The number of bytes read.
 
 SEE ALSO
+^^^^^^^^
 
 nibble_read_data, compat_write_data
+
+
 
 port->ops->compat_write_data - write a block of data in compatibility mode
-----------------------------
+--------------------------------------------------------------------------
 
 SYNOPSIS
+^^^^^^^^
 
-#include <linux/parport.h>
+::
 
-struct parport_operations {
-	...
-	size_t (*compat_write_data) (struct parport *port,
-				     const void *buf, size_t len, int flags);
-	...
-};
+	#include <linux/parport.h>
+
+	struct parport_operations {
+		...
+		size_t (*compat_write_data) (struct parport *port,
+					const void *buf, size_t len, int flags);
+		...
+	};
 
 DESCRIPTION
+^^^^^^^^^^^
 
-Writes a block of data in compatibility mode.  The 'flags' parameter
+Writes a block of data in compatibility mode.  The ``flags`` parameter
 is ignored.
 
 RETURN VALUE
+^^^^^^^^^^^^
 
 The number of bytes written.
 
 SEE ALSO
+^^^^^^^^
 
 nibble_read_data, byte_read_data
diff --git a/Documentation/percpu-rw-semaphore.txt b/Documentation/percpu-rw-semaphore.txt
index 7d3c824..247de64 100644
--- a/Documentation/percpu-rw-semaphore.txt
+++ b/Documentation/percpu-rw-semaphore.txt
@@ -1,5 +1,6 @@
+====================
 Percpu rw semaphores
---------------------
+====================
 
 Percpu rw semaphores is a new read-write semaphore design that is
 optimized for locking for reading.
diff --git a/Documentation/phy.txt b/Documentation/phy.txt
index 383cdd8..457c3e0 100644
--- a/Documentation/phy.txt
+++ b/Documentation/phy.txt
@@ -1,10 +1,14 @@
-			    PHY SUBSYSTEM
-		  Kishon Vijay Abraham I <kishon@ti.com>
+=============
+PHY subsystem
+=============
+
+:Author: Kishon Vijay Abraham I <kishon@ti.com>
 
 This document explains the Generic PHY Framework along with the APIs provided,
 and how-to-use.
 
-1. Introduction
+Introduction
+============
 
 *PHY* is the abbreviation for physical layer. It is used to connect a device
 to the physical medium e.g., the USB controller has a PHY to provide functions
@@ -21,7 +25,8 @@
 This framework will be of use only to devices that use external PHY (PHY
 functionality is not embedded within the controller).
 
-2. Registering/Unregistering the PHY provider
+Registering/Unregistering the PHY provider
+==========================================
 
 PHY provider refers to an entity that implements one or more PHY instances.
 For the simple case where the PHY provider implements only a single instance of
@@ -30,11 +35,14 @@
 should provide its own implementation of of_xlate. of_xlate is used only for
 dt boot case.
 
-#define of_phy_provider_register(dev, xlate)    \
-        __of_phy_provider_register((dev), NULL, THIS_MODULE, (xlate))
+::
 
-#define devm_of_phy_provider_register(dev, xlate)       \
-        __devm_of_phy_provider_register((dev), NULL, THIS_MODULE, (xlate))
+	#define of_phy_provider_register(dev, xlate)    \
+		__of_phy_provider_register((dev), NULL, THIS_MODULE, (xlate))
+
+	#define devm_of_phy_provider_register(dev, xlate)       \
+		__devm_of_phy_provider_register((dev), NULL, THIS_MODULE,
+						(xlate))
 
 of_phy_provider_register and devm_of_phy_provider_register macros can be used to
 register the phy_provider and it takes device and of_xlate as
@@ -47,28 +55,35 @@
 level of_phy_provider_register_full() and devm_of_phy_provider_register_full()
 macros can be used to override the node containing the children.
 
-#define of_phy_provider_register_full(dev, children, xlate) \
-	__of_phy_provider_register(dev, children, THIS_MODULE, xlate)
+::
 
-#define devm_of_phy_provider_register_full(dev, children, xlate) \
-	__devm_of_phy_provider_register_full(dev, children, THIS_MODULE, xlate)
+	#define of_phy_provider_register_full(dev, children, xlate) \
+		__of_phy_provider_register(dev, children, THIS_MODULE, xlate)
 
-void devm_of_phy_provider_unregister(struct device *dev,
-	struct phy_provider *phy_provider);
-void of_phy_provider_unregister(struct phy_provider *phy_provider);
+	#define devm_of_phy_provider_register_full(dev, children, xlate) \
+		__devm_of_phy_provider_register_full(dev, children,
+						     THIS_MODULE, xlate)
+
+	void devm_of_phy_provider_unregister(struct device *dev,
+		struct phy_provider *phy_provider);
+	void of_phy_provider_unregister(struct phy_provider *phy_provider);
 
 devm_of_phy_provider_unregister and of_phy_provider_unregister can be used to
 unregister the PHY.
 
-3. Creating the PHY
+Creating the PHY
+================
 
 The PHY driver should create the PHY in order for other peripheral controllers
 to make use of it. The PHY framework provides 2 APIs to create the PHY.
 
-struct phy *phy_create(struct device *dev, struct device_node *node,
-		       const struct phy_ops *ops);
-struct phy *devm_phy_create(struct device *dev, struct device_node *node,
-			    const struct phy_ops *ops);
+::
+
+	struct phy *phy_create(struct device *dev, struct device_node *node,
+			       const struct phy_ops *ops);
+	struct phy *devm_phy_create(struct device *dev,
+				    struct device_node *node,
+				    const struct phy_ops *ops);
 
 The PHY drivers can use one of the above 2 APIs to create the PHY by passing
 the device pointer and phy ops.
@@ -84,12 +99,16 @@
 Before the controller can make use of the PHY, it has to get a reference to
 it. This framework provides the following APIs to get a reference to the PHY.
 
-struct phy *phy_get(struct device *dev, const char *string);
-struct phy *phy_optional_get(struct device *dev, const char *string);
-struct phy *devm_phy_get(struct device *dev, const char *string);
-struct phy *devm_phy_optional_get(struct device *dev, const char *string);
-struct phy *devm_of_phy_get_by_index(struct device *dev, struct device_node *np,
-				     int index);
+::
+
+	struct phy *phy_get(struct device *dev, const char *string);
+	struct phy *phy_optional_get(struct device *dev, const char *string);
+	struct phy *devm_phy_get(struct device *dev, const char *string);
+	struct phy *devm_phy_optional_get(struct device *dev,
+					  const char *string);
+	struct phy *devm_of_phy_get_by_index(struct device *dev,
+					     struct device_node *np,
+					     int index);
 
 phy_get, phy_optional_get, devm_phy_get and devm_phy_optional_get can
 be used to get the PHY. In the case of dt boot, the string arguments
@@ -111,30 +130,35 @@
 phy_power_off() calls are all NOP when applied to a NULL phy. The NULL
 phy is useful in devices for handling optional phy devices.
 
-5. Releasing a reference to the PHY
+Releasing a reference to the PHY
+================================
 
 When the controller no longer needs the PHY, it has to release the reference
 to the PHY it has obtained using the APIs mentioned in the above section. The
 PHY framework provides 2 APIs to release a reference to the PHY.
 
-void phy_put(struct phy *phy);
-void devm_phy_put(struct device *dev, struct phy *phy);
+::
+
+	void phy_put(struct phy *phy);
+	void devm_phy_put(struct device *dev, struct phy *phy);
 
 Both these APIs are used to release a reference to the PHY and devm_phy_put
 destroys the devres associated with this PHY.
 
-6. Destroying the PHY
+Destroying the PHY
+==================
 
 When the driver that created the PHY is unloaded, it should destroy the PHY it
-created using one of the following 2 APIs.
+created using one of the following 2 APIs::
 
-void phy_destroy(struct phy *phy);
-void devm_phy_destroy(struct device *dev, struct phy *phy);
+	void phy_destroy(struct phy *phy);
+	void devm_phy_destroy(struct device *dev, struct phy *phy);
 
 Both these APIs destroy the PHY and devm_phy_destroy destroys the devres
 associated with this PHY.
 
-7. PM Runtime
+PM Runtime
+==========
 
 This subsystem is pm runtime enabled. So while creating the PHY,
 pm_runtime_enable of the phy device created by this subsystem is called and
@@ -150,7 +174,8 @@
 phy_pm_runtime_put, phy_pm_runtime_put_sync, phy_pm_runtime_allow and
 phy_pm_runtime_forbid for performing PM operations.
 
-8. PHY Mappings
+PHY Mappings
+============
 
 In order to get reference to a PHY without help from DeviceTree, the framework
 offers lookups which can be compared to clkdev that allow clk structures to be
@@ -158,12 +183,15 @@
 the struct phy already exists.
 
 The framework offers the following API for registering and unregistering the
-lookups.
+lookups::
 
-int phy_create_lookup(struct phy *phy, const char *con_id, const char *dev_id);
-void phy_remove_lookup(struct phy *phy, const char *con_id, const char *dev_id);
+	int phy_create_lookup(struct phy *phy, const char *con_id,
+			      const char *dev_id);
+	void phy_remove_lookup(struct phy *phy, const char *con_id,
+			       const char *dev_id);
 
-9. DeviceTree Binding
+DeviceTree Binding
+==================
 
 The documentation for PHY dt binding can be found @
 Documentation/devicetree/bindings/phy/phy-bindings.txt
diff --git a/Documentation/pi-futex.txt b/Documentation/pi-futex.txt
index 9a5bc86..aafddbe 100644
--- a/Documentation/pi-futex.txt
+++ b/Documentation/pi-futex.txt
@@ -1,5 +1,6 @@
+======================
 Lightweight PI-futexes
-----------------------
+======================
 
 We are calling them lightweight for 3 reasons:
 
@@ -25,8 +26,8 @@
 improve the statistical distribution of locking related application
 delays.
 
-The longer reply:
------------------
+The longer reply
+----------------
 
 Firstly, sharing locks between multiple tasks is a common programming
 technique that often cannot be replaced with lockless algorithms. As we
@@ -71,8 +72,8 @@
 could preempt the low-prio task while it holds the shared lock and
 executes the critical section, and could delay it indefinitely.
 
-Implementation:
----------------
+Implementation
+--------------
 
 As mentioned before, the userspace fastpath of PI-enabled pthread
 mutexes involves no kernel work at all - they behave quite similarly to
@@ -83,8 +84,8 @@
 
 To handle the slowpath, we have added two new futex ops:
 
-  FUTEX_LOCK_PI
-  FUTEX_UNLOCK_PI
+  - FUTEX_LOCK_PI
+  - FUTEX_UNLOCK_PI
 
 If the lock-acquire fastpath fails, [i.e. an atomic transition from 0 to
 TID fails], then FUTEX_LOCK_PI is called. The kernel does all the
diff --git a/Documentation/pnp.txt b/Documentation/pnp.txt
index 763e465..bab2d10 100644
--- a/Documentation/pnp.txt
+++ b/Documentation/pnp.txt
@@ -1,98 +1,118 @@
+=================================
 Linux Plug and Play Documentation
-by Adam Belay <ambx1@neo.rr.com>
-last updated: Oct. 16, 2002
----------------------------------------------------------------------------------------
+=================================
 
+:Author: Adam Belay <ambx1@neo.rr.com>
+:Last updated: Oct. 16, 2002
 
 
 Overview
 --------
-	Plug and Play provides a means of detecting and setting resources for legacy or
+
+Plug and Play provides a means of detecting and setting resources for legacy or
 otherwise unconfigurable devices.  The Linux Plug and Play Layer provides these 
 services to compatible drivers.
 
 
-
 The User Interface
 ------------------
-	The Linux Plug and Play user interface provides a means to activate PnP devices
+
+The Linux Plug and Play user interface provides a means to activate PnP devices
 for legacy and user level drivers that do not support Linux Plug and Play.  The 
 user interface is integrated into sysfs.
 
 In addition to the standard sysfs file the following are created in each
 device's directory:
-id - displays a list of support EISA IDs
-options - displays possible resource configurations
-resources - displays currently allocated resources and allows resource changes
+- id - displays a list of support EISA IDs
+- options - displays possible resource configurations
+- resources - displays currently allocated resources and allows resource changes
 
--activating a device
+activating a device
+^^^^^^^^^^^^^^^^^^^
 
-#echo "auto" > resources
+::
+
+	# echo "auto" > resources
 
 this will invoke the automatic resource config system to activate the device
 
--manually activating a device
+manually activating a device
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-#echo "manual <depnum> <mode>" > resources
-<depnum> - the configuration number
-<mode> - static or dynamic
-		static = for next boot
-		dynamic = now
+::
 
--disabling a device
+	# echo "manual <depnum> <mode>" > resources
 
-#echo "disable" > resources
+	<depnum> - the configuration number
+	<mode> - static or dynamic
+		 static = for next boot
+		 dynamic = now
+
+disabling a device
+^^^^^^^^^^^^^^^^^^
+
+::
+
+	# echo "disable" > resources
 
 
 EXAMPLE:
 
 Suppose you need to activate the floppy disk controller.
-1.) change to the proper directory, in my case it is 
-/driver/bus/pnp/devices/00:0f
-# cd /driver/bus/pnp/devices/00:0f
-# cat name
-PC standard floppy disk controller
 
-2.) check if the device is already active
-# cat resources
-DISABLED
+1. change to the proper directory, in my case it is
+   /driver/bus/pnp/devices/00:0f::
 
-- Notice the string "DISABLED".  This means the device is not active.
+	# cd /driver/bus/pnp/devices/00:0f
+	# cat name
+	PC standard floppy disk controller
 
-3.) check the device's possible configurations (optional)
-# cat options
-Dependent: 01 - Priority acceptable
-    port 0x3f0-0x3f0, align 0x7, size 0x6, 16-bit address decoding
-    port 0x3f7-0x3f7, align 0x0, size 0x1, 16-bit address decoding
-    irq 6
-    dma 2 8-bit compatible
-Dependent: 02 - Priority acceptable
-    port 0x370-0x370, align 0x7, size 0x6, 16-bit address decoding
-    port 0x377-0x377, align 0x0, size 0x1, 16-bit address decoding
-    irq 6
-    dma 2 8-bit compatible
+2. check if the device is already active::
 
-4.) now activate the device
-# echo "auto" > resources
+	# cat resources
+	DISABLED
 
-5.) finally check if the device is active
-# cat resources
-io 0x3f0-0x3f5
-io 0x3f7-0x3f7
-irq 6
-dma 2
+  - Notice the string "DISABLED".  This means the device is not active.
 
-also there are a series of kernel parameters:
-pnp_reserve_irq=irq1[,irq2] ....
-pnp_reserve_dma=dma1[,dma2] ....
-pnp_reserve_io=io1,size1[,io2,size2] ....
-pnp_reserve_mem=mem1,size1[,mem2,size2] ....
+3. check the device's possible configurations (optional)::
+
+	# cat options
+	Dependent: 01 - Priority acceptable
+	    port 0x3f0-0x3f0, align 0x7, size 0x6, 16-bit address decoding
+	    port 0x3f7-0x3f7, align 0x0, size 0x1, 16-bit address decoding
+	    irq 6
+	    dma 2 8-bit compatible
+	Dependent: 02 - Priority acceptable
+	    port 0x370-0x370, align 0x7, size 0x6, 16-bit address decoding
+	    port 0x377-0x377, align 0x0, size 0x1, 16-bit address decoding
+	    irq 6
+	    dma 2 8-bit compatible
+
+4. now activate the device::
+
+	# echo "auto" > resources
+
+5. finally check if the device is active::
+
+	# cat resources
+	io 0x3f0-0x3f5
+	io 0x3f7-0x3f7
+	irq 6
+	dma 2
+
+also there are a series of kernel parameters::
+
+	pnp_reserve_irq=irq1[,irq2] ....
+	pnp_reserve_dma=dma1[,dma2] ....
+	pnp_reserve_io=io1,size1[,io2,size2] ....
+	pnp_reserve_mem=mem1,size1[,mem2,size2] ....
 
 
 
 The Unified Plug and Play Layer
 -------------------------------
-	All Plug and Play drivers, protocols, and services meet at a central location 
+
+All Plug and Play drivers, protocols, and services meet at a central location
 called the Plug and Play Layer.  This layer is responsible for the exchange of 
 information between PnP drivers and PnP protocols.  Thus it automatically 
 forwards commands to the proper protocol.  This makes writing PnP drivers 
@@ -101,64 +121,73 @@
 The following functions are available from the Plug and Play Layer:
 
 pnp_get_protocol
-- increments the number of uses by one
+  increments the number of uses by one
 
 pnp_put_protocol
-- deincrements the number of uses by one
+  deincrements the number of uses by one
 
 pnp_register_protocol
-- use this to register a new PnP protocol
+  use this to register a new PnP protocol
 
 pnp_unregister_protocol
-- use this function to remove a PnP protocol from the Plug and Play Layer
+  use this function to remove a PnP protocol from the Plug and Play Layer
 
 pnp_register_driver
-- adds a PnP driver to the Plug and Play Layer
-- this includes driver model integration
-- returns zero for success or a negative error number for failure; count
+  adds a PnP driver to the Plug and Play Layer
+
+  this includes driver model integration
+  returns zero for success or a negative error number for failure; count
   calls to the .add() method if you need to know how many devices bind to
   the driver
 
 pnp_unregister_driver
-- removes a PnP driver from the Plug and Play Layer
+  removes a PnP driver from the Plug and Play Layer
 
 
 
 Plug and Play Protocols
 -----------------------
-	This section contains information for PnP protocol developers.
+
+This section contains information for PnP protocol developers.
 
 The following Protocols are currently available in the computing world:
-- PNPBIOS: used for system devices such as serial and parallel ports.
-- ISAPNP: provides PnP support for the ISA bus
-- ACPI: among its many uses, ACPI provides information about system level 
-devices.
+
+- PNPBIOS:
+    used for system devices such as serial and parallel ports.
+- ISAPNP:
+    provides PnP support for the ISA bus
+- ACPI:
+    among its many uses, ACPI provides information about system level
+    devices.
+
 It is meant to replace the PNPBIOS.  It is not currently supported by Linux
 Plug and Play but it is planned to be in the near future.
 
 
 Requirements for a Linux PnP protocol:
-1.) the protocol must use EISA IDs
-2.) the protocol must inform the PnP Layer of a device's current configuration
+1. the protocol must use EISA IDs
+2. the protocol must inform the PnP Layer of a device's current configuration
+
 - the ability to set resources is optional but preferred.
 
 The following are PnP protocol related functions:
 
 pnp_add_device
-- use this function to add a PnP device to the PnP layer
-- only call this function when all wanted values are set in the pnp_dev 
-structure
+  use this function to add a PnP device to the PnP layer
+
+  only call this function when all wanted values are set in the pnp_dev
+  structure
 
 pnp_init_device
-- call this to initialize the PnP structure
+  call this to initialize the PnP structure
 
 pnp_remove_device
-- call this to remove a device from the Plug and Play Layer.
-- it will fail if the device is still in use.
-- automatically will free mem used by the device and related structures
+  call this to remove a device from the Plug and Play Layer.
+  it will fail if the device is still in use.
+  automatically will free mem used by the device and related structures
 
 pnp_add_id
-- adds an EISA ID to the list of supported IDs for the specified device
+  adds an EISA ID to the list of supported IDs for the specified device
 
 For more information consult the source of a protocol such as
 /drivers/pnp/pnpbios/core.c.
@@ -167,85 +196,97 @@
 
 Linux Plug and Play Drivers
 ---------------------------
-	This section contains information for Linux PnP driver developers.
+
+This section contains information for Linux PnP driver developers.
 
 The New Way
-...........
-1.) first make a list of supported EISA IDS
-ex:
-static const struct pnp_id pnp_dev_table[] = {
-	/* Standard LPT Printer Port */
-	{.id = "PNP0400", .driver_data = 0},
-	/* ECP Printer Port */
-	{.id = "PNP0401", .driver_data = 0},
-	{.id = ""}
-};
+^^^^^^^^^^^
 
-Please note that the character 'X' can be used as a wild card in the function
-portion (last four characters).
-ex:
+1. first make a list of supported EISA IDS
+
+   ex::
+
+	static const struct pnp_id pnp_dev_table[] = {
+		/* Standard LPT Printer Port */
+		{.id = "PNP0400", .driver_data = 0},
+		/* ECP Printer Port */
+		{.id = "PNP0401", .driver_data = 0},
+		{.id = ""}
+	};
+
+   Please note that the character 'X' can be used as a wild card in the function
+   portion (last four characters).
+
+   ex::
+
 	/* Unknown PnP modems */
 	{	"PNPCXXX",		UNKNOWN_DEV	},
 
-Supported PnP card IDs can optionally be defined.
-ex:
-static const struct pnp_id pnp_card_table[] = {
-	{	"ANYDEVS",		0	},
-	{	"",			0	}
-};
+   Supported PnP card IDs can optionally be defined.
+   ex::
 
-2.) Optionally define probe and remove functions.  It may make sense not to 
-define these functions if the driver already has a reliable method of detecting
-the resources, such as the parport_pc driver.
-ex:
-static int
-serial_pnp_probe(struct pnp_dev * dev, const struct pnp_id *card_id, const 
-                 struct pnp_id *dev_id)
-{
-. . .
+	static const struct pnp_id pnp_card_table[] = {
+		{	"ANYDEVS",		0	},
+		{	"",			0	}
+	};
 
-ex:
-static void serial_pnp_remove(struct pnp_dev * dev)
-{
-. . .
+2. Optionally define probe and remove functions.  It may make sense not to
+   define these functions if the driver already has a reliable method of detecting
+   the resources, such as the parport_pc driver.
 
-consult /drivers/serial/8250_pnp.c for more information.
+   ex::
 
-3.) create a driver structure
-ex:
+	static int
+	serial_pnp_probe(struct pnp_dev * dev, const struct pnp_id *card_id, const
+			struct pnp_id *dev_id)
+	{
+	. . .
 
-static struct pnp_driver serial_pnp_driver = {
-	.name		= "serial",
-	.card_id_table	= pnp_card_table,
-	.id_table	= pnp_dev_table,
-	.probe		= serial_pnp_probe,
-	.remove		= serial_pnp_remove,
-};
+   ex::
 
-* name and id_table cannot be NULL.
+	static void serial_pnp_remove(struct pnp_dev * dev)
+	{
+	. . .
 
-4.) register the driver
-ex:
+   consult /drivers/serial/8250_pnp.c for more information.
 
-static int __init serial8250_pnp_init(void)
-{
-	return pnp_register_driver(&serial_pnp_driver);
-}
+3. create a driver structure
+
+   ex::
+
+	static struct pnp_driver serial_pnp_driver = {
+		.name		= "serial",
+		.card_id_table	= pnp_card_table,
+		.id_table	= pnp_dev_table,
+		.probe		= serial_pnp_probe,
+		.remove		= serial_pnp_remove,
+	};
+
+   * name and id_table cannot be NULL.
+
+4. register the driver
+
+   ex::
+
+	static int __init serial8250_pnp_init(void)
+	{
+		return pnp_register_driver(&serial_pnp_driver);
+	}
 
 The Old Way
-...........
+^^^^^^^^^^^
 
 A series of compatibility functions have been created to make it easy to convert
 ISAPNP drivers.  They should serve as a temporary solution only.
 
-They are as follows:
+They are as follows::
 
-struct pnp_card *pnp_find_card(unsigned short vendor,
-				 unsigned short device,
-				 struct pnp_card *from)
+	struct pnp_card *pnp_find_card(unsigned short vendor,
+				       unsigned short device,
+				       struct pnp_card *from)
 
-struct pnp_dev *pnp_find_dev(struct pnp_card *card,
-				unsigned short vendor,
-				unsigned short function,
-				struct pnp_dev *from)
+	struct pnp_dev *pnp_find_dev(struct pnp_card *card,
+				     unsigned short vendor,
+				     unsigned short function,
+				     struct pnp_dev *from)
 
diff --git a/Documentation/preempt-locking.txt b/Documentation/preempt-locking.txt
index e89ce66..c945062 100644
--- a/Documentation/preempt-locking.txt
+++ b/Documentation/preempt-locking.txt
@@ -1,10 +1,13 @@
-		  Proper Locking Under a Preemptible Kernel:
-		       Keeping Kernel Code Preempt-Safe
-			 Robert Love <rml@tech9.net>
-			  Last Updated: 28 Aug 2002
+===========================================================================
+Proper Locking Under a Preemptible Kernel: Keeping Kernel Code Preempt-Safe
+===========================================================================
+
+:Author: Robert Love <rml@tech9.net>
+:Last Updated: 28 Aug 2002
 
 
-INTRODUCTION
+Introduction
+============
 
 
 A preemptible kernel creates new locking issues.  The issues are the same as
@@ -17,9 +20,10 @@
  
 
 RULE #1: Per-CPU data structures need explicit protection
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 
-Two similar problems arise. An example code snippet:
+Two similar problems arise. An example code snippet::
 
 	struct this_needs_locking tux[NR_CPUS];
 	tux[smp_processor_id()] = some_value;
@@ -35,6 +39,7 @@
 
 
 RULE #2: CPU state must be protected.
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 
 Under preemption, the state of the CPU must be protected.  This is arch-
@@ -52,6 +57,7 @@
 
 
 RULE #3: Lock acquire and release must be performed by same task
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 
 A lock acquired in one task must be released by the same task.  This
@@ -61,17 +67,20 @@
 have the caller wait on an event by the other task.
 
 
-SOLUTION
+Solution
+========
 
 
 Data protection under preemption is achieved by disabling preemption for the
 duration of the critical region.
 
-preempt_enable()		decrement the preempt counter
-preempt_disable()		increment the preempt counter
-preempt_enable_no_resched()	decrement, but do not immediately preempt
-preempt_check_resched()		if needed, reschedule
-preempt_count()			return the preempt counter
+::
+
+  preempt_enable()		decrement the preempt counter
+  preempt_disable()		increment the preempt counter
+  preempt_enable_no_resched()	decrement, but do not immediately preempt
+  preempt_check_resched()	if needed, reschedule
+  preempt_count()		return the preempt counter
 
 The functions are nestable.  In other words, you can call preempt_disable
 n-times in a code path, and preemption will not be reenabled until the n-th
@@ -89,7 +98,7 @@
 affected codepath does not do any of this. Best policy is to use this only for
 small, atomic code that you wrote and which calls no complex functions.
 
-Example:
+Example::
 
 	cpucache_t *cc; /* this is per-CPU */
 	preempt_disable();
@@ -102,7 +111,7 @@
 	return 0;
 
 Notice how the preemption statements must encompass every reference of the
-critical variables.  Another example:
+critical variables.  Another example::
 
 	int buf[NR_CPUS];
 	set_cpu_val(buf);
@@ -114,7 +123,8 @@
 moving the spin_lock up two lines.
 
 
-PREVENTING PREEMPTION USING INTERRUPT DISABLING
+Preventing preemption using interrupt disabling
+===============================================
 
 
 It is possible to prevent a preemption event using local_irq_disable and
diff --git a/Documentation/printk-formats.txt b/Documentation/printk-formats.txt
index 619cdff..65ea591 100644
--- a/Documentation/printk-formats.txt
+++ b/Documentation/printk-formats.txt
@@ -1,5 +1,18 @@
-If variable is of Type,		use printk format specifier:
----------------------------------------------------------
+=========================================
+How to get printk format specifiers right
+=========================================
+
+:Author: Randy Dunlap <rdunlap@infradead.org>
+:Author: Andrew Murray <amurray@mpc-data.co.uk>
+
+
+Integer types
+=============
+
+::
+
+	If variable is of Type,		use printk format specifier:
+	------------------------------------------------------------
 		int			%d or %x
 		unsigned int		%u or %x
 		long			%ld or %lx
@@ -13,25 +26,29 @@
 		s64			%lld or %llx
 		u64			%llu or %llx
 
-If <type> is dependent on a config option for its size (e.g., sector_t,
-blkcnt_t) or is architecture-dependent for its size (e.g., tcflag_t), use a
-format specifier of its largest possible type and explicitly cast to it.
-Example:
+If <type> is dependent on a config option for its size (e.g., ``sector_t``,
+``blkcnt_t``) or is architecture-dependent for its size (e.g., ``tcflag_t``),
+use a format specifier of its largest possible type and explicitly cast to it.
+
+Example::
 
 	printk("test: sector number/total blocks: %llu/%llu\n",
 		(unsigned long long)sector, (unsigned long long)blockcount);
 
-Reminder: sizeof() result is of type size_t.
+Reminder: ``sizeof()`` result is of type ``size_t``.
 
-The kernel's printf does not support %n. For obvious reasons, floating
-point formats (%e, %f, %g, %a) are also not recognized. Use of any
+The kernel's printf does not support ``%n``. For obvious reasons, floating
+point formats (``%e, %f, %g, %a``) are also not recognized. Use of any
 unsupported specifier or length qualifier results in a WARN and early
 return from vsnprintf.
 
 Raw pointer value SHOULD be printed with %p. The kernel supports
 the following extended format specifiers for pointer types:
 
-Symbols/Function Pointers:
+Symbols/Function Pointers
+=========================
+
+::
 
 	%pF	versatile_init+0x0/0x110
 	%pf	versatile_init
@@ -41,99 +58,122 @@
 	%ps	versatile_init
 	%pB	prev_fn_of_versatile_init+0x88/0x88
 
-	For printing symbols and function pointers. The 'S' and 's' specifiers
-	result in the symbol name with ('S') or without ('s') offsets. Where
-	this is used on a kernel without KALLSYMS - the symbol address is
-	printed instead.
+For printing symbols and function pointers. The ``S`` and ``s`` specifiers
+result in the symbol name with (``S``) or without (``s``) offsets. Where
+this is used on a kernel without KALLSYMS - the symbol address is
+printed instead.
 
-	The 'B' specifier results in the symbol name with offsets and should be
-	used when printing stack backtraces. The specifier takes into
-	consideration the effect of compiler optimisations which may occur
-	when tail-call's are used and marked with the noreturn GCC attribute.
+The ``B`` specifier results in the symbol name with offsets and should be
+used when printing stack backtraces. The specifier takes into
+consideration the effect of compiler optimisations which may occur
+when tail-call``s are used and marked with the noreturn GCC attribute.
 
-	On ia64, ppc64 and parisc64 architectures function pointers are
-	actually function descriptors which must first be resolved. The 'F' and
-	'f' specifiers perform this resolution and then provide the same
-	functionality as the 'S' and 's' specifiers.
+On ia64, ppc64 and parisc64 architectures function pointers are
+actually function descriptors which must first be resolved. The ``F`` and
+``f`` specifiers perform this resolution and then provide the same
+functionality as the ``S`` and ``s`` specifiers.
 
-Kernel Pointers:
+Kernel Pointers
+===============
+
+::
 
 	%pK	0x01234567 or 0x0123456789abcdef
 
-	For printing kernel pointers which should be hidden from unprivileged
-	users. The behaviour of %pK depends on the kptr_restrict sysctl - see
-	Documentation/sysctl/kernel.txt for more details.
+For printing kernel pointers which should be hidden from unprivileged
+users. The behaviour of ``%pK`` depends on the ``kptr_restrict sysctl`` - see
+Documentation/sysctl/kernel.txt for more details.
 
-Struct Resources:
+Struct Resources
+================
+
+::
 
 	%pr	[mem 0x60000000-0x6fffffff flags 0x2200] or
 		[mem 0x0000000060000000-0x000000006fffffff flags 0x2200]
 	%pR	[mem 0x60000000-0x6fffffff pref] or
 		[mem 0x0000000060000000-0x000000006fffffff pref]
 
-	For printing struct resources. The 'R' and 'r' specifiers result in a
-	printed resource with ('R') or without ('r') a decoded flags member.
-	Passed by reference.
+For printing struct resources. The ``R`` and ``r`` specifiers result in a
+printed resource with (``R``) or without (``r``) a decoded flags member.
+Passed by reference.
 
-Physical addresses types phys_addr_t:
+Physical addresses types ``phys_addr_t``
+========================================
+
+::
 
 	%pa[p]	0x01234567 or 0x0123456789abcdef
 
-	For printing a phys_addr_t type (and its derivatives, such as
-	resource_size_t) which can vary based on build options, regardless of
-	the width of the CPU data path. Passed by reference.
+For printing a ``phys_addr_t`` type (and its derivatives, such as
+``resource_size_t``) which can vary based on build options, regardless of
+the width of the CPU data path. Passed by reference.
 
-DMA addresses types dma_addr_t:
+DMA addresses types ``dma_addr_t``
+==================================
+
+::
 
 	%pad	0x01234567 or 0x0123456789abcdef
 
-	For printing a dma_addr_t type which can vary based on build options,
-	regardless of the width of the CPU data path. Passed by reference.
+For printing a ``dma_addr_t`` type which can vary based on build options,
+regardless of the width of the CPU data path. Passed by reference.
 
-Raw buffer as an escaped string:
+Raw buffer as an escaped string
+===============================
+
+::
 
 	%*pE[achnops]
 
-	For printing raw buffer as an escaped string. For the following buffer
+For printing raw buffer as an escaped string. For the following buffer::
 
 		1b 62 20 5c 43 07 22 90 0d 5d
 
-	few examples show how the conversion would be done (the result string
-	without surrounding quotes):
+few examples show how the conversion would be done (the result string
+without surrounding quotes)::
 
 		%*pE		"\eb \C\a"\220\r]"
 		%*pEhp		"\x1bb \C\x07"\x90\x0d]"
 		%*pEa		"\e\142\040\\\103\a\042\220\r\135"
 
-	The conversion rules are applied according to an optional combination
-	of flags (see string_escape_mem() kernel documentation for the
-	details):
-		a - ESCAPE_ANY
-		c - ESCAPE_SPECIAL
-		h - ESCAPE_HEX
-		n - ESCAPE_NULL
-		o - ESCAPE_OCTAL
-		p - ESCAPE_NP
-		s - ESCAPE_SPACE
-	By default ESCAPE_ANY_NP is used.
+The conversion rules are applied according to an optional combination
+of flags (see :c:func:`string_escape_mem` kernel documentation for the
+details):
 
-	ESCAPE_ANY_NP is the sane choice for many cases, in particularly for
-	printing SSIDs.
+	- ``a`` - ESCAPE_ANY
+	- ``c`` - ESCAPE_SPECIAL
+	- ``h`` - ESCAPE_HEX
+	- ``n`` - ESCAPE_NULL
+	- ``o`` - ESCAPE_OCTAL
+	- ``p`` - ESCAPE_NP
+	- ``s`` - ESCAPE_SPACE
 
-	If field width is omitted the 1 byte only will be escaped.
+By default ESCAPE_ANY_NP is used.
 
-Raw buffer as a hex string:
+ESCAPE_ANY_NP is the sane choice for many cases, in particularly for
+printing SSIDs.
+
+If field width is omitted the 1 byte only will be escaped.
+
+Raw buffer as a hex string
+==========================
+
+::
 
 	%*ph	00 01 02  ...  3f
 	%*phC	00:01:02: ... :3f
 	%*phD	00-01-02- ... -3f
 	%*phN	000102 ... 3f
 
-	For printing a small buffers (up to 64 bytes long) as a hex string with
-	certain separator. For the larger buffers consider to use
-	print_hex_dump().
+For printing a small buffers (up to 64 bytes long) as a hex string with
+certain separator. For the larger buffers consider to use
+:c:func:`print_hex_dump`.
 
-MAC/FDDI addresses:
+MAC/FDDI addresses
+==================
+
+::
 
 	%pM	00:01:02:03:04:05
 	%pMR	05:04:03:02:01:00
@@ -141,53 +181,62 @@
 	%pm	000102030405
 	%pmR	050403020100
 
-	For printing 6-byte MAC/FDDI addresses in hex notation. The 'M' and 'm'
-	specifiers result in a printed address with ('M') or without ('m') byte
-	separators. The default byte separator is the colon (':').
+For printing 6-byte MAC/FDDI addresses in hex notation. The ``M`` and ``m``
+specifiers result in a printed address with (``M``) or without (``m``) byte
+separators. The default byte separator is the colon (``:``).
 
-	Where FDDI addresses are concerned the 'F' specifier can be used after
-	the 'M' specifier to use dash ('-') separators instead of the default
-	separator.
+Where FDDI addresses are concerned the ``F`` specifier can be used after
+the ``M`` specifier to use dash (``-``) separators instead of the default
+separator.
 
-	For Bluetooth addresses the 'R' specifier shall be used after the 'M'
-	specifier to use reversed byte order suitable for visual interpretation
-	of Bluetooth addresses which are in the little endian order.
+For Bluetooth addresses the ``R`` specifier shall be used after the ``M``
+specifier to use reversed byte order suitable for visual interpretation
+of Bluetooth addresses which are in the little endian order.
 
-	Passed by reference.
+Passed by reference.
 
-IPv4 addresses:
+IPv4 addresses
+==============
+
+::
 
 	%pI4	1.2.3.4
 	%pi4	001.002.003.004
 	%p[Ii]4[hnbl]
 
-	For printing IPv4 dot-separated decimal addresses. The 'I4' and 'i4'
-	specifiers result in a printed address with ('i4') or without ('I4')
-	leading zeros.
+For printing IPv4 dot-separated decimal addresses. The ``I4`` and ``i4``
+specifiers result in a printed address with (``i4``) or without (``I4``)
+leading zeros.
 
-	The additional 'h', 'n', 'b', and 'l' specifiers are used to specify
-	host, network, big or little endian order addresses respectively. Where
-	no specifier is provided the default network/big endian order is used.
+The additional ``h``, ``n``, ``b``, and ``l`` specifiers are used to specify
+host, network, big or little endian order addresses respectively. Where
+no specifier is provided the default network/big endian order is used.
 
-	Passed by reference.
+Passed by reference.
 
-IPv6 addresses:
+IPv6 addresses
+==============
+
+::
 
 	%pI6	0001:0002:0003:0004:0005:0006:0007:0008
 	%pi6	00010002000300040005000600070008
 	%pI6c	1:2:3:4:5:6:7:8
 
-	For printing IPv6 network-order 16-bit hex addresses. The 'I6' and 'i6'
-	specifiers result in a printed address with ('I6') or without ('i6')
-	colon-separators. Leading zeros are always used.
+For printing IPv6 network-order 16-bit hex addresses. The ``I6`` and ``i6``
+specifiers result in a printed address with (``I6``) or without (``i6``)
+colon-separators. Leading zeros are always used.
 
-	The additional 'c' specifier can be used with the 'I' specifier to
-	print a compressed IPv6 address as described by
-	http://tools.ietf.org/html/rfc5952
+The additional ``c`` specifier can be used with the ``I`` specifier to
+print a compressed IPv6 address as described by
+http://tools.ietf.org/html/rfc5952
 
-	Passed by reference.
+Passed by reference.
 
-IPv4/IPv6 addresses (generic, with port, flowinfo, scope):
+IPv4/IPv6 addresses (generic, with port, flowinfo, scope)
+=========================================================
+
+::
 
 	%pIS	1.2.3.4		or 0001:0002:0003:0004:0005:0006:0007:0008
 	%piS	001.002.003.004	or 00010002000300040005000600070008
@@ -195,87 +244,103 @@
 	%pISpc	1.2.3.4:12345	or [1:2:3:4:5:6:7:8]:12345
 	%p[Ii]S[pfschnbl]
 
-	For printing an IP address without the need to distinguish whether it's
-	of type AF_INET or AF_INET6, a pointer to a valid 'struct sockaddr',
-	specified through 'IS' or 'iS', can be passed to this format specifier.
+For printing an IP address without the need to distinguish whether it``s
+of type AF_INET or AF_INET6, a pointer to a valid ``struct sockaddr``,
+specified through ``IS`` or ``iS``, can be passed to this format specifier.
 
-	The additional 'p', 'f', and 's' specifiers are used to specify port
-	(IPv4, IPv6), flowinfo (IPv6) and scope (IPv6). Ports have a ':' prefix,
-	flowinfo a '/' and scope a '%', each followed by the actual value.
+The additional ``p``, ``f``, and ``s`` specifiers are used to specify port
+(IPv4, IPv6), flowinfo (IPv6) and scope (IPv6). Ports have a ``:`` prefix,
+flowinfo a ``/`` and scope a ``%``, each followed by the actual value.
 
-	In case of an IPv6 address the compressed IPv6 address as described by
-	http://tools.ietf.org/html/rfc5952 is being used if the additional
-	specifier 'c' is given. The IPv6 address is surrounded by '[', ']' in
-	case of additional specifiers 'p', 'f' or 's' as suggested by
-	https://tools.ietf.org/html/draft-ietf-6man-text-addr-representation-07
+In case of an IPv6 address the compressed IPv6 address as described by
+http://tools.ietf.org/html/rfc5952 is being used if the additional
+specifier ``c`` is given. The IPv6 address is surrounded by ``[``, ``]`` in
+case of additional specifiers ``p``, ``f`` or ``s`` as suggested by
+https://tools.ietf.org/html/draft-ietf-6man-text-addr-representation-07
 
-	In case of IPv4 addresses, the additional 'h', 'n', 'b', and 'l'
-	specifiers can be used as well and are ignored in case of an IPv6
-	address.
+In case of IPv4 addresses, the additional ``h``, ``n``, ``b``, and ``l``
+specifiers can be used as well and are ignored in case of an IPv6
+address.
 
-	Passed by reference.
+Passed by reference.
 
-	Further examples:
+Further examples::
 
 	%pISfc		1.2.3.4		or [1:2:3:4:5:6:7:8]/123456789
 	%pISsc		1.2.3.4		or [1:2:3:4:5:6:7:8]%1234567890
 	%pISpfc		1.2.3.4:12345	or [1:2:3:4:5:6:7:8]:12345/123456789
 
-UUID/GUID addresses:
+UUID/GUID addresses
+===================
+
+::
 
 	%pUb	00010203-0405-0607-0809-0a0b0c0d0e0f
 	%pUB	00010203-0405-0607-0809-0A0B0C0D0E0F
 	%pUl	03020100-0504-0706-0809-0a0b0c0e0e0f
 	%pUL	03020100-0504-0706-0809-0A0B0C0E0E0F
 
-	For printing 16-byte UUID/GUIDs addresses. The additional 'l', 'L',
-	'b' and 'B' specifiers are used to specify a little endian order in
-	lower ('l') or upper case ('L') hex characters - and big endian order
-	in lower ('b') or upper case ('B') hex characters.
+For printing 16-byte UUID/GUIDs addresses. The additional 'l', 'L',
+'b' and 'B' specifiers are used to specify a little endian order in
+lower ('l') or upper case ('L') hex characters - and big endian order
+in lower ('b') or upper case ('B') hex characters.
 
-	Where no additional specifiers are used the default big endian
-	order with lower case hex characters will be printed.
+Where no additional specifiers are used the default big endian
+order with lower case hex characters will be printed.
 
-	Passed by reference.
+Passed by reference.
 
-dentry names:
+dentry names
+============
+
+::
 
 	%pd{,2,3,4}
 	%pD{,2,3,4}
 
-	For printing dentry name; if we race with d_move(), the name might be
-	a mix of old and new ones, but it won't oops.  %pd dentry is a safer
-	equivalent of %s dentry->d_name.name we used to use, %pd<n> prints
-	n last components.  %pD does the same thing for struct file.
+For printing dentry name; if we race with :c:func:`d_move`, the name might be
+a mix of old and new ones, but it won't oops.  ``%pd`` dentry is a safer
+equivalent of ``%s`` ``dentry->d_name.name`` we used to use, ``%pd<n>`` prints
+``n`` last components.  ``%pD`` does the same thing for struct file.
 
-	Passed by reference.
+Passed by reference.
 
-block_device names:
+block_device names
+==================
+
+::
 
 	%pg	sda, sda1 or loop0p1
 
-	For printing name of block_device pointers.
+For printing name of block_device pointers.
 
-struct va_format:
+struct va_format
+================
+
+::
 
 	%pV
 
-	For printing struct va_format structures. These contain a format string
-	and va_list as follows:
+For printing struct va_format structures. These contain a format string
+and va_list as follows::
 
 	struct va_format {
 		const char *fmt;
 		va_list *va;
 	};
 
-	Implements a "recursive vsnprintf".
+Implements a "recursive vsnprintf".
 
-	Do not use this feature without some mechanism to verify the
-	correctness of the format string and va_list arguments.
+Do not use this feature without some mechanism to verify the
+correctness of the format string and va_list arguments.
 
-	Passed by reference.
+Passed by reference.
 
-kobjects:
+kobjects
+========
+
+::
+
 	%pO
 
 	Base specifier for kobject based structs. Must be followed with
@@ -311,61 +376,70 @@
 
 	Passed by reference.
 
-struct clk:
+
+struct clk
+==========
+
+::
 
 	%pC	pll1
 	%pCn	pll1
 	%pCr	1560000000
 
-	For printing struct clk structures. '%pC' and '%pCn' print the name
-	(Common Clock Framework) or address (legacy clock framework) of the
-	structure; '%pCr' prints the current clock rate.
+For printing struct clk structures. ``%pC`` and ``%pCn`` print the name
+(Common Clock Framework) or address (legacy clock framework) of the
+structure; ``%pCr`` prints the current clock rate.
 
-	Passed by reference.
+Passed by reference.
 
-bitmap and its derivatives such as cpumask and nodemask:
+bitmap and its derivatives such as cpumask and nodemask
+=======================================================
+
+::
 
 	%*pb	0779
 	%*pbl	0,3-6,8-10
 
-	For printing bitmap and its derivatives such as cpumask and nodemask,
-	%*pb output the bitmap with field width as the number of bits and %*pbl
-	output the bitmap as range list with field width as the number of bits.
+For printing bitmap and its derivatives such as cpumask and nodemask,
+``%*pb`` output the bitmap with field width as the number of bits and ``%*pbl``
+output the bitmap as range list with field width as the number of bits.
 
-	Passed by reference.
+Passed by reference.
 
-Flags bitfields such as page flags, gfp_flags:
+Flags bitfields such as page flags, gfp_flags
+=============================================
+
+::
 
 	%pGp	referenced|uptodate|lru|active|private
 	%pGg	GFP_USER|GFP_DMA32|GFP_NOWARN
 	%pGv	read|exec|mayread|maywrite|mayexec|denywrite
 
-	For printing flags bitfields as a collection of symbolic constants that
-	would construct the value. The type of flags is given by the third
-	character. Currently supported are [p]age flags, [v]ma_flags (both
-	expect unsigned long *) and [g]fp_flags (expects gfp_t *). The flag
-	names and print order depends on the particular	type.
+For printing flags bitfields as a collection of symbolic constants that
+would construct the value. The type of flags is given by the third
+character. Currently supported are [p]age flags, [v]ma_flags (both
+expect ``unsigned long *``) and [g]fp_flags (expects ``gfp_t *``). The flag
+names and print order depends on the particular	type.
 
-	Note that this format should not be used directly in TP_printk() part
-	of a tracepoint. Instead, use the show_*_flags() functions from
-	<trace/events/mmflags.h>.
+Note that this format should not be used directly in :c:func:`TP_printk()` part
+of a tracepoint. Instead, use the ``show_*_flags()`` functions from
+<trace/events/mmflags.h>.
 
-	Passed by reference.
+Passed by reference.
 
-Network device features:
+Network device features
+=======================
+
+::
 
 	%pNF	0x000000000000c000
 
-	For printing netdev_features_t.
+For printing netdev_features_t.
 
-	Passed by reference.
+Passed by reference.
 
-If you add other %p extensions, please extend lib/test_printf.c with
+If you add other ``%p`` extensions, please extend lib/test_printf.c with
 one or more test cases, if at all feasible.
 
 
 Thank you for your cooperation and attention.
-
-
-By Randy Dunlap <rdunlap@infradead.org> and
-Andrew Murray <amurray@mpc-data.co.uk>
diff --git a/Documentation/rbtree.txt b/Documentation/rbtree.txt
index b9d9cc5..b8a8c70 100644
--- a/Documentation/rbtree.txt
+++ b/Documentation/rbtree.txt
@@ -1,7 +1,10 @@
+=================================
 Red-black Trees (rbtree) in Linux
-January 18, 2007
-Rob Landley <rob@landley.net>
-=============================
+=================================
+
+
+:Date: January 18, 2007
+:Author: Rob Landley <rob@landley.net>
 
 What are red-black trees, and what are they for?
 ------------------------------------------------
@@ -56,7 +59,7 @@
 Creating a new rbtree
 ---------------------
 
-Data nodes in an rbtree tree are structures containing a struct rb_node member:
+Data nodes in an rbtree tree are structures containing a struct rb_node member::
 
   struct mytype {
   	struct rb_node node;
@@ -78,7 +81,7 @@
 Writing a search function for your tree is fairly straightforward: start at the
 root, compare each value, and follow the left or right branch as necessary.
 
-Example:
+Example::
 
   struct mytype *my_search(struct rb_root *root, char *string)
   {
@@ -110,7 +113,7 @@
 location of the pointer on which to graft the new node.  The new node also
 needs a link to its parent node for rebalancing purposes.
 
-Example:
+Example::
 
   int my_insert(struct rb_root *root, struct mytype *data)
   {
@@ -140,11 +143,11 @@
 Removing or replacing existing data in an rbtree
 ------------------------------------------------
 
-To remove an existing node from a tree, call:
+To remove an existing node from a tree, call::
 
   void rb_erase(struct rb_node *victim, struct rb_root *tree);
 
-Example:
+Example::
 
   struct mytype *data = mysearch(&mytree, "walrus");
 
@@ -153,7 +156,7 @@
   	myfree(data);
   }
 
-To replace an existing node in a tree with a new one with the same key, call:
+To replace an existing node in a tree with a new one with the same key, call::
 
   void rb_replace_node(struct rb_node *old, struct rb_node *new,
   			struct rb_root *tree);
@@ -166,7 +169,7 @@
 
 Four functions are provided for iterating through an rbtree's contents in
 sorted order.  These work on arbitrary trees, and should not need to be
-modified or wrapped (except for locking purposes):
+modified or wrapped (except for locking purposes)::
 
   struct rb_node *rb_first(struct rb_root *tree);
   struct rb_node *rb_last(struct rb_root *tree);
@@ -184,7 +187,7 @@
 macro, and individual members may be accessed directly via
 rb_entry(node, type, member).
 
-Example:
+Example::
 
   struct rb_node *node;
   for (node = rb_first(&mytree); node; node = rb_next(node))
@@ -241,7 +244,8 @@
 compiled code size.
 
 
-Sample usage:
+Sample usage
+^^^^^^^^^^^^
 
 Interval tree is an example of augmented rb tree. Reference -
 "Introduction to Algorithms" by Cormen, Leiserson, Rivest and Stein.
@@ -259,12 +263,12 @@
 information can be maintained at each node just be looking at the node
 and its immediate children. And this will be used in O(log n) lookup
 for lowest match (lowest start address among all possible matches)
-with something like:
+with something like::
 
-struct interval_tree_node *
-interval_tree_first_match(struct rb_root *root,
-			  unsigned long start, unsigned long last)
-{
+  struct interval_tree_node *
+  interval_tree_first_match(struct rb_root *root,
+			    unsigned long start, unsigned long last)
+  {
 	struct interval_tree_node *node;
 
 	if (!root->rb_node)
@@ -301,13 +305,13 @@
 		}
 		return NULL;	/* No match */
 	}
-}
+  }
 
-Insertion/removal are defined using the following augmented callbacks:
+Insertion/removal are defined using the following augmented callbacks::
 
-static inline unsigned long
-compute_subtree_last(struct interval_tree_node *node)
-{
+  static inline unsigned long
+  compute_subtree_last(struct interval_tree_node *node)
+  {
 	unsigned long max = node->last, subtree_last;
 	if (node->rb.rb_left) {
 		subtree_last = rb_entry(node->rb.rb_left,
@@ -322,10 +326,10 @@
 			max = subtree_last;
 	}
 	return max;
-}
+  }
 
-static void augment_propagate(struct rb_node *rb, struct rb_node *stop)
-{
+  static void augment_propagate(struct rb_node *rb, struct rb_node *stop)
+  {
 	while (rb != stop) {
 		struct interval_tree_node *node =
 			rb_entry(rb, struct interval_tree_node, rb);
@@ -335,20 +339,20 @@
 		node->__subtree_last = subtree_last;
 		rb = rb_parent(&node->rb);
 	}
-}
+  }
 
-static void augment_copy(struct rb_node *rb_old, struct rb_node *rb_new)
-{
+  static void augment_copy(struct rb_node *rb_old, struct rb_node *rb_new)
+  {
 	struct interval_tree_node *old =
 		rb_entry(rb_old, struct interval_tree_node, rb);
 	struct interval_tree_node *new =
 		rb_entry(rb_new, struct interval_tree_node, rb);
 
 	new->__subtree_last = old->__subtree_last;
-}
+  }
 
-static void augment_rotate(struct rb_node *rb_old, struct rb_node *rb_new)
-{
+  static void augment_rotate(struct rb_node *rb_old, struct rb_node *rb_new)
+  {
 	struct interval_tree_node *old =
 		rb_entry(rb_old, struct interval_tree_node, rb);
 	struct interval_tree_node *new =
@@ -356,15 +360,15 @@
 
 	new->__subtree_last = old->__subtree_last;
 	old->__subtree_last = compute_subtree_last(old);
-}
+  }
 
-static const struct rb_augment_callbacks augment_callbacks = {
+  static const struct rb_augment_callbacks augment_callbacks = {
 	augment_propagate, augment_copy, augment_rotate
-};
+  };
 
-void interval_tree_insert(struct interval_tree_node *node,
-			  struct rb_root *root)
-{
+  void interval_tree_insert(struct interval_tree_node *node,
+			    struct rb_root *root)
+  {
 	struct rb_node **link = &root->rb_node, *rb_parent = NULL;
 	unsigned long start = node->start, last = node->last;
 	struct interval_tree_node *parent;
@@ -383,10 +387,10 @@
 	node->__subtree_last = last;
 	rb_link_node(&node->rb, rb_parent, link);
 	rb_insert_augmented(&node->rb, root, &augment_callbacks);
-}
+  }
 
-void interval_tree_remove(struct interval_tree_node *node,
-			  struct rb_root *root)
-{
+  void interval_tree_remove(struct interval_tree_node *node,
+			    struct rb_root *root)
+  {
 	rb_erase_augmented(&node->rb, root, &augment_callbacks);
-}
+  }
diff --git a/Documentation/remoteproc.txt b/Documentation/remoteproc.txt
index f075974..77fb03a 100644
--- a/Documentation/remoteproc.txt
+++ b/Documentation/remoteproc.txt
@@ -1,6 +1,9 @@
+==========================
 Remote Processor Framework
+==========================
 
-1. Introduction
+Introduction
+============
 
 Modern SoCs typically have heterogeneous remote processor devices in asymmetric
 multiprocessing (AMP) configurations, which may be running different instances
@@ -26,44 +29,62 @@
 existing virtio drivers with remote processor backends at a minimal development
 cost.
 
-2. User API
+User API
+========
+
+::
 
   int rproc_boot(struct rproc *rproc)
-    - Boot a remote processor (i.e. load its firmware, power it on, ...).
-      If the remote processor is already powered on, this function immediately
-      returns (successfully).
-      Returns 0 on success, and an appropriate error value otherwise.
-      Note: to use this function you should already have a valid rproc
-      handle. There are several ways to achieve that cleanly (devres, pdata,
-      the way remoteproc_rpmsg.c does this, or, if this becomes prevalent, we
-      might also consider using dev_archdata for this).
+
+Boot a remote processor (i.e. load its firmware, power it on, ...).
+
+If the remote processor is already powered on, this function immediately
+returns (successfully).
+
+Returns 0 on success, and an appropriate error value otherwise.
+Note: to use this function you should already have a valid rproc
+handle. There are several ways to achieve that cleanly (devres, pdata,
+the way remoteproc_rpmsg.c does this, or, if this becomes prevalent, we
+might also consider using dev_archdata for this).
+
+::
 
   void rproc_shutdown(struct rproc *rproc)
-    - Power off a remote processor (previously booted with rproc_boot()).
-      In case @rproc is still being used by an additional user(s), then
-      this function will just decrement the power refcount and exit,
-      without really powering off the device.
-      Every call to rproc_boot() must (eventually) be accompanied by a call
-      to rproc_shutdown(). Calling rproc_shutdown() redundantly is a bug.
-      Notes:
-      - we're not decrementing the rproc's refcount, only the power refcount.
-        which means that the @rproc handle stays valid even after
-        rproc_shutdown() returns, and users can still use it with a subsequent
-        rproc_boot(), if needed.
+
+Power off a remote processor (previously booted with rproc_boot()).
+In case @rproc is still being used by an additional user(s), then
+this function will just decrement the power refcount and exit,
+without really powering off the device.
+
+Every call to rproc_boot() must (eventually) be accompanied by a call
+to rproc_shutdown(). Calling rproc_shutdown() redundantly is a bug.
+
+.. note::
+
+  we're not decrementing the rproc's refcount, only the power refcount.
+  which means that the @rproc handle stays valid even after
+  rproc_shutdown() returns, and users can still use it with a subsequent
+  rproc_boot(), if needed.
+
+::
 
   struct rproc *rproc_get_by_phandle(phandle phandle)
-    - Find an rproc handle using a device tree phandle. Returns the rproc
-      handle on success, and NULL on failure. This function increments
-      the remote processor's refcount, so always use rproc_put() to
-      decrement it back once rproc isn't needed anymore.
 
-3. Typical usage
+Find an rproc handle using a device tree phandle. Returns the rproc
+handle on success, and NULL on failure. This function increments
+the remote processor's refcount, so always use rproc_put() to
+decrement it back once rproc isn't needed anymore.
 
-#include <linux/remoteproc.h>
+Typical usage
+=============
 
-/* in case we were given a valid 'rproc' handle */
-int dummy_rproc_example(struct rproc *my_rproc)
-{
+::
+
+  #include <linux/remoteproc.h>
+
+  /* in case we were given a valid 'rproc' handle */
+  int dummy_rproc_example(struct rproc *my_rproc)
+  {
 	int ret;
 
 	/* let's power on and boot our remote processor */
@@ -80,84 +101,111 @@
 
 	/* let's shut it down now */
 	rproc_shutdown(my_rproc);
-}
+  }
 
-4. API for implementors
+API for implementors
+====================
+
+::
 
   struct rproc *rproc_alloc(struct device *dev, const char *name,
 				const struct rproc_ops *ops,
 				const char *firmware, int len)
-    - Allocate a new remote processor handle, but don't register
-      it yet. Required parameters are the underlying device, the
-      name of this remote processor, platform-specific ops handlers,
-      the name of the firmware to boot this rproc with, and the
-      length of private data needed by the allocating rproc driver (in bytes).
 
-      This function should be used by rproc implementations during
-      initialization of the remote processor.
-      After creating an rproc handle using this function, and when ready,
-      implementations should then call rproc_add() to complete
-      the registration of the remote processor.
-      On success, the new rproc is returned, and on failure, NULL.
+Allocate a new remote processor handle, but don't register
+it yet. Required parameters are the underlying device, the
+name of this remote processor, platform-specific ops handlers,
+the name of the firmware to boot this rproc with, and the
+length of private data needed by the allocating rproc driver (in bytes).
 
-      Note: _never_ directly deallocate @rproc, even if it was not registered
-      yet. Instead, when you need to unroll rproc_alloc(), use rproc_free().
+This function should be used by rproc implementations during
+initialization of the remote processor.
+
+After creating an rproc handle using this function, and when ready,
+implementations should then call rproc_add() to complete
+the registration of the remote processor.
+
+On success, the new rproc is returned, and on failure, NULL.
+
+.. note::
+
+  **never** directly deallocate @rproc, even if it was not registered
+  yet. Instead, when you need to unroll rproc_alloc(), use rproc_free().
+
+::
 
   void rproc_free(struct rproc *rproc)
-    - Free an rproc handle that was allocated by rproc_alloc.
-      This function essentially unrolls rproc_alloc(), by decrementing the
-      rproc's refcount. It doesn't directly free rproc; that would happen
-      only if there are no other references to rproc and its refcount now
-      dropped to zero.
+
+Free an rproc handle that was allocated by rproc_alloc.
+
+This function essentially unrolls rproc_alloc(), by decrementing the
+rproc's refcount. It doesn't directly free rproc; that would happen
+only if there are no other references to rproc and its refcount now
+dropped to zero.
+
+::
 
   int rproc_add(struct rproc *rproc)
-    - Register @rproc with the remoteproc framework, after it has been
-      allocated with rproc_alloc().
-      This is called by the platform-specific rproc implementation, whenever
-      a new remote processor device is probed.
-      Returns 0 on success and an appropriate error code otherwise.
-      Note: this function initiates an asynchronous firmware loading
-      context, which will look for virtio devices supported by the rproc's
-      firmware.
-      If found, those virtio devices will be created and added, so as a result
-      of registering this remote processor, additional virtio drivers might get
-      probed.
+
+Register @rproc with the remoteproc framework, after it has been
+allocated with rproc_alloc().
+
+This is called by the platform-specific rproc implementation, whenever
+a new remote processor device is probed.
+
+Returns 0 on success and an appropriate error code otherwise.
+Note: this function initiates an asynchronous firmware loading
+context, which will look for virtio devices supported by the rproc's
+firmware.
+
+If found, those virtio devices will be created and added, so as a result
+of registering this remote processor, additional virtio drivers might get
+probed.
+
+::
 
   int rproc_del(struct rproc *rproc)
-    - Unroll rproc_add().
-      This function should be called when the platform specific rproc
-      implementation decides to remove the rproc device. it should
-      _only_ be called if a previous invocation of rproc_add()
-      has completed successfully.
 
-      After rproc_del() returns, @rproc is still valid, and its
-      last refcount should be decremented by calling rproc_free().
+Unroll rproc_add().
 
-      Returns 0 on success and -EINVAL if @rproc isn't valid.
+This function should be called when the platform specific rproc
+implementation decides to remove the rproc device. it should
+_only_ be called if a previous invocation of rproc_add()
+has completed successfully.
+
+After rproc_del() returns, @rproc is still valid, and its
+last refcount should be decremented by calling rproc_free().
+
+Returns 0 on success and -EINVAL if @rproc isn't valid.
+
+::
 
   void rproc_report_crash(struct rproc *rproc, enum rproc_crash_type type)
-    - Report a crash in a remoteproc
-      This function must be called every time a crash is detected by the
-      platform specific rproc implementation. This should not be called from a
-      non-remoteproc driver. This function can be called from atomic/interrupt
-      context.
 
-5. Implementation callbacks
+Report a crash in a remoteproc
+
+This function must be called every time a crash is detected by the
+platform specific rproc implementation. This should not be called from a
+non-remoteproc driver. This function can be called from atomic/interrupt
+context.
+
+Implementation callbacks
+========================
 
 These callbacks should be provided by platform-specific remoteproc
-drivers:
+drivers::
 
-/**
- * struct rproc_ops - platform-specific device handlers
- * @start:	power on the device and boot it
- * @stop:	power off the device
- * @kick:	kick a virtqueue (virtqueue id given as a parameter)
- */
-struct rproc_ops {
+  /**
+   * struct rproc_ops - platform-specific device handlers
+   * @start:	power on the device and boot it
+   * @stop:	power off the device
+   * @kick:	kick a virtqueue (virtqueue id given as a parameter)
+   */
+  struct rproc_ops {
 	int (*start)(struct rproc *rproc);
 	int (*stop)(struct rproc *rproc);
 	void (*kick)(struct rproc *rproc, int vqid);
-};
+  };
 
 Every remoteproc implementation should at least provide the ->start and ->stop
 handlers. If rpmsg/virtio functionality is also desired, then the ->kick handler
@@ -179,7 +227,8 @@
 too expensive) to go through the existing virtqueues and look for new buffers
 in the used rings.
 
-6. Binary Firmware Structure
+Binary Firmware Structure
+=========================
 
 At this point remoteproc only supports ELF32 firmware binaries. However,
 it is quite expected that other platforms/devices which we'd want to
@@ -207,43 +256,43 @@
 or configurations by the remote processor, such as trace buffers and
 supported virtio devices (and their configurations).
 
-The resource table begins with this header:
+The resource table begins with this header::
 
-/**
- * struct resource_table - firmware resource table header
- * @ver: version number
- * @num: number of resource entries
- * @reserved: reserved (must be zero)
- * @offset: array of offsets pointing at the various resource entries
- *
- * The header of the resource table, as expressed by this structure,
- * contains a version number (should we need to change this format in the
- * future), the number of available resource entries, and their offsets
- * in the table.
- */
-struct resource_table {
+  /**
+   * struct resource_table - firmware resource table header
+   * @ver: version number
+   * @num: number of resource entries
+   * @reserved: reserved (must be zero)
+   * @offset: array of offsets pointing at the various resource entries
+   *
+   * The header of the resource table, as expressed by this structure,
+   * contains a version number (should we need to change this format in the
+   * future), the number of available resource entries, and their offsets
+   * in the table.
+   */
+  struct resource_table {
 	u32 ver;
 	u32 num;
 	u32 reserved[2];
 	u32 offset[0];
-} __packed;
+  } __packed;
 
 Immediately following this header are the resource entries themselves,
-each of which begins with the following resource entry header:
+each of which begins with the following resource entry header::
 
-/**
- * struct fw_rsc_hdr - firmware resource entry header
- * @type: resource type
- * @data: resource data
- *
- * Every resource entry begins with a 'struct fw_rsc_hdr' header providing
- * its @type. The content of the entry itself will immediately follow
- * this header, and it should be parsed according to the resource type.
- */
-struct fw_rsc_hdr {
+  /**
+   * struct fw_rsc_hdr - firmware resource entry header
+   * @type: resource type
+   * @data: resource data
+   *
+   * Every resource entry begins with a 'struct fw_rsc_hdr' header providing
+   * its @type. The content of the entry itself will immediately follow
+   * this header, and it should be parsed according to the resource type.
+   */
+  struct fw_rsc_hdr {
 	u32 type;
 	u8 data[0];
-} __packed;
+  } __packed;
 
 Some resources entries are mere announcements, where the host is informed
 of specific remoteproc configuration. Other entries require the host to
@@ -252,32 +301,32 @@
 the host should provide back its details (e.g. address of an allocated
 memory region).
 
-Here are the various resource types that are currently supported:
+Here are the various resource types that are currently supported::
 
-/**
- * enum fw_resource_type - types of resource entries
- *
- * @RSC_CARVEOUT:   request for allocation of a physically contiguous
- *		    memory region.
- * @RSC_DEVMEM:     request to iommu_map a memory-based peripheral.
- * @RSC_TRACE:	    announces the availability of a trace buffer into which
- *		    the remote processor will be writing logs.
- * @RSC_VDEV:       declare support for a virtio device, and serve as its
- *		    virtio header.
- * @RSC_LAST:       just keep this one at the end
- *
- * Please note that these values are used as indices to the rproc_handle_rsc
- * lookup table, so please keep them sane. Moreover, @RSC_LAST is used to
- * check the validity of an index before the lookup table is accessed, so
- * please update it as needed.
- */
-enum fw_resource_type {
+  /**
+   * enum fw_resource_type - types of resource entries
+   *
+   * @RSC_CARVEOUT:   request for allocation of a physically contiguous
+   *		    memory region.
+   * @RSC_DEVMEM:     request to iommu_map a memory-based peripheral.
+   * @RSC_TRACE:	    announces the availability of a trace buffer into which
+   *		    the remote processor will be writing logs.
+   * @RSC_VDEV:       declare support for a virtio device, and serve as its
+   *		    virtio header.
+   * @RSC_LAST:       just keep this one at the end
+   *
+   * Please note that these values are used as indices to the rproc_handle_rsc
+   * lookup table, so please keep them sane. Moreover, @RSC_LAST is used to
+   * check the validity of an index before the lookup table is accessed, so
+   * please update it as needed.
+   */
+  enum fw_resource_type {
 	RSC_CARVEOUT	= 0,
 	RSC_DEVMEM	= 1,
 	RSC_TRACE	= 2,
 	RSC_VDEV	= 3,
 	RSC_LAST	= 4,
-};
+  };
 
 For more details regarding a specific resource type, please see its
 dedicated structure in include/linux/remoteproc.h.
@@ -286,7 +335,8 @@
 at some point. When that happens, we could easily add a new RSC_PLATFORM
 type, and hand those resources to the platform-specific rproc driver to handle.
 
-7. Virtio and remoteproc
+Virtio and remoteproc
+=====================
 
 The firmware should provide remoteproc information about virtio devices
 that it supports, and their configurations: a RSC_VDEV resource entry
diff --git a/Documentation/rfkill.txt b/Documentation/rfkill.txt
index 8c17406..a289285 100644
--- a/Documentation/rfkill.txt
+++ b/Documentation/rfkill.txt
@@ -1,13 +1,13 @@
+===============================
 rfkill - RF kill switch support
 ===============================
 
-1. Introduction
-2. Implementation details
-3. Kernel API
-4. Userspace support
 
+.. contents::
+   :depth: 2
 
-1. Introduction
+Introduction
+============
 
 The rfkill subsystem provides a generic interface to disabling any radio
 transmitter in the system. When a transmitter is blocked, it shall not
@@ -21,17 +21,24 @@
 The rfkill subsystem has a concept of "hard" and "soft" block, which
 differ little in their meaning (block == transmitters off) but rather in
 whether they can be changed or not:
- - hard block: read-only radio block that cannot be overridden by software
- - soft block: writable radio block (need not be readable) that is set by
-               the system software.
+
+ - hard block
+	read-only radio block that cannot be overridden by software
+
+ - soft block
+	writable radio block (need not be readable) that is set by
+        the system software.
 
 The rfkill subsystem has two parameters, rfkill.default_state and
-rfkill.master_switch_mode, which are documented in admin-guide/kernel-parameters.rst.
+rfkill.master_switch_mode, which are documented in
+admin-guide/kernel-parameters.rst.
 
 
-2. Implementation details
+Implementation details
+======================
 
 The rfkill subsystem is composed of three main components:
+
  * the rfkill core,
  * the deprecated rfkill-input module (an input layer handler, being
    replaced by userspace policy code) and
@@ -55,7 +62,8 @@
 keeps track of soft and hard block separately.
 
 
-3. Kernel API
+Kernel API
+==========
 
 
 Drivers for radio transmitters normally implement an rfkill driver.
@@ -69,7 +77,7 @@
 suspend/hibernation, in which case it will be necessary to update the rfkill
 core with the current state is at resume time.
 
-To create an rfkill driver, driver's Kconfig needs to have
+To create an rfkill driver, driver's Kconfig needs to have::
 
 	depends on RFKILL || !RFKILL
 
@@ -87,7 +95,8 @@
 according to the switch state (LED_FULL when blocked, LED_OFF otherwise).
 
 
-5. Userspace support
+Userspace support
+=================
 
 The recommended userspace interface to use is /dev/rfkill, which is a misc
 character device that allows userspace to obtain and set the state of rfkill
@@ -112,11 +121,11 @@
 Additionally, each rfkill device is registered in sysfs and emits uevents.
 
 rfkill devices issue uevents (with an action of "change"), with the following
-environment variables set:
+environment variables set::
 
-RFKILL_NAME
-RFKILL_STATE
-RFKILL_TYPE
+	RFKILL_NAME
+	RFKILL_STATE
+	RFKILL_TYPE
 
 The contents of these variables corresponds to the "name", "state" and
 "type" sysfs files explained above.
diff --git a/Documentation/robust-futex-ABI.txt b/Documentation/robust-futex-ABI.txt
index 16eb314..8a5d34a 100644
--- a/Documentation/robust-futex-ABI.txt
+++ b/Documentation/robust-futex-ABI.txt
@@ -1,7 +1,9 @@
-Started by Paul Jackson <pj@sgi.com>
-
+====================
 The robust futex ABI
---------------------
+====================
+
+:Author: Started by Paul Jackson <pj@sgi.com>
+
 
 Robust_futexes provide a mechanism that is used in addition to normal
 futexes, for kernel assist of cleanup of held locks on task exit.
@@ -32,7 +34,7 @@
 waiting on the same locks.
 
 A thread that anticipates possibly using robust_futexes should first
-issue the system call:
+issue the system call::
 
     asmlinkage long
     sys_set_robust_list(struct robust_list_head __user *head, size_t len);
@@ -91,7 +93,7 @@
 When a thread has invoked the above system call to indicate it
 anticipates using robust_futexes, the kernel stores the passed in 'head'
 pointer for that task.  The task may retrieve that value later on by
-using the system call:
+using the system call::
 
     asmlinkage long
     sys_get_robust_list(int pid, struct robust_list_head __user **head_ptr,
@@ -135,6 +137,7 @@
 protocol on 'lock entry' insertion and removal:
 
 On insertion:
+
  1) set the 'list_op_pending' word to the address of the 'lock entry'
     to be inserted,
  2) acquire the futex lock,
@@ -143,6 +146,7 @@
  4) clear the 'list_op_pending' word.
 
 On removal:
+
  1) set the 'list_op_pending' word to the address of the 'lock entry'
     to be removed,
  2) remove the lock entry for this lock from the 'head' list,
diff --git a/Documentation/robust-futexes.txt b/Documentation/robust-futexes.txt
index 61c22d6..6c42c75 100644
--- a/Documentation/robust-futexes.txt
+++ b/Documentation/robust-futexes.txt
@@ -1,4 +1,8 @@
-Started by: Ingo Molnar <mingo@redhat.com>
+========================================
+A description of what robust futexes are
+========================================
+
+:Started by: Ingo Molnar <mingo@redhat.com>
 
 Background
 ----------
@@ -163,7 +167,7 @@
 ----------------------
 
 The patch adds two new syscalls: one to register the userspace list, and
-one to query the registered list pointer:
+one to query the registered list pointer::
 
  asmlinkage long
  sys_set_robust_list(struct robust_list_head __user *head,
@@ -185,7 +189,7 @@
 robust and normal futexes.
 
 If a futex is found to be held at exit time, the kernel sets the
-following bit of the futex word:
+following bit of the futex word::
 
 	#define FUTEX_OWNER_DIED        0x40000000
 
@@ -193,7 +197,7 @@
 the cleanup.
 
 Otherwise, robust futexes are acquired by glibc by putting the TID into
-the futex field atomically. Waiters set the FUTEX_WAITERS bit:
+the futex field atomically. Waiters set the FUTEX_WAITERS bit::
 
 	#define FUTEX_WAITERS           0x80000000
 
diff --git a/Documentation/rpmsg.txt b/Documentation/rpmsg.txt
index a95e36a..24b7a9e 100644
--- a/Documentation/rpmsg.txt
+++ b/Documentation/rpmsg.txt
@@ -1,10 +1,15 @@
+============================================
 Remote Processor Messaging (rpmsg) Framework
+============================================
 
-Note: this document describes the rpmsg bus and how to write rpmsg drivers.
-To learn how to add rpmsg support for new platforms, check out remoteproc.txt
-(also a resident of Documentation/).
+.. note::
 
-1. Introduction
+  This document describes the rpmsg bus and how to write rpmsg drivers.
+  To learn how to add rpmsg support for new platforms, check out remoteproc.txt
+  (also a resident of Documentation/).
+
+Introduction
+============
 
 Modern SoCs typically employ heterogeneous remote processor devices in
 asymmetric multiprocessing (AMP) configurations, which may be running
@@ -58,170 +63,222 @@
 with the payload of the inbound message).
 
 
-2. User API
+User API
+========
+
+::
 
   int rpmsg_send(struct rpmsg_channel *rpdev, void *data, int len);
-   - sends a message across to the remote processor on a given channel.
-     The caller should specify the channel, the data it wants to send,
-     and its length (in bytes). The message will be sent on the specified
-     channel, i.e. its source and destination address fields will be
-     set to the channel's src and dst addresses.
 
-     In case there are no TX buffers available, the function will block until
-     one becomes available (i.e. until the remote processor consumes
-     a tx buffer and puts it back on virtio's used descriptor ring),
-     or a timeout of 15 seconds elapses. When the latter happens,
-     -ERESTARTSYS is returned.
-     The function can only be called from a process context (for now).
-     Returns 0 on success and an appropriate error value on failure.
+sends a message across to the remote processor on a given channel.
+The caller should specify the channel, the data it wants to send,
+and its length (in bytes). The message will be sent on the specified
+channel, i.e. its source and destination address fields will be
+set to the channel's src and dst addresses.
+
+In case there are no TX buffers available, the function will block until
+one becomes available (i.e. until the remote processor consumes
+a tx buffer and puts it back on virtio's used descriptor ring),
+or a timeout of 15 seconds elapses. When the latter happens,
+-ERESTARTSYS is returned.
+
+The function can only be called from a process context (for now).
+Returns 0 on success and an appropriate error value on failure.
+
+::
 
   int rpmsg_sendto(struct rpmsg_channel *rpdev, void *data, int len, u32 dst);
-   - sends a message across to the remote processor on a given channel,
-     to a destination address provided by the caller.
-     The caller should specify the channel, the data it wants to send,
-     its length (in bytes), and an explicit destination address.
-     The message will then be sent to the remote processor to which the
-     channel belongs, using the channel's src address, and the user-provided
-     dst address (thus the channel's dst address will be ignored).
 
-     In case there are no TX buffers available, the function will block until
-     one becomes available (i.e. until the remote processor consumes
-     a tx buffer and puts it back on virtio's used descriptor ring),
-     or a timeout of 15 seconds elapses. When the latter happens,
-     -ERESTARTSYS is returned.
-     The function can only be called from a process context (for now).
-     Returns 0 on success and an appropriate error value on failure.
+sends a message across to the remote processor on a given channel,
+to a destination address provided by the caller.
+
+The caller should specify the channel, the data it wants to send,
+its length (in bytes), and an explicit destination address.
+
+The message will then be sent to the remote processor to which the
+channel belongs, using the channel's src address, and the user-provided
+dst address (thus the channel's dst address will be ignored).
+
+In case there are no TX buffers available, the function will block until
+one becomes available (i.e. until the remote processor consumes
+a tx buffer and puts it back on virtio's used descriptor ring),
+or a timeout of 15 seconds elapses. When the latter happens,
+-ERESTARTSYS is returned.
+
+The function can only be called from a process context (for now).
+Returns 0 on success and an appropriate error value on failure.
+
+::
 
   int rpmsg_send_offchannel(struct rpmsg_channel *rpdev, u32 src, u32 dst,
 							void *data, int len);
-   - sends a message across to the remote processor, using the src and dst
-     addresses provided by the user.
-     The caller should specify the channel, the data it wants to send,
-     its length (in bytes), and explicit source and destination addresses.
-     The message will then be sent to the remote processor to which the
-     channel belongs, but the channel's src and dst addresses will be
-     ignored (and the user-provided addresses will be used instead).
 
-     In case there are no TX buffers available, the function will block until
-     one becomes available (i.e. until the remote processor consumes
-     a tx buffer and puts it back on virtio's used descriptor ring),
-     or a timeout of 15 seconds elapses. When the latter happens,
-     -ERESTARTSYS is returned.
-     The function can only be called from a process context (for now).
-     Returns 0 on success and an appropriate error value on failure.
+
+sends a message across to the remote processor, using the src and dst
+addresses provided by the user.
+
+The caller should specify the channel, the data it wants to send,
+its length (in bytes), and explicit source and destination addresses.
+The message will then be sent to the remote processor to which the
+channel belongs, but the channel's src and dst addresses will be
+ignored (and the user-provided addresses will be used instead).
+
+In case there are no TX buffers available, the function will block until
+one becomes available (i.e. until the remote processor consumes
+a tx buffer and puts it back on virtio's used descriptor ring),
+or a timeout of 15 seconds elapses. When the latter happens,
+-ERESTARTSYS is returned.
+
+The function can only be called from a process context (for now).
+Returns 0 on success and an appropriate error value on failure.
+
+::
 
   int rpmsg_trysend(struct rpmsg_channel *rpdev, void *data, int len);
-   - sends a message across to the remote processor on a given channel.
-     The caller should specify the channel, the data it wants to send,
-     and its length (in bytes). The message will be sent on the specified
-     channel, i.e. its source and destination address fields will be
-     set to the channel's src and dst addresses.
 
-     In case there are no TX buffers available, the function will immediately
-     return -ENOMEM without waiting until one becomes available.
-     The function can only be called from a process context (for now).
-     Returns 0 on success and an appropriate error value on failure.
+sends a message across to the remote processor on a given channel.
+The caller should specify the channel, the data it wants to send,
+and its length (in bytes). The message will be sent on the specified
+channel, i.e. its source and destination address fields will be
+set to the channel's src and dst addresses.
+
+In case there are no TX buffers available, the function will immediately
+return -ENOMEM without waiting until one becomes available.
+
+The function can only be called from a process context (for now).
+Returns 0 on success and an appropriate error value on failure.
+
+::
 
   int rpmsg_trysendto(struct rpmsg_channel *rpdev, void *data, int len, u32 dst)
-   - sends a message across to the remote processor on a given channel,
-     to a destination address provided by the user.
-     The user should specify the channel, the data it wants to send,
-     its length (in bytes), and an explicit destination address.
-     The message will then be sent to the remote processor to which the
-     channel belongs, using the channel's src address, and the user-provided
-     dst address (thus the channel's dst address will be ignored).
 
-     In case there are no TX buffers available, the function will immediately
-     return -ENOMEM without waiting until one becomes available.
-     The function can only be called from a process context (for now).
-     Returns 0 on success and an appropriate error value on failure.
+
+sends a message across to the remote processor on a given channel,
+to a destination address provided by the user.
+
+The user should specify the channel, the data it wants to send,
+its length (in bytes), and an explicit destination address.
+
+The message will then be sent to the remote processor to which the
+channel belongs, using the channel's src address, and the user-provided
+dst address (thus the channel's dst address will be ignored).
+
+In case there are no TX buffers available, the function will immediately
+return -ENOMEM without waiting until one becomes available.
+
+The function can only be called from a process context (for now).
+Returns 0 on success and an appropriate error value on failure.
+
+::
 
   int rpmsg_trysend_offchannel(struct rpmsg_channel *rpdev, u32 src, u32 dst,
 							void *data, int len);
-   - sends a message across to the remote processor, using source and
-     destination addresses provided by the user.
-     The user should specify the channel, the data it wants to send,
-     its length (in bytes), and explicit source and destination addresses.
-     The message will then be sent to the remote processor to which the
-     channel belongs, but the channel's src and dst addresses will be
-     ignored (and the user-provided addresses will be used instead).
 
-     In case there are no TX buffers available, the function will immediately
-     return -ENOMEM without waiting until one becomes available.
-     The function can only be called from a process context (for now).
-     Returns 0 on success and an appropriate error value on failure.
+
+sends a message across to the remote processor, using source and
+destination addresses provided by the user.
+
+The user should specify the channel, the data it wants to send,
+its length (in bytes), and explicit source and destination addresses.
+The message will then be sent to the remote processor to which the
+channel belongs, but the channel's src and dst addresses will be
+ignored (and the user-provided addresses will be used instead).
+
+In case there are no TX buffers available, the function will immediately
+return -ENOMEM without waiting until one becomes available.
+
+The function can only be called from a process context (for now).
+Returns 0 on success and an appropriate error value on failure.
+
+::
 
   struct rpmsg_endpoint *rpmsg_create_ept(struct rpmsg_channel *rpdev,
 		void (*cb)(struct rpmsg_channel *, void *, int, void *, u32),
 		void *priv, u32 addr);
-   - every rpmsg address in the system is bound to an rx callback (so when
-     inbound messages arrive, they are dispatched by the rpmsg bus using the
-     appropriate callback handler) by means of an rpmsg_endpoint struct.
 
-     This function allows drivers to create such an endpoint, and by that,
-     bind a callback, and possibly some private data too, to an rpmsg address
-     (either one that is known in advance, or one that will be dynamically
-     assigned for them).
+every rpmsg address in the system is bound to an rx callback (so when
+inbound messages arrive, they are dispatched by the rpmsg bus using the
+appropriate callback handler) by means of an rpmsg_endpoint struct.
 
-     Simple rpmsg drivers need not call rpmsg_create_ept, because an endpoint
-     is already created for them when they are probed by the rpmsg bus
-     (using the rx callback they provide when they registered to the rpmsg bus).
+This function allows drivers to create such an endpoint, and by that,
+bind a callback, and possibly some private data too, to an rpmsg address
+(either one that is known in advance, or one that will be dynamically
+assigned for them).
 
-     So things should just work for simple drivers: they already have an
-     endpoint, their rx callback is bound to their rpmsg address, and when
-     relevant inbound messages arrive (i.e. messages which their dst address
-     equals to the src address of their rpmsg channel), the driver's handler
-     is invoked to process it.
+Simple rpmsg drivers need not call rpmsg_create_ept, because an endpoint
+is already created for them when they are probed by the rpmsg bus
+(using the rx callback they provide when they registered to the rpmsg bus).
 
-     That said, more complicated drivers might do need to allocate
-     additional rpmsg addresses, and bind them to different rx callbacks.
-     To accomplish that, those drivers need to call this function.
-     Drivers should provide their channel (so the new endpoint would bind
-     to the same remote processor their channel belongs to), an rx callback
-     function, an optional private data (which is provided back when the
-     rx callback is invoked), and an address they want to bind with the
-     callback. If addr is RPMSG_ADDR_ANY, then rpmsg_create_ept will
-     dynamically assign them an available rpmsg address (drivers should have
-     a very good reason why not to always use RPMSG_ADDR_ANY here).
+So things should just work for simple drivers: they already have an
+endpoint, their rx callback is bound to their rpmsg address, and when
+relevant inbound messages arrive (i.e. messages which their dst address
+equals to the src address of their rpmsg channel), the driver's handler
+is invoked to process it.
 
-     Returns a pointer to the endpoint on success, or NULL on error.
+That said, more complicated drivers might do need to allocate
+additional rpmsg addresses, and bind them to different rx callbacks.
+To accomplish that, those drivers need to call this function.
+Drivers should provide their channel (so the new endpoint would bind
+to the same remote processor their channel belongs to), an rx callback
+function, an optional private data (which is provided back when the
+rx callback is invoked), and an address they want to bind with the
+callback. If addr is RPMSG_ADDR_ANY, then rpmsg_create_ept will
+dynamically assign them an available rpmsg address (drivers should have
+a very good reason why not to always use RPMSG_ADDR_ANY here).
+
+Returns a pointer to the endpoint on success, or NULL on error.
+
+::
 
   void rpmsg_destroy_ept(struct rpmsg_endpoint *ept);
-   - destroys an existing rpmsg endpoint. user should provide a pointer
-     to an rpmsg endpoint that was previously created with rpmsg_create_ept().
+
+
+destroys an existing rpmsg endpoint. user should provide a pointer
+to an rpmsg endpoint that was previously created with rpmsg_create_ept().
+
+::
 
   int register_rpmsg_driver(struct rpmsg_driver *rpdrv);
-   - registers an rpmsg driver with the rpmsg bus. user should provide
-     a pointer to an rpmsg_driver struct, which contains the driver's
-     ->probe() and ->remove() functions, an rx callback, and an id_table
-     specifying the names of the channels this driver is interested to
-     be probed with.
+
+
+registers an rpmsg driver with the rpmsg bus. user should provide
+a pointer to an rpmsg_driver struct, which contains the driver's
+->probe() and ->remove() functions, an rx callback, and an id_table
+specifying the names of the channels this driver is interested to
+be probed with.
+
+::
 
   void unregister_rpmsg_driver(struct rpmsg_driver *rpdrv);
-   - unregisters an rpmsg driver from the rpmsg bus. user should provide
-     a pointer to a previously-registered rpmsg_driver struct.
-     Returns 0 on success, and an appropriate error value on failure.
 
 
-3. Typical usage
+unregisters an rpmsg driver from the rpmsg bus. user should provide
+a pointer to a previously-registered rpmsg_driver struct.
+Returns 0 on success, and an appropriate error value on failure.
+
+
+Typical usage
+=============
 
 The following is a simple rpmsg driver, that sends an "hello!" message
 on probe(), and whenever it receives an incoming message, it dumps its
 content to the console.
 
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/rpmsg.h>
+::
 
-static void rpmsg_sample_cb(struct rpmsg_channel *rpdev, void *data, int len,
+  #include <linux/kernel.h>
+  #include <linux/module.h>
+  #include <linux/rpmsg.h>
+
+  static void rpmsg_sample_cb(struct rpmsg_channel *rpdev, void *data, int len,
 						void *priv, u32 src)
-{
+  {
 	print_hex_dump(KERN_INFO, "incoming message:", DUMP_PREFIX_NONE,
 						16, 1, data, len, true);
-}
+  }
 
-static int rpmsg_sample_probe(struct rpmsg_channel *rpdev)
-{
+  static int rpmsg_sample_probe(struct rpmsg_channel *rpdev)
+  {
 	int err;
 
 	dev_info(&rpdev->dev, "chnl: 0x%x -> 0x%x\n", rpdev->src, rpdev->dst);
@@ -234,32 +291,35 @@
 	}
 
 	return 0;
-}
+  }
 
-static void rpmsg_sample_remove(struct rpmsg_channel *rpdev)
-{
+  static void rpmsg_sample_remove(struct rpmsg_channel *rpdev)
+  {
 	dev_info(&rpdev->dev, "rpmsg sample client driver is removed\n");
-}
+  }
 
-static struct rpmsg_device_id rpmsg_driver_sample_id_table[] = {
+  static struct rpmsg_device_id rpmsg_driver_sample_id_table[] = {
 	{ .name	= "rpmsg-client-sample" },
 	{ },
-};
-MODULE_DEVICE_TABLE(rpmsg, rpmsg_driver_sample_id_table);
+  };
+  MODULE_DEVICE_TABLE(rpmsg, rpmsg_driver_sample_id_table);
 
-static struct rpmsg_driver rpmsg_sample_client = {
+  static struct rpmsg_driver rpmsg_sample_client = {
 	.drv.name	= KBUILD_MODNAME,
 	.id_table	= rpmsg_driver_sample_id_table,
 	.probe		= rpmsg_sample_probe,
 	.callback	= rpmsg_sample_cb,
 	.remove		= rpmsg_sample_remove,
-};
-module_rpmsg_driver(rpmsg_sample_client);
+  };
+  module_rpmsg_driver(rpmsg_sample_client);
 
-Note: a similar sample which can be built and loaded can be found
-in samples/rpmsg/.
+.. note::
 
-4. Allocations of rpmsg channels:
+   a similar sample which can be built and loaded can be found
+   in samples/rpmsg/.
+
+Allocations of rpmsg channels
+=============================
 
 At this point we only support dynamic allocations of rpmsg channels.
 
diff --git a/Documentation/sgi-ioc4.txt b/Documentation/sgi-ioc4.txt
index 876c96a..7270922 100644
--- a/Documentation/sgi-ioc4.txt
+++ b/Documentation/sgi-ioc4.txt
@@ -1,3 +1,7 @@
+====================================
+SGI IOC4 PCI (multi function) device
+====================================
+
 The SGI IOC4 PCI device is a bit of a strange beast, so some notes on
 it are in order.
 
diff --git a/Documentation/siphash.txt b/Documentation/siphash.txt
index 908d348..9965821 100644
--- a/Documentation/siphash.txt
+++ b/Documentation/siphash.txt
@@ -1,6 +1,8 @@
-         SipHash - a short input PRF
------------------------------------------------
-Written by Jason A. Donenfeld <jason@zx2c4.com>
+===========================
+SipHash - a short input PRF
+===========================
+
+:Author: Written by Jason A. Donenfeld <jason@zx2c4.com>
 
 SipHash is a cryptographically secure PRF -- a keyed hash function -- that
 performs very well for short inputs, hence the name. It was designed by
@@ -13,58 +15,61 @@
 indistinguishable from random. You may then use that integer as part of secure
 sequence numbers, secure cookies, or mask it off for use in a hash table.
 
-1. Generating a key
+Generating a key
+================
 
 Keys should always be generated from a cryptographically secure source of
-random numbers, either using get_random_bytes or get_random_once:
+random numbers, either using get_random_bytes or get_random_once::
 
-siphash_key_t key;
-get_random_bytes(&key, sizeof(key));
+	siphash_key_t key;
+	get_random_bytes(&key, sizeof(key));
 
 If you're not deriving your key from here, you're doing it wrong.
 
-2. Using the functions
+Using the functions
+===================
 
 There are two variants of the function, one that takes a list of integers, and
-one that takes a buffer:
+one that takes a buffer::
 
-u64 siphash(const void *data, size_t len, const siphash_key_t *key);
+	u64 siphash(const void *data, size_t len, const siphash_key_t *key);
 
-And:
+And::
 
-u64 siphash_1u64(u64, const siphash_key_t *key);
-u64 siphash_2u64(u64, u64, const siphash_key_t *key);
-u64 siphash_3u64(u64, u64, u64, const siphash_key_t *key);
-u64 siphash_4u64(u64, u64, u64, u64, const siphash_key_t *key);
-u64 siphash_1u32(u32, const siphash_key_t *key);
-u64 siphash_2u32(u32, u32, const siphash_key_t *key);
-u64 siphash_3u32(u32, u32, u32, const siphash_key_t *key);
-u64 siphash_4u32(u32, u32, u32, u32, const siphash_key_t *key);
+	u64 siphash_1u64(u64, const siphash_key_t *key);
+	u64 siphash_2u64(u64, u64, const siphash_key_t *key);
+	u64 siphash_3u64(u64, u64, u64, const siphash_key_t *key);
+	u64 siphash_4u64(u64, u64, u64, u64, const siphash_key_t *key);
+	u64 siphash_1u32(u32, const siphash_key_t *key);
+	u64 siphash_2u32(u32, u32, const siphash_key_t *key);
+	u64 siphash_3u32(u32, u32, u32, const siphash_key_t *key);
+	u64 siphash_4u32(u32, u32, u32, u32, const siphash_key_t *key);
 
 If you pass the generic siphash function something of a constant length, it
 will constant fold at compile-time and automatically choose one of the
 optimized functions.
 
-3. Hashtable key function usage:
+Hashtable key function usage::
 
-struct some_hashtable {
-	DECLARE_HASHTABLE(hashtable, 8);
-	siphash_key_t key;
-};
+	struct some_hashtable {
+		DECLARE_HASHTABLE(hashtable, 8);
+		siphash_key_t key;
+	};
 
-void init_hashtable(struct some_hashtable *table)
-{
-	get_random_bytes(&table->key, sizeof(table->key));
-}
+	void init_hashtable(struct some_hashtable *table)
+	{
+		get_random_bytes(&table->key, sizeof(table->key));
+	}
 
-static inline hlist_head *some_hashtable_bucket(struct some_hashtable *table, struct interesting_input *input)
-{
-	return &table->hashtable[siphash(input, sizeof(*input), &table->key) & (HASH_SIZE(table->hashtable) - 1)];
-}
+	static inline hlist_head *some_hashtable_bucket(struct some_hashtable *table, struct interesting_input *input)
+	{
+		return &table->hashtable[siphash(input, sizeof(*input), &table->key) & (HASH_SIZE(table->hashtable) - 1)];
+	}
 
 You may then iterate like usual over the returned hash bucket.
 
-4. Security
+Security
+========
 
 SipHash has a very high security margin, with its 128-bit key. So long as the
 key is kept secret, it is impossible for an attacker to guess the outputs of
@@ -73,7 +78,8 @@
 
 Linux implements the "2-4" variant of SipHash.
 
-5. Struct-passing Pitfalls
+Struct-passing Pitfalls
+=======================
 
 Often times the XuY functions will not be large enough, and instead you'll
 want to pass a pre-filled struct to siphash. When doing this, it's important
@@ -81,30 +87,32 @@
 is to simply arrange the members of the struct in descending order of size,
 and to use offsetendof() instead of sizeof() for getting the size. For
 performance reasons, if possible, it's probably a good thing to align the
-struct to the right boundary. Here's an example:
+struct to the right boundary. Here's an example::
 
-const struct {
-	struct in6_addr saddr;
-	u32 counter;
-	u16 dport;
-} __aligned(SIPHASH_ALIGNMENT) combined = {
-	.saddr = *(struct in6_addr *)saddr,
-	.counter = counter,
-	.dport = dport
-};
-u64 h = siphash(&combined, offsetofend(typeof(combined), dport), &secret);
+	const struct {
+		struct in6_addr saddr;
+		u32 counter;
+		u16 dport;
+	} __aligned(SIPHASH_ALIGNMENT) combined = {
+		.saddr = *(struct in6_addr *)saddr,
+		.counter = counter,
+		.dport = dport
+	};
+	u64 h = siphash(&combined, offsetofend(typeof(combined), dport), &secret);
 
-6. Resources
+Resources
+=========
 
 Read the SipHash paper if you're interested in learning more:
 https://131002.net/siphash/siphash.pdf
 
+-------------------------------------------------------------------------------
 
-~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~=~
-
+===============================================
 HalfSipHash - SipHash's insecure younger cousin
------------------------------------------------
-Written by Jason A. Donenfeld <jason@zx2c4.com>
+===============================================
+
+:Author: Written by Jason A. Donenfeld <jason@zx2c4.com>
 
 On the off-chance that SipHash is not fast enough for your needs, you might be
 able to justify using HalfSipHash, a terrifying but potentially useful
@@ -120,7 +128,8 @@
 transmitted out of the kernel. This is only remotely useful over `jhash` as a
 means of mitigating hashtable flooding denial of service attacks.
 
-1. Generating a key
+Generating a key
+================
 
 Keys should always be generated from a cryptographically secure source of
 random numbers, either using get_random_bytes or get_random_once:
@@ -130,44 +139,49 @@
 
 If you're not deriving your key from here, you're doing it wrong.
 
-2. Using the functions
+Using the functions
+===================
 
 There are two variants of the function, one that takes a list of integers, and
-one that takes a buffer:
+one that takes a buffer::
 
-u32 hsiphash(const void *data, size_t len, const hsiphash_key_t *key);
+	u32 hsiphash(const void *data, size_t len, const hsiphash_key_t *key);
 
-And:
+And::
 
-u32 hsiphash_1u32(u32, const hsiphash_key_t *key);
-u32 hsiphash_2u32(u32, u32, const hsiphash_key_t *key);
-u32 hsiphash_3u32(u32, u32, u32, const hsiphash_key_t *key);
-u32 hsiphash_4u32(u32, u32, u32, u32, const hsiphash_key_t *key);
+	u32 hsiphash_1u32(u32, const hsiphash_key_t *key);
+	u32 hsiphash_2u32(u32, u32, const hsiphash_key_t *key);
+	u32 hsiphash_3u32(u32, u32, u32, const hsiphash_key_t *key);
+	u32 hsiphash_4u32(u32, u32, u32, u32, const hsiphash_key_t *key);
 
 If you pass the generic hsiphash function something of a constant length, it
 will constant fold at compile-time and automatically choose one of the
 optimized functions.
 
-3. Hashtable key function usage:
+Hashtable key function usage
+============================
 
-struct some_hashtable {
-	DECLARE_HASHTABLE(hashtable, 8);
-	hsiphash_key_t key;
-};
+::
 
-void init_hashtable(struct some_hashtable *table)
-{
-	get_random_bytes(&table->key, sizeof(table->key));
-}
+	struct some_hashtable {
+		DECLARE_HASHTABLE(hashtable, 8);
+		hsiphash_key_t key;
+	};
 
-static inline hlist_head *some_hashtable_bucket(struct some_hashtable *table, struct interesting_input *input)
-{
-	return &table->hashtable[hsiphash(input, sizeof(*input), &table->key) & (HASH_SIZE(table->hashtable) - 1)];
-}
+	void init_hashtable(struct some_hashtable *table)
+	{
+		get_random_bytes(&table->key, sizeof(table->key));
+	}
+
+	static inline hlist_head *some_hashtable_bucket(struct some_hashtable *table, struct interesting_input *input)
+	{
+		return &table->hashtable[hsiphash(input, sizeof(*input), &table->key) & (HASH_SIZE(table->hashtable) - 1)];
+	}
 
 You may then iterate like usual over the returned hash bucket.
 
-4. Performance
+Performance
+===========
 
 HalfSipHash is roughly 3 times slower than JenkinsHash. For many replacements,
 this will not be a problem, as the hashtable lookup isn't the bottleneck. And
diff --git a/Documentation/smsc_ece1099.txt b/Documentation/smsc_ece1099.txt
index 6b492e8..0792774 100644
--- a/Documentation/smsc_ece1099.txt
+++ b/Documentation/smsc_ece1099.txt
@@ -1,3 +1,7 @@
+=================================================
+Msc Keyboard Scan Expansion/GPIO Expansion device
+=================================================
+
 What is smsc-ece1099?
 ----------------------
 
diff --git a/Documentation/static-keys.txt b/Documentation/static-keys.txt
index ef419fd..b83dfa1 100644
--- a/Documentation/static-keys.txt
+++ b/Documentation/static-keys.txt
@@ -1,30 +1,34 @@
-			Static Keys
-			-----------
+===========
+Static Keys
+===========
 
-DEPRECATED API:
+.. warning::
 
-The use of 'struct static_key' directly, is now DEPRECATED. In addition
-static_key_{true,false}() is also DEPRECATED. IE DO NOT use the following:
+   DEPRECATED API:
 
-struct static_key false = STATIC_KEY_INIT_FALSE;
-struct static_key true = STATIC_KEY_INIT_TRUE;
-static_key_true()
-static_key_false()
+   The use of 'struct static_key' directly, is now DEPRECATED. In addition
+   static_key_{true,false}() is also DEPRECATED. IE DO NOT use the following::
 
-The updated API replacements are:
+	struct static_key false = STATIC_KEY_INIT_FALSE;
+	struct static_key true = STATIC_KEY_INIT_TRUE;
+	static_key_true()
+	static_key_false()
 
-DEFINE_STATIC_KEY_TRUE(key);
-DEFINE_STATIC_KEY_FALSE(key);
-DEFINE_STATIC_KEY_ARRAY_TRUE(keys, count);
-DEFINE_STATIC_KEY_ARRAY_FALSE(keys, count);
-static_branch_likely()
-static_branch_unlikely()
+   The updated API replacements are::
 
-0) Abstract
+	DEFINE_STATIC_KEY_TRUE(key);
+	DEFINE_STATIC_KEY_FALSE(key);
+	DEFINE_STATIC_KEY_ARRAY_TRUE(keys, count);
+	DEFINE_STATIC_KEY_ARRAY_FALSE(keys, count);
+	static_branch_likely()
+	static_branch_unlikely()
+
+Abstract
+========
 
 Static keys allows the inclusion of seldom used features in
 performance-sensitive fast-path kernel code, via a GCC feature and a code
-patching technique. A quick example:
+patching technique. A quick example::
 
 	DEFINE_STATIC_KEY_FALSE(key);
 
@@ -45,7 +49,8 @@
 impact to the likely code path as possible.
 
 
-1) Motivation
+Motivation
+==========
 
 
 Currently, tracepoints are implemented using a conditional branch. The
@@ -60,7 +65,8 @@
 kernel code paths should be able to make use of the static keys facility.
 
 
-2) Solution
+Solution
+========
 
 
 gcc (v4.5) adds a new 'asm goto' statement that allows branching to a label:
@@ -71,7 +77,7 @@
 by default, without the need to check memory. Then, at run-time, we can patch
 the branch site to change the branch direction.
 
-For example, if we have a simple branch that is disabled by default:
+For example, if we have a simple branch that is disabled by default::
 
 	if (static_branch_unlikely(&key))
 		printk("I am the true branch\n");
@@ -87,14 +93,15 @@
 This lowlevel patching mechanism is called 'jump label patching', and it gives
 the basis for the static keys facility.
 
-3) Static key label API, usage and examples:
+Static key label API, usage and examples
+========================================
 
 
-In order to make use of this optimization you must first define a key:
+In order to make use of this optimization you must first define a key::
 
 	DEFINE_STATIC_KEY_TRUE(key);
 
-or:
+or::
 
 	DEFINE_STATIC_KEY_FALSE(key);
 
@@ -102,14 +109,14 @@
 The key must be global, that is, it can't be allocated on the stack or dynamically
 allocated at run-time.
 
-The key is then used in code as:
+The key is then used in code as::
 
         if (static_branch_unlikely(&key))
                 do unlikely code
         else
                 do likely code
 
-Or:
+Or::
 
         if (static_branch_likely(&key))
                 do likely code
@@ -120,15 +127,15 @@
 be used in either static_branch_likely() or static_branch_unlikely()
 statements.
 
-Branch(es) can be set true via:
+Branch(es) can be set true via::
 
-static_branch_enable(&key);
+	static_branch_enable(&key);
 
-or false via:
+or false via::
 
-static_branch_disable(&key);
+	static_branch_disable(&key);
 
-The branch(es) can then be switched via reference counts:
+The branch(es) can then be switched via reference counts::
 
 	static_branch_inc(&key);
 	...
@@ -142,11 +149,11 @@
 key is initialized false, a 'static_branch_inc()', will change the branch to
 true. And then a 'static_branch_dec()', will again make the branch false.
 
-Where an array of keys is required, it can be defined as:
+Where an array of keys is required, it can be defined as::
 
 	DEFINE_STATIC_KEY_ARRAY_TRUE(keys, count);
 
-or:
+or::
 
 	DEFINE_STATIC_KEY_ARRAY_FALSE(keys, count);
 
@@ -159,96 +166,98 @@
 struct jump_entry table must be at least 4-byte aligned because the
 static_key->entry field makes use of the two least significant bits.
 
-* select HAVE_ARCH_JUMP_LABEL, see: arch/x86/Kconfig
+* ``select HAVE_ARCH_JUMP_LABEL``,
+    see: arch/x86/Kconfig
 
-* #define JUMP_LABEL_NOP_SIZE, see: arch/x86/include/asm/jump_label.h
+* ``#define JUMP_LABEL_NOP_SIZE``,
+    see: arch/x86/include/asm/jump_label.h
 
-* __always_inline bool arch_static_branch(struct static_key *key, bool branch), see:
-					arch/x86/include/asm/jump_label.h
+* ``__always_inline bool arch_static_branch(struct static_key *key, bool branch)``,
+    see: arch/x86/include/asm/jump_label.h
 
-* __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch),
-					see: arch/x86/include/asm/jump_label.h
+* ``__always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)``,
+    see: arch/x86/include/asm/jump_label.h
 
-* void arch_jump_label_transform(struct jump_entry *entry, enum jump_label_type type),
-					see: arch/x86/kernel/jump_label.c
+* ``void arch_jump_label_transform(struct jump_entry *entry, enum jump_label_type type)``,
+    see: arch/x86/kernel/jump_label.c
 
-* __init_or_module void arch_jump_label_transform_static(struct jump_entry *entry, enum jump_label_type type),
-					see: arch/x86/kernel/jump_label.c
+* ``__init_or_module void arch_jump_label_transform_static(struct jump_entry *entry, enum jump_label_type type)``,
+    see: arch/x86/kernel/jump_label.c
 
-
-* struct jump_entry, see: arch/x86/include/asm/jump_label.h
+* ``struct jump_entry``,
+    see: arch/x86/include/asm/jump_label.h
 
 
 5) Static keys / jump label analysis, results (x86_64):
 
 
 As an example, let's add the following branch to 'getppid()', such that the
-system call now looks like:
+system call now looks like::
 
-SYSCALL_DEFINE0(getppid)
-{
+  SYSCALL_DEFINE0(getppid)
+  {
         int pid;
 
-+       if (static_branch_unlikely(&key))
-+               printk("I am the true branch\n");
+  +     if (static_branch_unlikely(&key))
+  +             printk("I am the true branch\n");
 
         rcu_read_lock();
         pid = task_tgid_vnr(rcu_dereference(current->real_parent));
         rcu_read_unlock();
 
         return pid;
-}
+  }
 
-The resulting instructions with jump labels generated by GCC is:
+The resulting instructions with jump labels generated by GCC is::
 
-ffffffff81044290 <sys_getppid>:
-ffffffff81044290:       55                      push   %rbp
-ffffffff81044291:       48 89 e5                mov    %rsp,%rbp
-ffffffff81044294:       e9 00 00 00 00          jmpq   ffffffff81044299 <sys_getppid+0x9>
-ffffffff81044299:       65 48 8b 04 25 c0 b6    mov    %gs:0xb6c0,%rax
-ffffffff810442a0:       00 00
-ffffffff810442a2:       48 8b 80 80 02 00 00    mov    0x280(%rax),%rax
-ffffffff810442a9:       48 8b 80 b0 02 00 00    mov    0x2b0(%rax),%rax
-ffffffff810442b0:       48 8b b8 e8 02 00 00    mov    0x2e8(%rax),%rdi
-ffffffff810442b7:       e8 f4 d9 00 00          callq  ffffffff81051cb0 <pid_vnr>
-ffffffff810442bc:       5d                      pop    %rbp
-ffffffff810442bd:       48 98                   cltq
-ffffffff810442bf:       c3                      retq
-ffffffff810442c0:       48 c7 c7 e3 54 98 81    mov    $0xffffffff819854e3,%rdi
-ffffffff810442c7:       31 c0                   xor    %eax,%eax
-ffffffff810442c9:       e8 71 13 6d 00          callq  ffffffff8171563f <printk>
-ffffffff810442ce:       eb c9                   jmp    ffffffff81044299 <sys_getppid+0x9>
+  ffffffff81044290 <sys_getppid>:
+  ffffffff81044290:       55                      push   %rbp
+  ffffffff81044291:       48 89 e5                mov    %rsp,%rbp
+  ffffffff81044294:       e9 00 00 00 00          jmpq   ffffffff81044299 <sys_getppid+0x9>
+  ffffffff81044299:       65 48 8b 04 25 c0 b6    mov    %gs:0xb6c0,%rax
+  ffffffff810442a0:       00 00
+  ffffffff810442a2:       48 8b 80 80 02 00 00    mov    0x280(%rax),%rax
+  ffffffff810442a9:       48 8b 80 b0 02 00 00    mov    0x2b0(%rax),%rax
+  ffffffff810442b0:       48 8b b8 e8 02 00 00    mov    0x2e8(%rax),%rdi
+  ffffffff810442b7:       e8 f4 d9 00 00          callq  ffffffff81051cb0 <pid_vnr>
+  ffffffff810442bc:       5d                      pop    %rbp
+  ffffffff810442bd:       48 98                   cltq
+  ffffffff810442bf:       c3                      retq
+  ffffffff810442c0:       48 c7 c7 e3 54 98 81    mov    $0xffffffff819854e3,%rdi
+  ffffffff810442c7:       31 c0                   xor    %eax,%eax
+  ffffffff810442c9:       e8 71 13 6d 00          callq  ffffffff8171563f <printk>
+  ffffffff810442ce:       eb c9                   jmp    ffffffff81044299 <sys_getppid+0x9>
 
-Without the jump label optimization it looks like:
+Without the jump label optimization it looks like::
 
-ffffffff810441f0 <sys_getppid>:
-ffffffff810441f0:       8b 05 8a 52 d8 00       mov    0xd8528a(%rip),%eax        # ffffffff81dc9480 <key>
-ffffffff810441f6:       55                      push   %rbp
-ffffffff810441f7:       48 89 e5                mov    %rsp,%rbp
-ffffffff810441fa:       85 c0                   test   %eax,%eax
-ffffffff810441fc:       75 27                   jne    ffffffff81044225 <sys_getppid+0x35>
-ffffffff810441fe:       65 48 8b 04 25 c0 b6    mov    %gs:0xb6c0,%rax
-ffffffff81044205:       00 00
-ffffffff81044207:       48 8b 80 80 02 00 00    mov    0x280(%rax),%rax
-ffffffff8104420e:       48 8b 80 b0 02 00 00    mov    0x2b0(%rax),%rax
-ffffffff81044215:       48 8b b8 e8 02 00 00    mov    0x2e8(%rax),%rdi
-ffffffff8104421c:       e8 2f da 00 00          callq  ffffffff81051c50 <pid_vnr>
-ffffffff81044221:       5d                      pop    %rbp
-ffffffff81044222:       48 98                   cltq
-ffffffff81044224:       c3                      retq
-ffffffff81044225:       48 c7 c7 13 53 98 81    mov    $0xffffffff81985313,%rdi
-ffffffff8104422c:       31 c0                   xor    %eax,%eax
-ffffffff8104422e:       e8 60 0f 6d 00          callq  ffffffff81715193 <printk>
-ffffffff81044233:       eb c9                   jmp    ffffffff810441fe <sys_getppid+0xe>
-ffffffff81044235:       66 66 2e 0f 1f 84 00    data32 nopw %cs:0x0(%rax,%rax,1)
-ffffffff8104423c:       00 00 00 00
+  ffffffff810441f0 <sys_getppid>:
+  ffffffff810441f0:       8b 05 8a 52 d8 00       mov    0xd8528a(%rip),%eax        # ffffffff81dc9480 <key>
+  ffffffff810441f6:       55                      push   %rbp
+  ffffffff810441f7:       48 89 e5                mov    %rsp,%rbp
+  ffffffff810441fa:       85 c0                   test   %eax,%eax
+  ffffffff810441fc:       75 27                   jne    ffffffff81044225 <sys_getppid+0x35>
+  ffffffff810441fe:       65 48 8b 04 25 c0 b6    mov    %gs:0xb6c0,%rax
+  ffffffff81044205:       00 00
+  ffffffff81044207:       48 8b 80 80 02 00 00    mov    0x280(%rax),%rax
+  ffffffff8104420e:       48 8b 80 b0 02 00 00    mov    0x2b0(%rax),%rax
+  ffffffff81044215:       48 8b b8 e8 02 00 00    mov    0x2e8(%rax),%rdi
+  ffffffff8104421c:       e8 2f da 00 00          callq  ffffffff81051c50 <pid_vnr>
+  ffffffff81044221:       5d                      pop    %rbp
+  ffffffff81044222:       48 98                   cltq
+  ffffffff81044224:       c3                      retq
+  ffffffff81044225:       48 c7 c7 13 53 98 81    mov    $0xffffffff81985313,%rdi
+  ffffffff8104422c:       31 c0                   xor    %eax,%eax
+  ffffffff8104422e:       e8 60 0f 6d 00          callq  ffffffff81715193 <printk>
+  ffffffff81044233:       eb c9                   jmp    ffffffff810441fe <sys_getppid+0xe>
+  ffffffff81044235:       66 66 2e 0f 1f 84 00    data32 nopw %cs:0x0(%rax,%rax,1)
+  ffffffff8104423c:       00 00 00 00
 
 Thus, the disable jump label case adds a 'mov', 'test' and 'jne' instruction
 vs. the jump label case just has a 'no-op' or 'jmp 0'. (The jmp 0, is patched
 to a 5 byte atomic no-op instruction at boot-time.) Thus, the disabled jump
-label case adds:
+label case adds::
 
-6 (mov) + 2 (test) + 2 (jne) = 10 - 5 (5 byte jump 0) = 5 addition bytes.
+  6 (mov) + 2 (test) + 2 (jne) = 10 - 5 (5 byte jump 0) = 5 addition bytes.
 
 If we then include the padding bytes, the jump label code saves, 16 total bytes
 of instruction memory for this small function. In this case the non-jump label
@@ -262,7 +271,7 @@
 'pipe-test' (also known as 'perf bench sched pipe') can be used to show the
 performance improvement. Testing done on 3.3.0-rc2:
 
-jump label disabled:
+jump label disabled::
 
  Performance counter stats for 'bash -c /tmp/pipe-test' (50 runs):
 
@@ -279,7 +288,7 @@
 
        1.601607384 seconds time elapsed                                          ( +-  0.07% )
 
-jump label enabled:
+jump label enabled::
 
  Performance counter stats for 'bash -c /tmp/pipe-test' (50 runs):
 
diff --git a/Documentation/svga.txt b/Documentation/svga.txt
index cd66ec8..119f151 100644
--- a/Documentation/svga.txt
+++ b/Documentation/svga.txt
@@ -1,24 +1,31 @@
-		       Video Mode Selection Support 2.13
-		    (c) 1995--1999 Martin Mares, <mj@ucw.cz>
---------------------------------------------------------------------------------
+.. include:: <isonum.txt>
 
-1. Intro
-~~~~~~~~
-   This small document describes the "Video Mode Selection" feature which
+=================================
+Video Mode Selection Support 2.13
+=================================
+
+:Copyright: |copy| 1995--1999 Martin Mares, <mj@ucw.cz>
+
+Intro
+~~~~~
+
+This small document describes the "Video Mode Selection" feature which
 allows the use of various special video modes supported by the video BIOS. Due
 to usage of the BIOS, the selection is limited to boot time (before the
 kernel decompression starts) and works only on 80X86 machines.
 
-   **  Short intro for the impatient: Just use vga=ask for the first time,
-   **  enter `scan' on the video mode prompt, pick the mode you want to use,
-   **  remember its mode ID (the four-digit hexadecimal number) and then
-   **  set the vga parameter to this number (converted to decimal first).
+.. note::
 
-   The video mode to be used is selected by a kernel parameter which can be
+   Short intro for the impatient: Just use vga=ask for the first time,
+   enter ``scan`` on the video mode prompt, pick the mode you want to use,
+   remember its mode ID (the four-digit hexadecimal number) and then
+   set the vga parameter to this number (converted to decimal first).
+
+The video mode to be used is selected by a kernel parameter which can be
 specified in the kernel Makefile (the SVGA_MODE=... line) or by the "vga=..."
 option of LILO (or some other boot loader you use) or by the "vidmode" utility
 (present in standard Linux utility packages). You can use the following values
-of this parameter:
+of this parameter::
 
    NORMAL_VGA - Standard 80x25 mode available on all display adapters.
 
@@ -37,77 +44,79 @@
       for exact meaning of the ID). Warning: rdev and LILO don't support
       hexadecimal numbers -- you have to convert it to decimal manually.
 
-2. Menu
-~~~~~~~
-   The ASK_VGA mode causes the kernel to offer a video mode menu upon
+Menu
+~~~~
+
+The ASK_VGA mode causes the kernel to offer a video mode menu upon
 bootup. It displays a "Press <RETURN> to see video modes available, <SPACE>
 to continue or wait 30 secs" message. If you press <RETURN>, you enter the
 menu, if you press <SPACE> or wait 30 seconds, the kernel will boot up in
 the standard 80x25 mode.
 
-   The menu looks like:
+The menu looks like::
 
-Video adapter: <name-of-detected-video-adapter>
-Mode:    COLSxROWS:
-0  0F00  80x25
-1  0F01  80x50
-2  0F02  80x43
-3  0F03  80x26
-....
-Enter mode number or `scan': <flashing-cursor-here>
+	Video adapter: <name-of-detected-video-adapter>
+	Mode:    COLSxROWS:
+	0  0F00  80x25
+	1  0F01  80x50
+	2  0F02  80x43
+	3  0F03  80x26
+	....
+	Enter mode number or ``scan``: <flashing-cursor-here>
 
-   <name-of-detected-video-adapter> tells what video adapter did Linux detect
+<name-of-detected-video-adapter> tells what video adapter did Linux detect
 -- it's either a generic adapter name (MDA, CGA, HGC, EGA, VGA, VESA VGA [a VGA
 with VESA-compliant BIOS]) or a chipset name (e.g., Trident). Direct detection
 of chipsets is turned off by default (see CONFIG_VIDEO_SVGA in chapter 4 to see
 how to enable it if you really want) as it's inherently unreliable due to
 absolutely insane PC design.
 
-   "0  0F00  80x25" means that the first menu item (the menu items are numbered
+"0  0F00  80x25" means that the first menu item (the menu items are numbered
 from "0" to "9" and from "a" to "z") is a 80x25 mode with ID=0x0f00 (see the
 next section for a description of mode IDs).
 
-   <flashing-cursor-here> encourages you to enter the item number or mode ID
+<flashing-cursor-here> encourages you to enter the item number or mode ID
 you wish to set and press <RETURN>. If the computer complains something about
 "Unknown mode ID", it is trying to tell you that it isn't possible to set such
 a mode. It's also possible to press only <RETURN> which leaves the current mode.
 
-   The mode list usually contains a few basic modes and some VESA modes.  In
+The mode list usually contains a few basic modes and some VESA modes.  In
 case your chipset has been detected, some chipset-specific modes are shown as
 well (some of these might be missing or unusable on your machine as different
 BIOSes are often shipped with the same card and the mode numbers depend purely
 on the VGA BIOS).
 
-   The modes displayed on the menu are partially sorted: The list starts with
+The modes displayed on the menu are partially sorted: The list starts with
 the standard modes (80x25 and 80x50) followed by "special" modes (80x28 and
 80x43), local modes (if the local modes feature is enabled), VESA modes and
 finally SVGA modes for the auto-detected adapter.
 
-   If you are not happy with the mode list offered (e.g., if you think your card
+If you are not happy with the mode list offered (e.g., if you think your card
 is able to do more), you can enter "scan" instead of item number / mode ID.  The
 program will try to ask the BIOS for all possible video mode numbers and test
 what happens then. The screen will be probably flashing wildly for some time and
 strange noises will be heard from inside the monitor and so on and then, really
 all consistent video modes supported by your BIOS will appear (plus maybe some
-`ghost modes'). If you are afraid this could damage your monitor, don't use this
-function.
+``ghost modes``). If you are afraid this could damage your monitor, don't use
+this function.
 
-   After scanning, the mode ordering is a bit different: the auto-detected SVGA
-modes are not listed at all and the modes revealed by `scan' are shown before
+After scanning, the mode ordering is a bit different: the auto-detected SVGA
+modes are not listed at all and the modes revealed by ``scan`` are shown before
 all VESA modes.
 
-3. Mode IDs
-~~~~~~~~~~~
-   Because of the complexity of all the video stuff, the video mode IDs
+Mode IDs
+~~~~~~~~
+
+Because of the complexity of all the video stuff, the video mode IDs
 used here are also a bit complex. A video mode ID is a 16-bit number usually
 expressed in a hexadecimal notation (starting with "0x"). You can set a mode
 by entering its mode directly if you know it even if it isn't shown on the menu.
 
-The ID numbers can be divided to three regions:
+The ID numbers can be divided to those regions::
 
    0x0000 to 0x00ff - menu item references. 0x0000 is the first item. Don't use
 	outside the menu as this can change from boot to boot (especially if you
-	have used the `scan' feature).
+	have used the ``scan`` feature).
 
    0x0100 to 0x017f - standard BIOS modes. The ID is a BIOS video mode number
 	(as presented to INT 10, function 00) increased by 0x0100.
@@ -142,53 +151,54 @@
 	0xffff	equivalent to 0x0f00 (standard 80x25)
 	0xfffe	equivalent to 0x0f01 (EGA 80x43 or VGA 80x50)
 
-   If you add 0x8000 to the mode ID, the program will try to recalculate
+If you add 0x8000 to the mode ID, the program will try to recalculate
 vertical display timing according to mode parameters, which can be used to
 eliminate some annoying bugs of certain VGA BIOSes (usually those used for
 cards with S3 chipsets and old Cirrus Logic BIOSes) -- mainly extra lines at the
 end of the display.
 
-4. Options
-~~~~~~~~~~
-   Some options can be set in the source text (in arch/i386/boot/video.S).
+Options
+~~~~~~~
+
+Some options can be set in the source text (in arch/i386/boot/video.S).
 All of them are simple #define's -- change them to #undef's when you want to
 switch them off. Currently supported:
 
-   CONFIG_VIDEO_SVGA - enables autodetection of SVGA cards. This is switched
+CONFIG_VIDEO_SVGA - enables autodetection of SVGA cards. This is switched
 off by default as it's a bit unreliable due to terribly bad PC design. If you
-really want to have the adapter autodetected (maybe in case the `scan' feature
+really want to have the adapter autodetected (maybe in case the ``scan`` feature
 doesn't work on your machine), switch this on and don't cry if the results
 are not completely sane. In case you really need this feature, please drop me
 a mail as I think of removing it some day.
 
-   CONFIG_VIDEO_VESA - enables autodetection of VESA modes. If it doesn't work
+CONFIG_VIDEO_VESA - enables autodetection of VESA modes. If it doesn't work
 on your machine (or displays a "Error: Scanning of VESA modes failed" message),
 you can switch it off and report as a bug.
 
-   CONFIG_VIDEO_COMPACT - enables compacting of the video mode list. If there
+CONFIG_VIDEO_COMPACT - enables compacting of the video mode list. If there
 are more modes with the same screen size, only the first one is kept (see above
 for more info on mode ordering). However, in very strange cases it's possible
 that the first "version" of the mode doesn't work although some of the others
 do -- in this case turn this switch off to see the rest.
 
-   CONFIG_VIDEO_RETAIN - enables retaining of screen contents when switching
+CONFIG_VIDEO_RETAIN - enables retaining of screen contents when switching
 video modes. Works only with some boot loaders which leave enough room for the
 buffer. (If you have old LILO, you can adjust heap_end_ptr and loadflags
 in setup.S, but it's better to upgrade the boot loader...)
 
-   CONFIG_VIDEO_LOCAL - enables inclusion of "local modes" in the list. The
+CONFIG_VIDEO_LOCAL - enables inclusion of "local modes" in the list. The
 local modes are added automatically to the beginning of the list not depending
 on hardware configuration. The local modes are listed in the source text after
 the "local_mode_table:" line. The comment before this line describes the format
 of the table (which also includes a video card name to be displayed on the
 top of the menu).
 
-   CONFIG_VIDEO_400_HACK - force setting of 400 scan lines for standard VGA
+CONFIG_VIDEO_400_HACK - force setting of 400 scan lines for standard VGA
 modes. This option is intended to be used on certain buggy BIOSes which draw
 some useless logo using font download and then fail to reset the correct mode.
 Don't use unless needed as it forces resetting the video card.
 
-   CONFIG_VIDEO_GFX_HACK - includes special hack for setting of graphics modes
+CONFIG_VIDEO_GFX_HACK - includes special hack for setting of graphics modes
 to be used later by special drivers (e.g., 800x600 on IBM ThinkPad -- see
 ftp://ftp.phys.keio.ac.jp/pub/XFree86/800x600/XF86Configs/XF86Config.IBM_TP560).
 Allows to set _any_ BIOS mode including graphic ones and forcing specific
@@ -196,33 +206,36 @@
 unless you think you know what you're doing. To activate this setup, use
 mode number 0x0f08 (see section 3).
 
-5. Still doesn't work?
-~~~~~~~~~~~~~~~~~~~~~~
-   When the mode detection doesn't work (e.g., the mode list is incorrect or
+Still doesn't work?
+~~~~~~~~~~~~~~~~~~~
+
+When the mode detection doesn't work (e.g., the mode list is incorrect or
 the machine hangs instead of displaying the menu), try to switch off some of
 the configuration options listed in section 4. If it fails, you can still use
 your kernel with the video mode set directly via the kernel parameter.
 
-   In either case, please send me a bug report containing what _exactly_
+In either case, please send me a bug report containing what _exactly_
 happens and how do the configuration switches affect the behaviour of the bug.
 
-   If you start Linux from M$-DOS, you might also use some DOS tools for
+If you start Linux from M$-DOS, you might also use some DOS tools for
 video mode setting. In this case, you must specify the 0x0f04 mode ("leave
 current settings") to Linux, because if you don't and you use any non-standard
 mode, Linux will switch to 80x25 automatically.
 
-   If you set some extended mode and there's one or more extra lines on the
+If you set some extended mode and there's one or more extra lines on the
 bottom of the display containing already scrolled-out text, your VGA BIOS
 contains the most common video BIOS bug called "incorrect vertical display
 end setting". Adding 0x8000 to the mode ID might fix the problem. Unfortunately,
 this must be done manually -- no autodetection mechanisms are available.
 
-   If you have a VGA card and your display still looks as on EGA, your BIOS
+If you have a VGA card and your display still looks as on EGA, your BIOS
 is probably broken and you need to set the CONFIG_VIDEO_400_HACK switch to
 force setting of the correct mode.
 
-6. History
-~~~~~~~~~~
+History
+~~~~~~~
+
+=============== ================================================================
 1.0 (??-Nov-95)	First version supporting all adapters supported by the old
 		setup.S + Cirrus Logic 54XX. Present in some 1.3.4? kernels
 		and then removed due to instability on some machines.
@@ -260,17 +273,18 @@
 		  original version written by hhanemaa@cs.ruu.nl, patched by
 		  Jeff Chua, rewritten by me).
 		- Screen store/restore fixed.
-2.8 (14-Apr-96)	- Previous release was not compilable without CONFIG_VIDEO_SVGA.
+2.8 (14-Apr-96) - Previous release was not compilable without CONFIG_VIDEO_SVGA.
 		- Better recognition of text modes during mode scan.
 2.9 (12-May-96)	- Ignored VESA modes 0x80 - 0xff (more VESA BIOS bugs!)
-2.10 (11-Nov-96)- The whole thing made optional.
+2.10(11-Nov-96) - The whole thing made optional.
 		- Added the CONFIG_VIDEO_400_HACK switch.
 		- Added the CONFIG_VIDEO_GFX_HACK switch.
 		- Code cleanup.
-2.11 (03-May-97)- Yet another cleanup, now including also the documentation.
-		- Direct testing of SVGA adapters turned off by default, `scan'
+2.11(03-May-97) - Yet another cleanup, now including also the documentation.
+		- Direct testing of SVGA adapters turned off by default, ``scan``
 		  offered explicitly on the prompt line.
 		- Removed the doc section describing adding of new probing
 		  functions as I try to get rid of _all_ hardware probing here.
-2.12 (25-May-98)- Added support for VESA frame buffer graphics.
-2.13 (14-May-99)- Minor documentation fixes.
+2.12(25-May-98) Added support for VESA frame buffer graphics.
+2.13(14-May-99) Minor documentation fixes.
+=============== ================================================================
diff --git a/Documentation/tee.txt b/Documentation/tee.txt
index 7185993..56ea85f 100644
--- a/Documentation/tee.txt
+++ b/Documentation/tee.txt
@@ -1,4 +1,7 @@
+=============
 TEE subsystem
+=============
+
 This document describes the TEE subsystem in Linux.
 
 A TEE (Trusted Execution Environment) is a trusted OS running in some
@@ -80,27 +83,27 @@
 TEE API.
 
 Picture of the relationship between the different components in the
-OP-TEE architecture.
+OP-TEE architecture::
 
-    User space                  Kernel                   Secure world
-    ~~~~~~~~~~                  ~~~~~~                   ~~~~~~~~~~~~
- +--------+                                             +-------------+
- | Client |                                             | Trusted     |
- +--------+                                             | Application |
-    /\                                                  +-------------+
-    || +----------+                                           /\
-    || |tee-      |                                           ||
-    || |supplicant|                                           \/
-    || +----------+                                     +-------------+
-    \/      /\                                          | TEE Internal|
- +-------+  ||                                          | API         |
- + TEE   |  ||            +--------+--------+           +-------------+
- | Client|  ||            | TEE    | OP-TEE |           | OP-TEE      |
- | API   |  \/            | subsys | driver |           | Trusted OS  |
- +-------+----------------+----+-------+----+-----------+-------------+
- |      Generic TEE API        |       |     OP-TEE MSG               |
- |      IOCTL (TEE_IOC_*)      |       |     SMCCC (OPTEE_SMC_CALL_*) |
- +-----------------------------+       +------------------------------+
+      User space                  Kernel                   Secure world
+      ~~~~~~~~~~                  ~~~~~~                   ~~~~~~~~~~~~
+   +--------+                                             +-------------+
+   | Client |                                             | Trusted     |
+   +--------+                                             | Application |
+      /\                                                  +-------------+
+      || +----------+                                           /\
+      || |tee-      |                                           ||
+      || |supplicant|                                           \/
+      || +----------+                                     +-------------+
+      \/      /\                                          | TEE Internal|
+   +-------+  ||                                          | API         |
+   + TEE   |  ||            +--------+--------+           +-------------+
+   | Client|  ||            | TEE    | OP-TEE |           | OP-TEE      |
+   | API   |  \/            | subsys | driver |           | Trusted OS  |
+   +-------+----------------+----+-------+----+-----------+-------------+
+   |      Generic TEE API        |       |     OP-TEE MSG               |
+   |      IOCTL (TEE_IOC_*)      |       |     SMCCC (OPTEE_SMC_CALL_*) |
+   +-----------------------------+       +------------------------------+
 
 RPC (Remote Procedure Call) are requests from secure world to kernel driver
 or tee-supplicant. An RPC is identified by a special range of SMCCC return
@@ -109,10 +112,16 @@
 tee-supplicant without further involvement of the driver, except switching
 shared memory buffer representation.
 
-References:
+References
+==========
+
 [1] https://github.com/OP-TEE/optee_os
+
 [2] http://infocenter.arm.com/help/topic/com.arm.doc.den0028a/index.html
+
 [3] drivers/tee/optee/optee_smc.h
+
 [4] drivers/tee/optee/optee_msg.h
+
 [5] http://www.globalplatform.org/specificationsdevice.asp look for
     "TEE Client API Specification v1.0" and click download.
diff --git a/Documentation/this_cpu_ops.txt b/Documentation/this_cpu_ops.txt
index 2cbf719..5cb8b88 100644
--- a/Documentation/this_cpu_ops.txt
+++ b/Documentation/this_cpu_ops.txt
@@ -1,5 +1,9 @@
+===================
 this_cpu operations
--------------------
+===================
+
+:Author: Christoph Lameter, August 4th, 2014
+:Author: Pranith Kumar, Aug 2nd, 2014
 
 this_cpu operations are a way of optimizing access to per cpu
 variables associated with the *currently* executing processor. This is
@@ -39,7 +43,7 @@
 
 The following this_cpu() operations with implied preemption protection
 are defined. These operations can be used without worrying about
-preemption and interrupts.
+preemption and interrupts::
 
 	this_cpu_read(pcp)
 	this_cpu_write(pcp, val)
@@ -67,14 +71,14 @@
 the processor. So the relocation to the per cpu base is encoded in the
 instruction via a segment register prefix.
 
-For example:
+For example::
 
 	DEFINE_PER_CPU(int, x);
 	int z;
 
 	z = this_cpu_read(x);
 
-results in a single instruction
+results in a single instruction::
 
 	mov ax, gs:[x]
 
@@ -84,16 +88,16 @@
 prevent the kernel from moving the thread to a different processor
 while the calculation is performed.
 
-Consider the following this_cpu operation:
+Consider the following this_cpu operation::
 
 	this_cpu_inc(x)
 
-The above results in the following single instruction (no lock prefix!)
+The above results in the following single instruction (no lock prefix!)::
 
 	inc gs:[x]
 
 instead of the following operations required if there is no segment
-register:
+register::
 
 	int *y;
 	int cpu;
@@ -121,8 +125,10 @@
 counters when the value of a counter is needed.
 
 
-Special operations:
--------------------
+Special operations
+------------------
+
+::
 
 	y = this_cpu_ptr(&x)
 
@@ -153,11 +159,15 @@
 operations is invalid and will generally be treated like a NULL
 pointer dereference.
 
+::
+
 	DEFINE_PER_CPU(int, x);
 
 In the context of per cpu operations the above implies that x is a per
 cpu variable. Most this_cpu operations take a cpu variable.
 
+::
+
 	int __percpu *p = &x;
 
 &x and hence p is the *offset* of a per cpu variable. this_cpu_ptr()
@@ -168,7 +178,7 @@
 Operations on a field of a per cpu structure
 --------------------------------------------
 
-Let's say we have a percpu structure
+Let's say we have a percpu structure::
 
 	struct s {
 		int n,m;
@@ -177,14 +187,14 @@
 	DEFINE_PER_CPU(struct s, p);
 
 
-Operations on these fields are straightforward
+Operations on these fields are straightforward::
 
 	this_cpu_inc(p.m)
 
 	z = this_cpu_cmpxchg(p.m, 0, 1);
 
 
-If we have an offset to struct s:
+If we have an offset to struct s::
 
 	struct s __percpu *ps = &p;
 
@@ -194,7 +204,7 @@
 
 
 The calculation of the pointer may require the use of this_cpu_ptr()
-if we do not make use of this_cpu ops later to manipulate fields:
+if we do not make use of this_cpu ops later to manipulate fields::
 
 	struct s *pp;
 
@@ -206,7 +216,7 @@
 
 
 Variants of this_cpu ops
--------------------------
+------------------------
 
 this_cpu ops are interrupt safe. Some architectures do not support
 these per cpu local operations. In that case the operation must be
@@ -222,7 +232,7 @@
 and the scheduler cannot preempt, then they are safe. If any interrupts
 still occur while an operation is in progress and if the interrupt too
 modifies the variable, then RMW actions can not be guaranteed to be
-safe.
+safe::
 
 	__this_cpu_read(pcp)
 	__this_cpu_write(pcp, val)
@@ -279,7 +289,7 @@
 the remote CPU and perform the update to its per cpu area.
 
 To access per-cpu data structure remotely, typically the per_cpu_ptr()
-function is used:
+function is used::
 
 
 	DEFINE_PER_CPU(struct data, datap);
@@ -289,7 +299,7 @@
 This makes it explicit that we are getting ready to access a percpu
 area remotely.
 
-You can also do the following to convert the datap offset to an address
+You can also do the following to convert the datap offset to an address::
 
 	struct data *p = this_cpu_ptr(&datap);
 
@@ -305,7 +315,7 @@
 share a cache-line but the relaxed synchronization is applied to
 only one process updating the cache-line.
 
-Consider the following example
+Consider the following example::
 
 
 	struct test {
@@ -327,6 +337,3 @@
 that most likely will access it. If the processor wakes up and finds a
 missing local cache line of a per cpu area, its performance and hence
 the wake up times will be affected.
-
-Christoph Lameter, August 4th, 2014
-Pranith Kumar, Aug 2nd, 2014
diff --git a/Documentation/unaligned-memory-access.txt b/Documentation/unaligned-memory-access.txt
index 3f76c0c..51b4ff0 100644
--- a/Documentation/unaligned-memory-access.txt
+++ b/Documentation/unaligned-memory-access.txt
@@ -1,6 +1,15 @@
+=========================
 UNALIGNED MEMORY ACCESSES
 =========================
 
+:Author: Daniel Drake <dsd@gentoo.org>,
+:Author: Johannes Berg <johannes@sipsolutions.net>
+
+:With help from: Alan Cox, Avuton Olrich, Heikki Orsila, Jan Engelhardt,
+  Kyle McMartin, Kyle Moffett, Randy Dunlap, Robert Hancock, Uli Kunitz,
+  Vadim Lobanov
+
+
 Linux runs on a wide variety of architectures which have varying behaviour
 when it comes to memory access. This document presents some details about
 unaligned accesses, why you need to write code that doesn't cause them,
@@ -73,7 +82,7 @@
 
 Fortunately things are not too complex, as in most cases, the compiler
 ensures that things will work for you. For example, take the following
-structure:
+structure::
 
 	struct foo {
 		u16 field1;
@@ -106,7 +115,7 @@
 that you could reorder the fields in the structure in order to place fields
 where padding would otherwise be inserted, and hence reduce the overall
 resident memory size of structure instances. The optimal layout of the
-above example is:
+above example is::
 
 	struct foo {
 		u32 field2;
@@ -139,21 +148,21 @@
 With the above in mind, let's move onto a real life example of a function
 that can cause an unaligned memory access. The following function taken
 from include/linux/etherdevice.h is an optimized routine to compare two
-ethernet MAC addresses for equality.
+ethernet MAC addresses for equality::
 
-bool ether_addr_equal(const u8 *addr1, const u8 *addr2)
-{
-#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+  bool ether_addr_equal(const u8 *addr1, const u8 *addr2)
+  {
+  #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 	u32 fold = ((*(const u32 *)addr1) ^ (*(const u32 *)addr2)) |
 		   ((*(const u16 *)(addr1 + 4)) ^ (*(const u16 *)(addr2 + 4)));
 
 	return fold == 0;
-#else
+  #else
 	const u16 *a = (const u16 *)addr1;
 	const u16 *b = (const u16 *)addr2;
 	return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | (a[2] ^ b[2])) == 0;
-#endif
-}
+  #endif
+  }
 
 In the above function, when the hardware has efficient unaligned access
 capability, there is no issue with this code.  But when the hardware isn't
@@ -171,7 +180,8 @@
 which is true almost all of the time in ethernet networking context.
 
 
-Here is another example of some code that could cause unaligned accesses:
+Here is another example of some code that could cause unaligned accesses::
+
 	void myfunc(u8 *data, u32 value)
 	{
 		[...]
@@ -184,6 +194,7 @@
 
 In summary, the 2 main scenarios where you may run into unaligned access
 problems involve:
+
  1. Casting variables to types of different lengths
  2. Pointer arithmetic followed by access to at least 2 bytes of data
 
@@ -195,7 +206,7 @@
 put_unaligned() macros provided by the <asm/unaligned.h> header file.
 
 Going back to an earlier example of code that potentially causes unaligned
-access:
+access::
 
 	void myfunc(u8 *data, u32 value)
 	{
@@ -204,7 +215,7 @@
 		[...]
 	}
 
-To avoid the unaligned memory access, you would rewrite it as follows:
+To avoid the unaligned memory access, you would rewrite it as follows::
 
 	void myfunc(u8 *data, u32 value)
 	{
@@ -215,7 +226,7 @@
 	}
 
 The get_unaligned() macro works similarly. Assuming 'data' is a pointer to
-memory and you wish to avoid unaligned access, its usage is as follows:
+memory and you wish to avoid unaligned access, its usage is as follows::
 
 	u32 value = get_unaligned((u32 *) data);
 
@@ -245,18 +256,10 @@
 4*n+2 or non-ethernet hardware, this can be a problem, and it is then
 required to copy the incoming frame into an aligned buffer. Because this is
 unnecessary on architectures that can do unaligned accesses, the code can be
-made dependent on CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS like so:
+made dependent on CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS like so::
 
-#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
-	skb = original skb
-#else
-	skb = copy skb
-#endif
-
---
-Authors: Daniel Drake <dsd@gentoo.org>,
-         Johannes Berg <johannes@sipsolutions.net>
-With help from: Alan Cox, Avuton Olrich, Heikki Orsila, Jan Engelhardt,
-Kyle McMartin, Kyle Moffett, Randy Dunlap, Robert Hancock, Uli Kunitz,
-Vadim Lobanov
-
+	#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+		skb = original skb
+	#else
+		skb = copy skb
+	#endif
diff --git a/Documentation/vfio-mediated-device.txt b/Documentation/vfio-mediated-device.txt
index e5e57b4..1b39503 100644
--- a/Documentation/vfio-mediated-device.txt
+++ b/Documentation/vfio-mediated-device.txt
@@ -1,14 +1,17 @@
-/*
- * VFIO Mediated devices
- *
- * Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved.
- *     Author: Neo Jia <cjia@nvidia.com>
- *             Kirti Wankhede <kwankhede@nvidia.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+.. include:: <isonum.txt>
+
+=====================
+VFIO Mediated devices
+=====================
+
+:Copyright: |copy| 2016, NVIDIA CORPORATION. All rights reserved.
+:Author: Neo Jia <cjia@nvidia.com>
+:Author: Kirti Wankhede <kwankhede@nvidia.com>
+
+This program is free software; you can redistribute it and/or modify
+it under the terms of the GNU General Public License version 2 as
+published by the Free Software Foundation.
+
 
 Virtual Function I/O (VFIO) Mediated devices[1]
 ===============================================
@@ -42,7 +45,7 @@
 
 The following high-level block diagram shows the main components and interfaces
 in the VFIO mediated driver framework. The diagram shows NVIDIA, Intel, and IBM
-devices as examples, as these devices are the first devices to use this module.
+devices as examples, as these devices are the first devices to use this module::
 
      +---------------+
      |               |
@@ -91,7 +94,7 @@
 ------------------------------------------------
 
 The registration interface for a mediated bus driver provides the following
-structure to represent a mediated device's driver:
+structure to represent a mediated device's driver::
 
      /*
       * struct mdev_driver [2] - Mediated device's driver
@@ -110,14 +113,14 @@
 A mediated bus driver for mdev should use this structure in the function calls
 to register and unregister itself with the core driver:
 
-* Register:
+* Register::
 
-  extern int  mdev_register_driver(struct mdev_driver *drv,
+    extern int  mdev_register_driver(struct mdev_driver *drv,
 				   struct module *owner);
 
-* Unregister:
+* Unregister::
 
-  extern void mdev_unregister_driver(struct mdev_driver *drv);
+    extern void mdev_unregister_driver(struct mdev_driver *drv);
 
 The mediated bus driver is responsible for adding mediated devices to the VFIO
 group when devices are bound to the driver and removing mediated devices from
@@ -152,15 +155,15 @@
 * mmap: mmap emulation callback
 
 A driver should use the mdev_parent_ops structure in the function call to
-register itself with the mdev core driver:
+register itself with the mdev core driver::
 
-extern int  mdev_register_device(struct device *dev,
-                                 const struct mdev_parent_ops *ops);
+	extern int  mdev_register_device(struct device *dev,
+	                                 const struct mdev_parent_ops *ops);
 
 However, the mdev_parent_ops structure is not required in the function call
-that a driver should use to unregister itself with the mdev core driver:
+that a driver should use to unregister itself with the mdev core driver::
 
-extern void mdev_unregister_device(struct device *dev);
+	extern void mdev_unregister_device(struct device *dev);
 
 
 Mediated Device Management Interface Through sysfs
@@ -183,30 +186,32 @@
 Directories and files under the sysfs for Each Physical Device
 --------------------------------------------------------------
 
-|- [parent physical device]
-|--- Vendor-specific-attributes [optional]
-|--- [mdev_supported_types]
-|     |--- [<type-id>]
-|     |   |--- create
-|     |   |--- name
-|     |   |--- available_instances
-|     |   |--- device_api
-|     |   |--- description
-|     |   |--- [devices]
-|     |--- [<type-id>]
-|     |   |--- create
-|     |   |--- name
-|     |   |--- available_instances
-|     |   |--- device_api
-|     |   |--- description
-|     |   |--- [devices]
-|     |--- [<type-id>]
-|          |--- create
-|          |--- name
-|          |--- available_instances
-|          |--- device_api
-|          |--- description
-|          |--- [devices]
+::
+
+  |- [parent physical device]
+  |--- Vendor-specific-attributes [optional]
+  |--- [mdev_supported_types]
+  |     |--- [<type-id>]
+  |     |   |--- create
+  |     |   |--- name
+  |     |   |--- available_instances
+  |     |   |--- device_api
+  |     |   |--- description
+  |     |   |--- [devices]
+  |     |--- [<type-id>]
+  |     |   |--- create
+  |     |   |--- name
+  |     |   |--- available_instances
+  |     |   |--- device_api
+  |     |   |--- description
+  |     |   |--- [devices]
+  |     |--- [<type-id>]
+  |          |--- create
+  |          |--- name
+  |          |--- available_instances
+  |          |--- device_api
+  |          |--- description
+  |          |--- [devices]
 
 * [mdev_supported_types]
 
@@ -219,12 +224,12 @@
 
   The [<type-id>] name is created by adding the device driver string as a prefix
   to the string provided by the vendor driver. This format of this name is as
-  follows:
+  follows::
 
 	sprintf(buf, "%s-%s", dev_driver_string(parent->dev), group->name);
 
   (or using mdev_parent_dev(mdev) to arrive at the parent device outside
-   of the core mdev code)
+  of the core mdev code)
 
 * device_api
 
@@ -239,7 +244,7 @@
 * [device]
 
   This directory contains links to the devices of type <type-id> that have been
-created.
+  created.
 
 * name
 
@@ -253,21 +258,25 @@
 Directories and Files Under the sysfs for Each mdev Device
 ----------------------------------------------------------
 
-|- [parent phy device]
-|--- [$MDEV_UUID]
+::
+
+  |- [parent phy device]
+  |--- [$MDEV_UUID]
          |--- remove
          |--- mdev_type {link to its type}
          |--- vendor-specific-attributes [optional]
 
 * remove (write only)
+
 Writing '1' to the 'remove' file destroys the mdev device. The vendor driver can
 fail the remove() callback if that device is active and the vendor driver
 doesn't support hot unplug.
 
-Example:
+Example::
+
 	# echo 1 > /sys/bus/mdev/devices/$mdev_UUID/remove
 
-Mediated device Hot plug:
+Mediated device Hot plug
 ------------------------
 
 Mediated devices can be created and assigned at runtime. The procedure to hot
@@ -277,13 +286,13 @@
 =====================================
 
 The following APIs are provided for translating user pfn to host pfn in a VFIO
-driver:
+driver::
 
-extern int vfio_pin_pages(struct device *dev, unsigned long *user_pfn,
-                          int npage, int prot, unsigned long *phys_pfn);
+	extern int vfio_pin_pages(struct device *dev, unsigned long *user_pfn,
+				  int npage, int prot, unsigned long *phys_pfn);
 
-extern int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn,
-                            int npage);
+	extern int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn,
+				    int npage);
 
 These functions call back into the back-end IOMMU module by using the pin_pages
 and unpin_pages callbacks of the struct vfio_iommu_driver_ops[4]. Currently
@@ -304,81 +313,80 @@
 
    This step creates a dummy device, /sys/devices/virtual/mtty/mtty/
 
-   Files in this device directory in sysfs are similar to the following:
+   Files in this device directory in sysfs are similar to the following::
 
-   # tree /sys/devices/virtual/mtty/mtty/
-      /sys/devices/virtual/mtty/mtty/
-      |-- mdev_supported_types
-      |   |-- mtty-1
-      |   |   |-- available_instances
-      |   |   |-- create
-      |   |   |-- device_api
-      |   |   |-- devices
-      |   |   `-- name
-      |   `-- mtty-2
-      |       |-- available_instances
-      |       |-- create
-      |       |-- device_api
-      |       |-- devices
-      |       `-- name
-      |-- mtty_dev
-      |   `-- sample_mtty_dev
-      |-- power
-      |   |-- autosuspend_delay_ms
-      |   |-- control
-      |   |-- runtime_active_time
-      |   |-- runtime_status
-      |   `-- runtime_suspended_time
-      |-- subsystem -> ../../../../class/mtty
-      `-- uevent
+     # tree /sys/devices/virtual/mtty/mtty/
+        /sys/devices/virtual/mtty/mtty/
+        |-- mdev_supported_types
+        |   |-- mtty-1
+        |   |   |-- available_instances
+        |   |   |-- create
+        |   |   |-- device_api
+        |   |   |-- devices
+        |   |   `-- name
+        |   `-- mtty-2
+        |       |-- available_instances
+        |       |-- create
+        |       |-- device_api
+        |       |-- devices
+        |       `-- name
+        |-- mtty_dev
+        |   `-- sample_mtty_dev
+        |-- power
+        |   |-- autosuspend_delay_ms
+        |   |-- control
+        |   |-- runtime_active_time
+        |   |-- runtime_status
+        |   `-- runtime_suspended_time
+        |-- subsystem -> ../../../../class/mtty
+        `-- uevent
 
 2. Create a mediated device by using the dummy device that you created in the
-   previous step.
+   previous step::
 
-   # echo "83b8f4f2-509f-382f-3c1e-e6bfe0fa1001" >	\
+     # echo "83b8f4f2-509f-382f-3c1e-e6bfe0fa1001" >	\
               /sys/devices/virtual/mtty/mtty/mdev_supported_types/mtty-2/create
 
-3. Add parameters to qemu-kvm.
+3. Add parameters to qemu-kvm::
 
-   -device vfio-pci,\
-    sysfsdev=/sys/bus/mdev/devices/83b8f4f2-509f-382f-3c1e-e6bfe0fa1001
+     -device vfio-pci,\
+      sysfsdev=/sys/bus/mdev/devices/83b8f4f2-509f-382f-3c1e-e6bfe0fa1001
 
 4. Boot the VM.
 
    In the Linux guest VM, with no hardware on the host, the device appears
-   as  follows:
+   as  follows::
 
-   # lspci -s 00:05.0 -xxvv
-   00:05.0 Serial controller: Device 4348:3253 (rev 10) (prog-if 02 [16550])
-           Subsystem: Device 4348:3253
-           Physical Slot: 5
-           Control: I/O+ Mem- BusMaster- SpecCycle- MemWINV- VGASnoop- ParErr-
-   Stepping- SERR- FastB2B- DisINTx-
-           Status: Cap- 66MHz- UDF- FastB2B- ParErr- DEVSEL=medium >TAbort-
-   <TAbort- <MAbort- >SERR- <PERR- INTx-
-           Interrupt: pin A routed to IRQ 10
-           Region 0: I/O ports at c150 [size=8]
-           Region 1: I/O ports at c158 [size=8]
-           Kernel driver in use: serial
-   00: 48 43 53 32 01 00 00 02 10 02 00 07 00 00 00 00
-   10: 51 c1 00 00 59 c1 00 00 00 00 00 00 00 00 00 00
-   20: 00 00 00 00 00 00 00 00 00 00 00 00 48 43 53 32
-   30: 00 00 00 00 00 00 00 00 00 00 00 00 0a 01 00 00
+     # lspci -s 00:05.0 -xxvv
+     00:05.0 Serial controller: Device 4348:3253 (rev 10) (prog-if 02 [16550])
+             Subsystem: Device 4348:3253
+             Physical Slot: 5
+             Control: I/O+ Mem- BusMaster- SpecCycle- MemWINV- VGASnoop- ParErr-
+     Stepping- SERR- FastB2B- DisINTx-
+             Status: Cap- 66MHz- UDF- FastB2B- ParErr- DEVSEL=medium >TAbort-
+     <TAbort- <MAbort- >SERR- <PERR- INTx-
+             Interrupt: pin A routed to IRQ 10
+             Region 0: I/O ports at c150 [size=8]
+             Region 1: I/O ports at c158 [size=8]
+             Kernel driver in use: serial
+     00: 48 43 53 32 01 00 00 02 10 02 00 07 00 00 00 00
+     10: 51 c1 00 00 59 c1 00 00 00 00 00 00 00 00 00 00
+     20: 00 00 00 00 00 00 00 00 00 00 00 00 48 43 53 32
+     30: 00 00 00 00 00 00 00 00 00 00 00 00 0a 01 00 00
 
-   In the Linux guest VM, dmesg output for the device is as follows:
+     In the Linux guest VM, dmesg output for the device is as follows:
 
-   serial 0000:00:05.0: PCI INT A -> Link[LNKA] -> GSI 10 (level, high) -> IRQ
-10
-   0000:00:05.0: ttyS1 at I/O 0xc150 (irq = 10) is a 16550A
-   0000:00:05.0: ttyS2 at I/O 0xc158 (irq = 10) is a 16550A
+     serial 0000:00:05.0: PCI INT A -> Link[LNKA] -> GSI 10 (level, high) -> IRQ 10
+     0000:00:05.0: ttyS1 at I/O 0xc150 (irq = 10) is a 16550A
+     0000:00:05.0: ttyS2 at I/O 0xc158 (irq = 10) is a 16550A
 
 
-5. In the Linux guest VM, check the serial ports.
+5. In the Linux guest VM, check the serial ports::
 
-   # setserial -g /dev/ttyS*
-   /dev/ttyS0, UART: 16550A, Port: 0x03f8, IRQ: 4
-   /dev/ttyS1, UART: 16550A, Port: 0xc150, IRQ: 10
-   /dev/ttyS2, UART: 16550A, Port: 0xc158, IRQ: 10
+     # setserial -g /dev/ttyS*
+     /dev/ttyS0, UART: 16550A, Port: 0x03f8, IRQ: 4
+     /dev/ttyS1, UART: 16550A, Port: 0xc150, IRQ: 10
+     /dev/ttyS2, UART: 16550A, Port: 0xc158, IRQ: 10
 
 6. Using minicom or any terminal emulation program, open port /dev/ttyS1 or
    /dev/ttyS2 with hardware flow control disabled.
@@ -388,14 +396,14 @@
 
    Data is loop backed from hosts mtty driver.
 
-8. Destroy the mediated device that you created.
+8. Destroy the mediated device that you created::
 
-   # echo 1 > /sys/bus/mdev/devices/83b8f4f2-509f-382f-3c1e-e6bfe0fa1001/remove
+     # echo 1 > /sys/bus/mdev/devices/83b8f4f2-509f-382f-3c1e-e6bfe0fa1001/remove
 
 References
 ==========
 
-[1] See Documentation/vfio.txt for more information on VFIO.
-[2] struct mdev_driver in include/linux/mdev.h
-[3] struct mdev_parent_ops in include/linux/mdev.h
-[4] struct vfio_iommu_driver_ops in include/linux/vfio.h
+1. See Documentation/vfio.txt for more information on VFIO.
+2. struct mdev_driver in include/linux/mdev.h
+3. struct mdev_parent_ops in include/linux/mdev.h
+4. struct vfio_iommu_driver_ops in include/linux/vfio.h
diff --git a/Documentation/vfio.txt b/Documentation/vfio.txt
index 1dd3fdd..ef6a511 100644
--- a/Documentation/vfio.txt
+++ b/Documentation/vfio.txt
@@ -1,5 +1,7 @@
-VFIO - "Virtual Function I/O"[1]
--------------------------------------------------------------------------------
+==================================
+VFIO - "Virtual Function I/O" [1]_
+==================================
+
 Many modern system now provide DMA and interrupt remapping facilities
 to help ensure I/O devices behave within the boundaries they've been
 allotted.  This includes x86 hardware with AMD-Vi and Intel VT-d,
@@ -7,14 +9,14 @@
 systems such as Freescale PAMU.  The VFIO driver is an IOMMU/device
 agnostic framework for exposing direct device access to userspace, in
 a secure, IOMMU protected environment.  In other words, this allows
-safe[2], non-privileged, userspace drivers.
+safe [2]_, non-privileged, userspace drivers.
 
 Why do we want that?  Virtual machines often make use of direct device
 access ("device assignment") when configured for the highest possible
 I/O performance.  From a device and host perspective, this simply
 turns the VM into a userspace driver, with the benefits of
 significantly reduced latency, higher bandwidth, and direct use of
-bare-metal device drivers[3].
+bare-metal device drivers [3]_.
 
 Some applications, particularly in the high performance computing
 field, also benefit from low-overhead, direct device access from
@@ -31,7 +33,7 @@
 secure, more featureful userspace driver environment than UIO.
 
 Groups, Devices, and IOMMUs
--------------------------------------------------------------------------------
+---------------------------
 
 Devices are the main target of any I/O driver.  Devices typically
 create a programming interface made up of I/O access, interrupts,
@@ -114,40 +116,40 @@
 notifications.
 
 VFIO Usage Example
--------------------------------------------------------------------------------
+------------------
 
-Assume user wants to access PCI device 0000:06:0d.0
+Assume user wants to access PCI device 0000:06:0d.0::
 
-$ readlink /sys/bus/pci/devices/0000:06:0d.0/iommu_group
-../../../../kernel/iommu_groups/26
+	$ readlink /sys/bus/pci/devices/0000:06:0d.0/iommu_group
+	../../../../kernel/iommu_groups/26
 
 This device is therefore in IOMMU group 26.  This device is on the
 pci bus, therefore the user will make use of vfio-pci to manage the
-group:
+group::
 
-# modprobe vfio-pci
+	# modprobe vfio-pci
 
 Binding this device to the vfio-pci driver creates the VFIO group
-character devices for this group:
+character devices for this group::
 
-$ lspci -n -s 0000:06:0d.0
-06:0d.0 0401: 1102:0002 (rev 08)
-# echo 0000:06:0d.0 > /sys/bus/pci/devices/0000:06:0d.0/driver/unbind
-# echo 1102 0002 > /sys/bus/pci/drivers/vfio-pci/new_id
+	$ lspci -n -s 0000:06:0d.0
+	06:0d.0 0401: 1102:0002 (rev 08)
+	# echo 0000:06:0d.0 > /sys/bus/pci/devices/0000:06:0d.0/driver/unbind
+	# echo 1102 0002 > /sys/bus/pci/drivers/vfio-pci/new_id
 
 Now we need to look at what other devices are in the group to free
-it for use by VFIO:
+it for use by VFIO::
 
-$ ls -l /sys/bus/pci/devices/0000:06:0d.0/iommu_group/devices
-total 0
-lrwxrwxrwx. 1 root root 0 Apr 23 16:13 0000:00:1e.0 ->
-	../../../../devices/pci0000:00/0000:00:1e.0
-lrwxrwxrwx. 1 root root 0 Apr 23 16:13 0000:06:0d.0 ->
-	../../../../devices/pci0000:00/0000:00:1e.0/0000:06:0d.0
-lrwxrwxrwx. 1 root root 0 Apr 23 16:13 0000:06:0d.1 ->
-	../../../../devices/pci0000:00/0000:00:1e.0/0000:06:0d.1
+	$ ls -l /sys/bus/pci/devices/0000:06:0d.0/iommu_group/devices
+	total 0
+	lrwxrwxrwx. 1 root root 0 Apr 23 16:13 0000:00:1e.0 ->
+		../../../../devices/pci0000:00/0000:00:1e.0
+	lrwxrwxrwx. 1 root root 0 Apr 23 16:13 0000:06:0d.0 ->
+		../../../../devices/pci0000:00/0000:00:1e.0/0000:06:0d.0
+	lrwxrwxrwx. 1 root root 0 Apr 23 16:13 0000:06:0d.1 ->
+		../../../../devices/pci0000:00/0000:00:1e.0/0000:06:0d.1
 
-This device is behind a PCIe-to-PCI bridge[4], therefore we also
+This device is behind a PCIe-to-PCI bridge [4]_, therefore we also
 need to add device 0000:06:0d.1 to the group following the same
 procedure as above.  Device 0000:00:1e.0 is a bridge that does
 not currently have a host driver, therefore it's not required to
@@ -157,12 +159,12 @@
 The final step is to provide the user with access to the group if
 unprivileged operation is desired (note that /dev/vfio/vfio provides
 no capabilities on its own and is therefore expected to be set to
-mode 0666 by the system).
+mode 0666 by the system)::
 
-# chown user:user /dev/vfio/26
+	# chown user:user /dev/vfio/26
 
 The user now has full access to all the devices and the iommu for this
-group and can access them as follows:
+group and can access them as follows::
 
 	int container, group, device, i;
 	struct vfio_group_status group_status =
@@ -248,31 +250,31 @@
 VFIO bus drivers, such as vfio-pci make use of only a few interfaces
 into VFIO core.  When devices are bound and unbound to the driver,
 the driver should call vfio_add_group_dev() and vfio_del_group_dev()
-respectively:
+respectively::
 
-extern int vfio_add_group_dev(struct iommu_group *iommu_group,
-                              struct device *dev,
-                              const struct vfio_device_ops *ops,
-                              void *device_data);
+	extern int vfio_add_group_dev(struct iommu_group *iommu_group,
+	                              struct device *dev,
+				      const struct vfio_device_ops *ops,
+				      void *device_data);
 
-extern void *vfio_del_group_dev(struct device *dev);
+	extern void *vfio_del_group_dev(struct device *dev);
 
 vfio_add_group_dev() indicates to the core to begin tracking the
 specified iommu_group and register the specified dev as owned by
 a VFIO bus driver.  The driver provides an ops structure for callbacks
-similar to a file operations structure:
+similar to a file operations structure::
 
-struct vfio_device_ops {
-	int	(*open)(void *device_data);
-	void	(*release)(void *device_data);
-	ssize_t	(*read)(void *device_data, char __user *buf,
-			size_t count, loff_t *ppos);
-	ssize_t	(*write)(void *device_data, const char __user *buf,
-			 size_t size, loff_t *ppos);
-	long	(*ioctl)(void *device_data, unsigned int cmd,
-			 unsigned long arg);
-	int	(*mmap)(void *device_data, struct vm_area_struct *vma);
-};
+	struct vfio_device_ops {
+		int	(*open)(void *device_data);
+		void	(*release)(void *device_data);
+		ssize_t	(*read)(void *device_data, char __user *buf,
+				size_t count, loff_t *ppos);
+		ssize_t	(*write)(void *device_data, const char __user *buf,
+				 size_t size, loff_t *ppos);
+		long	(*ioctl)(void *device_data, unsigned int cmd,
+				 unsigned long arg);
+		int	(*mmap)(void *device_data, struct vm_area_struct *vma);
+	};
 
 Each function is passed the device_data that was originally registered
 in the vfio_add_group_dev() call above.  This allows the bus driver
@@ -285,50 +287,55 @@
 
 
 PPC64 sPAPR implementation note
--------------------------------------------------------------------------------
+-------------------------------
 
 This implementation has some specifics:
 
 1) On older systems (POWER7 with P5IOC2/IODA1) only one IOMMU group per
-container is supported as an IOMMU table is allocated at the boot time,
-one table per a IOMMU group which is a Partitionable Endpoint (PE)
-(PE is often a PCI domain but not always).
-Newer systems (POWER8 with IODA2) have improved hardware design which allows
-to remove this limitation and have multiple IOMMU groups per a VFIO container.
+   container is supported as an IOMMU table is allocated at the boot time,
+   one table per a IOMMU group which is a Partitionable Endpoint (PE)
+   (PE is often a PCI domain but not always).
+
+   Newer systems (POWER8 with IODA2) have improved hardware design which allows
+   to remove this limitation and have multiple IOMMU groups per a VFIO
+   container.
 
 2) The hardware supports so called DMA windows - the PCI address range
-within which DMA transfer is allowed, any attempt to access address space
-out of the window leads to the whole PE isolation.
+   within which DMA transfer is allowed, any attempt to access address space
+   out of the window leads to the whole PE isolation.
 
 3) PPC64 guests are paravirtualized but not fully emulated. There is an API
-to map/unmap pages for DMA, and it normally maps 1..32 pages per call and
-currently there is no way to reduce the number of calls. In order to make things
-faster, the map/unmap handling has been implemented in real mode which provides
-an excellent performance which has limitations such as inability to do
-locked pages accounting in real time.
+   to map/unmap pages for DMA, and it normally maps 1..32 pages per call and
+   currently there is no way to reduce the number of calls. In order to make
+   things faster, the map/unmap handling has been implemented in real mode
+   which provides an excellent performance which has limitations such as
+   inability to do locked pages accounting in real time.
 
 4) According to sPAPR specification, A Partitionable Endpoint (PE) is an I/O
-subtree that can be treated as a unit for the purposes of partitioning and
-error recovery. A PE may be a single or multi-function IOA (IO Adapter), a
-function of a multi-function IOA, or multiple IOAs (possibly including switch
-and bridge structures above the multiple IOAs). PPC64 guests detect PCI errors
-and recover from them via EEH RTAS services, which works on the basis of
-additional ioctl commands.
+   subtree that can be treated as a unit for the purposes of partitioning and
+   error recovery. A PE may be a single or multi-function IOA (IO Adapter), a
+   function of a multi-function IOA, or multiple IOAs (possibly including
+   switch and bridge structures above the multiple IOAs). PPC64 guests detect
+   PCI errors and recover from them via EEH RTAS services, which works on the
+   basis of additional ioctl commands.
 
-So 4 additional ioctls have been added:
+   So 4 additional ioctls have been added:
 
-	VFIO_IOMMU_SPAPR_TCE_GET_INFO - returns the size and the start
-		of the DMA window on the PCI bus.
+	VFIO_IOMMU_SPAPR_TCE_GET_INFO
+		returns the size and the start of the DMA window on the PCI bus.
 
-	VFIO_IOMMU_ENABLE - enables the container. The locked pages accounting
+	VFIO_IOMMU_ENABLE
+		enables the container. The locked pages accounting
 		is done at this point. This lets user first to know what
 		the DMA window is and adjust rlimit before doing any real job.
 
-	VFIO_IOMMU_DISABLE - disables the container.
+	VFIO_IOMMU_DISABLE
+		disables the container.
 
-	VFIO_EEH_PE_OP - provides an API for EEH setup, error detection and recovery.
+	VFIO_EEH_PE_OP
+		provides an API for EEH setup, error detection and recovery.
 
-The code flow from the example above should be slightly changed:
+   The code flow from the example above should be slightly changed::
 
 	struct vfio_eeh_pe_op pe_op = { .argsz = sizeof(pe_op), .flags = 0 };
 
@@ -442,73 +449,73 @@
 	....
 
 5) There is v2 of SPAPR TCE IOMMU. It deprecates VFIO_IOMMU_ENABLE/
-VFIO_IOMMU_DISABLE and implements 2 new ioctls:
-VFIO_IOMMU_SPAPR_REGISTER_MEMORY and VFIO_IOMMU_SPAPR_UNREGISTER_MEMORY
-(which are unsupported in v1 IOMMU).
+   VFIO_IOMMU_DISABLE and implements 2 new ioctls:
+   VFIO_IOMMU_SPAPR_REGISTER_MEMORY and VFIO_IOMMU_SPAPR_UNREGISTER_MEMORY
+   (which are unsupported in v1 IOMMU).
 
-PPC64 paravirtualized guests generate a lot of map/unmap requests,
-and the handling of those includes pinning/unpinning pages and updating
-mm::locked_vm counter to make sure we do not exceed the rlimit.
-The v2 IOMMU splits accounting and pinning into separate operations:
+   PPC64 paravirtualized guests generate a lot of map/unmap requests,
+   and the handling of those includes pinning/unpinning pages and updating
+   mm::locked_vm counter to make sure we do not exceed the rlimit.
+   The v2 IOMMU splits accounting and pinning into separate operations:
 
-- VFIO_IOMMU_SPAPR_REGISTER_MEMORY/VFIO_IOMMU_SPAPR_UNREGISTER_MEMORY ioctls
-receive a user space address and size of the block to be pinned.
-Bisecting is not supported and VFIO_IOMMU_UNREGISTER_MEMORY is expected to
-be called with the exact address and size used for registering
-the memory block. The userspace is not expected to call these often.
-The ranges are stored in a linked list in a VFIO container.
+   - VFIO_IOMMU_SPAPR_REGISTER_MEMORY/VFIO_IOMMU_SPAPR_UNREGISTER_MEMORY ioctls
+     receive a user space address and size of the block to be pinned.
+     Bisecting is not supported and VFIO_IOMMU_UNREGISTER_MEMORY is expected to
+     be called with the exact address and size used for registering
+     the memory block. The userspace is not expected to call these often.
+     The ranges are stored in a linked list in a VFIO container.
 
-- VFIO_IOMMU_MAP_DMA/VFIO_IOMMU_UNMAP_DMA ioctls only update the actual
-IOMMU table and do not do pinning; instead these check that the userspace
-address is from pre-registered range.
+   - VFIO_IOMMU_MAP_DMA/VFIO_IOMMU_UNMAP_DMA ioctls only update the actual
+     IOMMU table and do not do pinning; instead these check that the userspace
+     address is from pre-registered range.
 
-This separation helps in optimizing DMA for guests.
+   This separation helps in optimizing DMA for guests.
 
 6) sPAPR specification allows guests to have an additional DMA window(s) on
-a PCI bus with a variable page size. Two ioctls have been added to support
-this: VFIO_IOMMU_SPAPR_TCE_CREATE and VFIO_IOMMU_SPAPR_TCE_REMOVE.
-The platform has to support the functionality or error will be returned to
-the userspace. The existing hardware supports up to 2 DMA windows, one is
-2GB long, uses 4K pages and called "default 32bit window"; the other can
-be as big as entire RAM, use different page size, it is optional - guests
-create those in run-time if the guest driver supports 64bit DMA.
+   a PCI bus with a variable page size. Two ioctls have been added to support
+   this: VFIO_IOMMU_SPAPR_TCE_CREATE and VFIO_IOMMU_SPAPR_TCE_REMOVE.
+   The platform has to support the functionality or error will be returned to
+   the userspace. The existing hardware supports up to 2 DMA windows, one is
+   2GB long, uses 4K pages and called "default 32bit window"; the other can
+   be as big as entire RAM, use different page size, it is optional - guests
+   create those in run-time if the guest driver supports 64bit DMA.
 
-VFIO_IOMMU_SPAPR_TCE_CREATE receives a page shift, a DMA window size and
-a number of TCE table levels (if a TCE table is going to be big enough and
-the kernel may not be able to allocate enough of physically contiguous memory).
-It creates a new window in the available slot and returns the bus address where
-the new window starts. Due to hardware limitation, the user space cannot choose
-the location of DMA windows.
+   VFIO_IOMMU_SPAPR_TCE_CREATE receives a page shift, a DMA window size and
+   a number of TCE table levels (if a TCE table is going to be big enough and
+   the kernel may not be able to allocate enough of physically contiguous
+   memory). It creates a new window in the available slot and returns the bus
+   address where the new window starts. Due to hardware limitation, the user
+   space cannot choose the location of DMA windows.
 
-VFIO_IOMMU_SPAPR_TCE_REMOVE receives the bus start address of the window
-and removes it.
+   VFIO_IOMMU_SPAPR_TCE_REMOVE receives the bus start address of the window
+   and removes it.
 
 -------------------------------------------------------------------------------
 
-[1] VFIO was originally an acronym for "Virtual Function I/O" in its
-initial implementation by Tom Lyon while as Cisco.  We've since
-outgrown the acronym, but it's catchy.
+.. [1] VFIO was originally an acronym for "Virtual Function I/O" in its
+   initial implementation by Tom Lyon while as Cisco.  We've since
+   outgrown the acronym, but it's catchy.
 
-[2] "safe" also depends upon a device being "well behaved".  It's
-possible for multi-function devices to have backdoors between
-functions and even for single function devices to have alternative
-access to things like PCI config space through MMIO registers.  To
-guard against the former we can include additional precautions in the
-IOMMU driver to group multi-function PCI devices together
-(iommu=group_mf).  The latter we can't prevent, but the IOMMU should
-still provide isolation.  For PCI, SR-IOV Virtual Functions are the
-best indicator of "well behaved", as these are designed for
-virtualization usage models.
+.. [2] "safe" also depends upon a device being "well behaved".  It's
+   possible for multi-function devices to have backdoors between
+   functions and even for single function devices to have alternative
+   access to things like PCI config space through MMIO registers.  To
+   guard against the former we can include additional precautions in the
+   IOMMU driver to group multi-function PCI devices together
+   (iommu=group_mf).  The latter we can't prevent, but the IOMMU should
+   still provide isolation.  For PCI, SR-IOV Virtual Functions are the
+   best indicator of "well behaved", as these are designed for
+   virtualization usage models.
 
-[3] As always there are trade-offs to virtual machine device
-assignment that are beyond the scope of VFIO.  It's expected that
-future IOMMU technologies will reduce some, but maybe not all, of
-these trade-offs.
+.. [3] As always there are trade-offs to virtual machine device
+   assignment that are beyond the scope of VFIO.  It's expected that
+   future IOMMU technologies will reduce some, but maybe not all, of
+   these trade-offs.
 
-[4] In this case the device is below a PCI bridge, so transactions
-from either function of the device are indistinguishable to the iommu:
+.. [4] In this case the device is below a PCI bridge, so transactions
+   from either function of the device are indistinguishable to the iommu::
 
--[0000:00]-+-1e.0-[06]--+-0d.0
-                        \-0d.1
+	-[0000:00]-+-1e.0-[06]--+-0d.0
+				\-0d.1
 
-00:1e.0 PCI bridge: Intel Corporation 82801 PCI Bridge (rev 90)
+	00:1e.0 PCI bridge: Intel Corporation 82801 PCI Bridge (rev 90)
diff --git a/Documentation/xillybus.txt b/Documentation/xillybus.txt
index 1660145..2446ee3 100644
--- a/Documentation/xillybus.txt
+++ b/Documentation/xillybus.txt
@@ -1,12 +1,11 @@
+==========================================
+Xillybus driver for generic FPGA interface
+==========================================
 
-               ==========================================
-               Xillybus driver for generic FPGA interface
-               ==========================================
+:Author: Eli Billauer, Xillybus Ltd. (http://xillybus.com)
+:Email:  eli.billauer@gmail.com or as advertised on Xillybus' site.
 
-Author: Eli Billauer, Xillybus Ltd. (http://xillybus.com)
-Email:  eli.billauer@gmail.com or as advertised on Xillybus' site.
-
-Contents:
+.. Contents:
 
  - Introduction
   -- Background
@@ -17,7 +16,7 @@
   -- Synchronization
   -- Seekable pipes
 
-- Internals
+ - Internals
   -- Source code organization
   -- Pipe attributes
   -- Host never reads from the FPGA
@@ -29,7 +28,7 @@
   -- The "nonempty" message (supporting poll)
 
 
-INTRODUCTION
+Introduction
 ============
 
 Background
@@ -105,7 +104,7 @@
 The data structure just mentioned should not be confused with PCI's
 configuration space or the Flattened Device Tree.
 
-USAGE
+Usage
 =====
 
 User interface
@@ -117,11 +116,11 @@
 Probing below). To communicate with the FPGA, open the device file that
 corresponds to the hardware FIFO you want to send data or receive data from,
 and use plain write() or read() calls, just like with a regular pipe. In
-particular, it makes perfect sense to go:
+particular, it makes perfect sense to go::
 
-$ cat mydata > /dev/xillybus_thisfifo
+	$ cat mydata > /dev/xillybus_thisfifo
 
-$ cat /dev/xillybus_thatfifo > hisdata
+	$ cat /dev/xillybus_thatfifo > hisdata
 
 possibly pressing CTRL-C as some stage, even though the xillybus_* pipes have
 the capability to send an EOF (but may not use it).
@@ -178,7 +177,7 @@
 read() or write() as required.
 
 
-INTERNALS
+Internals
 =========
 
 Source code organization
@@ -365,7 +364,7 @@
 (except possibly for the last) are 100% utilized this way.
 
 The "nonempty" message (supporting poll)
----------------------------------------
+----------------------------------------
 
 In order to support the "poll" method (and hence select() ), there is a small
 catch regarding the FPGA to host direction: The FPGA may have filled a DMA
diff --git a/Documentation/xz.txt b/Documentation/xz.txt
index 2cf3e26..b2220d0 100644
--- a/Documentation/xz.txt
+++ b/Documentation/xz.txt
@@ -1,121 +1,127 @@
-
+============================
 XZ data compression in Linux
 ============================
 
 Introduction
+============
 
-    XZ is a general purpose data compression format with high compression
-    ratio and relatively fast decompression. The primary compression
-    algorithm (filter) is LZMA2. Additional filters can be used to improve
-    compression ratio even further. E.g. Branch/Call/Jump (BCJ) filters
-    improve compression ratio of executable data.
+XZ is a general purpose data compression format with high compression
+ratio and relatively fast decompression. The primary compression
+algorithm (filter) is LZMA2. Additional filters can be used to improve
+compression ratio even further. E.g. Branch/Call/Jump (BCJ) filters
+improve compression ratio of executable data.
 
-    The XZ decompressor in Linux is called XZ Embedded. It supports
-    the LZMA2 filter and optionally also BCJ filters. CRC32 is supported
-    for integrity checking. The home page of XZ Embedded is at
-    <http://tukaani.org/xz/embedded.html>, where you can find the
-    latest version and also information about using the code outside
-    the Linux kernel.
+The XZ decompressor in Linux is called XZ Embedded. It supports
+the LZMA2 filter and optionally also BCJ filters. CRC32 is supported
+for integrity checking. The home page of XZ Embedded is at
+<http://tukaani.org/xz/embedded.html>, where you can find the
+latest version and also information about using the code outside
+the Linux kernel.
 
-    For userspace, XZ Utils provide a zlib-like compression library
-    and a gzip-like command line tool. XZ Utils can be downloaded from
-    <http://tukaani.org/xz/>.
+For userspace, XZ Utils provide a zlib-like compression library
+and a gzip-like command line tool. XZ Utils can be downloaded from
+<http://tukaani.org/xz/>.
 
 XZ related components in the kernel
+===================================
 
-    The xz_dec module provides XZ decompressor with single-call (buffer
-    to buffer) and multi-call (stateful) APIs. The usage of the xz_dec
-    module is documented in include/linux/xz.h.
+The xz_dec module provides XZ decompressor with single-call (buffer
+to buffer) and multi-call (stateful) APIs. The usage of the xz_dec
+module is documented in include/linux/xz.h.
 
-    The xz_dec_test module is for testing xz_dec. xz_dec_test is not
-    useful unless you are hacking the XZ decompressor. xz_dec_test
-    allocates a char device major dynamically to which one can write
-    .xz files from userspace. The decompressed output is thrown away.
-    Keep an eye on dmesg to see diagnostics printed by xz_dec_test.
-    See the xz_dec_test source code for the details.
+The xz_dec_test module is for testing xz_dec. xz_dec_test is not
+useful unless you are hacking the XZ decompressor. xz_dec_test
+allocates a char device major dynamically to which one can write
+.xz files from userspace. The decompressed output is thrown away.
+Keep an eye on dmesg to see diagnostics printed by xz_dec_test.
+See the xz_dec_test source code for the details.
 
-    For decompressing the kernel image, initramfs, and initrd, there
-    is a wrapper function in lib/decompress_unxz.c. Its API is the
-    same as in other decompress_*.c files, which is defined in
-    include/linux/decompress/generic.h.
+For decompressing the kernel image, initramfs, and initrd, there
+is a wrapper function in lib/decompress_unxz.c. Its API is the
+same as in other decompress_*.c files, which is defined in
+include/linux/decompress/generic.h.
 
-    scripts/xz_wrap.sh is a wrapper for the xz command line tool found
-    from XZ Utils. The wrapper sets compression options to values suitable
-    for compressing the kernel image.
+scripts/xz_wrap.sh is a wrapper for the xz command line tool found
+from XZ Utils. The wrapper sets compression options to values suitable
+for compressing the kernel image.
 
-    For kernel makefiles, two commands are provided for use with
-    $(call if_needed). The kernel image should be compressed with
-    $(call if_needed,xzkern) which will use a BCJ filter and a big LZMA2
-    dictionary. It will also append a four-byte trailer containing the
-    uncompressed size of the file, which is needed by the boot code.
-    Other things should be compressed with $(call if_needed,xzmisc)
-    which will use no BCJ filter and 1 MiB LZMA2 dictionary.
+For kernel makefiles, two commands are provided for use with
+$(call if_needed). The kernel image should be compressed with
+$(call if_needed,xzkern) which will use a BCJ filter and a big LZMA2
+dictionary. It will also append a four-byte trailer containing the
+uncompressed size of the file, which is needed by the boot code.
+Other things should be compressed with $(call if_needed,xzmisc)
+which will use no BCJ filter and 1 MiB LZMA2 dictionary.
 
 Notes on compression options
+============================
 
-    Since the XZ Embedded supports only streams with no integrity check or
-    CRC32, make sure that you don't use some other integrity check type
-    when encoding files that are supposed to be decoded by the kernel. With
-    liblzma, you need to use either LZMA_CHECK_NONE or LZMA_CHECK_CRC32
-    when encoding. With the xz command line tool, use --check=none or
-    --check=crc32.
+Since the XZ Embedded supports only streams with no integrity check or
+CRC32, make sure that you don't use some other integrity check type
+when encoding files that are supposed to be decoded by the kernel. With
+liblzma, you need to use either LZMA_CHECK_NONE or LZMA_CHECK_CRC32
+when encoding. With the xz command line tool, use --check=none or
+--check=crc32.
 
-    Using CRC32 is strongly recommended unless there is some other layer
-    which will verify the integrity of the uncompressed data anyway.
-    Double checking the integrity would probably be waste of CPU cycles.
-    Note that the headers will always have a CRC32 which will be validated
-    by the decoder; you can only change the integrity check type (or
-    disable it) for the actual uncompressed data.
+Using CRC32 is strongly recommended unless there is some other layer
+which will verify the integrity of the uncompressed data anyway.
+Double checking the integrity would probably be waste of CPU cycles.
+Note that the headers will always have a CRC32 which will be validated
+by the decoder; you can only change the integrity check type (or
+disable it) for the actual uncompressed data.
 
-    In userspace, LZMA2 is typically used with dictionary sizes of several
-    megabytes. The decoder needs to have the dictionary in RAM, thus big
-    dictionaries cannot be used for files that are intended to be decoded
-    by the kernel. 1 MiB is probably the maximum reasonable dictionary
-    size for in-kernel use (maybe more is OK for initramfs). The presets
-    in XZ Utils may not be optimal when creating files for the kernel,
-    so don't hesitate to use custom settings. Example:
+In userspace, LZMA2 is typically used with dictionary sizes of several
+megabytes. The decoder needs to have the dictionary in RAM, thus big
+dictionaries cannot be used for files that are intended to be decoded
+by the kernel. 1 MiB is probably the maximum reasonable dictionary
+size for in-kernel use (maybe more is OK for initramfs). The presets
+in XZ Utils may not be optimal when creating files for the kernel,
+so don't hesitate to use custom settings. Example::
 
-        xz --check=crc32 --lzma2=dict=512KiB inputfile
+	xz --check=crc32 --lzma2=dict=512KiB inputfile
 
-    An exception to above dictionary size limitation is when the decoder
-    is used in single-call mode. Decompressing the kernel itself is an
-    example of this situation. In single-call mode, the memory usage
-    doesn't depend on the dictionary size, and it is perfectly fine to
-    use a big dictionary: for maximum compression, the dictionary should
-    be at least as big as the uncompressed data itself.
+An exception to above dictionary size limitation is when the decoder
+is used in single-call mode. Decompressing the kernel itself is an
+example of this situation. In single-call mode, the memory usage
+doesn't depend on the dictionary size, and it is perfectly fine to
+use a big dictionary: for maximum compression, the dictionary should
+be at least as big as the uncompressed data itself.
 
 Future plans
+============
 
-    Creating a limited XZ encoder may be considered if people think it is
-    useful. LZMA2 is slower to compress than e.g. Deflate or LZO even at
-    the fastest settings, so it isn't clear if LZMA2 encoder is wanted
-    into the kernel.
+Creating a limited XZ encoder may be considered if people think it is
+useful. LZMA2 is slower to compress than e.g. Deflate or LZO even at
+the fastest settings, so it isn't clear if LZMA2 encoder is wanted
+into the kernel.
 
-    Support for limited random-access reading is planned for the
-    decompression code. I don't know if it could have any use in the
-    kernel, but I know that it would be useful in some embedded projects
-    outside the Linux kernel.
+Support for limited random-access reading is planned for the
+decompression code. I don't know if it could have any use in the
+kernel, but I know that it would be useful in some embedded projects
+outside the Linux kernel.
 
 Conformance to the .xz file format specification
+================================================
 
-    There are a couple of corner cases where things have been simplified
-    at expense of detecting errors as early as possible. These should not
-    matter in practice all, since they don't cause security issues. But
-    it is good to know this if testing the code e.g. with the test files
-    from XZ Utils.
+There are a couple of corner cases where things have been simplified
+at expense of detecting errors as early as possible. These should not
+matter in practice all, since they don't cause security issues. But
+it is good to know this if testing the code e.g. with the test files
+from XZ Utils.
 
 Reporting bugs
+==============
 
-    Before reporting a bug, please check that it's not fixed already
-    at upstream. See <http://tukaani.org/xz/embedded.html> to get the
-    latest code.
+Before reporting a bug, please check that it's not fixed already
+at upstream. See <http://tukaani.org/xz/embedded.html> to get the
+latest code.
 
-    Report bugs to <lasse.collin@tukaani.org> or visit #tukaani on
-    Freenode and talk to Larhzu. I don't actively read LKML or other
-    kernel-related mailing lists, so if there's something I should know,
-    you should email to me personally or use IRC.
+Report bugs to <lasse.collin@tukaani.org> or visit #tukaani on
+Freenode and talk to Larhzu. I don't actively read LKML or other
+kernel-related mailing lists, so if there's something I should know,
+you should email to me personally or use IRC.
 
-    Don't bother Igor Pavlov with questions about the XZ implementation
-    in the kernel or about XZ Utils. While these two implementations
-    include essential code that is directly based on Igor Pavlov's code,
-    these implementations aren't maintained nor supported by him.
+Don't bother Igor Pavlov with questions about the XZ implementation
+in the kernel or about XZ Utils. While these two implementations
+include essential code that is directly based on Igor Pavlov's code,
+these implementations aren't maintained nor supported by him.
diff --git a/Documentation/zorro.txt b/Documentation/zorro.txt
index d530971..664072b 100644
--- a/Documentation/zorro.txt
+++ b/Documentation/zorro.txt
@@ -1,12 +1,13 @@
-		Writing Device Drivers for Zorro Devices
-		----------------------------------------
+========================================
+Writing Device Drivers for Zorro Devices
+========================================
 
-Written by Geert Uytterhoeven <geert@linux-m68k.org>
-Last revised: September 5, 2003
+:Author: Written by Geert Uytterhoeven <geert@linux-m68k.org>
+:Last revised: September 5, 2003
 
 
-1. Introduction
----------------
+Introduction
+------------
 
 The Zorro bus is the bus used in the Amiga family of computers. Thanks to
 AutoConfig(tm), it's 100% Plug-and-Play.
@@ -20,12 +21,12 @@
     with Zorro II. The Zorro III address space lies outside the first 16 MB.
 
 
-2. Probing for Zorro Devices
-----------------------------
+Probing for Zorro Devices
+-------------------------
 
-Zorro devices are found by calling `zorro_find_device()', which returns a
-pointer to the `next' Zorro device with the specified Zorro ID. A probe loop
-for the board with Zorro ID `ZORRO_PROD_xxx' looks like:
+Zorro devices are found by calling ``zorro_find_device()``, which returns a
+pointer to the ``next`` Zorro device with the specified Zorro ID. A probe loop
+for the board with Zorro ID ``ZORRO_PROD_xxx`` looks like::
 
     struct zorro_dev *z = NULL;
 
@@ -35,8 +36,8 @@
 	...
     }
 
-`ZORRO_WILDCARD' acts as a wildcard and finds any Zorro device. If your driver
-supports different types of boards, you can use a construct like:
+``ZORRO_WILDCARD`` acts as a wildcard and finds any Zorro device. If your driver
+supports different types of boards, you can use a construct like::
 
     struct zorro_dev *z = NULL;
 
@@ -49,24 +50,24 @@
     }
 
 
-3. Zorro Resources
-------------------
+Zorro Resources
+---------------
 
 Before you can access a Zorro device's registers, you have to make sure it's
 not yet in use. This is done using the I/O memory space resource management
-functions:
+functions::
 
     request_mem_region()
     release_mem_region()
 
-Shortcuts to claim the whole device's address space are provided as well:
+Shortcuts to claim the whole device's address space are provided as well::
 
     zorro_request_device
     zorro_release_device
 
 
-4. Accessing the Zorro Address Space
-------------------------------------
+Accessing the Zorro Address Space
+---------------------------------
 
 The address regions in the Zorro device resources are Zorro bus address
 regions. Due to the identity bus-physical address mapping on the Zorro bus,
@@ -78,26 +79,26 @@
     explicitly using z_ioremap().
     
     Conversion from bus/physical Zorro II addresses to kernel virtual addresses
-    and vice versa is done using:
+    and vice versa is done using::
 
 	virt_addr = ZTWO_VADDR(bus_addr);
 	bus_addr = ZTWO_PADDR(virt_addr);
 
   - Zorro III address space must be mapped explicitly using z_ioremap() first
-    before it can be accessed:
+    before it can be accessed::
  
 	virt_addr = z_ioremap(bus_addr, size);
 	...
 	z_iounmap(virt_addr);
 
 
-5. References
--------------
+References
+----------
 
-linux/include/linux/zorro.h
-linux/include/uapi/linux/zorro.h
-linux/include/uapi/linux/zorro_ids.h
-linux/arch/m68k/include/asm/zorro.h
-linux/drivers/zorro
-/proc/bus/zorro
+#. linux/include/linux/zorro.h
+#. linux/include/uapi/linux/zorro.h
+#. linux/include/uapi/linux/zorro_ids.h
+#. linux/arch/m68k/include/asm/zorro.h
+#. linux/drivers/zorro
+#. /proc/bus/zorro