Merge branch 'fixes' into devel

16 files changed, 120 insertions, 240 deletions

diff --git a/Documentation/DocBook/mtdnand.tmpl b/Documentation/DocBook/mtdnand.tmpl
index f508a8a27fea..5e7d84b48505 100644
--- a/Documentation/DocBook/mtdnand.tmpl
+++ b/Documentation/DocBook/mtdnand.tmpl
@@ -174,7 +174,7 @@
                 </para>
                 <programlisting>
 static struct mtd_info *board_mtd;
-static unsigned long baseaddr;
+static void __iomem *baseaddr;
                 </programlisting>
                 <para>
                         Static example
@@ -182,7 +182,7 @@ static unsigned long baseaddr;
                 <programlisting>
 static struct mtd_info board_mtd;
 static struct nand_chip board_chip;
-static unsigned long baseaddr;
+static void __iomem *baseaddr;
                 </programlisting>
         </sect1>
         <sect1 id="Partition_defines">
@@ -283,8 +283,8 @@ int __init board_init (void)
         }
 
         /* map physical address */
-        baseaddr = (unsigned long)ioremap(CHIP_PHYSICAL_ADDRESS, 1024);
-        if(!baseaddr){
+        baseaddr = ioremap(CHIP_PHYSICAL_ADDRESS, 1024);
+        if (!baseaddr) {
                 printk("Ioremap to access NAND chip failed\n");
                 err = -EIO;
                 goto out_mtd;
@@ -316,7 +316,7 @@ int __init board_init (void)
         goto out;
 
 out_ior:
-        iounmap((void *)baseaddr);
+        iounmap(baseaddr);
 out_mtd:
         kfree (board_mtd);
 out:
@@ -341,7 +341,7 @@ static void __exit board_cleanup (void)
         nand_release (board_mtd);
 
         /* unmap physical address */
-        iounmap((void *)baseaddr);
+        iounmap(baseaddr);
         
         /* Free the MTD device structure */
         kfree (board_mtd);
diff --git a/Documentation/IO-mapping.txt b/Documentation/IO-mapping.txt
index 78a440695e11..1b5aa10df845 100644
--- a/Documentation/IO-mapping.txt
+++ b/Documentation/IO-mapping.txt
@@ -157,7 +157,7 @@ For such memory, you can do things like
          * access only the 640k-1MB area, so anything else
          * has to be remapped.
          */
-        char * baseptr = ioremap(0xFC000000, 1024*1024);
+        void __iomem *baseptr = ioremap(0xFC000000, 1024*1024);
 
         /* write a 'A' to the offset 10 of the area */
         writeb('A',baseptr+10);
diff --git a/Documentation/DMA-mapping.txt b/Documentation/PCI/PCI-DMA-mapping.txt
index ecad88d9fe59..ecad88d9fe59 100644
--- a/Documentation/DMA-mapping.txt
+++ b/Documentation/PCI/PCI-DMA-mapping.txt
diff --git a/Documentation/block/00-INDEX b/Documentation/block/00-INDEX
index 961a0513f8c3..a406286f6f3e 100644
--- a/Documentation/block/00-INDEX
+++ b/Documentation/block/00-INDEX
@@ -1,7 +1,5 @@
 00-INDEX
         - This file
-as-iosched.txt
-        - Anticipatory IO scheduler
 barrier.txt
         - I/O Barriers
 biodoc.txt
diff --git a/Documentation/block/as-iosched.txt b/Documentation/block/as-iosched.txt
deleted file mode 100644
index 738b72be128e..000000000000
--- a/Documentation/block/as-iosched.txt
+++ /dev/null
@@ -1,172 +0,0 @@
-Anticipatory IO scheduler
--------------------------
-Nick Piggin <piggin@cyberone.com.au>    13 Sep 2003
-
-Attention! Database servers, especially those using "TCQ" disks should
-investigate performance with the 'deadline' IO scheduler. Any system with high
-disk performance requirements should do so, in fact.
-
-If you see unusual performance characteristics of your disk systems, or you
-see big performance regressions versus the deadline scheduler, please email
-me. Database users don't bother unless you're willing to test a lot of patches
-from me ;) its a known issue.
-
-Also, users with hardware RAID controllers, doing striping, may find
-highly variable performance results with using the as-iosched. The
-as-iosched anticipatory implementation is based on the notion that a disk
-device has only one physical seeking head.  A striped RAID controller
-actually has a head for each physical device in the logical RAID device.
-
-However, setting the antic_expire (see tunable parameters below) produces
-very similar behavior to the deadline IO scheduler.
-
-Selecting IO schedulers
------------------------
-Refer to Documentation/block/switching-sched.txt for information on
-selecting an io scheduler on a per-device basis.
-
-Anticipatory IO scheduler Policies
-----------------------------------
-The as-iosched implementation implements several layers of policies
-to determine when an IO request is dispatched to the disk controller.
-Here are the policies outlined, in order of application.
-
-1. one-way Elevator algorithm.
-
-The elevator algorithm is similar to that used in deadline scheduler, with
-the addition that it allows limited backward movement of the elevator
-(i.e. seeks backwards).  A seek backwards can occur when choosing between
-two IO requests where one is behind the elevator's current position, and
-the other is in front of the elevator's position. If the seek distance to
-the request in back of the elevator is less than half the seek distance to
-the request in front of the elevator, then the request in back can be chosen.
-Backward seeks are also limited to a maximum of MAXBACK (1024*1024) sectors.
-This favors forward movement of the elevator, while allowing opportunistic
-"short" backward seeks.
-
-2. FIFO expiration times for reads and for writes.
-
-This is again very similar to the deadline IO scheduler.  The expiration
-times for requests on these lists is tunable using the parameters read_expire
-and write_expire discussed below.  When a read or a write expires in this way,
-the IO scheduler will interrupt its current elevator sweep or read anticipation
-to service the expired request.
-
-3. Read and write request batching
-
-A batch is a collection of read requests or a collection of write
-requests.  The as scheduler alternates dispatching read and write batches
-to the driver.  In the case a read batch, the scheduler submits read
-requests to the driver as long as there are read requests to submit, and
-the read batch time limit has not been exceeded (read_batch_expire).
-The read batch time limit begins counting down only when there are
-competing write requests pending.
-
-In the case of a write batch, the scheduler submits write requests to
-the driver as long as there are write requests available, and the
-write batch time limit has not been exceeded (write_batch_expire).
-However, the length of write batches will be gradually shortened
-when read batches frequently exceed their time limit.
-
-When changing between batch types, the scheduler waits for all requests
-from the previous batch to complete before scheduling requests for the
-next batch.
-
-The read and write fifo expiration times described in policy 2 above
-are checked only when in scheduling IO of a batch for the corresponding
-(read/write) type.  So for example, the read FIFO timeout values are
-tested only during read batches.  Likewise, the write FIFO timeout
-values are tested only during write batches.  For this reason,
-it is generally not recommended for the read batch time
-to be longer than the write expiration time, nor for the write batch
-time to exceed the read expiration time (see tunable parameters below).
-
-When the IO scheduler changes from a read to a write batch,
-it begins the elevator from the request that is on the head of the
-write expiration FIFO.  Likewise, when changing from a write batch to
-a read batch, scheduler begins the elevator from the first entry
-on the read expiration FIFO.
-
-4. Read anticipation.
-
-Read anticipation occurs only when scheduling a read batch.
-This implementation of read anticipation allows only one read request
-to be dispatched to the disk controller at a time.  In
-contrast, many write requests may be dispatched to the disk controller
-at a time during a write batch.  It is this characteristic that can make
-the anticipatory scheduler perform anomalously with controllers supporting
-TCQ, or with hardware striped RAID devices. Setting the antic_expire
-queue parameter (see below) to zero disables this behavior, and the 
-anticipatory scheduler behaves essentially like the deadline scheduler.
-
-When read anticipation is enabled (antic_expire is not zero), reads
-are dispatched to the disk controller one at a time.
-At the end of each read request, the IO scheduler examines its next
-candidate read request from its sorted read list.  If that next request
-is from the same process as the request that just completed,
-or if the next request in the queue is "very close" to the
-just completed request, it is dispatched immediately.  Otherwise,
-statistics (average think time, average seek distance) on the process
-that submitted the just completed request are examined.  If it seems
-likely that that process will submit another request soon, and that
-request is likely to be near the just completed request, then the IO
-scheduler will stop dispatching more read requests for up to (antic_expire)
-milliseconds, hoping that process will submit a new request near the one
-that just completed.  If such a request is made, then it is dispatched
-immediately.  If the antic_expire wait time expires, then the IO scheduler
-will dispatch the next read request from the sorted read queue.
-
-To decide whether an anticipatory wait is worthwhile, the scheduler
-maintains statistics for each process that can be used to compute
-mean "think time" (the time between read requests), and mean seek
-distance for that process.  One observation is that these statistics
-are associated with each process, but those statistics are not associated
-with a specific IO device.  So for example, if a process is doing IO
-on several file systems on separate devices, the statistics will be
-a combination of IO behavior from all those devices.
-
-
-Tuning the anticipatory IO scheduler
-------------------------------------
-When using 'as', the anticipatory IO scheduler there are 5 parameters under
-/sys/block/*/queue/iosched/. All are units of milliseconds.
-
-The parameters are:
-* read_expire
-    Controls how long until a read request becomes "expired". It also controls the
-    interval between which expired requests are served, so set to 50, a request
-    might take anywhere < 100ms to be serviced _if_ it is the next on the
-    expired list. Obviously request expiration strategies won't make the disk
-    go faster. The result basically equates to the timeslice a single reader
-    gets in the presence of other IO. 100*((seek time / read_expire) + 1) is
-    very roughly the % streaming read efficiency your disk should get with
-    multiple readers.
-
-* read_batch_expire
-    Controls how much time a batch of reads is given before pending writes are
-    served. A higher value is more efficient. This might be set below read_expire
-    if writes are to be given higher priority than reads, but reads are to be
-    as efficient as possible when there are no writes. Generally though, it
-    should be some multiple of read_expire.
-
-* write_expire, and
-* write_batch_expire are equivalent to the above, for writes.
-
-* antic_expire
-    Controls the maximum amount of time we can anticipate a good read (one
-    with a short seek distance from the most recently completed request) before
-    giving up. Many other factors may cause anticipation to be stopped early,
-    or some processes will not be "anticipated" at all. Should be a bit higher
-    for big seek time devices though not a linear correspondence - most
-    processes have only a few ms thinktime.
-
-In addition to the tunables above there is a read-only file named est_time
-which, when read, will show:
-
-    - The probability of a task exiting without a cooperating task
-      submitting an anticipated IO.
-
-    - The current mean think time.
-
-    - The seek distance used to determine if an incoming IO is better.
-
diff --git a/Documentation/block/biodoc.txt b/Documentation/block/biodoc.txt
index 8d2158a1c6aa..6fab97ea7e6b 100644
--- a/Documentation/block/biodoc.txt
+++ b/Documentation/block/biodoc.txt
@@ -186,7 +186,7 @@ a virtual address mapping (unlike the earlier scheme of virtual address
 do not have a corresponding kernel virtual address space mapping) and
 low-memory pages.
 
-Note: Please refer to Documentation/DMA-mapping.txt for a discussion
+Note: Please refer to Documentation/PCI/PCI-DMA-mapping.txt for a discussion
 on PCI high mem DMA aspects and mapping of scatter gather lists, and support
 for 64 bit PCI.
 
diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
index af6885c3c821..e1def1786e50 100644
--- a/Documentation/filesystems/ext4.txt
+++ b/Documentation/filesystems/ext4.txt
@@ -196,7 +196,7 @@ nobarrier		This also requires an IO stack which can support
                         also be used to enable or disable barriers, for
                         consistency with other ext4 mount options.
 
-inode_readahead=n       This tuning parameter controls the maximum
+inode_readahead_blks=n  This tuning parameter controls the maximum
                         number of inode table blocks that ext4's inode
                         table readahead algorithm will pre-read into
                         the buffer cache.  The default value is 32 blocks.
diff --git a/Documentation/filesystems/nilfs2.txt b/Documentation/filesystems/nilfs2.txt
index 4949fcaa6b6a..839efd8a8a8c 100644
--- a/Documentation/filesystems/nilfs2.txt
+++ b/Documentation/filesystems/nilfs2.txt
@@ -28,7 +28,7 @@ described in the man pages included in the package.
 Project web page:    http://www.nilfs.org/en/
 Download page:       http://www.nilfs.org/en/download.html
 Git tree web page:   http://www.nilfs.org/git/
-NILFS mailing lists: http://www.nilfs.org/mailman/listinfo/users
+List info:           http://vger.kernel.org/vger-lists.html#linux-nilfs
 
 Caveats
 =======
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 5ba4d9dff113..736d45602886 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -240,7 +240,7 @@ and is between 256 and 4096 characters. It is defined in the file
 
         acpi_sleep=     [HW,ACPI] Sleep options
                         Format: { s3_bios, s3_mode, s3_beep, s4_nohwsig,
-                                  old_ordering, s4_nonvs }
+                                  old_ordering, s4_nonvs, sci_force_enable }
                         See Documentation/power/video.txt for information on
                         s3_bios and s3_mode.
                         s3_beep is for debugging; it makes the PC's speaker beep
@@ -253,6 +253,9 @@ and is between 256 and 4096 characters. It is defined in the file
                         of _PTS is used by default).
                         s4_nonvs prevents the kernel from saving/restoring the
                         ACPI NVS memory during hibernation.
+                        sci_force_enable causes the kernel to set SCI_EN directly
+                        on resume from S1/S3 (which is against the ACPI spec,
+                        but some broken systems don't work without it).
 
         acpi_use_timer_override [HW,ACPI]
                         Use timer override. For some broken Nvidia NF5 boards
diff --git a/Documentation/kvm/api.txt b/Documentation/kvm/api.txt
index e1a114161027..2811e452f756 100644
--- a/Documentation/kvm/api.txt
+++ b/Documentation/kvm/api.txt
@@ -685,7 +685,7 @@ struct kvm_vcpu_events {
                 __u8 pad;
         } nmi;
         __u32 sipi_vector;
-        __u32 flags;   /* must be zero */
+        __u32 flags;
 };
 
 4.30 KVM_SET_VCPU_EVENTS
@@ -701,6 +701,14 @@ vcpu.
 
 See KVM_GET_VCPU_EVENTS for the data structure.
 
+Fields that may be modified asynchronously by running VCPUs can be excluded
+from the update. These fields are nmi.pending and sipi_vector. Keep the
+corresponding bits in the flags field cleared to suppress overwriting the
+current in-kernel state. The bits are:
+
+KVM_VCPUEVENT_VALID_NMI_PENDING - transfer nmi.pending to the kernel
+KVM_VCPUEVENT_VALID_SIPI_VECTOR - transfer sipi_vector
+
 
 5. The kvm_run structure
 
diff --git a/Documentation/laptops/thinkpad-acpi.txt b/Documentation/laptops/thinkpad-acpi.txt
index 169091f75e6d..75afa1229fd7 100644
--- a/Documentation/laptops/thinkpad-acpi.txt
+++ b/Documentation/laptops/thinkpad-acpi.txt
@@ -1092,8 +1092,8 @@ WARNING:
     its level up and down at every change.
 
 
-Volume control
---------------
+Volume control (Console Audio control)
+--------------------------------------
 
 procfs: /proc/acpi/ibm/volume
 ALSA: "ThinkPad Console Audio Control", default ID: "ThinkPadEC"
@@ -1110,9 +1110,53 @@ the desktop environment to just provide on-screen-display feedback.
 Software volume control should be done only in the main AC97/HDA
 mixer.
 
-This feature allows volume control on ThinkPad models with a digital
-volume knob (when available, not all models have it), as well as
-mute/unmute control.  The available commands are:
+
+About the ThinkPad Console Audio control:
+
+ThinkPads have a built-in amplifier and muting circuit that drives the
+console headphone and speakers.  This circuit is after the main AC97
+or HDA mixer in the audio path, and under exclusive control of the
+firmware.
+
+ThinkPads have three special hotkeys to interact with the console
+audio control: volume up, volume down and mute.
+
+It is worth noting that the normal way the mute function works (on
+ThinkPads that do not have a "mute LED") is:
+
+1. Press mute to mute.  It will *always* mute, you can press it as
+   many times as you want, and the sound will remain mute.
+
+2. Press either volume key to unmute the ThinkPad (it will _not_
+   change the volume, it will just unmute).
+
+This is a very superior design when compared to the cheap software-only
+mute-toggle solution found on normal consumer laptops:  you can be
+absolutely sure the ThinkPad will not make noise if you press the mute
+button, no matter the previous state.
+
+The IBM ThinkPads, and the earlier Lenovo ThinkPads have variable-gain
+amplifiers driving the speakers and headphone output, and the firmware
+also handles volume control for the headphone and speakers on these
+ThinkPads without any help from the operating system (this volume
+control stage exists after the main AC97 or HDA mixer in the audio
+path).
+
+The newer Lenovo models only have firmware mute control, and depend on
+the main HDA mixer to do volume control (which is done by the operating
+system).  In this case, the volume keys are filtered out for unmute
+key press (there are some firmware bugs in this area) and delivered as
+normal key presses to the operating system (thinkpad-acpi is not
+involved).
+
+
+The ThinkPad-ACPI volume control:
+
+The preferred way to interact with the Console Audio control is the
+ALSA interface.
+
+The legacy procfs interface allows one to read the current state,
+and if volume control is enabled, accepts the following commands:
 
         echo up   >/proc/acpi/ibm/volume
         echo down >/proc/acpi/ibm/volume
@@ -1121,12 +1165,10 @@ mute/unmute control.  The available commands are:
         echo 'level <level>' >/proc/acpi/ibm/volume
 
 The <level> number range is 0 to 14 although not all of them may be
-distinct. The unmute the volume after the mute command, use either the
+distinct. To unmute the volume after the mute command, use either the
 up or down command (the level command will not unmute the volume), or
 the unmute command.
 
-The current volume level and mute state is shown in the file.
-
 You can use the volume_capabilities parameter to tell the driver
 whether your thinkpad has volume control or mute-only control:
 volume_capabilities=1 for mixers with mute and volume control,
diff --git a/Documentation/sound/alsa/Procfile.txt b/Documentation/sound/alsa/Procfile.txt
index 719a819f8cc2..07301de12cc4 100644
--- a/Documentation/sound/alsa/Procfile.txt
+++ b/Documentation/sound/alsa/Procfile.txt
@@ -95,7 +95,7 @@ card*/pcm*/xrun_debug
         It takes an integer value, can be changed by writing to this
         file, such as
 
-                 # cat 5 > /proc/asound/card0/pcm0p/xrun_debug
+                 # echo 5 > /proc/asound/card0/pcm0p/xrun_debug
 
         The value consists of the following bit flags:
           bit 0 = Enable XRUN/jiffies debug messages
diff --git a/Documentation/trace/ftrace-design.txt b/Documentation/trace/ftrace-design.txt
index 641a1ef2a7ff..239f14b2b55a 100644
--- a/Documentation/trace/ftrace-design.txt
+++ b/Documentation/trace/ftrace-design.txt
@@ -53,14 +53,14 @@ size of the mcount call that is embedded in the function).
 For example, if the function foo() calls bar(), when the bar() function calls
 mcount(), the arguments mcount() will pass to the tracer are:
         "frompc" - the address bar() will use to return to foo()
-        "selfpc" - the address bar() (with _mcount() size adjustment)
+        "selfpc" - the address bar() (with mcount() size adjustment)
 
 Also keep in mind that this mcount function will be called *a lot*, so
 optimizing for the default case of no tracer will help the smooth running of
 your system when tracing is disabled.  So the start of the mcount function is
-typically the bare min with checking things before returning.  That also means
-the code flow should usually kept linear (i.e. no branching in the nop case).
-This is of course an optimization and not a hard requirement.
+typically the bare minimum with checking things before returning.  That also
+means the code flow should usually be kept linear (i.e. no branching in the nop
+case).  This is of course an optimization and not a hard requirement.
 
 Here is some pseudo code that should help (these functions should actually be
 implemented in assembly):
@@ -131,10 +131,10 @@ some functions to save (hijack) and restore the return address.
 
 The mcount function should check the function pointers ftrace_graph_return
 (compare to ftrace_stub) and ftrace_graph_entry (compare to
-ftrace_graph_entry_stub).  If either of those are not set to the relevant stub
+ftrace_graph_entry_stub).  If either of those is not set to the relevant stub
 function, call the arch-specific function ftrace_graph_caller which in turn
 calls the arch-specific function prepare_ftrace_return.  Neither of these
-function names are strictly required, but you should use them anyways to stay
+function names is strictly required, but you should use them anyway to stay
 consistent across the architecture ports -- easier to compare & contrast
 things.
 
@@ -144,7 +144,7 @@ but the first argument should be a pointer to the "frompc".  Typically this is
 located on the stack.  This allows the function to hijack the return address
 temporarily to have it point to the arch-specific function return_to_handler.
 That function will simply call the common ftrace_return_to_handler function and
-that will return the original return address with which, you can return to the
+that will return the original return address with which you can return to the
 original call site.
 
 Here is the updated mcount pseudo code:
diff --git a/Documentation/trace/mmiotrace.txt b/Documentation/trace/mmiotrace.txt
index 162effbfbdec..664e7386d89e 100644
--- a/Documentation/trace/mmiotrace.txt
+++ b/Documentation/trace/mmiotrace.txt
@@ -44,7 +44,8 @@ Check for lost events.
 Usage
 -----
 
-Make sure debugfs is mounted to /sys/kernel/debug. If not, (requires root privileges)
+Make sure debugfs is mounted to /sys/kernel/debug.
+If not (requires root privileges):
 $ mount -t debugfs debugfs /sys/kernel/debug
 
 Check that the driver you are about to trace is not loaded.
@@ -91,7 +92,7 @@ $ dmesg > dmesg.txt
 $ tar zcf pciid-nick-mmiotrace.tar.gz mydump.txt lspci.txt dmesg.txt
 and then send the .tar.gz file. The trace compresses considerably. Replace
 "pciid" and "nick" with the PCI ID or model name of your piece of hardware
-under investigation and your nick name.
+under investigation and your nickname.
 
 
 How Mmiotrace Works
@@ -100,7 +101,7 @@ How Mmiotrace Works
 Access to hardware IO-memory is gained by mapping addresses from PCI bus by
 calling one of the ioremap_*() functions. Mmiotrace is hooked into the
 __ioremap() function and gets called whenever a mapping is created. Mapping is
-an event that is recorded into the trace log. Note, that ISA range mappings
+an event that is recorded into the trace log. Note that ISA range mappings
 are not caught, since the mapping always exists and is returned directly.
 
 MMIO accesses are recorded via page faults. Just before __ioremap() returns,
@@ -122,11 +123,11 @@ Trace Log Format
 ----------------
 
 The raw log is text and easily filtered with e.g. grep and awk. One record is
-one line in the log. A record starts with a keyword, followed by keyword
-dependant arguments. Arguments are separated by a space, or continue until the
+one line in the log. A record starts with a keyword, followed by keyword-
+dependent arguments. Arguments are separated by a space, or continue until the
 end of line. The format for version 20070824 is as follows:
 
-Explanation     Keyword Space separated arguments
+Explanation     Keyword Space-separated arguments
 ---------------------------------------------------------------------------
 
 read event      R       width, timestamp, map id, physical, value, PC, PID
@@ -136,7 +137,7 @@ iounmap event	UNMAP	timestamp, map id, PC, PID
 marker          MARK    timestamp, text
 version         VERSION the string "20070824"
 info for reader LSPCI   one line from lspci -v
-PCI address map PCIDEV  space separated /proc/bus/pci/devices data
+PCI address map PCIDEV  space-separated /proc/bus/pci/devices data
 unk. opcode     UNKNOWN timestamp, map id, physical, data, PC, PID
 
 Timestamp is in seconds with decimals. Physical is a PCI bus address, virtual
diff --git a/Documentation/trace/tracepoint-analysis.txt b/Documentation/trace/tracepoint-analysis.txt
index 5eb4e487e667..87bee3c129ba 100644
--- a/Documentation/trace/tracepoint-analysis.txt
+++ b/Documentation/trace/tracepoint-analysis.txt
@@ -10,8 +10,8 @@ Tracepoints (see Documentation/trace/tracepoints.txt) can be used without
 creating custom kernel modules to register probe functions using the event
 tracing infrastructure.
 
-Simplistically, tracepoints will represent an important event that when can
-be taken in conjunction with other tracepoints to build a "Big Picture" of
+Simplistically, tracepoints represent important events that can be
+taken in conjunction with other tracepoints to build a "Big Picture" of
 what is going on within the system. There are a large number of methods for
 gathering and interpreting these events. Lacking any current Best Practises,
 this document describes some of the methods that can be used.
@@ -33,12 +33,12 @@ calling
 
 will give a fair indication of the number of events available.
 
-2.2 PCL
+2.2 PCL (Performance Counters for Linux)
 -------
 
-Discovery and enumeration of all counters and events, including tracepoints
+Discovery and enumeration of all counters and events, including tracepoints,
 are available with the perf tool. Getting a list of available events is a
-simple case of
+simple case of:
 
   $ perf list 2>&1 | grep Tracepoint
   ext4:ext4_free_inode                     [Tracepoint event]
@@ -49,19 +49,19 @@ simple case of
   [ .... remaining output snipped .... ]
 
 
-2. Enabling Events
+3. Enabling Events
 ==================
 
-2.1 System-Wide Event Enabling
+3.1 System-Wide Event Enabling
 ------------------------------
 
 See Documentation/trace/events.txt for a proper description on how events
 can be enabled system-wide. A short example of enabling all events related
-to page allocation would look something like
+to page allocation would look something like:
 
   $ for i in `find /sys/kernel/debug/tracing/events -name "enable" | grep mm_`; do echo 1 > $i; done
 
-2.2 System-Wide Event Enabling with SystemTap
+3.2 System-Wide Event Enabling with SystemTap
 ---------------------------------------------
 
 In SystemTap, tracepoints are accessible using the kernel.trace() function
@@ -86,7 +86,7 @@ were allocating the pages.
           print_count()
   }
 
-2.3 System-Wide Event Enabling with PCL
+3.3 System-Wide Event Enabling with PCL
 ---------------------------------------
 
 By specifying the -a switch and analysing sleep, the system-wide events
@@ -107,16 +107,16 @@ for a duration of time can be examined.
 Similarly, one could execute a shell and exit it as desired to get a report
 at that point.
 
-2.4 Local Event Enabling
+3.4 Local Event Enabling
 ------------------------
 
 Documentation/trace/ftrace.txt describes how to enable events on a per-thread
 basis using set_ftrace_pid.
 
-2.5 Local Event Enablement with PCL
+3.5 Local Event Enablement with PCL
 -----------------------------------
 
-Events can be activate and tracked for the duration of a process on a local
+Events can be activated and tracked for the duration of a process on a local
 basis using PCL such as follows.
 
   $ perf stat -e kmem:mm_page_alloc -e kmem:mm_page_free_direct \
@@ -131,18 +131,18 @@ basis using PCL such as follows.
 
     0.973913387  seconds time elapsed
 
-3. Event Filtering
+4. Event Filtering
 ==================
 
 Documentation/trace/ftrace.txt covers in-depth how to filter events in
 ftrace.  Obviously using grep and awk of trace_pipe is an option as well
 as any script reading trace_pipe.
 
-4. Analysing Event Variances with PCL
+5. Analysing Event Variances with PCL
 =====================================
 
 Any workload can exhibit variances between runs and it can be important
-to know what the standard deviation in. By and large, this is left to the
+to know what the standard deviation is. By and large, this is left to the
 performance analyst to do it by hand. In the event that the discrete event
 occurrences are useful to the performance analyst, then perf can be used.
 
@@ -166,7 +166,7 @@ In the event that some higher-level event is required that depends on some
 aggregation of discrete events, then a script would need to be developed.
 
 Using --repeat, it is also possible to view how events are fluctuating over
-time on a system wide basis using -a and sleep.
+time on a system-wide basis using -a and sleep.
 
   $ perf stat -e kmem:mm_page_alloc -e kmem:mm_page_free_direct \
                 -e kmem:mm_pagevec_free \
@@ -180,7 +180,7 @@ time on a system wide basis using -a and sleep.
 
     1.002251757  seconds time elapsed   ( +-   0.005% )
 
-5. Higher-Level Analysis with Helper Scripts
+6. Higher-Level Analysis with Helper Scripts
 ============================================
 
 When events are enabled the events that are triggering can be read from
@@ -190,11 +190,11 @@ be gathered on-line as appropriate. Examples of post-processing might include
 
   o Reading information from /proc for the PID that triggered the event
   o Deriving a higher-level event from a series of lower-level events.
-  o Calculate latencies between two events
+  o Calculating latencies between two events
 
 Documentation/trace/postprocess/trace-pagealloc-postprocess.pl is an example
 script that can read trace_pipe from STDIN or a copy of a trace. When used
-on-line, it can be interrupted once to generate a report without existing
+on-line, it can be interrupted once to generate a report without exiting
 and twice to exit.
 
 Simplistically, the script just reads STDIN and counts up events but it
@@ -212,12 +212,12 @@ also can do more such as
     processes, the parent process responsible for creating all the helpers
     can be identified
 
-6. Lower-Level Analysis with PCL
+7. Lower-Level Analysis with PCL
 ================================
 
-There may also be a requirement to identify what functions with a program
+There may also be a requirement to identify what functions within a program
 were generating events within the kernel. To begin this sort of analysis, the
-data must be recorded. At the time of writing, this required root
+data must be recorded. At the time of writing, this required root:
 
   $ perf record -c 1 \
         -e kmem:mm_page_alloc -e kmem:mm_page_free_direct \
@@ -253,11 +253,11 @@ perf report.
   # (For more details, try: perf report --sort comm,dso,symbol)
   #
 
-According to this, the vast majority of events occured triggered on events
-within the VDSO. With simple binaries, this will often be the case so lets
+According to this, the vast majority of events triggered on events
+within the VDSO. With simple binaries, this will often be the case so let's
 take a slightly different example. In the course of writing this, it was
-noticed that X was generating an insane amount of page allocations so lets look
-at it
+noticed that X was generating an insane amount of page allocations so let's look
+at it:
 
   $ perf record -c 1 -f \
                 -e kmem:mm_page_alloc -e kmem:mm_page_free_direct \
@@ -280,8 +280,8 @@ This was interrupted after a few seconds and
   # (For more details, try: perf report --sort comm,dso,symbol)
   #
 
-So, almost half of the events are occuring in a library. To get an idea which
-symbol.
+So, almost half of the events are occurring in a library. To get an idea which
+symbol:
 
   $ perf report --sort comm,dso,symbol
   # Samples: 27666
@@ -297,7 +297,7 @@ symbol.
        0.01%     Xorg  /opt/gfx-test/lib/libpixman-1.so.0.13.1  [.] get_fast_path
        0.00%     Xorg  [kernel]                                 [k] ftrace_trace_userstack
 
-To see where within the function pixmanFillsse2 things are going wrong
+To see where within the function pixmanFillsse2 things are going wrong:
 
   $ perf annotate pixmanFillsse2
   [ ... ]
diff --git a/Documentation/vgaarbiter.txt b/Documentation/vgaarbiter.txt
index 987f9b0a5ece..43a9b0694fdd 100644
--- a/Documentation/vgaarbiter.txt
+++ b/Documentation/vgaarbiter.txt
@@ -103,7 +103,7 @@ I.2 libpciaccess
 ----------------
 
 To use the vga arbiter char device it was implemented an API inside the
-libpciaccess library. One fieldd was added to struct pci_device (each device
+libpciaccess library. One field was added to struct pci_device (each device
 on the system):
 
     /* the type of resource decoded by the device */