22 files changed, 428 insertions, 86 deletions

diff --git a/Documentation/SubmittingPatches b/Documentation/SubmittingPatches
index 0a523c9a5ff4..482c74947de0 100644
--- a/Documentation/SubmittingPatches
+++ b/Documentation/SubmittingPatches
@@ -794,6 +794,7 @@ Greg Kroah-Hartman, "How to piss off a kernel subsystem maintainer".
   <http://www.kroah.com/log/linux/maintainer-03.html>
   <http://www.kroah.com/log/linux/maintainer-04.html>
   <http://www.kroah.com/log/linux/maintainer-05.html>
+  <http://www.kroah.com/log/linux/maintainer-06.html>
 
 NO!!!! No more huge patch bombs to linux-kernel@vger.kernel.org people!
   <https://lkml.org/lkml/2005/7/11/336>
diff --git a/Documentation/devicetree/bindings/input/atmel,maxtouch.txt b/Documentation/devicetree/bindings/input/atmel,maxtouch.txt
index baef432e8369..0ac23f2ed104 100644
--- a/Documentation/devicetree/bindings/input/atmel,maxtouch.txt
+++ b/Documentation/devicetree/bindings/input/atmel,maxtouch.txt
@@ -15,6 +15,17 @@ Optional properties for main touchpad device:
     keycode generated by each GPIO. Linux keycodes are defined in
     <dt-bindings/input/input.h>.
 
+- linux,gpio-keymap: When enabled, the SPT_GPIOPWN_T19 object sends messages
+    on GPIO bit changes. An array of up to 8 entries can be provided
+    indicating the Linux keycode mapped to each bit of the status byte,
+    starting at the LSB. Linux keycodes are defined in
+    <dt-bindings/input/input.h>.
+
+    Note: the numbering of the GPIOs and the bit they start at varies between
+    maXTouch devices. You must either refer to the documentation, or
+    experiment to determine which bit corresponds to which input. Use
+    KEY_RESERVED for unused padding values.
+
 Example:
 
         touch@4b {
diff --git a/Documentation/devicetree/bindings/mfd/tc3589x.txt b/Documentation/devicetree/bindings/mfd/tc3589x.txt
new file mode 100644
index 000000000000..6fcedba46ae9
--- /dev/null
+++ b/Documentation/devicetree/bindings/mfd/tc3589x.txt
@@ -0,0 +1,107 @@
+* Toshiba TC3589x multi-purpose expander
+
+The Toshiba TC3589x series are I2C-based MFD devices which may expose the
+following built-in devices: gpio, keypad, rotator (vibrator), PWM (for
+e.g. LEDs or vibrators) The included models are:
+
+- TC35890
+- TC35892
+- TC35893
+- TC35894
+- TC35895
+- TC35896
+
+Required properties:
+ - compatible : must be "toshiba,tc35890", "toshiba,tc35892", "toshiba,tc35893",
+   "toshiba,tc35894", "toshiba,tc35895" or "toshiba,tc35896"
+ - reg : I2C address of the device
+ - interrupt-parent : specifies which IRQ controller we're connected to
+ - interrupts : the interrupt on the parent the controller is connected to
+ - interrupt-controller : marks the device node as an interrupt controller
+ - #interrupt-cells : should be <1>, the first cell is the IRQ offset on this
+   TC3589x interrupt controller.
+
+Optional nodes:
+
+- GPIO
+  This GPIO module inside the TC3589x has 24 (TC35890, TC35892) or 20
+  (other models) GPIO lines.
+ - compatible : must be "toshiba,tc3589x-gpio"
+ - interrupts : interrupt on the parent, which must be the tc3589x MFD device
+ - interrupt-controller : marks the device node as an interrupt controller
+ - #interrupt-cells : should be <2>, the first cell is the IRQ offset on this
+   TC3589x GPIO interrupt controller, the second cell is the interrupt flags
+   in accordance with <dt-bindings/interrupt-controller/irq.h>. The following
+   flags are valid:
+   - IRQ_TYPE_LEVEL_LOW
+   - IRQ_TYPE_LEVEL_HIGH
+   - IRQ_TYPE_EDGE_RISING
+   - IRQ_TYPE_EDGE_FALLING
+   - IRQ_TYPE_EDGE_BOTH
+ - gpio-controller : marks the device node as a GPIO controller
+ - #gpio-cells : should be <2>, the first cell is the GPIO offset on this
+   GPIO controller, the second cell is the flags.
+
+- Keypad
+  This keypad is the same on all variants, supporting up to 96 different
+  keys. The linux-specific properties are modeled on those already existing
+  in other input drivers.
+ - compatible : must be "toshiba,tc3589x-keypad"
+ - debounce-delay-ms : debounce interval in milliseconds
+ - keypad,num-rows : number of rows in the matrix, see
+   bindings/input/matrix-keymap.txt
+ - keypad,num-columns : number of columns in the matrix, see
+   bindings/input/matrix-keymap.txt
+ - linux,keymap: the definition can be found in
+   bindings/input/matrix-keymap.txt
+ - linux,no-autorepeat: do no enable autorepeat feature.
+ - linux,wakeup: use any event on keypad as wakeup event.
+
+Example:
+
+tc35893@44 {
+        compatible = "toshiba,tc35893";
+        reg = <0x44>;
+        interrupt-parent = <&gpio6>;
+        interrupts = <26 IRQ_TYPE_EDGE_RISING>;
+
+        interrupt-controller;
+        #interrupt-cells = <1>;
+
+        tc3589x_gpio {
+                compatible = "toshiba,tc3589x-gpio";
+                interrupts = <0>;
+
+                interrupt-controller;
+                #interrupt-cells = <2>;
+                gpio-controller;
+                #gpio-cells = <2>;
+        };
+        tc3589x_keypad {
+                compatible = "toshiba,tc3589x-keypad";
+                interrupts = <6>;
+                debounce-delay-ms = <4>;
+                keypad,num-columns = <8>;
+                keypad,num-rows = <8>;
+                linux,no-autorepeat;
+                linux,wakeup;
+                linux,keymap = <0x0301006b
+                                0x04010066
+                                0x06040072
+                                0x040200d7
+                                0x0303006a
+                                0x0205000e
+                                0x0607008b
+                                0x0500001c
+                                0x0403000b
+                                0x03040034
+                                0x05020067
+                                0x0305006c
+                                0x040500e7
+                                0x0005009e
+                                0x06020073
+                                0x01030039
+                                0x07060069
+                                0x050500d9>;
+        };
+};
diff --git a/Documentation/devicetree/bindings/mtd/gpmc-nand.txt b/Documentation/devicetree/bindings/mtd/gpmc-nand.txt
index 65f4f7c43136..ee654e95d8ad 100644
--- a/Documentation/devicetree/bindings/mtd/gpmc-nand.txt
+++ b/Documentation/devicetree/bindings/mtd/gpmc-nand.txt
@@ -22,7 +22,7 @@ Optional properties:
                                 width of 8 is assumed.
 
  - ti,nand-ecc-opt:             A string setting the ECC layout to use. One of:
-                "sw"            <deprecated> use "ham1" instead
+                "sw"            1-bit Hamming ecc code via software
                 "hw"            <deprecated> use "ham1" instead
                 "hw-romcode"    <deprecated> use "ham1" instead
                 "ham1"          1-bit Hamming ecc code
diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt
index 9b03c57563a4..e45ac3f926b1 100644
--- a/Documentation/devicetree/bindings/net/stmmac.txt
+++ b/Documentation/devicetree/bindings/net/stmmac.txt
@@ -39,6 +39,10 @@ Optional properties:
   further clocks may be specified in derived bindings.
 - clock-names: One name for each entry in the clocks property, the
   first one should be "stmmaceth".
+- clk_ptp_ref: this is the PTP reference clock; in case of the PTP is
+  available this clock is used for programming the Timestamp Addend Register.
+  If not passed then the system clock will be used and this is fine on some
+  platforms.
 
 Examples:
 
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,apq8064-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,apq8064-pinctrl.txt
index 0211c6d8a522..92fae82f35f2 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,apq8064-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,apq8064-pinctrl.txt
@@ -62,7 +62,7 @@ Example:
                 #gpio-cells = <2>;
                 interrupt-controller;
                 #interrupt-cells = <2>;
-                interrupts = <0 32 0x4>;
+                interrupts = <0 16 0x4>;
 
                 pinctrl-names = "default";
                 pinctrl-0 = <&gsbi5_uart_default>;
diff --git a/Documentation/devicetree/bindings/regulator/tps65090.txt b/Documentation/devicetree/bindings/regulator/tps65090.txt
index 340980239ea9..ca69f5e3040c 100644
--- a/Documentation/devicetree/bindings/regulator/tps65090.txt
+++ b/Documentation/devicetree/bindings/regulator/tps65090.txt
@@ -45,8 +45,8 @@ Example:
                 infet5-supply = <&some_reg>;
                 infet6-supply = <&some_reg>;
                 infet7-supply = <&some_reg>;
-                vsys_l1-supply = <&some_reg>;
-                vsys_l2-supply = <&some_reg>;
+                vsys-l1-supply = <&some_reg>;
+                vsys-l2-supply = <&some_reg>;
 
                 regulators {
                         dcdc1 {
diff --git a/Documentation/devicetree/bindings/sound/adi,axi-spdif-tx.txt b/Documentation/devicetree/bindings/sound/adi,axi-spdif-tx.txt
index 46f344965313..4eb7997674a0 100644
--- a/Documentation/devicetree/bindings/sound/adi,axi-spdif-tx.txt
+++ b/Documentation/devicetree/bindings/sound/adi,axi-spdif-tx.txt
@@ -1,7 +1,7 @@
 ADI AXI-SPDIF controller
 
 Required properties:
- - compatible : Must be "adi,axi-spdif-1.00.a"
+ - compatible : Must be "adi,axi-spdif-tx-1.00.a"
  - reg : Must contain SPDIF core's registers location and length
  - clocks : Pairs of phandle and specifier referencing the controller's clocks.
    The controller expects two clocks, the clock used for the AXI interface and
diff --git a/Documentation/dma-buf-sharing.txt b/Documentation/dma-buf-sharing.txt
index 67a4087d53f9..bb9753b635a3 100644
--- a/Documentation/dma-buf-sharing.txt
+++ b/Documentation/dma-buf-sharing.txt
@@ -56,10 +56,10 @@ The dma_buf buffer sharing API usage contains the following steps:
                                      size_t size, int flags,
                                      const char *exp_name)
 
-   If this succeeds, dma_buf_export allocates a dma_buf structure, and returns a
-   pointer to the same. It also associates an anonymous file with this buffer,
-   so it can be exported. On failure to allocate the dma_buf object, it returns
-   NULL.
+   If this succeeds, dma_buf_export_named allocates a dma_buf structure, and
+   returns a pointer to the same. It also associates an anonymous file with this
+   buffer, so it can be exported. On failure to allocate the dma_buf object,
+   it returns NULL.
 
    'exp_name' is the name of exporter - to facilitate information while
    debugging.
@@ -76,7 +76,7 @@ The dma_buf buffer sharing API usage contains the following steps:
    drivers and/or processes.
 
    Interface:
-      int dma_buf_fd(struct dma_buf *dmabuf)
+      int dma_buf_fd(struct dma_buf *dmabuf, int flags)
 
    This API installs an fd for the anonymous file associated with this buffer;
    returns either 'fd', or error.
@@ -157,7 +157,9 @@ to request use of buffer for allocation.
    "dma_buf->ops->" indirection from the users of this interface.
 
    In struct dma_buf_ops, unmap_dma_buf is defined as
-      void (*unmap_dma_buf)(struct dma_buf_attachment *, struct sg_table *);
+      void (*unmap_dma_buf)(struct dma_buf_attachment *,
+                            struct sg_table *,
+                            enum dma_data_direction);
 
    unmap_dma_buf signifies the end-of-DMA for the attachment provided. Like
    map_dma_buf, this API also must be implemented by the exporter.
diff --git a/Documentation/filesystems/nfs/nfs-rdma.txt b/Documentation/filesystems/nfs/nfs-rdma.txt
index e386f7e4bcee..724043858b08 100644
--- a/Documentation/filesystems/nfs/nfs-rdma.txt
+++ b/Documentation/filesystems/nfs/nfs-rdma.txt
@@ -138,9 +138,9 @@ Installation
   - Build, install, reboot
 
     The NFS/RDMA code will be enabled automatically if NFS and RDMA
-    are turned on. The NFS/RDMA client and server are configured via the hidden
-    SUNRPC_XPRT_RDMA config option that depends on SUNRPC and INFINIBAND. The
-    value of SUNRPC_XPRT_RDMA will be:
+    are turned on. The NFS/RDMA client and server are configured via the
+    SUNRPC_XPRT_RDMA_CLIENT and SUNRPC_XPRT_RDMA_SERVER config options that both
+    depend on SUNRPC and INFINIBAND. The default value of both options will be:
 
      - N if either SUNRPC or INFINIBAND are N, in this case the NFS/RDMA client
        and server will not be built
@@ -235,8 +235,9 @@ NFS/RDMA Setup
 
   - Start the NFS server
 
-    If the NFS/RDMA server was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in
-    kernel config), load the RDMA transport module:
+    If the NFS/RDMA server was built as a module
+    (CONFIG_SUNRPC_XPRT_RDMA_SERVER=m in kernel config), load the RDMA
+    transport module:
 
     $ modprobe svcrdma
 
@@ -255,8 +256,9 @@ NFS/RDMA Setup
 
   - On the client system
 
-    If the NFS/RDMA client was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in
-    kernel config), load the RDMA client module:
+    If the NFS/RDMA client was built as a module
+    (CONFIG_SUNRPC_XPRT_RDMA_CLIENT=m in kernel config), load the RDMA client
+    module:
 
     $ modprobe xprtrdma.ko
 
diff --git a/Documentation/filesystems/seq_file.txt b/Documentation/filesystems/seq_file.txt
index 1fe0ccb1af55..8ea3e90ace07 100644
--- a/Documentation/filesystems/seq_file.txt
+++ b/Documentation/filesystems/seq_file.txt
@@ -235,6 +235,39 @@ be used for more than one file, you can store an arbitrary pointer in the
 private field of the seq_file structure; that value can then be retrieved
 by the iterator functions.
 
+There is also a wrapper function to seq_open() called seq_open_private(). It
+kmallocs a zero filled block of memory and stores a pointer to it in the
+private field of the seq_file structure, returning 0 on success. The
+block size is specified in a third parameter to the function, e.g.:
+
+        static int ct_open(struct inode *inode, struct file *file)
+        {
+                return seq_open_private(file, &ct_seq_ops,
+                                        sizeof(struct mystruct));
+        }
+
+There is also a variant function, __seq_open_private(), which is functionally
+identical except that, if successful, it returns the pointer to the allocated
+memory block, allowing further initialisation e.g.:
+
+        static int ct_open(struct inode *inode, struct file *file)
+        {
+                struct mystruct *p =
+                        __seq_open_private(file, &ct_seq_ops, sizeof(*p));
+
+                if (!p)
+                        return -ENOMEM;
+
+                p->foo = bar; /* initialize my stuff */
+                        ...
+                p->baz = true;
+
+                return 0;
+        }
+
+A corresponding close function, seq_release_private() is available which
+frees the memory allocated in the corresponding open.
+
 The other operations of interest - read(), llseek(), and release() - are
 all implemented by the seq_file code itself. So a virtual file's
 file_operations structure will look like:
diff --git a/Documentation/gpio/consumer.txt b/Documentation/gpio/consumer.txt
index 76546324e968..6ce544191ca6 100644
--- a/Documentation/gpio/consumer.txt
+++ b/Documentation/gpio/consumer.txt
@@ -53,7 +53,20 @@ with IS_ERR() (they will never return a NULL pointer). -ENOENT will be returned
 if and only if no GPIO has been assigned to the device/function/index triplet,
 other error codes are used for cases where a GPIO has been assigned but an error
 occurred while trying to acquire it. This is useful to discriminate between mere
-errors and an absence of GPIO for optional GPIO parameters.
+errors and an absence of GPIO for optional GPIO parameters. For the common
+pattern where a GPIO is optional, the gpiod_get_optional() and
+gpiod_get_index_optional() functions can be used. These functions return NULL
+instead of -ENOENT if no GPIO has been assigned to the requested function:
+
+
+        struct gpio_desc *gpiod_get_optional(struct device *dev,
+                                             const char *con_id,
+                                             enum gpiod_flags flags)
+
+        struct gpio_desc *gpiod_get_index_optional(struct device *dev,
+                                                   const char *con_id,
+                                                   unsigned int index,
+                                                   enum gpiod_flags flags)
 
 Device-managed variants of these functions are also defined:
 
@@ -65,6 +78,15 @@ Device-managed variants of these functions are also defined:
                                                unsigned int idx,
                                                enum gpiod_flags flags)
 
+        struct gpio_desc *devm_gpiod_get_optional(struct device *dev,
+                                                  const char *con_id,
+                                                  enum gpiod_flags flags)
+
+        struct gpio_desc * devm_gpiod_get_index_optional(struct device *dev,
+                                                        const char *con_id,
+                                                        unsigned int index,
+                                                        enum gpiod_flags flags)
+
 A GPIO descriptor can be disposed of using the gpiod_put() function:
 
         void gpiod_put(struct gpio_desc *desc)
diff --git a/Documentation/i2c/dev-interface b/Documentation/i2c/dev-interface
index 3e742ba25536..2ac78ae1039d 100644
--- a/Documentation/i2c/dev-interface
+++ b/Documentation/i2c/dev-interface
@@ -57,12 +57,12 @@ Well, you are all set up now. You can now use SMBus commands or plain
 I2C to communicate with your device. SMBus commands are preferred if
 the device supports them. Both are illustrated below.
 
-  __u8 register = 0x10; /* Device register to access */
+  __u8 reg = 0x10; /* Device register to access */
   __s32 res;
   char buf[10];
 
   /* Using SMBus commands */
-  res = i2c_smbus_read_word_data(file, register);
+  res = i2c_smbus_read_word_data(file, reg);
   if (res < 0) {
     /* ERROR HANDLING: i2c transaction failed */
   } else {
@@ -70,11 +70,11 @@ the device supports them. Both are illustrated below.
   }
 
   /* Using I2C Write, equivalent of 
-     i2c_smbus_write_word_data(file, register, 0x6543) */
-  buf[0] = register;
+     i2c_smbus_write_word_data(file, reg, 0x6543) */
+  buf[0] = reg;
   buf[1] = 0x43;
   buf[2] = 0x65;
-  if (write(file, buf, 3) ! =3) {
+  if (write(file, buf, 3) != 3) {
     /* ERROR HANDLING: i2c transaction failed */
   }
 
diff --git a/Documentation/kdump/kdump.txt b/Documentation/kdump/kdump.txt
index 88d5a863712a..6c0b9f27e465 100644
--- a/Documentation/kdump/kdump.txt
+++ b/Documentation/kdump/kdump.txt
@@ -18,7 +18,7 @@ memory image to a dump file on the local disk, or across the network to
 a remote system.
 
 Kdump and kexec are currently supported on the x86, x86_64, ppc64, ia64,
-and s390x architectures.
+s390x and arm architectures.
 
 When the system kernel boots, it reserves a small section of memory for
 the dump-capture kernel. This ensures that ongoing Direct Memory Access
@@ -112,7 +112,7 @@ There are two possible methods of using Kdump.
 2) Or use the system kernel binary itself as dump-capture kernel and there is
    no need to build a separate dump-capture kernel. This is possible
    only with the architectures which support a relocatable kernel. As
-   of today, i386, x86_64, ppc64 and ia64 architectures support relocatable
+   of today, i386, x86_64, ppc64, ia64 and arm architectures support relocatable
    kernel.
 
 Building a relocatable kernel is advantageous from the point of view that
@@ -241,6 +241,13 @@ Dump-capture kernel config options (Arch Dependent, ia64)
   kernel will be aligned to 64Mb, so if the start address is not then
   any space below the alignment point will be wasted.
 
+Dump-capture kernel config options (Arch Dependent, arm)
+----------------------------------------------------------
+
+-   To use a relocatable kernel,
+    Enable "AUTO_ZRELADDR" support under "Boot" options:
+
+    AUTO_ZRELADDR=y
 
 Extended crashkernel syntax
 ===========================
@@ -256,6 +263,10 @@ The syntax is:
     crashkernel=<range1>:<size1>[,<range2>:<size2>,...][@offset]
     range=start-[end]
 
+Please note, on arm, the offset is required.
+    crashkernel=<range1>:<size1>[,<range2>:<size2>,...]@offset
+    range=start-[end]
+
     'start' is inclusive and 'end' is exclusive.
 
 For example:
@@ -296,6 +307,12 @@ Boot into System Kernel
    on the memory consumption of the kdump system. In general this is not
    dependent on the memory size of the production system.
 
+   On arm, use "crashkernel=Y@X". Note that the start address of the kernel
+   will be aligned to 128MiB (0x08000000), so if the start address is not then
+   any space below the alignment point may be overwritten by the dump-capture kernel,
+   which means it is possible that the vmcore is not that precise as expected.
+
+
 Load the Dump-capture Kernel
 ============================
 
@@ -315,7 +332,8 @@ For ia64:
         - Use vmlinux or vmlinuz.gz
 For s390x:
         - Use image or bzImage
-
+For arm:
+        - Use zImage
 
 If you are using a uncompressed vmlinux image then use following command
 to load dump-capture kernel.
@@ -331,6 +349,15 @@ to load dump-capture kernel.
    --initrd=<initrd-for-dump-capture-kernel> \
    --append="root=<root-dev> <arch-specific-options>"
 
+If you are using a compressed zImage, then use following command
+to load dump-capture kernel.
+
+   kexec --type zImage -p <dump-capture-kernel-bzImage> \
+   --initrd=<initrd-for-dump-capture-kernel> \
+   --dtb=<dtb-for-dump-capture-kernel> \
+   --append="root=<root-dev> <arch-specific-options>"
+
+
 Please note, that --args-linux does not need to be specified for ia64.
 It is planned to make this a no-op on that architecture, but for now
 it should be omitted
@@ -347,6 +374,9 @@ For ppc64:
 For s390x:
         "1 maxcpus=1 cgroup_disable=memory"
 
+For arm:
+        "1 maxcpus=1 reset_devices"
+
 Notes on loading the dump-capture kernel:
 
 * By default, the ELF headers are stored in ELF64 format to support
diff --git a/Documentation/misc-devices/lis3lv02d b/Documentation/misc-devices/lis3lv02d
index af815b9ba413..f89960a0ff95 100644
--- a/Documentation/misc-devices/lis3lv02d
+++ b/Documentation/misc-devices/lis3lv02d
@@ -59,7 +59,7 @@ acts similar to /dev/rtc and reacts on free-fall interrupts received
 from the device. It supports blocking operations, poll/select and
 fasync operation modes. You must read 1 bytes from the device.  The
 result is number of free-fall interrupts since the last successful
-read (or 255 if number of interrupts would not fit). See the hpfall.c
+read (or 255 if number of interrupts would not fit). See the freefall.c
 file for an example on using the device.
 
 
diff --git a/Documentation/power/regulator/consumer.txt b/Documentation/power/regulator/consumer.txt
index 81c0e2b49cd8..8afb236ca765 100644
--- a/Documentation/power/regulator/consumer.txt
+++ b/Documentation/power/regulator/consumer.txt
@@ -143,8 +143,9 @@ This will cause the core to recalculate the total load on the regulator (based
 on all its consumers) and change operating mode (if necessary and permitted)
 to best match the current operating load.
 
-The load_uA value can be determined from the consumers datasheet. e.g.most
-datasheets have tables showing the max current consumed in certain situations.
+The load_uA value can be determined from the consumer's datasheet. e.g. most
+datasheets have tables showing the maximum current consumed in certain
+situations.
 
 Most consumers will use indirect operating mode control since they have no
 knowledge of the regulator or whether the regulator is shared with other
@@ -173,7 +174,7 @@ Consumers can register interest in regulator events by calling :-
 int regulator_register_notifier(struct regulator *regulator,
                               struct notifier_block *nb);
 
-Consumers can uregister interest by calling :-
+Consumers can unregister interest by calling :-
 
 int regulator_unregister_notifier(struct regulator *regulator,
                                 struct notifier_block *nb);
diff --git a/Documentation/power/regulator/design.txt b/Documentation/power/regulator/design.txt
index f9b56b72b782..fdd919b96830 100644
--- a/Documentation/power/regulator/design.txt
+++ b/Documentation/power/regulator/design.txt
@@ -9,14 +9,14 @@ Safety
 
  - Errors in regulator configuration can have very serious consequences
    for the system, potentially including lasting hardware damage.
- - It is not possible to automatically determine the power confugration
+ - It is not possible to automatically determine the power configuration
    of the system - software-equivalent variants of the same chip may
-   have different power requirments, and not all components with power
+   have different power requirements, and not all components with power
    requirements are visible to software.
 
   => The API should make no changes to the hardware state unless it has
-     specific knowledge that these changes are safe to do perform on
-     this particular system.
+     specific knowledge that these changes are safe to perform on this
+     particular system.
 
 Consumer use cases
 ------------------
diff --git a/Documentation/power/regulator/machine.txt b/Documentation/power/regulator/machine.txt
index ce63af0a8e35..757e3b53dc11 100644
--- a/Documentation/power/regulator/machine.txt
+++ b/Documentation/power/regulator/machine.txt
@@ -11,7 +11,7 @@ Consider the following machine :-
                +-> [Consumer B @ 3.3V]
 
 The drivers for consumers A & B must be mapped to the correct regulator in
-order to control their power supply. This mapping can be achieved in machine
+order to control their power supplies. This mapping can be achieved in machine
 initialisation code by creating a struct regulator_consumer_supply for
 each regulator.
 
@@ -39,7 +39,7 @@ to the 'Vcc' supply for Consumer A.
 
 Constraints can now be registered by defining a struct regulator_init_data
 for each regulator power domain. This structure also maps the consumers
-to their supply regulator :-
+to their supply regulators :-
 
 static struct regulator_init_data regulator1_data = {
         .constraints = {
diff --git a/Documentation/power/regulator/overview.txt b/Documentation/power/regulator/overview.txt
index 8ed17587a74b..40ca2d6e2742 100644
--- a/Documentation/power/regulator/overview.txt
+++ b/Documentation/power/regulator/overview.txt
@@ -36,11 +36,11 @@ Some terms used in this document:-
                    Consumers can be classified into two types:-
 
                    Static: consumer does not change its supply voltage or
-                   current limit. It only needs to enable or disable it's
+                   current limit. It only needs to enable or disable its
                    power supply. Its supply voltage is set by the hardware,
                    bootloader, firmware or kernel board initialisation code.
 
-                   Dynamic: consumer needs to change it's supply voltage or
+                   Dynamic: consumer needs to change its supply voltage or
                    current limit to meet operation demands.
 
 
@@ -156,7 +156,7 @@ relevant to non SoC devices and is split into the following four interfaces:-
       This interface is for machine specific code and allows the creation of
       voltage/current domains (with constraints) for each regulator. It can
       provide regulator constraints that will prevent device damage through
-      overvoltage or over current caused by buggy client drivers. It also
+      overvoltage or overcurrent caused by buggy client drivers. It also
       allows the creation of a regulator tree whereby some regulators are
       supplied by others (similar to a clock tree).
 
diff --git a/Documentation/power/regulator/regulator.txt b/Documentation/power/regulator/regulator.txt
index 13902778ae44..b17e5833ce21 100644
--- a/Documentation/power/regulator/regulator.txt
+++ b/Documentation/power/regulator/regulator.txt
@@ -13,7 +13,7 @@ Drivers can register a regulator by calling :-
 struct regulator_dev *regulator_register(struct regulator_desc *regulator_desc,
                                          const struct regulator_config *config);
 
-This will register the regulators capabilities and operations to the regulator
+This will register the regulator's capabilities and operations to the regulator
 core.
 
 Regulators can be unregistered by calling :-
@@ -23,8 +23,8 @@ void regulator_unregister(struct regulator_dev *rdev);
 
 Regulator Events
 ================
-Regulators can send events (e.g. over temp, under voltage, etc) to consumer
-drivers by calling :-
+Regulators can send events (e.g. overtemperature, undervoltage, etc) to
+consumer drivers by calling :-
 
 int regulator_notifier_call_chain(struct regulator_dev *rdev,
                                   unsigned long event, void *data);
diff --git a/Documentation/this_cpu_ops.txt b/Documentation/this_cpu_ops.txt
index 1a4ce7e3e05f..0ec995712176 100644
--- a/Documentation/this_cpu_ops.txt
+++ b/Documentation/this_cpu_ops.txt
@@ -2,26 +2,26 @@ this_cpu operations
 -------------------
 
 this_cpu operations are a way of optimizing access to per cpu
-variables associated with the *currently* executing processor through
-the use of segment registers (or a dedicated register where the cpu
-permanently stored the beginning of the per cpu area for a specific
-processor).
+variables associated with the *currently* executing processor. This is
+done through the use of segment registers (or a dedicated register where
+the cpu permanently stored the beginning of the per cpu area for a
+specific processor).
 
-The this_cpu operations add a per cpu variable offset to the processor
-specific percpu base and encode that operation in the instruction
+this_cpu operations add a per cpu variable offset to the processor
+specific per cpu base and encode that operation in the instruction
 operating on the per cpu variable.
 
-This means there are no atomicity issues between the calculation of
+This means that there are no atomicity issues between the calculation of
 the offset and the operation on the data. Therefore it is not
-necessary to disable preempt or interrupts to ensure that the
+necessary to disable preemption or interrupts to ensure that the
 processor is not changed between the calculation of the address and
 the operation on the data.
 
 Read-modify-write operations are of particular interest. Frequently
 processors have special lower latency instructions that can operate
-without the typical synchronization overhead but still provide some
-sort of relaxed atomicity guarantee. The x86 for example can execute
-RMV (Read Modify Write) instructions like inc/dec/cmpxchg without the
+without the typical synchronization overhead, but still provide some
+sort of relaxed atomicity guarantees. The x86, for example, can execute
+RMW (Read Modify Write) instructions like inc/dec/cmpxchg without the
 lock prefix and the associated latency penalty.
 
 Access to the variable without the lock prefix is not synchronized but
@@ -30,6 +30,38 @@ data specific to the currently executing processor. Only the current
 processor should be accessing that variable and therefore there are no
 concurrency issues with other processors in the system.
 
+Please note that accesses by remote processors to a per cpu area are
+exceptional situations and may impact performance and/or correctness
+(remote write operations) of local RMW operations via this_cpu_*.
+
+The main use of the this_cpu operations has been to optimize counter
+operations.
+
+The following this_cpu() operations with implied preemption protection
+are defined. These operations can be used without worrying about
+preemption and interrupts.
+
+        this_cpu_add()
+        this_cpu_read(pcp)
+        this_cpu_write(pcp, val)
+        this_cpu_add(pcp, val)
+        this_cpu_and(pcp, val)
+        this_cpu_or(pcp, val)
+        this_cpu_add_return(pcp, val)
+        this_cpu_xchg(pcp, nval)
+        this_cpu_cmpxchg(pcp, oval, nval)
+        this_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+        this_cpu_sub(pcp, val)
+        this_cpu_inc(pcp)
+        this_cpu_dec(pcp)
+        this_cpu_sub_return(pcp, val)
+        this_cpu_inc_return(pcp)
+        this_cpu_dec_return(pcp)
+
+
+Inner working of this_cpu operations
+------------------------------------
+
 On x86 the fs: or the gs: segment registers contain the base of the
 per cpu area. It is then possible to simply use the segment override
 to relocate a per cpu relative address to the proper per cpu area for
@@ -48,22 +80,21 @@ results in a single instruction
         mov ax, gs:[x]
 
 instead of a sequence of calculation of the address and then a fetch
-from that address which occurs with the percpu operations. Before
+from that address which occurs with the per cpu operations. Before
 this_cpu_ops such sequence also required preempt disable/enable to
 prevent the kernel from moving the thread to a different processor
 while the calculation is performed.
 
-The main use of the this_cpu operations has been to optimize counter
-operations.
+Consider the following this_cpu operation:
 
         this_cpu_inc(x)
 
-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;
@@ -73,10 +104,10 @@ register.
         (*y)++;
         put_cpu();
 
-Note that these operations can only be used on percpu data that is
+Note that these operations can only be used on per cpu data that is
 reserved for a specific processor. Without disabling preemption in the
 surrounding code this_cpu_inc() will only guarantee that one of the
-percpu counters is correctly incremented. However, there is no
+per cpu counters is correctly incremented. However, there is no
 guarantee that the OS will not move the process directly before or
 after the this_cpu instruction is executed. In general this means that
 the value of the individual counters for each processor are
@@ -86,9 +117,9 @@ that is of interest.
 Per cpu variables are used for performance reasons. Bouncing cache
 lines can be avoided if multiple processors concurrently go through
 the same code paths.  Since each processor has its own per cpu
-variables no concurrent cacheline updates take place. The price that
+variables no concurrent cache line updates take place. The price that
 has to be paid for this optimization is the need to add up the per cpu
-counters when the value of the counter is needed.
+counters when the value of a counter is needed.
 
 
 Special operations:
@@ -100,33 +131,39 @@ Takes the offset of a per cpu variable (&x !) and returns the address
 of the per cpu variable that belongs to the currently executing
 processor.  this_cpu_ptr avoids multiple steps that the common
 get_cpu/put_cpu sequence requires. No processor number is
-available. Instead the offset of the local per cpu area is simply
-added to the percpu offset.
+available. Instead, the offset of the local per cpu area is simply
+added to the per cpu offset.
 
+Note that this operation is usually used in a code segment when
+preemption has been disabled. The pointer is then used to
+access local per cpu data in a critical section. When preemption
+is re-enabled this pointer is usually no longer useful since it may
+no longer point to per cpu data of the current processor.
 
 
 Per cpu variables and offsets
 -----------------------------
 
-Per cpu variables have *offsets* to the beginning of the percpu
+Per cpu variables have *offsets* to the beginning of the per cpu
 area. They do not have addresses although they look like that in the
 code. Offsets cannot be directly dereferenced. The offset must be
-added to a base pointer of a percpu area of a processor in order to
+added to a base pointer of a per cpu area of a processor in order to
 form a valid address.
 
 Therefore the use of x or &x outside of the context of per cpu
 operations is invalid and will generally be treated like a NULL
 pointer dereference.
 
-In the context of per cpu operations
+        DEFINE_PER_CPU(int, x);
 
-        x is a per cpu variable. Most this_cpu operations take a cpu
-        variable.
+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.
 
-        &x is the *offset* a per cpu variable. this_cpu_ptr() takes
-        the offset of a per cpu variable which makes this look a bit
-        strange.
+        int __percpu *p = &x;
 
+&x and hence p is the *offset* of a per cpu variable. this_cpu_ptr()
+takes the offset of a per cpu variable which makes this look a bit
+strange.
 
 
 Operations on a field of a per cpu structure
@@ -152,7 +189,7 @@ If we have an offset to struct s:
 
         struct s __percpu *ps = &p;
 
-        z = this_cpu_dec(ps->m);
+        this_cpu_dec(ps->m);
 
         z = this_cpu_inc_return(ps->n);
 
@@ -172,29 +209,52 @@ if we do not make use of this_cpu ops later to manipulate fields:
 Variants of this_cpu ops
 -------------------------
 
-this_cpu ops are interrupt safe. Some architecture do not support
+this_cpu ops are interrupt safe. Some architectures do not support
 these per cpu local operations. In that case the operation must be
 replaced by code that disables interrupts, then does the operations
-that are guaranteed to be atomic and then reenable interrupts. Doing
+that are guaranteed to be atomic and then re-enable interrupts. Doing
 so is expensive. If there are other reasons why the scheduler cannot
 change the processor we are executing on then there is no reason to
-disable interrupts. For that purpose the __this_cpu operations are
-provided. For example.
-
-        __this_cpu_inc(x);
-
-Will increment x and will not fallback to code that disables
+disable interrupts. For that purpose the following __this_cpu operations
+are provided.
+
+These operations have no guarantee against concurrent interrupts or
+preemption. If a per cpu variable is not used in an interrupt context
+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.
+
+        __this_cpu_add()
+        __this_cpu_read(pcp)
+        __this_cpu_write(pcp, val)
+        __this_cpu_add(pcp, val)
+        __this_cpu_and(pcp, val)
+        __this_cpu_or(pcp, val)
+        __this_cpu_add_return(pcp, val)
+        __this_cpu_xchg(pcp, nval)
+        __this_cpu_cmpxchg(pcp, oval, nval)
+        __this_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
+        __this_cpu_sub(pcp, val)
+        __this_cpu_inc(pcp)
+        __this_cpu_dec(pcp)
+        __this_cpu_sub_return(pcp, val)
+        __this_cpu_inc_return(pcp)
+        __this_cpu_dec_return(pcp)
+
+
+Will increment x and will not fall-back to code that disables
 interrupts on platforms that cannot accomplish atomicity through
 address relocation and a Read-Modify-Write operation in the same
 instruction.
 
 
-
 &this_cpu_ptr(pp)->n vs this_cpu_ptr(&pp->n)
 --------------------------------------------
 
 The first operation takes the offset and forms an address and then
-adds the offset of the n field.
+adds the offset of the n field. This may result in two add
+instructions emitted by the compiler.
 
 The second one first adds the two offsets and then does the
 relocation.  IMHO the second form looks cleaner and has an easier time
@@ -202,4 +262,73 @@ with (). The second form also is consistent with the way
 this_cpu_read() and friends are used.
 
 
-Christoph Lameter, April 3rd, 2013
+Remote access to per cpu data
+------------------------------
+
+Per cpu data structures are designed to be used by one cpu exclusively.
+If you use the variables as intended, this_cpu_ops() are guaranteed to
+be "atomic" as no other CPU has access to these data structures.
+
+There are special cases where you might need to access per cpu data
+structures remotely. It is usually safe to do a remote read access
+and that is frequently done to summarize counters. Remote write access
+something which could be problematic because this_cpu ops do not
+have lock semantics. A remote write may interfere with a this_cpu
+RMW operation.
+
+Remote write accesses to percpu data structures are highly discouraged
+unless absolutely necessary. Please consider using an IPI to wake up
+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:
+
+
+        DEFINE_PER_CPU(struct data, datap);
+
+        struct data *p = per_cpu_ptr(&datap, cpu);
+
+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
+
+        struct data *p = this_cpu_ptr(&datap);
+
+but, passing of pointers calculated via this_cpu_ptr to other cpus is
+unusual and should be avoided.
+
+Remote access are typically only for reading the status of another cpus
+per cpu data. Write accesses can cause unique problems due to the
+relaxed synchronization requirements for this_cpu operations.
+
+One example that illustrates some concerns with write operations is
+the following scenario that occurs because two per cpu variables
+share a cache-line but the relaxed synchronization is applied to
+only one process updating the cache-line.
+
+Consider the following example
+
+
+        struct test {
+                atomic_t a;
+                int b;
+        };
+
+        DEFINE_PER_CPU(struct test, onecacheline);
+
+There is some concern about what would happen if the field 'a' is updated
+remotely from one processor and the local processor would use this_cpu ops
+to update field b. Care should be taken that such simultaneous accesses to
+data within the same cache line are avoided. Also costly synchronization
+may be necessary. IPIs are generally recommended in such scenarios instead
+of a remote write to the per cpu area of another processor.
+
+Even in cases where the remote writes are rare, please bear in
+mind that a remote write will evict the cache line from the processor
+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/x86/tlb.txt b/Documentation/x86/tlb.txt
index 2b3a82e69151..39d172326703 100644
--- a/Documentation/x86/tlb.txt
+++ b/Documentation/x86/tlb.txt
@@ -35,7 +35,7 @@ invlpg instruction (or instructions _near_ it) show up high in
 profiles.  If you believe that individual invalidations being
 called too often, you can lower the tunable:
 
-        /sys/debug/kernel/x86/tlb_single_page_flush_ceiling
+        /sys/kernel/debug/x86/tlb_single_page_flush_ceiling
 
 This will cause us to do the global flush for more cases.
 Lowering it to 0 will disable the use of the individual flushes.