73 files changed, 2510 insertions, 449 deletions
diff --git a/Documentation/ABI/testing/configfs-usb-gadget-ffs b/Documentation/ABI/testing/configfs-usb-gadget-ffs
new file mode 100644
index 000000000000..14343e237e83
--- /dev/null
+++ b/Documentation/ABI/testing/configfs-usb-gadget-ffs
@@ -0,0 +1,9 @@
+What:           /config/usb-gadget/gadget/functions/ffs.name
+Date:           Nov 2013
+KenelVersion:   3.13
+Description:    The purpose of this directory is to create and remove it.
+                A corresponding USB function instance is created/removed.
+                There are no attributes here.
+                All parameters are set through FunctionFS.
diff --git a/Documentation/ABI/testing/configfs-usb-gadget-loopback b/Documentation/ABI/testing/configfs-usb-gadget-loopback
new file mode 100644
index 000000000000..852b2365a5b5
--- /dev/null
+++ b/Documentation/ABI/testing/configfs-usb-gadget-loopback
@@ -0,0 +1,8 @@
+What:           /config/usb-gadget/gadget/functions/Loopback.name
+Date:           Nov 2013
+KenelVersion:   3.13
+Description:
+                The attributes:
+                qlen            - depth of loopback queue
+                bulk_buflen     - buffer length
diff --git a/Documentation/ABI/testing/configfs-usb-gadget-sourcesink b/Documentation/ABI/testing/configfs-usb-gadget-sourcesink
new file mode 100644
index 000000000000..a30f3093ef6c
--- /dev/null
+++ b/Documentation/ABI/testing/configfs-usb-gadget-sourcesink
@@ -0,0 +1,12 @@
+What:           /config/usb-gadget/gadget/functions/SourceSink.name
+Date:           Nov 2013
+KenelVersion:   3.13
+Description:
+                The attributes:
+                pattern         - 0 (all zeros), 1 (mod63), 2 (none)
+                isoc_interval   - 1..16
+                isoc_maxpacket  - 0 - 1023 (fs), 0 - 1024 (hs/ss)
+                isoc_mult       - 0..2 (hs/ss only)
+                isoc_maxburst   - 0..15 (ss only)
+                qlen            - buffer length
diff --git a/Documentation/ABI/testing/debugfs-driver-genwqe b/Documentation/ABI/testing/debugfs-driver-genwqe
new file mode 100644
index 000000000000..1c2f25674e8c
--- /dev/null
+++ b/Documentation/ABI/testing/debugfs-driver-genwqe
@@ -0,0 +1,91 @@
+What:           /sys/kernel/debug/genwqe/genwqe<n>_card/ddcb_info
+Date:           Oct 2013
+Contact:        haver@linux.vnet.ibm.com
+Description:    DDCB queue dump used for debugging queueing problems.
+What:           /sys/kernel/debug/genwqe/genwqe<n>_card/curr_regs
+Date:           Oct 2013
+Contact:        haver@linux.vnet.ibm.com
+Description:    Dump of the current error registers.
+                Only available for PF.
+What:           /sys/kernel/debug/genwqe/genwqe<n>_card/curr_dbg_uid0
+Date:           Oct 2013
+Contact:        haver@linux.vnet.ibm.com
+Description:    Internal chip state of UID0 (unit id 0).
+                Only available for PF.
+What:           /sys/kernel/debug/genwqe/genwqe<n>_card/curr_dbg_uid1
+Date:           Oct 2013
+Contact:        haver@linux.vnet.ibm.com
+Description:    Internal chip state of UID1.
+                Only available for PF.
+What:           /sys/kernel/debug/genwqe/genwqe<n>_card/curr_dbg_uid2
+Date:           Oct 2013
+Contact:        haver@linux.vnet.ibm.com
+Description:    Internal chip state of UID2.
+                Only available for PF.
+What:           /sys/kernel/debug/genwqe/genwqe<n>_card/prev_regs
+Date:           Oct 2013
+Contact:        haver@linux.vnet.ibm.com
+Description:    Dump of the error registers before the last reset of
+                the card occured.
+                Only available for PF.
+What:           /sys/kernel/debug/genwqe/genwqe<n>_card/prev_dbg_uid0
+Date:           Oct 2013
+Contact:        haver@linux.vnet.ibm.com
+Description:    Internal chip state of UID0 before card was reset.
+                Only available for PF.
+What:           /sys/kernel/debug/genwqe/genwqe<n>_card/prev_dbg_uid1
+Date:           Oct 2013
+Contact:        haver@linux.vnet.ibm.com
+Description:    Internal chip state of UID1 before card was reset.
+                Only available for PF.
+What:           /sys/kernel/debug/genwqe/genwqe<n>_card/prev_dbg_uid2
+Date:           Oct 2013
+Contact:        haver@linux.vnet.ibm.com
+Description:    Internal chip state of UID2 before card was reset.
+                Only available for PF.
+What:           /sys/kernel/debug/genwqe/genwqe<n>_card/info
+Date:           Oct 2013
+Contact:        haver@linux.vnet.ibm.com
+Description:    Comprehensive summary of bitstream version and software
+                version. Used bitstream and bitstream clocking information.
+What:           /sys/kernel/debug/genwqe/genwqe<n>_card/err_inject
+Date:           Oct 2013
+Contact:        haver@linux.vnet.ibm.com
+Description:    Possibility to inject error cases to ensure that the drivers
+                error handling code works well.
+What:           /sys/kernel/debug/genwqe/genwqe<n>_card/vf<0..14>_jobtimeout_msec
+Date:           Oct 2013
+Contact:        haver@linux.vnet.ibm.com
+Description:    Default VF timeout 250ms. Testing might require 1000ms.
+                Using 0 will use the cards default value (whatever that is).
+                The timeout depends on the max number of available cards
+                in the system and the maximum allowed queue size.
+                The driver ensures that the settings are done just before
+                the VFs get enabled. Changing the timeouts in flight is not
+                possible.
+                Only available for PF.
+What:           /sys/kernel/debug/genwqe/genwqe<n>_card/jobtimer
+Date:           Oct 2013
+Contact:        haver@linux.vnet.ibm.com
+Description:    Dump job timeout register values for PF and VFs.
+                Only available for PF.
+What:           /sys/kernel/debug/genwqe/genwqe<n>_card/queue_working_time
+Date:           Dec 2013
+Contact:        haver@linux.vnet.ibm.com
+Description:    Dump queue working time register values for PF and VFs.
+                Only available for PF.
diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio
index b20e829d350f..6e02c5029152 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio
+++ b/Documentation/ABI/testing/sysfs-bus-iio
@@ -197,6 +197,19 @@ Description:
                Raw pressure measurement from channel Y. Units after
                application of scale and offset are kilopascal.
+What:           /sys/bus/iio/devices/iio:deviceX/in_humidityrelative_raw
+KernelVersion:  3.14
+Contact:        linux-iio@vger.kernel.org
+Description:
+                Raw humidity measurement of air. Units after application of
+                scale and offset are milli percent.
+What:           /sys/bus/iio/devices/iio:deviceX/in_humidityrelative_input
+KernelVersion:  3.14
+Contact:        linux-iio@vger.kernel.org
+Description:
+                Scaled humidity measurement in milli percent.
 What:           /sys/bus/iio/devices/iio:deviceX/in_accel_offset
 What:           /sys/bus/iio/devices/iio:deviceX/in_accel_x_offset
 What:           /sys/bus/iio/devices/iio:deviceX/in_accel_y_offset
diff --git a/Documentation/ABI/testing/sysfs-bus-usb b/Documentation/ABI/testing/sysfs-bus-usb
index 1430f584b266..614d451cee41 100644
--- a/Documentation/ABI/testing/sysfs-bus-usb
+++ b/Documentation/ABI/testing/sysfs-bus-usb
@@ -50,13 +50,19 @@ Description:
                This may allow the driver to support more hardware than
                was included in the driver's static device ID support
                table at compile time. The format for the device ID is:
-                idVendor idProduct bInterfaceClass.
+                idVendor idProduct bInterfaceClass RefIdVendor RefIdProduct
                The vendor ID and device ID fields are required, the
-                interface class is optional.
+                rest is optional. The Ref* tuple can be used to tell the
+                driver to use the same driver_data for the new device as
+                it is used for the reference device.
                Upon successfully adding an ID, the driver will probe
                for the device and attempt to bind to it.  For example:
                # echo "8086 10f5" > /sys/bus/usb/drivers/foo/new_id
+                Here add a new device (0458:7045) using driver_data from
+                an already supported device (0458:704c):
+                # echo "0458 7045 0 0458 704c" > /sys/bus/usb/drivers/foo/new_id
                Reading from this file will list all dynamically added
                device IDs in the same format, with one entry per
                line. For example:
diff --git a/Documentation/ABI/testing/sysfs-driver-genwqe b/Documentation/ABI/testing/sysfs-driver-genwqe
new file mode 100644
index 000000000000..1870737a1f5e
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-driver-genwqe
@@ -0,0 +1,62 @@
+What:           /sys/class/genwqe/genwqe<n>_card/version
+Date:           Oct 2013
+Contact:        haver@linux.vnet.ibm.com
+Description:    Unique bitstream identification e.g.
+                '0000000330336283.00000000475a4950'.
+What:           /sys/class/genwqe/genwqe<n>_card/appid
+Date:           Oct 2013
+Contact:        haver@linux.vnet.ibm.com
+Description:    Identifies the currently active card application e.g. 'GZIP'
+                for compression/decompression.
+What:           /sys/class/genwqe/genwqe<n>_card/type
+Date:           Oct 2013
+Contact:        haver@linux.vnet.ibm.com
+Description:    Type of the card e.g. 'GenWQE5-A7'.
+What:           /sys/class/genwqe/genwqe<n>_card/curr_bitstream
+Date:           Oct 2013
+Contact:        haver@linux.vnet.ibm.com
+Description:    Currently active bitstream. 1 is default, 0 is backup.
+What:           /sys/class/genwqe/genwqe<n>_card/next_bitstream
+Date:           Oct 2013
+Contact:        haver@linux.vnet.ibm.com
+Description:    Interface to set the next bitstream to be used.
+What:           /sys/class/genwqe/genwqe<n>_card/tempsens
+Date:           Oct 2013
+Contact:        haver@linux.vnet.ibm.com
+Description:    Interface to read the cards temperature sense register.
+What:           /sys/class/genwqe/genwqe<n>_card/freerunning_timer
+Date:           Oct 2013
+Contact:        haver@linux.vnet.ibm.com
+Description:    Interface to read the cards free running timer.
+                Used for performance and utilization measurements.
+What:           /sys/class/genwqe/genwqe<n>_card/queue_working_time
+Date:           Oct 2013
+Contact:        haver@linux.vnet.ibm.com
+Description:    Interface to read queue working time.
+                Used for performance and utilization measurements.
+What:           /sys/class/genwqe/genwqe<n>_card/state
+Date:           Oct 2013
+Contact:        haver@linux.vnet.ibm.com
+Description:    State of the card: "unused", "used", "error".
+What:           /sys/class/genwqe/genwqe<n>_card/base_clock
+Date:           Oct 2013
+Contact:        haver@linux.vnet.ibm.com
+Description:    Base clock frequency of the card.
+What:           /sys/class/genwqe/genwqe<n>_card/device/sriov_numvfs
+Date:           Oct 2013
+Contact:        haver@linux.vnet.ibm.com
+Description:    Enable VFs (1..15):
+                  sudo sh -c 'echo 15 > \
+                    /sys/bus/pci/devices/0000\:1b\:00.0/sriov_numvfs'
+                Disable VFs:
+                  Write a 0 into the same sysfs entry.
diff --git a/Documentation/ABI/testing/sysfs-firmware-efi b/Documentation/ABI/testing/sysfs-firmware-efi
new file mode 100644
index 000000000000..05874da7ce80
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-firmware-efi
@@ -0,0 +1,20 @@
+What:           /sys/firmware/efi/fw_vendor
+Date:           December 2013
+Contact:        Dave Young <dyoung@redhat.com>
+Description:    It shows the physical address of firmware vendor field in the
+                EFI system table.
+Users:          Kexec
+What:           /sys/firmware/efi/runtime
+Date:           December 2013
+Contact:        Dave Young <dyoung@redhat.com>
+Description:    It shows the physical address of runtime service table entry in
+                the EFI system table.
+Users:          Kexec
+What:           /sys/firmware/efi/config_table
+Date:           December 2013
+Contact:        Dave Young <dyoung@redhat.com>
+Description:    It shows the physical address of config table entry in the EFI
+                system table.
+Users:          Kexec
diff --git a/Documentation/ABI/testing/sysfs-firmware-efi-runtime-map b/Documentation/ABI/testing/sysfs-firmware-efi-runtime-map
new file mode 100644
index 000000000000..c61b9b348e99
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-firmware-efi-runtime-map
@@ -0,0 +1,34 @@
+What:           /sys/firmware/efi/runtime-map/
+Date:           December 2013
+Contact:        Dave Young <dyoung@redhat.com>
+Description:    Switching efi runtime services to virtual mode requires
+                that all efi memory ranges which have the runtime attribute
+                bit set to be mapped to virtual addresses.
+                The efi runtime services can only be switched to virtual
+                mode once without rebooting. The kexec kernel must maintain
+                the same physical to virtual address mappings as the first
+                kernel. The mappings are exported to sysfs so userspace tools
+                can reassemble them and pass them into the kexec kernel.
+                /sys/firmware/efi/runtime-map/ is the directory the kernel
+                exports that information in.
+                subdirectories are named with the number of the memory range:
+                        /sys/firmware/efi/runtime-map/0
+                        /sys/firmware/efi/runtime-map/1
+                        /sys/firmware/efi/runtime-map/2
+                        /sys/firmware/efi/runtime-map/3
+                        ...
+                Each subdirectory contains five files:
+                attribute : The attributes of the memory range.
+                num_pages : The size of the memory range in pages.
+                phys_addr : The physical address of the memory range.
+                type      : The type of the memory range.
+                virt_addr : The virtual address of the memory range.
+                Above values are all hexadecimal numbers with the '0x' prefix.
+Users:          Kexec
diff --git a/Documentation/ABI/testing/sysfs-kernel-boot_params b/Documentation/ABI/testing/sysfs-kernel-boot_params
new file mode 100644
index 000000000000..eca38ce2852d
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-kernel-boot_params
@@ -0,0 +1,38 @@
+What:           /sys/kernel/boot_params
+Date:           December 2013
+Contact:        Dave Young <dyoung@redhat.com>
+Description:    The /sys/kernel/boot_params directory contains two
+                files: "data" and "version" and one subdirectory "setup_data".
+                It is used to export the kernel boot parameters of an x86
+                platform to userspace for kexec and debugging purpose.
+                If there's no setup_data in boot_params the subdirectory will
+                not be created.
+                "data" file is the binary representation of struct boot_params.
+                "version" file is the string representation of boot
+                protocol version.
+                "setup_data" subdirectory contains the setup_data data
+                structure in boot_params. setup_data is maintained in kernel
+                as a link list. In "setup_data" subdirectory there's one
+                subdirectory for each link list node named with the number
+                of the list nodes. The list node subdirectory contains two
+                files "type" and "data". "type" file is the string
+                representation of setup_data type. "data" file is the binary
+                representation of setup_data payload.
+                The whole boot_params directory structure is like below:
+                /sys/kernel/boot_params
+                |__ data
+                |__ setup_data
+                |   |__ 0
+                |   |   |__ data
+                |   |   |__ type
+                |   |__ 1
+                |       |__ data
+                |       |__ type
+                |__ version
+Users:          Kexec
diff --git a/Documentation/ABI/testing/sysfs-platform-tahvo-usb b/Documentation/ABI/testing/sysfs-platform-tahvo-usb
new file mode 100644
index 000000000000..f6e20ce4b538
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-platform-tahvo-usb
@@ -0,0 +1,16 @@
+What:           /sys/bus/platform/devices/tahvo-usb/otg_mode
+Date:           December 2013
+Contact:        Aaro Koskinen <aaro.koskinen@iki.fi>
+Description:
+                Set or read the current OTG mode. Valid values are "host" and
+                "peripheral".
+                Reading: returns the current mode.
+What:           /sys/bus/platform/devices/tahvo-usb/vbus
+Date:           December 2013
+Contact:        Aaro Koskinen <aaro.koskinen@iki.fi>
+Description:
+                Read the current VBUS state.
+                Reading: returns "on" or "off".
diff --git a/Documentation/HOWTO b/Documentation/HOWTO
index 27faae3e3846..57cf5efb044d 100644
--- a/Documentation/HOWTO
+++ b/Documentation/HOWTO
@@ -112,7 +112,7 @@ required reading:
    Other excellent descriptions of how to create patches properly are:
        "The Perfect Patch"
-                http://kerneltrap.org/node/3737
+                http://www.ozlabs.org/~akpm/stuff/tpp.txt
        "Linux kernel patch submission format"
                http://linux.yyz.us/patch-format.html
@@ -579,7 +579,7 @@ all time.  It should describe the patch completely, containing:
 For more details on what this should all look like, please see the
 ChangeLog section of the document:
  "The Perfect Patch"
-      http://userweb.kernel.org/~akpm/stuff/tpp.txt
+      http://www.ozlabs.org/~akpm/stuff/tpp.txt
diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index f3778f8952da..910870b15acd 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -396,14 +396,14 @@ o	Each element of the form "3/3 ..>. 0:7 ^0" represents one rcu_node
 The output of "cat rcu/rcu_sched/rcu_pending" looks as follows:
-  0!np=26111 qsp=29 rpq=5386 cbr=1 cng=570 gpc=3674 gps=577 nn=15903
+  0!np=26111 qsp=29 rpq=5386 cbr=1 cng=570 gpc=3674 gps=577 nn=15903 ndw=0
-  1!np=28913 qsp=35 rpq=6097 cbr=1 cng=448 gpc=3700 gps=554 nn=18113
+  1!np=28913 qsp=35 rpq=6097 cbr=1 cng=448 gpc=3700 gps=554 nn=18113 ndw=0
-  2!np=32740 qsp=37 rpq=6202 cbr=0 cng=476 gpc=4627 gps=546 nn=20889
+  2!np=32740 qsp=37 rpq=6202 cbr=0 cng=476 gpc=4627 gps=546 nn=20889 ndw=0
-  3 np=23679 qsp=22 rpq=5044 cbr=1 cng=415 gpc=3403 gps=347 nn=14469
+  3 np=23679 qsp=22 rpq=5044 cbr=1 cng=415 gpc=3403 gps=347 nn=14469 ndw=0
-  4!np=30714 qsp=4 rpq=5574 cbr=0 cng=528 gpc=3931 gps=639 nn=20042
+  4!np=30714 qsp=4 rpq=5574 cbr=0 cng=528 gpc=3931 gps=639 nn=20042 ndw=0
-  5 np=28910 qsp=2 rpq=5246 cbr=0 cng=428 gpc=4105 gps=709 nn=18422
+  5 np=28910 qsp=2 rpq=5246 cbr=0 cng=428 gpc=4105 gps=709 nn=18422 ndw=0
-  6!np=38648 qsp=5 rpq=7076 cbr=0 cng=840 gpc=4072 gps=961 nn=25699
+  6!np=38648 qsp=5 rpq=7076 cbr=0 cng=840 gpc=4072 gps=961 nn=25699 ndw=0
-  7 np=37275 qsp=2 rpq=6873 cbr=0 cng=868 gpc=3416 gps=971 nn=25147
+  7 np=37275 qsp=2 rpq=6873 cbr=0 cng=868 gpc=3416 gps=971 nn=25147 ndw=0
 The fields are as follows:
@@ -432,6 +432,10 @@ o	"gpc" is the number of times that an old grace period had
 o       "gps" is the number of times that a new grace period had started,
        but this CPU was not yet aware of it.
+o       "ndw" is the number of times that a wakeup of an rcuo
+        callback-offload kthread had to be deferred in order to avoid
+        deadlock.
 o       "nn" is the number of times that this CPU needed nothing.
@@ -443,7 +447,7 @@ The output of "cat rcu/rcuboost" looks as follows:
    balk: nt=0 egt=6541 bt=0 nb=0 ny=126 nos=0
 This information is output only for rcu_preempt.  Each two-line entry
-corresponds to a leaf rcu_node strcuture.  The fields are as follows:
+corresponds to a leaf rcu_node structure.  The fields are as follows:
 o       "n:m" is the CPU-number range for the corresponding two-line
        entry.  In the sample output above, the first entry covers
diff --git a/Documentation/acpi/apei/einj.txt b/Documentation/acpi/apei/einj.txt
index a58b63da1a36..f51861bcb07b 100644
--- a/Documentation/acpi/apei/einj.txt
+++ b/Documentation/acpi/apei/einj.txt
@@ -45,11 +45,22 @@ directory apei/einj. The following files are provided.
  injection. Before this, please specify all necessary error
  parameters.
+- flags
+  Present for kernel version 3.13 and above. Used to specify which
+  of param{1..4} are valid and should be used by BIOS during injection.
+  Value is a bitmask as specified in ACPI5.0 spec for the
+  SET_ERROR_TYPE_WITH_ADDRESS data structure:
+        Bit 0 - Processor APIC field valid (see param3 below)
+        Bit 1 - Memory address and mask valid (param1 and param2)
+        Bit 2 - PCIe (seg,bus,dev,fn) valid (param4 below)
+  If set to zero, legacy behaviour is used where the type of injection
+  specifies just one bit set, and param1 is multiplexed.
 - param1
  This file is used to set the first error parameter value. Effect of
  parameter depends on error_type specified. For example, if error
  type is memory related type, the param1 should be a valid physical
-  memory address.
+  memory address. [Unless "flag" is set - see above]
 - param2
  This file is used to set the second error parameter value. Effect of
@@ -58,6 +69,12 @@ directory apei/einj. The following files are provided.
  address mask. Linux requires page or narrower granularity, say,
  0xfffffffffffff000.
+- param3
+  Used when the 0x1 bit is set in "flag" to specify the APIC id
+- param4
+  Used when the 0x4 bit is set in "flag" to specify target PCIe device
 - notrigger
  The EINJ mechanism is a two step process. First inject the error, then
  perform some actions to trigger it. Setting "notrigger" to 1 skips the
diff --git a/Documentation/acpi/enumeration.txt b/Documentation/acpi/enumeration.txt
index b994bcb32b92..2a1519b87177 100644
--- a/Documentation/acpi/enumeration.txt
+++ b/Documentation/acpi/enumeration.txt
@@ -293,36 +293,13 @@ the device to the driver. For example:
 These GPIO numbers are controller relative and path "\\_SB.PCI0.GPI0"
 specifies the path to the controller. In order to use these GPIOs in Linux
-we need to translate them to the Linux GPIO numbers.
+we need to translate them to the corresponding Linux GPIO descriptors.
-In a simple case of just getting the Linux GPIO number from device
+There is a standard GPIO API for that and is documented in
-resources one can use acpi_get_gpio_by_index() helper function. It takes
+Documentation/gpio.txt.
-pointer to the device and index of the GpioIo/GpioInt descriptor in the
-device resources list. For example:
-        int gpio_irq, gpio_power;
+In the above example we can get the corresponding two GPIO descriptors with
-        int ret;
+a code like this:
-        gpio_irq = acpi_get_gpio_by_index(dev, 1, NULL);
-        if (gpio_irq < 0)
-                /* handle error */
-        gpio_power = acpi_get_gpio_by_index(dev, 0, NULL);
-        if (gpio_power < 0)
-                /* handle error */
-        /* Now we can use the GPIO numbers */
-Other GpioIo parameters must be converted first by the driver to be
-suitable to the gpiolib before passing them.
-In case of GpioInt resource an additional call to gpio_to_irq() must be
-done before calling request_irq().
-Note that the above API is ACPI specific and not recommended for drivers
-that need to support non-ACPI systems. The recommended way is to use
-the descriptor based GPIO interfaces. The above example looks like this
-when converted to the GPIO desc:
        #include <linux/gpio/consumer.h>
        ...
@@ -339,4 +316,5 @@ when converted to the GPIO desc:
        /* Now we can use the GPIO descriptors */
-See also Documentation/gpio.txt.
+There are also devm_* versions of these functions which release the
+descriptors once the device is released.
diff --git a/Documentation/arm/Samsung-S3C24XX/GPIO.txt b/Documentation/arm/Samsung-S3C24XX/GPIO.txt
index 8b46c79679c4..0ebd7e2244d0 100644
--- a/Documentation/arm/Samsung-S3C24XX/GPIO.txt
+++ b/Documentation/arm/Samsung-S3C24XX/GPIO.txt
@@ -85,21 +85,10 @@ between the calls.
 Headers
 -------
-  See arch/arm/mach-s3c2410/include/mach/regs-gpio.h for the list
+  See arch/arm/mach-s3c24xx/include/mach/regs-gpio.h for the list
  of GPIO pins, and the configuration values for them. This
  is included by using #include <mach/regs-gpio.h>
-  The GPIO management functions are defined in the hardware
-  header arch/arm/mach-s3c2410/include/mach/hardware.h which can be
-  included by #include <mach/hardware.h>
-  A useful amount of documentation can be found in the hardware
-  header on how the GPIO functions (and others) work.
-  Whilst a number of these functions do make some checks on what
-  is passed to them, for speed of use, they may not always ensure
-  that the user supplied data to them is correct.
 PIN Numbers
 -----------
diff --git a/Documentation/circular-buffers.txt b/Documentation/circular-buffers.txt
index 8117e5bf6065..88951b179262 100644
--- a/Documentation/circular-buffers.txt
+++ b/Documentation/circular-buffers.txt
@@ -160,6 +160,7 @@ The producer will look something like this:
        spin_lock(&producer_lock);
        unsigned long head = buffer->head;
+        /* The spin_unlock() and next spin_lock() provide needed ordering. */
        unsigned long tail = ACCESS_ONCE(buffer->tail);
        if (CIRC_SPACE(head, tail, buffer->size) >= 1) {
@@ -168,9 +169,8 @@ The producer will look something like this:
                produce_item(item);
-                smp_wmb(); /* commit the item before incrementing the head */
+                smp_store_release(buffer->head,
+                                  (head + 1) & (buffer->size - 1));
-                buffer->head = (head + 1) & (buffer->size - 1);
                /* wake_up() will make sure that the head is committed before
                 * waking anyone up */
@@ -183,9 +183,14 @@ This will instruct the CPU that the contents of the new item must be written
 before the head index makes it available to the consumer and then instructs the
 CPU that the revised head index must be written before the consumer is woken.
-Note that wake_up() doesn't have to be the exact mechanism used, but whatever
+Note that wake_up() does not guarantee any sort of barrier unless something
-is used must guarantee a (write) memory barrier between the update of the head
+is actually awakened.  We therefore cannot rely on it for ordering.  However,
-index and the change of state of the consumer, if a change of state occurs.
+there is always one element of the array left empty.  Therefore, the
+producer must produce two elements before it could possibly corrupt the
+element currently being read by the consumer.  Therefore, the unlock-lock
+pair between consecutive invocations of the consumer provides the necessary
+ordering between the read of the index indicating that the consumer has
+vacated a given element and the write by the producer to that same element.
 THE CONSUMER
@@ -195,21 +200,20 @@ The consumer will look something like this:
        spin_lock(&consumer_lock);
-        unsigned long head = ACCESS_ONCE(buffer->head);
+        /* Read index before reading contents at that index. */
+        unsigned long head = smp_load_acquire(buffer->head);
        unsigned long tail = buffer->tail;
        if (CIRC_CNT(head, tail, buffer->size) >= 1) {
-                /* read index before reading contents at that index */
-                smp_read_barrier_depends();
                /* extract one item from the buffer */
                struct item *item = buffer[tail];
                consume_item(item);
-                smp_mb(); /* finish reading descriptor before incrementing tail */
+                /* Finish reading descriptor before incrementing tail. */
+                smp_store_release(buffer->tail,
-                buffer->tail = (tail + 1) & (buffer->size - 1);
+                                  (tail + 1) & (buffer->size - 1));
        }
        spin_unlock(&consumer_lock);
@@ -218,12 +222,17 @@ This will instruct the CPU to make sure the index is up to date before reading
 the new item, and then it shall make sure the CPU has finished reading the item
 before it writes the new tail pointer, which will erase the item.
+Note the use of ACCESS_ONCE() and smp_load_acquire() to read the
-Note the use of ACCESS_ONCE() in both algorithms to read the opposition index.
+opposition index.  This prevents the compiler from discarding and
-This prevents the compiler from discarding and reloading its cached value -
+reloading its cached value - which some compilers will do across
-which some compilers will do across smp_read_barrier_depends().  This isn't
+smp_read_barrier_depends().  This isn't strictly needed if you can
-strictly needed if you can be sure that the opposition index will _only_ be
+be sure that the opposition index will _only_ be used the once.
-used the once.
+The smp_load_acquire() additionally forces the CPU to order against
+subsequent memory references.  Similarly, smp_store_release() is used
+in both algorithms to write the thread's index.  This documents the
+fact that we are writing to something that can be read concurrently,
+prevents the compiler from tearing the store, and enforces ordering
+against previous accesses.
 ===============
diff --git a/Documentation/devicetree/bindings/arm/atmel-at91.txt b/Documentation/devicetree/bindings/arm/atmel-at91.txt
index 1196290082d1..78530e621a1e 100644
--- a/Documentation/devicetree/bindings/arm/atmel-at91.txt
+++ b/Documentation/devicetree/bindings/arm/atmel-at91.txt
@@ -20,6 +20,10 @@ TC/TCLIB Timer required properties:
 - interrupts: Should contain all interrupts for the TC block
  Note that you can specify several interrupt cells if the TC
  block has one interrupt per channel.
+- clock-names: tuple listing input clock names.
+        Required elements: "t0_clk"
+        Optional elements: "t1_clk", "t2_clk"
+- clocks: phandles to input clocks.
 Examples:
@@ -28,6 +32,8 @@ One interrupt per TC block:
                compatible = "atmel,at91rm9200-tcb";
                reg = <0xfff7c000 0x100>;
                interrupts = <18 4>;
+                clocks = <&tcb0_clk>;
+                clock-names = "t0_clk";
        };
 One interrupt per TC channel in a TC block:
@@ -35,6 +41,8 @@ One interrupt per TC channel in a TC block:
                compatible = "atmel,at91rm9200-tcb";
                reg = <0xfffdc000 0x100>;
                interrupts = <26 4 27 4 28 4>;
+                clocks = <&tcb1_clk>;
+                clock-names = "t0_clk";
        };
 RSTC Reset Controller required properties:
diff --git a/Documentation/devicetree/bindings/extcon/extcon-palmas.txt b/Documentation/devicetree/bindings/extcon/extcon-palmas.txt
index 7dab6a8f4a0e..45414bbcd945 100644
--- a/Documentation/devicetree/bindings/extcon/extcon-palmas.txt
+++ b/Documentation/devicetree/bindings/extcon/extcon-palmas.txt
@@ -2,7 +2,11 @@ EXTCON FOR PALMAS/TWL CHIPS
 PALMAS USB COMPARATOR
 Required Properties:
- - compatible : Should be "ti,palmas-usb" or "ti,twl6035-usb"
+ - compatible: should contain one of:
+   * "ti,palmas-usb-vid".
+   * "ti,twl6035-usb-vid".
+   * "ti,palmas-usb" (DEPRECATED - use "ti,palmas-usb-vid").
+   * "ti,twl6035-usb" (DEPRECATED - use "ti,twl6035-usb-vid").
 Optional Properties:
 - ti,wakeup : To enable the wakeup comparator in probe
diff --git a/Documentation/devicetree/bindings/gpio/gpio-mcp23s08.txt b/Documentation/devicetree/bindings/gpio/gpio-mcp23s08.txt
index daa30174bcc1..3ddc7ccfe5f3 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-mcp23s08.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-mcp23s08.txt
@@ -38,12 +38,38 @@ Required device specific properties (only for SPI chips):
    removed.
 - spi-max-frequency = The maximum frequency this chip is able to handle
-Example I2C:
+Optional properties:
+- #interrupt-cells : Should be two.
+  - first cell is the pin number
+  - second cell is used to specify flags.
+- interrupt-controller: Marks the device node as a interrupt controller.
+NOTE: The interrupt functionality is only supported for i2c versions of the
+chips. The spi chips can also do the interrupts, but this is not supported by
+the linux driver yet.
+Optional device specific properties:
+- microchip,irq-mirror: Sets the mirror flag in the IOCON register. Devices
+        with two interrupt outputs (these are the devices ending with 17 and
+        those that have 16 IOs) have two IO banks: IO 0-7 form bank 1 and
+        IO 8-15 are bank 2. These chips have two different interrupt outputs:
+        One for bank 1 and another for bank 2. If irq-mirror is set, both
+        interrupts are generated regardless of the bank that an input change
+        occured on. If it is not set, the interrupt are only generated for the
+        bank they belong to.
+        On devices with only one interrupt output this property is useless.
+Example I2C (with interrupt):
 gpiom1: gpio@20 {
        compatible = "microchip,mcp23017";
        gpio-controller;
        #gpio-cells = <2>;
        reg = <0x20>;
+        interrupt-parent = <&gpio1>;
+        interrupts = <17 IRQ_TYPE_LEVEL_LOW>;
+        interrupt-controller;
+        #interrupt-cells=<2>;
+        microchip,irq-mirror;
 };
 Example SPI:
diff --git a/Documentation/devicetree/bindings/gpio/moxa,moxart-gpio.txt b/Documentation/devicetree/bindings/gpio/moxa,moxart-gpio.txt
new file mode 100644
index 000000000000..f8e8f185a3db
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/moxa,moxart-gpio.txt
@@ -0,0 +1,19 @@
+MOXA ART GPIO Controller
+Required properties:
+- #gpio-cells : Should be 2, The first cell is the pin number,
+                the second cell is used to specify polarity:
+                        0 = active high
+                        1 = active low
+- compatible : Must be "moxa,moxart-gpio"
+- reg : Should contain registers location and length
+Example:
+        gpio: gpio@98700000 {
+                gpio-controller;
+                #gpio-cells = <2>;
+                compatible = "moxa,moxart-gpio";
+                reg =   <0x98700000 0xC>;
+        };
diff --git a/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt b/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt
index 8655df9440d5..f61cef74a212 100644
--- a/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt
+++ b/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt
@@ -2,10 +2,11 @@
 Required Properties:
-  - compatible: should be one of the following.
+  - compatible: should contain one of the following.
    - "renesas,gpio-r8a7778": for R8A7778 (R-Mobile M1) compatible GPIO controller.
    - "renesas,gpio-r8a7779": for R8A7779 (R-Car H1) compatible GPIO controller.
    - "renesas,gpio-r8a7790": for R8A7790 (R-Car H2) compatible GPIO controller.
+    - "renesas,gpio-r8a7791": for R8A7791 (R-Car M2) compatible GPIO controller.
    - "renesas,gpio-rcar": for generic R-Car GPIO controller.
  - reg: Base address and length of each memory resource used by the GPIO
diff --git a/Documentation/devicetree/bindings/i2c/i2c-at91.txt b/Documentation/devicetree/bindings/i2c/i2c-at91.txt
index b689a0d9441c..4fade84bea16 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-at91.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-at91.txt
@@ -9,6 +9,7 @@ Required properties :
 - interrupts: interrupt number to the cpu.
 - #address-cells = <1>;
 - #size-cells = <0>;
+- clocks: phandles to input clocks.
 Optional properties:
 - Child nodes conforming to i2c bus binding
@@ -21,6 +22,7 @@ i2c0: i2c@fff84000 {
        interrupts = <12 4 6>;
        #address-cells = <1>;
        #size-cells = <0>;
+        clocks = <&twi0_clk>;
        24c512@50 {
                compatible = "24c512";
diff --git a/Documentation/devicetree/bindings/i2c/i2c-mux-pca954x.txt b/Documentation/devicetree/bindings/i2c/i2c-mux-pca954x.txt
new file mode 100644
index 000000000000..34a3fb6f8488
--- /dev/null
+++ b/Documentation/devicetree/bindings/i2c/i2c-mux-pca954x.txt
@@ -0,0 +1,50 @@
+* NXP PCA954x I2C bus switch
+Required Properties:
+  - compatible: Must contain one of the following.
+    "nxp,pca9540", "nxp,pca9542", "nxp,pca9543", "nxp,pca9544",
+    "nxp,pca9545", "nxp,pca9546", "nxp,pca9547", "nxp,pca9548"
+  - reg: The I2C address of the device.
+  The following required properties are defined externally:
+  - Standard I2C mux properties. See i2c-mux.txt in this directory.
+  - I2C child bus nodes. See i2c-mux.txt in this directory.
+Optional Properties:
+  - reset-gpios: Reference to the GPIO connected to the reset input.
+Example:
+        i2c-switch@74 {
+                compatible = "nxp,pca9548";
+                #address-cells = <1>;
+                #size-cells = <0>;
+                reg = <0x74>;
+                i2c@2 {
+                        #address-cells = <1>;
+                        #size-cells = <0>;
+                        reg = <2>;
+                        eeprom@54 {
+                                compatible = "at,24c08";
+                                reg = <0x54>;
+                        };
+                };
+                i2c@4 {
+                        #address-cells = <1>;
+                        #size-cells = <0>;
+                        reg = <4>;
+                        rtc@51 {
+                                compatible = "nxp,pcf8563";
+                                reg = <0x51>;
+                        };
+                };
+        };
diff --git a/Documentation/devicetree/bindings/i2c/i2c-riic.txt b/Documentation/devicetree/bindings/i2c/i2c-riic.txt
new file mode 100644
index 000000000000..0bcc4716c319
--- /dev/null
+++ b/Documentation/devicetree/bindings/i2c/i2c-riic.txt
@@ -0,0 +1,29 @@
+Device tree configuration for Renesas RIIC driver
+Required properties:
+- compatible      : "renesas,riic-<soctype>". "renesas,riic-rz" as fallback
+- reg             : address start and address range size of device
+- interrupts      : 8 interrupts (TEI, RI, TI, SPI, STI, NAKI, ALI, TMOI)
+- clock-frequency : frequency of bus clock in Hz
+- #address-cells  : should be <1>
+- #size-cells     : should be <0>
+Pinctrl properties might be needed, too. See there.
+Example:
+        i2c0: i2c@fcfee000 {
+                compatible = "renesas,riic-r7s72100", "renesas,riic-rz";
+                reg = <0xfcfee000 0x44>;
+                interrupts = <0 157 IRQ_TYPE_LEVEL_HIGH>,
+                             <0 158 IRQ_TYPE_EDGE_RISING>,
+                             <0 159 IRQ_TYPE_EDGE_RISING>,
+                             <0 160 IRQ_TYPE_LEVEL_HIGH>,
+                             <0 161 IRQ_TYPE_LEVEL_HIGH>,
+                             <0 162 IRQ_TYPE_LEVEL_HIGH>,
+                             <0 163 IRQ_TYPE_LEVEL_HIGH>,
+                             <0 164 IRQ_TYPE_LEVEL_HIGH>;
+                clock-frequency = <100000>;
+                #address-cells = <1>;
+                #size-cells = <0>;
+        };
diff --git a/Documentation/devicetree/bindings/i2c/i2c-s3c2410.txt b/Documentation/devicetree/bindings/i2c/i2c-s3c2410.txt
index 296eb4536129..278de8e64bbf 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-s3c2410.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-s3c2410.txt
@@ -10,6 +10,8 @@ Required properties:
          inside HDMIPHY block found on several samsung SoCs
      (d) "samsung, exynos5440-i2c", for s3c2440-like i2c used
           on EXYNOS5440 which does not need GPIO configuration.
+      (e) "samsung, exynos5-sata-phy-i2c", for s3c2440-like i2c used as
+           a host to SATA PHY controller on an internal bus.
  - reg: physical base address of the controller and length of memory mapped
    region.
  - interrupts: interrupt number to the cpu.
diff --git a/Documentation/devicetree/bindings/i2c/trivial-devices.txt b/Documentation/devicetree/bindings/i2c/trivial-devices.txt
index b1cb3415e6f1..c65f71cfaa5c 100644
--- a/Documentation/devicetree/bindings/i2c/trivial-devices.txt
+++ b/Documentation/devicetree/bindings/i2c/trivial-devices.txt
@@ -16,6 +16,7 @@ adt7461			+/-1C TDM Extended Temp Range I.C
 at,24c08                i2c serial eeprom  (24cxx)
 atmel,24c02             i2c serial eeprom  (24cxx)
 atmel,at97sc3204t       i2c trusted platform module (TPM)
+capella,cm32181         CM32181: Ambient Light Sensor
 catalyst,24c32          i2c serial eeprom
 dallas,ds1307           64 x 8, Serial, I2C Real-Time Clock
 dallas,ds1338           I2C RTC with 56-Byte NV RAM
diff --git a/Documentation/devicetree/bindings/iio/humidity/dht11.txt b/Documentation/devicetree/bindings/iio/humidity/dht11.txt
new file mode 100644
index 000000000000..ecc24c199fd6
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/humidity/dht11.txt
@@ -0,0 +1,14 @@
+* DHT11 humidity/temperature sensor (and compatibles like DHT22)
+Required properties:
+  - compatible: Should be "dht11"
+  - gpios: Should specify the GPIO connected to the sensor's data
+    line, see "gpios property" in
+    Documentation/devicetree/bindings/gpio/gpio.txt.
+Example:
+humidity_sensor {
+        compatible = "dht11";
+        gpios = <&gpio0 6 0>;
+}
diff --git a/Documentation/devicetree/bindings/iio/light/tsl2563.txt b/Documentation/devicetree/bindings/iio/light/tsl2563.txt
new file mode 100644
index 000000000000..f91e809e736e
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/light/tsl2563.txt
@@ -0,0 +1,19 @@
+* AMS TAOS TSL2563 ambient light sensor
+Required properties:
+  - compatible : should be "amstaos,tsl2563"
+  - reg : the I2C address of the sensor
+Optional properties:
+  - amstaos,cover-comp-gain : integer used as multiplier for gain
+                              compensation (default = 1)
+Example:
+tsl2563@29 {
+        compatible = "amstaos,tsl2563";
+        reg = <0x29>;
+        amstaos,cover-comp-gain = <16>;
+};
diff --git a/Documentation/devicetree/bindings/iio/magnetometer/hmc5843.txt b/Documentation/devicetree/bindings/iio/magnetometer/hmc5843.txt
new file mode 100644
index 000000000000..90d5f34db04e
--- /dev/null
+++ b/Documentation/devicetree/bindings/iio/magnetometer/hmc5843.txt
@@ -0,0 +1,17 @@
+* Honeywell HMC5843 magnetometer sensor
+Required properties:
+  - compatible : should be "honeywell,hmc5843"
+  - reg : the I2C address of the magnetometer - typically 0x1e
+Optional properties:
+  - gpios : should be device tree identifier of the magnetometer DRDY pin
+Example:
+hmc5843@1e {
+        compatible = "honeywell,hmc5843"
+        reg = <0x1e>;
+};
diff --git a/Documentation/devicetree/bindings/misc/atmel-ssc.txt b/Documentation/devicetree/bindings/misc/atmel-ssc.txt
index a45ae08c8ed1..60960b2755f4 100644
--- a/Documentation/devicetree/bindings/misc/atmel-ssc.txt
+++ b/Documentation/devicetree/bindings/misc/atmel-ssc.txt
@@ -6,6 +6,9 @@ Required properties:
        - atmel,at91sam9g45-ssc: support dma transfer
 - reg: Should contain SSC registers location and length
 - interrupts: Should contain SSC interrupt
+- clock-names: tuple listing input clock names.
+        Required elements: "pclk"
+- clocks: phandles to input clocks.
 Required properties for devices compatible with "atmel,at91sam9g45-ssc":
@@ -20,6 +23,8 @@ ssc0: ssc@fffbc000 {
        compatible = "atmel,at91rm9200-ssc";
        reg = <0xfffbc000 0x4000>;
        interrupts = <14 4 5>;
+        clocks = <&ssc0_clk>;
+        clock-names = "pclk";
 };
 - DMA transfer:
diff --git a/Documentation/devicetree/bindings/misc/bmp085.txt b/Documentation/devicetree/bindings/misc/bmp085.txt
index 91dfda2e4e11..d7a6deb6b21e 100644
--- a/Documentation/devicetree/bindings/misc/bmp085.txt
+++ b/Documentation/devicetree/bindings/misc/bmp085.txt
@@ -8,6 +8,8 @@ Optional properties:
 - temp-measurement-period: temperature measurement period (milliseconds)
 - default-oversampling: default oversampling value to be used at startup,
  value range is 0-3 with rising sensitivity.
+- interrupt-parent: should be the phandle for the interrupt controller
+- interrupts: interrupt mapping for IRQ
 Example:
@@ -17,4 +19,6 @@ pressure@77 {
        chip-id = <10>;
        temp-measurement-period = <100>;
        default-oversampling = <2>;
+        interrupt-parent = <&gpio0>;
+        interrupts = <25 IRQ_TYPE_EDGE_RISING>;
 };
diff --git a/Documentation/devicetree/bindings/phy/bcm-phy.txt b/Documentation/devicetree/bindings/phy/bcm-phy.txt
new file mode 100644
index 000000000000..3dc8b3d2ffbb
--- /dev/null
+++ b/Documentation/devicetree/bindings/phy/bcm-phy.txt
@@ -0,0 +1,15 @@
+BROADCOM KONA USB2 PHY
+Required properties:
+ - compatible: brcm,kona-usb2-phy
+ - reg: offset and length of the PHY registers
+ - #phy-cells: must be 0
+Refer to phy/phy-bindings.txt for the generic PHY binding properties
+Example:
+        usbphy: usb-phy@3f130000 {
+                compatible = "brcm,kona-usb2-phy";
+                reg = <0x3f130000 0x28>;
+                #phy-cells = <0>;
+        };
diff --git a/Documentation/devicetree/bindings/pinctrl/brcm,capri-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/brcm,capri-pinctrl.txt
new file mode 100644
index 000000000000..9e9e9ef9f852
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/brcm,capri-pinctrl.txt
@@ -0,0 +1,461 @@
+Broadcom Capri Pin Controller
+This is a pin controller for the Broadcom BCM281xx SoC family, which includes
+BCM11130, BCM11140, BCM11351, BCM28145, and BCM28155 SoCs.
+=== Pin Controller Node ===
+Required Properties:
+- compatible:   Must be "brcm,capri-pinctrl".
+- reg:          Base address of the PAD Controller register block and the size
+                of the block.
+For example, the following is the bare minimum node:
+        pinctrl@35004800 {
+                compatible = "brcm,capri-pinctrl";
+                reg = <0x35004800 0x430>;
+        };
+As a pin controller device, in addition to the required properties, this node
+should also contain the pin configuration nodes that client devices reference,
+if any.
+=== Pin Configuration Node ===
+Each pin configuration node is a sub-node of the pin controller node and is a
+container of an arbitrary number of subnodes, called pin group nodes in this
+document.
+Please refer to the pinctrl-bindings.txt in this directory for details of the
+common pinctrl bindings used by client devices, including the definition of a
+"pin configuration node".
+=== Pin Group Node ===
+A pin group node specifies the desired pin mux and/or pin configuration for an
+arbitrary number of pins.  The name of the pin group node is optional and not
+used.
+A pin group node only affects the properties specified in the node, and has no
+effect on any properties that are omitted.
+The pin group node accepts a subset of the generic pin config properties. For
+details generic pin config properties, please refer to pinctrl-bindings.txt
+and <include/linux/pinctrl/pinconfig-generic.h>.
+Each pin controlled by this pin controller belong to one of three types:
+Standard, I2C, and HDMI.  Each type accepts a different set of pin config
+properties.  A list of pins and their types is provided below.
+Required Properties (applicable to all pins):
+- pins:         Multiple strings.  Specifies the name(s) of one or more pins to
+                be configured by this node.
+Optional Properties (for standard pins):
+- function:                     String. Specifies the pin mux selection. Values
+                                must be one of: "alt1", "alt2", "alt3", "alt4"
+- input-schmitt-enable:         No arguments. Enable schmitt-trigger mode.
+- input-schmitt-disable:        No arguments. Disable schmitt-trigger mode.
+- bias-pull-up:                 No arguments. Pull up on pin.
+- bias-pull-down:               No arguments. Pull down on pin.
+- bias-disable:                 No arguments. Disable pin bias.
+- slew-rate:                    Integer. Meaning depends on configured pin mux:
+                                *_SCL or *_SDA:
+                                        0: Standard(100kbps)& Fast(400kbps) mode
+                                        1: Highspeed (3.4Mbps) mode
+                                IC_DM or IC_DP:
+                                        0: normal slew rate
+                                        1: fast slew rate
+                                Otherwise:
+                                        0: fast slew rate
+                                        1: normal slew rate
+- input-enable:                 No arguements. Enable input (does not affect
+                                output.)
+- input-disable:                No arguements. Disable input (does not affect
+                                output.)
+- drive-strength:               Integer. Drive strength in mA.  Valid values are
+                                2, 4, 6, 8, 10, 12, 14, 16 mA.
+Optional Properties (for I2C pins):
+- function:                     String. Specifies the pin mux selection. Values
+                                must be one of: "alt1", "alt2", "alt3", "alt4"
+- bias-pull-up:                 Integer. Pull up strength in Ohm. There are 3
+                                pull-up resisitors (1.2k, 1.8k, 2.7k) available
+                                in parallel for I2C pins, so the valid values
+                                are: 568, 720, 831, 1080, 1200, 1800, 2700 Ohm.
+- bias-disable:                 No arguments. Disable pin bias.
+- slew-rate:                    Integer. Meaning depends on configured pin mux:
+                                *_SCL or *_SDA:
+                                        0: Standard(100kbps)& Fast(400kbps) mode
+                                        1: Highspeed (3.4Mbps) mode
+                                IC_DM or IC_DP:
+                                        0: normal slew rate
+                                        1: fast slew rate
+                                Otherwise:
+                                        0: fast slew rate
+                                        1: normal slew rate
+- input-enable:                 No arguements. Enable input (does not affect
+                                output.)
+- input-disable:                No arguements. Disable input (does not affect
+                                output.)
+Optional Properties (for HDMI pins):
+- function:                     String. Specifies the pin mux selection. Values
+                                must be one of: "alt1", "alt2", "alt3", "alt4"
+- slew-rate:                    Integer. Controls slew rate.
+                                        0: Standard(100kbps)& Fast(400kbps) mode
+                                        1: Highspeed (3.4Mbps) mode
+- input-enable:                 No arguements. Enable input (does not affect
+                                output.)
+- input-disable:                No arguements. Disable input (does not affect
+                                output.)
+Example:
+// pin controller node
+pinctrl@35004800 {
+        compatible = "brcm,capri-pinctrl";
+        reg = <0x35004800 0x430>;
+        // pin configuration node
+        dev_a_default: dev_a_active {
+                //group node defining 1 standard pin
+                grp_1 {
+                        pins            = "std_pin1";
+                        function        = "alt1";
+                        input-schmitt-enable;
+                        bias-disable;
+                        slew-rate       = <1>;
+                        drive-strength  = <4>;
+                };
+                // group node defining 2 I2C pins
+                grp_2 {
+                        pins            = "i2c_pin1", "i2c_pin2";
+                        function        = "alt2";
+                        bias-pull-up    = <720>;
+                        input-enable;
+                };
+                // group node defining 2 HDMI pins
+                grp_3 {
+                        pins            = "hdmi_pin1", "hdmi_pin2";
+                        function        = "alt3";
+                        slew-rate       = <1>;
+                };
+                // other pin group nodes
+                ...
+        };
+        // other pin configuration nodes
+        ...
+};
+In the example above, "dev_a_active" is a pin configuration node with a number
+of sub-nodes.  In the pin group node "grp_1", one pin, "std_pin1", is defined in
+the "pins" property.  Thus, the remaining properties in the "grp_1" node applies
+only to this pin, including the following settings:
+ - setting pinmux to "alt1"
+ - enabling schmitt-trigger (hystersis) mode
+ - disabling pin bias
+ - setting the slew-rate to 1
+ - setting the drive strength to 4 mA
+Note that neither "input-enable" nor "input-disable" was specified - the pinctrl
+subsystem will therefore leave this property unchanged from whatever state it
+was in before applying these changes.
+The "pins" property in the pin group node "grp_2" specifies two pins -
+"i2c_pin1" and "i2c_pin2"; the remaining properties in this pin group node,
+therefore, applies to both of these pins.  The properties include:
+ - setting pinmux to "alt2"
+ - setting pull-up resistance to 720 Ohm (ie. enabling 1.2k and 1.8k resistors
+   in parallel)
+ - enabling both pins' input
+"slew-rate" is not specified in this pin group node, so the slew-rate for these
+pins are left as-is.
+Finally, "grp_3" defines two HDMI pins.  The following properties are applied to
+both pins:
+ - setting pinmux to "alt3"
+ - setting slew-rate to 1; for HDMI pins, this corresponds to the 3.4 Mbps
+   Highspeed mode
+The input is neither enabled or disabled, and is left untouched.
+=== Pin Names and Type ===
+The following are valid pin names and their pin types:
+        "adcsync",              Standard
+        "bat_rm",               Standard
+        "bsc1_scl",             I2C
+        "bsc1_sda",             I2C
+        "bsc2_scl",             I2C
+        "bsc2_sda",             I2C
+        "classgpwr",            Standard
+        "clk_cx8",              Standard
+        "clkout_0",             Standard
+        "clkout_1",             Standard
+        "clkout_2",             Standard
+        "clkout_3",             Standard
+        "clkreq_in_0",          Standard
+        "clkreq_in_1",          Standard
+        "cws_sys_req1",         Standard
+        "cws_sys_req2",         Standard
+        "cws_sys_req3",         Standard
+        "digmic1_clk",          Standard
+        "digmic1_dq",           Standard
+        "digmic2_clk",          Standard
+        "digmic2_dq",           Standard
+        "gpen13",               Standard
+        "gpen14",               Standard
+        "gpen15",               Standard
+        "gpio00",               Standard
+        "gpio01",               Standard
+        "gpio02",               Standard
+        "gpio03",               Standard
+        "gpio04",               Standard
+        "gpio05",               Standard
+        "gpio06",               Standard
+        "gpio07",               Standard
+        "gpio08",               Standard
+        "gpio09",               Standard
+        "gpio10",               Standard
+        "gpio11",               Standard
+        "gpio12",               Standard
+        "gpio13",               Standard
+        "gpio14",               Standard
+        "gps_pablank",          Standard
+        "gps_tmark",            Standard
+        "hdmi_scl",             HDMI
+        "hdmi_sda",             HDMI
+        "ic_dm",                Standard
+        "ic_dp",                Standard
+        "kp_col_ip_0",          Standard
+        "kp_col_ip_1",          Standard
+        "kp_col_ip_2",          Standard
+        "kp_col_ip_3",          Standard
+        "kp_row_op_0",          Standard
+        "kp_row_op_1",          Standard
+        "kp_row_op_2",          Standard
+        "kp_row_op_3",          Standard
+        "lcd_b_0",              Standard
+        "lcd_b_1",              Standard
+        "lcd_b_2",              Standard
+        "lcd_b_3",              Standard
+        "lcd_b_4",              Standard
+        "lcd_b_5",              Standard
+        "lcd_b_6",              Standard
+        "lcd_b_7",              Standard
+        "lcd_g_0",              Standard
+        "lcd_g_1",              Standard
+        "lcd_g_2",              Standard
+        "lcd_g_3",              Standard
+        "lcd_g_4",              Standard
+        "lcd_g_5",              Standard
+        "lcd_g_6",              Standard
+        "lcd_g_7",              Standard
+        "lcd_hsync",            Standard
+        "lcd_oe",               Standard
+        "lcd_pclk",             Standard
+        "lcd_r_0",              Standard
+        "lcd_r_1",              Standard
+        "lcd_r_2",              Standard
+        "lcd_r_3",              Standard
+        "lcd_r_4",              Standard
+        "lcd_r_5",              Standard
+        "lcd_r_6",              Standard
+        "lcd_r_7",              Standard
+        "lcd_vsync",            Standard
+        "mdmgpio0",             Standard
+        "mdmgpio1",             Standard
+        "mdmgpio2",             Standard
+        "mdmgpio3",             Standard
+        "mdmgpio4",             Standard
+        "mdmgpio5",             Standard
+        "mdmgpio6",             Standard
+        "mdmgpio7",             Standard
+        "mdmgpio8",             Standard
+        "mphi_data_0",          Standard
+        "mphi_data_1",          Standard
+        "mphi_data_2",          Standard
+        "mphi_data_3",          Standard
+        "mphi_data_4",          Standard
+        "mphi_data_5",          Standard
+        "mphi_data_6",          Standard
+        "mphi_data_7",          Standard
+        "mphi_data_8",          Standard
+        "mphi_data_9",          Standard
+        "mphi_data_10",         Standard
+        "mphi_data_11",         Standard
+        "mphi_data_12",         Standard
+        "mphi_data_13",         Standard
+        "mphi_data_14",         Standard
+        "mphi_data_15",         Standard
+        "mphi_ha0",             Standard
+        "mphi_hat0",            Standard
+        "mphi_hat1",            Standard
+        "mphi_hce0_n",          Standard
+        "mphi_hce1_n",          Standard
+        "mphi_hrd_n",           Standard
+        "mphi_hwr_n",           Standard
+        "mphi_run0",            Standard
+        "mphi_run1",            Standard
+        "mtx_scan_clk",         Standard
+        "mtx_scan_data",        Standard
+        "nand_ad_0",            Standard
+        "nand_ad_1",            Standard
+        "nand_ad_2",            Standard
+        "nand_ad_3",            Standard
+        "nand_ad_4",            Standard
+        "nand_ad_5",            Standard
+        "nand_ad_6",            Standard
+        "nand_ad_7",            Standard
+        "nand_ale",             Standard
+        "nand_cen_0",           Standard
+        "nand_cen_1",           Standard
+        "nand_cle",             Standard
+        "nand_oen",             Standard
+        "nand_rdy_0",           Standard
+        "nand_rdy_1",           Standard
+        "nand_wen",             Standard
+        "nand_wp",              Standard
+        "pc1",                  Standard
+        "pc2",                  Standard
+        "pmu_int",              Standard
+        "pmu_scl",              I2C
+        "pmu_sda",              I2C
+        "rfst2g_mtsloten3g",    Standard
+        "rgmii_0_rx_ctl",       Standard
+        "rgmii_0_rxc",          Standard
+        "rgmii_0_rxd_0",        Standard
+        "rgmii_0_rxd_1",        Standard
+        "rgmii_0_rxd_2",        Standard
+        "rgmii_0_rxd_3",        Standard
+        "rgmii_0_tx_ctl",       Standard
+        "rgmii_0_txc",          Standard
+        "rgmii_0_txd_0",        Standard
+        "rgmii_0_txd_1",        Standard
+        "rgmii_0_txd_2",        Standard
+        "rgmii_0_txd_3",        Standard
+        "rgmii_1_rx_ctl",       Standard
+        "rgmii_1_rxc",          Standard
+        "rgmii_1_rxd_0",        Standard
+        "rgmii_1_rxd_1",        Standard
+        "rgmii_1_rxd_2",        Standard
+        "rgmii_1_rxd_3",        Standard
+        "rgmii_1_tx_ctl",       Standard
+        "rgmii_1_txc",          Standard
+        "rgmii_1_txd_0",        Standard
+        "rgmii_1_txd_1",        Standard
+        "rgmii_1_txd_2",        Standard
+        "rgmii_1_txd_3",        Standard
+        "rgmii_gpio_0",         Standard
+        "rgmii_gpio_1",         Standard
+        "rgmii_gpio_2",         Standard
+        "rgmii_gpio_3",         Standard
+        "rtxdata2g_txdata3g1",  Standard
+        "rtxen2g_txdata3g2",    Standard
+        "rxdata3g0",            Standard
+        "rxdata3g1",            Standard
+        "rxdata3g2",            Standard
+        "sdio1_clk",            Standard
+        "sdio1_cmd",            Standard
+        "sdio1_data_0",         Standard
+        "sdio1_data_1",         Standard
+        "sdio1_data_2",         Standard
+        "sdio1_data_3",         Standard
+        "sdio4_clk",            Standard
+        "sdio4_cmd",            Standard
+        "sdio4_data_0",         Standard
+        "sdio4_data_1",         Standard
+        "sdio4_data_2",         Standard
+        "sdio4_data_3",         Standard
+        "sim_clk",              Standard
+        "sim_data",             Standard
+        "sim_det",              Standard
+        "sim_resetn",           Standard
+        "sim2_clk",             Standard
+        "sim2_data",            Standard
+        "sim2_det",             Standard
+        "sim2_resetn",          Standard
+        "sri_c",                Standard
+        "sri_d",                Standard
+        "sri_e",                Standard
+        "ssp_extclk",           Standard
+        "ssp0_clk",             Standard
+        "ssp0_fs",              Standard
+        "ssp0_rxd",             Standard
+        "ssp0_txd",             Standard
+        "ssp2_clk",             Standard
+        "ssp2_fs_0",            Standard
+        "ssp2_fs_1",            Standard
+        "ssp2_fs_2",            Standard
+        "ssp2_fs_3",            Standard
+        "ssp2_rxd_0",           Standard
+        "ssp2_rxd_1",           Standard
+        "ssp2_txd_0",           Standard
+        "ssp2_txd_1",           Standard
+        "ssp3_clk",             Standard
+        "ssp3_fs",              Standard
+        "ssp3_rxd",             Standard
+        "ssp3_txd",             Standard
+        "ssp4_clk",             Standard
+        "ssp4_fs",              Standard
+        "ssp4_rxd",             Standard
+        "ssp4_txd",             Standard
+        "ssp5_clk",             Standard
+        "ssp5_fs",              Standard
+        "ssp5_rxd",             Standard
+        "ssp5_txd",             Standard
+        "ssp6_clk",             Standard
+        "ssp6_fs",              Standard
+        "ssp6_rxd",             Standard
+        "ssp6_txd",             Standard
+        "stat_1",               Standard
+        "stat_2",               Standard
+        "sysclken",             Standard
+        "traceclk",             Standard
+        "tracedt00",            Standard
+        "tracedt01",            Standard
+        "tracedt02",            Standard
+        "tracedt03",            Standard
+        "tracedt04",            Standard
+        "tracedt05",            Standard
+        "tracedt06",            Standard
+        "tracedt07",            Standard
+        "tracedt08",            Standard
+        "tracedt09",            Standard
+        "tracedt10",            Standard
+        "tracedt11",            Standard
+        "tracedt12",            Standard
+        "tracedt13",            Standard
+        "tracedt14",            Standard
+        "tracedt15",            Standard
+        "txdata3g0",            Standard
+        "txpwrind",             Standard
+        "uartb1_ucts",          Standard
+        "uartb1_urts",          Standard
+        "uartb1_urxd",          Standard
+        "uartb1_utxd",          Standard
+        "uartb2_urxd",          Standard
+        "uartb2_utxd",          Standard
+        "uartb3_ucts",          Standard
+        "uartb3_urts",          Standard
+        "uartb3_urxd",          Standard
+        "uartb3_utxd",          Standard
+        "uartb4_ucts",          Standard
+        "uartb4_urts",          Standard
+        "uartb4_urxd",          Standard
+        "uartb4_utxd",          Standard
+        "vc_cam1_scl",          I2C
+        "vc_cam1_sda",          I2C
+        "vc_cam2_scl",          I2C
+        "vc_cam2_sda",          I2C
+        "vc_cam3_scl",          I2C
+        "vc_cam3_sda",          I2C
diff --git a/Documentation/devicetree/bindings/pinctrl/fsl,imx25-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/fsl,imx25-pinctrl.txt
new file mode 100644
index 000000000000..fd653bde18d5
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/fsl,imx25-pinctrl.txt
@@ -0,0 +1,23 @@
+* Freescale IMX25 IOMUX Controller
+Please refer to fsl,imx-pinctrl.txt in this directory for common binding part
+and usage.
+CONFIG bits definition:
+PAD_CTL_HYS                     (1 << 8)
+PAD_CTL_PKE                     (1 << 7)
+PAD_CTL_PUE                     (1 << 6)
+PAD_CTL_PUS_100K_DOWN           (0 << 4)
+PAD_CTL_PUS_47K_UP              (1 << 4)
+PAD_CTL_PUS_100K_UP             (2 << 4)
+PAD_CTL_PUS_22K_UP              (3 << 4)
+PAD_CTL_ODE_CMOS                (0 << 3)
+PAD_CTL_ODE_OPENDRAIN           (1 << 3)
+PAD_CTL_DSE_NOMINAL             (0 << 1)
+PAD_CTL_DSE_HIGH                (1 << 1)
+PAD_CTL_DSE_MAX                 (2 << 1)
+PAD_CTL_SRE_FAST                (1 << 0)
+PAD_CTL_SRE_SLOW                (0 << 0)
+Refer to imx25-pinfunc.h in device tree source folder for all available
+imx25 PIN_FUNC_ID.
diff --git a/Documentation/devicetree/bindings/pinctrl/fsl,imx27-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/fsl,imx27-pinctrl.txt
index 353eca0efbf8..d1706ea82572 100644
--- a/Documentation/devicetree/bindings/pinctrl/fsl,imx27-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/fsl,imx27-pinctrl.txt
@@ -52,12 +52,25 @@ Required properties for pin configuration node:
  CONFIG can be 0 or 1, meaning Pullup disable/enable.
+The iomux controller has gpio child nodes which are embedded in the iomux
+control registers. They have to be defined as child nodes of the iomux device
+node. If gpio subnodes are defined "#address-cells", "#size-cells" and "ranges"
+properties for the iomux device node are required.
 Example:
 iomuxc: iomuxc@10015000 {
        compatible = "fsl,imx27-iomuxc";
        reg = <0x10015000 0x600>;
+        #address-cells = <1>;
+        #size-cells = <1>;
+        ranges;
+        gpio1: gpio@10015000 {
+                ...
+        };
+        ...
        uart {
                pinctrl_uart1: uart-1 {
@@ -83,6 +96,15 @@ The above example using macros:
 iomuxc: iomuxc@10015000 {
        compatible = "fsl,imx27-iomuxc";
        reg = <0x10015000 0x600>;
+        #address-cells = <1>;
+        #size-cells = <1>;
+        ranges;
+        gpio1: gpio@10015000 {
+                ...
+        };
+        ...
        uart {
                pinctrl_uart1: uart-1 {
diff --git a/Documentation/devicetree/bindings/pinctrl/nvidia,tegra124-pinmux.txt b/Documentation/devicetree/bindings/pinctrl/nvidia,tegra124-pinmux.txt
new file mode 100644
index 000000000000..6464bf769460
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/nvidia,tegra124-pinmux.txt
@@ -0,0 +1,144 @@
+NVIDIA Tegra124 pinmux controller
+The Tegra124 pinctrl binding is very similar to the Tegra20 and Tegra30
+pinctrl binding, as described in nvidia,tegra20-pinmux.txt and
+nvidia,tegra30-pinmux.txt. In fact, this document assumes that binding as
+a baseline, and only documents the differences between the two bindings.
+Required properties:
+- compatible: "nvidia,tegra124-pinmux"
+- reg: Should contain a list of base address and size pairs for:
+    -- first entry - the drive strength and pad control registers.
+    -- second entry - the pinmux registers
+Tegra124 adds the following optional properties for pin configuration subnodes.
+The macros for options are defined in the
+        include/dt-binding/pinctrl/pinctrl-tegra.h.
+- nvidia,enable-input: Integer. Enable the pin's input path.
+                enable :TEGRA_PIN_ENABLE0 and
+                disable or output only: TEGRA_PIN_DISABLE.
+- nvidia,open-drain: Integer.
+                enable: TEGRA_PIN_ENABLE.
+                disable: TEGRA_PIN_DISABLE.
+- nvidia,lock: Integer. Lock the pin configuration against further changes
+    until reset.
+                enable: TEGRA_PIN_ENABLE.
+                disable: TEGRA_PIN_DISABLE.
+- nvidia,io-reset: Integer. Reset the IO path.
+                enable: TEGRA_PIN_ENABLE.
+                disable: TEGRA_PIN_DISABLE.
+- nvidia,rcv-sel: Integer. Select VIL/VIH receivers.
+                normal: TEGRA_PIN_DISABLE
+                high: TEGRA_PIN_ENABLE
+Please refer the Tegra TRM for complete details regarding which groups
+support which functionality.
+Valid values for pin and group names are:
+  per-pin mux groups:
+    These all support nvidia,function, nvidia,tristate, nvidia,pull,
+    nvidia,enable-input. Some support nvidia,lock nvidia,open-drain,
+    nvidia,io-reset and nvidia,rcv-sel.
+        ulpi_data0_po1, ulpi_data1_po2, ulpi_data2_po3, ulpi_data3_po4,
+        ulpi_data4_po5, ulpi_data5_po6, ulpi_data6_po7, ulpi_data7_po0,
+        ulpi_clk_py0, ulpi_dir_py1, ulpi_nxt_py2, ulpi_stp_py3, dap3_fs_pp0,
+        dap3_din_pp1, dap3_dout_pp2, dap3_sclk_pp3, pv0, pv1, sdmmc1_clk_pz0,
+        sdmmc1_cmd_pz1, sdmmc1_dat3_py4, sdmmc1_dat2_py5, sdmmc1_dat1_py6,
+        sdmmc1_dat0_py7, clk2_out_pw5, clk2_req_pcc5, hdmi_int_pn7, ddc_scl_pv4,
+        ddc_sda_pv5, uart2_rxd_pc3, uart2_txd_pc2, uart2_rts_n_pj6,
+        uart2_cts_n_pj5, uart3_txd_pw6, uart3_rxd_pw7, uart3_cts_n_pa1,
+        uart3_rts_n_pc0, pu0, pu1, pu2, pu3, pu4, pu5, pu6, gen1_i2c_scl_pc4,
+        gen1_i2c_sda_pc5, dap4_fs_pp4, dap4_din_pp5, dap4_dout_pp6,
+        dap4_sclk_pp7, clk3_out_pee0, clk3_req_pee1, pc7, pi5, pi7, pk0, pk1,
+        pj0, pj2, pk3, pk4, pk2, pi3, pi6, pg0, pg1, pg2, pg3, pg4, pg5, pg6,
+        pg7, ph0, ph1, ph2, ph3, ph4, ph5, ph6, ph7, pj7, pb0, pb1, pk7, pi0,
+        pi1, pi2, pi4, gen2_i2c_scl_pt5, gen2_i2c_sda_pt6, sdmmc4_clk_pcc4,
+        sdmmc4_cmd_pt7, sdmmc4_dat0_paa0, sdmmc4_dat1_paa1, sdmmc4_dat2_paa2,
+        sdmmc4_dat3_paa3, sdmmc4_dat4_paa4, sdmmc4_dat5_paa5, sdmmc4_dat6_paa6,
+        sdmmc4_dat7_paa7, cam_mclk_pcc0, pcc1, pbb0, cam_i2c_scl_pbb1,
+        cam_i2c_sda_pbb2, pbb3, pbb4, pbb5, pbb6, pbb7, pcc2, jtag_rtck,
+        pwr_i2c_scl_pz6, pwr_i2c_sda_pz7, kb_row0_pr0, kb_row1_pr1, kb_row2_pr2,
+        kb_row3_pr3, kb_row4_pr4, kb_row5_pr5, kb_row6_pr6, kb_row7_pr7,
+        kb_row8_ps0, kb_row9_ps1, kb_row10_ps2, kb_row11_ps3, kb_row12_ps4,
+        kb_row13_ps5, kb_row14_ps6, kb_row15_ps7, kb_col0_pq0, kb_col1_pq1,
+        kb_col2_pq2, kb_col3_pq3, kb_col4_pq4, kb_col5_pq5, kb_col6_pq6,
+        kb_col7_pq7, clk_32k_out_pa0, core_pwr_req, cpu_pwr_req, pwr_int_n,
+        clk_32k_in, owr, dap1_fs_pn0, dap1_din_pn1, dap1_dout_pn2,
+        dap1_sclk_pn3, dap_mclk1_req_pee2, dap_mclk1_pw4, spdif_in_pk6,
+        spdif_out_pk5, dap2_fs_pa2, dap2_din_pa4, dap2_dout_pa5, dap2_sclk_pa3,
+        dvfs_pwm_px0, gpio_x1_aud_px1, gpio_x3_aud_px3, dvfs_clk_px2,
+        gpio_x4_aud_px4, gpio_x5_aud_px5, gpio_x6_aud_px6, gpio_x7_aud_px7,
+        sdmmc3_clk_pa6, sdmmc3_cmd_pa7, sdmmc3_dat0_pb7, sdmmc3_dat1_pb6,
+        sdmmc3_dat2_pb5, sdmmc3_dat3_pb4, pex_l0_rst_n_pdd1,
+        pex_l0_clkreq_n_pdd2, pex_wake_n_pdd3, pex_l1_rst_n_pdd5,
+        pex_l1_clkreq_n_pdd6, hdmi_cec_pee3, sdmmc1_wp_n_pv3,
+        sdmmc3_cd_n_pv2, gpio_w2_aud_pw2, gpio_w3_aud_pw3, usb_vbus_en0_pn4,
+        usb_vbus_en1_pn5, sdmmc3_clk_lb_out_pee4, sdmmc3_clk_lb_in_pee5,
+        gmi_clk_lb, reset_out_n, kb_row16_pt0, kb_row17_pt1, usb_vbus_en2_pff1,
+        pff2, dp_hpd_pff0,
+  drive groups:
+    These all support nvidia,pull-down-strength, nvidia,pull-up-strength,
+    nvidia,slew-rate-rising, nvidia,slew-rate-falling. Most but not all
+    support nvidia,high-speed-mode, nvidia,schmitt, nvidia,low-power-mode
+    and nvidia,drive-type.
+    ao1, ao2, at1, at2, at3, at4, at5, cdev1, cdev2, dap1, dap2, dap3, dap4,
+    dbg, sdio3, spi, uaa, uab, uart2, uart3, sdio1, ddc, gma, gme, gmf, gmg,
+    gmh, owr, uda, gpv, dev3, cec, usb_vbus_en, ao3, ao0, hv0, sdio4, ao4.
+Valid values for nvidia,functions are:
+  blink, cec, cldvfs, clk12, cpu, dap, dap1, dap2, dev3, displaya,
+  displaya_alt, displayb, dtv, extperiph1, extperiph2, extperiph3,
+  gmi, gmi_alt, hda, hsi, i2c1, i2c2, i2c3, i2c4, i2cpwr, i2s0,
+  i2s1, i2s2, i2s3, i2s4, irda, kbc, owr, pmi, pwm0, pwm1, pwm2, pwm3,
+  pwron, reset_out_n, rsvd1, rsvd2, rsvd3, rsvd4, sdmmc1, sdmmc2, sdmmc3,
+  sdmmc4, soc, spdif, spi1, spi2, spi3, spi4, spi5, spi6, trace, uarta,
+  uartb, uartc, uartd, ulpi, usb, vgp1, vgp2, vgp3, vgp4, vgp5, vgp6,
+  vi, vi_alt1, vi_alt3, vimclk2, vimclk2_alt, sata, ccla, pe0, pe, pe1,
+  dp, rtck, sys, clk tmds.
+Example:
+        pinmux: pinmux {
+                compatible = "nvidia,tegra124-pinmux";
+                reg = <0x70000868 0x164         /* Pad control registers */
+                       0x70003000 0x434>;       /* PinMux registers */
+        };
+Example pinmux entries:
+        pinctrl {
+                sdmmc4_default: pinmux {
+                        sdmmc4_clk_pcc4 {
+                                nvidia,pins = "sdmmc4_clk_pcc4",
+                                nvidia,function = "sdmmc4";
+                                nvidia,pull = <TEGRA_PIN_PULL_NONE>;
+                                nvidia,tristate = <TEGRA_PIN_DISABLE>;
+                        };
+                        sdmmc4_dat0_paa0 {
+                                nvidia,pins = "sdmmc4_dat0_paa0",
+                                                "sdmmc4_dat1_paa1",
+                                                "sdmmc4_dat2_paa2",
+                                                "sdmmc4_dat3_paa3",
+                                                "sdmmc4_dat4_paa4",
+                                                "sdmmc4_dat5_paa5",
+                                                "sdmmc4_dat6_paa6",
+                                                "sdmmc4_dat7_paa7";
+                                nvidia,function = "sdmmc4";
+                                nvidia,pull = <TEGRA_PIN_PULL_UP>;
+                                nvidia,tristate = <TEGRA_PIN_DISABLE>;
+                        };
+                };
+        };
+        sdhci@78000400 {
+                pinctrl-names = "default";
+                pinctrl-0 = <&sdmmc4_default>;
+        };
diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt b/Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt
index 1958ca9f9e5c..4414163e76d2 100644
--- a/Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt
+++ b/Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt
@@ -151,6 +151,8 @@ drive-push-pull		- drive actively high and low
 drive-open-drain        - drive with open drain
 drive-open-source       - drive with open source
 drive-strength          - sink or source at most X mA
+input-enable            - enable input on pin (no effect on output)
+input-disable           - disable input on pin (no effect on output)
 input-schmitt-enable    - enable schmitt-trigger mode
 input-schmitt-disable   - disable schmitt-trigger mode
 input-debounce          - debounce mode with debound time X
@@ -158,6 +160,7 @@ low-power-enable	- enable low power mode
 low-power-disable       - disable low power mode
 output-low              - set the pin to output mode with low level
 output-high             - set the pin to output mode with high level
+slew-rate               - set the slew rate
 Some of the generic properties take arguments. For those that do, the
 arguments are described below.
diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-single.txt b/Documentation/devicetree/bindings/pinctrl/pinctrl-single.txt
index 7069a0b84e3a..bc0dfdfdb148 100644
--- a/Documentation/devicetree/bindings/pinctrl/pinctrl-single.txt
+++ b/Documentation/devicetree/bindings/pinctrl/pinctrl-single.txt
@@ -98,7 +98,7 @@ below for more information.
 In case when one register changes more than one pin's mux the
 pinctrl-single,bits need to be used which takes three parameters:
-        pinctrl-single,bits = <0xdc 0x18, 0xff>;
+        pinctrl-single,bits = <0xdc 0x18 0xff>;
 Where 0xdc is the offset from the pinctrl register base address for the
 device pinctrl register, 0x18 is the desired value, and 0xff is the sub mask to
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8974-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,msm8974-pinctrl.txt
new file mode 100644
index 000000000000..4c352be5dd61
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8974-pinctrl.txt
@@ -0,0 +1,92 @@
+Qualcomm MSM8974 TLMM block
+Required properties:
+- compatible: "qcom,msm8x74-pinctrl"
+- reg: Should be the base address and length of the TLMM block.
+- interrupts: Should be the parent IRQ of the TLMM block.
+- interrupt-controller: Marks the device node as an interrupt controller.
+- #interrupt-cells: Should be two.
+- gpio-controller: Marks the device node as a GPIO controller.
+- #gpio-cells : Should be two.
+                The first cell is the gpio pin number and the
+                second cell is used for optional parameters.
+Please refer to ../gpio/gpio.txt and ../interrupt-controller/interrupts.txt for
+a general description of GPIO and interrupt bindings.
+Please refer to pinctrl-bindings.txt in this directory for details of the
+common pinctrl bindings used by client devices, including the meaning of the
+phrase "pin configuration node".
+Qualcomm's pin configuration nodes act as a container for an abitrary number of
+subnodes. Each of these subnodes represents some desired configuration for a
+pin, a group, or a list of pins or groups. This configuration can include the
+mux function to select on those pin(s)/group(s), and various pin configuration
+parameters, such as pull-up, drive strength, etc.
+The name of each subnode is not important; all subnodes should be enumerated
+and processed purely based on their content.
+Each subnode only affects those parameters that are explicitly listed. In
+other words, a subnode that lists a mux function but no pin configuration
+parameters implies no information about any pin configuration parameters.
+Similarly, a pin subnode that describes a pullup parameter implies no
+information about e.g. the mux function.
+The following generic properties as defined in pinctrl-bindings.txt are valid
+to specify in a pin configuration subnode:
+ pins, function, bias-disable, bias-pull-down, bias-pull,up, drive-strength.
+Non-empty subnodes must specify the 'pins' property.
+Note that not all properties are valid for all pins.
+Valid values for qcom,pins are:
+  gpio0-gpio145
+    Supports mux, bias and drive-strength
+  sdc1_clk, sdc1_cmd, sdc1_data, sdc2_clk, sdc2_cmd, sdc2_data
+    Supports bias and drive-strength
+Valid values for qcom,function are:
+  blsp_i2c2, blsp_i2c6, blsp_i2c11, blsp_spi1, blsp_uart2, blsp_uart8, slimbus
+  (Note that this is not yet the complete list of functions)
+Example:
+        msmgpio: pinctrl@fd510000 {
+                compatible = "qcom,msm8974-pinctrl";
+                reg = <0xfd510000 0x4000>;
+                gpio-controller;
+                #gpio-cells = <2>;
+                interrupt-controller;
+                #interrupt-cells = <2>;
+                interrupts = <0 208 0>;
+                pinctrl-names = "default";
+                pinctrl-0 = <&uart2_default>;
+                uart2_default: uart2_default {
+                        mux {
+                                qcom,pins = "gpio4", "gpio5";
+                                qcom,function = "blsp_uart2";
+                        };
+                        tx {
+                                qcom,pins = "gpio4";
+                                drive-strength = <4>;
+                                bias-disable;
+                        };
+                        rx {
+                                qcom,pins = "gpio5";
+                                drive-strength = <2>;
+                                bias-pull-up;
+                        };
+                };
+        };
diff --git a/Documentation/devicetree/bindings/pinctrl/renesas,pfc-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/renesas,pfc-pinctrl.txt
index d5dac7b843a9..35d2e1f186f0 100644
--- a/Documentation/devicetree/bindings/pinctrl/renesas,pfc-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/renesas,pfc-pinctrl.txt
@@ -26,6 +26,11 @@ Optional properties:
  - #gpio-range-cells: Mandatory when the PFC doesn't handle GPIO, forbidden
    otherwise. Should be 3.
+  - interrupts-extended: Specify the interrupts associated with external
+    IRQ pins. This property is mandatory when the PFC handles GPIOs and
+    forbidden otherwise. When specified, it must contain one interrupt per
+    external IRQ, sorted by external IRQ number.
 The PFC node also acts as a container for pin configuration nodes. Please refer
 to pinctrl-bindings.txt in this directory for the definition of the term "pin
 configuration node" and for the common pinctrl bindings used by client devices.
@@ -103,6 +108,15 @@ Example 1: SH73A0 (SH-Mobile AG5) pin controller node
                      <0xe605801c 0x1c>;
                gpio-controller;
                #gpio-cells = <2>;
+                interrupts-extended =
+                        <&irqpin0 0 0>, <&irqpin0 1 0>, <&irqpin0 2 0>, <&irqpin0 3 0>,
+                        <&irqpin0 4 0>, <&irqpin0 5 0>, <&irqpin0 6 0>, <&irqpin0 7 0>,
+                        <&irqpin1 0 0>, <&irqpin1 1 0>, <&irqpin1 2 0>, <&irqpin1 3 0>,
+                        <&irqpin1 4 0>, <&irqpin1 5 0>, <&irqpin1 6 0>, <&irqpin1 7 0>,
+                        <&irqpin2 0 0>, <&irqpin2 1 0>, <&irqpin2 2 0>, <&irqpin2 3 0>,
+                        <&irqpin2 4 0>, <&irqpin2 5 0>, <&irqpin2 6 0>, <&irqpin2 7 0>,
+                        <&irqpin3 0 0>, <&irqpin3 1 0>, <&irqpin3 2 0>, <&irqpin3 3 0>,
+                        <&irqpin3 4 0>, <&irqpin3 5 0>, <&irqpin3 6 0>, <&irqpin3 7 0>;
        };
 Example 2: A GPIO LED node that references a GPIO
diff --git a/Documentation/devicetree/bindings/serial/atmel-usart.txt b/Documentation/devicetree/bindings/serial/atmel-usart.txt
index 2191dcb9f1da..9c5d19ac935c 100644
--- a/Documentation/devicetree/bindings/serial/atmel-usart.txt
+++ b/Documentation/devicetree/bindings/serial/atmel-usart.txt
@@ -6,6 +6,9 @@ Required properties:
  additional mode or an USART new feature.
 - reg: Should contain registers location and length
 - interrupts: Should contain interrupt
+- clock-names: tuple listing input clock names.
+        Required elements: "usart"
+- clocks: phandles to input clocks.
 Optional properties:
 - atmel,use-dma-rx: use of PDC or DMA for receiving data
@@ -26,6 +29,8 @@ Example:
                compatible = "atmel,at91sam9260-usart";
                reg = <0xfff8c000 0x4000>;
                interrupts = <7>;
+                clocks = <&usart0_clk>;
+                clock-names = "usart";
                atmel,use-dma-rx;
                atmel,use-dma-tx;
        };
@@ -35,6 +40,8 @@ Example:
                compatible = "atmel,at91sam9260-usart";
                reg = <0xf001c000 0x100>;
                interrupts = <12 4 5>;
+                clocks = <&usart0_clk>;
+                clock-names = "usart";
                atmel,use-dma-rx;
                atmel,use-dma-tx;
                dmas = <&dma0 2 0x3>,
diff --git a/Documentation/devicetree/bindings/serial/cirrus,clps711x-uart.txt b/Documentation/devicetree/bindings/serial/cirrus,clps711x-uart.txt
new file mode 100644
index 000000000000..12f3cf834deb
--- /dev/null
+++ b/Documentation/devicetree/bindings/serial/cirrus,clps711x-uart.txt
@@ -0,0 +1,28 @@
+* Cirrus Logic CLPS711X Universal Asynchronous Receiver/Transmitter (UART)
+Required properties:
+- compatible: Should be "cirrus,clps711x-uart".
+- reg: Address and length of the register set for the device.
+- interrupts: Should contain UART TX and RX interrupt.
+- clocks: Should contain UART core clock number.
+- syscon: Phandle to SYSCON node, which contain UART control bits.
+Optional properties:
+- uart-use-ms: Indicate the UART has modem signal (DCD, DSR, CTS).
+Note: Each UART port should have an alias correctly numbered
+in "aliases" node.
+Example:
+        aliases {
+                serial0 = &uart1;
+        };
+        uart1: uart@80000480 {
+                compatible = "cirrus,clps711x-uart";
+                reg = <0x80000480 0x80>;
+                interrupts = <12 13>;
+                clocks = <&clks 11>;
+                syscon = <&syscon1>;
+                uart-use-ms;
+        };
diff --git a/Documentation/devicetree/bindings/staging/dwc2.txt b/Documentation/devicetree/bindings/staging/dwc2.txt
deleted file mode 100644
index 1a1b7cfa4845..000000000000
--- a/Documentation/devicetree/bindings/staging/dwc2.txt
+++ /dev/null
@@ -1,15 +0,0 @@
-Platform DesignWare HS OTG USB 2.0 controller
-----------------------------------------------------
-Required properties:
- compatible : "snps,dwc2"
- reg : Should contain 1 register range (address and length)
- interrupts : Should contain 1 interrupt
-Example:
-        usb@101c0000 {
-                compatible = "ralink,rt3050-usb, snps,dwc2";
-                reg = <0x101c0000 40000>;
-                interrupts = <18>;
-        };
diff --git a/Documentation/devicetree/bindings/staging/xillybus.txt b/Documentation/devicetree/bindings/staging/xillybus.txt
new file mode 100644
index 000000000000..9e316dc2e40f
--- /dev/null
+++ b/Documentation/devicetree/bindings/staging/xillybus.txt
@@ -0,0 +1,20 @@
+* Xillybus driver for generic FPGA interface
+Required properties:
+- compatible: Should be "xillybus,xillybus-1.00.a"
+- reg: Address and length of the register set for the device
+- interrupts: Contains one interrupt node, typically consisting of three cells.
+- interrupt-parent: the phandle for the interrupt controller that
+                    services interrupts for this device.
+Optional properties:
+- dma-coherent: Present if DMA operations are coherent
+Example:
+        xillybus@ff200400 {
+                compatible = "xillybus,xillybus-1.00.a";
+                reg = < 0xff200400 0x00000080 >;
+                interrupts = < 0 40 1 >;
+                interrupt-parent = <&intc>;
+        } ;
diff --git a/Documentation/devicetree/bindings/timer/allwinner,sun5i-a13-hstimer.txt b/Documentation/devicetree/bindings/timer/allwinner,sun5i-a13-hstimer.txt
new file mode 100644
index 000000000000..7c26154b8bbb
--- /dev/null
+++ b/Documentation/devicetree/bindings/timer/allwinner,sun5i-a13-hstimer.txt
@@ -0,0 +1,22 @@
+Allwinner SoCs High Speed Timer Controller
+Required properties:
+- compatible :  should be "allwinner,sun5i-a13-hstimer" or
+                "allwinner,sun7i-a20-hstimer"
+- reg : Specifies base physical address and size of the registers.
+- interrupts :  The interrupts of these timers (2 for the sun5i IP, 4 for the sun7i
+                one)
+- clocks: phandle to the source clock (usually the AHB clock)
+Example:
+timer@01c60000 {
+        compatible = "allwinner,sun7i-a20-hstimer";
+        reg = <0x01c60000 0x1000>;
+        interrupts = <0 51 1>,
+                     <0 52 1>,
+                     <0 53 1>,
+                     <0 54 1>;
+        clocks = <&ahb1_gates 19>;
+};
diff --git a/Documentation/devicetree/bindings/usb/ci13xxx-imx.txt b/Documentation/devicetree/bindings/usb/ci-hdrc-imx.txt
index b4b5b7906c88..b4b5b7906c88 100644
--- a/Documentation/devicetree/bindings/usb/ci13xxx-imx.txt
+++ b/Documentation/devicetree/bindings/usb/ci-hdrc-imx.txt
diff --git a/Documentation/devicetree/bindings/usb/dwc2.txt b/Documentation/devicetree/bindings/usb/dwc2.txt
new file mode 100644
index 000000000000..b8b6871f116f
--- /dev/null
+++ b/Documentation/devicetree/bindings/usb/dwc2.txt
@@ -0,0 +1,29 @@
+Platform DesignWare HS OTG USB 2.0 controller
+-----------------------------------------------------
+Required properties:
+- compatible : One of:
+  - brcm,bcm2835-usb: The DWC2 USB controller instance in the BCM2835 SoC.
+  - snps,dwc2: A generic DWC2 USB controller with default parameters.
+- reg : Should contain 1 register range (address and length)
+- interrupts : Should contain 1 interrupt
+- clocks: clock provider specifier
+- clock-names: shall be "otg"
+Refer to clk/clock-bindings.txt for generic clock consumer properties
+Optional properties:
+- phys: phy provider specifier
+- phy-names: shall be "device"
+Refer to phy/phy-bindings.txt for generic phy consumer properties
+Example:
+        usb@101c0000 {
+                compatible = "ralink,rt3050-usb, snps,dwc2";
+                reg = <0x101c0000 40000>;
+                interrupts = <18>;
+                clocks = <&usb_otg_ahb_clk>;
+                clock-names = "otg";
+                phys = <&usbphy>;
+                phy-names = "usb2-phy";
+        };
diff --git a/Documentation/devicetree/bindings/usb/gr-udc.txt b/Documentation/devicetree/bindings/usb/gr-udc.txt
new file mode 100644
index 000000000000..0c5118f7a916
--- /dev/null
+++ b/Documentation/devicetree/bindings/usb/gr-udc.txt
@@ -0,0 +1,28 @@
+USB Peripheral Controller driver for Aeroflex Gaisler GRUSBDC.
+The GRUSBDC USB Device Controller core is available in the GRLIB VHDL
+IP core library.
+Note: In the ordinary environment for the core, a Leon SPARC system,
+these properties are built from information in the AMBA plug&play.
+Required properties:
+- name : Should be "GAISLER_USBDC" or "01_021"
+- reg : Address and length of the register set for the device
+- interrupts : Interrupt numbers for this device
+Optional properties:
+- epobufsizes : An array of buffer sizes for OUT endpoints. If the property is
+        not present, or for endpoints outside of the array, 1024 is assumed by
+        the driver.
+- epibufsizes : An array of buffer sizes for IN endpoints. If the property is
+        not present, or for endpoints outside of the array, 1024 is assumed by
+        the driver.
+For further information look in the documentation for the GLIB IP core library:
+http://www.gaisler.com/products/grlib/grip.pdf
diff --git a/Documentation/devicetree/bindings/usb/omap-usb.txt b/Documentation/devicetree/bindings/usb/omap-usb.txt
index 090e5e22bd2b..c495135115cb 100644
--- a/Documentation/devicetree/bindings/usb/omap-usb.txt
+++ b/Documentation/devicetree/bindings/usb/omap-usb.txt
@@ -87,6 +87,8 @@ Required properties:
                        e.g. USB3 PHY and SATA PHY on OMAP5.
 "ti,control-phy-dra7usb2" - if it has power down register like USB2 PHY on
                        DRA7 platform.
+ "ti,control-phy-am437usb2" - if it has power down register like USB2 PHY on
+                        AM437 platform.
 - reg : Address and length of the register set for the device. It contains
   the address of "otghs_control" for control-phy-otghs or "power" register
   for other types.
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index edbb8d88c85e..f29cd78b6698 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -9,6 +9,7 @@ aeroflexgaisler	Aeroflex Gaisler AB
 ak      Asahi Kasei Corp.
 altr    Altera Corp.
 amcc    Applied Micro Circuits Corporation (APM, formally AMCC)
+amstaos AMS-Taos Inc.
 apm     Applied Micro Circuits Corporation (APM)
 arm     ARM Ltd.
 atmel   Atmel Corporation
diff --git a/Documentation/driver-model/design-patterns.txt b/Documentation/driver-model/design-patterns.txt
new file mode 100644
index 000000000000..ba7b2df64904
--- /dev/null
+++ b/Documentation/driver-model/design-patterns.txt
@@ -0,0 +1,116 @@
+Device Driver Design Patterns
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+This document describes a few common design patterns found in device drivers.
+It is likely that subsystem maintainers will ask driver developers to
+conform to these design patterns.
+1. State Container
+2. container_of()
+1. State Container
+~~~~~~~~~~~~~~~~~~
+While the kernel contains a few device drivers that assume that they will
+only be probed() once on a certain system (singletons), it is custom to assume
+that the device the driver binds to will appear in several instances. This
+means that the probe() function and all callbacks need to be reentrant.
+The most common way to achieve this is to use the state container design
+pattern. It usually has this form:
+struct foo {
+    spinlock_t lock; /* Example member */
+    (...)
+};
+static int foo_probe(...)
+{
+    struct foo *foo;
+    foo = devm_kzalloc(dev, sizeof(*foo), GFP_KERNEL);
+    if (!foo)
+        return -ENOMEM;
+    spin_lock_init(&foo->lock);
+    (...)
+}
+This will create an instance of struct foo in memory every time probe() is
+called. This is our state container for this instance of the device driver.
+Of course it is then necessary to always pass this instance of the
+state around to all functions that need access to the state and its members.
+For example, if the driver is registering an interrupt handler, you would
+pass around a pointer to struct foo like this:
+static irqreturn_t foo_handler(int irq, void *arg)
+{
+    struct foo *foo = arg;
+    (...)
+}
+static int foo_probe(...)
+{
+    struct foo *foo;
+    (...)
+    ret = request_irq(irq, foo_handler, 0, "foo", foo);
+}
+This way you always get a pointer back to the correct instance of foo in
+your interrupt handler.
+2. container_of()
+~~~~~~~~~~~~~~~~~
+Continuing on the above example we add an offloaded work:
+struct foo {
+    spinlock_t lock;
+    struct workqueue_struct *wq;
+    struct work_struct offload;
+    (...)
+};
+static void foo_work(struct work_struct *work)
+{
+    struct foo *foo = container_of(work, struct foo, offload);
+    (...)
+}
+static irqreturn_t foo_handler(int irq, void *arg)
+{
+    struct foo *foo = arg;
+    queue_work(foo->wq, &foo->offload);
+    (...)
+}
+static int foo_probe(...)
+{
+    struct foo *foo;
+    foo->wq = create_singlethread_workqueue("foo-wq");
+    INIT_WORK(&foo->offload, foo_work);
+    (...)
+}
+The design pattern is the same for an hrtimer or something similar that will
+return a single argument which is a pointer to a struct member in the
+callback.
+container_of() is a macro defined in <linux/kernel.h>
+What container_of() does is to obtain a pointer to the containing struct from
+a pointer to a member by a simple subtraction using the offsetof() macro from
+standard C, which allows something similar to object oriented behaviours.
+Notice that the contained member must not be a pointer, but an actual member
+for this to work.
+We can see here that we avoid having global pointers to our struct foo *
+instance this way, while still keeping the number of parameters passed to the
+work function to a single pointer.
diff --git a/Documentation/driver-model/devres.txt b/Documentation/driver-model/devres.txt
index 5bdc8cb5fc28..4f7897e99cba 100644
--- a/Documentation/driver-model/devres.txt
+++ b/Documentation/driver-model/devres.txt
@@ -242,6 +242,8 @@ IIO
  devm_iio_device_free()
  devm_iio_trigger_alloc()
  devm_iio_trigger_free()
+  devm_iio_device_register()
+  devm_iio_device_unregister()
 IO region
  devm_request_region()
diff --git a/Documentation/extcon/porting-android-switch-class b/Documentation/extcon/porting-android-switch-class
index 5377f6317961..49c81caef84d 100644
--- a/Documentation/extcon/porting-android-switch-class
+++ b/Documentation/extcon/porting-android-switch-class
@@ -50,7 +50,7 @@ so that they are still compatible with legacy userspace processes.
        Extcon's extended features for switch device drivers with
        complex features usually required magic numbers in state
        value of switch_dev. With extcon, such magic numbers that
-        support multiple cables (
+        support multiple cables are no more required or supported.
  1. Define cable names at edev->supported_cable.
  2. (Recommended) remove print_state callback.
@@ -114,11 +114,8 @@ exclusive, the two cables cannot be in ATTACHED state simulteneously.
 ****** ABI Location
-  If "CONFIG_ANDROID" is enabled and "CONFIG_ANDROID_SWITCH" is
+  If "CONFIG_ANDROID" is enabled, /sys/class/switch/* are created
-disabled, /sys/class/switch/* are created as symbolic links to
+as symbolic links to /sys/class/extcon/*.
-/sys/class/extcon/*. Because CONFIG_ANDROID_SWITCH creates
-/sys/class/switch directory, we disable symboling linking if
-CONFIG_ANDROID_SWITCH is enabled.
  The two files of switch class, name and state, are provided with
 extcon, too. When the multistate support (STEP 2 of CHAPTER 1.) is
diff --git a/Documentation/gpio/board.txt b/Documentation/gpio/board.txt
index 0d03506f2cc5..ba169faad5c6 100644
--- a/Documentation/gpio/board.txt
+++ b/Documentation/gpio/board.txt
@@ -72,10 +72,11 @@ where
  - chip_label is the label of the gpiod_chip instance providing the GPIO
  - chip_hwnum is the hardware number of the GPIO within the chip
-  - dev_id is the identifier of the device that will make use of this GPIO. If
+  - dev_id is the identifier of the device that will make use of this GPIO. It
-        NULL, the GPIO will be available to all devices.
+        can be NULL, in which case it will be matched for calls to gpiod_get()
+        with a NULL device.
  - con_id is the name of the GPIO function from the device point of view. It
-        can be NULL.
+        can be NULL, in which case it will match any function.
  - idx is the index of the GPIO within the function.
  - flags is defined to specify the following properties:
        * GPIOF_ACTIVE_LOW      - to configure the GPIO as active-low
@@ -86,18 +87,23 @@ In the future, these flags might be extended to support more properties.
 Note that GPIO_LOOKUP() is just a shortcut to GPIO_LOOKUP_IDX() where idx = 0.
-A lookup table can then be defined as follows:
+A lookup table can then be defined as follows, with an empty entry defining its
+end:
-        struct gpiod_lookup gpios_table[] = {
+struct gpiod_lookup_table gpios_table = {
-        GPIO_LOOKUP_IDX("gpio.0", 15, "foo.0", "led", 0, GPIO_ACTIVE_HIGH),
+        .dev_id = "foo.0",
-        GPIO_LOOKUP_IDX("gpio.0", 16, "foo.0", "led", 1, GPIO_ACTIVE_HIGH),
+        .table = {
-        GPIO_LOOKUP_IDX("gpio.0", 17, "foo.0", "led", 2, GPIO_ACTIVE_HIGH),
+                GPIO_LOOKUP_IDX("gpio.0", 15, "led", 0, GPIO_ACTIVE_HIGH),
-        GPIO_LOOKUP("gpio.0", 1, "foo.0", "power", GPIO_ACTIVE_LOW),
+                GPIO_LOOKUP_IDX("gpio.0", 16, "led", 1, GPIO_ACTIVE_HIGH),
-        };
+                GPIO_LOOKUP_IDX("gpio.0", 17, "led", 2, GPIO_ACTIVE_HIGH),
+                GPIO_LOOKUP("gpio.0", 1, "power", GPIO_ACTIVE_LOW),
+                { },
+        },
+};
 And the table can be added by the board code as follows:
-        gpiod_add_table(gpios_table, ARRAY_SIZE(gpios_table));
+        gpiod_add_lookup_table(&gpios_table);
 The driver controlling "foo.0" will then be able to obtain its GPIOs as follows:
diff --git a/Documentation/gpio/consumer.txt b/Documentation/gpio/consumer.txt
index 07c74a3765a0..e42f77d8d4ca 100644
--- a/Documentation/gpio/consumer.txt
+++ b/Documentation/gpio/consumer.txt
@@ -38,7 +38,11 @@ device that displays digits), an additional index argument can be specified:
                                          const char *con_id, unsigned int idx)
 Both functions return either a valid GPIO descriptor, or an error code checkable
-with IS_ERR(). They will never return a NULL pointer.
+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
+occured while trying to acquire it. This is useful to discriminate between mere
+errors and an absence of GPIO for optional GPIO parameters.
 Device-managed variants of these functions are also defined:
diff --git a/Documentation/i2c/fault-codes b/Documentation/i2c/fault-codes
index 045765c0b9b5..47c25abb7d52 100644
--- a/Documentation/i2c/fault-codes
+++ b/Documentation/i2c/fault-codes
@@ -64,9 +64,6 @@ EINVAL
        detected before any I/O operation was started.  Use a more
        specific fault code when you can.
-        One example would be a driver trying an SMBus Block Write
-        with block size outside the range of 1-32 bytes.
 EIO
        This rather vague error means something went wrong when
        performing an I/O operation.  Use a more specific fault
diff --git a/Documentation/ja_JP/HOWTO b/Documentation/ja_JP/HOWTO
index 8148a47fc70e..0091a8215ac1 100644
--- a/Documentation/ja_JP/HOWTO
+++ b/Documentation/ja_JP/HOWTO
@@ -149,7 +149,7 @@ linux-api@ver.kernel.org に送ることを勧めます。
     この他にパッチを作る方法についてのよくできた記述は-
        "The Perfect Patch"
-                http://userweb.kernel.org/~akpm/stuff/tpp.txt
+                http://www.ozlabs.org/~akpm/stuff/tpp.txt
        "Linux kernel patch submission format"
                http://linux.yyz.us/patch-format.html
@@ -622,7 +622,7 @@ Linux カーネルコミュニティは、一度に大量のコードの塊を�
 これについて全てがどのようにあるべきかについての詳細は、以下のドキュメ
 ントの ChangeLog セクションを見てください-
  "The Perfect Patch"
-      http://userweb.kernel.org/~akpm/stuff/tpp.txt
+      http://www.ozlabs.org/~akpm/stuff/tpp.txt
 これらのどれもが、時にはとても困難です。これらの慣例を完璧に実施するに
 は数年かかるかもしれません。これは継続的な改善のプロセスであり、そのた
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index b9e9bd854298..4252af6ffda1 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -774,6 +774,15 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
        disable=        [IPV6]
                        See Documentation/networking/ipv6.txt.
+        disable_cpu_apicid= [X86,APIC,SMP]
+                        Format: <int>
+                        The number of initial APIC ID for the
+                        corresponding CPU to be disabled at boot,
+                        mostly used for the kdump 2nd kernel to
+                        disable BSP to wake up multiple CPUs without
+                        causing system reset or hang due to sending
+                        INIT from AP to BSP.
        disable_ddw     [PPC/PSERIES]
                        Disable Dynamic DMA Window support. Use this if
                        to workaround buggy firmware.
@@ -881,6 +890,14 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
                        The xen output can only be used by Xen PV guests.
+        edac_report=    [HW,EDAC] Control how to report EDAC event
+                        Format: {"on" | "off" | "force"}
+                        on: enable EDAC to report H/W event. May be overridden
+                        by other higher priority error reporting module.
+                        off: disable H/W event reporting through EDAC.
+                        force: enforce the use of EDAC to report H/W event.
+                        default: on.
        ekgdboc=        [X86,KGDB] Allow early kernel console debugging
                        ekgdboc=kbd
@@ -890,6 +907,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
        edd=            [EDD]
                        Format: {"off" | "on" | "skip[mbr]"}
+        efi=            [EFI]
+                        Format: { "old_map" }
+                        old_map [X86-64]: switch to the old ioremap-based EFI
+                        runtime services mapping. 32-bit still uses this one by
+                        default.
        efi_no_storage_paranoia [EFI; X86]
                        Using this parameter you can use more than 50% of
                        your efi variable storage. Use this parameter only if
@@ -1994,6 +2017,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
        noapic          [SMP,APIC] Tells the kernel to not make use of any
                        IOAPICs that may be present in the system.
+        nokaslr         [X86]
+                        Disable kernel base offset ASLR (Address Space
+                        Layout Randomization) if built into the kernel.
        noautogroup     Disable scheduler automatic task group creation.
        nobats          [PPC] Do not use BATs for mapping kernel lowmem
@@ -2627,7 +2654,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
                        for RCU-preempt, and "s" for RCU-sched, and "N"
                        is the CPU number.  This reduces OS jitter on the
                        offloaded CPUs, which can be useful for HPC and
                        real-time workloads.  It can also improve energy
                        efficiency for asymmetric multiprocessors.
@@ -2643,8 +2669,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
                        periodically wake up to do the polling.
        rcutree.blimit= [KNL]
-                        Set maximum number of finished RCU callbacks to process
+                        Set maximum number of finished RCU callbacks to
-                        in one batch.
+                        process in one batch.
        rcutree.rcu_fanout_leaf= [KNL]
                        Increase the number of CPUs assigned to each
@@ -2663,8 +2689,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
                        value is one, and maximum value is HZ.
        rcutree.qhimark= [KNL]
-                        Set threshold of queued
+                        Set threshold of queued RCU callbacks beyond which
-                        RCU callbacks over which batch limiting is disabled.
+                        batch limiting is disabled.
        rcutree.qlowmark= [KNL]
                        Set threshold of queued RCU callbacks below which
diff --git a/Documentation/kmsg/s390/zcrypt b/Documentation/kmsg/s390/zcrypt
new file mode 100644
index 000000000000..7fb2087409d6
--- /dev/null
+++ b/Documentation/kmsg/s390/zcrypt
@@ -0,0 +1,20 @@
+/*?
+ * Text: "Cryptographic device %x failed and was set offline\n"
+ * Severity: Error
+ * Parameter:
+ *   @1: device index
+ * Description:
+ * A cryptographic device failed to process a cryptographic request.
+ * The cryptographic device driver could not correct the error and
+ * set the device offline. The application that issued the
+ * request received an indication that the request has failed.
+ * User action:
+ * Use the lszcrypt command to confirm that the cryptographic
+ * hardware is still configured to your LPAR or z/VM guest virtual
+ * machine. If the device is available to your Linux instance the
+ * command output contains a line that begins with 'card<device index>',
+ * where <device index> is the two-digit decimal number in the message text.
+ * After ensuring that the device is available, use the chzcrypt command to
+ * set it online again.
+ * If the error persists, contact your support organization.
+ */
diff --git a/Documentation/ko_KR/HOWTO b/Documentation/ko_KR/HOWTO
index 680e64635958..dc2ff8f611e0 100644
--- a/Documentation/ko_KR/HOWTO
+++ b/Documentation/ko_KR/HOWTO
@@ -122,7 +122,7 @@ mtk.manpages@gmail.com의 메인테이너에게 보낼 것을 권장한다.
    올바른 패치들을 만드는 법에 관한 훌륭한 다른 문서들이 있다.
    "The Perfect Patch"
-        http://userweb.kernel.org/~akpm/stuff/tpp.txt
+        http://www.ozlabs.org/~akpm/stuff/tpp.txt
    "Linux kernel patch submission format"
        http://linux.yyz.us/patch-format.html
@@ -213,7 +213,7 @@ Documentation/DocBook/ 디렉토리 내에서 만들어지며 PDF, Postscript, H
 것은 Linux Cross-Reference project이며 그것은 자기 참조 방식이며
 소스코드를 인덱스된 웹 페이지들의 형태로 보여준다. 최신의 멋진 커널
 코드 저장소는 다음을 통하여 참조할 수 있다.
-      http://users.sosdg.org/~qiyong/lxr/
+      http://lxr.linux.no/+trees
 개발 프로세스
@@ -222,20 +222,20 @@ Documentation/DocBook/ 디렉토리 내에서 만들어지며 PDF, Postscript, H
 리눅스 커널 개발 프로세스는 현재 몇몇 다른 메인 커널 "브랜치들"과
 서브시스템에 특화된 커널 브랜치들로 구성된다. 몇몇 다른 메인
 브랜치들은 다음과 같다.
-  - main 2.6.x 커널 트리
+  - main 3.x 커널 트리
-  - 2.6.x.y - 안정된 커널 트리
+  - 3.x.y - 안정된 커널 트리
-  - 2.6.x -git 커널 패치들
+  - 3.x -git 커널 패치들
-  - 2.6.x -mm 커널 패치들
  - 서브시스템을 위한 커널 트리들과 패치들
+  - 3.x - 통합 테스트를 위한 next 커널 트리
-2.6.x 커널 트리
+3.x 커널 트리
 ---------------
-2.6.x 커널들은 Linux Torvalds가 관리하며 kernel.org의 pub/linux/kernel/v2.6/
+3.x 커널들은 Linux Torvalds가 관리하며 kernel.org의 pub/linux/kernel/v3.x/
 디렉토리에서 참조될 수 있다.개발 프로세스는 다음과 같다.
  - 새로운 커널이 배포되자마자 2주의 시간이 주어진다. 이 기간동은
    메인테이너들은 큰 diff들을 Linus에게 제출할 수 있다. 대개 이 패치들은
-    몇 주 동안 -mm 커널내에 이미 있었던 것들이다. 큰 변경들을 제출하는 데
+    몇 주 동안 -next 커널내에 이미 있었던 것들이다. 큰 변경들을 제출하는 데
    선호되는 방법은  git(커널의 소스 관리 툴, 더 많은 정보들은 http://git.or.cz/
    에서 참조할 수 있다)를 사용하는 것이지만 순수한 패치파일의 형식으로 보내는
    것도 무관하다.
@@ -262,20 +262,20 @@ Andrew Morton의 글이 있다.
         버그의 상황에 따라 배포되는 것이지 미리정해 놓은 시간에 따라
         배포되는 것은 아니기 때문이다."
-2.6.x.y - 안정 커널 트리
+3.x.y - 안정 커널 트리
 ------------------------
-4 자리 숫자로 이루어진 버젼의 커널들은 -stable 커널들이다. 그것들은 2.6.x
+3 자리 숫자로 이루어진 버젼의 커널들은 -stable 커널들이다. 그것들은 3.x
 커널에서 발견된 큰 회귀들이나 보안 문제들 중 비교적 작고 중요한 수정들을
 포함한다.
 이것은 가장 최근의 안정적인 커널을 원하는 사용자에게 추천되는 브랜치이며,
 개발/실험적 버젼을 테스트하는 것을 돕고자 하는 사용자들과는 별로 관련이 없다.
-어떤 2.6.x.y 커널도 사용할 수 없다면 그때는 가장 높은 숫자의 2.6.x
+어떤 3.x.y 커널도 사용할 수 없다면 그때는 가장 높은 숫자의 3.x
 커널이 현재의 안정 커널이다.
-2.6.x.y는 "stable" 팀<stable@kernel.org>에 의해 관리되며 거의 매번 격주로
+3.x.y는 "stable" 팀<stable@vger.kernel.org>에 의해 관리되며 거의 매번 격주로
 배포된다.
 커널 트리 문서들 내에 Documentation/stable_kernel_rules.txt 파일은 어떤
@@ -283,84 +283,46 @@ Andrew Morton의 글이 있다.
 진행되는지를 설명한다.
-2.6.x -git 패치들
+3.x -git 패치들
 ------------------
 git 저장소(그러므로 -git이라는 이름이 붙음)에는 날마다 관리되는 Linus의
 커널 트리의 snapshot 들이 있다. 이 패치들은 일반적으로 날마다 배포되며
 Linus의 트리의 현재 상태를 나타낸다. 이 패치들은 정상적인지 조금도
 살펴보지 않고 자동적으로 생성된 것이므로 -rc 커널들 보다도 더 실험적이다.
-2.6.x -mm 커널 패치들
---------------------
-Andrew Morton에 의해 배포된 실험적인 커널 패치들이다. Andrew는 모든 다른
-서브시스템 커널 트리와 패치들을 가져와서 리눅스 커널 메일링 리스트로
-온 많은 패치들과 한데 묶는다. 이 트리는 새로운 기능들과 패치들을 위한
-장소를 제공하는 역할을 한다. 하나의 패치가 -mm에 한동안 있으면서 그 가치가
-증명되게 되면 Andrew나 서브시스템 메인테이너는 그것을 메인라인에 포함시키기
-위하여 Linus에게 보낸다.
-커널 트리에 포함하고 싶은 모든 새로운 패치들은 Linus에게 보내지기 전에
-mm 트리에서 테스트를 하는 것을 적극 추천한다.
-이 커널들은 안정되게 사용할 시스템에서에 실행하는 것은 적합하지 않으며
-다른 브랜치들의 어떤 것들보다 위험하다.
-여러분이 커널 개발 프로세스를 돕길 원한다면 이 커널 배포들을 사용하고
-테스트한 후 어떤 문제를 발견하거나 또는 모든 것이 잘 동작한다면 리눅스
-커널 메일링 리스트로 피드백을 해달라.
-이 커널들은 일반적으로 모든 다른 실험적인 패치들과 배포될 당시의
-사용가능한 메인라인 -git 커널들의 몇몇 변경을 포함한다.
-mm 커널들은 정해진 일정대로 배포되지 않는다. 하지만 대개 몇몇 -mm 커널들은
-각 -rc 커널(1부터 3이 흔함) 사이에서 배포된다.
 서브시스템 커널 트리들과 패치들
 -------------------------------
-많은 다른 커널 서브시스템 개발자들은 커널의 다른 부분들에서 무슨 일이
+다양한 커널 서브시스템의 메인테이너들 --- 그리고 많은 커널 서브시스템 개발자들
-일어나고 있는지를 볼수 있도록 그들의 개발 트리를 공개한다. 이 트리들은
+--- 은 그들의 현재 개발 상태를 소스 저장소로 노출한다. 이를 통해 다른 사람들도
-위에서 설명하였던 것 처럼 -mm 커널 배포들로 합쳐진다.
+커널의 다른 영역에 어떤 변화가 이루어지고 있는지 알 수 있다. 급속히 개발이
+진행되는 영역이 있고 그렇지 않은 영역이 있으므로, 개발자는 다른 개발자가 제출한
-다음은  활용가능한 커널 트리들을 나열한다.
+수정 사항과 자신의 수정사항의 충돌이나 동일한 일을 동시에 두사람이 따로
-  git trees:
+진행하는 사태를 방지하기 위해 급속히 개발이 진행되고 있는 영역에 작업의
-    - Kbuild development tree, Sam Ravnborg < sam@ravnborg.org>
+베이스를 맞춰줄 것이 요구된다.
-    git.kernel.org:/pub/scm/linux/kernel/git/sam/kbuild.git
+대부분의 이러한 저장소는 git 트리지만, git이 아닌 SCM으로 관리되거나, quilt
-    - ACPI development tree, Len Brown <len.brown@intel.com >
+시리즈로 제공되는 패치들도 존재한다. 이러한 서브시스템 저장소들은 MAINTAINERS
-    git.kernel.org:/pub/scm/linux/kernel/git/lenb/linux-acpi-2.6.git
+파일에 나열되어 있다. 대부분은 http://git.kernel.org 에서 볼 수 있다.
-    - Block development tree, Jens Axboe <jens.axboe@oracle.com>
+제안된 패치는 서브시스템 트리에 커밋되기 전에 메일링 리스트를 통해
-    git.kernel.org:/pub/scm/linux/kernel/git/axboe/linux-2.6-block.git
+리뷰된다(아래의 관련 섹션을 참고하기 바란다). 일부 커널 서브시스템의 경우, 이
+리뷰 프로세스는 patchwork라는 도구를 통해 추적된다. patchwork은 등록된 패치와
-    - DRM development tree, Dave Airlie <airlied@linux.ie>
+패치에 대한 코멘트, 패치의 버전을 볼 수 있는 웹 인터페이스를 제공하고,
-    git.kernel.org:/pub/scm/linux/kernel/git/airlied/drm-2.6.git
+메인테이너는 패치를 리뷰 중, 리뷰 통과, 또는 반려됨으로 표시할 수 있다.
+대부분의 이러한 patchwork 사이트는 http://patchwork.kernel.org/ 또는
-    - ia64 development tree, Tony Luck < tony.luck@intel.com>
+http://patchwork.ozlabs.org/ 에 나열되어 있다.
-    git.kernel.org:/pub/scm/linux/kernel/git/aegl/linux-2.6.git
+3.x - 통합 테스트를 위한 next 커널 트리
-    - infiniband, Roland Dreier <rolandd@cisco.com >
+-----------------------------------------
-    git.kernel.org:/pub/scm/linux/kernel/git/roland/infiniband.git
+서브시스템 트리들의 변경사항들은 mainline 3.x 트리로 들어오기 전에 통합
+테스트를 거쳐야 한다. 이런 목적으로, 모든 서브시스템 트리의 변경사항을 거의
-    - libata, Jeff Garzik <jgarzik@pobox.com>
+매일 받아가는 특수한 테스트 저장소가 존재한다:
-    git.kernel.org:/pub/scm/linux/kernel/git/jgarzik/libata-dev.git
+       http://git.kernel.org/?p=linux/kernel/git/sfr/linux-next.git
+       http://linux.f-seidel.de/linux-next/pmwiki/
-    - network drivers, Jeff Garzik <jgarzik@pobox.com>
-    git.kernel.org:/pub/scm/linux/kernel/git/jgarzik/netdev-2.6.git
+이런 식으로, -next 커널을 통해 다음 머지 기간에 메인라인 커널에 어떤 변경이
+가해질 것인지 간략히 알 수 있다. 모험심 강한 테스터라면 -next 커널에서 테스트를
-    - pcmcia, Dominik Brodowski < linux@dominikbrodowski.net>
+수행하는 것도 좋을 것이다.
-    git.kernel.org:/pub/scm/linux/kernel/git/brodo/pcmcia-2.6.git
-    - SCSI, James Bottomley < James.Bottomley@SteelEye.com>
-    git.kernel.org:/pub/scm/linux/kernel/git/jejb/scsi-misc-2.6.git
-  quilt trees:
-    - USB, PCI, Driver Core, and I2C, Greg Kroah-Hartman < gregkh@linuxfoundation.org>
-    kernel.org/pub/linux/kernel/people/gregkh/gregkh-2.6/
-    - x86-64, partly i386, Andi Kleen < ak@suse.de>
-        ftp.firstfloor.org:/pub/ak/x86_64/quilt/
-  다른 커널 트리들은 http://kernel.org/git와 MAINTAINERS 파일에서 참조할 수
-  있다.
 버그 보고
 ---------
@@ -597,7 +559,7 @@ Pat이라는 이름을 가진 여자가 있을 수도 있는 것이다. 리눅�
 이것이 무엇인지 더 자세한 것을 알고 싶다면 다음 문서의 ChageLog 항을 봐라.
   "The Perfect Patch"
-    http://userweb.kernel.org/~akpm/stuff/tpp.txt
+    http://www.ozlabs.org/~akpm/stuff/tpp.txt
diff --git a/Documentation/kobject.txt b/Documentation/kobject.txt
index c5182bb2c16c..f87241dfed87 100644
--- a/Documentation/kobject.txt
+++ b/Documentation/kobject.txt
@@ -342,7 +342,10 @@ kset use:
 When you are finished with the kset, call:
  void kset_unregister(struct kset *kset);
-to destroy it.
+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
+after kset_unregister() returns.
 An example of using a kset can be seen in the
 samples/kobject/kset-example.c file in the kernel tree.
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index c8c42e64e953..102dc19c4119 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -194,18 +194,22 @@ There are some minimal guarantees that may be expected of a CPU:
 (*) On any given CPU, dependent memory accesses will be issued in order, with
     respect to itself.  This means that for:
-        Q = P; D = *Q;
+        ACCESS_ONCE(Q) = P; smp_read_barrier_depends(); D = ACCESS_ONCE(*Q);
     the CPU will issue the following memory operations:
        Q = LOAD P, D = LOAD *Q
-     and always in that order.
+     and always in that order.  On most systems, smp_read_barrier_depends()
+     does nothing, but it is required for DEC Alpha.  The ACCESS_ONCE()
+     is required to prevent compiler mischief.  Please note that you
+     should normally use something like rcu_dereference() instead of
+     open-coding smp_read_barrier_depends().
 (*) Overlapping loads and stores within a particular CPU will appear to be
     ordered within that CPU.  This means that for:
-        a = *X; *X = b;
+        a = ACCESS_ONCE(*X); ACCESS_ONCE(*X) = b;
     the CPU will only issue the following sequence of memory operations:
@@ -213,7 +217,7 @@ There are some minimal guarantees that may be expected of a CPU:
     And for:
-        *X = c; d = *X;
+        ACCESS_ONCE(*X) = c; d = ACCESS_ONCE(*X);
     the CPU will only issue:
@@ -224,6 +228,12 @@ There are some minimal guarantees that may be expected of a CPU:
 And there are a number of things that _must_ or _must_not_ be assumed:
+ (*) It _must_not_ be assumed that the compiler will do what you want with
+     memory references that are not protected by ACCESS_ONCE().  Without
+     ACCESS_ONCE(), the compiler is within its rights to do all sorts
+     of "creative" transformations, which are covered in the Compiler
+     Barrier section.
 (*) It _must_not_ be assumed that independent loads and stores will be issued
     in the order given.  This means that for:
@@ -371,33 +381,44 @@ Memory barriers come in four basic varieties:
 And a couple of implicit varieties:
- (5) LOCK operations.
+ (5) ACQUIRE operations.
     This acts as a one-way permeable barrier.  It guarantees that all memory
-     operations after the LOCK operation will appear to happen after the LOCK
+     operations after the ACQUIRE operation will appear to happen after the
-     operation with respect to the other components of the system.
+     ACQUIRE operation with respect to the other components of the system.
+     ACQUIRE operations include LOCK operations and smp_load_acquire()
+     operations.
-     Memory operations that occur before a LOCK operation may appear to happen
+     Memory operations that occur before an ACQUIRE operation may appear to
-     after it completes.
+     happen after it completes.
-     A LOCK operation should almost always be paired with an UNLOCK operation.
+     An ACQUIRE operation should almost always be paired with a RELEASE
+     operation.
- (6) UNLOCK operations.
+ (6) RELEASE operations.
     This also acts as a one-way permeable barrier.  It guarantees that all
-     memory operations before the UNLOCK operation will appear to happen before
+     memory operations before the RELEASE operation will appear to happen
-     the UNLOCK operation with respect to the other components of the system.
+     before the RELEASE operation with respect to the other components of the
+     system. RELEASE operations include UNLOCK operations and
+     smp_store_release() operations.
-     Memory operations that occur after an UNLOCK operation may appear to
+     Memory operations that occur after a RELEASE operation may appear to
     happen before it completes.
-     LOCK and UNLOCK operations are guaranteed to appear with respect to each
+     The use of ACQUIRE and RELEASE operations generally precludes the need
-     other strictly in the order specified.
+     for other sorts of memory barrier (but note the exceptions mentioned in
+     the subsection "MMIO write barrier").  In addition, a RELEASE+ACQUIRE
+     pair is -not- guaranteed to act as a full memory barrier.  However, after
+     an ACQUIRE on a given variable, all memory accesses preceding any prior
+     RELEASE on that same variable are guaranteed to be visible.  In other
+     words, within a given variable's critical section, all accesses of all
+     previous critical sections for that variable are guaranteed to have
+     completed.
-     The use of LOCK and UNLOCK operations generally precludes the need for
+     This means that ACQUIRE acts as a minimal "acquire" operation and
-     other sorts of memory barrier (but note the exceptions mentioned in the
+     RELEASE acts as a minimal "release" operation.
-     subsection "MMIO write barrier").
 Memory barriers are only required where there's a possibility of interaction
@@ -450,14 +471,14 @@ The usage requirements of data dependency barriers are a little subtle, and
 it's not always obvious that they're needed.  To illustrate, consider the
 following sequence of events:
-        CPU 1           CPU 2
+        CPU 1                 CPU 2
-        =============== ===============
+        ===============       ===============
        { A == 1, B == 2, C = 3, P == &A, Q == &C }
        B = 4;
        <write barrier>
-        P = &B
+        ACCESS_ONCE(P) = &B
-                        Q = P;
+                              Q = ACCESS_ONCE(P);
-                        D = *Q;
+                              D = *Q;
 There's a clear data dependency here, and it would seem that by the end of the
 sequence, Q must be either &A or &B, and that:
@@ -477,15 +498,15 @@ Alpha).
 To deal with this, a data dependency barrier or better must be inserted
 between the address load and the data load:
-        CPU 1           CPU 2
+        CPU 1                 CPU 2
-        =============== ===============
+        ===============       ===============
        { A == 1, B == 2, C = 3, P == &A, Q == &C }
        B = 4;
        <write barrier>
-        P = &B
+        ACCESS_ONCE(P) = &B
-                        Q = P;
+                              Q = ACCESS_ONCE(P);
-                        <data dependency barrier>
+                              <data dependency barrier>
-                        D = *Q;
+                              D = *Q;
 This enforces the occurrence of one of the two implications, and prevents the
 third possibility from arising.
@@ -500,25 +521,26 @@ odd-numbered bank is idle, one can see the new value of the pointer P (&B),
 but the old value of the variable B (2).
-Another example of where data dependency barriers might by required is where a
+Another example of where data dependency barriers might be required is where a
 number is read from memory and then used to calculate the index for an array
 access:
-        CPU 1           CPU 2
+        CPU 1                 CPU 2
-        =============== ===============
+        ===============       ===============
        { M[0] == 1, M[1] == 2, M[3] = 3, P == 0, Q == 3 }
        M[1] = 4;
        <write barrier>
-        P = 1
+        ACCESS_ONCE(P) = 1
-                        Q = P;
+                              Q = ACCESS_ONCE(P);
-                        <data dependency barrier>
+                              <data dependency barrier>
-                        D = M[Q];
+                              D = M[Q];
-The data dependency barrier is very important to the RCU system, for example.
+The data dependency barrier is very important to the RCU system,
-See rcu_dereference() in include/linux/rcupdate.h.  This permits the current
+for example.  See rcu_assign_pointer() and rcu_dereference() in
-target of an RCU'd pointer to be replaced with a new modified target, without
+include/linux/rcupdate.h.  This permits the current target of an RCU'd
-the replacement target appearing to be incompletely initialised.
+pointer to be replaced with a new modified target, without the replacement
+target appearing to be incompletely initialised.
 See also the subsection on "Cache Coherency" for a more thorough example.
@@ -530,24 +552,190 @@ A control dependency requires a full read memory barrier, not simply a data
 dependency barrier to make it work correctly.  Consider the following bit of
 code:
-        q = &a;
+        q = ACCESS_ONCE(a);
-        if (p) {
+        if (q) {
-                <data dependency barrier>
+                <data dependency barrier>  /* BUG: No data dependency!!! */
-                q = &b;
+                p = ACCESS_ONCE(b);
        }
-        x = *q;
 This will not have the desired effect because there is no actual data
-dependency, but rather a control dependency that the CPU may short-circuit by
+dependency, but rather a control dependency that the CPU may short-circuit
-attempting to predict the outcome in advance.  In such a case what's actually
+by attempting to predict the outcome in advance, so that other CPUs see
-required is:
+the load from b as having happened before the load from a.  In such a
+case what's actually required is:
-        q = &a;
+        q = ACCESS_ONCE(a);
-        if (p) {
+        if (q) {
                <read barrier>
-                q = &b;
+                p = ACCESS_ONCE(b);
+        }
+However, stores are not speculated.  This means that ordering -is- provided
+in the following example:
+        q = ACCESS_ONCE(a);
+        if (ACCESS_ONCE(q)) {
+                ACCESS_ONCE(b) = p;
+        }
+Please note that ACCESS_ONCE() is not optional!  Without the ACCESS_ONCE(),
+the compiler is within its rights to transform this example:
+        q = a;
+        if (q) {
+                b = p;  /* BUG: Compiler can reorder!!! */
+                do_something();
+        } else {
+                b = p;  /* BUG: Compiler can reorder!!! */
+                do_something_else();
+        }
+into this, which of course defeats the ordering:
+        b = p;
+        q = a;
+        if (q)
+                do_something();
+        else
+                do_something_else();
+Worse yet, if the compiler is able to prove (say) that the value of
+variable 'a' is always non-zero, it would be well within its rights
+to optimize the original example by eliminating the "if" statement
+as follows:
+        q = a;
+        b = p;  /* BUG: Compiler can reorder!!! */
+        do_something();
+The solution is again ACCESS_ONCE(), which preserves the ordering between
+the load from variable 'a' and the store to variable 'b':
+        q = ACCESS_ONCE(a);
+        if (q) {
+                ACCESS_ONCE(b) = p;
+                do_something();
+        } else {
+                ACCESS_ONCE(b) = p;
+                do_something_else();
+        }
+You could also use barrier() to prevent the compiler from moving
+the stores to variable 'b', but barrier() would not prevent the
+compiler from proving to itself that a==1 always, so ACCESS_ONCE()
+is also needed.
+It is important to note that control dependencies absolutely require a
+a conditional.  For example, the following "optimized" version of
+the above example breaks ordering:
+        q = ACCESS_ONCE(a);
+        ACCESS_ONCE(b) = p;  /* BUG: No ordering vs. load from a!!! */
+        if (q) {
+                /* ACCESS_ONCE(b) = p; -- moved up, BUG!!! */
+                do_something();
+        } else {
+                /* ACCESS_ONCE(b) = p; -- moved up, BUG!!! */
+                do_something_else();
        }
-        x = *q;
+It is of course legal for the prior load to be part of the conditional,
+for example, as follows:
+        if (ACCESS_ONCE(a) > 0) {
+                ACCESS_ONCE(b) = q / 2;
+                do_something();
+        } else {
+                ACCESS_ONCE(b) = q / 3;
+                do_something_else();
+        }
+This will again ensure that the load from variable 'a' is ordered before the
+stores to variable 'b'.
+In addition, you need to be careful what you do with the local variable 'q',
+otherwise the compiler might be able to guess the value and again remove
+the needed conditional.  For example:
+        q = ACCESS_ONCE(a);
+        if (q % MAX) {
+                ACCESS_ONCE(b) = p;
+                do_something();
+        } else {
+                ACCESS_ONCE(b) = p;
+                do_something_else();
+        }
+If MAX is defined to be 1, then the compiler knows that (q % MAX) is
+equal to zero, in which case the compiler is within its rights to
+transform the above code into the following:
+        q = ACCESS_ONCE(a);
+        ACCESS_ONCE(b) = p;
+        do_something_else();
+This transformation loses the ordering between the load from variable 'a'
+and the store to variable 'b'.  If you are relying on this ordering, you
+should do something like the following:
+        q = ACCESS_ONCE(a);
+        BUILD_BUG_ON(MAX <= 1); /* Order load from a with store to b. */
+        if (q % MAX) {
+                ACCESS_ONCE(b) = p;
+                do_something();
+        } else {
+                ACCESS_ONCE(b) = p;
+                do_something_else();
+        }
+Finally, control dependencies do -not- provide transitivity.  This is
+demonstrated by two related examples:
+        CPU 0                     CPU 1
+        =====================     =====================
+        r1 = ACCESS_ONCE(x);      r2 = ACCESS_ONCE(y);
+        if (r1 >= 0)              if (r2 >= 0)
+          ACCESS_ONCE(y) = 1;       ACCESS_ONCE(x) = 1;
+        assert(!(r1 == 1 && r2 == 1));
+The above two-CPU example will never trigger the assert().  However,
+if control dependencies guaranteed transitivity (which they do not),
+then adding the following two CPUs would guarantee a related assertion:
+        CPU 2                     CPU 3
+        =====================     =====================
+        ACCESS_ONCE(x) = 2;       ACCESS_ONCE(y) = 2;
+        assert(!(r1 == 2 && r2 == 2 && x == 1 && y == 1)); /* FAILS!!! */
+But because control dependencies do -not- provide transitivity, the
+above assertion can fail after the combined four-CPU example completes.
+If you need the four-CPU example to provide ordering, you will need
+smp_mb() between the loads and stores in the CPU 0 and CPU 1 code fragments.
+In summary:
+  (*) Control dependencies can order prior loads against later stores.
+      However, they do -not- guarantee any other sort of ordering:
+      Not prior loads against later loads, nor prior stores against
+      later anything.  If you need these other forms of ordering,
+      use smb_rmb(), smp_wmb(), or, in the case of prior stores and
+      later loads, smp_mb().
+  (*) Control dependencies require at least one run-time conditional
+      between the prior load and the subsequent store.  If the compiler
+      is able to optimize the conditional away, it will have also
+      optimized away the ordering.  Careful use of ACCESS_ONCE() can
+      help to preserve the needed conditional.
+  (*) Control dependencies require that the compiler avoid reordering the
+      dependency into nonexistence.  Careful use of ACCESS_ONCE() or
+      barrier() can help to preserve your control dependency.  Please
+      see the Compiler Barrier section for more information.
+  (*) Control dependencies do -not- provide transitivity.  If you
+      need transitivity, use smp_mb().
 SMP BARRIER PAIRING
@@ -561,23 +749,23 @@ barrier, though a general barrier would also be viable.  Similarly a read
 barrier or a data dependency barrier should always be paired with at least an
 write barrier, though, again, a general barrier is viable:
-        CPU 1           CPU 2
+        CPU 1                 CPU 2
-        =============== ===============
+        ===============       ===============
-        a = 1;
+        ACCESS_ONCE(a) = 1;
        <write barrier>
-        b = 2;          x = b;
+        ACCESS_ONCE(b) = 2;   x = ACCESS_ONCE(b);
-                        <read barrier>
+                              <read barrier>
-                        y = a;
+                              y = ACCESS_ONCE(a);
 Or:
-        CPU 1           CPU 2
+        CPU 1                 CPU 2
-        =============== ===============================
+        ===============       ===============================
        a = 1;
        <write barrier>
-        b = &a;         x = b;
+        ACCESS_ONCE(b) = &a;  x = ACCESS_ONCE(b);
-                        <data dependency barrier>
+                              <data dependency barrier>
-                        y = *x;
+                              y = *x;
 Basically, the read barrier always has to be there, even though it can be of
 the "weaker" type.
@@ -586,13 +774,13 @@ the "weaker" type.
 match the loads after the read barrier or the data dependency barrier, and vice
 versa:
-        CPU 1                           CPU 2
+        CPU 1                               CPU 2
-        ===============                 ===============
+        ===================                 ===================
-        a = 1;           }----   --->{  v = c
+        ACCESS_ONCE(a) = 1;  }----   --->{  v = ACCESS_ONCE(c);
-        b = 2;           }    \ /    {  w = d
+        ACCESS_ONCE(b) = 2;  }    \ /    {  w = ACCESS_ONCE(d);
-        <write barrier>        \        <read barrier>
+        <write barrier>            \        <read barrier>
-        c = 3;           }    / \    {  x = a;
+        ACCESS_ONCE(c) = 3;  }    / \    {  x = ACCESS_ONCE(a);
-        d = 4;           }----   --->{  y = b;
+        ACCESS_ONCE(d) = 4;  }----   --->{  y = ACCESS_ONCE(b);
 EXAMPLES OF MEMORY BARRIER SEQUENCES
@@ -882,12 +1070,12 @@ cache it for later use.
 Consider:
-        CPU 1                   CPU 2
+        CPU 1                   CPU 2
        ======================= =======================
-                                LOAD B
+                                LOAD B
-                                DIVIDE          } Divide instructions generally
+                                DIVIDE          } Divide instructions generally
-                                DIVIDE          } take a long time to perform
+                                DIVIDE          } take a long time to perform
-                                LOAD A
+                                LOAD A
 Which might appear as this:
@@ -910,13 +1098,13 @@ Which might appear as this:
 Placing a read barrier or a data dependency barrier just before the second
 load:
-        CPU 1                   CPU 2
+        CPU 1                   CPU 2
        ======================= =======================
-                                LOAD B
+                                LOAD B
-                                DIVIDE
+                                DIVIDE
-                                DIVIDE
+                                DIVIDE
                                <read barrier>
-                                LOAD A
+                                LOAD A
 will force any value speculatively obtained to be reconsidered to an extent
 dependent on the type of barrier used.  If there was no change made to the
@@ -1042,10 +1230,277 @@ compiler from moving the memory accesses either side of it to the other side:
        barrier();
-This is a general barrier - lesser varieties of compiler barrier do not exist.
+This is a general barrier -- there are no read-read or write-write variants
+of barrier().  However, ACCESS_ONCE() can be thought of as a weak form
+for barrier() that affects only the specific accesses flagged by the
+ACCESS_ONCE().
+The barrier() function has the following effects:
+ (*) Prevents the compiler from reordering accesses following the
+     barrier() to precede any accesses preceding the barrier().
+     One example use for this property is to ease communication between
+     interrupt-handler code and the code that was interrupted.
+ (*) Within a loop, forces the compiler to load the variables used
+     in that loop's conditional on each pass through that loop.
+The ACCESS_ONCE() function can prevent any number of optimizations that,
+while perfectly safe in single-threaded code, can be fatal in concurrent
+code.  Here are some examples of these sorts of optimizations:
+ (*) The compiler is within its rights to merge successive loads from
+     the same variable.  Such merging can cause the compiler to "optimize"
+     the following code:
+        while (tmp = a)
+                do_something_with(tmp);
+     into the following code, which, although in some sense legitimate
+     for single-threaded code, is almost certainly not what the developer
+     intended:
+        if (tmp = a)
+                for (;;)
+                        do_something_with(tmp);
+     Use ACCESS_ONCE() to prevent the compiler from doing this to you:
+        while (tmp = ACCESS_ONCE(a))
+                do_something_with(tmp);
+ (*) The compiler is within its rights to reload a variable, for example,
+     in cases where high register pressure prevents the compiler from
+     keeping all data of interest in registers.  The compiler might
+     therefore optimize the variable 'tmp' out of our previous example:
+        while (tmp = a)
+                do_something_with(tmp);
+     This could result in the following code, which is perfectly safe in
+     single-threaded code, but can be fatal in concurrent code:
+        while (a)
+                do_something_with(a);
+     For example, the optimized version of this code could result in
+     passing a zero to do_something_with() in the case where the variable
+     a was modified by some other CPU between the "while" statement and
+     the call to do_something_with().
+     Again, use ACCESS_ONCE() to prevent the compiler from doing this:
+        while (tmp = ACCESS_ONCE(a))
+                do_something_with(tmp);
+     Note that if the compiler runs short of registers, it might save
+     tmp onto the stack.  The overhead of this saving and later restoring
+     is why compilers reload variables.  Doing so is perfectly safe for
+     single-threaded code, so you need to tell the compiler about cases
+     where it is not safe.
+ (*) The compiler is within its rights to omit a load entirely if it knows
+     what the value will be.  For example, if the compiler can prove that
+     the value of variable 'a' is always zero, it can optimize this code:
+        while (tmp = a)
+                do_something_with(tmp);
-The compiler barrier has no direct effect on the CPU, which may then reorder
+     Into this:
-things however it wishes.
+        do { } while (0);
+     This transformation is a win for single-threaded code because it gets
+     rid of a load and a branch.  The problem is that the compiler will
+     carry out its proof assuming that the current CPU is the only one
+     updating variable 'a'.  If variable 'a' is shared, then the compiler's
+     proof will be erroneous.  Use ACCESS_ONCE() to tell the compiler
+     that it doesn't know as much as it thinks it does:
+        while (tmp = ACCESS_ONCE(a))
+                do_something_with(tmp);
+     But please note that the compiler is also closely watching what you
+     do with the value after the ACCESS_ONCE().  For example, suppose you
+     do the following and MAX is a preprocessor macro with the value 1:
+        while ((tmp = ACCESS_ONCE(a)) % MAX)
+                do_something_with(tmp);
+     Then the compiler knows that the result of the "%" operator applied
+     to MAX will always be zero, again allowing the compiler to optimize
+     the code into near-nonexistence.  (It will still load from the
+     variable 'a'.)
+ (*) Similarly, the compiler is within its rights to omit a store entirely
+     if it knows that the variable already has the value being stored.
+     Again, the compiler assumes that the current CPU is the only one
+     storing into the variable, which can cause the compiler to do the
+     wrong thing for shared variables.  For example, suppose you have
+     the following:
+        a = 0;
+        /* Code that does not store to variable a. */
+        a = 0;
+     The compiler sees that the value of variable 'a' is already zero, so
+     it might well omit the second store.  This would come as a fatal
+     surprise if some other CPU might have stored to variable 'a' in the
+     meantime.
+     Use ACCESS_ONCE() to prevent the compiler from making this sort of
+     wrong guess:
+        ACCESS_ONCE(a) = 0;
+        /* Code that does not store to variable a. */
+        ACCESS_ONCE(a) = 0;
+ (*) The compiler is within its rights to reorder memory accesses unless
+     you tell it not to.  For example, consider the following interaction
+     between process-level code and an interrupt handler:
+        void process_level(void)
+        {
+                msg = get_message();
+                flag = true;
+        }
+        void interrupt_handler(void)
+        {
+                if (flag)
+                        process_message(msg);
+        }
+     There is nothing to prevent the the compiler from transforming
+     process_level() to the following, in fact, this might well be a
+     win for single-threaded code:
+        void process_level(void)
+        {
+                flag = true;
+                msg = get_message();
+        }
+     If the interrupt occurs between these two statement, then
+     interrupt_handler() might be passed a garbled msg.  Use ACCESS_ONCE()
+     to prevent this as follows:
+        void process_level(void)
+        {
+                ACCESS_ONCE(msg) = get_message();
+                ACCESS_ONCE(flag) = true;
+        }
+        void interrupt_handler(void)
+        {
+                if (ACCESS_ONCE(flag))
+                        process_message(ACCESS_ONCE(msg));
+        }
+     Note that the ACCESS_ONCE() wrappers in interrupt_handler()
+     are needed if this interrupt handler can itself be interrupted
+     by something that also accesses 'flag' and 'msg', for example,
+     a nested interrupt or an NMI.  Otherwise, ACCESS_ONCE() is not
+     needed in interrupt_handler() other than for documentation purposes.
+     (Note also that nested interrupts do not typically occur in modern
+     Linux kernels, in fact, if an interrupt handler returns with
+     interrupts enabled, you will get a WARN_ONCE() splat.)
+     You should assume that the compiler can move ACCESS_ONCE() past
+     code not containing ACCESS_ONCE(), barrier(), or similar primitives.
+     This effect could also be achieved using barrier(), but ACCESS_ONCE()
+     is more selective:  With ACCESS_ONCE(), the compiler need only forget
+     the contents of the indicated memory locations, while with barrier()
+     the compiler must discard the value of all memory locations that
+     it has currented cached in any machine registers.  Of course,
+     the compiler must also respect the order in which the ACCESS_ONCE()s
+     occur, though the CPU of course need not do so.
+ (*) The compiler is within its rights to invent stores to a variable,
+     as in the following example:
+        if (a)
+                b = a;
+        else
+                b = 42;
+     The compiler might save a branch by optimizing this as follows:
+        b = 42;
+        if (a)
+                b = a;
+     In single-threaded code, this is not only safe, but also saves
+     a branch.  Unfortunately, in concurrent code, this optimization
+     could cause some other CPU to see a spurious value of 42 -- even
+     if variable 'a' was never zero -- when loading variable 'b'.
+     Use ACCESS_ONCE() to prevent this as follows:
+        if (a)
+                ACCESS_ONCE(b) = a;
+        else
+                ACCESS_ONCE(b) = 42;
+     The compiler can also invent loads.  These are usually less
+     damaging, but they can result in cache-line bouncing and thus in
+     poor performance and scalability.  Use ACCESS_ONCE() to prevent
+     invented loads.
+ (*) For aligned memory locations whose size allows them to be accessed
+     with a single memory-reference instruction, prevents "load tearing"
+     and "store tearing," in which a single large access is replaced by
+     multiple smaller accesses.  For example, given an architecture having
+     16-bit store instructions with 7-bit immediate fields, the compiler
+     might be tempted to use two 16-bit store-immediate instructions to
+     implement the following 32-bit store:
+        p = 0x00010002;
+     Please note that GCC really does use this sort of optimization,
+     which is not surprising given that it would likely take more
+     than two instructions to build the constant and then store it.
+     This optimization can therefore be a win in single-threaded code.
+     In fact, a recent bug (since fixed) caused GCC to incorrectly use
+     this optimization in a volatile store.  In the absence of such bugs,
+     use of ACCESS_ONCE() prevents store tearing in the following example:
+        ACCESS_ONCE(p) = 0x00010002;
+     Use of packed structures can also result in load and store tearing,
+     as in this example:
+        struct __attribute__((__packed__)) foo {
+                short a;
+                int b;
+                short c;
+        };
+        struct foo foo1, foo2;
+        ...
+        foo2.a = foo1.a;
+        foo2.b = foo1.b;
+        foo2.c = foo1.c;
+     Because there are no ACCESS_ONCE() wrappers and no volatile markings,
+     the compiler would be well within its rights to implement these three
+     assignment statements as a pair of 32-bit loads followed by a pair
+     of 32-bit stores.  This would result in load tearing on 'foo1.b'
+     and store tearing on 'foo2.b'.  ACCESS_ONCE() again prevents tearing
+     in this example:
+        foo2.a = foo1.a;
+        ACCESS_ONCE(foo2.b) = ACCESS_ONCE(foo1.b);
+        foo2.c = foo1.c;
+All that aside, it is never necessary to use ACCESS_ONCE() on a variable
+that has been marked volatile.  For example, because 'jiffies' is marked
+volatile, it is never necessary to say ACCESS_ONCE(jiffies).  The reason
+for this is that ACCESS_ONCE() is implemented as a volatile cast, which
+has no effect when its argument is already marked volatile.
+Please note that these compiler barriers have no direct effect on the CPU,
+which may then reorder things however it wishes.
 CPU MEMORY BARRIERS
@@ -1135,7 +1590,7 @@ There are some more advanced barrier functions:
        clear_bit( ... );
     This prevents memory operations before the clear leaking to after it.  See
-     the subsection on "Locking Functions" with reference to UNLOCK operation
+     the subsection on "Locking Functions" with reference to RELEASE operation
     implications.
     See Documentation/atomic_ops.txt for more information.  See the "Atomic
@@ -1169,8 +1624,8 @@ provide more substantial guarantees, but these may not be relied upon outside
 of arch specific code.
-LOCKING FUNCTIONS
+ACQUIRING FUNCTIONS
-----------------
+-------------------
 The Linux kernel has a number of locking constructs:
@@ -1181,65 +1636,107 @@ The Linux kernel has a number of locking constructs:
 (*) R/W semaphores
 (*) RCU
-In all cases there are variants on "LOCK" operations and "UNLOCK" operations
+In all cases there are variants on "ACQUIRE" operations and "RELEASE" operations
 for each construct.  These operations all imply certain barriers:
- (1) LOCK operation implication:
+ (1) ACQUIRE operation implication:
-     Memory operations issued after the LOCK will be completed after the LOCK
+     Memory operations issued after the ACQUIRE will be completed after the
-     operation has completed.
+     ACQUIRE operation has completed.
-     Memory operations issued before the LOCK may be completed after the LOCK
+     Memory operations issued before the ACQUIRE may be completed after the
-     operation has completed.
+     ACQUIRE operation has completed.  An smp_mb__before_spinlock(), combined
+     with a following ACQUIRE, orders prior loads against subsequent stores and
+     stores and prior stores against subsequent stores.  Note that this is
+     weaker than smp_mb()!  The smp_mb__before_spinlock() primitive is free on
+     many architectures.
- (2) UNLOCK operation implication:
+ (2) RELEASE operation implication:
-     Memory operations issued before the UNLOCK will be completed before the
+     Memory operations issued before the RELEASE will be completed before the
-     UNLOCK operation has completed.
+     RELEASE operation has completed.
-     Memory operations issued after the UNLOCK may be completed before the
+     Memory operations issued after the RELEASE may be completed before the
-     UNLOCK operation has completed.
+     RELEASE operation has completed.
- (3) LOCK vs LOCK implication:
+ (3) ACQUIRE vs ACQUIRE implication:
-     All LOCK operations issued before another LOCK operation will be completed
+     All ACQUIRE operations issued before another ACQUIRE operation will be
-     before that LOCK operation.
+     completed before that ACQUIRE operation.
- (4) LOCK vs UNLOCK implication:
+ (4) ACQUIRE vs RELEASE implication:
-     All LOCK operations issued before an UNLOCK operation will be completed
+     All ACQUIRE operations issued before a RELEASE operation will be
-     before the UNLOCK operation.
+     completed before the RELEASE operation.
-     All UNLOCK operations issued before a LOCK operation will be completed
+ (5) Failed conditional ACQUIRE implication:
-     before the LOCK operation.
- (5) Failed conditional LOCK implication:
+     Certain locking variants of the ACQUIRE operation may fail, either due to
+     being unable to get the lock immediately, or due to receiving an unblocked
-     Certain variants of the LOCK operation may fail, either due to being
-     unable to get the lock immediately, or due to receiving an unblocked
     signal whilst asleep waiting for the lock to become available.  Failed
     locks do not imply any sort of barrier.
-Therefore, from (1), (2) and (4) an UNLOCK followed by an unconditional LOCK is
+[!] Note: one of the consequences of lock ACQUIREs and RELEASEs being only
-equivalent to a full barrier, but a LOCK followed by an UNLOCK is not.
+one-way barriers is that the effects of instructions outside of a critical
+section may seep into the inside of the critical section.
-[!] Note: one of the consequences of LOCKs and UNLOCKs being only one-way
-    barriers is that the effects of instructions outside of a critical section
-    may seep into the inside of the critical section.
-A LOCK followed by an UNLOCK may not be assumed to be full memory barrier
+An ACQUIRE followed by a RELEASE may not be assumed to be full memory barrier
-because it is possible for an access preceding the LOCK to happen after the
+because it is possible for an access preceding the ACQUIRE to happen after the
-LOCK, and an access following the UNLOCK to happen before the UNLOCK, and the
+ACQUIRE, and an access following the RELEASE to happen before the RELEASE, and
-two accesses can themselves then cross:
+the two accesses can themselves then cross:
        *A = a;
-        LOCK
+        ACQUIRE M
-        UNLOCK
+        RELEASE M
        *B = b;
 may occur as:
-        LOCK, STORE *B, STORE *A, UNLOCK
+        ACQUIRE M, STORE *B, STORE *A, RELEASE M
+This same reordering can of course occur if the lock's ACQUIRE and RELEASE are
+to the same lock variable, but only from the perspective of another CPU not
+holding that lock.
+In short, a RELEASE followed by an ACQUIRE may -not- be assumed to be a full
+memory barrier because it is possible for a preceding RELEASE to pass a
+later ACQUIRE from the viewpoint of the CPU, but not from the viewpoint
+of the compiler.  Note that deadlocks cannot be introduced by this
+interchange because if such a deadlock threatened, the RELEASE would
+simply complete.
+If it is necessary for a RELEASE-ACQUIRE pair to produce a full barrier, the
+ACQUIRE can be followed by an smp_mb__after_unlock_lock() invocation.  This
+will produce a full barrier if either (a) the RELEASE and the ACQUIRE are
+executed by the same CPU or task, or (b) the RELEASE and ACQUIRE act on the
+same variable.  The smp_mb__after_unlock_lock() primitive is free on many
+architectures.  Without smp_mb__after_unlock_lock(), the critical sections
+corresponding to the RELEASE and the ACQUIRE can cross:
+        *A = a;
+        RELEASE M
+        ACQUIRE N
+        *B = b;
+could occur as:
+        ACQUIRE N, STORE *B, STORE *A, RELEASE M
+With smp_mb__after_unlock_lock(), they cannot, so that:
+        *A = a;
+        RELEASE M
+        ACQUIRE N
+        smp_mb__after_unlock_lock();
+        *B = b;
+will always occur as either of the following:
+        STORE *A, RELEASE, ACQUIRE, STORE *B
+        STORE *A, ACQUIRE, RELEASE, STORE *B
+If the RELEASE and ACQUIRE were instead both operating on the same lock
+variable, only the first of these two alternatives can occur.
 Locks and semaphores may not provide any guarantee of ordering on UP compiled
 systems, and so cannot be counted on in such a situation to actually achieve
@@ -1253,33 +1750,33 @@ As an example, consider the following:
        *A = a;
        *B = b;
-        LOCK
+        ACQUIRE
        *C = c;
        *D = d;
-        UNLOCK
+        RELEASE
        *E = e;
        *F = f;
 The following sequence of events is acceptable:
-        LOCK, {*F,*A}, *E, {*C,*D}, *B, UNLOCK
+        ACQUIRE, {*F,*A}, *E, {*C,*D}, *B, RELEASE
        [+] Note that {*F,*A} indicates a combined access.
 But none of the following are:
-        {*F,*A}, *B,    LOCK, *C, *D,   UNLOCK, *E
+        {*F,*A}, *B,    ACQUIRE, *C, *D,        RELEASE, *E
-        *A, *B, *C,     LOCK, *D,       UNLOCK, *E, *F
+        *A, *B, *C,     ACQUIRE, *D,            RELEASE, *E, *F
-        *A, *B,         LOCK, *C,       UNLOCK, *D, *E, *F
+        *A, *B,         ACQUIRE, *C,            RELEASE, *D, *E, *F
-        *B,             LOCK, *C, *D,   UNLOCK, {*F,*A}, *E
+        *B,             ACQUIRE, *C, *D,        RELEASE, {*F,*A}, *E
 INTERRUPT DISABLING FUNCTIONS
 -----------------------------
-Functions that disable interrupts (LOCK equivalent) and enable interrupts
+Functions that disable interrupts (ACQUIRE equivalent) and enable interrupts
-(UNLOCK equivalent) will act as compiler barriers only.  So if memory or I/O
+(RELEASE equivalent) will act as compiler barriers only.  So if memory or I/O
 barriers are required in such a situation, they must be provided from some
 other means.
@@ -1418,75 +1915,81 @@ Other functions that imply barriers:
 (*) schedule() and similar imply full memory barriers.
-=================================
+===================================
-INTER-CPU LOCKING BARRIER EFFECTS
+INTER-CPU ACQUIRING BARRIER EFFECTS
-=================================
+===================================
 On SMP systems locking primitives give a more substantial form of barrier: one
 that does affect memory access ordering on other CPUs, within the context of
 conflict on any particular lock.
-LOCKS VS MEMORY ACCESSES
+ACQUIRES VS MEMORY ACCESSES
------------------------
+---------------------------
 Consider the following: the system has a pair of spinlocks (M) and (Q), and
 three CPUs; then should the following sequence of events occur:
        CPU 1                           CPU 2
        =============================== ===============================
-        *A = a;                         *E = e;
+        ACCESS_ONCE(*A) = a;            ACCESS_ONCE(*E) = e;
-        LOCK M                          LOCK Q
+        ACQUIRE M                       ACQUIRE Q
-        *B = b;                         *F = f;
+        ACCESS_ONCE(*B) = b;            ACCESS_ONCE(*F) = f;
-        *C = c;                         *G = g;
+        ACCESS_ONCE(*C) = c;            ACCESS_ONCE(*G) = g;
-        UNLOCK M                        UNLOCK Q
+        RELEASE M                       RELEASE Q
-        *D = d;                         *H = h;
+        ACCESS_ONCE(*D) = d;            ACCESS_ONCE(*H) = h;
 Then there is no guarantee as to what order CPU 3 will see the accesses to *A
 through *H occur in, other than the constraints imposed by the separate locks
 on the separate CPUs. It might, for example, see:
-        *E, LOCK M, LOCK Q, *G, *C, *F, *A, *B, UNLOCK Q, *D, *H, UNLOCK M
+        *E, ACQUIRE M, ACQUIRE Q, *G, *C, *F, *A, *B, RELEASE Q, *D, *H, RELEASE M
 But it won't see any of:
-        *B, *C or *D preceding LOCK M
+        *B, *C or *D preceding ACQUIRE M
-        *A, *B or *C following UNLOCK M
+        *A, *B or *C following RELEASE M
-        *F, *G or *H preceding LOCK Q
+        *F, *G or *H preceding ACQUIRE Q
-        *E, *F or *G following UNLOCK Q
+        *E, *F or *G following RELEASE Q
 However, if the following occurs:
        CPU 1                           CPU 2
        =============================== ===============================
-        *A = a;
+        ACCESS_ONCE(*A) = a;
-        LOCK M          [1]
+        ACQUIRE M                    [1]
-        *B = b;
+        ACCESS_ONCE(*B) = b;
-        *C = c;
+        ACCESS_ONCE(*C) = c;
-        UNLOCK M        [1]
+        RELEASE M            [1]
-        *D = d;                         *E = e;
+        ACCESS_ONCE(*D) = d;            ACCESS_ONCE(*E) = e;
-                                        LOCK M          [2]
+                                        ACQUIRE M                    [2]
-                                        *F = f;
+                                        smp_mb__after_unlock_lock();
-                                        *G = g;
+                                        ACCESS_ONCE(*F) = f;
-                                        UNLOCK M        [2]
+                                        ACCESS_ONCE(*G) = g;
-                                        *H = h;
+                                        RELEASE M            [2]
+                                        ACCESS_ONCE(*H) = h;
 CPU 3 might see:
-        *E, LOCK M [1], *C, *B, *A, UNLOCK M [1],
+        *E, ACQUIRE M [1], *C, *B, *A, RELEASE M [1],
-                LOCK M [2], *H, *F, *G, UNLOCK M [2], *D
+                ACQUIRE M [2], *H, *F, *G, RELEASE M [2], *D
 But assuming CPU 1 gets the lock first, CPU 3 won't see any of:
-        *B, *C, *D, *F, *G or *H preceding LOCK M [1]
+        *B, *C, *D, *F, *G or *H preceding ACQUIRE M [1]
-        *A, *B or *C following UNLOCK M [1]
+        *A, *B or *C following RELEASE M [1]
-        *F, *G or *H preceding LOCK M [2]
+        *F, *G or *H preceding ACQUIRE M [2]
-        *A, *B, *C, *E, *F or *G following UNLOCK M [2]
+        *A, *B, *C, *E, *F or *G following RELEASE M [2]
+Note that the smp_mb__after_unlock_lock() is critically important
+here: Without it CPU 3 might see some of the above orderings.
+Without smp_mb__after_unlock_lock(), the accesses are not guaranteed
+to be seen in order unless CPU 3 holds lock M.
-LOCKS VS I/O ACCESSES
---------------------
+ACQUIRES VS I/O ACCESSES
+------------------------
 Under certain circumstances (especially involving NUMA), I/O accesses within
 two spinlocked sections on two different CPUs may be seen as interleaved by the
@@ -1687,28 +2190,30 @@ explicit lock operations, described later).  These include:
        xchg();
        cmpxchg();
-        atomic_xchg();
+        atomic_xchg();                  atomic_long_xchg();
-        atomic_cmpxchg();
+        atomic_cmpxchg();               atomic_long_cmpxchg();
-        atomic_inc_return();
+        atomic_inc_return();            atomic_long_inc_return();
-        atomic_dec_return();
+        atomic_dec_return();            atomic_long_dec_return();
-        atomic_add_return();
+        atomic_add_return();            atomic_long_add_return();
-        atomic_sub_return();
+        atomic_sub_return();            atomic_long_sub_return();
-        atomic_inc_and_test();
+        atomic_inc_and_test();          atomic_long_inc_and_test();
-        atomic_dec_and_test();
+        atomic_dec_and_test();          atomic_long_dec_and_test();
-        atomic_sub_and_test();
+        atomic_sub_and_test();          atomic_long_sub_and_test();
-        atomic_add_negative();
+        atomic_add_negative();          atomic_long_add_negative();
-        atomic_add_unless();    /* when succeeds (returns 1) */
        test_and_set_bit();
        test_and_clear_bit();
        test_and_change_bit();
-These are used for such things as implementing LOCK-class and UNLOCK-class
+        /* when succeeds (returns 1) */
+        atomic_add_unless();            atomic_long_add_unless();
+These are used for such things as implementing ACQUIRE-class and RELEASE-class
 operations and adjusting reference counters towards object destruction, and as
 such the implicit memory barrier effects are necessary.
 The following operations are potential problems as they do _not_ imply memory
-barriers, but might be used for implementing such things as UNLOCK-class
+barriers, but might be used for implementing such things as RELEASE-class
 operations:
        atomic_set();
@@ -1750,7 +2255,7 @@ The following operations are special locking primitives:
        clear_bit_unlock();
        __clear_bit_unlock();
-These implement LOCK-class and UNLOCK-class operations. These should be used in
+These implement ACQUIRE-class and RELEASE-class operations. These should be used in
 preference to other operations when implementing locking primitives, because
 their implementations can be optimised on many architectures.
@@ -1887,8 +2392,8 @@ functions:
     space should suffice for PCI.
     [*] NOTE! attempting to load from the same location as was written to may
-         cause a malfunction - consider the 16550 Rx/Tx serial registers for
+         cause a malfunction - consider the 16550 Rx/Tx serial registers for
-         example.
+         example.
     Used with prefetchable I/O memory, an mmiowb() barrier may be required to
     force stores to be ordered.
@@ -1955,19 +2460,19 @@ barriers for the most part act at the interface between the CPU and its cache
                                  :
        +--------+    +--------+  :   +--------+    +-----------+
        |        |    |        |  :   |        |    |           |    +--------+
-        |  CPU   |    | Memory |  :   | CPU    |    |           |    |        |
+        |  CPU   |    | Memory |  :   | CPU    |    |           |    |        |
-        |  Core  |--->| Access |----->| Cache  |<-->|           |    |        |
+        |  Core  |--->| Access |----->| Cache  |<-->|           |    |        |
        |        |    | Queue  |  :   |        |    |           |--->| Memory |
-        |        |    |        |  :   |        |    |           |    |        |
+        |        |    |        |  :   |        |    |           |    |        |
-        +--------+    +--------+  :   +--------+    |           |    |        |
+        +--------+    +--------+  :   +--------+    |           |    |        |
                                  :                 | Cache     |    +--------+
                                  :                 | Coherency |
                                  :                 | Mechanism |    +--------+
        +--------+    +--------+  :   +--------+    |           |    |        |
        |        |    |        |  :   |        |    |           |    |        |
        |  CPU   |    | Memory |  :   | CPU    |    |           |--->| Device |
-        |  Core  |--->| Access |----->| Cache  |<-->|           |    |        |
+        |  Core  |--->| Access |----->| Cache  |<-->|           |    |        |
-        |        |    | Queue  |  :   |        |    |           |    |        |
+        |        |    | Queue  |  :   |        |    |           |    |        |
        |        |    |        |  :   |        |    |           |    +--------+
        +--------+    +--------+  :   +--------+    +-----------+
                                  :
@@ -2090,7 +2595,7 @@ CPU's caches by some other cache event:
        p = &v;         q = p;
                        <D:request p>
        <B:modify p=&v> <D:commit p=&v>
-                        <D:read p>
+                        <D:read p>
                        x = *q;
                        <C:read *q>     Reads from v before v updated in cache
                        <C:unbusy>
@@ -2115,7 +2620,7 @@ queue before processing any further requests:
        p = &v;         q = p;
                        <D:request p>
        <B:modify p=&v> <D:commit p=&v>
-                        <D:read p>
+                        <D:read p>
                        smp_read_barrier_depends()
                        <C:unbusy>
                        <C:commit v=2>
@@ -2177,11 +2682,11 @@ A programmer might take it for granted that the CPU will perform memory
 operations in exactly the order specified, so that if the CPU is, for example,
 given the following piece of code to execute:
-        a = *A;
+        a = ACCESS_ONCE(*A);
-        *B = b;
+        ACCESS_ONCE(*B) = b;
-        c = *C;
+        c = ACCESS_ONCE(*C);
-        d = *D;
+        d = ACCESS_ONCE(*D);
-        *E = e;
+        ACCESS_ONCE(*E) = e;
 they would then expect that the CPU will complete the memory operation for each
 instruction before moving on to the next one, leading to a definite sequence of
@@ -2228,12 +2733,12 @@ However, it is guaranteed that a CPU will be self-consistent: it will see its
 _own_ accesses appear to be correctly ordered, without the need for a memory
 barrier.  For instance with the following code:
-        U = *A;
+        U = ACCESS_ONCE(*A);
-        *A = V;
+        ACCESS_ONCE(*A) = V;
-        *A = W;
+        ACCESS_ONCE(*A) = W;
-        X = *A;
+        X = ACCESS_ONCE(*A);
-        *A = Y;
+        ACCESS_ONCE(*A) = Y;
-        Z = *A;
+        Z = ACCESS_ONCE(*A);
 and assuming no intervention by an external influence, it can be assumed that
 the final result will appear to be:
@@ -2250,7 +2755,12 @@ accesses:
 in that order, but, without intervention, the sequence may have almost any
 combination of elements combined or discarded, provided the program's view of
-the world remains consistent.
+the world remains consistent.  Note that ACCESS_ONCE() is -not- optional
+in the above example, as there are architectures where a given CPU might
+interchange successive loads to the same location.  On such architectures,
+ACCESS_ONCE() does whatever is necessary to prevent this, for example, on
+Itanium the volatile casts used by ACCESS_ONCE() cause GCC to emit the
+special ld.acq and st.rel instructions that prevent such reordering.
 The compiler may also combine, discard or defer elements of the sequence before
 the CPU even sees them.
@@ -2264,13 +2774,13 @@ may be reduced to:
        *A = W;
-since, without a write barrier, it can be assumed that the effect of the
+since, without either a write barrier or an ACCESS_ONCE(), it can be
-storage of V to *A is lost.  Similarly:
+assumed that the effect of the storage of V to *A is lost.  Similarly:
        *A = Y;
        Z = *A;
-may, without a memory barrier, be reduced to:
+may, without a memory barrier or an ACCESS_ONCE(), be reduced to:
        *A = Y;
        Z = Y;
diff --git a/Documentation/misc-devices/mei/mei-amt-version.c b/Documentation/misc-devices/mei/mei-amt-version.c
index 49e4f770864a..57d0d871dcf7 100644
--- a/Documentation/misc-devices/mei/mei-amt-version.c
+++ b/Documentation/misc-devices/mei/mei-amt-version.c
@@ -115,8 +115,6 @@ static bool mei_init(struct mei *me, const uuid_le *guid,
        struct mei_client *cl;
        struct mei_connect_client_data data;
-        mei_deinit(me);
        me->verbose = verbose;
        me->fd = open("/dev/mei", O_RDWR);
diff --git a/Documentation/pinctrl.txt b/Documentation/pinctrl.txt
index a7929cb47e7c..23f1590f49fe 100644
--- a/Documentation/pinctrl.txt
+++ b/Documentation/pinctrl.txt
@@ -18,7 +18,7 @@ Definition of PIN CONTROLLER:
 - A pin controller is a piece of hardware, usually a set of registers, that
  can control PINs. It may be able to multiplex, bias, set load capacitance,
-  set drive strength etc for individual pins or groups of pins.
+  set drive strength, etc. for individual pins or groups of pins.
 Definition of PIN:
@@ -90,7 +90,7 @@ selected drivers, you need to select them from your machine's Kconfig entry,
 since these are so tightly integrated with the machines they are used on.
 See for example arch/arm/mach-u300/Kconfig for an example.
-Pins usually have fancier names than this. You can find these in the dataheet
+Pins usually have fancier names than this. You can find these in the datasheet
 for your chip. Notice that the core pinctrl.h file provides a fancy macro
 called PINCTRL_PIN() to create the struct entries. As you can see I enumerated
 the pins from 0 in the upper left corner to 63 in the lower right corner.
@@ -185,7 +185,7 @@ static struct pinctrl_desc foo_desc = {
 };
 The pin control subsystem will call the .get_groups_count() function to
-determine total number of legal selectors, then it will call the other functions
+determine the total number of legal selectors, then it will call the other functions
 to retrieve the name and pins of the group. Maintaining the data structure of
 the groups is up to the driver, this is just a simple example - in practice you
 may need more entries in your group structure, for example specific register
@@ -195,7 +195,7 @@ ranges associated with each group and so on.
 Pin configuration
 =================
-Pins can sometimes be software-configured in an various ways, mostly related
+Pins can sometimes be software-configured in various ways, mostly related
 to their electronic properties when used as inputs or outputs. For example you
 may be able to make an output pin high impedance, or "tristate" meaning it is
 effectively disconnected. You may be able to connect an input pin to VDD or GND
@@ -291,7 +291,7 @@ Since the pin controller subsystem have its pinspace local to the pin
 controller we need a mapping so that the pin control subsystem can figure out
 which pin controller handles control of a certain GPIO pin. Since a single
 pin controller may be muxing several GPIO ranges (typically SoCs that have
-one set of pins but internally several GPIO silicon blocks, each modelled as
+one set of pins, but internally several GPIO silicon blocks, each modelled as
 a struct gpio_chip) any number of GPIO ranges can be added to a pin controller
 instance like this:
@@ -373,9 +373,9 @@ will be called on that specific pin controller.
 For all functionalities dealing with pin biasing, pin muxing etc, the pin
 controller subsystem will look up the corresponding pin number from the passed
-in gpio number, and use the range's internals to retrive a pin number. After
+in gpio number, and use the range's internals to retrieve a pin number. After
 that, the subsystem passes it on to the pin control driver, so the driver
-will get an pin number into its handled number range. Further it is also passed
+will get a pin number into its handled number range. Further it is also passed
 the range ID value, so that the pin controller knows which range it should
 deal with.
@@ -430,8 +430,8 @@ pins you see some will be taken by things like a few VCC and GND to feed power
 to the chip, and quite a few will be taken by large ports like an external
 memory interface. The remaining pins will often be subject to pin multiplexing.
-The example 8x8 PGA package above will have pin numbers 0 thru 63 assigned to
+The example 8x8 PGA package above will have pin numbers 0 through 63 assigned
-its physical pins. It will name the pins { A1, A2, A3 ... H6, H7, H8 } using
+to its physical pins. It will name the pins { A1, A2, A3 ... H6, H7, H8 } using
 pinctrl_register_pins() and a suitable data set as shown earlier.
 In this 8x8 BGA package the pins { A8, A7, A6, A5 } can be used as an SPI port
@@ -442,7 +442,7 @@ we cannot use the SPI port and I2C port at the same time. However in the inside
 of the package the silicon performing the SPI logic can alternatively be routed
 out on pins { G4, G3, G2, G1 }.
-On the botton row at { A1, B1, C1, D1, E1, F1, G1, H1 } we have something
+On the bottom row at { A1, B1, C1, D1, E1, F1, G1, H1 } we have something
 special - it's an external MMC bus that can be 2, 4 or 8 bits wide, and it will
 consume 2, 4 or 8 pins respectively, so either { A1, B1 } are taken or
 { A1, B1, C1, D1 } or all of them. If we use all 8 bits, we cannot use the SPI
@@ -549,7 +549,7 @@ Assumptions:
 We assume that the number of possible function maps to pin groups is limited by
 the hardware. I.e. we assume that there is no system where any function can be
-mapped to any pin, like in a phone exchange. So the available pins groups for
+mapped to any pin, like in a phone exchange. So the available pin groups for
 a certain function will be limited to a few choices (say up to eight or so),
 not hundreds or any amount of choices. This is the characteristic we have found
 by inspecting available pinmux hardware, and a necessary assumption since we
@@ -564,7 +564,7 @@ The pinmux core takes care of preventing conflicts on pins and calling
 the pin controller driver to execute different settings.
 It is the responsibility of the pinmux driver to impose further restrictions
-(say for example infer electronic limitations due to load etc) to determine
+(say for example infer electronic limitations due to load, etc.) to determine
 whether or not the requested function can actually be allowed, and in case it
 is possible to perform the requested mux setting, poke the hardware so that
 this happens.
@@ -755,7 +755,7 @@ Pin control interaction with the GPIO subsystem
 Note that the following implies that the use case is to use a certain pin
 from the Linux kernel using the API in <linux/gpio.h> with gpio_request()
 and similar functions. There are cases where you may be using something
-that your datasheet calls "GPIO mode" but actually is just an electrical
+that your datasheet calls "GPIO mode", but actually is just an electrical
 configuration for a certain device. See the section below named
 "GPIO mode pitfalls" for more details on this scenario.
@@ -871,7 +871,7 @@ hardware and shall be put into different subsystems:
 - Registers (or fields within registers) that control muxing of signals
  from various other HW blocks (e.g. I2C, MMC, or GPIO) onto pins should
-  be exposed through the pinctrl subssytem, as mux functions.
+  be exposed through the pinctrl subsystem, as mux functions.
 - Registers (or fields within registers) that control GPIO functionality
  such as setting a GPIO's output value, reading a GPIO's input value, or
@@ -895,7 +895,7 @@ Example: a pin is usually muxed in to be used as a UART TX line. But during
 system sleep, we need to put this pin into "GPIO mode" and ground it.
 If you make a 1-to-1 map to the GPIO subsystem for this pin, you may start
-to think that you need to come up with something real complex, that the
+to think that you need to come up with something really complex, that the
 pin shall be used for UART TX and GPIO at the same time, that you will grab
 a pin control handle and set it to a certain state to enable UART TX to be
 muxed in, then twist it over to GPIO mode and use gpio_direction_output()
@@ -964,12 +964,12 @@ GPIO mode.
 This will give the desired effect without any bogus interaction with the
 GPIO subsystem. It is just an electrical configuration used by that device
 when going to sleep, it might imply that the pin is set into something the
-datasheet calls "GPIO mode" but that is not the point: it is still used
+datasheet calls "GPIO mode", but that is not the point: it is still used
 by that UART device to control the pins that pertain to that very UART
 driver, putting them into modes needed by the UART. GPIO in the Linux
 kernel sense are just some 1-bit line, and is a different use case.
-How the registers are poked to attain the push/pull and output low
+How the registers are poked to attain the push or pull, and output low
 configuration and the muxing of the "u0" or "gpio-mode" group onto these
 pins is a question for the driver.
@@ -977,7 +977,7 @@ Some datasheets will be more helpful and refer to the "GPIO mode" as
 "low power mode" rather than anything to do with GPIO. This often means
 the same thing electrically speaking, but in this latter case the
 software engineers will usually quickly identify that this is some
-specific muxing/configuration rather than anything related to the GPIO
+specific muxing or configuration rather than anything related to the GPIO
 API.
@@ -1024,8 +1024,7 @@ up the device struct (just like with clockdev or regulators). The function name
 must match a function provided by the pinmux driver handling this pin range.
 As you can see we may have several pin controllers on the system and thus
-we need to specify which one of them that contain the functions we wish
+we need to specify which one of them contains the functions we wish to map.
-to map.
 You register this pinmux mapping to the pinmux subsystem by simply:
@@ -1254,10 +1253,10 @@ The semantics of the pinctrl APIs are:
  pinctrl_get().
 - pinctrl_lookup_state() is called in process context to obtain a handle to a
-  specific state for a the client device. This operation may be slow too.
+  specific state for a client device. This operation may be slow, too.
 - pinctrl_select_state() programs pin controller hardware according to the
-  definition of the state as given by the mapping table. In theory this is a
+  definition of the state as given by the mapping table. In theory, this is a
  fast-path operation, since it only involved blasting some register settings
  into hardware. However, note that some pin controllers may have their
  registers on a slow/IRQ-based bus, so client devices should not assume they
diff --git a/Documentation/robust-futex-ABI.txt b/Documentation/robust-futex-ABI.txt
index fd1cd8aae4eb..16eb314f56cc 100644
--- a/Documentation/robust-futex-ABI.txt
+++ b/Documentation/robust-futex-ABI.txt
@@ -146,8 +146,8 @@ 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,
- 2) release the futex lock, and
+ 3) release the futex lock, and
- 2) clear the 'lock_op_pending' word.
+ 4) clear the 'lock_op_pending' word.
 On exit, the kernel will consider the address stored in
 'list_op_pending' and the address of each 'lock word' found by walking
diff --git a/Documentation/security/IMA-templates.txt b/Documentation/security/IMA-templates.txt
index a777e5f1df5b..a4e102dddfea 100644
--- a/Documentation/security/IMA-templates.txt
+++ b/Documentation/security/IMA-templates.txt
@@ -67,12 +67,14 @@ descriptors by adding their identifier to the format string
 - 'd-ng': the digest of the event, calculated with an arbitrary hash
           algorithm (field format: [<hash algo>:]digest, where the digest
           prefix is shown only if the hash algorithm is not SHA1 or MD5);
- - 'n-ng': the name of the event, without size limitations.
+ - 'n-ng': the name of the event, without size limitations;
+ - 'sig': the file signature.
 Below, there is the list of defined template descriptors:
 - "ima": its format is 'd|n';
- - "ima-ng" (default): its format is 'd-ng|n-ng'.
+ - "ima-ng" (default): its format is 'd-ng|n-ng';
+ - "ima-sig": its format is 'd-ng|n-ng|sig'.
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index 26b7ee491df8..6d486404200e 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -428,11 +428,6 @@ rate for each task.
 numa_balancing_scan_size_mb is how many megabytes worth of pages are
 scanned for a given scan.
-numa_balancing_settle_count is how many scan periods must complete before
-the schedule balancer stops pushing the task towards a preferred node. This
-gives the scheduler a chance to place the task on an alternative node if the
-preferred node is overloaded.
 numa_balancing_migrate_deferred is how many page migrations get skipped
 unconditionally, after a page migration is skipped because a page is shared
 with other tasks. This reduces page migration overhead, and determines
diff --git a/Documentation/vme_api.txt b/Documentation/vme_api.txt
index 856efa35f6e3..ffe6e22a2ccd 100644
--- a/Documentation/vme_api.txt
+++ b/Documentation/vme_api.txt
@@ -393,4 +393,14 @@ Slot Detection
 This function returns the slot ID of the provided bridge.
-        int vme_slot_get(struct vme_dev *dev);
+        int vme_slot_num(struct vme_dev *dev);
+Bus Detection
+=============
+This function returns the bus ID of the provided bridge.
+        int vme_bus_num(struct vme_dev *dev);
diff --git a/Documentation/x86/boot.txt b/Documentation/x86/boot.txt
index f4f268c2b826..cb81741d3b0b 100644
--- a/Documentation/x86/boot.txt
+++ b/Documentation/x86/boot.txt
@@ -608,6 +608,9 @@ Protocol:       2.12+
        - If 1, the kernel supports the 64-bit EFI handoff entry point
          given at handover_offset + 0x200.
+  Bit 4 (read): XLF_EFI_KEXEC
+        - If 1, the kernel supports kexec EFI boot with EFI runtime support.
 Field name:     cmdline_size
 Type:           read
 Offset/size:    0x238/4
diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index 881582f75c9c..c584a51add15 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -28,4 +28,11 @@ reference.
 Current X86-64 implementations only support 40 bits of address space,
 but we support up to 46 bits. This expands into MBZ space in the page tables.
+->trampoline_pgd:
+We map EFI runtime services in the aforementioned PGD in the virtual
+range of 64Gb (arbitrarily set, can be raised if needed)
+0xffffffef00000000 - 0xffffffff00000000
 -Andi Kleen, Jul 2004
diff --git a/Documentation/zh_CN/HOWTO b/Documentation/zh_CN/HOWTO
index 7fba5aab9ef9..6c914aa87e71 100644
--- a/Documentation/zh_CN/HOWTO
+++ b/Documentation/zh_CN/HOWTO
@@ -112,7 +112,7 @@ Linux内核代码中包含有大量的文档。这些文档对于学习如何与
    其他关于如何正确地生成补丁的优秀文档包括：
    "The Perfect Patch"
-        http://userweb.kernel.org/~akpm/stuff/tpp.txt
+        http://www.ozlabs.org/~akpm/stuff/tpp.txt
    "Linux kernel patch submission format"
        http://linux.yyz.us/patch-format.html
@@ -515,7 +515,7 @@ Linux内核社区并不喜欢一下接收大段的代码。修改需要被恰当
 想了解它具体应该看起来像什么，请查阅以下文档中的“ChangeLog”章节：
  “The Perfect Patch”
-         http://userweb.kernel.org/~akpm/stuff/tpp.txt
+         http://www.ozlabs.org/~akpm/stuff/tpp.txt
 这些事情有时候做起来很难。要在任何方面都做到完美可能需要好几年时间。这是
diff --git a/Documentation/zorro.txt b/Documentation/zorro.txt
index d5829d14774a..90a64d52bea2 100644
--- a/Documentation/zorro.txt
+++ b/Documentation/zorro.txt
@@ -95,8 +95,9 @@ The treatment of these regions depends on the type of Zorro space:
 -------------
 linux/include/linux/zorro.h
-linux/include/asm-{m68k,ppc}/zorro.h
+linux/include/uapi/linux/zorro.h
-linux/include/linux/zorro_ids.h
+linux/include/uapi/linux/zorro_ids.h
+linux/arch/m68k/include/asm/zorro.h
 linux/drivers/zorro
 /proc/bus/zorro