char/misc driver patches for 4.11-rc1

Here is the big char/misc driver patchset for 4.11-rc1.
 
 Lots of different driver subsystems updated here.  Rework for the hyperv
 subsystem to handle new platforms better, mei and w1 and extcon driver
 updates, as well as a number of other "minor" driver updates.  Full
 details are in the shortlog below.
 
 All of these have been in linux-next for a while with no reported
 issues.
 
 Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 -----BEGIN PGP SIGNATURE-----
 
 iG0EABECAC0WIQT0tgzFv3jCIUoxPcsxR9QN2y37KQUCWK2iRQ8cZ3JlZ0Brcm9h
 aC5jb20ACgkQMUfUDdst+ynhFACguVE+/ixj5u5bT5DXQaZNai/6zIAAmgMWwd/t
 YTD2cwsJsGbTT1fY3SUe
 =CiSI
 -----END PGP SIGNATURE-----

Merge tag 'char-misc-4.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc

Pull char/misc driver updates from Greg KH:
 "Here is the big char/misc driver patchset for 4.11-rc1.

  Lots of different driver subsystems updated here: rework for the
  hyperv subsystem to handle new platforms better, mei and w1 and extcon
  driver updates, as well as a number of other "minor" driver updates.

  All of these have been in linux-next for a while with no reported
  issues"

* tag 'char-misc-4.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc: (169 commits)
  goldfish: Sanitize the broken interrupt handler
  x86/platform/goldfish: Prevent unconditional loading
  vmbus: replace modulus operation with subtraction
  vmbus: constify parameters where possible
  vmbus: expose hv_begin/end_read
  vmbus: remove conditional locking of vmbus_write
  vmbus: add direct isr callback mode
  vmbus: change to per channel tasklet
  vmbus: put related per-cpu variable together
  vmbus: callback is in softirq not workqueue
  binder: Add support for file-descriptor arrays
  binder: Add support for scatter-gather
  binder: Add extra size to allocator
  binder: Refactor binder_transact()
  binder: Support multiple /dev instances
  binder: Deal with contexts in debugfs
  binder: Support multiple context managers
  binder: Split flat_binder_object
  auxdisplay: ht16k33: remove private workqueue
  auxdisplay: ht16k33: rework input device initialization
  ...

Documentation/DocBook/Makefile

@@ -11,7 +11,7 @@ DOCBOOKS := z8530book.xml  \
 	    writing_usb_driver.xml networking.xml \
 	    kernel-api.xml filesystems.xml lsm.xml kgdb.xml \
 	    gadget.xml libata.xml mtdnand.xml librs.xml rapidio.xml \
-	    genericirq.xml s390-drivers.xml uio-howto.xml scsi.xml \
+	    genericirq.xml s390-drivers.xml scsi.xml \
 	    sh.xml regulator.xml w1.xml \
 	    writing_musb_glue_layer.xml iio.xml
 

Documentation/admin-guide/kernel-parameters.txt

@@ -1195,6 +1195,10 @@
 			When zero, profiling data is discarded and associated
 			debugfs files are removed at module unload time.
 
+	goldfish	[X86] Enable the goldfish android emulator platform.
+			Don't use this when you are not running on the
+			android emulator
+
 	gpt		[EFI] Forces disk with valid GPT signature but
 			invalid Protective MBR to be treated as GPT. If the
 			primary GPT is corrupted, it enables the backup/alternate

Documentation/devicetree/bindings/misc/idt_89hpesx.txt

@@ -0,0 +1,44 @@
+EEPROM / CSR SMBus-slave interface of IDT 89HPESx devices
+
+Required properties:
+  - compatible : should be "<manufacturer>,<type>"
+		 Basically there is only one manufacturer: idt, but some
+		 compatible devices may be produced in future. Following devices
+		 are supported: 89hpes8nt2, 89hpes12nt3, 89hpes24nt6ag2,
+		 89hpes32nt8ag2, 89hpes32nt8bg2, 89hpes12nt12g2, 89hpes16nt16g2,
+		 89hpes24nt24g2, 89hpes32nt24ag2, 89hpes32nt24bg2;
+		 89hpes12n3, 89hpes12n3a, 89hpes24n3, 89hpes24n3a;
+		 89hpes32h8, 89hpes32h8g2, 89hpes48h12, 89hpes48h12g2,
+		 89hpes48h12ag2, 89hpes16h16, 89hpes22h16, 89hpes22h16g2,
+		 89hpes34h16, 89hpes34h16g2, 89hpes64h16, 89hpes64h16g2,
+		 89hpes64h16ag2;
+		 89hpes12t3g2, 89hpes24t3g2, 89hpes16t4, 89hpes4t4g2,
+		 89hpes10t4g2, 89hpes16t4g2, 89hpes16t4ag2, 89hpes5t5,
+		 89hpes6t5, 89hpes8t5, 89hpes8t5a, 89hpes24t6, 89hpes6t6g2,
+		 89hpes24t6g2, 89hpes16t7, 89hpes32t8, 89hpes32t8g2,
+		 89hpes48t12, 89hpes48t12g2.
+  - reg :	 I2C address of the IDT 89HPESx device.
+
+Optionally there can be EEPROM-compatible subnode:
+  - compatible:  There are five EEPROM devices supported: 24c32, 24c64, 24c128,
+		 24c256 and 24c512 differed by size.
+  - reg:         Custom address of EEPROM device (If not specified IDT 89HPESx
+    (optional)	 device will try to communicate with EEPROM sited by default
+		 address - 0x50)
+  - read-only :	 Parameterless property disables writes to the EEPROM
+    (optional)
+
+Example:
+	idt@60 {
+		compatible = "idt,89hpes32nt8ag2";
+		reg = <0x74>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		eeprom@50 {
+			compatible = "onsemi,24c64";
+			reg = <0x50>;
+			read-only;
+		};
+	};
+

Documentation/devicetree/bindings/nvmem/imx-ocotp.txt

@@ -1,13 +1,15 @@
 Freescale i.MX6 On-Chip OTP Controller (OCOTP) device tree bindings
 
 This binding represents the on-chip eFuse OTP controller found on
-i.MX6Q/D, i.MX6DL/S, i.MX6SL, and i.MX6SX SoCs.
+i.MX6Q/D, i.MX6DL/S, i.MX6SL, i.MX6SX and i.MX6UL SoCs.
 
 Required properties:
 - compatible: should be one of
 	"fsl,imx6q-ocotp" (i.MX6Q/D/DL/S),
 	"fsl,imx6sl-ocotp" (i.MX6SL), or
-	"fsl,imx6sx-ocotp" (i.MX6SX), followed by "syscon".
+	"fsl,imx6sx-ocotp" (i.MX6SX),
+	"fsl,imx6ul-ocotp" (i.MX6UL),
+	followed by "syscon".
 - reg: Should contain the register base and length.
 - clocks: Should contain a phandle pointing to the gated peripheral clock.
 

Documentation/devicetree/bindings/sram/sram.txt

@@ -42,6 +42,12 @@ Optional properties in the area nodes:
          and in use by another device or devices
 - export : indicates that the reserved SRAM area may be accessed outside
            of the kernel, e.g. by bootloader or userspace
+- protect-exec : Same as 'pool' above but with the additional
+		 constraint that code wil be run from the region and
+		 that the memory is maintained as read-only, executable
+		 during code execution. NOTE: This region must be page
+		 aligned on start and end in order to properly allow
+		 manipulation of the page attributes.
 - label : the name for the reserved partition, if omitted, the label
           is taken from the node name excluding the unit address.
 

Documentation/driver-api/index.rst

@@ -30,6 +30,7 @@ available subsections can be seen below.
    miscellaneous
    vme
    80211/index
+   uio-howto
 
 .. only::  subproject and html
 

Documentation/driver-api/uio-howto.rst

@@ -0,0 +1,705 @@
+=======================
+The Userspace I/O HOWTO
+=======================
+
+:Author: Hans-Jürgen Koch Linux developer, Linutronix
+:Date:   2006-12-11
+
+About this document
+===================
+
+Translations
+------------
+
+If you know of any translations for this document, or you are interested
+in translating it, please email me hjk@hansjkoch.de.
+
+Preface
+-------
+
+For many types of devices, creating a Linux kernel driver is overkill.
+All that is really needed is some way to handle an interrupt and provide
+access to the memory space of the device. The logic of controlling the
+device does not necessarily have to be within the kernel, as the device
+does not need to take advantage of any of other resources that the
+kernel provides. One such common class of devices that are like this are
+for industrial I/O cards.
+
+To address this situation, the userspace I/O system (UIO) was designed.
+For typical industrial I/O cards, only a very small kernel module is
+needed. The main part of the driver will run in user space. This
+simplifies development and reduces the risk of serious bugs within a
+kernel module.
+
+Please note that UIO is not an universal driver interface. Devices that
+are already handled well by other kernel subsystems (like networking or
+serial or USB) are no candidates for an UIO driver. Hardware that is
+ideally suited for an UIO driver fulfills all of the following:
+
+-  The device has memory that can be mapped. The device can be
+   controlled completely by writing to this memory.
+
+-  The device usually generates interrupts.
+
+-  The device does not fit into one of the standard kernel subsystems.
+
+Acknowledgments
+---------------
+
+I'd like to thank Thomas Gleixner and Benedikt Spranger of Linutronix,
+who have not only written most of the UIO code, but also helped greatly
+writing this HOWTO by giving me all kinds of background information.
+
+Feedback
+--------
+
+Find something wrong with this document? (Or perhaps something right?) I
+would love to hear from you. Please email me at hjk@hansjkoch.de.
+
+About UIO
+=========
+
+If you use UIO for your card's driver, here's what you get:
+
+-  only one small kernel module to write and maintain.
+
+-  develop the main part of your driver in user space, with all the
+   tools and libraries you're used to.
+
+-  bugs in your driver won't crash the kernel.
+
+-  updates of your driver can take place without recompiling the kernel.
+
+How UIO works
+-------------
+
+Each UIO device is accessed through a device file and several sysfs
+attribute files. The device file will be called ``/dev/uio0`` for the
+first device, and ``/dev/uio1``, ``/dev/uio2`` and so on for subsequent
+devices.
+
+``/dev/uioX`` is used to access the address space of the card. Just use
+:c:func:`mmap()` to access registers or RAM locations of your card.
+
+Interrupts are handled by reading from ``/dev/uioX``. A blocking
+:c:func:`read()` from ``/dev/uioX`` will return as soon as an
+interrupt occurs. You can also use :c:func:`select()` on
+``/dev/uioX`` to wait for an interrupt. The integer value read from
+``/dev/uioX`` represents the total interrupt count. You can use this
+number to figure out if you missed some interrupts.
+
+For some hardware that has more than one interrupt source internally,
+but not separate IRQ mask and status registers, there might be
+situations where userspace cannot determine what the interrupt source
+was if the kernel handler disables them by writing to the chip's IRQ
+register. In such a case, the kernel has to disable the IRQ completely
+to leave the chip's register untouched. Now the userspace part can
+determine the cause of the interrupt, but it cannot re-enable
+interrupts. Another cornercase is chips where re-enabling interrupts is
+a read-modify-write operation to a combined IRQ status/acknowledge
+register. This would be racy if a new interrupt occurred simultaneously.
+
+To address these problems, UIO also implements a write() function. It is
+normally not used and can be ignored for hardware that has only a single
+interrupt source or has separate IRQ mask and status registers. If you
+need it, however, a write to ``/dev/uioX`` will call the
+:c:func:`irqcontrol()` function implemented by the driver. You have
+to write a 32-bit value that is usually either 0 or 1 to disable or
+enable interrupts. If a driver does not implement
+:c:func:`irqcontrol()`, :c:func:`write()` will return with
+``-ENOSYS``.
+
+To handle interrupts properly, your custom kernel module can provide its
+own interrupt handler. It will automatically be called by the built-in
+handler.
+
+For cards that don't generate interrupts but need to be polled, there is
+the possibility to set up a timer that triggers the interrupt handler at
+configurable time intervals. This interrupt simulation is done by
+calling :c:func:`uio_event_notify()` from the timer's event
+handler.
+
+Each driver provides attributes that are used to read or write
+variables. These attributes are accessible through sysfs files. A custom
+kernel driver module can add its own attributes to the device owned by
+the uio driver, but not added to the UIO device itself at this time.
+This might change in the future if it would be found to be useful.
+
+The following standard attributes are provided by the UIO framework:
+
+-  ``name``: The name of your device. It is recommended to use the name
+   of your kernel module for this.
+
+-  ``version``: A version string defined by your driver. This allows the
+   user space part of your driver to deal with different versions of the
+   kernel module.
+
+-  ``event``: The total number of interrupts handled by the driver since
+   the last time the device node was read.
+
+These attributes appear under the ``/sys/class/uio/uioX`` directory.
+Please note that this directory might be a symlink, and not a real
+directory. Any userspace code that accesses it must be able to handle
+this.
+
+Each UIO device can make one or more memory regions available for memory
+mapping. This is necessary because some industrial I/O cards require
+access to more than one PCI memory region in a driver.
+
+Each mapping has its own directory in sysfs, the first mapping appears
+as ``/sys/class/uio/uioX/maps/map0/``. Subsequent mappings create
+directories ``map1/``, ``map2/``, and so on. These directories will only
+appear if the size of the mapping is not 0.
+
+Each ``mapX/`` directory contains four read-only files that show
+attributes of the memory:
+
+-  ``name``: A string identifier for this mapping. This is optional, the
+   string can be empty. Drivers can set this to make it easier for
+   userspace to find the correct mapping.
+
+-  ``addr``: The address of memory that can be mapped.
+
+-  ``size``: The size, in bytes, of the memory pointed to by addr.
+
+-  ``offset``: The offset, in bytes, that has to be added to the pointer
+   returned by :c:func:`mmap()` to get to the actual device memory.
+   This is important if the device's memory is not page aligned.
+   Remember that pointers returned by :c:func:`mmap()` are always
+   page aligned, so it is good style to always add this offset.
+
+From userspace, the different mappings are distinguished by adjusting
+the ``offset`` parameter of the :c:func:`mmap()` call. To map the
+memory of mapping N, you have to use N times the page size as your
+offset::
+
+    offset = N * getpagesize();
+
+Sometimes there is hardware with memory-like regions that can not be
+mapped with the technique described here, but there are still ways to
+access them from userspace. The most common example are x86 ioports. On
+x86 systems, userspace can access these ioports using
+:c:func:`ioperm()`, :c:func:`iopl()`, :c:func:`inb()`,
+:c:func:`outb()`, and similar functions.
+
+Since these ioport regions can not be mapped, they will not appear under
+``/sys/class/uio/uioX/maps/`` like the normal memory described above.
+Without information about the port regions a hardware has to offer, it
+becomes difficult for the userspace part of the driver to find out which
+ports belong to which UIO device.
+
+To address this situation, the new directory
+``/sys/class/uio/uioX/portio/`` was added. It only exists if the driver
+wants to pass information about one or more port regions to userspace.
+If that is the case, subdirectories named ``port0``, ``port1``, and so
+on, will appear underneath ``/sys/class/uio/uioX/portio/``.
+
+Each ``portX/`` directory contains four read-only files that show name,
+start, size, and type of the port region:
+
+-  ``name``: A string identifier for this port region. The string is
+   optional and can be empty. Drivers can set it to make it easier for
+   userspace to find a certain port region.
+
+-  ``start``: The first port of this region.
+
+-  ``size``: The number of ports in this region.
+
+-  ``porttype``: A string describing the type of port.
+
+Writing your own kernel module
+==============================
+
+Please have a look at ``uio_cif.c`` as an example. The following
+paragraphs explain the different sections of this file.
+
+struct uio_info
+---------------
+
+This structure tells the framework the details of your driver, Some of
+the members are required, others are optional.
+
+-  ``const char *name``: Required. The name of your driver as it will
+   appear in sysfs. I recommend using the name of your module for this.
+
+-  ``const char *version``: Required. This string appears in
+   ``/sys/class/uio/uioX/version``.
+
+-  ``struct uio_mem mem[ MAX_UIO_MAPS ]``: Required if you have memory
+   that can be mapped with :c:func:`mmap()`. For each mapping you
+   need to fill one of the ``uio_mem`` structures. See the description
+   below for details.
+
+-  ``struct uio_port port[ MAX_UIO_PORTS_REGIONS ]``: Required if you
+   want to pass information about ioports to userspace. For each port
+   region you need to fill one of the ``uio_port`` structures. See the
+   description below for details.
+
+-  ``long irq``: Required. If your hardware generates an interrupt, it's
+   your modules task to determine the irq number during initialization.
+   If you don't have a hardware generated interrupt but want to trigger
+   the interrupt handler in some other way, set ``irq`` to
+   ``UIO_IRQ_CUSTOM``. If you had no interrupt at all, you could set
+   ``irq`` to ``UIO_IRQ_NONE``, though this rarely makes sense.
+
+-  ``unsigned long irq_flags``: Required if you've set ``irq`` to a
+   hardware interrupt number. The flags given here will be used in the
+   call to :c:func:`request_irq()`.
+
+-  ``int (*mmap)(struct uio_info *info, struct vm_area_struct *vma)``:
+   Optional. If you need a special :c:func:`mmap()`
+   function, you can set it here. If this pointer is not NULL, your
+   :c:func:`mmap()` will be called instead of the built-in one.
+
+-  ``int (*open)(struct uio_info *info, struct inode *inode)``:
+   Optional. You might want to have your own :c:func:`open()`,
+   e.g. to enable interrupts only when your device is actually used.
+
+-  ``int (*release)(struct uio_info *info, struct inode *inode)``:
+   Optional. If you define your own :c:func:`open()`, you will
+   probably also want a custom :c:func:`release()` function.
+
+-  ``int (*irqcontrol)(struct uio_info *info, s32 irq_on)``:
+   Optional. If you need to be able to enable or disable interrupts
+   from userspace by writing to ``/dev/uioX``, you can implement this
+   function. The parameter ``irq_on`` will be 0 to disable interrupts
+   and 1 to enable them.
+
+Usually, your device will have one or more memory regions that can be
+mapped to user space. For each region, you have to set up a
+``struct uio_mem`` in the ``mem[]`` array. Here's a description of the
+fields of ``struct uio_mem``:
+
+-  ``const char *name``: Optional. Set this to help identify the memory
+   region, it will show up in the corresponding sysfs node.
+
+-  ``int memtype``: Required if the mapping is used. Set this to
+   ``UIO_MEM_PHYS`` if you you have physical memory on your card to be
+   mapped. Use ``UIO_MEM_LOGICAL`` for logical memory (e.g. allocated
+   with :c:func:`kmalloc()`). There's also ``UIO_MEM_VIRTUAL`` for
+   virtual memory.
+
+-  ``phys_addr_t addr``: Required if the mapping is used. Fill in the
+   address of your memory block. This address is the one that appears in
+   sysfs.
+
+-  ``resource_size_t size``: Fill in the size of the memory block that
+   ``addr`` points to. If ``size`` is zero, the mapping is considered
+   unused. Note that you *must* initialize ``size`` with zero for all
+   unused mappings.
+
+-  ``void *internal_addr``: If you have to access this memory region
+   from within your kernel module, you will want to map it internally by
+   using something like :c:func:`ioremap()`. Addresses returned by
+   this function cannot be mapped to user space, so you must not store
+   it in ``addr``. Use ``internal_addr`` instead to remember such an
+   address.
+
+Please do not touch the ``map`` element of ``struct uio_mem``! It is
+used by the UIO framework to set up sysfs files for this mapping. Simply
+leave it alone.
+
+Sometimes, your device can have one or more port regions which can not
+be mapped to userspace. But if there are other possibilities for
+userspace to access these ports, it makes sense to make information
+about the ports available in sysfs. For each region, you have to set up
+a ``struct uio_port`` in the ``port[]`` array. Here's a description of
+the fields of ``struct uio_port``:
+
+-  ``char *porttype``: Required. Set this to one of the predefined
+   constants. Use ``UIO_PORT_X86`` for the ioports found in x86
+   architectures.
+
+-  ``unsigned long start``: Required if the port region is used. Fill in
+   the number of the first port of this region.
+
+-  ``unsigned long size``: Fill in the number of ports in this region.
+   If ``size`` is zero, the region is considered unused. Note that you
+   *must* initialize ``size`` with zero for all unused regions.
+
+Please do not touch the ``portio`` element of ``struct uio_port``! It is
+used internally by the UIO framework to set up sysfs files for this
+region. Simply leave it alone.
+
+Adding an interrupt handler
+---------------------------
+
+What you need to do in your interrupt handler depends on your hardware
+and on how you want to handle it. You should try to keep the amount of
+code in your kernel interrupt handler low. If your hardware requires no
+action that you *have* to perform after each interrupt, then your
+handler can be empty.
+
+If, on the other hand, your hardware *needs* some action to be performed
+after each interrupt, then you *must* do it in your kernel module. Note
+that you cannot rely on the userspace part of your driver. Your
+userspace program can terminate at any time, possibly leaving your
+hardware in a state where proper interrupt handling is still required.
+
+There might also be applications where you want to read data from your
+hardware at each interrupt and buffer it in a piece of kernel memory
+you've allocated for that purpose. With this technique you could avoid
+loss of data if your userspace program misses an interrupt.
+
+A note on shared interrupts: Your driver should support interrupt
+sharing whenever this is possible. It is possible if and only if your
+driver can detect whether your hardware has triggered the interrupt or
+not. This is usually done by looking at an interrupt status register. If
+your driver sees that the IRQ bit is actually set, it will perform its
+actions, and the handler returns IRQ_HANDLED. If the driver detects
+that it was not your hardware that caused the interrupt, it will do
+nothing and return IRQ_NONE, allowing the kernel to call the next
+possible interrupt handler.
+
+If you decide not to support shared interrupts, your card won't work in
+computers with no free interrupts. As this frequently happens on the PC
+platform, you can save yourself a lot of trouble by supporting interrupt
+sharing.
+
+Using uio_pdrv for platform devices
+-----------------------------------
+
+In many cases, UIO drivers for platform devices can be handled in a
+generic way. In the same place where you define your
+``struct platform_device``, you simply also implement your interrupt
+handler and fill your ``struct uio_info``. A pointer to this
+``struct uio_info`` is then used as ``platform_data`` for your platform
+device.
+
+You also need to set up an array of ``struct resource`` containing
+addresses and sizes of your memory mappings. This information is passed
+to the driver using the ``.resource`` and ``.num_resources`` elements of
+``struct platform_device``.
+
+You now have to set the ``.name`` element of ``struct platform_device``
+to ``"uio_pdrv"`` to use the generic UIO platform device driver. This
+driver will fill the ``mem[]`` array according to the resources given,
+and register the device.
+
+The advantage of this approach is that you only have to edit a file you
+need to edit anyway. You do not have to create an extra driver.
+
+Using uio_pdrv_genirq for platform devices
+------------------------------------------
+
+Especially in embedded devices, you frequently find chips where the irq
+pin is tied to its own dedicated interrupt line. In such cases, where
+you can be really sure the interrupt is not shared, we can take the
+concept of ``uio_pdrv`` one step further and use a generic interrupt
+handler. That's what ``uio_pdrv_genirq`` does.
+
+The setup for this driver is the same as described above for
+``uio_pdrv``, except that you do not implement an interrupt handler. The
+``.handler`` element of ``struct uio_info`` must remain ``NULL``. The
+``.irq_flags`` element must not contain ``IRQF_SHARED``.
+
+You will set the ``.name`` element of ``struct platform_device`` to
+``"uio_pdrv_genirq"`` to use this driver.
+
+The generic interrupt handler of ``uio_pdrv_genirq`` will simply disable
+the interrupt line using :c:func:`disable_irq_nosync()`. After
+doing its work, userspace can reenable the interrupt by writing
+0x00000001 to the UIO device file. The driver already implements an
+:c:func:`irq_control()` to make this possible, you must not
+implement your own.
+
+Using ``uio_pdrv_genirq`` not only saves a few lines of interrupt
+handler code. You also do not need to know anything about the chip's
+internal registers to create the kernel part of the driver. All you need
+to know is the irq number of the pin the chip is connected to.
+
+Using uio_dmem_genirq for platform devices
+------------------------------------------
+
+In addition to statically allocated memory ranges, they may also be a
+desire to use dynamically allocated regions in a user space driver. In
+particular, being able to access memory made available through the
+dma-mapping API, may be particularly useful. The ``uio_dmem_genirq``
+driver provides a way to accomplish this.
+
+This driver is used in a similar manner to the ``"uio_pdrv_genirq"``
+driver with respect to interrupt configuration and handling.
+
+Set the ``.name`` element of ``struct platform_device`` to
+``"uio_dmem_genirq"`` to use this driver.
+
+When using this driver, fill in the ``.platform_data`` element of
+``struct platform_device``, which is of type
+``struct uio_dmem_genirq_pdata`` and which contains the following
+elements:
+
+-  ``struct uio_info uioinfo``: The same structure used as the
+   ``uio_pdrv_genirq`` platform data
+
+-  ``unsigned int *dynamic_region_sizes``: Pointer to list of sizes of
+   dynamic memory regions to be mapped into user space.
+
+-  ``unsigned int num_dynamic_regions``: Number of elements in
+   ``dynamic_region_sizes`` array.
+
+The dynamic regions defined in the platform data will be appended to the
+`` mem[] `` array after the platform device resources, which implies
+that the total number of static and dynamic memory regions cannot exceed
+``MAX_UIO_MAPS``.
+
+The dynamic memory regions will be allocated when the UIO device file,
+``/dev/uioX`` is opened. Similar to static memory resources, the memory
+region information for dynamic regions is then visible via sysfs at
+``/sys/class/uio/uioX/maps/mapY/*``. The dynamic memory regions will be
+freed when the UIO device file is closed. When no processes are holding
+the device file open, the address returned to userspace is ~0.
+
+Writing a driver in userspace
+=============================
+
+Once you have a working kernel module for your hardware, you can write
+the userspace part of your driver. You don't need any special libraries,
+your driver can be written in any reasonable language, you can use
+floating point numbers and so on. In short, you can use all the tools
+and libraries you'd normally use for writing a userspace application.
+
+Getting information about your UIO device
+-----------------------------------------
+
+Information about all UIO devices is available in sysfs. The first thing
+you should do in your driver is check ``name`` and ``version`` to make
+sure your talking to the right device and that its kernel driver has the
+version you expect.
+
+You should also make sure that the memory mapping you need exists and
+has the size you expect.
+
+There is a tool called ``lsuio`` that lists UIO devices and their
+attributes. It is available here:
+
+http://www.osadl.org/projects/downloads/UIO/user/
+
+With ``lsuio`` you can quickly check if your kernel module is loaded and
+which attributes it exports. Have a look at the manpage for details.
+
+The source code of ``lsuio`` can serve as an example for getting
+information about an UIO device. The file ``uio_helper.c`` contains a
+lot of functions you could use in your userspace driver code.
+
+mmap() device memory
+--------------------
+
+After you made sure you've got the right device with the memory mappings
+you need, all you have to do is to call :c:func:`mmap()` to map the
+device's memory to userspace.
+
+The parameter ``offset`` of the :c:func:`mmap()` call has a special
+meaning for UIO devices: It is used to select which mapping of your
+device you want to map. To map the memory of mapping N, you have to use
+N times the page size as your offset::
+
+        offset = N * getpagesize();
+
+N starts from zero, so if you've got only one memory range to map, set
+``offset = 0``. A drawback of this technique is that memory is always
+mapped beginning with its start address.
+
+Waiting for interrupts
+----------------------
+
+After you successfully mapped your devices memory, you can access it
+like an ordinary array. Usually, you will perform some initialization.
+After that, your hardware starts working and will generate an interrupt
+as soon as it's finished, has some data available, or needs your
+attention because an error occurred.
+
+``/dev/uioX`` is a read-only file. A :c:func:`read()` will always
+block until an interrupt occurs. There is only one legal value for the
+``count`` parameter of :c:func:`read()`, and that is the size of a
+signed 32 bit integer (4). Any other value for ``count`` causes
+:c:func:`read()` to fail. The signed 32 bit integer read is the
+interrupt count of your device. If the value is one more than the value
+you read the last time, everything is OK. If the difference is greater
+than one, you missed interrupts.
+
+You can also use :c:func:`select()` on ``/dev/uioX``.
+
+Generic PCI UIO driver
+======================
+
+The generic driver is a kernel module named uio_pci_generic. It can
+work with any device compliant to PCI 2.3 (circa 2002) and any compliant
+PCI Express device. Using this, you only need to write the userspace
+driver, removing the need to write a hardware-specific kernel module.
+
+Making the driver recognize the device
+--------------------------------------
+
+Since the driver does not declare any device ids, it will not get loaded
+automatically and will not automatically bind to any devices, you must
+load it and allocate id to the driver yourself. For example::
+
+     modprobe uio_pci_generic
+     echo "8086 10f5" > /sys/bus/pci/drivers/uio_pci_generic/new_id
+
+If there already is a hardware specific kernel driver for your device,
+the generic driver still won't bind to it, in this case if you want to
+use the generic driver (why would you?) you'll have to manually unbind
+the hardware specific driver and bind the generic driver, like this::
+
+        echo -n 0000:00:19.0 > /sys/bus/pci/drivers/e1000e/unbind
+        echo -n 0000:00:19.0 > /sys/bus/pci/drivers/uio_pci_generic/bind
+
+You can verify that the device has been bound to the driver by looking
+for it in sysfs, for example like the following::
+
+        ls -l /sys/bus/pci/devices/0000:00:19.0/driver
+
+Which if successful should print::
+
+      .../0000:00:19.0/driver -> ../../../bus/pci/drivers/uio_pci_generic
+
+Note that the generic driver will not bind to old PCI 2.2 devices. If
+binding the device failed, run the following command::
+
+      dmesg
+
+and look in the output for failure reasons.
+
+Things to know about uio_pci_generic
+------------------------------------
+
+Interrupts are handled using the Interrupt Disable bit in the PCI
+command register and Interrupt Status bit in the PCI status register.
+All devices compliant to PCI 2.3 (circa 2002) and all compliant PCI
+Express devices should support these bits. uio_pci_generic detects
+this support, and won't bind to devices which do not support the
+Interrupt Disable Bit in the command register.
+
+On each interrupt, uio_pci_generic sets the Interrupt Disable bit.
+This prevents the device from generating further interrupts until the
+bit is cleared. The userspace driver should clear this bit before
+blocking and waiting for more interrupts.
+
+Writing userspace driver using uio_pci_generic
+------------------------------------------------
+
+Userspace driver can use pci sysfs interface, or the libpci library that
+wraps it, to talk to the device and to re-enable interrupts by writing
+to the command register.
+
+Example code using uio_pci_generic
+----------------------------------
+
+Here is some sample userspace driver code using uio_pci_generic::
+
+    #include <stdlib.h>
+    #include <stdio.h>
+    #include <unistd.h>
+    #include <sys/types.h>
+    #include <sys/stat.h>
+    #include <fcntl.h>
+    #include <errno.h>
+
+    int main()
+    {
+        int uiofd;
+        int configfd;
+        int err;
+        int i;
+        unsigned icount;
+        unsigned char command_high;
+
+        uiofd = open("/dev/uio0", O_RDONLY);
+        if (uiofd < 0) {
+            perror("uio open:");
+            return errno;
+        }
+        configfd = open("/sys/class/uio/uio0/device/config", O_RDWR);
+        if (configfd < 0) {
+            perror("config open:");
+            return errno;
+        }
+
+        /* Read and cache command value */
+        err = pread(configfd, &command_high, 1, 5);
+        if (err != 1) {
+            perror("command config read:");
+            return errno;
+        }
+        command_high &= ~0x4;
+
+        for(i = 0;; ++i) {
+            /* Print out a message, for debugging. */
+            if (i == 0)
+                fprintf(stderr, "Started uio test driver.\n");
+            else
+                fprintf(stderr, "Interrupts: %d\n", icount);
+
+            /****************************************/
+            /* Here we got an interrupt from the
+               device. Do something to it. */
+            /****************************************/
+
+            /* Re-enable interrupts. */
+            err = pwrite(configfd, &command_high, 1, 5);
+            if (err != 1) {
+                perror("config write:");
+                break;
+            }
+
+            /* Wait for next interrupt. */
+            err = read(uiofd, &icount, 4);
+            if (err != 4) {
+                perror("uio read:");
+                break;
+            }
+
+        }
+        return errno;
+    }
+
+Generic Hyper-V UIO driver
+==========================
+
+The generic driver is a kernel module named uio_hv_generic. It
+supports devices on the Hyper-V VMBus similar to uio_pci_generic on
+PCI bus.
+
+Making the driver recognize the device
+--------------------------------------
+
+Since the driver does not declare any device GUID's, it will not get
+loaded automatically and will not automatically bind to any devices, you
+must load it and allocate id to the driver yourself. For example, to use
+the network device GUID::
+
+     modprobe uio_hv_generic
+     echo "f8615163-df3e-46c5-913f-f2d2f965ed0e" > /sys/bus/vmbus/drivers/uio_hv_generic/new_id
+
+If there already is a hardware specific kernel driver for the device,
+the generic driver still won't bind to it, in this case if you want to
+use the generic driver (why would you?) you'll have to manually unbind
+the hardware specific driver and bind the generic driver, like this::
+
+          echo -n vmbus-ed963694-e847-4b2a-85af-bc9cfc11d6f3 > /sys/bus/vmbus/drivers/hv_netvsc/unbind
+          echo -n vmbus-ed963694-e847-4b2a-85af-bc9cfc11d6f3 > /sys/bus/vmbus/drivers/uio_hv_generic/bind
+
+You can verify that the device has been bound to the driver by looking
+for it in sysfs, for example like the following::
+
+        ls -l /sys/bus/vmbus/devices/vmbus-ed963694-e847-4b2a-85af-bc9cfc11d6f3/driver
+
+Which if successful should print::
+
+      .../vmbus-ed963694-e847-4b2a-85af-bc9cfc11d6f3/driver -> ../../../bus/vmbus/drivers/uio_hv_generic
+
+Things to know about uio_hv_generic
+-----------------------------------
+
+On each interrupt, uio_hv_generic sets the Interrupt Disable bit. This
+prevents the device from generating further interrupts until the bit is
+cleared. The userspace driver should clear this bit before blocking and
+waiting for more interrupts.
+
+Further information
+===================
+
+-  `OSADL homepage. <http://www.osadl.org>`_
+
+-  `Linutronix homepage. <http://www.linutronix.de>`_

Documentation/extcon/intel-int3496.txt

@@ -0,0 +1,22 @@
+Intel INT3496 ACPI device extcon driver documentation
+-----------------------------------------------------
+
+The Intel INT3496 ACPI device extcon driver is a driver for ACPI
+devices with an acpi-id of INT3496, such as found for example on
+Intel Baytrail and Cherrytrail tablets.
+
+This ACPI device describes how the OS can read the id-pin of the devices'
+USB-otg port, as well as how it optionally can enable Vbus output on the
+otg port and how it can optionally control the muxing of the data pins
+between an USB host and an USB peripheral controller.
+
+The ACPI devices exposes this functionality by returning an array with up
+to 3 gpio descriptors from its ACPI _CRS (Current Resource Settings) call:
+
+Index 0: The input gpio for the id-pin, this is always present and valid
+Index 1: The output gpio for enabling Vbus output from the device to the otg
+         port, write 1 to enable the Vbus output (this gpio descriptor may
+         be absent or invalid)
+Index 2: The output gpio for muxing of the data pins between the USB host and
+         the USB peripheral controller, write 1 to mux to the peripheral
+         controller

Documentation/fpga/fpga-mgr.txt

@@ -22,7 +22,16 @@ To program the FPGA from a file or from a buffer:
 			      struct fpga_image_info *info,
 		              const char *buf, size_t count);
 
-Load the FPGA from an image which exists as a buffer in memory.
+Load the FPGA from an image which exists as a contiguous buffer in
+memory. Allocating contiguous kernel memory for the buffer should be avoided,
+users are encouraged to use the _sg interface instead of this.
+
+        int fpga_mgr_buf_load_sg(struct fpga_manager *mgr,
+				 struct fpga_image_info *info,
+				 struct sg_table *sgt);
+
+Load the FPGA from an image from non-contiguous in memory. Callers can
+construct a sg_table using alloc_page backed memory.
 
 	int fpga_mgr_firmware_load(struct fpga_manager *mgr,
 				   struct fpga_image_info *info,
@@ -166,7 +175,7 @@ success or negative error codes otherwise.
 
 The programming sequence is:
  1. .write_init
- 2. .write (may be called once or multiple times)
+ 2. .write or .write_sg (may be called once or multiple times)
  3. .write_complete
 
 The .write_init function will prepare the FPGA to receive the image data.  The
@@ -176,7 +185,11 @@ buffer up at least this much before starting.
 
 The .write function writes a buffer to the FPGA. The buffer may be contain the
 whole FPGA image or may be a smaller chunk of an FPGA image.  In the latter
-case, this function is called multiple times for successive chunks.
+case, this function is called multiple times for successive chunks. This interface
+is suitable for drivers which use PIO.
+
+The .write_sg version behaves the same as .write except the input is a sg_table
+scatter list. This interface is suitable for drivers which use DMA.
 
 The .write_complete function is called after all the image has been written
 to put the FPGA into operating mode.

MAINTAINERS

@@ -5993,6 +5993,7 @@ S:	Maintained
 F:	arch/x86/include/asm/mshyperv.h
 F:	arch/x86/include/uapi/asm/hyperv.h
 F:	arch/x86/kernel/cpu/mshyperv.c
+F:	arch/x86/hyperv
 F:	drivers/hid/hid-hyperv.c
 F:	drivers/hv/
 F:	drivers/input/serio/hyperv-keyboard.c
@@ -13071,7 +13072,7 @@ USERSPACE I/O (UIO)
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc.git
-F:	Documentation/DocBook/uio-howto.tmpl
+F:	Documentation/driver-api/uio-howto.rst
 F:	drivers/uio/
 F:	include/linux/uio*.h
 

arch/arm/mach-davinci/da850.c

@@ -557,15 +557,7 @@ static struct clk_lookup da850_clks[] = {
 	CLK("da830-mmc.0",	NULL,		&mmcsd0_clk),
 	CLK("da830-mmc.1",	NULL,		&mmcsd1_clk),
 	CLK("ti-aemif",		NULL,		&aemif_clk),
-	/*
+	CLK("davinci-nand.0",	"aemif",	&aemif_nand_clk),
-	 * The only user of this clock is davinci_nand and it get's it through
-	 * con_id. The nand node itself is created from within the aemif
-	 * driver to guarantee that it's probed after the aemif timing
-	 * parameters are configured. of_dev_auxdata is not accessible from
-	 * the aemif driver and can't be passed to of_platform_populate(). For
-	 * that reason we're leaving the dev_id here as NULL.
-	 */
-	CLK(NULL,		"aemif",	&aemif_nand_clk),
 	CLK("ohci-da8xx",	"usb11",	&usb11_clk),
 	CLK("musb-da8xx",	"usb20",	&usb20_clk),
 	CLK("spi_davinci.0",	NULL,		&spi0_clk),

arch/arm/mach-davinci/da8xx-dt.c

@@ -11,6 +11,7 @@
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <linux/irqdomain.h>
+#include <linux/platform_data/ti-aemif.h>
 
 #include <asm/mach/arch.h>
 
@@ -18,6 +19,15 @@
 #include "cp_intc.h"
 #include <mach/da8xx.h>
 
+static struct of_dev_auxdata da850_aemif_auxdata_lookup[] = {
+	OF_DEV_AUXDATA("ti,davinci-nand", 0x62000000, "davinci-nand.0", NULL),
+	{}
+};
+
+static struct aemif_platform_data aemif_data = {
+	.dev_lookup = da850_aemif_auxdata_lookup,
+};
+
 static struct of_dev_auxdata da850_auxdata_lookup[] __initdata = {
 	OF_DEV_AUXDATA("ti,davinci-i2c", 0x01c22000, "i2c_davinci.1", NULL),
 	OF_DEV_AUXDATA("ti,davinci-i2c", 0x01e28000, "i2c_davinci.2", NULL),
@@ -37,7 +47,7 @@ static struct of_dev_auxdata da850_auxdata_lookup[] __initdata = {
 	OF_DEV_AUXDATA("ti,davinci-dm6467-emac", 0x01e20000, "davinci_emac.1",
 		       NULL),
 	OF_DEV_AUXDATA("ti,da830-mcasp-audio", 0x01d00000, "davinci-mcasp.0", NULL),
-	OF_DEV_AUXDATA("ti,da850-aemif", 0x68000000, "ti-aemif", NULL),
+	OF_DEV_AUXDATA("ti,da850-aemif", 0x68000000, "ti-aemif", &aemif_data),
 	OF_DEV_AUXDATA("ti,da850-tilcdc", 0x01e13000, "da8xx_lcdc.0", NULL),
 	OF_DEV_AUXDATA("ti,da830-ohci", 0x01e25000, "ohci-da8xx", NULL),
 	OF_DEV_AUXDATA("ti,da830-musb", 0x01e00000, "musb-da8xx", NULL),

arch/x86/Kbuild

@@ -7,6 +7,9 @@ obj-$(CONFIG_KVM) += kvm/
 # Xen paravirtualization support
 obj-$(CONFIG_XEN) += xen/
 
+# Hyper-V paravirtualization support
+obj-$(CONFIG_HYPERVISOR_GUEST) += hyperv/
+
 # lguest paravirtualization support
 obj-$(CONFIG_LGUEST_GUEST) += lguest/
 

arch/x86/hyperv/Makefile

@@ -0,0 +1 @@
+obj-y		:= hv_init.o

arch/x86/hyperv/hv_init.c

@@ -0,0 +1,277 @@
+/*
+ * X86 specific Hyper-V initialization code.
+ *
+ * Copyright (C) 2016, Microsoft, Inc.
+ *
+ * Author : K. Y. Srinivasan <kys@microsoft.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ */
+
+#include <linux/types.h>
+#include <asm/hypervisor.h>
+#include <asm/hyperv.h>
+#include <asm/mshyperv.h>
+#include <linux/version.h>
+#include <linux/vmalloc.h>
+#include <linux/mm.h>
+#include <linux/clockchips.h>
+
+
+#ifdef CONFIG_X86_64
+
+static struct ms_hyperv_tsc_page *tsc_pg;
+
+static u64 read_hv_clock_tsc(struct clocksource *arg)
+{
+	u64 current_tick;
+
+	if (tsc_pg->tsc_sequence != 0) {
+		/*
+		 * Use the tsc page to compute the value.
+		 */
+
+		while (1) {
+			u64 tmp;
+			u32 sequence = tsc_pg->tsc_sequence;
+			u64 cur_tsc;
+			u64 scale = tsc_pg->tsc_scale;
+			s64 offset = tsc_pg->tsc_offset;
+
+			rdtscll(cur_tsc);
+			/* current_tick = ((cur_tsc *scale) >> 64) + offset */
+			asm("mulq %3"
+				: "=d" (current_tick), "=a" (tmp)
+				: "a" (cur_tsc), "r" (scale));
+
+			current_tick += offset;
+			if (tsc_pg->tsc_sequence == sequence)
+				return current_tick;
+
+			if (tsc_pg->tsc_sequence != 0)
+				continue;
+			/*
+			 * Fallback using MSR method.
+			 */
+			break;
+		}
+	}
+	rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick);
+	return current_tick;
+}
+
+static struct clocksource hyperv_cs_tsc = {
+		.name		= "hyperv_clocksource_tsc_page",
+		.rating		= 400,
+		.read		= read_hv_clock_tsc,
+		.mask		= CLOCKSOURCE_MASK(64),
+		.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
+};
+#endif
+
+static u64 read_hv_clock_msr(struct clocksource *arg)
+{
+	u64 current_tick;
+	/*
+	 * Read the partition counter to get the current tick count. This count
+	 * is set to 0 when the partition is created and is incremented in
+	 * 100 nanosecond units.
+	 */
+	rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick);
+	return current_tick;
+}
+
+static struct clocksource hyperv_cs_msr = {
+	.name		= "hyperv_clocksource_msr",
+	.rating		= 400,
+	.read		= read_hv_clock_msr,
+	.mask		= CLOCKSOURCE_MASK(64),
+	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+static void *hypercall_pg;
+struct clocksource *hyperv_cs;
+EXPORT_SYMBOL_GPL(hyperv_cs);
+
+/*
+ * This function is to be invoked early in the boot sequence after the
+ * hypervisor has been detected.
+ *
+ * 1. Setup the hypercall page.
+ * 2. Register Hyper-V specific clocksource.
+ */
+void hyperv_init(void)
+{
+	u64 guest_id;
+	union hv_x64_msr_hypercall_contents hypercall_msr;
+
+	if (x86_hyper != &x86_hyper_ms_hyperv)
+		return;
+
+	/*
+	 * Setup the hypercall page and enable hypercalls.
+	 * 1. Register the guest ID
+	 * 2. Enable the hypercall and register the hypercall page
+	 */
+	guest_id = generate_guest_id(0, LINUX_VERSION_CODE, 0);
+	wrmsrl(HV_X64_MSR_GUEST_OS_ID, guest_id);
+
+	hypercall_pg  = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL_RX);
+	if (hypercall_pg == NULL) {
+		wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
+		return;
+	}
+
+	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+	hypercall_msr.enable = 1;
+	hypercall_msr.guest_physical_address = vmalloc_to_pfn(hypercall_pg);
+	wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+
+	/*
+	 * Register Hyper-V specific clocksource.
+	 */
+#ifdef CONFIG_X86_64
+	if (ms_hyperv.features & HV_X64_MSR_REFERENCE_TSC_AVAILABLE) {
+		union hv_x64_msr_hypercall_contents tsc_msr;
+
+		tsc_pg = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL);
+		if (!tsc_pg)
+			goto register_msr_cs;
+
+		hyperv_cs = &hyperv_cs_tsc;
+
+		rdmsrl(HV_X64_MSR_REFERENCE_TSC, tsc_msr.as_uint64);
+
+		tsc_msr.enable = 1;
+		tsc_msr.guest_physical_address = vmalloc_to_pfn(tsc_pg);
+
+		wrmsrl(HV_X64_MSR_REFERENCE_TSC, tsc_msr.as_uint64);
+		clocksource_register_hz(&hyperv_cs_tsc, NSEC_PER_SEC/100);
+		return;
+	}
+#endif
+	/*
+	 * For 32 bit guests just use the MSR based mechanism for reading
+	 * the partition counter.
+	 */
+
+register_msr_cs:
+	hyperv_cs = &hyperv_cs_msr;
+	if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
+		clocksource_register_hz(&hyperv_cs_msr, NSEC_PER_SEC/100);
+}
+
+/*
+ * This routine is called before kexec/kdump, it does the required cleanup.
+ */
+void hyperv_cleanup(void)
+{
+	union hv_x64_msr_hypercall_contents hypercall_msr;
+
+	/* Reset our OS id */
+	wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
+
+	/* Reset the hypercall page */
+	hypercall_msr.as_uint64 = 0;
+	wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+
+	/* Reset the TSC page */
+	hypercall_msr.as_uint64 = 0;
+	wrmsrl(HV_X64_MSR_REFERENCE_TSC, hypercall_msr.as_uint64);
+}
+EXPORT_SYMBOL_GPL(hyperv_cleanup);
+
+/*
+ * hv_do_hypercall- Invoke the specified hypercall
+ */
+u64 hv_do_hypercall(u64 control, void *input, void *output)
+{
+	u64 input_address = (input) ? virt_to_phys(input) : 0;
+	u64 output_address = (output) ? virt_to_phys(output) : 0;
+#ifdef CONFIG_X86_64
+	u64 hv_status = 0;
+
+	if (!hypercall_pg)
+		return (u64)ULLONG_MAX;
+
+	__asm__ __volatile__("mov %0, %%r8" : : "r" (output_address) : "r8");
+	__asm__ __volatile__("call *%3" : "=a" (hv_status) :
+			     "c" (control), "d" (input_address),
+			     "m" (hypercall_pg));
+
+	return hv_status;
+
+#else
+
+	u32 control_hi = control >> 32;
+	u32 control_lo = control & 0xFFFFFFFF;
+	u32 hv_status_hi = 1;
+	u32 hv_status_lo = 1;
+	u32 input_address_hi = input_address >> 32;
+	u32 input_address_lo = input_address & 0xFFFFFFFF;
+	u32 output_address_hi = output_address >> 32;
+	u32 output_address_lo = output_address & 0xFFFFFFFF;
+
+	if (!hypercall_pg)
+		return (u64)ULLONG_MAX;
+
+	__asm__ __volatile__ ("call *%8" : "=d"(hv_status_hi),
+			      "=a"(hv_status_lo) : "d" (control_hi),
+			      "a" (control_lo), "b" (input_address_hi),
+			      "c" (input_address_lo), "D"(output_address_hi),
+			      "S"(output_address_lo), "m" (hypercall_pg));
+
+	return hv_status_lo | ((u64)hv_status_hi << 32);
+#endif /* !x86_64 */
+}
+EXPORT_SYMBOL_GPL(hv_do_hypercall);
+
+void hyperv_report_panic(struct pt_regs *regs)
+{
+	static bool panic_reported;
+
+	/*
+	 * We prefer to report panic on 'die' chain as we have proper
+	 * registers to report, but if we miss it (e.g. on BUG()) we need
+	 * to report it on 'panic'.
+	 */
+	if (panic_reported)
+		return;
+	panic_reported = true;
+
+	wrmsrl(HV_X64_MSR_CRASH_P0, regs->ip);
+	wrmsrl(HV_X64_MSR_CRASH_P1, regs->ax);
+	wrmsrl(HV_X64_MSR_CRASH_P2, regs->bx);
+	wrmsrl(HV_X64_MSR_CRASH_P3, regs->cx);
+	wrmsrl(HV_X64_MSR_CRASH_P4, regs->dx);
+
+	/*
+	 * Let Hyper-V know there is crash data available
+	 */
+	wrmsrl(HV_X64_MSR_CRASH_CTL, HV_CRASH_CTL_CRASH_NOTIFY);
+}
+EXPORT_SYMBOL_GPL(hyperv_report_panic);
+
+bool hv_is_hypercall_page_setup(void)
+{
+	union hv_x64_msr_hypercall_contents hypercall_msr;
+
+	/* Check if the hypercall page is setup */
+	hypercall_msr.as_uint64 = 0;
+	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+
+	if (!hypercall_msr.enable)
+		return false;
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(hv_is_hypercall_page_setup);

arch/x86/include/asm/mshyperv.h

@@ -3,8 +3,28 @@
 
 #include <linux/types.h>
 #include <linux/interrupt.h>
+#include <linux/clocksource.h>
 #include <asm/hyperv.h>
 
+/*
+ * The below CPUID leaves are present if VersionAndFeatures.HypervisorPresent
+ * is set by CPUID(HVCPUID_VERSION_FEATURES).
+ */
+enum hv_cpuid_function {
+	HVCPUID_VERSION_FEATURES		= 0x00000001,
+	HVCPUID_VENDOR_MAXFUNCTION		= 0x40000000,
+	HVCPUID_INTERFACE			= 0x40000001,
+
+	/*
+	 * The remaining functions depend on the value of
+	 * HVCPUID_INTERFACE
+	 */
+	HVCPUID_VERSION				= 0x40000002,
+	HVCPUID_FEATURES			= 0x40000003,
+	HVCPUID_ENLIGHTENMENT_INFO		= 0x40000004,
+	HVCPUID_IMPLEMENTATION_LIMITS		= 0x40000005,
+};
+
 struct ms_hyperv_info {
 	u32 features;
 	u32 misc_features;
@@ -13,6 +33,128 @@ struct ms_hyperv_info {
 
 extern struct ms_hyperv_info ms_hyperv;
 
+/*
+ * Declare the MSR used to setup pages used to communicate with the hypervisor.
+ */
+union hv_x64_msr_hypercall_contents {
+	u64 as_uint64;
+	struct {
+		u64 enable:1;
+		u64 reserved:11;
+		u64 guest_physical_address:52;
+	};
+};
+
+/*
+ * TSC page layout.
+ */
+
+struct ms_hyperv_tsc_page {
+	volatile u32 tsc_sequence;
+	u32 reserved1;
+	volatile u64 tsc_scale;
+	volatile s64 tsc_offset;
+	u64 reserved2[509];
+};
+
+/*
+ * The guest OS needs to register the guest ID with the hypervisor.
+ * The guest ID is a 64 bit entity and the structure of this ID is
+ * specified in the Hyper-V specification:
+ *
+ * msdn.microsoft.com/en-us/library/windows/hardware/ff542653%28v=vs.85%29.aspx
+ *
+ * While the current guideline does not specify how Linux guest ID(s)
+ * need to be generated, our plan is to publish the guidelines for
+ * Linux and other guest operating systems that currently are hosted
+ * on Hyper-V. The implementation here conforms to this yet
+ * unpublished guidelines.
+ *
+ *
+ * Bit(s)
+ * 63 - Indicates if the OS is Open Source or not; 1 is Open Source
+ * 62:56 - Os Type; Linux is 0x100
+ * 55:48 - Distro specific identification
+ * 47:16 - Linux kernel version number
+ * 15:0  - Distro specific identification
+ *
+ *
+ */
+
+#define HV_LINUX_VENDOR_ID              0x8100
+
+/*
+ * Generate the guest ID based on the guideline described above.
+ */
+
+static inline  __u64 generate_guest_id(__u64 d_info1, __u64 kernel_version,
+				       __u64 d_info2)
+{
+	__u64 guest_id = 0;
+
+	guest_id = (((__u64)HV_LINUX_VENDOR_ID) << 48);
+	guest_id |= (d_info1 << 48);
+	guest_id |= (kernel_version << 16);
+	guest_id |= d_info2;
+
+	return guest_id;
+}
+
+
+/* Free the message slot and signal end-of-message if required */
+static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type)
+{
+	/*
+	 * On crash we're reading some other CPU's message page and we need
+	 * to be careful: this other CPU may already had cleared the header
+	 * and the host may already had delivered some other message there.
+	 * In case we blindly write msg->header.message_type we're going
+	 * to lose it. We can still lose a message of the same type but
+	 * we count on the fact that there can only be one
+	 * CHANNELMSG_UNLOAD_RESPONSE and we don't care about other messages
+	 * on crash.
+	 */
+	if (cmpxchg(&msg->header.message_type, old_msg_type,
+		    HVMSG_NONE) != old_msg_type)
+		return;
+
+	/*
+	 * Make sure the write to MessageType (ie set to
+	 * HVMSG_NONE) happens before we read the
+	 * MessagePending and EOMing. Otherwise, the EOMing
+	 * will not deliver any more messages since there is
+	 * no empty slot
+	 */
+	mb();
+
+	if (msg->header.message_flags.msg_pending) {
+		/*
+		 * This will cause message queue rescan to
+		 * possibly deliver another msg from the
+		 * hypervisor
+		 */
+		wrmsrl(HV_X64_MSR_EOM, 0);
+	}
+}
+
+#define hv_get_current_tick(tick) rdmsrl(HV_X64_MSR_TIME_REF_COUNT, tick)
+#define hv_init_timer(timer, tick) wrmsrl(timer, tick)
+#define hv_init_timer_config(config, val) wrmsrl(config, val)
+
+#define hv_get_simp(val) rdmsrl(HV_X64_MSR_SIMP, val)
+#define hv_set_simp(val) wrmsrl(HV_X64_MSR_SIMP, val)
+
+#define hv_get_siefp(val) rdmsrl(HV_X64_MSR_SIEFP, val)
+#define hv_set_siefp(val) wrmsrl(HV_X64_MSR_SIEFP, val)
+
+#define hv_get_synic_state(val) rdmsrl(HV_X64_MSR_SCONTROL, val)
+#define hv_set_synic_state(val) wrmsrl(HV_X64_MSR_SCONTROL, val)
+
+#define hv_get_vp_index(index) rdmsrl(HV_X64_MSR_VP_INDEX, index)
+
+#define hv_get_synint_state(int_num, val) rdmsrl(int_num, val)
+#define hv_set_synint_state(int_num, val) wrmsrl(int_num, val)
+
 void hyperv_callback_vector(void);
 #ifdef CONFIG_TRACING
 #define trace_hyperv_callback_vector hyperv_callback_vector
@@ -25,4 +167,13 @@ void hv_setup_kexec_handler(void (*handler)(void));
 void hv_remove_kexec_handler(void);
 void hv_setup_crash_handler(void (*handler)(struct pt_regs *regs));
 void hv_remove_crash_handler(void);
+
+#if IS_ENABLED(CONFIG_HYPERV)
+extern struct clocksource *hyperv_cs;
+
+void hyperv_init(void);
+void hyperv_report_panic(struct pt_regs *regs);
+bool hv_is_hypercall_page_setup(void);
+void hyperv_cleanup(void);
+#endif
 #endif

arch/x86/include/uapi/asm/hyperv.h

@@ -73,6 +73,9 @@
   */
 #define HV_X64_MSR_STAT_PAGES_AVAILABLE		(1 << 8)
 
+/* Crash MSR available */
+#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE (1 << 10)
+
 /*
  * Feature identification: EBX indicates which flags were specified at
  * partition creation. The format is the same as the partition creation
@@ -144,6 +147,11 @@
  */
 #define HV_X64_RELAXED_TIMING_RECOMMENDED	(1 << 5)
 
+/*
+ * Crash notification flag.
+ */
+#define HV_CRASH_CTL_CRASH_NOTIFY (1ULL << 63)
+
 /* MSR used to identify the guest OS. */
 #define HV_X64_MSR_GUEST_OS_ID			0x40000000
 

arch/x86/kernel/cpu/mshyperv.c

@@ -133,26 +133,6 @@ static uint32_t  __init ms_hyperv_platform(void)
 	return 0;
 }
 
-static u64 read_hv_clock(struct clocksource *arg)
-{
-	u64 current_tick;
-	/*
-	 * Read the partition counter to get the current tick count. This count
-	 * is set to 0 when the partition is created and is incremented in
-	 * 100 nanosecond units.
-	 */
-	rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick);
-	return current_tick;
-}
-
-static struct clocksource hyperv_cs = {
-	.name		= "hyperv_clocksource",
-	.rating		= 400, /* use this when running on Hyperv*/
-	.read		= read_hv_clock,
-	.mask		= CLOCKSOURCE_MASK(64),
-	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
-};
-
 static unsigned char hv_get_nmi_reason(void)
 {
 	return 0;
@@ -180,6 +160,11 @@ static int hv_nmi_unknown(unsigned int val, struct pt_regs *regs)
 
 static void __init ms_hyperv_init_platform(void)
 {
+	int hv_host_info_eax;
+	int hv_host_info_ebx;
+	int hv_host_info_ecx;
+	int hv_host_info_edx;
+
 	/*
 	 * Extract the features and hints
 	 */
@@ -190,6 +175,21 @@ static void __init ms_hyperv_init_platform(void)
 	pr_info("HyperV: features 0x%x, hints 0x%x\n",
 		ms_hyperv.features, ms_hyperv.hints);
 
+	/*
+	 * Extract host information.
+	 */
+	if (cpuid_eax(HVCPUID_VENDOR_MAXFUNCTION) >= HVCPUID_VERSION) {
+		hv_host_info_eax = cpuid_eax(HVCPUID_VERSION);
+		hv_host_info_ebx = cpuid_ebx(HVCPUID_VERSION);
+		hv_host_info_ecx = cpuid_ecx(HVCPUID_VERSION);
+		hv_host_info_edx = cpuid_edx(HVCPUID_VERSION);
+
+		pr_info("Hyper-V Host Build:%d-%d.%d-%d-%d.%d\n",
+			hv_host_info_eax, hv_host_info_ebx >> 16,
+			hv_host_info_ebx & 0xFFFF, hv_host_info_ecx,
+			hv_host_info_edx >> 24, hv_host_info_edx & 0xFFFFFF);
+	}
+
 #ifdef CONFIG_X86_LOCAL_APIC
 	if (ms_hyperv.features & HV_X64_MSR_APIC_FREQUENCY_AVAILABLE) {
 		/*
@@ -208,9 +208,6 @@ static void __init ms_hyperv_init_platform(void)
 			     "hv_nmi_unknown");
 #endif
 
-	if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
-		clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100);
-
 #ifdef CONFIG_X86_IO_APIC
 	no_timer_check = 1;
 #endif
@@ -227,6 +224,13 @@ static void __init ms_hyperv_init_platform(void)
 	 */
 	if (efi_enabled(EFI_BOOT))
 		x86_platform.get_nmi_reason = hv_get_nmi_reason;
+
+#if IS_ENABLED(CONFIG_HYPERV)
+	/*
+	 * Setup the hook to get control post apic initialization.
+	 */
+	x86_platform.apic_post_init = hyperv_init;
+#endif
 }
 
 const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {

arch/x86/platform/goldfish/goldfish.c

@@ -42,8 +42,20 @@ static struct resource goldfish_pdev_bus_resources[] = {
 	}
 };
 
+static bool goldfish_enable __initdata;
+
+static int __init goldfish_setup(char *str)
+{
+	goldfish_enable = true;
+	return 0;
+}
+__setup("goldfish", goldfish_setup);
+
 static int __init goldfish_init(void)
 {
+	if (!goldfish_enable)
+		return -ENODEV;
+
 	platform_device_register_simple("goldfish_pdev_bus", -1,
 					goldfish_pdev_bus_resources, 2);
 	return 0;

drivers/Kconfig

@@ -202,4 +202,6 @@ source "drivers/hwtracing/intel_th/Kconfig"
 
 source "drivers/fpga/Kconfig"
 
+source "drivers/fsi/Kconfig"
+
 endmenu

drivers/Makefile

@@ -173,3 +173,4 @@ obj-$(CONFIG_STM)		+= hwtracing/stm/
 obj-$(CONFIG_ANDROID)		+= android/
 obj-$(CONFIG_NVMEM)		+= nvmem/
 obj-$(CONFIG_FPGA)		+= fpga/
+obj-$(CONFIG_FSI)		+= fsi/

drivers/android/Kconfig

@@ -19,6 +19,18 @@ config ANDROID_BINDER_IPC
 	  Android process, using Binder to identify, invoke and pass arguments
 	  between said processes.
 
+config ANDROID_BINDER_DEVICES
+	string "Android Binder devices"
+	depends on ANDROID_BINDER_IPC
+	default "binder"
+	---help---
+	  Default value for the binder.devices parameter.
+
+	  The binder.devices parameter is a comma-separated list of strings
+	  that specifies the names of the binder device nodes that will be
+	  created. Each binder device has its own context manager, and is
+	  therefore logically separated from the other devices.
+
 config ANDROID_BINDER_IPC_32BIT
 	bool
 	depends on !64BIT && ANDROID_BINDER_IPC

drivers/auxdisplay/ht16k33.c

@@ -56,14 +56,16 @@
 #define HT16K33_FB_SIZE		(HT16K33_MATRIX_LED_MAX_COLS * BYTES_PER_ROW)
 
 struct ht16k33_keypad {
+	struct i2c_client *client;
 	struct input_dev *dev;
-	spinlock_t lock;
-	struct delayed_work work;
 	uint32_t cols;
 	uint32_t rows;
 	uint32_t row_shift;
 	uint32_t debounce_ms;
 	uint16_t last_key_state[HT16K33_MATRIX_KEYPAD_MAX_COLS];
+
+	wait_queue_head_t wait;
+	bool stopped;
 };
 
 struct ht16k33_fbdev {
@@ -78,7 +80,6 @@ struct ht16k33_priv {
 	struct i2c_client *client;
 	struct ht16k33_keypad keypad;
 	struct ht16k33_fbdev fbdev;
-	struct workqueue_struct *workqueue;
 };
 
 static struct fb_fix_screeninfo ht16k33_fb_fix = {
@@ -124,18 +125,10 @@ static void ht16k33_fb_queue(struct ht16k33_priv *priv)
 {
 	struct ht16k33_fbdev *fbdev = &priv->fbdev;
 
-	queue_delayed_work(priv->workqueue, &fbdev->work,
+	schedule_delayed_work(&fbdev->work,
 			      msecs_to_jiffies(HZ / fbdev->refresh_rate));
 }
 
-static void ht16k33_keypad_queue(struct ht16k33_priv *priv)
-{
-	struct ht16k33_keypad *keypad = &priv->keypad;
-
-	queue_delayed_work(priv->workqueue, &keypad->work,
-		msecs_to_jiffies(keypad->debounce_ms));
-}
-
 /*
  * This gets the fb data from cache and copies it to ht16k33 display RAM
  */
@@ -182,32 +175,6 @@ static void ht16k33_fb_update(struct work_struct *work)
 	ht16k33_fb_queue(priv);
 }
 
-static int ht16k33_keypad_start(struct input_dev *dev)
-{
-	struct ht16k33_priv *priv = input_get_drvdata(dev);
-	struct ht16k33_keypad *keypad = &priv->keypad;
-
-	/*
-	 * Schedule an immediate key scan to capture current key state;
-	 * columns will be activated and IRQs be enabled after the scan.
-	 */
-	queue_delayed_work(priv->workqueue, &keypad->work, 0);
-	return 0;
-}
-
-static void ht16k33_keypad_stop(struct input_dev *dev)
-{
-	struct ht16k33_priv *priv = input_get_drvdata(dev);
-	struct ht16k33_keypad *keypad = &priv->keypad;
-
-	cancel_delayed_work(&keypad->work);
-	/*
-	 * ht16k33_keypad_scan() will leave IRQs enabled;
-	 * we should disable them now.
-	 */
-	disable_irq_nosync(priv->client->irq);
-}
-
 static int ht16k33_initialize(struct ht16k33_priv *priv)
 {
 	uint8_t byte;
@@ -233,61 +200,6 @@ static int ht16k33_initialize(struct ht16k33_priv *priv)
 	return i2c_smbus_write_byte(priv->client, byte);
 }
 
-/*
- * This gets the keys from keypad and reports it to input subsystem
- */
-static void ht16k33_keypad_scan(struct work_struct *work)
-{
-	struct ht16k33_keypad *keypad =
-		container_of(work, struct ht16k33_keypad, work.work);
-	struct ht16k33_priv *priv =
-		container_of(keypad, struct ht16k33_priv, keypad);
-	const unsigned short *keycodes = keypad->dev->keycode;
-	uint16_t bits_changed, new_state[HT16K33_MATRIX_KEYPAD_MAX_COLS];
-	uint8_t data[HT16K33_MATRIX_KEYPAD_MAX_COLS * 2];
-	int row, col, code;
-	bool reschedule = false;
-
-	if (i2c_smbus_read_i2c_block_data(priv->client, 0x40, 6, data) != 6) {
-		dev_err(&priv->client->dev, "Failed to read key data\n");
-		goto end;
-	}
-
-	for (col = 0; col < keypad->cols; col++) {
-		new_state[col] = (data[col * 2 + 1] << 8) | data[col * 2];
-		if (new_state[col])
-			reschedule = true;
-		bits_changed = keypad->last_key_state[col] ^ new_state[col];
-
-		while (bits_changed) {
-			row = ffs(bits_changed) - 1;
-			code = MATRIX_SCAN_CODE(row, col, keypad->row_shift);
-			input_event(keypad->dev, EV_MSC, MSC_SCAN, code);
-			input_report_key(keypad->dev, keycodes[code],
-					 new_state[col] & BIT(row));
-			bits_changed &= ~BIT(row);
-		}
-	}
-	input_sync(keypad->dev);
-	memcpy(keypad->last_key_state, new_state, sizeof(new_state));
-
-end:
-	if (reschedule)
-		ht16k33_keypad_queue(priv);
-	else
-		enable_irq(priv->client->irq);
-}
-
-static irqreturn_t ht16k33_irq_thread(int irq, void *dev)
-{
-	struct ht16k33_priv *priv = dev;
-
-	disable_irq_nosync(priv->client->irq);
-	ht16k33_keypad_queue(priv);
-
-	return IRQ_HANDLED;
-}
-
 static int ht16k33_bl_update_status(struct backlight_device *bl)
 {
 	int brightness = bl->props.brightness;
@@ -334,15 +246,152 @@ static struct fb_ops ht16k33_fb_ops = {
 	.fb_mmap = ht16k33_mmap,
 };
 
+/*
+ * This gets the keys from keypad and reports it to input subsystem.
+ * Returns true if a key is pressed.
+ */
+static bool ht16k33_keypad_scan(struct ht16k33_keypad *keypad)
+{
+	const unsigned short *keycodes = keypad->dev->keycode;
+	u16 new_state[HT16K33_MATRIX_KEYPAD_MAX_COLS];
+	u8 data[HT16K33_MATRIX_KEYPAD_MAX_COLS * 2];
+	unsigned long bits_changed;
+	int row, col, code;
+	bool pressed = false;
+
+	if (i2c_smbus_read_i2c_block_data(keypad->client, 0x40, 6, data) != 6) {
+		dev_err(&keypad->client->dev, "Failed to read key data\n");
+		return false;
+	}
+
+	for (col = 0; col < keypad->cols; col++) {
+		new_state[col] = (data[col * 2 + 1] << 8) | data[col * 2];
+		if (new_state[col])
+			pressed = true;
+		bits_changed = keypad->last_key_state[col] ^ new_state[col];
+
+		for_each_set_bit(row, &bits_changed, BITS_PER_LONG) {
+			code = MATRIX_SCAN_CODE(row, col, keypad->row_shift);
+			input_event(keypad->dev, EV_MSC, MSC_SCAN, code);
+			input_report_key(keypad->dev, keycodes[code],
+					 new_state[col] & BIT(row));
+		}
+	}
+	input_sync(keypad->dev);
+	memcpy(keypad->last_key_state, new_state, sizeof(new_state));
+
+	return pressed;
+}
+
+static irqreturn_t ht16k33_keypad_irq_thread(int irq, void *dev)
+{
+	struct ht16k33_keypad *keypad = dev;
+
+	do {
+		wait_event_timeout(keypad->wait, keypad->stopped,
+				    msecs_to_jiffies(keypad->debounce_ms));
+		if (keypad->stopped)
+			break;
+	} while (ht16k33_keypad_scan(keypad));
+
+	return IRQ_HANDLED;
+}
+
+static int ht16k33_keypad_start(struct input_dev *dev)
+{
+	struct ht16k33_keypad *keypad = input_get_drvdata(dev);
+
+	keypad->stopped = false;
+	mb();
+	enable_irq(keypad->client->irq);
+
+	return 0;
+}
+
+static void ht16k33_keypad_stop(struct input_dev *dev)
+{
+	struct ht16k33_keypad *keypad = input_get_drvdata(dev);
+
+	keypad->stopped = true;
+	mb();
+	wake_up(&keypad->wait);
+	disable_irq(keypad->client->irq);
+}
+
+static int ht16k33_keypad_probe(struct i2c_client *client,
+				struct ht16k33_keypad *keypad)
+{
+	struct device_node *node = client->dev.of_node;
+	u32 rows = HT16K33_MATRIX_KEYPAD_MAX_ROWS;
+	u32 cols = HT16K33_MATRIX_KEYPAD_MAX_COLS;
+	int err;
+
+	keypad->client = client;
+	init_waitqueue_head(&keypad->wait);
+
+	keypad->dev = devm_input_allocate_device(&client->dev);
+	if (!keypad->dev)
+		return -ENOMEM;
+
+	input_set_drvdata(keypad->dev, keypad);
+
+	keypad->dev->name = DRIVER_NAME"-keypad";
+	keypad->dev->id.bustype = BUS_I2C;
+	keypad->dev->open = ht16k33_keypad_start;
+	keypad->dev->close = ht16k33_keypad_stop;
+
+	if (!of_get_property(node, "linux,no-autorepeat", NULL))
+		__set_bit(EV_REP, keypad->dev->evbit);
+
+	err = of_property_read_u32(node, "debounce-delay-ms",
+				   &keypad->debounce_ms);
+	if (err) {
+		dev_err(&client->dev, "key debounce delay not specified\n");
+		return err;
+	}
+
+	err = matrix_keypad_parse_of_params(&client->dev, &rows, &cols);
+	if (err)
+		return err;
+
+	keypad->rows = rows;
+	keypad->cols = cols;
+	keypad->row_shift = get_count_order(cols);
+
+	err = matrix_keypad_build_keymap(NULL, NULL, rows, cols, NULL,
+					 keypad->dev);
+	if (err) {
+		dev_err(&client->dev, "failed to build keymap\n");
+		return err;
+	}
+
+	err = devm_request_threaded_irq(&client->dev, client->irq,
+					NULL, ht16k33_keypad_irq_thread,
+					IRQF_TRIGGER_HIGH | IRQF_ONESHOT,
+					DRIVER_NAME, keypad);
+	if (err) {
+		dev_err(&client->dev, "irq request failed %d, error %d\n",
+			client->irq, err);
+		return err;
+	}
+
+	ht16k33_keypad_stop(keypad->dev);
+
+	err = input_register_device(keypad->dev);
+	if (err)
+		return err;
+
+	return 0;
+}
+
 static int ht16k33_probe(struct i2c_client *client,
 				  const struct i2c_device_id *id)
 {
 	int err;
-	uint32_t rows, cols, dft_brightness;
+	uint32_t dft_brightness;
 	struct backlight_device *bl;
 	struct backlight_properties bl_props;
 	struct ht16k33_priv *priv;
-	struct ht16k33_keypad *keypad;
 	struct ht16k33_fbdev *fbdev;
 	struct device_node *node = client->dev.of_node;
 
@@ -363,23 +412,16 @@ static int ht16k33_probe(struct i2c_client *client,
 	priv->client = client;
 	i2c_set_clientdata(client, priv);
 	fbdev = &priv->fbdev;
-	keypad = &priv->keypad;
-
-	priv->workqueue = create_singlethread_workqueue(DRIVER_NAME "-wq");
-	if (priv->workqueue == NULL)
-		return -ENOMEM;
 
 	err = ht16k33_initialize(priv);
 	if (err)
-		goto err_destroy_wq;
+		return err;
 
 	/* Framebuffer (2 bytes per column) */
 	BUILD_BUG_ON(PAGE_SIZE < HT16K33_FB_SIZE);
 	fbdev->buffer = (unsigned char *) get_zeroed_page(GFP_KERNEL);
-	if (!fbdev->buffer) {
+	if (!fbdev->buffer)
-		err = -ENOMEM;
+		return -ENOMEM;
-		goto err_free_fbdev;
-	}
 
 	fbdev->cache = devm_kmalloc(&client->dev, HT16K33_FB_SIZE, GFP_KERNEL);
 	if (!fbdev->cache) {
@@ -415,59 +457,7 @@ static int ht16k33_probe(struct i2c_client *client,
 	if (err)
 		goto err_fbdev_info;
 
-	/* Keypad */
+	err = ht16k33_keypad_probe(client, &priv->keypad);
-	keypad->dev = devm_input_allocate_device(&client->dev);
-	if (!keypad->dev) {
-		err = -ENOMEM;
-		goto err_fbdev_unregister;
-	}
-
-	keypad->dev->name = DRIVER_NAME"-keypad";
-	keypad->dev->id.bustype = BUS_I2C;
-	keypad->dev->open = ht16k33_keypad_start;
-	keypad->dev->close = ht16k33_keypad_stop;
-
-	if (!of_get_property(node, "linux,no-autorepeat", NULL))
-		__set_bit(EV_REP, keypad->dev->evbit);
-
-	err = of_property_read_u32(node, "debounce-delay-ms",
-				   &keypad->debounce_ms);
-	if (err) {
-		dev_err(&client->dev, "key debounce delay not specified\n");
-		goto err_fbdev_unregister;
-	}
-
-	err = devm_request_threaded_irq(&client->dev, client->irq, NULL,
-					ht16k33_irq_thread,
-					IRQF_TRIGGER_RISING | IRQF_ONESHOT,
-					DRIVER_NAME, priv);
-	if (err) {
-		dev_err(&client->dev, "irq request failed %d, error %d\n",
-			client->irq, err);
-		goto err_fbdev_unregister;
-	}
-
-	disable_irq_nosync(client->irq);
-	rows = HT16K33_MATRIX_KEYPAD_MAX_ROWS;
-	cols = HT16K33_MATRIX_KEYPAD_MAX_COLS;
-	err = matrix_keypad_parse_of_params(&client->dev, &rows, &cols);
-	if (err)
-		goto err_fbdev_unregister;
-
-	err = matrix_keypad_build_keymap(NULL, NULL, rows, cols, NULL,
-					 keypad->dev);
-	if (err) {
-		dev_err(&client->dev, "failed to build keymap\n");
-		goto err_fbdev_unregister;
-	}
-
-	input_set_drvdata(keypad->dev, priv);
-	keypad->rows = rows;
-	keypad->cols = cols;
-	keypad->row_shift = get_count_order(cols);
-	INIT_DELAYED_WORK(&keypad->work, ht16k33_keypad_scan);
-
-	err = input_register_device(keypad->dev);
 	if (err)
 		goto err_fbdev_unregister;
 
@@ -482,7 +472,7 @@ static int ht16k33_probe(struct i2c_client *client,
 	if (IS_ERR(bl)) {
 		dev_err(&client->dev, "failed to register backlight\n");
 		err = PTR_ERR(bl);
-		goto err_keypad_unregister;
+		goto err_fbdev_unregister;
 	}
 
 	err = of_property_read_u32(node, "default-brightness-level",
@@ -502,18 +492,12 @@ static int ht16k33_probe(struct i2c_client *client,
 	ht16k33_fb_queue(priv);
 	return 0;
 
-err_keypad_unregister:
-	input_unregister_device(keypad->dev);
 err_fbdev_unregister:
 	unregister_framebuffer(fbdev->info);
 err_fbdev_info:
 	framebuffer_release(fbdev->info);
 err_fbdev_buffer:
 	free_page((unsigned long) fbdev->buffer);
-err_free_fbdev:
-	kfree(fbdev);
-err_destroy_wq:
-	destroy_workqueue(priv->workqueue);
 
 	return err;
 }
@@ -521,17 +505,13 @@ static int ht16k33_probe(struct i2c_client *client,
 static int ht16k33_remove(struct i2c_client *client)
 {
 	struct ht16k33_priv *priv = i2c_get_clientdata(client);
-	struct ht16k33_keypad *keypad = &priv->keypad;
 	struct ht16k33_fbdev *fbdev = &priv->fbdev;
 
-	ht16k33_keypad_stop(keypad->dev);
-
 	cancel_delayed_work(&fbdev->work);
 	unregister_framebuffer(fbdev->info);
 	framebuffer_release(fbdev->info);
 	free_page((unsigned long) fbdev->buffer);
 
-	destroy_workqueue(priv->workqueue);
 	return 0;
 }
 

drivers/char/Kconfig

@@ -571,9 +571,12 @@ config TELCLOCK
 	  controlling the behavior of this hardware.
 
 config DEVPORT
-	bool
+	bool "/dev/port character device"
 	depends on ISA || PCI
 	default y
+	help
+	  Say Y here if you want to support the /dev/port device. The /dev/port
+	  device is similar to /dev/mem, but for I/O ports.
 
 source "drivers/s390/char/Kconfig"
 

drivers/char/apm-emulation.c

@@ -31,13 +31,6 @@
 #include <linux/kthread.h>
 #include <linux/delay.h>
 
-
-/*
- * The apm_bios device is one of the misc char devices.
- * This is its minor number.
- */
-#define APM_MINOR_DEV	134
-
 /*
  * One option can be changed at boot time as follows:
  *	apm=on/off			enable/disable APM

drivers/char/ds1302.c

@@ -17,7 +17,6 @@
 #include <linux/init.h>
 #include <linux/mm.h>
 #include <linux/module.h>
-#include <linux/miscdevice.h>
 #include <linux/delay.h>
 #include <linux/bcd.h>
 #include <linux/mutex.h>

drivers/char/mmtimer.c

@@ -463,9 +463,9 @@ static int mmtimer_mmap(struct file *file, struct vm_area_struct *vma)
 }
 
 static struct miscdevice mmtimer_miscdev = {
-	SGI_MMTIMER,
+	.minor = SGI_MMTIMER,
-	MMTIMER_NAME,
+	.name = MMTIMER_NAME,
-	&mmtimer_fops
+	.fops = &mmtimer_fops
 };
 
 static struct timespec sgi_clock_offset;

drivers/char/xilinx_hwicap/buffer_icap.c

@@ -269,7 +269,6 @@ int buffer_icap_set_configuration(struct hwicap_drvdata *drvdata, u32 *data,
 {
 	int status;
 	s32 buffer_count = 0;
-	s32 num_writes = 0;
 	bool dirty = false;
 	u32 i;
 	void __iomem *base_address = drvdata->base_address;
@@ -298,7 +297,6 @@ int buffer_icap_set_configuration(struct hwicap_drvdata *drvdata, u32 *data,
 		}
 
 		buffer_count = 0;
-		num_writes++;
 		dirty = false;
 	}
 
@@ -328,7 +326,6 @@ int buffer_icap_get_configuration(struct hwicap_drvdata *drvdata, u32 *data,
 {
 	int status;
 	s32 buffer_count = 0;
-	s32 read_count = 0;
 	u32 i;
 	void __iomem *base_address = drvdata->base_address;
 
@@ -353,7 +350,6 @@ int buffer_icap_get_configuration(struct hwicap_drvdata *drvdata, u32 *data,
 			}
 
 			buffer_count = 0;
-			read_count++;
 		}
 
 		/* Copy data from bram */

drivers/extcon/Kconfig

@@ -42,6 +42,16 @@ config EXTCON_GPIO
 	  Say Y here to enable GPIO based extcon support. Note that GPIO
 	  extcon supports single state per extcon instance.
 
+config EXTCON_INTEL_INT3496
+	tristate "Intel INT3496 ACPI device extcon driver"
+	depends on GPIOLIB && ACPI
+	help
+	  Say Y here to enable extcon support for USB OTG ports controlled by
+	  an Intel INT3496 ACPI device.
+
+	  This ACPI device is typically found on Intel Baytrail or Cherrytrail
+	  based tablets, or other Baytrail / Cherrytrail devices.
+
 config EXTCON_MAX14577
 	tristate "Maxim MAX14577/77836 EXTCON Support"
 	depends on MFD_MAX14577

drivers/extcon/Makefile

@@ -8,6 +8,7 @@ obj-$(CONFIG_EXTCON_ADC_JACK)	+= extcon-adc-jack.o
 obj-$(CONFIG_EXTCON_ARIZONA)	+= extcon-arizona.o
 obj-$(CONFIG_EXTCON_AXP288)	+= extcon-axp288.o
 obj-$(CONFIG_EXTCON_GPIO)	+= extcon-gpio.o
+obj-$(CONFIG_EXTCON_INTEL_INT3496) += extcon-intel-int3496.o
 obj-$(CONFIG_EXTCON_MAX14577)	+= extcon-max14577.o
 obj-$(CONFIG_EXTCON_MAX3355)	+= extcon-max3355.o
 obj-$(CONFIG_EXTCON_MAX77693)	+= extcon-max77693.o

drivers/extcon/devres.c

@@ -14,7 +14,7 @@
  * GNU General Public License for more details.
  */
 
-#include <linux/extcon.h>
+#include "extcon.h"
 
 static int devm_extcon_dev_match(struct device *dev, void *res, void *data)
 {

drivers/extcon/extcon-adc-jack.c

@@ -67,7 +67,7 @@ static void adc_jack_handler(struct work_struct *work)
 
 	ret = iio_read_channel_raw(data->chan, &adc_val);
 	if (ret < 0) {
-		dev_err(&data->edev->dev, "read channel() error: %d\n", ret);
+		dev_err(data->dev, "read channel() error: %d\n", ret);
 		return;
 	}
 

drivers/extcon/extcon-arizona.c

@@ -236,10 +236,6 @@ static void arizona_extcon_set_mode(struct arizona_extcon_info *info, int mode)
 
 	mode %= info->micd_num_modes;
 
-	if (arizona->pdata.micd_pol_gpio > 0)
-		gpio_set_value_cansleep(arizona->pdata.micd_pol_gpio,
-					info->micd_modes[mode].gpio);
-	else
 	gpiod_set_value_cansleep(info->micd_pol_gpio,
 				 info->micd_modes[mode].gpio);
 
@@ -1412,21 +1408,21 @@ static int arizona_extcon_probe(struct platform_device *pdev)
 		regmap_update_bits(arizona->regmap, ARIZONA_GP_SWITCH_1,
 				ARIZONA_SW1_MODE_MASK, arizona->pdata.gpsw);
 
-	if (arizona->pdata.micd_pol_gpio > 0) {
+	if (pdata->micd_pol_gpio > 0) {
 		if (info->micd_modes[0].gpio)
 			mode = GPIOF_OUT_INIT_HIGH;
 		else
 			mode = GPIOF_OUT_INIT_LOW;
 
-		ret = devm_gpio_request_one(&pdev->dev,
+		ret = devm_gpio_request_one(&pdev->dev, pdata->micd_pol_gpio,
-					    arizona->pdata.micd_pol_gpio,
+					    mode, "MICD polarity");
-					    mode,
-					    "MICD polarity");
 		if (ret != 0) {
 			dev_err(arizona->dev, "Failed to request GPIO%d: %d\n",
-				arizona->pdata.micd_pol_gpio, ret);
+				pdata->micd_pol_gpio, ret);
 			goto err_register;
 		}
+
+		info->micd_pol_gpio = gpio_to_desc(pdata->micd_pol_gpio);
 	} else {
 		if (info->micd_modes[0].gpio)
 			mode = GPIOD_OUT_HIGH;

drivers/extcon/extcon-axp288.c

@@ -21,7 +21,6 @@
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
 #include <linux/property.h>
-#include <linux/usb/phy.h>
 #include <linux/notifier.h>
 #include <linux/extcon.h>
 #include <linux/regmap.h>
@@ -71,12 +70,6 @@
 #define DET_STAT_CDP			2
 #define DET_STAT_DCP			3
 
-/* IRQ enable-1 register */
-#define PWRSRC_IRQ_CFG_MASK		(BIT(4)|BIT(3)|BIT(2))
-
-/* IRQ enable-6 register */
-#define BC12_IRQ_CFG_MASK		BIT(1)
-
 enum axp288_extcon_reg {
 	AXP288_PS_STAT_REG		= 0x00,
 	AXP288_PS_BOOT_REASON_REG	= 0x02,
@@ -84,8 +77,6 @@ enum axp288_extcon_reg {
 	AXP288_BC_VBUS_CNTL_REG		= 0x2d,
 	AXP288_BC_USB_STAT_REG		= 0x2e,
 	AXP288_BC_DET_STAT_REG		= 0x2f,
-	AXP288_PWRSRC_IRQ_CFG_REG	= 0x40,
-	AXP288_BC12_IRQ_CFG_REG		= 0x45,
 };
 
 enum axp288_mux_select {
@@ -105,6 +96,7 @@ static const unsigned int axp288_extcon_cables[] = {
 	EXTCON_CHG_USB_SDP,
 	EXTCON_CHG_USB_CDP,
 	EXTCON_CHG_USB_DCP,
+	EXTCON_USB,
 	EXTCON_NONE,
 };
 
@@ -112,11 +104,11 @@ struct axp288_extcon_info {
 	struct device *dev;
 	struct regmap *regmap;
 	struct regmap_irq_chip_data *regmap_irqc;
-	struct axp288_extcon_pdata *pdata;
+	struct gpio_desc *gpio_mux_cntl;
 	int irq[EXTCON_IRQ_END];
 	struct extcon_dev *edev;
 	struct notifier_block extcon_nb;
-	struct usb_phy *otg;
+	unsigned int previous_cable;
 };
 
 /* Power up/down reason string array */
@@ -156,10 +148,9 @@ static void axp288_extcon_log_rsi(struct axp288_extcon_info *info)
 
 static int axp288_handle_chrg_det_event(struct axp288_extcon_info *info)
 {
-	static bool notify_otg, notify_charger;
-	static unsigned int cable;
 	int ret, stat, cfg, pwr_stat;
 	u8 chrg_type;
+	unsigned int cable = info->previous_cable;
 	bool vbus_attach = false;
 
 	ret = regmap_read(info->regmap, AXP288_PS_STAT_REG, &pwr_stat);
@@ -168,9 +159,9 @@ static int axp288_handle_chrg_det_event(struct axp288_extcon_info *info)
 		return ret;
 	}
 
-	vbus_attach = (pwr_stat & PS_STAT_VBUS_PRESENT);
+	vbus_attach = (pwr_stat & PS_STAT_VBUS_VALID);
 	if (!vbus_attach)
-		goto notify_otg;
+		goto no_vbus;
 
 	/* Check charger detection completion status */
 	ret = regmap_read(info->regmap, AXP288_BC_GLOBAL_REG, &cfg);
@@ -190,19 +181,14 @@ static int axp288_handle_chrg_det_event(struct axp288_extcon_info *info)
 	switch (chrg_type) {
 	case DET_STAT_SDP:
 		dev_dbg(info->dev, "sdp cable is connected\n");
-		notify_otg = true;
-		notify_charger = true;
 		cable = EXTCON_CHG_USB_SDP;
 		break;
 	case DET_STAT_CDP:
 		dev_dbg(info->dev, "cdp cable is connected\n");
-		notify_otg = true;
-		notify_charger = true;
 		cable = EXTCON_CHG_USB_CDP;
 		break;
 	case DET_STAT_DCP:
 		dev_dbg(info->dev, "dcp cable is connected\n");
-		notify_charger = true;
 		cable = EXTCON_CHG_USB_DCP;
 		break;
 	default:
@@ -210,27 +196,28 @@ static int axp288_handle_chrg_det_event(struct axp288_extcon_info *info)
 			"disconnect or unknown or ID event\n");
 	}
 
-notify_otg:
+no_vbus:
-	if (notify_otg) {
 	/*
 	 * If VBUS is absent Connect D+/D- lines to PMIC for BC
 	 * detection. Else connect them to SOC for USB communication.
 	 */
-		if (info->pdata->gpio_mux_cntl)
+	if (info->gpio_mux_cntl)
-			gpiod_set_value(info->pdata->gpio_mux_cntl,
+		gpiod_set_value(info->gpio_mux_cntl,
 			vbus_attach ? EXTCON_GPIO_MUX_SEL_SOC
 					: EXTCON_GPIO_MUX_SEL_PMIC);
 
-		atomic_notifier_call_chain(&info->otg->notifier,
+	extcon_set_state_sync(info->edev, info->previous_cable, false);
-			vbus_attach ? USB_EVENT_VBUS : USB_EVENT_NONE, NULL);
+	if (info->previous_cable == EXTCON_CHG_USB_SDP)
-	}
+		extcon_set_state_sync(info->edev, EXTCON_USB, false);
 
-	if (notify_charger)
+	if (vbus_attach) {
 		extcon_set_state_sync(info->edev, cable, vbus_attach);
+		if (cable == EXTCON_CHG_USB_SDP)
+			extcon_set_state_sync(info->edev, EXTCON_USB,
+						vbus_attach);
 
-	/* Clear the flags on disconnect event */
+		info->previous_cable = cable;
-	if (!vbus_attach)
+	}
-		notify_otg = notify_charger = false;
 
 	return 0;
 
@@ -253,15 +240,10 @@ static irqreturn_t axp288_extcon_isr(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static void axp288_extcon_enable_irq(struct axp288_extcon_info *info)
+static void axp288_extcon_enable(struct axp288_extcon_info *info)
 {
-	/* Unmask VBUS interrupt */
-	regmap_write(info->regmap, AXP288_PWRSRC_IRQ_CFG_REG,
-						PWRSRC_IRQ_CFG_MASK);
 	regmap_update_bits(info->regmap, AXP288_BC_GLOBAL_REG,
 						BC_GLOBAL_RUN, 0);
-	/* Unmask the BC1.2 complete interrupts */
-	regmap_write(info->regmap, AXP288_BC12_IRQ_CFG_REG, BC12_IRQ_CFG_MASK);
 	/* Enable the charger detection logic */
 	regmap_update_bits(info->regmap, AXP288_BC_GLOBAL_REG,
 					BC_GLOBAL_RUN, BC_GLOBAL_RUN);
@@ -271,6 +253,7 @@ static int axp288_extcon_probe(struct platform_device *pdev)
 {
 	struct axp288_extcon_info *info;
 	struct axp20x_dev *axp20x = dev_get_drvdata(pdev->dev.parent);
+	struct axp288_extcon_pdata *pdata = pdev->dev.platform_data;
 	int ret, i, pirq, gpio;
 
 	info = devm_kzalloc(&pdev->dev, sizeof(*info), GFP_KERNEL);
@@ -280,15 +263,10 @@ static int axp288_extcon_probe(struct platform_device *pdev)
 	info->dev = &pdev->dev;
 	info->regmap = axp20x->regmap;
 	info->regmap_irqc = axp20x->regmap_irqc;
-	info->pdata = pdev->dev.platform_data;
+	info->previous_cable = EXTCON_NONE;
+	if (pdata)
+		info->gpio_mux_cntl = pdata->gpio_mux_cntl;
 
-	if (!info->pdata) {
-		/* Try ACPI provided pdata via device properties */
-		if (!device_property_present(&pdev->dev,
-					"axp288_extcon_data\n"))
-			dev_err(&pdev->dev, "failed to get platform data\n");
-		return -ENODEV;
-	}
 	platform_set_drvdata(pdev, info);
 
 	axp288_extcon_log_rsi(info);
@@ -308,23 +286,16 @@ static int axp288_extcon_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	/* Get otg transceiver phy */
-	info->otg = devm_usb_get_phy(&pdev->dev, USB_PHY_TYPE_USB2);
-	if (IS_ERR(info->otg)) {
-		dev_err(&pdev->dev, "failed to get otg transceiver\n");
-		return PTR_ERR(info->otg);
-	}
-
 	/* Set up gpio control for USB Mux */
-	if (info->pdata->gpio_mux_cntl) {
+	if (info->gpio_mux_cntl) {
-		gpio = desc_to_gpio(info->pdata->gpio_mux_cntl);
+		gpio = desc_to_gpio(info->gpio_mux_cntl);
 		ret = devm_gpio_request(&pdev->dev, gpio, "USB_MUX");
 		if (ret < 0) {
 			dev_err(&pdev->dev,
 				"failed to request the gpio=%d\n", gpio);
 			return ret;
 		}
-		gpiod_direction_output(info->pdata->gpio_mux_cntl,
+		gpiod_direction_output(info->gpio_mux_cntl,
 						EXTCON_GPIO_MUX_SEL_PMIC);
 	}
 
@@ -349,14 +320,21 @@ static int axp288_extcon_probe(struct platform_device *pdev)
 		}
 	}
 
-	/* Enable interrupts */
+	/* Start charger cable type detection */
-	axp288_extcon_enable_irq(info);
+	axp288_extcon_enable(info);
 
 	return 0;
 }
 
+static const struct platform_device_id axp288_extcon_table[] = {
+	{ .name = "axp288_extcon" },
+	{},
+};
+MODULE_DEVICE_TABLE(platform, axp288_extcon_table);
+
 static struct platform_driver axp288_extcon_driver = {
 	.probe = axp288_extcon_probe,
+	.id_table = axp288_extcon_table,
 	.driver = {
 		.name = "axp288_extcon",
 	},

drivers/extcon/extcon-intel-int3496.c

@@ -0,0 +1,179 @@
+/*
+ * Intel INT3496 ACPI device extcon driver
+ *
+ * Copyright (c) 2016 Hans de Goede <hdegoede@redhat.com>
+ *
+ * Based on android x86 kernel code which is:
+ *
+ * Copyright (c) 2014, Intel Corporation.
+ * Author: David Cohen <david.a.cohen@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/acpi.h>
+#include <linux/extcon.h>
+#include <linux/gpio.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+
+#define INT3496_GPIO_USB_ID	0
+#define INT3496_GPIO_VBUS_EN	1
+#define INT3496_GPIO_USB_MUX	2
+#define DEBOUNCE_TIME		msecs_to_jiffies(50)
+
+struct int3496_data {
+	struct device *dev;
+	struct extcon_dev *edev;
+	struct delayed_work work;
+	struct gpio_desc *gpio_usb_id;
+	struct gpio_desc *gpio_vbus_en;
+	struct gpio_desc *gpio_usb_mux;
+	int usb_id_irq;
+};
+
+static const unsigned int int3496_cable[] = {
+	EXTCON_USB_HOST,
+	EXTCON_NONE,
+};
+
+static void int3496_do_usb_id(struct work_struct *work)
+{
+	struct int3496_data *data =
+		container_of(work, struct int3496_data, work.work);
+	int id = gpiod_get_value_cansleep(data->gpio_usb_id);
+
+	/* id == 1: PERIPHERAL, id == 0: HOST */
+	dev_dbg(data->dev, "Connected %s cable\n", id ? "PERIPHERAL" : "HOST");
+
+	/*
+	 * Peripheral: set USB mux to peripheral and disable VBUS
+	 * Host: set USB mux to host and enable VBUS
+	 */
+	if (!IS_ERR(data->gpio_usb_mux))
+		gpiod_direction_output(data->gpio_usb_mux, id);
+
+	if (!IS_ERR(data->gpio_vbus_en))
+		gpiod_direction_output(data->gpio_vbus_en, !id);
+
+	extcon_set_state_sync(data->edev, EXTCON_USB_HOST, !id);
+}
+
+static irqreturn_t int3496_thread_isr(int irq, void *priv)
+{
+	struct int3496_data *data = priv;
+
+	/* Let the pin settle before processing it */
+	mod_delayed_work(system_wq, &data->work, DEBOUNCE_TIME);
+
+	return IRQ_HANDLED;
+}
+
+static int int3496_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct int3496_data *data;
+	int ret;
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->dev = dev;
+	INIT_DELAYED_WORK(&data->work, int3496_do_usb_id);
+
+	data->gpio_usb_id = devm_gpiod_get_index(dev, "id",
+						INT3496_GPIO_USB_ID,
+						GPIOD_IN);
+	if (IS_ERR(data->gpio_usb_id)) {
+		ret = PTR_ERR(data->gpio_usb_id);
+		dev_err(dev, "can't request USB ID GPIO: %d\n", ret);
+		return ret;
+	}
+
+	data->usb_id_irq = gpiod_to_irq(data->gpio_usb_id);
+	if (data->usb_id_irq <= 0) {
+		dev_err(dev, "can't get USB ID IRQ: %d\n", data->usb_id_irq);
+		return -EINVAL;
+	}
+
+	data->gpio_vbus_en = devm_gpiod_get_index(dev, "vbus en",
+						 INT3496_GPIO_VBUS_EN,
+						 GPIOD_ASIS);
+	if (IS_ERR(data->gpio_vbus_en))
+		dev_info(dev, "can't request VBUS EN GPIO\n");
+
+	data->gpio_usb_mux = devm_gpiod_get_index(dev, "usb mux",
+						 INT3496_GPIO_USB_MUX,
+						 GPIOD_ASIS);
+	if (IS_ERR(data->gpio_usb_mux))
+		dev_info(dev, "can't request USB MUX GPIO\n");
+
+	/* register extcon device */
+	data->edev = devm_extcon_dev_allocate(dev, int3496_cable);
+	if (IS_ERR(data->edev))
+		return -ENOMEM;
+
+	ret = devm_extcon_dev_register(dev, data->edev);
+	if (ret < 0) {
+		dev_err(dev, "can't register extcon device: %d\n", ret);
+		return ret;
+	}
+
+	ret = devm_request_threaded_irq(dev, data->usb_id_irq,
+					NULL, int3496_thread_isr,
+					IRQF_SHARED | IRQF_ONESHOT |
+					IRQF_TRIGGER_RISING |
+					IRQF_TRIGGER_FALLING,
+					dev_name(dev), data);
+	if (ret < 0) {
+		dev_err(dev, "can't request IRQ for USB ID GPIO: %d\n", ret);
+		return ret;
+	}
+
+	/* queue initial processing of id-pin */
+	queue_delayed_work(system_wq, &data->work, 0);
+
+	platform_set_drvdata(pdev, data);
+
+	return 0;
+}
+
+static int int3496_remove(struct platform_device *pdev)
+{
+	struct int3496_data *data = platform_get_drvdata(pdev);
+
+	devm_free_irq(&pdev->dev, data->usb_id_irq, data);
+	cancel_delayed_work_sync(&data->work);
+
+	return 0;
+}
+
+static struct acpi_device_id int3496_acpi_match[] = {
+	{ "INT3496" },
+	{ }
+};
+MODULE_DEVICE_TABLE(acpi, int3496_acpi_match);
+
+static struct platform_driver int3496_driver = {
+	.driver = {
+		.name = "intel-int3496",
+		.acpi_match_table = int3496_acpi_match,
+	},
+	.probe = int3496_probe,
+	.remove = int3496_remove,
+};
+
+module_platform_driver(int3496_driver);
+
+MODULE_AUTHOR("Hans de Goede <hdegoede@redhat.com>");
+MODULE_DESCRIPTION("Intel INT3496 ACPI device extcon driver");
+MODULE_LICENSE("GPL");

drivers/extcon/extcon-max14577.c

@@ -531,8 +531,10 @@ static int max14577_parse_irq(struct max14577_muic_info *info, int irq_type)
 	case MAX14577_IRQ_INT1_ADC:
 	case MAX14577_IRQ_INT1_ADCLOW:
 	case MAX14577_IRQ_INT1_ADCERR:
-		/* Handle all of accessory except for
+		/*
-		   type of charger accessory */
+		 * Handle all of accessory except for
+		 * type of charger accessory.
+		 */
 		info->irq_adc = true;
 		return 1;
 	case MAX14577_IRQ_INT2_CHGTYP:

drivers/extcon/extcon-max77693.c

@@ -188,8 +188,10 @@ enum max77693_muic_acc_type {
 	MAX77693_MUIC_ADC_AUDIO_MODE_REMOTE,
 	MAX77693_MUIC_ADC_OPEN,
 
-	/* The below accessories have same ADC value so ADCLow and
+	/*
-	   ADC1K bit is used to separate specific accessory */
+	 * The below accessories have same ADC value so ADCLow and
+	 * ADC1K bit is used to separate specific accessory.
+	 */
 						/* ADC|VBVolot|ADCLow|ADC1K| */
 	MAX77693_MUIC_GND_USB_HOST = 0x100,	/* 0x0|      0|     0|    0| */
 	MAX77693_MUIC_GND_USB_HOST_VB = 0x104,	/* 0x0|      1|     0|    0| */
@@ -970,8 +972,10 @@ static void max77693_muic_irq_work(struct work_struct *work)
 	case MAX77693_MUIC_IRQ_INT1_ADC_LOW:
 	case MAX77693_MUIC_IRQ_INT1_ADC_ERR:
 	case MAX77693_MUIC_IRQ_INT1_ADC1K:
-		/* Handle all of accessory except for
+		/*
-		   type of charger accessory */
+		 * Handle all of accessory except for
+		 * type of charger accessory.
+		 */
 		ret = max77693_muic_adc_handler(info);
 		break;
 	case MAX77693_MUIC_IRQ_INT2_CHGTYP:

drivers/extcon/extcon-max77843.c

@@ -97,8 +97,10 @@ enum max77843_muic_accessory_type {
 	MAX77843_MUIC_ADC_AUDIO_DEVICE_TYPE1,
 	MAX77843_MUIC_ADC_OPEN,
 
-	/* The blow accessories should check
+	/*
-	   not only ADC value but also ADC1K and VBVolt value. */
+	 * The below accessories should check
+	 * not only ADC value but also ADC1K and VBVolt value.
+	 */
 						/* Offset|ADC1K|VBVolt| */
 	MAX77843_MUIC_GND_USB_HOST = 0x100,	/*    0x1|    0|     0| */
 	MAX77843_MUIC_GND_USB_HOST_VB = 0x101,	/*    0x1|    0|     1| */
@@ -265,16 +267,20 @@ static int max77843_muic_get_cable_type(struct max77843_muic_info *info,
 		/* Check GROUND accessory with charger cable */
 		if (adc == MAX77843_MUIC_ADC_GROUND) {
 			if (chg_type == MAX77843_MUIC_CHG_NONE) {
-				/* The following state when charger cable is
+				/*
+				 * The following state when charger cable is
 				 * disconnected but the GROUND accessory still
-				 * connected */
+				 * connected.
+				 */
 				*attached = false;
 				cable_type = info->prev_chg_type;
 				info->prev_chg_type = MAX77843_MUIC_CHG_NONE;
 			} else {
 
-				/* The following state when charger cable is
+				/*
-				 * connected on the GROUND accessory */
+				 * The following state when charger cable is
+				 * connected on the GROUND accessory.
+				 */
 				*attached = true;
 				cable_type = MAX77843_MUIC_CHG_GND;
 				info->prev_chg_type = MAX77843_MUIC_CHG_GND;
@@ -299,11 +305,13 @@ static int max77843_muic_get_cable_type(struct max77843_muic_info *info,
 		} else {
 			*attached = true;
 
-			/* Offset|ADC1K|VBVolt|
+			/*
+			 * Offset|ADC1K|VBVolt|
 			 *    0x1|    0|     0| USB-HOST
 			 *    0x1|    0|     1| USB-HOST with VB
 			 *    0x1|    1|     0| MHL
-			 *    0x1|    1|     1| MHL with VB */
+			 *    0x1|    1|     1| MHL with VB
+			 */
 			/* Get ADC1K register bit */
 			gnd_type = (info->status[MAX77843_MUIC_STATUS1] &
 					MAX77843_MUIC_STATUS1_ADC1K_MASK);

drivers/extcon/extcon-palmas.c

@@ -62,7 +62,7 @@ static irqreturn_t palmas_vbus_irq_handler(int irq, void *_palmas_usb)
 		if (palmas_usb->linkstat != PALMAS_USB_STATE_VBUS) {
 			palmas_usb->linkstat = PALMAS_USB_STATE_VBUS;
 			extcon_set_state_sync(edev, EXTCON_USB, true);
-			dev_info(palmas_usb->dev, "USB cable is attached\n");
+			dev_dbg(palmas_usb->dev, "USB cable is attached\n");
 		} else {
 			dev_dbg(palmas_usb->dev,
 				"Spurious connect event detected\n");
@@ -71,7 +71,7 @@ static irqreturn_t palmas_vbus_irq_handler(int irq, void *_palmas_usb)
 		if (palmas_usb->linkstat == PALMAS_USB_STATE_VBUS) {
 			palmas_usb->linkstat = PALMAS_USB_STATE_DISCONNECT;
 			extcon_set_state_sync(edev, EXTCON_USB, false);
-			dev_info(palmas_usb->dev, "USB cable is detached\n");
+			dev_dbg(palmas_usb->dev, "USB cable is detached\n");
 		} else {
 			dev_dbg(palmas_usb->dev,
 				"Spurious disconnect event detected\n");
@@ -99,7 +99,7 @@ static irqreturn_t palmas_id_irq_handler(int irq, void *_palmas_usb)
 			PALMAS_USB_ID_INT_EN_HI_CLR_ID_GND);
 		palmas_usb->linkstat = PALMAS_USB_STATE_ID;
 		extcon_set_state_sync(edev, EXTCON_USB_HOST, true);
-		dev_info(palmas_usb->dev, "USB-HOST cable is attached\n");
+		dev_dbg(palmas_usb->dev, "USB-HOST cable is attached\n");
 	} else if ((set & PALMAS_USB_ID_INT_SRC_ID_FLOAT) &&
 				(id_src & PALMAS_USB_ID_INT_SRC_ID_FLOAT)) {
 		palmas_write(palmas_usb->palmas, PALMAS_USB_OTG_BASE,
@@ -107,17 +107,17 @@ static irqreturn_t palmas_id_irq_handler(int irq, void *_palmas_usb)
 			PALMAS_USB_ID_INT_EN_HI_CLR_ID_FLOAT);
 		palmas_usb->linkstat = PALMAS_USB_STATE_DISCONNECT;
 		extcon_set_state_sync(edev, EXTCON_USB_HOST, false);
-		dev_info(palmas_usb->dev, "USB-HOST cable is detached\n");
+		dev_dbg(palmas_usb->dev, "USB-HOST cable is detached\n");
 	} else if ((palmas_usb->linkstat == PALMAS_USB_STATE_ID) &&
 				(!(set & PALMAS_USB_ID_INT_SRC_ID_GND))) {
 		palmas_usb->linkstat = PALMAS_USB_STATE_DISCONNECT;
 		extcon_set_state_sync(edev, EXTCON_USB_HOST, false);
-		dev_info(palmas_usb->dev, "USB-HOST cable is detached\n");
+		dev_dbg(palmas_usb->dev, "USB-HOST cable is detached\n");
 	} else if ((palmas_usb->linkstat == PALMAS_USB_STATE_DISCONNECT) &&
 				(id_src & PALMAS_USB_ID_INT_SRC_ID_GND)) {
 		palmas_usb->linkstat = PALMAS_USB_STATE_ID;
 		extcon_set_state_sync(edev, EXTCON_USB_HOST, true);
-		dev_info(palmas_usb->dev, " USB-HOST cable is attached\n");
+		dev_dbg(palmas_usb->dev, " USB-HOST cable is attached\n");
 	}
 
 	return IRQ_HANDLED;
@@ -138,10 +138,10 @@ static void palmas_gpio_id_detect(struct work_struct *work)
 
 	if (id) {
 		extcon_set_state_sync(edev, EXTCON_USB_HOST, false);
-		dev_info(palmas_usb->dev, "USB-HOST cable is detached\n");
+		dev_dbg(palmas_usb->dev, "USB-HOST cable is detached\n");
 	} else {
 		extcon_set_state_sync(edev, EXTCON_USB_HOST, true);
-		dev_info(palmas_usb->dev, "USB-HOST cable is attached\n");
+		dev_dbg(palmas_usb->dev, "USB-HOST cable is attached\n");
 	}
 }
 
@@ -190,6 +190,11 @@ static int palmas_usb_probe(struct platform_device *pdev)
 	struct palmas_usb *palmas_usb;
 	int status;
 
+	if (!palmas) {
+		dev_err(&pdev->dev, "failed to get valid parent\n");
+		return -EINVAL;
+	}
+
 	palmas_usb = devm_kzalloc(&pdev->dev, sizeof(*palmas_usb), GFP_KERNEL);
 	if (!palmas_usb)
 		return -ENOMEM;

drivers/extcon/extcon-rt8973a.c

@@ -142,8 +142,10 @@ enum rt8973a_muic_acc_type {
 	RT8973A_MUIC_ADC_UNKNOWN_ACC_5,
 	RT8973A_MUIC_ADC_OPEN = 0x1f,
 
-	/* The below accessories has same ADC value (0x1f).
+	/*
-	   So, Device type1 is used to separate specific accessory. */
+	 * The below accessories has same ADC value (0x1f).
+	 * So, Device type1 is used to separate specific accessory.
+	 */
 					/* |---------|--ADC| */
 					/* |    [7:5]|[4:0]| */
 	RT8973A_MUIC_ADC_USB = 0x3f,	/* |      001|11111| */

drivers/extcon/extcon-sm5502.c

@@ -135,8 +135,10 @@ enum sm5502_muic_acc_type {
 	SM5502_MUIC_ADC_AUDIO_TYPE1,
 	SM5502_MUIC_ADC_OPEN = 0x1f,
 
-	/* The below accessories have same ADC value (0x1f or 0x1e).
+	/*
-	   So, Device type1 is used to separate specific accessory. */
+	 * The below accessories have same ADC value (0x1f or 0x1e).
+	 * So, Device type1 is used to separate specific accessory.
+	 */
 							/* |---------|--ADC| */
 							/* |    [7:5]|[4:0]| */
 	SM5502_MUIC_ADC_AUDIO_TYPE1_FULL_REMOTE = 0x3e,	/* |      001|11110| */

drivers/extcon/extcon-usb-gpio.c

@@ -27,6 +27,7 @@
 #include <linux/slab.h>
 #include <linux/workqueue.h>
 #include <linux/acpi.h>
+#include <linux/pinctrl/consumer.h>
 
 #define USB_GPIO_DEBOUNCE_MS	20	/* ms */
 
@@ -245,6 +246,9 @@ static int usb_extcon_suspend(struct device *dev)
 	if (info->vbus_gpiod)
 		disable_irq(info->vbus_irq);
 
+	if (!device_may_wakeup(dev))
+		pinctrl_pm_select_sleep_state(dev);
+
 	return ret;
 }
 
@@ -253,6 +257,9 @@ static int usb_extcon_resume(struct device *dev)
 	struct usb_extcon_info *info = dev_get_drvdata(dev);
 	int ret = 0;
 
+	if (!device_may_wakeup(dev))
+		pinctrl_pm_select_default_state(dev);
+
 	if (device_may_wakeup(dev)) {
 		if (info->id_gpiod) {
 			ret = disable_irq_wake(info->id_irq);

drivers/extcon/extcon.c

@@ -30,11 +30,12 @@
 #include <linux/device.h>
 #include <linux/fs.h>
 #include <linux/err.h>
-#include <linux/extcon.h>
 #include <linux/of.h>
 #include <linux/slab.h>
 #include <linux/sysfs.h>
 
+#include "extcon.h"
+
 #define SUPPORTED_CABLE_MAX	32
 #define CABLE_NAME_MAX		30
 
@@ -59,7 +60,7 @@ struct __extcon_info {
 	[EXTCON_USB_HOST] = {
 		.type = EXTCON_TYPE_USB,
 		.id = EXTCON_USB_HOST,
-		.name = "USB_HOST",
+		.name = "USB-HOST",
 	},
 
 	/* Charging external connector */
@@ -98,6 +99,11 @@ struct __extcon_info {
 		.id = EXTCON_CHG_WPT,
 		.name = "WPT",
 	},
+	[EXTCON_CHG_USB_PD] = {
+		.type = EXTCON_TYPE_CHG | EXTCON_TYPE_USB,
+		.id = EXTCON_CHG_USB_PD,
+		.name = "PD",
+	},
 
 	/* Jack external connector */
 	[EXTCON_JACK_MICROPHONE] = {
@@ -906,10 +912,9 @@ int extcon_register_notifier(struct extcon_dev *edev, unsigned int id,
 	unsigned long flags;
 	int ret, idx = -EINVAL;
 
-	if (!nb)
+	if (!edev || !nb)
 		return -EINVAL;
 
-	if (edev) {
 	idx = find_cable_index_by_id(edev, id);
 	if (idx < 0)
 		return idx;
@@ -917,24 +922,6 @@ int extcon_register_notifier(struct extcon_dev *edev, unsigned int id,
 	spin_lock_irqsave(&edev->lock, flags);
 	ret = raw_notifier_chain_register(&edev->nh[idx], nb);
 	spin_unlock_irqrestore(&edev->lock, flags);
-	} else {
-		struct extcon_dev *extd;
-
-		mutex_lock(&extcon_dev_list_lock);
-		list_for_each_entry(extd, &extcon_dev_list, entry) {
-			idx = find_cable_index_by_id(extd, id);
-			if (idx >= 0)
-				break;
-		}
-		mutex_unlock(&extcon_dev_list_lock);
-
-		if (idx >= 0) {
-			edev = extd;
-			return extcon_register_notifier(extd, id, nb);
-		} else {
-			ret = -ENODEV;
-		}
-	}
 
 	return ret;
 }

drivers/extcon/extcon.h

@@ -0,0 +1,62 @@
+#ifndef __LINUX_EXTCON_INTERNAL_H__
+#define __LINUX_EXTCON_INTERNAL_H__
+
+#include <linux/extcon.h>
+
+/**
+ * struct extcon_dev - An extcon device represents one external connector.
+ * @name:		The name of this extcon device. Parent device name is
+ *			used if NULL.
+ * @supported_cable:	Array of supported cable names ending with EXTCON_NONE.
+ *			If supported_cable is NULL, cable name related APIs
+ *			are disabled.
+ * @mutually_exclusive:	Array of mutually exclusive set of cables that cannot
+ *			be attached simultaneously. The array should be
+ *			ending with NULL or be NULL (no mutually exclusive
+ *			cables). For example, if it is { 0x7, 0x30, 0}, then,
+ *			{0, 1}, {0, 1, 2}, {0, 2}, {1, 2}, or {4, 5} cannot
+ *			be attached simulataneously. {0x7, 0} is equivalent to
+ *			{0x3, 0x6, 0x5, 0}. If it is {0xFFFFFFFF, 0}, there
+ *			can be no simultaneous connections.
+ * @dev:		Device of this extcon.
+ * @state:		Attach/detach state of this extcon. Do not provide at
+ *			register-time.
+ * @nh:			Notifier for the state change events from this extcon
+ * @entry:		To support list of extcon devices so that users can
+ *			search for extcon devices based on the extcon name.
+ * @lock:
+ * @max_supported:	Internal value to store the number of cables.
+ * @extcon_dev_type:	Device_type struct to provide attribute_groups
+ *			customized for each extcon device.
+ * @cables:		Sysfs subdirectories. Each represents one cable.
+ *
+ * In most cases, users only need to provide "User initializing data" of
+ * this struct when registering an extcon. In some exceptional cases,
+ * optional callbacks may be needed. However, the values in "internal data"
+ * are overwritten by register function.
+ */
+struct extcon_dev {
+	/* Optional user initializing data */
+	const char *name;
+	const unsigned int *supported_cable;
+	const u32 *mutually_exclusive;
+
+	/* Internal data. Please do not set. */
+	struct device dev;
+	struct raw_notifier_head *nh;
+	struct list_head entry;
+	int max_supported;
+	spinlock_t lock;	/* could be called by irq handler */
+	u32 state;
+
+	/* /sys/class/extcon/.../cable.n/... */
+	struct device_type extcon_dev_type;
+	struct extcon_cable *cables;
+
+	/* /sys/class/extcon/.../mutually_exclusive/... */
+	struct attribute_group attr_g_muex;
+	struct attribute **attrs_muex;
+	struct device_attribute *d_attrs_muex;
+};
+
+#endif /* __LINUX_EXTCON_INTERNAL_H__ */

drivers/fpga/fpga-mgr.c

@@ -25,16 +25,106 @@
 #include <linux/of.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
+#include <linux/scatterlist.h>
+#include <linux/highmem.h>
 
 static DEFINE_IDA(fpga_mgr_ida);
 static struct class *fpga_mgr_class;
 
+/*
+ * Call the low level driver's write_init function.  This will do the
+ * device-specific things to get the FPGA into the state where it is ready to
+ * receive an FPGA image. The low level driver only gets to see the first
+ * initial_header_size bytes in the buffer.
+ */
+static int fpga_mgr_write_init_buf(struct fpga_manager *mgr,
+				   struct fpga_image_info *info,
+				   const char *buf, size_t count)
+{
+	int ret;
+
+	mgr->state = FPGA_MGR_STATE_WRITE_INIT;
+	if (!mgr->mops->initial_header_size)
+		ret = mgr->mops->write_init(mgr, info, NULL, 0);
+	else
+		ret = mgr->mops->write_init(
+		    mgr, info, buf, min(mgr->mops->initial_header_size, count));
+
+	if (ret) {
+		dev_err(&mgr->dev, "Error preparing FPGA for writing\n");
+		mgr->state = FPGA_MGR_STATE_WRITE_INIT_ERR;
+		return ret;
+	}
+
+	return 0;
+}
+
+static int fpga_mgr_write_init_sg(struct fpga_manager *mgr,
+				  struct fpga_image_info *info,
+				  struct sg_table *sgt)
+{
+	struct sg_mapping_iter miter;
+	size_t len;
+	char *buf;
+	int ret;
+
+	if (!mgr->mops->initial_header_size)
+		return fpga_mgr_write_init_buf(mgr, info, NULL, 0);
+
+	/*
+	 * First try to use miter to map the first fragment to access the
+	 * header, this is the typical path.
+	 */
+	sg_miter_start(&miter, sgt->sgl, sgt->nents, SG_MITER_FROM_SG);
+	if (sg_miter_next(&miter) &&
+	    miter.length >= mgr->mops->initial_header_size) {
+		ret = fpga_mgr_write_init_buf(mgr, info, miter.addr,
+					      miter.length);
+		sg_miter_stop(&miter);
+		return ret;
+	}
+	sg_miter_stop(&miter);
+
+	/* Otherwise copy the fragments into temporary memory. */
+	buf = kmalloc(mgr->mops->initial_header_size, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	len = sg_copy_to_buffer(sgt->sgl, sgt->nents, buf,
+				mgr->mops->initial_header_size);
+	ret = fpga_mgr_write_init_buf(mgr, info, buf, len);
+
+	kfree(buf);
+
+	return ret;
+}
+
+/*
+ * After all the FPGA image has been written, do the device specific steps to
+ * finish and set the FPGA into operating mode.
+ */
+static int fpga_mgr_write_complete(struct fpga_manager *mgr,
+				   struct fpga_image_info *info)
+{
+	int ret;
+
+	mgr->state = FPGA_MGR_STATE_WRITE_COMPLETE;
+	ret = mgr->mops->write_complete(mgr, info);
+	if (ret) {
+		dev_err(&mgr->dev, "Error after writing image data to FPGA\n");
+		mgr->state = FPGA_MGR_STATE_WRITE_COMPLETE_ERR;
+		return ret;
+	}
+	mgr->state = FPGA_MGR_STATE_OPERATING;
+
+	return 0;
+}
+
 /**
- * fpga_mgr_buf_load - load fpga from image in buffer
+ * fpga_mgr_buf_load_sg - load fpga from image in buffer from a scatter list
  * @mgr:	fpga manager
  * @info:	fpga image specific information
- * @buf:	buffer contain fpga image
+ * @sgt:	scatterlist table
- * @count:	byte count of buf
  *
  * Step the low level fpga manager through the device-specific steps of getting
  * an FPGA ready to be configured, writing the image to it, then doing whatever
@@ -42,54 +132,139 @@ static struct class *fpga_mgr_class;
  * mgr pointer from of_fpga_mgr_get() or fpga_mgr_get() and checked that it is
  * not an error code.
  *
+ * This is the preferred entry point for FPGA programming, it does not require
+ * any contiguous kernel memory.
+ *
  * Return: 0 on success, negative error code otherwise.
  */
-int fpga_mgr_buf_load(struct fpga_manager *mgr, struct fpga_image_info *info,
+int fpga_mgr_buf_load_sg(struct fpga_manager *mgr, struct fpga_image_info *info,
-		      const char *buf, size_t count)
+			 struct sg_table *sgt)
 {
-	struct device *dev = &mgr->dev;
 	int ret;
 
-	/*
+	ret = fpga_mgr_write_init_sg(mgr, info, sgt);
-	 * Call the low level driver's write_init function.  This will do the
+	if (ret)
-	 * device-specific things to get the FPGA into the state where it is
+		return ret;
-	 * ready to receive an FPGA image. The low level driver only gets to
+
-	 * see the first initial_header_size bytes in the buffer.
+	/* Write the FPGA image to the FPGA. */
-	 */
+	mgr->state = FPGA_MGR_STATE_WRITE;
-	mgr->state = FPGA_MGR_STATE_WRITE_INIT;
+	if (mgr->mops->write_sg) {
-	ret = mgr->mops->write_init(mgr, info, buf,
+		ret = mgr->mops->write_sg(mgr, sgt);
-				    min(mgr->mops->initial_header_size, count));
+	} else {
+		struct sg_mapping_iter miter;
+
+		sg_miter_start(&miter, sgt->sgl, sgt->nents, SG_MITER_FROM_SG);
+		while (sg_miter_next(&miter)) {
+			ret = mgr->mops->write(mgr, miter.addr, miter.length);
+			if (ret)
+				break;
+		}
+		sg_miter_stop(&miter);
+	}
+
 	if (ret) {
-		dev_err(dev, "Error preparing FPGA for writing\n");
+		dev_err(&mgr->dev, "Error while writing image data to FPGA\n");
-		mgr->state = FPGA_MGR_STATE_WRITE_INIT_ERR;
+		mgr->state = FPGA_MGR_STATE_WRITE_ERR;
 		return ret;
 	}
 
+	return fpga_mgr_write_complete(mgr, info);
+}
+EXPORT_SYMBOL_GPL(fpga_mgr_buf_load_sg);
+
+static int fpga_mgr_buf_load_mapped(struct fpga_manager *mgr,
+				    struct fpga_image_info *info,
+				    const char *buf, size_t count)
+{
+	int ret;
+
+	ret = fpga_mgr_write_init_buf(mgr, info, buf, count);
+	if (ret)
+		return ret;
+
 	/*
 	 * Write the FPGA image to the FPGA.
 	 */
 	mgr->state = FPGA_MGR_STATE_WRITE;
 	ret = mgr->mops->write(mgr, buf, count);
 	if (ret) {
-		dev_err(dev, "Error while writing image data to FPGA\n");
+		dev_err(&mgr->dev, "Error while writing image data to FPGA\n");
 		mgr->state = FPGA_MGR_STATE_WRITE_ERR;
 		return ret;
 	}
 
-	/*
+	return fpga_mgr_write_complete(mgr, info);
-	 * After all the FPGA image has been written, do the device specific
-	 * steps to finish and set the FPGA into operating mode.
-	 */
-	mgr->state = FPGA_MGR_STATE_WRITE_COMPLETE;
-	ret = mgr->mops->write_complete(mgr, info);
-	if (ret) {
-		dev_err(dev, "Error after writing image data to FPGA\n");
-		mgr->state = FPGA_MGR_STATE_WRITE_COMPLETE_ERR;
-		return ret;
 }
-	mgr->state = FPGA_MGR_STATE_OPERATING;
 
-	return 0;
+/**
+ * fpga_mgr_buf_load - load fpga from image in buffer
+ * @mgr:	fpga manager
+ * @flags:	flags setting fpga confuration modes
+ * @buf:	buffer contain fpga image
+ * @count:	byte count of buf
+ *
+ * Step the low level fpga manager through the device-specific steps of getting
+ * an FPGA ready to be configured, writing the image to it, then doing whatever
+ * post-configuration steps necessary.  This code assumes the caller got the
+ * mgr pointer from of_fpga_mgr_get() and checked that it is not an error code.
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+int fpga_mgr_buf_load(struct fpga_manager *mgr, struct fpga_image_info *info,
+		      const char *buf, size_t count)
+{
+	struct page **pages;
+	struct sg_table sgt;
+	const void *p;
+	int nr_pages;
+	int index;
+	int rc;
+
+	/*
+	 * This is just a fast path if the caller has already created a
+	 * contiguous kernel buffer and the driver doesn't require SG, non-SG
+	 * drivers will still work on the slow path.
+	 */
+	if (mgr->mops->write)
+		return fpga_mgr_buf_load_mapped(mgr, info, buf, count);
+
+	/*
+	 * Convert the linear kernel pointer into a sg_table of pages for use
+	 * by the driver.
+	 */
+	nr_pages = DIV_ROUND_UP((unsigned long)buf + count, PAGE_SIZE) -
+		   (unsigned long)buf / PAGE_SIZE;
+	pages = kmalloc_array(nr_pages, sizeof(struct page *), GFP_KERNEL);
+	if (!pages)
+		return -ENOMEM;
+
+	p = buf - offset_in_page(buf);
+	for (index = 0; index < nr_pages; index++) {
+		if (is_vmalloc_addr(p))
+			pages[index] = vmalloc_to_page(p);
+		else
+			pages[index] = kmap_to_page((void *)p);
+		if (!pages[index]) {
+			kfree(pages);
+			return -EFAULT;
+		}
+		p += PAGE_SIZE;
+	}
+
+	/*
+	 * The temporary pages list is used to code share the merging algorithm
+	 * in sg_alloc_table_from_pages
+	 */
+	rc = sg_alloc_table_from_pages(&sgt, pages, index, offset_in_page(buf),
+				       count, GFP_KERNEL);
+	kfree(pages);
+	if (rc)
+		return rc;
+
+	rc = fpga_mgr_buf_load_sg(mgr, info, &sgt);
+	sg_free_table(&sgt);
+
+	return rc;
 }
 EXPORT_SYMBOL_GPL(fpga_mgr_buf_load);
 
@@ -291,8 +466,9 @@ int fpga_mgr_register(struct device *dev, const char *name,
 	struct fpga_manager *mgr;
 	int id, ret;
 
-	if (!mops || !mops->write_init || !mops->write ||
+	if (!mops || !mops->write_complete || !mops->state ||
-	    !mops->write_complete || !mops->state) {
+	    !mops->write_init || (!mops->write && !mops->write_sg) ||
+	    (mops->write && mops->write_sg)) {
 		dev_err(dev, "Attempt to register without fpga_manager_ops\n");
 		return -EINVAL;
 	}

drivers/fpga/zynq-fpga.c

@@ -30,6 +30,7 @@
 #include <linux/pm.h>
 #include <linux/regmap.h>
 #include <linux/string.h>
+#include <linux/scatterlist.h>
 
 /* Offsets into SLCR regmap */
 
@@ -80,6 +81,7 @@
 
 /* FPGA init status */
 #define STATUS_DMA_Q_F			BIT(31)
+#define STATUS_DMA_Q_E			BIT(30)
 #define STATUS_PCFG_INIT_MASK		BIT(4)
 
 /* Interrupt Status/Mask Register Bit definitions */
@@ -89,7 +91,7 @@
 #define IXR_D_P_DONE_MASK		BIT(12)
  /* FPGA programmed */
 #define IXR_PCFG_DONE_MASK		BIT(2)
-#define IXR_ERROR_FLAGS_MASK		0x00F0F860
+#define IXR_ERROR_FLAGS_MASK		0x00F0C860
 #define IXR_ALL_MASK			0xF8F7F87F
 
 /* Miscellaneous constant values */
@@ -98,12 +100,16 @@
 #define DMA_INVALID_ADDRESS		GENMASK(31, 0)
 /* Used to unlock the dev */
 #define UNLOCK_MASK			0x757bdf0d
-/* Timeout for DMA to complete */
-#define DMA_DONE_TIMEOUT		msecs_to_jiffies(1000)
 /* Timeout for polling reset bits */
 #define INIT_POLL_TIMEOUT		2500000
 /* Delay for polling reset bits */
 #define INIT_POLL_DELAY			20
+/* Signal this is the last DMA transfer, wait for the AXI and PCAP before
+ * interrupting
+ */
+#define DMA_SRC_LAST_TRANSFER		1
+/* Timeout for DMA completion */
+#define DMA_TIMEOUT_MS			5000
 
 /* Masks for controlling stuff in SLCR */
 /* Disable all Level shifters */
@@ -124,6 +130,11 @@ struct zynq_fpga_priv {
 	void __iomem *io_base;
 	struct regmap *slcr;
 
+	spinlock_t dma_lock;
+	unsigned int dma_elm;
+	unsigned int dma_nelms;
+	struct scatterlist *cur_sg;
+
 	struct completion dma_done;
 };
 
@@ -143,37 +154,104 @@ static inline u32 zynq_fpga_read(const struct zynq_fpga_priv *priv,
 	readl_poll_timeout(priv->io_base + addr, val, cond, sleep_us, \
 			   timeout_us)
 
-static void zynq_fpga_mask_irqs(struct zynq_fpga_priv *priv)
+/* Cause the specified irq mask bits to generate IRQs */
+static inline void zynq_fpga_set_irq(struct zynq_fpga_priv *priv, u32 enable)
 {
-	u32 intr_mask;
+	zynq_fpga_write(priv, INT_MASK_OFFSET, ~enable);
-
-	intr_mask = zynq_fpga_read(priv, INT_MASK_OFFSET);
-	zynq_fpga_write(priv, INT_MASK_OFFSET,
-			intr_mask | IXR_DMA_DONE_MASK | IXR_ERROR_FLAGS_MASK);
 }
 
-static void zynq_fpga_unmask_irqs(struct zynq_fpga_priv *priv)
+/* Must be called with dma_lock held */
+static void zynq_step_dma(struct zynq_fpga_priv *priv)
 {
-	u32 intr_mask;
+	u32 addr;
+	u32 len;
+	bool first;
 
-	intr_mask = zynq_fpga_read(priv, INT_MASK_OFFSET);
+	first = priv->dma_elm == 0;
-	zynq_fpga_write(priv, INT_MASK_OFFSET,
+	while (priv->cur_sg) {
-			intr_mask
+		/* Feed the DMA queue until it is full. */
-			& ~(IXR_D_P_DONE_MASK | IXR_ERROR_FLAGS_MASK));
+		if (zynq_fpga_read(priv, STATUS_OFFSET) & STATUS_DMA_Q_F)
+			break;
+
+		addr = sg_dma_address(priv->cur_sg);
+		len = sg_dma_len(priv->cur_sg);
+		if (priv->dma_elm + 1 == priv->dma_nelms) {
+			/* The last transfer waits for the PCAP to finish too,
+			 * notice this also changes the irq_mask to ignore
+			 * IXR_DMA_DONE_MASK which ensures we do not trigger
+			 * the completion too early.
+			 */
+			addr |= DMA_SRC_LAST_TRANSFER;
+			priv->cur_sg = NULL;
+		} else {
+			priv->cur_sg = sg_next(priv->cur_sg);
+			priv->dma_elm++;
+		}
+
+		zynq_fpga_write(priv, DMA_SRC_ADDR_OFFSET, addr);
+		zynq_fpga_write(priv, DMA_DST_ADDR_OFFSET, DMA_INVALID_ADDRESS);
+		zynq_fpga_write(priv, DMA_SRC_LEN_OFFSET, len / 4);
+		zynq_fpga_write(priv, DMA_DEST_LEN_OFFSET, 0);
+	}
+
+	/* Once the first transfer is queued we can turn on the ISR, future
+	 * calls to zynq_step_dma will happen from the ISR context. The
+	 * dma_lock spinlock guarentees this handover is done coherently, the
+	 * ISR enable is put at the end to avoid another CPU spinning in the
+	 * ISR on this lock.
+	 */
+	if (first && priv->cur_sg) {
+		zynq_fpga_set_irq(priv,
+				  IXR_DMA_DONE_MASK | IXR_ERROR_FLAGS_MASK);
+	} else if (!priv->cur_sg) {
+		/* The last transfer changes to DMA & PCAP mode since we do
+		 * not want to continue until everything has been flushed into
+		 * the PCAP.
+		 */
+		zynq_fpga_set_irq(priv,
+				  IXR_D_P_DONE_MASK | IXR_ERROR_FLAGS_MASK);
+	}
 }
 
 static irqreturn_t zynq_fpga_isr(int irq, void *data)
 {
 	struct zynq_fpga_priv *priv = data;
+	u32 intr_status;
 
-	/* disable DMA and error IRQs */
+	/* If anything other than DMA completion is reported stop and hand
-	zynq_fpga_mask_irqs(priv);
+	 * control back to zynq_fpga_ops_write, something went wrong,
+	 * otherwise progress the DMA.
+	 */
+	spin_lock(&priv->dma_lock);
+	intr_status = zynq_fpga_read(priv, INT_STS_OFFSET);
+	if (!(intr_status & IXR_ERROR_FLAGS_MASK) &&
+	    (intr_status & IXR_DMA_DONE_MASK) && priv->cur_sg) {
+		zynq_fpga_write(priv, INT_STS_OFFSET, IXR_DMA_DONE_MASK);
+		zynq_step_dma(priv);
+		spin_unlock(&priv->dma_lock);
+		return IRQ_HANDLED;
+	}
+	spin_unlock(&priv->dma_lock);
 
+	zynq_fpga_set_irq(priv, 0);
 	complete(&priv->dma_done);
 
 	return IRQ_HANDLED;
 }
 
+/* Sanity check the proposed bitstream. It must start with the sync word in
+ * the correct byte order, and be dword aligned. The input is a Xilinx .bin
+ * file with every 32 bit quantity swapped.
+ */
+static bool zynq_fpga_has_sync(const u8 *buf, size_t count)
+{
+	for (; count >= 4; buf += 4, count -= 4)
+		if (buf[0] == 0x66 && buf[1] == 0x55 && buf[2] == 0x99 &&
+		    buf[3] == 0xaa)
+			return true;
+	return false;
+}
+
 static int zynq_fpga_ops_write_init(struct fpga_manager *mgr,
 				    struct fpga_image_info *info,
 				    const char *buf, size_t count)
@@ -190,6 +268,13 @@ static int zynq_fpga_ops_write_init(struct fpga_manager *mgr,
 
 	/* don't globally reset PL if we're doing partial reconfig */
 	if (!(info->flags & FPGA_MGR_PARTIAL_RECONFIG)) {
+		if (!zynq_fpga_has_sync(buf, count)) {
+			dev_err(&mgr->dev,
+				"Invalid bitstream, could not find a sync word. Bitstream must be a byte swapped .bin file\n");
+			err = -EINVAL;
+			goto out_err;
+		}
+
 		/* assert AXI interface resets */
 		regmap_write(priv->slcr, SLCR_FPGA_RST_CTRL_OFFSET,
 			     FPGA_RST_ALL_MASK);
@@ -259,10 +344,11 @@ static int zynq_fpga_ops_write_init(struct fpga_manager *mgr,
 	zynq_fpga_write(priv, CTRL_OFFSET,
 			(CTRL_PCAP_PR_MASK | CTRL_PCAP_MODE_MASK | ctrl));
 
-	/* check that we have room in the command queue */
+	/* We expect that the command queue is empty right now. */
 	status = zynq_fpga_read(priv, STATUS_OFFSET);
-	if (status & STATUS_DMA_Q_F) {
+	if ((status & STATUS_DMA_Q_F) ||
-		dev_err(&mgr->dev, "DMA command queue full\n");
+	    (status & STATUS_DMA_Q_E) != STATUS_DMA_Q_E) {
+		dev_err(&mgr->dev, "DMA command queue not right\n");
 		err = -EBUSY;
 		goto out_err;
 	}
@@ -281,26 +367,36 @@ static int zynq_fpga_ops_write_init(struct fpga_manager *mgr,
 	return err;
 }
 
-static int zynq_fpga_ops_write(struct fpga_manager *mgr,
+static int zynq_fpga_ops_write(struct fpga_manager *mgr, struct sg_table *sgt)
-			       const char *buf, size_t count)
 {
 	struct zynq_fpga_priv *priv;
+	const char *why;
 	int err;
-	char *kbuf;
-	size_t in_count;
-	dma_addr_t dma_addr;
-	u32 transfer_length;
 	u32 intr_status;
+	unsigned long timeout;
+	unsigned long flags;
+	struct scatterlist *sg;
+	int i;
 
-	in_count = count;
 	priv = mgr->priv;
 
-	kbuf =
+	/* The hardware can only DMA multiples of 4 bytes, and it requires the
-	    dma_alloc_coherent(mgr->dev.parent, count, &dma_addr, GFP_KERNEL);
+	 * starting addresses to be aligned to 64 bits (UG585 pg 212).
-	if (!kbuf)
+	 */
-		return -ENOMEM;
+	for_each_sg(sgt->sgl, sg, sgt->nents, i) {
+		if ((sg->offset % 8) || (sg->length % 4)) {
+			dev_err(&mgr->dev,
+			    "Invalid bitstream, chunks must be aligned\n");
+			return -EINVAL;
+		}
+	}
 
-	memcpy(kbuf, buf, count);
+	priv->dma_nelms =
+	    dma_map_sg(mgr->dev.parent, sgt->sgl, sgt->nents, DMA_TO_DEVICE);
+	if (priv->dma_nelms == 0) {
+		dev_err(&mgr->dev, "Unable to DMA map (TO_DEVICE)\n");
+		return -ENOMEM;
+	}
 
 	/* enable clock */
 	err = clk_enable(priv->clk);
@@ -308,38 +404,67 @@ static int zynq_fpga_ops_write(struct fpga_manager *mgr,
 		goto out_free;
 
 	zynq_fpga_write(priv, INT_STS_OFFSET, IXR_ALL_MASK);
-
 	reinit_completion(&priv->dma_done);
 
-	/* enable DMA and error IRQs */
+	/* zynq_step_dma will turn on interrupts */
-	zynq_fpga_unmask_irqs(priv);
+	spin_lock_irqsave(&priv->dma_lock, flags);
+	priv->dma_elm = 0;
+	priv->cur_sg = sgt->sgl;
+	zynq_step_dma(priv);
+	spin_unlock_irqrestore(&priv->dma_lock, flags);
 
-	/* the +1 in the src addr is used to hold off on DMA_DONE IRQ
+	timeout = wait_for_completion_timeout(&priv->dma_done,
-	 * until both AXI and PCAP are done ...
+					      msecs_to_jiffies(DMA_TIMEOUT_MS));
-	 */
-	zynq_fpga_write(priv, DMA_SRC_ADDR_OFFSET, (u32)(dma_addr) + 1);
-	zynq_fpga_write(priv, DMA_DST_ADDR_OFFSET, (u32)DMA_INVALID_ADDRESS);
 
-	/* convert #bytes to #words */
+	spin_lock_irqsave(&priv->dma_lock, flags);
-	transfer_length = (count + 3) / 4;
+	zynq_fpga_set_irq(priv, 0);
-
+	priv->cur_sg = NULL;
-	zynq_fpga_write(priv, DMA_SRC_LEN_OFFSET, transfer_length);
+	spin_unlock_irqrestore(&priv->dma_lock, flags);
-	zynq_fpga_write(priv, DMA_DEST_LEN_OFFSET, 0);
-
-	wait_for_completion(&priv->dma_done);
 
 	intr_status = zynq_fpga_read(priv, INT_STS_OFFSET);
-	zynq_fpga_write(priv, INT_STS_OFFSET, intr_status);
+	zynq_fpga_write(priv, INT_STS_OFFSET, IXR_ALL_MASK);
 
-	if (!((intr_status & IXR_D_P_DONE_MASK) == IXR_D_P_DONE_MASK)) {
+	/* There doesn't seem to be a way to force cancel any DMA, so if
-		dev_err(&mgr->dev, "Error configuring FPGA\n");
+	 * something went wrong we are relying on the hardware to have halted
-		err = -EFAULT;
+	 * the DMA before we get here, if there was we could use
+	 * wait_for_completion_interruptible too.
+	 */
+
+	if (intr_status & IXR_ERROR_FLAGS_MASK) {
+		why = "DMA reported error";
+		err = -EIO;
+		goto out_report;
 	}
 
+	if (priv->cur_sg ||
+	    !((intr_status & IXR_D_P_DONE_MASK) == IXR_D_P_DONE_MASK)) {
+		if (timeout == 0)
+			why = "DMA timed out";
+		else
+			why = "DMA did not complete";
+		err = -EIO;
+		goto out_report;
+	}
+
+	err = 0;
+	goto out_clk;
+
+out_report:
+	dev_err(&mgr->dev,
+		"%s: INT_STS:0x%x CTRL:0x%x LOCK:0x%x INT_MASK:0x%x STATUS:0x%x MCTRL:0x%x\n",
+		why,
+		intr_status,
+		zynq_fpga_read(priv, CTRL_OFFSET),
+		zynq_fpga_read(priv, LOCK_OFFSET),
+		zynq_fpga_read(priv, INT_MASK_OFFSET),
+		zynq_fpga_read(priv, STATUS_OFFSET),
+		zynq_fpga_read(priv, MCTRL_OFFSET));
+
+out_clk:
 	clk_disable(priv->clk);
 
 out_free:
-	dma_free_coherent(mgr->dev.parent, count, kbuf, dma_addr);
+	dma_unmap_sg(mgr->dev.parent, sgt->sgl, sgt->nents, DMA_TO_DEVICE);
 	return err;
 }
 
@@ -400,9 +525,10 @@ static enum fpga_mgr_states zynq_fpga_ops_state(struct fpga_manager *mgr)
 }
 
 static const struct fpga_manager_ops zynq_fpga_ops = {
+	.initial_header_size = 128,
 	.state = zynq_fpga_ops_state,
 	.write_init = zynq_fpga_ops_write_init,
-	.write = zynq_fpga_ops_write,
+	.write_sg = zynq_fpga_ops_write,
 	.write_complete = zynq_fpga_ops_write_complete,
 };
 
@@ -416,6 +542,7 @@ static int zynq_fpga_probe(struct platform_device *pdev)
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
+	spin_lock_init(&priv->dma_lock);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	priv->io_base = devm_ioremap_resource(dev, res);
@@ -452,7 +579,7 @@ static int zynq_fpga_probe(struct platform_device *pdev)
 	/* unlock the device */
 	zynq_fpga_write(priv, UNLOCK_OFFSET, UNLOCK_MASK);
 
-	zynq_fpga_write(priv, INT_MASK_OFFSET, 0xFFFFFFFF);
+	zynq_fpga_set_irq(priv, 0);
 	zynq_fpga_write(priv, INT_STS_OFFSET, IXR_ALL_MASK);
 	err = devm_request_irq(dev, priv->irq, zynq_fpga_isr, 0, dev_name(dev),
 			       priv);

drivers/fsi/Kconfig

@@ -0,0 +1,12 @@
+#
+# FSI subsystem
+#
+
+menu "FSI support"
+
+config FSI
+	tristate "FSI support"
+	---help---
+	  FSI - the FRU Support Interface - is a simple bus for low-level
+	  access to POWER-based hardware.
+endmenu

drivers/fsi/Makefile

@@ -0,0 +1,2 @@
+
+obj-$(CONFIG_FSI) += fsi-core.o

drivers/fsi/fsi-core.c

@@ -0,0 +1,59 @@
+/*
+ * FSI core driver
+ *
+ * Copyright (C) IBM Corporation 2016
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/device.h>
+#include <linux/fsi.h>
+#include <linux/module.h>
+
+/* FSI core & Linux bus type definitions */
+
+static int fsi_bus_match(struct device *dev, struct device_driver *drv)
+{
+	struct fsi_device *fsi_dev = to_fsi_dev(dev);
+	struct fsi_driver *fsi_drv = to_fsi_drv(drv);
+	const struct fsi_device_id *id;
+
+	if (!fsi_drv->id_table)
+		return 0;
+
+	for (id = fsi_drv->id_table; id->engine_type; id++) {
+		if (id->engine_type != fsi_dev->engine_type)
+			continue;
+		if (id->version == FSI_VERSION_ANY ||
+				id->version == fsi_dev->version)
+			return 1;
+	}
+
+	return 0;
+}
+
+struct bus_type fsi_bus_type = {
+	.name		= "fsi",
+	.match		= fsi_bus_match,
+};
+EXPORT_SYMBOL_GPL(fsi_bus_type);
+
+static int fsi_init(void)
+{
+	return bus_register(&fsi_bus_type);
+}
+
+static void fsi_exit(void)
+{
+	bus_unregister(&fsi_bus_type);
+}
+
+module_init(fsi_init);
+module_exit(fsi_exit);

drivers/hv/channel.c

@@ -47,12 +47,8 @@ void vmbus_setevent(struct vmbus_channel *channel)
 	 * For channels marked as in "low latency" mode
 	 * bypass the monitor page mechanism.
 	 */
-	if ((channel->offermsg.monitor_allocated) &&
+	if (channel->offermsg.monitor_allocated && !channel->low_latency) {
-	    (!channel->low_latency)) {
+		vmbus_send_interrupt(channel->offermsg.child_relid);
-		/* Each u32 represents 32 channels */
-		sync_set_bit(channel->offermsg.child_relid & 31,
-			(unsigned long *) vmbus_connection.send_int_page +
-			(channel->offermsg.child_relid >> 5));
 
 		/* Get the child to parent monitor page */
 		monitorpage = vmbus_connection.monitor_pages[1];
@@ -157,6 +153,7 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size,
 	}
 
 	init_completion(&open_info->waitevent);
+	open_info->waiting_channel = newchannel;
 
 	open_msg = (struct vmbus_channel_open_channel *)open_info->msg;
 	open_msg->header.msgtype = CHANNELMSG_OPENCHANNEL;
@@ -181,7 +178,7 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size,
 	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
 
 	ret = vmbus_post_msg(open_msg,
-			       sizeof(struct vmbus_channel_open_channel));
+			     sizeof(struct vmbus_channel_open_channel), true);
 
 	if (ret != 0) {
 		err = ret;
@@ -194,6 +191,11 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size,
 	list_del(&open_info->msglistentry);
 	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
 
+	if (newchannel->rescind) {
+		err = -ENODEV;
+		goto error_free_gpadl;
+	}
+
 	if (open_info->response.open_result.status) {
 		err = -EAGAIN;
 		goto error_free_gpadl;
@@ -233,7 +235,7 @@ int vmbus_send_tl_connect_request(const uuid_le *shv_guest_servie_id,
 	conn_msg.guest_endpoint_id = *shv_guest_servie_id;
 	conn_msg.host_service_id = *shv_host_servie_id;
 
-	return vmbus_post_msg(&conn_msg, sizeof(conn_msg));
+	return vmbus_post_msg(&conn_msg, sizeof(conn_msg), true);
 }
 EXPORT_SYMBOL_GPL(vmbus_send_tl_connect_request);
 
@@ -405,6 +407,7 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer,
 		return ret;
 
 	init_completion(&msginfo->waitevent);
+	msginfo->waiting_channel = channel;
 
 	gpadlmsg = (struct vmbus_channel_gpadl_header *)msginfo->msg;
 	gpadlmsg->header.msgtype = CHANNELMSG_GPADL_HEADER;
@@ -419,7 +422,7 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer,
 	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
 
 	ret = vmbus_post_msg(gpadlmsg, msginfo->msgsize -
-			       sizeof(*msginfo));
+			     sizeof(*msginfo), true);
 	if (ret != 0)
 		goto cleanup;
 
@@ -433,14 +436,19 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer,
 		gpadl_body->gpadl = next_gpadl_handle;
 
 		ret = vmbus_post_msg(gpadl_body,
-				     submsginfo->msgsize -
+				     submsginfo->msgsize - sizeof(*submsginfo),
-				     sizeof(*submsginfo));
+				     true);
 		if (ret != 0)
 			goto cleanup;
 
 	}
 	wait_for_completion(&msginfo->waitevent);
 
+	if (channel->rescind) {
+		ret = -ENODEV;
+		goto cleanup;
+	}
+
 	/* At this point, we received the gpadl created msg */
 	*gpadl_handle = gpadlmsg->gpadl;
 
@@ -474,6 +482,7 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle)
 		return -ENOMEM;
 
 	init_completion(&info->waitevent);
+	info->waiting_channel = channel;
 
 	msg = (struct vmbus_channel_gpadl_teardown *)info->msg;
 
@@ -485,14 +494,19 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle)
 	list_add_tail(&info->msglistentry,
 		      &vmbus_connection.chn_msg_list);
 	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
-	ret = vmbus_post_msg(msg,
+	ret = vmbus_post_msg(msg, sizeof(struct vmbus_channel_gpadl_teardown),
-			       sizeof(struct vmbus_channel_gpadl_teardown));
+			     true);
 
 	if (ret)
 		goto post_msg_err;
 
 	wait_for_completion(&info->waitevent);
 
+	if (channel->rescind) {
+		ret = -ENODEV;
+		goto post_msg_err;
+	}
+
 post_msg_err:
 	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
 	list_del(&info->msglistentry);
@@ -516,7 +530,7 @@ static int vmbus_close_internal(struct vmbus_channel *channel)
 	int ret;
 
 	/*
-	 * process_chn_event(), running in the tasklet, can race
+	 * vmbus_on_event(), running in the tasklet, can race
 	 * with vmbus_close_internal() in the case of SMP guest, e.g., when
 	 * the former is accessing channel->inbound.ring_buffer, the latter
 	 * could be freeing the ring_buffer pages.
@@ -557,7 +571,8 @@ static int vmbus_close_internal(struct vmbus_channel *channel)
 	msg->header.msgtype = CHANNELMSG_CLOSECHANNEL;
 	msg->child_relid = channel->offermsg.child_relid;
 
-	ret = vmbus_post_msg(msg, sizeof(struct vmbus_channel_close_channel));
+	ret = vmbus_post_msg(msg, sizeof(struct vmbus_channel_close_channel),
+			     true);
 
 	if (ret) {
 		pr_err("Close failed: close post msg return is %d\n", ret);
@@ -629,14 +644,13 @@ EXPORT_SYMBOL_GPL(vmbus_close);
 
 int vmbus_sendpacket_ctl(struct vmbus_channel *channel, void *buffer,
 			 u32 bufferlen, u64 requestid,
-			   enum vmbus_packet_type type, u32 flags, bool kick_q)
+			 enum vmbus_packet_type type, u32 flags)
 {
 	struct vmpacket_descriptor desc;
 	u32 packetlen = sizeof(struct vmpacket_descriptor) + bufferlen;
 	u32 packetlen_aligned = ALIGN(packetlen, sizeof(u64));
 	struct kvec bufferlist[3];
 	u64 aligned_data = 0;
-	bool lock = channel->acquire_ring_lock;
 	int num_vecs = ((bufferlen != 0) ? 3 : 1);
 
 
@@ -655,9 +669,7 @@ int vmbus_sendpacket_ctl(struct vmbus_channel *channel, void *buffer,
 	bufferlist[2].iov_base = &aligned_data;
 	bufferlist[2].iov_len = (packetlen_aligned - packetlen);
 
-	return hv_ringbuffer_write(channel, bufferlist, num_vecs,
+	return hv_ringbuffer_write(channel, bufferlist, num_vecs);
-				   lock, kick_q);
-
 }
 EXPORT_SYMBOL(vmbus_sendpacket_ctl);
 
@@ -680,7 +692,7 @@ int vmbus_sendpacket(struct vmbus_channel *channel, void *buffer,
 			   enum vmbus_packet_type type, u32 flags)
 {
 	return vmbus_sendpacket_ctl(channel, buffer, bufferlen, requestid,
-				    type, flags, true);
+				    type, flags);
 }
 EXPORT_SYMBOL(vmbus_sendpacket);
 
@@ -694,9 +706,7 @@ EXPORT_SYMBOL(vmbus_sendpacket);
 int vmbus_sendpacket_pagebuffer_ctl(struct vmbus_channel *channel,
 				    struct hv_page_buffer pagebuffers[],
 				    u32 pagecount, void *buffer, u32 bufferlen,
-				     u64 requestid,
+				    u64 requestid, u32 flags)
-				     u32 flags,
-				     bool kick_q)
 {
 	int i;
 	struct vmbus_channel_packet_page_buffer desc;
@@ -705,12 +715,10 @@ int vmbus_sendpacket_pagebuffer_ctl(struct vmbus_channel *channel,
 	u32 packetlen_aligned;
 	struct kvec bufferlist[3];
 	u64 aligned_data = 0;
-	bool lock = channel->acquire_ring_lock;
 
 	if (pagecount > MAX_PAGE_BUFFER_COUNT)
 		return -EINVAL;
 
-
 	/*
 	 * Adjust the size down since vmbus_channel_packet_page_buffer is the
 	 * largest size we support
@@ -742,8 +750,7 @@ int vmbus_sendpacket_pagebuffer_ctl(struct vmbus_channel *channel,
 	bufferlist[2].iov_base = &aligned_data;
 	bufferlist[2].iov_len = (packetlen_aligned - packetlen);
 
-	return hv_ringbuffer_write(channel, bufferlist, 3,
+	return hv_ringbuffer_write(channel, bufferlist, 3);
-				   lock, kick_q);
 }
 EXPORT_SYMBOL_GPL(vmbus_sendpacket_pagebuffer_ctl);
 
@@ -757,9 +764,10 @@ int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel,
 				     u64 requestid)
 {
 	u32 flags = VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED;
+
 	return vmbus_sendpacket_pagebuffer_ctl(channel, pagebuffers, pagecount,
-					       buffer, bufferlen, requestid,
+					       buffer, bufferlen,
-					       flags, true);
+					       requestid, flags);
 
 }
 EXPORT_SYMBOL_GPL(vmbus_sendpacket_pagebuffer);
@@ -778,7 +786,6 @@ int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel,
 	u32 packetlen_aligned;
 	struct kvec bufferlist[3];
 	u64 aligned_data = 0;
-	bool lock = channel->acquire_ring_lock;
 
 	packetlen = desc_size + bufferlen;
 	packetlen_aligned = ALIGN(packetlen, sizeof(u64));
@@ -798,8 +805,7 @@ int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel,
 	bufferlist[2].iov_base = &aligned_data;
 	bufferlist[2].iov_len = (packetlen_aligned - packetlen);
 
-	return hv_ringbuffer_write(channel, bufferlist, 3,
+	return hv_ringbuffer_write(channel, bufferlist, 3);
-				   lock, true);
 }
 EXPORT_SYMBOL_GPL(vmbus_sendpacket_mpb_desc);
 
@@ -817,7 +823,6 @@ int vmbus_sendpacket_multipagebuffer(struct vmbus_channel *channel,
 	u32 packetlen_aligned;
 	struct kvec bufferlist[3];
 	u64 aligned_data = 0;
-	bool lock = channel->acquire_ring_lock;
 	u32 pfncount = NUM_PAGES_SPANNED(multi_pagebuffer->offset,
 					 multi_pagebuffer->len);
 
@@ -856,8 +861,7 @@ int vmbus_sendpacket_multipagebuffer(struct vmbus_channel *channel,
 	bufferlist[2].iov_base = &aligned_data;
 	bufferlist[2].iov_len = (packetlen_aligned - packetlen);
 
-	return hv_ringbuffer_write(channel, bufferlist, 3,
+	return hv_ringbuffer_write(channel, bufferlist, 3);
-				   lock, true);
 }
 EXPORT_SYMBOL_GPL(vmbus_sendpacket_multipagebuffer);
 

drivers/hv/channel_mgmt.c

@@ -31,6 +31,7 @@
 #include <linux/completion.h>
 #include <linux/delay.h>
 #include <linux/hyperv.h>
+#include <asm/mshyperv.h>
 
 #include "hyperv_vmbus.h"
 
@@ -147,6 +148,29 @@ static const struct {
 	{ HV_RDV_GUID	},
 };
 
+/*
+ * The rescinded channel may be blocked waiting for a response from the host;
+ * take care of that.
+ */
+static void vmbus_rescind_cleanup(struct vmbus_channel *channel)
+{
+	struct vmbus_channel_msginfo *msginfo;
+	unsigned long flags;
+
+
+	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
+
+	list_for_each_entry(msginfo, &vmbus_connection.chn_msg_list,
+				msglistentry) {
+
+		if (msginfo->waiting_channel == channel) {
+			complete(&msginfo->waitevent);
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
+}
+
 static bool is_unsupported_vmbus_devs(const uuid_le *guid)
 {
 	int i;
@@ -180,33 +204,34 @@ static u16 hv_get_dev_type(const struct vmbus_channel *channel)
  * @buf: Raw buffer channel data
  *
  * @icmsghdrp is of type &struct icmsg_hdr.
- * @negop is of type &struct icmsg_negotiate.
  * Set up and fill in default negotiate response message.
  *
- * The fw_version specifies the  framework version that
+ * The fw_version and fw_vercnt specifies the framework version that
- * we can support and srv_version specifies the service
+ * we can support.
- * version we can support.
+ *
+ * The srv_version and srv_vercnt specifies the service
+ * versions we can support.
+ *
+ * Versions are given in decreasing order.
+ *
+ * nego_fw_version and nego_srv_version store the selected protocol versions.
  *
  * Mainly used by Hyper-V drivers.
  */
 bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp,
-				struct icmsg_negotiate *negop, u8 *buf,
+				u8 *buf, const int *fw_version, int fw_vercnt,
-				int fw_version, int srv_version)
+				const int *srv_version, int srv_vercnt,
+				int *nego_fw_version, int *nego_srv_version)
 {
 	int icframe_major, icframe_minor;
 	int icmsg_major, icmsg_minor;
 	int fw_major, fw_minor;
 	int srv_major, srv_minor;
-	int i;
+	int i, j;
 	bool found_match = false;
+	struct icmsg_negotiate *negop;
 
 	icmsghdrp->icmsgsize = 0x10;
-	fw_major = (fw_version >> 16);
-	fw_minor = (fw_version & 0xFFFF);
-
-	srv_major = (srv_version >> 16);
-	srv_minor = (srv_version & 0xFFFF);
-
 	negop = (struct icmsg_negotiate *)&buf[
 		sizeof(struct vmbuspipe_hdr) +
 		sizeof(struct icmsg_hdr)];
@@ -222,30 +247,51 @@ bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp,
 	 * support.
 	 */
 
-	for (i = 0; i < negop->icframe_vercnt; i++) {
+	for (i = 0; i < fw_vercnt; i++) {
-		if ((negop->icversion_data[i].major == fw_major) &&
+		fw_major = (fw_version[i] >> 16);
-		   (negop->icversion_data[i].minor == fw_minor)) {
+		fw_minor = (fw_version[i] & 0xFFFF);
-			icframe_major = negop->icversion_data[i].major;
+
-			icframe_minor = negop->icversion_data[i].minor;
+		for (j = 0; j < negop->icframe_vercnt; j++) {
+			if ((negop->icversion_data[j].major == fw_major) &&
+			    (negop->icversion_data[j].minor == fw_minor)) {
+				icframe_major = negop->icversion_data[j].major;
+				icframe_minor = negop->icversion_data[j].minor;
 				found_match = true;
+				break;
 			}
 		}
 
+		if (found_match)
+			break;
+	}
+
 	if (!found_match)
 		goto fw_error;
 
 	found_match = false;
 
-	for (i = negop->icframe_vercnt;
+	for (i = 0; i < srv_vercnt; i++) {
-		 (i < negop->icframe_vercnt + negop->icmsg_vercnt); i++) {
+		srv_major = (srv_version[i] >> 16);
-		if ((negop->icversion_data[i].major == srv_major) &&
+		srv_minor = (srv_version[i] & 0xFFFF);
-		   (negop->icversion_data[i].minor == srv_minor)) {
+
-			icmsg_major = negop->icversion_data[i].major;
+		for (j = negop->icframe_vercnt;
-			icmsg_minor = negop->icversion_data[i].minor;
+			(j < negop->icframe_vercnt + negop->icmsg_vercnt);
+			j++) {
+
+			if ((negop->icversion_data[j].major == srv_major) &&
+				(negop->icversion_data[j].minor == srv_minor)) {
+
+				icmsg_major = negop->icversion_data[j].major;
+				icmsg_minor = negop->icversion_data[j].minor;
 				found_match = true;
+				break;
 			}
 		}
 
+		if (found_match)
+			break;
+	}
+
 	/*
 	 * Respond with the framework and service
 	 * version numbers we can support.
@@ -260,6 +306,12 @@ bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp,
 		negop->icmsg_vercnt = 1;
 	}
 
+	if (nego_fw_version)
+		*nego_fw_version = (icframe_major << 16) | icframe_minor;
+
+	if (nego_srv_version)
+		*nego_srv_version = (icmsg_major << 16) | icmsg_minor;
+
 	negop->icversion_data[0].major = icframe_major;
 	negop->icversion_data[0].minor = icframe_minor;
 	negop->icversion_data[1].major = icmsg_major;
@@ -280,13 +332,15 @@ static struct vmbus_channel *alloc_channel(void)
 	if (!channel)
 		return NULL;
 
-	channel->acquire_ring_lock = true;
 	spin_lock_init(&channel->inbound_lock);
 	spin_lock_init(&channel->lock);
 
 	INIT_LIST_HEAD(&channel->sc_list);
 	INIT_LIST_HEAD(&channel->percpu_list);
 
+	tasklet_init(&channel->callback_event,
+		     vmbus_on_event, (unsigned long)channel);
+
 	return channel;
 }
 
@@ -295,15 +349,17 @@ static struct vmbus_channel *alloc_channel(void)
  */
 static void free_channel(struct vmbus_channel *channel)
 {
+	tasklet_kill(&channel->callback_event);
 	kfree(channel);
 }
 
 static void percpu_channel_enq(void *arg)
 {
 	struct vmbus_channel *channel = arg;
-	int cpu = smp_processor_id();
+	struct hv_per_cpu_context *hv_cpu
+		= this_cpu_ptr(hv_context.cpu_context);
 
-	list_add_tail(&channel->percpu_list, &hv_context.percpu_list[cpu]);
+	list_add_tail(&channel->percpu_list, &hv_cpu->chan_list);
 }
 
 static void percpu_channel_deq(void *arg)
@@ -321,24 +377,21 @@ static void vmbus_release_relid(u32 relid)
 	memset(&msg, 0, sizeof(struct vmbus_channel_relid_released));
 	msg.child_relid = relid;
 	msg.header.msgtype = CHANNELMSG_RELID_RELEASED;
-	vmbus_post_msg(&msg, sizeof(struct vmbus_channel_relid_released));
+	vmbus_post_msg(&msg, sizeof(struct vmbus_channel_relid_released),
+		       true);
 }
 
 void hv_event_tasklet_disable(struct vmbus_channel *channel)
 {
-	struct tasklet_struct *tasklet;
+	tasklet_disable(&channel->callback_event);
-	tasklet = hv_context.event_dpc[channel->target_cpu];
-	tasklet_disable(tasklet);
 }
 
 void hv_event_tasklet_enable(struct vmbus_channel *channel)
 {
-	struct tasklet_struct *tasklet;
+	tasklet_enable(&channel->callback_event);
-	tasklet = hv_context.event_dpc[channel->target_cpu];
-	tasklet_enable(tasklet);
 
 	/* In case there is any pending event */
-	tasklet_schedule(tasklet);
+	tasklet_schedule(&channel->callback_event);
 }
 
 void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid)
@@ -673,9 +726,12 @@ static void vmbus_wait_for_unload(void)
 			break;
 
 		for_each_online_cpu(cpu) {
-			page_addr = hv_context.synic_message_page[cpu];
+			struct hv_per_cpu_context *hv_cpu
-			msg = (struct hv_message *)page_addr +
+				= per_cpu_ptr(hv_context.cpu_context, cpu);
-				VMBUS_MESSAGE_SINT;
+
+			page_addr = hv_cpu->synic_message_page;
+			msg = (struct hv_message *)page_addr
+				+ VMBUS_MESSAGE_SINT;
 
 			message_type = READ_ONCE(msg->header.message_type);
 			if (message_type == HVMSG_NONE)
@@ -699,7 +755,10 @@ static void vmbus_wait_for_unload(void)
 	 * messages after we reconnect.
 	 */
 	for_each_online_cpu(cpu) {
-		page_addr = hv_context.synic_message_page[cpu];
+		struct hv_per_cpu_context *hv_cpu
+			= per_cpu_ptr(hv_context.cpu_context, cpu);
+
+		page_addr = hv_cpu->synic_message_page;
 		msg = (struct hv_message *)page_addr + VMBUS_MESSAGE_SINT;
 		msg->header.message_type = HVMSG_NONE;
 	}
@@ -728,7 +787,8 @@ void vmbus_initiate_unload(bool crash)
 	init_completion(&vmbus_connection.unload_event);
 	memset(&hdr, 0, sizeof(struct vmbus_channel_message_header));
 	hdr.msgtype = CHANNELMSG_UNLOAD;
-	vmbus_post_msg(&hdr, sizeof(struct vmbus_channel_message_header));
+	vmbus_post_msg(&hdr, sizeof(struct vmbus_channel_message_header),
+		       !crash);
 
 	/*
 	 * vmbus_initiate_unload() is also called on crash and the crash can be
@@ -758,13 +818,6 @@ static void vmbus_onoffer(struct vmbus_channel_message_header *hdr)
 		return;
 	}
 
-	/*
-	 * By default we setup state to enable batched
-	 * reading. A specific service can choose to
-	 * disable this prior to opening the channel.
-	 */
-	newchannel->batched_reading = true;
-
 	/*
 	 * Setup state for signalling the host.
 	 */
@@ -823,6 +876,8 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr)
 	channel->rescind = true;
 	spin_unlock_irqrestore(&channel->lock, flags);
 
+	vmbus_rescind_cleanup(channel);
+
 	if (channel->device_obj) {
 		if (channel->chn_rescind_callback) {
 			channel->chn_rescind_callback(channel);
@@ -1116,8 +1171,8 @@ int vmbus_request_offers(void)
 	msg->msgtype = CHANNELMSG_REQUESTOFFERS;
 
 
-	ret = vmbus_post_msg(msg,
+	ret = vmbus_post_msg(msg, sizeof(struct vmbus_channel_message_header),
-			       sizeof(struct vmbus_channel_message_header));
+			     true);
 	if (ret != 0) {
 		pr_err("Unable to request offers - %d\n", ret);
 

drivers/hv/connection.c

@@ -93,12 +93,10 @@ static int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo,
 	 * all the CPUs. This is needed for kexec to work correctly where
 	 * the CPU attempting to connect may not be CPU 0.
 	 */
-	if (version >= VERSION_WIN8_1) {
+	if (version >= VERSION_WIN8_1)
-		msg->target_vcpu = hv_context.vp_index[get_cpu()];
+		msg->target_vcpu = hv_context.vp_index[smp_processor_id()];
-		put_cpu();
+	else
-	} else {
 		msg->target_vcpu = 0;
-	}
 
 	/*
 	 * Add to list before we send the request since we may
@@ -111,7 +109,8 @@ static int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo,
 	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
 
 	ret = vmbus_post_msg(msg,
-			       sizeof(struct vmbus_channel_initiate_contact));
+			     sizeof(struct vmbus_channel_initiate_contact),
+			     true);
 	if (ret != 0) {
 		spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
 		list_del(&msginfo->msglistentry);
@@ -220,10 +219,7 @@ int vmbus_connect(void)
 		goto cleanup;
 
 	vmbus_proto_version = version;
-	pr_info("Hyper-V Host Build:%d-%d.%d-%d-%d.%d; Vmbus version:%d.%d\n",
+	pr_info("Vmbus version:%d.%d\n",
-		    host_info_eax, host_info_ebx >> 16,
-		    host_info_ebx & 0xFFFF, host_info_ecx,
-		    host_info_edx >> 24, host_info_edx & 0xFFFFFF,
 		version >> 16, version & 0xFFFF);
 
 	kfree(msginfo);
@@ -263,29 +259,6 @@ void vmbus_disconnect(void)
 	vmbus_connection.monitor_pages[1] = NULL;
 }
 
-/*
- * Map the given relid to the corresponding channel based on the
- * per-cpu list of channels that have been affinitized to this CPU.
- * This will be used in the channel callback path as we can do this
- * mapping in a lock-free fashion.
- */
-static struct vmbus_channel *pcpu_relid2channel(u32 relid)
-{
-	struct vmbus_channel *channel;
-	struct vmbus_channel *found_channel  = NULL;
-	int cpu = smp_processor_id();
-	struct list_head *pcpu_head = &hv_context.percpu_list[cpu];
-
-	list_for_each_entry(channel, pcpu_head, percpu_list) {
-		if (channel->offermsg.child_relid == relid) {
-			found_channel = channel;
-			break;
-		}
-	}
-
-	return found_channel;
-}
-
 /*
  * relid2channel - Get the channel object given its
  * child relative id (ie channel id)
@@ -322,23 +295,12 @@ struct vmbus_channel *relid2channel(u32 relid)
 }
 
 /*
- * process_chn_event - Process a channel event notification
+ * vmbus_on_event - Process a channel event notification
  */
-static void process_chn_event(u32 relid)
+void vmbus_on_event(unsigned long data)
 {
-	struct vmbus_channel *channel;
+	struct vmbus_channel *channel = (void *) data;
-	void *arg;
+	void (*callback_fn)(void *);
-	bool read_state;
-	u32 bytes_to_read;
-
-	/*
-	 * Find the channel based on this relid and invokes the
-	 * channel callback to process the event
-	 */
-	channel = pcpu_relid2channel(relid);
-
-	if (!channel)
-		return;
 
 	/*
 	 * A channel once created is persistent even when there
@@ -348,10 +310,13 @@ static void process_chn_event(u32 relid)
 	 * Thus, checking and invoking the driver specific callback takes
 	 * care of orderly unloading of the driver.
 	 */
+	callback_fn = READ_ONCE(channel->onchannel_callback);
+	if (unlikely(callback_fn == NULL))
+		return;
 
-	if (channel->onchannel_callback != NULL) {
+	(*callback_fn)(channel->channel_callback_context);
-		arg = channel->channel_callback_context;
+
-		read_state = channel->batched_reading;
+	if (channel->callback_mode == HV_CALL_BATCHED) {
 		/*
 		 * This callback reads the messages sent by the host.
 		 * We can optimize host to guest signaling by ensuring:
@@ -363,71 +328,10 @@ static void process_chn_event(u32 relid)
 		 *    state is set we check to see if additional packets are
 		 *    available to read. In this case we repeat the process.
 		 */
-
+		if (hv_end_read(&channel->inbound) != 0) {
-		do {
-			if (read_state)
 			hv_begin_read(&channel->inbound);
-			channel->onchannel_callback(arg);
-			if (read_state)
-				bytes_to_read = hv_end_read(&channel->inbound);
-			else
-				bytes_to_read = 0;
-		} while (read_state && (bytes_to_read != 0));
-	}
-}
 
-/*
+			tasklet_schedule(&channel->callback_event);
- * vmbus_on_event - Handler for events
- */
-void vmbus_on_event(unsigned long data)
-{
-	u32 dword;
-	u32 maxdword;
-	int bit;
-	u32 relid;
-	u32 *recv_int_page = NULL;
-	void *page_addr;
-	int cpu = smp_processor_id();
-	union hv_synic_event_flags *event;
-
-	if (vmbus_proto_version < VERSION_WIN8) {
-		maxdword = MAX_NUM_CHANNELS_SUPPORTED >> 5;
-		recv_int_page = vmbus_connection.recv_int_page;
-	} else {
-		/*
-		 * When the host is win8 and beyond, the event page
-		 * can be directly checked to get the id of the channel
-		 * that has the interrupt pending.
-		 */
-		maxdword = HV_EVENT_FLAGS_DWORD_COUNT;
-		page_addr = hv_context.synic_event_page[cpu];
-		event = (union hv_synic_event_flags *)page_addr +
-						 VMBUS_MESSAGE_SINT;
-		recv_int_page = event->flags32;
-	}
-
-
-
-	/* Check events */
-	if (!recv_int_page)
-		return;
-	for (dword = 0; dword < maxdword; dword++) {
-		if (!recv_int_page[dword])
-			continue;
-		for (bit = 0; bit < 32; bit++) {
-			if (sync_test_and_clear_bit(bit,
-				(unsigned long *)&recv_int_page[dword])) {
-				relid = (dword << 5) + bit;
-
-				if (relid == 0)
-					/*
-					 * Special case - vmbus
-					 * channel protocol msg
-					 */
-					continue;
-
-				process_chn_event(relid);
-			}
 		}
 	}
 }
@@ -435,7 +339,7 @@ void vmbus_on_event(unsigned long data)
 /*
  * vmbus_post_msg - Send a msg on the vmbus's message connection
  */
-int vmbus_post_msg(void *buffer, size_t buflen)
+int vmbus_post_msg(void *buffer, size_t buflen, bool can_sleep)
 {
 	union hv_connection_id conn_id;
 	int ret = 0;
@@ -450,7 +354,7 @@ int vmbus_post_msg(void *buffer, size_t buflen)
 	 * insufficient resources. Retry the operation a couple of
 	 * times before giving up.
 	 */
-	while (retries < 20) {
+	while (retries < 100) {
 		ret = hv_post_message(conn_id, 1, buffer, buflen);
 
 		switch (ret) {
@@ -473,8 +377,14 @@ int vmbus_post_msg(void *buffer, size_t buflen)
 		}
 
 		retries++;
+		if (can_sleep && usec > 1000)
+			msleep(usec / 1000);
+		else if (usec < MAX_UDELAY_MS * 1000)
 			udelay(usec);
-		if (usec < 2048)
+		else
+			mdelay(usec / 1000);
+
+		if (usec < 256000)
 			usec *= 2;
 	}
 	return ret;
@@ -487,12 +397,8 @@ void vmbus_set_event(struct vmbus_channel *channel)
 {
 	u32 child_relid = channel->offermsg.child_relid;
 
-	if (!channel->is_dedicated_interrupt) {
+	if (!channel->is_dedicated_interrupt)
-		/* Each u32 represents 32 channels */
+		vmbus_send_interrupt(child_relid);
-		sync_set_bit(child_relid & 31,
-			(unsigned long *)vmbus_connection.send_int_page +
-			(child_relid >> 5));
-	}
 
 	hv_do_hypercall(HVCALL_SIGNAL_EVENT, channel->sig_event, NULL);
 }

drivers/hv/hv.c

@@ -36,154 +36,12 @@
 /* The one and only */
 struct hv_context hv_context = {
 	.synic_initialized	= false,
-	.hypercall_page		= NULL,
 };
 
 #define HV_TIMER_FREQUENCY (10 * 1000 * 1000) /* 100ns period */
 #define HV_MAX_MAX_DELTA_TICKS 0xffffffff
 #define HV_MIN_DELTA_TICKS 1
 
-/*
- * query_hypervisor_info - Get version info of the windows hypervisor
- */
-unsigned int host_info_eax;
-unsigned int host_info_ebx;
-unsigned int host_info_ecx;
-unsigned int host_info_edx;
-
-static int query_hypervisor_info(void)
-{
-	unsigned int eax;
-	unsigned int ebx;
-	unsigned int ecx;
-	unsigned int edx;
-	unsigned int max_leaf;
-	unsigned int op;
-
-	/*
-	* Its assumed that this is called after confirming that Viridian
-	* is present. Query id and revision.
-	*/
-	eax = 0;
-	ebx = 0;
-	ecx = 0;
-	edx = 0;
-	op = HVCPUID_VENDOR_MAXFUNCTION;
-	cpuid(op, &eax, &ebx, &ecx, &edx);
-
-	max_leaf = eax;
-
-	if (max_leaf >= HVCPUID_VERSION) {
-		eax = 0;
-		ebx = 0;
-		ecx = 0;
-		edx = 0;
-		op = HVCPUID_VERSION;
-		cpuid(op, &eax, &ebx, &ecx, &edx);
-		host_info_eax = eax;
-		host_info_ebx = ebx;
-		host_info_ecx = ecx;
-		host_info_edx = edx;
-	}
-	return max_leaf;
-}
-
-/*
- * hv_do_hypercall- Invoke the specified hypercall
- */
-u64 hv_do_hypercall(u64 control, void *input, void *output)
-{
-	u64 input_address = (input) ? virt_to_phys(input) : 0;
-	u64 output_address = (output) ? virt_to_phys(output) : 0;
-	void *hypercall_page = hv_context.hypercall_page;
-#ifdef CONFIG_X86_64
-	u64 hv_status = 0;
-
-	if (!hypercall_page)
-		return (u64)ULLONG_MAX;
-
-	__asm__ __volatile__("mov %0, %%r8" : : "r" (output_address) : "r8");
-	__asm__ __volatile__("call *%3" : "=a" (hv_status) :
-			     "c" (control), "d" (input_address),
-			     "m" (hypercall_page));
-
-	return hv_status;
-
-#else
-
-	u32 control_hi = control >> 32;
-	u32 control_lo = control & 0xFFFFFFFF;
-	u32 hv_status_hi = 1;
-	u32 hv_status_lo = 1;
-	u32 input_address_hi = input_address >> 32;
-	u32 input_address_lo = input_address & 0xFFFFFFFF;
-	u32 output_address_hi = output_address >> 32;
-	u32 output_address_lo = output_address & 0xFFFFFFFF;
-
-	if (!hypercall_page)
-		return (u64)ULLONG_MAX;
-
-	__asm__ __volatile__ ("call *%8" : "=d"(hv_status_hi),
-			      "=a"(hv_status_lo) : "d" (control_hi),
-			      "a" (control_lo), "b" (input_address_hi),
-			      "c" (input_address_lo), "D"(output_address_hi),
-			      "S"(output_address_lo), "m" (hypercall_page));
-
-	return hv_status_lo | ((u64)hv_status_hi << 32);
-#endif /* !x86_64 */
-}
-EXPORT_SYMBOL_GPL(hv_do_hypercall);
-
-#ifdef CONFIG_X86_64
-static u64 read_hv_clock_tsc(struct clocksource *arg)
-{
-	u64 current_tick;
-	struct ms_hyperv_tsc_page *tsc_pg = hv_context.tsc_page;
-
-	if (tsc_pg->tsc_sequence != 0) {
-		/*
-		 * Use the tsc page to compute the value.
-		 */
-
-		while (1) {
-			u64 tmp;
-			u32 sequence = tsc_pg->tsc_sequence;
-			u64 cur_tsc;
-			u64 scale = tsc_pg->tsc_scale;
-			s64 offset = tsc_pg->tsc_offset;
-
-			rdtscll(cur_tsc);
-			/* current_tick = ((cur_tsc *scale) >> 64) + offset */
-			asm("mulq %3"
-				: "=d" (current_tick), "=a" (tmp)
-				: "a" (cur_tsc), "r" (scale));
-
-			current_tick += offset;
-			if (tsc_pg->tsc_sequence == sequence)
-				return current_tick;
-
-			if (tsc_pg->tsc_sequence != 0)
-				continue;
-			/*
-			 * Fallback using MSR method.
-			 */
-			break;
-		}
-	}
-	rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick);
-	return current_tick;
-}
-
-static struct clocksource hyperv_cs_tsc = {
-		.name           = "hyperv_clocksource_tsc_page",
-		.rating         = 425,
-		.read           = read_hv_clock_tsc,
-		.mask           = CLOCKSOURCE_MASK(64),
-		.flags          = CLOCK_SOURCE_IS_CONTINUOUS,
-};
-#endif
-
-
 /*
  * hv_init - Main initialization routine.
  *
@@ -191,129 +49,14 @@ static struct clocksource hyperv_cs_tsc = {
  */
 int hv_init(void)
 {
-	int max_leaf;
+	if (!hv_is_hypercall_page_setup())
-	union hv_x64_msr_hypercall_contents hypercall_msr;
-	void *virtaddr = NULL;
-
-	memset(hv_context.synic_event_page, 0, sizeof(void *) * NR_CPUS);
-	memset(hv_context.synic_message_page, 0,
-	       sizeof(void *) * NR_CPUS);
-	memset(hv_context.post_msg_page, 0,
-	       sizeof(void *) * NR_CPUS);
-	memset(hv_context.vp_index, 0,
-	       sizeof(int) * NR_CPUS);
-	memset(hv_context.event_dpc, 0,
-	       sizeof(void *) * NR_CPUS);
-	memset(hv_context.msg_dpc, 0,
-	       sizeof(void *) * NR_CPUS);
-	memset(hv_context.clk_evt, 0,
-	       sizeof(void *) * NR_CPUS);
-
-	max_leaf = query_hypervisor_info();
-
-	/*
-	 * Write our OS ID.
-	 */
-	hv_context.guestid = generate_guest_id(0, LINUX_VERSION_CODE, 0);
-	wrmsrl(HV_X64_MSR_GUEST_OS_ID, hv_context.guestid);
-
-	/* See if the hypercall page is already set */
-	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
-
-	virtaddr = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL_EXEC);
-
-	if (!virtaddr)
-		goto cleanup;
-
-	hypercall_msr.enable = 1;
-
-	hypercall_msr.guest_physical_address = vmalloc_to_pfn(virtaddr);
-	wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
-
-	/* Confirm that hypercall page did get setup. */
-	hypercall_msr.as_uint64 = 0;
-	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
-
-	if (!hypercall_msr.enable)
-		goto cleanup;
-
-	hv_context.hypercall_page = virtaddr;
-
-#ifdef CONFIG_X86_64
-	if (ms_hyperv.features & HV_X64_MSR_REFERENCE_TSC_AVAILABLE) {
-		union hv_x64_msr_hypercall_contents tsc_msr;
-		void *va_tsc;
-
-		va_tsc = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL);
-		if (!va_tsc)
-			goto cleanup;
-		hv_context.tsc_page = va_tsc;
-
-		rdmsrl(HV_X64_MSR_REFERENCE_TSC, tsc_msr.as_uint64);
-
-		tsc_msr.enable = 1;
-		tsc_msr.guest_physical_address = vmalloc_to_pfn(va_tsc);
-
-		wrmsrl(HV_X64_MSR_REFERENCE_TSC, tsc_msr.as_uint64);
-		clocksource_register_hz(&hyperv_cs_tsc, NSEC_PER_SEC/100);
-	}
-#endif
-	return 0;
-
-cleanup:
-	if (virtaddr) {
-		if (hypercall_msr.enable) {
-			hypercall_msr.as_uint64 = 0;
-			wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
-		}
-
-		vfree(virtaddr);
-	}
-
 		return -ENOTSUPP;
-}
 
-/*
+	hv_context.cpu_context = alloc_percpu(struct hv_per_cpu_context);
- * hv_cleanup - Cleanup routine.
+	if (!hv_context.cpu_context)
- *
+		return -ENOMEM;
- * This routine is called normally during driver unloading or exiting.
- */
-void hv_cleanup(bool crash)
-{
-	union hv_x64_msr_hypercall_contents hypercall_msr;
 
-	/* Reset our OS id */
+	return 0;
-	wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
-
-	if (hv_context.hypercall_page) {
-		hypercall_msr.as_uint64 = 0;
-		wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
-		if (!crash)
-			vfree(hv_context.hypercall_page);
-		hv_context.hypercall_page = NULL;
-	}
-
-#ifdef CONFIG_X86_64
-	/*
-	 * Cleanup the TSC page based CS.
-	 */
-	if (ms_hyperv.features & HV_X64_MSR_REFERENCE_TSC_AVAILABLE) {
-		/*
-		 * Crash can happen in an interrupt context and unregistering
-		 * a clocksource is impossible and redundant in this case.
-		 */
-		if (!oops_in_progress) {
-			clocksource_change_rating(&hyperv_cs_tsc, 10);
-			clocksource_unregister(&hyperv_cs_tsc);
-		}
-
-		hypercall_msr.as_uint64 = 0;
-		wrmsrl(HV_X64_MSR_REFERENCE_TSC, hypercall_msr.as_uint64);
-		if (!crash)
-			vfree(hv_context.tsc_page);
-		hv_context.tsc_page = NULL;
-	}
-#endif
 }
 
 /*
@@ -325,25 +68,24 @@ int hv_post_message(union hv_connection_id connection_id,
 		  enum hv_message_type message_type,
 		  void *payload, size_t payload_size)
 {
-
 	struct hv_input_post_message *aligned_msg;
+	struct hv_per_cpu_context *hv_cpu;
 	u64 status;
 
 	if (payload_size > HV_MESSAGE_PAYLOAD_BYTE_COUNT)
 		return -EMSGSIZE;
 
-	aligned_msg = (struct hv_input_post_message *)
+	hv_cpu = get_cpu_ptr(hv_context.cpu_context);
-			hv_context.post_msg_page[get_cpu()];
+	aligned_msg = hv_cpu->post_msg_page;
-
 	aligned_msg->connectionid = connection_id;
 	aligned_msg->reserved = 0;
 	aligned_msg->message_type = message_type;
 	aligned_msg->payload_size = payload_size;
 	memcpy((void *)aligned_msg->payload, payload, payload_size);
+	put_cpu_ptr(hv_cpu);
 
 	status = hv_do_hypercall(HVCALL_POST_MESSAGE, aligned_msg, NULL);
 
-	put_cpu();
 	return status & 0xFFFF;
 }
 
@@ -354,16 +96,16 @@ static int hv_ce_set_next_event(unsigned long delta,
 
 	WARN_ON(!clockevent_state_oneshot(evt));
 
-	rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick);
+	hv_get_current_tick(current_tick);
 	current_tick += delta;
-	wrmsrl(HV_X64_MSR_STIMER0_COUNT, current_tick);
+	hv_init_timer(HV_X64_MSR_STIMER0_COUNT, current_tick);
 	return 0;
 }
 
 static int hv_ce_shutdown(struct clock_event_device *evt)
 {
-	wrmsrl(HV_X64_MSR_STIMER0_COUNT, 0);
+	hv_init_timer(HV_X64_MSR_STIMER0_COUNT, 0);
-	wrmsrl(HV_X64_MSR_STIMER0_CONFIG, 0);
+	hv_init_timer_config(HV_X64_MSR_STIMER0_CONFIG, 0);
 
 	return 0;
 }
@@ -375,7 +117,7 @@ static int hv_ce_set_oneshot(struct clock_event_device *evt)
 	timer_cfg.enable = 1;
 	timer_cfg.auto_enable = 1;
 	timer_cfg.sintx = VMBUS_MESSAGE_SINT;
-	wrmsrl(HV_X64_MSR_STIMER0_CONFIG, timer_cfg.as_uint64);
+	hv_init_timer_config(HV_X64_MSR_STIMER0_CONFIG, timer_cfg.as_uint64);
 
 	return 0;
 }
@@ -400,8 +142,6 @@ static void hv_init_clockevent_device(struct clock_event_device *dev, int cpu)
 
 int hv_synic_alloc(void)
 {
-	size_t size = sizeof(struct tasklet_struct);
-	size_t ced_size = sizeof(struct clock_event_device);
 	int cpu;
 
 	hv_context.hv_numa_map = kzalloc(sizeof(struct cpumask) * nr_node_ids,
@@ -411,52 +151,42 @@ int hv_synic_alloc(void)
 		goto err;
 	}
 
-	for_each_online_cpu(cpu) {
+	for_each_present_cpu(cpu) {
-		hv_context.event_dpc[cpu] = kmalloc(size, GFP_ATOMIC);
+		struct hv_per_cpu_context *hv_cpu
-		if (hv_context.event_dpc[cpu] == NULL) {
+			= per_cpu_ptr(hv_context.cpu_context, cpu);
-			pr_err("Unable to allocate event dpc\n");
-			goto err;
-		}
-		tasklet_init(hv_context.event_dpc[cpu], vmbus_on_event, cpu);
 
-		hv_context.msg_dpc[cpu] = kmalloc(size, GFP_ATOMIC);
+		memset(hv_cpu, 0, sizeof(*hv_cpu));
-		if (hv_context.msg_dpc[cpu] == NULL) {
+		tasklet_init(&hv_cpu->msg_dpc,
-			pr_err("Unable to allocate event dpc\n");
+			     vmbus_on_msg_dpc, (unsigned long) hv_cpu);
-			goto err;
-		}
-		tasklet_init(hv_context.msg_dpc[cpu], vmbus_on_msg_dpc, cpu);
 
-		hv_context.clk_evt[cpu] = kzalloc(ced_size, GFP_ATOMIC);
+		hv_cpu->clk_evt = kzalloc(sizeof(struct clock_event_device),
-		if (hv_context.clk_evt[cpu] == NULL) {
+					  GFP_KERNEL);
+		if (hv_cpu->clk_evt == NULL) {
 			pr_err("Unable to allocate clock event device\n");
 			goto err;
 		}
+		hv_init_clockevent_device(hv_cpu->clk_evt, cpu);
 
-		hv_init_clockevent_device(hv_context.clk_evt[cpu], cpu);
+		hv_cpu->synic_message_page =
-
-		hv_context.synic_message_page[cpu] =
 			(void *)get_zeroed_page(GFP_ATOMIC);
-
+		if (hv_cpu->synic_message_page == NULL) {
-		if (hv_context.synic_message_page[cpu] == NULL) {
 			pr_err("Unable to allocate SYNIC message page\n");
 			goto err;
 		}
 
-		hv_context.synic_event_page[cpu] =
+		hv_cpu->synic_event_page = (void *)get_zeroed_page(GFP_ATOMIC);
-			(void *)get_zeroed_page(GFP_ATOMIC);
+		if (hv_cpu->synic_event_page == NULL) {
-
-		if (hv_context.synic_event_page[cpu] == NULL) {
 			pr_err("Unable to allocate SYNIC event page\n");
 			goto err;
 		}
 
-		hv_context.post_msg_page[cpu] =
+		hv_cpu->post_msg_page = (void *)get_zeroed_page(GFP_ATOMIC);
-			(void *)get_zeroed_page(GFP_ATOMIC);
+		if (hv_cpu->post_msg_page == NULL) {
-
-		if (hv_context.post_msg_page[cpu] == NULL) {
 			pr_err("Unable to allocate post msg page\n");
 			goto err;
 		}
+
+		INIT_LIST_HEAD(&hv_cpu->chan_list);
 	}
 
 	return 0;
@@ -464,26 +194,24 @@ int hv_synic_alloc(void)
 	return -ENOMEM;
 }
 
-static void hv_synic_free_cpu(int cpu)
-{
-	kfree(hv_context.event_dpc[cpu]);
-	kfree(hv_context.msg_dpc[cpu]);
-	kfree(hv_context.clk_evt[cpu]);
-	if (hv_context.synic_event_page[cpu])
-		free_page((unsigned long)hv_context.synic_event_page[cpu]);
-	if (hv_context.synic_message_page[cpu])
-		free_page((unsigned long)hv_context.synic_message_page[cpu]);
-	if (hv_context.post_msg_page[cpu])
-		free_page((unsigned long)hv_context.post_msg_page[cpu]);
-}
 
 void hv_synic_free(void)
 {
 	int cpu;
 
+	for_each_present_cpu(cpu) {
+		struct hv_per_cpu_context *hv_cpu
+			= per_cpu_ptr(hv_context.cpu_context, cpu);
+
+		if (hv_cpu->synic_event_page)
+			free_page((unsigned long)hv_cpu->synic_event_page);
+		if (hv_cpu->synic_message_page)
+			free_page((unsigned long)hv_cpu->synic_message_page);
+		if (hv_cpu->post_msg_page)
+			free_page((unsigned long)hv_cpu->post_msg_page);
+	}
+
 	kfree(hv_context.hv_numa_map);
-	for_each_online_cpu(cpu)
-		hv_synic_free_cpu(cpu);
 }
 
 /*
@@ -493,54 +221,49 @@ void hv_synic_free(void)
  * retrieve the initialized message and event pages.  Otherwise, we create and
  * initialize the message and event pages.
  */
-void hv_synic_init(void *arg)
+int hv_synic_init(unsigned int cpu)
 {
-	u64 version;
+	struct hv_per_cpu_context *hv_cpu
+		= per_cpu_ptr(hv_context.cpu_context, cpu);
 	union hv_synic_simp simp;
 	union hv_synic_siefp siefp;
 	union hv_synic_sint shared_sint;
 	union hv_synic_scontrol sctrl;
 	u64 vp_index;
 
-	int cpu = smp_processor_id();
-
-	if (!hv_context.hypercall_page)
-		return;
-
-	/* Check the version */
-	rdmsrl(HV_X64_MSR_SVERSION, version);
-
 	/* Setup the Synic's message page */
-	rdmsrl(HV_X64_MSR_SIMP, simp.as_uint64);
+	hv_get_simp(simp.as_uint64);
 	simp.simp_enabled = 1;
-	simp.base_simp_gpa = virt_to_phys(hv_context.synic_message_page[cpu])
+	simp.base_simp_gpa = virt_to_phys(hv_cpu->synic_message_page)
 		>> PAGE_SHIFT;
 
-	wrmsrl(HV_X64_MSR_SIMP, simp.as_uint64);
+	hv_set_simp(simp.as_uint64);
 
 	/* Setup the Synic's event page */
-	rdmsrl(HV_X64_MSR_SIEFP, siefp.as_uint64);
+	hv_get_siefp(siefp.as_uint64);
 	siefp.siefp_enabled = 1;
-	siefp.base_siefp_gpa = virt_to_phys(hv_context.synic_event_page[cpu])
+	siefp.base_siefp_gpa = virt_to_phys(hv_cpu->synic_event_page)
 		>> PAGE_SHIFT;
 
-	wrmsrl(HV_X64_MSR_SIEFP, siefp.as_uint64);
+	hv_set_siefp(siefp.as_uint64);
 
 	/* Setup the shared SINT. */
-	rdmsrl(HV_X64_MSR_SINT0 + VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
+	hv_get_synint_state(HV_X64_MSR_SINT0 + VMBUS_MESSAGE_SINT,
+			    shared_sint.as_uint64);
 
 	shared_sint.as_uint64 = 0;
 	shared_sint.vector = HYPERVISOR_CALLBACK_VECTOR;
 	shared_sint.masked = false;
 	shared_sint.auto_eoi = true;
 
-	wrmsrl(HV_X64_MSR_SINT0 + VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
+	hv_set_synint_state(HV_X64_MSR_SINT0 + VMBUS_MESSAGE_SINT,
+			    shared_sint.as_uint64);
 
 	/* Enable the global synic bit */
-	rdmsrl(HV_X64_MSR_SCONTROL, sctrl.as_uint64);
+	hv_get_synic_state(sctrl.as_uint64);
 	sctrl.enable = 1;
 
-	wrmsrl(HV_X64_MSR_SCONTROL, sctrl.as_uint64);
+	hv_set_synic_state(sctrl.as_uint64);
 
 	hv_context.synic_initialized = true;
 
@@ -549,20 +272,18 @@ void hv_synic_init(void *arg)
 	 * of cpuid and Linux' notion of cpuid.
 	 * This array will be indexed using Linux cpuid.
 	 */
-	rdmsrl(HV_X64_MSR_VP_INDEX, vp_index);
+	hv_get_vp_index(vp_index);
 	hv_context.vp_index[cpu] = (u32)vp_index;
 
-	INIT_LIST_HEAD(&hv_context.percpu_list[cpu]);
-
 	/*
 	 * Register the per-cpu clockevent source.
 	 */
 	if (ms_hyperv.features & HV_X64_MSR_SYNTIMER_AVAILABLE)
-		clockevents_config_and_register(hv_context.clk_evt[cpu],
+		clockevents_config_and_register(hv_cpu->clk_evt,
 						HV_TIMER_FREQUENCY,
 						HV_MIN_DELTA_TICKS,
 						HV_MAX_MAX_DELTA_TICKS);
-	return;
+	return 0;
 }
 
 /*
@@ -575,52 +296,94 @@ void hv_synic_clockevents_cleanup(void)
 	if (!(ms_hyperv.features & HV_X64_MSR_SYNTIMER_AVAILABLE))
 		return;
 
-	for_each_present_cpu(cpu)
+	for_each_present_cpu(cpu) {
-		clockevents_unbind_device(hv_context.clk_evt[cpu], cpu);
+		struct hv_per_cpu_context *hv_cpu
+			= per_cpu_ptr(hv_context.cpu_context, cpu);
+
+		clockevents_unbind_device(hv_cpu->clk_evt, cpu);
+	}
 }
 
 /*
  * hv_synic_cleanup - Cleanup routine for hv_synic_init().
  */
-void hv_synic_cleanup(void *arg)
+int hv_synic_cleanup(unsigned int cpu)
 {
 	union hv_synic_sint shared_sint;
 	union hv_synic_simp simp;
 	union hv_synic_siefp siefp;
 	union hv_synic_scontrol sctrl;
-	int cpu = smp_processor_id();
+	struct vmbus_channel *channel, *sc;
+	bool channel_found = false;
+	unsigned long flags;
 
 	if (!hv_context.synic_initialized)
-		return;
+		return -EFAULT;
+
+	/*
+	 * Search for channels which are bound to the CPU we're about to
+	 * cleanup. In case we find one and vmbus is still connected we need to
+	 * fail, this will effectively prevent CPU offlining. There is no way
+	 * we can re-bind channels to different CPUs for now.
+	 */
+	mutex_lock(&vmbus_connection.channel_mutex);
+	list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
+		if (channel->target_cpu == cpu) {
+			channel_found = true;
+			break;
+		}
+		spin_lock_irqsave(&channel->lock, flags);
+		list_for_each_entry(sc, &channel->sc_list, sc_list) {
+			if (sc->target_cpu == cpu) {
+				channel_found = true;
+				break;
+			}
+		}
+		spin_unlock_irqrestore(&channel->lock, flags);
+		if (channel_found)
+			break;
+	}
+	mutex_unlock(&vmbus_connection.channel_mutex);
+
+	if (channel_found && vmbus_connection.conn_state == CONNECTED)
+		return -EBUSY;
 
 	/* Turn off clockevent device */
 	if (ms_hyperv.features & HV_X64_MSR_SYNTIMER_AVAILABLE) {
-		clockevents_unbind_device(hv_context.clk_evt[cpu], cpu);
+		struct hv_per_cpu_context *hv_cpu
-		hv_ce_shutdown(hv_context.clk_evt[cpu]);
+			= this_cpu_ptr(hv_context.cpu_context);
+
+		clockevents_unbind_device(hv_cpu->clk_evt, cpu);
+		hv_ce_shutdown(hv_cpu->clk_evt);
+		put_cpu_ptr(hv_cpu);
 	}
 
-	rdmsrl(HV_X64_MSR_SINT0 + VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
+	hv_get_synint_state(HV_X64_MSR_SINT0 + VMBUS_MESSAGE_SINT,
+			    shared_sint.as_uint64);
 
 	shared_sint.masked = 1;
 
 	/* Need to correctly cleanup in the case of SMP!!! */
 	/* Disable the interrupt */
-	wrmsrl(HV_X64_MSR_SINT0 + VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
+	hv_set_synint_state(HV_X64_MSR_SINT0 + VMBUS_MESSAGE_SINT,
+			    shared_sint.as_uint64);
 
-	rdmsrl(HV_X64_MSR_SIMP, simp.as_uint64);
+	hv_get_simp(simp.as_uint64);
 	simp.simp_enabled = 0;
 	simp.base_simp_gpa = 0;
 
-	wrmsrl(HV_X64_MSR_SIMP, simp.as_uint64);
+	hv_set_simp(simp.as_uint64);
 
-	rdmsrl(HV_X64_MSR_SIEFP, siefp.as_uint64);
+	hv_get_siefp(siefp.as_uint64);
 	siefp.siefp_enabled = 0;
 	siefp.base_siefp_gpa = 0;
 
-	wrmsrl(HV_X64_MSR_SIEFP, siefp.as_uint64);
+	hv_set_siefp(siefp.as_uint64);
 
 	/* Disable the global synic bit */
-	rdmsrl(HV_X64_MSR_SCONTROL, sctrl.as_uint64);
+	hv_get_synic_state(sctrl.as_uint64);
 	sctrl.enable = 0;
-	wrmsrl(HV_X64_MSR_SCONTROL, sctrl.as_uint64);
+	hv_set_synic_state(sctrl.as_uint64);
+
+	return 0;
 }

drivers/hv/hv_balloon.c

@@ -587,6 +587,7 @@ static int hv_memory_notifier(struct notifier_block *nb, unsigned long val,
 		spin_lock_irqsave(&dm_device.ha_lock, flags);
 		dm_device.num_pages_onlined += mem->nr_pages;
 		spin_unlock_irqrestore(&dm_device.ha_lock, flags);
+		/* Fall through */
 	case MEM_CANCEL_ONLINE:
 		if (dm_device.ha_waiting) {
 			dm_device.ha_waiting = false;

drivers/hv/hv_fcopy.c

@@ -31,6 +31,16 @@
 #define WIN8_SRV_MINOR		1
 #define WIN8_SRV_VERSION	(WIN8_SRV_MAJOR << 16 | WIN8_SRV_MINOR)
 
+#define FCOPY_VER_COUNT 1
+static const int fcopy_versions[] = {
+	WIN8_SRV_VERSION
+};
+
+#define FW_VER_COUNT 1
+static const int fw_versions[] = {
+	UTIL_FW_VERSION
+};
+
 /*
  * Global state maintained for transaction that is being processed.
  * For a class of integration services, including the "file copy service",
@@ -61,6 +71,7 @@ static DECLARE_WORK(fcopy_send_work, fcopy_send_data);
 static const char fcopy_devname[] = "vmbus/hv_fcopy";
 static u8 *recv_buffer;
 static struct hvutil_transport *hvt;
+static struct completion release_event;
 /*
  * This state maintains the version number registered by the daemon.
  */
@@ -227,8 +238,6 @@ void hv_fcopy_onchannelcallback(void *context)
 	u64 requestid;
 	struct hv_fcopy_hdr *fcopy_msg;
 	struct icmsg_hdr *icmsghdr;
-	struct icmsg_negotiate *negop = NULL;
-	int util_fw_version;
 	int fcopy_srv_version;
 
 	if (fcopy_transaction.state > HVUTIL_READY)
@@ -242,10 +251,15 @@ void hv_fcopy_onchannelcallback(void *context)
 	icmsghdr = (struct icmsg_hdr *)&recv_buffer[
 			sizeof(struct vmbuspipe_hdr)];
 	if (icmsghdr->icmsgtype == ICMSGTYPE_NEGOTIATE) {
-		util_fw_version = UTIL_FW_VERSION;
+		if (vmbus_prep_negotiate_resp(icmsghdr, recv_buffer,
-		fcopy_srv_version = WIN8_SRV_VERSION;
+				fw_versions, FW_VER_COUNT,
-		vmbus_prep_negotiate_resp(icmsghdr, negop, recv_buffer,
+				fcopy_versions, FCOPY_VER_COUNT,
-				util_fw_version, fcopy_srv_version);
+				NULL, &fcopy_srv_version)) {
+
+			pr_info("FCopy IC version %d.%d\n",
+				fcopy_srv_version >> 16,
+				fcopy_srv_version & 0xFFFF);
+		}
 	} else {
 		fcopy_msg = (struct hv_fcopy_hdr *)&recv_buffer[
 				sizeof(struct vmbuspipe_hdr) +
@@ -317,6 +331,7 @@ static void fcopy_on_reset(void)
 
 	if (cancel_delayed_work_sync(&fcopy_timeout_work))
 		fcopy_respond_to_host(HV_E_FAIL);
+	complete(&release_event);
 }
 
 int hv_fcopy_init(struct hv_util_service *srv)
@@ -324,6 +339,7 @@ int hv_fcopy_init(struct hv_util_service *srv)
 	recv_buffer = srv->recv_buffer;
 	fcopy_transaction.recv_channel = srv->channel;
 
+	init_completion(&release_event);
 	/*
 	 * When this driver loads, the user level daemon that
 	 * processes the host requests may not yet be running.
@@ -345,4 +361,5 @@ void hv_fcopy_deinit(void)
 	fcopy_transaction.state = HVUTIL_DEVICE_DYING;
 	cancel_delayed_work_sync(&fcopy_timeout_work);
 	hvutil_transport_destroy(hvt);
+	wait_for_completion(&release_event);
 }

drivers/hv/hv_kvp.c

@@ -46,6 +46,19 @@
 #define WIN8_SRV_MINOR   0
 #define WIN8_SRV_VERSION     (WIN8_SRV_MAJOR << 16 | WIN8_SRV_MINOR)
 
+#define KVP_VER_COUNT 3
+static const int kvp_versions[] = {
+	WIN8_SRV_VERSION,
+	WIN7_SRV_VERSION,
+	WS2008_SRV_VERSION
+};
+
+#define FW_VER_COUNT 2
+static const int fw_versions[] = {
+	UTIL_FW_VERSION,
+	UTIL_WS2K8_FW_VERSION
+};
+
 /*
  * Global state maintained for transaction that is being processed. For a class
  * of integration services, including the "KVP service", the specified protocol
@@ -88,6 +101,7 @@ static DECLARE_WORK(kvp_sendkey_work, kvp_send_key);
 static const char kvp_devname[] = "vmbus/hv_kvp";
 static u8 *recv_buffer;
 static struct hvutil_transport *hvt;
+static struct completion release_event;
 /*
  * Register the kernel component with the user-level daemon.
  * As part of this registration, pass the LIC version number.
@@ -609,8 +623,6 @@ void hv_kvp_onchannelcallback(void *context)
 	struct hv_kvp_msg *kvp_msg;
 
 	struct icmsg_hdr *icmsghdrp;
-	struct icmsg_negotiate *negop = NULL;
-	int util_fw_version;
 	int kvp_srv_version;
 	static enum {NEGO_NOT_STARTED,
 		     NEGO_IN_PROGRESS,
@@ -639,28 +651,14 @@ void hv_kvp_onchannelcallback(void *context)
 			sizeof(struct vmbuspipe_hdr)];
 
 		if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) {
-			/*
+			if (vmbus_prep_negotiate_resp(icmsghdrp,
-			 * Based on the host, select appropriate
+				 recv_buffer, fw_versions, FW_VER_COUNT,
-			 * framework and service versions we will
+				 kvp_versions, KVP_VER_COUNT,
-			 * negotiate.
+				 NULL, &kvp_srv_version)) {
-			 */
+				pr_info("KVP IC version %d.%d\n",
-			switch (vmbus_proto_version) {
+					kvp_srv_version >> 16,
-			case (VERSION_WS2008):
+					kvp_srv_version & 0xFFFF);
-				util_fw_version = UTIL_WS2K8_FW_VERSION;
-				kvp_srv_version = WS2008_SRV_VERSION;
-				break;
-			case (VERSION_WIN7):
-				util_fw_version = UTIL_FW_VERSION;
-				kvp_srv_version = WIN7_SRV_VERSION;
-				break;
-			default:
-				util_fw_version = UTIL_FW_VERSION;
-				kvp_srv_version = WIN8_SRV_VERSION;
 			}
-			vmbus_prep_negotiate_resp(icmsghdrp, negop,
-				 recv_buffer, util_fw_version,
-				 kvp_srv_version);
-
 		} else {
 			kvp_msg = (struct hv_kvp_msg *)&recv_buffer[
 				sizeof(struct vmbuspipe_hdr) +
@@ -716,6 +714,7 @@ static void kvp_on_reset(void)
 	if (cancel_delayed_work_sync(&kvp_timeout_work))
 		kvp_respond_to_host(NULL, HV_E_FAIL);
 	kvp_transaction.state = HVUTIL_DEVICE_INIT;
+	complete(&release_event);
 }
 
 int
@@ -724,6 +723,7 @@ hv_kvp_init(struct hv_util_service *srv)
 	recv_buffer = srv->recv_buffer;
 	kvp_transaction.recv_channel = srv->channel;
 
+	init_completion(&release_event);
 	/*
 	 * When this driver loads, the user level daemon that
 	 * processes the host requests may not yet be running.
@@ -747,4 +747,5 @@ void hv_kvp_deinit(void)
 	cancel_delayed_work_sync(&kvp_timeout_work);
 	cancel_work_sync(&kvp_sendkey_work);
 	hvutil_transport_destroy(hvt);
+	wait_for_completion(&release_event);
 }

drivers/hv/hv_snapshot.c

@@ -31,6 +31,16 @@
 #define VSS_MINOR  0
 #define VSS_VERSION    (VSS_MAJOR << 16 | VSS_MINOR)
 
+#define VSS_VER_COUNT 1
+static const int vss_versions[] = {
+	VSS_VERSION
+};
+
+#define FW_VER_COUNT 1
+static const int fw_versions[] = {
+	UTIL_FW_VERSION
+};
+
 /*
  * Timeout values are based on expecations from host
  */
@@ -69,6 +79,7 @@ static int dm_reg_value;
 static const char vss_devname[] = "vmbus/hv_vss";
 static __u8 *recv_buffer;
 static struct hvutil_transport *hvt;
+static struct completion release_event;
 
 static void vss_timeout_func(struct work_struct *dummy);
 static void vss_handle_request(struct work_struct *dummy);
@@ -293,10 +304,9 @@ void hv_vss_onchannelcallback(void *context)
 	u32 recvlen;
 	u64 requestid;
 	struct hv_vss_msg *vss_msg;
-
+	int vss_srv_version;
 
 	struct icmsg_hdr *icmsghdrp;
-	struct icmsg_negotiate *negop = NULL;
 
 	if (vss_transaction.state > HVUTIL_READY)
 		return;
@@ -309,9 +319,15 @@ void hv_vss_onchannelcallback(void *context)
 			sizeof(struct vmbuspipe_hdr)];
 
 		if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) {
-			vmbus_prep_negotiate_resp(icmsghdrp, negop,
+			if (vmbus_prep_negotiate_resp(icmsghdrp,
-				 recv_buffer, UTIL_FW_VERSION,
+				 recv_buffer, fw_versions, FW_VER_COUNT,
-				 VSS_VERSION);
+				 vss_versions, VSS_VER_COUNT,
+				 NULL, &vss_srv_version)) {
+
+				pr_info("VSS IC version %d.%d\n",
+					vss_srv_version >> 16,
+					vss_srv_version & 0xFFFF);
+			}
 		} else {
 			vss_msg = (struct hv_vss_msg *)&recv_buffer[
 				sizeof(struct vmbuspipe_hdr) +
@@ -345,11 +361,13 @@ static void vss_on_reset(void)
 	if (cancel_delayed_work_sync(&vss_timeout_work))
 		vss_respond_to_host(HV_E_FAIL);
 	vss_transaction.state = HVUTIL_DEVICE_INIT;
+	complete(&release_event);
 }
 
 int
 hv_vss_init(struct hv_util_service *srv)
 {
+	init_completion(&release_event);
 	if (vmbus_proto_version < VERSION_WIN8_1) {
 		pr_warn("Integration service 'Backup (volume snapshot)'"
 			" not supported on this host version.\n");
@@ -382,4 +400,5 @@ void hv_vss_deinit(void)
 	cancel_delayed_work_sync(&vss_timeout_work);
 	cancel_work_sync(&vss_handle_request_work);
 	hvutil_transport_destroy(hvt);
+	wait_for_completion(&release_event);
 }

drivers/hv/hv_util.c

@@ -27,6 +27,9 @@
 #include <linux/sysctl.h>
 #include <linux/reboot.h>
 #include <linux/hyperv.h>
+#include <linux/clockchips.h>
+#include <linux/ptp_clock_kernel.h>
+#include <asm/mshyperv.h>
 
 #include "hyperv_vmbus.h"
 
@@ -57,7 +60,31 @@
 static int sd_srv_version;
 static int ts_srv_version;
 static int hb_srv_version;
-static int util_fw_version;
+
+#define SD_VER_COUNT 2
+static const int sd_versions[] = {
+	SD_VERSION,
+	SD_VERSION_1
+};
+
+#define TS_VER_COUNT 3
+static const int ts_versions[] = {
+	TS_VERSION,
+	TS_VERSION_3,
+	TS_VERSION_1
+};
+
+#define HB_VER_COUNT 2
+static const int hb_versions[] = {
+	HB_VERSION,
+	HB_VERSION_1
+};
+
+#define FW_VER_COUNT 2
+static const int fw_versions[] = {
+	UTIL_FW_VERSION,
+	UTIL_WS2K8_FW_VERSION
+};
 
 static void shutdown_onchannelcallback(void *context);
 static struct hv_util_service util_shutdown = {
@@ -118,7 +145,6 @@ static void shutdown_onchannelcallback(void *context)
 	struct shutdown_msg_data *shutdown_msg;
 
 	struct icmsg_hdr *icmsghdrp;
-	struct icmsg_negotiate *negop = NULL;
 
 	vmbus_recvpacket(channel, shut_txf_buf,
 			 PAGE_SIZE, &recvlen, &requestid);
@@ -128,9 +154,14 @@ static void shutdown_onchannelcallback(void *context)
 			sizeof(struct vmbuspipe_hdr)];
 
 		if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) {
-			vmbus_prep_negotiate_resp(icmsghdrp, negop,
+			if (vmbus_prep_negotiate_resp(icmsghdrp, shut_txf_buf,
-					shut_txf_buf, util_fw_version,
+					fw_versions, FW_VER_COUNT,
-					sd_srv_version);
+					sd_versions, SD_VER_COUNT,
+					NULL, &sd_srv_version)) {
+				pr_info("Shutdown IC version %d.%d\n",
+					sd_srv_version >> 16,
+					sd_srv_version & 0xFFFF);
+			}
 		} else {
 			shutdown_msg =
 				(struct shutdown_msg_data *)&shut_txf_buf[
@@ -182,30 +213,16 @@ struct adj_time_work {
 static void hv_set_host_time(struct work_struct *work)
 {
 	struct adj_time_work *wrk;
-	s64 host_tns;
+	struct timespec64 host_ts;
-	u64 newtime;
+	u64 reftime, newtime;
-	struct timespec host_ts;
 
 	wrk = container_of(work, struct adj_time_work, work);
 
-	newtime = wrk->host_time;
+	reftime = hyperv_cs->read(hyperv_cs);
-	if (ts_srv_version > TS_VERSION_3) {
+	newtime = wrk->host_time + (reftime - wrk->ref_time);
-		/*
+	host_ts = ns_to_timespec64((newtime - WLTIMEDELTA) * 100);
-		 * Some latency has been introduced since Hyper-V generated
-		 * its time sample. Take that latency into account before
-		 * using TSC reference time sample from Hyper-V.
-		 *
-		 * This sample is given by TimeSync v4 and above hosts.
-		 */
-		u64 current_tick;
 
-		rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick);
+	do_settimeofday64(&host_ts);
-		newtime += (current_tick - wrk->ref_time);
-	}
-	host_tns = (newtime - WLTIMEDELTA) * 100;
-	host_ts = ns_to_timespec(host_tns);
-
-	do_settimeofday(&host_ts);
 }
 
 /*
@@ -222,22 +239,60 @@ static void hv_set_host_time(struct work_struct *work)
  * to discipline the clock.
  */
 static struct adj_time_work  wrk;
-static inline void adj_guesttime(u64 hosttime, u64 reftime, u8 flags)
+
+/*
+ * The last time sample, received from the host. PTP device responds to
+ * requests by using this data and the current partition-wide time reference
+ * count.
+ */
+static struct {
+	u64				host_time;
+	u64				ref_time;
+	struct system_time_snapshot	snap;
+	spinlock_t			lock;
+} host_ts;
+
+static inline void adj_guesttime(u64 hosttime, u64 reftime, u8 adj_flags)
 {
+	unsigned long flags;
+	u64 cur_reftime;
 
 	/*
 	 * This check is safe since we are executing in the
-	 * interrupt context and time synch messages arre always
+	 * interrupt context and time synch messages are always
 	 * delivered on the same CPU.
 	 */
+	if (adj_flags & ICTIMESYNCFLAG_SYNC) {
+		/* Queue a job to do do_settimeofday64() */
 		if (work_pending(&wrk.work))
 			return;
 
 		wrk.host_time = hosttime;
 		wrk.ref_time = reftime;
-	wrk.flags = flags;
+		wrk.flags = adj_flags;
-	if ((flags & (ICTIMESYNCFLAG_SYNC | ICTIMESYNCFLAG_SAMPLE)) != 0) {
 		schedule_work(&wrk.work);
+	} else {
+		/*
+		 * Save the adjusted time sample from the host and the snapshot
+		 * of the current system time for PTP device.
+		 */
+		spin_lock_irqsave(&host_ts.lock, flags);
+
+		cur_reftime = hyperv_cs->read(hyperv_cs);
+		host_ts.host_time = hosttime;
+		host_ts.ref_time = cur_reftime;
+		ktime_get_snapshot(&host_ts.snap);
+
+		/*
+		 * TimeSync v4 messages contain reference time (guest's Hyper-V
+		 * clocksource read when the time sample was generated), we can
+		 * improve the precision by adding the delta between now and the
+		 * time of generation.
+		 */
+		if (ts_srv_version > TS_VERSION_3)
+			host_ts.host_time += (cur_reftime - reftime);
+
+		spin_unlock_irqrestore(&host_ts.lock, flags);
 	}
 }
 
@@ -253,7 +308,6 @@ static void timesync_onchannelcallback(void *context)
 	struct ictimesync_data *timedatap;
 	struct ictimesync_ref_data *refdata;
 	u8 *time_txf_buf = util_timesynch.recv_buffer;
-	struct icmsg_negotiate *negop = NULL;
 
 	vmbus_recvpacket(channel, time_txf_buf,
 			 PAGE_SIZE, &recvlen, &requestid);
@@ -263,12 +317,14 @@ static void timesync_onchannelcallback(void *context)
 				sizeof(struct vmbuspipe_hdr)];
 
 		if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) {
-			vmbus_prep_negotiate_resp(icmsghdrp, negop,
+			if (vmbus_prep_negotiate_resp(icmsghdrp, time_txf_buf,
-						time_txf_buf,
+						fw_versions, FW_VER_COUNT,
-						util_fw_version,
+						ts_versions, TS_VER_COUNT,
-						ts_srv_version);
+						NULL, &ts_srv_version)) {
-			pr_info("Using TimeSync version %d.%d\n",
+				pr_info("TimeSync IC version %d.%d\n",
-				ts_srv_version >> 16, ts_srv_version & 0xFFFF);
+					ts_srv_version >> 16,
+					ts_srv_version & 0xFFFF);
+			}
 		} else {
 			if (ts_srv_version > TS_VERSION_3) {
 				refdata = (struct ictimesync_ref_data *)
@@ -312,7 +368,6 @@ static void heartbeat_onchannelcallback(void *context)
 	struct icmsg_hdr *icmsghdrp;
 	struct heartbeat_msg_data *heartbeat_msg;
 	u8 *hbeat_txf_buf = util_heartbeat.recv_buffer;
-	struct icmsg_negotiate *negop = NULL;
 
 	while (1) {
 
@@ -326,9 +381,16 @@ static void heartbeat_onchannelcallback(void *context)
 				sizeof(struct vmbuspipe_hdr)];
 
 		if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) {
-			vmbus_prep_negotiate_resp(icmsghdrp, negop,
+			if (vmbus_prep_negotiate_resp(icmsghdrp,
-				hbeat_txf_buf, util_fw_version,
+					hbeat_txf_buf,
-				hb_srv_version);
+					fw_versions, FW_VER_COUNT,
+					hb_versions, HB_VER_COUNT,
+					NULL, &hb_srv_version)) {
+
+				pr_info("Heartbeat IC version %d.%d\n",
+					hb_srv_version >> 16,
+					hb_srv_version & 0xFFFF);
+			}
 		} else {
 			heartbeat_msg =
 				(struct heartbeat_msg_data *)&hbeat_txf_buf[
@@ -373,38 +435,10 @@ static int util_probe(struct hv_device *dev,
 	 * Turn off batched reading for all util drivers before we open the
 	 * channel.
 	 */
-
+	set_channel_read_mode(dev->channel, HV_CALL_DIRECT);
-	set_channel_read_state(dev->channel, false);
 
 	hv_set_drvdata(dev, srv);
 
-	/*
-	 * Based on the host; initialize the framework and
-	 * service version numbers we will negotiate.
-	 */
-	switch (vmbus_proto_version) {
-	case (VERSION_WS2008):
-		util_fw_version = UTIL_WS2K8_FW_VERSION;
-		sd_srv_version = SD_VERSION_1;
-		ts_srv_version = TS_VERSION_1;
-		hb_srv_version = HB_VERSION_1;
-		break;
-	case VERSION_WIN7:
-	case VERSION_WIN8:
-	case VERSION_WIN8_1:
-		util_fw_version = UTIL_FW_VERSION;
-		sd_srv_version = SD_VERSION;
-		ts_srv_version = TS_VERSION_3;
-		hb_srv_version = HB_VERSION;
-		break;
-	case VERSION_WIN10:
-	default:
-		util_fw_version = UTIL_FW_VERSION;
-		sd_srv_version = SD_VERSION;
-		ts_srv_version = TS_VERSION;
-		hb_srv_version = HB_VERSION;
-	}
-
 	ret = vmbus_open(dev->channel, 4 * PAGE_SIZE, 4 * PAGE_SIZE, NULL, 0,
 			srv->util_cb, dev->channel);
 	if (ret)
@@ -470,14 +504,113 @@ static  struct hv_driver util_drv = {
 	.remove =  util_remove,
 };
 
+static int hv_ptp_enable(struct ptp_clock_info *info,
+			 struct ptp_clock_request *request, int on)
+{
+	return -EOPNOTSUPP;
+}
+
+static int hv_ptp_settime(struct ptp_clock_info *p, const struct timespec64 *ts)
+{
+	return -EOPNOTSUPP;
+}
+
+static int hv_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta)
+{
+	return -EOPNOTSUPP;
+}
+static int hv_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+	return -EOPNOTSUPP;
+}
+
+static int hv_ptp_gettime(struct ptp_clock_info *info, struct timespec64 *ts)
+{
+	unsigned long flags;
+	u64 newtime, reftime;
+
+	spin_lock_irqsave(&host_ts.lock, flags);
+	reftime = hyperv_cs->read(hyperv_cs);
+	newtime = host_ts.host_time + (reftime - host_ts.ref_time);
+	*ts = ns_to_timespec64((newtime - WLTIMEDELTA) * 100);
+	spin_unlock_irqrestore(&host_ts.lock, flags);
+
+	return 0;
+}
+
+static int hv_ptp_get_syncdevicetime(ktime_t *device,
+				     struct system_counterval_t *system,
+				     void *ctx)
+{
+	system->cs = hyperv_cs;
+	system->cycles = host_ts.ref_time;
+	*device = ns_to_ktime((host_ts.host_time - WLTIMEDELTA) * 100);
+
+	return 0;
+}
+
+static int hv_ptp_getcrosststamp(struct ptp_clock_info *ptp,
+				 struct system_device_crosststamp *xtstamp)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&host_ts.lock, flags);
+
+	/*
+	 * host_ts contains the last time sample from the host and the snapshot
+	 * of system time. We don't need to calculate the time delta between
+	 * the reception and now as get_device_system_crosststamp() does the
+	 * required interpolation.
+	 */
+	ret = get_device_system_crosststamp(hv_ptp_get_syncdevicetime,
+					    NULL, &host_ts.snap, xtstamp);
+
+	spin_unlock_irqrestore(&host_ts.lock, flags);
+
+	return ret;
+}
+
+static struct ptp_clock_info ptp_hyperv_info = {
+	.name		= "hyperv",
+	.enable         = hv_ptp_enable,
+	.adjtime        = hv_ptp_adjtime,
+	.adjfreq        = hv_ptp_adjfreq,
+	.gettime64      = hv_ptp_gettime,
+	.getcrosststamp = hv_ptp_getcrosststamp,
+	.settime64      = hv_ptp_settime,
+	.owner		= THIS_MODULE,
+};
+
+static struct ptp_clock *hv_ptp_clock;
+
 static int hv_timesync_init(struct hv_util_service *srv)
 {
+	/* TimeSync requires Hyper-V clocksource. */
+	if (!hyperv_cs)
+		return -ENODEV;
+
 	INIT_WORK(&wrk.work, hv_set_host_time);
+
+	/*
+	 * ptp_clock_register() returns NULL when CONFIG_PTP_1588_CLOCK is
+	 * disabled but the driver is still useful without the PTP device
+	 * as it still handles the ICTIMESYNCFLAG_SYNC case.
+	 */
+	hv_ptp_clock = ptp_clock_register(&ptp_hyperv_info, NULL);
+	if (IS_ERR_OR_NULL(hv_ptp_clock)) {
+		pr_err("cannot register PTP clock: %ld\n",
+		       PTR_ERR(hv_ptp_clock));
+		hv_ptp_clock = NULL;
+	}
+
 	return 0;
 }
 
 static void hv_timesync_deinit(void)
 {
+	if (hv_ptp_clock)
+		ptp_clock_unregister(hv_ptp_clock);
 	cancel_work_sync(&wrk.work);
 }
 

drivers/hv/hyperv_vmbus.h

@@ -29,6 +29,7 @@
 #include <asm/sync_bitops.h>
 #include <linux/atomic.h>
 #include <linux/hyperv.h>
+#include <linux/interrupt.h>
 
 /*
  * Timeout for services such as KVP and fcopy.
@@ -40,95 +41,9 @@
  */
 #define HV_UTIL_NEGO_TIMEOUT 55
 
-/*
- * The below CPUID leaves are present if VersionAndFeatures.HypervisorPresent
- * is set by CPUID(HVCPUID_VERSION_FEATURES).
- */
-enum hv_cpuid_function {
-	HVCPUID_VERSION_FEATURES		= 0x00000001,
-	HVCPUID_VENDOR_MAXFUNCTION		= 0x40000000,
-	HVCPUID_INTERFACE			= 0x40000001,
-
-	/*
-	 * The remaining functions depend on the value of
-	 * HVCPUID_INTERFACE
-	 */
-	HVCPUID_VERSION			= 0x40000002,
-	HVCPUID_FEATURES			= 0x40000003,
-	HVCPUID_ENLIGHTENMENT_INFO	= 0x40000004,
-	HVCPUID_IMPLEMENTATION_LIMITS		= 0x40000005,
-};
-
-#define  HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE   0x400
-
-#define HV_X64_MSR_CRASH_P0   0x40000100
-#define HV_X64_MSR_CRASH_P1   0x40000101
-#define HV_X64_MSR_CRASH_P2   0x40000102
-#define HV_X64_MSR_CRASH_P3   0x40000103
-#define HV_X64_MSR_CRASH_P4   0x40000104
-#define HV_X64_MSR_CRASH_CTL  0x40000105
-
-#define HV_CRASH_CTL_CRASH_NOTIFY (1ULL << 63)
-
-/* Define version of the synthetic interrupt controller. */
-#define HV_SYNIC_VERSION		(1)
-
-#define HV_ANY_VP			(0xFFFFFFFF)
-
 /* Define synthetic interrupt controller flag constants. */
 #define HV_EVENT_FLAGS_COUNT		(256 * 8)
-#define HV_EVENT_FLAGS_BYTE_COUNT	(256)
+#define HV_EVENT_FLAGS_LONG_COUNT	(256 / sizeof(unsigned long))
-#define HV_EVENT_FLAGS_DWORD_COUNT	(256 / sizeof(u32))
-
-/* Define invalid partition identifier. */
-#define HV_PARTITION_ID_INVALID		((u64)0x0)
-
-/* Define port type. */
-enum hv_port_type {
-	HVPORT_MSG	= 1,
-	HVPORT_EVENT		= 2,
-	HVPORT_MONITOR	= 3
-};
-
-/* Define port information structure. */
-struct hv_port_info {
-	enum hv_port_type port_type;
-	u32 padding;
-	union {
-		struct {
-			u32 target_sint;
-			u32 target_vp;
-			u64 rsvdz;
-		} message_port_info;
-		struct {
-			u32 target_sint;
-			u32 target_vp;
-			u16 base_flag_number;
-			u16 flag_count;
-			u32 rsvdz;
-		} event_port_info;
-		struct {
-			u64 monitor_address;
-			u64 rsvdz;
-		} monitor_port_info;
-	};
-};
-
-struct hv_connection_info {
-	enum hv_port_type port_type;
-	u32 padding;
-	union {
-		struct {
-			u64 rsvdz;
-		} message_connection_info;
-		struct {
-			u64 rsvdz;
-		} event_connection_info;
-		struct {
-			u64 monitor_address;
-		} monitor_connection_info;
-	};
-};
 
 /*
  * Timer configuration register.
@@ -146,18 +61,10 @@ union hv_timer_config {
 	};
 };
 
-/* Define the number of message buffers associated with each port. */
-#define HV_PORT_MESSAGE_BUFFER_COUNT	(16)
 
 /* Define the synthetic interrupt controller event flags format. */
 union hv_synic_event_flags {
-	u8 flags8[HV_EVENT_FLAGS_BYTE_COUNT];
+	unsigned long flags[HV_EVENT_FLAGS_LONG_COUNT];
-	u32 flags32[HV_EVENT_FLAGS_DWORD_COUNT];
-};
-
-/* Define the synthetic interrupt flags page layout. */
-struct hv_synic_event_flags_page {
-	union hv_synic_event_flags sintevent_flags[HV_SYNIC_SINT_COUNT];
 };
 
 /* Define SynIC control register. */
@@ -261,6 +168,8 @@ struct hv_monitor_page {
 	u8 rsvdz4[1984];
 };
 
+#define HV_HYPERCALL_PARAM_ALIGN	sizeof(u64)
+
 /* Definition of the hv_post_message hypercall input structure. */
 struct hv_input_post_message {
 	union hv_connection_id connectionid;
@@ -270,56 +179,6 @@ struct hv_input_post_message {
 	u64 payload[HV_MESSAGE_PAYLOAD_QWORD_COUNT];
 };
 
-/*
- * Versioning definitions used for guests reporting themselves to the
- * hypervisor, and visa versa.
- */
-
-/* Version info reported by guest OS's */
-enum hv_guest_os_vendor {
-	HVGUESTOS_VENDOR_MICROSOFT	= 0x0001
-};
-
-enum hv_guest_os_microsoft_ids {
-	HVGUESTOS_MICROSOFT_UNDEFINED	= 0x00,
-	HVGUESTOS_MICROSOFT_MSDOS		= 0x01,
-	HVGUESTOS_MICROSOFT_WINDOWS3X	= 0x02,
-	HVGUESTOS_MICROSOFT_WINDOWS9X	= 0x03,
-	HVGUESTOS_MICROSOFT_WINDOWSNT	= 0x04,
-	HVGUESTOS_MICROSOFT_WINDOWSCE	= 0x05
-};
-
-/*
- * Declare the MSR used to identify the guest OS.
- */
-#define HV_X64_MSR_GUEST_OS_ID	0x40000000
-
-union hv_x64_msr_guest_os_id_contents {
-	u64 as_uint64;
-	struct {
-		u64 build_number:16;
-		u64 service_version:8; /* Service Pack, etc. */
-		u64 minor_version:8;
-		u64 major_version:8;
-		u64 os_id:8; /* enum hv_guest_os_microsoft_ids (if Vendor=MS) */
-		u64 vendor_id:16; /* enum hv_guest_os_vendor */
-	};
-};
-
-/*
- * Declare the MSR used to setup pages used to communicate with the hypervisor.
- */
-#define HV_X64_MSR_HYPERCALL	0x40000001
-
-union hv_x64_msr_hypercall_contents {
-	u64 as_uint64;
-	struct {
-		u64 enable:1;
-		u64 reserved:11;
-		u64 guest_physical_address:52;
-	};
-};
-
 
 enum {
 	VMBUS_MESSAGE_CONNECTION_ID	= 1,
@@ -331,111 +190,44 @@ enum {
 	VMBUS_MESSAGE_SINT		= 2,
 };
 
-/* #defines */
+/*
-
+ * Per cpu state for channel handling
-#define HV_PRESENT_BIT			0x80000000
+ */
+struct hv_per_cpu_context {
+	void *synic_message_page;
+	void *synic_event_page;
+	/*
+	 * buffer to post messages to the host.
+	 */
+	void *post_msg_page;
 
 	/*
- * The guest OS needs to register the guest ID with the hypervisor.
+	 * Starting with win8, we can take channel interrupts on any CPU;
- * The guest ID is a 64 bit entity and the structure of this ID is
+	 * we will manage the tasklet that handles events messages on a per CPU
- * specified in the Hyper-V specification:
+	 * basis.
- *
- * http://msdn.microsoft.com/en-us/library/windows/hardware/ff542653%28v=vs.85%29.aspx
- *
- * While the current guideline does not specify how Linux guest ID(s)
- * need to be generated, our plan is to publish the guidelines for
- * Linux and other guest operating systems that currently are hosted
- * on Hyper-V. The implementation here conforms to this yet
- * unpublished guidelines.
- *
- *
- * Bit(s)
- * 63 - Indicates if the OS is Open Source or not; 1 is Open Source
- * 62:56 - Os Type; Linux is 0x100
- * 55:48 - Distro specific identification
- * 47:16 - Linux kernel version number
- * 15:0  - Distro specific identification
- *
- *
 	 */
-
+	struct tasklet_struct msg_dpc;
-#define HV_LINUX_VENDOR_ID		0x8100
 
 	/*
- * Generate the guest ID based on the guideline described above.
+	 * To optimize the mapping of relid to channel, maintain
+	 * per-cpu list of the channels based on their CPU affinity.
 	 */
-
+	struct list_head chan_list;
-static inline  __u64 generate_guest_id(__u8 d_info1, __u32 kernel_version,
+	struct clock_event_device *clk_evt;
-					__u16 d_info2)
-{
-	__u64 guest_id = 0;
-
-	guest_id = (((__u64)HV_LINUX_VENDOR_ID) << 48);
-	guest_id |= (((__u64)(d_info1)) << 48);
-	guest_id |= (((__u64)(kernel_version)) << 16);
-	guest_id |= ((__u64)(d_info2));
-
-	return guest_id;
-}
-
-
-#define HV_CPU_POWER_MANAGEMENT		(1 << 0)
-#define HV_RECOMMENDATIONS_MAX		4
-
-#define HV_X64_MAX			5
-#define HV_CAPS_MAX			8
-
-
-#define HV_HYPERCALL_PARAM_ALIGN	sizeof(u64)
-
-
-/* Service definitions */
-
-#define HV_SERVICE_PARENT_PORT				(0)
-#define HV_SERVICE_PARENT_CONNECTION			(0)
-
-#define HV_SERVICE_CONNECT_RESPONSE_SUCCESS		(0)
-#define HV_SERVICE_CONNECT_RESPONSE_INVALID_PARAMETER	(1)
-#define HV_SERVICE_CONNECT_RESPONSE_UNKNOWN_SERVICE	(2)
-#define HV_SERVICE_CONNECT_RESPONSE_CONNECTION_REJECTED	(3)
-
-#define HV_SERVICE_CONNECT_REQUEST_MESSAGE_ID		(1)
-#define HV_SERVICE_CONNECT_RESPONSE_MESSAGE_ID		(2)
-#define HV_SERVICE_DISCONNECT_REQUEST_MESSAGE_ID	(3)
-#define HV_SERVICE_DISCONNECT_RESPONSE_MESSAGE_ID	(4)
-#define HV_SERVICE_MAX_MESSAGE_ID				(4)
-
-#define HV_SERVICE_PROTOCOL_VERSION (0x0010)
-#define HV_CONNECT_PAYLOAD_BYTE_COUNT 64
-
-/* #define VMBUS_REVISION_NUMBER	6 */
-
-/* Our local vmbus's port and connection id. Anything >0 is fine */
-/* #define VMBUS_PORT_ID		11 */
-
-/* 628180B8-308D-4c5e-B7DB-1BEB62E62EF4 */
-static const uuid_le VMBUS_SERVICE_ID = {
-	.b = {
-		0xb8, 0x80, 0x81, 0x62, 0x8d, 0x30, 0x5e, 0x4c,
-		0xb7, 0xdb, 0x1b, 0xeb, 0x62, 0xe6, 0x2e, 0xf4
-	},
 };
 
-
-
 struct hv_context {
 	/* We only support running on top of Hyper-V
 	* So at this point this really can only contain the Hyper-V ID
 	*/
 	u64 guestid;
 
-	void *hypercall_page;
 	void *tsc_page;
 
 	bool synic_initialized;
 
-	void *synic_message_page[NR_CPUS];
+	struct hv_per_cpu_context __percpu *cpu_context;
-	void *synic_event_page[NR_CPUS];
+
 	/*
 	 * Hypervisor's notion of virtual processor ID is different from
 	 * Linux' notion of CPU ID. This information can only be retrieved
@@ -446,26 +238,7 @@ struct hv_context {
 	 * Linux cpuid 'a'.
 	 */
 	u32 vp_index[NR_CPUS];
-	/*
+
-	 * Starting with win8, we can take channel interrupts on any CPU;
-	 * we will manage the tasklet that handles events messages on a per CPU
-	 * basis.
-	 */
-	struct tasklet_struct *event_dpc[NR_CPUS];
-	struct tasklet_struct *msg_dpc[NR_CPUS];
-	/*
-	 * To optimize the mapping of relid to channel, maintain
-	 * per-cpu list of the channels based on their CPU affinity.
-	 */
-	struct list_head percpu_list[NR_CPUS];
-	/*
-	 * buffer to post messages to the host.
-	 */
-	void *post_msg_page[NR_CPUS];
-	/*
-	 * Support PV clockevent device.
-	 */
-	struct clock_event_device *clk_evt[NR_CPUS];
 	/*
 	 * To manage allocations in a NUMA node.
 	 * Array indexed by numa node ID.
@@ -475,14 +248,6 @@ struct hv_context {
 
 extern struct hv_context hv_context;
 
-struct ms_hyperv_tsc_page {
-	volatile u32 tsc_sequence;
-	u32 reserved1;
-	volatile u64 tsc_scale;
-	volatile s64 tsc_offset;
-	u64 reserved2[509];
-};
-
 struct hv_ring_buffer_debug_info {
 	u32 current_interrupt_mask;
 	u32 current_read_index;
@@ -495,8 +260,6 @@ struct hv_ring_buffer_debug_info {
 
 extern int hv_init(void);
 
-extern void hv_cleanup(bool crash);
-
 extern int hv_post_message(union hv_connection_id connection_id,
 			 enum hv_message_type message_type,
 			 void *payload, size_t payload_size);
@@ -505,20 +268,12 @@ extern int hv_synic_alloc(void);
 
 extern void hv_synic_free(void);
 
-extern void hv_synic_init(void *irqarg);
+extern int hv_synic_init(unsigned int cpu);
 
-extern void hv_synic_cleanup(void *arg);
+extern int hv_synic_cleanup(unsigned int cpu);
 
 extern void hv_synic_clockevents_cleanup(void);
 
-/*
- * Host version information.
- */
-extern unsigned int host_info_eax;
-extern unsigned int host_info_ebx;
-extern unsigned int host_info_ecx;
-extern unsigned int host_info_edx;
-
 /* Interface */
 
 
@@ -528,21 +283,15 @@ int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info,
 void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info);
 
 int hv_ringbuffer_write(struct vmbus_channel *channel,
-		    struct kvec *kv_list,
+			const struct kvec *kv_list, u32 kv_count);
-		    u32 kv_count, bool lock,
-		    bool kick_q);
 
 int hv_ringbuffer_read(struct vmbus_channel *channel,
 		       void *buffer, u32 buflen, u32 *buffer_actual_len,
 		       u64 *requestid, bool raw);
 
-void hv_ringbuffer_get_debuginfo(struct hv_ring_buffer_info *ring_info,
+void hv_ringbuffer_get_debuginfo(const struct hv_ring_buffer_info *ring_info,
 				 struct hv_ring_buffer_debug_info *debug_info);
 
-void hv_begin_read(struct hv_ring_buffer_info *rbi);
-
-u32 hv_end_read(struct hv_ring_buffer_info *rbi);
-
 /*
  * Maximum channels is determined by the size of the interrupt page
  * which is PAGE_SIZE. 1/2 of PAGE_SIZE is for send endpoint interrupt
@@ -608,6 +357,11 @@ struct vmbus_msginfo {
 
 extern struct vmbus_connection vmbus_connection;
 
+static inline void vmbus_send_interrupt(u32 relid)
+{
+	sync_set_bit(relid, vmbus_connection.send_int_page);
+}
+
 enum vmbus_message_handler_type {
 	/* The related handler can sleep. */
 	VMHT_BLOCKING = 0,
@@ -625,41 +379,6 @@ struct vmbus_channel_message_table_entry {
 extern struct vmbus_channel_message_table_entry
 	channel_message_table[CHANNELMSG_COUNT];
 
-/* Free the message slot and signal end-of-message if required */
-static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type)
-{
-	/*
-	 * On crash we're reading some other CPU's message page and we need
-	 * to be careful: this other CPU may already had cleared the header
-	 * and the host may already had delivered some other message there.
-	 * In case we blindly write msg->header.message_type we're going
-	 * to lose it. We can still lose a message of the same type but
-	 * we count on the fact that there can only be one
-	 * CHANNELMSG_UNLOAD_RESPONSE and we don't care about other messages
-	 * on crash.
-	 */
-	if (cmpxchg(&msg->header.message_type, old_msg_type,
-		    HVMSG_NONE) != old_msg_type)
-		return;
-
-	/*
-	 * Make sure the write to MessageType (ie set to
-	 * HVMSG_NONE) happens before we read the
-	 * MessagePending and EOMing. Otherwise, the EOMing
-	 * will not deliver any more messages since there is
-	 * no empty slot
-	 */
-	mb();
-
-	if (msg->header.message_flags.msg_pending) {
-		/*
-		 * This will cause message queue rescan to
-		 * possibly deliver another msg from the
-		 * hypervisor
-		 */
-		wrmsrl(HV_X64_MSR_EOM, 0);
-	}
-}
 
 /* General vmbus interface */
 
@@ -670,10 +389,6 @@ struct hv_device *vmbus_device_create(const uuid_le *type,
 int vmbus_device_register(struct hv_device *child_device_obj);
 void vmbus_device_unregister(struct hv_device *device_obj);
 
-/* static void */
-/* VmbusChildDeviceDestroy( */
-/* struct hv_device *); */
-
 struct vmbus_channel *relid2channel(u32 relid);
 
 void vmbus_free_channels(void);
@@ -683,7 +398,7 @@ void vmbus_free_channels(void);
 int vmbus_connect(void);
 void vmbus_disconnect(void);
 
-int vmbus_post_msg(void *buffer, size_t buflen);
+int vmbus_post_msg(void *buffer, size_t buflen, bool can_sleep);
 
 void vmbus_on_event(unsigned long data);
 void vmbus_on_msg_dpc(unsigned long data);

drivers/hv/ring_buffer.c

@@ -32,26 +32,6 @@
 
 #include "hyperv_vmbus.h"
 
-void hv_begin_read(struct hv_ring_buffer_info *rbi)
-{
-	rbi->ring_buffer->interrupt_mask = 1;
-	virt_mb();
-}
-
-u32 hv_end_read(struct hv_ring_buffer_info *rbi)
-{
-
-	rbi->ring_buffer->interrupt_mask = 0;
-	virt_mb();
-
-	/*
-	 * Now check to see if the ring buffer is still empty.
-	 * If it is not, we raced and we need to process new
-	 * incoming messages.
-	 */
-	return hv_get_bytes_to_read(rbi);
-}
-
 /*
  * When we write to the ring buffer, check if the host needs to
  * be signaled. Here is the details of this protocol:
@@ -77,8 +57,7 @@ u32 hv_end_read(struct hv_ring_buffer_info *rbi)
  * host logic is fixed.
  */
 
-static void hv_signal_on_write(u32 old_write, struct vmbus_channel *channel,
+static void hv_signal_on_write(u32 old_write, struct vmbus_channel *channel)
-			       bool kick_q)
 {
 	struct hv_ring_buffer_info *rbi = &channel->outbound;
 
@@ -117,11 +96,9 @@ hv_set_next_write_location(struct hv_ring_buffer_info *ring_info,
 
 /* Get the next read location for the specified ring buffer. */
 static inline u32
-hv_get_next_read_location(struct hv_ring_buffer_info *ring_info)
+hv_get_next_read_location(const struct hv_ring_buffer_info *ring_info)
 {
-	u32 next = ring_info->ring_buffer->read_index;
+	return ring_info->ring_buffer->read_index;
-
-	return next;
 }
 
 /*
@@ -129,13 +106,14 @@ hv_get_next_read_location(struct hv_ring_buffer_info *ring_info)
  * This allows the caller to skip.
  */
 static inline u32
-hv_get_next_readlocation_withoffset(struct hv_ring_buffer_info *ring_info,
+hv_get_next_readlocation_withoffset(const struct hv_ring_buffer_info *ring_info,
 				    u32 offset)
 {
 	u32 next = ring_info->ring_buffer->read_index;
 
 	next += offset;
-	next %= ring_info->ring_datasize;
+	if (next >= ring_info->ring_datasize)
+		next -= ring_info->ring_datasize;
 
 	return next;
 }
@@ -151,7 +129,7 @@ hv_set_next_read_location(struct hv_ring_buffer_info *ring_info,
 
 /* Get the size of the ring buffer. */
 static inline u32
-hv_get_ring_buffersize(struct hv_ring_buffer_info *ring_info)
+hv_get_ring_buffersize(const struct hv_ring_buffer_info *ring_info)
 {
 	return ring_info->ring_datasize;
 }
@@ -168,7 +146,7 @@ hv_get_ring_bufferindices(struct hv_ring_buffer_info *ring_info)
  * Assume there is enough room. Handles wrap-around in src case only!!
  */
 static u32 hv_copyfrom_ringbuffer(
-	struct hv_ring_buffer_info	*ring_info,
+	const struct hv_ring_buffer_info *ring_info,
 	void				*dest,
 	u32				destlen,
 	u32				start_read_offset)
@@ -179,7 +157,8 @@ static u32 hv_copyfrom_ringbuffer(
 	memcpy(dest, ring_buffer + start_read_offset, destlen);
 
 	start_read_offset += destlen;
-	start_read_offset %= ring_buffer_size;
+	if (start_read_offset >= ring_buffer_size)
+		start_read_offset -= ring_buffer_size;
 
 	return start_read_offset;
 }
@@ -192,7 +171,7 @@ static u32 hv_copyfrom_ringbuffer(
 static u32 hv_copyto_ringbuffer(
 	struct hv_ring_buffer_info	*ring_info,
 	u32				start_write_offset,
-	void				*src,
+	const void			*src,
 	u32				srclen)
 {
 	void *ring_buffer = hv_get_ring_buffer(ring_info);
@@ -201,13 +180,14 @@ static u32 hv_copyto_ringbuffer(
 	memcpy(ring_buffer + start_write_offset, src, srclen);
 
 	start_write_offset += srclen;
-	start_write_offset %= ring_buffer_size;
+	if (start_write_offset >= ring_buffer_size)
+		start_write_offset -= ring_buffer_size;
 
 	return start_write_offset;
 }
 
 /* Get various debug metrics for the specified ring buffer. */
-void hv_ringbuffer_get_debuginfo(struct hv_ring_buffer_info *ring_info,
+void hv_ringbuffer_get_debuginfo(const struct hv_ring_buffer_info *ring_info,
 				 struct hv_ring_buffer_debug_info *debug_info)
 {
 	u32 bytes_avail_towrite;
@@ -285,8 +265,7 @@ void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info)
 
 /* Write to the ring buffer. */
 int hv_ringbuffer_write(struct vmbus_channel *channel,
-		    struct kvec *kv_list, u32 kv_count, bool lock,
+			const struct kvec *kv_list, u32 kv_count)
-		    bool kick_q)
 {
 	int i = 0;
 	u32 bytes_avail_towrite;
@@ -298,12 +277,14 @@ int hv_ringbuffer_write(struct vmbus_channel *channel,
 	unsigned long flags = 0;
 	struct hv_ring_buffer_info *outring_info = &channel->outbound;
 
+	if (channel->rescind)
+		return -ENODEV;
+
 	for (i = 0; i < kv_count; i++)
 		totalbytes_towrite += kv_list[i].iov_len;
 
 	totalbytes_towrite += sizeof(u64);
 
-	if (lock)
 	spin_lock_irqsave(&outring_info->ring_lock, flags);
 
 	bytes_avail_towrite = hv_get_bytes_to_write(outring_info);
@@ -314,7 +295,6 @@ int hv_ringbuffer_write(struct vmbus_channel *channel,
 	 * is empty since the read index == write index.
 	 */
 	if (bytes_avail_towrite <= totalbytes_towrite) {
-		if (lock)
 		spin_unlock_irqrestore(&outring_info->ring_lock, flags);
 		return -EAGAIN;
 	}
@@ -346,10 +326,13 @@ int hv_ringbuffer_write(struct vmbus_channel *channel,
 	hv_set_next_write_location(outring_info, next_write_location);
 
 
-	if (lock)
 	spin_unlock_irqrestore(&outring_info->ring_lock, flags);
 
-	hv_signal_on_write(old_write, channel, kick_q);
+	hv_signal_on_write(old_write, channel);
+
+	if (channel->rescind)
+		return -ENODEV;
+
 	return 0;
 }
 

drivers/hv/vmbus_drv.c

@@ -54,31 +54,7 @@ static struct acpi_device  *hv_acpi_dev;
 
 static struct completion probe_event;
 
-
+static int hyperv_cpuhp_online;
-static void hyperv_report_panic(struct pt_regs *regs)
-{
-	static bool panic_reported;
-
-	/*
-	 * We prefer to report panic on 'die' chain as we have proper
-	 * registers to report, but if we miss it (e.g. on BUG()) we need
-	 * to report it on 'panic'.
-	 */
-	if (panic_reported)
-		return;
-	panic_reported = true;
-
-	wrmsrl(HV_X64_MSR_CRASH_P0, regs->ip);
-	wrmsrl(HV_X64_MSR_CRASH_P1, regs->ax);
-	wrmsrl(HV_X64_MSR_CRASH_P2, regs->bx);
-	wrmsrl(HV_X64_MSR_CRASH_P3, regs->cx);
-	wrmsrl(HV_X64_MSR_CRASH_P4, regs->dx);
-
-	/*
-	 * Let Hyper-V know there is crash data available
-	 */
-	wrmsrl(HV_X64_MSR_CRASH_CTL, HV_CRASH_CTL_CRASH_NOTIFY);
-}
 
 static int hyperv_panic_event(struct notifier_block *nb, unsigned long val,
 			      void *args)
@@ -859,9 +835,10 @@ static void vmbus_onmessage_work(struct work_struct *work)
 	kfree(ctx);
 }
 
-static void hv_process_timer_expiration(struct hv_message *msg, int cpu)
+static void hv_process_timer_expiration(struct hv_message *msg,
+					struct hv_per_cpu_context *hv_cpu)
 {
-	struct clock_event_device *dev = hv_context.clk_evt[cpu];
+	struct clock_event_device *dev = hv_cpu->clk_evt;
 
 	if (dev->event_handler)
 		dev->event_handler(dev);
@@ -871,8 +848,8 @@ static void hv_process_timer_expiration(struct hv_message *msg, int cpu)
 
 void vmbus_on_msg_dpc(unsigned long data)
 {
-	int cpu = smp_processor_id();
+	struct hv_per_cpu_context *hv_cpu = (void *)data;
-	void *page_addr = hv_context.synic_message_page[cpu];
+	void *page_addr = hv_cpu->synic_message_page;
 	struct hv_message *msg = (struct hv_message *)page_addr +
 				  VMBUS_MESSAGE_SINT;
 	struct vmbus_channel_message_header *hdr;
@@ -908,16 +885,88 @@ void vmbus_on_msg_dpc(unsigned long data)
 	vmbus_signal_eom(msg, message_type);
 }
 
+
+/*
+ * Direct callback for channels using other deferred processing
+ */
+static void vmbus_channel_isr(struct vmbus_channel *channel)
+{
+	void (*callback_fn)(void *);
+
+	callback_fn = READ_ONCE(channel->onchannel_callback);
+	if (likely(callback_fn != NULL))
+		(*callback_fn)(channel->channel_callback_context);
+}
+
+/*
+ * Schedule all channels with events pending
+ */
+static void vmbus_chan_sched(struct hv_per_cpu_context *hv_cpu)
+{
+	unsigned long *recv_int_page;
+	u32 maxbits, relid;
+
+	if (vmbus_proto_version < VERSION_WIN8) {
+		maxbits = MAX_NUM_CHANNELS_SUPPORTED;
+		recv_int_page = vmbus_connection.recv_int_page;
+	} else {
+		/*
+		 * When the host is win8 and beyond, the event page
+		 * can be directly checked to get the id of the channel
+		 * that has the interrupt pending.
+		 */
+		void *page_addr = hv_cpu->synic_event_page;
+		union hv_synic_event_flags *event
+			= (union hv_synic_event_flags *)page_addr +
+						 VMBUS_MESSAGE_SINT;
+
+		maxbits = HV_EVENT_FLAGS_COUNT;
+		recv_int_page = event->flags;
+	}
+
+	if (unlikely(!recv_int_page))
+		return;
+
+	for_each_set_bit(relid, recv_int_page, maxbits) {
+		struct vmbus_channel *channel;
+
+		if (!sync_test_and_clear_bit(relid, recv_int_page))
+			continue;
+
+		/* Special case - vmbus channel protocol msg */
+		if (relid == 0)
+			continue;
+
+		/* Find channel based on relid */
+		list_for_each_entry(channel, &hv_cpu->chan_list, percpu_list) {
+			if (channel->offermsg.child_relid != relid)
+				continue;
+
+			switch (channel->callback_mode) {
+			case HV_CALL_ISR:
+				vmbus_channel_isr(channel);
+				break;
+
+			case HV_CALL_BATCHED:
+				hv_begin_read(&channel->inbound);
+				/* fallthrough */
+			case HV_CALL_DIRECT:
+				tasklet_schedule(&channel->callback_event);
+			}
+		}
+	}
+}
+
 static void vmbus_isr(void)
 {
-	int cpu = smp_processor_id();
+	struct hv_per_cpu_context *hv_cpu
-	void *page_addr;
+		= this_cpu_ptr(hv_context.cpu_context);
+	void *page_addr = hv_cpu->synic_event_page;
 	struct hv_message *msg;
 	union hv_synic_event_flags *event;
 	bool handled = false;
 
-	page_addr = hv_context.synic_event_page[cpu];
+	if (unlikely(page_addr == NULL))
-	if (page_addr == NULL)
 		return;
 
 	event = (union hv_synic_event_flags *)page_addr +
@@ -932,10 +981,8 @@ static void vmbus_isr(void)
 		(vmbus_proto_version == VERSION_WIN7)) {
 
 		/* Since we are a child, we only need to check bit 0 */
-		if (sync_test_and_clear_bit(0,
+		if (sync_test_and_clear_bit(0, event->flags))
-			(unsigned long *) &event->flags32[0])) {
 			handled = true;
-		}
 	} else {
 		/*
 		 * Our host is win8 or above. The signaling mechanism
@@ -947,18 +994,17 @@ static void vmbus_isr(void)
 	}
 
 	if (handled)
-		tasklet_schedule(hv_context.event_dpc[cpu]);
+		vmbus_chan_sched(hv_cpu);
 
-
+	page_addr = hv_cpu->synic_message_page;
-	page_addr = hv_context.synic_message_page[cpu];
 	msg = (struct hv_message *)page_addr + VMBUS_MESSAGE_SINT;
 
 	/* Check if there are actual msgs to be processed */
 	if (msg->header.message_type != HVMSG_NONE) {
 		if (msg->header.message_type == HVMSG_TIMER_EXPIRED)
-			hv_process_timer_expiration(msg, cpu);
+			hv_process_timer_expiration(msg, hv_cpu);
 		else
-			tasklet_schedule(hv_context.msg_dpc[cpu]);
+			tasklet_schedule(&hv_cpu->msg_dpc);
 	}
 
 	add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR, 0);
@@ -986,7 +1032,7 @@ static int vmbus_bus_init(void)
 
 	ret = bus_register(&hv_bus);
 	if (ret)
-		goto err_cleanup;
+		return ret;
 
 	hv_setup_vmbus_irq(vmbus_isr);
 
@@ -997,14 +1043,16 @@ static int vmbus_bus_init(void)
 	 * Initialize the per-cpu interrupt state and
 	 * connect to the host.
 	 */
-	on_each_cpu(hv_synic_init, NULL, 1);
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/hyperv:online",
+				hv_synic_init, hv_synic_cleanup);
+	if (ret < 0)
+		goto err_alloc;
+	hyperv_cpuhp_online = ret;
+
 	ret = vmbus_connect();
 	if (ret)
 		goto err_connect;
 
-	if (vmbus_proto_version > VERSION_WIN7)
-		cpu_hotplug_disable();
-
 	/*
 	 * Only register if the crash MSRs are available
 	 */
@@ -1019,16 +1067,13 @@ static int vmbus_bus_init(void)
 	return 0;
 
 err_connect:
-	on_each_cpu(hv_synic_cleanup, NULL, 1);
+	cpuhp_remove_state(hyperv_cpuhp_online);
 err_alloc:
 	hv_synic_free();
 	hv_remove_vmbus_irq();
 
 	bus_unregister(&hv_bus);
 
-err_cleanup:
-	hv_cleanup(false);
-
 	return ret;
 }
 
@@ -1478,13 +1523,13 @@ static struct acpi_driver vmbus_acpi_driver = {
 
 static void hv_kexec_handler(void)
 {
-	int cpu;
-
 	hv_synic_clockevents_cleanup();
 	vmbus_initiate_unload(false);
-	for_each_online_cpu(cpu)
+	vmbus_connection.conn_state = DISCONNECTED;
-		smp_call_function_single(cpu, hv_synic_cleanup, NULL, 1);
+	/* Make sure conn_state is set as hv_synic_cleanup checks for it */
-	hv_cleanup(false);
+	mb();
+	cpuhp_remove_state(hyperv_cpuhp_online);
+	hyperv_cleanup();
 };
 
 static void hv_crash_handler(struct pt_regs *regs)
@@ -1495,8 +1540,9 @@ static void hv_crash_handler(struct pt_regs *regs)
 	 * doing the cleanup for current CPU only. This should be sufficient
 	 * for kdump.
 	 */
-	hv_synic_cleanup(NULL);
+	vmbus_connection.conn_state = DISCONNECTED;
-	hv_cleanup(true);
+	hv_synic_cleanup(smp_processor_id());
+	hyperv_cleanup();
 };
 
 static int __init hv_acpi_init(void)
@@ -1547,24 +1593,24 @@ static void __exit vmbus_exit(void)
 	hv_synic_clockevents_cleanup();
 	vmbus_disconnect();
 	hv_remove_vmbus_irq();
-	for_each_online_cpu(cpu)
+	for_each_online_cpu(cpu) {
-		tasklet_kill(hv_context.msg_dpc[cpu]);
+		struct hv_per_cpu_context *hv_cpu
+			= per_cpu_ptr(hv_context.cpu_context, cpu);
+
+		tasklet_kill(&hv_cpu->msg_dpc);
+	}
 	vmbus_free_channels();
+
 	if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) {
 		unregister_die_notifier(&hyperv_die_block);
 		atomic_notifier_chain_unregister(&panic_notifier_list,
 						 &hyperv_panic_block);
 	}
 	bus_unregister(&hv_bus);
-	hv_cleanup(false);
+
-	for_each_online_cpu(cpu) {
+	cpuhp_remove_state(hyperv_cpuhp_online);
-		tasklet_kill(hv_context.event_dpc[cpu]);
-		smp_call_function_single(cpu, hv_synic_cleanup, NULL, 1);
-	}
 	hv_synic_free();
 	acpi_bus_unregister_driver(&vmbus_acpi_driver);
-	if (vmbus_proto_version > VERSION_WIN7)
-		cpu_hotplug_enable();
 }
 
 

drivers/hwtracing/coresight/coresight-etm-perf.c

@@ -242,6 +242,7 @@ static void *etm_setup_aux(int event_cpu, void **pages,
 	if (!sink_ops(sink)->alloc_buffer)
 		goto err;
 
+	cpu = cpumask_first(mask);
 	/* Get the AUX specific data from the sink buffer */
 	event_data->snk_config =
 			sink_ops(sink)->alloc_buffer(sink, cpu, pages,

drivers/hwtracing/coresight/coresight-etm4x.c

@@ -216,10 +216,14 @@ static int etm4_parse_event_config(struct etmv4_drvdata *drvdata,
 		goto out;
 
 	/* Go from generic option to ETMv4 specifics */
-	if (attr->config & BIT(ETM_OPT_CYCACC))
+	if (attr->config & BIT(ETM_OPT_CYCACC)) {
-		config->cfg |= ETMv4_MODE_CYCACC;
+		config->cfg |= BIT(4);
+		/* TRM: Must program this for cycacc to work */
+		config->ccctlr = ETM_CYC_THRESHOLD_DEFAULT;
+	}
 	if (attr->config & BIT(ETM_OPT_TS))
-		config->cfg |= ETMv4_MODE_TIMESTAMP;
+		/* bit[11], Global timestamp tracing bit */
+		config->cfg |= BIT(11);
 
 out:
 	return ret;

drivers/hwtracing/coresight/coresight-etm4x.h

@@ -146,6 +146,7 @@
 #define ETM_ARCH_V4			0x40
 #define ETMv4_SYNC_MASK			0x1F
 #define ETM_CYC_THRESHOLD_MASK		0xFFF
+#define ETM_CYC_THRESHOLD_DEFAULT       0x100
 #define ETMv4_EVENT_MASK		0xFF
 #define ETM_CNTR_MAX_VAL		0xFFFF
 #define ETM_TRACEID_MASK		0x3f

drivers/hwtracing/coresight/coresight-stm.c

@@ -356,7 +356,7 @@ static void stm_generic_unlink(struct stm_data *stm_data,
 	if (!drvdata || !drvdata->csdev)
 		return;
 
-	stm_disable(drvdata->csdev, NULL);
+	coresight_disable(drvdata->csdev);
 }
 
 static phys_addr_t

drivers/memory/ti-aemif.c

@@ -20,6 +20,7 @@
 #include <linux/of.h>
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
+#include <linux/platform_data/ti-aemif.h>
 
 #define TA_SHIFT	2
 #define RHOLD_SHIFT	4
@@ -335,6 +336,8 @@ static int aemif_probe(struct platform_device *pdev)
 	struct device_node *np = dev->of_node;
 	struct device_node *child_np;
 	struct aemif_device *aemif;
+	struct aemif_platform_data *pdata;
+	struct of_dev_auxdata *dev_lookup;
 
 	if (np == NULL)
 		return 0;
@@ -343,6 +346,9 @@ static int aemif_probe(struct platform_device *pdev)
 	if (!aemif)
 		return -ENOMEM;
 
+	pdata = dev_get_platdata(&pdev->dev);
+	dev_lookup = pdata ? pdata->dev_lookup : NULL;
+
 	platform_set_drvdata(pdev, aemif);
 
 	aemif->clk = devm_clk_get(dev, NULL);
@@ -390,7 +396,7 @@ static int aemif_probe(struct platform_device *pdev)
 	 * parameters are set.
 	 */
 	for_each_available_child_of_node(np, child_np) {
-		ret = of_platform_populate(child_np, NULL, NULL, dev);
+		ret = of_platform_populate(child_np, NULL, dev_lookup, dev);
 		if (ret < 0)
 			goto error;
 	}

drivers/misc/Kconfig

@@ -474,11 +474,15 @@ config SRAM
 	bool "Generic on-chip SRAM driver"
 	depends on HAS_IOMEM
 	select GENERIC_ALLOCATOR
+	select SRAM_EXEC if ARM
 	help
 	  This driver allows you to declare a memory region to be managed by
 	  the genalloc API. It is supposed to be used for small on-chip SRAM
 	  areas found on many SoCs.
 
+config SRAM_EXEC
+	bool
+
 config VEXPRESS_SYSCFG
 	bool "Versatile Express System Configuration driver"
 	depends on VEXPRESS_CONFIG
@@ -487,6 +491,7 @@ config VEXPRESS_SYSCFG
 	  ARM Ltd. Versatile Express uses specialised platform configuration
 	  bus. System Configuration interface is one of the possible means
 	  of generating transactions on this bus.
+
 config PANEL
 	tristate "Parallel port LCD/Keypad Panel support"
 	depends on PARPORT
@@ -494,14 +499,14 @@ config PANEL
 	  Say Y here if you have an HD44780 or KS-0074 LCD connected to your
 	  parallel port. This driver also features 4 and 6-key keypads. The LCD
 	  is accessible through the /dev/lcd char device (10, 156), and the
-	  keypad through /dev/keypad (10, 185). Both require misc device to be
+	  keypad through /dev/keypad (10, 185). This code can either be
-	  enabled. This code can either be compiled as a module, or linked into
+	  compiled as a module, or linked into the kernel and started at boot.
-	  the kernel and started at boot. If you don't understand what all this
+	  If you don't understand what all this is about, say N.
-	  is about, say N.
+
+if PANEL
 
 config PANEL_PARPORT
 	int "Default parallel port number (0=LPT1)"
-	depends on PANEL
 	range 0 255
 	default "0"
 	---help---
@@ -513,7 +518,6 @@ config PANEL_PARPORT
 
 config PANEL_PROFILE
 	int "Default panel profile (0-5, 0=custom)"
-	depends on PANEL
 	range 0 5
 	default "5"
 	---help---
@@ -534,7 +538,7 @@ config PANEL_PROFILE
 	  for experts.
 
 config PANEL_KEYPAD
-	depends on PANEL && PANEL_PROFILE="0"
+	depends on PANEL_PROFILE="0"
 	int "Keypad type (0=none, 1=old 6 keys, 2=new 6 keys, 3=Nexcom 4 keys)"
 	range 0 3
 	default 0
@@ -551,7 +555,7 @@ config PANEL_KEYPAD
 	  supports simultaneous keys pressed when the keypad supports them.
 
 config PANEL_LCD
-	depends on PANEL && PANEL_PROFILE="0"
+	depends on PANEL_PROFILE="0"
 	int "LCD type (0=none, 1=custom, 2=old //, 3=ks0074, 4=hantronix, 5=Nexcom)"
 	range 0 5
 	default 0
@@ -574,7 +578,7 @@ config PANEL_LCD
 	   that those values changed from the 2.4 driver for better consistency.
 
 config PANEL_LCD_HEIGHT
-	depends on PANEL && PANEL_PROFILE="0" && PANEL_LCD="1"
+	depends on PANEL_PROFILE="0" && PANEL_LCD="1"
 	int "Number of lines on the LCD (1-2)"
 	range 1 2
 	default 2
@@ -583,7 +587,7 @@ config PANEL_LCD_HEIGHT
 	  It can either be 1 or 2.
 
 config PANEL_LCD_WIDTH
-	depends on PANEL && PANEL_PROFILE="0" && PANEL_LCD="1"
+	depends on PANEL_PROFILE="0" && PANEL_LCD="1"
 	int "Number of characters per line on the LCD (1-40)"
 	range 1 40
 	default 40
@@ -592,7 +596,7 @@ config PANEL_LCD_WIDTH
 	  Common values are 16,20,24,40.
 
 config PANEL_LCD_BWIDTH
-	depends on PANEL && PANEL_PROFILE="0" && PANEL_LCD="1"
+	depends on PANEL_PROFILE="0" && PANEL_LCD="1"
 	int "Internal LCD line width (1-40, 40 by default)"
 	range 1 40
 	default 40
@@ -608,7 +612,7 @@ config PANEL_LCD_BWIDTH
 	  If you don't know, put '40' here.
 
 config PANEL_LCD_HWIDTH
-	depends on PANEL && PANEL_PROFILE="0" && PANEL_LCD="1"
+	depends on PANEL_PROFILE="0" && PANEL_LCD="1"
 	int "Hardware LCD line width (1-64, 64 by default)"
 	range 1 64
 	default 64
@@ -622,7 +626,7 @@ config PANEL_LCD_HWIDTH
 	  64 here for a 2x40.
 
 config PANEL_LCD_CHARSET
-	depends on PANEL && PANEL_PROFILE="0" && PANEL_LCD="1"
+	depends on PANEL_PROFILE="0" && PANEL_LCD="1"
 	int "LCD character set (0=normal, 1=KS0074)"
 	range 0 1
 	default 0
@@ -638,7 +642,7 @@ config PANEL_LCD_CHARSET
 	  If you don't know, use the normal one (0).
 
 config PANEL_LCD_PROTO
-	depends on PANEL && PANEL_PROFILE="0" && PANEL_LCD="1"
+	depends on PANEL_PROFILE="0" && PANEL_LCD="1"
 	int "LCD communication mode (0=parallel 8 bits, 1=serial)"
 	range 0 1
 	default 0
@@ -651,7 +655,7 @@ config PANEL_LCD_PROTO
 	  parallel LCD, and 1 for a serial LCD.
 
 config PANEL_LCD_PIN_E
-	depends on PANEL && PANEL_PROFILE="0" && PANEL_LCD="1" && PANEL_LCD_PROTO="0"
+	depends on PANEL_PROFILE="0" && PANEL_LCD="1" && PANEL_LCD_PROTO="0"
         int "Parallel port pin number & polarity connected to the LCD E signal (-17...17) "
 	range -17 17
 	default 14
@@ -666,7 +670,7 @@ config PANEL_LCD_PIN_E
 	  Default for the 'E' pin in custom profile is '14' (AUTOFEED).
 
 config PANEL_LCD_PIN_RS
-	depends on PANEL && PANEL_PROFILE="0" && PANEL_LCD="1" && PANEL_LCD_PROTO="0"
+	depends on PANEL_PROFILE="0" && PANEL_LCD="1" && PANEL_LCD_PROTO="0"
         int "Parallel port pin number & polarity connected to the LCD RS signal (-17...17) "
 	range -17 17
 	default 17
@@ -681,7 +685,7 @@ config PANEL_LCD_PIN_RS
 	  Default for the 'RS' pin in custom profile is '17' (SELECT IN).
 
 config PANEL_LCD_PIN_RW
-	depends on PANEL && PANEL_PROFILE="0" && PANEL_LCD="1" && PANEL_LCD_PROTO="0"
+	depends on PANEL_PROFILE="0" && PANEL_LCD="1" && PANEL_LCD_PROTO="0"
         int "Parallel port pin number & polarity connected to the LCD RW signal (-17...17) "
 	range -17 17
 	default 16
@@ -696,7 +700,7 @@ config PANEL_LCD_PIN_RW
 	  Default for the 'RW' pin in custom profile is '16' (INIT).
 
 config PANEL_LCD_PIN_SCL
-	depends on PANEL && PANEL_PROFILE="0" && PANEL_LCD="1" && PANEL_LCD_PROTO!="0"
+	depends on PANEL_PROFILE="0" && PANEL_LCD="1" && PANEL_LCD_PROTO!="0"
         int "Parallel port pin number & polarity connected to the LCD SCL signal (-17...17) "
 	range -17 17
 	default 1
@@ -711,7 +715,7 @@ config PANEL_LCD_PIN_SCL
 	  Default for the 'SCL' pin in custom profile is '1' (STROBE).
 
 config PANEL_LCD_PIN_SDA
-	depends on PANEL && PANEL_PROFILE="0" && PANEL_LCD="1" && PANEL_LCD_PROTO!="0"
+	depends on PANEL_PROFILE="0" && PANEL_LCD="1" && PANEL_LCD_PROTO!="0"
         int "Parallel port pin number & polarity connected to the LCD SDA signal (-17...17) "
 	range -17 17
 	default 2
@@ -726,7 +730,7 @@ config PANEL_LCD_PIN_SDA
 	  Default for the 'SDA' pin in custom profile is '2' (D0).
 
 config PANEL_LCD_PIN_BL
-	depends on PANEL && PANEL_PROFILE="0" && PANEL_LCD="1"
+	depends on PANEL_PROFILE="0" && PANEL_LCD="1"
         int "Parallel port pin number & polarity connected to the LCD backlight signal (-17...17) "
 	range -17 17
 	default 0
@@ -741,7 +745,6 @@ config PANEL_LCD_PIN_BL
 	  Default for the 'BL' pin in custom profile is '0' (uncontrolled).
 
 config PANEL_CHANGE_MESSAGE
-	depends on PANEL
 	bool "Change LCD initialization message ?"
 	default "n"
 	---help---
@@ -754,7 +757,7 @@ config PANEL_CHANGE_MESSAGE
 	  say 'N' and keep the default message with the version.
 
 config PANEL_BOOT_MESSAGE
-	depends on PANEL && PANEL_CHANGE_MESSAGE="y"
+	depends on PANEL_CHANGE_MESSAGE="y"
 	string "New initialization message"
 	default ""
 	---help---
@@ -766,6 +769,8 @@ config PANEL_BOOT_MESSAGE
 	  An empty message will only clear the display at driver init time. Any other
 	  printf()-formatted message is valid with newline and escape codes.
 
+endif # PANEL
+
 source "drivers/misc/c2port/Kconfig"
 source "drivers/misc/eeprom/Kconfig"
 source "drivers/misc/cb710/Kconfig"

drivers/misc/Makefile

@@ -47,6 +47,7 @@ obj-$(CONFIG_INTEL_MEI)		+= mei/
 obj-$(CONFIG_VMWARE_VMCI)	+= vmw_vmci/
 obj-$(CONFIG_LATTICE_ECP3_CONFIG)	+= lattice-ecp3-config.o
 obj-$(CONFIG_SRAM)		+= sram.o
+obj-$(CONFIG_SRAM_EXEC)		+= sram-exec.o
 obj-y				+= mic/
 obj-$(CONFIG_GENWQE)		+= genwqe/
 obj-$(CONFIG_ECHO)		+= echo/

drivers/misc/eeprom/Kconfig

@@ -100,4 +100,14 @@ config EEPROM_DIGSY_MTC_CFG
 
 	  If unsure, say N.
 
+config EEPROM_IDT_89HPESX
+	tristate "IDT 89HPESx PCIe-swtiches EEPROM / CSR support"
+	depends on I2C && SYSFS
+	help
+	  Enable this driver to get read/write access to EEPROM / CSRs
+	  over IDT PCIe-swtich i2c-slave interface.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called idt_89hpesx.
+
 endmenu

drivers/misc/eeprom/Makefile

@@ -5,3 +5,4 @@ obj-$(CONFIG_EEPROM_MAX6875)	+= max6875.o
 obj-$(CONFIG_EEPROM_93CX6)	+= eeprom_93cx6.o
 obj-$(CONFIG_EEPROM_93XX46)	+= eeprom_93xx46.o
 obj-$(CONFIG_EEPROM_DIGSY_MTC_CFG) += digsy_mtc_eeprom.o
+obj-$(CONFIG_EEPROM_IDT_89HPESX) += idt_89hpesx.o

drivers/misc/genwqe/card_base.c

@@ -1336,7 +1336,6 @@ static int genwqe_sriov_configure(struct pci_dev *dev, int numvfs)
 static struct pci_error_handlers genwqe_err_handler = {
 	.error_detected = genwqe_err_error_detected,
 	.mmio_enabled	= genwqe_err_result_none,
-	.link_reset	= genwqe_err_result_none,
 	.slot_reset	= genwqe_err_slot_reset,
 	.resume		= genwqe_err_resume,
 };

drivers/misc/lkdtm_bugs.c

@@ -81,12 +81,17 @@ void lkdtm_OVERFLOW(void)
 	(void) recursive_loop(recur_count);
 }
 
+static noinline void __lkdtm_CORRUPT_STACK(void *stack)
+{
+	memset(stack, 'a', 64);
+}
+
 noinline void lkdtm_CORRUPT_STACK(void)
 {
 	/* Use default char array length that triggers stack protection. */
 	char data[8];
+	__lkdtm_CORRUPT_STACK(&data);
 
-	memset((void *)data, 'a', 64);
 	pr_info("Corrupted stack with '%16s'...\n", data);
 }
 

drivers/misc/lkdtm_core.c

@@ -539,7 +539,9 @@ static void __exit lkdtm_module_exit(void)
 	/* Handle test-specific clean-up. */
 	lkdtm_usercopy_exit();
 
+	if (lkdtm_jprobe != NULL)
 		unregister_jprobe(lkdtm_jprobe);
+
 	pr_info("Crash point unregistered\n");
 }
 

drivers/misc/mei/amthif.c

@@ -132,8 +132,7 @@ int mei_amthif_run_next_cmd(struct mei_device *dev)
 
 	dev_dbg(dev->dev, "complete amthif cmd_list cb.\n");
 
-	cb = list_first_entry_or_null(&dev->amthif_cmd_list.list,
+	cb = list_first_entry_or_null(&dev->amthif_cmd_list, typeof(*cb), list);
-					typeof(*cb), list);
 	if (!cb) {
 		dev->iamthif_state = MEI_IAMTHIF_IDLE;
 		cl->fp = NULL;
@@ -167,7 +166,7 @@ int mei_amthif_write(struct mei_cl *cl, struct mei_cl_cb *cb)
 
 	struct mei_device *dev = cl->dev;
 
-	list_add_tail(&cb->list, &dev->amthif_cmd_list.list);
+	list_add_tail(&cb->list, &dev->amthif_cmd_list);
 
 	/*
 	 * The previous request is still in processing, queue this one.
@@ -211,7 +210,7 @@ unsigned int mei_amthif_poll(struct file *file, poll_table *wait)
  * Return: 0, OK; otherwise, error.
  */
 int mei_amthif_irq_write(struct mei_cl *cl, struct mei_cl_cb *cb,
-			 struct mei_cl_cb *cmpl_list)
+			 struct list_head *cmpl_list)
 {
 	int ret;
 
@@ -237,7 +236,7 @@ int mei_amthif_irq_write(struct mei_cl *cl, struct mei_cl_cb *cb,
  */
 int mei_amthif_irq_read_msg(struct mei_cl *cl,
 			    struct mei_msg_hdr *mei_hdr,
-			    struct mei_cl_cb *cmpl_list)
+			    struct list_head *cmpl_list)
 {
 	struct mei_device *dev;
 	int ret;
@@ -311,51 +310,31 @@ void mei_amthif_complete(struct mei_cl *cl, struct mei_cl_cb *cb)
 	}
 }
 
-/**
- * mei_clear_list - removes all callbacks associated with file
- *		from mei_cb_list
- *
- * @file: file structure
- * @mei_cb_list: callbacks list
- *
- * mei_clear_list is called to clear resources associated with file
- * when application calls close function or Ctrl-C was pressed
- */
-static void mei_clear_list(const struct file *file,
-			   struct list_head *mei_cb_list)
-{
-	struct mei_cl_cb *cb, *next;
-
-	list_for_each_entry_safe(cb, next, mei_cb_list, list)
-		if (file == cb->fp)
-			mei_io_cb_free(cb);
-}
-
 /**
 * mei_amthif_release - the release function
 *
 *  @dev: device structure
-*  @file: pointer to file structure
+*  @fp: pointer to file structure
 *
 *  Return: 0 on success, <0 on error
 */
-int mei_amthif_release(struct mei_device *dev, struct file *file)
+int mei_amthif_release(struct mei_device *dev, struct file *fp)
 {
-	struct mei_cl *cl = file->private_data;
+	struct mei_cl *cl = fp->private_data;
 
 	if (dev->iamthif_open_count > 0)
 		dev->iamthif_open_count--;
 
-	if (cl->fp == file && dev->iamthif_state != MEI_IAMTHIF_IDLE) {
+	if (cl->fp == fp && dev->iamthif_state != MEI_IAMTHIF_IDLE) {
 
 		dev_dbg(dev->dev, "amthif canceled iamthif state %d\n",
 			dev->iamthif_state);
 		dev->iamthif_canceled = true;
 	}
 
-	mei_clear_list(file, &dev->amthif_cmd_list.list);
+	/* Don't clean ctrl_rd_list here, the reads has to be completed */
-	mei_clear_list(file, &cl->rd_completed);
+	mei_io_list_free_fp(&dev->amthif_cmd_list, fp);
-	mei_clear_list(file, &dev->ctrl_rd_list.list);
+	mei_io_list_free_fp(&cl->rd_completed, fp);
 
 	return 0;
 }

drivers/misc/mei/bus.c

@@ -498,6 +498,25 @@ int mei_cldev_enable(struct mei_cl_device *cldev)
 }
 EXPORT_SYMBOL_GPL(mei_cldev_enable);
 
+/**
+ * mei_cldev_unregister_callbacks - internal wrapper for unregistering
+ *  callbacks.
+ *
+ * @cldev: client device
+ */
+static void mei_cldev_unregister_callbacks(struct mei_cl_device *cldev)
+{
+	if (cldev->rx_cb) {
+		cancel_work_sync(&cldev->rx_work);
+		cldev->rx_cb = NULL;
+	}
+
+	if (cldev->notif_cb) {
+		cancel_work_sync(&cldev->notif_work);
+		cldev->notif_cb = NULL;
+	}
+}
+
 /**
  * mei_cldev_disable - disable me client device
  *     disconnect form the me client
@@ -519,6 +538,8 @@ int mei_cldev_disable(struct mei_cl_device *cldev)
 
 	bus = cldev->bus;
 
+	mei_cldev_unregister_callbacks(cldev);
+
 	mutex_lock(&bus->device_lock);
 
 	if (!mei_cl_is_connected(cl)) {
@@ -541,6 +562,37 @@ int mei_cldev_disable(struct mei_cl_device *cldev)
 }
 EXPORT_SYMBOL_GPL(mei_cldev_disable);
 
+/**
+ * mei_cl_bus_module_get - acquire module of the underlying
+ *    hw module.
+ *
+ * @cl: host client
+ *
+ * Return: true on success; false if the module was removed.
+ */
+bool mei_cl_bus_module_get(struct mei_cl *cl)
+{
+	struct mei_cl_device *cldev = cl->cldev;
+
+	if (!cldev)
+		return true;
+
+	return try_module_get(cldev->bus->dev->driver->owner);
+}
+
+/**
+ * mei_cl_bus_module_put -  release the underlying hw module.
+ *
+ * @cl: host client
+ */
+void mei_cl_bus_module_put(struct mei_cl *cl)
+{
+	struct mei_cl_device *cldev = cl->cldev;
+
+	if (cldev)
+		module_put(cldev->bus->dev->driver->owner);
+}
+
 /**
  * mei_cl_device_find - find matching entry in the driver id table
  *
@@ -665,19 +717,12 @@ static int mei_cl_device_remove(struct device *dev)
 	if (!cldev || !dev->driver)
 		return 0;
 
-	if (cldev->rx_cb) {
-		cancel_work_sync(&cldev->rx_work);
-		cldev->rx_cb = NULL;
-	}
-	if (cldev->notif_cb) {
-		cancel_work_sync(&cldev->notif_work);
-		cldev->notif_cb = NULL;
-	}
-
 	cldrv = to_mei_cl_driver(dev->driver);
 	if (cldrv->remove)
 		ret = cldrv->remove(cldev);
 
+	mei_cldev_unregister_callbacks(cldev);
+
 	module_put(THIS_MODULE);
 	dev->driver = NULL;
 	return ret;

drivers/misc/mei/client.c

@@ -377,19 +377,19 @@ static struct mei_cl_cb *mei_io_cb_init(struct mei_cl *cl,
 }
 
 /**
- * __mei_io_list_flush - removes and frees cbs belonging to cl.
+ * __mei_io_list_flush_cl - removes and frees cbs belonging to cl.
  *
- * @list:  an instance of our list structure
+ * @head:  an instance of our list structure
  * @cl:    host client, can be NULL for flushing the whole list
  * @free:  whether to free the cbs
  */
-static void __mei_io_list_flush(struct mei_cl_cb *list,
+static void __mei_io_list_flush_cl(struct list_head *head,
-				struct mei_cl *cl, bool free)
+				   const struct mei_cl *cl, bool free)
 {
 	struct mei_cl_cb *cb, *next;
 
 	/* enable removing everything if no cl is specified */
-	list_for_each_entry_safe(cb, next, &list->list, list) {
+	list_for_each_entry_safe(cb, next, head, list) {
 		if (!cl || mei_cl_cmp_id(cl, cb->cl)) {
 			list_del_init(&cb->list);
 			if (free)
@@ -399,25 +399,42 @@ static void __mei_io_list_flush(struct mei_cl_cb *list,
 }
 
 /**
- * mei_io_list_flush - removes list entry belonging to cl.
+ * mei_io_list_flush_cl - removes list entry belonging to cl.
  *
- * @list:  An instance of our list structure
+ * @head: An instance of our list structure
  * @cl: host client
  */
-void mei_io_list_flush(struct mei_cl_cb *list, struct mei_cl *cl)
+static inline void mei_io_list_flush_cl(struct list_head *head,
+					const struct mei_cl *cl)
 {
-	__mei_io_list_flush(list, cl, false);
+	__mei_io_list_flush_cl(head, cl, false);
 }
 
 /**
- * mei_io_list_free - removes cb belonging to cl and free them
+ * mei_io_list_free_cl - removes cb belonging to cl and free them
  *
- * @list:  An instance of our list structure
+ * @head: An instance of our list structure
  * @cl: host client
  */
-static inline void mei_io_list_free(struct mei_cl_cb *list, struct mei_cl *cl)
+static inline void mei_io_list_free_cl(struct list_head *head,
+				       const struct mei_cl *cl)
 {
-	__mei_io_list_flush(list, cl, true);
+	__mei_io_list_flush_cl(head, cl, true);
+}
+
+/**
+ * mei_io_list_free_fp - free cb from a list that matches file pointer
+ *
+ * @head: io list
+ * @fp: file pointer (matching cb file object), may be NULL
+ */
+void mei_io_list_free_fp(struct list_head *head, const struct file *fp)
+{
+	struct mei_cl_cb *cb, *next;
+
+	list_for_each_entry_safe(cb, next, head, list)
+		if (!fp || fp == cb->fp)
+			mei_io_cb_free(cb);
 }
 
 /**
@@ -479,7 +496,7 @@ struct mei_cl_cb *mei_cl_enqueue_ctrl_wr_cb(struct mei_cl *cl, size_t length,
 	if (!cb)
 		return NULL;
 
-	list_add_tail(&cb->list, &cl->dev->ctrl_wr_list.list);
+	list_add_tail(&cb->list, &cl->dev->ctrl_wr_list);
 	return cb;
 }
 
@@ -503,27 +520,6 @@ struct mei_cl_cb *mei_cl_read_cb(const struct mei_cl *cl, const struct file *fp)
 	return NULL;
 }
 
-/**
- * mei_cl_read_cb_flush - free client's read pending and completed cbs
- *   for a specific file
- *
- * @cl: host client
- * @fp: file pointer (matching cb file object), may be NULL
- */
-void mei_cl_read_cb_flush(const struct mei_cl *cl, const struct file *fp)
-{
-	struct mei_cl_cb *cb, *next;
-
-	list_for_each_entry_safe(cb, next, &cl->rd_completed, list)
-		if (!fp || fp == cb->fp)
-			mei_io_cb_free(cb);
-
-
-	list_for_each_entry_safe(cb, next, &cl->rd_pending, list)
-		if (!fp || fp == cb->fp)
-			mei_io_cb_free(cb);
-}
-
 /**
  * mei_cl_flush_queues - flushes queue lists belonging to cl.
  *
@@ -542,18 +538,16 @@ int mei_cl_flush_queues(struct mei_cl *cl, const struct file *fp)
 	dev = cl->dev;
 
 	cl_dbg(dev, cl, "remove list entry belonging to cl\n");
-	mei_io_list_free(&cl->dev->write_list, cl);
+	mei_io_list_free_cl(&cl->dev->write_list, cl);
-	mei_io_list_free(&cl->dev->write_waiting_list, cl);
+	mei_io_list_free_cl(&cl->dev->write_waiting_list, cl);
-	mei_io_list_flush(&cl->dev->ctrl_wr_list, cl);
+	mei_io_list_flush_cl(&cl->dev->ctrl_wr_list, cl);
-	mei_io_list_flush(&cl->dev->ctrl_rd_list, cl);
+	mei_io_list_flush_cl(&cl->dev->ctrl_rd_list, cl);
-	mei_io_list_flush(&cl->dev->amthif_cmd_list, cl);
+	mei_io_list_free_fp(&cl->rd_pending, fp);
-
+	mei_io_list_free_fp(&cl->rd_completed, fp);
-	mei_cl_read_cb_flush(cl, fp);
 
 	return 0;
 }
 
-
 /**
  * mei_cl_init - initializes cl.
  *
@@ -756,7 +750,7 @@ static void mei_cl_wake_all(struct mei_cl *cl)
  *
  * @cl: host client
  */
-void mei_cl_set_disconnected(struct mei_cl *cl)
+static void mei_cl_set_disconnected(struct mei_cl *cl)
 {
 	struct mei_device *dev = cl->dev;
 
@@ -765,15 +759,18 @@ void mei_cl_set_disconnected(struct mei_cl *cl)
 		return;
 
 	cl->state = MEI_FILE_DISCONNECTED;
-	mei_io_list_free(&dev->write_list, cl);
+	mei_io_list_free_cl(&dev->write_list, cl);
-	mei_io_list_free(&dev->write_waiting_list, cl);
+	mei_io_list_free_cl(&dev->write_waiting_list, cl);
-	mei_io_list_flush(&dev->ctrl_rd_list, cl);
+	mei_io_list_flush_cl(&dev->ctrl_rd_list, cl);
-	mei_io_list_flush(&dev->ctrl_wr_list, cl);
+	mei_io_list_flush_cl(&dev->ctrl_wr_list, cl);
+	mei_io_list_free_cl(&dev->amthif_cmd_list, cl);
 	mei_cl_wake_all(cl);
 	cl->rx_flow_ctrl_creds = 0;
 	cl->tx_flow_ctrl_creds = 0;
 	cl->timer_count = 0;
 
+	mei_cl_bus_module_put(cl);
+
 	if (!cl->me_cl)
 		return;
 
@@ -829,7 +826,7 @@ static int mei_cl_send_disconnect(struct mei_cl *cl, struct mei_cl_cb *cb)
 		return ret;
 	}
 
-	list_move_tail(&cb->list, &dev->ctrl_rd_list.list);
+	list_move_tail(&cb->list, &dev->ctrl_rd_list);
 	cl->timer_count = MEI_CONNECT_TIMEOUT;
 	mei_schedule_stall_timer(dev);
 
@@ -847,7 +844,7 @@ static int mei_cl_send_disconnect(struct mei_cl *cl, struct mei_cl_cb *cb)
  * Return: 0, OK; otherwise, error.
  */
 int mei_cl_irq_disconnect(struct mei_cl *cl, struct mei_cl_cb *cb,
-			    struct mei_cl_cb *cmpl_list)
+			  struct list_head *cmpl_list)
 {
 	struct mei_device *dev = cl->dev;
 	u32 msg_slots;
@@ -862,7 +859,7 @@ int mei_cl_irq_disconnect(struct mei_cl *cl, struct mei_cl_cb *cb,
 
 	ret = mei_cl_send_disconnect(cl, cb);
 	if (ret)
-		list_move_tail(&cb->list, &cmpl_list->list);
+		list_move_tail(&cb->list, cmpl_list);
 
 	return ret;
 }
@@ -984,7 +981,7 @@ static bool mei_cl_is_other_connecting(struct mei_cl *cl)
 
 	dev = cl->dev;
 
-	list_for_each_entry(cb, &dev->ctrl_rd_list.list, list) {
+	list_for_each_entry(cb, &dev->ctrl_rd_list, list) {
 		if (cb->fop_type == MEI_FOP_CONNECT &&
 		    mei_cl_me_id(cl) == mei_cl_me_id(cb->cl))
 			return true;
@@ -1015,7 +1012,7 @@ static int mei_cl_send_connect(struct mei_cl *cl, struct mei_cl_cb *cb)
 		return ret;
 	}
 
-	list_move_tail(&cb->list, &dev->ctrl_rd_list.list);
+	list_move_tail(&cb->list, &dev->ctrl_rd_list);
 	cl->timer_count = MEI_CONNECT_TIMEOUT;
 	mei_schedule_stall_timer(dev);
 	return 0;
@@ -1031,7 +1028,7 @@ static int mei_cl_send_connect(struct mei_cl *cl, struct mei_cl_cb *cb)
  * Return: 0, OK; otherwise, error.
  */
 int mei_cl_irq_connect(struct mei_cl *cl, struct mei_cl_cb *cb,
-			      struct mei_cl_cb *cmpl_list)
+		       struct list_head *cmpl_list)
 {
 	struct mei_device *dev = cl->dev;
 	u32 msg_slots;
@@ -1049,7 +1046,7 @@ int mei_cl_irq_connect(struct mei_cl *cl, struct mei_cl_cb *cb,
 
 	rets = mei_cl_send_connect(cl, cb);
 	if (rets)
-		list_move_tail(&cb->list, &cmpl_list->list);
+		list_move_tail(&cb->list, cmpl_list);
 
 	return rets;
 }
@@ -1077,13 +1074,17 @@ int mei_cl_connect(struct mei_cl *cl, struct mei_me_client *me_cl,
 
 	dev = cl->dev;
 
+	if (!mei_cl_bus_module_get(cl))
+		return -ENODEV;
+
 	rets = mei_cl_set_connecting(cl, me_cl);
 	if (rets)
-		return rets;
+		goto nortpm;
 
 	if (mei_cl_is_fixed_address(cl)) {
 		cl->state = MEI_FILE_CONNECTED;
-		return 0;
+		rets = 0;
+		goto nortpm;
 	}
 
 	rets = pm_runtime_get(dev->dev);
@@ -1117,8 +1118,8 @@ int mei_cl_connect(struct mei_cl *cl, struct mei_me_client *me_cl,
 
 	if (!mei_cl_is_connected(cl)) {
 		if (cl->state == MEI_FILE_DISCONNECT_REQUIRED) {
-			mei_io_list_flush(&dev->ctrl_rd_list, cl);
+			mei_io_list_flush_cl(&dev->ctrl_rd_list, cl);
-			mei_io_list_flush(&dev->ctrl_wr_list, cl);
+			mei_io_list_flush_cl(&dev->ctrl_wr_list, cl);
 			 /* ignore disconnect return valuue;
 			  * in case of failure reset will be invoked
 			  */
@@ -1270,7 +1271,7 @@ enum mei_cb_file_ops mei_cl_notify_req2fop(u8 req)
  * Return: 0 on such and error otherwise.
  */
 int mei_cl_irq_notify(struct mei_cl *cl, struct mei_cl_cb *cb,
-		      struct mei_cl_cb *cmpl_list)
+		      struct list_head *cmpl_list)
 {
 	struct mei_device *dev = cl->dev;
 	u32 msg_slots;
@@ -1288,11 +1289,11 @@ int mei_cl_irq_notify(struct mei_cl *cl, struct mei_cl_cb *cb,
 	ret = mei_hbm_cl_notify_req(dev, cl, request);
 	if (ret) {
 		cl->status = ret;
-		list_move_tail(&cb->list, &cmpl_list->list);
+		list_move_tail(&cb->list, cmpl_list);
 		return ret;
 	}
 
-	list_move_tail(&cb->list, &dev->ctrl_rd_list.list);
+	list_move_tail(&cb->list, &dev->ctrl_rd_list);
 	return 0;
 }
 
@@ -1325,6 +1326,9 @@ int mei_cl_notify_request(struct mei_cl *cl,
 		return -EOPNOTSUPP;
 	}
 
+	if (!mei_cl_is_connected(cl))
+		return -ENODEV;
+
 	rets = pm_runtime_get(dev->dev);
 	if (rets < 0 && rets != -EINPROGRESS) {
 		pm_runtime_put_noidle(dev->dev);
@@ -1344,7 +1348,7 @@ int mei_cl_notify_request(struct mei_cl *cl,
 			rets = -ENODEV;
 			goto out;
 		}
-		list_move_tail(&cb->list, &dev->ctrl_rd_list.list);
+		list_move_tail(&cb->list, &dev->ctrl_rd_list);
 	}
 
 	mutex_unlock(&dev->device_lock);
@@ -1419,6 +1423,11 @@ int mei_cl_notify_get(struct mei_cl *cl, bool block, bool *notify_ev)
 
 	dev = cl->dev;
 
+	if (!dev->hbm_f_ev_supported) {
+		cl_dbg(dev, cl, "notifications not supported\n");
+		return -EOPNOTSUPP;
+	}
+
 	if (!mei_cl_is_connected(cl))
 		return -ENODEV;
 
@@ -1519,7 +1528,7 @@ int mei_cl_read_start(struct mei_cl *cl, size_t length, const struct file *fp)
  * Return: 0, OK; otherwise error.
  */
 int mei_cl_irq_write(struct mei_cl *cl, struct mei_cl_cb *cb,
-		     struct mei_cl_cb *cmpl_list)
+		     struct list_head *cmpl_list)
 {
 	struct mei_device *dev;
 	struct mei_msg_data *buf;
@@ -1591,13 +1600,13 @@ int mei_cl_irq_write(struct mei_cl *cl, struct mei_cl_cb *cb,
 	}
 
 	if (mei_hdr.msg_complete)
-		list_move_tail(&cb->list, &dev->write_waiting_list.list);
+		list_move_tail(&cb->list, &dev->write_waiting_list);
 
 	return 0;
 
 err:
 	cl->status = rets;
-	list_move_tail(&cb->list, &cmpl_list->list);
+	list_move_tail(&cb->list, cmpl_list);
 	return rets;
 }
 
@@ -1687,9 +1696,9 @@ int mei_cl_write(struct mei_cl *cl, struct mei_cl_cb *cb)
 
 out:
 	if (mei_hdr.msg_complete)
-		list_add_tail(&cb->list, &dev->write_waiting_list.list);
+		list_add_tail(&cb->list, &dev->write_waiting_list);
 	else
-		list_add_tail(&cb->list, &dev->write_list.list);
+		list_add_tail(&cb->list, &dev->write_list);
 
 	cb = NULL;
 	if (blocking && cl->writing_state != MEI_WRITE_COMPLETE) {

drivers/misc/mei/client.h

@@ -83,17 +83,7 @@ static inline u8 mei_me_cl_ver(const struct mei_me_client *me_cl)
  * MEI IO Functions
  */
 void mei_io_cb_free(struct mei_cl_cb *priv_cb);
-
+void mei_io_list_free_fp(struct list_head *head, const struct file *fp);
-/**
- * mei_io_list_init - Sets up a queue list.
- *
- * @list: An instance cl callback structure
- */
-static inline void mei_io_list_init(struct mei_cl_cb *list)
-{
-	INIT_LIST_HEAD(&list->list);
-}
-void mei_io_list_flush(struct mei_cl_cb *list, struct mei_cl *cl);
 
 /*
  * MEI Host Client Functions
@@ -110,7 +100,6 @@ struct mei_cl *mei_cl_alloc_linked(struct mei_device *dev);
 
 struct mei_cl_cb *mei_cl_read_cb(const struct mei_cl *cl,
 				 const struct file *fp);
-void mei_cl_read_cb_flush(const struct mei_cl *cl, const struct file *fp);
 struct mei_cl_cb *mei_cl_alloc_cb(struct mei_cl *cl, size_t length,
 				  enum mei_cb_file_ops type,
 				  const struct file *fp);
@@ -209,19 +198,18 @@ static inline u8 mei_cl_host_addr(const struct mei_cl *cl)
 }
 
 int mei_cl_disconnect(struct mei_cl *cl);
-void mei_cl_set_disconnected(struct mei_cl *cl);
 int mei_cl_irq_disconnect(struct mei_cl *cl, struct mei_cl_cb *cb,
-			  struct mei_cl_cb *cmpl_list);
+			  struct list_head *cmpl_list);
 int mei_cl_connect(struct mei_cl *cl, struct mei_me_client *me_cl,
 		   const struct file *file);
 int mei_cl_irq_connect(struct mei_cl *cl, struct mei_cl_cb *cb,
-			      struct mei_cl_cb *cmpl_list);
+		       struct list_head *cmpl_list);
 int mei_cl_read_start(struct mei_cl *cl, size_t length, const struct file *fp);
 int mei_cl_irq_read_msg(struct mei_cl *cl, struct mei_msg_hdr *hdr,
-			struct mei_cl_cb *cmpl_list);
+			struct list_head *cmpl_list);
 int mei_cl_write(struct mei_cl *cl, struct mei_cl_cb *cb);
 int mei_cl_irq_write(struct mei_cl *cl, struct mei_cl_cb *cb,
-		     struct mei_cl_cb *cmpl_list);
+		     struct list_head *cmpl_list);
 
 void mei_cl_complete(struct mei_cl *cl, struct mei_cl_cb *cb);
 
@@ -232,7 +220,7 @@ enum mei_cb_file_ops mei_cl_notify_req2fop(u8 request);
 int mei_cl_notify_request(struct mei_cl *cl,
 			  const struct file *file, u8 request);
 int mei_cl_irq_notify(struct mei_cl *cl, struct mei_cl_cb *cb,
-		      struct mei_cl_cb *cmpl_list);
+		      struct list_head *cmpl_list);
 int mei_cl_notify_get(struct mei_cl *cl, bool block, bool *notify_ev);
 void mei_cl_notify(struct mei_cl *cl);
 

drivers/misc/mei/hbm.c

@@ -815,7 +815,7 @@ static void mei_hbm_cl_res(struct mei_device *dev,
 	struct mei_cl_cb *cb, *next;
 
 	cl = NULL;
-	list_for_each_entry_safe(cb, next, &dev->ctrl_rd_list.list, list) {
+	list_for_each_entry_safe(cb, next, &dev->ctrl_rd_list, list) {
 
 		cl = cb->cl;
 

drivers/misc/mei/hw-me.c

@@ -139,6 +139,19 @@ static inline void mei_hcsr_set(struct mei_device *dev, u32 reg)
 	mei_hcsr_write(dev, reg);
 }
 
+/**
+ * mei_hcsr_set_hig - set host interrupt (set H_IG)
+ *
+ * @dev: the device structure
+ */
+static inline void mei_hcsr_set_hig(struct mei_device *dev)
+{
+	u32 hcsr;
+
+	hcsr = mei_hcsr_read(dev) | H_IG;
+	mei_hcsr_set(dev, hcsr);
+}
+
 /**
  * mei_me_d0i3c_read - Reads 32bit data from the D0I3C register
  *
@@ -380,6 +393,19 @@ static bool mei_me_hw_is_ready(struct mei_device *dev)
 	return (mecsr & ME_RDY_HRA) == ME_RDY_HRA;
 }
 
+/**
+ * mei_me_hw_is_resetting - check whether the me(hw) is in reset
+ *
+ * @dev: mei device
+ * Return: bool
+ */
+static bool mei_me_hw_is_resetting(struct mei_device *dev)
+{
+	u32 mecsr = mei_me_mecsr_read(dev);
+
+	return (mecsr & ME_RST_HRA) == ME_RST_HRA;
+}
+
 /**
  * mei_me_hw_ready_wait - wait until the me(hw) has turned ready
  *  or timeout is reached
@@ -505,7 +531,6 @@ static int mei_me_hbuf_write(struct mei_device *dev,
 	unsigned long rem;
 	unsigned long length = header->length;
 	u32 *reg_buf = (u32 *)buf;
-	u32 hcsr;
 	u32 dw_cnt;
 	int i;
 	int empty_slots;
@@ -532,8 +557,7 @@ static int mei_me_hbuf_write(struct mei_device *dev,
 		mei_me_hcbww_write(dev, reg);
 	}
 
-	hcsr = mei_hcsr_read(dev) | H_IG;
+	mei_hcsr_set_hig(dev);
-	mei_hcsr_set(dev, hcsr);
 	if (!mei_me_hw_is_ready(dev))
 		return -EIO;
 
@@ -580,7 +604,6 @@ static int mei_me_read_slots(struct mei_device *dev, unsigned char *buffer,
 		    unsigned long buffer_length)
 {
 	u32 *reg_buf = (u32 *)buffer;
-	u32 hcsr;
 
 	for (; buffer_length >= sizeof(u32); buffer_length -= sizeof(u32))
 		*reg_buf++ = mei_me_mecbrw_read(dev);
@@ -591,8 +614,7 @@ static int mei_me_read_slots(struct mei_device *dev, unsigned char *buffer,
 		memcpy(reg_buf, &reg, buffer_length);
 	}
 
-	hcsr = mei_hcsr_read(dev) | H_IG;
+	mei_hcsr_set_hig(dev);
-	mei_hcsr_set(dev, hcsr);
 	return 0;
 }
 
@@ -1189,7 +1211,7 @@ irqreturn_t mei_me_irq_quick_handler(int irq, void *dev_id)
 irqreturn_t mei_me_irq_thread_handler(int irq, void *dev_id)
 {
 	struct mei_device *dev = (struct mei_device *) dev_id;
-	struct mei_cl_cb complete_list;
+	struct list_head cmpl_list;
 	s32 slots;
 	u32 hcsr;
 	int rets = 0;
@@ -1201,7 +1223,7 @@ irqreturn_t mei_me_irq_thread_handler(int irq, void *dev_id)
 	hcsr = mei_hcsr_read(dev);
 	me_intr_clear(dev, hcsr);
 
-	mei_io_list_init(&complete_list);
+	INIT_LIST_HEAD(&cmpl_list);
 
 	/* check if ME wants a reset */
 	if (!mei_hw_is_ready(dev) && dev->dev_state != MEI_DEV_RESETTING) {
@@ -1210,6 +1232,9 @@ irqreturn_t mei_me_irq_thread_handler(int irq, void *dev_id)
 		goto end;
 	}
 
+	if (mei_me_hw_is_resetting(dev))
+		mei_hcsr_set_hig(dev);
+
 	mei_me_pg_intr(dev, me_intr_src(hcsr));
 
 	/*  check if we need to start the dev */
@@ -1227,7 +1252,7 @@ irqreturn_t mei_me_irq_thread_handler(int irq, void *dev_id)
 	slots = mei_count_full_read_slots(dev);
 	while (slots > 0) {
 		dev_dbg(dev->dev, "slots to read = %08x\n", slots);
-		rets = mei_irq_read_handler(dev, &complete_list, &slots);
+		rets = mei_irq_read_handler(dev, &cmpl_list, &slots);
 		/* There is a race between ME write and interrupt delivery:
 		 * Not all data is always available immediately after the
 		 * interrupt, so try to read again on the next interrupt.
@@ -1252,11 +1277,11 @@ irqreturn_t mei_me_irq_thread_handler(int irq, void *dev_id)
 	 */
 	if (dev->pg_event != MEI_PG_EVENT_WAIT &&
 	    dev->pg_event != MEI_PG_EVENT_RECEIVED) {
-		rets = mei_irq_write_handler(dev, &complete_list);
+		rets = mei_irq_write_handler(dev, &cmpl_list);
 		dev->hbuf_is_ready = mei_hbuf_is_ready(dev);
 	}
 
-	mei_irq_compl_handler(dev, &complete_list);
+	mei_irq_compl_handler(dev, &cmpl_list);
 
 end:
 	dev_dbg(dev->dev, "interrupt thread end ret = %d\n", rets);
@@ -1389,7 +1414,7 @@ const struct mei_cfg mei_me_pch8_sps_cfg = {
  * @pdev: The pci device structure
  * @cfg: per device generation config
  *
- * Return: The mei_device_device pointer on success, NULL on failure.
+ * Return: The mei_device pointer on success, NULL on failure.
  */
 struct mei_device *mei_me_dev_init(struct pci_dev *pdev,
 				   const struct mei_cfg *cfg)
@@ -1397,7 +1422,7 @@ struct mei_device *mei_me_dev_init(struct pci_dev *pdev,
 	struct mei_device *dev;
 	struct mei_me_hw *hw;
 
-	dev = kzalloc(sizeof(struct mei_device) +
+	dev = devm_kzalloc(&pdev->dev, sizeof(struct mei_device) +
 			   sizeof(struct mei_me_hw), GFP_KERNEL);
 	if (!dev)
 		return NULL;

drivers/misc/mei/hw-txe.c

@@ -1057,7 +1057,7 @@ irqreturn_t mei_txe_irq_thread_handler(int irq, void *dev_id)
 {
 	struct mei_device *dev = (struct mei_device *) dev_id;
 	struct mei_txe_hw *hw = to_txe_hw(dev);
-	struct mei_cl_cb complete_list;
+	struct list_head cmpl_list;
 	s32 slots;
 	int rets = 0;
 
@@ -1069,7 +1069,7 @@ irqreturn_t mei_txe_irq_thread_handler(int irq, void *dev_id)
 
 	/* initialize our complete list */
 	mutex_lock(&dev->device_lock);
-	mei_io_list_init(&complete_list);
+	INIT_LIST_HEAD(&cmpl_list);
 
 	if (pci_dev_msi_enabled(to_pci_dev(dev->dev)))
 		mei_txe_check_and_ack_intrs(dev, true);
@@ -1126,7 +1126,7 @@ irqreturn_t mei_txe_irq_thread_handler(int irq, void *dev_id)
 	slots = mei_count_full_read_slots(dev);
 	if (test_and_clear_bit(TXE_INTR_OUT_DB_BIT, &hw->intr_cause)) {
 		/* Read from TXE */
-		rets = mei_irq_read_handler(dev, &complete_list, &slots);
+		rets = mei_irq_read_handler(dev, &cmpl_list, &slots);
 		if (rets && dev->dev_state != MEI_DEV_RESETTING) {
 			dev_err(dev->dev,
 				"mei_irq_read_handler ret = %d.\n", rets);
@@ -1144,14 +1144,14 @@ irqreturn_t mei_txe_irq_thread_handler(int irq, void *dev_id)
 	if (hw->aliveness && dev->hbuf_is_ready) {
 		/* get the real register value */
 		dev->hbuf_is_ready = mei_hbuf_is_ready(dev);
-		rets = mei_irq_write_handler(dev, &complete_list);
+		rets = mei_irq_write_handler(dev, &cmpl_list);
 		if (rets && rets != -EMSGSIZE)
 			dev_err(dev->dev, "mei_irq_write_handler ret = %d.\n",
 				rets);
 		dev->hbuf_is_ready = mei_hbuf_is_ready(dev);
 	}
 
-	mei_irq_compl_handler(dev, &complete_list);
+	mei_irq_compl_handler(dev, &cmpl_list);
 
 end:
 	dev_dbg(dev->dev, "interrupt thread end ret = %d\n", rets);
@@ -1207,7 +1207,7 @@ struct mei_device *mei_txe_dev_init(struct pci_dev *pdev)
 	struct mei_device *dev;
 	struct mei_txe_hw *hw;
 
-	dev = kzalloc(sizeof(struct mei_device) +
+	dev = devm_kzalloc(&pdev->dev, sizeof(struct mei_device) +
 			   sizeof(struct mei_txe_hw), GFP_KERNEL);
 	if (!dev)
 		return NULL;

drivers/misc/mei/hw-txe.h

@@ -45,7 +45,7 @@
  * @intr_cause:          translated interrupt cause
  */
 struct mei_txe_hw {
-	void __iomem *mem_addr[NUM_OF_MEM_BARS];
+	void __iomem * const *mem_addr;
 	u32 aliveness;
 	u32 readiness;
 	u32 slots;

drivers/misc/mei/init.c

@@ -349,16 +349,16 @@ EXPORT_SYMBOL_GPL(mei_stop);
 bool mei_write_is_idle(struct mei_device *dev)
 {
 	bool idle = (dev->dev_state == MEI_DEV_ENABLED &&
-		list_empty(&dev->ctrl_wr_list.list) &&
+		list_empty(&dev->ctrl_wr_list) &&
-		list_empty(&dev->write_list.list)   &&
+		list_empty(&dev->write_list)   &&
-		list_empty(&dev->write_waiting_list.list));
+		list_empty(&dev->write_waiting_list));
 
 	dev_dbg(dev->dev, "write pg: is idle[%d] state=%s ctrl=%01d write=%01d wwait=%01d\n",
 		idle,
 		mei_dev_state_str(dev->dev_state),
-		list_empty(&dev->ctrl_wr_list.list),
+		list_empty(&dev->ctrl_wr_list),
-		list_empty(&dev->write_list.list),
+		list_empty(&dev->write_list),
-		list_empty(&dev->write_waiting_list.list));
+		list_empty(&dev->write_waiting_list));
 
 	return idle;
 }
@@ -388,17 +388,17 @@ void mei_device_init(struct mei_device *dev,
 	dev->dev_state = MEI_DEV_INITIALIZING;
 	dev->reset_count = 0;
 
-	mei_io_list_init(&dev->write_list);
+	INIT_LIST_HEAD(&dev->write_list);
-	mei_io_list_init(&dev->write_waiting_list);
+	INIT_LIST_HEAD(&dev->write_waiting_list);
-	mei_io_list_init(&dev->ctrl_wr_list);
+	INIT_LIST_HEAD(&dev->ctrl_wr_list);
-	mei_io_list_init(&dev->ctrl_rd_list);
+	INIT_LIST_HEAD(&dev->ctrl_rd_list);
 
 	INIT_DELAYED_WORK(&dev->timer_work, mei_timer);
 	INIT_WORK(&dev->reset_work, mei_reset_work);
 	INIT_WORK(&dev->bus_rescan_work, mei_cl_bus_rescan_work);
 
 	INIT_LIST_HEAD(&dev->iamthif_cl.link);
-	mei_io_list_init(&dev->amthif_cmd_list);
+	INIT_LIST_HEAD(&dev->amthif_cmd_list);
 
 	bitmap_zero(dev->host_clients_map, MEI_CLIENTS_MAX);
 	dev->open_handle_count = 0;

drivers/misc/mei/interrupt.c

@@ -35,14 +35,14 @@
  *	for the completed callbacks
  *
  * @dev: mei device
- * @compl_list: list of completed cbs
+ * @cmpl_list: list of completed cbs
  */
-void mei_irq_compl_handler(struct mei_device *dev, struct mei_cl_cb *compl_list)
+void mei_irq_compl_handler(struct mei_device *dev, struct list_head *cmpl_list)
 {
 	struct mei_cl_cb *cb, *next;
 	struct mei_cl *cl;
 
-	list_for_each_entry_safe(cb, next, &compl_list->list, list) {
+	list_for_each_entry_safe(cb, next, cmpl_list, list) {
 		cl = cb->cl;
 		list_del_init(&cb->list);
 
@@ -92,13 +92,13 @@ void mei_irq_discard_msg(struct mei_device *dev, struct mei_msg_hdr *hdr)
  *
  * @cl: reading client
  * @mei_hdr: header of mei client message
- * @complete_list: completion list
+ * @cmpl_list: completion list
  *
  * Return: always 0
  */
 int mei_cl_irq_read_msg(struct mei_cl *cl,
 		       struct mei_msg_hdr *mei_hdr,
-		       struct mei_cl_cb *complete_list)
+		       struct list_head *cmpl_list)
 {
 	struct mei_device *dev = cl->dev;
 	struct mei_cl_cb *cb;
@@ -144,7 +144,7 @@ int mei_cl_irq_read_msg(struct mei_cl *cl,
 
 	if (mei_hdr->msg_complete) {
 		cl_dbg(dev, cl, "completed read length = %zu\n", cb->buf_idx);
-		list_move_tail(&cb->list, &complete_list->list);
+		list_move_tail(&cb->list, cmpl_list);
 	} else {
 		pm_runtime_mark_last_busy(dev->dev);
 		pm_request_autosuspend(dev->dev);
@@ -154,7 +154,7 @@ int mei_cl_irq_read_msg(struct mei_cl *cl,
 
 discard:
 	if (cb)
-		list_move_tail(&cb->list, &complete_list->list);
+		list_move_tail(&cb->list, cmpl_list);
 	mei_irq_discard_msg(dev, mei_hdr);
 	return 0;
 }
@@ -169,7 +169,7 @@ int mei_cl_irq_read_msg(struct mei_cl *cl,
  * Return: 0, OK; otherwise, error.
  */
 static int mei_cl_irq_disconnect_rsp(struct mei_cl *cl, struct mei_cl_cb *cb,
-				     struct mei_cl_cb *cmpl_list)
+				     struct list_head *cmpl_list)
 {
 	struct mei_device *dev = cl->dev;
 	u32 msg_slots;
@@ -183,7 +183,7 @@ static int mei_cl_irq_disconnect_rsp(struct mei_cl *cl, struct mei_cl_cb *cb,
 		return -EMSGSIZE;
 
 	ret = mei_hbm_cl_disconnect_rsp(dev, cl);
-	list_move_tail(&cb->list, &cmpl_list->list);
+	list_move_tail(&cb->list, cmpl_list);
 
 	return ret;
 }
@@ -199,7 +199,7 @@ static int mei_cl_irq_disconnect_rsp(struct mei_cl *cl, struct mei_cl_cb *cb,
  * Return: 0, OK; otherwise, error.
  */
 static int mei_cl_irq_read(struct mei_cl *cl, struct mei_cl_cb *cb,
-			   struct mei_cl_cb *cmpl_list)
+			   struct list_head *cmpl_list)
 {
 	struct mei_device *dev = cl->dev;
 	u32 msg_slots;
@@ -219,7 +219,7 @@ static int mei_cl_irq_read(struct mei_cl *cl, struct mei_cl_cb *cb,
 	if (ret) {
 		cl->status = ret;
 		cb->buf_idx = 0;
-		list_move_tail(&cb->list, &cmpl_list->list);
+		list_move_tail(&cb->list, cmpl_list);
 		return ret;
 	}
 
@@ -249,7 +249,7 @@ static inline bool hdr_is_fixed(struct mei_msg_hdr *mei_hdr)
  * Return: 0 on success, <0 on failure.
  */
 int mei_irq_read_handler(struct mei_device *dev,
-		struct mei_cl_cb *cmpl_list, s32 *slots)
+			 struct list_head *cmpl_list, s32 *slots)
 {
 	struct mei_msg_hdr *mei_hdr;
 	struct mei_cl *cl;
@@ -347,12 +347,11 @@ EXPORT_SYMBOL_GPL(mei_irq_read_handler);
  *
  * Return: 0 on success, <0 on failure.
  */
-int mei_irq_write_handler(struct mei_device *dev, struct mei_cl_cb *cmpl_list)
+int mei_irq_write_handler(struct mei_device *dev, struct list_head *cmpl_list)
 {
 
 	struct mei_cl *cl;
 	struct mei_cl_cb *cb, *next;
-	struct mei_cl_cb *list;
 	s32 slots;
 	int ret;
 
@@ -367,19 +366,18 @@ int mei_irq_write_handler(struct mei_device *dev, struct mei_cl_cb *cmpl_list)
 	/* complete all waiting for write CB */
 	dev_dbg(dev->dev, "complete all waiting for write cb.\n");
 
-	list = &dev->write_waiting_list;
+	list_for_each_entry_safe(cb, next, &dev->write_waiting_list, list) {
-	list_for_each_entry_safe(cb, next, &list->list, list) {
 		cl = cb->cl;
 
 		cl->status = 0;
 		cl_dbg(dev, cl, "MEI WRITE COMPLETE\n");
 		cl->writing_state = MEI_WRITE_COMPLETE;
-		list_move_tail(&cb->list, &cmpl_list->list);
+		list_move_tail(&cb->list, cmpl_list);
 	}
 
 	/* complete control write list CB */
 	dev_dbg(dev->dev, "complete control write list cb.\n");
-	list_for_each_entry_safe(cb, next, &dev->ctrl_wr_list.list, list) {
+	list_for_each_entry_safe(cb, next, &dev->ctrl_wr_list, list) {
 		cl = cb->cl;
 		switch (cb->fop_type) {
 		case MEI_FOP_DISCONNECT:
@@ -423,7 +421,7 @@ int mei_irq_write_handler(struct mei_device *dev, struct mei_cl_cb *cmpl_list)
 	}
 	/* complete  write list CB */
 	dev_dbg(dev->dev, "complete write list cb.\n");
-	list_for_each_entry_safe(cb, next, &dev->write_list.list, list) {
+	list_for_each_entry_safe(cb, next, &dev->write_list, list) {
 		cl = cb->cl;
 		if (cl == &dev->iamthif_cl)
 			ret = mei_amthif_irq_write(cl, cb, cmpl_list);

drivers/misc/mei/main.c

@@ -182,32 +182,36 @@ static ssize_t mei_read(struct file *file, char __user *ubuf,
 		goto out;
 	}
 
-	if (rets == -EBUSY &&
-	    !mei_cl_enqueue_ctrl_wr_cb(cl, length, MEI_FOP_READ, file)) {
-		rets = -ENOMEM;
-		goto out;
-	}
 
-	do {
+again:
 	mutex_unlock(&dev->device_lock);
-
 	if (wait_event_interruptible(cl->rx_wait,
-					     (!list_empty(&cl->rd_completed)) ||
+				     !list_empty(&cl->rd_completed) ||
-					     (!mei_cl_is_connected(cl)))) {
+				     !mei_cl_is_connected(cl))) {
-
 		if (signal_pending(current))
 			return -EINTR;
 		return -ERESTARTSYS;
 	}
-
 	mutex_lock(&dev->device_lock);
+
 	if (!mei_cl_is_connected(cl)) {
 		rets = -ENODEV;
 		goto out;
 	}
 
 	cb = mei_cl_read_cb(cl, file);
-	} while (!cb);
+	if (!cb) {
+		/*
+		 * For amthif all the waiters are woken up,
+		 * but only fp with matching cb->fp get the cb,
+		 * the others have to return to wait on read.
+		 */
+		if (cl == &dev->iamthif_cl)
+			goto again;
+
+		rets = 0;
+		goto out;
+	}
 
 copy_buffer:
 	/* now copy the data to user space */

drivers/misc/mei/mei_dev.h

@@ -328,6 +328,8 @@ ssize_t __mei_cl_recv(struct mei_cl *cl, u8 *buf, size_t length,
 bool mei_cl_bus_rx_event(struct mei_cl *cl);
 bool mei_cl_bus_notify_event(struct mei_cl *cl);
 void mei_cl_bus_remove_devices(struct mei_device *bus);
+bool mei_cl_bus_module_get(struct mei_cl *cl);
+void mei_cl_bus_module_put(struct mei_cl *cl);
 int mei_cl_bus_init(void);
 void mei_cl_bus_exit(void);
 
@@ -439,10 +441,10 @@ struct mei_device {
 	struct cdev cdev;
 	int minor;
 
-	struct mei_cl_cb write_list;
+	struct list_head write_list;
-	struct mei_cl_cb write_waiting_list;
+	struct list_head write_waiting_list;
-	struct mei_cl_cb ctrl_wr_list;
+	struct list_head ctrl_wr_list;
-	struct mei_cl_cb ctrl_rd_list;
+	struct list_head ctrl_rd_list;
 
 	struct list_head file_list;
 	long open_handle_count;
@@ -499,7 +501,7 @@ struct mei_device {
 	bool override_fixed_address;
 
 	/* amthif list for cmd waiting */
-	struct mei_cl_cb amthif_cmd_list;
+	struct list_head amthif_cmd_list;
 	struct mei_cl iamthif_cl;
 	long iamthif_open_count;
 	u32 iamthif_stall_timer;
@@ -571,10 +573,10 @@ void mei_cancel_work(struct mei_device *dev);
 void mei_timer(struct work_struct *work);
 void mei_schedule_stall_timer(struct mei_device *dev);
 int mei_irq_read_handler(struct mei_device *dev,
-		struct mei_cl_cb *cmpl_list, s32 *slots);
+			 struct list_head *cmpl_list, s32 *slots);
 
-int mei_irq_write_handler(struct mei_device *dev, struct mei_cl_cb *cmpl_list);
+int mei_irq_write_handler(struct mei_device *dev, struct list_head *cmpl_list);
-void mei_irq_compl_handler(struct mei_device *dev, struct mei_cl_cb *cmpl_list);
+void mei_irq_compl_handler(struct mei_device *dev, struct list_head *cmpl_list);
 
 /*
  * AMTHIF - AMT Host Interface Functions
@@ -590,12 +592,12 @@ int mei_amthif_release(struct mei_device *dev, struct file *file);
 int mei_amthif_write(struct mei_cl *cl, struct mei_cl_cb *cb);
 int mei_amthif_run_next_cmd(struct mei_device *dev);
 int mei_amthif_irq_write(struct mei_cl *cl, struct mei_cl_cb *cb,
-			struct mei_cl_cb *cmpl_list);
+			 struct list_head *cmpl_list);
 
 void mei_amthif_complete(struct mei_cl *cl, struct mei_cl_cb *cb);
 int mei_amthif_irq_read_msg(struct mei_cl *cl,
 			    struct mei_msg_hdr *mei_hdr,
-			    struct mei_cl_cb *complete_list);
+			    struct list_head *cmpl_list);
 int mei_amthif_irq_read(struct mei_device *dev, s32 *slots);
 
 /*

drivers/misc/mei/pci-me.c

@@ -149,18 +149,18 @@ static int mei_me_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		return -ENODEV;
 
 	/* enable pci dev */
-	err = pci_enable_device(pdev);
+	err = pcim_enable_device(pdev);
 	if (err) {
 		dev_err(&pdev->dev, "failed to enable pci device.\n");
 		goto end;
 	}
 	/* set PCI host mastering  */
 	pci_set_master(pdev);
-	/* pci request regions for mei driver */
+	/* pci request regions and mapping IO device memory for mei driver */
-	err = pci_request_regions(pdev, KBUILD_MODNAME);
+	err = pcim_iomap_regions(pdev, BIT(0), KBUILD_MODNAME);
 	if (err) {
 		dev_err(&pdev->dev, "failed to get pci regions.\n");
-		goto disable_device;
+		goto end;
 	}
 
 	if (dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)) ||
@@ -173,24 +173,18 @@ static int mei_me_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 	if (err) {
 		dev_err(&pdev->dev, "No usable DMA configuration, aborting\n");
-		goto release_regions;
+		goto end;
 	}
 
-
 	/* allocates and initializes the mei dev structure */
 	dev = mei_me_dev_init(pdev, cfg);
 	if (!dev) {
 		err = -ENOMEM;
-		goto release_regions;
+		goto end;
 	}
 	hw = to_me_hw(dev);
-	/* mapping  IO device memory */
+	hw->mem_addr = pcim_iomap_table(pdev)[0];
-	hw->mem_addr = pci_iomap(pdev, 0, 0);
+
-	if (!hw->mem_addr) {
-		dev_err(&pdev->dev, "mapping I/O device memory failure.\n");
-		err = -ENOMEM;
-		goto free_device;
-	}
 	pci_enable_msi(pdev);
 
 	 /* request and enable interrupt */
@@ -203,7 +197,7 @@ static int mei_me_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (err) {
 		dev_err(&pdev->dev, "request_threaded_irq failure. irq = %d\n",
 		       pdev->irq);
-		goto disable_msi;
+		goto end;
 	}
 
 	if (mei_start(dev)) {
@@ -242,15 +236,6 @@ static int mei_me_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	mei_cancel_work(dev);
 	mei_disable_interrupts(dev);
 	free_irq(pdev->irq, dev);
-disable_msi:
-	pci_disable_msi(pdev);
-	pci_iounmap(pdev, hw->mem_addr);
-free_device:
-	kfree(dev);
-release_regions:
-	pci_release_regions(pdev);
-disable_device:
-	pci_disable_device(pdev);
 end:
 	dev_err(&pdev->dev, "initialization failed.\n");
 	return err;
@@ -267,7 +252,6 @@ static int mei_me_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 static void mei_me_remove(struct pci_dev *pdev)
 {
 	struct mei_device *dev;
-	struct mei_me_hw *hw;
 
 	dev = pci_get_drvdata(pdev);
 	if (!dev)
@@ -276,33 +260,19 @@ static void mei_me_remove(struct pci_dev *pdev)
 	if (mei_pg_is_enabled(dev))
 		pm_runtime_get_noresume(&pdev->dev);
 
-	hw = to_me_hw(dev);
-
-
 	dev_dbg(&pdev->dev, "stop\n");
 	mei_stop(dev);
 
 	if (!pci_dev_run_wake(pdev))
 		mei_me_unset_pm_domain(dev);
 
-	/* disable interrupts */
 	mei_disable_interrupts(dev);
 
 	free_irq(pdev->irq, dev);
-	pci_disable_msi(pdev);
-
-	if (hw->mem_addr)
-		pci_iounmap(pdev, hw->mem_addr);
 
 	mei_deregister(dev);
-
-	kfree(dev);
-
-	pci_release_regions(pdev);
-	pci_disable_device(pdev);
-
-
 }
+
 #ifdef CONFIG_PM_SLEEP
 static int mei_me_pci_suspend(struct device *device)
 {

drivers/misc/mei/pci-txe.c

@@ -52,17 +52,6 @@ static inline void mei_txe_set_pm_domain(struct mei_device *dev) {}
 static inline void mei_txe_unset_pm_domain(struct mei_device *dev) {}
 #endif /* CONFIG_PM */
 
-static void mei_txe_pci_iounmap(struct pci_dev *pdev, struct mei_txe_hw *hw)
-{
-	int i;
-
-	for (i = SEC_BAR; i < NUM_OF_MEM_BARS; i++) {
-		if (hw->mem_addr[i]) {
-			pci_iounmap(pdev, hw->mem_addr[i]);
-			hw->mem_addr[i] = NULL;
-		}
-	}
-}
 /**
  * mei_txe_probe - Device Initialization Routine
  *
@@ -75,22 +64,22 @@ static int mei_txe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct mei_device *dev;
 	struct mei_txe_hw *hw;
+	const int mask = BIT(SEC_BAR) | BIT(BRIDGE_BAR);
 	int err;
-	int i;
 
 	/* enable pci dev */
-	err = pci_enable_device(pdev);
+	err = pcim_enable_device(pdev);
 	if (err) {
 		dev_err(&pdev->dev, "failed to enable pci device.\n");
 		goto end;
 	}
 	/* set PCI host mastering  */
 	pci_set_master(pdev);
-	/* pci request regions for mei driver */
+	/* pci request regions and mapping IO device memory for mei driver */
-	err = pci_request_regions(pdev, KBUILD_MODNAME);
+	err = pcim_iomap_regions(pdev, mask, KBUILD_MODNAME);
 	if (err) {
 		dev_err(&pdev->dev, "failed to get pci regions.\n");
-		goto disable_device;
+		goto end;
 	}
 
 	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(36));
@@ -98,7 +87,7 @@ static int mei_txe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
 		if (err) {
 			dev_err(&pdev->dev, "No suitable DMA available.\n");
-			goto release_regions;
+			goto end;
 		}
 	}
 
@@ -106,20 +95,10 @@ static int mei_txe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	dev = mei_txe_dev_init(pdev);
 	if (!dev) {
 		err = -ENOMEM;
-		goto release_regions;
+		goto end;
 	}
 	hw = to_txe_hw(dev);
-
+	hw->mem_addr = pcim_iomap_table(pdev);
-	/* mapping  IO device memory */
-	for (i = SEC_BAR; i < NUM_OF_MEM_BARS; i++) {
-		hw->mem_addr[i] = pci_iomap(pdev, i, 0);
-		if (!hw->mem_addr[i]) {
-			dev_err(&pdev->dev, "mapping I/O device memory failure.\n");
-			err = -ENOMEM;
-			goto free_device;
-		}
-	}
-
 
 	pci_enable_msi(pdev);
 
@@ -140,7 +119,7 @@ static int mei_txe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (err) {
 		dev_err(&pdev->dev, "mei: request_threaded_irq failure. irq = %d\n",
 			pdev->irq);
-		goto free_device;
+		goto end;
 	}
 
 	if (mei_start(dev)) {
@@ -173,23 +152,9 @@ static int mei_txe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 stop:
 	mei_stop(dev);
 release_irq:
-
 	mei_cancel_work(dev);
-
-	/* disable interrupts */
 	mei_disable_interrupts(dev);
-
 	free_irq(pdev->irq, dev);
-	pci_disable_msi(pdev);
-
-free_device:
-	mei_txe_pci_iounmap(pdev, hw);
-
-	kfree(dev);
-release_regions:
-	pci_release_regions(pdev);
-disable_device:
-	pci_disable_device(pdev);
 end:
 	dev_err(&pdev->dev, "initialization failed.\n");
 	return err;
@@ -206,38 +171,24 @@ static int mei_txe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 static void mei_txe_remove(struct pci_dev *pdev)
 {
 	struct mei_device *dev;
-	struct mei_txe_hw *hw;
 
 	dev = pci_get_drvdata(pdev);
 	if (!dev) {
-		dev_err(&pdev->dev, "mei: dev =NULL\n");
+		dev_err(&pdev->dev, "mei: dev == NULL\n");
 		return;
 	}
 
 	pm_runtime_get_noresume(&pdev->dev);
 
-	hw = to_txe_hw(dev);
-
 	mei_stop(dev);
 
 	if (!pci_dev_run_wake(pdev))
 		mei_txe_unset_pm_domain(dev);
 
-	/* disable interrupts */
 	mei_disable_interrupts(dev);
 	free_irq(pdev->irq, dev);
-	pci_disable_msi(pdev);
-
-	pci_set_drvdata(pdev, NULL);
-
-	mei_txe_pci_iounmap(pdev, hw);
 
 	mei_deregister(dev);
-
-	kfree(dev);
-
-	pci_release_regions(pdev);
-	pci_disable_device(pdev);
 }
 
 

drivers/misc/mic/vop/vop_vringh.c

@@ -292,7 +292,6 @@ static int vop_virtio_add_device(struct vop_vdev *vdev,
 	if (ret) {
 		dev_err(vop_dev(vdev), "%s %d err %d\n",
 			__func__, __LINE__, ret);
-		kfree(vdev);
 		return ret;
 	}
 

drivers/misc/panel.c

@@ -56,6 +56,7 @@
 #include <linux/list.h>
 #include <linux/notifier.h>
 #include <linux/reboot.h>
+#include <linux/workqueue.h>
 #include <generated/utsrelease.h>
 
 #include <linux/io.h>
@@ -64,8 +65,6 @@
 #define LCD_MINOR		156
 #define KEYPAD_MINOR		185
 
-#define PANEL_VERSION		"0.9.5"
-
 #define LCD_MAXBYTES		256	/* max burst write */
 
 #define KEYPAD_BUFFER		64
@@ -77,8 +76,8 @@
 /* a key repeats this times INPUT_POLL_TIME */
 #define KEYPAD_REP_DELAY	(2)
 
-/* keep the light on this times INPUT_POLL_TIME for each flash */
+/* keep the light on this many seconds for each flash */
-#define FLASH_LIGHT_TEMPO	(200)
+#define FLASH_LIGHT_TEMPO	(4)
 
 /* converts an r_str() input to an active high, bits string : 000BAOSE */
 #define PNL_PINPUT(a)		((((unsigned char)(a)) ^ 0x7F) >> 3)
@@ -121,8 +120,6 @@
 #define PIN_SELECP		17
 #define PIN_NOT_SET		127
 
-#define LCD_FLAG_S		0x0001
-#define LCD_FLAG_ID		0x0002
 #define LCD_FLAG_B		0x0004	/* blink on */
 #define LCD_FLAG_C		0x0008	/* cursor on */
 #define LCD_FLAG_D		0x0010	/* display on */
@@ -256,7 +253,10 @@ static struct {
 	int hwidth;
 	int charset;
 	int proto;
-	int light_tempo;
+
+	struct delayed_work bl_work;
+	struct mutex bl_tempo_lock;	/* Protects access to bl_tempo */
+	bool bl_tempo;
 
 	/* TODO: use union here? */
 	struct {
@@ -661,8 +661,6 @@ static void lcd_get_bits(unsigned int port, int *val)
 	}
 }
 
-static void init_scan_timer(void);
-
 /* sets data port bits according to current signals values */
 static int set_data_bits(void)
 {
@@ -794,11 +792,8 @@ static void lcd_send_serial(int byte)
 }
 
 /* turn the backlight on or off */
-static void lcd_backlight(int on)
+static void __lcd_backlight(int on)
 {
-	if (lcd.pins.bl == PIN_NONE)
-		return;
-
 	/* The backlight is activated by setting the AUTOFEED line to +5V  */
 	spin_lock_irq(&pprt_lock);
 	if (on)
@@ -809,6 +804,44 @@ static void lcd_backlight(int on)
 	spin_unlock_irq(&pprt_lock);
 }
 
+static void lcd_backlight(int on)
+{
+	if (lcd.pins.bl == PIN_NONE)
+		return;
+
+	mutex_lock(&lcd.bl_tempo_lock);
+	if (!lcd.bl_tempo)
+		__lcd_backlight(on);
+	mutex_unlock(&lcd.bl_tempo_lock);
+}
+
+static void lcd_bl_off(struct work_struct *work)
+{
+	mutex_lock(&lcd.bl_tempo_lock);
+	if (lcd.bl_tempo) {
+		lcd.bl_tempo = false;
+		if (!(lcd.flags & LCD_FLAG_L))
+			__lcd_backlight(0);
+	}
+	mutex_unlock(&lcd.bl_tempo_lock);
+}
+
+/* turn the backlight on for a little while */
+static void lcd_poke(void)
+{
+	if (lcd.pins.bl == PIN_NONE)
+		return;
+
+	cancel_delayed_work_sync(&lcd.bl_work);
+
+	mutex_lock(&lcd.bl_tempo_lock);
+	if (!lcd.bl_tempo && !(lcd.flags & LCD_FLAG_L))
+		__lcd_backlight(1);
+	lcd.bl_tempo = true;
+	schedule_delayed_work(&lcd.bl_work, FLASH_LIGHT_TEMPO * HZ);
+	mutex_unlock(&lcd.bl_tempo_lock);
+}
+
 /* send a command to the LCD panel in serial mode */
 static void lcd_write_cmd_s(int cmd)
 {
@@ -907,6 +940,13 @@ static void lcd_gotoxy(void)
 			 (lcd.hwidth - 1) : lcd.bwidth - 1));
 }
 
+static void lcd_home(void)
+{
+	lcd.addr.x = 0;
+	lcd.addr.y = 0;
+	lcd_gotoxy();
+}
+
 static void lcd_print(char c)
 {
 	if (lcd.addr.x < lcd.bwidth) {
@@ -925,9 +965,7 @@ static void lcd_clear_fast_s(void)
 {
 	int pos;
 
-	lcd.addr.x = 0;
+	lcd_home();
-	lcd.addr.y = 0;
-	lcd_gotoxy();
 
 	spin_lock_irq(&pprt_lock);
 	for (pos = 0; pos < lcd.height * lcd.hwidth; pos++) {
@@ -939,9 +977,7 @@ static void lcd_clear_fast_s(void)
 	}
 	spin_unlock_irq(&pprt_lock);
 
-	lcd.addr.x = 0;
+	lcd_home();
-	lcd.addr.y = 0;
-	lcd_gotoxy();
 }
 
 /* fills the display with spaces and resets X/Y */
@@ -949,9 +985,7 @@ static void lcd_clear_fast_p8(void)
 {
 	int pos;
 
-	lcd.addr.x = 0;
+	lcd_home();
-	lcd.addr.y = 0;
-	lcd_gotoxy();
 
 	spin_lock_irq(&pprt_lock);
 	for (pos = 0; pos < lcd.height * lcd.hwidth; pos++) {
@@ -977,9 +1011,7 @@ static void lcd_clear_fast_p8(void)
 	}
 	spin_unlock_irq(&pprt_lock);
 
-	lcd.addr.x = 0;
+	lcd_home();
-	lcd.addr.y = 0;
-	lcd_gotoxy();
 }
 
 /* fills the display with spaces and resets X/Y */
@@ -987,9 +1019,7 @@ static void lcd_clear_fast_tilcd(void)
 {
 	int pos;
 
-	lcd.addr.x = 0;
+	lcd_home();
-	lcd.addr.y = 0;
-	lcd_gotoxy();
 
 	spin_lock_irq(&pprt_lock);
 	for (pos = 0; pos < lcd.height * lcd.hwidth; pos++) {
@@ -1000,9 +1030,7 @@ static void lcd_clear_fast_tilcd(void)
 
 	spin_unlock_irq(&pprt_lock);
 
-	lcd.addr.x = 0;
+	lcd_home();
-	lcd.addr.y = 0;
-	lcd_gotoxy();
 }
 
 /* clears the display and resets X/Y */
@@ -1108,13 +1136,8 @@ static inline int handle_lcd_special_code(void)
 		processed = 1;
 		break;
 	case '*':
-		/* flash back light using the keypad timer */
+		/* flash back light */
-		if (scan_timer.function) {
+		lcd_poke();
-			if (lcd.light_tempo == 0 &&
-			    ((lcd.flags & LCD_FLAG_L) == 0))
-				lcd_backlight(1);
-			lcd.light_tempo = FLASH_LIGHT_TEMPO;
-		}
 		processed = 1;
 		break;
 	case 'f':	/* Small Font */
@@ -1278,21 +1301,14 @@ static inline int handle_lcd_special_code(void)
 			lcd_write_cmd(LCD_CMD_FUNCTION_SET
 				      | LCD_CMD_DATA_LEN_8BITS
 				      | ((lcd.flags & LCD_FLAG_F)
-						      ? LCD_CMD_TWO_LINES : 0)
-				      | ((lcd.flags & LCD_FLAG_N)
 						      ? LCD_CMD_FONT_5X10_DOTS
+								      : 0)
+				      | ((lcd.flags & LCD_FLAG_N)
+						      ? LCD_CMD_TWO_LINES
 								      : 0));
 		/* check whether L flag was changed */
-		else if ((oldflags ^ lcd.flags) & (LCD_FLAG_L)) {
+		else if ((oldflags ^ lcd.flags) & (LCD_FLAG_L))
-			if (lcd.flags & (LCD_FLAG_L))
+			lcd_backlight(!!(lcd.flags & LCD_FLAG_L));
-				lcd_backlight(1);
-			else if (lcd.light_tempo == 0)
-				/*
-				 * switch off the light only when the tempo
-				 * lighting is gone
-				 */
-				lcd_backlight(0);
-		}
 	}
 
 	return processed;
@@ -1376,9 +1392,7 @@ static void lcd_write_char(char c)
 			processed = 1;
 		} else if (!strcmp(lcd.esc_seq.buf, "[H")) {
 			/* cursor to home */
-			lcd.addr.x = 0;
+			lcd_home();
-			lcd.addr.y = 0;
-			lcd_gotoxy();
 			processed = 1;
 		}
 		/* codes starting with ^[[L */
@@ -1625,8 +1639,10 @@ static void lcd_init(void)
 	else
 		lcd_char_conv = NULL;
 
-	if (lcd.pins.bl != PIN_NONE)
+	if (lcd.pins.bl != PIN_NONE) {
-		init_scan_timer();
+		mutex_init(&lcd.bl_tempo_lock);
+		INIT_DELAYED_WORK(&lcd.bl_work, lcd_bl_off);
+	}
 
 	pin_to_bits(lcd.pins.e, lcd_bits[LCD_PORT_D][LCD_BIT_E],
 		    lcd_bits[LCD_PORT_C][LCD_BIT_E]);
@@ -1655,14 +1671,11 @@ static void lcd_init(void)
 	panel_lcd_print("\x1b[Lc\x1b[Lb\x1b[L*" CONFIG_PANEL_BOOT_MESSAGE);
 #endif
 #else
-	panel_lcd_print("\x1b[Lc\x1b[Lb\x1b[L*Linux-" UTS_RELEASE "\nPanel-"
+	panel_lcd_print("\x1b[Lc\x1b[Lb\x1b[L*Linux-" UTS_RELEASE);
-			PANEL_VERSION);
 #endif
-	lcd.addr.x = 0;
-	lcd.addr.y = 0;
 	/* clear the display on the next device opening */
 	lcd.must_clear = true;
-	lcd_gotoxy();
+	lcd_home();
 }
 
 /*
@@ -1997,19 +2010,8 @@ static void panel_scan_timer(void)
 			panel_process_inputs();
 	}
 
-	if (lcd.enabled && lcd.initialized) {
+	if (keypressed && lcd.enabled && lcd.initialized)
-		if (keypressed) {
+		lcd_poke();
-			if (lcd.light_tempo == 0 &&
-			    ((lcd.flags & LCD_FLAG_L) == 0))
-				lcd_backlight(1);
-			lcd.light_tempo = FLASH_LIGHT_TEMPO;
-		} else if (lcd.light_tempo > 0) {
-			lcd.light_tempo--;
-			if (lcd.light_tempo == 0 &&
-			    ((lcd.flags & LCD_FLAG_L) == 0))
-				lcd_backlight(0);
-		}
-	}
 
 	mod_timer(&scan_timer, jiffies + INPUT_POLL_TIME);
 }
@@ -2270,16 +2272,18 @@ static void panel_detach(struct parport *port)
 	if (scan_timer.function)
 		del_timer_sync(&scan_timer);
 
-	if (pprt) {
 	if (keypad.enabled) {
 		misc_deregister(&keypad_dev);
 		keypad_initialized = 0;
 	}
 
 	if (lcd.enabled) {
-			panel_lcd_print("\x0cLCD driver " PANEL_VERSION
+		panel_lcd_print("\x0cLCD driver unloaded.\x1b[Lc\x1b[Lb\x1b[L-");
-					"\nunloaded.\x1b[Lc\x1b[Lb\x1b[L-");
 		misc_deregister(&lcd_dev);
+		if (lcd.pins.bl != PIN_NONE) {
+			cancel_delayed_work_sync(&lcd.bl_work);
+			__lcd_backlight(0);
+		}
 		lcd.initialized = false;
 	}
 
@@ -2289,7 +2293,6 @@ static void panel_detach(struct parport *port)
 	pprt = NULL;
 	unregister_reboot_notifier(&panel_notifier);
 }
-}
 
 static struct parport_driver panel_driver = {
 	.name = "panel",
@@ -2400,7 +2403,7 @@ static int __init panel_init_module(void)
 
 	if (!lcd.enabled && !keypad.enabled) {
 		/* no device enabled, let's exit */
-		pr_err("driver version " PANEL_VERSION " disabled.\n");
+		pr_err("panel driver disabled.\n");
 		return -ENODEV;
 	}
 
@@ -2411,12 +2414,10 @@ static int __init panel_init_module(void)
 	}
 
 	if (pprt)
-		pr_info("driver version " PANEL_VERSION
+		pr_info("panel driver registered on parport%d (io=0x%lx).\n",
-			" registered on parport%d (io=0x%lx).\n", parport,
+			parport, pprt->port->base);
-			pprt->port->base);
 	else
-		pr_info("driver version " PANEL_VERSION
+		pr_info("panel driver not yet registered\n");
-			" not yet registered\n");
 	return 0;
 }
 

drivers/misc/sram-exec.c

@@ -0,0 +1,105 @@
+/*
+ * SRAM protect-exec region helper functions
+ *
+ * Copyright (C) 2017 Texas Instruments Incorporated - http://www.ti.com/
+ *	Dave Gerlach
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/device.h>
+#include <linux/genalloc.h>
+#include <linux/sram.h>
+
+#include <asm/cacheflush.h>
+
+#include "sram.h"
+
+static DEFINE_MUTEX(exec_pool_list_mutex);
+static LIST_HEAD(exec_pool_list);
+
+int sram_check_protect_exec(struct sram_dev *sram, struct sram_reserve *block,
+			    struct sram_partition *part)
+{
+	unsigned long base = (unsigned long)part->base;
+	unsigned long end = base + block->size;
+
+	if (!PAGE_ALIGNED(base) || !PAGE_ALIGNED(end)) {
+		dev_err(sram->dev,
+			"SRAM pool marked with 'protect-exec' is not page aligned and will not be created.\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+int sram_add_protect_exec(struct sram_partition *part)
+{
+	mutex_lock(&exec_pool_list_mutex);
+	list_add_tail(&part->list, &exec_pool_list);
+	mutex_unlock(&exec_pool_list_mutex);
+
+	return 0;
+}
+
+/**
+ * sram_exec_copy - copy data to a protected executable region of sram
+ *
+ * @pool: struct gen_pool retrieved that is part of this sram
+ * @dst: Destination address for the copy, that must be inside pool
+ * @src: Source address for the data to copy
+ * @size: Size of copy to perform, which starting from dst, must reside in pool
+ *
+ * This helper function allows sram driver to act as central control location
+ * of 'protect-exec' pools which are normal sram pools but are always set
+ * read-only and executable except when copying data to them, at which point
+ * they are set to read-write non-executable, to make sure no memory is
+ * writeable and executable at the same time. This region must be page-aligned
+ * and is checked during probe, otherwise page attribute manipulation would
+ * not be possible.
+ */
+int sram_exec_copy(struct gen_pool *pool, void *dst, void *src,
+		   size_t size)
+{
+	struct sram_partition *part = NULL, *p;
+	unsigned long base;
+	int pages;
+
+	mutex_lock(&exec_pool_list_mutex);
+	list_for_each_entry(p, &exec_pool_list, list) {
+		if (p->pool == pool)
+			part = p;
+	}
+	mutex_unlock(&exec_pool_list_mutex);
+
+	if (!part)
+		return -EINVAL;
+
+	if (!addr_in_gen_pool(pool, (unsigned long)dst, size))
+		return -EINVAL;
+
+	base = (unsigned long)part->base;
+	pages = PAGE_ALIGN(size) / PAGE_SIZE;
+
+	mutex_lock(&part->lock);
+
+	set_memory_nx((unsigned long)base, pages);
+	set_memory_rw((unsigned long)base, pages);
+
+	memcpy(dst, src, size);
+
+	set_memory_ro((unsigned long)base, pages);
+	set_memory_x((unsigned long)base, pages);
+
+	mutex_unlock(&part->lock);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(sram_exec_copy);

drivers/misc/sram.c

@@ -31,36 +31,10 @@
 #include <linux/mfd/syscon.h>
 #include <soc/at91/atmel-secumod.h>
 
+#include "sram.h"
+
 #define SRAM_GRANULARITY	32
 
-struct sram_partition {
-	void __iomem *base;
-
-	struct gen_pool *pool;
-	struct bin_attribute battr;
-	struct mutex lock;
-};
-
-struct sram_dev {
-	struct device *dev;
-	void __iomem *virt_base;
-
-	struct gen_pool *pool;
-	struct clk *clk;
-
-	struct sram_partition *partition;
-	u32 partitions;
-};
-
-struct sram_reserve {
-	struct list_head list;
-	u32 start;
-	u32 size;
-	bool export;
-	bool pool;
-	const char *label;
-};
-
 static ssize_t sram_read(struct file *filp, struct kobject *kobj,
 			 struct bin_attribute *attr,
 			 char *buf, loff_t pos, size_t count)
@@ -148,6 +122,18 @@ static int sram_add_partition(struct sram_dev *sram, struct sram_reserve *block,
 		if (ret)
 			return ret;
 	}
+	if (block->protect_exec) {
+		ret = sram_check_protect_exec(sram, block, part);
+		if (ret)
+			return ret;
+
+		ret = sram_add_pool(sram, block, start, part);
+		if (ret)
+			return ret;
+
+		sram_add_protect_exec(part);
+	}
+
 	sram->partitions++;
 
 	return 0;
@@ -233,7 +219,11 @@ static int sram_reserve_regions(struct sram_dev *sram, struct resource *res)
 		if (of_find_property(child, "pool", NULL))
 			block->pool = true;
 
-		if ((block->export || block->pool) && block->size) {
+		if (of_find_property(child, "protect-exec", NULL))
+			block->protect_exec = true;
+
+		if ((block->export || block->pool || block->protect_exec) &&
+		    block->size) {
 			exports++;
 
 			label = NULL;
@@ -249,8 +239,10 @@ static int sram_reserve_regions(struct sram_dev *sram, struct resource *res)
 
 			block->label = devm_kstrdup(sram->dev,
 						    label, GFP_KERNEL);
-			if (!block->label)
+			if (!block->label) {
+				ret = -ENOMEM;
 				goto err_chunks;
+			}
 
 			dev_dbg(sram->dev, "found %sblock '%s' 0x%x-0x%x\n",
 				block->export ? "exported " : "", block->label,
@@ -293,7 +285,8 @@ static int sram_reserve_regions(struct sram_dev *sram, struct resource *res)
 			goto err_chunks;
 		}
 
-		if ((block->export || block->pool) && block->size) {
+		if ((block->export || block->pool || block->protect_exec) &&
+		    block->size) {
 			ret = sram_add_partition(sram, block,
 						 res->start + block->start);
 			if (ret) {

drivers/misc/sram.h

@@ -0,0 +1,58 @@
+/*
+ * Defines for the SRAM driver
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef __SRAM_H
+#define __SRAM_H
+
+struct sram_partition {
+	void __iomem *base;
+
+	struct gen_pool *pool;
+	struct bin_attribute battr;
+	struct mutex lock;
+	struct list_head list;
+};
+
+struct sram_dev {
+	struct device *dev;
+	void __iomem *virt_base;
+
+	struct gen_pool *pool;
+	struct clk *clk;
+
+	struct sram_partition *partition;
+	u32 partitions;
+};
+
+struct sram_reserve {
+	struct list_head list;
+	u32 start;
+	u32 size;
+	bool export;
+	bool pool;
+	bool protect_exec;
+	const char *label;
+};
+
+#ifdef CONFIG_SRAM_EXEC
+int sram_check_protect_exec(struct sram_dev *sram, struct sram_reserve *block,
+			    struct sram_partition *part);
+int sram_add_protect_exec(struct sram_partition *part);
+#else
+static inline int sram_check_protect_exec(struct sram_dev *sram,
+					  struct sram_reserve *block,
+					  struct sram_partition *part)
+{
+	return -ENODEV;
+}
+
+static inline int sram_add_protect_exec(struct sram_partition *part)
+{
+	return -ENODEV;
+}
+#endif /* CONFIG_SRAM_EXEC */
+#endif /* __SRAM_H */

drivers/misc/vmw_vmci/vmci_guest.c

@@ -54,10 +54,7 @@ struct vmci_guest_device {
 	struct device *dev;	/* PCI device we are attached to */
 	void __iomem *iobase;
 
-	unsigned int irq;
-	unsigned int intr_type;
 	bool exclusive_vectors;
-	struct msix_entry msix_entries[VMCI_MAX_INTRS];
 
 	struct tasklet_struct datagram_tasklet;
 	struct tasklet_struct bm_tasklet;
@@ -368,30 +365,6 @@ static void vmci_process_bitmap(unsigned long data)
 	vmci_dbell_scan_notification_entries(dev->notification_bitmap);
 }
 
-/*
- * Enable MSI-X.  Try exclusive vectors first, then shared vectors.
- */
-static int vmci_enable_msix(struct pci_dev *pdev,
-			    struct vmci_guest_device *vmci_dev)
-{
-	int i;
-	int result;
-
-	for (i = 0; i < VMCI_MAX_INTRS; ++i) {
-		vmci_dev->msix_entries[i].entry = i;
-		vmci_dev->msix_entries[i].vector = i;
-	}
-
-	result = pci_enable_msix_exact(pdev,
-				       vmci_dev->msix_entries, VMCI_MAX_INTRS);
-	if (result == 0)
-		vmci_dev->exclusive_vectors = true;
-	else if (result == -ENOSPC)
-		result = pci_enable_msix_exact(pdev, vmci_dev->msix_entries, 1);
-
-	return result;
-}
-
 /*
  * Interrupt handler for legacy or MSI interrupt, or for first MSI-X
  * interrupt (vector VMCI_INTR_DATAGRAM).
@@ -406,7 +379,7 @@ static irqreturn_t vmci_interrupt(int irq, void *_dev)
 	 * Otherwise we must read the ICR to determine what to do.
 	 */
 
-	if (dev->intr_type == VMCI_INTR_TYPE_MSIX && dev->exclusive_vectors) {
+	if (dev->exclusive_vectors) {
 		tasklet_schedule(&dev->datagram_tasklet);
 	} else {
 		unsigned int icr;
@@ -491,7 +464,6 @@ static int vmci_guest_probe_device(struct pci_dev *pdev,
 	}
 
 	vmci_dev->dev = &pdev->dev;
-	vmci_dev->intr_type = VMCI_INTR_TYPE_INTX;
 	vmci_dev->exclusive_vectors = false;
 	vmci_dev->iobase = iobase;
 
@@ -592,26 +564,26 @@ static int vmci_guest_probe_device(struct pci_dev *pdev,
 	 * Enable interrupts.  Try MSI-X first, then MSI, and then fallback on
 	 * legacy interrupts.
 	 */
-	if (!vmci_disable_msix && !vmci_enable_msix(pdev, vmci_dev)) {
+	error = pci_alloc_irq_vectors(pdev, VMCI_MAX_INTRS, VMCI_MAX_INTRS,
-		vmci_dev->intr_type = VMCI_INTR_TYPE_MSIX;
+			PCI_IRQ_MSIX);
-		vmci_dev->irq = vmci_dev->msix_entries[0].vector;
+	if (error) {
-	} else if (!vmci_disable_msi && !pci_enable_msi(pdev)) {
+		error = pci_alloc_irq_vectors(pdev, 1, 1,
-		vmci_dev->intr_type = VMCI_INTR_TYPE_MSI;
+				PCI_IRQ_MSIX | PCI_IRQ_MSI | PCI_IRQ_LEGACY);
-		vmci_dev->irq = pdev->irq;
+		if (error)
+			goto err_remove_bitmap;
 	} else {
-		vmci_dev->intr_type = VMCI_INTR_TYPE_INTX;
+		vmci_dev->exclusive_vectors = true;
-		vmci_dev->irq = pdev->irq;
 	}
 
 	/*
 	 * Request IRQ for legacy or MSI interrupts, or for first
 	 * MSI-X vector.
 	 */
-	error = request_irq(vmci_dev->irq, vmci_interrupt, IRQF_SHARED,
+	error = request_irq(pci_irq_vector(pdev, 0), vmci_interrupt,
-			    KBUILD_MODNAME, vmci_dev);
+			    IRQF_SHARED, KBUILD_MODNAME, vmci_dev);
 	if (error) {
 		dev_err(&pdev->dev, "Irq %u in use: %d\n",
-			vmci_dev->irq, error);
+			pci_irq_vector(pdev, 0), error);
 		goto err_disable_msi;
 	}
 
@@ -622,13 +594,13 @@ static int vmci_guest_probe_device(struct pci_dev *pdev,
 	 * between the vectors.
 	 */
 	if (vmci_dev->exclusive_vectors) {
-		error = request_irq(vmci_dev->msix_entries[1].vector,
+		error = request_irq(pci_irq_vector(pdev, 1),
 				    vmci_interrupt_bm, 0, KBUILD_MODNAME,
 				    vmci_dev);
 		if (error) {
 			dev_err(&pdev->dev,
 				"Failed to allocate irq %u: %d\n",
-				vmci_dev->msix_entries[1].vector, error);
+				pci_irq_vector(pdev, 1), error);
 			goto err_free_irq;
 		}
 	}
@@ -651,15 +623,12 @@ static int vmci_guest_probe_device(struct pci_dev *pdev,
 	return 0;
 
 err_free_irq:
-	free_irq(vmci_dev->irq, vmci_dev);
+	free_irq(pci_irq_vector(pdev, 0), vmci_dev);
 	tasklet_kill(&vmci_dev->datagram_tasklet);
 	tasklet_kill(&vmci_dev->bm_tasklet);
 
 err_disable_msi:
-	if (vmci_dev->intr_type == VMCI_INTR_TYPE_MSIX)
+	pci_free_irq_vectors(pdev);
-		pci_disable_msix(pdev);
-	else if (vmci_dev->intr_type == VMCI_INTR_TYPE_MSI)
-		pci_disable_msi(pdev);
 
 	vmci_err = vmci_event_unsubscribe(ctx_update_sub_id);
 	if (vmci_err < VMCI_SUCCESS)
@@ -719,14 +688,10 @@ static void vmci_guest_remove_device(struct pci_dev *pdev)
 	 * MSI-X, we might have multiple vectors, each with their own
 	 * IRQ, which we must free too.
 	 */
-	free_irq(vmci_dev->irq, vmci_dev);
-	if (vmci_dev->intr_type == VMCI_INTR_TYPE_MSIX) {
 	if (vmci_dev->exclusive_vectors)
-			free_irq(vmci_dev->msix_entries[1].vector, vmci_dev);
+		free_irq(pci_irq_vector(pdev, 1), vmci_dev);
-		pci_disable_msix(pdev);
+	free_irq(pci_irq_vector(pdev, 0), vmci_dev);
-	} else if (vmci_dev->intr_type == VMCI_INTR_TYPE_MSI) {
+	pci_free_irq_vectors(pdev);
-		pci_disable_msi(pdev);
-	}
 
 	tasklet_kill(&vmci_dev->datagram_tasklet);
 	tasklet_kill(&vmci_dev->bm_tasklet);

drivers/net/hyperv/netvsc.c

@@ -703,8 +703,6 @@ static u32 netvsc_copy_to_send_buf(struct netvsc_device *net_device,
 	char *dest = start + (section_index * net_device->send_section_size)
 		     + pend_size;
 	int i;
-	bool is_data_pkt = (skb != NULL) ? true : false;
-	bool xmit_more = (skb != NULL) ? skb->xmit_more : false;
 	u32 msg_size = 0;
 	u32 padding = 0;
 	u32 remain = packet->total_data_buflen % net_device->pkt_align;
@@ -712,7 +710,7 @@ static u32 netvsc_copy_to_send_buf(struct netvsc_device *net_device,
 		packet->page_buf_cnt;
 
 	/* Add padding */
-	if (is_data_pkt && xmit_more && remain &&
+	if (skb && skb->xmit_more && remain &&
 	    !packet->cp_partial) {
 		padding = net_device->pkt_align - remain;
 		rndis_msg->msg_len += padding;
@@ -754,7 +752,6 @@ static inline int netvsc_send_pkt(
 	int ret;
 	struct hv_page_buffer *pgbuf;
 	u32 ring_avail = hv_ringbuf_avail_percent(&out_channel->outbound);
-	bool xmit_more = (skb != NULL) ? skb->xmit_more : false;
 
 	nvmsg.hdr.msg_type = NVSP_MSG1_TYPE_SEND_RNDIS_PKT;
 	if (skb != NULL) {
@@ -778,16 +775,6 @@ static inline int netvsc_send_pkt(
 	if (out_channel->rescind)
 		return -ENODEV;
 
-	/*
-	 * It is possible that once we successfully place this packet
-	 * on the ringbuffer, we may stop the queue. In that case, we want
-	 * to notify the host independent of the xmit_more flag. We don't
-	 * need to be precise here; in the worst case we may signal the host
-	 * unnecessarily.
-	 */
-	if (ring_avail < (RING_AVAIL_PERCENT_LOWATER + 1))
-		xmit_more = false;
-
 	if (packet->page_buf_cnt) {
 		pgbuf = packet->cp_partial ? (*pb) +
 			packet->rmsg_pgcnt : (*pb);
@@ -797,15 +784,13 @@ static inline int netvsc_send_pkt(
 						      &nvmsg,
 						      sizeof(struct nvsp_message),
 						      req_id,
-						      VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED,
+						      VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
-						      !xmit_more);
 	} else {
 		ret = vmbus_sendpacket_ctl(out_channel, &nvmsg,
 					   sizeof(struct nvsp_message),
 					   req_id,
 					   VM_PKT_DATA_INBAND,
-					   VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED,
+					   VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
-					   !xmit_more);
 	}
 
 	if (ret == 0) {

drivers/nvmem/core.c

@@ -608,7 +608,7 @@ static struct nvmem_device *nvmem_find(const char *name)
 /**
  * of_nvmem_device_get() - Get nvmem device from a given id
  *
- * @dev node: Device tree node that uses the nvmem device
+ * @np: Device tree node that uses the nvmem device.
  * @id: nvmem name from nvmem-names property.
  *
  * Return: ERR_PTR() on error or a valid pointer to a struct nvmem_device
@@ -634,8 +634,8 @@ EXPORT_SYMBOL_GPL(of_nvmem_device_get);
 /**
  * nvmem_device_get() - Get nvmem device from a given id
  *
- * @dev : Device that uses the nvmem device
+ * @dev: Device that uses the nvmem device.
- * @id: nvmem name from nvmem-names property.
+ * @dev_name: name of the requested nvmem device.
  *
  * Return: ERR_PTR() on error or a valid pointer to a struct nvmem_device
  * on success.
@@ -674,6 +674,7 @@ static void devm_nvmem_device_release(struct device *dev, void *res)
 /**
  * devm_nvmem_device_put() - put alredy got nvmem device
  *
+ * @dev: Device that uses the nvmem device.
  * @nvmem: pointer to nvmem device allocated by devm_nvmem_cell_get(),
  * that needs to be released.
  */
@@ -702,8 +703,8 @@ EXPORT_SYMBOL_GPL(nvmem_device_put);
 /**
  * devm_nvmem_device_get() - Get nvmem cell of device form a given id
  *
- * @dev node: Device tree node that uses the nvmem cell
+ * @dev: Device that requests the nvmem device.
- * @id: nvmem name in nvmems property.
+ * @id: name id for the requested nvmem device.
  *
  * Return: ERR_PTR() on error or a valid pointer to a struct nvmem_cell
  * on success.  The nvmem_cell will be freed by the automatically once the
@@ -745,8 +746,10 @@ static struct nvmem_cell *nvmem_cell_get_from_list(const char *cell_id)
 /**
  * of_nvmem_cell_get() - Get a nvmem cell from given device node and cell id
  *
- * @dev node: Device tree node that uses the nvmem cell
+ * @np: Device tree node that uses the nvmem cell.
- * @id: nvmem cell name from nvmem-cell-names property.
+ * @name: nvmem cell name from nvmem-cell-names property, or NULL
+ *	  for the cell at index 0 (the lone cell with no accompanying
+ *	  nvmem-cell-names property).
  *
  * Return: Will be an ERR_PTR() on error or a valid pointer
  * to a struct nvmem_cell.  The nvmem_cell will be freed by the
@@ -759,8 +762,11 @@ struct nvmem_cell *of_nvmem_cell_get(struct device_node *np,
 	struct nvmem_cell *cell;
 	struct nvmem_device *nvmem;
 	const __be32 *addr;
-	int rval, len, index;
+	int rval, len;
+	int index = 0;
 
+	/* if cell name exists, find index to the name */
+	if (name)
 		index = of_property_match_string(np, "nvmem-cell-names", name);
 
 	cell_np = of_parse_phandle(np, "nvmem-cells", index);
@@ -830,8 +836,8 @@ EXPORT_SYMBOL_GPL(of_nvmem_cell_get);
 /**
  * nvmem_cell_get() - Get nvmem cell of device form a given cell name
  *
- * @dev node: Device tree node that uses the nvmem cell
+ * @dev: Device that requests the nvmem cell.
- * @id: nvmem cell name to get.
+ * @cell_id: nvmem cell name to get.
  *
  * Return: Will be an ERR_PTR() on error or a valid pointer
  * to a struct nvmem_cell.  The nvmem_cell will be freed by the
@@ -859,8 +865,8 @@ static void devm_nvmem_cell_release(struct device *dev, void *res)
 /**
  * devm_nvmem_cell_get() - Get nvmem cell of device form a given id
  *
- * @dev node: Device tree node that uses the nvmem cell
+ * @dev: Device that requests the nvmem cell.
- * @id: nvmem id in nvmem-names property.
+ * @id: nvmem cell name id to get.
  *
  * Return: Will be an ERR_PTR() on error or a valid pointer
  * to a struct nvmem_cell.  The nvmem_cell will be freed by the
@@ -900,7 +906,8 @@ static int devm_nvmem_cell_match(struct device *dev, void *res, void *data)
  * devm_nvmem_cell_put() - Release previously allocated nvmem cell
  * from devm_nvmem_cell_get.
  *
- * @cell: Previously allocated nvmem cell by devm_nvmem_cell_get()
+ * @dev: Device that requests the nvmem cell.
+ * @cell: Previously allocated nvmem cell by devm_nvmem_cell_get().
  */
 void devm_nvmem_cell_put(struct device *dev, struct nvmem_cell *cell)
 {
@@ -916,7 +923,7 @@ EXPORT_SYMBOL(devm_nvmem_cell_put);
 /**
  * nvmem_cell_put() - Release previously allocated nvmem cell.
  *
- * @cell: Previously allocated nvmem cell by nvmem_cell_get()
+ * @cell: Previously allocated nvmem cell by nvmem_cell_get().
  */
 void nvmem_cell_put(struct nvmem_cell *cell)
 {
@@ -970,6 +977,7 @@ static int __nvmem_cell_read(struct nvmem_device *nvmem,
 	if (cell->bit_offset || cell->nbits)
 		nvmem_shift_read_buffer_in_place(cell, buf);
 
+	if (len)
 		*len = cell->bytes;
 
 	return 0;
@@ -979,7 +987,8 @@ static int __nvmem_cell_read(struct nvmem_device *nvmem,
  * nvmem_cell_read() - Read a given nvmem cell
  *
  * @cell: nvmem cell to be read.
- * @len: pointer to length of cell which will be populated on successful read.
+ * @len: pointer to length of cell which will be populated on successful read;
+ *	 can be NULL.
  *
  * Return: ERR_PTR() on error or a valid pointer to a buffer on success. The
  * buffer should be freed by the consumer with a kfree().
@@ -1126,7 +1135,7 @@ EXPORT_SYMBOL_GPL(nvmem_device_cell_read);
  * nvmem_device_cell_write() - Write cell to a given nvmem device
  *
  * @nvmem: nvmem device to be written to.
- * @info: nvmem cell info to be written
+ * @info: nvmem cell info to be written.
  * @buf: buffer to be written to cell.
  *
  * Return: length of bytes written or negative error code on failure.

drivers/nvmem/imx-ocotp.c

@@ -73,6 +73,7 @@ static const struct of_device_id imx_ocotp_dt_ids[] = {
 	{ .compatible = "fsl,imx6q-ocotp",  (void *)128 },
 	{ .compatible = "fsl,imx6sl-ocotp", (void *)64 },
 	{ .compatible = "fsl,imx6sx-ocotp", (void *)128 },
+	{ .compatible = "fsl,imx6ul-ocotp", (void *)128 },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, imx_ocotp_dt_ids);

drivers/platform/goldfish/pdev_bus.c

@@ -157,24 +157,27 @@ static int goldfish_new_pdev(void)
 static irqreturn_t goldfish_pdev_bus_interrupt(int irq, void *dev_id)
 {
 	irqreturn_t ret = IRQ_NONE;
+
 	while (1) {
 		u32 op = readl(pdev_bus_base + PDEV_BUS_OP);
-		switch (op) {
-		case PDEV_BUS_OP_DONE:
-			return IRQ_NONE;
 
+		switch (op) {
 		case PDEV_BUS_OP_REMOVE_DEV:
 			goldfish_pdev_remove();
+			ret = IRQ_HANDLED;
 			break;
 
 		case PDEV_BUS_OP_ADD_DEV:
 			goldfish_new_pdev();
-			break;
-		}
 			ret = IRQ_HANDLED;
-	}
+			break;
+
+		case PDEV_BUS_OP_DONE:
+		default:
 			return ret;
 		}
+	}
+}
 
 static int goldfish_pdev_bus_probe(struct platform_device *pdev)
 {