Merge 6.2-rc3 into usb-next

We need the USB fixes in here as well.

Signed-off-by: Greg Kroah-Hartman <[e-mail]>

.gitignore

···
 *.o.*
 *.patch
 *.rmeta
+*.rpm
 *.rsi
 *.s
 *.so

Documentation/ABI/testing/debugfs-pktcdvd

···
+What:           /sys/kernel/debug/pktcdvd/pktcdvd[0-7]
+Date:           Oct. 2006
+KernelVersion:  2.6.20
+Contact:        Thomas Maier <[e-mail]>
+Description:
+
+The pktcdvd module (packet writing driver) creates
+these files in debugfs:
+
+/sys/kernel/debug/pktcdvd/pktcdvd[0-7]/
+
+    ====            ====== ====================================
+    info            0444   Lots of driver statistics and infos.
+    ====            ====== ====================================
+
+Example::
+
+    cat /sys/kernel/debug/pktcdvd/pktcdvd0/info

Documentation/ABI/testing/sysfs-class-pktcdvd

···
+sysfs interface
+---------------
+The pktcdvd module (packet writing driver) creates the following files in the
+sysfs: (<devid> is in the format major:minor)
+
+What:		/sys/class/pktcdvd/add
+What:		/sys/class/pktcdvd/remove
+What:		/sys/class/pktcdvd/device_map
+Date:		Oct. 2006
+KernelVersion:	2.6.20
+Contact:	Thomas Maier <[e-mail]>
+Description:
+
+		==========	==============================================
+		add		(WO) Write a block device id (major:minor) to
+				create a new pktcdvd device and map it to the
+				block device.
+
+		remove		(WO) Write the pktcdvd device id (major:minor)
+				to remove the pktcdvd device.
+
+		device_map	(RO) Shows the device mapping in format:
+				pktcdvd[0-7] <pktdevid> <blkdevid>
+		==========	==============================================
+
+
+What:		/sys/class/pktcdvd/pktcdvd[0-7]/dev
+What:		/sys/class/pktcdvd/pktcdvd[0-7]/uevent
+Date:		Oct. 2006
+KernelVersion:	2.6.20
+Contact:	Thomas Maier <[e-mail]>
+Description:
+		dev:	(RO) Device id
+
+		uevent:	(WO) To send a uevent
+
+
+What:		/sys/class/pktcdvd/pktcdvd[0-7]/stat/packets_started
+What:		/sys/class/pktcdvd/pktcdvd[0-7]/stat/packets_finished
+What:		/sys/class/pktcdvd/pktcdvd[0-7]/stat/kb_written
+What:		/sys/class/pktcdvd/pktcdvd[0-7]/stat/kb_read
+What:		/sys/class/pktcdvd/pktcdvd[0-7]/stat/kb_read_gather
+What:		/sys/class/pktcdvd/pktcdvd[0-7]/stat/reset
+Date:		Oct. 2006
+KernelVersion:	2.6.20
+Contact:	Thomas Maier <[e-mail]>
+Description:
+		packets_started:	(RO) Number of started packets.
+
+		packets_finished:	(RO) Number of finished packets.
+
+		kb_written:		(RO) kBytes written.
+
+		kb_read:		(RO) kBytes read.
+
+		kb_read_gather:		(RO) kBytes read to fill write packets.
+
+		reset:			(WO) Write any value to it to reset
+					pktcdvd device statistic values, like
+					bytes read/written.
+
+
+What:		/sys/class/pktcdvd/pktcdvd[0-7]/write_queue/size
+What:		/sys/class/pktcdvd/pktcdvd[0-7]/write_queue/congestion_off
+What:		/sys/class/pktcdvd/pktcdvd[0-7]/write_queue/congestion_on
+Date:		Oct. 2006
+KernelVersion:	2.6.20
+Contact:	Thomas Maier <[e-mail]>
+Description:
+		==============	================================================
+		size		(RO) Contains the size of the bio write queue.
+
+		congestion_off	(RW) If bio write queue size is below this mark,
+				accept new bio requests from the block layer.
+
+		congestion_on	(RW) If bio write queue size is higher as this
+				mark, do no longer accept bio write requests
+				from the block layer and wait till the pktcdvd
+				device has processed enough bio's so that bio
+				write queue size is below congestion off mark.
+				A value of <= 0 disables congestion control.
+		==============	================================================
+
+
+Example:
+--------
+To use the pktcdvd sysfs interface directly, you can do::
+
+    # create a new pktcdvd device mapped to /dev/hdc
+    echo "22:0" >/sys/class/pktcdvd/add
+    cat /sys/class/pktcdvd/device_map
+    # assuming device pktcdvd0 was created, look at stat's
+    cat /sys/class/pktcdvd/pktcdvd0/stat/kb_written
+    # print the device id of the mapped block device
+    fgrep pktcdvd0 /sys/class/pktcdvd/device_map
+    # remove device, using pktcdvd0 device id   253:0
+    echo "253:0" >/sys/class/pktcdvd/remove

Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml

···
   clock-names:
     const: stmmaceth
 
+  phy-supply:
+    description: PHY regulator
+
   syscon:
     $ref: /schemas/types.yaml#/definitions/phandle
     description:

Documentation/devicetree/bindings/net/marvell,orion-mdio.yaml

···
   8k has a second unit which provides an interface with the xMDIO bus. This
   driver handles these interfaces.
 
-allOf:
-  - $ref: "mdio.yaml#"
-
 properties:
   compatible:
     enum:
···
   - compatible
   - reg
 
+allOf:
+  - $ref: mdio.yaml#
+
+  - if:
+      required:
+        - interrupts
+
+    then:
+      properties:
+        reg:
+          items:
+            - items:
+                - $ref: /schemas/types.yaml#/definitions/cell
+                - const: 0x84
+
+    else:
+      properties:
+        reg:
+          items:
+            - items:
+                - $ref: /schemas/types.yaml#/definitions/cell
+                - enum:
+                    - 0x4
+                    - 0x10
+
 unevaluatedProperties: false
 
 examples:
   - |
     mdio@d0072004 {
       compatible = "marvell,orion-mdio";
-      reg = <0xd0072004 0x4>;
+      reg = <0xd0072004 0x84>;
       #address-cells = <1>;
       #size-cells = <0>;
       interrupts = <30>;

Documentation/devicetree/bindings/soundwire/qcom,soundwire.yaml

···
       or applicable for the respective data port.
       More info in MIPI Alliance SoundWire 1.0 Specifications.
     minItems: 3
-    maxItems: 5
+    maxItems: 8
 
   qcom,ports-sinterval-low:
     $ref: /schemas/types.yaml#/definitions/uint8-array
···
       or applicable for the respective data port.
       More info in MIPI Alliance SoundWire 1.0 Specifications.
     minItems: 3
-    maxItems: 5
+    maxItems: 8
 
   qcom,ports-block-pack-mode:
     $ref: /schemas/types.yaml#/definitions/uint8-array
···
       or applicable for the respective data port.
       More info in MIPI Alliance SoundWire 1.0 Specifications.
     minItems: 3
-    maxItems: 5
+    maxItems: 8
     items:
       oneOf:
         - minimum: 0
···
       or applicable for the respective data port.
       More info in MIPI Alliance SoundWire 1.0 Specifications.
     minItems: 3
-    maxItems: 5
+    maxItems: 8
     items:
       oneOf:
         - minimum: 0
···
       or applicable for the respective data port.
       More info in MIPI Alliance SoundWire 1.0 Specifications.
     minItems: 3
-    maxItems: 5
+    maxItems: 8
     items:
       oneOf:
         - minimum: 0

Documentation/maintainer/maintainer-entry-profile.rst

···
    ../riscv/patch-acceptance
    ../driver-api/media/maintainer-entry-profile
    ../driver-api/vfio-pci-device-specific-driver-acceptance
+   ../nvme/feature-and-quirk-policy

Documentation/nvme/feature-and-quirk-policy.rst

···
+.. SPDX-License-Identifier: GPL-2.0
+
+=======================================
+Linux NVMe feature and and quirk policy
+=======================================
+
+This file explains the policy used to decide what is supported by the
+Linux NVMe driver and what is not.
+
+
+Introduction
+============
+
+NVM Express is an open collection of standards and information.
+
+The Linux NVMe host driver in drivers/nvme/host/ supports devices
+implementing the NVM Express (NVMe) family of specifications, which
+currently consists of a number of documents:
+
+ - the NVMe Base specification
+ - various Command Set specifications (e.g. NVM Command Set)
+ - various Transport specifications (e.g. PCIe, Fibre Channel, RDMA, TCP)
+ - the NVMe Management Interface specification
+
+See https://nvmexpress.org/developers/ for the NVMe specifications.
+
+
+Supported features
+==================
+
+NVMe is a large suite of specifications, and contains features that are only
+useful or suitable for specific use-cases. It is important to note that Linux
+does not aim to implement every feature in the specification.  Every additional
+feature implemented introduces more code, more maintenance and potentially more
+bugs.  Hence there is an inherent tradeoff between functionality and
+maintainability of the NVMe host driver.
+
+Any feature implemented in the Linux NVMe host driver must support the
+following requirements:
+
+  1. The feature is specified in a release version of an official NVMe
+     specification, or in a ratified Technical Proposal (TP) that is
+     available on NVMe website. Or if it is not directly related to the
+     on-wire protocol, does not contradict any of the NVMe specifications.
+  2. Does not conflict with the Linux architecture, nor the design of the
+     NVMe host driver.
+  3. Has a clear, indisputable value-proposition and a wide consensus across
+     the community.
+
+Vendor specific extensions are generally not supported in the NVMe host
+driver.
+
+It is strongly recommended to work with the Linux NVMe and block layer
+maintainers and get feedback on specification changes that are intended
+to be used by the Linux NVMe host driver in order to avoid conflict at a
+later stage.
+
+
+Quirks
+======
+
+Sometimes implementations of open standards fail to correctly implement parts
+of the standards.  Linux uses identifier-based quirks to work around such
+implementation bugs.  The intent of quirks is to deal with widely available
+hardware, usually consumer, which Linux users can't use without these quirks.
+Typically these implementations are not or only superficially tested with Linux
+by the hardware manufacturer.
+
+The Linux NVMe maintainers decide ad hoc whether to quirk implementations
+based on the impact of the problem to Linux users and how it impacts
+maintainability of the driver.  In general quirks are a last resort, if no
+firmware updates or other workarounds are available from the vendor.
+
+Quirks will not be added to the Linux kernel for hardware that isn't available
+on the mass market.  Hardware that fails qualification for enterprise Linux
+distributions, ChromeOS, Android or other consumers of the Linux kernel
+should be fixed before it is shipped instead of relying on Linux quirks.

Documentation/process/maintainer-netdev.rst

···
 
 .. _netdev-FAQ:
 
-==========
-netdev FAQ
-==========
+=============================
+Networking subsystem (netdev)
+=============================
 
 tl;dr
 -----
···
  - don't repost your patches within one 24h period
  - reverse xmas tree
 
-What is netdev?
----------------
-It is a mailing list for all network-related Linux stuff.  This
+netdev
+------
+
+netdev is a mailing list for all network-related Linux stuff.  This
 includes anything found under net/ (i.e. core code like IPv6) and
 drivers/net (i.e. hardware specific drivers) in the Linux source tree.
 
 Note that some subsystems (e.g. wireless drivers) which have a high
-volume of traffic have their own specific mailing lists.
+volume of traffic have their own specific mailing lists and trees.
 
 The netdev list is managed (like many other Linux mailing lists) through
 VGER (http://vger.kernel.org/) with archives available at
···
 Linux development (i.e. RFC, review, comments, etc.) takes place on
 netdev.
 
-How do the changes posted to netdev make their way into Linux?
---------------------------------------------------------------
-There are always two trees (git repositories) in play.  Both are
-driven by David Miller, the main network maintainer.  There is the
-``net`` tree, and the ``net-next`` tree.  As you can probably guess from
-the names, the ``net`` tree is for fixes to existing code already in the
-mainline tree from Linus, and ``net-next`` is where the new code goes
-for the future release.  You can find the trees here:
+Development cycle
+-----------------
 
-- https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
-- https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
-
-How do I indicate which tree (net vs. net-next) my patch should be in?
-----------------------------------------------------------------------
-To help maintainers and CI bots you should explicitly mark which tree
-your patch is targeting. Assuming that you use git, use the prefix
-flag::
-
-  git format-patch --subject-prefix='PATCH net-next' start..finish
-
-Use ``net`` instead of ``net-next`` (always lower case) in the above for
-bug-fix ``net`` content.
-
-How often do changes from these trees make it to the mainline Linus tree?
--------------------------------------------------------------------------
-To understand this, you need to know a bit of background information on
+Here is a bit of background information on
 the cadence of Linux development.  Each new release starts off with a
 two week "merge window" where the main maintainers feed their new stuff
 to Linus for merging into the mainline tree.  After the two weeks, the
···
 state of churn), and a week after the last vX.Y-rcN was done, the
 official vX.Y is released.
 
-Relating that to netdev: At the beginning of the 2-week merge window,
-the ``net-next`` tree will be closed - no new changes/features.  The
-accumulated new content of the past ~10 weeks will be passed onto
+To find out where we are now in the cycle - load the mainline (Linus)
+page here:
+
+  https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
+
+and note the top of the "tags" section.  If it is rc1, it is early in
+the dev cycle.  If it was tagged rc7 a week ago, then a release is
+probably imminent. If the most recent tag is a final release tag
+(without an ``-rcN`` suffix) - we are most likely in a merge window
+and ``net-next`` is closed.
+
+git trees and patch flow
+------------------------
+
+There are two networking trees (git repositories) in play.  Both are
+driven by David Miller, the main network maintainer.  There is the
+``net`` tree, and the ``net-next`` tree.  As you can probably guess from
+the names, the ``net`` tree is for fixes to existing code already in the
+mainline tree from Linus, and ``net-next`` is where the new code goes
+for the future release.  You can find the trees here:
+
+- https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
+- https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
+
+Relating that to kernel development: At the beginning of the 2-week
+merge window, the ``net-next`` tree will be closed - no new changes/features.
+The accumulated new content of the past ~10 weeks will be passed onto
 mainline/Linus via a pull request for vX.Y -- at the same time, the
 ``net`` tree will start accumulating fixes for this pulled content
 relating to vX.Y
···
 
 Finally, the vX.Y gets released, and the whole cycle starts over.
 
-So where are we now in this cycle?
-----------------------------------
+netdev patch review
+-------------------
 
-Load the mainline (Linus) page here:
+Patch status
+~~~~~~~~~~~~
 
-  https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
-
-and note the top of the "tags" section.  If it is rc1, it is early in
-the dev cycle.  If it was tagged rc7 a week ago, then a release is
-probably imminent. If the most recent tag is a final release tag
-(without an ``-rcN`` suffix) - we are most likely in a merge window
-and ``net-next`` is closed.
-
-How can I tell the status of a patch I've sent?
------------------------------------------------
-Start by looking at the main patchworks queue for netdev:
+Status of a patch can be checked by looking at the main patchwork
+queue for netdev:
 
   https://patchwork.kernel.org/project/netdevbpf/list/
 
···
 which carried them so if you have trouble finding your patch append
 the value of ``Message-ID`` to the URL above.
 
-How long before my patch is accepted?
--------------------------------------
+Updating patch status
+~~~~~~~~~~~~~~~~~~~~~
+
+It may be tempting to help the maintainers and update the state of your
+own patches when you post a new version or spot a bug. Please **do not**
+do that.
+Interfering with the patch status on patchwork will only cause confusion. Leave
+it to the maintainer to figure out what is the most recent and current
+version that should be applied. If there is any doubt, the maintainer
+will reply and ask what should be done.
+
+Review timelines
+~~~~~~~~~~~~~~~~
+
 Generally speaking, the patches get triaged quickly (in less than
 48h). But be patient, if your patch is active in patchwork (i.e. it's
 listed on the project's patch list) the chances it was missed are close to zero.
···
 patch is a good way to ensure your patch is ignored or pushed to the
 bottom of the priority list.
 
-Should I directly update patchwork state of my own patches?
------------------------------------------------------------
-It may be tempting to help the maintainers and update the state of your
-own patches when you post a new version or spot a bug. Please do not do that.
-Interfering with the patch status on patchwork will only cause confusion. Leave
-it to the maintainer to figure out what is the most recent and current
-version that should be applied. If there is any doubt, the maintainer
-will reply and ask what should be done.
+Partial resends
+~~~~~~~~~~~~~~~
 
-How do I divide my work into patches?
--------------------------------------
-
-Put yourself in the shoes of the reviewer. Each patch is read separately
-and therefore should constitute a comprehensible step towards your stated
-goal.
-
-Avoid sending series longer than 15 patches. Larger series takes longer
-to review as reviewers will defer looking at it until they find a large
-chunk of time. A small series can be reviewed in a short time, so Maintainers
-just do it. As a result, a sequence of smaller series gets merged quicker and
-with better review coverage. Re-posting large series also increases the mailing
-list traffic.
-
-I made changes to only a few patches in a patch series should I resend only those changed?
-------------------------------------------------------------------------------------------
-No, please resend the entire patch series and make sure you do number your
+Please always resend the entire patch series and make sure you do number your
 patches such that it is clear this is the latest and greatest set of patches
-that can be applied.
+that can be applied. Do not try to resend just the patches which changed.
 
-I have received review feedback, when should I post a revised version of the patches?
--------------------------------------------------------------------------------------
-Allow at least 24 hours to pass between postings. This will ensure reviewers
-from all geographical locations have a chance to chime in. Do not wait
-too long (weeks) between postings either as it will make it harder for reviewers
-to recall all the context.
+Handling misapplied patches
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-Make sure you address all the feedback in your new posting. Do not post a new
-version of the code if the discussion about the previous version is still
-ongoing, unless directly instructed by a reviewer.
-
-I submitted multiple versions of a patch series and it looks like a version other than the last one has been accepted, what should I do?
-----------------------------------------------------------------------------------------------------------------------------------------
+Occasionally a patch series gets applied before receiving critical feedback,
+or the wrong version of a series gets applied.
 There is no revert possible, once it is pushed out, it stays like that.
 Please send incremental versions on top of what has been merged in order to fix
 the patches the way they would look like if your latest patch series was to be
 merged.
 
-Are there special rules regarding stable submissions on netdev?
----------------------------------------------------------------
+Stable tree
+~~~~~~~~~~~
+
 While it used to be the case that netdev submissions were not supposed
 to carry explicit ``CC: [e-mail]`` tags that is no longer
 the case today. Please follow the standard stable rules in
 :ref:`Documentation/process/stable-kernel-rules.rst <stable_kernel_rules>`,
 and make sure you include appropriate Fixes tags!
 
-Is the comment style convention different for the networking content?
----------------------------------------------------------------------
-Yes, in a largely trivial way.  Instead of this::
+Security fixes
+~~~~~~~~~~~~~~
 
-  /*
-   * foobar blah blah blah
-   * another line of text
-   */
-
-it is requested that you make it look like this::
-
-  /* foobar blah blah blah
-   * another line of text
-   */
-
-What is "reverse xmas tree"?
-----------------------------
-
-Netdev has a convention for ordering local variables in functions.
-Order the variable declaration lines longest to shortest, e.g.::
-
-  struct scatterlist *sg;
-  struct sk_buff *skb;
-  int err, i;
-
-If there are dependencies between the variables preventing the ordering
-move the initialization out of line.
-
-I am working in existing code which uses non-standard formatting. Which formatting should I use?
-------------------------------------------------------------------------------------------------
-Make your code follow the most recent guidelines, so that eventually all code
-in the domain of netdev is in the preferred format.
-
-I found a bug that might have possible security implications or similar. Should I mail the main netdev maintainer off-list?
----------------------------------------------------------------------------------------------------------------------------
-No. The current netdev maintainer has consistently requested that
+Do not email netdev maintainers directly if you think you discovered
+a bug that might have possible security implications.
+The current netdev maintainer has consistently requested that
 people use the mailing lists and not reach out directly.  If you aren't
 OK with that, then perhaps consider mailing [e-mail] or
 reading about http://oss-security.openwall.org/wiki/mailing-lists/distros
 as possible alternative mechanisms.
 
-What level of testing is expected before I submit my change?
-------------------------------------------------------------
-At the very minimum your changes must survive an ``allyesconfig`` and an
-``allmodconfig`` build with ``W=1`` set without new warnings or failures.
 
-Ideally you will have done run-time testing specific to your change,
-and the patch series contains a set of kernel selftest for
-``tools/testing/selftests/net`` or using the KUnit framework.
+Co-posting changes to user space components
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-You are expected to test your changes on top of the relevant networking
-tree (``net`` or ``net-next``) and not e.g. a stable tree or ``linux-next``.
-
-How do I post corresponding changes to user space components?
--------------------------------------------------------------
 User space code exercising kernel features should be posted
 alongside kernel patches. This gives reviewers a chance to see
 how any new interface is used and how well it works.
···
 Posting as one thread is discouraged because it confuses patchwork
 (as of patchwork 2.2.2).
 
-Can I reproduce the checks from patchwork on my local machine?
---------------------------------------------------------------
+Preparing changes
+-----------------
 
-Checks in patchwork are mostly simple wrappers around existing kernel
-scripts, the sources are available at:
-
-https://github.com/kuba-moo/nipa/tree/master/tests
-
-Running all the builds and checks locally is a pain, can I post my patches and have the patchwork bot validate them?
---------------------------------------------------------------------------------------------------------------------
-
-No, you must ensure that your patches are ready by testing them locally
-before posting to the mailing list. The patchwork build bot instance
-gets overloaded very easily and netdev@vger really doesn't need more
-traffic if we can help it.
-
-netdevsim is great, can I extend it for my out-of-tree tests?
--------------------------------------------------------------
-
-No, ``netdevsim`` is a test vehicle solely for upstream tests.
-(Please add your tests under ``tools/testing/selftests/``.)
-
-We also give no guarantees that ``netdevsim`` won't change in the future
-in a way which would break what would normally be considered uAPI.
-
-Is netdevsim considered a "user" of an API?
--------------------------------------------
-
-Linux kernel has a long standing rule that no API should be added unless
-it has a real, in-tree user. Mock-ups and tests based on ``netdevsim`` are
-strongly encouraged when adding new APIs, but ``netdevsim`` in itself
-is **not** considered a use case/user.
-
-Any other tips to help ensure my net/net-next patch gets OK'd?
---------------------------------------------------------------
-Attention to detail.  Re-read your own work as if you were the
+Attention to detail is important.  Re-read your own work as if you were the
 reviewer.  You can start with using ``checkpatch.pl``, perhaps even with
 the ``--strict`` flag.  But do not be mindlessly robotic in doing so.
 If your change is a bug fix, make sure your commit log indicates the
···
 :ref:`Documentation/process/submitting-patches.rst <submittingpatches>`
 to be sure you are not repeating some common mistake documented there.
 
-My company uses peer feedback in employee performance reviews. Can I ask netdev maintainers for feedback?
----------------------------------------------------------------------------------------------------------
+Indicating target tree
+~~~~~~~~~~~~~~~~~~~~~~
 
-Yes, especially if you spend significant amount of time reviewing code
+To help maintainers and CI bots you should explicitly mark which tree
+your patch is targeting. Assuming that you use git, use the prefix
+flag::
+
+  git format-patch --subject-prefix='PATCH net-next' start..finish
+
+Use ``net`` instead of ``net-next`` (always lower case) in the above for
+bug-fix ``net`` content.
+
+Dividing work into patches
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Put yourself in the shoes of the reviewer. Each patch is read separately
+and therefore should constitute a comprehensible step towards your stated
+goal.
+
+Avoid sending series longer than 15 patches. Larger series takes longer
+to review as reviewers will defer looking at it until they find a large
+chunk of time. A small series can be reviewed in a short time, so Maintainers
+just do it. As a result, a sequence of smaller series gets merged quicker and
+with better review coverage. Re-posting large series also increases the mailing
+list traffic.
+
+Multi-line comments
+~~~~~~~~~~~~~~~~~~~
+
+Comment style convention is slightly different for networking and most of
+the tree.  Instead of this::
+
+  /*
+   * foobar blah blah blah
+   * another line of text
+   */
+
+it is requested that you make it look like this::
+
+  /* foobar blah blah blah
+   * another line of text
+   */
+
+Local variable ordering ("reverse xmas tree", "RCS")
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Netdev has a convention for ordering local variables in functions.
+Order the variable declaration lines longest to shortest, e.g.::
+
+  struct scatterlist *sg;
+  struct sk_buff *skb;
+  int err, i;
+
+If there are dependencies between the variables preventing the ordering
+move the initialization out of line.
+
+Format precedence
+~~~~~~~~~~~~~~~~~
+
+When working in existing code which uses nonstandard formatting make
+your code follow the most recent guidelines, so that eventually all code
+in the domain of netdev is in the preferred format.
+
+Resending after review
+~~~~~~~~~~~~~~~~~~~~~~
+
+Allow at least 24 hours to pass between postings. This will ensure reviewers
+from all geographical locations have a chance to chime in. Do not wait
+too long (weeks) between postings either as it will make it harder for reviewers
+to recall all the context.
+
+Make sure you address all the feedback in your new posting. Do not post a new
+version of the code if the discussion about the previous version is still
+ongoing, unless directly instructed by a reviewer.
+
+Testing
+-------
+
+Expected level of testing
+~~~~~~~~~~~~~~~~~~~~~~~~~
+
+At the very minimum your changes must survive an ``allyesconfig`` and an
+``allmodconfig`` build with ``W=1`` set without new warnings or failures.
+
+Ideally you will have done run-time testing specific to your change,
+and the patch series contains a set of kernel selftest for
+``tools/testing/selftests/net`` or using the KUnit framework.
+
+You are expected to test your changes on top of the relevant networking
+tree (``net`` or ``net-next``) and not e.g. a stable tree or ``linux-next``.
+
+patchwork checks
+~~~~~~~~~~~~~~~~
+
+Checks in patchwork are mostly simple wrappers around existing kernel
+scripts, the sources are available at:
+
+https://github.com/kuba-moo/nipa/tree/master/tests
+
+**Do not** post your patches just to run them through the checks.
+You must ensure that your patches are ready by testing them locally
+before posting to the mailing list. The patchwork build bot instance
+gets overloaded very easily and netdev@vger really doesn't need more
+traffic if we can help it.
+
+netdevsim
+~~~~~~~~~
+
+``netdevsim`` is a test driver which can be used to exercise driver
+configuration APIs without requiring capable hardware.
+Mock-ups and tests based on ``netdevsim`` are strongly encouraged when
+adding new APIs, but ``netdevsim`` in itself is **not** considered
+a use case/user. You must also implement the new APIs in a real driver.
+
+We give no guarantees that ``netdevsim`` won't change in the future
+in a way which would break what would normally be considered uAPI.
+
+``netdevsim`` is reserved for use by upstream tests only, so any
+new ``netdevsim`` features must be accompanied by selftests under
+``tools/testing/selftests/``.
+
+Testimonials / feedback
+-----------------------
+
+Some companies use peer feedback in employee performance reviews.
+Please feel free to request feedback from netdev maintainers,
+especially if you spend significant amount of time reviewing code
 and go out of your way to improve shared infrastructure.
 
 The feedback must be requested by you, the contributor, and will always

Documentation/virt/kvm/api.rst

···
   32 vCPUs in the shared_info page, KVM does not automatically do so
   and instead requires that KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO be used
   explicitly even when the vcpu_info for a given vCPU resides at the
-  "default" location in the shared_info page. This is because KVM is
-  not aware of the Xen CPU id which is used as the index into the
-  vcpu_info[] array, so cannot know the correct default location.
+  "default" location in the shared_info page. This is because KVM may
+  not be aware of the Xen CPU id which is used as the index into the
+  vcpu_info[] array, so may know the correct default location.
 
   Note that the shared info page may be constantly written to by KVM;
   it contains the event channel bitmap used to deliver interrupts to
···
   any vCPU has been running or any event channel interrupts can be
   routed to the guest.
 
+  Setting the gfn to KVM_XEN_INVALID_GFN will disable the shared info
+  page.
+
 KVM_XEN_ATTR_TYPE_UPCALL_VECTOR
   Sets the exception vector used to deliver Xen event channel upcalls.
   This is the HVM-wide vector injected directly by the hypervisor
   (not through the local APIC), typically configured by a guest via
-  HVM_PARAM_CALLBACK_IRQ.
+  HVM_PARAM_CALLBACK_IRQ. This can be disabled again (e.g. for guest
+  SHUTDOWN_soft_reset) by setting it to zero.
 
 KVM_XEN_ATTR_TYPE_EVTCHN
   This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates
   support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It configures
   an outbound port number for interception of EVTCHNOP_send requests
-  from the guest. A given sending port number may be directed back
-  to a specified vCPU (by APIC ID) / port / priority on the guest,
-  or to trigger events on an eventfd. The vCPU and priority can be
-  changed by setting KVM_XEN_EVTCHN_UPDATE in a subsequent call,
-  but other fields cannot change for a given sending port. A port
-  mapping is removed by using KVM_XEN_EVTCHN_DEASSIGN in the flags
-  field.
+  from the guest. A given sending port number may be directed back to
+  a specified vCPU (by APIC ID) / port / priority on the guest, or to
+  trigger events on an eventfd. The vCPU and priority can be changed
+  by setting KVM_XEN_EVTCHN_UPDATE in a subsequent call, but but other
+  fields cannot change for a given sending port. A port mapping is
+  removed by using KVM_XEN_EVTCHN_DEASSIGN in the flags field. Passing
+  KVM_XEN_EVTCHN_RESET in the flags field removes all interception of
+  outbound event channels. The values of the flags field are mutually
+  exclusive and cannot be combined as a bitmask.
 
 KVM_XEN_ATTR_TYPE_XEN_VERSION
   This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates
···
   support for KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG. It enables the
   XEN_RUNSTATE_UPDATE flag which allows guest vCPUs to safely read
   other vCPUs' vcpu_runstate_info. Xen guests enable this feature via
-  the VM_ASST_TYPE_runstate_update_flag of the HYPERVISOR_vm_assist
+  the VMASST_TYPE_runstate_update_flag of the HYPERVISOR_vm_assist
   hypercall.
 
 4.127 KVM_XEN_HVM_GET_ATTR
···
   As with the shared_info page for the VM, the corresponding page may be
   dirtied at any time if event channel interrupt delivery is enabled, so
   userspace should always assume that the page is dirty without relying
-  on dirty logging.
+  on dirty logging. Setting the gpa to KVM_XEN_INVALID_GPA will disable
+  the vcpu_info.
 
 KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO
   Sets the guest physical address of an additional pvclock structure
   for a given vCPU. This is typically used for guest vsyscall support.
+  Setting the gpa to KVM_XEN_INVALID_GPA will disable the structure.
 
 KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR
   Sets the guest physical address of the vcpu_runstate_info for a given
   vCPU. This is how a Xen guest tracks CPU state such as steal time.
+  Setting the gpa to KVM_XEN_INVALID_GPA will disable the runstate area.
 
 KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT
   Sets the runstate (RUNSTATE_running/_runnable/_blocked/_offline) of
···
   This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates
   support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It sets the
   event channel port/priority for the VIRQ_TIMER of the vCPU, as well
-  as allowing a pending timer to be saved/restored.
+  as allowing a pending timer to be saved/restored. Setting the timer
+  port to zero disables kernel handling of the singleshot timer.
 
 KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR
   This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates
···
   per-vCPU local APIC upcall vector, configured by a Xen guest with
   the HVMOP_set_evtchn_upcall_vector hypercall. This is typically
   used by Windows guests, and is distinct from the HVM-wide upcall
-  vector configured with HVM_PARAM_CALLBACK_IRQ.
+  vector configured with HVM_PARAM_CALLBACK_IRQ. It is disabled by
+  setting the vector to zero.
 
 
 4.129 KVM_XEN_VCPU_GET_ATTR
···
 Please note that the kernel is allowed to use the kvm_run structure as the
 primary storage for certain register types. Therefore, the kernel may use the
 values in kvm_run even if the corresponding bit in kvm_dirty_regs is not set.
-
-::
-
-  };
-
 
 
 6. Capabilities that can be enabled on vCPUs

Documentation/virt/kvm/locking.rst

···
 - kvm->slots_lock is taken outside kvm->irq_lock, though acquiring
   them together is quite rare.
 
-- Unlike kvm->slots_lock, kvm->slots_arch_lock is released before
-  synchronize_srcu(&kvm->srcu).  Therefore kvm->slots_arch_lock
-  can be taken inside a kvm->srcu read-side critical section,
-  while kvm->slots_lock cannot.
-
 - kvm->mn_active_invalidate_count ensures that pairs of
   invalidate_range_start() and invalidate_range_end() callbacks
   use the same memslots array.  kvm->slots_lock and kvm->slots_arch_lock
   are taken on the waiting side in install_new_memslots, so MMU notifiers
   must not take either kvm->slots_lock or kvm->slots_arch_lock.
+
+For SRCU:
+
+- ``synchronize_srcu(&kvm->srcu)`` is called _inside_
+  the kvm->slots_lock critical section, therefore kvm->slots_lock
+  cannot be taken inside a kvm->srcu read-side critical section.
+  Instead, kvm->slots_arch_lock is released before the call
+  to ``synchronize_srcu()`` and _can_ be taken inside a
+  kvm->srcu read-side critical section.
+
+- kvm->lock is taken inside kvm->srcu, therefore
+  ``synchronize_srcu(&kvm->srcu)`` cannot be called inside
+  a kvm->lock critical section.  If you cannot delay the
+  call until after kvm->lock is released, use ``call_srcu``.
 
 On x86:
 

MAINTAINERS

···
 F:	arch/x86/kvm/kvm_onhyperv.*
 F:	arch/x86/kvm/svm/hyperv.*
 F:	arch/x86/kvm/svm/svm_onhyperv.*
-F:	arch/x86/kvm/vmx/evmcs.*
+F:	arch/x86/kvm/vmx/hyperv.*
 
 KVM X86 Xen (KVM/Xen)
 M:	David Woodhouse <[e-mail]>
···
 S:	Supported
 W:	http://git.infradead.org/nvme.git
 T:	git://git.infradead.org/nvme.git
+F:	Documentation/nvme/
 F:	drivers/nvme/host/
 F:	drivers/nvme/common/
 F:	include/linux/nvme*
···
 S:	Supported
 F:	Documentation/devicetree/bindings/input/pine64,pinephone-keyboard.yaml
 F:	drivers/input/keyboard/pinephone-keyboard.c
+
+PKTCDVD DRIVER
+M:	[e-mail]
+S:	Orphan
+F:	drivers/block/pktcdvd.c
+F:	include/linux/pktcdvd.h
+F:	include/uapi/linux/pktcdvd.h
 
 PLANTOWER PMS7003 AIR POLLUTION SENSOR DRIVER
 M:	Tomasz Duszynski <[e-mail]>
···
 F:	drivers/scsi/vmw_pvscsi.h
 
 VMWARE VIRTUAL PTP CLOCK DRIVER
-M:	Vivek Thampi <[e-mail]>
+M:	Srivatsa S. Bhat (VMware) <[e-mail]>
+M:	Deep Shah <[e-mail]>
+R:	Alexey Makhalov <[e-mail]>
 R:	VMware PV-Drivers Reviewers <[e-mail]>
 L:	[e-mail]
 S:	Supported

Makefile

···
 VERSION = 6
 PATCHLEVEL = 2
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc3
 NAME = Hurr durr I'ma ninja sloth
 
 # *DOCUMENTATION*
···
 			headers_install modules_install kernelrelease image_name
 no-sync-config-targets := $(no-dot-config-targets) %install kernelrelease \
 			  image_name
-single-targets := %.a %.i %.rsi %.ko %.lds %.ll %.lst %.mod %.o %.s %.symtypes %/
+single-targets := %.a %.i %.ko %.lds %.ll %.lst %.mod %.o %.rsi %.s %.symtypes %/
 
 config-build	:=
 mixed-build	:=
···
 # Remove MODORDER when done because it is not the real one.
 PHONY += single_modules
 single_modules: $(single-no-ko) modules_prepare
-	$(Q){ $(foreach m, $(single-ko), echo $(extmod_prefix)$m;) } > $(MODORDER)
+	$(Q){ $(foreach m, $(single-ko), echo $(extmod_prefix)$(m:%.ko=%.o);) } > $(MODORDER)
 	$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modpost
 ifneq ($(KBUILD_MODPOST_NOFINAL),1)
 	$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modfinal

arch/arm/include/asm/thread_info.h

···
 #define TIF_NEED_RESCHED	1	/* rescheduling necessary */
 #define TIF_NOTIFY_RESUME	2	/* callback before returning to user */
 #define TIF_UPROBE		3	/* breakpointed or singlestepping */
-#define TIF_SYSCALL_TRACE	4	/* syscall trace active */
-#define TIF_SYSCALL_AUDIT	5	/* syscall auditing active */
-#define TIF_SYSCALL_TRACEPOINT	6	/* syscall tracepoint instrumentation */
-#define TIF_SECCOMP		7	/* seccomp syscall filtering active */
-#define TIF_NOTIFY_SIGNAL	8	/* signal notifications exist */
+#define TIF_NOTIFY_SIGNAL	4	/* signal notifications exist */
 
 #define TIF_USING_IWMMXT	17
 #define TIF_MEMDIE		18	/* is terminating due to OOM killer */
-#define TIF_RESTORE_SIGMASK	20
+#define TIF_RESTORE_SIGMASK	19
+#define TIF_SYSCALL_TRACE	20	/* syscall trace active */
+#define TIF_SYSCALL_AUDIT	21	/* syscall auditing active */
+#define TIF_SYSCALL_TRACEPOINT	22	/* syscall tracepoint instrumentation */
+#define TIF_SECCOMP		23	/* seccomp syscall filtering active */
+
 
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)

arch/arm64/crypto/sm4-ce-ccm-core.S

···
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/assembler.h>
 #include "sm4-ce-asm.h"
 
···
 SYM_FUNC_END(sm4_ce_ccm_final)
 
 .align 3
-SYM_FUNC_START(sm4_ce_ccm_enc)
+SYM_TYPED_FUNC_START(sm4_ce_ccm_enc)
 	/* input:
 	 *   x0: round key array, CTX
 	 *   x1: dst
···
 SYM_FUNC_END(sm4_ce_ccm_enc)
 
 .align 3
-SYM_FUNC_START(sm4_ce_ccm_dec)
+SYM_TYPED_FUNC_START(sm4_ce_ccm_dec)
 	/* input:
 	 *   x0: round key array, CTX
 	 *   x1: dst

arch/arm64/crypto/sm4-ce-gcm-core.S

···
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/assembler.h>
 #include "sm4-ce-asm.h"
 
···
 SYM_FUNC_END(pmull_ghash_update)
 
 .align 3
-SYM_FUNC_START(sm4_ce_pmull_gcm_enc)
+SYM_TYPED_FUNC_START(sm4_ce_pmull_gcm_enc)
 	/* input:
 	 *   x0: round key array, CTX
 	 *   x1: dst
···
 #define	RH3	v20
 
 .align 3
-SYM_FUNC_START(sm4_ce_pmull_gcm_dec)
+SYM_TYPED_FUNC_START(sm4_ce_pmull_gcm_dec)
 	/* input:
 	 *   x0: round key array, CTX
 	 *   x1: dst

arch/mips/ralink/of.c

···
 	dtb = get_fdt();
 	__dt_setup_arch(dtb);
 
-	if (!early_init_dt_scan_memory())
+	if (early_init_dt_scan_memory())
 		return;
 
 	if (soc_info.mem_detect)

arch/powerpc/boot/dts/fsl/t2081si-post.dtsi

···
 		interrupts = <16 2 1 9>;
 	};
 };
+
+&fman0_rx_0x08 {
+	/delete-property/ fsl,fman-10g-port;
+};
+
+&fman0_tx_0x28 {
+	/delete-property/ fsl,fman-10g-port;
+};
+
+&fman0_rx_0x09 {
+	/delete-property/ fsl,fman-10g-port;
+};
+
+&fman0_tx_0x29 {
+	/delete-property/ fsl,fman-10g-port;
+};

arch/powerpc/kernel/vmlinux.lds.S

···
 #define BSS_FIRST_SECTIONS *(.bss.prominit)
 #define EMITS_PT_NOTE
 #define RO_EXCEPTION_TABLE_ALIGN	0
+#define RUNTIME_DISCARD_EXIT
 
 #define SOFT_MASK_TABLE(align)						\
 	. = ALIGN(align);						\
···
 	DISCARDS
 	/DISCARD/ : {
 		*(*.EMB.apuinfo)
-		*(.glink .iplt .plt .rela* .comment)
+		*(.glink .iplt .plt)
 		*(.gnu.version*)
 		*(.gnu.attributes)
 		*(.eh_frame)
+#ifndef CONFIG_RELOCATABLE
+		*(.rela*)
+#endif
 	}
 }

arch/riscv/include/asm/uaccess.h

···
 	might_fault();						\
 	access_ok(__p, sizeof(*__p)) ?		\
 		__get_user((x), __p) :				\
-		((x) = 0, -EFAULT);				\
+		((x) = (__force __typeof__(x))0, -EFAULT);	\
 })
 
 #define __put_user_asm(insn, x, ptr, err)			\

arch/riscv/kernel/probes/simulate-insn.h

···
 	} while (0)
 
 __RISCV_INSN_FUNCS(c_j,		0xe003, 0xa001);
-__RISCV_INSN_FUNCS(c_jr,	0xf007, 0x8002);
+__RISCV_INSN_FUNCS(c_jr,	0xf07f, 0x8002);
 __RISCV_INSN_FUNCS(c_jal,	0xe003, 0x2001);
-__RISCV_INSN_FUNCS(c_jalr,	0xf007, 0x9002);
+__RISCV_INSN_FUNCS(c_jalr,	0xf07f, 0x9002);
 __RISCV_INSN_FUNCS(c_beqz,	0xe003, 0xc001);
 __RISCV_INSN_FUNCS(c_bnez,	0xe003, 0xe001);
 __RISCV_INSN_FUNCS(c_ebreak,	0xffff, 0x9002);

arch/x86/coco/tdx/tdx.c

···
 {
 	unsigned long *reg, val, vaddr;
 	char buffer[MAX_INSN_SIZE];
+	enum insn_mmio_type mmio;
 	struct insn insn = {};
-	enum mmio_type mmio;
 	int size, extend_size;
 	u8 extend_val = 0;
 
···
 		return -EINVAL;
 
 	mmio = insn_decode_mmio(&insn, &size);
-	if (WARN_ON_ONCE(mmio == MMIO_DECODE_FAILED))
+	if (WARN_ON_ONCE(mmio == INSN_MMIO_DECODE_FAILED))
 		return -EINVAL;
 
-	if (mmio != MMIO_WRITE_IMM && mmio != MMIO_MOVS) {
+	if (mmio != INSN_MMIO_WRITE_IMM && mmio != INSN_MMIO_MOVS) {
 		reg = insn_get_modrm_reg_ptr(&insn, regs);
 		if (!reg)
 			return -EINVAL;
···
 
 	/* Handle writes first */
 	switch (mmio) {
-	case MMIO_WRITE:
+	case INSN_MMIO_WRITE:
 		memcpy(&val, reg, size);
 		if (!mmio_write(size, ve->gpa, val))
 			return -EIO;
 		return insn.length;
-	case MMIO_WRITE_IMM:
+	case INSN_MMIO_WRITE_IMM:
 		val = insn.immediate.value;
 		if (!mmio_write(size, ve->gpa, val))
 			return -EIO;
 		return insn.length;
-	case MMIO_READ:
-	case MMIO_READ_ZERO_EXTEND:
-	case MMIO_READ_SIGN_EXTEND:
+	case INSN_MMIO_READ:
+	case INSN_MMIO_READ_ZERO_EXTEND:
+	case INSN_MMIO_READ_SIGN_EXTEND:
 		/* Reads are handled below */
 		break;
-	case MMIO_MOVS:
-	case MMIO_DECODE_FAILED:
+	case INSN_MMIO_MOVS:
+	case INSN_MMIO_DECODE_FAILED:
 		/*
 		 * MMIO was accessed with an instruction that could not be
 		 * decoded or handled properly. It was likely not using io.h
···
 		return -EIO;
 
 	switch (mmio) {
-	case MMIO_READ:
+	case INSN_MMIO_READ:
 		/* Zero-extend for 32-bit operation */
 		extend_size = size == 4 ? sizeof(*reg) : 0;
 		break;
-	case MMIO_READ_ZERO_EXTEND:
+	case INSN_MMIO_READ_ZERO_EXTEND:
 		/* Zero extend based on operand size */
 		extend_size = insn.opnd_bytes;
 		break;
-	case MMIO_READ_SIGN_EXTEND:
+	case INSN_MMIO_READ_SIGN_EXTEND:
 		/* Sign extend based on operand size */
 		extend_size = insn.opnd_bytes;
 		if (size == 1 && val & BIT(7))

arch/x86/events/amd/core.c

···
 		 * numbered counter following it.
 		 */
 		for (i = 0; i < x86_pmu.num_counters - 1; i += 2)
-			even_ctr_mask |= 1 << i;
+			even_ctr_mask |= BIT_ULL(i);
 
 		pair_constraint = (struct event_constraint)
 				    __EVENT_CONSTRAINT(0, even_ctr_mask, 0,

arch/x86/events/rapl.c

···
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X,		&model_hsx),
 	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L,		&model_skl),
 	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE,		&model_skl),
+	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L,		&model_skl),
+	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE,		&model_skl),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE,		&model_skl),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L,		&model_skl),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N,		&model_skl),
 	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X,	&model_spr),
+	X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X,	&model_spr),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE,		&model_skl),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P,	&model_skl),
 	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S,	&model_skl),
+	X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE,		&model_skl),
+	X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L,	&model_skl),
 	{},
 };
 MODULE_DEVICE_TABLE(x86cpu, rapl_model_match);

arch/x86/include/asm/insn-eval.h

···
 bool insn_decode_from_regs(struct insn *insn, struct pt_regs *regs,
 			   unsigned char buf[MAX_INSN_SIZE], int buf_size);
 
-enum mmio_type {
-	MMIO_DECODE_FAILED,
-	MMIO_WRITE,
-	MMIO_WRITE_IMM,
-	MMIO_READ,
-	MMIO_READ_ZERO_EXTEND,
-	MMIO_READ_SIGN_EXTEND,
-	MMIO_MOVS,
+enum insn_mmio_type {
+	INSN_MMIO_DECODE_FAILED,
+	INSN_MMIO_WRITE,
+	INSN_MMIO_WRITE_IMM,
+	INSN_MMIO_READ,
+	INSN_MMIO_READ_ZERO_EXTEND,
+	INSN_MMIO_READ_SIGN_EXTEND,
+	INSN_MMIO_MOVS,
 };
 
-enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes);
+enum insn_mmio_type insn_decode_mmio(struct insn *insn, int *bytes);
 
 #endif /* _ASM_X86_INSN_EVAL_H */

arch/x86/kernel/callthunks.c

···
 	return within_module_coretext(addr);
 }
 
-static __init_or_module bool skip_addr(void *dest)
+static bool skip_addr(void *dest)
 {
 	if (dest == error_entry)
 		return true;
···
 	0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90,
 };
 
-static __init_or_module void *patch_dest(void *dest, bool direct)
+static void *patch_dest(void *dest, bool direct)
 {
 	unsigned int tsize = SKL_TMPL_SIZE;
 	u8 *pad = dest - tsize;

arch/x86/kernel/cpu/bugs.c

···
 		if (ctrl == PR_SPEC_FORCE_DISABLE)
 			task_set_spec_ib_force_disable(task);
 		task_update_spec_tif(task);
+		if (task == current)
+			indirect_branch_prediction_barrier();
 		break;
 	default:
 		return -ERANGE;

arch/x86/kernel/crash.c

···
 	kbuf.buf_align = ELF_CORE_HEADER_ALIGN;
 	kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 	ret = kexec_add_buffer(&kbuf);
-	if (ret) {
-		vfree((void *)image->elf_headers);
+	if (ret)
 		return ret;
-	}
 	image->elf_load_addr = kbuf.mem;
 	pr_debug("Loaded ELF headers at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
 		 image->elf_load_addr, kbuf.bufsz, kbuf.memsz);

arch/x86/kernel/kprobes/core.c

···
 #include <linux/extable.h>
 #include <linux/kdebug.h>
 #include <linux/kallsyms.h>
+#include <linux/kgdb.h>
 #include <linux/ftrace.h>
 #include <linux/kasan.h>
 #include <linux/moduleloader.h>
···
 		if (ret < 0)
 			return 0;
 
+#ifdef CONFIG_KGDB
 		/*
-		 * Another debugging subsystem might insert this breakpoint.
-		 * In that case, we can't recover it.
+		 * If there is a dynamically installed kgdb sw breakpoint,
+		 * this function should not be probed.
 		 */
-		if (insn.opcode.bytes[0] == INT3_INSN_OPCODE)
+		if (insn.opcode.bytes[0] == INT3_INSN_OPCODE &&
+		    kgdb_has_hit_break(addr))
 			return 0;
+#endif
 		addr += insn.length;
 	}
 

arch/x86/kernel/kprobes/opt.c

···
 #include <linux/extable.h>
 #include <linux/kdebug.h>
 #include <linux/kallsyms.h>
+#include <linux/kgdb.h>
 #include <linux/ftrace.h>
 #include <linux/objtool.h>
 #include <linux/pgtable.h>
···
 	return ret;
 }
 
-static bool is_padding_int3(unsigned long addr, unsigned long eaddr)
-{
-	unsigned char ops;
-
-	for (; addr < eaddr; addr++) {
-		if (get_kernel_nofault(ops, (void *)addr) < 0 ||
-		    ops != INT3_INSN_OPCODE)
-			return false;
-	}
-
-	return true;
-}
-
 /* Decode whole function to ensure any instructions don't jump into target */
 static int can_optimize(unsigned long paddr)
 {
···
 		ret = insn_decode_kernel(&insn, (void *)recovered_insn);
 		if (ret < 0)
 			return 0;
-
+#ifdef CONFIG_KGDB
 		/*
-		 * In the case of detecting unknown breakpoint, this could be
-		 * a padding INT3 between functions. Let's check that all the
-		 * rest of the bytes are also INT3.
+		 * If there is a dynamically installed kgdb sw breakpoint,
+		 * this function should not be probed.
 		 */
-		if (insn.opcode.bytes[0] == INT3_INSN_OPCODE)
-			return is_padding_int3(addr, paddr - offset + size) ? 1 : 0;
-
+		if (insn.opcode.bytes[0] == INT3_INSN_OPCODE &&
+		    kgdb_has_hit_break(addr))
+			return 0;
+#endif
 		/* Recover address */
 		insn.kaddr = (void *)addr;
 		insn.next_byte = (void *)(addr + insn.length);

arch/x86/kernel/sev.c

···
 static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
 {
 	struct insn *insn = &ctxt->insn;
+	enum insn_mmio_type mmio;
 	unsigned int bytes = 0;
-	enum mmio_type mmio;
 	enum es_result ret;
 	u8 sign_byte;
 	long *reg_data;
 
 	mmio = insn_decode_mmio(insn, &bytes);
-	if (mmio == MMIO_DECODE_FAILED)
+	if (mmio == INSN_MMIO_DECODE_FAILED)
 		return ES_DECODE_FAILED;
 
-	if (mmio != MMIO_WRITE_IMM && mmio != MMIO_MOVS) {
+	if (mmio != INSN_MMIO_WRITE_IMM && mmio != INSN_MMIO_MOVS) {
 		reg_data = insn_get_modrm_reg_ptr(insn, ctxt->regs);
 		if (!reg_data)
 			return ES_DECODE_FAILED;
 	}
 
 	switch (mmio) {
-	case MMIO_WRITE:
+	case INSN_MMIO_WRITE:
 		memcpy(ghcb->shared_buffer, reg_data, bytes);
 		ret = vc_do_mmio(ghcb, ctxt, bytes, false);
 		break;
-	case MMIO_WRITE_IMM:
+	case INSN_MMIO_WRITE_IMM:
 		memcpy(ghcb->shared_buffer, insn->immediate1.bytes, bytes);
 		ret = vc_do_mmio(ghcb, ctxt, bytes, false);
 		break;
-	case MMIO_READ:
+	case INSN_MMIO_READ:
 		ret = vc_do_mmio(ghcb, ctxt, bytes, true);
 		if (ret)
 			break;
···
 
 		memcpy(reg_data, ghcb->shared_buffer, bytes);
 		break;
-	case MMIO_READ_ZERO_EXTEND:
+	case INSN_MMIO_READ_ZERO_EXTEND:
 		ret = vc_do_mmio(ghcb, ctxt, bytes, true);
 		if (ret)
 			break;
···
 		memset(reg_data, 0, insn->opnd_bytes);
 		memcpy(reg_data, ghcb->shared_buffer, bytes);
 		break;
-	case MMIO_READ_SIGN_EXTEND:
+	case INSN_MMIO_READ_SIGN_EXTEND:
 		ret = vc_do_mmio(ghcb, ctxt, bytes, true);
 		if (ret)
 			break;
···
 		memset(reg_data, sign_byte, insn->opnd_bytes);
 		memcpy(reg_data, ghcb->shared_buffer, bytes);
 		break;
-	case MMIO_MOVS:
+	case INSN_MMIO_MOVS:
 		ret = vc_handle_mmio_movs(ctxt, bytes);
 		break;
 	default:

arch/x86/kvm/hyperv.c

···
 }
 
 struct kvm_hv_hcall {
+	/* Hypercall input data */
 	u64 param;
 	u64 ingpa;
 	u64 outgpa;
···
 	bool fast;
 	bool rep;
 	sse128_t xmm[HV_HYPERCALL_MAX_XMM_REGISTERS];
+
+	/*
+	 * Current read offset when KVM reads hypercall input data gradually,
+	 * either offset in bytes from 'ingpa' for regular hypercalls or the
+	 * number of already consumed 'XMM halves' for 'fast' hypercalls.
+	 */
+	union {
+		gpa_t data_offset;
+		int consumed_xmm_halves;
+	};
 };
 
 
 static int kvm_hv_get_hc_data(struct kvm *kvm, struct kvm_hv_hcall *hc,
-			      u16 orig_cnt, u16 cnt_cap, u64 *data,
-			      int consumed_xmm_halves, gpa_t offset)
+			      u16 orig_cnt, u16 cnt_cap, u64 *data)
 {
 	/*
 	 * Preserve the original count when ignoring entries via a "cap", KVM
···
 		 * Each XMM holds two sparse banks, but do not count halves that
 		 * have already been consumed for hypercall parameters.
 		 */
-		if (orig_cnt > 2 * HV_HYPERCALL_MAX_XMM_REGISTERS - consumed_xmm_halves)
+		if (orig_cnt > 2 * HV_HYPERCALL_MAX_XMM_REGISTERS - hc->consumed_xmm_halves)
 			return HV_STATUS_INVALID_HYPERCALL_INPUT;
 
 		for (i = 0; i < cnt; i++) {
-			j = i + consumed_xmm_halves;
+			j = i + hc->consumed_xmm_halves;
 			if (j % 2)
 				data[i] = sse128_hi(hc->xmm[j / 2]);
 			else
···
 		return 0;
 	}
 
-	return kvm_read_guest(kvm, hc->ingpa + offset, data,
+	return kvm_read_guest(kvm, hc->ingpa + hc->data_offset, data,
 			      cnt * sizeof(*data));
 }
 
 static u64 kvm_get_sparse_vp_set(struct kvm *kvm, struct kvm_hv_hcall *hc,
-				 u64 *sparse_banks, int consumed_xmm_halves,
-				 gpa_t offset)
+				 u64 *sparse_banks)
 {
 	if (hc->var_cnt > HV_MAX_SPARSE_VCPU_BANKS)
 		return -EINVAL;
 
 	/* Cap var_cnt to ignore banks that cannot contain a legal VP index. */
 	return kvm_hv_get_hc_data(kvm, hc, hc->var_cnt, KVM_HV_MAX_SPARSE_VCPU_SET_BITS,
-				  sparse_banks, consumed_xmm_halves, offset);
+				  sparse_banks);
 }
 
-static int kvm_hv_get_tlb_flush_entries(struct kvm *kvm, struct kvm_hv_hcall *hc, u64 entries[],
-					int consumed_xmm_halves, gpa_t offset)
+static int kvm_hv_get_tlb_flush_entries(struct kvm *kvm, struct kvm_hv_hcall *hc, u64 entries[])
 {
-	return kvm_hv_get_hc_data(kvm, hc, hc->rep_cnt, hc->rep_cnt,
-				  entries, consumed_xmm_halves, offset);
+	return kvm_hv_get_hc_data(kvm, hc, hc->rep_cnt, hc->rep_cnt, entries);
 }
 
 static void hv_tlb_flush_enqueue(struct kvm_vcpu *vcpu,
···
 	struct kvm_vcpu *v;
 	unsigned long i;
 	bool all_cpus;
-	int consumed_xmm_halves = 0;
-	gpa_t data_offset;
 
 	/*
 	 * The Hyper-V TLFS doesn't allow more than HV_MAX_SPARSE_VCPU_BANKS
···
 			flush.address_space = hc->ingpa;
 			flush.flags = hc->outgpa;
 			flush.processor_mask = sse128_lo(hc->xmm[0]);
-			consumed_xmm_halves = 1;
+			hc->consumed_xmm_halves = 1;
 		} else {
 			if (unlikely(kvm_read_guest(kvm, hc->ingpa,
 						    &flush, sizeof(flush))))
 				return HV_STATUS_INVALID_HYPERCALL_INPUT;
-			data_offset = sizeof(flush);
+			hc->data_offset = sizeof(flush);
 		}
 
 		trace_kvm_hv_flush_tlb(flush.processor_mask,
···
 			flush_ex.flags = hc->outgpa;
 			memcpy(&flush_ex.hv_vp_set,
 			       &hc->xmm[0], sizeof(hc->xmm[0]));
-			consumed_xmm_halves = 2;
+			hc->consumed_xmm_halves = 2;
 		} else {
 			if (unlikely(kvm_read_guest(kvm, hc->ingpa, &flush_ex,
 						    sizeof(flush_ex))))
 				return HV_STATUS_INVALID_HYPERCALL_INPUT;
-			data_offset = sizeof(flush_ex);
+			hc->data_offset = sizeof(flush_ex);
 		}
 
 		trace_kvm_hv_flush_tlb_ex(flush_ex.hv_vp_set.valid_bank_mask,
···
 			if (!hc->var_cnt)
 				goto ret_success;
 
-			if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks,
-						  consumed_xmm_halves, data_offset))
+			if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks))
 				return HV_STATUS_INVALID_HYPERCALL_INPUT;
 		}
 
···
 		 * consumed_xmm_halves to make sure TLB flush entries are read
 		 * from the correct offset.
 		 */
-		data_offset += hc->var_cnt * sizeof(sparse_banks[0]);
-		consumed_xmm_halves += hc->var_cnt;
+		if (hc->fast)
+			hc->consumed_xmm_halves += hc->var_cnt;
+		else
+			hc->data_offset += hc->var_cnt * sizeof(sparse_banks[0]);
 	}
 
 	if (hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE ||
···
 	    hc->rep_cnt > ARRAY_SIZE(__tlb_flush_entries)) {
 		tlb_flush_entries = NULL;
 	} else {
-		if (kvm_hv_get_tlb_flush_entries(kvm, hc, __tlb_flush_entries,
-						consumed_xmm_halves, data_offset))
+		if (kvm_hv_get_tlb_flush_entries(kvm, hc, __tlb_flush_entries))
 			return HV_STATUS_INVALID_HYPERCALL_INPUT;
 		tlb_flush_entries = __tlb_flush_entries;
 	}
···
 		if (!hc->var_cnt)
 			goto ret_success;
 
-		if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks, 1,
-					  offsetof(struct hv_send_ipi_ex,
-						   vp_set.bank_contents)))
+		if (!hc->fast)
+			hc->data_offset = offsetof(struct hv_send_ipi_ex,
+						   vp_set.bank_contents);
+		else
+			hc->consumed_xmm_halves = 1;
+
+		if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks))
 			return HV_STATUS_INVALID_HYPERCALL_INPUT;
 	}
 

arch/x86/kvm/irq_comm.c

···
 			kvm_set_msi_irq(vcpu->kvm, entry, &irq);
 
 			if (irq.trig_mode &&
-			    kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT,
-						irq.dest_id, irq.dest_mode))
+			    (kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT,
+						 irq.dest_id, irq.dest_mode) ||
+			     kvm_apic_pending_eoi(vcpu, irq.vector)))
 				__set_bit(irq.vector, ioapic_handled_vectors);
 		}
 	}

arch/x86/kvm/lapic.h

···
 
 extern struct static_key_false_deferred apic_hw_disabled;
 
-static inline int kvm_apic_hw_enabled(struct kvm_lapic *apic)
+static inline bool kvm_apic_hw_enabled(struct kvm_lapic *apic)
 {
 	if (static_branch_unlikely(&apic_hw_disabled.key))
 		return apic->vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE;
-	return MSR_IA32_APICBASE_ENABLE;
+	return true;
 }
 
 extern struct static_key_false_deferred apic_sw_disabled;

arch/x86/kvm/mmu/spte.h

···
  * A shadow-present leaf SPTE may be non-writable for 4 possible reasons:
  *
  *  1. To intercept writes for dirty logging. KVM write-protects huge pages
- *     so that they can be split be split down into the dirty logging
+ *     so that they can be split down into the dirty logging
  *     granularity (4KiB) whenever the guest writes to them. KVM also
  *     write-protects 4KiB pages so that writes can be recorded in the dirty log
  *     (e.g. if not using PML). SPTEs are write-protected for dirty logging

arch/x86/kvm/mmu/tdp_mmu.c

···
 	int ret = RET_PF_FIXED;
 	bool wrprot = false;
 
-	WARN_ON(sp->role.level != fault->goal_level);
+	if (WARN_ON_ONCE(sp->role.level != fault->goal_level))
+		return RET_PF_RETRY;
+
 	if (unlikely(!fault->slot))
 		new_spte = make_mmio_spte(vcpu, iter->gfn, ACC_ALL);
 	else
···
 		if (fault->nx_huge_page_workaround_enabled)
 			disallowed_hugepage_adjust(fault, iter.old_spte, iter.level);
 
-		if (iter.level == fault->goal_level)
-			break;
-
 		/*
 		 * If SPTE has been frozen by another thread, just give up and
 		 * retry, avoiding unnecessary page table allocation and free.
 		 */
 		if (is_removed_spte(iter.old_spte))
 			goto retry;
+
+		if (iter.level == fault->goal_level)
+			goto map_target_level;
 
 		/* Step down into the lower level page table if it exists. */
 		if (is_shadow_present_pte(iter.old_spte) &&
···
 			r = tdp_mmu_link_sp(kvm, &iter, sp, true);
 
 		/*
-		 * Also force the guest to retry the access if the upper level SPTEs
-		 * aren't in place.
+		 * Force the guest to retry if installing an upper level SPTE
+		 * failed, e.g. because a different task modified the SPTE.
 		 */
 		if (r) {
 			tdp_mmu_free_sp(sp);
···
 		if (fault->huge_page_disallowed &&
 		    fault->req_level >= iter.level) {
 			spin_lock(&kvm->arch.tdp_mmu_pages_lock);
-			track_possible_nx_huge_page(kvm, sp);
+			if (sp->nx_huge_page_disallowed)
+				track_possible_nx_huge_page(kvm, sp);
 			spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
 		}
 	}
 
+	/*
+	 * The walk aborted before reaching the target level, e.g. because the
+	 * iterator detected an upper level SPTE was frozen during traversal.
+	 */
+	WARN_ON_ONCE(iter.level == fault->goal_level);
+	goto retry;
+
+map_target_level:
 	ret = tdp_mmu_map_handle_target_level(vcpu, fault, &iter);
 
 retry:

arch/x86/kvm/pmu.c

···
 		return false;
 
 	/* recalibrate sample period and check if it's accepted by perf core */
-	if (perf_event_period(pmc->perf_event,
+	if (is_sampling_event(pmc->perf_event) &&
+	    perf_event_period(pmc->perf_event,
 			      get_sample_period(pmc, pmc->counter)))
 		return false;
 

arch/x86/kvm/pmu.h

···
 
 static inline void pmc_update_sample_period(struct kvm_pmc *pmc)
 {
-	if (!pmc->perf_event || pmc->is_paused)
+	if (!pmc->perf_event || pmc->is_paused ||
+	    !is_sampling_event(pmc->perf_event))
 		return;
 
 	perf_event_period(pmc->perf_event,

arch/x86/kvm/vmx/nested.c

···
 		if (vmptr == vmx->nested.current_vmptr)
 			nested_release_vmcs12(vcpu);
 
-		kvm_vcpu_write_guest(vcpu,
-				     vmptr + offsetof(struct vmcs12,
-						      launch_state),
-				     &zero, sizeof(zero));
+		/*
+		 * Silently ignore memory errors on VMCLEAR, Intel's pseudocode
+		 * for VMCLEAR includes a "ensure that data for VMCS referenced
+		 * by the operand is in memory" clause that guards writes to
+		 * memory, i.e. doing nothing for I/O is architecturally valid.
+		 *
+		 * FIXME: Suppress failures if and only if no memslot is found,
+		 * i.e. exit to userspace if __copy_to_user() fails.
+		 */
+		(void)kvm_vcpu_write_guest(vcpu,
+					   vmptr + offsetof(struct vmcs12,
+							    launch_state),
+					   &zero, sizeof(zero));
 	} else if (vmx->nested.hv_evmcs && vmptr == vmx->nested.hv_evmcs_vmptr) {
 		nested_release_evmcs(vcpu);
 	}
···
 		SECONDARY_EXEC_ENABLE_INVPCID |
 		SECONDARY_EXEC_RDSEED_EXITING |
 		SECONDARY_EXEC_XSAVES |
-		SECONDARY_EXEC_TSC_SCALING;
+		SECONDARY_EXEC_TSC_SCALING |
+		SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE;
 
 	/*
 	 * We can emulate "VMCS shadowing," even if the hardware

arch/x86/kvm/vmx/vmx.c

···
 	 * controls for features that are/aren't exposed to the guest.
 	 */
 	if (nested) {
+		/*
+		 * All features that can be added or removed to VMX MSRs must
+		 * be supported in the first place for nested virtualization.
+		 */
+		if (WARN_ON_ONCE(!(vmcs_config.nested.secondary_ctls_high & control)))
+			enabled = false;
+
 		if (enabled)
 			vmx->nested.msrs.secondary_ctls_high |= control;
 		else

arch/x86/kvm/x86.c

···
 			      struct x86_exception *e)
 {
 	if (r == X86EMUL_PROPAGATE_FAULT) {
+		if (KVM_BUG_ON(!e, vcpu->kvm))
+			return -EIO;
+
 		kvm_inject_emulated_page_fault(vcpu, e);
 		return 1;
 	}

arch/x86/kvm/xen.c

···
 	int ret = 0;
 	int idx = srcu_read_lock(&kvm->srcu);
 
-	if (gfn == GPA_INVALID) {
+	if (gfn == KVM_XEN_INVALID_GFN) {
 		kvm_gpc_deactivate(gpc);
 		goto out;
 	}
···
 		if (kvm->arch.xen.shinfo_cache.active)
 			data->u.shared_info.gfn = gpa_to_gfn(kvm->arch.xen.shinfo_cache.gpa);
 		else
-			data->u.shared_info.gfn = GPA_INVALID;
+			data->u.shared_info.gfn = KVM_XEN_INVALID_GFN;
 		r = 0;
 		break;
 
···
 		BUILD_BUG_ON(offsetof(struct vcpu_info, time) !=
 			     offsetof(struct compat_vcpu_info, time));
 
-		if (data->u.gpa == GPA_INVALID) {
+		if (data->u.gpa == KVM_XEN_INVALID_GPA) {
 			kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_info_cache);
 			r = 0;
 			break;
···
 		break;
 
 	case KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO:
-		if (data->u.gpa == GPA_INVALID) {
+		if (data->u.gpa == KVM_XEN_INVALID_GPA) {
 			kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_time_info_cache);
 			r = 0;
 			break;
···
 			r = -EOPNOTSUPP;
 			break;
 		}
-		if (data->u.gpa == GPA_INVALID) {
+		if (data->u.gpa == KVM_XEN_INVALID_GPA) {
 			r = 0;
 		deactivate_out:
 			kvm_gpc_deactivate(&vcpu->arch.xen.runstate_cache);
···
 		if (vcpu->arch.xen.vcpu_info_cache.active)
 			data->u.gpa = vcpu->arch.xen.vcpu_info_cache.gpa;
 		else
-			data->u.gpa = GPA_INVALID;
+			data->u.gpa = KVM_XEN_INVALID_GPA;
 		r = 0;
 		break;
 
···
 		if (vcpu->arch.xen.vcpu_time_info_cache.active)
 			data->u.gpa = vcpu->arch.xen.vcpu_time_info_cache.gpa;
 		else
-			data->u.gpa = GPA_INVALID;
+			data->u.gpa = KVM_XEN_INVALID_GPA;
 		r = 0;
 		break;
 
···
 		u8 blob_size = lm ? kvm->arch.xen_hvm_config.blob_size_64
 				  : kvm->arch.xen_hvm_config.blob_size_32;
 		u8 *page;
+		int ret;
 
 		if (page_num >= blob_size)
 			return 1;
···
 		if (IS_ERR(page))
 			return PTR_ERR(page);
 
-		if (kvm_vcpu_write_guest(vcpu, page_addr, page, PAGE_SIZE)) {
-			kfree(page);
+		ret = kvm_vcpu_write_guest(vcpu, page_addr, page, PAGE_SIZE);
+		kfree(page);
+		if (ret)
 			return 1;
-		}
 	}
 	return 0;
 }
···
 static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode,
 				 u64 param, u64 *r)
 {
-	int idx, i;
 	struct sched_poll sched_poll;
 	evtchn_port_t port, *ports;
-	gpa_t gpa;
+	struct x86_exception e;
+	int i;
 
 	if (!lapic_in_kernel(vcpu) ||
 	    !(vcpu->kvm->arch.xen_hvm_config.flags & KVM_XEN_HVM_CONFIG_EVTCHN_SEND))
 		return false;
-
-	idx = srcu_read_lock(&vcpu->kvm->srcu);
-	gpa = kvm_mmu_gva_to_gpa_system(vcpu, param, NULL);
-	srcu_read_unlock(&vcpu->kvm->srcu, idx);
-	if (!gpa) {
-		*r = -EFAULT;
-		return true;
-	}
 
 	if (IS_ENABLED(CONFIG_64BIT) && !longmode) {
 		struct compat_sched_poll sp32;
···
 		/* Sanity check that the compat struct definition is correct */
 		BUILD_BUG_ON(sizeof(sp32) != 16);
 
-		if (kvm_vcpu_read_guest(vcpu, gpa, &sp32, sizeof(sp32))) {
+		if (kvm_read_guest_virt(vcpu, param, &sp32, sizeof(sp32), &e)) {
 			*r = -EFAULT;
 			return true;
 		}
···
 		sched_poll.nr_ports = sp32.nr_ports;
 		sched_poll.timeout = sp32.timeout;
 	} else {
-		if (kvm_vcpu_read_guest(vcpu, gpa, &sched_poll,
-					sizeof(sched_poll))) {
+		if (kvm_read_guest_virt(vcpu, param, &sched_poll,
+					sizeof(sched_poll), &e)) {
 			*r = -EFAULT;
 			return true;
 		}
···
 	} else
 		ports = &port;
 
-	for (i = 0; i < sched_poll.nr_ports; i++) {
-		idx = srcu_read_lock(&vcpu->kvm->srcu);
-		gpa = kvm_mmu_gva_to_gpa_system(vcpu,
-						(gva_t)(sched_poll.ports + i),
-						NULL);
-		srcu_read_unlock(&vcpu->kvm->srcu, idx);
+	if (kvm_read_guest_virt(vcpu, (gva_t)sched_poll.ports, ports,
+				sched_poll.nr_ports * sizeof(*ports), &e)) {
+		*r = -EFAULT;
+		return true;
+	}
 
-		if (!gpa || kvm_vcpu_read_guest(vcpu, gpa,
-						&ports[i], sizeof(port))) {
-			*r = -EFAULT;
-			goto out;
-		}
+	for (i = 0; i < sched_poll.nr_ports; i++) {
 		if (ports[i] >= max_evtchn_port(vcpu->kvm)) {
 			*r = -EINVAL;
 			goto out;
···
 				  int vcpu_id, u64 param, u64 *r)
 {
 	struct vcpu_set_singleshot_timer oneshot;
+	struct x86_exception e;
 	s64 delta;
-	gpa_t gpa;
-	int idx;
 
 	if (!kvm_xen_timer_enabled(vcpu))
 		return false;
···
 			*r = -EINVAL;
 			return true;
 		}
-		idx = srcu_read_lock(&vcpu->kvm->srcu);
-		gpa = kvm_mmu_gva_to_gpa_system(vcpu, param, NULL);
-		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 
 		/*
 		 * The only difference for 32-bit compat is the 4 bytes of
···
 		BUILD_BUG_ON(sizeof_field(struct compat_vcpu_set_singleshot_timer, flags) !=
 			     sizeof_field(struct vcpu_set_singleshot_timer, flags));
 
-		if (!gpa ||
-		    kvm_vcpu_read_guest(vcpu, gpa, &oneshot, longmode ? sizeof(oneshot) :
-					sizeof(struct compat_vcpu_set_singleshot_timer))) {
+		if (kvm_read_guest_virt(vcpu, param, &oneshot, longmode ? sizeof(oneshot) :
+					sizeof(struct compat_vcpu_set_singleshot_timer), &e)) {
 			*r = -EFAULT;
 			return true;
 		}
···
 {
 	u32 port = data->u.evtchn.send_port;
 	struct evtchnfd *evtchnfd;
+	int ret;
 
-	if (!port || port >= max_evtchn_port(kvm))
-		return -EINVAL;
-
+	/* Protect writes to evtchnfd as well as the idr lookup.  */
 	mutex_lock(&kvm->lock);
 	evtchnfd = idr_find(&kvm->arch.xen.evtchn_ports, port);
-	mutex_unlock(&kvm->lock);
 
+	ret = -ENOENT;
 	if (!evtchnfd)
-		return -ENOENT;
+		goto out_unlock;
 
 	/* For an UPDATE, nothing may change except the priority/vcpu */
+	ret = -EINVAL;
 	if (evtchnfd->type != data->u.evtchn.type)
-		return -EINVAL;
+		goto out_unlock;
 
 	/*
 	 * Port cannot change, and if it's zero that was an eventfd
···
 	 */
 	if (!evtchnfd->deliver.port.port ||
 	    evtchnfd->deliver.port.port != data->u.evtchn.deliver.port.port)
-		return -EINVAL;
+		goto out_unlock;
 
 	/* We only support 2 level event channels for now */
 	if (data->u.evtchn.deliver.port.priority != KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL)
-		return -EINVAL;
+		goto out_unlock;
 
-	mutex_lock(&kvm->lock);
 	evtchnfd->deliver.port.priority = data->u.evtchn.deliver.port.priority;
 	if (evtchnfd->deliver.port.vcpu_id != data->u.evtchn.deliver.port.vcpu) {
 		evtchnfd->deliver.port.vcpu_id = data->u.evtchn.deliver.port.vcpu;
 		evtchnfd->deliver.port.vcpu_idx = -1;
 	}
+	ret = 0;
+out_unlock:
 	mutex_unlock(&kvm->lock);
-	return 0;
+	return ret;
 }
 
 /*
···
 {
 	u32 port = data->u.evtchn.send_port;
 	struct eventfd_ctx *eventfd = NULL;
-	struct evtchnfd *evtchnfd = NULL;
+	struct evtchnfd *evtchnfd;
 	int ret = -EINVAL;
-
-	if (!port || port >= max_evtchn_port(kvm))
-		return -EINVAL;
 
 	evtchnfd = kzalloc(sizeof(struct evtchnfd), GFP_KERNEL);
 	if (!evtchnfd)
···
 	if (!evtchnfd)
 		return -ENOENT;
 
-	if (kvm)
-		synchronize_srcu(&kvm->srcu);
+	synchronize_srcu(&kvm->srcu);
 	if (!evtchnfd->deliver.port.port)
 		eventfd_ctx_put(evtchnfd->deliver.eventfd.ctx);
 	kfree(evtchnfd);
···
 
 static int kvm_xen_eventfd_reset(struct kvm *kvm)
 {
-	struct evtchnfd *evtchnfd;
+	struct evtchnfd *evtchnfd, **all_evtchnfds;
 	int i;
+	int n = 0;
 
 	mutex_lock(&kvm->lock);
+
+	/*
+	 * Because synchronize_srcu() cannot be called inside the
+	 * critical section, first collect all the evtchnfd objects
+	 * in an array as they are removed from evtchn_ports.
+	 */
+	idr_for_each_entry(&kvm->arch.xen.evtchn_ports, evtchnfd, i)
+		n++;
+
+	all_evtchnfds = kmalloc_array(n, sizeof(struct evtchnfd *), GFP_KERNEL);
+	if (!all_evtchnfds) {
+		mutex_unlock(&kvm->lock);
+		return -ENOMEM;
+	}
+
+	n = 0;
 	idr_for_each_entry(&kvm->arch.xen.evtchn_ports, evtchnfd, i) {
+		all_evtchnfds[n++] = evtchnfd;
 		idr_remove(&kvm->arch.xen.evtchn_ports, evtchnfd->send_port);
-		synchronize_srcu(&kvm->srcu);
+	}
+	mutex_unlock(&kvm->lock);
+
+	synchronize_srcu(&kvm->srcu);
+
+	while (n--) {
+		evtchnfd = all_evtchnfds[n];
 		if (!evtchnfd->deliver.port.port)
 			eventfd_ctx_put(evtchnfd->deliver.eventfd.ctx);
 		kfree(evtchnfd);
 	}
-	mutex_unlock(&kvm->lock);
+	kfree(all_evtchnfds);
 
 	return 0;
 }
···
 {
 	struct evtchnfd *evtchnfd;
 	struct evtchn_send send;
-	gpa_t gpa;
-	int idx;
+	struct x86_exception e;
 
-	idx = srcu_read_lock(&vcpu->kvm->srcu);
-	gpa = kvm_mmu_gva_to_gpa_system(vcpu, param, NULL);
-	srcu_read_unlock(&vcpu->kvm->srcu, idx);
-
-	if (!gpa || kvm_vcpu_read_guest(vcpu, gpa, &send, sizeof(send))) {
+	/* Sanity check: this structure is the same for 32-bit and 64-bit */
+	BUILD_BUG_ON(sizeof(send) != 4);
+	if (kvm_read_guest_virt(vcpu, param, &send, sizeof(send), &e)) {
 		*r = -EFAULT;
 		return true;
 	}
 
-	/* The evtchn_ports idr is protected by vcpu->kvm->srcu */
+	/*
+	 * evtchnfd is protected by kvm->srcu; the idr lookup instead
+	 * is protected by RCU.
+	 */
+	rcu_read_lock();
 	evtchnfd = idr_find(&vcpu->kvm->arch.xen.evtchn_ports, send.port);
+	rcu_read_unlock();
 	if (!evtchnfd)
 		return false;
 

arch/x86/lib/insn-eval.c

···
  * Returns:
  *
  * Type of the instruction. Size of the memory operand is stored in
- * @bytes. If decode failed, MMIO_DECODE_FAILED returned.
+ * @bytes. If decode failed, INSN_MMIO_DECODE_FAILED returned.
  */
-enum mmio_type insn_decode_mmio(struct insn *insn, int *bytes)
+enum insn_mmio_type insn_decode_mmio(struct insn *insn, int *bytes)
 {
-	enum mmio_type type = MMIO_DECODE_FAILED;
+	enum insn_mmio_type type = INSN_MMIO_DECODE_FAILED;
 
 	*bytes = 0;
 
 	if (insn_get_opcode(insn))
-		return MMIO_DECODE_FAILED;
+		return INSN_MMIO_DECODE_FAILED;
 
 	switch (insn->opcode.bytes[0]) {
 	case 0x88: /* MOV m8,r8 */
···
 	case 0x89: /* MOV m16/m32/m64, r16/m32/m64 */
 		if (!*bytes)
 			*bytes = insn->opnd_bytes;
-		type = MMIO_WRITE;
+		type = INSN_MMIO_WRITE;
 		break;
 
 	case 0xc6: /* MOV m8, imm8 */
···
 	case 0xc7: /* MOV m16/m32/m64, imm16/imm32/imm64 */
 		if (!*bytes)
 			*bytes = insn->opnd_bytes;
-		type = MMIO_WRITE_IMM;
+		type = INSN_MMIO_WRITE_IMM;
 		break;
 
 	case 0x8a: /* MOV r8, m8 */
···
 	case 0x8b: /* MOV r16/r32/r64, m16/m32/m64 */
 		if (!*bytes)
 			*bytes = insn->opnd_bytes;
-		type = MMIO_READ;
+		type = INSN_MMIO_READ;
 		break;
 
 	case 0xa4: /* MOVS m8, m8 */
···
 	case 0xa5: /* MOVS m16/m32/m64, m16/m32/m64 */
 		if (!*bytes)
 			*bytes = insn->opnd_bytes;
-		type = MMIO_MOVS;
+		type = INSN_MMIO_MOVS;
 		break;
 
 	case 0x0f: /* Two-byte instruction */
···
 		case 0xb7: /* MOVZX r32/r64, m16 */
 			if (!*bytes)
 				*bytes = 2;
-			type = MMIO_READ_ZERO_EXTEND;
+			type = INSN_MMIO_READ_ZERO_EXTEND;
 			break;
 
 		case 0xbe: /* MOVSX r16/r32/r64, m8 */
···
 		case 0xbf: /* MOVSX r32/r64, m16 */
 			if (!*bytes)
 				*bytes = 2;
-			type = MMIO_READ_SIGN_EXTEND;
+			type = INSN_MMIO_READ_SIGN_EXTEND;
 			break;
 		}
 		break;

arch/x86/lib/iomap_copy_64.S

···
  */
 SYM_FUNC_START(__iowrite32_copy)
 	movl %edx,%ecx
-	rep movsd
+	rep movsl
 	RET
 SYM_FUNC_END(__iowrite32_copy)

block/Kconfig

···
        bool "Enable the block layer" if EXPERT
        default y
        select SBITMAP
-       select SRCU
        help
 	 Provide block layer support for the kernel.
 

block/bfq-iosched.c

···
 		unsigned long flags;
 
 		spin_lock_irqsave(&bfqd->lock, flags);
-		bfq_exit_bfqq(bfqd, bfqq);
 		bic_set_bfqq(bic, NULL, is_sync);
+		bfq_exit_bfqq(bfqd, bfqq);
 		spin_unlock_irqrestore(&bfqd->lock, flags);
 	}
 }

block/bio.c

···
 }
 EXPORT_SYMBOL(__bio_advance);
 
+void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter,
+			struct bio *src, struct bvec_iter *src_iter)
+{
+	while (src_iter->bi_size && dst_iter->bi_size) {
+		struct bio_vec src_bv = bio_iter_iovec(src, *src_iter);
+		struct bio_vec dst_bv = bio_iter_iovec(dst, *dst_iter);
+		unsigned int bytes = min(src_bv.bv_len, dst_bv.bv_len);
+		void *src_buf = bvec_kmap_local(&src_bv);
+		void *dst_buf = bvec_kmap_local(&dst_bv);
+
+		memcpy(dst_buf, src_buf, bytes);
+
+		kunmap_local(dst_buf);
+		kunmap_local(src_buf);
+
+		bio_advance_iter_single(src, src_iter, bytes);
+		bio_advance_iter_single(dst, dst_iter, bytes);
+	}
+}
+EXPORT_SYMBOL(bio_copy_data_iter);
+
 /**
  * bio_copy_data - copy contents of data buffers from one bio to another
  * @src: source bio
···
 	struct bvec_iter src_iter = src->bi_iter;
 	struct bvec_iter dst_iter = dst->bi_iter;
 
-	while (src_iter.bi_size && dst_iter.bi_size) {
-		struct bio_vec src_bv = bio_iter_iovec(src, src_iter);
-		struct bio_vec dst_bv = bio_iter_iovec(dst, dst_iter);
-		unsigned int bytes = min(src_bv.bv_len, dst_bv.bv_len);
-		void *src_buf = bvec_kmap_local(&src_bv);
-		void *dst_buf = bvec_kmap_local(&dst_bv);
-
-		memcpy(dst_buf, src_buf, bytes);
-
-		kunmap_local(dst_buf);
-		kunmap_local(src_buf);
-
-		bio_advance_iter_single(src, &src_iter, bytes);
-		bio_advance_iter_single(dst, &dst_iter, bytes);
-	}
+	bio_copy_data_iter(dst, &dst_iter, src, &src_iter);
 }
 EXPORT_SYMBOL(bio_copy_data);
 

block/blk-merge.c

···
 	*segs = nsegs;
 	return NULL;
 split:
+	/*
+	 * We can't sanely support splitting for a REQ_NOWAIT bio. End it
+	 * with EAGAIN if splitting is required and return an error pointer.
+	 */
+	if (bio->bi_opf & REQ_NOWAIT) {
+		bio->bi_status = BLK_STS_AGAIN;
+		bio_endio(bio);
+		return ERR_PTR(-EAGAIN);
+	}
+
 	*segs = nsegs;
 
 	/*
···
 	default:
 		split = bio_split_rw(bio, lim, nr_segs, bs,
 				get_max_io_size(bio, lim) << SECTOR_SHIFT);
+		if (IS_ERR(split))
+			return NULL;
 		break;
 	}
 
 	if (split) {
-		/* there isn't chance to merge the splitted bio */
+		/* there isn't chance to merge the split bio */
 		split->bi_opf |= REQ_NOMERGE;
 
 		blkcg_bio_issue_init(split);

block/blk-mq.c

···
 	blk_status_t ret;
 
 	bio = blk_queue_bounce(bio, q);
-	if (bio_may_exceed_limits(bio, &q->limits))
+	if (bio_may_exceed_limits(bio, &q->limits)) {
 		bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
+		if (!bio)
+			return;
+	}
 
 	if (!bio_integrity_prep(bio))
 		return;

block/genhd.c

···
 	.dev_uevent	= block_uevent,
 };
 
+static char *block_devnode(struct device *dev, umode_t *mode,
+			   kuid_t *uid, kgid_t *gid)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	if (disk->fops->devnode)
+		return disk->fops->devnode(disk, mode);
+	return NULL;
+}
+
 const struct device_type disk_type = {
 	.name		= "disk",
 	.groups		= disk_attr_groups,
 	.release	= disk_release,
+	.devnode	= block_devnode,
 };
 
 #ifdef CONFIG_PROC_FS

drivers/acpi/acpi_video.c

···
 static int only_lcd = -1;
 module_param(only_lcd, int, 0444);
 
-/*
- * Display probing is known to take up to 5 seconds, so delay the fallback
- * backlight registration by 5 seconds + 3 seconds for some extra margin.
- */
-static int register_backlight_delay = 8;
+static int register_backlight_delay;
 module_param(register_backlight_delay, int, 0444);
 MODULE_PARM_DESC(register_backlight_delay,
 	"Delay in seconds before doing fallback (non GPU driver triggered) "
···
 
 	return false;
 }
+
+/*
+ * At least one graphics driver has reported that no LCD is connected
+ * via the native interface. cancel the registration for fallback acpi_video0.
+ * If another driver still deems this necessary, it can explicitly register it.
+ */
+void acpi_video_report_nolcd(void)
+{
+	cancel_delayed_work(&video_bus_register_backlight_work);
+}
+EXPORT_SYMBOL(acpi_video_report_nolcd);
 
 int acpi_video_register(void)
 {

drivers/acpi/resource.c

···
 			DMI_MATCH(DMI_BOARD_NAME, "S5602ZA"),
 		},
 	},
+	{
+		.ident = "Asus ExpertBook B2502",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_BOARD_NAME, "B2502CBA"),
+		},
+	},
 	{ }
 };
 
-static const struct dmi_system_id lenovo_82ra[] = {
+static const struct dmi_system_id lenovo_laptop[] = {
+	{
+		.ident = "LENOVO IdeaPad Flex 5 14ALC7",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "82R9"),
+		},
+	},
 	{
 		.ident = "LENOVO IdeaPad Flex 5 16ALC7",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "82RA"),
+		},
+	},
+	{ }
+};
+
+static const struct dmi_system_id schenker_gm_rg[] = {
+	{
+		.ident = "XMG CORE 15 (M22)",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "SchenkerTechnologiesGmbH"),
+			DMI_MATCH(DMI_BOARD_NAME, "GMxRGxx"),
 		},
 	},
 	{ }
···
 static const struct irq_override_cmp override_table[] = {
 	{ medion_laptop, 1, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, false },
 	{ asus_laptop, 1, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, false },
-	{ lenovo_82ra, 6, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, true },
-	{ lenovo_82ra, 10, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, true },
+	{ lenovo_laptop, 6, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, true },
+	{ lenovo_laptop, 10, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_LOW, 0, true },
+	{ schenker_gm_rg, 1, ACPI_EDGE_SENSITIVE, ACPI_ACTIVE_LOW, 1, true },
 };
 
 static bool acpi_dev_irq_override(u32 gsi, u8 triggering, u8 polarity,

drivers/acpi/video_detect.c

···
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/platform_data/x86/nvidia-wmi-ec-backlight.h>
+#include <linux/pnp.h>
 #include <linux/types.h>
 #include <linux/workqueue.h>
 #include <acpi/video.h>
···
 	return false;
 }
 #endif
+
+static bool apple_gmux_backlight_present(void)
+{
+	struct acpi_device *adev;
+	struct device *dev;
+
+	adev = acpi_dev_get_first_match_dev(GMUX_ACPI_HID, NULL, -1);
+	if (!adev)
+		return false;
+
+	dev = acpi_get_first_physical_node(adev);
+	if (!dev)
+		return false;
+
+	/*
+	 * drivers/platform/x86/apple-gmux.c only supports old style
+	 * Apple GMUX with an IO-resource.
+	 */
+	return pnp_get_resource(to_pnp_dev(dev), IORESOURCE_IO, 0) != NULL;
+}
 
 /* Force to use vendor driver when the ACPI device is known to be
  * buggy */
···
 	if (nvidia_wmi_ec_present)
 		return acpi_backlight_nvidia_wmi_ec;
 
-	if (apple_gmux_present())
+	if (apple_gmux_backlight_present())
 		return acpi_backlight_apple_gmux;
 
 	/* Use ACPI video if available, except when native should be preferred. */

drivers/acpi/x86/s2idle.c

···
 module_param(sleep_no_lps0, bool, 0644);
 MODULE_PARM_DESC(sleep_no_lps0, "Do not use the special LPS0 device interface");
 
-static bool prefer_microsoft_dsm_guid __read_mostly;
-module_param(prefer_microsoft_dsm_guid, bool, 0644);
-MODULE_PARM_DESC(prefer_microsoft_dsm_guid, "Prefer using Microsoft GUID in LPS0 device _DSM evaluation");
-
 static const struct acpi_device_id lps0_device_ids[] = {
 	{"PNP0D80", },
 	{"", },
···
 }
 
 struct amd_lps0_hid_device_data {
-	const unsigned int rev_id;
 	const bool check_off_by_one;
-	const bool prefer_amd_guid;
 };
 
 static const struct amd_lps0_hid_device_data amd_picasso = {
-	.rev_id = 0,
 	.check_off_by_one = true,
-	.prefer_amd_guid = false,
 };
 
 static const struct amd_lps0_hid_device_data amd_cezanne = {
-	.rev_id = 0,
 	.check_off_by_one = false,
-	.prefer_amd_guid = false,
-};
-
-static const struct amd_lps0_hid_device_data amd_rembrandt = {
-	.rev_id = 2,
-	.check_off_by_one = false,
-	.prefer_amd_guid = true,
 };
 
 static const struct acpi_device_id amd_hid_ids[] = {
···
 	{"AMD0005",	(kernel_ulong_t)&amd_picasso,	},
 	{"AMDI0005",	(kernel_ulong_t)&amd_picasso,	},
 	{"AMDI0006",	(kernel_ulong_t)&amd_cezanne,	},
-	{"AMDI0007",	(kernel_ulong_t)&amd_rembrandt,	},
 	{}
 };
 
-static int lps0_prefer_microsoft(const struct dmi_system_id *id)
+static int lps0_prefer_amd(const struct dmi_system_id *id)
 {
-	pr_debug("Preferring Microsoft GUID.\n");
-	prefer_microsoft_dsm_guid = true;
+	pr_debug("Using AMD GUID w/ _REV 2.\n");
+	rev_id = 2;
 	return 0;
 }
-
 static const struct dmi_system_id s2idle_dmi_table[] __initconst = {
 	{
 		/*
-		 * ASUS TUF Gaming A17 FA707RE
-		 * https://bugzilla.kernel.org/show_bug.cgi?id=216101
+		 * AMD Rembrandt based HP EliteBook 835/845/865 G9
+		 * Contains specialized AML in AMD/_REV 2 path to avoid
+		 * triggering a bug in Qualcomm WLAN firmware. This may be
+		 * removed in the future if that firmware is fixed.
 		 */
-		.callback = lps0_prefer_microsoft,
+		.callback = lps0_prefer_amd,
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "ASUS TUF Gaming A17"),
-		},
-	},
-	{
-		/* ASUS ROG Zephyrus G14 (2022) */
-		.callback = lps0_prefer_microsoft,
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "ROG Zephyrus G14 GA402"),
-		},
-	},
-	{
-		/*
-		 * Lenovo Yoga Slim 7 Pro X 14ARH7
-		 * https://bugzilla.kernel.org/show_bug.cgi?id=216473 : 82V2
-		 * https://bugzilla.kernel.org/show_bug.cgi?id=216438 : 82TL
-		 */
-		.callback = lps0_prefer_microsoft,
-		.matches = {
-			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "82"),
-		},
-	},
-	{
-		/*
-		 * ASUSTeK COMPUTER INC. ROG Flow X13 GV301RE_GV301RE
-		 * https://gitlab.freedesktop.org/drm/amd/-/issues/2148
-		 */
-		.callback = lps0_prefer_microsoft,
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "ROG Flow X13 GV301"),
-		},
-	},
-	{
-		/*
-		 * ASUSTeK COMPUTER INC. ROG Flow X16 GV601RW_GV601RW
-		 * https://gitlab.freedesktop.org/drm/amd/-/issues/2148
-		 */
-		.callback = lps0_prefer_microsoft,
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "ROG Flow X16 GV601"),
+			DMI_MATCH(DMI_BOARD_VENDOR, "HP"),
+			DMI_MATCH(DMI_BOARD_NAME, "8990"),
 		},
 	},
 	{}
···
 		if (dev_id->id[0])
 			data = (const struct amd_lps0_hid_device_data *) dev_id->driver_data;
 		else
-			data = &amd_rembrandt;
-		rev_id = data->rev_id;
+			data = &amd_cezanne;
 		lps0_dsm_func_mask = validate_dsm(adev->handle,
 					ACPI_LPS0_DSM_UUID_AMD, rev_id, &lps0_dsm_guid);
 		if (lps0_dsm_func_mask > 0x3 && data->check_off_by_one) {
 			lps0_dsm_func_mask = (lps0_dsm_func_mask << 1) | 0x1;
 			acpi_handle_debug(adev->handle, "_DSM UUID %s: Adjusted function mask: 0x%x\n",
 					  ACPI_LPS0_DSM_UUID_AMD, lps0_dsm_func_mask);
-		} else if (lps0_dsm_func_mask_microsoft > 0 && data->prefer_amd_guid &&
-				!prefer_microsoft_dsm_guid) {
+		} else if (lps0_dsm_func_mask_microsoft > 0 && rev_id) {
 			lps0_dsm_func_mask_microsoft = -EINVAL;
 			acpi_handle_debug(adev->handle, "_DSM Using AMD method\n");
 		}
···
 		rev_id = 1;
 		lps0_dsm_func_mask = validate_dsm(adev->handle,
 					ACPI_LPS0_DSM_UUID, rev_id, &lps0_dsm_guid);
-		if (!prefer_microsoft_dsm_guid)
-			lps0_dsm_func_mask_microsoft = -EINVAL;
+		lps0_dsm_func_mask_microsoft = -EINVAL;
 	}
 
 	if (lps0_dsm_func_mask < 0 && lps0_dsm_func_mask_microsoft < 0)

drivers/ata/ahci.c

···
 static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent);
 static void ahci_remove_one(struct pci_dev *dev);
 static void ahci_shutdown_one(struct pci_dev *dev);
+static void ahci_intel_pcs_quirk(struct pci_dev *pdev, struct ahci_host_priv *hpriv);
 static int ahci_vt8251_hardreset(struct ata_link *link, unsigned int *class,
 				 unsigned long deadline);
 static int ahci_avn_hardreset(struct ata_link *link, unsigned int *class,
···
 	ahci_save_initial_config(&pdev->dev, hpriv);
 }
 
+static int ahci_pci_reset_controller(struct ata_host *host)
+{
+	struct pci_dev *pdev = to_pci_dev(host->dev);
+	struct ahci_host_priv *hpriv = host->private_data;
+	int rc;
+
+	rc = ahci_reset_controller(host);
+	if (rc)
+		return rc;
+
+	/*
+	 * If platform firmware failed to enable ports, try to enable
+	 * them here.
+	 */
+	ahci_intel_pcs_quirk(pdev, hpriv);
+
+	return 0;
+}
+
 static void ahci_pci_init_controller(struct ata_host *host)
 {
 	struct ahci_host_priv *hpriv = host->private_data;
···
 	struct ata_host *host = pci_get_drvdata(pdev);
 	int rc;
 
-	rc = ahci_reset_controller(host);
+	rc = ahci_pci_reset_controller(host);
 	if (rc)
 		return rc;
 	ahci_pci_init_controller(host);
···
 		ahci_mcp89_apple_enable(pdev);
 
 	if (pdev->dev.power.power_state.event == PM_EVENT_SUSPEND) {
-		rc = ahci_reset_controller(host);
+		rc = ahci_pci_reset_controller(host);
 		if (rc)
 			return rc;
 
···
 	/* save initial config */
 	ahci_pci_save_initial_config(pdev, hpriv);
 
-	/*
-	 * If platform firmware failed to enable ports, try to enable
-	 * them here.
-	 */
-	ahci_intel_pcs_quirk(pdev, hpriv);
-
 	/* prepare host */
 	if (hpriv->cap & HOST_CAP_NCQ) {
 		pi.flags |= ATA_FLAG_NCQ;
···
 	if (rc)
 		return rc;
 
-	rc = ahci_reset_controller(host);
+	rc = ahci_pci_reset_controller(host);
 	if (rc)
 		return rc;
 

drivers/block/Kconfig

···
 	  The default value is 4096 kilobytes. Only change this if you know
 	  what you are doing.
 
+config CDROM_PKTCDVD
+	tristate "Packet writing on CD/DVD media (DEPRECATED)"
+	depends on !UML
+	depends on SCSI
+	select CDROM
+	help
+	  Note: This driver is deprecated and will be removed from the
+	  kernel in the near future!
+
+	  If you have a CDROM/DVD drive that supports packet writing, say
+	  Y to include support. It should work with any MMC/Mt Fuji
+	  compliant ATAPI or SCSI drive, which is just about any newer
+	  DVD/CD writer.
+
+	  Currently only writing to CD-RW, DVD-RW, DVD+RW and DVDRAM discs
+	  is possible.
+	  DVD-RW disks must be in restricted overwrite mode.
+
+	  See the file <file:Documentation/cdrom/packet-writing.rst>
+	  for further information on the use of this driver.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called pktcdvd.
+
+config CDROM_PKTCDVD_BUFFERS
+	int "Free buffers for data gathering"
+	depends on CDROM_PKTCDVD
+	default "8"
+	help
+	  This controls the maximum number of active concurrent packets. More
+	  concurrent packets can increase write performance, but also require
+	  more memory. Each concurrent packet will require approximately 64Kb
+	  of non-swappable kernel memory, memory which will be allocated when
+	  a disc is opened for writing.
+
+config CDROM_PKTCDVD_WCACHE
+	bool "Enable write caching"
+	depends on CDROM_PKTCDVD
+	help
+	  If enabled, write caching will be set for the CD-R/W device. For now
+	  this option is dangerous unless the CD-RW media is known good, as we
+	  don't do deferred write error handling yet.
+
 config ATA_OVER_ETH
 	tristate "ATA over Ethernet support"
 	depends on NET

drivers/block/Makefile

···
 obj-$(CONFIG_N64CART)		+= n64cart.o
 obj-$(CONFIG_BLK_DEV_RAM)	+= brd.o
 obj-$(CONFIG_BLK_DEV_LOOP)	+= loop.o
+obj-$(CONFIG_CDROM_PKTCDVD)	+= pktcdvd.o
 obj-$(CONFIG_SUNVDC)		+= sunvdc.o
 
 obj-$(CONFIG_BLK_DEV_NBD)	+= nbd.o

drivers/block/drbd/drbd_req.c

···
 	struct drbd_device *device = bio->bi_bdev->bd_disk->private_data;
 
 	bio = bio_split_to_limits(bio);
+	if (!bio)
+		return;
 
 	/*
 	 * what we "blindly" assume:

drivers/block/pktcdvd.c

···
+/*
+ * Copyright (C) 2000 Jens Axboe <[e-mail]>
+ * Copyright (C) 2001-2004 Peter Osterlund <[e-mail]>
+ * Copyright (C) 2006 Thomas Maier <[e-mail]>
+ *
+ * May be copied or modified under the terms of the GNU General Public
+ * License.  See linux/COPYING for more information.
+ *
+ * Packet writing layer for ATAPI and SCSI CD-RW, DVD+RW, DVD-RW and
+ * DVD-RAM devices.
+ *
+ * Theory of operation:
+ *
+ * At the lowest level, there is the standard driver for the CD/DVD device,
+ * such as drivers/scsi/sr.c. This driver can handle read and write requests,
+ * but it doesn't know anything about the special restrictions that apply to
+ * packet writing. One restriction is that write requests must be aligned to
+ * packet boundaries on the physical media, and the size of a write request
+ * must be equal to the packet size. Another restriction is that a
+ * GPCMD_FLUSH_CACHE command has to be issued to the drive before a read
+ * command, if the previous command was a write.
+ *
+ * The purpose of the packet writing driver is to hide these restrictions from
+ * higher layers, such as file systems, and present a block device that can be
+ * randomly read and written using 2kB-sized blocks.
+ *
+ * The lowest layer in the packet writing driver is the packet I/O scheduler.
+ * Its data is defined by the struct packet_iosched and includes two bio
+ * queues with pending read and write requests. These queues are processed
+ * by the pkt_iosched_process_queue() function. The write requests in this
+ * queue are already properly aligned and sized. This layer is responsible for
+ * issuing the flush cache commands and scheduling the I/O in a good order.
+ *
+ * The next layer transforms unaligned write requests to aligned writes. This
+ * transformation requires reading missing pieces of data from the underlying
+ * block device, assembling the pieces to full packets and queuing them to the
+ * packet I/O scheduler.
+ *
+ * At the top layer there is a custom ->submit_bio function that forwards
+ * read requests directly to the iosched queue and puts write requests in the
+ * unaligned write queue. A kernel thread performs the necessary read
+ * gathering to convert the unaligned writes to aligned writes and then feeds
+ * them to the packet I/O scheduler.
+ *
+ *************************************************************************/
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/pktcdvd.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/compat.h>
+#include <linux/kthread.h>
+#include <linux/errno.h>
+#include <linux/spinlock.h>
+#include <linux/file.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/miscdevice.h>
+#include <linux/freezer.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/backing-dev.h>
+#include <scsi/scsi_cmnd.h>
+#include <scsi/scsi_ioctl.h>
+#include <scsi/scsi.h>
+#include <linux/debugfs.h>
+#include <linux/device.h>
+#include <linux/nospec.h>
+#include <linux/uaccess.h>
+
+#define DRIVER_NAME	"pktcdvd"
+
+#define pkt_err(pd, fmt, ...)						\
+	pr_err("%s: " fmt, pd->name, ##__VA_ARGS__)
+#define pkt_notice(pd, fmt, ...)					\
+	pr_notice("%s: " fmt, pd->name, ##__VA_ARGS__)
+#define pkt_info(pd, fmt, ...)						\
+	pr_info("%s: " fmt, pd->name, ##__VA_ARGS__)
+
+#define pkt_dbg(level, pd, fmt, ...)					\
+do {									\
+	if (level == 2 && PACKET_DEBUG >= 2)				\
+		pr_notice("%s: %s():" fmt,				\
+			  pd->name, __func__, ##__VA_ARGS__);		\
+	else if (level == 1 && PACKET_DEBUG >= 1)			\
+		pr_notice("%s: " fmt, pd->name, ##__VA_ARGS__);		\
+} while (0)
+
+#define MAX_SPEED 0xffff
+
+static DEFINE_MUTEX(pktcdvd_mutex);
+static struct pktcdvd_device *pkt_devs[MAX_WRITERS];
+static struct proc_dir_entry *pkt_proc;
+static int pktdev_major;
+static int write_congestion_on  = PKT_WRITE_CONGESTION_ON;
+static int write_congestion_off = PKT_WRITE_CONGESTION_OFF;
+static struct mutex ctl_mutex;	/* Serialize open/close/setup/teardown */
+static mempool_t psd_pool;
+static struct bio_set pkt_bio_set;
+
+static struct class	*class_pktcdvd = NULL;    /* /sys/class/pktcdvd */
+static struct dentry	*pkt_debugfs_root = NULL; /* /sys/kernel/debug/pktcdvd */
+
+/* forward declaration */
+static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev);
+static int pkt_remove_dev(dev_t pkt_dev);
+static int pkt_seq_show(struct seq_file *m, void *p);
+
+static sector_t get_zone(sector_t sector, struct pktcdvd_device *pd)
+{
+	return (sector + pd->offset) & ~(sector_t)(pd->settings.size - 1);
+}
+
+/**********************************************************
+ * sysfs interface for pktcdvd
+ * by (C) 2006  Thomas Maier <[e-mail]>
+ 
+  /sys/class/pktcdvd/pktcdvd[0-7]/
+                     stat/reset
+                     stat/packets_started
+                     stat/packets_finished
+                     stat/kb_written
+                     stat/kb_read
+                     stat/kb_read_gather
+                     write_queue/size
+                     write_queue/congestion_off
+                     write_queue/congestion_on
+ **********************************************************/
+
+static ssize_t packets_started_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	struct pktcdvd_device *pd = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%lu\n", pd->stats.pkt_started);
+}
+static DEVICE_ATTR_RO(packets_started);
+
+static ssize_t packets_finished_show(struct device *dev,
+				     struct device_attribute *attr, char *buf)
+{
+	struct pktcdvd_device *pd = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%lu\n", pd->stats.pkt_ended);
+}
+static DEVICE_ATTR_RO(packets_finished);
+
+static ssize_t kb_written_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	struct pktcdvd_device *pd = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%lu\n", pd->stats.secs_w >> 1);
+}
+static DEVICE_ATTR_RO(kb_written);
+
+static ssize_t kb_read_show(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	struct pktcdvd_device *pd = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%lu\n", pd->stats.secs_r >> 1);
+}
+static DEVICE_ATTR_RO(kb_read);
+
+static ssize_t kb_read_gather_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct pktcdvd_device *pd = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%lu\n", pd->stats.secs_rg >> 1);
+}
+static DEVICE_ATTR_RO(kb_read_gather);
+
+static ssize_t reset_store(struct device *dev, struct device_attribute *attr,
+			   const char *buf, size_t len)
+{
+	struct pktcdvd_device *pd = dev_get_drvdata(dev);
+
+	if (len > 0) {
+		pd->stats.pkt_started = 0;
+		pd->stats.pkt_ended = 0;
+		pd->stats.secs_w = 0;
+		pd->stats.secs_rg = 0;
+		pd->stats.secs_r = 0;
+	}
+	return len;
+}
+static DEVICE_ATTR_WO(reset);
+
+static struct attribute *pkt_stat_attrs[] = {
+	&dev_attr_packets_finished.attr,
+	&dev_attr_packets_started.attr,
+	&dev_attr_kb_read.attr,
+	&dev_attr_kb_written.attr,
+	&dev_attr_kb_read_gather.attr,
+	&dev_attr_reset.attr,
+	NULL,
+};
+
+static const struct attribute_group pkt_stat_group = {
+	.name = "stat",
+	.attrs = pkt_stat_attrs,
+};
+
+static ssize_t size_show(struct device *dev,
+			 struct device_attribute *attr, char *buf)
+{
+	struct pktcdvd_device *pd = dev_get_drvdata(dev);
+	int n;
+
+	spin_lock(&pd->lock);
+	n = sysfs_emit(buf, "%d\n", pd->bio_queue_size);
+	spin_unlock(&pd->lock);
+	return n;
+}
+static DEVICE_ATTR_RO(size);
+
+static void init_write_congestion_marks(int* lo, int* hi)
+{
+	if (*hi > 0) {
+		*hi = max(*hi, 500);
+		*hi = min(*hi, 1000000);
+		if (*lo <= 0)
+			*lo = *hi - 100;
+		else {
+			*lo = min(*lo, *hi - 100);
+			*lo = max(*lo, 100);
+		}
+	} else {
+		*hi = -1;
+		*lo = -1;
+	}
+}
+
+static ssize_t congestion_off_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct pktcdvd_device *pd = dev_get_drvdata(dev);
+	int n;
+
+	spin_lock(&pd->lock);
+	n = sysfs_emit(buf, "%d\n", pd->write_congestion_off);
+	spin_unlock(&pd->lock);
+	return n;
+}
+
+static ssize_t congestion_off_store(struct device *dev,
+				    struct device_attribute *attr,
+				    const char *buf, size_t len)
+{
+	struct pktcdvd_device *pd = dev_get_drvdata(dev);
+	int val;
+
+	if (sscanf(buf, "%d", &val) == 1) {
+		spin_lock(&pd->lock);
+		pd->write_congestion_off = val;
+		init_write_congestion_marks(&pd->write_congestion_off,
+					&pd->write_congestion_on);
+		spin_unlock(&pd->lock);
+	}
+	return len;
+}
+static DEVICE_ATTR_RW(congestion_off);
+
+static ssize_t congestion_on_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
+{
+	struct pktcdvd_device *pd = dev_get_drvdata(dev);
+	int n;
+
+	spin_lock(&pd->lock);
+	n = sysfs_emit(buf, "%d\n", pd->write_congestion_on);
+	spin_unlock(&pd->lock);
+	return n;
+}
+
+static ssize_t congestion_on_store(struct device *dev,
+				   struct device_attribute *attr,
+				   const char *buf, size_t len)
+{
+	struct pktcdvd_device *pd = dev_get_drvdata(dev);
+	int val;
+
+	if (sscanf(buf, "%d", &val) == 1) {
+		spin_lock(&pd->lock);
+		pd->write_congestion_on = val;
+		init_write_congestion_marks(&pd->write_congestion_off,
+					&pd->write_congestion_on);
+		spin_unlock(&pd->lock);
+	}
+	return len;
+}
+static DEVICE_ATTR_RW(congestion_on);
+
+static struct attribute *pkt_wq_attrs[] = {
+	&dev_attr_congestion_on.attr,
+	&dev_attr_congestion_off.attr,
+	&dev_attr_size.attr,
+	NULL,
+};
+
+static const struct attribute_group pkt_wq_group = {
+	.name = "write_queue",
+	.attrs = pkt_wq_attrs,
+};
+
+static const struct attribute_group *pkt_groups[] = {
+	&pkt_stat_group,
+	&pkt_wq_group,
+	NULL,
+};
+
+static void pkt_sysfs_dev_new(struct pktcdvd_device *pd)
+{
+	if (class_pktcdvd) {
+		pd->dev = device_create_with_groups(class_pktcdvd, NULL,
+						    MKDEV(0, 0), pd, pkt_groups,
+						    "%s", pd->name);
+		if (IS_ERR(pd->dev))
+			pd->dev = NULL;
+	}
+}
+
+static void pkt_sysfs_dev_remove(struct pktcdvd_device *pd)
+{
+	if (class_pktcdvd)
+		device_unregister(pd->dev);
+}
+
+
+/********************************************************************
+  /sys/class/pktcdvd/
+                     add            map block device
+                     remove         unmap packet dev
+                     device_map     show mappings
+ *******************************************************************/
+
+static void class_pktcdvd_release(struct class *cls)
+{
+	kfree(cls);
+}
+
+static ssize_t device_map_show(struct class *c, struct class_attribute *attr,
+			       char *data)
+{
+	int n = 0;
+	int idx;
+	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+	for (idx = 0; idx < MAX_WRITERS; idx++) {
+		struct pktcdvd_device *pd = pkt_devs[idx];
+		if (!pd)
+			continue;
+		n += sprintf(data+n, "%s %u:%u %u:%u\n",
+			pd->name,
+			MAJOR(pd->pkt_dev), MINOR(pd->pkt_dev),
+			MAJOR(pd->bdev->bd_dev),
+			MINOR(pd->bdev->bd_dev));
+	}
+	mutex_unlock(&ctl_mutex);
+	return n;
+}
+static CLASS_ATTR_RO(device_map);
+
+static ssize_t add_store(struct class *c, struct class_attribute *attr,
+			 const char *buf, size_t count)
+{
+	unsigned int major, minor;
+
+	if (sscanf(buf, "%u:%u", &major, &minor) == 2) {
+		/* pkt_setup_dev() expects caller to hold reference to self */
+		if (!try_module_get(THIS_MODULE))
+			return -ENODEV;
+
+		pkt_setup_dev(MKDEV(major, minor), NULL);
+
+		module_put(THIS_MODULE);
+
+		return count;
+	}
+
+	return -EINVAL;
+}
+static CLASS_ATTR_WO(add);
+
+static ssize_t remove_store(struct class *c, struct class_attribute *attr,
+			    const char *buf, size_t count)
+{
+	unsigned int major, minor;
+	if (sscanf(buf, "%u:%u", &major, &minor) == 2) {
+		pkt_remove_dev(MKDEV(major, minor));
+		return count;
+	}
+	return -EINVAL;
+}
+static CLASS_ATTR_WO(remove);
+
+static struct attribute *class_pktcdvd_attrs[] = {
+	&class_attr_add.attr,
+	&class_attr_remove.attr,
+	&class_attr_device_map.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(class_pktcdvd);
+
+static int pkt_sysfs_init(void)
+{
+	int ret = 0;
+
+	/*
+	 * create control files in sysfs
+	 * /sys/class/pktcdvd/...
+	 */
+	class_pktcdvd = kzalloc(sizeof(*class_pktcdvd), GFP_KERNEL);
+	if (!class_pktcdvd)
+		return -ENOMEM;
+	class_pktcdvd->name = DRIVER_NAME;
+	class_pktcdvd->owner = THIS_MODULE;
+	class_pktcdvd->class_release = class_pktcdvd_release;
+	class_pktcdvd->class_groups = class_pktcdvd_groups;
+	ret = class_register(class_pktcdvd);
+	if (ret) {
+		kfree(class_pktcdvd);
+		class_pktcdvd = NULL;
+		pr_err("failed to create class pktcdvd\n");
+		return ret;
+	}
+	return 0;
+}
+
+static void pkt_sysfs_cleanup(void)
+{
+	if (class_pktcdvd)
+		class_destroy(class_pktcdvd);
+	class_pktcdvd = NULL;
+}
+
+/********************************************************************
+  entries in debugfs
+
+  /sys/kernel/debug/pktcdvd[0-7]/
+			info
+
+ *******************************************************************/
+
+static int pkt_debugfs_seq_show(struct seq_file *m, void *p)
+{
+	return pkt_seq_show(m, p);
+}
+
+static int pkt_debugfs_fops_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, pkt_debugfs_seq_show, inode->i_private);
+}
+
+static const struct file_operations debug_fops = {
+	.open		= pkt_debugfs_fops_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+	.owner		= THIS_MODULE,
+};
+
+static void pkt_debugfs_dev_new(struct pktcdvd_device *pd)
+{
+	if (!pkt_debugfs_root)
+		return;
+	pd->dfs_d_root = debugfs_create_dir(pd->name, pkt_debugfs_root);
+	if (!pd->dfs_d_root)
+		return;
+
+	pd->dfs_f_info = debugfs_create_file("info", 0444,
+					     pd->dfs_d_root, pd, &debug_fops);
+}
+
+static void pkt_debugfs_dev_remove(struct pktcdvd_device *pd)
+{
+	if (!pkt_debugfs_root)
+		return;
+	debugfs_remove(pd->dfs_f_info);
+	debugfs_remove(pd->dfs_d_root);
+	pd->dfs_f_info = NULL;
+	pd->dfs_d_root = NULL;
+}
+
+static void pkt_debugfs_init(void)
+{
+	pkt_debugfs_root = debugfs_create_dir(DRIVER_NAME, NULL);
+}
+
+static void pkt_debugfs_cleanup(void)
+{
+	debugfs_remove(pkt_debugfs_root);
+	pkt_debugfs_root = NULL;
+}
+
+/* ----------------------------------------------------------*/
+
+
+static void pkt_bio_finished(struct pktcdvd_device *pd)
+{
+	BUG_ON(atomic_read(&pd->cdrw.pending_bios) <= 0);
+	if (atomic_dec_and_test(&pd->cdrw.pending_bios)) {
+		pkt_dbg(2, pd, "queue empty\n");
+		atomic_set(&pd->iosched.attention, 1);
+		wake_up(&pd->wqueue);
+	}
+}
+
+/*
+ * Allocate a packet_data struct
+ */
+static struct packet_data *pkt_alloc_packet_data(int frames)
+{
+	int i;
+	struct packet_data *pkt;
+
+	pkt = kzalloc(sizeof(struct packet_data), GFP_KERNEL);
+	if (!pkt)
+		goto no_pkt;
+
+	pkt->frames = frames;
+	pkt->w_bio = bio_kmalloc(frames, GFP_KERNEL);
+	if (!pkt->w_bio)
+		goto no_bio;
+
+	for (i = 0; i < frames / FRAMES_PER_PAGE; i++) {
+		pkt->pages[i] = alloc_page(GFP_KERNEL|__GFP_ZERO);
+		if (!pkt->pages[i])
+			goto no_page;
+	}
+
+	spin_lock_init(&pkt->lock);
+	bio_list_init(&pkt->orig_bios);
+
+	for (i = 0; i < frames; i++) {
+		pkt->r_bios[i] = bio_kmalloc(1, GFP_KERNEL);
+		if (!pkt->r_bios[i])
+			goto no_rd_bio;
+	}
+
+	return pkt;
+
+no_rd_bio:
+	for (i = 0; i < frames; i++)
+		kfree(pkt->r_bios[i]);
+no_page:
+	for (i = 0; i < frames / FRAMES_PER_PAGE; i++)
+		if (pkt->pages[i])
+			__free_page(pkt->pages[i]);
+	kfree(pkt->w_bio);
+no_bio:
+	kfree(pkt);
+no_pkt:
+	return NULL;
+}
+
+/*
+ * Free a packet_data struct
+ */
+static void pkt_free_packet_data(struct packet_data *pkt)
+{
+	int i;
+
+	for (i = 0; i < pkt->frames; i++)
+		kfree(pkt->r_bios[i]);
+	for (i = 0; i < pkt->frames / FRAMES_PER_PAGE; i++)
+		__free_page(pkt->pages[i]);
+	kfree(pkt->w_bio);
+	kfree(pkt);
+}
+
+static void pkt_shrink_pktlist(struct pktcdvd_device *pd)
+{
+	struct packet_data *pkt, *next;
+
+	BUG_ON(!list_empty(&pd->cdrw.pkt_active_list));
+
+	list_for_each_entry_safe(pkt, next, &pd->cdrw.pkt_free_list, list) {
+		pkt_free_packet_data(pkt);
+	}
+	INIT_LIST_HEAD(&pd->cdrw.pkt_free_list);
+}
+
+static int pkt_grow_pktlist(struct pktcdvd_device *pd, int nr_packets)
+{
+	struct packet_data *pkt;
+
+	BUG_ON(!list_empty(&pd->cdrw.pkt_free_list));
+
+	while (nr_packets > 0) {
+		pkt = pkt_alloc_packet_data(pd->settings.size >> 2);
+		if (!pkt) {
+			pkt_shrink_pktlist(pd);
+			return 0;
+		}
+		pkt->id = nr_packets;
+		pkt->pd = pd;
+		list_add(&pkt->list, &pd->cdrw.pkt_free_list);
+		nr_packets--;
+	}
+	return 1;
+}
+
+static inline struct pkt_rb_node *pkt_rbtree_next(struct pkt_rb_node *node)
+{
+	struct rb_node *n = rb_next(&node->rb_node);
+	if (!n)
+		return NULL;
+	return rb_entry(n, struct pkt_rb_node, rb_node);
+}
+
+static void pkt_rbtree_erase(struct pktcdvd_device *pd, struct pkt_rb_node *node)
+{
+	rb_erase(&node->rb_node, &pd->bio_queue);
+	mempool_free(node, &pd->rb_pool);
+	pd->bio_queue_size--;
+	BUG_ON(pd->bio_queue_size < 0);
+}
+
+/*
+ * Find the first node in the pd->bio_queue rb tree with a starting sector >= s.
+ */
+static struct pkt_rb_node *pkt_rbtree_find(struct pktcdvd_device *pd, sector_t s)
+{
+	struct rb_node *n = pd->bio_queue.rb_node;
+	struct rb_node *next;
+	struct pkt_rb_node *tmp;
+
+	if (!n) {
+		BUG_ON(pd->bio_queue_size > 0);
+		return NULL;
+	}
+
+	for (;;) {
+		tmp = rb_entry(n, struct pkt_rb_node, rb_node);
+		if (s <= tmp->bio->bi_iter.bi_sector)
+			next = n->rb_left;
+		else
+			next = n->rb_right;
+		if (!next)
+			break;
+		n = next;
+	}
+
+	if (s > tmp->bio->bi_iter.bi_sector) {
+		tmp = pkt_rbtree_next(tmp);
+		if (!tmp)
+			return NULL;
+	}
+	BUG_ON(s > tmp->bio->bi_iter.bi_sector);
+	return tmp;
+}
+
+/*
+ * Insert a node into the pd->bio_queue rb tree.
+ */
+static void pkt_rbtree_insert(struct pktcdvd_device *pd, struct pkt_rb_node *node)
+{
+	struct rb_node **p = &pd->bio_queue.rb_node;
+	struct rb_node *parent = NULL;
+	sector_t s = node->bio->bi_iter.bi_sector;
+	struct pkt_rb_node *tmp;
+
+	while (*p) {
+		parent = *p;
+		tmp = rb_entry(parent, struct pkt_rb_node, rb_node);
+		if (s < tmp->bio->bi_iter.bi_sector)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+	rb_link_node(&node->rb_node, parent, p);
+	rb_insert_color(&node->rb_node, &pd->bio_queue);
+	pd->bio_queue_size++;
+}
+
+/*
+ * Send a packet_command to the underlying block device and
+ * wait for completion.
+ */
+static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *cgc)
+{
+	struct request_queue *q = bdev_get_queue(pd->bdev);
+	struct scsi_cmnd *scmd;
+	struct request *rq;
+	int ret = 0;
+
+	rq = scsi_alloc_request(q, (cgc->data_direction == CGC_DATA_WRITE) ?
+			     REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
+	scmd = blk_mq_rq_to_pdu(rq);
+
+	if (cgc->buflen) {
+		ret = blk_rq_map_kern(q, rq, cgc->buffer, cgc->buflen,
+				      GFP_NOIO);
+		if (ret)
+			goto out;
+	}
+
+	scmd->cmd_len = COMMAND_SIZE(cgc->cmd[0]);
+	memcpy(scmd->cmnd, cgc->cmd, CDROM_PACKET_SIZE);
+
+	rq->timeout = 60*HZ;
+	if (cgc->quiet)
+		rq->rq_flags |= RQF_QUIET;
+
+	blk_execute_rq(rq, false);
+	if (scmd->result)
+		ret = -EIO;
+out:
+	blk_mq_free_request(rq);
+	return ret;
+}
+
+static const char *sense_key_string(__u8 index)
+{
+	static const char * const info[] = {
+		"No sense", "Recovered error", "Not ready",
+		"Medium error", "Hardware error", "Illegal request",
+		"Unit attention", "Data protect", "Blank check",
+	};
+
+	return index < ARRAY_SIZE(info) ? info[index] : "INVALID";
+}
+
+/*
+ * A generic sense dump / resolve mechanism should be implemented across
+ * all ATAPI + SCSI devices.
+ */
+static void pkt_dump_sense(struct pktcdvd_device *pd,
+			   struct packet_command *cgc)
+{
+	struct scsi_sense_hdr *sshdr = cgc->sshdr;
+
+	if (sshdr)
+		pkt_err(pd, "%*ph - sense %02x.%02x.%02x (%s)\n",
+			CDROM_PACKET_SIZE, cgc->cmd,
+			sshdr->sense_key, sshdr->asc, sshdr->ascq,
+			sense_key_string(sshdr->sense_key));
+	else
+		pkt_err(pd, "%*ph - no sense\n", CDROM_PACKET_SIZE, cgc->cmd);
+}
+
+/*
+ * flush the drive cache to media
+ */
+static int pkt_flush_cache(struct pktcdvd_device *pd)
+{
+	struct packet_command cgc;
+
+	init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
+	cgc.cmd[0] = GPCMD_FLUSH_CACHE;
+	cgc.quiet = 1;
+
+	/*
+	 * the IMMED bit -- we default to not setting it, although that
+	 * would allow a much faster close, this is safer
+	 */
+#if 0
+	cgc.cmd[1] = 1 << 1;
+#endif
+	return pkt_generic_packet(pd, &cgc);
+}
+
+/*
+ * speed is given as the normal factor, e.g. 4 for 4x
+ */
+static noinline_for_stack int pkt_set_speed(struct pktcdvd_device *pd,
+				unsigned write_speed, unsigned read_speed)
+{
+	struct packet_command cgc;
+	struct scsi_sense_hdr sshdr;
+	int ret;
+
+	init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
+	cgc.sshdr = &sshdr;
+	cgc.cmd[0] = GPCMD_SET_SPEED;
+	cgc.cmd[2] = (read_speed >> 8) & 0xff;
+	cgc.cmd[3] = read_speed & 0xff;
+	cgc.cmd[4] = (write_speed >> 8) & 0xff;
+	cgc.cmd[5] = write_speed & 0xff;
+
+	ret = pkt_generic_packet(pd, &cgc);
+	if (ret)
+		pkt_dump_sense(pd, &cgc);
+
+	return ret;
+}
+
+/*
+ * Queue a bio for processing by the low-level CD device. Must be called
+ * from process context.
+ */
+static void pkt_queue_bio(struct pktcdvd_device *pd, struct bio *bio)
+{
+	spin_lock(&pd->iosched.lock);
+	if (bio_data_dir(bio) == READ)
+		bio_list_add(&pd->iosched.read_queue, bio);
+	else
+		bio_list_add(&pd->iosched.write_queue, bio);
+	spin_unlock(&pd->iosched.lock);
+
+	atomic_set(&pd->iosched.attention, 1);
+	wake_up(&pd->wqueue);
+}
+
+/*
+ * Process the queued read/write requests. This function handles special
+ * requirements for CDRW drives:
+ * - A cache flush command must be inserted before a read request if the
+ *   previous request was a write.
+ * - Switching between reading and writing is slow, so don't do it more often
+ *   than necessary.
+ * - Optimize for throughput at the expense of latency. This means that streaming
+ *   writes will never be interrupted by a read, but if the drive has to seek
+ *   before the next write, switch to reading instead if there are any pending
+ *   read requests.
+ * - Set the read speed according to current usage pattern. When only reading
+ *   from the device, it's best to use the highest possible read speed, but
+ *   when switching often between reading and writing, it's better to have the
+ *   same read and write speeds.
+ */
+static void pkt_iosched_process_queue(struct pktcdvd_device *pd)
+{
+
+	if (atomic_read(&pd->iosched.attention) == 0)
+		return;
+	atomic_set(&pd->iosched.attention, 0);
+
+	for (;;) {
+		struct bio *bio;
+		int reads_queued, writes_queued;
+
+		spin_lock(&pd->iosched.lock);
+		reads_queued = !bio_list_empty(&pd->iosched.read_queue);
+		writes_queued = !bio_list_empty(&pd->iosched.write_queue);
+		spin_unlock(&pd->iosched.lock);
+
+		if (!reads_queued && !writes_queued)
+			break;
+
+		if (pd->iosched.writing) {
+			int need_write_seek = 1;
+			spin_lock(&pd->iosched.lock);
+			bio = bio_list_peek(&pd->iosched.write_queue);
+			spin_unlock(&pd->iosched.lock);
+			if (bio && (bio->bi_iter.bi_sector ==
+				    pd->iosched.last_write))
+				need_write_seek = 0;
+			if (need_write_seek && reads_queued) {
+				if (atomic_read(&pd->cdrw.pending_bios) > 0) {
+					pkt_dbg(2, pd, "write, waiting\n");
+					break;
+				}
+				pkt_flush_cache(pd);
+				pd->iosched.writing = 0;
+			}
+		} else {
+			if (!reads_queued && writes_queued) {
+				if (atomic_read(&pd->cdrw.pending_bios) > 0) {
+					pkt_dbg(2, pd, "read, waiting\n");
+					break;
+				}
+				pd->iosched.writing = 1;
+			}
+		}
+
+		spin_lock(&pd->iosched.lock);
+		if (pd->iosched.writing)
+			bio = bio_list_pop(&pd->iosched.write_queue);
+		else
+			bio = bio_list_pop(&pd->iosched.read_queue);
+		spin_unlock(&pd->iosched.lock);
+
+		if (!bio)
+			continue;
+
+		if (bio_data_dir(bio) == READ)
+			pd->iosched.successive_reads +=
+				bio->bi_iter.bi_size >> 10;
+		else {
+			pd->iosched.successive_reads = 0;
+			pd->iosched.last_write = bio_end_sector(bio);
+		}
+		if (pd->iosched.successive_reads >= HI_SPEED_SWITCH) {
+			if (pd->read_speed == pd->write_speed) {
+				pd->read_speed = MAX_SPEED;
+				pkt_set_speed(pd, pd->write_speed, pd->read_speed);
+			}
+		} else {
+			if (pd->read_speed != pd->write_speed) {
+				pd->read_speed = pd->write_speed;
+				pkt_set_speed(pd, pd->write_speed, pd->read_speed);
+			}
+		}
+
+		atomic_inc(&pd->cdrw.pending_bios);
+		submit_bio_noacct(bio);
+	}
+}
+
+/*
+ * Special care is needed if the underlying block device has a small
+ * max_phys_segments value.
+ */
+static int pkt_set_segment_merging(struct pktcdvd_device *pd, struct request_queue *q)
+{
+	if ((pd->settings.size << 9) / CD_FRAMESIZE
+	    <= queue_max_segments(q)) {
+		/*
+		 * The cdrom device can handle one segment/frame
+		 */
+		clear_bit(PACKET_MERGE_SEGS, &pd->flags);
+		return 0;
+	} else if ((pd->settings.size << 9) / PAGE_SIZE
+		   <= queue_max_segments(q)) {
+		/*
+		 * We can handle this case at the expense of some extra memory
+		 * copies during write operations
+		 */
+		set_bit(PACKET_MERGE_SEGS, &pd->flags);
+		return 0;
+	} else {
+		pkt_err(pd, "cdrom max_phys_segments too small\n");
+		return -EIO;
+	}
+}
+
+static void pkt_end_io_read(struct bio *bio)
+{
+	struct packet_data *pkt = bio->bi_private;
+	struct pktcdvd_device *pd = pkt->pd;
+	BUG_ON(!pd);
+
+	pkt_dbg(2, pd, "bio=%p sec0=%llx sec=%llx err=%d\n",
+		bio, (unsigned long long)pkt->sector,
+		(unsigned long long)bio->bi_iter.bi_sector, bio->bi_status);
+
+	if (bio->bi_status)
+		atomic_inc(&pkt->io_errors);
+	bio_uninit(bio);
+	if (atomic_dec_and_test(&pkt->io_wait)) {
+		atomic_inc(&pkt->run_sm);
+		wake_up(&pd->wqueue);
+	}
+	pkt_bio_finished(pd);
+}
+
+static void pkt_end_io_packet_write(struct bio *bio)
+{
+	struct packet_data *pkt = bio->bi_private;
+	struct pktcdvd_device *pd = pkt->pd;
+	BUG_ON(!pd);
+
+	pkt_dbg(2, pd, "id=%d, err=%d\n", pkt->id, bio->bi_status);
+
+	pd->stats.pkt_ended++;
+
+	bio_uninit(bio);
+	pkt_bio_finished(pd);
+	atomic_dec(&pkt->io_wait);
+	atomic_inc(&pkt->run_sm);
+	wake_up(&pd->wqueue);
+}
+
+/*
+ * Schedule reads for the holes in a packet
+ */
+static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt)
+{
+	int frames_read = 0;
+	struct bio *bio;
+	int f;
+	char written[PACKET_MAX_SIZE];
+
+	BUG_ON(bio_list_empty(&pkt->orig_bios));
+
+	atomic_set(&pkt->io_wait, 0);
+	atomic_set(&pkt->io_errors, 0);
+
+	/*
+	 * Figure out which frames we need to read before we can write.
+	 */
+	memset(written, 0, sizeof(written));
+	spin_lock(&pkt->lock);
+	bio_list_for_each(bio, &pkt->orig_bios) {
+		int first_frame = (bio->bi_iter.bi_sector - pkt->sector) /
+			(CD_FRAMESIZE >> 9);
+		int num_frames = bio->bi_iter.bi_size / CD_FRAMESIZE;
+		pd->stats.secs_w += num_frames * (CD_FRAMESIZE >> 9);
+		BUG_ON(first_frame < 0);
+		BUG_ON(first_frame + num_frames > pkt->frames);
+		for (f = first_frame; f < first_frame + num_frames; f++)
+			written[f] = 1;
+	}
+	spin_unlock(&pkt->lock);
+
+	if (pkt->cache_valid) {
+		pkt_dbg(2, pd, "zone %llx cached\n",
+			(unsigned long long)pkt->sector);
+		goto out_account;
+	}
+
+	/*
+	 * Schedule reads for missing parts of the packet.
+	 */
+	for (f = 0; f < pkt->frames; f++) {
+		int p, offset;
+
+		if (written[f])
+			continue;
+
+		bio = pkt->r_bios[f];
+		bio_init(bio, pd->bdev, bio->bi_inline_vecs, 1, REQ_OP_READ);
+		bio->bi_iter.bi_sector = pkt->sector + f * (CD_FRAMESIZE >> 9);
+		bio->bi_end_io = pkt_end_io_read;
+		bio->bi_private = pkt;
+
+		p = (f * CD_FRAMESIZE) / PAGE_SIZE;
+		offset = (f * CD_FRAMESIZE) % PAGE_SIZE;
+		pkt_dbg(2, pd, "Adding frame %d, page:%p offs:%d\n",
+			f, pkt->pages[p], offset);
+		if (!bio_add_page(bio, pkt->pages[p], CD_FRAMESIZE, offset))
+			BUG();
+
+		atomic_inc(&pkt->io_wait);
+		pkt_queue_bio(pd, bio);
+		frames_read++;
+	}
+
+out_account:
+	pkt_dbg(2, pd, "need %d frames for zone %llx\n",
+		frames_read, (unsigned long long)pkt->sector);
+	pd->stats.pkt_started++;
+	pd->stats.secs_rg += frames_read * (CD_FRAMESIZE >> 9);
+}
+
+/*
+ * Find a packet matching zone, or the least recently used packet if
+ * there is no match.
+ */
+static struct packet_data *pkt_get_packet_data(struct pktcdvd_device *pd, int zone)
+{
+	struct packet_data *pkt;
+
+	list_for_each_entry(pkt, &pd->cdrw.pkt_free_list, list) {
+		if (pkt->sector == zone || pkt->list.next == &pd->cdrw.pkt_free_list) {
+			list_del_init(&pkt->list);
+			if (pkt->sector != zone)
+				pkt->cache_valid = 0;
+			return pkt;
+		}
+	}
+	BUG();
+	return NULL;
+}
+
+static void pkt_put_packet_data(struct pktcdvd_device *pd, struct packet_data *pkt)
+{
+	if (pkt->cache_valid) {
+		list_add(&pkt->list, &pd->cdrw.pkt_free_list);
+	} else {
+		list_add_tail(&pkt->list, &pd->cdrw.pkt_free_list);
+	}
+}
+
+static inline void pkt_set_state(struct packet_data *pkt, enum packet_data_state state)
+{
+#if PACKET_DEBUG > 1
+	static const char *state_name[] = {
+		"IDLE", "WAITING", "READ_WAIT", "WRITE_WAIT", "RECOVERY", "FINISHED"
+	};
+	enum packet_data_state old_state = pkt->state;
+	pkt_dbg(2, pd, "pkt %2d : s=%6llx %s -> %s\n",
+		pkt->id, (unsigned long long)pkt->sector,
+		state_name[old_state], state_name[state]);
+#endif
+	pkt->state = state;
+}
+
+/*
+ * Scan the work queue to see if we can start a new packet.
+ * returns non-zero if any work was done.
+ */
+static int pkt_handle_queue(struct pktcdvd_device *pd)
+{
+	struct packet_data *pkt, *p;
+	struct bio *bio = NULL;
+	sector_t zone = 0; /* Suppress gcc warning */
+	struct pkt_rb_node *node, *first_node;
+	struct rb_node *n;
+
+	atomic_set(&pd->scan_queue, 0);
+
+	if (list_empty(&pd->cdrw.pkt_free_list)) {
+		pkt_dbg(2, pd, "no pkt\n");
+		return 0;
+	}
+
+	/*
+	 * Try to find a zone we are not already working on.
+	 */
+	spin_lock(&pd->lock);
+	first_node = pkt_rbtree_find(pd, pd->current_sector);
+	if (!first_node) {
+		n = rb_first(&pd->bio_queue);
+		if (n)
+			first_node = rb_entry(n, struct pkt_rb_node, rb_node);
+	}
+	node = first_node;
+	while (node) {
+		bio = node->bio;
+		zone = get_zone(bio->bi_iter.bi_sector, pd);
+		list_for_each_entry(p, &pd->cdrw.pkt_active_list, list) {
+			if (p->sector == zone) {
+				bio = NULL;
+				goto try_next_bio;
+			}
+		}
+		break;
+try_next_bio:
+		node = pkt_rbtree_next(node);
+		if (!node) {
+			n = rb_first(&pd->bio_queue);
+			if (n)
+				node = rb_entry(n, struct pkt_rb_node, rb_node);
+		}
+		if (node == first_node)
+			node = NULL;
+	}
+	spin_unlock(&pd->lock);
+	if (!bio) {
+		pkt_dbg(2, pd, "no bio\n");
+		return 0;
+	}
+
+	pkt = pkt_get_packet_data(pd, zone);
+
+	pd->current_sector = zone + pd->settings.size;
+	pkt->sector = zone;
+	BUG_ON(pkt->frames != pd->settings.size >> 2);
+	pkt->write_size = 0;
+
+	/*
+	 * Scan work queue for bios in the same zone and link them
+	 * to this packet.
+	 */
+	spin_lock(&pd->lock);
+	pkt_dbg(2, pd, "looking for zone %llx\n", (unsigned long long)zone);
+	while ((node = pkt_rbtree_find(pd, zone)) != NULL) {
+		bio = node->bio;
+		pkt_dbg(2, pd, "found zone=%llx\n", (unsigned long long)
+			get_zone(bio->bi_iter.bi_sector, pd));
+		if (get_zone(bio->bi_iter.bi_sector, pd) != zone)
+			break;
+		pkt_rbtree_erase(pd, node);
+		spin_lock(&pkt->lock);
+		bio_list_add(&pkt->orig_bios, bio);
+		pkt->write_size += bio->bi_iter.bi_size / CD_FRAMESIZE;
+		spin_unlock(&pkt->lock);
+	}
+	/* check write congestion marks, and if bio_queue_size is
+	 * below, wake up any waiters
+	 */
+	if (pd->congested &&
+	    pd->bio_queue_size <= pd->write_congestion_off) {
+		pd->congested = false;
+		wake_up_var(&pd->congested);
+	}
+	spin_unlock(&pd->lock);
+
+	pkt->sleep_time = max(PACKET_WAIT_TIME, 1);
+	pkt_set_state(pkt, PACKET_WAITING_STATE);
+	atomic_set(&pkt->run_sm, 1);
+
+	spin_lock(&pd->cdrw.active_list_lock);
+	list_add(&pkt->list, &pd->cdrw.pkt_active_list);
+	spin_unlock(&pd->cdrw.active_list_lock);
+
+	return 1;
+}
+
+/**
+ * bio_list_copy_data - copy contents of data buffers from one chain of bios to
+ * another
+ * @src: source bio list
+ * @dst: destination bio list
+ *
+ * Stops when it reaches the end of either the @src list or @dst list - that is,
+ * copies min(src->bi_size, dst->bi_size) bytes (or the equivalent for lists of
+ * bios).
+ */
+static void bio_list_copy_data(struct bio *dst, struct bio *src)
+{
+	struct bvec_iter src_iter = src->bi_iter;
+	struct bvec_iter dst_iter = dst->bi_iter;
+
+	while (1) {
+		if (!src_iter.bi_size) {
+			src = src->bi_next;
+			if (!src)
+				break;
+
+			src_iter = src->bi_iter;
+		}
+
+		if (!dst_iter.bi_size) {
+			dst = dst->bi_next;
+			if (!dst)
+				break;
+
+			dst_iter = dst->bi_iter;
+		}
+
+		bio_copy_data_iter(dst, &dst_iter, src, &src_iter);
+	}
+}
+
+/*
+ * Assemble a bio to write one packet and queue the bio for processing
+ * by the underlying block device.
+ */
+static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt)
+{
+	int f;
+
+	bio_init(pkt->w_bio, pd->bdev, pkt->w_bio->bi_inline_vecs, pkt->frames,
+		 REQ_OP_WRITE);
+	pkt->w_bio->bi_iter.bi_sector = pkt->sector;
+	pkt->w_bio->bi_end_io = pkt_end_io_packet_write;
+	pkt->w_bio->bi_private = pkt;
+
+	/* XXX: locking? */
+	for (f = 0; f < pkt->frames; f++) {
+		struct page *page = pkt->pages[(f * CD_FRAMESIZE) / PAGE_SIZE];
+		unsigned offset = (f * CD_FRAMESIZE) % PAGE_SIZE;
+
+		if (!bio_add_page(pkt->w_bio, page, CD_FRAMESIZE, offset))
+			BUG();
+	}
+	pkt_dbg(2, pd, "vcnt=%d\n", pkt->w_bio->bi_vcnt);
+
+	/*
+	 * Fill-in bvec with data from orig_bios.
+	 */
+	spin_lock(&pkt->lock);
+	bio_list_copy_data(pkt->w_bio, pkt->orig_bios.head);
+
+	pkt_set_state(pkt, PACKET_WRITE_WAIT_STATE);
+	spin_unlock(&pkt->lock);
+
+	pkt_dbg(2, pd, "Writing %d frames for zone %llx\n",
+		pkt->write_size, (unsigned long long)pkt->sector);
+
+	if (test_bit(PACKET_MERGE_SEGS, &pd->flags) || (pkt->write_size < pkt->frames))
+		pkt->cache_valid = 1;
+	else
+		pkt->cache_valid = 0;
+
+	/* Start the write request */
+	atomic_set(&pkt->io_wait, 1);
+	pkt_queue_bio(pd, pkt->w_bio);
+}
+
+static void pkt_finish_packet(struct packet_data *pkt, blk_status_t status)
+{
+	struct bio *bio;
+
+	if (status)
+		pkt->cache_valid = 0;
+
+	/* Finish all bios corresponding to this packet */
+	while ((bio = bio_list_pop(&pkt->orig_bios))) {
+		bio->bi_status = status;
+		bio_endio(bio);
+	}
+}
+
+static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data *pkt)
+{
+	pkt_dbg(2, pd, "pkt %d\n", pkt->id);
+
+	for (;;) {
+		switch (pkt->state) {
+		case PACKET_WAITING_STATE:
+			if ((pkt->write_size < pkt->frames) && (pkt->sleep_time > 0))
+				return;
+
+			pkt->sleep_time = 0;
+			pkt_gather_data(pd, pkt);
+			pkt_set_state(pkt, PACKET_READ_WAIT_STATE);
+			break;
+
+		case PACKET_READ_WAIT_STATE:
+			if (atomic_read(&pkt->io_wait) > 0)
+				return;
+
+			if (atomic_read(&pkt->io_errors) > 0) {
+				pkt_set_state(pkt, PACKET_RECOVERY_STATE);
+			} else {
+				pkt_start_write(pd, pkt);
+			}
+			break;
+
+		case PACKET_WRITE_WAIT_STATE:
+			if (atomic_read(&pkt->io_wait) > 0)
+				return;
+
+			if (!pkt->w_bio->bi_status) {
+				pkt_set_state(pkt, PACKET_FINISHED_STATE);
+			} else {
+				pkt_set_state(pkt, PACKET_RECOVERY_STATE);
+			}
+			break;
+
+		case PACKET_RECOVERY_STATE:
+			pkt_dbg(2, pd, "No recovery possible\n");
+			pkt_set_state(pkt, PACKET_FINISHED_STATE);
+			break;
+
+		case PACKET_FINISHED_STATE:
+			pkt_finish_packet(pkt, pkt->w_bio->bi_status);
+			return;
+
+		default:
+			BUG();
+			break;
+		}
+	}
+}
+
+static void pkt_handle_packets(struct pktcdvd_device *pd)
+{
+	struct packet_data *pkt, *next;
+
+	/*
+	 * Run state machine for active packets
+	 */
+	list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
+		if (atomic_read(&pkt->run_sm) > 0) {
+			atomic_set(&pkt->run_sm, 0);
+			pkt_run_state_machine(pd, pkt);
+		}
+	}
+
+	/*
+	 * Move no longer active packets to the free list
+	 */
+	spin_lock(&pd->cdrw.active_list_lock);
+	list_for_each_entry_safe(pkt, next, &pd->cdrw.pkt_active_list, list) {
+		if (pkt->state == PACKET_FINISHED_STATE) {
+			list_del(&pkt->list);
+			pkt_put_packet_data(pd, pkt);
+			pkt_set_state(pkt, PACKET_IDLE_STATE);
+			atomic_set(&pd->scan_queue, 1);
+		}
+	}
+	spin_unlock(&pd->cdrw.active_list_lock);
+}
+
+static void pkt_count_states(struct pktcdvd_device *pd, int *states)
+{
+	struct packet_data *pkt;
+	int i;
+
+	for (i = 0; i < PACKET_NUM_STATES; i++)
+		states[i] = 0;
+
+	spin_lock(&pd->cdrw.active_list_lock);
+	list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
+		states[pkt->state]++;
+	}
+	spin_unlock(&pd->cdrw.active_list_lock);
+}
+
+/*
+ * kcdrwd is woken up when writes have been queued for one of our
+ * registered devices
+ */
+static int kcdrwd(void *foobar)
+{
+	struct pktcdvd_device *pd = foobar;
+	struct packet_data *pkt;
+	long min_sleep_time, residue;
+
+	set_user_nice(current, MIN_NICE);
+	set_freezable();
+
+	for (;;) {
+		DECLARE_WAITQUEUE(wait, current);
+
+		/*
+		 * Wait until there is something to do
+		 */
+		add_wait_queue(&pd->wqueue, &wait);
+		for (;;) {
+			set_current_state(TASK_INTERRUPTIBLE);
+
+			/* Check if we need to run pkt_handle_queue */
+			if (atomic_read(&pd->scan_queue) > 0)
+				goto work_to_do;
+
+			/* Check if we need to run the state machine for some packet */
+			list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
+				if (atomic_read(&pkt->run_sm) > 0)
+					goto work_to_do;
+			}
+
+			/* Check if we need to process the iosched queues */
+			if (atomic_read(&pd->iosched.attention) != 0)
+				goto work_to_do;
+
+			/* Otherwise, go to sleep */
+			if (PACKET_DEBUG > 1) {
+				int states[PACKET_NUM_STATES];
+				pkt_count_states(pd, states);
+				pkt_dbg(2, pd, "i:%d ow:%d rw:%d ww:%d rec:%d fin:%d\n",
+					states[0], states[1], states[2],
+					states[3], states[4], states[5]);
+			}
+
+			min_sleep_time = MAX_SCHEDULE_TIMEOUT;
+			list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
+				if (pkt->sleep_time && pkt->sleep_time < min_sleep_time)
+					min_sleep_time = pkt->sleep_time;
+			}
+
+			pkt_dbg(2, pd, "sleeping\n");
+			residue = schedule_timeout(min_sleep_time);
+			pkt_dbg(2, pd, "wake up\n");
+
+			/* make swsusp happy with our thread */
+			try_to_freeze();
+
+			list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
+				if (!pkt->sleep_time)
+					continue;
+				pkt->sleep_time -= min_sleep_time - residue;
+				if (pkt->sleep_time <= 0) {
+					pkt->sleep_time = 0;
+					atomic_inc(&pkt->run_sm);
+				}
+			}
+
+			if (kthread_should_stop())
+				break;
+		}
+work_to_do:
+		set_current_state(TASK_RUNNING);
+		remove_wait_queue(&pd->wqueue, &wait);
+
+		if (kthread_should_stop())
+			break;
+
+		/*
+		 * if pkt_handle_queue returns true, we can queue
+		 * another request.
+		 */
+		while (pkt_handle_queue(pd))
+			;
+
+		/*
+		 * Handle packet state machine
+		 */
+		pkt_handle_packets(pd);
+
+		/*
+		 * Handle iosched queues
+		 */
+		pkt_iosched_process_queue(pd);
+	}
+
+	return 0;
+}
+
+static void pkt_print_settings(struct pktcdvd_device *pd)
+{
+	pkt_info(pd, "%s packets, %u blocks, Mode-%c disc\n",
+		 pd->settings.fp ? "Fixed" : "Variable",
+		 pd->settings.size >> 2,
+		 pd->settings.block_mode == 8 ? '1' : '2');
+}
+
+static int pkt_mode_sense(struct pktcdvd_device *pd, struct packet_command *cgc, int page_code, int page_control)
+{
+	memset(cgc->cmd, 0, sizeof(cgc->cmd));
+
+	cgc->cmd[0] = GPCMD_MODE_SENSE_10;
+	cgc->cmd[2] = page_code | (page_control << 6);
+	cgc->cmd[7] = cgc->buflen >> 8;
+	cgc->cmd[8] = cgc->buflen & 0xff;
+	cgc->data_direction = CGC_DATA_READ;
+	return pkt_generic_packet(pd, cgc);
+}
+
+static int pkt_mode_select(struct pktcdvd_device *pd, struct packet_command *cgc)
+{
+	memset(cgc->cmd, 0, sizeof(cgc->cmd));
+	memset(cgc->buffer, 0, 2);
+	cgc->cmd[0] = GPCMD_MODE_SELECT_10;
+	cgc->cmd[1] = 0x10;		/* PF */
+	cgc->cmd[7] = cgc->buflen >> 8;
+	cgc->cmd[8] = cgc->buflen & 0xff;
+	cgc->data_direction = CGC_DATA_WRITE;
+	return pkt_generic_packet(pd, cgc);
+}
+
+static int pkt_get_disc_info(struct pktcdvd_device *pd, disc_information *di)
+{
+	struct packet_command cgc;
+	int ret;
+
+	/* set up command and get the disc info */
+	init_cdrom_command(&cgc, di, sizeof(*di), CGC_DATA_READ);
+	cgc.cmd[0] = GPCMD_READ_DISC_INFO;
+	cgc.cmd[8] = cgc.buflen = 2;
+	cgc.quiet = 1;
+
+	ret = pkt_generic_packet(pd, &cgc);
+	if (ret)
+		return ret;
+
+	/* not all drives have the same disc_info length, so requeue
+	 * packet with the length the drive tells us it can supply
+	 */
+	cgc.buflen = be16_to_cpu(di->disc_information_length) +
+		     sizeof(di->disc_information_length);
+
+	if (cgc.buflen > sizeof(disc_information))
+		cgc.buflen = sizeof(disc_information);
+
+	cgc.cmd[8] = cgc.buflen;
+	return pkt_generic_packet(pd, &cgc);
+}
+
+static int pkt_get_track_info(struct pktcdvd_device *pd, __u16 track, __u8 type, track_information *ti)
+{
+	struct packet_command cgc;
+	int ret;
+
+	init_cdrom_command(&cgc, ti, 8, CGC_DATA_READ);
+	cgc.cmd[0] = GPCMD_READ_TRACK_RZONE_INFO;
+	cgc.cmd[1] = type & 3;
+	cgc.cmd[4] = (track & 0xff00) >> 8;
+	cgc.cmd[5] = track & 0xff;
+	cgc.cmd[8] = 8;
+	cgc.quiet = 1;
+
+	ret = pkt_generic_packet(pd, &cgc);
+	if (ret)
+		return ret;
+
+	cgc.buflen = be16_to_cpu(ti->track_information_length) +
+		     sizeof(ti->track_information_length);
+
+	if (cgc.buflen > sizeof(track_information))
+		cgc.buflen = sizeof(track_information);
+
+	cgc.cmd[8] = cgc.buflen;
+	return pkt_generic_packet(pd, &cgc);
+}
+
+static noinline_for_stack int pkt_get_last_written(struct pktcdvd_device *pd,
+						long *last_written)
+{
+	disc_information di;
+	track_information ti;
+	__u32 last_track;
+	int ret;
+
+	ret = pkt_get_disc_info(pd, &di);
+	if (ret)
+		return ret;
+
+	last_track = (di.last_track_msb << 8) | di.last_track_lsb;
+	ret = pkt_get_track_info(pd, last_track, 1, &ti);
+	if (ret)
+		return ret;
+
+	/* if this track is blank, try the previous. */
+	if (ti.blank) {
+		last_track--;
+		ret = pkt_get_track_info(pd, last_track, 1, &ti);
+		if (ret)
+			return ret;
+	}
+
+	/* if last recorded field is valid, return it. */
+	if (ti.lra_v) {
+		*last_written = be32_to_cpu(ti.last_rec_address);
+	} else {
+		/* make it up instead */
+		*last_written = be32_to_cpu(ti.track_start) +
+				be32_to_cpu(ti.track_size);
+		if (ti.free_blocks)
+			*last_written -= (be32_to_cpu(ti.free_blocks) + 7);
+	}
+	return 0;
+}
+
+/*
+ * write mode select package based on pd->settings
+ */
+static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd)
+{
+	struct packet_command cgc;
+	struct scsi_sense_hdr sshdr;
+	write_param_page *wp;
+	char buffer[128];
+	int ret, size;
+
+	/* doesn't apply to DVD+RW or DVD-RAM */
+	if ((pd->mmc3_profile == 0x1a) || (pd->mmc3_profile == 0x12))
+		return 0;
+
+	memset(buffer, 0, sizeof(buffer));
+	init_cdrom_command(&cgc, buffer, sizeof(*wp), CGC_DATA_READ);
+	cgc.sshdr = &sshdr;
+	ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0);
+	if (ret) {
+		pkt_dump_sense(pd, &cgc);
+		return ret;
+	}
+
+	size = 2 + ((buffer[0] << 8) | (buffer[1] & 0xff));
+	pd->mode_offset = (buffer[6] << 8) | (buffer[7] & 0xff);
+	if (size > sizeof(buffer))
+		size = sizeof(buffer);
+
+	/*
+	 * now get it all
+	 */
+	init_cdrom_command(&cgc, buffer, size, CGC_DATA_READ);
+	cgc.sshdr = &sshdr;
+	ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0);
+	if (ret) {
+		pkt_dump_sense(pd, &cgc);
+		return ret;
+	}
+
+	/*
+	 * write page is offset header + block descriptor length
+	 */
+	wp = (write_param_page *) &buffer[sizeof(struct mode_page_header) + pd->mode_offset];
+
+	wp->fp = pd->settings.fp;
+	wp->track_mode = pd->settings.track_mode;
+	wp->write_type = pd->settings.write_type;
+	wp->data_block_type = pd->settings.block_mode;
+
+	wp->multi_session = 0;
+
+#ifdef PACKET_USE_LS
+	wp->link_size = 7;
+	wp->ls_v = 1;
+#endif
+
+	if (wp->data_block_type == PACKET_BLOCK_MODE1) {
+		wp->session_format = 0;
+		wp->subhdr2 = 0x20;
+	} else if (wp->data_block_type == PACKET_BLOCK_MODE2) {
+		wp->session_format = 0x20;
+		wp->subhdr2 = 8;
+#if 0
+		wp->mcn[0] = 0x80;
+		memcpy(&wp->mcn[1], PACKET_MCN, sizeof(wp->mcn) - 1);
+#endif
+	} else {
+		/*
+		 * paranoia
+		 */
+		pkt_err(pd, "write mode wrong %d\n", wp->data_block_type);
+		return 1;
+	}
+	wp->packet_size = cpu_to_be32(pd->settings.size >> 2);
+
+	cgc.buflen = cgc.cmd[8] = size;
+	ret = pkt_mode_select(pd, &cgc);
+	if (ret) {
+		pkt_dump_sense(pd, &cgc);
+		return ret;
+	}
+
+	pkt_print_settings(pd);
+	return 0;
+}
+
+/*
+ * 1 -- we can write to this track, 0 -- we can't
+ */
+static int pkt_writable_track(struct pktcdvd_device *pd, track_information *ti)
+{
+	switch (pd->mmc3_profile) {
+		case 0x1a: /* DVD+RW */
+		case 0x12: /* DVD-RAM */
+			/* The track is always writable on DVD+RW/DVD-RAM */
+			return 1;
+		default:
+			break;
+	}
+
+	if (!ti->packet || !ti->fp)
+		return 0;
+
+	/*
+	 * "good" settings as per Mt Fuji.
+	 */
+	if (ti->rt == 0 && ti->blank == 0)
+		return 1;
+
+	if (ti->rt == 0 && ti->blank == 1)
+		return 1;
+
+	if (ti->rt == 1 && ti->blank == 0)
+		return 1;
+
+	pkt_err(pd, "bad state %d-%d-%d\n", ti->rt, ti->blank, ti->packet);
+	return 0;
+}
+
+/*
+ * 1 -- we can write to this disc, 0 -- we can't
+ */
+static int pkt_writable_disc(struct pktcdvd_device *pd, disc_information *di)
+{
+	switch (pd->mmc3_profile) {
+		case 0x0a: /* CD-RW */
+		case 0xffff: /* MMC3 not supported */
+			break;
+		case 0x1a: /* DVD+RW */
+		case 0x13: /* DVD-RW */
+		case 0x12: /* DVD-RAM */
+			return 1;
+		default:
+			pkt_dbg(2, pd, "Wrong disc profile (%x)\n",
+				pd->mmc3_profile);
+			return 0;
+	}
+
+	/*
+	 * for disc type 0xff we should probably reserve a new track.
+	 * but i'm not sure, should we leave this to user apps? probably.
+	 */
+	if (di->disc_type == 0xff) {
+		pkt_notice(pd, "unknown disc - no track?\n");
+		return 0;
+	}
+
+	if (di->disc_type != 0x20 && di->disc_type != 0) {
+		pkt_err(pd, "wrong disc type (%x)\n", di->disc_type);
+		return 0;
+	}
+
+	if (di->erasable == 0) {
+		pkt_notice(pd, "disc not erasable\n");
+		return 0;
+	}
+
+	if (di->border_status == PACKET_SESSION_RESERVED) {
+		pkt_err(pd, "can't write to last track (reserved)\n");
+		return 0;
+	}
+
+	return 1;
+}
+
+static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd)
+{
+	struct packet_command cgc;
+	unsigned char buf[12];
+	disc_information di;
+	track_information ti;
+	int ret, track;
+
+	init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_READ);
+	cgc.cmd[0] = GPCMD_GET_CONFIGURATION;
+	cgc.cmd[8] = 8;
+	ret = pkt_generic_packet(pd, &cgc);
+	pd->mmc3_profile = ret ? 0xffff : buf[6] << 8 | buf[7];
+
+	memset(&di, 0, sizeof(disc_information));
+	memset(&ti, 0, sizeof(track_information));
+
+	ret = pkt_get_disc_info(pd, &di);
+	if (ret) {
+		pkt_err(pd, "failed get_disc\n");
+		return ret;
+	}
+
+	if (!pkt_writable_disc(pd, &di))
+		return -EROFS;
+
+	pd->type = di.erasable ? PACKET_CDRW : PACKET_CDR;
+
+	track = 1; /* (di.last_track_msb << 8) | di.last_track_lsb; */
+	ret = pkt_get_track_info(pd, track, 1, &ti);
+	if (ret) {
+		pkt_err(pd, "failed get_track\n");
+		return ret;
+	}
+
+	if (!pkt_writable_track(pd, &ti)) {
+		pkt_err(pd, "can't write to this track\n");
+		return -EROFS;
+	}
+
+	/*
+	 * we keep packet size in 512 byte units, makes it easier to
+	 * deal with request calculations.
+	 */
+	pd->settings.size = be32_to_cpu(ti.fixed_packet_size) << 2;
+	if (pd->settings.size == 0) {
+		pkt_notice(pd, "detected zero packet size!\n");
+		return -ENXIO;
+	}
+	if (pd->settings.size > PACKET_MAX_SECTORS) {
+		pkt_err(pd, "packet size is too big\n");
+		return -EROFS;
+	}
+	pd->settings.fp = ti.fp;
+	pd->offset = (be32_to_cpu(ti.track_start) << 2) & (pd->settings.size - 1);
+
+	if (ti.nwa_v) {
+		pd->nwa = be32_to_cpu(ti.next_writable);
+		set_bit(PACKET_NWA_VALID, &pd->flags);
+	}
+
+	/*
+	 * in theory we could use lra on -RW media as well and just zero
+	 * blocks that haven't been written yet, but in practice that
+	 * is just a no-go. we'll use that for -R, naturally.
+	 */
+	if (ti.lra_v) {
+		pd->lra = be32_to_cpu(ti.last_rec_address);
+		set_bit(PACKET_LRA_VALID, &pd->flags);
+	} else {
+		pd->lra = 0xffffffff;
+		set_bit(PACKET_LRA_VALID, &pd->flags);
+	}
+
+	/*
+	 * fine for now
+	 */
+	pd->settings.link_loss = 7;
+	pd->settings.write_type = 0;	/* packet */
+	pd->settings.track_mode = ti.track_mode;
+
+	/*
+	 * mode1 or mode2 disc
+	 */
+	switch (ti.data_mode) {
+		case PACKET_MODE1:
+			pd->settings.block_mode = PACKET_BLOCK_MODE1;
+			break;
+		case PACKET_MODE2:
+			pd->settings.block_mode = PACKET_BLOCK_MODE2;
+			break;
+		default:
+			pkt_err(pd, "unknown data mode\n");
+			return -EROFS;
+	}
+	return 0;
+}
+
+/*
+ * enable/disable write caching on drive
+ */
+static noinline_for_stack int pkt_write_caching(struct pktcdvd_device *pd,
+						int set)
+{
+	struct packet_command cgc;
+	struct scsi_sense_hdr sshdr;
+	unsigned char buf[64];
+	int ret;
+
+	init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_READ);
+	cgc.sshdr = &sshdr;
+	cgc.buflen = pd->mode_offset + 12;
+
+	/*
+	 * caching mode page might not be there, so quiet this command
+	 */
+	cgc.quiet = 1;
+
+	ret = pkt_mode_sense(pd, &cgc, GPMODE_WCACHING_PAGE, 0);
+	if (ret)
+		return ret;
+
+	buf[pd->mode_offset + 10] |= (!!set << 2);
+
+	cgc.buflen = cgc.cmd[8] = 2 + ((buf[0] << 8) | (buf[1] & 0xff));
+	ret = pkt_mode_select(pd, &cgc);
+	if (ret) {
+		pkt_err(pd, "write caching control failed\n");
+		pkt_dump_sense(pd, &cgc);
+	} else if (!ret && set)
+		pkt_notice(pd, "enabled write caching\n");
+	return ret;
+}
+
+static int pkt_lock_door(struct pktcdvd_device *pd, int lockflag)
+{
+	struct packet_command cgc;
+
+	init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
+	cgc.cmd[0] = GPCMD_PREVENT_ALLOW_MEDIUM_REMOVAL;
+	cgc.cmd[4] = lockflag ? 1 : 0;
+	return pkt_generic_packet(pd, &cgc);
+}
+
+/*
+ * Returns drive maximum write speed
+ */
+static noinline_for_stack int pkt_get_max_speed(struct pktcdvd_device *pd,
+						unsigned *write_speed)
+{
+	struct packet_command cgc;
+	struct scsi_sense_hdr sshdr;
+	unsigned char buf[256+18];
+	unsigned char *cap_buf;
+	int ret, offset;
+
+	cap_buf = &buf[sizeof(struct mode_page_header) + pd->mode_offset];
+	init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_UNKNOWN);
+	cgc.sshdr = &sshdr;
+
+	ret = pkt_mode_sense(pd, &cgc, GPMODE_CAPABILITIES_PAGE, 0);
+	if (ret) {
+		cgc.buflen = pd->mode_offset + cap_buf[1] + 2 +
+			     sizeof(struct mode_page_header);
+		ret = pkt_mode_sense(pd, &cgc, GPMODE_CAPABILITIES_PAGE, 0);
+		if (ret) {
+			pkt_dump_sense(pd, &cgc);
+			return ret;
+		}
+	}
+
+	offset = 20;			    /* Obsoleted field, used by older drives */
+	if (cap_buf[1] >= 28)
+		offset = 28;		    /* Current write speed selected */
+	if (cap_buf[1] >= 30) {
+		/* If the drive reports at least one "Logical Unit Write
+		 * Speed Performance Descriptor Block", use the information
+		 * in the first block. (contains the highest speed)
+		 */
+		int num_spdb = (cap_buf[30] << 8) + cap_buf[31];
+		if (num_spdb > 0)
+			offset = 34;
+	}
+
+	*write_speed = (cap_buf[offset] << 8) | cap_buf[offset + 1];
+	return 0;
+}
+
+/* These tables from cdrecord - I don't have orange book */
+/* standard speed CD-RW (1-4x) */
+static char clv_to_speed[16] = {
+	/* 0  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 */
+	   0, 2, 4, 6, 8, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
+};
+/* high speed CD-RW (-10x) */
+static char hs_clv_to_speed[16] = {
+	/* 0  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 */
+	   0, 2, 4, 6, 10, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
+};
+/* ultra high speed CD-RW */
+static char us_clv_to_speed[16] = {
+	/* 0  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 */
+	   0, 2, 4, 8, 0, 0,16, 0,24,32,40,48, 0, 0, 0, 0
+};
+
+/*
+ * reads the maximum media speed from ATIP
+ */
+static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd,
+						unsigned *speed)
+{
+	struct packet_command cgc;
+	struct scsi_sense_hdr sshdr;
+	unsigned char buf[64];
+	unsigned int size, st, sp;
+	int ret;
+
+	init_cdrom_command(&cgc, buf, 2, CGC_DATA_READ);
+	cgc.sshdr = &sshdr;
+	cgc.cmd[0] = GPCMD_READ_TOC_PMA_ATIP;
+	cgc.cmd[1] = 2;
+	cgc.cmd[2] = 4; /* READ ATIP */
+	cgc.cmd[8] = 2;
+	ret = pkt_generic_packet(pd, &cgc);
+	if (ret) {
+		pkt_dump_sense(pd, &cgc);
+		return ret;
+	}
+	size = ((unsigned int) buf[0]<<8) + buf[1] + 2;
+	if (size > sizeof(buf))
+		size = sizeof(buf);
+
+	init_cdrom_command(&cgc, buf, size, CGC_DATA_READ);
+	cgc.sshdr = &sshdr;
+	cgc.cmd[0] = GPCMD_READ_TOC_PMA_ATIP;
+	cgc.cmd[1] = 2;
+	cgc.cmd[2] = 4;
+	cgc.cmd[8] = size;
+	ret = pkt_generic_packet(pd, &cgc);
+	if (ret) {
+		pkt_dump_sense(pd, &cgc);
+		return ret;
+	}
+
+	if (!(buf[6] & 0x40)) {
+		pkt_notice(pd, "disc type is not CD-RW\n");
+		return 1;
+	}
+	if (!(buf[6] & 0x4)) {
+		pkt_notice(pd, "A1 values on media are not valid, maybe not CDRW?\n");
+		return 1;
+	}
+
+	st = (buf[6] >> 3) & 0x7; /* disc sub-type */
+
+	sp = buf[16] & 0xf; /* max speed from ATIP A1 field */
+
+	/* Info from cdrecord */
+	switch (st) {
+		case 0: /* standard speed */
+			*speed = clv_to_speed[sp];
+			break;
+		case 1: /* high speed */
+			*speed = hs_clv_to_speed[sp];
+			break;
+		case 2: /* ultra high speed */
+			*speed = us_clv_to_speed[sp];
+			break;
+		default:
+			pkt_notice(pd, "unknown disc sub-type %d\n", st);
+			return 1;
+	}
+	if (*speed) {
+		pkt_info(pd, "maximum media speed: %d\n", *speed);
+		return 0;
+	} else {
+		pkt_notice(pd, "unknown speed %d for sub-type %d\n", sp, st);
+		return 1;
+	}
+}
+
+static noinline_for_stack int pkt_perform_opc(struct pktcdvd_device *pd)
+{
+	struct packet_command cgc;
+	struct scsi_sense_hdr sshdr;
+	int ret;
+
+	pkt_dbg(2, pd, "Performing OPC\n");
+
+	init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
+	cgc.sshdr = &sshdr;
+	cgc.timeout = 60*HZ;
+	cgc.cmd[0] = GPCMD_SEND_OPC;
+	cgc.cmd[1] = 1;
+	ret = pkt_generic_packet(pd, &cgc);
+	if (ret)
+		pkt_dump_sense(pd, &cgc);
+	return ret;
+}
+
+static int pkt_open_write(struct pktcdvd_device *pd)
+{
+	int ret;
+	unsigned int write_speed, media_write_speed, read_speed;
+
+	ret = pkt_probe_settings(pd);
+	if (ret) {
+		pkt_dbg(2, pd, "failed probe\n");
+		return ret;
+	}
+
+	ret = pkt_set_write_settings(pd);
+	if (ret) {
+		pkt_dbg(1, pd, "failed saving write settings\n");
+		return -EIO;
+	}
+
+	pkt_write_caching(pd, USE_WCACHING);
+
+	ret = pkt_get_max_speed(pd, &write_speed);
+	if (ret)
+		write_speed = 16 * 177;
+	switch (pd->mmc3_profile) {
+		case 0x13: /* DVD-RW */
+		case 0x1a: /* DVD+RW */
+		case 0x12: /* DVD-RAM */
+			pkt_dbg(1, pd, "write speed %ukB/s\n", write_speed);
+			break;
+		default:
+			ret = pkt_media_speed(pd, &media_write_speed);
+			if (ret)
+				media_write_speed = 16;
+			write_speed = min(write_speed, media_write_speed * 177);
+			pkt_dbg(1, pd, "write speed %ux\n", write_speed / 176);
+			break;
+	}
+	read_speed = write_speed;
+
+	ret = pkt_set_speed(pd, write_speed, read_speed);
+	if (ret) {
+		pkt_dbg(1, pd, "couldn't set write speed\n");
+		return -EIO;
+	}
+	pd->write_speed = write_speed;
+	pd->read_speed = read_speed;
+
+	ret = pkt_perform_opc(pd);
+	if (ret) {
+		pkt_dbg(1, pd, "Optimum Power Calibration failed\n");
+	}
+
+	return 0;
+}
+
+/*
+ * called at open time.
+ */
+static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write)
+{
+	int ret;
+	long lba;
+	struct request_queue *q;
+	struct block_device *bdev;
+
+	/*
+	 * We need to re-open the cdrom device without O_NONBLOCK to be able
+	 * to read/write from/to it. It is already opened in O_NONBLOCK mode
+	 * so open should not fail.
+	 */
+	bdev = blkdev_get_by_dev(pd->bdev->bd_dev, FMODE_READ | FMODE_EXCL, pd);
+	if (IS_ERR(bdev)) {
+		ret = PTR_ERR(bdev);
+		goto out;
+	}
+
+	ret = pkt_get_last_written(pd, &lba);
+	if (ret) {
+		pkt_err(pd, "pkt_get_last_written failed\n");
+		goto out_putdev;
+	}
+
+	set_capacity(pd->disk, lba << 2);
+	set_capacity_and_notify(pd->bdev->bd_disk, lba << 2);
+
+	q = bdev_get_queue(pd->bdev);
+	if (write) {
+		ret = pkt_open_write(pd);
+		if (ret)
+			goto out_putdev;
+		/*
+		 * Some CDRW drives can not handle writes larger than one packet,
+		 * even if the size is a multiple of the packet size.
+		 */
+		blk_queue_max_hw_sectors(q, pd->settings.size);
+		set_bit(PACKET_WRITABLE, &pd->flags);
+	} else {
+		pkt_set_speed(pd, MAX_SPEED, MAX_SPEED);
+		clear_bit(PACKET_WRITABLE, &pd->flags);
+	}
+
+	ret = pkt_set_segment_merging(pd, q);
+	if (ret)
+		goto out_putdev;
+
+	if (write) {
+		if (!pkt_grow_pktlist(pd, CONFIG_CDROM_PKTCDVD_BUFFERS)) {
+			pkt_err(pd, "not enough memory for buffers\n");
+			ret = -ENOMEM;
+			goto out_putdev;
+		}
+		pkt_info(pd, "%lukB available on disc\n", lba << 1);
+	}
+
+	return 0;
+
+out_putdev:
+	blkdev_put(bdev, FMODE_READ | FMODE_EXCL);
+out:
+	return ret;
+}
+
+/*
+ * called when the device is closed. makes sure that the device flushes
+ * the internal cache before we close.
+ */
+static void pkt_release_dev(struct pktcdvd_device *pd, int flush)
+{
+	if (flush && pkt_flush_cache(pd))
+		pkt_dbg(1, pd, "not flushing cache\n");
+
+	pkt_lock_door(pd, 0);
+
+	pkt_set_speed(pd, MAX_SPEED, MAX_SPEED);
+	blkdev_put(pd->bdev, FMODE_READ | FMODE_EXCL);
+
+	pkt_shrink_pktlist(pd);
+}
+
+static struct pktcdvd_device *pkt_find_dev_from_minor(unsigned int dev_minor)
+{
+	if (dev_minor >= MAX_WRITERS)
+		return NULL;
+
+	dev_minor = array_index_nospec(dev_minor, MAX_WRITERS);
+	return pkt_devs[dev_minor];
+}
+
+static int pkt_open(struct block_device *bdev, fmode_t mode)
+{
+	struct pktcdvd_device *pd = NULL;
+	int ret;
+
+	mutex_lock(&pktcdvd_mutex);
+	mutex_lock(&ctl_mutex);
+	pd = pkt_find_dev_from_minor(MINOR(bdev->bd_dev));
+	if (!pd) {
+		ret = -ENODEV;
+		goto out;
+	}
+	BUG_ON(pd->refcnt < 0);
+
+	pd->refcnt++;
+	if (pd->refcnt > 1) {
+		if ((mode & FMODE_WRITE) &&
+		    !test_bit(PACKET_WRITABLE, &pd->flags)) {
+			ret = -EBUSY;
+			goto out_dec;
+		}
+	} else {
+		ret = pkt_open_dev(pd, mode & FMODE_WRITE);
+		if (ret)
+			goto out_dec;
+		/*
+		 * needed here as well, since ext2 (among others) may change
+		 * the blocksize at mount time
+		 */
+		set_blocksize(bdev, CD_FRAMESIZE);
+	}
+
+	mutex_unlock(&ctl_mutex);
+	mutex_unlock(&pktcdvd_mutex);
+	return 0;
+
+out_dec:
+	pd->refcnt--;
+out:
+	mutex_unlock(&ctl_mutex);
+	mutex_unlock(&pktcdvd_mutex);
+	return ret;
+}
+
+static void pkt_close(struct gendisk *disk, fmode_t mode)
+{
+	struct pktcdvd_device *pd = disk->private_data;
+
+	mutex_lock(&pktcdvd_mutex);
+	mutex_lock(&ctl_mutex);
+	pd->refcnt--;
+	BUG_ON(pd->refcnt < 0);
+	if (pd->refcnt == 0) {
+		int flush = test_bit(PACKET_WRITABLE, &pd->flags);
+		pkt_release_dev(pd, flush);
+	}
+	mutex_unlock(&ctl_mutex);
+	mutex_unlock(&pktcdvd_mutex);
+}
+
+
+static void pkt_end_io_read_cloned(struct bio *bio)
+{
+	struct packet_stacked_data *psd = bio->bi_private;
+	struct pktcdvd_device *pd = psd->pd;
+
+	psd->bio->bi_status = bio->bi_status;
+	bio_put(bio);
+	bio_endio(psd->bio);
+	mempool_free(psd, &psd_pool);
+	pkt_bio_finished(pd);
+}
+
+static void pkt_make_request_read(struct pktcdvd_device *pd, struct bio *bio)
+{
+	struct bio *cloned_bio =
+		bio_alloc_clone(pd->bdev, bio, GFP_NOIO, &pkt_bio_set);
+	struct packet_stacked_data *psd = mempool_alloc(&psd_pool, GFP_NOIO);
+
+	psd->pd = pd;
+	psd->bio = bio;
+	cloned_bio->bi_private = psd;
+	cloned_bio->bi_end_io = pkt_end_io_read_cloned;
+	pd->stats.secs_r += bio_sectors(bio);
+	pkt_queue_bio(pd, cloned_bio);
+}
+
+static void pkt_make_request_write(struct request_queue *q, struct bio *bio)
+{
+	struct pktcdvd_device *pd = q->queuedata;
+	sector_t zone;
+	struct packet_data *pkt;
+	int was_empty, blocked_bio;
+	struct pkt_rb_node *node;
+
+	zone = get_zone(bio->bi_iter.bi_sector, pd);
+
+	/*
+	 * If we find a matching packet in state WAITING or READ_WAIT, we can
+	 * just append this bio to that packet.
+	 */
+	spin_lock(&pd->cdrw.active_list_lock);
+	blocked_bio = 0;
+	list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
+		if (pkt->sector == zone) {
+			spin_lock(&pkt->lock);
+			if ((pkt->state == PACKET_WAITING_STATE) ||
+			    (pkt->state == PACKET_READ_WAIT_STATE)) {
+				bio_list_add(&pkt->orig_bios, bio);
+				pkt->write_size +=
+					bio->bi_iter.bi_size / CD_FRAMESIZE;
+				if ((pkt->write_size >= pkt->frames) &&
+				    (pkt->state == PACKET_WAITING_STATE)) {
+					atomic_inc(&pkt->run_sm);
+					wake_up(&pd->wqueue);
+				}
+				spin_unlock(&pkt->lock);
+				spin_unlock(&pd->cdrw.active_list_lock);
+				return;
+			} else {
+				blocked_bio = 1;
+			}
+			spin_unlock(&pkt->lock);
+		}
+	}
+	spin_unlock(&pd->cdrw.active_list_lock);
+
+	/*
+	 * Test if there is enough room left in the bio work queue
+	 * (queue size >= congestion on mark).
+	 * If not, wait till the work queue size is below the congestion off mark.
+	 */
+	spin_lock(&pd->lock);
+	if (pd->write_congestion_on > 0
+	    && pd->bio_queue_size >= pd->write_congestion_on) {
+		struct wait_bit_queue_entry wqe;
+
+		init_wait_var_entry(&wqe, &pd->congested, 0);
+		for (;;) {
+			prepare_to_wait_event(__var_waitqueue(&pd->congested),
+					      &wqe.wq_entry,
+					      TASK_UNINTERRUPTIBLE);
+			if (pd->bio_queue_size <= pd->write_congestion_off)
+				break;
+			pd->congested = true;
+			spin_unlock(&pd->lock);
+			schedule();
+			spin_lock(&pd->lock);
+		}
+	}
+	spin_unlock(&pd->lock);
+
+	/*
+	 * No matching packet found. Store the bio in the work queue.
+	 */
+	node = mempool_alloc(&pd->rb_pool, GFP_NOIO);
+	node->bio = bio;
+	spin_lock(&pd->lock);
+	BUG_ON(pd->bio_queue_size < 0);
+	was_empty = (pd->bio_queue_size == 0);
+	pkt_rbtree_insert(pd, node);
+	spin_unlock(&pd->lock);
+
+	/*
+	 * Wake up the worker thread.
+	 */
+	atomic_set(&pd->scan_queue, 1);
+	if (was_empty) {
+		/* This wake_up is required for correct operation */
+		wake_up(&pd->wqueue);
+	} else if (!list_empty(&pd->cdrw.pkt_free_list) && !blocked_bio) {
+		/*
+		 * This wake up is not required for correct operation,
+		 * but improves performance in some cases.
+		 */
+		wake_up(&pd->wqueue);
+	}
+}
+
+static void pkt_submit_bio(struct bio *bio)
+{
+	struct pktcdvd_device *pd = bio->bi_bdev->bd_disk->queue->queuedata;
+	struct bio *split;
+
+	bio = bio_split_to_limits(bio);
+
+	pkt_dbg(2, pd, "start = %6llx stop = %6llx\n",
+		(unsigned long long)bio->bi_iter.bi_sector,
+		(unsigned long long)bio_end_sector(bio));
+
+	/*
+	 * Clone READ bios so we can have our own bi_end_io callback.
+	 */
+	if (bio_data_dir(bio) == READ) {
+		pkt_make_request_read(pd, bio);
+		return;
+	}
+
+	if (!test_bit(PACKET_WRITABLE, &pd->flags)) {
+		pkt_notice(pd, "WRITE for ro device (%llu)\n",
+			   (unsigned long long)bio->bi_iter.bi_sector);
+		goto end_io;
+	}
+
+	if (!bio->bi_iter.bi_size || (bio->bi_iter.bi_size % CD_FRAMESIZE)) {
+		pkt_err(pd, "wrong bio size\n");
+		goto end_io;
+	}
+
+	do {
+		sector_t zone = get_zone(bio->bi_iter.bi_sector, pd);
+		sector_t last_zone = get_zone(bio_end_sector(bio) - 1, pd);
+
+		if (last_zone != zone) {
+			BUG_ON(last_zone != zone + pd->settings.size);
+
+			split = bio_split(bio, last_zone -
+					  bio->bi_iter.bi_sector,
+					  GFP_NOIO, &pkt_bio_set);
+			bio_chain(split, bio);
+		} else {
+			split = bio;
+		}
+
+		pkt_make_request_write(bio->bi_bdev->bd_disk->queue, split);
+	} while (split != bio);
+
+	return;
+end_io:
+	bio_io_error(bio);
+}
+
+static void pkt_init_queue(struct pktcdvd_device *pd)
+{
+	struct request_queue *q = pd->disk->queue;
+
+	blk_queue_logical_block_size(q, CD_FRAMESIZE);
+	blk_queue_max_hw_sectors(q, PACKET_MAX_SECTORS);
+	q->queuedata = pd;
+}
+
+static int pkt_seq_show(struct seq_file *m, void *p)
+{
+	struct pktcdvd_device *pd = m->private;
+	char *msg;
+	int states[PACKET_NUM_STATES];
+
+	seq_printf(m, "Writer %s mapped to %pg:\n", pd->name, pd->bdev);
+
+	seq_printf(m, "\nSettings:\n");
+	seq_printf(m, "\tpacket size:\t\t%dkB\n", pd->settings.size / 2);
+
+	if (pd->settings.write_type == 0)
+		msg = "Packet";
+	else
+		msg = "Unknown";
+	seq_printf(m, "\twrite type:\t\t%s\n", msg);
+
+	seq_printf(m, "\tpacket type:\t\t%s\n", pd->settings.fp ? "Fixed" : "Variable");
+	seq_printf(m, "\tlink loss:\t\t%d\n", pd->settings.link_loss);
+
+	seq_printf(m, "\ttrack mode:\t\t%d\n", pd->settings.track_mode);
+
+	if (pd->settings.block_mode == PACKET_BLOCK_MODE1)
+		msg = "Mode 1";
+	else if (pd->settings.block_mode == PACKET_BLOCK_MODE2)
+		msg = "Mode 2";
+	else
+		msg = "Unknown";
+	seq_printf(m, "\tblock mode:\t\t%s\n", msg);
+
+	seq_printf(m, "\nStatistics:\n");
+	seq_printf(m, "\tpackets started:\t%lu\n", pd->stats.pkt_started);
+	seq_printf(m, "\tpackets ended:\t\t%lu\n", pd->stats.pkt_ended);
+	seq_printf(m, "\twritten:\t\t%lukB\n", pd->stats.secs_w >> 1);
+	seq_printf(m, "\tread gather:\t\t%lukB\n", pd->stats.secs_rg >> 1);
+	seq_printf(m, "\tread:\t\t\t%lukB\n", pd->stats.secs_r >> 1);
+
+	seq_printf(m, "\nMisc:\n");
+	seq_printf(m, "\treference count:\t%d\n", pd->refcnt);
+	seq_printf(m, "\tflags:\t\t\t0x%lx\n", pd->flags);
+	seq_printf(m, "\tread speed:\t\t%ukB/s\n", pd->read_speed);
+	seq_printf(m, "\twrite speed:\t\t%ukB/s\n", pd->write_speed);
+	seq_printf(m, "\tstart offset:\t\t%lu\n", pd->offset);
+	seq_printf(m, "\tmode page offset:\t%u\n", pd->mode_offset);
+
+	seq_printf(m, "\nQueue state:\n");
+	seq_printf(m, "\tbios queued:\t\t%d\n", pd->bio_queue_size);
+	seq_printf(m, "\tbios pending:\t\t%d\n", atomic_read(&pd->cdrw.pending_bios));
+	seq_printf(m, "\tcurrent sector:\t\t0x%llx\n", (unsigned long long)pd->current_sector);
+
+	pkt_count_states(pd, states);
+	seq_printf(m, "\tstate:\t\t\ti:%d ow:%d rw:%d ww:%d rec:%d fin:%d\n",
+		   states[0], states[1], states[2], states[3], states[4], states[5]);
+
+	seq_printf(m, "\twrite congestion marks:\toff=%d on=%d\n",
+			pd->write_congestion_off,
+			pd->write_congestion_on);
+	return 0;
+}
+
+static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
+{
+	int i;
+	struct block_device *bdev;
+	struct scsi_device *sdev;
+
+	if (pd->pkt_dev == dev) {
+		pkt_err(pd, "recursive setup not allowed\n");
+		return -EBUSY;
+	}
+	for (i = 0; i < MAX_WRITERS; i++) {
+		struct pktcdvd_device *pd2 = pkt_devs[i];
+		if (!pd2)
+			continue;
+		if (pd2->bdev->bd_dev == dev) {
+			pkt_err(pd, "%pg already setup\n", pd2->bdev);
+			return -EBUSY;
+		}
+		if (pd2->pkt_dev == dev) {
+			pkt_err(pd, "can't chain pktcdvd devices\n");
+			return -EBUSY;
+		}
+	}
+
+	bdev = blkdev_get_by_dev(dev, FMODE_READ | FMODE_NDELAY, NULL);
+	if (IS_ERR(bdev))
+		return PTR_ERR(bdev);
+	sdev = scsi_device_from_queue(bdev->bd_disk->queue);
+	if (!sdev) {
+		blkdev_put(bdev, FMODE_READ | FMODE_NDELAY);
+		return -EINVAL;
+	}
+	put_device(&sdev->sdev_gendev);
+
+	/* This is safe, since we have a reference from open(). */
+	__module_get(THIS_MODULE);
+
+	pd->bdev = bdev;
+	set_blocksize(bdev, CD_FRAMESIZE);
+
+	pkt_init_queue(pd);
+
+	atomic_set(&pd->cdrw.pending_bios, 0);
+	pd->cdrw.thread = kthread_run(kcdrwd, pd, "%s", pd->name);
+	if (IS_ERR(pd->cdrw.thread)) {
+		pkt_err(pd, "can't start kernel thread\n");
+		goto out_mem;
+	}
+
+	proc_create_single_data(pd->name, 0, pkt_proc, pkt_seq_show, pd);
+	pkt_dbg(1, pd, "writer mapped to %pg\n", bdev);
+	return 0;
+
+out_mem:
+	blkdev_put(bdev, FMODE_READ | FMODE_NDELAY);
+	/* This is safe: open() is still holding a reference. */
+	module_put(THIS_MODULE);
+	return -ENOMEM;
+}
+
+static int pkt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg)
+{
+	struct pktcdvd_device *pd = bdev->bd_disk->private_data;
+	int ret;
+
+	pkt_dbg(2, pd, "cmd %x, dev %d:%d\n",
+		cmd, MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev));
+
+	mutex_lock(&pktcdvd_mutex);
+	switch (cmd) {
+	case CDROMEJECT:
+		/*
+		 * The door gets locked when the device is opened, so we
+		 * have to unlock it or else the eject command fails.
+		 */
+		if (pd->refcnt == 1)
+			pkt_lock_door(pd, 0);
+		fallthrough;
+	/*
+	 * forward selected CDROM ioctls to CD-ROM, for UDF
+	 */
+	case CDROMMULTISESSION:
+	case CDROMREADTOCENTRY:
+	case CDROM_LAST_WRITTEN:
+	case CDROM_SEND_PACKET:
+	case SCSI_IOCTL_SEND_COMMAND:
+		if (!bdev->bd_disk->fops->ioctl)
+			ret = -ENOTTY;
+		else
+			ret = bdev->bd_disk->fops->ioctl(bdev, mode, cmd, arg);
+		break;
+	default:
+		pkt_dbg(2, pd, "Unknown ioctl (%x)\n", cmd);
+		ret = -ENOTTY;
+	}
+	mutex_unlock(&pktcdvd_mutex);
+
+	return ret;
+}
+
+static unsigned int pkt_check_events(struct gendisk *disk,
+				     unsigned int clearing)
+{
+	struct pktcdvd_device *pd = disk->private_data;
+	struct gendisk *attached_disk;
+
+	if (!pd)
+		return 0;
+	if (!pd->bdev)
+		return 0;
+	attached_disk = pd->bdev->bd_disk;
+	if (!attached_disk || !attached_disk->fops->check_events)
+		return 0;
+	return attached_disk->fops->check_events(attached_disk, clearing);
+}
+
+static char *pkt_devnode(struct gendisk *disk, umode_t *mode)
+{
+	return kasprintf(GFP_KERNEL, "pktcdvd/%s", disk->disk_name);
+}
+
+static const struct block_device_operations pktcdvd_ops = {
+	.owner =		THIS_MODULE,
+	.submit_bio =		pkt_submit_bio,
+	.open =			pkt_open,
+	.release =		pkt_close,
+	.ioctl =		pkt_ioctl,
+	.compat_ioctl =		blkdev_compat_ptr_ioctl,
+	.check_events =		pkt_check_events,
+	.devnode =		pkt_devnode,
+};
+
+/*
+ * Set up mapping from pktcdvd device to CD-ROM device.
+ */
+static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
+{
+	int idx;
+	int ret = -ENOMEM;
+	struct pktcdvd_device *pd;
+	struct gendisk *disk;
+
+	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+	for (idx = 0; idx < MAX_WRITERS; idx++)
+		if (!pkt_devs[idx])
+			break;
+	if (idx == MAX_WRITERS) {
+		pr_err("max %d writers supported\n", MAX_WRITERS);
+		ret = -EBUSY;
+		goto out_mutex;
+	}
+
+	pd = kzalloc(sizeof(struct pktcdvd_device), GFP_KERNEL);
+	if (!pd)
+		goto out_mutex;
+
+	ret = mempool_init_kmalloc_pool(&pd->rb_pool, PKT_RB_POOL_SIZE,
+					sizeof(struct pkt_rb_node));
+	if (ret)
+		goto out_mem;
+
+	INIT_LIST_HEAD(&pd->cdrw.pkt_free_list);
+	INIT_LIST_HEAD(&pd->cdrw.pkt_active_list);
+	spin_lock_init(&pd->cdrw.active_list_lock);
+
+	spin_lock_init(&pd->lock);
+	spin_lock_init(&pd->iosched.lock);
+	bio_list_init(&pd->iosched.read_queue);
+	bio_list_init(&pd->iosched.write_queue);
+	sprintf(pd->name, DRIVER_NAME"%d", idx);
+	init_waitqueue_head(&pd->wqueue);
+	pd->bio_queue = RB_ROOT;
+
+	pd->write_congestion_on  = write_congestion_on;
+	pd->write_congestion_off = write_congestion_off;
+
+	ret = -ENOMEM;
+	disk = blk_alloc_disk(NUMA_NO_NODE);
+	if (!disk)
+		goto out_mem;
+	pd->disk = disk;
+	disk->major = pktdev_major;
+	disk->first_minor = idx;
+	disk->minors = 1;
+	disk->fops = &pktcdvd_ops;
+	disk->flags = GENHD_FL_REMOVABLE | GENHD_FL_NO_PART;
+	strcpy(disk->disk_name, pd->name);
+	disk->private_data = pd;
+
+	pd->pkt_dev = MKDEV(pktdev_major, idx);
+	ret = pkt_new_dev(pd, dev);
+	if (ret)
+		goto out_mem2;
+
+	/* inherit events of the host device */
+	disk->events = pd->bdev->bd_disk->events;
+
+	ret = add_disk(disk);
+	if (ret)
+		goto out_mem2;
+
+	pkt_sysfs_dev_new(pd);
+	pkt_debugfs_dev_new(pd);
+
+	pkt_devs[idx] = pd;
+	if (pkt_dev)
+		*pkt_dev = pd->pkt_dev;
+
+	mutex_unlock(&ctl_mutex);
+	return 0;
+
+out_mem2:
+	put_disk(disk);
+out_mem:
+	mempool_exit(&pd->rb_pool);
+	kfree(pd);
+out_mutex:
+	mutex_unlock(&ctl_mutex);
+	pr_err("setup of pktcdvd device failed\n");
+	return ret;
+}
+
+/*
+ * Tear down mapping from pktcdvd device to CD-ROM device.
+ */
+static int pkt_remove_dev(dev_t pkt_dev)
+{
+	struct pktcdvd_device *pd;
+	int idx;
+	int ret = 0;
+
+	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+	for (idx = 0; idx < MAX_WRITERS; idx++) {
+		pd = pkt_devs[idx];
+		if (pd && (pd->pkt_dev == pkt_dev))
+			break;
+	}
+	if (idx == MAX_WRITERS) {
+		pr_debug("dev not setup\n");
+		ret = -ENXIO;
+		goto out;
+	}
+
+	if (pd->refcnt > 0) {
+		ret = -EBUSY;
+		goto out;
+	}
+	if (!IS_ERR(pd->cdrw.thread))
+		kthread_stop(pd->cdrw.thread);
+
+	pkt_devs[idx] = NULL;
+
+	pkt_debugfs_dev_remove(pd);
+	pkt_sysfs_dev_remove(pd);
+
+	blkdev_put(pd->bdev, FMODE_READ | FMODE_NDELAY);
+
+	remove_proc_entry(pd->name, pkt_proc);
+	pkt_dbg(1, pd, "writer unmapped\n");
+
+	del_gendisk(pd->disk);
+	put_disk(pd->disk);
+
+	mempool_exit(&pd->rb_pool);
+	kfree(pd);
+
+	/* This is safe: open() is still holding a reference. */
+	module_put(THIS_MODULE);
+
+out:
+	mutex_unlock(&ctl_mutex);
+	return ret;
+}
+
+static void pkt_get_status(struct pkt_ctrl_command *ctrl_cmd)
+{
+	struct pktcdvd_device *pd;
+
+	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
+
+	pd = pkt_find_dev_from_minor(ctrl_cmd->dev_index);
+	if (pd) {
+		ctrl_cmd->dev = new_encode_dev(pd->bdev->bd_dev);
+		ctrl_cmd->pkt_dev = new_encode_dev(pd->pkt_dev);
+	} else {
+		ctrl_cmd->dev = 0;
+		ctrl_cmd->pkt_dev = 0;
+	}
+	ctrl_cmd->num_devices = MAX_WRITERS;
+
+	mutex_unlock(&ctl_mutex);
+}
+
+static long pkt_ctl_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	void __user *argp = (void __user *)arg;
+	struct pkt_ctrl_command ctrl_cmd;
+	int ret = 0;
+	dev_t pkt_dev = 0;
+
+	if (cmd != PACKET_CTRL_CMD)
+		return -ENOTTY;
+
+	if (copy_from_user(&ctrl_cmd, argp, sizeof(struct pkt_ctrl_command)))
+		return -EFAULT;
+
+	switch (ctrl_cmd.command) {
+	case PKT_CTRL_CMD_SETUP:
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+		ret = pkt_setup_dev(new_decode_dev(ctrl_cmd.dev), &pkt_dev);
+		ctrl_cmd.pkt_dev = new_encode_dev(pkt_dev);
+		break;
+	case PKT_CTRL_CMD_TEARDOWN:
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+		ret = pkt_remove_dev(new_decode_dev(ctrl_cmd.pkt_dev));
+		break;
+	case PKT_CTRL_CMD_STATUS:
+		pkt_get_status(&ctrl_cmd);
+		break;
+	default:
+		return -ENOTTY;
+	}
+
+	if (copy_to_user(argp, &ctrl_cmd, sizeof(struct pkt_ctrl_command)))
+		return -EFAULT;
+	return ret;
+}
+
+#ifdef CONFIG_COMPAT
+static long pkt_ctl_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	return pkt_ctl_ioctl(file, cmd, (unsigned long)compat_ptr(arg));
+}
+#endif
+
+static const struct file_operations pkt_ctl_fops = {
+	.open		= nonseekable_open,
+	.unlocked_ioctl	= pkt_ctl_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= pkt_ctl_compat_ioctl,
+#endif
+	.owner		= THIS_MODULE,
+	.llseek		= no_llseek,
+};
+
+static struct miscdevice pkt_misc = {
+	.minor 		= MISC_DYNAMIC_MINOR,
+	.name  		= DRIVER_NAME,
+	.nodename	= "pktcdvd/control",
+	.fops  		= &pkt_ctl_fops
+};
+
+static int __init pkt_init(void)
+{
+	int ret;
+
+	mutex_init(&ctl_mutex);
+
+	ret = mempool_init_kmalloc_pool(&psd_pool, PSD_POOL_SIZE,
+				    sizeof(struct packet_stacked_data));
+	if (ret)
+		return ret;
+	ret = bioset_init(&pkt_bio_set, BIO_POOL_SIZE, 0, 0);
+	if (ret) {
+		mempool_exit(&psd_pool);
+		return ret;
+	}
+
+	ret = register_blkdev(pktdev_major, DRIVER_NAME);
+	if (ret < 0) {
+		pr_err("unable to register block device\n");
+		goto out2;
+	}
+	if (!pktdev_major)
+		pktdev_major = ret;
+
+	ret = pkt_sysfs_init();
+	if (ret)
+		goto out;
+
+	pkt_debugfs_init();
+
+	ret = misc_register(&pkt_misc);
+	if (ret) {
+		pr_err("unable to register misc device\n");
+		goto out_misc;
+	}
+
+	pkt_proc = proc_mkdir("driver/"DRIVER_NAME, NULL);
+
+	return 0;
+
+out_misc:
+	pkt_debugfs_cleanup();
+	pkt_sysfs_cleanup();
+out:
+	unregister_blkdev(pktdev_major, DRIVER_NAME);
+out2:
+	mempool_exit(&psd_pool);
+	bioset_exit(&pkt_bio_set);
+	return ret;
+}
+
+static void __exit pkt_exit(void)
+{
+	remove_proc_entry("driver/"DRIVER_NAME, NULL);
+	misc_deregister(&pkt_misc);
+
+	pkt_debugfs_cleanup();
+	pkt_sysfs_cleanup();
+
+	unregister_blkdev(pktdev_major, DRIVER_NAME);
+	mempool_exit(&psd_pool);
+	bioset_exit(&pkt_bio_set);
+}
+
+MODULE_DESCRIPTION("Packet writing layer for CD/DVD drives");
+MODULE_AUTHOR("Jens Axboe <[e-mail]>");
+MODULE_LICENSE("GPL");
+
+module_init(pkt_init);
+module_exit(pkt_exit);

drivers/block/ps3vram.c

···
 	dev_dbg(&dev->core, "%s\n", __func__);
 
 	bio = bio_split_to_limits(bio);
+	if (!bio)
+		return;
 
 	spin_lock_irq(&priv->lock);
 	busy = !bio_list_empty(&priv->list);

drivers/block/ublk_drv.c

···
 	struct ublksrv_ctrl_cmd *header = (struct ublksrv_ctrl_cmd *)cmd->cmd;
 	int ret = -EINVAL;
 
+	if (issue_flags & IO_URING_F_NONBLOCK)
+		return -EAGAIN;
+
 	ublk_ctrl_cmd_dump(cmd);
 
 	if (!(issue_flags & IO_URING_F_SQE128))

drivers/block/virtio_blk.c

···
 		virtqueue_notify(vq->vq);
 }
 
+static blk_status_t virtblk_fail_to_queue(struct request *req, int rc)
+{
+	virtblk_cleanup_cmd(req);
+	switch (rc) {
+	case -ENOSPC:
+		return BLK_STS_DEV_RESOURCE;
+	case -ENOMEM:
+		return BLK_STS_RESOURCE;
+	default:
+		return BLK_STS_IOERR;
+	}
+}
+
 static blk_status_t virtblk_prep_rq(struct blk_mq_hw_ctx *hctx,
 					struct virtio_blk *vblk,
 					struct request *req,
 					struct virtblk_req *vbr)
 {
 	blk_status_t status;
+	int num;
 
 	status = virtblk_setup_cmd(vblk->vdev, req, vbr);
 	if (unlikely(status))
 		return status;
 
-	vbr->sg_table.nents = virtblk_map_data(hctx, req, vbr);
-	if (unlikely(vbr->sg_table.nents < 0)) {
-		virtblk_cleanup_cmd(req);
-		return BLK_STS_RESOURCE;
-	}
+	num = virtblk_map_data(hctx, req, vbr);
+	if (unlikely(num < 0))
+		return virtblk_fail_to_queue(req, -ENOMEM);
+	vbr->sg_table.nents = num;
 
 	blk_mq_start_request(req);
 
···
 			blk_mq_stop_hw_queue(hctx);
 		spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags);
 		virtblk_unmap_data(req, vbr);
-		virtblk_cleanup_cmd(req);
-		switch (err) {
-		case -ENOSPC:
-			return BLK_STS_DEV_RESOURCE;
-		case -ENOMEM:
-			return BLK_STS_RESOURCE;
-		default:
-			return BLK_STS_IOERR;
-		}
+		return virtblk_fail_to_queue(req, err);
 	}
 
 	if (bd->last && virtqueue_kick_prepare(vblk->vqs[qid].vq))
···
 	blk_queue_max_segments(q, sg_elems);
 
 	/* No real sector limit. */
-	blk_queue_max_hw_sectors(q, -1U);
+	blk_queue_max_hw_sectors(q, UINT_MAX);
 
 	max_size = virtio_max_dma_size(vdev);
 

drivers/char/tpm/tpm-interface.c

···
 	}
 
 suspended:
-	return rc;
+	if (rc)
+		dev_err(dev, "Ignoring error %d while suspending\n", rc);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(tpm_pm_suspend);
 

drivers/crypto/caam/blob_gen.c

···
 	}
 
 	ctrlpriv = dev_get_drvdata(jrdev->parent);
-	moo = FIELD_GET(CSTA_MOO, ioread32(&ctrlpriv->ctrl->perfmon.status));
+	moo = FIELD_GET(CSTA_MOO, rd_reg32(&ctrlpriv->ctrl->perfmon.status));
 	if (moo != CSTA_MOO_SECURE && moo != CSTA_MOO_TRUSTED)
 		dev_warn(jrdev,
 			 "using insecure test key, enable HAB to use unique device key!\n");

drivers/crypto/virtio/virtio_crypto_skcipher_algs.c

···
 		pr_err("virtio_crypto: Close session failed status: %u, session_id: 0x%llx\n",
 			ctrl_status->status, destroy_session->session_id);
 
-		return -EINVAL;
+		err = -EINVAL;
+		goto out;
 	}
 
 	err = 0;

drivers/dma-buf/dma-buf-sysfs-stats.c

···
 	kset_unregister(dma_buf_stats_kset);
 }
 
-int dma_buf_stats_setup(struct dma_buf *dmabuf)
+int dma_buf_stats_setup(struct dma_buf *dmabuf, struct file *file)
 {
 	struct dma_buf_sysfs_entry *sysfs_entry;
 	int ret;
-
-	if (!dmabuf || !dmabuf->file)
-		return -EINVAL;
 
 	if (!dmabuf->exp_name) {
 		pr_err("exporter name must not be empty if stats needed\n");
···
 
 	/* create the directory for buffer stats */
 	ret = kobject_init_and_add(&sysfs_entry->kobj, &dma_buf_ktype, NULL,
-				   "%lu", file_inode(dmabuf->file)->i_ino);
+				   "%lu", file_inode(file)->i_ino);
 	if (ret)
 		goto err_sysfs_dmabuf;
 

drivers/dma-buf/dma-buf-sysfs-stats.h

···
 int dma_buf_init_sysfs_statistics(void);
 void dma_buf_uninit_sysfs_statistics(void);
 
-int dma_buf_stats_setup(struct dma_buf *dmabuf);
+int dma_buf_stats_setup(struct dma_buf *dmabuf, struct file *file);
 
 void dma_buf_stats_teardown(struct dma_buf *dmabuf);
 #else
···
 
 static inline void dma_buf_uninit_sysfs_statistics(void) {}
 
-static inline int dma_buf_stats_setup(struct dma_buf *dmabuf)
+static inline int dma_buf_stats_setup(struct dma_buf *dmabuf, struct file *file)
 {
 	return 0;
 }

drivers/dma-buf/dma-buf.c

···
 		return -EINVAL;
 
 	dmabuf = file->private_data;
-
-	mutex_lock(&db_list.lock);
-	list_del(&dmabuf->list_node);
-	mutex_unlock(&db_list.lock);
+	if (dmabuf) {
+		mutex_lock(&db_list.lock);
+		list_del(&dmabuf->list_node);
+		mutex_unlock(&db_list.lock);
+	}
 
 	return 0;
 }
···
 	return file->f_op == &dma_buf_fops;
 }
 
-static struct file *dma_buf_getfile(struct dma_buf *dmabuf, int flags)
+static struct file *dma_buf_getfile(size_t size, int flags)
 {
 	static atomic64_t dmabuf_inode = ATOMIC64_INIT(0);
-	struct file *file;
 	struct inode *inode = alloc_anon_inode(dma_buf_mnt->mnt_sb);
+	struct file *file;
 
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
 
-	inode->i_size = dmabuf->size;
-	inode_set_bytes(inode, dmabuf->size);
+	inode->i_size = size;
+	inode_set_bytes(inode, size);
 
 	/*
 	 * The ->i_ino acquired from get_next_ino() is not unique thus
···
 				 flags, &dma_buf_fops);
 	if (IS_ERR(file))
 		goto err_alloc_file;
-	file->private_data = dmabuf;
-	file->f_path.dentry->d_fsdata = dmabuf;
 
 	return file;
 
···
 	size_t alloc_size = sizeof(struct dma_buf);
 	int ret;
 
-	if (!exp_info->resv)
-		alloc_size += sizeof(struct dma_resv);
-	else
-		/* prevent &dma_buf[1] == dma_buf->resv */
-		alloc_size += 1;
-
-	if (WARN_ON(!exp_info->priv
-			  || !exp_info->ops
-			  || !exp_info->ops->map_dma_buf
-			  || !exp_info->ops->unmap_dma_buf
-			  || !exp_info->ops->release)) {
+	if (WARN_ON(!exp_info->priv || !exp_info->ops
+		    || !exp_info->ops->map_dma_buf
+		    || !exp_info->ops->unmap_dma_buf
+		    || !exp_info->ops->release))
 		return ERR_PTR(-EINVAL);
-	}
 
 	if (WARN_ON(exp_info->ops->cache_sgt_mapping &&
 		    (exp_info->ops->pin || exp_info->ops->unpin)))
···
 	if (!try_module_get(exp_info->owner))
 		return ERR_PTR(-ENOENT);
 
+	file = dma_buf_getfile(exp_info->size, exp_info->flags);
+	if (IS_ERR(file)) {
+		ret = PTR_ERR(file);
+		goto err_module;
+	}
+
+	if (!exp_info->resv)
+		alloc_size += sizeof(struct dma_resv);
+	else
+		/* prevent &dma_buf[1] == dma_buf->resv */
+		alloc_size += 1;
 	dmabuf = kzalloc(alloc_size, GFP_KERNEL);
 	if (!dmabuf) {
 		ret = -ENOMEM;
-		goto err_module;
+		goto err_file;
 	}
 
 	dmabuf->priv = exp_info->priv;
···
 	init_waitqueue_head(&dmabuf->poll);
 	dmabuf->cb_in.poll = dmabuf->cb_out.poll = &dmabuf->poll;
 	dmabuf->cb_in.active = dmabuf->cb_out.active = 0;
+	INIT_LIST_HEAD(&dmabuf->attachments);
 
 	if (!resv) {
-		resv = (struct dma_resv *)&dmabuf[1];
-		dma_resv_init(resv);
+		dmabuf->resv = (struct dma_resv *)&dmabuf[1];
+		dma_resv_init(dmabuf->resv);
+	} else {
+		dmabuf->resv = resv;
 	}
-	dmabuf->resv = resv;
 
-	file = dma_buf_getfile(dmabuf, exp_info->flags);
-	if (IS_ERR(file)) {
-		ret = PTR_ERR(file);
+	ret = dma_buf_stats_setup(dmabuf, file);
+	if (ret)
 		goto err_dmabuf;
-	}
 
+	file->private_data = dmabuf;
+	file->f_path.dentry->d_fsdata = dmabuf;
 	dmabuf->file = file;
-
-	INIT_LIST_HEAD(&dmabuf->attachments);
 
 	mutex_lock(&db_list.lock);
 	list_add(&dmabuf->list_node, &db_list.head);
 	mutex_unlock(&db_list.lock);
 
-	ret = dma_buf_stats_setup(dmabuf);
-	if (ret)
-		goto err_sysfs;
-
 	return dmabuf;
 
-err_sysfs:
-	/*
-	 * Set file->f_path.dentry->d_fsdata to NULL so that when
-	 * dma_buf_release() gets invoked by dentry_ops, it exits
-	 * early before calling the release() dma_buf op.
-	 */
-	file->f_path.dentry->d_fsdata = NULL;
-	fput(file);
 err_dmabuf:
+	if (!resv)
+		dma_resv_fini(dmabuf->resv);
 	kfree(dmabuf);
+err_file:
+	fput(file);
 err_module:
 	module_put(exp_info->owner);
 	return ERR_PTR(ret);

drivers/gpio/gpio-eic-sprd.c

···
 
 struct sprd_eic {
 	struct gpio_chip chip;
-	struct irq_chip intc;
 	void __iomem *base[SPRD_EIC_MAX_BANK];
 	enum sprd_eic_type type;
 	spinlock_t lock;
···
 	default:
 		dev_err(chip->parent, "Unsupported EIC type.\n");
 	}
+
+	gpiochip_disable_irq(chip, offset);
 }
 
 static void sprd_eic_irq_unmask(struct irq_data *data)
···
 	struct gpio_chip *chip = irq_data_get_irq_chip_data(data);
 	struct sprd_eic *sprd_eic = gpiochip_get_data(chip);
 	u32 offset = irqd_to_hwirq(data);
+
+	gpiochip_enable_irq(chip, offset);
 
 	switch (sprd_eic->type) {
 	case SPRD_EIC_DEBOUNCE:
···
 	chained_irq_exit(ic, desc);
 }
 
+static const struct irq_chip sprd_eic_irq = {
+	.name		= "sprd-eic",
+	.irq_ack	= sprd_eic_irq_ack,
+	.irq_mask	= sprd_eic_irq_mask,
+	.irq_unmask	= sprd_eic_irq_unmask,
+	.irq_set_type	= sprd_eic_irq_set_type,
+	.flags		= IRQCHIP_SKIP_SET_WAKE | IRQCHIP_IMMUTABLE,
+	GPIOCHIP_IRQ_RESOURCE_HELPERS,
+};
 static int sprd_eic_probe(struct platform_device *pdev)
 {
 	const struct sprd_eic_variant_data *pdata;
···
 		break;
 	}
 
-	sprd_eic->intc.name = dev_name(&pdev->dev);
-	sprd_eic->intc.irq_ack = sprd_eic_irq_ack;
-	sprd_eic->intc.irq_mask = sprd_eic_irq_mask;
-	sprd_eic->intc.irq_unmask = sprd_eic_irq_unmask;
-	sprd_eic->intc.irq_set_type = sprd_eic_irq_set_type;
-	sprd_eic->intc.flags = IRQCHIP_SKIP_SET_WAKE;
-
 	irq = &sprd_eic->chip.irq;
-	irq->chip = &sprd_eic->intc;
+	gpio_irq_chip_set_chip(irq, &sprd_eic_irq);
 	irq->handler = handle_bad_irq;
 	irq->default_type = IRQ_TYPE_NONE;
 	irq->parent_handler = sprd_eic_irq_handler;

drivers/gpio/gpio-pca953x.c

···
 	case PCAL6524_DEBOUNCE:
 		pinctrl = ((reg & PCAL_PINCTRL_MASK) >> 1) + 0x1c;
 		break;
+	default:
+		pinctrl = 0;
+		break;
 	}
 
 	return pinctrl + addr + (off / BANK_SZ);

drivers/gpio/gpio-pmic-eic-sprd.c

···
 /**
  * struct sprd_pmic_eic - PMIC EIC controller
  * @chip: the gpio_chip structure.
- * @intc: the irq_chip structure.
  * @map:  the regmap from the parent device.
  * @offset: the EIC controller's offset address of the PMIC.
  * @reg: the array to cache the EIC registers.
···
  */
 struct sprd_pmic_eic {
 	struct gpio_chip chip;
-	struct irq_chip intc;
 	struct regmap *map;
 	u32 offset;
 	u8 reg[CACHE_NR_REGS];
···
 {
 	struct gpio_chip *chip = irq_data_get_irq_chip_data(data);
 	struct sprd_pmic_eic *pmic_eic = gpiochip_get_data(chip);
+	u32 offset = irqd_to_hwirq(data);
 
 	pmic_eic->reg[REG_IE] = 0;
 	pmic_eic->reg[REG_TRIG] = 0;
+
+	gpiochip_disable_irq(chip, offset);
 }
 
 static void sprd_pmic_eic_irq_unmask(struct irq_data *data)
 {
 	struct gpio_chip *chip = irq_data_get_irq_chip_data(data);
 	struct sprd_pmic_eic *pmic_eic = gpiochip_get_data(chip);
+	u32 offset = irqd_to_hwirq(data);
+
+	gpiochip_enable_irq(chip, offset);
 
 	pmic_eic->reg[REG_IE] = 1;
 	pmic_eic->reg[REG_TRIG] = 1;
···
 	return IRQ_HANDLED;
 }
 
+static const struct irq_chip pmic_eic_irq_chip = {
+	.name			= "sprd-pmic-eic",
+	.irq_mask		= sprd_pmic_eic_irq_mask,
+	.irq_unmask		= sprd_pmic_eic_irq_unmask,
+	.irq_set_type		= sprd_pmic_eic_irq_set_type,
+	.irq_bus_lock		= sprd_pmic_eic_bus_lock,
+	.irq_bus_sync_unlock	= sprd_pmic_eic_bus_sync_unlock,
+	.flags			= IRQCHIP_SKIP_SET_WAKE | IRQCHIP_IMMUTABLE,
+	GPIOCHIP_IRQ_RESOURCE_HELPERS,
+};
+
 static int sprd_pmic_eic_probe(struct platform_device *pdev)
 {
 	struct gpio_irq_chip *irq;
···
 	pmic_eic->chip.set = sprd_pmic_eic_set;
 	pmic_eic->chip.get = sprd_pmic_eic_get;
 
-	pmic_eic->intc.name = dev_name(&pdev->dev);
-	pmic_eic->intc.irq_mask = sprd_pmic_eic_irq_mask;
-	pmic_eic->intc.irq_unmask = sprd_pmic_eic_irq_unmask;
-	pmic_eic->intc.irq_set_type = sprd_pmic_eic_irq_set_type;
-	pmic_eic->intc.irq_bus_lock = sprd_pmic_eic_bus_lock;
-	pmic_eic->intc.irq_bus_sync_unlock = sprd_pmic_eic_bus_sync_unlock;
-	pmic_eic->intc.flags = IRQCHIP_SKIP_SET_WAKE;
-
 	irq = &pmic_eic->chip.irq;
-	irq->chip = &pmic_eic->intc;
+	gpio_irq_chip_set_chip(irq, &pmic_eic_irq_chip);
 	irq->threaded = true;
 
 	ret = devm_gpiochip_add_data(&pdev->dev, &pmic_eic->chip, pmic_eic);

drivers/gpio/gpio-sifive.c

···
 		return -ENODEV;
 	}
 	parent = irq_find_host(irq_parent);
+	of_node_put(irq_parent);
 	if (!parent) {
 		dev_err(dev, "no IRQ parent domain\n");
 		return -ENODEV;

drivers/gpio/gpio-sprd.c

···
 	u32 offset = irqd_to_hwirq(data);
 
 	sprd_gpio_update(chip, offset, SPRD_GPIO_IE, 0);
+	gpiochip_disable_irq(chip, offset);
 }
 
 static void sprd_gpio_irq_ack(struct irq_data *data)
···
 	u32 offset = irqd_to_hwirq(data);
 
 	sprd_gpio_update(chip, offset, SPRD_GPIO_IE, 1);
+	gpiochip_enable_irq(chip, offset);
 }
 
 static int sprd_gpio_irq_set_type(struct irq_data *data,
···
 	chained_irq_exit(ic, desc);
 }
 
-static struct irq_chip sprd_gpio_irqchip = {
+static const struct irq_chip sprd_gpio_irqchip = {
 	.name = "sprd-gpio",
 	.irq_ack = sprd_gpio_irq_ack,
 	.irq_mask = sprd_gpio_irq_mask,
 	.irq_unmask = sprd_gpio_irq_unmask,
 	.irq_set_type = sprd_gpio_irq_set_type,
-	.flags = IRQCHIP_SKIP_SET_WAKE,
+	.flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_IMMUTABLE,
+	GPIOCHIP_IRQ_RESOURCE_HELPERS,
 };
 
 static int sprd_gpio_probe(struct platform_device *pdev)
···
 	sprd_gpio->chip.direction_output = sprd_gpio_direction_output;
 
 	irq = &sprd_gpio->chip.irq;
-	irq->chip = &sprd_gpio_irqchip;
+	gpio_irq_chip_set_chip(irq, &sprd_gpio_irqchip);
 	irq->handler = handle_bad_irq;
 	irq->default_type = IRQ_TYPE_NONE;
 	irq->parent_handler = sprd_gpio_irq_handler;

drivers/gpio/gpiolib.c

···
 						const char *label,
 						bool platform_lookup_allowed)
 {
+	unsigned long lookupflags = GPIO_LOOKUP_FLAGS_DEFAULT;
 	struct gpio_desc *desc = ERR_PTR(-ENOENT);
-	unsigned long lookupflags;
 	int ret;
 
 	if (!IS_ERR_OR_NULL(fwnode))

drivers/gpu/drm/amd/amdgpu/amdgpu.h

···
 extern uint amdgpu_smu_memory_pool_size;
 extern int amdgpu_smu_pptable_id;
 extern uint amdgpu_dc_feature_mask;
+extern uint amdgpu_freesync_vid_mode;
 extern uint amdgpu_dc_debug_mask;
 extern uint amdgpu_dc_visual_confirm;
 extern uint amdgpu_dm_abm_level;

drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c

···
 int amdgpu_noretry = -1;
 int amdgpu_force_asic_type = -1;
 int amdgpu_tmz = -1; /* auto */
+uint amdgpu_freesync_vid_mode;
 int amdgpu_reset_method = -1; /* auto */
 int amdgpu_num_kcq = -1;
 int amdgpu_smartshift_bias;
···
  */
 MODULE_PARM_DESC(tmz, "Enable TMZ feature (-1 = auto (default), 0 = off, 1 = on)");
 module_param_named(tmz, amdgpu_tmz, int, 0444);
+
+/**
+ * DOC: freesync_video (uint)
+ * Enable the optimization to adjust front porch timing to achieve seamless
+ * mode change experience when setting a freesync supported mode for which full
+ * modeset is not needed.
+ *
+ * The Display Core will add a set of modes derived from the base FreeSync
+ * video mode into the corresponding connector's mode list based on commonly
+ * used refresh rates and VRR range of the connected display, when users enable
+ * this feature. From the userspace perspective, they can see a seamless mode
+ * change experience when the change between different refresh rates under the
+ * same resolution. Additionally, userspace applications such as Video playback
+ * can read this modeset list and change the refresh rate based on the video
+ * frame rate. Finally, the userspace can also derive an appropriate mode for a
+ * particular refresh rate based on the FreeSync Mode and add it to the
+ * connector's mode list.
+ *
+ * Note: This is an experimental feature.
+ *
+ * The default value: 0 (off).
+ */
+MODULE_PARM_DESC(
+	freesync_video,
+	"Enable freesync modesetting optimization feature (0 = off (default), 1 = on)");
+module_param_named(freesync_video, amdgpu_freesync_vid_mode, uint, 0444);
 
 /**
  * DOC: reset_method (int)

drivers/gpu/drm/amd/amdkfd/kfd_topology.c

···
 
 		p2plink->attr.name = "properties";
 		p2plink->attr.mode = KFD_SYSFS_FILE_MODE;
-		sysfs_attr_init(&iolink->attr);
+		sysfs_attr_init(&p2plink->attr);
 		ret = sysfs_create_file(p2plink->kobj, &p2plink->attr);
 		if (ret < 0)
 			return ret;

drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c

···
 		amdgpu_set_panel_orientation(&aconnector->base);
 	}
 
+	/* If we didn't find a panel, notify the acpi video detection */
+	if (dm->adev->flags & AMD_IS_APU && dm->num_of_edps == 0)
+		acpi_video_report_nolcd();
+
 	/* Software is initialized. Now we can register interrupt handlers. */
 	switch (adev->asic_type) {
 #if defined(CONFIG_DRM_AMD_DC_SI)
···
 		 */
 		DRM_DEBUG_DRIVER("No preferred mode found\n");
 	} else {
-		recalculate_timing = is_freesync_video_mode(&mode, aconnector);
+		recalculate_timing = amdgpu_freesync_vid_mode &&
+				 is_freesync_video_mode(&mode, aconnector);
 		if (recalculate_timing) {
 			freesync_mode = get_highest_refresh_rate_mode(aconnector, false);
 			drm_mode_copy(&saved_mode, &mode);
···
 	struct amdgpu_dm_connector *amdgpu_dm_connector =
 		to_amdgpu_dm_connector(connector);
 
-	if (!edid)
+	if (!(amdgpu_freesync_vid_mode && edid))
 		return;
 
 	if (amdgpu_dm_connector->max_vfreq - amdgpu_dm_connector->min_vfreq > 10)
···
 		 * TODO: Refactor this function to allow this check to work
 		 * in all conditions.
 		 */
-		if (dm_new_crtc_state->stream &&
+		if (amdgpu_freesync_vid_mode &&
+		    dm_new_crtc_state->stream &&
 		    is_timing_unchanged_for_freesync(new_crtc_state, old_crtc_state))
 			goto skip_modeset;
 
···
 		if (!dm_old_crtc_state->stream)
 			goto skip_modeset;
 
-		if (dm_new_crtc_state->stream &&
+		if (amdgpu_freesync_vid_mode && dm_new_crtc_state->stream &&
 		    is_timing_unchanged_for_freesync(new_crtc_state,
 						     old_crtc_state)) {
 			new_crtc_state->mode_changed = false;
···
 			set_freesync_fixed_config(dm_new_crtc_state);
 
 			goto skip_modeset;
-		} else if (aconnector &&
+		} else if (amdgpu_freesync_vid_mode && aconnector &&
 			   is_freesync_video_mode(&new_crtc_state->mode,
 						  aconnector)) {
 			struct drm_display_mode *high_mode;

drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c

···
 	double SwathSizePerSurfaceC[DC__NUM_DPP__MAX];
 	bool NotEnoughDETSwathFillLatencyHiding = false;
 
-	/* calculate sum of single swath size for all pipes in bytes*/
+	/* calculate sum of single swath size for all pipes in bytes */
 	for (k = 0; k < NumberOfActiveSurfaces; k++) {
-		SwathSizePerSurfaceY[k] += SwathHeightY[k] * SwathWidthY[k] * BytePerPixelInDETY[k] * NumOfDPP[k];
+		SwathSizePerSurfaceY[k] = SwathHeightY[k] * SwathWidthY[k] * BytePerPixelInDETY[k] * NumOfDPP[k];
 
 		if (SwathHeightC[k] != 0)
-			SwathSizePerSurfaceC[k] += SwathHeightC[k] * SwathWidthC[k] * BytePerPixelInDETC[k] * NumOfDPP[k];
+			SwathSizePerSurfaceC[k] = SwathHeightC[k] * SwathWidthC[k] * BytePerPixelInDETC[k] * NumOfDPP[k];
 		else
 			SwathSizePerSurfaceC[k] = 0;
 

drivers/gpu/drm/i915/display/intel_dsi_vbt.c

···
 
 #include "i915_drv.h"
 #include "i915_reg.h"
+#include "intel_de.h"
 #include "intel_display_types.h"
 #include "intel_dsi.h"
 #include "intel_dsi_vbt.h"
+#include "intel_gmbus_regs.h"
 #include "vlv_dsi.h"
 #include "vlv_dsi_regs.h"
 #include "vlv_sideband.h"
···
 	drm_dbg_kms(&dev_priv->drm, "Skipping ICL GPIO element execution\n");
 }
 
+enum {
+	MIPI_RESET_1 = 0,
+	MIPI_AVDD_EN_1,
+	MIPI_BKLT_EN_1,
+	MIPI_AVEE_EN_1,
+	MIPI_VIO_EN_1,
+	MIPI_RESET_2,
+	MIPI_AVDD_EN_2,
+	MIPI_BKLT_EN_2,
+	MIPI_AVEE_EN_2,
+	MIPI_VIO_EN_2,
+};
+
+static void icl_native_gpio_set_value(struct drm_i915_private *dev_priv,
+				      int gpio, bool value)
+{
+	int index;
+
+	if (drm_WARN_ON(&dev_priv->drm, DISPLAY_VER(dev_priv) == 11 && gpio >= MIPI_RESET_2))
+		return;
+
+	switch (gpio) {
+	case MIPI_RESET_1:
+	case MIPI_RESET_2:
+		index = gpio == MIPI_RESET_1 ? HPD_PORT_A : HPD_PORT_B;
+
+		/*
+		 * Disable HPD to set the pin to output, and set output
+		 * value. The HPD pin should not be enabled for DSI anyway,
+		 * assuming the board design and VBT are sane, and the pin isn't
+		 * used by a non-DSI encoder.
+		 *
+		 * The locking protects against concurrent SHOTPLUG_CTL_DDI
+		 * modifications in irq setup and handling.
+		 */
+		spin_lock_irq(&dev_priv->irq_lock);
+		intel_de_rmw(dev_priv, SHOTPLUG_CTL_DDI,
+			     SHOTPLUG_CTL_DDI_HPD_ENABLE(index) |
+			     SHOTPLUG_CTL_DDI_HPD_OUTPUT_DATA(index),
+			     value ? SHOTPLUG_CTL_DDI_HPD_OUTPUT_DATA(index) : 0);
+		spin_unlock_irq(&dev_priv->irq_lock);
+		break;
+	case MIPI_AVDD_EN_1:
+	case MIPI_AVDD_EN_2:
+		index = gpio == MIPI_AVDD_EN_1 ? 0 : 1;
+
+		intel_de_rmw(dev_priv, PP_CONTROL(index), PANEL_POWER_ON,
+			     value ? PANEL_POWER_ON : 0);
+		break;
+	case MIPI_BKLT_EN_1:
+	case MIPI_BKLT_EN_2:
+		index = gpio == MIPI_BKLT_EN_1 ? 0 : 1;
+
+		intel_de_rmw(dev_priv, PP_CONTROL(index), EDP_BLC_ENABLE,
+			     value ? EDP_BLC_ENABLE : 0);
+		break;
+	case MIPI_AVEE_EN_1:
+	case MIPI_AVEE_EN_2:
+		index = gpio == MIPI_AVEE_EN_1 ? 1 : 2;
+
+		intel_de_rmw(dev_priv, GPIO(dev_priv, index),
+			     GPIO_CLOCK_VAL_OUT,
+			     GPIO_CLOCK_DIR_MASK | GPIO_CLOCK_DIR_OUT |
+			     GPIO_CLOCK_VAL_MASK | (value ? GPIO_CLOCK_VAL_OUT : 0));
+		break;
+	case MIPI_VIO_EN_1:
+	case MIPI_VIO_EN_2:
+		index = gpio == MIPI_VIO_EN_1 ? 1 : 2;
+
+		intel_de_rmw(dev_priv, GPIO(dev_priv, index),
+			     GPIO_DATA_VAL_OUT,
+			     GPIO_DATA_DIR_MASK | GPIO_DATA_DIR_OUT |
+			     GPIO_DATA_VAL_MASK | (value ? GPIO_DATA_VAL_OUT : 0));
+		break;
+	default:
+		MISSING_CASE(gpio);
+	}
+}
+
 static const u8 *mipi_exec_gpio(struct intel_dsi *intel_dsi, const u8 *data)
 {
 	struct drm_device *dev = intel_dsi->base.base.dev;
···
 	struct intel_connector *connector = intel_dsi->attached_connector;
 	u8 gpio_source, gpio_index = 0, gpio_number;
 	bool value;
-
-	drm_dbg_kms(&dev_priv->drm, "\n");
+	bool native = DISPLAY_VER(dev_priv) >= 11;
 
 	if (connector->panel.vbt.dsi.seq_version >= 3)
 		gpio_index = *data++;
···
 	else
 		gpio_source = 0;
 
+	if (connector->panel.vbt.dsi.seq_version >= 4 && *data & BIT(1))
+		native = false;
+
 	/* pull up/down */
 	value = *data++ & 1;
 
-	if (DISPLAY_VER(dev_priv) >= 11)
+	drm_dbg_kms(&dev_priv->drm, "GPIO index %u, number %u, source %u, native %s, set to %s\n",
+		    gpio_index, gpio_number, gpio_source, str_yes_no(native), str_on_off(value));
+
+	if (native)
+		icl_native_gpio_set_value(dev_priv, gpio_number, value);
+	else if (DISPLAY_VER(dev_priv) >= 11)
 		icl_exec_gpio(connector, gpio_source, gpio_index, value);
 	else if (IS_VALLEYVIEW(dev_priv))
 		vlv_exec_gpio(connector, gpio_source, gpio_number, value);

drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c

···
 	bool unpinned;
 
 	/*
-	 * Attempt to pin all of the buffers into the GTT.
-	 * This is done in 2 phases:
+	 * We have one more buffers that we couldn't bind, which could be due to
+	 * various reasons. To resolve this we have 4 passes, with every next
+	 * level turning the screws tighter:
 	 *
-	 * 1. Unbind all objects that do not match the GTT constraints for
-	 *    the execbuffer (fenceable, mappable, alignment etc).
-	 * 2. Bind new objects.
+	 * 0. Unbind all objects that do not match the GTT constraints for the
+	 * execbuffer (fenceable, mappable, alignment etc). Bind all new
+	 * objects.  This avoids unnecessary unbinding of later objects in order
+	 * to make room for the earlier objects *unless* we need to defragment.
 	 *
-	 * This avoid unnecessary unbinding of later objects in order to make
-	 * room for the earlier objects *unless* we need to defragment.
+	 * 1. Reorder the buffers, where objects with the most restrictive
+	 * placement requirements go first (ignoring fixed location buffers for
+	 * now).  For example, objects needing the mappable aperture (the first
+	 * 256M of GTT), should go first vs objects that can be placed just
+	 * about anywhere. Repeat the previous pass.
 	 *
-	 * Defragmenting is skipped if all objects are pinned at a fixed location.
+	 * 2. Consider buffers that are pinned at a fixed location. Also try to
+	 * evict the entire VM this time, leaving only objects that we were
+	 * unable to lock. Try again to bind the buffers. (still using the new
+	 * buffer order).
+	 *
+	 * 3. We likely have object lock contention for one or more stubborn
+	 * objects in the VM, for which we need to evict to make forward
+	 * progress (perhaps we are fighting the shrinker?). When evicting the
+	 * VM this time around, anything that we can't lock we now track using
+	 * the busy_bo, using the full lock (after dropping the vm->mutex to
+	 * prevent deadlocks), instead of trylock. We then continue to evict the
+	 * VM, this time with the stubborn object locked, which we can now
+	 * hopefully unbind (if still bound in the VM). Repeat until the VM is
+	 * evicted. Finally we should be able bind everything.
 	 */
-	for (pass = 0; pass <= 2; pass++) {
+	for (pass = 0; pass <= 3; pass++) {
 		int pin_flags = PIN_USER | PIN_VALIDATE;
 
 		if (pass == 0)
 			pin_flags |= PIN_NONBLOCK;
 
 		if (pass >= 1)
-			unpinned = eb_unbind(eb, pass == 2);
+			unpinned = eb_unbind(eb, pass >= 2);
 
 		if (pass == 2) {
 			err = mutex_lock_interruptible(&eb->context->vm->mutex);
 			if (!err) {
-				err = i915_gem_evict_vm(eb->context->vm, &eb->ww);
+				err = i915_gem_evict_vm(eb->context->vm, &eb->ww, NULL);
 				mutex_unlock(&eb->context->vm->mutex);
+			}
+			if (err)
+				return err;
+		}
+
+		if (pass == 3) {
+retry:
+			err = mutex_lock_interruptible(&eb->context->vm->mutex);
+			if (!err) {
+				struct drm_i915_gem_object *busy_bo = NULL;
+
+				err = i915_gem_evict_vm(eb->context->vm, &eb->ww, &busy_bo);
+				mutex_unlock(&eb->context->vm->mutex);
+				if (err && busy_bo) {
+					err = i915_gem_object_lock(busy_bo, &eb->ww);
+					i915_gem_object_put(busy_bo);
+					if (!err)
+						goto retry;
+				}
 			}
 			if (err)
 				return err;

drivers/gpu/drm/i915/gem/i915_gem_mman.c

···
 		if (vma == ERR_PTR(-ENOSPC)) {
 			ret = mutex_lock_interruptible(&ggtt->vm.mutex);
 			if (!ret) {
-				ret = i915_gem_evict_vm(&ggtt->vm, &ww);
+				ret = i915_gem_evict_vm(&ggtt->vm, &ww, NULL);
 				mutex_unlock(&ggtt->vm.mutex);
 			}
 			if (ret)

drivers/gpu/drm/i915/gt/intel_gt.c

···
 			continue;
 
 		if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) {
+			u32 val = BIT(engine->instance);
+
+			if (engine->class == VIDEO_DECODE_CLASS ||
+			    engine->class == VIDEO_ENHANCEMENT_CLASS ||
+			    engine->class == COMPUTE_CLASS)
+				val = _MASKED_BIT_ENABLE(val);
 			intel_gt_mcr_multicast_write_fw(gt,
 							xehp_regs[engine->class],
-							BIT(engine->instance));
+							val);
 		} else {
 			rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
 			if (!i915_mmio_reg_offset(rb.reg))

drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c

···
 	return 0;
 }
 
+static int try_firmware_load(struct intel_uc_fw *uc_fw, const struct firmware **fw)
+{
+	struct intel_gt *gt = __uc_fw_to_gt(uc_fw);
+	struct device *dev = gt->i915->drm.dev;
+	int err;
+
+	err = firmware_request_nowarn(fw, uc_fw->file_selected.path, dev);
+
+	if (err)
+		return err;
+
+	if ((*fw)->size > INTEL_UC_RSVD_GGTT_PER_FW) {
+		drm_err(&gt->i915->drm,
+			"%s firmware %s: size (%zuKB) exceeds max supported size (%uKB)\n",
+			intel_uc_fw_type_repr(uc_fw->type), uc_fw->file_selected.path,
+			(*fw)->size / SZ_1K, INTEL_UC_RSVD_GGTT_PER_FW / SZ_1K);
+
+		/* try to find another blob to load */
+		release_firmware(*fw);
+		*fw = NULL;
+		return -ENOENT;
+	}
+
+	return 0;
+}
+
 /**
  * intel_uc_fw_fetch - fetch uC firmware
  * @uc_fw: uC firmware
···
 	struct intel_gt *gt = __uc_fw_to_gt(uc_fw);
 	struct drm_i915_private *i915 = gt->i915;
 	struct intel_uc_fw_file file_ideal;
-	struct device *dev = i915->drm.dev;
 	struct drm_i915_gem_object *obj;
 	const struct firmware *fw = NULL;
 	bool old_ver = false;
···
 	__force_fw_fetch_failures(uc_fw, -EINVAL);
 	__force_fw_fetch_failures(uc_fw, -ESTALE);
 
-	err = firmware_request_nowarn(&fw, uc_fw->file_selected.path, dev);
+	err = try_firmware_load(uc_fw, &fw);
 	memcpy(&file_ideal, &uc_fw->file_wanted, sizeof(file_ideal));
-
-	if (!err && fw->size > INTEL_UC_RSVD_GGTT_PER_FW) {
-		drm_err(&i915->drm,
-			"%s firmware %s: size (%zuKB) exceeds max supported size (%uKB)\n",
-			intel_uc_fw_type_repr(uc_fw->type), uc_fw->file_selected.path,
-			fw->size / SZ_1K, INTEL_UC_RSVD_GGTT_PER_FW / SZ_1K);
-
-		/* try to find another blob to load */
-		release_firmware(fw);
-		err = -ENOENT;
-	}
 
 	/* Any error is terminal if overriding. Don't bother searching for older versions */
 	if (err && intel_uc_fw_is_overridden(uc_fw))
···
 			break;
 		}
 
-		err = firmware_request_nowarn(&fw, uc_fw->file_selected.path, dev);
+		err = try_firmware_load(uc_fw, &fw);
 	}
 
 	if (err)

drivers/gpu/drm/i915/gvt/debugfs.c

···
 			vgpu_scan_nonprivbb_get, vgpu_scan_nonprivbb_set,
 			"0x%llx\n");
 
+static int vgpu_status_get(void *data, u64 *val)
+{
+	struct intel_vgpu *vgpu = (struct intel_vgpu *)data;
+
+	*val = 0;
+
+	if (test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
+		*val |= (1 << INTEL_VGPU_STATUS_ATTACHED);
+	if (test_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status))
+		*val |= (1 << INTEL_VGPU_STATUS_ACTIVE);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(vgpu_status_fops, vgpu_status_get, NULL, "0x%llx\n");
+
 /**
  * intel_gvt_debugfs_add_vgpu - register debugfs entries for a vGPU
  * @vgpu: a vGPU
···
 	snprintf(name, 16, "vgpu%d", vgpu->id);
 	vgpu->debugfs = debugfs_create_dir(name, vgpu->gvt->debugfs_root);
 
-	debugfs_create_bool("active", 0444, vgpu->debugfs, &vgpu->active);
 	debugfs_create_file("mmio_diff", 0444, vgpu->debugfs, vgpu,
 			    &vgpu_mmio_diff_fops);
 	debugfs_create_file("scan_nonprivbb", 0644, vgpu->debugfs, vgpu,
 			    &vgpu_scan_nonprivbb_fops);
+	debugfs_create_file("status", 0644, vgpu->debugfs, vgpu,
+			    &vgpu_status_fops);
 }
 
 /**
···
  */
 void intel_gvt_debugfs_remove_vgpu(struct intel_vgpu *vgpu)
 {
-	debugfs_remove_recursive(vgpu->debugfs);
-	vgpu->debugfs = NULL;
+	struct intel_gvt *gvt = vgpu->gvt;
+	struct drm_minor *minor = gvt->gt->i915->drm.primary;
+
+	if (minor->debugfs_root && gvt->debugfs_root) {
+		debugfs_remove_recursive(vgpu->debugfs);
+		vgpu->debugfs = NULL;
+	}
 }
 
 /**
···
  */
 void intel_gvt_debugfs_clean(struct intel_gvt *gvt)
 {
-	debugfs_remove_recursive(gvt->debugfs_root);
-	gvt->debugfs_root = NULL;
+	struct drm_minor *minor = gvt->gt->i915->drm.primary;
+
+	if (minor->debugfs_root) {
+		debugfs_remove_recursive(gvt->debugfs_root);
+		gvt->debugfs_root = NULL;
+	}
 }

drivers/gpu/drm/i915/gvt/dmabuf.c

···
 	struct list_head *pos;
 	struct intel_vgpu_dmabuf_obj *dmabuf_obj;
 
-	if (vgpu && vgpu->active && !list_empty(&vgpu->dmabuf_obj_list_head)) {
+	if (vgpu && test_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status) &&
+	    !list_empty(&vgpu->dmabuf_obj_list_head)) {
 		list_for_each(pos, &vgpu->dmabuf_obj_list_head) {
 			dmabuf_obj = list_entry(pos, struct intel_vgpu_dmabuf_obj, list);
 			if (dmabuf_obj == obj) {

drivers/gpu/drm/i915/gvt/gtt.c

···
 	int idx;
 	bool ret;
 
-	if (!vgpu->attached)
+	if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
 		return false;
 
 	idx = srcu_read_lock(&kvm->srcu);
···
 	if (!HAS_PAGE_SIZES(vgpu->gvt->gt->i915, I915_GTT_PAGE_SIZE_2M))
 		return 0;
 
-	if (!vgpu->attached)
+	if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
 		return -EINVAL;
 	pfn = gfn_to_pfn(vgpu->vfio_device.kvm, ops->get_pfn(entry));
 	if (is_error_noslot_pfn(pfn))
···
 	for_each_shadow_entry(sub_spt, &sub_se, sub_index) {
 		ret = intel_gvt_dma_map_guest_page(vgpu, start_gfn + sub_index,
 						   PAGE_SIZE, &dma_addr);
-		if (ret) {
-			ppgtt_invalidate_spt(spt);
-			return ret;
-		}
+		if (ret)
+			goto err;
 		sub_se.val64 = se->val64;
 
 		/* Copy the PAT field from PDE. */
···
 	ops->set_pfn(se, sub_spt->shadow_page.mfn);
 	ppgtt_set_shadow_entry(spt, se, index);
 	return 0;
+err:
+	/* Cancel the existing addess mappings of DMA addr. */
+	for_each_present_shadow_entry(sub_spt, &sub_se, sub_index) {
+		gvt_vdbg_mm("invalidate 4K entry\n");
+		ppgtt_invalidate_pte(sub_spt, &sub_se);
+	}
+	/* Release the new allocated spt. */
+	trace_spt_change(sub_spt->vgpu->id, "release", sub_spt,
+		sub_spt->guest_page.gfn, sub_spt->shadow_page.type);
+	ppgtt_free_spt(sub_spt);
+	return ret;
 }
 
 static int split_64KB_gtt_entry(struct intel_vgpu *vgpu,

drivers/gpu/drm/i915/gvt/gvt.h

···
 
 #define KVMGT_DEBUGFS_FILENAME		"kvmgt_nr_cache_entries"
 
+enum {
+	INTEL_VGPU_STATUS_ATTACHED = 0,
+	INTEL_VGPU_STATUS_ACTIVE,
+	INTEL_VGPU_STATUS_NR_BITS,
+};
+
 struct intel_vgpu {
 	struct vfio_device vfio_device;
 	struct intel_gvt *gvt;
 	struct mutex vgpu_lock;
 	int id;
-	bool active;
-	bool attached;
+	DECLARE_BITMAP(status, INTEL_VGPU_STATUS_NR_BITS);
 	bool pv_notified;
 	bool failsafe;
 	unsigned int resetting_eng;
···
 
 #define for_each_active_vgpu(gvt, vgpu, id) \
 	idr_for_each_entry((&(gvt)->vgpu_idr), (vgpu), (id)) \
-		for_each_if(vgpu->active)
+		for_each_if(test_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status))
 
 static inline void intel_vgpu_write_pci_bar(struct intel_vgpu *vgpu,
 					    u32 offset, u32 val, bool low)
···
 static inline int intel_gvt_read_gpa(struct intel_vgpu *vgpu, unsigned long gpa,
 		void *buf, unsigned long len)
 {
-	if (!vgpu->attached)
+	if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
 		return -ESRCH;
 	return vfio_dma_rw(&vgpu->vfio_device, gpa, buf, len, false);
 }
···
 static inline int intel_gvt_write_gpa(struct intel_vgpu *vgpu,
 		unsigned long gpa, void *buf, unsigned long len)
 {
-	if (!vgpu->attached)
+	if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
 		return -ESRCH;
 	return vfio_dma_rw(&vgpu->vfio_device, gpa, buf, len, true);
 }

drivers/gpu/drm/i915/gvt/interrupt.c

···
 	 * enabled by guest. so if msi_trigger is null, success is still
 	 * returned and don't inject interrupt into guest.
 	 */
-	if (!vgpu->attached)
+	if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
 		return -ESRCH;
 	if (vgpu->msi_trigger && eventfd_signal(vgpu->msi_trigger, 1) != 1)
 		return -EFAULT;

drivers/gpu/drm/i915/gvt/kvmgt.c

···
 
 	mutex_lock(&vgpu->gvt->lock);
 	for_each_active_vgpu(vgpu->gvt, itr, id) {
-		if (!itr->attached)
+		if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, itr->status))
 			continue;
 
 		if (vgpu->vfio_device.kvm == itr->vfio_device.kvm) {
···
 {
 	struct intel_vgpu *vgpu = vfio_dev_to_vgpu(vfio_dev);
 
-	if (vgpu->attached)
-		return -EEXIST;
-
 	if (!vgpu->vfio_device.kvm ||
 	    vgpu->vfio_device.kvm->mm != current->mm) {
 		gvt_vgpu_err("KVM is required to use Intel vGPU\n");
···
 	if (__kvmgt_vgpu_exist(vgpu))
 		return -EEXIST;
 
-	vgpu->attached = true;
-
 	vgpu->track_node.track_write = kvmgt_page_track_write;
 	vgpu->track_node.track_flush_slot = kvmgt_page_track_flush_slot;
 	kvm_get_kvm(vgpu->vfio_device.kvm);
 	kvm_page_track_register_notifier(vgpu->vfio_device.kvm,
 					 &vgpu->track_node);
+
+	set_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status);
 
 	debugfs_create_ulong(KVMGT_DEBUGFS_FILENAME, 0444, vgpu->debugfs,
 			     &vgpu->nr_cache_entries);
···
 {
 	struct intel_vgpu *vgpu = vfio_dev_to_vgpu(vfio_dev);
 
-	if (!vgpu->attached)
-		return;
-
 	intel_gvt_release_vgpu(vgpu);
+
+	clear_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status);
 
 	debugfs_remove(debugfs_lookup(KVMGT_DEBUGFS_FILENAME, vgpu->debugfs));
 
···
 	vgpu->dma_addr_cache = RB_ROOT;
 
 	intel_vgpu_release_msi_eventfd_ctx(vgpu);
-
-	vgpu->attached = false;
 }
 
 static u64 intel_vgpu_get_bar_addr(struct intel_vgpu *vgpu, int bar)
···
 {
 	struct intel_vgpu *vgpu = dev_get_drvdata(&mdev->dev);
 
-	if (WARN_ON_ONCE(vgpu->attached))
-		return;
-
 	vfio_unregister_group_dev(&vgpu->vfio_device);
 	vfio_put_device(&vgpu->vfio_device);
 }
···
 	struct kvm_memory_slot *slot;
 	int idx;
 
-	if (!info->attached)
+	if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, info->status))
 		return -ESRCH;
 
 	idx = srcu_read_lock(&kvm->srcu);
···
 	struct kvm_memory_slot *slot;
 	int idx;
 
-	if (!info->attached)
-		return 0;
+	if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, info->status))
+		return -ESRCH;
 
 	idx = srcu_read_lock(&kvm->srcu);
 	slot = gfn_to_memslot(kvm, gfn);
···
 	struct gvt_dma *entry;
 	int ret;
 
-	if (!vgpu->attached)
+	if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
 		return -EINVAL;
 
 	mutex_lock(&vgpu->cache_lock);
···
 	struct gvt_dma *entry;
 	int ret = 0;
 
-	if (!vgpu->attached)
-		return -ENODEV;
+	if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
+		return -EINVAL;
 
 	mutex_lock(&vgpu->cache_lock);
 	entry = __gvt_cache_find_dma_addr(vgpu, dma_addr);
···
 {
 	struct gvt_dma *entry;
 
-	if (!vgpu->attached)
+	if (!test_bit(INTEL_VGPU_STATUS_ATTACHED, vgpu->status))
 		return;
 
 	mutex_lock(&vgpu->cache_lock);
···
 	idr_for_each_entry((&(gvt)->vgpu_idr), (vgpu), (id)) {
 		if (test_and_clear_bit(INTEL_GVT_REQUEST_EMULATE_VBLANK + id,
 				       (void *)&gvt->service_request)) {
-			if (vgpu->active)
+			if (test_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status))
 				intel_vgpu_emulate_vblank(vgpu);
 		}
 	}

drivers/gpu/drm/i915/gvt/scheduler.c

···
 
 	if (workload->shadow_mm->type != INTEL_GVT_MM_PPGTT ||
 	    !workload->shadow_mm->ppgtt_mm.shadowed) {
+		intel_vgpu_unpin_mm(workload->shadow_mm);
 		gvt_vgpu_err("workload shadow ppgtt isn't ready\n");
 		return -EINVAL;
 	}
···
 		goto out;
 	}
 
-	if (!scheduler->current_vgpu->active ||
+	if (!test_bit(INTEL_VGPU_STATUS_ACTIVE,
+		      scheduler->current_vgpu->status) ||
 	    list_empty(workload_q_head(scheduler->current_vgpu, engine)))
 		goto out;
 

drivers/gpu/drm/i915/gvt/vgpu.c

···
  */
 void intel_gvt_activate_vgpu(struct intel_vgpu *vgpu)
 {
-	mutex_lock(&vgpu->vgpu_lock);
-	vgpu->active = true;
-	mutex_unlock(&vgpu->vgpu_lock);
+	set_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status);
 }
 
 /**
···
 {
 	mutex_lock(&vgpu->vgpu_lock);
 
-	vgpu->active = false;
+	clear_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status);
 
 	if (atomic_read(&vgpu->submission.running_workload_num)) {
 		mutex_unlock(&vgpu->vgpu_lock);
···
 	struct intel_gvt *gvt = vgpu->gvt;
 	struct drm_i915_private *i915 = gvt->gt->i915;
 
-	drm_WARN(&i915->drm, vgpu->active, "vGPU is still active!\n");
+	drm_WARN(&i915->drm, test_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status),
+		 "vGPU is still active!\n");
 
 	/*
 	 * remove idr first so later clean can judge if need to stop
···
 	if (ret)
 		goto out_free_vgpu;
 
-	vgpu->active = false;
-
+	clear_bit(INTEL_VGPU_STATUS_ACTIVE, vgpu->status);
 	return vgpu;
 
 out_free_vgpu:

drivers/gpu/drm/i915/i915_gem_evict.c

···
  * @vm: Address space to cleanse
  * @ww: An optional struct i915_gem_ww_ctx. If not NULL, i915_gem_evict_vm
  * will be able to evict vma's locked by the ww as well.
+ * @busy_bo: Optional pointer to struct drm_i915_gem_object. If not NULL, then
+ * in the event i915_gem_evict_vm() is unable to trylock an object for eviction,
+ * then @busy_bo will point to it. -EBUSY is also returned. The caller must drop
+ * the vm->mutex, before trying again to acquire the contended lock. The caller
+ * also owns a reference to the object.
  *
  * This function evicts all vmas from a vm.
  *
···
  * To clarify: This is for freeing up virtual address space, not for freeing
  * memory in e.g. the shrinker.
  */
-int i915_gem_evict_vm(struct i915_address_space *vm, struct i915_gem_ww_ctx *ww)
+int i915_gem_evict_vm(struct i915_address_space *vm, struct i915_gem_ww_ctx *ww,
+		      struct drm_i915_gem_object **busy_bo)
 {
 	int ret = 0;
 
···
 			 * the resv is shared among multiple objects, we still
 			 * need the object ref.
 			 */
-			if (dying_vma(vma) ||
+			if (!i915_gem_object_get_rcu(vma->obj) ||
 			    (ww && (dma_resv_locking_ctx(vma->obj->base.resv) == &ww->ctx))) {
 				__i915_vma_pin(vma);
 				list_add(&vma->evict_link, &locked_eviction_list);
 				continue;
 			}
 
-			if (!i915_gem_object_trylock(vma->obj, ww))
+			if (!i915_gem_object_trylock(vma->obj, ww)) {
+				if (busy_bo) {
+					*busy_bo = vma->obj; /* holds ref */
+					ret = -EBUSY;
+					break;
+				}
+				i915_gem_object_put(vma->obj);
 				continue;
+			}
 
 			__i915_vma_pin(vma);
 			list_add(&vma->evict_link, &eviction_list);
···
 		if (list_empty(&eviction_list) && list_empty(&locked_eviction_list))
 			break;
 
-		ret = 0;
 		/* Unbind locked objects first, before unlocking the eviction_list */
 		list_for_each_entry_safe(vma, vn, &locked_eviction_list, evict_link) {
 			__i915_vma_unpin(vma);
 
-			if (ret == 0)
+			if (ret == 0) {
 				ret = __i915_vma_unbind(vma);
-			if (ret != -EINTR) /* "Get me out of here!" */
-				ret = 0;
+				if (ret != -EINTR) /* "Get me out of here!" */
+					ret = 0;
+			}
+			if (!dying_vma(vma))
+				i915_gem_object_put(vma->obj);
 		}
 
 		list_for_each_entry_safe(vma, vn, &eviction_list, evict_link) {
 			__i915_vma_unpin(vma);
-			if (ret == 0)
+			if (ret == 0) {
 				ret = __i915_vma_unbind(vma);
-			if (ret != -EINTR) /* "Get me out of here!" */
-				ret = 0;
+				if (ret != -EINTR) /* "Get me out of here!" */
+					ret = 0;
+			}
 
 			i915_gem_object_unlock(vma->obj);
+			i915_gem_object_put(vma->obj);
 		}
 	} while (ret == 0);
 

drivers/gpu/drm/i915/i915_gem_evict.h

···
 struct drm_mm_node;
 struct i915_address_space;
 struct i915_gem_ww_ctx;
+struct drm_i915_gem_object;
 
 int __must_check i915_gem_evict_something(struct i915_address_space *vm,
 					  struct i915_gem_ww_ctx *ww,
···
 					 struct drm_mm_node *node,
 					 unsigned int flags);
 int i915_gem_evict_vm(struct i915_address_space *vm,
-		      struct i915_gem_ww_ctx *ww);
+		      struct i915_gem_ww_ctx *ww,
+		      struct drm_i915_gem_object **busy_bo);
 
 #endif /* __I915_GEM_EVICT_H__ */

drivers/gpu/drm/i915/i915_irq.c

···
 	if (ddi_hotplug_trigger) {
 		u32 dig_hotplug_reg;
 
+		/* Locking due to DSI native GPIO sequences */
+		spin_lock(&dev_priv->irq_lock);
 		dig_hotplug_reg = intel_uncore_rmw(&dev_priv->uncore, SHOTPLUG_CTL_DDI, 0, 0);
+		spin_unlock(&dev_priv->irq_lock);
 
 		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
 				   ddi_hotplug_trigger, dig_hotplug_reg,

drivers/gpu/drm/i915/i915_pci.c

···
 	{}
 };
 
-__maybe_unused
 static const struct intel_device_info mtl_info = {
 	XE_HP_FEATURES,
 	XE_LPDP_FEATURES,

drivers/gpu/drm/i915/i915_reg.h

···
 
 #define SHOTPLUG_CTL_DDI				_MMIO(0xc4030)
 #define   SHOTPLUG_CTL_DDI_HPD_ENABLE(hpd_pin)			(0x8 << (_HPD_PIN_DDI(hpd_pin) * 4))
+#define   SHOTPLUG_CTL_DDI_HPD_OUTPUT_DATA(hpd_pin)		(0x4 << (_HPD_PIN_DDI(hpd_pin) * 4))
 #define   SHOTPLUG_CTL_DDI_HPD_STATUS_MASK(hpd_pin)		(0x3 << (_HPD_PIN_DDI(hpd_pin) * 4))
 #define   SHOTPLUG_CTL_DDI_HPD_NO_DETECT(hpd_pin)		(0x0 << (_HPD_PIN_DDI(hpd_pin) * 4))
 #define   SHOTPLUG_CTL_DDI_HPD_SHORT_DETECT(hpd_pin)		(0x1 << (_HPD_PIN_DDI(hpd_pin) * 4))

drivers/gpu/drm/i915/i915_vma.c

···
 			 * locked objects when called from execbuf when pinning
 			 * is removed. This would probably regress badly.
 			 */
-			i915_gem_evict_vm(vm, NULL);
+			i915_gem_evict_vm(vm, NULL, NULL);
 			mutex_unlock(&vm->mutex);
 		}
 	} while (1);

drivers/gpu/drm/i915/selftests/i915_gem_evict.c

···
 
 	/* Everything is pinned, nothing should happen */
 	mutex_lock(&ggtt->vm.mutex);
-	err = i915_gem_evict_vm(&ggtt->vm, NULL);
+	err = i915_gem_evict_vm(&ggtt->vm, NULL, NULL);
 	mutex_unlock(&ggtt->vm.mutex);
 	if (err) {
 		pr_err("i915_gem_evict_vm on a full GGTT returned err=%d]\n",
···
 
 	for_i915_gem_ww(&ww, err, false) {
 		mutex_lock(&ggtt->vm.mutex);
-		err = i915_gem_evict_vm(&ggtt->vm, &ww);
+		err = i915_gem_evict_vm(&ggtt->vm, &ww, NULL);
 		mutex_unlock(&ggtt->vm.mutex);
 	}
 

drivers/gpu/drm/imx/ipuv3-plane.c

···
 		break;
 	}
 
+	if (ipu_plane->dp_flow == IPU_DP_FLOW_SYNC_BG)
+		width = ipu_src_rect_width(new_state);
+	else
+		width = drm_rect_width(&new_state->src) >> 16;
+
 	eba = drm_plane_state_to_eba(new_state, 0);
 
 	/*
···
 	 */
 	if (ipu_state->use_pre) {
 		axi_id = ipu_chan_assign_axi_id(ipu_plane->dma);
-		ipu_prg_channel_configure(ipu_plane->ipu_ch, axi_id,
-					  ipu_src_rect_width(new_state),
+		ipu_prg_channel_configure(ipu_plane->ipu_ch, axi_id, width,
 					  drm_rect_height(&new_state->src) >> 16,
 					  fb->pitches[0], fb->format->format,
 					  fb->modifier, &eba);
···
 		break;
 	}
 
-	ipu_dmfc_config_wait4eot(ipu_plane->dmfc, ALIGN(drm_rect_width(dst), 8));
+	ipu_dmfc_config_wait4eot(ipu_plane->dmfc, width);
 
-	width = ipu_src_rect_width(new_state);
 	height = drm_rect_height(&new_state->src) >> 16;
 	info = drm_format_info(fb->format->format);
 	ipu_calculate_bursts(width, info->cpp[0], fb->pitches[0],
···
 		ipu_cpmem_set_burstsize(ipu_plane->ipu_ch, 16);
 
 		ipu_cpmem_zero(ipu_plane->alpha_ch);
-		ipu_cpmem_set_resolution(ipu_plane->alpha_ch,
-					 ipu_src_rect_width(new_state),
+		ipu_cpmem_set_resolution(ipu_plane->alpha_ch, width,
 					 drm_rect_height(&new_state->src) >> 16);
 		ipu_cpmem_set_format_passthrough(ipu_plane->alpha_ch, 8);
 		ipu_cpmem_set_high_priority(ipu_plane->alpha_ch);

drivers/gpu/drm/meson/meson_viu.c

···
 
 	/* Initialize OSD1 fifo control register */
 	reg = VIU_OSD_DDR_PRIORITY_URGENT |
-		VIU_OSD_HOLD_FIFO_LINES(31) |
 		VIU_OSD_FIFO_DEPTH_VAL(32) | /* fifo_depth_val: 32*8=256 */
 		VIU_OSD_WORDS_PER_BURST(4) | /* 4 words in 1 burst */
 		VIU_OSD_FIFO_LIMITS(2);      /* fifo_lim: 2*16=32 */
 
 	if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A))
-		reg |= VIU_OSD_BURST_LENGTH_32;
+		reg |= (VIU_OSD_BURST_LENGTH_32 | VIU_OSD_HOLD_FIFO_LINES(31));
 	else
-		reg |= VIU_OSD_BURST_LENGTH_64;
+		reg |= (VIU_OSD_BURST_LENGTH_64 | VIU_OSD_HOLD_FIFO_LINES(4));
 
 	writel_relaxed(reg, priv->io_base + _REG(VIU_OSD1_FIFO_CTRL_STAT));
 	writel_relaxed(reg, priv->io_base + _REG(VIU_OSD2_FIFO_CTRL_STAT));

drivers/gpu/drm/panfrost/panfrost_drv.c

···
 	struct panfrost_gem_object *bo;
 	struct drm_panfrost_create_bo *args = data;
 	struct panfrost_gem_mapping *mapping;
+	int ret;
 
 	if (!args->size || args->pad ||
 	    (args->flags & ~(PANFROST_BO_NOEXEC | PANFROST_BO_HEAP)))
···
 	    !(args->flags & PANFROST_BO_NOEXEC))
 		return -EINVAL;
 
-	bo = panfrost_gem_create_with_handle(file, dev, args->size, args->flags,
-					     &args->handle);
+	bo = panfrost_gem_create(dev, args->size, args->flags);
 	if (IS_ERR(bo))
 		return PTR_ERR(bo);
 
+	ret = drm_gem_handle_create(file, &bo->base.base, &args->handle);
+	if (ret)
+		goto out;
+
 	mapping = panfrost_gem_mapping_get(bo, priv);
-	if (!mapping) {
-		drm_gem_object_put(&bo->base.base);
-		return -EINVAL;
+	if (mapping) {
+		args->offset = mapping->mmnode.start << PAGE_SHIFT;
+		panfrost_gem_mapping_put(mapping);
+	} else {
+		/* This can only happen if the handle from
+		 * drm_gem_handle_create() has already been guessed and freed
+		 * by user space
+		 */
+		ret = -EINVAL;
 	}
 
-	args->offset = mapping->mmnode.start << PAGE_SHIFT;
-	panfrost_gem_mapping_put(mapping);
-
-	return 0;
+out:
+	drm_gem_object_put(&bo->base.base);
+	return ret;
 }
 
 /**

drivers/gpu/drm/panfrost/panfrost_gem.c

···
 }
 
 struct panfrost_gem_object *
-panfrost_gem_create_with_handle(struct drm_file *file_priv,
-				struct drm_device *dev, size_t size,
-				u32 flags,
-				uint32_t *handle)
+panfrost_gem_create(struct drm_device *dev, size_t size, u32 flags)
 {
-	int ret;
 	struct drm_gem_shmem_object *shmem;
 	struct panfrost_gem_object *bo;
 
···
 	bo = to_panfrost_bo(&shmem->base);
 	bo->noexec = !!(flags & PANFROST_BO_NOEXEC);
 	bo->is_heap = !!(flags & PANFROST_BO_HEAP);
-
-	/*
-	 * Allocate an id of idr table where the obj is registered
-	 * and handle has the id what user can see.
-	 */
-	ret = drm_gem_handle_create(file_priv, &shmem->base, handle);
-	/* drop reference from allocate - handle holds it now. */
-	drm_gem_object_put(&shmem->base);
-	if (ret)
-		return ERR_PTR(ret);
 
 	return bo;
 }

drivers/gpu/drm/panfrost/panfrost_gem.h

···
 				   struct sg_table *sgt);
 
 struct panfrost_gem_object *
-panfrost_gem_create_with_handle(struct drm_file *file_priv,
-				struct drm_device *dev, size_t size,
-				u32 flags,
-				uint32_t *handle);
+panfrost_gem_create(struct drm_device *dev, size_t size, u32 flags);
 
 int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv);
 void panfrost_gem_close(struct drm_gem_object *obj,

drivers/gpu/drm/scheduler/sched_entity.c

···
 	init_completion(&entity->entity_idle);
 
 	/* We start in an idle state. */
-	complete(&entity->entity_idle);
+	complete_all(&entity->entity_idle);
 
 	spin_lock_init(&entity->rq_lock);
 	spsc_queue_init(&entity->job_queue);

drivers/gpu/drm/scheduler/sched_main.c

···
 		sched_job = drm_sched_entity_pop_job(entity);
 
 		if (!sched_job) {
-			complete(&entity->entity_idle);
+			complete_all(&entity->entity_idle);
 			continue;
 		}
 
···
 
 		trace_drm_run_job(sched_job, entity);
 		fence = sched->ops->run_job(sched_job);
-		complete(&entity->entity_idle);
+		complete_all(&entity->entity_idle);
 		drm_sched_fence_scheduled(s_fence);
 
 		if (!IS_ERR_OR_NULL(fence)) {

drivers/gpu/drm/tests/Makefile

···
 	drm_mm_test.o \
 	drm_plane_helper_test.o \
 	drm_rect_test.o
+
+CFLAGS_drm_mm_test.o := $(DISABLE_STRUCTLEAK_PLUGIN)

drivers/gpu/drm/tests/drm_mm_test.c

···
 	return false;
 }
 
-static bool check_reserve_boundaries(struct kunit *test, struct drm_mm *mm,
-				     unsigned int count,
-				     u64 size)
+static bool noinline_for_stack check_reserve_boundaries(struct kunit *test, struct drm_mm *mm,
+							unsigned int count,
+							u64 size)
 {
 	const struct boundary {
 		u64 start, size;

drivers/gpu/drm/virtio/virtgpu_object.c

···
 	struct virtio_gpu_object_array *objs = NULL;
 	struct drm_gem_shmem_object *shmem_obj;
 	struct virtio_gpu_object *bo;
-	struct virtio_gpu_mem_entry *ents;
+	struct virtio_gpu_mem_entry *ents = NULL;
 	unsigned int nents;
 	int ret;
 
···
 		ret = -ENOMEM;
 		objs = virtio_gpu_array_alloc(1);
 		if (!objs)
-			goto err_put_id;
+			goto err_free_entry;
 		virtio_gpu_array_add_obj(objs, &bo->base.base);
 
 		ret = virtio_gpu_array_lock_resv(objs);
···
 
 err_put_objs:
 	virtio_gpu_array_put_free(objs);
+err_free_entry:
+	kvfree(ents);
 err_put_id:
 	virtio_gpu_resource_id_put(vgdev, bo->hw_res_handle);
 err_free_gem:

drivers/infiniband/hw/mlx5/counters.c

···
 	const struct mlx5_ib_counters *cnts = get_counters(dev, port_num - 1);
 	struct mlx5_core_dev *mdev;
 	int ret, num_counters;
-	u32 mdev_port_num;
 
 	if (!stats)
 		return -EINVAL;
···
 	}
 
 	if (MLX5_CAP_GEN(dev->mdev, cc_query_allowed)) {
-		mdev = mlx5_ib_get_native_port_mdev(dev, port_num,
-						    &mdev_port_num);
+		if (!port_num)
+			port_num = 1;
+		mdev = mlx5_ib_get_native_port_mdev(dev, port_num, NULL);
 		if (!mdev) {
 			/* If port is not affiliated yet, its in down state
 			 * which doesn't have any counters yet, so it would be

drivers/infiniband/hw/mlx5/qp.c

···
 	return false;
 }
 
+static int validate_rd_atomic(struct mlx5_ib_dev *dev, struct ib_qp_attr *attr,
+			      int attr_mask, enum ib_qp_type qp_type)
+{
+	int log_max_ra_res;
+	int log_max_ra_req;
+
+	if (qp_type == MLX5_IB_QPT_DCI) {
+		log_max_ra_res = 1 << MLX5_CAP_GEN(dev->mdev,
+						   log_max_ra_res_dc);
+		log_max_ra_req = 1 << MLX5_CAP_GEN(dev->mdev,
+						   log_max_ra_req_dc);
+	} else {
+		log_max_ra_res = 1 << MLX5_CAP_GEN(dev->mdev,
+						   log_max_ra_res_qp);
+		log_max_ra_req = 1 << MLX5_CAP_GEN(dev->mdev,
+						   log_max_ra_req_qp);
+	}
+
+	if (attr_mask & IB_QP_MAX_QP_RD_ATOMIC &&
+	    attr->max_rd_atomic > log_max_ra_res) {
+		mlx5_ib_dbg(dev, "invalid max_rd_atomic value %d\n",
+			    attr->max_rd_atomic);
+		return false;
+	}
+
+	if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC &&
+	    attr->max_dest_rd_atomic > log_max_ra_req) {
+		mlx5_ib_dbg(dev, "invalid max_dest_rd_atomic value %d\n",
+			    attr->max_dest_rd_atomic);
+		return false;
+	}
+	return true;
+}
+
 int mlx5_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 		      int attr_mask, struct ib_udata *udata)
 {
···
 		goto out;
 	}
 
-	if (attr_mask & IB_QP_MAX_QP_RD_ATOMIC &&
-	    attr->max_rd_atomic >
-	    (1 << MLX5_CAP_GEN(dev->mdev, log_max_ra_res_qp))) {
-		mlx5_ib_dbg(dev, "invalid max_rd_atomic value %d\n",
-			    attr->max_rd_atomic);
+	if (!validate_rd_atomic(dev, attr, attr_mask, qp_type))
 		goto out;
-	}
-
-	if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC &&
-	    attr->max_dest_rd_atomic >
-	    (1 << MLX5_CAP_GEN(dev->mdev, log_max_ra_req_qp))) {
-		mlx5_ib_dbg(dev, "invalid max_dest_rd_atomic value %d\n",
-			    attr->max_dest_rd_atomic);
-		goto out;
-	}
 
 	if (cur_state == new_state && cur_state == IB_QPS_RESET) {
 		err = 0;

drivers/infiniband/ulp/srp/ib_srp.h

···
 	SRP_DEFAULT_CMD_SQ_SIZE = SRP_DEFAULT_QUEUE_SIZE - SRP_RSP_SQ_SIZE -
 				  SRP_TSK_MGMT_SQ_SIZE,
 
-	SRP_TAG_NO_REQ		= ~0U,
-	SRP_TAG_TSK_MGMT	= 1U << 31,
-
 	SRP_MAX_PAGES_PER_MR	= 512,
 
 	SRP_MAX_ADD_CDB_LEN	= 16,
···
 	SRP_IMM_DATA_OFFSET	= sizeof(struct srp_cmd) +
 				  SRP_MAX_ADD_CDB_LEN +
 				  sizeof(struct srp_imm_buf),
+};
+
+enum {
+	SRP_TAG_NO_REQ		= ~0U,
+	SRP_TAG_TSK_MGMT	= BIT(31),
 };
 
 enum srp_target_state {

drivers/md/dm.c

···
 		 * otherwise associated queue_limits won't be imposed.
 		 */
 		bio = bio_split_to_limits(bio);
+		if (!bio)
+			return;
 	}
 
 	init_clone_info(&ci, md, map, bio, is_abnormal);

drivers/md/md.c

···
 	}
 
 	bio = bio_split_to_limits(bio);
+	if (!bio)
+		return;
 
 	if (mddev->ro == MD_RDONLY && unlikely(rw == WRITE)) {
 		if (bio_sectors(bio) != 0)

drivers/net/bonding/bond_3ad.c

···
 			slave_err(bond->dev, port->slave->dev,
 				  "Port %d did not find a suitable aggregator\n",
 				  port->actor_port_number);
+			return;
 		}
 	}
 	/* if all aggregator's ports are READY_N == TRUE, set ready=TRUE

drivers/net/bonding/bond_main.c

···
 
 static void bond_miimon_commit(struct bonding *bond)
 {
-	struct slave *slave, *primary;
+	struct slave *slave, *primary, *active;
 	bool do_failover = false;
 	struct list_head *iter;
+
+	ASSERT_RTNL();
 
 	bond_for_each_slave(bond, slave, iter) {
 		switch (slave->link_new_state) {
···
 
 			bond_miimon_link_change(bond, slave, BOND_LINK_UP);
 
-			if (!rcu_access_pointer(bond->curr_active_slave) || slave == primary ||
-			    slave->prio > rcu_dereference(bond->curr_active_slave)->prio)
+			active = rtnl_dereference(bond->curr_active_slave);
+			if (!active || slave == primary || slave->prio > active->prio)
 				do_failover = true;
 
 			continue;

drivers/net/dsa/mv88e6xxx/Kconfig

···
 config NET_DSA_MV88E6XXX
 	tristate "Marvell 88E6xxx Ethernet switch fabric support"
 	depends on NET_DSA
-	depends on PTP_1588_CLOCK_OPTIONAL
 	select IRQ_DOMAIN
 	select NET_DSA_TAG_EDSA
 	select NET_DSA_TAG_DSA
···
 config NET_DSA_MV88E6XXX_PTP
 	bool "PTP support for Marvell 88E6xxx"
 	default n
-	depends on NET_DSA_MV88E6XXX && PTP_1588_CLOCK
+	depends on (NET_DSA_MV88E6XXX = y && PTP_1588_CLOCK = y) || \
+	           (NET_DSA_MV88E6XXX = m && PTP_1588_CLOCK)
 	help
 	  Say Y to enable PTP hardware timestamping on Marvell 88E6xxx switch
 	  chips that support it.

drivers/net/dsa/qca/qca8k-8xxx.c

···
 }
 
 static int
-qca8k_set_lo(struct qca8k_priv *priv, int phy_id, u32 regnum, u16 lo)
+qca8k_mii_write_lo(struct mii_bus *bus, int phy_id, u32 regnum, u32 val)
 {
-	u16 *cached_lo = &priv->mdio_cache.lo;
-	struct mii_bus *bus = priv->bus;
 	int ret;
+	u16 lo;
 
-	if (lo == *cached_lo)
-		return 0;
-
+	lo = val & 0xffff;
 	ret = bus->write(bus, phy_id, regnum, lo);
 	if (ret < 0)
 		dev_err_ratelimited(&bus->dev,
 				    "failed to write qca8k 32bit lo register\n");
 
-	*cached_lo = lo;
-	return 0;
+	return ret;
 }
 
 static int
-qca8k_set_hi(struct qca8k_priv *priv, int phy_id, u32 regnum, u16 hi)
+qca8k_mii_write_hi(struct mii_bus *bus, int phy_id, u32 regnum, u32 val)
 {
-	u16 *cached_hi = &priv->mdio_cache.hi;
-	struct mii_bus *bus = priv->bus;
 	int ret;
+	u16 hi;
 
-	if (hi == *cached_hi)
-		return 0;
-
+	hi = (u16)(val >> 16);
 	ret = bus->write(bus, phy_id, regnum, hi);
 	if (ret < 0)
 		dev_err_ratelimited(&bus->dev,
 				    "failed to write qca8k 32bit hi register\n");
 
-	*cached_hi = hi;
+	return ret;
+}
+
+static int
+qca8k_mii_read_lo(struct mii_bus *bus, int phy_id, u32 regnum, u32 *val)
+{
+	int ret;
+
+	ret = bus->read(bus, phy_id, regnum);
+	if (ret < 0)
+		goto err;
+
+	*val = ret & 0xffff;
 	return 0;
+
+err:
+	dev_err_ratelimited(&bus->dev,
+			    "failed to read qca8k 32bit lo register\n");
+	*val = 0;
+
+	return ret;
+}
+
+static int
+qca8k_mii_read_hi(struct mii_bus *bus, int phy_id, u32 regnum, u32 *val)
+{
+	int ret;
+
+	ret = bus->read(bus, phy_id, regnum);
+	if (ret < 0)
+		goto err;
+
+	*val = ret << 16;
+	return 0;
+
+err:
+	dev_err_ratelimited(&bus->dev,
+			    "failed to read qca8k 32bit hi register\n");
+	*val = 0;
+
+	return ret;
 }
 
 static int
 qca8k_mii_read32(struct mii_bus *bus, int phy_id, u32 regnum, u32 *val)
 {
+	u32 hi, lo;
 	int ret;
 
-	ret = bus->read(bus, phy_id, regnum);
-	if (ret >= 0) {
-		*val = ret;
-		ret = bus->read(bus, phy_id, regnum + 1);
-		*val |= ret << 16;
-	}
+	*val = 0;
 
-	if (ret < 0) {
-		dev_err_ratelimited(&bus->dev,
-				    "failed to read qca8k 32bit register\n");
-		*val = 0;
-		return ret;
-	}
+	ret = qca8k_mii_read_lo(bus, phy_id, regnum, &lo);
+	if (ret < 0)
+		goto err;
 
-	return 0;
+	ret = qca8k_mii_read_hi(bus, phy_id, regnum + 1, &hi);
+	if (ret < 0)
+		goto err;
+
+	*val = lo | hi;
+
+err:
+	return ret;
 }
 
 static void
-qca8k_mii_write32(struct qca8k_priv *priv, int phy_id, u32 regnum, u32 val)
+qca8k_mii_write32(struct mii_bus *bus, int phy_id, u32 regnum, u32 val)
 {
-	u16 lo, hi;
-	int ret;
+	if (qca8k_mii_write_lo(bus, phy_id, regnum, val) < 0)
+		return;
 
-	lo = val & 0xffff;
-	hi = (u16)(val >> 16);
-
-	ret = qca8k_set_lo(priv, phy_id, regnum, lo);
-	if (ret >= 0)
-		ret = qca8k_set_hi(priv, phy_id, regnum + 1, hi);
+	qca8k_mii_write_hi(bus, phy_id, regnum + 1, val);
 }
 
 static int
···
 
 	command = get_unaligned_le32(&mgmt_ethhdr->command);
 	cmd = FIELD_GET(QCA_HDR_MGMT_CMD, command);
+
 	len = FIELD_GET(QCA_HDR_MGMT_LENGTH, command);
+	/* Special case for len of 15 as this is the max value for len and needs to
+	 * be increased before converting it from word to dword.
+	 */
+	if (len == 15)
+		len++;
+
+	/* We can ignore odd value, we always round up them in the alloc function. */
+	len *= sizeof(u16);
 
 	/* Make sure the seq match the requested packet */
 	if (get_unaligned_le32(&mgmt_ethhdr->seq) == mgmt_eth_data->seq)
···
 	if (!skb)
 		return NULL;
 
-	/* Max value for len reg is 15 (0xf) but the switch actually return 16 byte
-	 * Actually for some reason the steps are:
-	 * 0: nothing
-	 * 1-4: first 4 byte
-	 * 5-6: first 12 byte
-	 * 7-15: all 16 byte
+	/* Hdr mgmt length value is in step of word size.
+	 * As an example to process 4 byte of data the correct length to set is 2.
+	 * To process 8 byte 4, 12 byte 6, 16 byte 8...
+	 *
+	 * Odd values will always return the next size on the ack packet.
+	 * (length of 3 (6 byte) will always return 8 bytes of data)
+	 *
+	 * This means that a value of 15 (0xf) actually means reading/writing 32 bytes
+	 * of data.
+	 *
+	 * To correctly calculate the length we devide the requested len by word and
+	 * round up.
+	 * On the ack function we can skip the odd check as we already handle the
+	 * case here.
 	 */
-	if (len == 16)
-		real_len = 15;
-	else
-		real_len = len;
+	real_len = DIV_ROUND_UP(len, sizeof(u16));
+
+	/* We check if the result len is odd and we round up another time to
+	 * the next size. (length of 3 will be increased to 4 as switch will always
+	 * return 8 bytes)
+	 */
+	if (real_len % sizeof(u16) != 0)
+		real_len++;
+
+	/* Max reg value is 0xf(15) but switch will always return the next size (32 byte) */
+	if (real_len == 16)
+		real_len--;
 
 	skb_reset_mac_header(skb);
 	skb_set_network_header(skb, skb->len);
···
 	if (ret < 0)
 		goto exit;
 
-	qca8k_mii_write32(priv, 0x10 | r2, r1, val);
+	qca8k_mii_write32(bus, 0x10 | r2, r1, val);
 
 exit:
 	mutex_unlock(&bus->mdio_lock);
···
 
 	val &= ~mask;
 	val |= write_val;
-	qca8k_mii_write32(priv, 0x10 | r2, r1, val);
+	qca8k_mii_write32(bus, 0x10 | r2, r1, val);
 
 exit:
 	mutex_unlock(&bus->mdio_lock);
···
 
 	qca8k_split_addr(reg, &r1, &r2, &page);
 
-	ret = read_poll_timeout(qca8k_mii_read32, ret1, !(val & mask), 0,
+	ret = read_poll_timeout(qca8k_mii_read_hi, ret1, !(val & mask), 0,
 				QCA8K_BUSY_WAIT_TIMEOUT * USEC_PER_MSEC, false,
-				bus, 0x10 | r2, r1, &val);
+				bus, 0x10 | r2, r1 + 1, &val);
 
 	/* Check if qca8k_read has failed for a different reason
 	 * before returnting -ETIMEDOUT
···
 	if (ret)
 		goto exit;
 
-	qca8k_mii_write32(priv, 0x10 | r2, r1, val);
+	qca8k_mii_write32(bus, 0x10 | r2, r1, val);
 
 	ret = qca8k_mdio_busy_wait(bus, QCA8K_MDIO_MASTER_CTRL,
 				   QCA8K_MDIO_MASTER_BUSY);
 
 exit:
 	/* even if the busy_wait timeouts try to clear the MASTER_EN */
-	qca8k_mii_write32(priv, 0x10 | r2, r1, 0);
+	qca8k_mii_write_hi(bus, 0x10 | r2, r1 + 1, 0);
 
 	mutex_unlock(&bus->mdio_lock);
 
···
 	if (ret)
 		goto exit;
 
-	qca8k_mii_write32(priv, 0x10 | r2, r1, val);
+	qca8k_mii_write_hi(bus, 0x10 | r2, r1 + 1, val);
 
 	ret = qca8k_mdio_busy_wait(bus, QCA8K_MDIO_MASTER_CTRL,
 				   QCA8K_MDIO_MASTER_BUSY);
 	if (ret)
 		goto exit;
 
-	ret = qca8k_mii_read32(bus, 0x10 | r2, r1, &val);
+	ret = qca8k_mii_read_lo(bus, 0x10 | r2, r1, &val);
 
 exit:
 	/* even if the busy_wait timeouts try to clear the MASTER_EN */
-	qca8k_mii_write32(priv, 0x10 | r2, r1, 0);
+	qca8k_mii_write_hi(bus, 0x10 | r2, r1 + 1, 0);
 
 	mutex_unlock(&bus->mdio_lock);
 
···
 	}
 
 	priv->mdio_cache.page = 0xffff;
-	priv->mdio_cache.lo = 0xffff;
-	priv->mdio_cache.hi = 0xffff;
 
 	/* Check the detected switch id */
 	ret = qca8k_read_switch_id(priv);

drivers/net/dsa/qca/qca8k.h

···
  * mdio writes
  */
 	u16 page;
-/* lo and hi can also be cached and from Documentation we can skip one
- * extra mdio write if lo or hi is didn't change.
- */
-	u16 lo;
-	u16 hi;
 };
 
 struct qca8k_pcs {

drivers/net/ethernet/amazon/ena/ena_com.c

···
 		return -EOPNOTSUPP;
 	}
 
-	switch (func) {
-	case ENA_ADMIN_TOEPLITZ:
-		if (key) {
-			if (key_len != sizeof(hash_key->key)) {
-				netdev_err(ena_dev->net_device,
-					   "key len (%u) doesn't equal the supported size (%zu)\n",
-					   key_len, sizeof(hash_key->key));
-				return -EINVAL;
-			}
-			memcpy(hash_key->key, key, key_len);
-			rss->hash_init_val = init_val;
-			hash_key->key_parts = key_len / sizeof(hash_key->key[0]);
+	if ((func == ENA_ADMIN_TOEPLITZ) && key) {
+		if (key_len != sizeof(hash_key->key)) {
+			netdev_err(ena_dev->net_device,
+				   "key len (%u) doesn't equal the supported size (%zu)\n",
+				   key_len, sizeof(hash_key->key));
+			return -EINVAL;
 		}
-		break;
-	case ENA_ADMIN_CRC32:
-		rss->hash_init_val = init_val;
-		break;
-	default:
-		netdev_err(ena_dev->net_device, "Invalid hash function (%d)\n",
-			   func);
-		return -EINVAL;
+		memcpy(hash_key->key, key, key_len);
+		hash_key->key_parts = key_len / sizeof(hash_key->key[0]);
 	}
 
+	rss->hash_init_val = init_val;
 	old_func = rss->hash_func;
 	rss->hash_func = func;
 	rc = ena_com_set_hash_function(ena_dev);

drivers/net/ethernet/amazon/ena/ena_ethtool.c

···
 	switch (tuna->id) {
 	case ETHTOOL_RX_COPYBREAK:
 		len = *(u32 *)data;
-		if (len > adapter->netdev->mtu) {
-			ret = -EINVAL;
-			break;
-		}
-		adapter->rx_copybreak = len;
+		ret = ena_set_rx_copybreak(adapter, len);
 		break;
 	default:
 		ret = -EINVAL;

drivers/net/ethernet/amazon/ena/ena_netdev.c

···
 
 static int ena_xdp_execute(struct ena_ring *rx_ring, struct xdp_buff *xdp)
 {
+	u32 verdict = ENA_XDP_PASS;
 	struct bpf_prog *xdp_prog;
 	struct ena_ring *xdp_ring;
-	u32 verdict = XDP_PASS;
 	struct xdp_frame *xdpf;
 	u64 *xdp_stat;
 
···
 		if (unlikely(!xdpf)) {
 			trace_xdp_exception(rx_ring->netdev, xdp_prog, verdict);
 			xdp_stat = &rx_ring->rx_stats.xdp_aborted;
-			verdict = XDP_ABORTED;
+			verdict = ENA_XDP_DROP;
 			break;
 		}
 
···
 
 		spin_unlock(&xdp_ring->xdp_tx_lock);
 		xdp_stat = &rx_ring->rx_stats.xdp_tx;
+		verdict = ENA_XDP_TX;
 		break;
 	case XDP_REDIRECT:
 		if (likely(!xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog))) {
 			xdp_stat = &rx_ring->rx_stats.xdp_redirect;
+			verdict = ENA_XDP_REDIRECT;
 			break;
 		}
 		trace_xdp_exception(rx_ring->netdev, xdp_prog, verdict);
 		xdp_stat = &rx_ring->rx_stats.xdp_aborted;
-		verdict = XDP_ABORTED;
+		verdict = ENA_XDP_DROP;
 		break;
 	case XDP_ABORTED:
 		trace_xdp_exception(rx_ring->netdev, xdp_prog, verdict);
 		xdp_stat = &rx_ring->rx_stats.xdp_aborted;
+		verdict = ENA_XDP_DROP;
 		break;
 	case XDP_DROP:
 		xdp_stat = &rx_ring->rx_stats.xdp_drop;
+		verdict = ENA_XDP_DROP;
 		break;
 	case XDP_PASS:
 		xdp_stat = &rx_ring->rx_stats.xdp_pass;
+		verdict = ENA_XDP_PASS;
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, verdict);
 		xdp_stat = &rx_ring->rx_stats.xdp_invalid;
+		verdict = ENA_XDP_DROP;
 	}
 
 	ena_increase_stat(xdp_stat, 1, &rx_ring->syncp);
···
 						 struct bpf_prog *prog,
 						 int first, int count)
 {
+	struct bpf_prog *old_bpf_prog;
 	struct ena_ring *rx_ring;
 	int i = 0;
 
 	for (i = first; i < count; i++) {
 		rx_ring = &adapter->rx_ring[i];
-		xchg(&rx_ring->xdp_bpf_prog, prog);
-		if (prog) {
+		old_bpf_prog = xchg(&rx_ring->xdp_bpf_prog, prog);
+
+		if (!old_bpf_prog && prog) {
 			ena_xdp_register_rxq_info(rx_ring);
 			rx_ring->rx_headroom = XDP_PACKET_HEADROOM;
-		} else {
+		} else if (old_bpf_prog && !prog) {
 			ena_xdp_unregister_rxq_info(rx_ring);
 			rx_ring->rx_headroom = NET_SKB_PAD;
 		}
···
 	ring->ena_dev = adapter->ena_dev;
 	ring->per_napi_packets = 0;
 	ring->cpu = 0;
+	ring->numa_node = 0;
 	ring->no_interrupt_event_cnt = 0;
 	u64_stats_init(&ring->syncp);
 }
···
 	tx_ring->next_to_use = 0;
 	tx_ring->next_to_clean = 0;
 	tx_ring->cpu = ena_irq->cpu;
+	tx_ring->numa_node = node;
 	return 0;
 
 err_push_buf_intermediate_buf:
···
 	rx_ring->next_to_clean = 0;
 	rx_ring->next_to_use = 0;
 	rx_ring->cpu = ena_irq->cpu;
+	rx_ring->numa_node = node;
 
 	return 0;
 }
···
 	 * we expect, then we simply drop it
 	 */
 	if (unlikely(rx_ring->ena_bufs[0].len > ENA_XDP_MAX_MTU))
-		return XDP_DROP;
+		return ENA_XDP_DROP;
 
 	ret = ena_xdp_execute(rx_ring, xdp);
 
 	/* The xdp program might expand the headers */
-	if (ret == XDP_PASS) {
+	if (ret == ENA_XDP_PASS) {
 		rx_info->page_offset = xdp->data - xdp->data_hard_start;
 		rx_ring->ena_bufs[0].len = xdp->data_end - xdp->data;
 	}
···
 	xdp_init_buff(&xdp, ENA_PAGE_SIZE, &rx_ring->xdp_rxq);
 
 	do {
-		xdp_verdict = XDP_PASS;
+		xdp_verdict = ENA_XDP_PASS;
 		skb = NULL;
 		ena_rx_ctx.ena_bufs = rx_ring->ena_bufs;
 		ena_rx_ctx.max_bufs = rx_ring->sgl_size;
···
 			xdp_verdict = ena_xdp_handle_buff(rx_ring, &xdp);
 
 		/* allocate skb and fill it */
-		if (xdp_verdict == XDP_PASS)
+		if (xdp_verdict == ENA_XDP_PASS)
 			skb = ena_rx_skb(rx_ring,
 					 rx_ring->ena_bufs,
 					 ena_rx_ctx.descs,
···
 				/* Packets was passed for transmission, unmap it
 				 * from RX side.
 				 */
-				if (xdp_verdict == XDP_TX || xdp_verdict == XDP_REDIRECT) {
+				if (xdp_verdict & ENA_XDP_FORWARDED) {
 					ena_unmap_rx_buff(rx_ring,
 							  &rx_ring->rx_buffer_info[req_id]);
 					rx_ring->rx_buffer_info[req_id].page = NULL;
 				}
 			}
-			if (xdp_verdict != XDP_PASS) {
+			if (xdp_verdict != ENA_XDP_PASS) {
 				xdp_flags |= xdp_verdict;
+				total_len += ena_rx_ctx.ena_bufs[0].len;
 				res_budget--;
 				continue;
 			}
···
 		ena_refill_rx_bufs(rx_ring, refill_required);
 	}
 
-	if (xdp_flags & XDP_REDIRECT)
+	if (xdp_flags & ENA_XDP_REDIRECT)
 		xdp_do_flush_map();
 
 	return work_done;
···
 static void ena_unmask_interrupt(struct ena_ring *tx_ring,
 					struct ena_ring *rx_ring)
 {
+	u32 rx_interval = tx_ring->smoothed_interval;
 	struct ena_eth_io_intr_reg intr_reg;
-	u32 rx_interval = 0;
+
 	/* Rx ring can be NULL when for XDP tx queues which don't have an
 	 * accompanying rx_ring pair.
 	 */
···
 	if (likely(tx_ring->cpu == cpu))
 		goto out;
 
+	tx_ring->cpu = cpu;
+	if (rx_ring)
+		rx_ring->cpu = cpu;
+
 	numa_node = cpu_to_node(cpu);
+
+	if (likely(tx_ring->numa_node == numa_node))
+		goto out;
+
 	put_cpu();
 
 	if (numa_node != NUMA_NO_NODE) {
 		ena_com_update_numa_node(tx_ring->ena_com_io_cq, numa_node);
-		if (rx_ring)
+		tx_ring->numa_node = numa_node;
+		if (rx_ring) {
+			rx_ring->numa_node = numa_node;
 			ena_com_update_numa_node(rx_ring->ena_com_io_cq,
 						 numa_node);
+		}
 	}
-
-	tx_ring->cpu = cpu;
-	if (rx_ring)
-		rx_ring->cpu = cpu;
 
 	return;
 out:
···
 			if (ena_com_get_adaptive_moderation_enabled(rx_ring->ena_dev))
 				ena_adjust_adaptive_rx_intr_moderation(ena_napi);
 
+			ena_update_ring_numa_node(tx_ring, rx_ring);
 			ena_unmask_interrupt(tx_ring, rx_ring);
 		}
-
-		ena_update_ring_numa_node(tx_ring, rx_ring);
 
 		ret = rx_work_done;
 	} else {
···
 	ctx.mem_queue_type = ena_dev->tx_mem_queue_type;
 	ctx.msix_vector = msix_vector;
 	ctx.queue_size = tx_ring->ring_size;
-	ctx.numa_node = cpu_to_node(tx_ring->cpu);
+	ctx.numa_node = tx_ring->numa_node;
 
 	rc = ena_com_create_io_queue(ena_dev, &ctx);
 	if (rc) {
···
 	ctx.mem_queue_type = ENA_ADMIN_PLACEMENT_POLICY_HOST;
 	ctx.msix_vector = msix_vector;
 	ctx.queue_size = rx_ring->ring_size;
-	ctx.numa_node = cpu_to_node(rx_ring->cpu);
+	ctx.numa_node = rx_ring->numa_node;
 
 	rc = ena_com_create_io_queue(ena_dev, &ctx);
 	if (rc) {
···
 			  adapter->xdp_num_queues +
 			  adapter->num_io_queues);
 	return dev_was_up ? ena_up(adapter) : 0;
+}
+
+int ena_set_rx_copybreak(struct ena_adapter *adapter, u32 rx_copybreak)
+{
+	struct ena_ring *rx_ring;
+	int i;
+
+	if (rx_copybreak > min_t(u16, adapter->netdev->mtu, ENA_PAGE_SIZE))
+		return -EINVAL;
+
+	adapter->rx_copybreak = rx_copybreak;
+
+	for (i = 0; i < adapter->num_io_queues; i++) {
+		rx_ring = &adapter->rx_ring[i];
+		rx_ring->rx_copybreak = rx_copybreak;
+	}
+
+	return 0;
 }
 
 int ena_update_queue_count(struct ena_adapter *adapter, u32 new_channel_count)

drivers/net/ethernet/amazon/ena/ena_netdev.h

···
 	bool disable_meta_caching;
 	u16 no_interrupt_event_cnt;
 
-	/* cpu for TPH */
+	/* cpu and NUMA for TPH */
 	int cpu;
-	 /* number of tx/rx_buffer_info's entries */
+	int numa_node;
+
+	/* number of tx/rx_buffer_info's entries */
 	int ring_size;
 
 	enum ena_admin_placement_policy_type tx_mem_queue_type;
···
 
 int ena_update_queue_count(struct ena_adapter *adapter, u32 new_channel_count);
 
+int ena_set_rx_copybreak(struct ena_adapter *adapter, u32 rx_copybreak);
+
 int ena_get_sset_count(struct net_device *netdev, int sset);
 
 static inline void ena_reset_device(struct ena_adapter *adapter,
···
 	ENA_XDP_CURRENT_MTU_TOO_LARGE,
 	ENA_XDP_NO_ENOUGH_QUEUES,
 };
+
+enum ENA_XDP_ACTIONS {
+	ENA_XDP_PASS		= 0,
+	ENA_XDP_TX		= BIT(0),
+	ENA_XDP_REDIRECT	= BIT(1),
+	ENA_XDP_DROP		= BIT(2)
+};
+
+#define ENA_XDP_FORWARDED (ENA_XDP_TX | ENA_XDP_REDIRECT)
 
 static inline bool ena_xdp_present(struct ena_adapter *adapter)
 {

drivers/net/ethernet/amd/xgbe/xgbe-drv.c

···
 
 	devm_free_irq(pdata->dev, pdata->dev_irq, pdata);
 
+	tasklet_kill(&pdata->tasklet_dev);
+	tasklet_kill(&pdata->tasklet_ecc);
+
 	if (pdata->vdata->ecc_support && (pdata->dev_irq != pdata->ecc_irq))
 		devm_free_irq(pdata->dev, pdata->ecc_irq, pdata);
 

drivers/net/ethernet/amd/xgbe/xgbe-i2c.c

···
 	xgbe_i2c_disable(pdata);
 	xgbe_i2c_clear_all_interrupts(pdata);
 
-	if (pdata->dev_irq != pdata->i2c_irq)
+	if (pdata->dev_irq != pdata->i2c_irq) {
 		devm_free_irq(pdata->dev, pdata->i2c_irq, pdata);
+		tasklet_kill(&pdata->tasklet_i2c);
+	}
 }
 
 static int xgbe_i2c_start(struct xgbe_prv_data *pdata)

drivers/net/ethernet/amd/xgbe/xgbe-mdio.c

···
 	/* Disable auto-negotiation */
 	xgbe_an_disable_all(pdata);
 
-	if (pdata->dev_irq != pdata->an_irq)
+	if (pdata->dev_irq != pdata->an_irq) {
 		devm_free_irq(pdata->dev, pdata->an_irq, pdata);
+		tasklet_kill(&pdata->tasklet_an);
+	}
 
 	pdata->phy_if.phy_impl.stop(pdata);
 

drivers/net/ethernet/broadcom/bcm63xx_enet.c

···
 	return 0;
 }
 
-static int bcm_enet_shared_remove(struct platform_device *pdev)
-{
-	return 0;
-}
-
 /* this "shared" driver is needed because both macs share a single
  * address space
  */
 struct platform_driver bcm63xx_enet_shared_driver = {
 	.probe	= bcm_enet_shared_probe,
-	.remove	= bcm_enet_shared_remove,
 	.driver	= {
 		.name	= "bcm63xx_enet_shared",
 		.owner  = THIS_MODULE,

drivers/net/ethernet/broadcom/bnxt/bnxt.c

···
 	dma_addr -= bp->rx_dma_offset;
 	dma_unmap_page_attrs(&bp->pdev->dev, dma_addr, PAGE_SIZE, bp->rx_dir,
 			     DMA_ATTR_WEAK_ORDERING);
-	skb = build_skb(page_address(page), BNXT_PAGE_MODE_BUF_SIZE +
-					    bp->rx_dma_offset);
+	skb = build_skb(page_address(page), PAGE_SIZE);
 	if (!skb) {
 		__free_page(page);
 		return NULL;
···
 	dma_addr = rx_buf->mapping;
 
 	if (bnxt_xdp_attached(bp, rxr)) {
-		bnxt_xdp_buff_init(bp, rxr, cons, &data_ptr, &len, &xdp);
+		bnxt_xdp_buff_init(bp, rxr, cons, data_ptr, len, &xdp);
 		if (agg_bufs) {
 			u32 frag_len = bnxt_rx_agg_pages_xdp(bp, cpr, &xdp,
 							     cp_cons, agg_bufs,
···
 	}
 
 	if (xdp_active) {
-		if (bnxt_rx_xdp(bp, rxr, cons, xdp, data, &len, event)) {
+		if (bnxt_rx_xdp(bp, rxr, cons, xdp, data, &data_ptr, &len, event)) {
 			rc = 1;
 			goto next_rx;
 		}
···
 		bp->rx_agg_ring_mask = (bp->rx_agg_nr_pages * RX_DESC_CNT) - 1;
 
 		if (BNXT_RX_PAGE_MODE(bp)) {
-			rx_space = BNXT_PAGE_MODE_BUF_SIZE;
-			rx_size = BNXT_MAX_PAGE_MODE_MTU;
+			rx_space = PAGE_SIZE;
+			rx_size = PAGE_SIZE -
+				  ALIGN(max(NET_SKB_PAD, XDP_PACKET_HEADROOM), 8) -
+				  SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 		} else {
 			rx_size = SKB_DATA_ALIGN(BNXT_RX_COPY_THRESH + NET_IP_ALIGN);
 			rx_space = rx_size + NET_SKB_PAD +
···
 	req->flags = cpu_to_le32(VNIC_PLCMODES_CFG_REQ_FLAGS_JUMBO_PLACEMENT);
 	req->enables = cpu_to_le32(VNIC_PLCMODES_CFG_REQ_ENABLES_JUMBO_THRESH_VALID);
 
-	if (BNXT_RX_PAGE_MODE(bp) && !BNXT_RX_JUMBO_MODE(bp)) {
+	if (BNXT_RX_PAGE_MODE(bp)) {
+		req->jumbo_thresh = cpu_to_le16(bp->rx_buf_use_size);
+	} else {
 		req->flags |= cpu_to_le32(VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV4 |
 					  VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV6);
 		req->enables |=
 			cpu_to_le32(VNIC_PLCMODES_CFG_REQ_ENABLES_HDS_THRESHOLD_VALID);
+		req->jumbo_thresh = cpu_to_le16(bp->rx_copy_thresh);
+		req->hds_threshold = cpu_to_le16(bp->rx_copy_thresh);
 	}
-	/* thresholds not implemented in firmware yet */
-	req->jumbo_thresh = cpu_to_le16(bp->rx_copy_thresh);
-	req->hds_threshold = cpu_to_le16(bp->rx_copy_thresh);
 	req->vnic_id = cpu_to_le32(vnic->fw_vnic_id);
 	return hwrm_req_send(bp, req);
 }
···
 		return -ENOMEM;
 
 	bp = netdev_priv(dev);
-	SET_NETDEV_DEVLINK_PORT(dev, &bp->dl_port);
 	bp->board_idx = ent->driver_data;
 	bp->msg_enable = BNXT_DEF_MSG_ENABLE;
 	bnxt_set_max_func_irqs(bp, max_irqs);
 
 	if (bnxt_vf_pciid(bp->board_idx))
 		bp->flags |= BNXT_FLAG_VF;
+
+	/* No devlink port registration in case of a VF */
+	if (BNXT_PF(bp))
+		SET_NETDEV_DEVLINK_PORT(dev, &bp->dl_port);
 
 	if (pdev->msix_cap)
 		bp->flags |= BNXT_FLAG_MSIX_CAP;

drivers/net/ethernet/broadcom/bnxt/bnxt.h

···
 #define BNXT_RX_PAGE_SIZE (1 << BNXT_RX_PAGE_SHIFT)
 
 #define BNXT_MAX_MTU		9500
-#define BNXT_PAGE_MODE_BUF_SIZE \
+
+/* First RX buffer page in XDP multi-buf mode
+ *
+ * +-------------------------------------------------------------------------+
+ * | XDP_PACKET_HEADROOM | bp->rx_buf_use_size              | skb_shared_info|
+ * | (bp->rx_dma_offset) |                                  |                |
+ * +-------------------------------------------------------------------------+
+ */
+#define BNXT_MAX_PAGE_MODE_MTU_SBUF \
 	((unsigned int)PAGE_SIZE - VLAN_ETH_HLEN - NET_IP_ALIGN -	\
 	 XDP_PACKET_HEADROOM)
 #define BNXT_MAX_PAGE_MODE_MTU	\
-	BNXT_PAGE_MODE_BUF_SIZE - \
-	SKB_DATA_ALIGN((unsigned int)sizeof(struct skb_shared_info))
+	(BNXT_MAX_PAGE_MODE_MTU_SBUF - \
+	 SKB_DATA_ALIGN((unsigned int)sizeof(struct skb_shared_info)))
 
 #define BNXT_MIN_PKT_SIZE	52
 
···
 #define BNXT_DUMP_CRASH		1
 
 	struct bpf_prog		*xdp_prog;
-	u8			xdp_has_frags;
 
 	struct bnxt_ptp_cfg	*ptp_cfg;
 	u8			ptp_all_rx_tstamp;

drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c

···
 }
 
 void bnxt_xdp_buff_init(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
-			u16 cons, u8 **data_ptr, unsigned int *len,
+			u16 cons, u8 *data_ptr, unsigned int len,
 			struct xdp_buff *xdp)
 {
 	struct bnxt_sw_rx_bd *rx_buf;
···
 	offset = bp->rx_offset;
 
 	mapping = rx_buf->mapping - bp->rx_dma_offset;
-	dma_sync_single_for_cpu(&pdev->dev, mapping + offset, *len, bp->rx_dir);
-
-	if (bp->xdp_has_frags)
-		buflen = BNXT_PAGE_MODE_BUF_SIZE + offset;
+	dma_sync_single_for_cpu(&pdev->dev, mapping + offset, len, bp->rx_dir);
 
 	xdp_init_buff(xdp, buflen, &rxr->xdp_rxq);
-	xdp_prepare_buff(xdp, *data_ptr - offset, offset, *len, false);
+	xdp_prepare_buff(xdp, data_ptr - offset, offset, len, false);
 }
 
 void bnxt_xdp_buff_frags_free(struct bnxt_rx_ring_info *rxr,
···
  * false   - packet should be passed to the stack.
  */
 bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
-		 struct xdp_buff xdp, struct page *page, unsigned int *len, u8 *event)
+		 struct xdp_buff xdp, struct page *page, u8 **data_ptr,
+		 unsigned int *len, u8 *event)
 {
 	struct bpf_prog *xdp_prog = READ_ONCE(rxr->xdp_prog);
 	struct bnxt_tx_ring_info *txr;
···
 		*event &= ~BNXT_RX_EVENT;
 
 	*len = xdp.data_end - xdp.data;
-	if (orig_data != xdp.data)
+	if (orig_data != xdp.data) {
 		offset = xdp.data - xdp.data_hard_start;
+		*data_ptr = xdp.data_hard_start + offset;
+	}
 
 	switch (act) {
 	case XDP_PASS:
···
 		netdev_warn(dev, "ethtool rx/tx channels must be combined to support XDP.\n");
 		return -EOPNOTSUPP;
 	}
-	if (prog) {
+	if (prog)
 		tx_xdp = bp->rx_nr_rings;
-		bp->xdp_has_frags = prog->aux->xdp_has_frags;
-	}
 
 	tc = netdev_get_num_tc(dev);
 	if (!tc)

drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h

···
 				   struct xdp_buff *xdp);
 void bnxt_tx_int_xdp(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts);
 bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
-		 struct xdp_buff xdp, struct page *page, unsigned int *len,
-		 u8 *event);
+		 struct xdp_buff xdp, struct page *page, u8 **data_ptr,
+		 unsigned int *len, u8 *event);
 int bnxt_xdp(struct net_device *dev, struct netdev_bpf *xdp);
 int bnxt_xdp_xmit(struct net_device *dev, int num_frames,
 		  struct xdp_frame **frames, u32 flags);
···
 bool bnxt_xdp_attached(struct bnxt *bp, struct bnxt_rx_ring_info *rxr);
 
 void bnxt_xdp_buff_init(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
-			u16 cons, u8 **data_ptr, unsigned int *len,
+			u16 cons, u8 *data_ptr, unsigned int len,
 			struct xdp_buff *xdp);
 void bnxt_xdp_buff_frags_free(struct bnxt_rx_ring_info *rxr,
 			      struct xdp_buff *xdp);

drivers/net/ethernet/freescale/enetc/enetc_ierb.c

···
 	return 0;
 }
 
-static int enetc_ierb_remove(struct platform_device *pdev)
-{
-	return 0;
-}
-
 static const struct of_device_id enetc_ierb_match[] = {
 	{ .compatible = "fsl,ls1028a-enetc-ierb", },
 	{},
···
 		.of_match_table = enetc_ierb_match,
 	},
 	.probe = enetc_ierb_probe,
-	.remove = enetc_ierb_remove,
 };
 
 module_platform_driver(enetc_ierb_driver);

drivers/net/ethernet/freescale/fman/fman_dtsec.c

···
 	dtsec->dtsec_drv_param->tx_pad_crc = true;
 
 	phy_node = of_parse_phandle(mac_node, "tbi-handle", 0);
-	if (!phy_node || of_device_is_available(phy_node)) {
+	if (!phy_node || !of_device_is_available(phy_node)) {
 		of_node_put(phy_node);
 		err = -EINVAL;
 		dev_err_probe(mac_dev->dev, err,

drivers/net/ethernet/hisilicon/hns3/hns3_enet.c

···
 	return 0;
 }
 
-static bool hns3_checksum_complete(struct hns3_enet_ring *ring,
+static void hns3_checksum_complete(struct hns3_enet_ring *ring,
 				   struct sk_buff *skb, u32 ptype, u16 csum)
 {
 	if (ptype == HNS3_INVALID_PTYPE ||
 	    hns3_rx_ptype_tbl[ptype].ip_summed != CHECKSUM_COMPLETE)
-		return false;
+		return;
 
 	hns3_ring_stats_update(ring, csum_complete);
 	skb->ip_summed = CHECKSUM_COMPLETE;
 	skb->csum = csum_unfold((__force __sum16)csum);
-
-	return true;
 }
 
 static void hns3_rx_handle_csum(struct sk_buff *skb, u32 l234info,
···
 		ptype = hnae3_get_field(ol_info, HNS3_RXD_PTYPE_M,
 					HNS3_RXD_PTYPE_S);
 
-	if (hns3_checksum_complete(ring, skb, ptype, csum))
-		return;
+	hns3_checksum_complete(ring, skb, ptype, csum);
 
 	/* check if hardware has done checksum */
 	if (!(bd_base_info & BIT(HNS3_RXD_L3L4P_B)))
···
 	if (unlikely(l234info & (BIT(HNS3_RXD_L3E_B) | BIT(HNS3_RXD_L4E_B) |
 				 BIT(HNS3_RXD_OL3E_B) |
 				 BIT(HNS3_RXD_OL4E_B)))) {
+		skb->ip_summed = CHECKSUM_NONE;
 		hns3_ring_stats_update(ring, l3l4_csum_err);
 
 		return;

drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c

···
 			return ret;
 		}
 
-		if (!reset || !test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state))
+		if (!reset ||
+		    !test_bit(HCLGE_VPORT_STATE_INITED, &vport->state))
 			continue;
+
+		if (!test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state) &&
+		    hdev->reset_type == HNAE3_FUNC_RESET) {
+			set_bit(HCLGE_VPORT_NEED_NOTIFY_RESET,
+				&vport->need_notify);
+			continue;
+		}
 
 		/* Inform VF to process the reset.
 		 * hclge_inform_reset_assert_to_vf may fail if VF
···
 
 static void hclge_update_vport_alive(struct hclge_dev *hdev)
 {
+#define HCLGE_ALIVE_SECONDS_NORMAL		8
+
+	unsigned long alive_time = HCLGE_ALIVE_SECONDS_NORMAL * HZ;
 	int i;
 
 	/* start from vport 1 for PF is always alive */
 	for (i = 1; i < hdev->num_alloc_vport; i++) {
 		struct hclge_vport *vport = &hdev->vport[i];
 
-		if (time_after(jiffies, vport->last_active_jiffies + 8 * HZ))
+		if (!test_bit(HCLGE_VPORT_STATE_INITED, &vport->state) ||
+		    !test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state))
+			continue;
+		if (time_after(jiffies, vport->last_active_jiffies +
+			       alive_time)) {
 			clear_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
-
-		/* If vf is not alive, set to default value */
-		if (!test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state))
-			vport->mps = HCLGE_MAC_DEFAULT_FRAME;
+			dev_warn(&hdev->pdev->dev,
+				 "VF %u heartbeat timeout\n",
+				 i - HCLGE_VF_VPORT_START_NUM);
+		}
 	}
 }
 
···
 {
 	struct hclge_dev *hdev = vport->back;
 
+	set_bit(HCLGE_VPORT_STATE_INITED, &vport->state);
 	set_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
 	set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, &vport->state);
 	vport->last_active_jiffies = jiffies;
+	vport->need_notify = 0;
 
 	if (test_bit(vport->vport_id, hdev->vport_config_block)) {
 		if (vport->vport_id) {
···
 
 void hclge_vport_stop(struct hclge_vport *vport)
 {
+	clear_bit(HCLGE_VPORT_STATE_INITED, &vport->state);
 	clear_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
+	vport->need_notify = 0;
 }
 
 static int hclge_client_start(struct hnae3_handle *handle)
···
 		return 0;
 	}
 
-	dev_info(&hdev->pdev->dev, "MAC of VF %d has been set to %s\n",
+	dev_info(&hdev->pdev->dev,
+		 "MAC of VF %d has been set to %s, will be active after VF reset\n",
 		 vf, format_mac_addr);
 	return 0;
 }
···
 	 * for DEVICE_VERSION_V3, vf doesn't need to know about the port based
 	 * VLAN state.
 	 */
-	if (ae_dev->dev_version < HNAE3_DEVICE_VERSION_V3 &&
-	    test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state))
-		(void)hclge_push_vf_port_base_vlan_info(&hdev->vport[0],
-							vport->vport_id,
-							state, &vlan_info);
-
+	if (ae_dev->dev_version < HNAE3_DEVICE_VERSION_V3) {
+		if (test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state))
+			(void)hclge_push_vf_port_base_vlan_info(&hdev->vport[0],
+								vport->vport_id,
+								state,
+								&vlan_info);
+		else
+			set_bit(HCLGE_VPORT_NEED_NOTIFY_VF_VLAN,
+				&vport->need_notify);
+	}
 	return 0;
 }
 
···
 	int i;
 
 	for (i = 0; i < hdev->num_alloc_vport; i++) {
-		hclge_vport_stop(vport);
+		clear_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
 		vport++;
 	}
 }
···
 	return ret;
 }
 
-static void hclge_sync_promisc_mode(struct hclge_dev *hdev)
+static int hclge_sync_vport_promisc_mode(struct hclge_vport *vport)
 {
-	struct hclge_vport *vport = &hdev->vport[0];
 	struct hnae3_handle *handle = &vport->nic;
+	struct hclge_dev *hdev = vport->back;
+	bool uc_en = false;
+	bool mc_en = false;
 	u8 tmp_flags;
+	bool bc_en;
 	int ret;
-	u16 i;
 
 	if (vport->last_promisc_flags != vport->overflow_promisc_flags) {
 		set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, &vport->state);
 		vport->last_promisc_flags = vport->overflow_promisc_flags;
 	}
 
-	if (test_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, &vport->state)) {
+	if (!test_and_clear_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE,
+				&vport->state))
+		return 0;
+
+	/* for PF */
+	if (!vport->vport_id) {
 		tmp_flags = handle->netdev_flags | vport->last_promisc_flags;
 		ret = hclge_set_promisc_mode(handle, tmp_flags & HNAE3_UPE,
 					     tmp_flags & HNAE3_MPE);
-		if (!ret) {
-			clear_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE,
-				  &vport->state);
+		if (!ret)
 			set_bit(HCLGE_VPORT_STATE_VLAN_FLTR_CHANGE,
 				&vport->state);
-		}
-	}
-
-	for (i = 1; i < hdev->num_alloc_vport; i++) {
-		bool uc_en = false;
-		bool mc_en = false;
-		bool bc_en;
-
-		vport = &hdev->vport[i];
-
-		if (!test_and_clear_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE,
-					&vport->state))
-			continue;
-
-		if (vport->vf_info.trusted) {
-			uc_en = vport->vf_info.request_uc_en > 0 ||
-				vport->overflow_promisc_flags &
-				HNAE3_OVERFLOW_UPE;
-			mc_en = vport->vf_info.request_mc_en > 0 ||
-				vport->overflow_promisc_flags &
-				HNAE3_OVERFLOW_MPE;
-		}
-		bc_en = vport->vf_info.request_bc_en > 0;
-
-		ret = hclge_cmd_set_promisc_mode(hdev, vport->vport_id, uc_en,
-						 mc_en, bc_en);
-		if (ret) {
+		else
 			set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE,
 				&vport->state);
+		return ret;
+	}
+
+	/* for VF */
+	if (vport->vf_info.trusted) {
+		uc_en = vport->vf_info.request_uc_en > 0 ||
+			vport->overflow_promisc_flags & HNAE3_OVERFLOW_UPE;
+		mc_en = vport->vf_info.request_mc_en > 0 ||
+			vport->overflow_promisc_flags & HNAE3_OVERFLOW_MPE;
+	}
+	bc_en = vport->vf_info.request_bc_en > 0;
+
+	ret = hclge_cmd_set_promisc_mode(hdev, vport->vport_id, uc_en,
+					 mc_en, bc_en);
+	if (ret) {
+		set_bit(HCLGE_VPORT_STATE_PROMISC_CHANGE, &vport->state);
+		return ret;
+	}
+	hclge_set_vport_vlan_fltr_change(vport);
+
+	return 0;
+}
+
+static void hclge_sync_promisc_mode(struct hclge_dev *hdev)
+{
+	struct hclge_vport *vport;
+	int ret;
+	u16 i;
+
+	for (i = 0; i < hdev->num_alloc_vport; i++) {
+		vport = &hdev->vport[i];
+
+		ret = hclge_sync_vport_promisc_mode(vport);
+		if (ret)
 			return;
-		}
-		hclge_set_vport_vlan_fltr_change(vport);
 	}
 }
 
···
 	struct hclge_dev *hdev = vport->back;
 	struct hclge_vlan_info vlan_info;
 	int ret;
+
+	clear_bit(HCLGE_VPORT_STATE_INITED, &vport->state);
+	clear_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
+	vport->need_notify = 0;
+	vport->mps = 0;
 
 	/* after disable sriov, clean VF rate configured by PF */
 	ret = hclge_tm_qs_shaper_cfg(vport, 0);

drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h

···
 	HCLGE_VPORT_STATE_MAC_TBL_CHANGE,
 	HCLGE_VPORT_STATE_PROMISC_CHANGE,
 	HCLGE_VPORT_STATE_VLAN_FLTR_CHANGE,
+	HCLGE_VPORT_STATE_INITED,
 	HCLGE_VPORT_STATE_MAX
+};
+
+enum HCLGE_VPORT_NEED_NOTIFY {
+	HCLGE_VPORT_NEED_NOTIFY_RESET,
+	HCLGE_VPORT_NEED_NOTIFY_VF_VLAN,
 };
 
 struct hclge_vlan_info {
···
 	struct hnae3_handle roce;
 
 	unsigned long state;
+	unsigned long need_notify;
 	unsigned long last_active_jiffies;
 	u32 mps; /* Max packet size */
 	struct hclge_vf_info vf_info;

drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c

···
 	return status;
 }
 
+static int hclge_inform_vf_reset(struct hclge_vport *vport, u16 reset_type)
+{
+	__le16 msg_data;
+	u8 dest_vfid;
+
+	dest_vfid = (u8)vport->vport_id;
+	msg_data = cpu_to_le16(reset_type);
+
+	/* send this requested info to VF */
+	return hclge_send_mbx_msg(vport, (u8 *)&msg_data, sizeof(msg_data),
+				  HCLGE_MBX_ASSERTING_RESET, dest_vfid);
+}
+
 int hclge_inform_reset_assert_to_vf(struct hclge_vport *vport)
 {
 	struct hclge_dev *hdev = vport->back;
-	__le16 msg_data;
 	u16 reset_type;
-	u8 dest_vfid;
 
 	BUILD_BUG_ON(HNAE3_MAX_RESET > U16_MAX);
-
-	dest_vfid = (u8)vport->vport_id;
 
 	if (hdev->reset_type == HNAE3_FUNC_RESET)
 		reset_type = HNAE3_VF_PF_FUNC_RESET;
···
 	else
 		reset_type = HNAE3_VF_FUNC_RESET;
 
-	msg_data = cpu_to_le16(reset_type);
-
-	/* send this requested info to VF */
-	return hclge_send_mbx_msg(vport, (u8 *)&msg_data, sizeof(msg_data),
-				  HCLGE_MBX_ASSERTING_RESET, dest_vfid);
+	return hclge_inform_vf_reset(vport, reset_type);
 }
 
 static void hclge_free_vector_ring_chain(struct hnae3_ring_chain_node *head)
···
 	return hclge_func_reset_cmd(hdev, vport->vport_id);
 }
 
+static void hclge_notify_vf_config(struct hclge_vport *vport)
+{
+	struct hclge_dev *hdev = vport->back;
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
+	struct hclge_port_base_vlan_config *vlan_cfg;
+	int ret;
+
+	hclge_push_vf_link_status(vport);
+	if (test_bit(HCLGE_VPORT_NEED_NOTIFY_RESET, &vport->need_notify)) {
+		ret = hclge_inform_vf_reset(vport, HNAE3_VF_PF_FUNC_RESET);
+		if (ret) {
+			dev_err(&hdev->pdev->dev,
+				"failed to inform VF %u reset!",
+				vport->vport_id - HCLGE_VF_VPORT_START_NUM);
+			return;
+		}
+		vport->need_notify = 0;
+		return;
+	}
+
+	if (ae_dev->dev_version < HNAE3_DEVICE_VERSION_V3 &&
+	    test_bit(HCLGE_VPORT_NEED_NOTIFY_VF_VLAN, &vport->need_notify)) {
+		vlan_cfg = &vport->port_base_vlan_cfg;
+		ret = hclge_push_vf_port_base_vlan_info(&hdev->vport[0],
+							vport->vport_id,
+							vlan_cfg->state,
+							&vlan_cfg->vlan_info);
+		if (ret) {
+			dev_err(&hdev->pdev->dev,
+				"failed to inform VF %u port base vlan!",
+				vport->vport_id - HCLGE_VF_VPORT_START_NUM);
+			return;
+		}
+		clear_bit(HCLGE_VPORT_NEED_NOTIFY_VF_VLAN, &vport->need_notify);
+	}
+}
+
 static void hclge_vf_keep_alive(struct hclge_vport *vport)
 {
+	struct hclge_dev *hdev = vport->back;
+
 	vport->last_active_jiffies = jiffies;
+
+	if (test_bit(HCLGE_VPORT_STATE_INITED, &vport->state) &&
+	    !test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state)) {
+		set_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
+		dev_info(&hdev->pdev->dev, "VF %u is alive!",
+			 vport->vport_id - HCLGE_VF_VPORT_START_NUM);
+		hclge_notify_vf_config(vport);
+	}
 }
 
 static int hclge_set_vf_mtu(struct hclge_vport *vport,
···
 	hclge_rm_vport_all_mac_table(param->vport, true,
 				     HCLGE_MAC_ADDR_MC);
 	hclge_rm_vport_all_vlan_table(param->vport, true);
+	param->vport->mps = 0;
 	return 0;
 }
 

drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c

···
 	struct pci_dev *pdev = hdev->pdev;
 	int ret = 0;
 
-	if (hdev->reset_type == HNAE3_VF_FULL_RESET &&
+	if ((hdev->reset_type == HNAE3_VF_FULL_RESET ||
+	     hdev->reset_type == HNAE3_FLR_RESET) &&
 	    test_bit(HCLGEVF_STATE_IRQ_INITED, &hdev->state)) {
 		hclgevf_misc_irq_uninit(hdev);
 		hclgevf_uninit_msi(hdev);

drivers/net/ethernet/intel/ice/ice_xsk.c

···
 static void
 ice_clean_xdp_tx_buf(struct ice_tx_ring *xdp_ring, struct ice_tx_buf *tx_buf)
 {
-	xdp_return_frame((struct xdp_frame *)tx_buf->raw_buf);
+	page_frag_free(tx_buf->raw_buf);
 	xdp_ring->xdp_tx_active--;
 	dma_unmap_single(xdp_ring->dev, dma_unmap_addr(tx_buf, dma),
 			 dma_unmap_len(tx_buf, len), DMA_TO_DEVICE);

drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c

···
 	u16 pcifunc = req->hdr.pcifunc;
 	struct mcs_rsrc_map *map;
 	struct mcs *mcs;
-	int rc;
+	int rc = 0;
 
 	if (req->mcs_id >= rvu->mcs_blk_cnt)
 		return MCS_AF_ERR_INVALID_MCSID;

drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c

···
 	rbpool = cq->rbpool;
 	free_ptrs = cq->pool_ptrs;
 
+	get_cpu();
 	while (cq->pool_ptrs) {
 		if (otx2_alloc_rbuf(pfvf, rbpool, &bufptr)) {
 			/* Schedule a WQ if we fails to free atleast half of the
···
 		pfvf->hw_ops->aura_freeptr(pfvf, qidx, bufptr + OTX2_HEAD_ROOM);
 		cq->pool_ptrs--;
 	}
+	put_cpu();
 	cq->refill_task_sched = false;
 }
 
···
 	if (err)
 		goto fail;
 
+	get_cpu();
 	/* Allocate pointers and free them to aura/pool */
 	for (qidx = 0; qidx < hw->tot_tx_queues; qidx++) {
 		pool_id = otx2_get_pool_idx(pfvf, AURA_NIX_SQ, qidx);
···
 		sq = &qset->sq[qidx];
 		sq->sqb_count = 0;
 		sq->sqb_ptrs = kcalloc(num_sqbs, sizeof(*sq->sqb_ptrs), GFP_KERNEL);
-		if (!sq->sqb_ptrs)
-			return -ENOMEM;
+		if (!sq->sqb_ptrs) {
+			err = -ENOMEM;
+			goto err_mem;
+		}
 
 		for (ptr = 0; ptr < num_sqbs; ptr++) {
-			if (otx2_alloc_rbuf(pfvf, pool, &bufptr))
-				return -ENOMEM;
+			err = otx2_alloc_rbuf(pfvf, pool, &bufptr);
+			if (err)
+				goto err_mem;
 			pfvf->hw_ops->aura_freeptr(pfvf, pool_id, bufptr);
 			sq->sqb_ptrs[sq->sqb_count++] = (u64)bufptr;
 		}
 	}
 
-	return 0;
+err_mem:
+	put_cpu();
+	return err ? -ENOMEM : 0;
+
 fail:
 	otx2_mbox_reset(&pfvf->mbox.mbox, 0);
 	otx2_aura_pool_free(pfvf);
···
 	if (err)
 		goto fail;
 
+	get_cpu();
 	/* Allocate pointers and free them to aura/pool */
 	for (pool_id = 0; pool_id < hw->rqpool_cnt; pool_id++) {
 		pool = &pfvf->qset.pool[pool_id];
 		for (ptr = 0; ptr < num_ptrs; ptr++) {
-			if (otx2_alloc_rbuf(pfvf, pool, &bufptr))
-				return -ENOMEM;
+			err = otx2_alloc_rbuf(pfvf, pool, &bufptr);
+			if (err)
+				goto err_mem;
 			pfvf->hw_ops->aura_freeptr(pfvf, pool_id,
 						   bufptr + OTX2_HEAD_ROOM);
 		}
 	}
-
-	return 0;
+err_mem:
+	put_cpu();
+	return err ? -ENOMEM : 0;
 fail:
 	otx2_mbox_reset(&pfvf->mbox.mbox, 0);
 	otx2_aura_pool_free(pfvf);

drivers/net/ethernet/mellanox/mlx5/core/devlink.c

···
 	bool new_state = val.vbool;
 
 	if (new_state && !MLX5_CAP_GEN(dev, roce) &&
-	    !MLX5_CAP_GEN(dev, roce_rw_supported)) {
+	    !(MLX5_CAP_GEN(dev, roce_rw_supported) && MLX5_CAP_GEN_MAX(dev, roce))) {
 		NL_SET_ERR_MSG_MOD(extack, "Device doesn't support RoCE");
 		return -EOPNOTSUPP;
 	}
···
 					  union devlink_param_value val,
 					  struct netlink_ext_ack *extack)
 {
-	return (val.vu16 >= 64 && val.vu16 <= 4096) ? 0 : -EINVAL;
+	return (val.vu32 >= 64 && val.vu32 <= 4096) ? 0 : -EINVAL;
 }
 
 static const struct devlink_param mlx5_devlink_params[] = {

drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c

···
 		goto unlock;
 
 	for (i = 0; i < priv->channels.num; i++) {
-		struct mlx5e_rq *rq = &priv->channels.c[i]->rq;
+		struct mlx5e_channel *c = priv->channels.c[i];
+		struct mlx5e_rq *rq;
+
+		rq = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state) ?
+			&c->xskrq : &c->rq;
 
 		err = mlx5e_rx_reporter_build_diagnose_output(rq, fmsg);
 		if (err)

drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c

···
 static void
 mlx5_ct_tc_create_dbgfs(struct mlx5_tc_ct_priv *ct_priv)
 {
-	bool is_fdb = ct_priv->ns_type == MLX5_FLOW_NAMESPACE_FDB;
 	struct mlx5_tc_ct_debugfs *ct_dbgfs = &ct_priv->debugfs;
-	char dirname[16] = {};
 
-	if (sscanf(dirname, "ct_%s", is_fdb ? "fdb" : "nic") < 0)
-		return;
-
-	ct_dbgfs->root = debugfs_create_dir(dirname, mlx5_debugfs_get_dev_root(ct_priv->dev));
+	ct_dbgfs->root = debugfs_create_dir("ct", mlx5_debugfs_get_dev_root(ct_priv->dev));
 	debugfs_create_atomic_t("offloaded", 0400, ct_dbgfs->root,
 				&ct_dbgfs->stats.offloaded);
 	debugfs_create_atomic_t("rx_dropped", 0400, ct_dbgfs->root,

drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c

···
 	int err;
 
 	list_for_each_entry(flow, flow_list, tmp_list) {
-		if (!mlx5e_is_offloaded_flow(flow) || flow_flag_test(flow, SLOW))
+		if (!mlx5e_is_offloaded_flow(flow))
 			continue;
 
 		attr = mlx5e_tc_get_encap_attr(flow);
···
 		/* mark the flow's encap dest as non-valid */
 		esw_attr->dests[flow->tmp_entry_index].flags &= ~MLX5_ESW_DEST_ENCAP_VALID;
 		esw_attr->dests[flow->tmp_entry_index].pkt_reformat = NULL;
+
+		/* Clear pkt_reformat before checking slow path flag. Because
+		 * in next iteration, the same flow is already set slow path
+		 * flag, but still need to clear the pkt_reformat.
+		 */
+		if (flow_flag_test(flow, SLOW))
+			continue;
 
 		/* update from encap rule to slow path rule */
 		spec = &flow->attr->parse_attr->spec;

drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c

···
 		 geneve_tlv_option_0_data, be32_to_cpu(opt_data_key));
 	MLX5_SET(fte_match_set_misc3, misc_3_c,
 		 geneve_tlv_option_0_data, be32_to_cpu(opt_data_mask));
+	if (MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev,
+				       ft_field_support.geneve_tlv_option_0_exist)) {
+		MLX5_SET_TO_ONES(fte_match_set_misc, misc_c, geneve_tlv_option_0_exist);
+		MLX5_SET_TO_ONES(fte_match_set_misc, misc_v, geneve_tlv_option_0_exist);
+	}
 
 	spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_3;
 

drivers/net/ethernet/mellanox/mlx5/core/en_main.c

···
 	sq->channel   = c;
 	sq->uar_map   = mdev->mlx5e_res.hw_objs.bfreg.map;
 	sq->min_inline_mode = params->tx_min_inline_mode;
-	sq->hw_mtu    = MLX5E_SW2HW_MTU(params, params->sw_mtu);
+	sq->hw_mtu    = MLX5E_SW2HW_MTU(params, params->sw_mtu) - ETH_FCS_LEN;
 	sq->xsk_pool  = xsk_pool;
 
 	sq->stats = sq->xsk_pool ?

drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c

···
 int esw_acl_egress_lgcy_setup(struct mlx5_eswitch *esw,
 			      struct mlx5_vport *vport)
 {
+	bool vst_mode_steering = esw_vst_mode_is_steering(esw);
 	struct mlx5_flow_destination drop_ctr_dst = {};
 	struct mlx5_flow_destination *dst = NULL;
 	struct mlx5_fc *drop_counter = NULL;
···
 	 */
 	int table_size = 2;
 	int dest_num = 0;
+	int actions_flag;
 	int err = 0;
 
 	if (vport->egress.legacy.drop_counter) {
···
 		  vport->vport, vport->info.vlan, vport->info.qos);
 
 	/* Allowed vlan rule */
+	actions_flag = MLX5_FLOW_CONTEXT_ACTION_ALLOW;
+	if (vst_mode_steering)
+		actions_flag |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP;
 	err = esw_egress_acl_vlan_create(esw, vport, NULL, vport->info.vlan,
-					 MLX5_FLOW_CONTEXT_ACTION_ALLOW);
+					 actions_flag);
 	if (err)
 		goto out;
 

drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c

···
 int esw_acl_ingress_lgcy_setup(struct mlx5_eswitch *esw,
 			       struct mlx5_vport *vport)
 {
+	bool vst_mode_steering = esw_vst_mode_is_steering(esw);
 	struct mlx5_flow_destination drop_ctr_dst = {};
 	struct mlx5_flow_destination *dst = NULL;
 	struct mlx5_flow_act flow_act = {};
 	struct mlx5_flow_spec *spec = NULL;
 	struct mlx5_fc *counter = NULL;
+	bool vst_check_cvlan = false;
+	bool vst_push_cvlan = false;
 	/* The ingress acl table contains 4 groups
 	 * (2 active rules at the same time -
 	 *      1 allow rule from one of the first 3 groups.
···
 		goto out;
 	}
 
-	if (vport->info.vlan || vport->info.qos)
+	if ((vport->info.vlan || vport->info.qos)) {
+		if (vst_mode_steering)
+			vst_push_cvlan = true;
+		else if (!MLX5_CAP_ESW(esw->dev, vport_cvlan_insert_always))
+			vst_check_cvlan = true;
+	}
+
+	if (vst_check_cvlan || vport->info.spoofchk)
+		spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+
+	/* Create ingress allow rule */
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW;
+	if (vst_push_cvlan) {
+		flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH;
+		flow_act.vlan[0].prio = vport->info.qos;
+		flow_act.vlan[0].vid = vport->info.vlan;
+		flow_act.vlan[0].ethtype = ETH_P_8021Q;
+	}
+
+	if (vst_check_cvlan)
 		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
 				 outer_headers.cvlan_tag);
 
···
 		ether_addr_copy(smac_v, vport->info.mac);
 	}
 
-	/* Create ingress allow rule */
-	spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
-	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW;
 	vport->ingress.allow_rule = mlx5_add_flow_rules(vport->ingress.acl, spec,
 							&flow_act, NULL, 0);
 	if (IS_ERR(vport->ingress.allow_rule)) {
···
 		vport->ingress.allow_rule = NULL;
 		goto out;
 	}
+
+	if (!vst_check_cvlan && !vport->info.spoofchk)
+		goto out;
 
 	memset(&flow_act, 0, sizeof(flow_act));
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP;
···
 	return 0;
 
 out:
-	esw_acl_ingress_lgcy_cleanup(esw, vport);
+	if (err)
+		esw_acl_ingress_lgcy_cleanup(esw, vport);
 	kvfree(spec);
 	return err;
 }

drivers/net/ethernet/mellanox/mlx5/core/eswitch.c

···
 			 esw_vport_context.vport_cvlan_strip, 1);
 
 	if (set_flags & SET_VLAN_INSERT) {
-		/* insert only if no vlan in packet */
-		MLX5_SET(modify_esw_vport_context_in, in,
-			 esw_vport_context.vport_cvlan_insert, 1);
-
+		if (MLX5_CAP_ESW(dev, vport_cvlan_insert_always)) {
+			/* insert either if vlan exist in packet or not */
+			MLX5_SET(modify_esw_vport_context_in, in,
+				 esw_vport_context.vport_cvlan_insert,
+				 MLX5_VPORT_CVLAN_INSERT_ALWAYS);
+		} else {
+			/* insert only if no vlan in packet */
+			MLX5_SET(modify_esw_vport_context_in, in,
+				 esw_vport_context.vport_cvlan_insert,
+				 MLX5_VPORT_CVLAN_INSERT_WHEN_NO_CVLAN);
+		}
 		MLX5_SET(modify_esw_vport_context_in, in,
 			 esw_vport_context.cvlan_pcp, qos);
 		MLX5_SET(modify_esw_vport_context_in, in,
···
 
 static int esw_vport_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
 {
+	bool vst_mode_steering = esw_vst_mode_is_steering(esw);
 	u16 vport_num = vport->vport;
 	int flags;
 	int err;
···
 
 	flags = (vport->info.vlan || vport->info.qos) ?
 		SET_VLAN_STRIP | SET_VLAN_INSERT : 0;
-	modify_esw_vport_cvlan(esw->dev, vport_num, vport->info.vlan,
-			       vport->info.qos, flags);
+	if (esw->mode == MLX5_ESWITCH_OFFLOADS || !vst_mode_steering)
+		modify_esw_vport_cvlan(esw->dev, vport_num, vport->info.vlan,
+				       vport->info.qos, flags);
 
 	return 0;
 
···
 				  u16 vport, u16 vlan, u8 qos, u8 set_flags)
 {
 	struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport);
+	bool vst_mode_steering = esw_vst_mode_is_steering(esw);
 	int err = 0;
 
 	if (IS_ERR(evport))
···
 	if (vlan > 4095 || qos > 7)
 		return -EINVAL;
 
-	err = modify_esw_vport_cvlan(esw->dev, vport, vlan, qos, set_flags);
-	if (err)
-		return err;
+	if (esw->mode == MLX5_ESWITCH_OFFLOADS || !vst_mode_steering) {
+		err = modify_esw_vport_cvlan(esw->dev, vport, vlan, qos, set_flags);
+		if (err)
+			return err;
+	}
 
 	evport->info.vlan = vlan;
 	evport->info.qos = qos;

drivers/net/ethernet/mellanox/mlx5/core/eswitch.h

···
 int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
 				  u16 vport, u16 vlan, u8 qos, u8 set_flags);
 
+static inline bool esw_vst_mode_is_steering(struct mlx5_eswitch *esw)
+{
+	return (MLX5_CAP_ESW_EGRESS_ACL(esw->dev, pop_vlan) &&
+		MLX5_CAP_ESW_INGRESS_ACL(esw->dev, push_vlan));
+}
+
 static inline bool mlx5_eswitch_vlan_actions_supported(struct mlx5_core_dev *dev,
 						       u8 vlan_depth)
 {

drivers/net/ethernet/mellanox/mlx5/core/health.c

···
 	dev = container_of(priv, struct mlx5_core_dev, priv);
 	devlink = priv_to_devlink(dev);
 
+	mutex_lock(&dev->intf_state_mutex);
+	if (test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags)) {
+		mlx5_core_err(dev, "health works are not permitted at this stage\n");
+		return;
+	}
+	mutex_unlock(&dev->intf_state_mutex);
 	enter_error_state(dev, false);
 	if (IS_ERR_OR_NULL(health->fw_fatal_reporter)) {
 		devl_lock(devlink);

drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c

···
 	params->packet_merge.type = MLX5E_PACKET_MERGE_NONE;
 	params->hard_mtu = MLX5_IB_GRH_BYTES + MLX5_IPOIB_HARD_LEN;
 	params->tunneled_offload_en = false;
+
+	/* CQE compression is not supported for IPoIB */
+	params->rx_cqe_compress_def = false;
+	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS, params->rx_cqe_compress_def);
 }
 
 /* Called directly after IPoIB netdevice was created to initialize SW structs */

drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c

···
 	if (ldev->nb.notifier_call)
 		unregister_netdevice_notifier_net(&init_net, &ldev->nb);
 	mlx5_lag_mp_cleanup(ldev);
+	cancel_delayed_work_sync(&ldev->bond_work);
 	destroy_workqueue(ldev->wq);
 	mlx5_lag_mpesw_cleanup(ldev);
 	mutex_destroy(&ldev->lock);

drivers/net/ethernet/mellanox/mlx5/core/main.c

···
 		MLX5_SET(cmd_hca_cap, set_hca_cap, num_total_dynamic_vf_msix,
 			 MLX5_CAP_GEN_MAX(dev, num_total_dynamic_vf_msix));
 
-	if (MLX5_CAP_GEN(dev, roce_rw_supported))
+	if (MLX5_CAP_GEN(dev, roce_rw_supported) && MLX5_CAP_GEN_MAX(dev, roce))
 		MLX5_SET(cmd_hca_cap, set_hca_cap, roce,
 			 mlx5_is_roce_on(dev));
 
···
 err_tables_cleanup:
 	mlx5_geneve_destroy(dev->geneve);
 	mlx5_vxlan_destroy(dev->vxlan);
+	mlx5_cleanup_clock(dev);
+	mlx5_cleanup_reserved_gids(dev);
 	mlx5_cq_debugfs_cleanup(dev);
 	mlx5_fw_reset_cleanup(dev);
 err_events_cleanup:

drivers/net/ethernet/microchip/lan966x/lan966x_port.c

···
 	}
 
 	/* Take PCS out of reset */
-	lan_rmw(DEV_CLOCK_CFG_LINK_SPEED_SET(2) |
+	lan_rmw(DEV_CLOCK_CFG_LINK_SPEED_SET(LAN966X_SPEED_1000) |
 		DEV_CLOCK_CFG_PCS_RX_RST_SET(0) |
 		DEV_CLOCK_CFG_PCS_TX_RST_SET(0),
 		DEV_CLOCK_CFG_LINK_SPEED |

drivers/net/ethernet/microchip/sparx5/sparx5_main.c

···
 	if (err)
 		goto cleanup_config;
 
-	if (!of_get_mac_address(np, sparx5->base_mac)) {
+	if (of_get_mac_address(np, sparx5->base_mac)) {
 		dev_info(sparx5->dev, "MAC addr was not set, use random MAC\n");
 		eth_random_addr(sparx5->base_mac);
 		sparx5->base_mac[5] = 0;

drivers/net/ethernet/netronome/nfp/nfp_net.h

···
  * @vnic_no_name:	For non-port PF vNIC make ndo_get_phys_port_name return
  *			-EOPNOTSUPP to keep backwards compatibility (set by app)
  * @port:		Pointer to nfp_port structure if vNIC is a port
+ * @mc_lock:		Protect mc_addrs list
+ * @mc_addrs:		List of mc addrs to add/del to HW
+ * @mc_work:		Work to update mc addrs
  * @app_priv:		APP private data for this vNIC
  */
 struct nfp_net {
···
 	bool vnic_no_name;
 
 	struct nfp_port *port;
+
+	spinlock_t mc_lock;
+	struct list_head mc_addrs;
+	struct work_struct mc_work;
 
 	void *app_priv;
 };

drivers/net/ethernet/netronome/nfp/nfp_net_common.c

···
 	return err;
 }
 
-static int nfp_net_mc_cfg(struct net_device *netdev, const unsigned char *addr, const u32 cmd)
+struct nfp_mc_addr_entry {
+	u8 addr[ETH_ALEN];
+	u32 cmd;
+	struct list_head list;
+};
+
+static int nfp_net_mc_cfg(struct nfp_net *nn, const unsigned char *addr, const u32 cmd)
 {
-	struct nfp_net *nn = netdev_priv(netdev);
 	int ret;
 
 	ret = nfp_net_mbox_lock(nn, NFP_NET_CFG_MULTICAST_SZ);
···
 	return nfp_net_mbox_reconfig_and_unlock(nn, cmd);
 }
 
+static int nfp_net_mc_prep(struct nfp_net *nn, const unsigned char *addr, const u32 cmd)
+{
+	struct nfp_mc_addr_entry *entry;
+
+	entry = kmalloc(sizeof(*entry), GFP_ATOMIC);
+	if (!entry)
+		return -ENOMEM;
+
+	ether_addr_copy(entry->addr, addr);
+	entry->cmd = cmd;
+	spin_lock_bh(&nn->mc_lock);
+	list_add_tail(&entry->list, &nn->mc_addrs);
+	spin_unlock_bh(&nn->mc_lock);
+
+	schedule_work(&nn->mc_work);
+
+	return 0;
+}
+
 static int nfp_net_mc_sync(struct net_device *netdev, const unsigned char *addr)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
···
 		return -EINVAL;
 	}
 
-	return nfp_net_mc_cfg(netdev, addr, NFP_NET_CFG_MBOX_CMD_MULTICAST_ADD);
+	return nfp_net_mc_prep(nn, addr, NFP_NET_CFG_MBOX_CMD_MULTICAST_ADD);
 }
 
 static int nfp_net_mc_unsync(struct net_device *netdev, const unsigned char *addr)
 {
-	return nfp_net_mc_cfg(netdev, addr, NFP_NET_CFG_MBOX_CMD_MULTICAST_DEL);
+	struct nfp_net *nn = netdev_priv(netdev);
+
+	return nfp_net_mc_prep(nn, addr, NFP_NET_CFG_MBOX_CMD_MULTICAST_DEL);
+}
+
+static void nfp_net_mc_addr_config(struct work_struct *work)
+{
+	struct nfp_net *nn = container_of(work, struct nfp_net, mc_work);
+	struct nfp_mc_addr_entry *entry, *tmp;
+	struct list_head tmp_list;
+
+	INIT_LIST_HEAD(&tmp_list);
+
+	spin_lock_bh(&nn->mc_lock);
+	list_splice_init(&nn->mc_addrs, &tmp_list);
+	spin_unlock_bh(&nn->mc_lock);
+
+	list_for_each_entry_safe(entry, tmp, &tmp_list, list) {
+		if (nfp_net_mc_cfg(nn, entry->addr, entry->cmd))
+			nn_err(nn, "Config mc address to HW failed.\n");
+
+		list_del(&entry->list);
+		kfree(entry);
+	}
 }
 
 static void nfp_net_set_rx_mode(struct net_device *netdev)
···
 
 	if (!nn->dp.netdev)
 		return 0;
+
+	spin_lock_init(&nn->mc_lock);
+	INIT_LIST_HEAD(&nn->mc_addrs);
+	INIT_WORK(&nn->mc_work, nfp_net_mc_addr_config);
+
 	return register_netdev(nn->dp.netdev);
 
 err_clean_mbox:
···
 	unregister_netdev(nn->dp.netdev);
 	nfp_net_ipsec_clean(nn);
 	nfp_ccm_mbox_clean(nn);
+	flush_work(&nn->mc_work);
 	nfp_net_reconfig_wait_posted(nn);
 }

drivers/net/ethernet/qlogic/qed/qed_debug.c

···
 					    struct qed_ptt *p_ptt,
 					    u32 image_type,
 					    u32 *nvram_offset_bytes,
-					    u32 *nvram_size_bytes)
+					    u32 *nvram_size_bytes,
+					    bool b_can_sleep)
 {
 	u32 ret_mcp_resp, ret_mcp_param, ret_txn_size;
 	struct mcp_file_att file_att;
···
 					&ret_mcp_resp,
 					&ret_mcp_param,
 					&ret_txn_size,
-					(u32 *)&file_att, false);
+					(u32 *)&file_att,
+					b_can_sleep);
 
 	/* Check response */
 	if (nvm_result || (ret_mcp_resp & FW_MSG_CODE_MASK) !=
···
 static enum dbg_status qed_nvram_read(struct qed_hwfn *p_hwfn,
 				      struct qed_ptt *p_ptt,
 				      u32 nvram_offset_bytes,
-				      u32 nvram_size_bytes, u32 *ret_buf)
+				      u32 nvram_size_bytes,
+				      u32 *ret_buf,
+				      bool b_can_sleep)
 {
 	u32 ret_mcp_resp, ret_mcp_param, ret_read_size, bytes_to_copy;
 	s32 bytes_left = nvram_size_bytes;
···
 				       &ret_mcp_resp,
 				       &ret_mcp_param, &ret_read_size,
 				       (u32 *)((u8 *)ret_buf + read_offset),
-				       false))
+				       b_can_sleep))
 			return DBG_STATUS_NVRAM_READ_FAILED;
 
 		/* Check response */
···
 				      p_ptt,
 				      NVM_TYPE_HW_DUMP_OUT,
 				      &hw_dump_offset_bytes,
-				      &hw_dump_size_bytes);
+				      &hw_dump_size_bytes,
+				      false);
 	if (status != DBG_STATUS_OK)
 		return 0;
 
···
 		status = qed_nvram_read(p_hwfn,
 					p_ptt,
 					hw_dump_offset_bytes,
-					hw_dump_size_bytes, dump_buf + offset);
+					hw_dump_size_bytes,
+					dump_buf + offset,
+					false);
 		if (status != DBG_STATUS_OK) {
 			DP_NOTICE(p_hwfn,
 				  "Failed to read MCP HW Dump image from NVRAM\n");
···
 	return qed_find_nvram_image(p_hwfn,
 				    p_ptt,
 				    nvram_image_type,
-				    trace_meta_offset, trace_meta_size);
+				    trace_meta_offset,
+				    trace_meta_size,
+				    true);
 }
 
 /* Reads the MCP Trace meta data from NVRAM into the specified buffer */
···
 	/* Read meta data from NVRAM */
 	status = qed_nvram_read(p_hwfn,
 				p_ptt,
-				nvram_offset_in_bytes, size_in_bytes, buf);
+				nvram_offset_in_bytes,
+				size_in_bytes,
+				buf,
+				true);
 	if (status != DBG_STATUS_OK)
 		return status;
 

drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c

···
 		goto disable_mbx_intr;
 
 	qlcnic_83xx_clear_function_resources(adapter);
-	qlcnic_dcb_enable(adapter->dcb);
+
+	err = qlcnic_dcb_enable(adapter->dcb);
+	if (err) {
+		qlcnic_dcb_free(adapter->dcb);
+		goto disable_mbx_intr;
+	}
+
 	qlcnic_83xx_initialize_nic(adapter, 1);
 	qlcnic_dcb_get_info(adapter->dcb);
 

drivers/net/ethernet/qlogic/qlcnic/qlcnic_dcb.h

···
 	unsigned long			state;
 };
 
-static inline void qlcnic_clear_dcb_ops(struct qlcnic_dcb *dcb)
-{
-	kfree(dcb);
-}
-
 static inline int qlcnic_dcb_get_hw_capability(struct qlcnic_dcb *dcb)
 {
 	if (dcb && dcb->ops->get_hw_capability)
···
 		dcb->ops->init_dcbnl_ops(dcb);
 }
 
-static inline void qlcnic_dcb_enable(struct qlcnic_dcb *dcb)
+static inline int qlcnic_dcb_enable(struct qlcnic_dcb *dcb)
 {
-	if (dcb && qlcnic_dcb_attach(dcb))
-		qlcnic_clear_dcb_ops(dcb);
+	return dcb ? qlcnic_dcb_attach(dcb) : 0;
 }
 #endif

drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c

···
 			 "Device does not support MSI interrupts\n");
 
 	if (qlcnic_82xx_check(adapter)) {
-		qlcnic_dcb_enable(adapter->dcb);
+		err = qlcnic_dcb_enable(adapter->dcb);
+		if (err) {
+			qlcnic_dcb_free(adapter->dcb);
+			dev_err(&pdev->dev, "Failed to enable DCB\n");
+			goto err_out_free_hw;
+		}
+
 		qlcnic_dcb_get_info(adapter->dcb);
 		err = qlcnic_setup_intr(adapter);
 

drivers/net/ethernet/realtek/r8169_main.c

···
 	return 0;
 }
 
-static void rtl_wol_enable_rx(struct rtl8169_private *tp)
-{
-	if (tp->mac_version >= RTL_GIGA_MAC_VER_25)
-		RTL_W32(tp, RxConfig, RTL_R32(tp, RxConfig) |
-			AcceptBroadcast | AcceptMulticast | AcceptMyPhys);
-}
-
-static void rtl_prepare_power_down(struct rtl8169_private *tp)
-{
-	if (tp->dash_type != RTL_DASH_NONE)
-		return;
-
-	if (tp->mac_version == RTL_GIGA_MAC_VER_32 ||
-	    tp->mac_version == RTL_GIGA_MAC_VER_33)
-		rtl_ephy_write(tp, 0x19, 0xff64);
-
-	if (device_may_wakeup(tp_to_dev(tp))) {
-		phy_speed_down(tp->phydev, false);
-		rtl_wol_enable_rx(tp);
-	}
-}
-
 static void rtl_init_rxcfg(struct rtl8169_private *tp)
 {
 	switch (tp->mac_version) {
···
 	RTL_W32(tp, MISC, RTL_R32(tp, MISC) | RXDV_GATED_EN);
 	fsleep(2000);
 	rtl_wait_txrx_fifo_empty(tp);
+}
+
+static void rtl_wol_enable_rx(struct rtl8169_private *tp)
+{
+	if (tp->mac_version >= RTL_GIGA_MAC_VER_25)
+		RTL_W32(tp, RxConfig, RTL_R32(tp, RxConfig) |
+			AcceptBroadcast | AcceptMulticast | AcceptMyPhys);
+
+	if (tp->mac_version >= RTL_GIGA_MAC_VER_40)
+		rtl_disable_rxdvgate(tp);
+}
+
+static void rtl_prepare_power_down(struct rtl8169_private *tp)
+{
+	if (tp->dash_type != RTL_DASH_NONE)
+		return;
+
+	if (tp->mac_version == RTL_GIGA_MAC_VER_32 ||
+	    tp->mac_version == RTL_GIGA_MAC_VER_33)
+		rtl_ephy_write(tp, 0x19, 0xff64);
+
+	if (device_may_wakeup(tp_to_dev(tp))) {
+		phy_speed_down(tp->phydev, false);
+		rtl_wol_enable_rx(tp);
+	}
 }
 
 static void rtl_set_tx_config_registers(struct rtl8169_private *tp)
···
 	netdev_reset_queue(tp->dev);
 }
 
-static void rtl8169_cleanup(struct rtl8169_private *tp, bool going_down)
+static void rtl8169_cleanup(struct rtl8169_private *tp)
 {
 	napi_disable(&tp->napi);
 
···
 	rtl8169_irq_mask_and_ack(tp);
 
 	rtl_rx_close(tp);
-
-	if (going_down && tp->dev->wol_enabled)
-		goto no_reset;
 
 	switch (tp->mac_version) {
 	case RTL_GIGA_MAC_VER_28:
···
 	}
 
 	rtl_hw_reset(tp);
-no_reset:
+
 	rtl8169_tx_clear(tp);
 	rtl8169_init_ring_indexes(tp);
 }
···
 
 	netif_stop_queue(tp->dev);
 
-	rtl8169_cleanup(tp, false);
+	rtl8169_cleanup(tp);
 
 	for (i = 0; i < NUM_RX_DESC; i++)
 		rtl8169_mark_to_asic(tp->RxDescArray + i);
···
 	pci_clear_master(tp->pci_dev);
 	rtl_pci_commit(tp);
 
-	rtl8169_cleanup(tp, true);
+	rtl8169_cleanup(tp);
 	rtl_disable_exit_l1(tp);
 	rtl_prepare_power_down(tp);
 }

drivers/net/ethernet/renesas/rswitch.c

···
 {
 	struct platform_device *pdev = priv->pdev;
 	struct rswitch_device *rdev;
+	struct device_node *port;
 	struct net_device *ndev;
 	int err;
 
···
 
 	netif_napi_add(ndev, &rdev->napi, rswitch_poll);
 
-	err = of_get_ethdev_address(pdev->dev.of_node, ndev);
+	port = rswitch_get_port_node(rdev);
+	err = of_get_ethdev_address(port, ndev);
+	of_node_put(port);
 	if (err) {
 		if (is_valid_ether_addr(rdev->etha->mac_addr))
 			eth_hw_addr_set(ndev, rdev->etha->mac_addr);
···
 	pm_runtime_get_sync(&pdev->dev);
 
 	ret = rswitch_init(priv);
+	if (ret < 0) {
+		pm_runtime_put(&pdev->dev);
+		pm_runtime_disable(&pdev->dev);
+		return ret;
+	}
 
 	device_set_wakeup_capable(&pdev->dev, 1);
 

drivers/net/ipa/ipa_interrupt.c

···
 					  u32 endpoint_id, bool enable)
 {
 	struct ipa *ipa = interrupt->ipa;
+	u32 mask = BIT(endpoint_id % 32);
 	u32 unit = endpoint_id / 32;
 	const struct ipa_reg *reg;
 	u32 offset;
-	u32 mask;
 	u32 val;
 
 	WARN_ON(!test_bit(endpoint_id, ipa->available));
···
 	offset = ipa_reg_n_offset(reg, unit);
 	val = ioread32(ipa->reg_virt + offset);
 
-	mask = BIT(endpoint_id);
 	if (enable)
 		val |= mask;
 	else

drivers/net/phy/xilinx_gmii2rgmii.c

···
 
 	if (!priv->phy_dev->drv) {
 		dev_info(dev, "Attached phy not ready\n");
+		put_device(&priv->phy_dev->mdio.dev);
 		return -EPROBE_DEFER;
 	}
 

drivers/net/usb/rndis_host.c

···
 
 	off = le32_to_cpu(u.get_c->offset);
 	len = le32_to_cpu(u.get_c->len);
-	if (unlikely((8 + off + len) > CONTROL_BUFFER_SIZE))
+	if (unlikely((off > CONTROL_BUFFER_SIZE - 8) ||
+		     (len > CONTROL_BUFFER_SIZE - 8 - off)))
 		goto response_error;
 
 	if (*reply_len != -1 && len != *reply_len)

drivers/net/veth.c

···
 	xdp_set_return_frame_no_direct();
 	done = veth_xdp_rcv(rq, budget, &bq, &stats);
 
+	if (stats.xdp_redirect > 0)
+		xdp_do_flush();
+
 	if (done < budget && napi_complete_done(napi, done)) {
 		/* Write rx_notify_masked before reading ptr_ring */
 		smp_store_mb(rq->rx_notify_masked, false);
···
 
 	if (stats.xdp_tx > 0)
 		veth_xdp_flush(rq, &bq);
-	if (stats.xdp_redirect > 0)
-		xdp_do_flush();
 	xdp_clear_return_frame_no_direct();
 
 	return done;

drivers/net/vmxnet3/vmxnet3_drv.c

···
 		    (le32_to_cpu(gdesc->dword[3]) &
 		     VMXNET3_RCD_CSUM_OK) == VMXNET3_RCD_CSUM_OK) {
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
+			if ((le32_to_cpu(gdesc->dword[0]) &
+				     (1UL << VMXNET3_RCD_HDR_INNER_SHIFT))) {
+				skb->csum_level = 1;
+			}
 			WARN_ON_ONCE(!(gdesc->rcd.tcp || gdesc->rcd.udp) &&
 				     !(le32_to_cpu(gdesc->dword[0]) &
 				     (1UL << VMXNET3_RCD_HDR_INNER_SHIFT)));
···
 		} else if (gdesc->rcd.v6 && (le32_to_cpu(gdesc->dword[3]) &
 					     (1 << VMXNET3_RCD_TUC_SHIFT))) {
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
+			if ((le32_to_cpu(gdesc->dword[0]) &
+				     (1UL << VMXNET3_RCD_HDR_INNER_SHIFT))) {
+				skb->csum_level = 1;
+			}
 			WARN_ON_ONCE(!(gdesc->rcd.tcp || gdesc->rcd.udp) &&
 				     !(le32_to_cpu(gdesc->dword[0]) &
 				     (1UL << VMXNET3_RCD_HDR_INNER_SHIFT)));

drivers/net/vrf.c

···
 
 	/* loopback, multicast & non-ND link-local traffic; do not push through
 	 * packet taps again. Reset pkt_type for upper layers to process skb.
-	 * For strict packets with a source LLA, determine the dst using the
-	 * original ifindex.
+	 * For non-loopback strict packets, determine the dst using the original
+	 * ifindex.
 	 */
 	if (skb->pkt_type == PACKET_LOOPBACK || (need_strict && !is_ndisc)) {
 		skb->dev = vrf_dev;
···
 
 		if (skb->pkt_type == PACKET_LOOPBACK)
 			skb->pkt_type = PACKET_HOST;
-		else if (ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)
+		else
 			vrf_ip6_input_dst(skb, vrf_dev, orig_iif);
 
 		goto out;

drivers/net/vxlan/vxlan_core.c

···
 		vxlan_vnigroup_init(vxlan);
 
 	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
-	if (!dev->tstats)
-		return -ENOMEM;
-
-	err = gro_cells_init(&vxlan->gro_cells, dev);
-	if (err) {
-		free_percpu(dev->tstats);
-		return err;
+	if (!dev->tstats) {
+		err = -ENOMEM;
+		goto err_vnigroup_uninit;
 	}
 
+	err = gro_cells_init(&vxlan->gro_cells, dev);
+	if (err)
+		goto err_free_percpu;
+
 	return 0;
+
+err_free_percpu:
+	free_percpu(dev->tstats);
+err_vnigroup_uninit:
+	if (vxlan->cfg.flags & VXLAN_F_VNIFILTER)
+		vxlan_vnigroup_uninit(vxlan);
+	return err;
 }
 
 static void vxlan_fdb_delete_default(struct vxlan_dev *vxlan, __be32 vni)

drivers/net/wireless/ath/ath9k/htc.h

···
 }
 
 #ifdef CONFIG_ATH9K_HTC_DEBUGFS
-#define __STAT_SAFE(hif_dev, expr)	((hif_dev)->htc_handle->drv_priv ? (expr) : 0)
-#define CAB_STAT_INC(priv)		((priv)->debug.tx_stats.cab_queued++)
-#define TX_QSTAT_INC(priv, q)		((priv)->debug.tx_stats.queue_stats[q]++)
+#define __STAT_SAFE(hif_dev, expr)	do { ((hif_dev)->htc_handle->drv_priv ? (expr) : 0); } while (0)
+#define CAB_STAT_INC(priv)		do { ((priv)->debug.tx_stats.cab_queued++); } while (0)
+#define TX_QSTAT_INC(priv, q)		do { ((priv)->debug.tx_stats.queue_stats[q]++); } while (0)
 
 #define TX_STAT_INC(hif_dev, c) \
 		__STAT_SAFE((hif_dev), (hif_dev)->htc_handle->drv_priv->debug.tx_stats.c++)
···
 			    struct ethtool_stats *stats, u64 *data);
 #else
 
-#define TX_STAT_INC(hif_dev, c)
-#define TX_STAT_ADD(hif_dev, c, a)
-#define RX_STAT_INC(hif_dev, c)
-#define RX_STAT_ADD(hif_dev, c, a)
+#define TX_STAT_INC(hif_dev, c)		do { } while (0)
+#define TX_STAT_ADD(hif_dev, c, a)	do { } while (0)
+#define RX_STAT_INC(hif_dev, c)		do { } while (0)
+#define RX_STAT_ADD(hif_dev, c, a)	do { } while (0)
 
 #define CAB_STAT_INC(priv)
 #define TX_QSTAT_INC(priv, c)

drivers/net/wireless/intel/iwlwifi/fw/acpi.c

···
         int i, j, num_sub_bands;
         s8 *gain;
 
+	/* many firmware images for JF lie about this */
+	if (CSR_HW_RFID_TYPE(fwrt->trans->hw_rf_id) ==
+	    CSR_HW_RFID_TYPE(CSR_HW_RF_ID_TYPE_JF))
+		return -EOPNOTSUPP;
+
         if (!fw_has_capa(&fwrt->fw->ucode_capa, IWL_UCODE_TLV_CAPA_SET_PPAG)) {
                 IWL_DEBUG_RADIO(fwrt,
                                 "PPAG capability not supported by FW, command not sent.\n");

drivers/net/wireless/mediatek/mt76/mt7996/Kconfig

···
 config MT7996E
 	tristate "MediaTek MT7996 (PCIe) support"
 	select MT76_CONNAC_LIB
+	select RELAY
 	depends on MAC80211
 	depends on PCI
 	help

drivers/net/wireless/ti/Makefile

···
 obj-$(CONFIG_WL12XX)			+= wl12xx/
 obj-$(CONFIG_WL1251)			+= wl1251/
 obj-$(CONFIG_WL18XX)			+= wl18xx/
-
-# small builtin driver bit
-obj-$(CONFIG_WILINK_PLATFORM_DATA)	+= wilink_platform_data.o

drivers/nvme/host/auth.c

···
 		goto err_free_dhchap_secret;
 
 	if (!ctrl->opts->dhchap_secret && !ctrl->opts->dhchap_ctrl_secret)
-		return ret;
+		return 0;
 
 	ctrl->dhchap_ctxs = kvcalloc(ctrl_max_dhchaps(ctrl),
 				sizeof(*chap), GFP_KERNEL);

drivers/nvme/host/core.c

···
 	return 0;
 }
 
+static u32 nvme_known_nvm_effects(u8 opcode)
+{
+	switch (opcode) {
+	case nvme_cmd_write:
+	case nvme_cmd_write_zeroes:
+	case nvme_cmd_write_uncor:
+		 return NVME_CMD_EFFECTS_LBCC;
+	default:
+		return 0;
+	}
+}
+
 u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode)
 {
 	u32 effects = 0;
···
 	if (ns) {
 		if (ns->head->effects)
 			effects = le32_to_cpu(ns->head->effects->iocs[opcode]);
+		if (ns->head->ids.csi == NVME_CAP_CSS_NVM)
+			effects |= nvme_known_nvm_effects(opcode);
 		if (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC))
 			dev_warn_once(ctrl->device,
-				"IO command:%02x has unhandled effects:%08x\n",
+				"IO command:%02x has unusual effects:%08x\n",
 				opcode, effects);
-		return 0;
-	}
 
-	if (ctrl->effects)
-		effects = le32_to_cpu(ctrl->effects->acs[opcode]);
-	effects |= nvme_known_admin_effects(opcode);
+		/*
+		 * NVME_CMD_EFFECTS_CSE_MASK causes a freeze all I/O queues,
+		 * which would deadlock when done on an I/O command.  Note that
+		 * We already warn about an unusual effect above.
+		 */
+		effects &= ~NVME_CMD_EFFECTS_CSE_MASK;
+	} else {
+		if (ctrl->effects)
+			effects = le32_to_cpu(ctrl->effects->acs[opcode]);
+		effects |= nvme_known_admin_effects(opcode);
+	}
 
 	return effects;
 }
···
 
 	memset(set, 0, sizeof(*set));
 	set->ops = ops;
-	set->queue_depth = ctrl->sqsize + 1;
+	set->queue_depth = min_t(unsigned, ctrl->sqsize, BLK_MQ_MAX_DEPTH - 1);
 	/*
 	 * Some Apple controllers requires tags to be unique across admin and
 	 * the (only) I/O queue, so reserve the first 32 tags of the I/O queue.

drivers/nvme/host/ioctl.c

···
 static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c,
 		fmode_t mode)
 {
+	u32 effects;
+
 	if (capable(CAP_SYS_ADMIN))
 		return true;
 
···
 	}
 
 	/*
-	 * Only allow I/O commands that transfer data to the controller if the
-	 * special file is open for writing, but always allow I/O commands that
-	 * transfer data from the controller.
+	 * Check if the controller provides a Commands Supported and Effects log
+	 * and marks this command as supported.  If not reject unprivileged
+	 * passthrough.
 	 */
-	if (nvme_is_write(c))
+	effects = nvme_command_effects(ns->ctrl, ns, c->common.opcode);
+	if (!(effects & NVME_CMD_EFFECTS_CSUPP))
+		return false;
+
+	/*
+	 * Don't allow passthrough for command that have intrusive (or unknown)
+	 * effects.
+	 */
+	if (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC |
+			NVME_CMD_EFFECTS_UUID_SEL |
+			NVME_CMD_EFFECTS_SCOPE_MASK))
+		return false;
+
+	/*
+	 * Only allow I/O commands that transfer data to the controller or that
+	 * change the logical block contents if the file descriptor is open for
+	 * writing.
+	 */
+	if (nvme_is_write(c) || (effects & NVME_CMD_EFFECTS_LBCC))
 		return mode & FMODE_WRITE;
 	return true;
 }

drivers/nvme/host/multipath.c

···
 	 * pool from the original queue to allocate the bvecs from.
 	 */
 	bio = bio_split_to_limits(bio);
+	if (!bio)
+		return;
 
 	srcu_idx = srcu_read_lock(&head->srcu);
 	ns = nvme_find_path(head);

drivers/nvme/host/nvme.h

···
 {
 	struct nvme_ns *ns = req->q->queuedata;
 
-	if (req->cmd_flags & REQ_NVME_MPATH)
+	if ((req->cmd_flags & REQ_NVME_MPATH) && req->bio)
 		trace_block_bio_complete(ns->head->disk->queue, req->bio);
 }
 

drivers/nvme/host/pci.c

···
 #define SQ_SIZE(q)	((q)->q_depth << (q)->sqes)
 #define CQ_SIZE(q)	((q)->q_depth * sizeof(struct nvme_completion))
 
-#define SGES_PER_PAGE	(PAGE_SIZE / sizeof(struct nvme_sgl_desc))
+#define SGES_PER_PAGE	(NVME_CTRL_PAGE_SIZE / sizeof(struct nvme_sgl_desc))
 
 /*
  * These can be higher, but we need to ensure that any command doesn't
···
 	mempool_t *iod_mempool;
 
 	/* shadow doorbell buffer support: */
-	u32 *dbbuf_dbs;
+	__le32 *dbbuf_dbs;
 	dma_addr_t dbbuf_dbs_dma_addr;
-	u32 *dbbuf_eis;
+	__le32 *dbbuf_eis;
 	dma_addr_t dbbuf_eis_dma_addr;
 
 	/* host memory buffer support: */
···
 #define NVMEQ_SQ_CMB		1
 #define NVMEQ_DELETE_ERROR	2
 #define NVMEQ_POLLED		3
-	u32 *dbbuf_sq_db;
-	u32 *dbbuf_cq_db;
-	u32 *dbbuf_sq_ei;
-	u32 *dbbuf_cq_ei;
+	__le32 *dbbuf_sq_db;
+	__le32 *dbbuf_cq_db;
+	__le32 *dbbuf_sq_ei;
+	__le32 *dbbuf_cq_ei;
 	struct completion delete_done;
 };
 
···
 }
 
 /* Update dbbuf and return true if an MMIO is required */
-static bool nvme_dbbuf_update_and_check_event(u16 value, u32 *dbbuf_db,
-					      volatile u32 *dbbuf_ei)
+static bool nvme_dbbuf_update_and_check_event(u16 value, __le32 *dbbuf_db,
+					      volatile __le32 *dbbuf_ei)
 {
 	if (dbbuf_db) {
-		u16 old_value;
+		u16 old_value, event_idx;
 
 		/*
 		 * Ensure that the queue is written before updating
···
 		 */
 		wmb();
 
-		old_value = *dbbuf_db;
-		*dbbuf_db = value;
+		old_value = le32_to_cpu(*dbbuf_db);
+		*dbbuf_db = cpu_to_le32(value);
 
 		/*
 		 * Ensure that the doorbell is updated before reading the event
···
 		 */
 		mb();
 
-		if (!nvme_dbbuf_need_event(*dbbuf_ei, value, old_value))
+		event_idx = le32_to_cpu(*dbbuf_ei);
+		if (!nvme_dbbuf_need_event(event_idx, value, old_value))
 			return false;
 	}
 
···
  */
 static int nvme_pci_npages_prp(void)
 {
-	unsigned nprps = DIV_ROUND_UP(NVME_MAX_KB_SZ + NVME_CTRL_PAGE_SIZE,
-				      NVME_CTRL_PAGE_SIZE);
-	return DIV_ROUND_UP(8 * nprps, PAGE_SIZE - 8);
+	unsigned max_bytes = (NVME_MAX_KB_SZ * 1024) + NVME_CTRL_PAGE_SIZE;
+	unsigned nprps = DIV_ROUND_UP(max_bytes, NVME_CTRL_PAGE_SIZE);
+	return DIV_ROUND_UP(8 * nprps, NVME_CTRL_PAGE_SIZE - 8);
 }
 
 /*
···
 static int nvme_pci_npages_sgl(void)
 {
 	return DIV_ROUND_UP(NVME_MAX_SEGS * sizeof(struct nvme_sgl_desc),
-			PAGE_SIZE);
+			NVME_CTRL_PAGE_SIZE);
 }
 
 static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
···
 		sge->length = cpu_to_le32(entries * sizeof(*sge));
 		sge->type = NVME_SGL_FMT_LAST_SEG_DESC << 4;
 	} else {
-		sge->length = cpu_to_le32(PAGE_SIZE);
+		sge->length = cpu_to_le32(NVME_CTRL_PAGE_SIZE);
 		sge->type = NVME_SGL_FMT_SEG_DESC << 4;
 	}
 }
···
 	if (dev->cmb_use_sqes) {
 		result = nvme_cmb_qdepth(dev, nr_io_queues,
 				sizeof(struct nvme_command));
-		if (result > 0)
+		if (result > 0) {
 			dev->q_depth = result;
-		else
+			dev->ctrl.sqsize = result - 1;
+		} else {
 			dev->cmb_use_sqes = false;
+		}
 	}
 
 	do {
···
 
 	dev->q_depth = min_t(u32, NVME_CAP_MQES(dev->ctrl.cap) + 1,
 				io_queue_depth);
-	dev->ctrl.sqsize = dev->q_depth - 1; /* 0's based queue depth */
 	dev->db_stride = 1 << NVME_CAP_STRIDE(dev->ctrl.cap);
 	dev->dbs = dev->bar + 4096;
 
···
 		dev_warn(dev->ctrl.device, "IO queue depth clamped to %d\n",
 			 dev->q_depth);
 	}
-
+	dev->ctrl.sqsize = dev->q_depth - 1; /* 0's based queue depth */
 
 	nvme_map_cmb(dev);
 

drivers/nvme/target/admin-cmd.c

···
 
 static void nvmet_get_cmd_effects_nvm(struct nvme_effects_log *log)
 {
-	log->acs[nvme_admin_get_log_page]	= cpu_to_le32(1 << 0);
-	log->acs[nvme_admin_identify]		= cpu_to_le32(1 << 0);
-	log->acs[nvme_admin_abort_cmd]		= cpu_to_le32(1 << 0);
-	log->acs[nvme_admin_set_features]	= cpu_to_le32(1 << 0);
-	log->acs[nvme_admin_get_features]	= cpu_to_le32(1 << 0);
-	log->acs[nvme_admin_async_event]	= cpu_to_le32(1 << 0);
-	log->acs[nvme_admin_keep_alive]		= cpu_to_le32(1 << 0);
+	log->acs[nvme_admin_get_log_page] =
+	log->acs[nvme_admin_identify] =
+	log->acs[nvme_admin_abort_cmd] =
+	log->acs[nvme_admin_set_features] =
+	log->acs[nvme_admin_get_features] =
+	log->acs[nvme_admin_async_event] =
+	log->acs[nvme_admin_keep_alive] =
+		cpu_to_le32(NVME_CMD_EFFECTS_CSUPP);
 
-	log->iocs[nvme_cmd_read]		= cpu_to_le32(1 << 0);
-	log->iocs[nvme_cmd_write]		= cpu_to_le32(1 << 0);
-	log->iocs[nvme_cmd_flush]		= cpu_to_le32(1 << 0);
-	log->iocs[nvme_cmd_dsm]			= cpu_to_le32(1 << 0);
-	log->iocs[nvme_cmd_write_zeroes]	= cpu_to_le32(1 << 0);
+	log->iocs[nvme_cmd_read] =
+	log->iocs[nvme_cmd_flush] =
+	log->iocs[nvme_cmd_dsm]	=
+		cpu_to_le32(NVME_CMD_EFFECTS_CSUPP);
+	log->iocs[nvme_cmd_write] =
+	log->iocs[nvme_cmd_write_zeroes] =
+		cpu_to_le32(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC);
 }
 
 static void nvmet_get_cmd_effects_zns(struct nvme_effects_log *log)
 {
-	log->iocs[nvme_cmd_zone_append]		= cpu_to_le32(1 << 0);
-	log->iocs[nvme_cmd_zone_mgmt_send]	= cpu_to_le32(1 << 0);
-	log->iocs[nvme_cmd_zone_mgmt_recv]	= cpu_to_le32(1 << 0);
+	log->iocs[nvme_cmd_zone_append] =
+	log->iocs[nvme_cmd_zone_mgmt_send] =
+		cpu_to_le32(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC);
+	log->iocs[nvme_cmd_zone_mgmt_recv] =
+		cpu_to_le32(NVME_CMD_EFFECTS_CSUPP);
 }
 
 static void nvmet_execute_get_log_cmd_effects_ns(struct nvmet_req *req)

drivers/nvme/target/passthru.c

···
 	}
 
 	/*
-	 * If there are effects for the command we are about to execute, or
-	 * an end_req function we need to use nvme_execute_passthru_rq()
-	 * synchronously in a work item seeing the end_req function and
-	 * nvme_passthru_end() can't be called in the request done callback
-	 * which is typically in interrupt context.
+	 * If a command needs post-execution fixups, or there are any
+	 * non-trivial effects, make sure to execute the command synchronously
+	 * in a workqueue so that nvme_passthru_end gets called.
 	 */
 	effects = nvme_command_effects(ctrl, ns, req->cmd->common.opcode);
-	if (req->p.use_workqueue || effects) {
+	if (req->p.use_workqueue ||
+	    (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC))) {
 		INIT_WORK(&req->p.work, nvmet_passthru_execute_cmd_work);
 		req->p.rq = rq;
 		queue_work(nvmet_wq, &req->p.work);

drivers/of/fdt.c

···
  */
 int __init early_init_dt_scan_memory(void)
 {
-	int node;
+	int node, found_memory = 0;
 	const void *fdt = initial_boot_params;
 
 	fdt_for_each_subnode(node, fdt, 0) {
···
 
 			early_init_dt_add_memory_arch(base, size);
 
+			found_memory = 1;
+
 			if (!hotpluggable)
 				continue;
 
···
 					base, base + size);
 		}
 	}
-	return 0;
+	return found_memory;
 }
 
 int __init early_init_dt_scan_chosen(char *cmdline)
···
 	if (node < 0)
 		node = fdt_path_offset(fdt, "/chosen@0");
 	if (node < 0)
-		return -ENOENT;
+		/* Handle the cmdline config options even if no /chosen node */
+		goto handle_cmdline;
 
 	chosen_node_offset = node;
 
 	early_init_dt_check_for_initrd(node);
 	early_init_dt_check_for_elfcorehdr(node);
-
-	/* Retrieve command line */
-	p = of_get_flat_dt_prop(node, "bootargs", &l);
-	if (p != NULL && l > 0)
-		strscpy(cmdline, p, min(l, COMMAND_LINE_SIZE));
 
 	rng_seed = of_get_flat_dt_prop(node, "rng-seed", &l);
 	if (rng_seed && l > 0) {
···
 		of_fdt_crc32 = crc32_be(~0, initial_boot_params,
 				fdt_totalsize(initial_boot_params));
 	}
+
+	/* Retrieve command line */
+	p = of_get_flat_dt_prop(node, "bootargs", &l);
+	if (p != NULL && l > 0)
+		strscpy(cmdline, p, min(l, COMMAND_LINE_SIZE));
+
+handle_cmdline:
+	/*
+	 * CONFIG_CMDLINE is meant to be a default in case nothing else
+	 * managed to set the command line, unless CONFIG_CMDLINE_FORCE
+	 * is set in which case we override whatever was found earlier.
+	 */
+#ifdef CONFIG_CMDLINE
+#if defined(CONFIG_CMDLINE_EXTEND)
+	strlcat(cmdline, " ", COMMAND_LINE_SIZE);
+	strlcat(cmdline, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
+#elif defined(CONFIG_CMDLINE_FORCE)
+	strscpy(cmdline, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
+#else
+	/* No arguments from boot loader, use kernel's  cmdl*/
+	if (!((char *)cmdline)[0])
+		strscpy(cmdline, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
+#endif
+#endif /* CONFIG_CMDLINE */
+
+	pr_debug("Command line is: %s\n", (char *)cmdline);
 
 	return 0;
 }
···
 	rc = early_init_dt_scan_chosen(boot_command_line);
 	if (rc)
 		pr_warn("No chosen node found, continuing without\n");
-
-	/*
-	 * CONFIG_CMDLINE is meant to be a default in case nothing else
-	 * managed to set the command line, unless CONFIG_CMDLINE_FORCE
-	 * is set in which case we override whatever was found earlier.
-	 */
-#ifdef CONFIG_CMDLINE
-#if defined(CONFIG_CMDLINE_EXTEND)
-	strlcat(boot_command_line, " ", COMMAND_LINE_SIZE);
-	strlcat(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
-#elif defined(CONFIG_CMDLINE_FORCE)
-	strscpy(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
-#else
-	/* No arguments from boot loader, use kernel's cmdl */
-	if (!boot_command_line[0])
-		strscpy(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE);
-#endif
-#endif /* CONFIG_CMDLINE */
-
-	pr_debug("Command line is: %s\n", boot_command_line);
 
 	/* Setup memory, calling early_init_dt_add_memory_arch */
 	early_init_dt_scan_memory();

drivers/s390/block/dcssblk.c

···
 	unsigned long bytes_done;
 
 	bio = bio_split_to_limits(bio);
+	if (!bio)
+		return;
 
 	bytes_done = 0;
 	dev_info = bio->bi_bdev->bd_disk->private_data;

drivers/s390/net/qeth_core_sys.c

···
 
 	switch (card->options.isolation) {
 	case ISOLATION_MODE_NONE:
-		return snprintf(buf, 6, "%s\n", ATTR_QETH_ISOLATION_NONE);
+		return sysfs_emit(buf, "%s\n", ATTR_QETH_ISOLATION_NONE);
 	case ISOLATION_MODE_FWD:
-		return snprintf(buf, 9, "%s\n", ATTR_QETH_ISOLATION_FWD);
+		return sysfs_emit(buf, "%s\n", ATTR_QETH_ISOLATION_FWD);
 	case ISOLATION_MODE_DROP:
-		return snprintf(buf, 6, "%s\n", ATTR_QETH_ISOLATION_DROP);
+		return sysfs_emit(buf, "%s\n", ATTR_QETH_ISOLATION_DROP);
 	default:
-		return snprintf(buf, 5, "%s\n", "N/A");
+		return sysfs_emit(buf, "%s\n", "N/A");
 	}
 }
 
···
 	struct qeth_card *card = dev_get_drvdata(dev);
 
 	if (card->info.hwtrap)
-		return snprintf(buf, 5, "arm\n");
+		return sysfs_emit(buf, "arm\n");
 	else
-		return snprintf(buf, 8, "disarm\n");
+		return sysfs_emit(buf, "disarm\n");
 }
 
 static ssize_t qeth_hw_trap_store(struct device *dev,

drivers/thermal/intel/int340x_thermal/processor_thermal_rfim.c

···
 RFIM_SHOW(rfi_restriction_run_busy, 1)
 RFIM_SHOW(rfi_restriction_err_code, 1)
 RFIM_SHOW(rfi_restriction_data_rate, 1)
+RFIM_SHOW(rfi_restriction_data_rate_base, 1)
 RFIM_SHOW(ddr_data_rate_point_0, 1)
 RFIM_SHOW(ddr_data_rate_point_1, 1)
 RFIM_SHOW(ddr_data_rate_point_2, 1)
···
 RFIM_STORE(rfi_restriction_run_busy, 1)
 RFIM_STORE(rfi_restriction_err_code, 1)
 RFIM_STORE(rfi_restriction_data_rate, 1)
+RFIM_STORE(rfi_restriction_data_rate_base, 1)
 RFIM_STORE(rfi_disable, 1)
 
 static DEVICE_ATTR_RW(rfi_restriction_run_busy);
 static DEVICE_ATTR_RW(rfi_restriction_err_code);
 static DEVICE_ATTR_RW(rfi_restriction_data_rate);
+static DEVICE_ATTR_RW(rfi_restriction_data_rate_base);
 static DEVICE_ATTR_RO(ddr_data_rate_point_0);
 static DEVICE_ATTR_RO(ddr_data_rate_point_1);
 static DEVICE_ATTR_RO(ddr_data_rate_point_2);
···
 	&dev_attr_rfi_restriction_run_busy.attr,
 	&dev_attr_rfi_restriction_err_code.attr,
 	&dev_attr_rfi_restriction_data_rate.attr,
+	&dev_attr_rfi_restriction_data_rate_base.attr,
 	&dev_attr_ddr_data_rate_point_0.attr,
 	&dev_attr_ddr_data_rate_point_1.attr,
 	&dev_attr_ddr_data_rate_point_2.attr,

drivers/usb/common/ulpi.c

···
 	/* Test the interface */
 	ret = ulpi_write(ulpi, ULPI_SCRATCH, 0xaa);
 	if (ret < 0)
-		return ret;
+		goto err;
 
 	ret = ulpi_read(ulpi, ULPI_SCRATCH);
 	if (ret < 0)

drivers/usb/dwc3/dwc3-xilinx.c

···
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
+#include <linux/gpio/consumer.h>
 #include <linux/of_gpio.h>
 #include <linux/of_platform.h>
 #include <linux/pm_runtime.h>

drivers/usb/dwc3/gadget.c

···
 	else if (!ret)
 		dep->flags |= DWC3_EP_END_TRANSFER_PENDING;
 
+	dep->flags &= ~DWC3_EP_DELAY_STOP;
 	return ret;
 }
 
···
 	if (dep->number <= 1 && dwc->ep0state != EP0_DATA_PHASE)
 		return;
 
+	if (interrupt && (dep->flags & DWC3_EP_DELAY_STOP))
+		return;
+
 	if (!(dep->flags & DWC3_EP_TRANSFER_STARTED) ||
-	    (dep->flags & DWC3_EP_DELAY_STOP) ||
 	    (dep->flags & DWC3_EP_END_TRANSFER_PENDING))
 		return;
 

drivers/usb/fotg210/fotg210-core.c

···
 
 static int __init fotg210_init(void)
 {
-	if (usb_disabled())
-		return -ENODEV;
-
-	if (IS_ENABLED(CONFIG_USB_FOTG210_HCD))
+	if (IS_ENABLED(CONFIG_USB_FOTG210_HCD) && !usb_disabled())
 		fotg210_hcd_init();
 	return platform_driver_register(&fotg210_driver);
 }

drivers/usb/fotg210/fotg210-udc.c

···
 		dev_info(dev, "found and initialized PHY\n");
 	}
 
+	ret = -ENOMEM;
+
 	for (i = 0; i < FOTG210_MAX_NUM_EP; i++) {
 		fotg210->ep[i] = kzalloc(sizeof(struct fotg210_ep), GFP_KERNEL);
 		if (!fotg210->ep[i])

drivers/vdpa/mlx5/core/mlx5_vdpa.h

···
 			  int inlen);
 int mlx5_vdpa_destroy_mkey(struct mlx5_vdpa_dev *mvdev, u32 mkey);
 int mlx5_vdpa_handle_set_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
-			     bool *change_map);
-int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb);
+			     bool *change_map, unsigned int asid);
+int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
+			unsigned int asid);
 void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev);
 
 #define mlx5_vdpa_warn(__dev, format, ...)                                                         \

drivers/vdpa/mlx5/core/mr.c

···
 	u64 st;
 	u64 sz;
 	int err;
-	int i = 0;
 
 	st = start;
 	while (size) {
···
 		mr->num_directs++;
 		mr->num_klms++;
 		st += sz;
-		i++;
 	}
 	list_splice_tail(&tmp, &mr->head);
 	return 0;
···
 	mutex_unlock(&mr->mkey_mtx);
 }
 
-static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
+static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev,
+				struct vhost_iotlb *iotlb, unsigned int asid)
 {
 	struct mlx5_vdpa_mr *mr = &mvdev->mr;
 	int err;
···
 	if (mr->initialized)
 		return 0;
 
-	if (iotlb)
-		err = create_user_mr(mvdev, iotlb);
-	else
-		err = create_dma_mr(mvdev, mr);
+	if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] == asid) {
+		if (iotlb)
+			err = create_user_mr(mvdev, iotlb);
+		else
+			err = create_dma_mr(mvdev, mr);
 
-	if (err)
-		return err;
+		if (err)
+			return err;
+	}
 
-	err = dup_iotlb(mvdev, iotlb);
-	if (err)
-		goto out_err;
+	if (mvdev->group2asid[MLX5_VDPA_CVQ_GROUP] == asid) {
+		err = dup_iotlb(mvdev, iotlb);
+		if (err)
+			goto out_err;
+	}
 
 	mr->initialized = true;
 	return 0;
 
 out_err:
-	if (iotlb)
-		destroy_user_mr(mvdev, mr);
-	else
-		destroy_dma_mr(mvdev, mr);
+	if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] == asid) {
+		if (iotlb)
+			destroy_user_mr(mvdev, mr);
+		else
+			destroy_dma_mr(mvdev, mr);
+	}
 
 	return err;
 }
 
-int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
+int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
+			unsigned int asid)
 {
 	int err;
 
 	mutex_lock(&mvdev->mr.mkey_mtx);
-	err = _mlx5_vdpa_create_mr(mvdev, iotlb);
+	err = _mlx5_vdpa_create_mr(mvdev, iotlb, asid);
 	mutex_unlock(&mvdev->mr.mkey_mtx);
 	return err;
 }
 
 int mlx5_vdpa_handle_set_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
-			     bool *change_map)
+			     bool *change_map, unsigned int asid)
 {
 	struct mlx5_vdpa_mr *mr = &mvdev->mr;
 	int err = 0;
···
 		*change_map = true;
 	}
 	if (!*change_map)
-		err = _mlx5_vdpa_create_mr(mvdev, iotlb);
+		err = _mlx5_vdpa_create_mr(mvdev, iotlb, asid);
 	mutex_unlock(&mr->mkey_mtx);
 
 	return err;

drivers/vdpa/mlx5/net/mlx5_vnet.c

···
 	dmac_v = MLX5_ADDR_OF(fte_match_param, headers_v, outer_headers.dmac_47_16);
 	eth_broadcast_addr(dmac_c);
 	ether_addr_copy(dmac_v, mac);
-	MLX5_SET(fte_match_set_lyr_2_4, headers_c, cvlan_tag, 1);
+	if (ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VLAN)) {
+		MLX5_SET(fte_match_set_lyr_2_4, headers_c, cvlan_tag, 1);
+		MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, first_vid);
+	}
 	if (tagged) {
 		MLX5_SET(fte_match_set_lyr_2_4, headers_v, cvlan_tag, 1);
-		MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, first_vid);
-		MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_vid, vid);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_vid, vid);
 	}
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_TIR;
···
 
 		/* Need recreate the flow table entry, so that the packet could forward back
 		 */
-		mac_vlan_del(ndev, ndev->config.mac, 0, false);
+		mac_vlan_del(ndev, mac_back, 0, false);
 
 		if (mac_vlan_add(ndev, ndev->config.mac, 0, false)) {
 			mlx5_vdpa_warn(mvdev, "failed to insert forward rules, try to restore\n");
···
 	__virtio16 vlan;
 	size_t read;
 	u16 id;
+
+	if (!(ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VLAN)))
+		return status;
 
 	switch (cmd) {
 	case VIRTIO_NET_CTRL_VLAN_ADD:
···
 	}
 }
 
-static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
+static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev,
+				struct vhost_iotlb *iotlb, unsigned int asid)
 {
 	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
 	int err;
···
 
 	teardown_driver(ndev);
 	mlx5_vdpa_destroy_mr(mvdev);
-	err = mlx5_vdpa_create_mr(mvdev, iotlb);
+	err = mlx5_vdpa_create_mr(mvdev, iotlb, asid);
 	if (err)
 		goto err_mr;
 
···
 	++mvdev->generation;
 
 	if (MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) {
-		if (mlx5_vdpa_create_mr(mvdev, NULL))
+		if (mlx5_vdpa_create_mr(mvdev, NULL, 0))
 			mlx5_vdpa_warn(mvdev, "create MR failed\n");
 	}
 	up_write(&ndev->reslock);
···
 	return mvdev->generation;
 }
 
-static int set_map_control(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
-{
-	u64 start = 0ULL, last = 0ULL - 1;
-	struct vhost_iotlb_map *map;
-	int err = 0;
-
-	spin_lock(&mvdev->cvq.iommu_lock);
-	vhost_iotlb_reset(mvdev->cvq.iotlb);
-
-	for (map = vhost_iotlb_itree_first(iotlb, start, last); map;
-	     map = vhost_iotlb_itree_next(map, start, last)) {
-		err = vhost_iotlb_add_range(mvdev->cvq.iotlb, map->start,
-					    map->last, map->addr, map->perm);
-		if (err)
-			goto out;
-	}
-
-out:
-	spin_unlock(&mvdev->cvq.iommu_lock);
-	return err;
-}
-
-static int set_map_data(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
+static int set_map_data(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
+			unsigned int asid)
 {
 	bool change_map;
 	int err;
 
-	err = mlx5_vdpa_handle_set_map(mvdev, iotlb, &change_map);
+	err = mlx5_vdpa_handle_set_map(mvdev, iotlb, &change_map, asid);
 	if (err) {
 		mlx5_vdpa_warn(mvdev, "set map failed(%d)\n", err);
 		return err;
 	}
 
 	if (change_map)
-		err = mlx5_vdpa_change_map(mvdev, iotlb);
+		err = mlx5_vdpa_change_map(mvdev, iotlb, asid);
 
 	return err;
 }
···
 	int err = -EINVAL;
 
 	down_write(&ndev->reslock);
-	if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] == asid) {
-		err = set_map_data(mvdev, iotlb);
-		if (err)
-			goto out;
-	}
-
-	if (mvdev->group2asid[MLX5_VDPA_CVQ_GROUP] == asid)
-		err = set_map_control(mvdev, iotlb);
-
-out:
+	err = set_map_data(mvdev, iotlb, asid);
 	up_write(&ndev->reslock);
 	return err;
 }
···
 	int i;
 
 	down_write(&ndev->reslock);
-	mlx5_notifier_unregister(mvdev->mdev, &ndev->nb);
 	ndev->nb_registered = false;
+	mlx5_notifier_unregister(mvdev->mdev, &ndev->nb);
 	flush_workqueue(ndev->mvdev.wq);
 	for (i = 0; i < ndev->cur_num_vqs; i++) {
 		mvq = &ndev->vqs[i];
···
 	else
 		ndev->config.status &= cpu_to_mlx5vdpa16(mvdev, ~VIRTIO_NET_S_LINK_UP);
 
-	if (ndev->config_cb.callback)
+	if (ndev->nb_registered && ndev->config_cb.callback)
 		ndev->config_cb.callback(ndev->config_cb.private);
 
 	kfree(wqent);
···
 		switch (eqe->sub_type) {
 		case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
 		case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
-			down_read(&ndev->reslock);
-			if (!ndev->nb_registered) {
-				up_read(&ndev->reslock);
-				return NOTIFY_DONE;
-			}
 			wqent = kzalloc(sizeof(*wqent), GFP_ATOMIC);
-			if (!wqent) {
-				up_read(&ndev->reslock);
+			if (!wqent)
 				return NOTIFY_DONE;
-			}
 
 			wqent->mvdev = &ndev->mvdev;
 			INIT_WORK(&wqent->work, update_carrier);
 			queue_work(ndev->mvdev.wq, &wqent->work);
-			up_read(&ndev->reslock);
 			ret = NOTIFY_OK;
 			break;
 		default:
···
 		goto err_mpfs;
 
 	if (MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) {
-		err = mlx5_vdpa_create_mr(mvdev, NULL);
+		err = mlx5_vdpa_create_mr(mvdev, NULL, 0);
 		if (err)
 			goto err_res;
 	}
···
 	struct workqueue_struct *wq;
 
 	if (ndev->nb_registered) {
-		mlx5_notifier_unregister(mvdev->mdev, &ndev->nb);
 		ndev->nb_registered = false;
+		mlx5_notifier_unregister(mvdev->mdev, &ndev->nb);
 	}
 	wq = mvdev->wq;
 	mvdev->wq = NULL;

drivers/vdpa/vdpa.c

···
 
 	features_device = vdev->config->get_device_features(vdev);
 
-	if (nla_put_u64_64bit(msg, VDPA_ATTR_VDPA_DEV_SUPPORTED_FEATURES, features_device,
+	if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_FEATURES, features_device,
 			      VDPA_ATTR_PAD))
 		return -EMSGSIZE;
 
···
 {
 	struct virtio_net_config config = {};
 	u64 features;
-	u16 max_vqp;
 	u8 status;
 	int err;
 
···
 	}
 	vdpa_get_config_unlocked(vdev, 0, &config, sizeof(config));
 
-	max_vqp = __virtio16_to_cpu(true, config.max_virtqueue_pairs);
-	if (nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MAX_VQP, max_vqp))
-		return -EMSGSIZE;
-
 	features = vdev->config->get_driver_features(vdev);
 	if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_NEGOTIATED_FEATURES,
 			      features, VDPA_ATTR_PAD))
 		return -EMSGSIZE;
+
+	err = vdpa_dev_net_mq_config_fill(msg, features, &config);
+	if (err)
+		return err;
 
 	if (nla_put_u32(msg, VDPA_ATTR_DEV_QUEUE_INDEX, index))
 		return -EMSGSIZE;

drivers/vdpa/vdpa_sim/vdpa_sim.c

···
 {
 	struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx];
 
-	vringh_init_iotlb(&vq->vring, vdpasim->dev_attr.supported_features,
-			  VDPASIM_QUEUE_MAX, false,
+	vringh_init_iotlb(&vq->vring, vdpasim->features, vq->num, false,
 			  (struct vring_desc *)(uintptr_t)vq->desc_addr,
 			  (struct vring_avail *)
 			  (uintptr_t)vq->driver_addr,
···
 	}
 
 	kvfree(vdpasim->buffer);
-	vhost_iotlb_free(vdpasim->iommu);
+	for (i = 0; i < vdpasim->dev_attr.nas; i++)
+		vhost_iotlb_reset(&vdpasim->iommu[i]);
+	kfree(vdpasim->iommu);
 	kfree(vdpasim->vqs);
 	kfree(vdpasim->config);
 }

drivers/vdpa/vdpa_sim/vdpa_sim_blk.c

···
 	int ret;
 
 	ret = device_register(&vdpasim_blk_mgmtdev);
-	if (ret)
+	if (ret) {
+		put_device(&vdpasim_blk_mgmtdev);
 		return ret;
+	}
 
 	ret = vdpa_mgmtdev_register(&mgmt_dev);
 	if (ret)

drivers/vdpa/vdpa_sim/vdpa_sim_net.c

···
 	if (len < ETH_ALEN + hdr_len)
 		return false;
 
+	if (is_broadcast_ether_addr(vdpasim->buffer + hdr_len) ||
+	    is_multicast_ether_addr(vdpasim->buffer + hdr_len))
+		return true;
 	if (!strncmp(vdpasim->buffer + hdr_len, vio_config->mac, ETH_ALEN))
 		return true;
 
···
 	int ret;
 
 	ret = device_register(&vdpasim_net_mgmtdev);
-	if (ret)
+	if (ret) {
+		put_device(&vdpasim_net_mgmtdev);
 		return ret;
+	}
 
 	ret = vdpa_mgmtdev_register(&mgmt_dev);
 	if (ret)

drivers/vdpa/vdpa_user/vduse_dev.c

···
 	if (config->config_size > PAGE_SIZE)
 		return false;
 
+	if (config->vq_num > 0xffff)
+		return false;
+
 	if (!device_is_allowed(config->device_id))
 		return false;
 

drivers/vdpa/virtio_pci/vp_vdpa.c

···
 	mdev = vp_vdpa_mgtdev->mdev;
 	vp_modern_remove(mdev);
 	vdpa_mgmtdev_unregister(&vp_vdpa_mgtdev->mgtdev);
-	kfree(&vp_vdpa_mgtdev->mgtdev.id_table);
+	kfree(vp_vdpa_mgtdev->mgtdev.id_table);
 	kfree(mdev);
 	kfree(vp_vdpa_mgtdev);
 }

drivers/vhost/vdpa.c

···
 
 static dev_t vhost_vdpa_major;
 
+static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v,
+				   struct vhost_iotlb *iotlb, u64 start,
+				   u64 last, u32 asid);
+
 static inline u32 iotlb_to_asid(struct vhost_iotlb *iotlb)
 {
 	struct vhost_vdpa_as *as = container_of(iotlb, struct
···
 		return -EINVAL;
 
 	hlist_del(&as->hash_link);
-	vhost_iotlb_reset(&as->iotlb);
+	vhost_vdpa_iotlb_unmap(v, &as->iotlb, 0ULL, 0ULL - 1, asid);
 	kfree(as);
 
 	return 0;
···
 	mutex_unlock(&d->mutex);
 	return r;
 }
+static void vhost_vdpa_general_unmap(struct vhost_vdpa *v,
+				     struct vhost_iotlb_map *map, u32 asid)
+{
+	struct vdpa_device *vdpa = v->vdpa;
+	const struct vdpa_config_ops *ops = vdpa->config;
+	if (ops->dma_map) {
+		ops->dma_unmap(vdpa, asid, map->start, map->size);
+	} else if (ops->set_map == NULL) {
+		iommu_unmap(v->domain, map->start, map->size);
+	}
+}
 
-static void vhost_vdpa_pa_unmap(struct vhost_vdpa *v,
-				struct vhost_iotlb *iotlb,
-				u64 start, u64 last)
+static void vhost_vdpa_pa_unmap(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,
+				u64 start, u64 last, u32 asid)
 {
 	struct vhost_dev *dev = &v->vdev;
 	struct vhost_iotlb_map *map;
···
 			unpin_user_page(page);
 		}
 		atomic64_sub(PFN_DOWN(map->size), &dev->mm->pinned_vm);
+		vhost_vdpa_general_unmap(v, map, asid);
 		vhost_iotlb_map_free(iotlb, map);
 	}
 }
 
-static void vhost_vdpa_va_unmap(struct vhost_vdpa *v,
-				struct vhost_iotlb *iotlb,
-				u64 start, u64 last)
+static void vhost_vdpa_va_unmap(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,
+				u64 start, u64 last, u32 asid)
 {
 	struct vhost_iotlb_map *map;
 	struct vdpa_map_file *map_file;
···
 		map_file = (struct vdpa_map_file *)map->opaque;
 		fput(map_file->file);
 		kfree(map_file);
+		vhost_vdpa_general_unmap(v, map, asid);
 		vhost_iotlb_map_free(iotlb, map);
 	}
 }
 
 static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v,
-				   struct vhost_iotlb *iotlb,
-				   u64 start, u64 last)
+				   struct vhost_iotlb *iotlb, u64 start,
+				   u64 last, u32 asid)
 {
 	struct vdpa_device *vdpa = v->vdpa;
 
 	if (vdpa->use_va)
-		return vhost_vdpa_va_unmap(v, iotlb, start, last);
+		return vhost_vdpa_va_unmap(v, iotlb, start, last, asid);
 
-	return vhost_vdpa_pa_unmap(v, iotlb, start, last);
+	return vhost_vdpa_pa_unmap(v, iotlb, start, last, asid);
 }
 
 static int perm_to_iommu_flags(u32 perm)
···
 	const struct vdpa_config_ops *ops = vdpa->config;
 	u32 asid = iotlb_to_asid(iotlb);
 
-	vhost_vdpa_iotlb_unmap(v, iotlb, iova, iova + size - 1);
+	vhost_vdpa_iotlb_unmap(v, iotlb, iova, iova + size - 1, asid);
 
-	if (ops->dma_map) {
-		ops->dma_unmap(vdpa, asid, iova, size);
-	} else if (ops->set_map) {
+	if (ops->set_map) {
 		if (!v->in_batch)
 			ops->set_map(vdpa, asid, iotlb);
-	} else {
-		iommu_unmap(v->domain, iova, size);
 	}
-
 	/* If we are in the middle of batch processing, delay the free
 	 * of AS until BATCH_END.
 	 */
···
 	struct vhost_vdpa_as *as;
 	u32 asid;
 
-	vhost_dev_cleanup(&v->vdev);
-	kfree(v->vdev.vqs);
-
 	for (asid = 0; asid < v->vdpa->nas; asid++) {
 		as = asid_to_as(v, asid);
 		if (as)
 			vhost_vdpa_remove_as(v, asid);
 	}
+
+	vhost_dev_cleanup(&v->vdev);
+	kfree(v->vdev.vqs);
 }
 
 static int vhost_vdpa_open(struct inode *inode, struct file *filep)

drivers/vhost/vhost.c

···
 	struct vhost_dev *dev = vq->dev;
 	struct vhost_iotlb *umem = dev->iotlb ? dev->iotlb : dev->umem;
 	struct iovec *_iov;
-	u64 s = 0;
+	u64 s = 0, last = addr + len - 1;
 	int ret = 0;
 
 	while ((u64)len > s) {
···
 			break;
 		}
 
-		map = vhost_iotlb_itree_first(umem, addr, addr + len - 1);
+		map = vhost_iotlb_itree_first(umem, addr, last);
 		if (map == NULL || map->start > addr) {
 			if (umem != dev->iotlb) {
 				ret = -EFAULT;

drivers/vhost/vringh.c

···
 	struct vhost_iotlb_map *map;
 	struct vhost_iotlb *iotlb = vrh->iotlb;
 	int ret = 0;
-	u64 s = 0;
+	u64 s = 0, last = addr + len - 1;
 
 	spin_lock(vrh->iotlb_lock);
 
···
 			break;
 		}
 
-		map = vhost_iotlb_itree_first(iotlb, addr,
-					      addr + len - 1);
+		map = vhost_iotlb_itree_first(iotlb, addr, last);
 		if (!map || map->start > addr) {
 			ret = -EINVAL;
 			break;

drivers/vhost/vsock.c

···
 				  VSOCK_TRANSPORT_F_H2G);
 	if (ret < 0)
 		return ret;
-	return misc_register(&vhost_vsock_misc);
+
+	ret = misc_register(&vhost_vsock_misc);
+	if (ret) {
+		vsock_core_unregister(&vhost_transport.transport);
+		return ret;
+	}
+
+	return 0;
 };
 
 static void __exit vhost_vsock_exit(void)

drivers/video/fbdev/Kconfig

···
 	  chipset found in Ataris.
 
 config FB_OF
-	bool "Open Firmware frame buffer device support"
-	depends on (FB = y) && PPC && (!PPC_PSERIES || PCI)
+	tristate "Open Firmware frame buffer device support"
+	depends on FB && PPC && (!PPC_PSERIES || PCI)
 	depends on !DRM_OFDRM
 	select APERTURE_HELPERS
 	select FB_CFB_FILLRECT

drivers/video/fbdev/aty/atyfb_base.c

···
 		 * which we print to the screen.
 		 */
 		id = *(u8 *)par->lcd_table;
-		strncpy(model, (char *)par->lcd_table+1, 24);
-		model[23] = 0;
+		strscpy(model, (char *)par->lcd_table+1, sizeof(model));
 
 		width = par->lcd_width = *(u16 *)(par->lcd_table+25);
 		height = par->lcd_height = *(u16 *)(par->lcd_table+27);

drivers/video/fbdev/matrox/matroxfb_base.c

···
 	.lowlevel = &matrox_G100
 };
 static struct video_board vbG200eW = {
-	.maxvram = 0x100000,
-	.maxdisplayable = 0x800000,
+	.maxvram = 0x1000000,
+	.maxdisplayable = 0x0800000,
 	.accelID = FB_ACCEL_MATROX_MGAG200,
 	.lowlevel = &matrox_G100
 };

drivers/video/fbdev/omap/omapfb_main.c

···
 	info->fbops = &omapfb_ops;
 	info->flags = FBINFO_FLAG_DEFAULT;
 
-	strncpy(fix->id, MODULE_NAME, sizeof(fix->id));
+	strscpy(fix->id, MODULE_NAME, sizeof(fix->id));
 
 	info->pseudo_palette = fbdev->pseudo_palette;
 
···
 
 	fbdev->ctrl = NULL;
 
-	strncpy(name, conf->lcd.ctrl_name, sizeof(name) - 1);
-	name[sizeof(name) - 1] = '\0';
+	strscpy(name, conf->lcd.ctrl_name, sizeof(name));
 
 	if (strcmp(name, "internal") == 0) {
 		fbdev->ctrl = fbdev->int_ctrl;

drivers/video/fbdev/omap2/omapfb/dss/dsi.c

···
 {
 	struct dsi_data *dsi = dsi_get_dsidrv_data(dsidev);
 	unsigned long flags;
-	struct dsi_irq_stats stats;
+	struct dsi_irq_stats *stats;
+
+	stats = kzalloc(sizeof(*stats), GFP_KERNEL);
+	if (!stats) {
+		seq_printf(s, "out of memory\n");
+		return;
+	}
 
 	spin_lock_irqsave(&dsi->irq_stats_lock, flags);
 
-	stats = dsi->irq_stats;
+	*stats = dsi->irq_stats;
 	memset(&dsi->irq_stats, 0, sizeof(dsi->irq_stats));
 	dsi->irq_stats.last_reset = jiffies;
 
 	spin_unlock_irqrestore(&dsi->irq_stats_lock, flags);
 
 	seq_printf(s, "period %u ms\n",
-			jiffies_to_msecs(jiffies - stats.last_reset));
+			jiffies_to_msecs(jiffies - stats->last_reset));
 
-	seq_printf(s, "irqs %d\n", stats.irq_count);
+	seq_printf(s, "irqs %d\n", stats->irq_count);
 #define PIS(x) \
-	seq_printf(s, "%-20s %10d\n", #x, stats.dsi_irqs[ffs(DSI_IRQ_##x)-1])
+	seq_printf(s, "%-20s %10d\n", #x, stats->dsi_irqs[ffs(DSI_IRQ_##x)-1])
 
 	seq_printf(s, "-- DSI%d interrupts --\n", dsi->module_id + 1);
 	PIS(VC0);
···
 
 #define PIS(x) \
 	seq_printf(s, "%-20s %10d %10d %10d %10d\n", #x, \
-			stats.vc_irqs[0][ffs(DSI_VC_IRQ_##x)-1], \
-			stats.vc_irqs[1][ffs(DSI_VC_IRQ_##x)-1], \
-			stats.vc_irqs[2][ffs(DSI_VC_IRQ_##x)-1], \
-			stats.vc_irqs[3][ffs(DSI_VC_IRQ_##x)-1]);
+			stats->vc_irqs[0][ffs(DSI_VC_IRQ_##x)-1], \
+			stats->vc_irqs[1][ffs(DSI_VC_IRQ_##x)-1], \
+			stats->vc_irqs[2][ffs(DSI_VC_IRQ_##x)-1], \
+			stats->vc_irqs[3][ffs(DSI_VC_IRQ_##x)-1]);
 
 	seq_printf(s, "-- VC interrupts --\n");
 	PIS(CS);
···
 
 #define PIS(x) \
 	seq_printf(s, "%-20s %10d\n", #x, \
-			stats.cio_irqs[ffs(DSI_CIO_IRQ_##x)-1]);
+			stats->cio_irqs[ffs(DSI_CIO_IRQ_##x)-1]);
 
 	seq_printf(s, "-- CIO interrupts --\n");
 	PIS(ERRSYNCESC1);
···
 	PIS(ULPSACTIVENOT_ALL0);
 	PIS(ULPSACTIVENOT_ALL1);
 #undef PIS
+
+	kfree(stats);
 }
 
 static void dsi1_dump_irqs(struct seq_file *s)

drivers/virtio/virtio.c

···
 			   struct device_attribute *attr, char *buf)
 {
 	struct virtio_device *dev = dev_to_virtio(_d);
-	return sprintf(buf, "0x%04x\n", dev->id.device);
+	return sysfs_emit(buf, "0x%04x\n", dev->id.device);
 }
 static DEVICE_ATTR_RO(device);
 
···
 			   struct device_attribute *attr, char *buf)
 {
 	struct virtio_device *dev = dev_to_virtio(_d);
-	return sprintf(buf, "0x%04x\n", dev->id.vendor);
+	return sysfs_emit(buf, "0x%04x\n", dev->id.vendor);
 }
 static DEVICE_ATTR_RO(vendor);
 
···
 			   struct device_attribute *attr, char *buf)
 {
 	struct virtio_device *dev = dev_to_virtio(_d);
-	return sprintf(buf, "0x%08x\n", dev->config->get_status(dev));
+	return sysfs_emit(buf, "0x%08x\n", dev->config->get_status(dev));
 }
 static DEVICE_ATTR_RO(status);
 
···
 			     struct device_attribute *attr, char *buf)
 {
 	struct virtio_device *dev = dev_to_virtio(_d);
-	return sprintf(buf, "virtio:d%08Xv%08X\n",
+	return sysfs_emit(buf, "virtio:d%08Xv%08X\n",
 		       dev->id.device, dev->id.vendor);
 }
 static DEVICE_ATTR_RO(modalias);
···
 	/* We actually represent this as a bitstring, as it could be
 	 * arbitrary length in future. */
 	for (i = 0; i < sizeof(dev->features)*8; i++)
-		len += sprintf(buf+len, "%c",
+		len += sysfs_emit_at(buf, len, "%c",
 			       __virtio_test_bit(dev, i) ? '1' : '0');
-	len += sprintf(buf+len, "\n");
+	len += sysfs_emit_at(buf, len, "\n");
 	return len;
 }
 static DEVICE_ATTR_RO(features);

drivers/virtio/virtio_pci_modern.c

···
 	int err;
 
 	if (index >= vp_modern_get_num_queues(mdev))
-		return ERR_PTR(-ENOENT);
+		return ERR_PTR(-EINVAL);
 
 	/* Check if queue is either not available or already active. */
 	num = vp_modern_get_queue_size(mdev, index);
 	if (!num || vp_modern_get_queue_enable(mdev, index))
 		return ERR_PTR(-ENOENT);
 
-	if (num & (num - 1)) {
+	if (!is_power_of_2(num)) {
 		dev_warn(&vp_dev->pci_dev->dev, "bad queue size %u", num);
 		return ERR_PTR(-EINVAL);
 	}

drivers/virtio/virtio_ring.c

···
 	dma_addr_t dma_addr;
 
 	/* We assume num is a power of 2. */
-	if (num & (num - 1)) {
+	if (!is_power_of_2(num)) {
 		dev_warn(&vdev->dev, "Bad virtqueue length %u\n", num);
 		return -EINVAL;
 	}

fs/btrfs/backref.c

···
 	u64 wanted_disk_byte = ref->wanted_disk_byte;
 	u64 count = 0;
 	u64 data_offset;
+	u8 type;
 
 	if (level != 0) {
 		eb = path->nodes[level];
···
 			continue;
 		}
 		fi = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item);
+		type = btrfs_file_extent_type(eb, fi);
+		if (type == BTRFS_FILE_EXTENT_INLINE)
+			goto next;
 		disk_byte = btrfs_file_extent_disk_bytenr(eb, fi);
 		data_offset = btrfs_file_extent_offset(eb, fi);
 

fs/btrfs/bio.c

···
 				      &map_length, &bioc, mirror_num);
 		if (ret)
 			goto out_counter_dec;
-		BUG_ON(mirror_num != bioc->mirror_num);
+		/*
+		 * This happens when dev-replace is also running, and the
+		 * mirror_num indicates the dev-replace target.
+		 *
+		 * In this case, we don't need to do anything, as the read
+		 * error just means the replace progress hasn't reached our
+		 * read range, and later replace routine would handle it well.
+		 */
+		if (mirror_num != bioc->mirror_num)
+			goto out_counter_dec;
 	}
 
 	sector = bioc->stripes[bioc->mirror_num - 1].physical >> 9;

fs/btrfs/defrag.c

···
 		goto out;
 
 	path = btrfs_alloc_path();
-	if (!path)
-		return -ENOMEM;
+	if (!path) {
+		ret = -ENOMEM;
+		goto out;
+	}
 
 	level = btrfs_header_level(root->node);
 

fs/btrfs/disk-io.c

···
 	}
 
 	if (found_level != check->level) {
+		btrfs_err(fs_info,
+		"level verify failed on logical %llu mirror %u wanted %u found %u",
+			  eb->start, eb->read_mirror, check->level, found_level);
 		ret = -EIO;
 		goto out;
 	}
···
 /*
  * Do various sanity and dependency checks of different features.
  *
+ * @is_rw_mount:	If the mount is read-write.
+ *
  * This is the place for less strict checks (like for subpage or artificial
  * feature dependencies).
  *
···
  * (space cache related) can modify on-disk format like free space tree and
  * screw up certain feature dependencies.
  */
-int btrfs_check_features(struct btrfs_fs_info *fs_info, struct super_block *sb)
+int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount)
 {
 	struct btrfs_super_block *disk_super = fs_info->super_copy;
 	u64 incompat = btrfs_super_incompat_flags(disk_super);
···
 	if (btrfs_super_nodesize(disk_super) > PAGE_SIZE)
 		incompat |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA;
 
-	if (compat_ro_unsupp && !sb_rdonly(sb)) {
+	if (compat_ro_unsupp && is_rw_mount) {
 		btrfs_err(fs_info,
 	"cannot mount read-write because of unknown compat_ro features (0x%llx)",
 		       compat_ro);
···
 		goto fail_alloc;
 	}
 
-	ret = btrfs_check_features(fs_info, sb);
+	ret = btrfs_check_features(fs_info, !sb_rdonly(sb));
 	if (ret < 0) {
 		err = ret;
 		goto fail_alloc;

fs/btrfs/disk-io.h

···
 void __cold close_ctree(struct btrfs_fs_info *fs_info);
 int btrfs_validate_super(struct btrfs_fs_info *fs_info,
 			 struct btrfs_super_block *sb, int mirror_num);
-int btrfs_check_features(struct btrfs_fs_info *fs_info, struct super_block *sb);
+int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount);
 int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors);
 struct btrfs_super_block *btrfs_read_dev_super(struct block_device *bdev);
 struct btrfs_super_block *btrfs_read_dev_one_super(struct block_device *bdev,

fs/btrfs/extent-io-tree.c

···
 	u64 last = 0;
 	int found = 0;
 
-	if (WARN_ON(search_end <= cur_start))
+	if (WARN_ON(search_end < cur_start))
 		return 0;
 
 	spin_lock(&tree->lock);

fs/btrfs/extent-tree.c

···
 		BUG();
 	if (ret && insert_reserved)
 		btrfs_pin_extent(trans, node->bytenr, node->num_bytes, 1);
+	if (ret < 0)
+		btrfs_err(trans->fs_info,
+"failed to run delayed ref for logical %llu num_bytes %llu type %u action %u ref_mod %d: %d",
+			  node->bytenr, node->num_bytes, node->type,
+			  node->action, node->ref_mod, ret);
 	return ret;
 }
 
···
 		if (ret) {
 			unselect_delayed_ref_head(delayed_refs, locked_ref);
 			btrfs_put_delayed_ref(ref);
-			btrfs_debug(fs_info, "run_one_delayed_ref returned %d",
-				    ret);
 			return ret;
 		}
 

fs/btrfs/extent_io.c

···
 	btrfs_bio_end_io_t end_io_func;
 
 	/*
+	 * This is for metadata read, to provide the extra needed verification
+	 * info.  This has to be provided for submit_one_bio(), as
+	 * submit_one_bio() can submit a bio if it ends at stripe boundary.  If
+	 * no such parent_check is provided, the metadata can hit false alert at
+	 * endio time.
+	 */
+	struct btrfs_tree_parent_check *parent_check;
+
+	/*
 	 * Tell writepage not to lock the state bits for this range, it still
 	 * does the unlocking.
 	 */
···
 
 	btrfs_bio(bio)->file_offset = page_offset(bv->bv_page) + bv->bv_offset;
 
-	if (!is_data_inode(&inode->vfs_inode))
+	if (!is_data_inode(&inode->vfs_inode)) {
+		if (btrfs_op(bio) != BTRFS_MAP_WRITE) {
+			/*
+			 * For metadata read, we should have the parent_check,
+			 * and copy it to bbio for metadata verification.
+			 */
+			ASSERT(bio_ctrl->parent_check);
+			memcpy(&btrfs_bio(bio)->parent_check,
+			       bio_ctrl->parent_check,
+			       sizeof(struct btrfs_tree_parent_check));
+		}
 		btrfs_submit_metadata_bio(inode, bio, mirror_num);
-	else if (btrfs_op(bio) == BTRFS_MAP_WRITE)
+	} else if (btrfs_op(bio) == BTRFS_MAP_WRITE) {
 		btrfs_submit_data_write_bio(inode, bio, mirror_num);
-	else
+	} else {
 		btrfs_submit_data_read_bio(inode, bio, mirror_num,
 					   bio_ctrl->compress_type);
+	}
 
 	/* The bio is owned by the end_io handler now */
 	bio_ctrl->bio = NULL;
···
 	struct extent_state *cached_state = NULL;
 	struct btrfs_bio_ctrl bio_ctrl = {
 		.mirror_num = mirror_num,
+		.parent_check = check,
 	};
 	int ret = 0;
 
···
 		 */
 		atomic_dec(&eb->io_pages);
 	}
-	memcpy(&btrfs_bio(bio_ctrl.bio)->parent_check, check, sizeof(*check));
 	submit_one_bio(&bio_ctrl);
 	if (ret || wait != WAIT_COMPLETE) {
 		free_extent_state(cached_state);
···
 	unsigned long num_reads = 0;
 	struct btrfs_bio_ctrl bio_ctrl = {
 		.mirror_num = mirror_num,
+		.parent_check = check,
 	};
 
 	if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))
···
 		}
 	}
 
-	memcpy(&btrfs_bio(bio_ctrl.bio)->parent_check, check, sizeof(*check));
 	submit_one_bio(&bio_ctrl);
 
 	if (ret || wait != WAIT_COMPLETE)

fs/btrfs/file.c

···
 	bool search_io_tree = true;
 	bool ret = false;
 
-	while (cur_offset < end) {
+	while (cur_offset <= end) {
 		u64 delalloc_start;
 		u64 delalloc_end;
 		bool delalloc;

fs/btrfs/inode.c

···
 		 * Other members are not utilized for inline extents.
 		 */
 		ASSERT(em->block_start == EXTENT_MAP_INLINE);
-		ASSERT(em->len = fs_info->sectorsize);
+		ASSERT(em->len == fs_info->sectorsize);
 
 		ret = read_inline_extent(inode, path, page);
 		if (ret < 0)
···
 
 	if (flags & RENAME_WHITEOUT) {
 		whiteout_args.inode = new_whiteout_inode(mnt_userns, old_dir);
-		if (!whiteout_args.inode)
-			return -ENOMEM;
+		if (!whiteout_args.inode) {
+			ret = -ENOMEM;
+			goto out_fscrypt_names;
+		}
 		ret = btrfs_new_inode_prepare(&whiteout_args, &trans_num_items);
 		if (ret)
 			goto out_whiteout_inode;

fs/btrfs/qgroup.c

···
 			 * current root. It's safe inside commit_transaction().
 			 */
 			ctx.trans = trans;
+			ctx.time_seq = BTRFS_SEQ_LAST;
 			ret = btrfs_find_all_roots(&ctx, false);
 			if (ret < 0)
 				goto cleanup;

fs/btrfs/raid56.c

···
 	void **pointers = NULL;
 	void **unmap_array = NULL;
 	int sector_nr;
-	int ret;
+	int ret = 0;
 
 	/*
 	 * @pointers array stores the pointer for each sector.

fs/btrfs/super.c

···
 	if (ret)
 		goto restore;
 
-	ret = btrfs_check_features(fs_info, sb);
+	ret = btrfs_check_features(fs_info, !(*flags & SB_RDONLY));
 	if (ret < 0)
 		goto restore;
 
···
 static void __exit exit_btrfs_fs(void)
 {
 	btrfs_exit_btrfs_fs();
+	btrfs_cleanup_fs_uuids();
 }
 
 static int __init init_btrfs_fs(void)

fs/btrfs/tree-log.c

···
 		 * not fail, but if it does, it's not serious, just bail out and
 		 * mark the log for a full commit.
 		 */
-		if (WARN_ON_ONCE(ret < 0))
+		if (WARN_ON_ONCE(ret < 0)) {
+			fscrypt_free_filename(&fname);
 			goto out;
+		}
+
 		log_pinned = true;
 
 		path = btrfs_alloc_path();

fs/ceph/caps.c

···
 
 	while (true) {
 		flags &= CEPH_FILE_MODE_MASK;
-		if (atomic_read(&fi->num_locks))
+		if (vfs_inode_has_locks(inode))
 			flags |= CHECK_FILELOCK;
 		_got = 0;
 		ret = try_get_cap_refs(inode, need, want, endoff,

fs/ceph/locks.c

···
 
 static void ceph_fl_copy_lock(struct file_lock *dst, struct file_lock *src)
 {
-	struct ceph_file_info *fi = dst->fl_file->private_data;
 	struct inode *inode = file_inode(dst->fl_file);
 	atomic_inc(&ceph_inode(inode)->i_filelock_ref);
-	atomic_inc(&fi->num_locks);
+	dst->fl_u.ceph.inode = igrab(inode);
 }
 
+/*
+ * Do not use the 'fl->fl_file' in release function, which
+ * is possibly already released by another thread.
+ */
 static void ceph_fl_release_lock(struct file_lock *fl)
 {
-	struct ceph_file_info *fi = fl->fl_file->private_data;
-	struct inode *inode = file_inode(fl->fl_file);
-	struct ceph_inode_info *ci = ceph_inode(inode);
-	atomic_dec(&fi->num_locks);
+	struct inode *inode = fl->fl_u.ceph.inode;
+	struct ceph_inode_info *ci;
+
+	/*
+	 * If inode is NULL it should be a request file_lock,
+	 * nothing we can do.
+	 */
+	if (!inode)
+		return;
+
+	ci = ceph_inode(inode);
 	if (atomic_dec_and_test(&ci->i_filelock_ref)) {
 		/* clear error when all locks are released */
 		spin_lock(&ci->i_ceph_lock);
 		ci->i_ceph_flags &= ~CEPH_I_ERROR_FILELOCK;
 		spin_unlock(&ci->i_ceph_lock);
 	}
+	fl->fl_u.ceph.inode = NULL;
+	iput(inode);
 }
 
 static const struct file_lock_operations ceph_fl_lock_ops = {

fs/ceph/super.h

···
 	struct list_head rw_contexts;
 
 	u32 filp_gen;
-	atomic_t num_locks;
 };
 
 struct ceph_dir_file_info {

fs/cifs/dfs.c

···
 	return rc;
 }
 
-static int target_share_matches_server(struct TCP_Server_Info *server, const char *tcp_host,
-				       size_t tcp_host_len, char *share, bool *target_match)
+static int target_share_matches_server(struct TCP_Server_Info *server, char *share,
+				       bool *target_match)
 {
 	int rc = 0;
 	const char *dfs_host;
···
 	extract_unc_hostname(share, &dfs_host, &dfs_host_len);
 
 	/* Check if hostnames or addresses match */
-	if (dfs_host_len != tcp_host_len || strncasecmp(dfs_host, tcp_host, dfs_host_len) != 0) {
-		cifs_dbg(FYI, "%s: %.*s doesn't match %.*s\n", __func__, (int)dfs_host_len,
-			 dfs_host, (int)tcp_host_len, tcp_host);
+	cifs_server_lock(server);
+	if (dfs_host_len != strlen(server->hostname) ||
+	    strncasecmp(dfs_host, server->hostname, dfs_host_len)) {
+		cifs_dbg(FYI, "%s: %.*s doesn't match %s\n", __func__,
+			 (int)dfs_host_len, dfs_host, server->hostname);
 		rc = match_target_ip(server, dfs_host, dfs_host_len, target_match);
 		if (rc)
 			cifs_dbg(VFS, "%s: failed to match target ip: %d\n", __func__, rc);
 	}
+	cifs_server_unlock(server);
 	return rc;
 }
 
···
 	struct cifs_ses *root_ses = CIFS_DFS_ROOT_SES(tcon->ses);
 	struct cifs_tcon *ipc = root_ses->tcon_ipc;
 	char *share = NULL, *prefix = NULL;
-	const char *tcp_host;
-	size_t tcp_host_len;
 	struct dfs_cache_tgt_iterator *tit;
 	bool target_match;
-
-	extract_unc_hostname(server->hostname, &tcp_host, &tcp_host_len);
 
 	tit = dfs_cache_get_tgt_iterator(tl);
 	if (!tit) {
···
 			break;
 		}
 
-		rc = target_share_matches_server(server, tcp_host, tcp_host_len, share,
-						 &target_match);
+		rc = target_share_matches_server(server, share, &target_match);
 		if (rc)
 			break;
 		if (!target_match) {
···
 		if (ipc->need_reconnect) {
 			scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", server->hostname);
 			rc = ops->tree_connect(xid, ipc->ses, tree, ipc, cifs_sb->local_nls);
-			if (rc)
-				break;
+			cifs_dbg(FYI, "%s: reconnect ipc: %d\n", __func__, rc);
 		}
 
 		scnprintf(tree, MAX_TREE_SIZE, "\\%s", share);
···
 	}
 
 	if (tcon->ipc) {
+		cifs_server_lock(server);
 		scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", server->hostname);
+		cifs_server_unlock(server);
 		rc = ops->tree_connect(xid, tcon->ses, tree, tcon, nlsc);
 		goto out;
 	}

fs/cifs/misc.c

···
 	if (rc < 0)
 		return rc;
 
+	spin_lock(&server->srv_lock);
 	*result = cifs_match_ipaddr((struct sockaddr *)&server->dstaddr, (struct sockaddr *)&ss);
+	spin_unlock(&server->srv_lock);
 	cifs_dbg(FYI, "%s: ip addresses match: %u\n", __func__, *result);
 	return 0;
 }

fs/cifs/sess.c

···
 			continue;
 		}
 		kref_get(&iface->refcount);
+		break;
 	}
 
-	if (!list_entry_is_head(iface, &ses->iface_list, iface_head)) {
+	if (list_entry_is_head(iface, &ses->iface_list, iface_head)) {
 		rc = 1;
 		iface = NULL;
 		cifs_dbg(FYI, "unable to find a suitable iface\n");

fs/cifs/smb2ops.c

···
 	p = buf;
 
 	spin_lock(&ses->iface_lock);
-	ses->iface_count = 0;
 	/*
 	 * Go through iface_list and do kref_put to remove
 	 * any unused ifaces. ifaces in use will be removed
···
 				 iface_head) {
 		iface->is_active = 0;
 		kref_put(&iface->refcount, release_iface);
+		ses->iface_count--;
 	}
 	spin_unlock(&ses->iface_lock);
 
···
 				/* just get a ref so that it doesn't get picked/freed */
 				iface->is_active = 1;
 				kref_get(&iface->refcount);
+				ses->iface_count++;
 				spin_unlock(&ses->iface_lock);
 				goto next_iface;
 			} else if (ret < 0) {
···
 
 		/* copy pages form the old */
 		for (j = 0; j < npages; j++) {
-			char *dst, *src;
 			unsigned int offset, len;
 
 			rqst_page_get_length(new, j, &len, &offset);
 
-			dst = kmap_local_page(new->rq_pages[j]) + offset;
-			src = kmap_local_page(old->rq_pages[j]) + offset;
-
-			memcpy(dst, src, len);
-			kunmap(new->rq_pages[j]);
-			kunmap(old->rq_pages[j]);
+			memcpy_page(new->rq_pages[j], offset,
+				    old->rq_pages[j], offset, len);
 		}
 	}
 

fs/cifs/smb2pdu.c

···
 assemble_neg_contexts(struct smb2_negotiate_req *req,
 		      struct TCP_Server_Info *server, unsigned int *total_len)
 {
-	char *pneg_ctxt;
-	char *hostname = NULL;
 	unsigned int ctxt_len, neg_context_count;
+	struct TCP_Server_Info *pserver;
+	char *pneg_ctxt;
+	char *hostname;
 
 	if (*total_len > 200) {
 		/* In case length corrupted don't want to overrun smb buffer */
···
 	 * secondary channels don't have the hostname field populated
 	 * use the hostname field in the primary channel instead
 	 */
-	hostname = CIFS_SERVER_IS_CHAN(server) ?
-		server->primary_server->hostname : server->hostname;
+	pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server;
+	cifs_server_lock(pserver);
+	hostname = pserver->hostname;
 	if (hostname && (hostname[0] != 0)) {
 		ctxt_len = build_netname_ctxt((struct smb2_netname_neg_context *)pneg_ctxt,
 					      hostname);
···
 		neg_context_count = 3;
 	} else
 		neg_context_count = 2;
+	cifs_server_unlock(pserver);
 
 	build_posix_ctxt((struct smb2_posix_neg_context *)pneg_ctxt);
 	*total_len += sizeof(struct smb2_posix_neg_context);

fs/f2fs/data.c

···
 	sector_t last_block_in_file;
 	const unsigned blocksize = blks_to_bytes(inode, 1);
 	struct decompress_io_ctx *dic = NULL;
-	struct extent_info ei = {0, };
+	struct extent_info ei = {};
 	bool from_dnode = true;
 	int i;
 	int ret = 0;

fs/f2fs/extent_cache.c

···
 	struct extent_node *en;
 	bool ret = false;
 
-	f2fs_bug_on(sbi, !et);
+	if (!et)
+		return false;
 
 	trace_f2fs_lookup_extent_tree_start(inode, pgofs, type);
 
···
 }
 
 /* This returns a new age and allocated blocks in ei */
-static int __get_new_block_age(struct inode *inode, struct extent_info *ei)
+static int __get_new_block_age(struct inode *inode, struct extent_info *ei,
+						block_t blkaddr)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	loff_t f_size = i_size_read(inode);
 	unsigned long long cur_blocks =
 				atomic64_read(&sbi->allocated_data_blocks);
+	struct extent_info tei = *ei;	/* only fofs and len are valid */
 
 	/*
 	 * When I/O is not aligned to a PAGE_SIZE, update will happen to the last
···
 	 * block here.
 	 */
 	if ((f_size >> PAGE_SHIFT) == ei->fofs && f_size & (PAGE_SIZE - 1) &&
-			ei->blk == NEW_ADDR)
+			blkaddr == NEW_ADDR)
 		return -EINVAL;
 
-	if (__lookup_extent_tree(inode, ei->fofs, ei, EX_BLOCK_AGE)) {
+	if (__lookup_extent_tree(inode, ei->fofs, &tei, EX_BLOCK_AGE)) {
 		unsigned long long cur_age;
 
-		if (cur_blocks >= ei->last_blocks)
-			cur_age = cur_blocks - ei->last_blocks;
+		if (cur_blocks >= tei.last_blocks)
+			cur_age = cur_blocks - tei.last_blocks;
 		else
 			/* allocated_data_blocks overflow */
-			cur_age = ULLONG_MAX - ei->last_blocks + cur_blocks;
+			cur_age = ULLONG_MAX - tei.last_blocks + cur_blocks;
 
-		if (ei->age)
-			ei->age = __calculate_block_age(cur_age, ei->age);
+		if (tei.age)
+			ei->age = __calculate_block_age(cur_age, tei.age);
 		else
 			ei->age = cur_age;
 		ei->last_blocks = cur_blocks;
···
 		return 0;
 	}
 
-	f2fs_bug_on(sbi, ei->blk == NULL_ADDR);
+	f2fs_bug_on(sbi, blkaddr == NULL_ADDR);
 
 	/* the data block was allocated for the first time */
-	if (ei->blk == NEW_ADDR)
+	if (blkaddr == NEW_ADDR)
 		goto out;
 
-	if (__is_valid_data_blkaddr(ei->blk) &&
-			!f2fs_is_valid_blkaddr(sbi, ei->blk, DATA_GENERIC_ENHANCE)) {
+	if (__is_valid_data_blkaddr(blkaddr) &&
+	    !f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE)) {
 		f2fs_bug_on(sbi, 1);
 		return -EINVAL;
 	}
···
 
 static void __update_extent_cache(struct dnode_of_data *dn, enum extent_type type)
 {
-	struct extent_info ei;
+	struct extent_info ei = {};
 
 	if (!__may_extent_tree(dn->inode, type))
 		return;
···
 		else
 			ei.blk = dn->data_blkaddr;
 	} else if (type == EX_BLOCK_AGE) {
-		ei.blk = dn->data_blkaddr;
-		if (__get_new_block_age(dn->inode, &ei))
+		if (__get_new_block_age(dn->inode, &ei, dn->data_blkaddr))
 			return;
 	}
 	__update_extent_tree_range(dn->inode, &ei, type);

fs/f2fs/file.c

···
 	struct f2fs_map_blocks map = { .m_next_extent = NULL,
 					.m_seg_type = NO_CHECK_TYPE,
 					.m_may_create = false };
-	struct extent_info ei = {0, };
+	struct extent_info ei = {};
 	pgoff_t pg_start, pg_end, next_pgofs;
 	unsigned int blk_per_seg = sbi->blocks_per_seg;
 	unsigned int total = 0, sec_num;

fs/f2fs/segment.c

···
 	if (IS_ERR(fcc->f2fs_issue_flush)) {
 		int err = PTR_ERR(fcc->f2fs_issue_flush);
 
-		kfree(fcc);
-		SM_I(sbi)->fcc_info = NULL;
+		fcc->f2fs_issue_flush = NULL;
 		return err;
 	}
 
···
 static int __get_age_segment_type(struct inode *inode, pgoff_t pgofs)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	struct extent_info ei;
+	struct extent_info ei = {};
 
 	if (f2fs_lookup_age_extent_cache(inode, pgofs, &ei)) {
 		if (!ei.age)
···
 
 	init_f2fs_rwsem(&sm_info->curseg_lock);
 
-	if (!f2fs_readonly(sbi->sb)) {
-		err = f2fs_create_flush_cmd_control(sbi);
-		if (err)
-			return err;
-	}
+	err = f2fs_create_flush_cmd_control(sbi);
+	if (err)
+		return err;
 
 	err = create_discard_cmd_control(sbi);
 	if (err)

fs/hfs/inode.c

···
 		/* panic? */
 		return -EIO;
 
+	res = -EIO;
 	if (HFS_I(main_inode)->cat_key.CName.len > HFS_NAMELEN)
-		return -EIO;
+		goto out;
 	fd.search_key->cat = HFS_I(main_inode)->cat_key;
 	if (hfs_brec_find(&fd))
-		/* panic? */
 		goto out;
 
 	if (S_ISDIR(main_inode->i_mode)) {
-		WARN_ON(fd.entrylength < sizeof(struct hfs_cat_dir));
+		if (fd.entrylength < sizeof(struct hfs_cat_dir))
+			goto out;
 		hfs_bnode_read(fd.bnode, &rec, fd.entryoffset,
 			   sizeof(struct hfs_cat_dir));
 		if (rec.type != HFS_CDR_DIR ||
···
 		hfs_bnode_write(fd.bnode, &rec, fd.entryoffset,
 			    sizeof(struct hfs_cat_dir));
 	} else if (HFS_IS_RSRC(inode)) {
+		if (fd.entrylength < sizeof(struct hfs_cat_file))
+			goto out;
 		hfs_bnode_read(fd.bnode, &rec, fd.entryoffset,
 			       sizeof(struct hfs_cat_file));
 		hfs_inode_write_fork(inode, rec.file.RExtRec,
···
 		hfs_bnode_write(fd.bnode, &rec, fd.entryoffset,
 				sizeof(struct hfs_cat_file));
 	} else {
-		WARN_ON(fd.entrylength < sizeof(struct hfs_cat_file));
+		if (fd.entrylength < sizeof(struct hfs_cat_file))
+			goto out;
 		hfs_bnode_read(fd.bnode, &rec, fd.entryoffset,
 			   sizeof(struct hfs_cat_file));
 		if (rec.type != HFS_CDR_FIL ||
···
 		hfs_bnode_write(fd.bnode, &rec, fd.entryoffset,
 			    sizeof(struct hfs_cat_file));
 	}
+	res = 0;
 out:
 	hfs_find_exit(&fd);
-	return 0;
+	return res;
 }
 
 static struct dentry *hfs_file_lookup(struct inode *dir, struct dentry *dentry,

fs/nfs/dir.c

···
 				 const struct cred *cred)
 {
 	const struct task_struct *parent;
+	const struct cred *pcred;
 	u64 ret;
 
 	rcu_read_lock();
 	for (;;) {
 		parent = rcu_dereference(task->real_parent);
-		if (parent == task || cred_fscmp(parent->cred, cred) != 0)
+		pcred = rcu_dereference(parent->cred);
+		if (parent == task || cred_fscmp(pcred, cred) != 0)
 			break;
 		task = parent;
 	}
···
 	 * but do it without locking.
 	 */
 	struct nfs_inode *nfsi = NFS_I(inode);
+	u64 login_time = nfs_access_login_time(current, cred);
 	struct nfs_access_entry *cache;
 	int err = -ECHILD;
 	struct list_head *lh;
···
 	    access_cmp(cred, cache) != 0)
 		cache = NULL;
 	if (cache == NULL)
+		goto out;
+	if ((s64)(login_time - cache->timestamp) > 0)
 		goto out;
 	if (nfs_check_cache_invalid(inode, NFS_INO_INVALID_ACCESS))
 		goto out;

fs/nfs/filelayout/filelayout.c

···
 	return &fl->generic_hdr;
 }
 
+static bool
+filelayout_lseg_is_striped(const struct nfs4_filelayout_segment *flseg)
+{
+	return flseg->num_fh > 1;
+}
+
 /*
  * filelayout_pg_test(). Called by nfs_can_coalesce_requests()
  *
···
 	size = pnfs_generic_pg_test(pgio, prev, req);
 	if (!size)
 		return 0;
+	else if (!filelayout_lseg_is_striped(FILELAYOUT_LSEG(pgio->pg_lseg)))
+		return size;
 
 	/* see if req and prev are in the same stripe */
 	if (prev) {

fs/nfsd/nfs4xdr.c

···
 	case nfserr_noent:
 		xdr_truncate_encode(xdr, start_offset);
 		goto skip_entry;
+	case nfserr_jukebox:
+		/*
+		 * The pseudoroot should only display dentries that lead to
+		 * exports. If we get EJUKEBOX here, then we can't tell whether
+		 * this entry should be included. Just fail the whole READDIR
+		 * with NFS4ERR_DELAY in that case, and hope that the situation
+		 * will resolve itself by the client's next attempt.
+		 */
+		if (cd->rd_fhp->fh_export->ex_flags & NFSEXP_V4ROOT)
+			goto fail;
+		fallthrough;
 	default:
 		/*
 		 * If the client requested the RDATTR_ERROR attribute,

fs/nfsd/nfssvc.c

···
 {
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
-	nfsd_file_cache_shutdown_net(net);
 	nfs4_state_shutdown_net(net);
+	nfsd_file_cache_shutdown_net(net);
 	if (nn->lockd_up) {
 		lockd_down(net);
 		nn->lockd_up = false;

fs/ntfs3/file.c

···
 
 	new_valid = ntfs_up_block(sb, min_t(u64, ni->i_valid, new_size));
 
-	ni_lock(ni);
-
 	truncate_setsize(inode, new_size);
+
+	ni_lock(ni);
 
 	down_write(&ni->file.run_lock);
 	err = attr_set_size(ni, ATTR_DATA, NULL, 0, &ni->file.run, new_size,

fs/udf/inode.c

···
 	 */
 	if (new_elen <= (last_ext->extLength & UDF_EXTENT_LENGTH_MASK))
 		return;
-	added_bytes = (last_ext->extLength & UDF_EXTENT_LENGTH_MASK) - new_elen;
+	added_bytes = new_elen - (last_ext->extLength & UDF_EXTENT_LENGTH_MASK);
 	last_ext->extLength += added_bytes;
 	UDF_I(inode)->i_lenExtents += added_bytes;
 
···
 	struct kernel_lb_addr eloc, tmpeloc;
 	int c = 1;
 	loff_t lbcount = 0, b_off = 0;
-	udf_pblk_t newblocknum, newblock;
+	udf_pblk_t newblocknum, newblock = 0;
 	sector_t offset = 0;
 	int8_t etype;
 	struct udf_inode_info *iinfo = UDF_I(inode);
···
 		ret = udf_do_extend_file(inode, &prev_epos, laarr, hole_len);
 		if (ret < 0) {
 			*err = ret;
-			newblock = 0;
 			goto out_free;
 		}
 		c = 0;
···
 				goal, err);
 		if (!newblocknum) {
 			*err = -ENOSPC;
-			newblock = 0;
 			goto out_free;
 		}
 		if (isBeyondEOF)

include/acpi/video.h

···
 };
 
 #if IS_ENABLED(CONFIG_ACPI_VIDEO)
+extern void acpi_video_report_nolcd(void);
 extern int acpi_video_register(void);
 extern void acpi_video_unregister(void);
 extern void acpi_video_register_backlight(void);
···
 				 struct acpi_video_device_brightness **dev_br,
 				 int *pmax_level);
 #else
+static inline void acpi_video_report_nolcd(void) { return; };
 static inline int acpi_video_register(void) { return -ENODEV; }
 static inline void acpi_video_unregister(void) { return; }
 static inline void acpi_video_register_backlight(void) { return; }

include/asm-generic/vmlinux.lds.h

···
 #define PRINTK_INDEX
 #endif
 
+/*
+ * Discard .note.GNU-stack, which is emitted as PROGBITS by the compiler.
+ * Otherwise, the type of .notes section would become PROGBITS instead of NOTES.
+ */
 #define NOTES								\
+	/DISCARD/ : { *(.note.GNU-stack) }				\
 	.notes : AT(ADDR(.notes) - LOAD_OFFSET) {			\
 		BOUNDED_SECTION_BY(.note.*, _notes)			\
 	} NOTES_HEADERS							\

include/drm/drm_plane_helper.h

···
 
 #include <linux/types.h>
 
+struct drm_atomic_state;
 struct drm_crtc;
 struct drm_framebuffer;
 struct drm_modeset_acquire_ctx;

include/linux/bio.h

···
 extern void bio_set_pages_dirty(struct bio *bio);
 extern void bio_check_pages_dirty(struct bio *bio);
 
+extern void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter,
+			       struct bio *src, struct bvec_iter *src_iter);
 extern void bio_copy_data(struct bio *dst, struct bio *src);
 extern void bio_free_pages(struct bio *bio);
 void guard_bio_eod(struct bio *bio);

include/linux/blkdev.h

···
 	void (*swap_slot_free_notify) (struct block_device *, unsigned long);
 	int (*report_zones)(struct gendisk *, sector_t sector,
 			unsigned int nr_zones, report_zones_cb cb, void *data);
+	char *(*devnode)(struct gendisk *disk, umode_t *mode);
 	/* returns the length of the identifier or a negative errno: */
 	int (*get_unique_id)(struct gendisk *disk, u8 id[16],
 			enum blk_unique_id id_type);

include/linux/dsa/tag_qca.h

···
 					QCA_HDR_MGMT_COMMAND_LEN + \
 					QCA_HDR_MGMT_DATA1_LEN)
 
-#define QCA_HDR_MGMT_DATA2_LEN		12 /* Other 12 byte for the mdio data */
-#define QCA_HDR_MGMT_PADDING_LEN	34 /* Padding to reach the min Ethernet packet */
+#define QCA_HDR_MGMT_DATA2_LEN		28 /* Other 28 byte for the mdio data */
+#define QCA_HDR_MGMT_PADDING_LEN	18 /* Padding to reach the min Ethernet packet */
 
 #define QCA_HDR_MGMT_PKT_LEN		(QCA_HDR_MGMT_HEADER_LEN + \
 					QCA_HDR_LEN + \

include/linux/fs.h

···
 			int state;		/* state of grant or error if -ve */
 			unsigned int	debug_id;
 		} afs;
+		struct {
+			struct inode *inode;
+		} ceph;
 	} fl_u;
 } __randomize_layout;
 

include/linux/io_uring_types.h

···
 	struct {
 		spinlock_t		completion_lock;
 
+		bool			poll_multi_queue;
+
 		/*
 		 * ->iopoll_list is protected by the ctx->uring_lock for
 		 * io_uring instances that don't use IORING_SETUP_SQPOLL.
···
 		 */
 		struct io_wq_work_list	iopoll_list;
 		struct io_hash_table	cancel_table;
-		bool			poll_multi_queue;
 
 		struct llist_head	work_llist;
 

include/linux/mlx5/device.h

···
 };
 
 enum {
+	MLX5_VPORT_CVLAN_INSERT_WHEN_NO_CVLAN  = 0x1,
+	MLX5_VPORT_CVLAN_INSERT_ALWAYS         = 0x3,
+};
+
+enum {
 	MLX5_L3_PROT_TYPE_IPV4		= 0,
 	MLX5_L3_PROT_TYPE_IPV6		= 1,
 };

include/linux/mlx5/mlx5_ifc.h

···
 	u8         vport_svlan_insert[0x1];
 	u8         vport_cvlan_insert_if_not_exist[0x1];
 	u8         vport_cvlan_insert_overwrite[0x1];
-	u8         reserved_at_5[0x2];
+	u8         reserved_at_5[0x1];
+	u8         vport_cvlan_insert_always[0x1];
 	u8         esw_shared_ingress_acl[0x1];
 	u8         esw_uplink_ingress_acl[0x1];
 	u8         root_ft_on_other_esw[0x1];

include/linux/netfilter/ipset/ip_set.h

···
 };
 
 /* Max range where every element is added/deleted in one step */
-#define IPSET_MAX_RANGE		(1<<20)
+#define IPSET_MAX_RANGE		(1<<14)
 
 /* The max revision number supported by any set type + 1 */
 #define IPSET_REVISION_MAX	9

include/linux/nvme.h

···
 #ifndef _LINUX_NVME_H
 #define _LINUX_NVME_H
 
+#include <linux/bits.h>
 #include <linux/types.h>
 #include <linux/uuid.h>
 
···
 	NVME_CMD_EFFECTS_NCC		= 1 << 2,
 	NVME_CMD_EFFECTS_NIC		= 1 << 3,
 	NVME_CMD_EFFECTS_CCC		= 1 << 4,
-	NVME_CMD_EFFECTS_CSE_MASK	= 3 << 16,
+	NVME_CMD_EFFECTS_CSE_MASK	= GENMASK(18, 16),
 	NVME_CMD_EFFECTS_UUID_SEL	= 1 << 19,
+	NVME_CMD_EFFECTS_SCOPE_MASK	= GENMASK(31, 20),
 };
 
 struct nvme_effects_log {

include/linux/phy.h

···
 	 * whether to advertise lower-speed modes for that interface. It is
 	 * assumed that if a rate matching mode is supported on an interface,
 	 * then that interface's rate can be adapted to all slower link speeds
-	 * supported by the phy. If iface is %PHY_INTERFACE_MODE_NA, and the phy
-	 * supports any kind of rate matching for any interface, then it must
-	 * return that rate matching mode (preferring %RATE_MATCH_PAUSE to
-	 * %RATE_MATCH_CRS). If the interface is not supported, this should
+	 * supported by the phy. If the interface is not supported, this should
 	 * return %RATE_MATCH_NONE.
 	 */
 	int (*get_rate_matching)(struct phy_device *phydev,

include/linux/pktcdvd.h

···
+/*
+ * Copyright (C) 2000 Jens Axboe <[e-mail]>
+ * Copyright (C) 2001-2004 Peter Osterlund <[e-mail]>
+ *
+ * May be copied or modified under the terms of the GNU General Public
+ * License.  See linux/COPYING for more information.
+ *
+ * Packet writing layer for ATAPI and SCSI CD-R, CD-RW, DVD-R, and
+ * DVD-RW devices.
+ *
+ */
+#ifndef __PKTCDVD_H
+#define __PKTCDVD_H
+
+#include <linux/blkdev.h>
+#include <linux/completion.h>
+#include <linux/cdrom.h>
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
+#include <linux/mempool.h>
+#include <uapi/linux/pktcdvd.h>
+
+/* default bio write queue congestion marks */
+#define PKT_WRITE_CONGESTION_ON    10000
+#define PKT_WRITE_CONGESTION_OFF   9000
+
+
+struct packet_settings
+{
+	__u32			size;		/* packet size in (512 byte) sectors */
+	__u8			fp;		/* fixed packets */
+	__u8			link_loss;	/* the rest is specified
+						 * as per Mt Fuji */
+	__u8			write_type;
+	__u8			track_mode;
+	__u8			block_mode;
+};
+
+/*
+ * Very crude stats for now
+ */
+struct packet_stats
+{
+	unsigned long		pkt_started;
+	unsigned long		pkt_ended;
+	unsigned long		secs_w;
+	unsigned long		secs_rg;
+	unsigned long		secs_r;
+};
+
+struct packet_cdrw
+{
+	struct list_head	pkt_free_list;
+	struct list_head	pkt_active_list;
+	spinlock_t		active_list_lock; /* Serialize access to pkt_active_list */
+	struct task_struct	*thread;
+	atomic_t		pending_bios;
+};
+
+/*
+ * Switch to high speed reading after reading this many kilobytes
+ * with no interspersed writes.
+ */
+#define HI_SPEED_SWITCH 512
+
+struct packet_iosched
+{
+	atomic_t		attention;	/* Set to non-zero when queue processing is needed */
+	int			writing;	/* Non-zero when writing, zero when reading */
+	spinlock_t		lock;		/* Protecting read/write queue manipulations */
+	struct bio_list		read_queue;
+	struct bio_list		write_queue;
+	sector_t		last_write;	/* The sector where the last write ended */
+	int			successive_reads;
+};
+
+/*
+ * 32 buffers of 2048 bytes
+ */
+#if (PAGE_SIZE % CD_FRAMESIZE) != 0
+#error "PAGE_SIZE must be a multiple of CD_FRAMESIZE"
+#endif
+#define PACKET_MAX_SIZE		128
+#define FRAMES_PER_PAGE		(PAGE_SIZE / CD_FRAMESIZE)
+#define PACKET_MAX_SECTORS	(PACKET_MAX_SIZE * CD_FRAMESIZE >> 9)
+
+enum packet_data_state {
+	PACKET_IDLE_STATE,			/* Not used at the moment */
+	PACKET_WAITING_STATE,			/* Waiting for more bios to arrive, so */
+						/* we don't have to do as much */
+						/* data gathering */
+	PACKET_READ_WAIT_STATE,			/* Waiting for reads to fill in holes */
+	PACKET_WRITE_WAIT_STATE,		/* Waiting for the write to complete */
+	PACKET_RECOVERY_STATE,			/* Recover after read/write errors */
+	PACKET_FINISHED_STATE,			/* After write has finished */
+
+	PACKET_NUM_STATES			/* Number of possible states */
+};
+
+/*
+ * Information needed for writing a single packet
+ */
+struct pktcdvd_device;
+
+struct packet_data
+{
+	struct list_head	list;
+
+	spinlock_t		lock;		/* Lock protecting state transitions and */
+						/* orig_bios list */
+
+	struct bio_list		orig_bios;	/* Original bios passed to pkt_make_request */
+						/* that will be handled by this packet */
+	int			write_size;	/* Total size of all bios in the orig_bios */
+						/* list, measured in number of frames */
+
+	struct bio		*w_bio;		/* The bio we will send to the real CD */
+						/* device once we have all data for the */
+						/* packet we are going to write */
+	sector_t		sector;		/* First sector in this packet */
+	int			frames;		/* Number of frames in this packet */
+
+	enum packet_data_state	state;		/* Current state */
+	atomic_t		run_sm;		/* Incremented whenever the state */
+						/* machine needs to be run */
+	long			sleep_time;	/* Set this to non-zero to make the state */
+						/* machine run after this many jiffies. */
+
+	atomic_t		io_wait;	/* Number of pending IO operations */
+	atomic_t		io_errors;	/* Number of read/write errors during IO */
+
+	struct bio		*r_bios[PACKET_MAX_SIZE]; /* bios to use during data gathering */
+	struct page		*pages[PACKET_MAX_SIZE / FRAMES_PER_PAGE];
+
+	int			cache_valid;	/* If non-zero, the data for the zone defined */
+						/* by the sector variable is completely cached */
+						/* in the pages[] vector. */
+
+	int			id;		/* ID number for debugging */
+	struct pktcdvd_device	*pd;
+};
+
+struct pkt_rb_node {
+	struct rb_node		rb_node;
+	struct bio		*bio;
+};
+
+struct packet_stacked_data
+{
+	struct bio		*bio;		/* Original read request bio */
+	struct pktcdvd_device	*pd;
+};
+#define PSD_POOL_SIZE		64
+
+struct pktcdvd_device
+{
+	struct block_device	*bdev;		/* dev attached */
+	dev_t			pkt_dev;	/* our dev */
+	char			name[20];
+	struct packet_settings	settings;
+	struct packet_stats	stats;
+	int			refcnt;		/* Open count */
+	int			write_speed;	/* current write speed, kB/s */
+	int			read_speed;	/* current read speed, kB/s */
+	unsigned long		offset;		/* start offset */
+	__u8			mode_offset;	/* 0 / 8 */
+	__u8			type;
+	unsigned long		flags;
+	__u16			mmc3_profile;
+	__u32			nwa;		/* next writable address */
+	__u32			lra;		/* last recorded address */
+	struct packet_cdrw	cdrw;
+	wait_queue_head_t	wqueue;
+
+	spinlock_t		lock;		/* Serialize access to bio_queue */
+	struct rb_root		bio_queue;	/* Work queue of bios we need to handle */
+	int			bio_queue_size;	/* Number of nodes in bio_queue */
+	bool			congested;	/* Someone is waiting for bio_queue_size
+						 * to drop. */
+	sector_t		current_sector;	/* Keep track of where the elevator is */
+	atomic_t		scan_queue;	/* Set to non-zero when pkt_handle_queue */
+						/* needs to be run. */
+	mempool_t		rb_pool;	/* mempool for pkt_rb_node allocations */
+
+	struct packet_iosched   iosched;
+	struct gendisk		*disk;
+
+	int			write_congestion_off;
+	int			write_congestion_on;
+
+	struct device		*dev;		/* sysfs pktcdvd[0-7] dev */
+
+	struct dentry		*dfs_d_root;	/* debugfs: devname directory */
+	struct dentry		*dfs_f_info;	/* debugfs: info file */
+};
+
+#endif /* __PKTCDVD_H */

include/linux/sunrpc/rpc_pipe_fs.h

···
 				       char __user *, size_t);
 extern int rpc_queue_upcall(struct rpc_pipe *, struct rpc_pipe_msg *);
 
+/* returns true if the msg is in-flight, i.e., already eaten by the peer */
+static inline bool rpc_msg_is_inflight(const struct rpc_pipe_msg *msg) {
+	return (msg->copied != 0 && list_empty(&msg->list));
+}
+
 struct rpc_clnt;
 extern struct dentry *rpc_create_client_dir(struct dentry *, const char *, struct rpc_clnt *);
 extern int rpc_remove_client_dir(struct rpc_clnt *);

include/net/inet_hashtables.h

···
 	struct hlist_node	node;
 	/* List of sockets hashed to this bucket */
 	struct hlist_head	owners;
+	/* bhash has twsk in owners, but bhash2 has twsk in
+	 * deathrow not to add a member in struct sock_common.
+	 */
+	struct hlist_head	deathrow;
 };
 
 static inline struct net *ib_net(const struct inet_bind_bucket *ib)

include/net/inet_timewait_sock.h

···
 	u32			tw_priority;
 	struct timer_list	tw_timer;
 	struct inet_bind_bucket	*tw_tb;
+	struct inet_bind2_bucket	*tw_tb2;
+	struct hlist_node		tw_bind2_node;
 };
 #define tw_tclass tw_tos
+
+#define twsk_for_each_bound_bhash2(__tw, list) \
+	hlist_for_each_entry(__tw, list, tw_bind2_node)
 
 static inline struct inet_timewait_sock *inet_twsk(const struct sock *sk)
 {

include/net/netfilter/nf_tables.h

···
 /**
  *	struct nft_set_desc - description of set elements
  *
+ *	@ktype: key type
  *	@klen: key length
+ *	@dtype: data type
  *	@dlen: data length
+ *	@objtype: object type
+ *	@flags: flags
  *	@size: number of set elements
+ *	@policy: set policy
+ *	@gc_int: garbage collector interval
  *	@field_len: length of each field in concatenation, bytes
  *	@field_count: number of concatenated fields in element
  *	@expr: set must support for expressions
  */
 struct nft_set_desc {
+	u32			ktype;
 	unsigned int		klen;
+	u32			dtype;
 	unsigned int		dlen;
+	u32			objtype;
 	unsigned int		size;
+	u32			policy;
+	u32			gc_int;
+	u64			timeout;
 	u8			field_len[NFT_REG32_COUNT];
 	u8			field_count;
 	bool			expr;
···
 
 static inline unsigned long nft_set_gc_interval(const struct nft_set *set)
 {
-	return set->gc_int ? msecs_to_jiffies(set->gc_int) : HZ;
+	u32 gc_int = READ_ONCE(set->gc_int);
+
+	return gc_int ? msecs_to_jiffies(gc_int) : HZ;
 }
 
 /**
···
 struct nft_trans_set {
 	struct nft_set			*set;
 	u32				set_id;
+	u32				gc_int;
+	u64				timeout;
+	bool				update;
 	bool				bound;
 };
 
···
 	(((struct nft_trans_set *)trans->data)->set_id)
 #define nft_trans_set_bound(trans)	\
 	(((struct nft_trans_set *)trans->data)->bound)
+#define nft_trans_set_update(trans)	\
+	(((struct nft_trans_set *)trans->data)->update)
+#define nft_trans_set_timeout(trans)	\
+	(((struct nft_trans_set *)trans->data)->timeout)
+#define nft_trans_set_gc_int(trans)	\
+	(((struct nft_trans_set *)trans->data)->gc_int)
 
 struct nft_trans_chain {
 	bool				update;

include/net/tc_wrapper.h

···
 	return tp->classify(skb, tp, res);
 }
 
+#endif /* CONFIG_NET_CLS */
+
 static inline void tc_wrapper_init(void)
 {
 #ifdef CONFIG_X86
···
 		static_branch_enable(&tc_skip_wrapper);
 #endif
 }
-
-#endif /* CONFIG_NET_CLS */
 
 #else
 

include/trace/events/btrfs.h

···
 	EM( FLUSH_DELALLOC_WAIT,	"FLUSH_DELALLOC_WAIT")		\
 	EM( FLUSH_DELALLOC_FULL,	"FLUSH_DELALLOC_FULL")		\
 	EM( FLUSH_DELAYED_REFS_NR,	"FLUSH_DELAYED_REFS_NR")	\
-	EM( FLUSH_DELAYED_REFS,		"FLUSH_ELAYED_REFS")		\
+	EM( FLUSH_DELAYED_REFS,		"FLUSH_DELAYED_REFS")		\
 	EM( ALLOC_CHUNK,		"ALLOC_CHUNK")			\
 	EM( ALLOC_CHUNK_FORCE,		"ALLOC_CHUNK_FORCE")		\
 	EM( RUN_DELAYED_IPUTS,		"RUN_DELAYED_IPUTS")		\

include/trace/events/rxrpc.h

···
 	    );
 
 TRACE_EVENT(rxrpc_recvmsg,
-	    TP_PROTO(struct rxrpc_call *call, enum rxrpc_recvmsg_trace why,
+	    TP_PROTO(unsigned int call_debug_id, enum rxrpc_recvmsg_trace why,
 		     int ret),
 
-	    TP_ARGS(call, why, ret),
+	    TP_ARGS(call_debug_id, why, ret),
 
 	    TP_STRUCT__entry(
 		    __field(unsigned int,		call		)
···
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call ? call->debug_id : 0;
+		    __entry->call = call_debug_id;
 		    __entry->why = why;
 		    __entry->ret = ret;
 			   ),

include/uapi/linux/atmbr2684.h

···
  */
 #define BR2684_ENCAPS_VC	(0)	/* VC-mux */
 #define BR2684_ENCAPS_LLC	(1)
-#define BR2684_ENCAPS_AUTODETECT (2)	/* Unsuported */
+#define BR2684_ENCAPS_AUTODETECT (2)	/* Unsupported */
 
 /*
  * Is this VC bridged or routed?

include/uapi/linux/io_uring.h

···
 
 #include <linux/fs.h>
 #include <linux/types.h>
+/*
+ * this file is shared with liburing and that has to autodetect
+ * if linux/time_types.h is available or not, it can
+ * define UAPI_LINUX_IO_URING_H_SKIP_LINUX_TIME_TYPES_H
+ * if linux/time_types.h is not available
+ */
+#ifndef UAPI_LINUX_IO_URING_H_SKIP_LINUX_TIME_TYPES_H
 #include <linux/time_types.h>
+#endif
 
 #ifdef __cplusplus
 extern "C" {

include/uapi/linux/kvm.h

···
 		__u8 runstate_update_flag;
 		struct {
 			__u64 gfn;
+#define KVM_XEN_INVALID_GFN ((__u64)-1)
 		} shared_info;
 		struct {
 			__u32 send_port;
···
 	} u;
 };
 
+
 /* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
 #define KVM_XEN_ATTR_TYPE_LONG_MODE		0x0
 #define KVM_XEN_ATTR_TYPE_SHARED_INFO		0x1
···
 	__u16 pad[3];
 	union {
 		__u64 gpa;
+#define KVM_XEN_INVALID_GPA ((__u64)-1)
 		__u64 pad[8];
 		struct {
 			__u64 state;

include/uapi/linux/pktcdvd.h

···
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2000 Jens Axboe <[e-mail]>
+ * Copyright (C) 2001-2004 Peter Osterlund <[e-mail]>
+ *
+ * May be copied or modified under the terms of the GNU General Public
+ * License.  See linux/COPYING for more information.
+ *
+ * Packet writing layer for ATAPI and SCSI CD-R, CD-RW, DVD-R, and
+ * DVD-RW devices.
+ *
+ */
+#ifndef _UAPI__PKTCDVD_H
+#define _UAPI__PKTCDVD_H
+
+#include <linux/types.h>
+
+/*
+ * 1 for normal debug messages, 2 is very verbose. 0 to turn it off.
+ */
+#define PACKET_DEBUG		1
+
+#define	MAX_WRITERS		8
+
+#define PKT_RB_POOL_SIZE	512
+
+/*
+ * How long we should hold a non-full packet before starting data gathering.
+ */
+#define PACKET_WAIT_TIME	(HZ * 5 / 1000)
+
+/*
+ * use drive write caching -- we need deferred error handling to be
+ * able to successfully recover with this option (drive will return good
+ * status as soon as the cdb is validated).
+ */
+#if defined(CONFIG_CDROM_PKTCDVD_WCACHE)
+#define USE_WCACHING		1
+#else
+#define USE_WCACHING		0
+#endif
+
+/*
+ * No user-servicable parts beyond this point ->
+ */
+
+/*
+ * device types
+ */
+#define PACKET_CDR		1
+#define	PACKET_CDRW		2
+#define PACKET_DVDR		3
+#define PACKET_DVDRW		4
+
+/*
+ * flags
+ */
+#define PACKET_WRITABLE		1	/* pd is writable */
+#define PACKET_NWA_VALID	2	/* next writable address valid */
+#define PACKET_LRA_VALID	3	/* last recorded address valid */
+#define PACKET_MERGE_SEGS	4	/* perform segment merging to keep */
+					/* underlying cdrom device happy */
+
+/*
+ * Disc status -- from READ_DISC_INFO
+ */
+#define PACKET_DISC_EMPTY	0
+#define PACKET_DISC_INCOMPLETE	1
+#define PACKET_DISC_COMPLETE	2
+#define PACKET_DISC_OTHER	3
+
+/*
+ * write type, and corresponding data block type
+ */
+#define PACKET_MODE1		1
+#define PACKET_MODE2		2
+#define PACKET_BLOCK_MODE1	8
+#define PACKET_BLOCK_MODE2	10
+
+/*
+ * Last session/border status
+ */
+#define PACKET_SESSION_EMPTY		0
+#define PACKET_SESSION_INCOMPLETE	1
+#define PACKET_SESSION_RESERVED		2
+#define PACKET_SESSION_COMPLETE		3
+
+#define PACKET_MCN			"4a656e734178626f65323030300000"
+
+#undef PACKET_USE_LS
+
+#define PKT_CTRL_CMD_SETUP	0
+#define PKT_CTRL_CMD_TEARDOWN	1
+#define PKT_CTRL_CMD_STATUS	2
+
+struct pkt_ctrl_command {
+	__u32 command;				/* in: Setup, teardown, status */
+	__u32 dev_index;			/* in/out: Device index */
+	__u32 dev;				/* in/out: Device nr for cdrw device */
+	__u32 pkt_dev;				/* in/out: Device nr for packet device */
+	__u32 num_devices;			/* out: Largest device index + 1 */
+	__u32 padding;				/* Not used */
+};
+
+/*
+ * packet ioctls
+ */
+#define PACKET_IOCTL_MAGIC	('X')
+#define PACKET_CTRL_CMD		_IOWR(PACKET_IOCTL_MAGIC, 1, struct pkt_ctrl_command)
+
+
+#endif /* _UAPI__PKTCDVD_H */

include/uapi/linux/vdpa.h

···
 	VDPA_ATTR_DEV_VENDOR_ATTR_NAME,		/* string */
 	VDPA_ATTR_DEV_VENDOR_ATTR_VALUE,        /* u64 */
 
+	/* virtio features that are provisioned to the vDPA device */
 	VDPA_ATTR_DEV_FEATURES,                 /* u64 */
-
-	/* virtio features that are supported by the vDPA device */
-	VDPA_ATTR_VDPA_DEV_SUPPORTED_FEATURES,	/* u64 */
 
 	/* new attributes must be added above here */
 	VDPA_ATTR_MAX,

io_uring/cancel.c

···
 
 		ret = __io_sync_cancel(current->io_uring, &cd, sc.fd);
 
+		mutex_unlock(&ctx->uring_lock);
 		if (ret != -EALREADY)
 			break;
 
-		mutex_unlock(&ctx->uring_lock);
 		ret = io_run_task_work_sig(ctx);
-		if (ret < 0) {
-			mutex_lock(&ctx->uring_lock);
+		if (ret < 0)
 			break;
-		}
 		ret = schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS);
-		mutex_lock(&ctx->uring_lock);
 		if (!ret) {
 			ret = -ETIME;
 			break;
 		}
+		mutex_lock(&ctx->uring_lock);
 	} while (1);
 
 	finish_wait(&ctx->cq_wait, &wait);
+	mutex_lock(&ctx->uring_lock);
 
 	if (ret == -ENOENT || ret > 0)
 		ret = 0;

io_uring/io-wq.c

···
 
 		worker = container_of(cb, struct io_worker, create_work);
 		io_worker_cancel_cb(worker);
+		kfree(worker);
 	}
 }
 

io_uring/io_uring.c

···
 	io_cq_unlock_post(ctx);
 }
 
+static void io_cqring_do_overflow_flush(struct io_ring_ctx *ctx)
+{
+	/* iopoll syncs against uring_lock, not completion_lock */
+	if (ctx->flags & IORING_SETUP_IOPOLL)
+		mutex_lock(&ctx->uring_lock);
+	__io_cqring_overflow_flush(ctx);
+	if (ctx->flags & IORING_SETUP_IOPOLL)
+		mutex_unlock(&ctx->uring_lock);
+}
+
 static void io_cqring_overflow_flush(struct io_ring_ctx *ctx)
 {
-	if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)) {
-		/* iopoll syncs against uring_lock, not completion_lock */
-		if (ctx->flags & IORING_SETUP_IOPOLL)
-			mutex_lock(&ctx->uring_lock);
-		__io_cqring_overflow_flush(ctx);
-		if (ctx->flags & IORING_SETUP_IOPOLL)
-			mutex_unlock(&ctx->uring_lock);
-	}
+	if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq))
+		io_cqring_do_overflow_flush(ctx);
 }
 
 void __io_put_task(struct task_struct *task, int nr)
···
 	struct io_overflow_cqe *ocqe;
 	size_t ocq_size = sizeof(struct io_overflow_cqe);
 	bool is_cqe32 = (ctx->flags & IORING_SETUP_CQE32);
+
+	lockdep_assert_held(&ctx->completion_lock);
 
 	if (is_cqe32)
 		ocq_size += sizeof(struct io_uring_cqe);
···
 			      u32 cflags)
 {
 	struct io_uring_cqe *cqe;
-
-	if (!ctx->task_complete)
-		lockdep_assert_held(&ctx->completion_lock);
 
 	ctx->cq_extra++;
 
···
 {
 	struct io_ring_ctx *ctx = req->ctx;
 
-	if (!llist_add(&req->io_task_work.node, &ctx->work_llist))
+	percpu_ref_get(&ctx->refs);
+
+	if (!llist_add(&req->io_task_work.node, &ctx->work_llist)) {
+		percpu_ref_put(&ctx->refs);
 		return;
+	}
 	/* need it for the following io_cqring_wake() */
 	smp_mb__after_atomic();
 
 	if (unlikely(atomic_read(&req->task->io_uring->in_idle))) {
 		io_move_task_work_from_local(ctx);
+		percpu_ref_put(&ctx->refs);
 		return;
 	}
 
···
 	if (ctx->has_evfd)
 		io_eventfd_signal(ctx);
 	__io_cqring_wake(ctx);
+	percpu_ref_put(&ctx->refs);
 }
 
 void __io_req_task_work_add(struct io_kiocb *req, bool allow_local)
···
 /* when returns >0, the caller should retry */
 static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
 					  struct io_wait_queue *iowq,
-					  ktime_t timeout)
+					  ktime_t *timeout)
 {
 	int ret;
 	unsigned long check_cq;
···
 		if (check_cq & BIT(IO_CHECK_CQ_DROPPED_BIT))
 			return -EBADR;
 	}
-	if (!schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS))
+	if (!schedule_hrtimeout(timeout, HRTIMER_MODE_ABS))
 		return -ETIME;
 
 	/*
···
 
 	trace_io_uring_cqring_wait(ctx, min_events);
 	do {
-		io_cqring_overflow_flush(ctx);
+		if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq)) {
+			finish_wait(&ctx->cq_wait, &iowq.wq);
+			io_cqring_do_overflow_flush(ctx);
+		}
 		prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq,
 						TASK_INTERRUPTIBLE);
-		ret = io_cqring_wait_schedule(ctx, &iowq, timeout);
+		ret = io_cqring_wait_schedule(ctx, &iowq, &timeout);
 		if (__io_cqring_events_user(ctx) >= min_events)
 			break;
 		cond_resched();
···
 		return -EEXIST;
 
 	if (ctx->restricted) {
-		if (opcode >= IORING_REGISTER_LAST)
-			return -EINVAL;
 		opcode = array_index_nospec(opcode, IORING_REGISTER_LAST);
 		if (!test_bit(opcode, ctx->restrictions.register_op))
 			return -EACCES;
···
 	struct io_ring_ctx *ctx;
 	long ret = -EBADF;
 	struct fd f;
+
+	if (opcode >= IORING_REGISTER_LAST)
+		return -EINVAL;
 
 	f = fdget(fd);
 	if (!f.file)

io_uring/io_uring.h

···
 bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task,
 			bool cancel_all);
 
+#define io_lockdep_assert_cq_locked(ctx)				\
+	do {								\
+		if (ctx->flags & IORING_SETUP_IOPOLL) {			\
+			lockdep_assert_held(&ctx->uring_lock);		\
+		} else if (!ctx->task_complete) {			\
+			lockdep_assert_held(&ctx->completion_lock);	\
+		} else if (ctx->submitter_task->flags & PF_EXITING) {	\
+			lockdep_assert(current_work());			\
+		} else {						\
+			lockdep_assert(current == ctx->submitter_task);	\
+		}							\
+	} while (0)
+
 static inline void io_req_task_work_add(struct io_kiocb *req)
 {
 	__io_req_task_work_add(req, true);
···
 static inline struct io_uring_cqe *io_get_cqe_overflow(struct io_ring_ctx *ctx,
 						       bool overflow)
 {
+	io_lockdep_assert_cq_locked(ctx);
+
 	if (likely(ctx->cqe_cached < ctx->cqe_sentinel)) {
 		struct io_uring_cqe *cqe = ctx->cqe_cached;
 

kernel/bpf/bpf_lsm.c

···
 BTF_ID(func, bpf_lsm_bpf_prog_free_security)
 BTF_ID(func, bpf_lsm_file_alloc_security)
 BTF_ID(func, bpf_lsm_file_free_security)
+#ifdef CONFIG_SECURITY_NETWORK
 BTF_ID(func, bpf_lsm_sk_alloc_security)
 BTF_ID(func, bpf_lsm_sk_free_security)
+#endif /* CONFIG_SECURITY_NETWORK */
 BTF_ID(func, bpf_lsm_task_free)
 BTF_SET_END(untrusted_lsm_hooks)
 

kernel/bpf/task_iter.c

···
 	 */
 	struct bpf_iter_seq_task_common common;
 	struct task_struct *task;
+	struct mm_struct *mm;
 	struct vm_area_struct *vma;
 	u32 tid;
 	unsigned long prev_vm_start;
···
 	enum bpf_task_vma_iter_find_op op;
 	struct vm_area_struct *curr_vma;
 	struct task_struct *curr_task;
+	struct mm_struct *curr_mm;
 	u32 saved_tid = info->tid;
 
 	/* If this function returns a non-NULL vma, it holds a reference to
-	 * the task_struct, and holds read lock on vma->mm->mmap_lock.
+	 * the task_struct, holds a refcount on mm->mm_users, and holds
+	 * read lock on vma->mm->mmap_lock.
 	 * If this function returns NULL, it does not hold any reference or
 	 * lock.
 	 */
 	if (info->task) {
 		curr_task = info->task;
 		curr_vma = info->vma;
+		curr_mm = info->mm;
 		/* In case of lock contention, drop mmap_lock to unblock
 		 * the writer.
 		 *
···
 		 *    4.2) VMA2 and VMA2' covers different ranges, process
 		 *         VMA2'.
 		 */
-		if (mmap_lock_is_contended(curr_task->mm)) {
+		if (mmap_lock_is_contended(curr_mm)) {
 			info->prev_vm_start = curr_vma->vm_start;
 			info->prev_vm_end = curr_vma->vm_end;
 			op = task_vma_iter_find_vma;
-			mmap_read_unlock(curr_task->mm);
-			if (mmap_read_lock_killable(curr_task->mm))
+			mmap_read_unlock(curr_mm);
+			if (mmap_read_lock_killable(curr_mm)) {
+				mmput(curr_mm);
 				goto finish;
+			}
 		} else {
 			op = task_vma_iter_next_vma;
 		}
···
 			op = task_vma_iter_find_vma;
 		}
 
-		if (!curr_task->mm)
+		curr_mm = get_task_mm(curr_task);
+		if (!curr_mm)
 			goto next_task;
 
-		if (mmap_read_lock_killable(curr_task->mm))
+		if (mmap_read_lock_killable(curr_mm)) {
+			mmput(curr_mm);
 			goto finish;
+		}
 	}
 
 	switch (op) {
 	case task_vma_iter_first_vma:
-		curr_vma = find_vma(curr_task->mm, 0);
+		curr_vma = find_vma(curr_mm, 0);
 		break;
 	case task_vma_iter_next_vma:
-		curr_vma = find_vma(curr_task->mm, curr_vma->vm_end);
+		curr_vma = find_vma(curr_mm, curr_vma->vm_end);
 		break;
 	case task_vma_iter_find_vma:
 		/* We dropped mmap_lock so it is necessary to use find_vma
 		 * to find the next vma. This is similar to the  mechanism
 		 * in show_smaps_rollup().
 		 */
-		curr_vma = find_vma(curr_task->mm, info->prev_vm_end - 1);
+		curr_vma = find_vma(curr_mm, info->prev_vm_end - 1);
 		/* case 1) and 4.2) above just use curr_vma */
 
 		/* check for case 2) or case 4.1) above */
 		if (curr_vma &&
 		    curr_vma->vm_start == info->prev_vm_start &&
 		    curr_vma->vm_end == info->prev_vm_end)
-			curr_vma = find_vma(curr_task->mm, curr_vma->vm_end);
+			curr_vma = find_vma(curr_mm, curr_vma->vm_end);
 		break;
 	}
 	if (!curr_vma) {
 		/* case 3) above, or case 2) 4.1) with vma->next == NULL */
-		mmap_read_unlock(curr_task->mm);
+		mmap_read_unlock(curr_mm);
+		mmput(curr_mm);
 		goto next_task;
 	}
 	info->task = curr_task;
 	info->vma = curr_vma;
+	info->mm = curr_mm;
 	return curr_vma;
 
 next_task:
···
 
 	put_task_struct(curr_task);
 	info->task = NULL;
+	info->mm = NULL;
 	info->tid++;
 	goto again;
 
···
 		put_task_struct(curr_task);
 	info->task = NULL;
 	info->vma = NULL;
+	info->mm = NULL;
 	return NULL;
 }
 
···
 		 */
 		info->prev_vm_start = ~0UL;
 		info->prev_vm_end = info->vma->vm_end;
-		mmap_read_unlock(info->task->mm);
+		mmap_read_unlock(info->mm);
+		mmput(info->mm);
+		info->mm = NULL;
 		put_task_struct(info->task);
 		info->task = NULL;
 	}

kernel/bpf/trampoline.c

···
 		/* reset fops->func and fops->trampoline for re-register */
 		tr->fops->func = NULL;
 		tr->fops->trampoline = 0;
+
+		/* reset im->image memory attr for arch_prepare_bpf_trampoline */
+		set_memory_nx((long)im->image, 1);
+		set_memory_rw((long)im->image, 1);
 		goto again;
 	}
 #endif

kernel/bpf/verifier.c

···
  */
 static void *copy_array(void *dst, const void *src, size_t n, size_t size, gfp_t flags)
 {
+	size_t alloc_bytes;
+	void *orig = dst;
 	size_t bytes;
 
 	if (ZERO_OR_NULL_PTR(src))
···
 	if (unlikely(check_mul_overflow(n, size, &bytes)))
 		return NULL;
 
-	if (ksize(dst) < ksize(src)) {
-		kfree(dst);
-		dst = kmalloc_track_caller(kmalloc_size_roundup(bytes), flags);
-		if (!dst)
-			return NULL;
+	alloc_bytes = max(ksize(orig), kmalloc_size_roundup(bytes));
+	dst = krealloc(orig, alloc_bytes, flags);
+	if (!dst) {
+		kfree(orig);
+		return NULL;
 	}
 
 	memcpy(dst, src, bytes);
···
 	 *      register B - not null
 	 * for JNE A, B, ... - A is not null in the false branch;
 	 * for JEQ A, B, ... - A is not null in the true branch.
+	 *
+	 * Since PTR_TO_BTF_ID points to a kernel struct that does
+	 * not need to be null checked by the BPF program, i.e.,
+	 * could be null even without PTR_MAYBE_NULL marking, so
+	 * only propagate nullness when neither reg is that type.
 	 */
 	if (!is_jmp32 && BPF_SRC(insn->code) == BPF_X &&
 	    __is_pointer_value(false, src_reg) && __is_pointer_value(false, dst_reg) &&
-	    type_may_be_null(src_reg->type) != type_may_be_null(dst_reg->type)) {
+	    type_may_be_null(src_reg->type) != type_may_be_null(dst_reg->type) &&
+	    base_type(src_reg->type) != PTR_TO_BTF_ID &&
+	    base_type(dst_reg->type) != PTR_TO_BTF_ID) {
 		eq_branch_regs = NULL;
 		switch (opcode) {
 		case BPF_JEQ:

kernel/events/core.c

···
 
 /*
  * perf_sched_events : >0 events exist
- * perf_cgroup_events: >0 per-cpu cgroup events exist on this cpu
  */
 
 static void perf_sched_delayed(struct work_struct *work);
···
 static DEFINE_MUTEX(perf_sched_mutex);
 static atomic_t perf_sched_count;
 
-static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
 static DEFINE_PER_CPU(struct pmu_event_list, pmu_sb_events);
 
 static atomic_t nr_mmap_events __read_mostly;
···
 	struct perf_cpu_context *cpuctx = this_cpu_ptr(&perf_cpu_context);
 	struct perf_cgroup *cgrp;
 
-	cgrp = perf_cgroup_from_task(task, NULL);
+	/*
+	 * cpuctx->cgrp is set when the first cgroup event enabled,
+	 * and is cleared when the last cgroup event disabled.
+	 */
+	if (READ_ONCE(cpuctx->cgrp) == NULL)
+		return;
 
 	WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0);
+
+	cgrp = perf_cgroup_from_task(task, NULL);
 	if (READ_ONCE(cpuctx->cgrp) == cgrp)
 		return;
 
···
 	 * to check if we have to switch out PMU state.
 	 * cgroup event are system-wide mode only
 	 */
-	if (atomic_read(this_cpu_ptr(&perf_cgroup_events)))
-		perf_cgroup_switch(next);
+	perf_cgroup_switch(next);
 }
 
 static bool perf_less_group_idx(const void *l, const void *r)
···
 		detach_sb_event(event);
 }
 
-static void unaccount_event_cpu(struct perf_event *event, int cpu)
-{
-	if (event->parent)
-		return;
-
-	if (is_cgroup_event(event))
-		atomic_dec(&per_cpu(perf_cgroup_events, cpu));
-}
-
 #ifdef CONFIG_NO_HZ_FULL
 static DEFINE_SPINLOCK(nr_freq_lock);
 #endif
···
 		if (!atomic_add_unless(&perf_sched_count, -1, 1))
 			schedule_delayed_work(&perf_sched_work, HZ);
 	}
-
-	unaccount_event_cpu(event, event->cpu);
 
 	unaccount_pmu_sb_event(event);
 }
···
 		attach_sb_event(event);
 }
 
-static void account_event_cpu(struct perf_event *event, int cpu)
-{
-	if (event->parent)
-		return;
-
-	if (is_cgroup_event(event))
-		atomic_inc(&per_cpu(perf_cgroup_events, cpu));
-}
-
 /* Freq events need the tick to stay alive (see perf_event_task_tick). */
 static void account_freq_event_nohz(void)
 {
···
 		mutex_unlock(&perf_sched_mutex);
 	}
 enabled:
-
-	account_event_cpu(event, event->cpu);
 
 	account_pmu_sb_event(event);
 }
···
 	if (flags & ~PERF_FLAG_ALL)
 		return -EINVAL;
 
-	/* Do we allow access to perf_event_open(2) ? */
-	err = security_perf_event_open(&attr, PERF_SECURITY_OPEN);
+	err = perf_copy_attr(attr_uptr, &attr);
 	if (err)
 		return err;
 
-	err = perf_copy_attr(attr_uptr, &attr);
+	/* Do we allow access to perf_event_open(2) ? */
+	err = security_perf_event_open(&attr, PERF_SECURITY_OPEN);
 	if (err)
 		return err;
 
···
 	return event_fd;
 
 err_context:
-	/* event->pmu_ctx freed by free_event() */
+	put_pmu_ctx(event->pmu_ctx);
+	event->pmu_ctx = NULL; /* _free_event() */
 err_locked:
 	mutex_unlock(&ctx->mutex);
 	perf_unpin_context(ctx);
···
 
 err_pmu_ctx:
 	put_pmu_ctx(pmu_ctx);
+	event->pmu_ctx = NULL; /* _free_event() */
 err_unlock:
 	mutex_unlock(&ctx->mutex);
 	perf_unpin_context(ctx);
···
 
 	perf_event_groups_for_cpu_pmu(event, groups, cpu, pmu) {
 		perf_remove_from_context(event, 0);
-		unaccount_event_cpu(event, cpu);
 		put_pmu_ctx(event->pmu_ctx);
 		list_add(&event->migrate_entry, events);
 
 		for_each_sibling_event(sibling, event) {
 			perf_remove_from_context(sibling, 0);
-			unaccount_event_cpu(sibling, cpu);
 			put_pmu_ctx(sibling->pmu_ctx);
 			list_add(&sibling->migrate_entry, events);
 		}
···
 
 	if (event->state >= PERF_EVENT_STATE_OFF)
 		event->state = PERF_EVENT_STATE_INACTIVE;
-	account_event_cpu(event, cpu);
 	perf_install_in_context(ctx, event, cpu);
 }
 
···
 	pmu_ctx = find_get_pmu_context(child_event->pmu, child_ctx, child_event);
 	if (IS_ERR(pmu_ctx)) {
 		free_event(child_event);
-		return NULL;
+		return ERR_CAST(pmu_ctx);
 	}
 	child_event->pmu_ctx = pmu_ctx;
 
···
 	struct task_struct *task = info;
 
 	preempt_disable();
-	if (atomic_read(this_cpu_ptr(&perf_cgroup_events)))
-		perf_cgroup_switch(task);
+	perf_cgroup_switch(task);
 	preempt_enable();
 
 	return 0;

kernel/futex/syscalls.c

···
 	}
 
 	futexv = kcalloc(nr_futexes, sizeof(*futexv), GFP_KERNEL);
-	if (!futexv)
-		return -ENOMEM;
+	if (!futexv) {
+		ret = -ENOMEM;
+		goto destroy_timer;
+	}
 
 	ret = futex_parse_waitv(futexv, waiters, nr_futexes);
 	if (!ret)
 		ret = futex_wait_multiple(futexv, nr_futexes, timeout ? &to : NULL);
 
+	kfree(futexv);
+
+destroy_timer:
 	if (timeout) {
 		hrtimer_cancel(&to.timer);
 		destroy_hrtimer_on_stack(&to.timer);
 	}
-
-	kfree(futexv);
 	return ret;
 }
 

kernel/locking/rtmutex.c

···
  * set this bit before looking at the lock.
  */
 
-static __always_inline void
-rt_mutex_set_owner(struct rt_mutex_base *lock, struct task_struct *owner)
+static __always_inline struct task_struct *
+rt_mutex_owner_encode(struct rt_mutex_base *lock, struct task_struct *owner)
 {
 	unsigned long val = (unsigned long)owner;
 
 	if (rt_mutex_has_waiters(lock))
 		val |= RT_MUTEX_HAS_WAITERS;
 
-	WRITE_ONCE(lock->owner, (struct task_struct *)val);
+	return (struct task_struct *)val;
+}
+
+static __always_inline void
+rt_mutex_set_owner(struct rt_mutex_base *lock, struct task_struct *owner)
+{
+	/*
+	 * lock->wait_lock is held but explicit acquire semantics are needed
+	 * for a new lock owner so WRITE_ONCE is insufficient.
+	 */
+	xchg_acquire(&lock->owner, rt_mutex_owner_encode(lock, owner));
+}
+
+static __always_inline void rt_mutex_clear_owner(struct rt_mutex_base *lock)
+{
+	/* lock->wait_lock is held so the unlock provides release semantics. */
+	WRITE_ONCE(lock->owner, rt_mutex_owner_encode(lock, NULL));
 }
 
 static __always_inline void clear_rt_mutex_waiters(struct rt_mutex_base *lock)
···
 			((unsigned long)lock->owner & ~RT_MUTEX_HAS_WAITERS);
 }
 
-static __always_inline void fixup_rt_mutex_waiters(struct rt_mutex_base *lock)
+static __always_inline void
+fixup_rt_mutex_waiters(struct rt_mutex_base *lock, bool acquire_lock)
 {
 	unsigned long owner, *p = (unsigned long *) &lock->owner;
 
···
 	 * still set.
 	 */
 	owner = READ_ONCE(*p);
-	if (owner & RT_MUTEX_HAS_WAITERS)
-		WRITE_ONCE(*p, owner & ~RT_MUTEX_HAS_WAITERS);
+	if (owner & RT_MUTEX_HAS_WAITERS) {
+		/*
+		 * See rt_mutex_set_owner() and rt_mutex_clear_owner() on
+		 * why xchg_acquire() is used for updating owner for
+		 * locking and WRITE_ONCE() for unlocking.
+		 *
+		 * WRITE_ONCE() would work for the acquire case too, but
+		 * in case that the lock acquisition failed it might
+		 * force other lockers into the slow path unnecessarily.
+		 */
+		if (acquire_lock)
+			xchg_acquire(p, owner & ~RT_MUTEX_HAS_WAITERS);
+		else
+			WRITE_ONCE(*p, owner & ~RT_MUTEX_HAS_WAITERS);
+	}
 }
 
 /*
···
 		owner = *p;
 	} while (cmpxchg_relaxed(p, owner,
 				 owner | RT_MUTEX_HAS_WAITERS) != owner);
+
+	/*
+	 * The cmpxchg loop above is relaxed to avoid back-to-back ACQUIRE
+	 * operations in the event of contention. Ensure the successful
+	 * cmpxchg is visible.
+	 */
+	smp_mb__after_atomic();
 }
 
 /*
···
 	 * try_to_take_rt_mutex() sets the lock waiters bit
 	 * unconditionally. Clean this up.
 	 */
-	fixup_rt_mutex_waiters(lock);
+	fixup_rt_mutex_waiters(lock, true);
 
 	return ret;
 }
···
 	 * try_to_take_rt_mutex() sets the waiter bit
 	 * unconditionally. We might have to fix that up.
 	 */
-	fixup_rt_mutex_waiters(lock);
+	fixup_rt_mutex_waiters(lock, true);
 
 	trace_contention_end(lock, ret);
 
···
 	 * try_to_take_rt_mutex() sets the waiter bit unconditionally.
 	 * We might have to fix that up:
 	 */
-	fixup_rt_mutex_waiters(lock);
+	fixup_rt_mutex_waiters(lock, true);
 	debug_rt_mutex_free_waiter(&waiter);
 
 	trace_contention_end(lock, 0);

kernel/locking/rtmutex_api.c

···
 void __sched rt_mutex_proxy_unlock(struct rt_mutex_base *lock)
 {
 	debug_rt_mutex_proxy_unlock(lock);
-	rt_mutex_set_owner(lock, NULL);
+	rt_mutex_clear_owner(lock);
 }
 
 /**
···
 	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
 	 * have to fix that up.
 	 */
-	fixup_rt_mutex_waiters(lock);
+	fixup_rt_mutex_waiters(lock, true);
 	raw_spin_unlock_irq(&lock->wait_lock);
 
 	return ret;
···
 	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
 	 * have to fix that up.
 	 */
-	fixup_rt_mutex_waiters(lock);
+	fixup_rt_mutex_waiters(lock, false);
 
 	raw_spin_unlock_irq(&lock->wait_lock);
 

lib/kunit/string-stream.c

···
 		return ERR_PTR(-ENOMEM);
 
 	frag->fragment = kunit_kmalloc(test, len, gfp);
-	if (!frag->fragment)
+	if (!frag->fragment) {
+		kunit_kfree(test, frag);
 		return ERR_PTR(-ENOMEM);
+	}
 
 	return frag;
 }

lib/scatterlist.c

···
 		/* Merge contiguous pages into the last SG */
 		prv_len = sgt_append->prv->length;
 		last_pg = sg_page(sgt_append->prv);
-		while (n_pages && pages_are_mergeable(last_pg, pages[0])) {
+		while (n_pages && pages_are_mergeable(pages[0], last_pg)) {
 			if (sgt_append->prv->length + PAGE_SIZE > max_segment)
 				break;
 			sgt_append->prv->length += PAGE_SIZE;

mm/memblock.c

···
  * @base: phys starting address of the  boot memory block
  * @size: size of the boot memory block in bytes
  *
- * Free boot memory block previously allocated by memblock_alloc_xx() API.
+ * Free boot memory block previously allocated by memblock_phys_alloc_xx() API.
  * The freeing memory will not be released to the buddy allocator.
  */
 int __init_memblock memblock_phys_free(phys_addr_t base, phys_addr_t size)

net/caif/cfctrl.c

···
 	default:
 		pr_warn("Request setup of bad link type = %d\n",
 			param->linktype);
+		cfpkt_destroy(pkt);
 		return -EINVAL;
 	}
 	req = kzalloc(sizeof(*req), GFP_KERNEL);
-	if (!req)
+	if (!req) {
+		cfpkt_destroy(pkt);
 		return -ENOMEM;
+	}
+
 	req->client_layer = user_layer;
 	req->cmd = CFCTRL_CMD_LINK_SETUP;
 	req->param = *param;

net/core/filter.c

···
 
 static int bpf_skb_generic_pop(struct sk_buff *skb, u32 off, u32 len)
 {
+	void *old_data;
+
 	/* skb_ensure_writable() is not needed here, as we're
 	 * already working on an uncloned skb.
 	 */
 	if (unlikely(!pskb_may_pull(skb, off + len)))
 		return -ENOMEM;
 
-	skb_postpull_rcsum(skb, skb->data + off, len);
-	memmove(skb->data + len, skb->data, off);
+	old_data = skb->data;
 	__skb_pull(skb, len);
+	skb_postpull_rcsum(skb, old_data + off, len);
+	memmove(skb->data, old_data, off);
 
 	return 0;
 }

net/ethtool/ioctl.c

···
 	return ret;
 }
 
-static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr)
+static int ethtool_vzalloc_stats_array(int n_stats, u64 **data)
 {
-	const struct ethtool_phy_ops *phy_ops = ethtool_phy_ops;
-	const struct ethtool_ops *ops = dev->ethtool_ops;
-	struct phy_device *phydev = dev->phydev;
-	struct ethtool_stats stats;
-	u64 *data;
-	int ret, n_stats;
-
-	if (!phydev && (!ops->get_ethtool_phy_stats || !ops->get_sset_count))
-		return -EOPNOTSUPP;
-
-	if (phydev && !ops->get_ethtool_phy_stats &&
-	    phy_ops && phy_ops->get_sset_count)
-		n_stats = phy_ops->get_sset_count(phydev);
-	else
-		n_stats = ops->get_sset_count(dev, ETH_SS_PHY_STATS);
 	if (n_stats < 0)
 		return n_stats;
 	if (n_stats > S32_MAX / sizeof(u64))
 		return -ENOMEM;
-	WARN_ON_ONCE(!n_stats);
+	if (WARN_ON_ONCE(!n_stats))
+		return -EOPNOTSUPP;
+
+	*data = vzalloc(array_size(n_stats, sizeof(u64)));
+	if (!*data)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static int ethtool_get_phy_stats_phydev(struct phy_device *phydev,
+					 struct ethtool_stats *stats,
+					 u64 **data)
+ {
+	const struct ethtool_phy_ops *phy_ops = ethtool_phy_ops;
+	int n_stats, ret;
+
+	if (!phy_ops || !phy_ops->get_sset_count || !phy_ops->get_stats)
+		return -EOPNOTSUPP;
+
+	n_stats = phy_ops->get_sset_count(phydev);
+
+	ret = ethtool_vzalloc_stats_array(n_stats, data);
+	if (ret)
+		return ret;
+
+	stats->n_stats = n_stats;
+	return phy_ops->get_stats(phydev, stats, *data);
+}
+
+static int ethtool_get_phy_stats_ethtool(struct net_device *dev,
+					  struct ethtool_stats *stats,
+					  u64 **data)
+{
+	const struct ethtool_ops *ops = dev->ethtool_ops;
+	int n_stats, ret;
+
+	if (!ops || !ops->get_sset_count || ops->get_ethtool_phy_stats)
+		return -EOPNOTSUPP;
+
+	n_stats = ops->get_sset_count(dev, ETH_SS_PHY_STATS);
+
+	ret = ethtool_vzalloc_stats_array(n_stats, data);
+	if (ret)
+		return ret;
+
+	stats->n_stats = n_stats;
+	ops->get_ethtool_phy_stats(dev, stats, *data);
+
+	return 0;
+}
+
+static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr)
+{
+	struct phy_device *phydev = dev->phydev;
+	struct ethtool_stats stats;
+	u64 *data = NULL;
+	int ret = -EOPNOTSUPP;
 
 	if (copy_from_user(&stats, useraddr, sizeof(stats)))
 		return -EFAULT;
 
-	stats.n_stats = n_stats;
+	if (phydev)
+		ret = ethtool_get_phy_stats_phydev(phydev, &stats, &data);
 
-	if (n_stats) {
-		data = vzalloc(array_size(n_stats, sizeof(u64)));
-		if (!data)
-			return -ENOMEM;
+	if (ret == -EOPNOTSUPP)
+		ret = ethtool_get_phy_stats_ethtool(dev, &stats, &data);
 
-		if (phydev && !ops->get_ethtool_phy_stats &&
-		    phy_ops && phy_ops->get_stats) {
-			ret = phy_ops->get_stats(phydev, &stats, data);
-			if (ret < 0)
-				goto out;
-		} else {
-			ops->get_ethtool_phy_stats(dev, &stats, data);
-		}
-	} else {
-		data = NULL;
+	if (ret)
+		goto out;
+
+	if (copy_to_user(useraddr, &stats, sizeof(stats))) {
+		ret = -EFAULT;
+		goto out;
 	}
 
-	ret = -EFAULT;
-	if (copy_to_user(useraddr, &stats, sizeof(stats)))
-		goto out;
 	useraddr += sizeof(stats);
-	if (n_stats && copy_to_user(useraddr, data, array_size(n_stats, sizeof(u64))))
-		goto out;
-	ret = 0;
+	if (copy_to_user(useraddr, data, array_size(stats.n_stats, sizeof(u64))))
+		ret = -EFAULT;
 
  out:
 	vfree(data);

net/ipv4/af_inet.c

···
 	if (rc == 0) {
 		*sk = sock->sk;
 		(*sk)->sk_allocation = GFP_ATOMIC;
+		(*sk)->sk_use_task_frag = false;
 		/*
 		 * Unhash it so that IP input processing does not even see it,
 		 * we do not wish this socket to see incoming packets.

net/ipv4/inet_connection_sock.c

···
 	return false;
 }
 
+static bool __inet_bhash2_conflict(const struct sock *sk, struct sock *sk2,
+				   kuid_t sk_uid, bool relax,
+				   bool reuseport_cb_ok, bool reuseport_ok)
+{
+	if (sk->sk_family == AF_INET && ipv6_only_sock(sk2))
+		return false;
+
+	return inet_bind_conflict(sk, sk2, sk_uid, relax,
+				  reuseport_cb_ok, reuseport_ok);
+}
+
 static bool inet_bhash2_conflict(const struct sock *sk,
 				 const struct inet_bind2_bucket *tb2,
 				 kuid_t sk_uid,
 				 bool relax, bool reuseport_cb_ok,
 				 bool reuseport_ok)
 {
+	struct inet_timewait_sock *tw2;
 	struct sock *sk2;
 
 	sk_for_each_bound_bhash2(sk2, &tb2->owners) {
-		if (sk->sk_family == AF_INET && ipv6_only_sock(sk2))
-			continue;
-
-		if (inet_bind_conflict(sk, sk2, sk_uid, relax,
-				       reuseport_cb_ok, reuseport_ok))
+		if (__inet_bhash2_conflict(sk, sk2, sk_uid, relax,
+					   reuseport_cb_ok, reuseport_ok))
 			return true;
 	}
+
+	twsk_for_each_bound_bhash2(tw2, &tb2->deathrow) {
+		sk2 = (struct sock *)tw2;
+
+		if (__inet_bhash2_conflict(sk, sk2, sk_uid, relax,
+					   reuseport_cb_ok, reuseport_ok))
+			return true;
+	}
+
 	return false;
 }
 
···
 }
 EXPORT_SYMBOL(inet_csk_prepare_forced_close);
 
+static int inet_ulp_can_listen(const struct sock *sk)
+{
+	const struct inet_connection_sock *icsk = inet_csk(sk);
+
+	if (icsk->icsk_ulp_ops && !icsk->icsk_ulp_ops->clone)
+		return -EINVAL;
+
+	return 0;
+}
+
 int inet_csk_listen_start(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct inet_sock *inet = inet_sk(sk);
 	int err;
+
+	err = inet_ulp_can_listen(sk);
+	if (unlikely(err))
+		return err;
 
 	reqsk_queue_alloc(&icsk->icsk_accept_queue);
 

net/ipv4/inet_hashtables.c

···
 #endif
 		tb->rcv_saddr = sk->sk_rcv_saddr;
 	INIT_HLIST_HEAD(&tb->owners);
+	INIT_HLIST_HEAD(&tb->deathrow);
 	hlist_add_head(&tb->node, &head->chain);
 }
 
···
 /* Caller must hold hashbucket lock for this tb with local BH disabled */
 void inet_bind2_bucket_destroy(struct kmem_cache *cachep, struct inet_bind2_bucket *tb)
 {
-	if (hlist_empty(&tb->owners)) {
+	if (hlist_empty(&tb->owners) && hlist_empty(&tb->deathrow)) {
 		__hlist_del(&tb->node);
 		kmem_cache_free(cachep, tb);
 	}
···
 	/* Head lock still held and bh's disabled */
 	inet_bind_hash(sk, tb, tb2, port);
 
-	spin_unlock(&head2->lock);
-
 	if (sk_unhashed(sk)) {
 		inet_sk(sk)->inet_sport = htons(port);
 		inet_ehash_nolisten(sk, (struct sock *)tw, NULL);
 	}
 	if (tw)
 		inet_twsk_bind_unhash(tw, hinfo);
+
+	spin_unlock(&head2->lock);
 	spin_unlock(&head->lock);
+
 	if (tw)
 		inet_twsk_deschedule_put(tw);
 	local_bh_enable();

net/ipv4/inet_timewait_sock.c

···
 void inet_twsk_bind_unhash(struct inet_timewait_sock *tw,
 			  struct inet_hashinfo *hashinfo)
 {
+	struct inet_bind2_bucket *tb2 = tw->tw_tb2;
 	struct inet_bind_bucket *tb = tw->tw_tb;
 
 	if (!tb)
···
 	__hlist_del(&tw->tw_bind_node);
 	tw->tw_tb = NULL;
 	inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb);
+
+	__hlist_del(&tw->tw_bind2_node);
+	tw->tw_tb2 = NULL;
+	inet_bind2_bucket_destroy(hashinfo->bind2_bucket_cachep, tb2);
+
 	__sock_put((struct sock *)tw);
 }
 
···
 {
 	struct inet_hashinfo *hashinfo = tw->tw_dr->hashinfo;
 	spinlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash);
-	struct inet_bind_hashbucket *bhead;
+	struct inet_bind_hashbucket *bhead, *bhead2;
 
 	spin_lock(lock);
 	sk_nulls_del_node_init_rcu((struct sock *)tw);
···
 	/* Disassociate with bind bucket. */
 	bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), tw->tw_num,
 			hashinfo->bhash_size)];
+	bhead2 = inet_bhashfn_portaddr(hashinfo, (struct sock *)tw,
+				       twsk_net(tw), tw->tw_num);
 
 	spin_lock(&bhead->lock);
+	spin_lock(&bhead2->lock);
 	inet_twsk_bind_unhash(tw, hashinfo);
+	spin_unlock(&bhead2->lock);
 	spin_unlock(&bhead->lock);
 
 	refcount_dec(&tw->tw_dr->tw_refcount);
···
 	hlist_add_head(&tw->tw_bind_node, list);
 }
 
+static void inet_twsk_add_bind2_node(struct inet_timewait_sock *tw,
+				     struct hlist_head *list)
+{
+	hlist_add_head(&tw->tw_bind2_node, list);
+}
+
 /*
  * Enter the time wait state. This is called with locally disabled BH.
  * Essentially we whip up a timewait bucket, copy the relevant info into it
···
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	struct inet_ehash_bucket *ehead = inet_ehash_bucket(hashinfo, sk->sk_hash);
 	spinlock_t *lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
-	struct inet_bind_hashbucket *bhead;
+	struct inet_bind_hashbucket *bhead, *bhead2;
+
 	/* Step 1: Put TW into bind hash. Original socket stays there too.
 	   Note, that any socket with inet->num != 0 MUST be bound in
 	   binding cache, even if it is closed.
 	 */
 	bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num,
 			hashinfo->bhash_size)];
+	bhead2 = inet_bhashfn_portaddr(hashinfo, sk, twsk_net(tw), inet->inet_num);
+
 	spin_lock(&bhead->lock);
+	spin_lock(&bhead2->lock);
+
 	tw->tw_tb = icsk->icsk_bind_hash;
 	WARN_ON(!icsk->icsk_bind_hash);
 	inet_twsk_add_bind_node(tw, &tw->tw_tb->owners);
+
+	tw->tw_tb2 = icsk->icsk_bind2_hash;
+	WARN_ON(!icsk->icsk_bind2_hash);
+	inet_twsk_add_bind2_node(tw, &tw->tw_tb2->deathrow);
+
+	spin_unlock(&bhead2->lock);
 	spin_unlock(&bhead->lock);
 
 	spin_lock(lock);

net/ipv4/tcp_ulp.c

···
 	if (sk->sk_socket)
 		clear_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags);
 
+	err = -EINVAL;
+	if (!ulp_ops->clone && sk->sk_state == TCP_LISTEN)
+		goto out_err;
+
 	err = ulp_ops->init(sk);
 	if (err)
 		goto out_err;

net/mptcp/protocol.c

···
 	set_bit(MPTCP_NOSPACE, &mptcp_sk(sk)->flags);
 }
 
+static int mptcp_disconnect(struct sock *sk, int flags);
+
 static int mptcp_sendmsg_fastopen(struct sock *sk, struct sock *ssk, struct msghdr *msg,
 				  size_t len, int *copied_syn)
 {
···
 	lock_sock(ssk);
 	msg->msg_flags |= MSG_DONTWAIT;
 	msk->connect_flags = O_NONBLOCK;
-	msk->is_sendmsg = 1;
+	msk->fastopening = 1;
 	ret = tcp_sendmsg_fastopen(ssk, msg, copied_syn, len, NULL);
-	msk->is_sendmsg = 0;
+	msk->fastopening = 0;
 	msg->msg_flags = saved_flags;
 	release_sock(ssk);
 
···
 		 */
 		if (ret && ret != -EINPROGRESS && ret != -ERESTARTSYS && ret != -EINTR)
 			*copied_syn = 0;
+	} else if (ret && ret != -EINPROGRESS) {
+		mptcp_disconnect(sk, 0);
 	}
 
 	return ret;
···
 		/* otherwise tcp will dispose of the ssk and subflow ctx */
 		if (ssk->sk_state == TCP_LISTEN) {
 			tcp_set_state(ssk, TCP_CLOSE);
-			mptcp_subflow_queue_clean(ssk);
+			mptcp_subflow_queue_clean(sk, ssk);
 			inet_csk_listen_stop(ssk);
 			mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED);
 		}
···
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
+	/* We are on the fastopen error path. We can't call straight into the
+	 * subflows cleanup code due to lock nesting (we are already under
+	 * msk->firstsocket lock). Do nothing and leave the cleanup to the
+	 * caller.
+	 */
+	if (msk->fastopening)
+		return 0;
+
 	inet_sk_state_store(sk, TCP_CLOSE);
 
 	mptcp_stop_timer(sk);
···
 	/* if reaching here via the fastopen/sendmsg path, the caller already
 	 * acquired the subflow socket lock, too.
 	 */
-	if (msk->is_sendmsg)
+	if (msk->fastopening)
 		err = __inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags, 1);
 	else
 		err = inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags);

net/mptcp/protocol.h

···
 	u8		recvmsg_inq:1,
 			cork:1,
 			nodelay:1,
-			is_sendmsg:1;
+			fastopening:1;
 	int		connect_flags;
 	struct work_struct work;
 	struct sk_buff  *ooo_last_skb;
···
 		     struct mptcp_subflow_context *subflow);
 void __mptcp_subflow_send_ack(struct sock *ssk);
 void mptcp_subflow_reset(struct sock *ssk);
-void mptcp_subflow_queue_clean(struct sock *ssk);
+void mptcp_subflow_queue_clean(struct sock *sk, struct sock *ssk);
 void mptcp_sock_graft(struct sock *sk, struct socket *parent);
 struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk);
 bool __mptcp_close(struct sock *sk, long timeout);

net/mptcp/subflow.c

···
 	}
 }
 
-void mptcp_subflow_queue_clean(struct sock *listener_ssk)
+void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk)
 {
 	struct request_sock_queue *queue = &inet_csk(listener_ssk)->icsk_accept_queue;
 	struct mptcp_sock *msk, *next, *head = NULL;
···
 
 		do_cancel_work = __mptcp_close(sk, 0);
 		release_sock(sk);
-		if (do_cancel_work)
+		if (do_cancel_work) {
+			/* lockdep will report a false positive ABBA deadlock
+			 * between cancel_work_sync and the listener socket.
+			 * The involved locks belong to different sockets WRT
+			 * the existing AB chain.
+			 * Using a per socket key is problematic as key
+			 * deregistration requires process context and must be
+			 * performed at socket disposal time, in atomic
+			 * context.
+			 * Just tell lockdep to consider the listener socket
+			 * released here.
+			 */
+			mutex_release(&listener_sk->sk_lock.dep_map, _RET_IP_);
 			mptcp_cancel_work(sk);
+			mutex_acquire(&listener_sk->sk_lock.dep_map,
+				      SINGLE_DEPTH_NESTING, 0, _RET_IP_);
+		}
 		sock_put(sk);
 	}
 

net/netfilter/ipset/ip_set_core.c

···
 		ret = set->variant->uadt(set, tb, adt, &lineno, flags, retried);
 		ip_set_unlock(set);
 		retried = true;
-	} while (ret == -EAGAIN &&
-		 set->variant->resize &&
-		 (ret = set->variant->resize(set, retried)) == 0);
+	} while (ret == -ERANGE ||
+		 (ret == -EAGAIN &&
+		  set->variant->resize &&
+		  (ret = set->variant->resize(set, retried)) == 0));
 
 	if (!ret || (ret == -IPSET_ERR_EXIST && eexist))
 		return 0;

net/netfilter/ipset/ip_set_hash_ip.c

···
 hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[],
 	      enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
 {
-	const struct hash_ip4 *h = set->data;
+	struct hash_ip4 *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_ip4_elem e = { 0 };
 	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
-	u32 ip = 0, ip_to = 0, hosts;
+	u32 ip = 0, ip_to = 0, hosts, i = 0;
 	int ret = 0;
 
 	if (tb[IPSET_ATTR_LINENO])
···
 
 	hosts = h->netmask == 32 ? 1 : 2 << (32 - h->netmask - 1);
 
-	/* 64bit division is not allowed on 32bit */
-	if (((u64)ip_to - ip + 1) >> (32 - h->netmask) > IPSET_MAX_RANGE)
-		return -ERANGE;
-
 	if (retried)
 		ip = ntohl(h->next.ip);
-	for (; ip <= ip_to;) {
+	for (; ip <= ip_to; i++) {
 		e.ip = htonl(ip);
+		if (i > IPSET_MAX_RANGE) {
+			hash_ip4_data_next(&h->next, &e);
+			return -ERANGE;
+		}
 		ret = adtfn(set, &e, &ext, &ext, flags);
 		if (ret && !ip_set_eexist(ret, flags))
 			return ret;

net/netfilter/ipset/ip_set_hash_ipmark.c

···
 hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[],
 		  enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
 {
-	const struct hash_ipmark4 *h = set->data;
+	struct hash_ipmark4 *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_ipmark4_elem e = { };
 	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
-	u32 ip, ip_to = 0;
+	u32 ip, ip_to = 0, i = 0;
 	int ret;
 
 	if (tb[IPSET_ATTR_LINENO])
···
 		ip_set_mask_from_to(ip, ip_to, cidr);
 	}
 
-	if (((u64)ip_to - ip + 1) > IPSET_MAX_RANGE)
-		return -ERANGE;
-
 	if (retried)
 		ip = ntohl(h->next.ip);
-	for (; ip <= ip_to; ip++) {
+	for (; ip <= ip_to; ip++, i++) {
 		e.ip = htonl(ip);
+		if (i > IPSET_MAX_RANGE) {
+			hash_ipmark4_data_next(&h->next, &e);
+			return -ERANGE;
+		}
 		ret = adtfn(set, &e, &ext, &ext, flags);
 
 		if (ret && !ip_set_eexist(ret, flags))

net/netfilter/ipset/ip_set_hash_ipport.c

···
 hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[],
 		  enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
 {
-	const struct hash_ipport4 *h = set->data;
+	struct hash_ipport4 *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_ipport4_elem e = { .ip = 0 };
 	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
-	u32 ip, ip_to = 0, p = 0, port, port_to;
+	u32 ip, ip_to = 0, p = 0, port, port_to, i = 0;
 	bool with_ports = false;
 	int ret;
 
···
 			swap(port, port_to);
 	}
 
-	if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE)
-		return -ERANGE;
-
 	if (retried)
 		ip = ntohl(h->next.ip);
 	for (; ip <= ip_to; ip++) {
 		p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port)
 						       : port;
-		for (; p <= port_to; p++) {
+		for (; p <= port_to; p++, i++) {
 			e.ip = htonl(ip);
 			e.port = htons(p);
+			if (i > IPSET_MAX_RANGE) {
+				hash_ipport4_data_next(&h->next, &e);
+				return -ERANGE;
+			}
 			ret = adtfn(set, &e, &ext, &ext, flags);
 
 			if (ret && !ip_set_eexist(ret, flags))

net/netfilter/ipset/ip_set_hash_ipportip.c

···
 hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[],
 		    enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
 {
-	const struct hash_ipportip4 *h = set->data;
+	struct hash_ipportip4 *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_ipportip4_elem e = { .ip = 0 };
 	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
-	u32 ip, ip_to = 0, p = 0, port, port_to;
+	u32 ip, ip_to = 0, p = 0, port, port_to, i = 0;
 	bool with_ports = false;
 	int ret;
 
···
 			swap(port, port_to);
 	}
 
-	if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE)
-		return -ERANGE;
-
 	if (retried)
 		ip = ntohl(h->next.ip);
 	for (; ip <= ip_to; ip++) {
 		p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port)
 						       : port;
-		for (; p <= port_to; p++) {
+		for (; p <= port_to; p++, i++) {
 			e.ip = htonl(ip);
 			e.port = htons(p);
+			if (i > IPSET_MAX_RANGE) {
+				hash_ipportip4_data_next(&h->next, &e);
+				return -ERANGE;
+			}
 			ret = adtfn(set, &e, &ext, &ext, flags);
 
 			if (ret && !ip_set_eexist(ret, flags))

net/netfilter/ipset/ip_set_hash_ipportnet.c

···
 hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
 		     enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
 {
-	const struct hash_ipportnet4 *h = set->data;
+	struct hash_ipportnet4 *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_ipportnet4_elem e = { .cidr = HOST_MASK - 1 };
 	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
 	u32 ip = 0, ip_to = 0, p = 0, port, port_to;
-	u32 ip2_from = 0, ip2_to = 0, ip2;
+	u32 ip2_from = 0, ip2_to = 0, ip2, i = 0;
 	bool with_ports = false;
 	u8 cidr;
 	int ret;
···
 			swap(port, port_to);
 	}
 
-	if (((u64)ip_to - ip + 1)*(port_to - port + 1) > IPSET_MAX_RANGE)
-		return -ERANGE;
-
 	ip2_to = ip2_from;
 	if (tb[IPSET_ATTR_IP2_TO]) {
 		ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2_TO], &ip2_to);
···
 		for (; p <= port_to; p++) {
 			e.port = htons(p);
 			do {
+				i++;
 				e.ip2 = htonl(ip2);
 				ip2 = ip_set_range_to_cidr(ip2, ip2_to, &cidr);
 				e.cidr = cidr - 1;
+				if (i > IPSET_MAX_RANGE) {
+					hash_ipportnet4_data_next(&h->next,
+								  &e);
+					return -ERANGE;
+				}
 				ret = adtfn(set, &e, &ext, &ext, flags);
 
 				if (ret && !ip_set_eexist(ret, flags))

net/netfilter/ipset/ip_set_hash_net.c

···
 hash_net4_uadt(struct ip_set *set, struct nlattr *tb[],
 	       enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
 {
-	const struct hash_net4 *h = set->data;
+	struct hash_net4 *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_net4_elem e = { .cidr = HOST_MASK };
 	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
-	u32 ip = 0, ip_to = 0, ipn, n = 0;
+	u32 ip = 0, ip_to = 0, i = 0;
 	int ret;
 
 	if (tb[IPSET_ATTR_LINENO])
···
 		if (ip + UINT_MAX == ip_to)
 			return -IPSET_ERR_HASH_RANGE;
 	}
-	ipn = ip;
-	do {
-		ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr);
-		n++;
-	} while (ipn++ < ip_to);
-
-	if (n > IPSET_MAX_RANGE)
-		return -ERANGE;
 
 	if (retried)
 		ip = ntohl(h->next.ip);
 	do {
+		i++;
 		e.ip = htonl(ip);
+		if (i > IPSET_MAX_RANGE) {
+			hash_net4_data_next(&h->next, &e);
+			return -ERANGE;
+		}
 		ip = ip_set_range_to_cidr(ip, ip_to, &e.cidr);
 		ret = adtfn(set, &e, &ext, &ext, flags);
 		if (ret && !ip_set_eexist(ret, flags))

net/netfilter/ipset/ip_set_hash_netiface.c

···
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_netiface4_elem e = { .cidr = HOST_MASK, .elem = 1 };
 	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
-	u32 ip = 0, ip_to = 0, ipn, n = 0;
+	u32 ip = 0, ip_to = 0, i = 0;
 	int ret;
 
 	if (tb[IPSET_ATTR_LINENO])
···
 	} else {
 		ip_set_mask_from_to(ip, ip_to, e.cidr);
 	}
-	ipn = ip;
-	do {
-		ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr);
-		n++;
-	} while (ipn++ < ip_to);
-
-	if (n > IPSET_MAX_RANGE)
-		return -ERANGE;
 
 	if (retried)
 		ip = ntohl(h->next.ip);
 	do {
+		i++;
 		e.ip = htonl(ip);
+		if (i > IPSET_MAX_RANGE) {
+			hash_netiface4_data_next(&h->next, &e);
+			return -ERANGE;
+		}
 		ip = ip_set_range_to_cidr(ip, ip_to, &e.cidr);
 		ret = adtfn(set, &e, &ext, &ext, flags);
 

net/netfilter/ipset/ip_set_hash_netnet.c

···
 hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[],
 		  enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
 {
-	const struct hash_netnet4 *h = set->data;
+	struct hash_netnet4 *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_netnet4_elem e = { };
 	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
 	u32 ip = 0, ip_to = 0;
-	u32 ip2 = 0, ip2_from = 0, ip2_to = 0, ipn;
-	u64 n = 0, m = 0;
+	u32 ip2 = 0, ip2_from = 0, ip2_to = 0, i = 0;
 	int ret;
 
 	if (tb[IPSET_ATTR_LINENO])
···
 	} else {
 		ip_set_mask_from_to(ip2_from, ip2_to, e.cidr[1]);
 	}
-	ipn = ip;
-	do {
-		ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr[0]);
-		n++;
-	} while (ipn++ < ip_to);
-	ipn = ip2_from;
-	do {
-		ipn = ip_set_range_to_cidr(ipn, ip2_to, &e.cidr[1]);
-		m++;
-	} while (ipn++ < ip2_to);
-
-	if (n*m > IPSET_MAX_RANGE)
-		return -ERANGE;
 
 	if (retried) {
 		ip = ntohl(h->next.ip[0]);
···
 		e.ip[0] = htonl(ip);
 		ip = ip_set_range_to_cidr(ip, ip_to, &e.cidr[0]);
 		do {
+			i++;
 			e.ip[1] = htonl(ip2);
+			if (i > IPSET_MAX_RANGE) {
+				hash_netnet4_data_next(&h->next, &e);
+				return -ERANGE;
+			}
 			ip2 = ip_set_range_to_cidr(ip2, ip2_to, &e.cidr[1]);
 			ret = adtfn(set, &e, &ext, &ext, flags);
 			if (ret && !ip_set_eexist(ret, flags))

net/netfilter/ipset/ip_set_hash_netport.c

···
 hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[],
 		   enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
 {
-	const struct hash_netport4 *h = set->data;
+	struct hash_netport4 *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_netport4_elem e = { .cidr = HOST_MASK - 1 };
 	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
-	u32 port, port_to, p = 0, ip = 0, ip_to = 0, ipn;
-	u64 n = 0;
+	u32 port, port_to, p = 0, ip = 0, ip_to = 0, i = 0;
 	bool with_ports = false;
 	u8 cidr;
 	int ret;
···
 	} else {
 		ip_set_mask_from_to(ip, ip_to, e.cidr + 1);
 	}
-	ipn = ip;
-	do {
-		ipn = ip_set_range_to_cidr(ipn, ip_to, &cidr);
-		n++;
-	} while (ipn++ < ip_to);
-
-	if (n*(port_to - port + 1) > IPSET_MAX_RANGE)
-		return -ERANGE;
 
 	if (retried) {
 		ip = ntohl(h->next.ip);
···
 		e.ip = htonl(ip);
 		ip = ip_set_range_to_cidr(ip, ip_to, &cidr);
 		e.cidr = cidr - 1;
-		for (; p <= port_to; p++) {
+		for (; p <= port_to; p++, i++) {
 			e.port = htons(p);
+			if (i > IPSET_MAX_RANGE) {
+				hash_netport4_data_next(&h->next, &e);
+				return -ERANGE;
+			}
 			ret = adtfn(set, &e, &ext, &ext, flags);
 			if (ret && !ip_set_eexist(ret, flags))
 				return ret;

net/netfilter/ipset/ip_set_hash_netportnet.c

···
 	return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags);
 }
 
+static u32
+hash_netportnet4_range_to_cidr(u32 from, u32 to, u8 *cidr)
+{
+	if (from == 0 && to == UINT_MAX) {
+		*cidr = 0;
+		return to;
+	}
+	return ip_set_range_to_cidr(from, to, cidr);
+}
+
 static int
 hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
 		      enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
 {
-	const struct hash_netportnet4 *h = set->data;
+	struct hash_netportnet4 *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_netportnet4_elem e = { };
 	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
 	u32 ip = 0, ip_to = 0, p = 0, port, port_to;
-	u32 ip2_from = 0, ip2_to = 0, ip2, ipn;
-	u64 n = 0, m = 0;
+	u32 ip2_from = 0, ip2_to = 0, ip2, i = 0;
 	bool with_ports = false;
 	int ret;
 
···
 	} else {
 		ip_set_mask_from_to(ip2_from, ip2_to, e.cidr[1]);
 	}
-	ipn = ip;
-	do {
-		ipn = ip_set_range_to_cidr(ipn, ip_to, &e.cidr[0]);
-		n++;
-	} while (ipn++ < ip_to);
-	ipn = ip2_from;
-	do {
-		ipn = ip_set_range_to_cidr(ipn, ip2_to, &e.cidr[1]);
-		m++;
-	} while (ipn++ < ip2_to);
-
-	if (n*m*(port_to - port + 1) > IPSET_MAX_RANGE)
-		return -ERANGE;
 
 	if (retried) {
 		ip = ntohl(h->next.ip[0]);
···
 
 	do {
 		e.ip[0] = htonl(ip);
-		ip = ip_set_range_to_cidr(ip, ip_to, &e.cidr[0]);
+		ip = hash_netportnet4_range_to_cidr(ip, ip_to, &e.cidr[0]);
 		for (; p <= port_to; p++) {
 			e.port = htons(p);
 			do {
+				i++;
 				e.ip[1] = htonl(ip2);
-				ip2 = ip_set_range_to_cidr(ip2, ip2_to,
-							   &e.cidr[1]);
+				if (i > IPSET_MAX_RANGE) {
+					hash_netportnet4_data_next(&h->next,
+								   &e);
+					return -ERANGE;
+				}
+				ip2 = hash_netportnet4_range_to_cidr(ip2,
+							ip2_to, &e.cidr[1]);
 				ret = adtfn(set, &e, &ext, &ext, flags);
 				if (ret && !ip_set_eexist(ret, flags))
 					return ret;

net/netfilter/nf_conntrack_proto.c

···
 	struct nf_conn *ct;
 	bool seqadj_needed;
 	__be16 frag_off;
+	int start;
 	u8 pnum;
 
 	ct = nf_ct_get(skb, &ctinfo);
···
 		break;
 	case NFPROTO_IPV6:
 		pnum = ipv6_hdr(skb)->nexthdr;
-		protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum, &frag_off);
-		if (protoff < 0 || (frag_off & htons(~0x7)) != 0)
+		start = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum, &frag_off);
+		if (start < 0 || (frag_off & htons(~0x7)) != 0)
 			return nf_conntrack_confirm(skb);
+
+		protoff = start;
 		break;
 	default:
 		return nf_conntrack_confirm(skb);

net/netfilter/nf_tables_api.c

···
 	return 0;
 }
 
-static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type,
-			     struct nft_set *set)
+static int __nft_trans_set_add(const struct nft_ctx *ctx, int msg_type,
+			       struct nft_set *set,
+			       const struct nft_set_desc *desc)
 {
 	struct nft_trans *trans;
 
···
 	if (trans == NULL)
 		return -ENOMEM;
 
-	if (msg_type == NFT_MSG_NEWSET && ctx->nla[NFTA_SET_ID] != NULL) {
+	if (msg_type == NFT_MSG_NEWSET && ctx->nla[NFTA_SET_ID] && !desc) {
 		nft_trans_set_id(trans) =
 			ntohl(nla_get_be32(ctx->nla[NFTA_SET_ID]));
 		nft_activate_next(ctx->net, set);
 	}
 	nft_trans_set(trans) = set;
+	if (desc) {
+		nft_trans_set_update(trans) = true;
+		nft_trans_set_gc_int(trans) = desc->gc_int;
+		nft_trans_set_timeout(trans) = desc->timeout;
+	}
 	nft_trans_commit_list_add_tail(ctx->net, trans);
 
 	return 0;
+}
+
+static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type,
+			     struct nft_set *set)
+{
+	return __nft_trans_set_add(ctx, msg_type, set, NULL);
 }
 
 static int nft_delset(const struct nft_ctx *ctx, struct nft_set *set)
···
 static const struct nft_set_ops *
 nft_select_set_ops(const struct nft_ctx *ctx,
 		   const struct nlattr * const nla[],
-		   const struct nft_set_desc *desc,
-		   enum nft_set_policies policy)
+		   const struct nft_set_desc *desc)
 {
 	struct nftables_pernet *nft_net = nft_pernet(ctx->net);
 	const struct nft_set_ops *ops, *bops;
···
 		if (!ops->estimate(desc, flags, &est))
 			continue;
 
-		switch (policy) {
+		switch (desc->policy) {
 		case NFT_SET_POL_PERFORMANCE:
 			if (est.lookup < best.lookup)
 				break;
···
 static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
 			      const struct nft_set *set, u16 event, u16 flags)
 {
-	struct nlmsghdr *nlh;
+	u64 timeout = READ_ONCE(set->timeout);
+	u32 gc_int = READ_ONCE(set->gc_int);
 	u32 portid = ctx->portid;
+	struct nlmsghdr *nlh;
 	struct nlattr *nest;
 	u32 seq = ctx->seq;
 	int i;
···
 	    nla_put_be32(skb, NFTA_SET_OBJ_TYPE, htonl(set->objtype)))
 		goto nla_put_failure;
 
-	if (set->timeout &&
+	if (timeout &&
 	    nla_put_be64(skb, NFTA_SET_TIMEOUT,
-			 nf_jiffies64_to_msecs(set->timeout),
+			 nf_jiffies64_to_msecs(timeout),
 			 NFTA_SET_PAD))
 		goto nla_put_failure;
-	if (set->gc_int &&
-	    nla_put_be32(skb, NFTA_SET_GC_INTERVAL, htonl(set->gc_int)))
+	if (gc_int &&
+	    nla_put_be32(skb, NFTA_SET_GC_INTERVAL, htonl(gc_int)))
 		goto nla_put_failure;
 
 	if (set->policy != NFT_SET_POL_PERFORMANCE) {
···
 	return err;
 }
 
+static int nft_set_expr_alloc(struct nft_ctx *ctx, struct nft_set *set,
+			      const struct nlattr * const *nla,
+			      struct nft_expr **exprs, int *num_exprs,
+			      u32 flags)
+{
+	struct nft_expr *expr;
+	int err, i;
+
+	if (nla[NFTA_SET_EXPR]) {
+		expr = nft_set_elem_expr_alloc(ctx, set, nla[NFTA_SET_EXPR]);
+		if (IS_ERR(expr)) {
+			err = PTR_ERR(expr);
+			goto err_set_expr_alloc;
+		}
+		exprs[0] = expr;
+		(*num_exprs)++;
+	} else if (nla[NFTA_SET_EXPRESSIONS]) {
+		struct nlattr *tmp;
+		int left;
+
+		if (!(flags & NFT_SET_EXPR)) {
+			err = -EINVAL;
+			goto err_set_expr_alloc;
+		}
+		i = 0;
+		nla_for_each_nested(tmp, nla[NFTA_SET_EXPRESSIONS], left) {
+			if (i == NFT_SET_EXPR_MAX) {
+				err = -E2BIG;
+				goto err_set_expr_alloc;
+			}
+			if (nla_type(tmp) != NFTA_LIST_ELEM) {
+				err = -EINVAL;
+				goto err_set_expr_alloc;
+			}
+			expr = nft_set_elem_expr_alloc(ctx, set, tmp);
+			if (IS_ERR(expr)) {
+				err = PTR_ERR(expr);
+				goto err_set_expr_alloc;
+			}
+			exprs[i++] = expr;
+			(*num_exprs)++;
+		}
+	}
+
+	return 0;
+
+err_set_expr_alloc:
+	for (i = 0; i < *num_exprs; i++)
+		nft_expr_destroy(ctx, exprs[i]);
+
+	return err;
+}
+
+static bool nft_set_is_same(const struct nft_set *set,
+			    const struct nft_set_desc *desc,
+			    struct nft_expr *exprs[], u32 num_exprs, u32 flags)
+{
+	int i;
+
+	if (set->ktype != desc->ktype ||
+	    set->dtype != desc->dtype ||
+	    set->flags != flags ||
+	    set->klen != desc->klen ||
+	    set->dlen != desc->dlen ||
+	    set->field_count != desc->field_count ||
+	    set->num_exprs != num_exprs)
+		return false;
+
+	for (i = 0; i < desc->field_count; i++) {
+		if (set->field_len[i] != desc->field_len[i])
+			return false;
+	}
+
+	for (i = 0; i < num_exprs; i++) {
+		if (set->exprs[i]->ops != exprs[i]->ops)
+			return false;
+	}
+
+	return true;
+}
+
 static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
 			    const struct nlattr * const nla[])
 {
-	u32 ktype, dtype, flags, policy, gc_int, objtype;
 	struct netlink_ext_ack *extack = info->extack;
 	u8 genmask = nft_genmask_next(info->net);
 	u8 family = info->nfmsg->nfgen_family;
 	const struct nft_set_ops *ops;
-	struct nft_expr *expr = NULL;
 	struct net *net = info->net;
 	struct nft_set_desc desc;
 	struct nft_table *table;
···
 	struct nft_set *set;
 	struct nft_ctx ctx;
 	size_t alloc_size;
-	u64 timeout;
+	int num_exprs = 0;
 	char *name;
 	int err, i;
 	u16 udlen;
+	u32 flags;
 	u64 size;
 
 	if (nla[NFTA_SET_TABLE] == NULL ||
···
 
 	memset(&desc, 0, sizeof(desc));
 
-	ktype = NFT_DATA_VALUE;
+	desc.ktype = NFT_DATA_VALUE;
 	if (nla[NFTA_SET_KEY_TYPE] != NULL) {
-		ktype = ntohl(nla_get_be32(nla[NFTA_SET_KEY_TYPE]));
-		if ((ktype & NFT_DATA_RESERVED_MASK) == NFT_DATA_RESERVED_MASK)
+		desc.ktype = ntohl(nla_get_be32(nla[NFTA_SET_KEY_TYPE]));
+		if ((desc.ktype & NFT_DATA_RESERVED_MASK) == NFT_DATA_RESERVED_MASK)
 			return -EINVAL;
 	}
 
···
 			return -EOPNOTSUPP;
 	}
 
-	dtype = 0;
+	desc.dtype = 0;
 	if (nla[NFTA_SET_DATA_TYPE] != NULL) {
 		if (!(flags & NFT_SET_MAP))
 			return -EINVAL;
 
-		dtype = ntohl(nla_get_be32(nla[NFTA_SET_DATA_TYPE]));
-		if ((dtype & NFT_DATA_RESERVED_MASK) == NFT_DATA_RESERVED_MASK &&
-		    dtype != NFT_DATA_VERDICT)
+		desc.dtype = ntohl(nla_get_be32(nla[NFTA_SET_DATA_TYPE]));
+		if ((desc.dtype & NFT_DATA_RESERVED_MASK) == NFT_DATA_RESERVED_MASK &&
+		    desc.dtype != NFT_DATA_VERDICT)
 			return -EINVAL;
 
-		if (dtype != NFT_DATA_VERDICT) {
+		if (desc.dtype != NFT_DATA_VERDICT) {
 			if (nla[NFTA_SET_DATA_LEN] == NULL)
 				return -EINVAL;
 			desc.dlen = ntohl(nla_get_be32(nla[NFTA_SET_DATA_LEN]));
···
 		if (!(flags & NFT_SET_OBJECT))
 			return -EINVAL;
 
-		objtype = ntohl(nla_get_be32(nla[NFTA_SET_OBJ_TYPE]));
-		if (objtype == NFT_OBJECT_UNSPEC ||
-		    objtype > NFT_OBJECT_MAX)
+		desc.objtype = ntohl(nla_get_be32(nla[NFTA_SET_OBJ_TYPE]));
+		if (desc.objtype == NFT_OBJECT_UNSPEC ||
+		    desc.objtype > NFT_OBJECT_MAX)
 			return -EOPNOTSUPP;
 	} else if (flags & NFT_SET_OBJECT)
 		return -EINVAL;
 	else
-		objtype = NFT_OBJECT_UNSPEC;
+		desc.objtype = NFT_OBJECT_UNSPEC;
 
-	timeout = 0;
+	desc.timeout = 0;
 	if (nla[NFTA_SET_TIMEOUT] != NULL) {
 		if (!(flags & NFT_SET_TIMEOUT))
 			return -EINVAL;
 
-		err = nf_msecs_to_jiffies64(nla[NFTA_SET_TIMEOUT], &timeout);
+		err = nf_msecs_to_jiffies64(nla[NFTA_SET_TIMEOUT], &desc.timeout);
 		if (err)
 			return err;
 	}
-	gc_int = 0;
+	desc.gc_int = 0;
 	if (nla[NFTA_SET_GC_INTERVAL] != NULL) {
 		if (!(flags & NFT_SET_TIMEOUT))
 			return -EINVAL;
-		gc_int = ntohl(nla_get_be32(nla[NFTA_SET_GC_INTERVAL]));
+		desc.gc_int = ntohl(nla_get_be32(nla[NFTA_SET_GC_INTERVAL]));
 	}
 
-	policy = NFT_SET_POL_PERFORMANCE;
+	desc.policy = NFT_SET_POL_PERFORMANCE;
 	if (nla[NFTA_SET_POLICY] != NULL)
-		policy = ntohl(nla_get_be32(nla[NFTA_SET_POLICY]));
+		desc.policy = ntohl(nla_get_be32(nla[NFTA_SET_POLICY]));
 
 	if (nla[NFTA_SET_DESC] != NULL) {
 		err = nf_tables_set_desc_parse(&desc, nla[NFTA_SET_DESC]);
···
 			return PTR_ERR(set);
 		}
 	} else {
+		struct nft_expr *exprs[NFT_SET_EXPR_MAX] = {};
+
 		if (info->nlh->nlmsg_flags & NLM_F_EXCL) {
 			NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]);
 			return -EEXIST;
···
 		if (info->nlh->nlmsg_flags & NLM_F_REPLACE)
 			return -EOPNOTSUPP;
 
-		return 0;
+		err = nft_set_expr_alloc(&ctx, set, nla, exprs, &num_exprs, flags);
+		if (err < 0)
+			return err;
+
+		err = 0;
+		if (!nft_set_is_same(set, &desc, exprs, num_exprs, flags)) {
+			NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]);
+			err = -EEXIST;
+		}
+
+		for (i = 0; i < num_exprs; i++)
+			nft_expr_destroy(&ctx, exprs[i]);
+
+		if (err < 0)
+			return err;
+
+		return __nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set, &desc);
 	}
 
 	if (!(info->nlh->nlmsg_flags & NLM_F_CREATE))
 		return -ENOENT;
 
-	ops = nft_select_set_ops(&ctx, nla, &desc, policy);
+	ops = nft_select_set_ops(&ctx, nla, &desc);
 	if (IS_ERR(ops))
 		return PTR_ERR(ops);
 
···
 	set->table = table;
 	write_pnet(&set->net, net);
 	set->ops = ops;
-	set->ktype = ktype;
+	set->ktype = desc.ktype;
 	set->klen = desc.klen;
-	set->dtype = dtype;
-	set->objtype = objtype;
+	set->dtype = desc.dtype;
+	set->objtype = desc.objtype;
 	set->dlen = desc.dlen;
 	set->flags = flags;
 	set->size = desc.size;
-	set->policy = policy;
+	set->policy = desc.policy;
 	set->udlen = udlen;
 	set->udata = udata;
-	set->timeout = timeout;
-	set->gc_int = gc_int;
+	set->timeout = desc.timeout;
+	set->gc_int = desc.gc_int;
 
 	set->field_count = desc.field_count;
 	for (i = 0; i < desc.field_count; i++)
···
 	if (err < 0)
 		goto err_set_init;
 
-	if (nla[NFTA_SET_EXPR]) {
-		expr = nft_set_elem_expr_alloc(&ctx, set, nla[NFTA_SET_EXPR]);
-		if (IS_ERR(expr)) {
-			err = PTR_ERR(expr);
-			goto err_set_expr_alloc;
-		}
-		set->exprs[0] = expr;
-		set->num_exprs++;
-	} else if (nla[NFTA_SET_EXPRESSIONS]) {
-		struct nft_expr *expr;
-		struct nlattr *tmp;
-		int left;
+	err = nft_set_expr_alloc(&ctx, set, nla, set->exprs, &num_exprs, flags);
+	if (err < 0)
+		goto err_set_destroy;
 
-		if (!(flags & NFT_SET_EXPR)) {
-			err = -EINVAL;
-			goto err_set_expr_alloc;
-		}
-		i = 0;
-		nla_for_each_nested(tmp, nla[NFTA_SET_EXPRESSIONS], left) {
-			if (i == NFT_SET_EXPR_MAX) {
-				err = -E2BIG;
-				goto err_set_expr_alloc;
-			}
-			if (nla_type(tmp) != NFTA_LIST_ELEM) {
-				err = -EINVAL;
-				goto err_set_expr_alloc;
-			}
-			expr = nft_set_elem_expr_alloc(&ctx, set, tmp);
-			if (IS_ERR(expr)) {
-				err = PTR_ERR(expr);
-				goto err_set_expr_alloc;
-			}
-			set->exprs[i++] = expr;
-			set->num_exprs++;
-		}
-	}
-
+	set->num_exprs = num_exprs;
 	set->handle = nf_tables_alloc_handle(table);
 
 	err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set);
···
 err_set_expr_alloc:
 	for (i = 0; i < set->num_exprs; i++)
 		nft_expr_destroy(&ctx, set->exprs[i]);
-
+err_set_destroy:
 	ops->destroy(set);
 err_set_init:
 	kfree(set->name);
···
 			return err;
 	} else if (set->flags & NFT_SET_TIMEOUT &&
 		   !(flags & NFT_SET_ELEM_INTERVAL_END)) {
-		timeout = set->timeout;
+		timeout = READ_ONCE(set->timeout);
 	}
 
 	expiration = 0;
···
 		if (err < 0)
 			goto err_parse_key_end;
 
-		if (timeout != set->timeout) {
+		if (timeout != READ_ONCE(set->timeout)) {
 			err = nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT);
 			if (err < 0)
 				goto err_parse_key_end;
···
 				nft_flow_rule_destroy(nft_trans_flow_rule(trans));
 			break;
 		case NFT_MSG_NEWSET:
-			nft_clear(net, nft_trans_set(trans));
-			/* This avoids hitting -EBUSY when deleting the table
-			 * from the transaction.
-			 */
-			if (nft_set_is_anonymous(nft_trans_set(trans)) &&
-			    !list_empty(&nft_trans_set(trans)->bindings))
-				trans->ctx.table->use--;
+			if (nft_trans_set_update(trans)) {
+				struct nft_set *set = nft_trans_set(trans);
 
+				WRITE_ONCE(set->timeout, nft_trans_set_timeout(trans));
+				WRITE_ONCE(set->gc_int, nft_trans_set_gc_int(trans));
+			} else {
+				nft_clear(net, nft_trans_set(trans));
+				/* This avoids hitting -EBUSY when deleting the table
+				 * from the transaction.
+				 */
+				if (nft_set_is_anonymous(nft_trans_set(trans)) &&
+				    !list_empty(&nft_trans_set(trans)->bindings))
+					trans->ctx.table->use--;
+			}
 			nf_tables_set_notify(&trans->ctx, nft_trans_set(trans),
 					     NFT_MSG_NEWSET, GFP_KERNEL);
 			nft_trans_destroy(trans);
···
 			nft_trans_destroy(trans);
 			break;
 		case NFT_MSG_NEWSET:
+			if (nft_trans_set_update(trans)) {
+				nft_trans_destroy(trans);
+				break;
+			}
 			trans->ctx.table->use--;
 			if (nft_trans_set_bound(trans)) {
 				nft_trans_destroy(trans);

net/nfc/netlink.c

···
 	u32 dev_idx, se_idx;
 	u8 *apdu;
 	size_t apdu_len;
+	int rc;
 
 	if (!info->attrs[NFC_ATTR_DEVICE_INDEX] ||
 	    !info->attrs[NFC_ATTR_SE_INDEX] ||
···
 	if (!dev)
 		return -ENODEV;
 
-	if (!dev->ops || !dev->ops->se_io)
-		return -ENOTSUPP;
+	if (!dev->ops || !dev->ops->se_io) {
+		rc = -EOPNOTSUPP;
+		goto put_dev;
+	}
 
 	apdu_len = nla_len(info->attrs[NFC_ATTR_SE_APDU]);
-	if (apdu_len == 0)
-		return -EINVAL;
+	if (apdu_len == 0) {
+		rc = -EINVAL;
+		goto put_dev;
+	}
 
 	apdu = nla_data(info->attrs[NFC_ATTR_SE_APDU]);
-	if (!apdu)
-		return -EINVAL;
+	if (!apdu) {
+		rc = -EINVAL;
+		goto put_dev;
+	}
 
 	ctx = kzalloc(sizeof(struct se_io_ctx), GFP_KERNEL);
-	if (!ctx)
-		return -ENOMEM;
+	if (!ctx) {
+		rc = -ENOMEM;
+		goto put_dev;
+	}
 
 	ctx->dev_idx = dev_idx;
 	ctx->se_idx = se_idx;
 
-	return nfc_se_io(dev, se_idx, apdu, apdu_len, se_io_cb, ctx);
+	rc = nfc_se_io(dev, se_idx, apdu, apdu_len, se_io_cb, ctx);
+
+put_dev:
+	nfc_put_device(dev);
+	return rc;
 }
 
 static int nfc_genl_vendor_cmd(struct sk_buff *skb,
···
 	subcmd = nla_get_u32(info->attrs[NFC_ATTR_VENDOR_SUBCMD]);
 
 	dev = nfc_get_device(dev_idx);
-	if (!dev || !dev->vendor_cmds || !dev->n_vendor_cmds)
+	if (!dev)
 		return -ENODEV;
+
+	if (!dev->vendor_cmds || !dev->n_vendor_cmds) {
+		err = -ENODEV;
+		goto put_dev;
+	}
 
 	if (info->attrs[NFC_ATTR_VENDOR_DATA]) {
 		data = nla_data(info->attrs[NFC_ATTR_VENDOR_DATA]);
 		data_len = nla_len(info->attrs[NFC_ATTR_VENDOR_DATA]);
-		if (data_len == 0)
-			return -EINVAL;
+		if (data_len == 0) {
+			err = -EINVAL;
+			goto put_dev;
+		}
 	} else {
 		data = NULL;
 		data_len = 0;
···
 		dev->cur_cmd_info = info;
 		err = cmd->doit(dev, data, data_len);
 		dev->cur_cmd_info = NULL;
-		return err;
+		goto put_dev;
 	}
 
-	return -EOPNOTSUPP;
+	err = -EOPNOTSUPP;
+
+put_dev:
+	nfc_put_device(dev);
+	return err;
 }
 
 /* message building helper */

net/openvswitch/datapath.c

···
 	vport->upcall_stats = netdev_alloc_pcpu_stats(struct vport_upcall_stats_percpu);
 	if (!vport->upcall_stats) {
 		err = -ENOMEM;
-		goto err_destroy_portids;
+		goto err_destroy_vport;
 	}
 
 	err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid,
···
 	ovs_notify(&dp_datapath_genl_family, reply, info);
 	return 0;
 
+err_destroy_vport:
+	ovs_dp_detach_port(vport);
 err_destroy_portids:
 	kfree(rcu_dereference_raw(dp->upcall_portids));
 err_unlock_and_destroy_meters:
···
 	vport->upcall_stats = netdev_alloc_pcpu_stats(struct vport_upcall_stats_percpu);
 	if (!vport->upcall_stats) {
 		err = -ENOMEM;
-		goto exit_unlock_free;
+		goto exit_unlock_free_vport;
 	}
 
 	err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info),
···
 	ovs_notify(&dp_vport_genl_family, reply, info);
 	return 0;
 
+exit_unlock_free_vport:
+	ovs_dp_detach_port(vport);
 exit_unlock_free:
 	ovs_unlock();
 	kfree_skb(reply);

net/rxrpc/recvmsg.c

···
 	struct rxrpc_call *call;
 	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
 	struct list_head *l;
+	unsigned int call_debug_id = 0;
 	size_t copied = 0;
 	long timeo;
 	int ret;
 
 	DEFINE_WAIT(wait);
 
-	trace_rxrpc_recvmsg(NULL, rxrpc_recvmsg_enter, 0);
+	trace_rxrpc_recvmsg(0, rxrpc_recvmsg_enter, 0);
 
 	if (flags & (MSG_OOB | MSG_TRUNC))
 		return -EOPNOTSUPP;
···
 		if (list_empty(&rx->recvmsg_q)) {
 			if (signal_pending(current))
 				goto wait_interrupted;
-			trace_rxrpc_recvmsg(NULL, rxrpc_recvmsg_wait, 0);
+			trace_rxrpc_recvmsg(0, rxrpc_recvmsg_wait, 0);
 			timeo = schedule_timeout(timeo);
 		}
 		finish_wait(sk_sleep(&rx->sk), &wait);
···
 		rxrpc_get_call(call, rxrpc_call_get_recvmsg);
 	write_unlock(&rx->recvmsg_lock);
 
-	trace_rxrpc_recvmsg(call, rxrpc_recvmsg_dequeue, 0);
+	call_debug_id = call->debug_id;
+	trace_rxrpc_recvmsg(call_debug_id, rxrpc_recvmsg_dequeue, 0);
 
 	/* We're going to drop the socket lock, so we need to lock the call
 	 * against interference by sendmsg.
···
 error_unlock_call:
 	mutex_unlock(&call->user_mutex);
 	rxrpc_put_call(call, rxrpc_call_put_recvmsg);
-	trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, ret);
+	trace_rxrpc_recvmsg(call_debug_id, rxrpc_recvmsg_return, ret);
 	return ret;
 
 error_requeue_call:
···
 		write_lock(&rx->recvmsg_lock);
 		list_add(&call->recvmsg_link, &rx->recvmsg_q);
 		write_unlock(&rx->recvmsg_lock);
-		trace_rxrpc_recvmsg(call, rxrpc_recvmsg_requeue, 0);
+		trace_rxrpc_recvmsg(call_debug_id, rxrpc_recvmsg_requeue, 0);
 	} else {
 		rxrpc_put_call(call, rxrpc_call_put_recvmsg);
 	}
 error_no_call:
 	release_sock(&rx->sk);
 error_trace:
-	trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, ret);
+	trace_rxrpc_recvmsg(call_debug_id, rxrpc_recvmsg_return, ret);
 	return ret;
 
 wait_interrupted:

net/sched/cls_tcindex.c

···
 		  struct tcindex_filter_result *r, struct nlattr **tb,
 		  struct nlattr *est, u32 flags, struct netlink_ext_ack *extack)
 {
-	struct tcindex_filter_result new_filter_result, *old_r = r;
+	struct tcindex_filter_result new_filter_result;
 	struct tcindex_data *cp = NULL, *oldp;
 	struct tcindex_filter *f = NULL; /* make gcc behave */
 	struct tcf_result cr = {};
···
 	err = tcindex_filter_result_init(&new_filter_result, cp, net);
 	if (err < 0)
 		goto errout_alloc;
-	if (old_r)
+	if (r)
 		cr = r->res;
 
 	err = -EBUSY;
···
 	if (tb[TCA_TCINDEX_CLASSID]) {
 		cr.classid = nla_get_u32(tb[TCA_TCINDEX_CLASSID]);
 		tcf_bind_filter(tp, &cr, base);
-	}
-
-	if (old_r && old_r != r) {
-		err = tcindex_filter_result_init(old_r, cp, net);
-		if (err < 0) {
-			kfree(f);
-			goto errout_alloc;
-		}
 	}
 
 	oldp = p;

net/sched/sch_atm.c

···
 				result = tcf_classify(skb, NULL, fl, &res, true);
 				if (result < 0)
 					continue;
+				if (result == TC_ACT_SHOT)
+					goto done;
+
 				flow = (struct atm_flow_data *)res.class;
 				if (!flow)
 					flow = lookup_flow(sch, res.classid);
-				goto done;
+				goto drop;
 			}
 		}
 		flow = NULL;

net/sched/sch_cbq.c

···
 		result = tcf_classify(skb, NULL, fl, &res, true);
 		if (!fl || result < 0)
 			goto fallback;
+		if (result == TC_ACT_SHOT)
+			return NULL;
 
 		cl = (void *)res.class;
 		if (!cl) {
···
 		case TC_ACT_TRAP:
 			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
 			fallthrough;
-		case TC_ACT_SHOT:
-			return NULL;
 		case TC_ACT_RECLASSIFY:
 			return cbq_reclassify(skb, cl);
 		}

net/sched/sch_htb.c

···
 {
 	return (unsigned long)htb_find(handle, sch);
 }
+
+#define HTB_DIRECT ((struct htb_class *)-1L)
+
 /**
  * htb_classify - classify a packet into class
+ * @skb: the socket buffer
+ * @sch: the active queue discipline
+ * @qerr: pointer for returned status code
  *
  * It returns NULL if the packet should be dropped or -1 if the packet
  * should be passed directly thru. In all other cases leaf class is returned.
···
  * have no valid leaf we try to use MAJOR:default leaf. It still unsuccessful
  * then finish and return direct queue.
  */
-#define HTB_DIRECT ((struct htb_class *)-1L)
-
 static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch,
 				      int *qerr)
 {

net/sunrpc/auth_gss/auth_gss.c

···
 	list_for_each_entry(pos, &pipe->in_downcall, list) {
 		if (!uid_eq(pos->uid, uid))
 			continue;
-		if (auth && pos->auth->service != auth->service)
+		if (pos->auth->service != auth->service)
 			continue;
 		refcount_inc(&pos->count);
 		return pos;
···
 	return err;
 }
 
+static struct gss_upcall_msg *
+gss_find_downcall(struct rpc_pipe *pipe, kuid_t uid)
+{
+	struct gss_upcall_msg *pos;
+	list_for_each_entry(pos, &pipe->in_downcall, list) {
+		if (!uid_eq(pos->uid, uid))
+			continue;
+		if (!rpc_msg_is_inflight(&pos->msg))
+			continue;
+		refcount_inc(&pos->count);
+		return pos;
+	}
+	return NULL;
+}
+
 #define MSG_BUF_MAXSIZE 1024
 
 static ssize_t
···
 	err = -ENOENT;
 	/* Find a matching upcall */
 	spin_lock(&pipe->lock);
-	gss_msg = __gss_find_upcall(pipe, uid, NULL);
+	gss_msg = gss_find_downcall(pipe, uid);
 	if (gss_msg == NULL) {
 		spin_unlock(&pipe->lock);
 		goto err_put_ctx;

scripts/Makefile.modpost

···
 	$(if $(CONFIG_MODVERSIONS),-m)							\
 	$(if $(CONFIG_MODULE_SRCVERSION_ALL),-a)					\
 	$(if $(CONFIG_SECTION_MISMATCH_WARN_ONLY),,-E)					\
+	$(if $(KBUILD_MODPOST_WARN),-w)							\
 	$(if $(KBUILD_NSDEPS),-d $(MODULES_NSDEPS))					\
 	$(if $(CONFIG_MODULE_ALLOW_MISSING_NAMESPACE_IMPORTS)$(KBUILD_NSDEPS),-N)	\
 	-o $@
···
 # 'make -i -k' ignores compile errors, and builds as many modules as possible.
 ifneq ($(findstring i,$(filter-out --%,$(MAKEFLAGS))),)
 modpost-args += -n
+endif
+
+# Read out modules.order to pass in modpost.
+# Otherwise, allmodconfig would fail with "Argument list too long".
+ifdef KBUILD_MODULES
+modpost-args += -T $(MODORDER)
+modpost-deps += $(MODORDER)
 endif
 
 ifeq ($(KBUILD_EXTMOD),)
···
 
 endif # ($(KBUILD_EXTMOD),)
 
-ifneq ($(KBUILD_MODPOST_WARN)$(missing-input),)
+ifneq ($(missing-input),)
 modpost-args += -w
 endif
 
-ifdef KBUILD_MODULES
-modpost-args += -T $(MODORDER)
-modpost-deps += $(MODORDER)
-endif
-
-# Read out modules.order to pass in modpost.
-# Otherwise, allmodconfig would fail with "Argument list too long".
 quiet_cmd_modpost = MODPOST $@
       cmd_modpost = \
 	$(if $(missing-input), \

scripts/Makefile.package

···
 PHONY += help
 help:
 	@echo '  rpm-pkg             - Build both source and binary RPM kernel packages'
+	@echo '  srcrpm-pkg          - Build only the source kernel RPM package'
 	@echo '  binrpm-pkg          - Build only the binary kernel RPM package'
 	@echo '  deb-pkg             - Build both source and binary deb kernel packages'
 	@echo '  bindeb-pkg          - Build only the binary kernel deb package'

scripts/basic/fixdep.c

···
 #include <unistd.h>
 #include <fcntl.h>
 #include <string.h>
-#include <stdarg.h>
 #include <stdlib.h>
 #include <stdio.h>
 #include <ctype.h>

scripts/kconfig/mconf.c

···
 "(especially with a larger number of unrolled categories) than the\n"
 "default mode.\n"
 "\n"
+
+"Search\n"
+"-------\n"
+"Pressing the forward-slash (/) anywhere brings up a search dialog box.\n"
+"\n"
+
 "Different color themes available\n"
 "--------------------------------\n"
 "It is possible to select different color themes using the variable\n"

scripts/package/mkspec

···
 	URL: https://www.kernel.org
 $S	Source: kernel-$__KERNELRELEASE.tar.gz
 	Provides: $PROVIDES
-$S	BuildRequires: bc binutils bison dwarves elfutils-libelf-devel flex
+$S	BuildRequires: bc binutils bison dwarves
+$S	BuildRequires: (elfutils-libelf-devel or libelf-devel) flex
 $S	BuildRequires: gcc make openssl openssl-devel perl python3 rsync
 
 	# $UTS_MACHINE as a fallback of _arch in case

sound/pci/hda/patch_hdmi.c

···
 	struct hdmi_ops ops;
 
 	bool dyn_pin_out;
+	bool static_pcm_mapping;
 	/* hdmi interrupt trigger control flag for Nvidia codec */
 	bool hdmi_intr_trig_ctrl;
 	bool nv_dp_workaround; /* workaround DP audio infoframe for Nvidia */
···
 	 */
 	pcm_jack = pin_idx_to_pcm_jack(codec, per_pin);
 
-	if (eld->eld_valid) {
-		hdmi_attach_hda_pcm(spec, per_pin);
-		hdmi_pcm_setup_pin(spec, per_pin);
-	} else {
-		hdmi_pcm_reset_pin(spec, per_pin);
-		hdmi_detach_hda_pcm(spec, per_pin);
+	if (!spec->static_pcm_mapping) {
+		if (eld->eld_valid) {
+			hdmi_attach_hda_pcm(spec, per_pin);
+			hdmi_pcm_setup_pin(spec, per_pin);
+		} else {
+			hdmi_pcm_reset_pin(spec, per_pin);
+			hdmi_detach_hda_pcm(spec, per_pin);
+		}
 	}
+
 	/* if pcm_idx == -1, it means this is in monitor connection event
 	 * we can get the correct pcm_idx now.
 	 */
···
 	struct hdmi_spec *spec = codec->spec;
 	int idx, pcm_num;
 
-	/* limit the PCM devices to the codec converters */
-	pcm_num = spec->num_cvts;
+	/* limit the PCM devices to the codec converters or available PINs */
+	pcm_num = min(spec->num_cvts, spec->num_pins);
 	codec_dbg(codec, "hdmi: pcm_num set to %d\n", pcm_num);
 
 	for (idx = 0; idx < pcm_num; idx++) {
···
 	for (pin_idx = 0; pin_idx < spec->num_pins; pin_idx++) {
 		struct hdmi_spec_per_pin *per_pin = get_pin(spec, pin_idx);
 		struct hdmi_eld *pin_eld = &per_pin->sink_eld;
+
+		if (spec->static_pcm_mapping) {
+			hdmi_attach_hda_pcm(spec, per_pin);
+			hdmi_pcm_setup_pin(spec, per_pin);
+		}
 
 		pin_eld->eld_valid = false;
 		hdmi_present_sense(per_pin, 0);
···
 	codec->patch_ops.init = atihdmi_init;
 
 	spec = codec->spec;
+
+	spec->static_pcm_mapping = true;
 
 	spec->ops.pin_get_eld = atihdmi_pin_get_eld;
 	spec->ops.pin_setup_infoframe = atihdmi_pin_setup_infoframe;

sound/pci/hda/patch_realtek.c

···
 	ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK,
 	ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN,
 	ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS,
+	ALC236_FIXUP_DELL_DUAL_CODECS,
 };
 
 /* A special fixup for Lenovo C940 and Yoga Duet 7;
···
 		.chained = true,
 		.chain_id = ALC269_FIXUP_DELL4_MIC_NO_PRESENCE,
 	},
+	[ALC236_FIXUP_DELL_DUAL_CODECS] = {
+		.type = HDA_FIXUP_PINS,
+		.v.func = alc1220_fixup_gb_dual_codecs,
+		.chained = true,
+		.chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+	},
 };
 
 static const struct snd_pci_quirk alc269_fixup_tbl[] = {
···
 	SND_PCI_QUIRK(0x1028, 0x0b1a, "Dell Precision 5570", ALC289_FIXUP_DUAL_SPK),
 	SND_PCI_QUIRK(0x1028, 0x0b37, "Dell Inspiron 16 Plus 7620 2-in-1", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS),
 	SND_PCI_QUIRK(0x1028, 0x0b71, "Dell Inspiron 16 Plus 7620", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS),
+	SND_PCI_QUIRK(0x1028, 0x0c19, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS),
+	SND_PCI_QUIRK(0x1028, 0x0c1a, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS),
+	SND_PCI_QUIRK(0x1028, 0x0c1b, "Dell Precision 3440", ALC236_FIXUP_DELL_DUAL_CODECS),
+	SND_PCI_QUIRK(0x1028, 0x0c1c, "Dell Precision 3540", ALC236_FIXUP_DELL_DUAL_CODECS),
+	SND_PCI_QUIRK(0x1028, 0x0c1d, "Dell Precision 3440", ALC236_FIXUP_DELL_DUAL_CODECS),
+	SND_PCI_QUIRK(0x1028, 0x0c1e, "Dell Precision 3540", ALC236_FIXUP_DELL_DUAL_CODECS),
 	SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2),

sound/usb/line6/driver.c

···
 		for (;;) {
 			done =
 				line6_midibuf_read(mb, line6->buffer_message,
-						LINE6_MIDI_MESSAGE_MAXLEN);
+						   LINE6_MIDI_MESSAGE_MAXLEN,
+						   LINE6_MIDIBUF_READ_RX);
 
 			if (done <= 0)
 				break;

sound/usb/line6/midi.c

···
 	int req, done;
 
 	for (;;) {
-		req = min(line6_midibuf_bytes_free(mb), line6->max_packet_size);
+		req = min3(line6_midibuf_bytes_free(mb), line6->max_packet_size,
+			   LINE6_FALLBACK_MAXPACKETSIZE);
 		done = snd_rawmidi_transmit_peek(substream, chunk, req);
 
 		if (done == 0)
···
 
 	for (;;) {
 		done = line6_midibuf_read(mb, chunk,
-					  LINE6_FALLBACK_MAXPACKETSIZE);
+					  LINE6_FALLBACK_MAXPACKETSIZE,
+					  LINE6_MIDIBUF_READ_TX);
 
 		if (done == 0)
 			break;

sound/usb/line6/midibuf.c

···
 
 #include "midibuf.h"
 
+
 static int midibuf_message_length(unsigned char code)
 {
 	int message_length;
···
 
 		message_length = length[(code >> 4) - 8];
 	} else {
-		/*
-		   Note that according to the MIDI specification 0xf2 is
-		   the "Song Position Pointer", but this is used by Line 6
-		   to send sysex messages to the host.
-		 */
-		static const int length[] = { -1, 2, -1, 2, -1, -1, 1, 1, 1, 1,
+		static const int length[] = { -1, 2, 2, 2, -1, -1, 1, 1, 1, -1,
 			1, 1, 1, -1, 1, 1
 		};
 		message_length = length[code & 0x0f];
···
 }
 
 int line6_midibuf_read(struct midi_buffer *this, unsigned char *data,
-		       int length)
+		       int length, int read_type)
 {
 	int bytes_used;
 	int length1, length2;
···
 
 	length1 = this->size - this->pos_read;
 
-	/* check MIDI command length */
 	command = this->buf[this->pos_read];
+	/*
+	   PODxt always has status byte lower nibble set to 0010,
+	   when it means to send 0000, so we correct if here so
+	   that control/program changes come on channel 1 and
+	   sysex message status byte is correct
+	 */
+	if (read_type == LINE6_MIDIBUF_READ_RX) {
+		if (command == 0xb2 || command == 0xc2 || command == 0xf2) {
+			unsigned char fixed = command & 0xf0;
+			this->buf[this->pos_read] = fixed;
+			command = fixed;
+		}
+	}
 
+	/* check MIDI command length */
 	if (command & 0x80) {
 		midi_length = midibuf_message_length(command);
 		this->command_prev = command;

sound/usb/line6/midibuf.h

···
 #ifndef MIDIBUF_H
 #define MIDIBUF_H
 
+#define LINE6_MIDIBUF_READ_TX 0
+#define LINE6_MIDIBUF_READ_RX 1
+
 struct midi_buffer {
 	unsigned char *buf;
 	int size;
···
 extern int line6_midibuf_ignore(struct midi_buffer *mb, int length);
 extern int line6_midibuf_init(struct midi_buffer *mb, int size, int split);
 extern int line6_midibuf_read(struct midi_buffer *mb, unsigned char *data,
-			      int length);
+			      int length, int read_type);
 extern void line6_midibuf_reset(struct midi_buffer *mb);
 extern int line6_midibuf_write(struct midi_buffer *mb, unsigned char *data,
 			       int length);

sound/usb/line6/pod.c

···
 	.bytes_per_channel = 3 /* SNDRV_PCM_FMTBIT_S24_3LE */
 };
 
+
 static const char pod_version_header[] = {
-	0xf2, 0x7e, 0x7f, 0x06, 0x02
+	0xf0, 0x7e, 0x7f, 0x06, 0x02
 };
 
 static char *pod_alloc_sysex_buffer(struct usb_line6_pod *pod, int code,

tools/bpf/bpftool/Makefile

···
   LLVM_CONFIG_LIB_COMPONENTS := mcdisassembler all-targets
   CFLAGS  += $(shell $(LLVM_CONFIG) --cflags --libs $(LLVM_CONFIG_LIB_COMPONENTS))
   LIBS    += $(shell $(LLVM_CONFIG) --libs $(LLVM_CONFIG_LIB_COMPONENTS))
+  ifeq ($(shell $(LLVM_CONFIG) --shared-mode),static)
+    LIBS += $(shell $(LLVM_CONFIG) --system-libs $(LLVM_CONFIG_LIB_COMPONENTS))
+    LIBS += -lstdc++
+  endif
   LDFLAGS += $(shell $(LLVM_CONFIG) --ldflags)
 else
   # Fall back on libbfd

tools/perf/Documentation/Makefile

···
 	$(ASCIIDOC) -b docbook -d manpage \
 		$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) \
 		-aperf_date=$(shell git log -1 --pretty="format:%cd" \
-				--date=short $<) \
+				--date=short --no-show-signature $<) \
 		-o $@+ $< && \
 	mv $@+ $@
 

tools/perf/Makefile.perf

···
 
 $(LIBAPI): FORCE | $(LIBAPI_OUTPUT)
 	$(Q)$(MAKE) -C $(LIBAPI_DIR) O=$(LIBAPI_OUTPUT) \
-		DESTDIR=$(LIBAPI_DESTDIR) prefix= \
+		DESTDIR=$(LIBAPI_DESTDIR) prefix= subdir= \
 		$@ install_headers
 
 $(LIBAPI)-clean:
···
 
 $(LIBBPF): FORCE | $(LIBBPF_OUTPUT)
 	$(Q)$(MAKE) -C $(LIBBPF_DIR) FEATURES_DUMP=$(FEATURE_DUMP_EXPORT) \
-		O= OUTPUT=$(LIBBPF_OUTPUT)/ DESTDIR=$(LIBBPF_DESTDIR) prefix= \
+		O= OUTPUT=$(LIBBPF_OUTPUT)/ DESTDIR=$(LIBBPF_DESTDIR) prefix= subdir= \
 		$@ install_headers
 
 $(LIBBPF)-clean:
···
 
 $(LIBPERF): FORCE | $(LIBPERF_OUTPUT)
 	$(Q)$(MAKE) -C $(LIBPERF_DIR) O=$(LIBPERF_OUTPUT) \
-		DESTDIR=$(LIBPERF_DESTDIR) prefix= \
+		DESTDIR=$(LIBPERF_DESTDIR) prefix= subdir= \
 		$@ install_headers
 
 $(LIBPERF)-clean:
···
 
 $(LIBSUBCMD): FORCE | $(LIBSUBCMD_OUTPUT)
 	$(Q)$(MAKE) -C $(LIBSUBCMD_DIR) O=$(LIBSUBCMD_OUTPUT) \
-		DESTDIR=$(LIBSUBCMD_DESTDIR) prefix= \
+		DESTDIR=$(LIBSUBCMD_DESTDIR) prefix= subdir= \
 		$@ install_headers
 
 $(LIBSUBCMD)-clean:
···
 
 $(LIBSYMBOL): FORCE | $(LIBSYMBOL_OUTPUT)
 	$(Q)$(MAKE) -C $(LIBSYMBOL_DIR) O=$(LIBSYMBOL_OUTPUT) \
-		DESTDIR=$(LIBSYMBOL_DESTDIR) prefix= \
+		DESTDIR=$(LIBSYMBOL_DESTDIR) prefix= subdir= \
 		$@ install_headers
 
 $(LIBSYMBOL)-clean:

tools/perf/arch/riscv/util/unwind-libdw.c

···
 #include <elfutils/libdwfl.h>
 #include "../../util/unwind-libdw.h"
 #include "../../util/perf_regs.h"
-#include "../../util/event.h"
+#include "../../util/sample.h"
 
 bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
 {

tools/perf/builtin-lock.c

···
 
 	/* for lock function check */
 	symbol_conf.sort_by_name = true;
+	symbol_conf.allow_aliases = true;
 	symbol__init(&session->header.env);
 
 	if (!data.is_pipe) {
···
 
 	/* for lock function check */
 	symbol_conf.sort_by_name = true;
+	symbol_conf.allow_aliases = true;
 	symbol__init(&session->header.env);
 
 	if (use_bpf) {

tools/perf/command-list.txt

···
 perf-inject			mainporcelain common
 perf-iostat			mainporcelain common
 perf-kallsyms			mainporcelain common
-perf-kmem			mainporcelain common
+perf-kmem			mainporcelain traceevent
 perf-kvm			mainporcelain common
-perf-kwork			mainporcelain common
+perf-kwork			mainporcelain traceevent
 perf-list			mainporcelain common
-perf-lock			mainporcelain common
+perf-lock			mainporcelain traceevent
 perf-mem			mainporcelain common
 perf-probe			mainporcelain full
 perf-record			mainporcelain common
 perf-report			mainporcelain common
-perf-sched			mainporcelain common
+perf-sched			mainporcelain traceevent
 perf-script			mainporcelain common
 perf-stat			mainporcelain common
 perf-test			mainporcelain common
-perf-timechart			mainporcelain common
+perf-timechart			mainporcelain traceevent
 perf-top			mainporcelain common
 perf-trace			mainporcelain audit
 perf-version			mainporcelain common

tools/perf/tests/shell/record+probe_libc_inet_pton.sh

···
 	case "$(uname -m)" in
 	s390x)
 		eventattr='call-graph=dwarf,max-stack=4'
+		echo "text_to_binary_address.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
 		echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
 		echo "(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
 		echo "main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
···
 	perf_data=`mktemp -u /tmp/perf.data.XXX`
 	perf_script=`mktemp -u /tmp/perf.script.XXX`
 	perf record -e $event_name/$eventattr/ -o $perf_data ping -6 -c 1 ::1 > /dev/null 2>&1
-	perf script -i $perf_data > $perf_script
+	perf script -i $perf_data | tac | grep -m1 ^ping -B9 | tac > $perf_script
 
 	exec 3<$perf_script
 	exec 4<$expected

tools/perf/util/PERF-VERSION-GEN

···
 if test -d ../../.git -o -f ../../.git
 then
 	TAG=$(MAKEFLAGS= make -sC ../.. kernelversion)
-	CID=$(git log -1 --abbrev=12 --pretty=format:"%h" 2>/dev/null) && CID="-g$CID"
+	CID=$(git log -1 --abbrev=12 --pretty=format:"%h" --no-show-signature 2>/dev/null) && CID="-g$CID"
 elif test -f ../../PERF-VERSION-FILE
 then
 	TAG=$(cut -d' ' -f3 ../../PERF-VERSION-FILE | sed -e 's/\"//g')

tools/perf/util/bpf_counter_cgroup.c

···
 
 			/* open single copy of the events w/o cgroup */
 			err = evsel__open_per_cpu(evsel, evsel->core.cpus, -1);
-			if (err) {
-				pr_err("Failed to open first cgroup events\n");
-				goto out;
-			}
+			if (err == 0)
+				evsel->supported = true;
 
 			map_fd = bpf_map__fd(skel->maps.events);
 			perf_cpu_map__for_each_cpu(cpu, j, evsel->core.cpus) {
 				int fd = FD(evsel, j);
 				__u32 idx = evsel->core.idx * total_cpus + cpu.cpu;
 
-				err = bpf_map_update_elem(map_fd, &idx, &fd,
-							  BPF_ANY);
-				if (err < 0) {
-					pr_err("Failed to update perf_event fd\n");
-					goto out;
-				}
+				bpf_map_update_elem(map_fd, &idx, &fd, BPF_ANY);
 			}
 
 			evsel->cgrp = leader_cgrp;
 		}
-		evsel->supported = true;
 
 		if (evsel->cgrp == cgrp)
 			continue;

tools/perf/util/cgroup.c

···
 	return 0;
 }
 
+static int check_and_add_cgroup_name(const char *fpath)
+{
+	struct cgroup_name *cn;
+
+	list_for_each_entry(cn, &cgroup_list, list) {
+		if (!strcmp(cn->name, fpath))
+			return 0;
+	}
+
+	/* pretend if it's added by ftw() */
+	return add_cgroup_name(fpath, NULL, FTW_D, NULL);
+}
+
 static void release_cgroup_list(void)
 {
 	struct cgroup_name *cn;
···
 	struct cgroup_name *cn;
 	char *s;
 
-	/* use given name as is - for testing purpose */
+	/* use given name as is when no regex is given */
 	for (;;) {
 		p = strchr(str, ',');
 		e = p ? p : eos;
···
 			s = strndup(str, e - str);
 			if (!s)
 				return -1;
-			/* pretend if it's added by ftw() */
-			ret = add_cgroup_name(s, NULL, FTW_D, NULL);
+
+			ret = check_and_add_cgroup_name(s);
 			free(s);
-			if (ret)
+			if (ret < 0)
 				return -1;
 		} else {
-			if (add_cgroup_name("", NULL, FTW_D, NULL) < 0)
+			if (check_and_add_cgroup_name("/") < 0)
 				return -1;
 		}
 

tools/perf/util/data.c

···
 		file->size = st.st_size;
 	}
 
+	closedir(dir);
 	if (!files)
 		return -EINVAL;
 
···
 	return 0;
 
 out_err:
+	closedir(dir);
 	close_dir(files, nr);
 	return ret;
 }

tools/perf/util/generate-cmdlist.sh

···
 done
 echo "#endif /* HAVE_LIBELF_SUPPORT */"
 
-echo "#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT)"
+echo "#if defined(HAVE_LIBTRACEEVENT) && (defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT))"
 sed -n -e 's/^perf-\([^ 	]*\)[ 	].* audit*/\1/p' command-list.txt |
 sort |
 while read cmd
···
 	    p
      }' "Documentation/perf-$cmd.txt"
 done
-echo "#endif /* HAVE_LIBELF_SUPPORT */"
+echo "#endif /* HAVE_LIBTRACEEVENT && (HAVE_LIBAUDIT_SUPPORT || HAVE_SYSCALL_TABLE_SUPPORT) */"
+
+echo "#ifdef HAVE_LIBTRACEEVENT"
+sed -n -e 's/^perf-\([^ 	]*\)[ 	].* traceevent.*/\1/p' command-list.txt |
+sort |
+while read cmd
+do
+     sed -n '
+     /^NAME/,/perf-'"$cmd"'/H
+     ${
+            x
+            s/.*perf-'"$cmd"' - \(.*\)/  {"'"$cmd"'", "\1"},/
+            p
+     }' "Documentation/perf-$cmd.txt"
+done
+echo "#endif /* HAVE_LIBTRACEEVENT */"
 echo "};"

tools/perf/util/sort.c

···
 		ret = add_all_matching_fields(evlist, field_name, raw_trace, level);
 		goto out;
 	}
+#else
+	evlist__for_each_entry(evlist, evsel) {
+		if (evsel->core.attr.type == PERF_TYPE_TRACEPOINT) {
+			pr_err("%s %s", ret ? "," : "This perf binary isn't linked with libtraceevent, can't process", evsel__name(evsel));
+			ret = -ENOTSUP;
+		}
+	}
+
+	if (ret) {
+		pr_err("\n");
+		goto out;
+	}
 #endif
 
 	evsel = find_evsel(evlist, event_name);

tools/perf/util/trace-event.h

···
 
 #include <stdbool.h>
 #include <stdio.h>
+#include <sys/types.h>
 #include <linux/types.h>
 
 struct evlist;

tools/testing/memblock/.gitignore

···
 main
 memblock.c
 linux/memblock.h
+asm/asm.h
 asm/cmpxchg.h

tools/testing/memblock/Makefile

···
 
 	@mkdir -p linux
 	test -L linux/memblock.h || ln -s ../../../../include/linux/memblock.h linux/memblock.h
+	test -L asm/asm.h || ln -s ../../../arch/x86/include/asm/asm.h asm/asm.h
 	test -L asm/cmpxchg.h || ln -s ../../../arch/x86/include/asm/cmpxchg.h asm/cmpxchg.h
 
 memblock.c: $(EXTR_SRC)
 	test -L memblock.c || ln -s $(EXTR_SRC) memblock.c
 
 clean:
-	$(RM) $(TARGETS) $(OFILES) linux/memblock.h memblock.c asm/cmpxchg.h
+	$(RM) $(TARGETS) $(OFILES) linux/memblock.h memblock.c asm/asm.h asm/cmpxchg.h
 
 help:
 	@echo  'Memblock simulator'

tools/testing/selftests/bpf/.gitignore

···
 *.lskel.h
 /no_alu32
 /bpf_gcc
+/host-tools
 /tools
 /runqslower
 /bench

tools/testing/selftests/bpf/DENYLIST.s390x

···
 cgrp_local_storage                       # prog_attach unexpected error: -524                                          (trampoline)
 core_read_macros                         # unknown func bpf_probe_read#4                                               (overlapping)
 d_path                                   # failed to auto-attach program 'prog_stat': -524                             (trampoline)
+decap_sanity                             # JIT does not support calling kernel function                                (kfunc)
 deny_namespace                           # failed to attach: ERROR: strerror_r(-524)=22                                (trampoline)
 dummy_st_ops                             # test_run unexpected error: -524 (errno 524)                                 (trampoline)
 fentry_fexit                             # fentry attach failed: -524                                                  (trampoline)

tools/testing/selftests/bpf/prog_tests/bpf_iter.c

···
 	bpf_iter_task_vma__destroy(skel);
 }
 
+static void test_task_vma_dead_task(void)
+{
+	struct bpf_iter_task_vma *skel;
+	int wstatus, child_pid = -1;
+	time_t start_tm, cur_tm;
+	int err, iter_fd = -1;
+	int wait_sec = 3;
+
+	skel = bpf_iter_task_vma__open();
+	if (!ASSERT_OK_PTR(skel, "bpf_iter_task_vma__open"))
+		return;
+
+	skel->bss->pid = getpid();
+
+	err = bpf_iter_task_vma__load(skel);
+	if (!ASSERT_OK(err, "bpf_iter_task_vma__load"))
+		goto out;
+
+	skel->links.proc_maps = bpf_program__attach_iter(
+		skel->progs.proc_maps, NULL);
+
+	if (!ASSERT_OK_PTR(skel->links.proc_maps, "bpf_program__attach_iter")) {
+		skel->links.proc_maps = NULL;
+		goto out;
+	}
+
+	start_tm = time(NULL);
+	cur_tm = start_tm;
+
+	child_pid = fork();
+	if (child_pid == 0) {
+		/* Fork short-lived processes in the background. */
+		while (cur_tm < start_tm + wait_sec) {
+			system("echo > /dev/null");
+			cur_tm = time(NULL);
+		}
+		exit(0);
+	}
+
+	if (!ASSERT_GE(child_pid, 0, "fork_child"))
+		goto out;
+
+	while (cur_tm < start_tm + wait_sec) {
+		iter_fd = bpf_iter_create(bpf_link__fd(skel->links.proc_maps));
+		if (!ASSERT_GE(iter_fd, 0, "create_iter"))
+			goto out;
+
+		/* Drain all data from iter_fd. */
+		while (cur_tm < start_tm + wait_sec) {
+			err = read_fd_into_buffer(iter_fd, task_vma_output, CMP_BUFFER_SIZE);
+			if (!ASSERT_GE(err, 0, "read_iter_fd"))
+				goto out;
+
+			cur_tm = time(NULL);
+
+			if (err == 0)
+				break;
+		}
+
+		close(iter_fd);
+		iter_fd = -1;
+	}
+
+	check_bpf_link_info(skel->progs.proc_maps);
+
+out:
+	waitpid(child_pid, &wstatus, 0);
+	close(iter_fd);
+	bpf_iter_task_vma__destroy(skel);
+}
+
 void test_bpf_sockmap_map_iter_fd(void)
 {
 	struct bpf_iter_sockmap *skel;
···
 		test_task_file();
 	if (test__start_subtest("task_vma"))
 		test_task_vma();
+	if (test__start_subtest("task_vma_dead_task"))
+		test_task_vma_dead_task();
 	if (test__start_subtest("task_btf"))
 		test_task_btf();
 	if (test__start_subtest("tcp4"))

tools/testing/selftests/bpf/prog_tests/btf_dump.c

···
 static void test_btf_dump_var_data(struct btf *btf, struct btf_dump *d,
 				   char *str)
 {
-#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__)
+#if 0
 	TEST_BTF_DUMP_VAR(btf, d, NULL, str, "cpu_number", int, BTF_F_COMPACT,
 			  "int cpu_number = (int)100", 100);
 #endif

tools/testing/selftests/bpf/prog_tests/decap_sanity.c

···
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <net/if.h>
+#include <linux/in6.h>
+
+#include "test_progs.h"
+#include "network_helpers.h"
+#include "decap_sanity.skel.h"
+
+#define SYS(fmt, ...)						\
+	({							\
+		char cmd[1024];					\
+		snprintf(cmd, sizeof(cmd), fmt, ##__VA_ARGS__);	\
+		if (!ASSERT_OK(system(cmd), cmd))		\
+			goto fail;				\
+	})
+
+#define NS_TEST "decap_sanity_ns"
+#define IPV6_IFACE_ADDR "face::1"
+#define UDP_TEST_PORT 7777
+
+void test_decap_sanity(void)
+{
+	LIBBPF_OPTS(bpf_tc_hook, qdisc_hook, .attach_point = BPF_TC_EGRESS);
+	LIBBPF_OPTS(bpf_tc_opts, tc_attach);
+	struct nstoken *nstoken = NULL;
+	struct decap_sanity *skel;
+	struct sockaddr_in6 addr;
+	socklen_t addrlen;
+	char buf[128] = {};
+	int sockfd, err;
+
+	skel = decap_sanity__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel open_and_load"))
+		return;
+
+	SYS("ip netns add %s", NS_TEST);
+	SYS("ip -net %s -6 addr add %s/128 dev lo nodad", NS_TEST, IPV6_IFACE_ADDR);
+	SYS("ip -net %s link set dev lo up", NS_TEST);
+
+	nstoken = open_netns(NS_TEST);
+	if (!ASSERT_OK_PTR(nstoken, "open_netns"))
+		goto fail;
+
+	qdisc_hook.ifindex = if_nametoindex("lo");
+	if (!ASSERT_GT(qdisc_hook.ifindex, 0, "if_nametoindex lo"))
+		goto fail;
+
+	err = bpf_tc_hook_create(&qdisc_hook);
+	if (!ASSERT_OK(err, "create qdisc hook"))
+		goto fail;
+
+	tc_attach.prog_fd = bpf_program__fd(skel->progs.decap_sanity);
+	err = bpf_tc_attach(&qdisc_hook, &tc_attach);
+	if (!ASSERT_OK(err, "attach filter"))
+		goto fail;
+
+	addrlen = sizeof(addr);
+	err = make_sockaddr(AF_INET6, IPV6_IFACE_ADDR, UDP_TEST_PORT,
+			    (void *)&addr, &addrlen);
+	if (!ASSERT_OK(err, "make_sockaddr"))
+		goto fail;
+	sockfd = socket(AF_INET6, SOCK_DGRAM, 0);
+	if (!ASSERT_NEQ(sockfd, -1, "socket"))
+		goto fail;
+	err = sendto(sockfd, buf, sizeof(buf), 0, (void *)&addr, addrlen);
+	close(sockfd);
+	if (!ASSERT_EQ(err, sizeof(buf), "send"))
+		goto fail;
+
+	ASSERT_TRUE(skel->bss->init_csum_partial, "init_csum_partial");
+	ASSERT_TRUE(skel->bss->final_csum_none, "final_csum_none");
+	ASSERT_FALSE(skel->bss->broken_csum_start, "broken_csum_start");
+
+fail:
+	if (nstoken) {
+		bpf_tc_hook_destroy(&qdisc_hook);
+		close_netns(nstoken);
+	}
+	system("ip netns del " NS_TEST " >& /dev/null");
+	decap_sanity__destroy(skel);
+}

tools/testing/selftests/bpf/prog_tests/jeq_infer_not_null.c

···
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "jeq_infer_not_null_fail.skel.h"
+
+void test_jeq_infer_not_null(void)
+{
+	RUN_TESTS(jeq_infer_not_null_fail);
+}

tools/testing/selftests/bpf/progs/bpf_tracing_net.h

···
 #define ICSK_TIME_LOSS_PROBE	5
 #define ICSK_TIME_REO_TIMEOUT	6
 
+#define ETH_HLEN		14
+#define ETH_P_IPV6		0x86DD
+
+#define CHECKSUM_NONE		0
+#define CHECKSUM_PARTIAL	3
+
 #define IFNAMSIZ		16
 
 #define RTF_GATEWAY		0x0002

tools/testing/selftests/bpf/progs/decap_sanity.c

···
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include "bpf_tracing_net.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define UDP_TEST_PORT 7777
+
+void *bpf_cast_to_kern_ctx(void *) __ksym;
+bool init_csum_partial = false;
+bool final_csum_none = false;
+bool broken_csum_start = false;
+
+static unsigned int skb_headlen(const struct sk_buff *skb)
+{
+	return skb->len - skb->data_len;
+}
+
+static unsigned int skb_headroom(const struct sk_buff *skb)
+{
+	return skb->data - skb->head;
+}
+
+static int skb_checksum_start_offset(const struct sk_buff *skb)
+{
+	return skb->csum_start - skb_headroom(skb);
+}
+
+SEC("tc")
+int decap_sanity(struct __sk_buff *skb)
+{
+	struct sk_buff *kskb;
+	struct ipv6hdr ip6h;
+	struct udphdr udph;
+	int err;
+
+	if (skb->protocol != __bpf_constant_htons(ETH_P_IPV6))
+		return TC_ACT_SHOT;
+
+	if (bpf_skb_load_bytes(skb, ETH_HLEN, &ip6h, sizeof(ip6h)))
+		return TC_ACT_SHOT;
+
+	if (ip6h.nexthdr != IPPROTO_UDP)
+		return TC_ACT_SHOT;
+
+	if (bpf_skb_load_bytes(skb, ETH_HLEN + sizeof(ip6h), &udph, sizeof(udph)))
+		return TC_ACT_SHOT;
+
+	if (udph.dest != __bpf_constant_htons(UDP_TEST_PORT))
+		return TC_ACT_SHOT;
+
+	kskb = bpf_cast_to_kern_ctx(skb);
+	init_csum_partial = (kskb->ip_summed == CHECKSUM_PARTIAL);
+	err = bpf_skb_adjust_room(skb, -(s32)(ETH_HLEN + sizeof(ip6h) + sizeof(udph)),
+				  1, BPF_F_ADJ_ROOM_FIXED_GSO);
+	if (err)
+		return TC_ACT_SHOT;
+	final_csum_none = (kskb->ip_summed == CHECKSUM_NONE);
+	if (kskb->ip_summed == CHECKSUM_PARTIAL &&
+	    (unsigned int)skb_checksum_start_offset(kskb) >= skb_headlen(kskb))
+		broken_csum_start = true;
+
+	return TC_ACT_SHOT;
+}
+
+char __license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/progs/jeq_infer_not_null_fail.c

···
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 1);
+	__type(key, u64);
+	__type(value, u64);
+} m_hash SEC(".maps");
+
+SEC("?raw_tp")
+__failure __msg("R8 invalid mem access 'map_value_or_null")
+int jeq_infer_not_null_ptr_to_btfid(void *ctx)
+{
+	struct bpf_map *map = (struct bpf_map *)&m_hash;
+	struct bpf_map *inner_map = map->inner_map_meta;
+	u64 key = 0, ret = 0, *val;
+
+	val = bpf_map_lookup_elem(map, &key);
+	/* Do not mark ptr as non-null if one of them is
+	 * PTR_TO_BTF_ID (R9), reject because of invalid
+	 * access to map value (R8).
+	 *
+	 * Here, we need to inline those insns to access
+	 * R8 directly, since compiler may use other reg
+	 * once it figures out val==inner_map.
+	 */
+	asm volatile("r8 = %[val];\n"
+		     "r9 = %[inner_map];\n"
+		     "if r8 != r9 goto +1;\n"
+		     "%[ret] = *(u64 *)(r8 +0);\n"
+		     : [ret] "+r"(ret)
+		     : [inner_map] "r"(inner_map), [val] "r"(val)
+		     : "r8", "r9");
+
+	return ret;
+}

tools/testing/selftests/kvm/.gitignore

···
 # SPDX-License-Identifier: GPL-2.0-only
-/aarch64/aarch32_id_regs
-/aarch64/arch_timer
-/aarch64/debug-exceptions
-/aarch64/get-reg-list
-/aarch64/hypercalls
-/aarch64/page_fault_test
-/aarch64/psci_test
-/aarch64/vcpu_width_config
-/aarch64/vgic_init
-/aarch64/vgic_irq
-/s390x/memop
-/s390x/resets
-/s390x/sync_regs_test
-/s390x/tprot
-/x86_64/amx_test
-/x86_64/cpuid_test
-/x86_64/cr4_cpuid_sync_test
-/x86_64/debug_regs
-/x86_64/exit_on_emulation_failure_test
-/x86_64/fix_hypercall_test
-/x86_64/get_msr_index_features
-/x86_64/kvm_clock_test
-/x86_64/kvm_pv_test
-/x86_64/hyperv_clock
-/x86_64/hyperv_cpuid
-/x86_64/hyperv_evmcs
-/x86_64/hyperv_features
-/x86_64/hyperv_ipi
-/x86_64/hyperv_svm_test
-/x86_64/hyperv_tlb_flush
-/x86_64/max_vcpuid_cap_test
-/x86_64/mmio_warning_test
-/x86_64/monitor_mwait_test
-/x86_64/nested_exceptions_test
-/x86_64/nx_huge_pages_test
-/x86_64/platform_info_test
-/x86_64/pmu_event_filter_test
-/x86_64/set_boot_cpu_id
-/x86_64/set_sregs_test
-/x86_64/sev_migrate_tests
-/x86_64/smaller_maxphyaddr_emulation_test
-/x86_64/smm_test
-/x86_64/state_test
-/x86_64/svm_vmcall_test
-/x86_64/svm_int_ctl_test
-/x86_64/svm_nested_soft_inject_test
-/x86_64/svm_nested_shutdown_test
-/x86_64/sync_regs_test
-/x86_64/tsc_msrs_test
-/x86_64/tsc_scaling_sync
-/x86_64/ucna_injection_test
-/x86_64/userspace_io_test
-/x86_64/userspace_msr_exit_test
-/x86_64/vmx_apic_access_test
-/x86_64/vmx_close_while_nested_test
-/x86_64/vmx_dirty_log_test
-/x86_64/vmx_exception_with_invalid_guest_state
-/x86_64/vmx_invalid_nested_guest_state
-/x86_64/vmx_msrs_test
-/x86_64/vmx_preemption_timer_test
-/x86_64/vmx_set_nested_state_test
-/x86_64/vmx_tsc_adjust_test
-/x86_64/vmx_nested_tsc_scaling_test
-/x86_64/xapic_ipi_test
-/x86_64/xapic_state_test
-/x86_64/xen_shinfo_test
-/x86_64/xen_vmcall_test
-/x86_64/xss_msr_test
-/x86_64/vmx_pmu_caps_test
-/x86_64/triple_fault_event_test
-/access_tracking_perf_test
-/demand_paging_test
-/dirty_log_test
-/dirty_log_perf_test
-/hardware_disable_test
-/kvm_create_max_vcpus
-/kvm_page_table_test
-/max_guest_memory_test
-/memslot_modification_stress_test
-/memslot_perf_test
-/rseq_test
-/set_memory_region_test
-/steal_time
-/kvm_binary_stats_test
-/system_counter_offset_test
+*
+!/**/
+!*.c
+!*.h
+!*.S
+!*.sh

tools/testing/selftests/kvm/Makefile

···
 include $(top_srcdir)/scripts/subarch.include
 ARCH            ?= $(SUBARCH)
 
-# For cross-builds to work, UNAME_M has to map to ARCH and arch specific
-# directories and targets in this Makefile. "uname -m" doesn't map to
-# arch specific sub-directory names.
-#
-# UNAME_M variable to used to run the compiles pointing to the right arch
-# directories and build the right targets for these supported architectures.
-#
-# TEST_GEN_PROGS and LIBKVM are set using UNAME_M variable.
-# LINUX_TOOL_ARCH_INCLUDE is set using ARCH variable.
-#
-# x86_64 targets are named to include x86_64 as a suffix and directories
-# for includes are in x86_64 sub-directory. s390x and aarch64 follow the
-# same convention. "uname -m" doesn't result in the correct mapping for
-# s390x and aarch64.
-#
-# No change necessary for x86_64
-UNAME_M := $(shell uname -m)
-
-# Set UNAME_M for arm64 compile/install to work
-ifeq ($(ARCH),arm64)
-	UNAME_M := aarch64
-endif
-# Set UNAME_M s390x compile/install to work
-ifeq ($(ARCH),s390)
-	UNAME_M := s390x
-endif
-# Set UNAME_M riscv compile/install to work
-ifeq ($(ARCH),riscv)
-	UNAME_M := riscv
+ifeq ($(ARCH),x86)
+	ARCH_DIR := x86_64
+else ifeq ($(ARCH),arm64)
+	ARCH_DIR := aarch64
+else ifeq ($(ARCH),s390)
+	ARCH_DIR := s390x
+else
+	ARCH_DIR := $(ARCH)
 endif
 
 LIBKVM += lib/assert.c
···
 TEST_GEN_PROGS_riscv += set_memory_region_test
 TEST_GEN_PROGS_riscv += kvm_binary_stats_test
 
-TEST_PROGS += $(TEST_PROGS_$(UNAME_M))
-TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M))
-TEST_GEN_PROGS_EXTENDED += $(TEST_GEN_PROGS_EXTENDED_$(UNAME_M))
-LIBKVM += $(LIBKVM_$(UNAME_M))
+TEST_PROGS += $(TEST_PROGS_$(ARCH_DIR))
+TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(ARCH_DIR))
+TEST_GEN_PROGS_EXTENDED += $(TEST_GEN_PROGS_EXTENDED_$(ARCH_DIR))
+LIBKVM += $(LIBKVM_$(ARCH_DIR))
+
+# lib.mak defines $(OUTPUT), prepends $(OUTPUT)/ to $(TEST_GEN_PROGS), and most
+# importantly defines, i.e. overwrites, $(CC) (unless `make -e` or `make CC=`,
+# which causes the environment variable to override the makefile).
+include ../lib.mk
 
 INSTALL_HDR_PATH = $(top_srcdir)/usr
 LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
···
 LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/$(ARCH)/include
 endif
 CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \
+	-Wno-gnu-variable-sized-type-not-at-end \
+	-fno-builtin-memcmp -fno-builtin-memcpy -fno-builtin-memset \
 	-fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \
 	-I$(LINUX_TOOL_ARCH_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude \
-	-I$(<D) -Iinclude/$(UNAME_M) -I ../rseq -I.. $(EXTRA_CFLAGS) \
+	-I$(<D) -Iinclude/$(ARCH_DIR) -I ../rseq -I.. $(EXTRA_CFLAGS) \
 	$(KHDR_INCLUDES)
 
-no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \
-        $(CC) -Werror -no-pie -x c - -o "$$TMP", -no-pie)
+no-pie-option := $(call try-run, echo 'int main(void) { return 0; }' | \
+        $(CC) -Werror $(CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie)
 
 # On s390, build the testcases KVM-enabled
-pgste-option = $(call try-run, echo 'int main() { return 0; }' | \
+pgste-option = $(call try-run, echo 'int main(void) { return 0; }' | \
 	$(CC) -Werror -Wl$(comma)--s390-pgste -x c - -o "$$TMP",-Wl$(comma)--s390-pgste)
 
 LDLIBS += -ldl
 LDFLAGS += -pthread $(no-pie-option) $(pgste-option)
-
-# After inclusion, $(OUTPUT) is defined and
-# $(TEST_GEN_PROGS) starts with $(OUTPUT)/
-include ../lib.mk
 
 LIBKVM_C := $(filter %.c,$(LIBKVM))
 LIBKVM_S := $(filter %.S,$(LIBKVM))

tools/testing/selftests/kvm/aarch64/page_fault_test.c

···
 	GUEST_ASSERT(guest_check_lse());
 	asm volatile(".arch_extension lse\n"
 		     "casal %0, %1, [%2]\n"
-		     :: "r" (0), "r" (TEST_DATA), "r" (guest_test_memory));
+		     :: "r" (0ul), "r" (TEST_DATA), "r" (guest_test_memory));
 	val = READ_ONCE(*guest_test_memory);
 	GUEST_ASSERT_EQ(val, TEST_DATA);
 }

tools/testing/selftests/kvm/lib/aarch64/ucall.c

···
 
 void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa)
 {
-	virt_pg_map(vm, mmio_gpa, mmio_gpa);
+	vm_vaddr_t mmio_gva = vm_vaddr_unused_gap(vm, vm->page_size, KVM_UTIL_MIN_VADDR);
+
+	virt_map(vm, mmio_gva, mmio_gpa, 1);
 
 	vm->ucall_mmio_addr = mmio_gpa;
 
-	write_guest_global(vm, ucall_exit_mmio_addr, (vm_vaddr_t *)mmio_gpa);
+	write_guest_global(vm, ucall_exit_mmio_addr, (vm_vaddr_t *)mmio_gva);
 }
 
 void ucall_arch_do_ucall(vm_vaddr_t uc)

tools/testing/selftests/kvm/lib/kvm_util.c

···
 _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES,
 	       "Missing new mode params?");
 
+/*
+ * Initializes vm->vpages_valid to match the canonical VA space of the
+ * architecture.
+ *
+ * The default implementation is valid for architectures which split the
+ * range addressed by a single page table into a low and high region
+ * based on the MSB of the VA. On architectures with this behavior
+ * the VA region spans [0, 2^(va_bits - 1)), [-(2^(va_bits - 1), -1].
+ */
 __weak void vm_vaddr_populate_bitmap(struct kvm_vm *vm)
 {
 	sparsebit_set_num(vm->vpages_valid,
···
 
 	while (npages--) {
 		virt_pg_map(vm, vaddr, paddr);
+		sparsebit_set(vm->vpages_mapped, vaddr >> vm->page_shift);
+
 		vaddr += page_size;
 		paddr += page_size;
-
-		sparsebit_set(vm->vpages_mapped, vaddr >> vm->page_shift);
 	}
 }
 

tools/testing/selftests/kvm/lib/ucall_common.c

···
 #include "linux/bitmap.h"
 #include "linux/atomic.h"
 
+#define GUEST_UCALL_FAILED -1
+
 struct ucall_header {
 	DECLARE_BITMAP(in_use, KVM_MAX_VCPUS);
 	struct ucall ucalls[KVM_MAX_VCPUS];
···
 	struct ucall *uc;
 	int i;
 
-	GUEST_ASSERT(ucall_pool);
+	if (!ucall_pool)
+		goto ucall_failed;
 
 	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
 		if (!test_and_set_bit(i, ucall_pool->in_use)) {
···
 		}
 	}
 
-	GUEST_ASSERT(0);
+ucall_failed:
+	/*
+	 * If the vCPU cannot grab a ucall structure, make a bare ucall with a
+	 * magic value to signal to get_ucall() that things went sideways.
+	 * GUEST_ASSERT() depends on ucall_alloc() and so cannot be used here.
+	 */
+	ucall_arch_do_ucall(GUEST_UCALL_FAILED);
 	return NULL;
 }
 
···
 
 	addr = ucall_arch_get_ucall(vcpu);
 	if (addr) {
+		TEST_ASSERT(addr != (void *)GUEST_UCALL_FAILED,
+			    "Guest failed to allocate ucall struct");
+
 		memcpy(uc, addr, sizeof(*uc));
 		vcpu_run_complete_io(vcpu);
 	} else {

tools/testing/selftests/kvm/lib/x86_64/processor.c

···
 void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits)
 {
 	if (!kvm_cpu_has_p(X86_PROPERTY_MAX_PHY_ADDR)) {
-		*pa_bits == kvm_cpu_has(X86_FEATURE_PAE) ? 36 : 32;
+		*pa_bits = kvm_cpu_has(X86_FEATURE_PAE) ? 36 : 32;
 		*va_bits = 32;
 	} else {
 		*pa_bits = kvm_cpu_property(X86_PROPERTY_MAX_PHY_ADDR);

tools/testing/selftests/kvm/memslot_perf_test.c

···
 	slots = data->nslots;
 	while (--slots > 1) {
 		pages_per_slot = mempages / slots;
+		if (!pages_per_slot)
+			continue;
+
 		rempages = mempages % pages_per_slot;
 		if (check_slot_pages(host_page_size, guest_page_size,
 				     pages_per_slot, rempages))

tools/testing/selftests/kvm/x86_64/hyperv_ipi.c

···
 	GUEST_SYNC(stage++);
 	/*
 	 * 'XMM Fast' HvCallSendSyntheticClusterIpiEx to HV_GENERIC_SET_ALL.
-	 * Nothing to write anything to XMM regs.
 	 */
+	ipi_ex->vp_set.valid_bank_mask = 0;
+	hyperv_write_xmm_input(&ipi_ex->vp_set.valid_bank_mask, 2);
 	hyperv_hypercall(HVCALL_SEND_IPI_EX | HV_HYPERCALL_FAST_BIT,
 			 IPI_VECTOR, HV_GENERIC_SET_ALL);
 	nop_loop();

tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c

···
 static void l2_guest_code_int(void)
 {
 	GUEST_ASSERT_1(int_fired == 1, int_fired);
-	vmmcall();
-	ud2();
+
+	/*
+         * Same as the vmmcall() function, but with a ud2 sneaked after the
+         * vmmcall.  The caller injects an exception with the return address
+         * increased by 2, so the "pop rbp" must be after the ud2 and we cannot
+	 * use vmmcall() directly.
+         */
+	__asm__ __volatile__("push %%rbp; vmmcall; ud2; pop %%rbp"
+                             : : "a"(0xdeadbeef), "c"(0xbeefdead)
+                             : "rbx", "rdx", "rsi", "rdi", "r8", "r9",
+                               "r10", "r11", "r12", "r13", "r14", "r15");
 
 	GUEST_ASSERT_1(bp_fired == 1, bp_fired);
 	hlt();

tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c

···
 	NUM_VMX_PAGES,
 };
 
-struct kvm_single_msr {
-	struct kvm_msrs header;
-	struct kvm_msr_entry entry;
-} __attribute__((packed));
-
 /* The virtual machine object. */
 static struct kvm_vm *vm;
 

tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c

···
 	}
 
  done:
+	struct kvm_xen_hvm_attr evt_reset = {
+		.type = KVM_XEN_ATTR_TYPE_EVTCHN,
+		.u.evtchn.flags = KVM_XEN_EVTCHN_RESET,
+	};
+	vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &evt_reset);
+
 	alarm(0);
 	clock_gettime(CLOCK_REALTIME, &max_ts);
 

tools/testing/selftests/net/.gitignore

···
 # SPDX-License-Identifier: GPL-2.0-only
 bind_bhash
+bind_timewait
 csum
 cmsg_sender
 diag_uid

tools/testing/selftests/net/arp_ndisc_evict_nocarrier.sh

···
 readonly V6_ADDR0=2001:db8:91::1
 readonly V6_ADDR1=2001:db8:91::2
 nsid=100
+ret=0
 
 cleanup_v6()
 {
     ip netns del me
     ip netns del peer
 
-    sysctl -w net.ipv4.conf.veth0.ndisc_evict_nocarrier=1 >/dev/null 2>&1
-    sysctl -w net.ipv4.conf.all.ndisc_evict_nocarrier=1 >/dev/null 2>&1
+    sysctl -w net.ipv6.conf.veth1.ndisc_evict_nocarrier=1 >/dev/null 2>&1
+    sysctl -w net.ipv6.conf.all.ndisc_evict_nocarrier=1 >/dev/null 2>&1
 }
 
 create_ns()
···
     if [ $? -ne 0 ]; then
         cleanup_v6
         echo "failed"
-        exit
+        exit 1
     fi
 
     # Set veth2 down, which will put veth1 in NOCARRIER state
···
     if [ $? -ne 0 ]; then
         cleanup_v4
         echo "failed"
-        exit
+        exit 1
     fi
 
     # Set veth1 down, which will put veth0 in NOCARRIER state
···
 
     if [ $? -eq 0 ];then
         echo "failed"
+        ret=1
     else
         echo "ok"
     fi
···
         echo "ok"
     else
         echo "failed"
+        ret=1
     fi
 
     cleanup_v4
···
 
     if [ $? -eq 0 ];then
         echo "failed"
+        ret=1
     else
         echo "ok"
     fi
···
         echo "ok"
     else
         echo "failed"
+        ret=1
     fi
 
     cleanup_v6
···
         echo "ok"
     else
         echo "failed"
+        ret=1
     fi
 
     cleanup_v6
···
 fi
 
 run_all_tests
+exit $ret

tools/testing/selftests/net/bind_timewait.c

···
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright Amazon.com Inc. or its affiliates. */
+
+#include <sys/socket.h>
+#include <netinet/in.h>
+
+#include "../kselftest_harness.h"
+
+FIXTURE(bind_timewait)
+{
+	struct sockaddr_in addr;
+	socklen_t addrlen;
+};
+
+FIXTURE_VARIANT(bind_timewait)
+{
+	__u32 addr_const;
+};
+
+FIXTURE_VARIANT_ADD(bind_timewait, localhost)
+{
+	.addr_const = INADDR_LOOPBACK
+};
+
+FIXTURE_VARIANT_ADD(bind_timewait, addrany)
+{
+	.addr_const = INADDR_ANY
+};
+
+FIXTURE_SETUP(bind_timewait)
+{
+	self->addr.sin_family = AF_INET;
+	self->addr.sin_port = 0;
+	self->addr.sin_addr.s_addr = htonl(variant->addr_const);
+	self->addrlen = sizeof(self->addr);
+}
+
+FIXTURE_TEARDOWN(bind_timewait)
+{
+}
+
+void create_timewait_socket(struct __test_metadata *_metadata,
+			    FIXTURE_DATA(bind_timewait) *self)
+{
+	int server_fd, client_fd, child_fd, ret;
+	struct sockaddr_in addr;
+	socklen_t addrlen;
+
+	server_fd = socket(AF_INET, SOCK_STREAM, 0);
+	ASSERT_GT(server_fd, 0);
+
+	ret = bind(server_fd, (struct sockaddr *)&self->addr, self->addrlen);
+	ASSERT_EQ(ret, 0);
+
+	ret = listen(server_fd, 1);
+	ASSERT_EQ(ret, 0);
+
+	ret = getsockname(server_fd, (struct sockaddr *)&self->addr, &self->addrlen);
+	ASSERT_EQ(ret, 0);
+
+	client_fd = socket(AF_INET, SOCK_STREAM, 0);
+	ASSERT_GT(client_fd, 0);
+
+	ret = connect(client_fd, (struct sockaddr *)&self->addr, self->addrlen);
+	ASSERT_EQ(ret, 0);
+
+	addrlen = sizeof(addr);
+	child_fd = accept(server_fd, (struct sockaddr *)&addr, &addrlen);
+	ASSERT_GT(child_fd, 0);
+
+	close(child_fd);
+	close(client_fd);
+	close(server_fd);
+}
+
+TEST_F(bind_timewait, 1)
+{
+	int fd, ret;
+
+	create_timewait_socket(_metadata, self);
+
+	fd = socket(AF_INET, SOCK_STREAM, 0);
+	ASSERT_GT(fd, 0);
+
+	ret = bind(fd, (struct sockaddr *)&self->addr, self->addrlen);
+	ASSERT_EQ(ret, -1);
+	ASSERT_EQ(errno, EADDRINUSE);
+
+	close(fd);
+}
+
+TEST_HARNESS_MAIN

tools/testing/selftests/net/cmsg_sender.c

···
 
 static void cs_parse_args(int argc, char *argv[])
 {
-	char o;
+	int o;
 
 	while ((o = getopt(argc, argv, "46sS:p:m:M:d:tf:F:c:C:l:L:H:")) != -1) {
 		switch (o) {

tools/virtio/ringtest/main.h

···
 #define smp_wmb() smp_release()
 #endif
 
-#ifdef __alpha__
-#define smp_read_barrier_depends() smp_acquire()
-#else
-#define smp_read_barrier_depends() do {} while(0)
-#endif
-
 static __always_inline
 void __read_once_size(const volatile void *p, void *res, int size)
 {
-        switch (size) {                                                 \
-        case 1: *(unsigned char *)res = *(volatile unsigned char *)p; break;              \
-        case 2: *(unsigned short *)res = *(volatile unsigned short *)p; break;            \
-        case 4: *(unsigned int *)res = *(volatile unsigned int *)p; break;            \
-        case 8: *(unsigned long long *)res = *(volatile unsigned long long *)p; break;            \
-        default:                                                        \
-                barrier();                                              \
-                __builtin_memcpy((void *)res, (const void *)p, size);   \
-                barrier();                                              \
-        }                                                               \
+	switch (size) {
+	case 1: *(unsigned char *)res = *(volatile unsigned char *)p; break;
+	case 2: *(unsigned short *)res = *(volatile unsigned short *)p; break;
+	case 4: *(unsigned int *)res = *(volatile unsigned int *)p; break;
+	case 8: *(unsigned long long *)res = *(volatile unsigned long long *)p; break;
+	default:
+		barrier();
+		__builtin_memcpy((void *)res, (const void *)p, size);
+		barrier();
+	}
 }
 
 static __always_inline void __write_once_size(volatile void *p, void *res, int size)
···
 	}
 }
 
+#ifdef __alpha__
 #define READ_ONCE(x) \
 ({									\
 	union { typeof(x) __val; char __c[1]; } __u;			\
 	__read_once_size(&(x), __u.__c, sizeof(x));		\
-	smp_read_barrier_depends(); /* Enforce dependency ordering from x */ \
+	smp_mb(); /* Enforce dependency ordering from x */		\
 	__u.__val;							\
 })
+#else
+#define READ_ONCE(x)							\
+({									\
+	union { typeof(x) __val; char __c[1]; } __u;			\
+	__read_once_size(&(x), __u.__c, sizeof(x));			\
+	__u.__val;							\
+})
+#endif
 
 #define WRITE_ONCE(x, val) \
 ({							\

tools/virtio/virtio-trace/trace-agent-ctl.c

···
 
 		if (ret)
 			break;
-	};
+	}
 
 	return ret;
 

tools/virtio/virtio_test.c

···
 	long started = 0, completed = 0, next_reset = reset_n;
 	long completed_before, started_before;
 	int r, test = 1;
-	unsigned len;
+	unsigned int len;
 	long long spurious = 0;
 	const bool random_batch = batch == RANDOM_BATCH;
 

tools/virtio/vringh_test.c

···
 
 		gvdev.vdev.features = features;
 		INIT_LIST_HEAD(&gvdev.vdev.vqs);
+		spin_lock_init(&gvdev.vdev.vqs_list_lock);
 		gvdev.to_host_fd = to_host[1];
 		gvdev.notifies = 0;
 
···
 	getrange = getrange_iov;
 	vdev.features = 0;
 	INIT_LIST_HEAD(&vdev.vqs);
+	spin_lock_init(&vdev.vqs_list_lock);
 
 	while (argv[1]) {
 		if (strcmp(argv[1], "--indirect") == 0)

virt/kvm/kvm_mm.h

···
 #define KVM_MMU_LOCK_INIT(kvm)		rwlock_init(&(kvm)->mmu_lock)
 #define KVM_MMU_LOCK(kvm)		write_lock(&(kvm)->mmu_lock)
 #define KVM_MMU_UNLOCK(kvm)		write_unlock(&(kvm)->mmu_lock)
-#define KVM_MMU_READ_LOCK(kvm)		read_lock(&(kvm)->mmu_lock)
-#define KVM_MMU_READ_UNLOCK(kvm)	read_unlock(&(kvm)->mmu_lock)
 #else
 #define KVM_MMU_LOCK_INIT(kvm)		spin_lock_init(&(kvm)->mmu_lock)
 #define KVM_MMU_LOCK(kvm)		spin_lock(&(kvm)->mmu_lock)
 #define KVM_MMU_UNLOCK(kvm)		spin_unlock(&(kvm)->mmu_lock)
-#define KVM_MMU_READ_LOCK(kvm)		spin_lock(&(kvm)->mmu_lock)
-#define KVM_MMU_READ_UNLOCK(kvm)	spin_unlock(&(kvm)->mmu_lock)
 #endif /* KVM_HAVE_MMU_RWLOCK */
 
 kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool interruptible,