Merge tag 'powerpc-5.8-8' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc fix from Michael Ellerman:
 "Fix a bug introduced by the changes we made to lockless page table
  walking this cycle.

  When using the hash MMU, and perf with callchain recording, we can
  deadlock if the PMI interrupts a hash fault, and the callchain
  recording then takes a hash fault on the same page.

  Thanks to Nicholas Piggin, Aneesh Kumar K.V, Anton Blanchard, and
  Athira Rajeev"

* tag 'powerpc-5.8-8' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
  powerpc/64s/hash: Fix hash_preload running with interrupts enabled
diff --git a/.gitignore b/.gitignore
index 87b9dd8..d5f4804 100644
--- a/.gitignore
+++ b/.gitignore
@@ -143,6 +143,9 @@
 /allrandom.config
 /allyes.config
 
+# Kconfig savedefconfig output
+/defconfig
+
 # Kdevelop4
 *.kdev4
 
diff --git a/.mailmap b/.mailmap
index c69d9c7..db4f229 100644
--- a/.mailmap
+++ b/.mailmap
@@ -90,11 +90,16 @@
 Frank Zago <fzago@systemfabricworks.com>
 Gao Xiang <xiang@kernel.org> <gaoxiang25@huawei.com>
 Gao Xiang <xiang@kernel.org> <hsiangkao@aol.com>
+Gerald Schaefer <gerald.schaefer@linux.ibm.com> <gerald.schaefer@de.ibm.com>
+Gerald Schaefer <gerald.schaefer@linux.ibm.com> <geraldsc@de.ibm.com>
+Gerald Schaefer <gerald.schaefer@linux.ibm.com> <geraldsc@linux.vnet.ibm.com>
 Greg Kroah-Hartman <greg@echidna.(none)>
 Greg Kroah-Hartman <gregkh@suse.de>
 Greg Kroah-Hartman <greg@kroah.com>
 Gregory CLEMENT <gregory.clement@bootlin.com> <gregory.clement@free-electrons.com>
 Hanjun Guo <guohanjun@huawei.com> <hanjun.guo@linaro.org>
+Heiko Carstens <hca@linux.ibm.com> <h.carstens@de.ibm.com>
+Heiko Carstens <hca@linux.ibm.com> <heiko.carstens@de.ibm.com>
 Henk Vergonet <Henk.Vergonet@gmail.com>
 Henrik Kretzschmar <henne@nachtwindheim.de>
 Henrik Rydberg <rydberg@bitmath.org>
@@ -193,6 +198,9 @@
 Mayuresh Janorkar <mayur@ti.com>
 Michael Buesch <m@bues.ch>
 Michel Dänzer <michel@tungstengraphics.com>
+Mike Rapoport <rppt@kernel.org> <mike@compulab.co.il>
+Mike Rapoport <rppt@kernel.org> <mike.rapoport@gmail.com>
+Mike Rapoport <rppt@kernel.org> <rppt@linux.ibm.com>
 Miodrag Dinic <miodrag.dinic@mips.com> <miodrag.dinic@imgtec.com>
 Miquel Raynal <miquel.raynal@bootlin.com> <miquel.raynal@free-electrons.com>
 Mitesh shah <mshah@teja.com>
diff --git a/Documentation/ABI/testing/debugfs-driver-habanalabs b/Documentation/ABI/testing/debugfs-driver-habanalabs
index f6d9c2a..2e9ae31 100644
--- a/Documentation/ABI/testing/debugfs-driver-habanalabs
+++ b/Documentation/ABI/testing/debugfs-driver-habanalabs
@@ -16,7 +16,16 @@
                 gating mechanism in Gaudi. Due to how Gaudi is built, the
                 clock gating needs to be disabled in order to access the
                 registers of the TPC and MME engines. This is sometimes needed
-                during debug by the user and hence the user needs this option
+                during debug by the user and hence the user needs this option.
+                The user can supply a bitmask value, each bit represents
+                a different engine to disable/enable its clock gating feature.
+                The bitmask is composed of 20 bits:
+                0  -  7 : DMA channels
+                8  - 11 : MME engines
+                12 - 19 : TPC engines
+                The bit's location of a specific engine can be determined
+                using (1 << GAUDI_ENGINE_ID_*). GAUDI_ENGINE_ID_* values
+                are defined in uapi habanalabs.h file in enum gaudi_engine_id
 
 What:           /sys/kernel/debug/habanalabs/hl<n>/command_buffers
 Date:           Jan 2019
diff --git a/Documentation/ABI/testing/dev-kmsg b/Documentation/ABI/testing/dev-kmsg
index 1e6c28b..f307506 100644
--- a/Documentation/ABI/testing/dev-kmsg
+++ b/Documentation/ABI/testing/dev-kmsg
@@ -56,11 +56,6 @@
 		  seek after the last record available at the time
 		  the last SYSLOG_ACTION_CLEAR was issued.
 
-		Due to the record nature of this interface with a "read all"
-		behavior and the specific positions each seek operation sets,
-		SEEK_CUR is not supported, returning -ESPIPE (invalid seek) to
-		errno whenever requested.
-
 		The output format consists of a prefix carrying the syslog
 		prefix including priority and facility, the 64 bit message
 		sequence number and the monotonic timestamp in microseconds,
diff --git a/Documentation/ABI/testing/sysfs-platform-chipidea-usb-otg b/Documentation/ABI/testing/sysfs-platform-chipidea-usb-otg
index 151c595..f58cfb0 100644
--- a/Documentation/ABI/testing/sysfs-platform-chipidea-usb-otg
+++ b/Documentation/ABI/testing/sysfs-platform-chipidea-usb-otg
@@ -1,6 +1,6 @@
 What:		/sys/bus/platform/devices/ci_hdrc.0/inputs/a_bus_req
 Date:		Feb 2014
-Contact:	Li Jun <b47624@freescale.com>
+Contact:	Li Jun <jun.li@nxp.com>
 Description:
 		Can be set and read.
 		Set a_bus_req(A-device bus request) input to be 1 if
@@ -17,7 +17,7 @@
 
 What:		/sys/bus/platform/devices/ci_hdrc.0/inputs/a_bus_drop
 Date:		Feb 2014
-Contact:	Li Jun <b47624@freescale.com>
+Contact:	Li Jun <jun.li@nxp.com>
 Description:
 		Can be set and read
 		The a_bus_drop(A-device bus drop) input is 1 when the
@@ -32,7 +32,7 @@
 
 What:		/sys/bus/platform/devices/ci_hdrc.0/inputs/b_bus_req
 Date:		Feb 2014
-Contact:	Li Jun <b47624@freescale.com>
+Contact:	Li Jun <jun.li@nxp.com>
 Description:
 		Can be set and read.
 		The b_bus_req(B-device bus request) input is 1 during the time
@@ -47,7 +47,7 @@
 
 What:		/sys/bus/platform/devices/ci_hdrc.0/inputs/a_clr_err
 Date:		Feb 2014
-Contact:	Li Jun <b47624@freescale.com>
+Contact:	Li Jun <jun.li@nxp.com>
 Description:
 		Only can be set.
 		The a_clr_err(A-device Vbus error clear) input is used to clear
diff --git a/Documentation/admin-guide/README.rst b/Documentation/admin-guide/README.rst
index 5fb5269..5aad534 100644
--- a/Documentation/admin-guide/README.rst
+++ b/Documentation/admin-guide/README.rst
@@ -258,7 +258,7 @@
 Compiling the kernel
 --------------------
 
- - Make sure you have at least gcc 4.6 available.
+ - Make sure you have at least gcc 4.9 available.
    For more information, refer to :ref:`Documentation/process/changes.rst <changes>`.
 
    Please note that you can still run a.out user programs with this kernel.
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index ce3e05e..d09471a 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1356,8 +1356,8 @@
 
 	  thp_fault_alloc
 		Number of transparent hugepages which were allocated to satisfy
-		a page fault, including COW faults. This counter is not present
-		when CONFIG_TRANSPARENT_HUGEPAGE is not set.
+		a page fault. This counter is not present when CONFIG_TRANSPARENT_HUGEPAGE
+                is not set.
 
 	  thp_collapse_alloc
 		Number of transparent hugepages which were allocated to allow
diff --git a/Documentation/admin-guide/device-mapper/index.rst b/Documentation/admin-guide/device-mapper/index.rst
index ec62fcc..6cf8adc 100644
--- a/Documentation/admin-guide/device-mapper/index.rst
+++ b/Documentation/admin-guide/device-mapper/index.rst
@@ -11,6 +11,7 @@
     dm-clone
     dm-crypt
     dm-dust
+    dm-ebs
     dm-flakey
     dm-init
     dm-integrity
diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst
index 6a233e4..b2acd0d 100644
--- a/Documentation/admin-guide/mm/transhuge.rst
+++ b/Documentation/admin-guide/mm/transhuge.rst
@@ -305,8 +305,7 @@
 
 thp_fault_alloc
 	is incremented every time a huge page is successfully
-	allocated to handle a page fault. This applies to both the
-	first time a page is faulted and for COW faults.
+	allocated to handle a page fault.
 
 thp_collapse_alloc
 	is incremented by khugepaged when it has found
diff --git a/Documentation/arm64/cpu-feature-registers.rst b/Documentation/arm64/cpu-feature-registers.rst
index 314fa5b..f28853f 100644
--- a/Documentation/arm64/cpu-feature-registers.rst
+++ b/Documentation/arm64/cpu-feature-registers.rst
@@ -171,6 +171,7 @@
 
 
   3) ID_AA64PFR1_EL1 - Processor Feature Register 1
+
      +------------------------------+---------+---------+
      | Name                         |  bits   | visible |
      +------------------------------+---------+---------+
@@ -181,6 +182,7 @@
 
 
   4) MIDR_EL1 - Main ID Register
+
      +------------------------------+---------+---------+
      | Name                         |  bits   | visible |
      +------------------------------+---------+---------+
diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst
index 936cf2a..3f7c3a7 100644
--- a/Documentation/arm64/silicon-errata.rst
+++ b/Documentation/arm64/silicon-errata.rst
@@ -147,6 +147,14 @@
 +----------------+-----------------+-----------------+-----------------------------+
 | Qualcomm Tech. | Falkor v{1,2}   | E1041           | QCOM_FALKOR_ERRATUM_1041    |
 +----------------+-----------------+-----------------+-----------------------------+
+| Qualcomm Tech. | Kryo4xx Gold    | N/A             | ARM64_ERRATUM_1463225       |
++----------------+-----------------+-----------------+-----------------------------+
+| Qualcomm Tech. | Kryo4xx Gold    | N/A             | ARM64_ERRATUM_1418040       |
++----------------+-----------------+-----------------+-----------------------------+
+| Qualcomm Tech. | Kryo4xx Silver  | N/A             | ARM64_ERRATUM_1530923       |
++----------------+-----------------+-----------------+-----------------------------+
+| Qualcomm Tech. | Kryo4xx Silver  | N/A             | ARM64_ERRATUM_1024718       |
++----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+
 | Fujitsu        | A64FX           | E#010001        | FUJITSU_ERRATUM_010001      |
 +----------------+-----------------+-----------------+-----------------------------+
diff --git a/Documentation/block/bfq-iosched.rst b/Documentation/block/bfq-iosched.rst
index 0d237d4..19d4d15 100644
--- a/Documentation/block/bfq-iosched.rst
+++ b/Documentation/block/bfq-iosched.rst
@@ -492,13 +492,6 @@
 it with auto-tuning. An alternative way to achieve this goal is to
 just increase the value of timeout_sync, leaving max_budget equal to 0.
 
-weights
--------
-
-Read-only parameter, used to show the weights of the currently active
-BFQ queues.
-
-
 4. Group scheduling with BFQ
 ============================
 
@@ -566,7 +559,7 @@
 For each group, there is only the following parameter to set.
 
 weight (namely blkio.bfq.weight or io.bfq-weight): the weight of the
-group inside its parent. Available values: 1..10000 (default 100). The
+group inside its parent. Available values: 1..1000 (default 100). The
 linear mapping between ioprio and weights, described at the beginning
 of the tunable section, is still valid, but all weights higher than
 IOPRIO_BE_NR*10 are mapped to ioprio 0.
diff --git a/Documentation/bpf/prog_cgroup_sockopt.rst b/Documentation/bpf/prog_cgroup_sockopt.rst
index c47d9746..172f957 100644
--- a/Documentation/bpf/prog_cgroup_sockopt.rst
+++ b/Documentation/bpf/prog_cgroup_sockopt.rst
@@ -86,6 +86,20 @@
 *not* the original input ``setsockopt`` arguments. The potentially
 modified values will be then passed down to the kernel.
 
+Large optval
+============
+When the ``optval`` is greater than the ``PAGE_SIZE``, the BPF program
+can access only the first ``PAGE_SIZE`` of that data. So it has to options:
+
+* Set ``optlen`` to zero, which indicates that the kernel should
+  use the original buffer from the userspace. Any modifications
+  done by the BPF program to the ``optval`` are ignored.
+* Set ``optlen`` to the value less than ``PAGE_SIZE``, which
+  indicates that the kernel should use BPF's trimmed ``optval``.
+
+When the BPF program returns with the ``optlen`` greater than
+``PAGE_SIZE``, the userspace will receive ``EFAULT`` errno.
+
 Example
 =======
 
diff --git a/Documentation/core-api/dma-api.rst b/Documentation/core-api/dma-api.rst
index 2d8d2fe..f416204 100644
--- a/Documentation/core-api/dma-api.rst
+++ b/Documentation/core-api/dma-api.rst
@@ -206,6 +206,14 @@
 
 ::
 
+	bool
+	dma_need_sync(struct device *dev, dma_addr_t dma_addr);
+
+Returns %true if dma_sync_single_for_{device,cpu} calls are required to
+transfer memory ownership.  Returns %false if those calls can be skipped.
+
+::
+
 	unsigned long
 	dma_get_merge_boundary(struct device *dev);
 
diff --git a/Documentation/core-api/pin_user_pages.rst b/Documentation/core-api/pin_user_pages.rst
index 6068266..7ca8c7b 100644
--- a/Documentation/core-api/pin_user_pages.rst
+++ b/Documentation/core-api/pin_user_pages.rst
@@ -33,7 +33,7 @@
 pin_user_pages*() APIs are clearly distinct from the get_user_pages*() APIs, so
 that's a natural dividing line, and a good point to make separate wrapper calls.
 In other words, use pin_user_pages*() for DMA-pinned pages, and
-get_user_pages*() for other cases. There are four cases described later on in
+get_user_pages*() for other cases. There are five cases described later on in
 this document, to further clarify that concept.
 
 FOLL_PIN and FOLL_GET are mutually exclusive for a given gup call. However,
diff --git a/Documentation/dev-tools/kcsan.rst b/Documentation/dev-tools/kcsan.rst
index ce4bbd9..b38379f 100644
--- a/Documentation/dev-tools/kcsan.rst
+++ b/Documentation/dev-tools/kcsan.rst
@@ -114,12 +114,6 @@
   To dynamically limit for which functions to generate reports, see the
   `DebugFS interface`_ blacklist/whitelist feature.
 
-  For ``__always_inline`` functions, replace ``__always_inline`` with
-  ``__no_kcsan_or_inline`` (which implies ``__always_inline``)::
-
-    static __no_kcsan_or_inline void foo(void) {
-        ...
-
 * To disable data race detection for a particular compilation unit, add to the
   ``Makefile``::
 
diff --git a/Documentation/dev-tools/kunit/faq.rst b/Documentation/dev-tools/kunit/faq.rst
index ea55b24..1628862 100644
--- a/Documentation/dev-tools/kunit/faq.rst
+++ b/Documentation/dev-tools/kunit/faq.rst
@@ -61,3 +61,43 @@
   kernel by installing a production configuration of the kernel on production
   hardware with a production userspace and then trying to exercise some behavior
   that depends on interactions between the hardware, the kernel, and userspace.
+
+KUnit isn't working, what should I do?
+======================================
+
+Unfortunately, there are a number of things which can break, but here are some
+things to try.
+
+1. Try running ``./tools/testing/kunit/kunit.py run`` with the ``--raw_output``
+   parameter. This might show details or error messages hidden by the kunit_tool
+   parser.
+2. Instead of running ``kunit.py run``, try running ``kunit.py config``,
+   ``kunit.py build``, and ``kunit.py exec`` independently. This can help track
+   down where an issue is occurring. (If you think the parser is at fault, you
+   can run it manually against stdin or a file with ``kunit.py parse``.)
+3. Running the UML kernel directly can often reveal issues or error messages
+   kunit_tool ignores. This should be as simple as running ``./vmlinux`` after
+   building the UML kernel (e.g., by using ``kunit.py build``). Note that UML
+   has some unusual requirements (such as the host having a tmpfs filesystem
+   mounted), and has had issues in the past when built statically and the host
+   has KASLR enabled. (On older host kernels, you may need to run ``setarch
+   `uname -m` -R ./vmlinux`` to disable KASLR.)
+4. Make sure the kernel .config has ``CONFIG_KUNIT=y`` and at least one test
+   (e.g. ``CONFIG_KUNIT_EXAMPLE_TEST=y``). kunit_tool will keep its .config
+   around, so you can see what config was used after running ``kunit.py run``.
+   It also preserves any config changes you might make, so you can
+   enable/disable things with ``make ARCH=um menuconfig`` or similar, and then
+   re-run kunit_tool.
+5. Try to run ``make ARCH=um defconfig`` before running ``kunit.py run``. This
+   may help clean up any residual config items which could be causing problems.
+6. Finally, try running KUnit outside UML. KUnit and KUnit tests can run be
+   built into any kernel, or can be built as a module and loaded at runtime.
+   Doing so should allow you to determine if UML is causing the issue you're
+   seeing. When tests are built-in, they will execute when the kernel boots, and
+   modules will automatically execute associated tests when loaded. Test results
+   can be collected from ``/sys/kernel/debug/kunit/<test suite>/results``, and
+   can be parsed with ``kunit.py parse``. For more details, see "KUnit on
+   non-UML architectures" in :doc:`usage`.
+
+If none of the above tricks help, you are always welcome to email any issues to
+kunit-dev@googlegroups.com.
diff --git a/Documentation/devicetree/bindings/Makefile b/Documentation/devicetree/bindings/Makefile
index a638989..91c4d00 100644
--- a/Documentation/devicetree/bindings/Makefile
+++ b/Documentation/devicetree/bindings/Makefile
@@ -2,7 +2,6 @@
 DT_DOC_CHECKER ?= dt-doc-validate
 DT_EXTRACT_EX ?= dt-extract-example
 DT_MK_SCHEMA ?= dt-mk-schema
-DT_MK_SCHEMA_USERONLY_FLAG := $(if $(DT_SCHEMA_FILES), -u)
 
 DT_SCHEMA_MIN_VERSION = 2020.5
 
@@ -35,21 +34,40 @@
 
 DT_DOCS = $(shell $(find_cmd) | sed -e 's|^$(srctree)/||')
 
-DT_SCHEMA_FILES ?= $(DT_DOCS)
-
-extra-$(CHECK_DT_BINDING) += $(patsubst $(src)/%.yaml,%.example.dts, $(DT_SCHEMA_FILES))
-extra-$(CHECK_DT_BINDING) += $(patsubst $(src)/%.yaml,%.example.dt.yaml, $(DT_SCHEMA_FILES))
-extra-$(CHECK_DT_BINDING) += processed-schema-examples.yaml
-
 override DTC_FLAGS := \
 	-Wno-avoid_unnecessary_addr_size \
-	-Wno-graph_child_address
+	-Wno-graph_child_address \
+	-Wno-interrupt_provider
 
 $(obj)/processed-schema-examples.yaml: $(DT_DOCS) check_dtschema_version FORCE
 	$(call if_changed,mk_schema)
 
-$(obj)/processed-schema.yaml: DT_MK_SCHEMA_FLAGS := $(DT_MK_SCHEMA_USERONLY_FLAG)
+ifeq ($(DT_SCHEMA_FILES),)
+
+# Unless DT_SCHEMA_FILES is specified, use the full schema for dtbs_check too.
+# Just copy processed-schema-examples.yaml
+
+$(obj)/processed-schema.yaml: $(obj)/processed-schema-examples.yaml FORCE
+	$(call if_changed,copy)
+
+DT_SCHEMA_FILES = $(DT_DOCS)
+
+else
+
+# If DT_SCHEMA_FILES is specified, use it for processed-schema.yaml
+
+$(obj)/processed-schema.yaml: DT_MK_SCHEMA_FLAGS := -u
 $(obj)/processed-schema.yaml: $(DT_SCHEMA_FILES) check_dtschema_version FORCE
 	$(call if_changed,mk_schema)
 
-extra-y += processed-schema.yaml
+endif
+
+extra-$(CHECK_DT_BINDING) += $(patsubst $(src)/%.yaml,%.example.dts, $(DT_SCHEMA_FILES))
+extra-$(CHECK_DT_BINDING) += $(patsubst $(src)/%.yaml,%.example.dt.yaml, $(DT_SCHEMA_FILES))
+extra-$(CHECK_DT_BINDING) += processed-schema-examples.yaml
+extra-$(CHECK_DTBS) += processed-schema.yaml
+
+# Hack: avoid 'Argument list too long' error for 'make clean'. Remove most of
+# build artifacts here before they are processed by scripts/Makefile.clean
+clean-files = $(shell find $(obj) \( -name '*.example.dts' -o \
+			-name '*.example.dt.yaml' \) -delete 2>/dev/null)
diff --git a/Documentation/devicetree/bindings/arm/freescale/fsl,scu.txt b/Documentation/devicetree/bindings/arm/freescale/fsl,scu.txt
index 7150474..10b8459 100644
--- a/Documentation/devicetree/bindings/arm/freescale/fsl,scu.txt
+++ b/Documentation/devicetree/bindings/arm/freescale/fsl,scu.txt
@@ -47,7 +47,7 @@
 			  &lsio_mu1 1 2
 			  &lsio_mu1 1 3
 			  &lsio_mu1 3 3>;
-		See Documentation/devicetree/bindings/mailbox/fsl,mu.txt
+		See Documentation/devicetree/bindings/mailbox/fsl,mu.yaml
 		for detailed mailbox binding.
 
 Note: Each mu which supports general interrupt should have an alias correctly
diff --git a/Documentation/devicetree/bindings/bus/socionext,uniphier-system-bus.yaml b/Documentation/devicetree/bindings/bus/socionext,uniphier-system-bus.yaml
index c4c9119..a0c6c5d 100644
--- a/Documentation/devicetree/bindings/bus/socionext,uniphier-system-bus.yaml
+++ b/Documentation/devicetree/bindings/bus/socionext,uniphier-system-bus.yaml
@@ -80,14 +80,14 @@
         ranges = <1 0x00000000 0x42000000 0x02000000>,
                  <5 0x00000000 0x46000000 0x01000000>;
 
-        ethernet@1,01f00000 {
+        ethernet@1,1f00000 {
             compatible = "smsc,lan9115";
             reg = <1 0x01f00000 0x1000>;
             interrupts = <0 48 4>;
             phy-mode = "mii";
         };
 
-        uart@5,00200000 {
+        serial@5,200000 {
             compatible = "ns16550a";
             reg = <5 0x00200000 0x20>;
             interrupts = <0 49 4>;
diff --git a/Documentation/devicetree/bindings/clock/imx27-clock.yaml b/Documentation/devicetree/bindings/clock/imx27-clock.yaml
index b5f3ed0..a753654 100644
--- a/Documentation/devicetree/bindings/clock/imx27-clock.yaml
+++ b/Documentation/devicetree/bindings/clock/imx27-clock.yaml
@@ -7,7 +7,7 @@
 title: Clock bindings for Freescale i.MX27
 
 maintainers:
-  - Fabio Estevam <fabio.estevam@freescale.com>
+  - Fabio Estevam <fabio.estevam@nxp.com>
 
 description: |
   The clock consumer should specify the desired clock by having the clock
diff --git a/Documentation/devicetree/bindings/clock/imx31-clock.yaml b/Documentation/devicetree/bindings/clock/imx31-clock.yaml
index 1b6f75d..a25a374 100644
--- a/Documentation/devicetree/bindings/clock/imx31-clock.yaml
+++ b/Documentation/devicetree/bindings/clock/imx31-clock.yaml
@@ -7,7 +7,7 @@
 title: Clock bindings for Freescale i.MX31
 
 maintainers:
-  - Fabio Estevam <fabio.estevam@freescale.com>
+  - Fabio Estevam <fabio.estevam@nxp.com>
 
 description: |
   The clock consumer should specify the desired clock by having the clock
diff --git a/Documentation/devicetree/bindings/clock/imx5-clock.yaml b/Documentation/devicetree/bindings/clock/imx5-clock.yaml
index f5c2b3d..4d9e7c7 100644
--- a/Documentation/devicetree/bindings/clock/imx5-clock.yaml
+++ b/Documentation/devicetree/bindings/clock/imx5-clock.yaml
@@ -7,7 +7,7 @@
 title: Clock bindings for Freescale i.MX5
 
 maintainers:
-  - Fabio Estevam <fabio.estevam@freescale.com>
+  - Fabio Estevam <fabio.estevam@nxp.com>
 
 description: |
   The clock consumer should specify the desired clock by having the clock
diff --git a/Documentation/devicetree/bindings/display/bridge/sii902x.txt b/Documentation/devicetree/bindings/display/bridge/sii902x.txt
index 6e14e08..0d1db3f 100644
--- a/Documentation/devicetree/bindings/display/bridge/sii902x.txt
+++ b/Documentation/devicetree/bindings/display/bridge/sii902x.txt
@@ -37,7 +37,7 @@
 	simple-card or audio-graph-card binding. See their binding
 	documents on how to describe the way the sii902x device is
 	connected to the rest of the audio system:
-	Documentation/devicetree/bindings/sound/simple-card.txt
+	Documentation/devicetree/bindings/sound/simple-card.yaml
 	Documentation/devicetree/bindings/sound/audio-graph-card.txt
 	Note: In case of the audio-graph-card binding the used port
 	index should be 3.
diff --git a/Documentation/devicetree/bindings/display/imx/fsl-imx-drm.txt b/Documentation/devicetree/bindings/display/imx/fsl-imx-drm.txt
index 5bf77f6..5a99490 100644
--- a/Documentation/devicetree/bindings/display/imx/fsl-imx-drm.txt
+++ b/Documentation/devicetree/bindings/display/imx/fsl-imx-drm.txt
@@ -68,7 +68,7 @@
   datasheet
 - clocks : phandle to the PRE axi clock input, as described
   in Documentation/devicetree/bindings/clock/clock-bindings.txt and
-  Documentation/devicetree/bindings/clock/imx6q-clock.txt.
+  Documentation/devicetree/bindings/clock/imx6q-clock.yaml.
 - clock-names: should be "axi"
 - interrupts: should contain the PRE interrupt
 - fsl,iram: phandle pointing to the mmio-sram device node, that should be
@@ -94,7 +94,7 @@
   datasheet
 - clocks : phandles to the PRG ipg and axi clock inputs, as described
   in Documentation/devicetree/bindings/clock/clock-bindings.txt and
-  Documentation/devicetree/bindings/clock/imx6q-clock.txt.
+  Documentation/devicetree/bindings/clock/imx6q-clock.yaml.
 - clock-names: should be "ipg" and "axi"
 - fsl,pres: phandles to the PRE units attached to this PRG, with the fixed
   PRE as the first entry and the muxable PREs following.
diff --git a/Documentation/devicetree/bindings/display/imx/ldb.txt b/Documentation/devicetree/bindings/display/imx/ldb.txt
index 38c637f..8e6e7d7 100644
--- a/Documentation/devicetree/bindings/display/imx/ldb.txt
+++ b/Documentation/devicetree/bindings/display/imx/ldb.txt
@@ -30,8 +30,8 @@
                 "di2_sel" - IPU2 DI0 mux
                 "di3_sel" - IPU2 DI1 mux
         The needed clock numbers for each are documented in
-        Documentation/devicetree/bindings/clock/imx5-clock.txt, and in
-        Documentation/devicetree/bindings/clock/imx6q-clock.txt.
+        Documentation/devicetree/bindings/clock/imx5-clock.yaml, and in
+        Documentation/devicetree/bindings/clock/imx6q-clock.yaml.
 
 Optional properties:
  - pinctrl-names : should be "default" on i.MX53, not used on i.MX6q
diff --git a/Documentation/devicetree/bindings/display/panel/arm,versatile-tft-panel.yaml b/Documentation/devicetree/bindings/display/panel/arm,versatile-tft-panel.yaml
index 41fd571..be69e0c 100644
--- a/Documentation/devicetree/bindings/display/panel/arm,versatile-tft-panel.yaml
+++ b/Documentation/devicetree/bindings/display/panel/arm,versatile-tft-panel.yaml
@@ -33,7 +33,7 @@
 
 examples:
   - |
-    sysreg {
+    sysreg@0 {
         compatible = "arm,versatile-sysreg", "syscon", "simple-mfd";
         reg = <0x00000 0x1000>;
 
diff --git a/Documentation/devicetree/bindings/display/rockchip/rockchip-drm.yaml b/Documentation/devicetree/bindings/display/rockchip/rockchip-drm.yaml
index ec8ae74..7204da5 100644
--- a/Documentation/devicetree/bindings/display/rockchip/rockchip-drm.yaml
+++ b/Documentation/devicetree/bindings/display/rockchip/rockchip-drm.yaml
@@ -24,7 +24,7 @@
     description: |
       Should contain a list of phandles pointing to display interface port
       of vop devices. vop definitions as defined in
-      Documentation/devicetree/bindings/display/rockchip/rockchip-vop.txt
+      Documentation/devicetree/bindings/display/rockchip/rockchip-vop.yaml
 
 required:
   - compatible
diff --git a/Documentation/devicetree/bindings/gpio/mediatek,mt7621-gpio.txt b/Documentation/devicetree/bindings/gpio/mediatek,mt7621-gpio.txt
index ba45558..e1c49b6 100644
--- a/Documentation/devicetree/bindings/gpio/mediatek,mt7621-gpio.txt
+++ b/Documentation/devicetree/bindings/gpio/mediatek,mt7621-gpio.txt
@@ -12,7 +12,7 @@
    Only the GPIO_ACTIVE_HIGH and GPIO_ACTIVE_LOW flags are supported.
 - #interrupt-cells : Specifies the number of cells needed to encode an
    interrupt. Should be 2. The first cell defines the interrupt number,
-   the second encodes the triger flags encoded as described in
+   the second encodes the trigger flags encoded as described in
    Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
 - compatible:
   - "mediatek,mt7621-gpio" for Mediatek controllers
diff --git a/Documentation/devicetree/bindings/interrupt-controller/csky,mpintc.txt b/Documentation/devicetree/bindings/interrupt-controller/csky,mpintc.txt
index e134053..e6bbcae 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/csky,mpintc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/csky,mpintc.txt
@@ -10,7 +10,7 @@
  16-31  : private  irq, and we use 16 as the co-processor timer.
  31-1024: common irq for soc ip.
 
-Interrupt triger mode: (Defined in dt-bindings/interrupt-controller/irq.h)
+Interrupt trigger mode: (Defined in dt-bindings/interrupt-controller/irq.h)
  IRQ_TYPE_LEVEL_HIGH (default)
  IRQ_TYPE_LEVEL_LOW
  IRQ_TYPE_EDGE_RISING
diff --git a/Documentation/devicetree/bindings/mailbox/xlnx,zynqmp-ipi-mailbox.txt b/Documentation/devicetree/bindings/mailbox/xlnx,zynqmp-ipi-mailbox.txt
index 4438432..ad76edc 100644
--- a/Documentation/devicetree/bindings/mailbox/xlnx,zynqmp-ipi-mailbox.txt
+++ b/Documentation/devicetree/bindings/mailbox/xlnx,zynqmp-ipi-mailbox.txt
@@ -87,7 +87,7 @@
 		ranges;
 
 		/* APU<->RPU0 IPI mailbox controller */
-		ipi_mailbox_rpu0: mailbox@ff90400 {
+		ipi_mailbox_rpu0: mailbox@ff990400 {
 			reg = <0xff990400 0x20>,
 			      <0xff990420 0x20>,
 			      <0xff990080 0x20>,
diff --git a/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-video-engine.yaml b/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-video-engine.yaml
index 526593c..4cc1a67 100644
--- a/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-video-engine.yaml
+++ b/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-video-engine.yaml
@@ -47,6 +47,9 @@
     $ref: /schemas/types.yaml#/definitions/phandle-array
     description: Phandle to the device SRAM
 
+  iommus:
+    maxItems: 1
+
   memory-region:
     description:
       CMA pool to use for buffers allocation instead of the default
diff --git a/Documentation/devicetree/bindings/misc/olpc,xo1.75-ec.txt b/Documentation/devicetree/bindings/misc/olpc,xo1.75-ec.txt
index 8c4d649..2d7cdf1 100644
--- a/Documentation/devicetree/bindings/misc/olpc,xo1.75-ec.txt
+++ b/Documentation/devicetree/bindings/misc/olpc,xo1.75-ec.txt
@@ -8,7 +8,7 @@
 to receive a transfer (that is, when TX FIFO contains the response data) by
 strobing the ACK pin with the ready signal. See the "ready-gpios" property of the
 SSP binding as documented in:
-<Documentation/devicetree/bindings/spi/spi-pxa2xx.txt>.
+<Documentation/devicetree/bindings/spi/marvell,mmp2-ssp.yaml>.
 
 Example:
 	&ssp3 {
diff --git a/Documentation/devicetree/bindings/net/mediatek-bluetooth.txt b/Documentation/devicetree/bindings/net/mediatek-bluetooth.txt
index 219bcbd..9ef5bac 100644
--- a/Documentation/devicetree/bindings/net/mediatek-bluetooth.txt
+++ b/Documentation/devicetree/bindings/net/mediatek-bluetooth.txt
@@ -3,7 +3,7 @@
 
 This device is a serial attached device to BTIF device and thus it must be a
 child node of the serial node with BTIF. The dt-bindings details for BTIF
-device can be known via Documentation/devicetree/bindings/serial/8250.txt.
+device can be known via Documentation/devicetree/bindings/serial/8250.yaml.
 
 Required properties:
 
diff --git a/Documentation/devicetree/bindings/pinctrl/renesas,pfc-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/renesas,pfc-pinctrl.txt
index b686131..1b8e8b4 100644
--- a/Documentation/devicetree/bindings/pinctrl/renesas,pfc-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/renesas,pfc-pinctrl.txt
@@ -114,7 +114,7 @@
    [flags]>
 
 On other mach-shmobile platforms GPIO is handled by the gpio-rcar driver.
-Please refer to Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt
+Please refer to Documentation/devicetree/bindings/gpio/renesas,rcar-gpio.yaml
 for documentation of the GPIO device tree bindings on those platforms.
 
 
diff --git a/Documentation/devicetree/bindings/sound/audio-graph-card.txt b/Documentation/devicetree/bindings/sound/audio-graph-card.txt
index 2696826..d5f6919 100644
--- a/Documentation/devicetree/bindings/sound/audio-graph-card.txt
+++ b/Documentation/devicetree/bindings/sound/audio-graph-card.txt
@@ -5,7 +5,7 @@
 see ${LINUX}/Documentation/devicetree/bindings/graph.txt
 
 Basically, Audio Graph Card property is same as Simple Card.
-see ${LINUX}/Documentation/devicetree/bindings/sound/simple-card.txt
+see ${LINUX}/Documentation/devicetree/bindings/sound/simple-card.yaml
 
 Below are same as Simple-Card.
 
diff --git a/Documentation/devicetree/bindings/sound/simple-card.yaml b/Documentation/devicetree/bindings/sound/simple-card.yaml
index 8132d0c..35e6690 100644
--- a/Documentation/devicetree/bindings/sound/simple-card.yaml
+++ b/Documentation/devicetree/bindings/sound/simple-card.yaml
@@ -378,6 +378,8 @@
   - |
     sound {
         compatible = "simple-audio-card";
+        #address-cells = <1>;
+        #size-cells = <0>;
 
         simple-audio-card,name = "rsnd-ak4643";
         simple-audio-card,format = "left_j";
@@ -391,10 +393,12 @@
                                     "ak4642 Playback", "DAI1 Playback";
 
         dpcmcpu: simple-audio-card,cpu@0 {
+            reg = <0>;
             sound-dai = <&rcar_sound 0>;
         };
 
         simple-audio-card,cpu@1 {
+            reg = <1>;
             sound-dai = <&rcar_sound 1>;
         };
 
@@ -418,6 +422,8 @@
   - |
     sound {
         compatible = "simple-audio-card";
+        #address-cells = <1>;
+        #size-cells = <0>;
 
         simple-audio-card,routing =
             "pcm3168a Playback", "DAI1 Playback",
@@ -426,6 +432,7 @@
             "pcm3168a Playback", "DAI4 Playback";
 
         simple-audio-card,dai-link@0 {
+            reg = <0>;
             format = "left_j";
             bitclock-master = <&sndcpu0>;
             frame-master = <&sndcpu0>;
@@ -439,22 +446,23 @@
         };
 
         simple-audio-card,dai-link@1 {
+            reg = <1>;
             format = "i2s";
             bitclock-master = <&sndcpu1>;
             frame-master = <&sndcpu1>;
 
             convert-channels = <8>; /* TDM Split */
 
-            sndcpu1: cpu@0 {
+            sndcpu1: cpu0 {
                 sound-dai = <&rcar_sound 1>;
             };
-            cpu@1 {
+            cpu1 {
                 sound-dai = <&rcar_sound 2>;
             };
-            cpu@2 {
+            cpu2 {
                 sound-dai = <&rcar_sound 3>;
             };
-            cpu@3 {
+            cpu3 {
                 sound-dai = <&rcar_sound 4>;
             };
             codec {
@@ -466,6 +474,7 @@
         };
 
         simple-audio-card,dai-link@2 {
+            reg = <2>;
             format = "i2s";
             bitclock-master = <&sndcpu2>;
             frame-master = <&sndcpu2>;
diff --git a/Documentation/devicetree/bindings/sound/st,sti-asoc-card.txt b/Documentation/devicetree/bindings/sound/st,sti-asoc-card.txt
index 4d51f3f..a6ffcde 100644
--- a/Documentation/devicetree/bindings/sound/st,sti-asoc-card.txt
+++ b/Documentation/devicetree/bindings/sound/st,sti-asoc-card.txt
@@ -5,7 +5,7 @@
 
 sti sound drivers allows to expose sti SoC audio interface through the
 generic ASoC simple card. For details about sound card declaration please refer to
-Documentation/devicetree/bindings/sound/simple-card.txt.
+Documentation/devicetree/bindings/sound/simple-card.yaml.
 
 1) sti-uniperiph-dai: audio dai device.
 ---------------------------------------
diff --git a/Documentation/devicetree/bindings/spi/amlogic,meson-gx-spicc.yaml b/Documentation/devicetree/bindings/spi/amlogic,meson-gx-spicc.yaml
index 9147df2..38efb50 100644
--- a/Documentation/devicetree/bindings/spi/amlogic,meson-gx-spicc.yaml
+++ b/Documentation/devicetree/bindings/spi/amlogic,meson-gx-spicc.yaml
@@ -34,12 +34,15 @@
     maxItems: 1
 
   clocks:
-    maxItems: 1
+    minItems: 1
+    maxItems: 2
+    items:
+      - description: controller register bus clock
+      - description: baud rate generator and delay control clock
 
   clock-names:
-    description: input clock for the baud rate generator
-    items:
-      - const: core
+    minItems: 1
+    maxItems: 2
 
 if:
   properties:
@@ -51,17 +54,22 @@
 then:
   properties:
     clocks:
-      contains:
-        items:
-          - description: controller register bus clock
-          - description: baud rate generator and delay control clock
+      minItems: 2
 
     clock-names:
-      minItems: 2
       items:
         - const: core
         - const: pclk
 
+else:
+  properties:
+    clocks:
+      maxItems: 1
+
+    clock-names:
+      items:
+        - const: core
+
 required:
   - compatible
   - reg
diff --git a/Documentation/devicetree/bindings/spi/qcom,spi-geni-qcom.txt b/Documentation/devicetree/bindings/spi/qcom,spi-geni-qcom.txt
index 790311a..c8c1e91 100644
--- a/Documentation/devicetree/bindings/spi/qcom,spi-geni-qcom.txt
+++ b/Documentation/devicetree/bindings/spi/qcom,spi-geni-qcom.txt
@@ -19,7 +19,7 @@
 
 SPI Controller nodes must be child of GENI based Qualcomm Universal
 Peripharal. Please refer GENI based QUP wrapper controller node bindings
-described in Documentation/devicetree/bindings/soc/qcom/qcom,geni-se.txt.
+described in Documentation/devicetree/bindings/soc/qcom/qcom,geni-se.yaml.
 
 SPI slave nodes must be children of the SPI master node and conform to SPI bus
 binding as described in Documentation/devicetree/bindings/spi/spi-bus.txt.
diff --git a/Documentation/devicetree/bindings/thermal/thermal-sensor.yaml b/Documentation/devicetree/bindings/thermal/thermal-sensor.yaml
index fcd25a0..727d045 100644
--- a/Documentation/devicetree/bindings/thermal/thermal-sensor.yaml
+++ b/Documentation/devicetree/bindings/thermal/thermal-sensor.yaml
@@ -41,7 +41,7 @@
     #include <dt-bindings/interrupt-controller/arm-gic.h>
 
     // Example 1: SDM845 TSENS
-    soc: soc@0 {
+    soc: soc {
             #address-cells = <2>;
             #size-cells = <2>;
 
diff --git a/Documentation/devicetree/bindings/thermal/thermal-zones.yaml b/Documentation/devicetree/bindings/thermal/thermal-zones.yaml
index b8515d3..3ec9cc8 100644
--- a/Documentation/devicetree/bindings/thermal/thermal-zones.yaml
+++ b/Documentation/devicetree/bindings/thermal/thermal-zones.yaml
@@ -224,7 +224,7 @@
     #include <dt-bindings/thermal/thermal.h>
 
     // Example 1: SDM845 TSENS
-    soc: soc@0 {
+    soc {
             #address-cells = <2>;
             #size-cells = <2>;
 
diff --git a/Documentation/devicetree/bindings/thermal/ti,am654-thermal.yaml b/Documentation/devicetree/bindings/thermal/ti,am654-thermal.yaml
index 25b9209..ea14de8 100644
--- a/Documentation/devicetree/bindings/thermal/ti,am654-thermal.yaml
+++ b/Documentation/devicetree/bindings/thermal/ti,am654-thermal.yaml
@@ -35,7 +35,7 @@
     #include <dt-bindings/soc/ti,sci_pm_domain.h>
     vtm: thermal@42050000 {
         compatible = "ti,am654-vtm";
-        reg = <0x0 0x42050000 0x0 0x25c>;
+        reg = <0x42050000 0x25c>;
         power-domains = <&k3_pds 80 TI_SCI_PD_EXCLUSIVE>;
         #thermal-sensor-cells = <1>;
     };
diff --git a/Documentation/devicetree/bindings/timer/csky,mptimer.txt b/Documentation/devicetree/bindings/timer/csky,mptimer.txt
index 15cfec0..f5c7e99 100644
--- a/Documentation/devicetree/bindings/timer/csky,mptimer.txt
+++ b/Documentation/devicetree/bindings/timer/csky,mptimer.txt
@@ -8,7 +8,7 @@
  - PTIM_CTLR "cr<0, 14>" Control reg to start reset timer.
  - PTIM_TSR  "cr<1, 14>" Interrupt cleanup status reg.
  - PTIM_CCVR "cr<3, 14>" Current counter value reg.
- - PTIM_LVR  "cr<6, 14>" Window value reg to triger next event.
+ - PTIM_LVR  "cr<6, 14>" Window value reg to trigger next event.
 
 ==============================
 timer node bindings definition
diff --git a/Documentation/devicetree/bindings/usb/aspeed,usb-vhub.yaml b/Documentation/devicetree/bindings/usb/aspeed,usb-vhub.yaml
index e4e83d3..8b019ac 100644
--- a/Documentation/devicetree/bindings/usb/aspeed,usb-vhub.yaml
+++ b/Documentation/devicetree/bindings/usb/aspeed,usb-vhub.yaml
@@ -127,8 +127,8 @@
                 #address-cells = <1>;
                 #size-cells = <0>;
 
-                string@0409 {
-                        reg = <0x0409>;
+                string@409 {
+                        reg = <0x409>;
                         manufacturer = "ASPEED";
                         product = "USB Virtual Hub";
                         serial-number = "0000";
diff --git a/Documentation/devicetree/writing-schema.rst b/Documentation/devicetree/writing-schema.rst
index 220cf46..8c74a99 100644
--- a/Documentation/devicetree/writing-schema.rst
+++ b/Documentation/devicetree/writing-schema.rst
@@ -1,4 +1,4 @@
-:orphan:
+.. SPDX-License-Identifier: GPL-2.0
 
 Writing DeviceTree Bindings in json-schema
 ==========================================
@@ -124,9 +124,12 @@
 libyaml and its headers be installed on the host system. For some distributions
 that involves installing the development package, such as:
 
-Debian:
+Debian::
+
   apt-get install libyaml-dev
-Fedora:
+
+Fedora::
+
   dnf -y install libyaml-devel
 
 Running checks
diff --git a/Documentation/driver-api/ptp.rst b/Documentation/driver-api/ptp.rst
index a15192e..664838a 100644
--- a/Documentation/driver-api/ptp.rst
+++ b/Documentation/driver-api/ptp.rst
@@ -23,6 +23,7 @@
   + Ancillary clock features
     - Time stamp external events
     - Period output signals configurable from user space
+    - Low Pass Filter (LPF) access from user space
     - Synchronization of the Linux system time via the PPS subsystem
 
 PTP hardware clock kernel API
@@ -94,3 +95,14 @@
 
      - Auxiliary Slave/Master Mode Snapshot (optional interrupt)
      - Target Time (optional interrupt)
+
+   * Renesas (IDT) ClockMatrix™
+
+     - Up to 4 independent PHC channels
+     - Integrated low pass filter (LPF), access via .adjPhase (compliant to ITU-T G.8273.2)
+     - Programmable output periodic signals
+     - Programmable inputs can time stamp external triggers
+     - Driver and/or hardware configuration through firmware (idtcm.bin)
+          - LPF settings (bandwidth, phase limiting, automatic holdover, physical layer assist (per ITU-T G.8273.2))
+          - Programmable output PTP clocks, any frequency up to 1GHz (to other PHY/MAC time stampers, refclk to ASSPs/SoCs/FPGAs)
+          - Lock to GNSS input, automatic switching between GNSS and user-space PHC control (optional)
diff --git a/Documentation/filesystems/overlayfs.rst b/Documentation/filesystems/overlayfs.rst
index 660dbaf..fcda5d6 100644
--- a/Documentation/filesystems/overlayfs.rst
+++ b/Documentation/filesystems/overlayfs.rst
@@ -560,8 +560,8 @@
 verified on mount time to check that upper file handles are not stale.
 This verification may cause significant overhead in some cases.
 
-Note: the mount options index=off,nfs_export=on are conflicting and will
-result in an error.
+Note: the mount options index=off,nfs_export=on are conflicting for a
+read-write mount and will result in an error.
 
 
 Testsuite
diff --git a/Documentation/i2c/slave-eeprom-backend.rst b/Documentation/i2c/slave-eeprom-backend.rst
index 0b8cd83..38d951f 100644
--- a/Documentation/i2c/slave-eeprom-backend.rst
+++ b/Documentation/i2c/slave-eeprom-backend.rst
@@ -1,14 +1,26 @@
 ==============================
-Linux I2C slave eeprom backend
+Linux I2C slave EEPROM backend
 ==============================
 
-by Wolfram Sang <wsa@sang-engineering.com> in 2014-15
+by Wolfram Sang <wsa@sang-engineering.com> in 2014-20
 
-This is a proof-of-concept backend which acts like an EEPROM on the connected
-I2C bus. The memory contents can be modified from userspace via this file
-located in sysfs::
+This backend simulates an EEPROM on the connected I2C bus. Its memory contents
+can be accessed from userspace via this file located in sysfs::
 
 	/sys/bus/i2c/devices/<device-directory>/slave-eeprom
 
+The following types are available: 24c02, 24c32, 24c64, and 24c512. Read-only
+variants are also supported. The name needed for instantiating has the form
+'slave-<type>[ro]'. Examples follow:
+
+24c02, read/write, address 0x64:
+  # echo slave-24c02 0x1064 > /sys/bus/i2c/devices/i2c-1/new_device
+
+24c512, read-only, address 0x42:
+  # echo slave-24c512ro 0x1042 > /sys/bus/i2c/devices/i2c-1/new_device
+
+You can also preload data during boot if a device-property named
+'firmware-name' contains a valid filename (DT or ACPI only).
+
 As of 2015, Linux doesn't support poll on binary sysfs files, so there is no
 notification when another master changed the content.
diff --git a/Documentation/kbuild/modules.rst b/Documentation/kbuild/modules.rst
index a45cccf..85ccc87 100644
--- a/Documentation/kbuild/modules.rst
+++ b/Documentation/kbuild/modules.rst
@@ -182,7 +182,8 @@
 	8123_pci.c
 	8123_bin.o_shipped	<= Binary blob
 
---- 3.1 Shared Makefile
+3.1 Shared Makefile
+-------------------
 
 	An external module always includes a wrapper makefile that
 	supports building the module using "make" with no arguments.
@@ -470,9 +471,9 @@
 
 	The syntax of the Module.symvers file is::
 
-	<CRC>       <Symbol>         <Module>                         <Export Type>     <Namespace>
+		<CRC>       <Symbol>         <Module>                         <Export Type>     <Namespace>
 
-	0xe1cc2a05  usb_stor_suspend drivers/usb/storage/usb-storage  EXPORT_SYMBOL_GPL USB_STORAGE
+		0xe1cc2a05  usb_stor_suspend drivers/usb/storage/usb-storage  EXPORT_SYMBOL_GPL USB_STORAGE
 
 	The fields are separated by tabs and values may be empty (e.g.
 	if no namespace is defined for an exported symbol).
diff --git a/Documentation/kbuild/reproducible-builds.rst b/Documentation/kbuild/reproducible-builds.rst
index 5033938..3b25655 100644
--- a/Documentation/kbuild/reproducible-builds.rst
+++ b/Documentation/kbuild/reproducible-builds.rst
@@ -101,7 +101,7 @@
 
 If you enable ``CONFIG_GCC_PLUGIN_RANDSTRUCT``, you will need to
 pre-generate the random seed in
-``scripts/gcc-plgins/randomize_layout_seed.h`` so the same value
+``scripts/gcc-plugins/randomize_layout_seed.h`` so the same value
 is used in rebuilds.
 
 Debug info conflicts
diff --git a/Documentation/mips/ingenic-tcu.rst b/Documentation/mips/ingenic-tcu.rst
index c5a646b..2b75760 100644
--- a/Documentation/mips/ingenic-tcu.rst
+++ b/Documentation/mips/ingenic-tcu.rst
@@ -68,4 +68,4 @@
 drivers access their registers through the same regmap.
 
 For more information regarding the devicetree bindings of the TCU drivers,
-have a look at Documentation/devicetree/bindings/timer/ingenic,tcu.txt.
+have a look at Documentation/devicetree/bindings/timer/ingenic,tcu.yaml.
diff --git a/Documentation/networking/arcnet.rst b/Documentation/networking/arcnet.rst
index e93d982..82fce60 100644
--- a/Documentation/networking/arcnet.rst
+++ b/Documentation/networking/arcnet.rst
@@ -434,7 +434,7 @@
 	ifconfig arc0 insight
 	route add insight arc0
 	route add freedom arc0	/* I would use the subnet here (like I said
-					to to in "single protocol" above),
+					to in "single protocol" above),
 					but the rest of the subnet
 					unfortunately lies across the PPP
 					link on freedom, which confuses
diff --git a/Documentation/networking/ax25.rst b/Documentation/networking/ax25.rst
index 824afd7..f060cfb 100644
--- a/Documentation/networking/ax25.rst
+++ b/Documentation/networking/ax25.rst
@@ -6,7 +6,7 @@
 
 To use the amateur radio protocols within Linux you will need to get a
 suitable copy of the AX.25 Utilities. More detailed information about
-AX.25, NET/ROM and ROSE, associated programs and and utilities can be
+AX.25, NET/ROM and ROSE, associated programs and utilities can be
 found on http://www.linux-ax25.org.
 
 There is an active mailing list for discussing Linux amateur radio matters
diff --git a/Documentation/networking/bareudp.rst b/Documentation/networking/bareudp.rst
index 465a8b2..ff40656 100644
--- a/Documentation/networking/bareudp.rst
+++ b/Documentation/networking/bareudp.rst
@@ -26,7 +26,7 @@
 
 1) Device creation & deletion
 
-    a) ip link add dev bareudp0 type bareudp dstport 6635 ethertype 0x8847.
+    a) ip link add dev bareudp0 type bareudp dstport 6635 ethertype mpls_uc
 
        This creates a bareudp tunnel device which tunnels L3 traffic with ethertype
        0x8847 (MPLS traffic). The destination port of the UDP header will be set to
@@ -34,14 +34,21 @@
 
     b) ip link delete bareudp0
 
-2) Device creation with multiple proto mode enabled
+2) Device creation with multiproto mode enabled
 
-There are two ways to create a bareudp device for MPLS & IP with multiproto mode
-enabled.
+The multiproto mode allows bareudp tunnels to handle several protocols of the
+same family. It is currently only available for IP and MPLS. This mode has to
+be enabled explicitly with the "multiproto" flag.
 
-    a) ip link add dev  bareudp0 type bareudp dstport 6635 ethertype 0x8847 multiproto
+    a) ip link add dev bareudp0 type bareudp dstport 6635 ethertype ipv4 multiproto
 
-    b) ip link add dev  bareudp0 type bareudp dstport 6635 ethertype mpls
+       For an IPv4 tunnel the multiproto mode allows the tunnel to also handle
+       IPv6.
+
+    b) ip link add dev bareudp0 type bareudp dstport 6635 ethertype mpls_uc multiproto
+
+       For MPLS, the multiproto mode allows the tunnel to handle both unicast
+       and multicast MPLS packets.
 
 3) Device Usage
 
diff --git a/Documentation/networking/can_ucan_protocol.rst b/Documentation/networking/can_ucan_protocol.rst
index 4cef88d..638ac1e 100644
--- a/Documentation/networking/can_ucan_protocol.rst
+++ b/Documentation/networking/can_ucan_protocol.rst
@@ -144,7 +144,7 @@
 
 *Host2Dev; mandatory*
 
-Setup bittiming by sending the the structure
+Setup bittiming by sending the structure
 ``ucan_ctl_payload_t.cmd_set_bittiming`` (see ``struct bittiming`` for
 details)
 
@@ -232,7 +232,7 @@
   zero
 
 The CAN device has sent a message to the CAN bus. It answers with a
-list of of tuples <echo-ids, flags>.
+list of tuples <echo-ids, flags>.
 
 The echo-id identifies the frame from (echos the id from a previous
 UCAN_OUT_TX message). The flag indicates the result of the
diff --git a/Documentation/networking/dsa/dsa.rst b/Documentation/networking/dsa/dsa.rst
index 563d56c..a8d15dd 100644
--- a/Documentation/networking/dsa/dsa.rst
+++ b/Documentation/networking/dsa/dsa.rst
@@ -95,7 +95,7 @@
 Networking stack hooks
 ----------------------
 
-When a master netdev is used with DSA, a small hook is placed in in the
+When a master netdev is used with DSA, a small hook is placed in the
 networking stack is in order to have the DSA subsystem process the Ethernet
 switch specific tagging protocol. DSA accomplishes this by registering a
 specific (and fake) Ethernet type (later becoming ``skb->protocol``) with the
diff --git a/Documentation/networking/ieee802154.rst b/Documentation/networking/ieee802154.rst
index 36ca823..6f4bf84 100644
--- a/Documentation/networking/ieee802154.rst
+++ b/Documentation/networking/ieee802154.rst
@@ -30,8 +30,8 @@
 
 The address family, socket addresses etc. are defined in the
 include/net/af_ieee802154.h header or in the special header
-in the userspace package (see either http://wpan.cakelab.org/ or the
-git tree at https://github.com/linux-wpan/wpan-tools).
+in the userspace package (see either https://linux-wpan.org/wpan-tools.html
+or the git tree at https://github.com/linux-wpan/wpan-tools).
 
 6LoWPAN Linux implementation
 ============================
diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index b72f89d..837d51f 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -741,7 +741,7 @@
 
 	Default: 0x1
 
-	Note that that additional client or server features are only
+	Note that additional client or server features are only
 	effective if the basic support (0x1 and 0x2) are enabled respectively.
 
 tcp_fastopen_blackhole_timeout_sec - INTEGER
diff --git a/Documentation/networking/ipvs-sysctl.rst b/Documentation/networking/ipvs-sysctl.rst
index be36c46..2afccc6 100644
--- a/Documentation/networking/ipvs-sysctl.rst
+++ b/Documentation/networking/ipvs-sysctl.rst
@@ -114,7 +114,7 @@
 	modes (when there is no enough available memory, the strategy
 	is enabled and the variable is automatically set to 2,
 	otherwise the strategy is disabled and the variable is set to
-	1), and 3 means that that the strategy is always enabled.
+	1), and 3 means that the strategy is always enabled.
 
 drop_packet - INTEGER
 	- 0  - disabled (default)
diff --git a/Documentation/networking/rxrpc.rst b/Documentation/networking/rxrpc.rst
index 68552b9..39c2249 100644
--- a/Documentation/networking/rxrpc.rst
+++ b/Documentation/networking/rxrpc.rst
@@ -186,7 +186,7 @@
      time [tunable] after the last connection using it discarded, in case a new
      connection is made that could use it.
 
- (#) A client-side connection is only shared between calls if they have have
+ (#) A client-side connection is only shared between calls if they have
      the same key struct describing their security (and assuming the calls
      would otherwise share the connection).  Non-secured calls would also be
      able to share connections with each other.
diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst
index 5cfb54c..8f68e72 100644
--- a/Documentation/process/changes.rst
+++ b/Documentation/process/changes.rst
@@ -29,7 +29,7 @@
 ====================== ===============  ========================================
         Program        Minimal version       Command to check the version
 ====================== ===============  ========================================
-GNU C                  4.8              gcc --version
+GNU C                  4.9              gcc --version
 GNU make               3.81             make --version
 binutils               2.23             ld -v
 flex                   2.5.35           flex --version
diff --git a/Documentation/process/coding-style.rst b/Documentation/process/coding-style.rst
index 2657a55..1bee6f8 100644
--- a/Documentation/process/coding-style.rst
+++ b/Documentation/process/coding-style.rst
@@ -319,6 +319,26 @@
 problem, which is called the function-growth-hormone-imbalance syndrome.
 See chapter 6 (Functions).
 
+For symbol names and documentation, avoid introducing new usage of
+'master / slave' (or 'slave' independent of 'master') and 'blacklist /
+whitelist'.
+
+Recommended replacements for 'master / slave' are:
+    '{primary,main} / {secondary,replica,subordinate}'
+    '{initiator,requester} / {target,responder}'
+    '{controller,host} / {device,worker,proxy}'
+    'leader / follower'
+    'director / performer'
+
+Recommended replacements for 'blacklist/whitelist' are:
+    'denylist / allowlist'
+    'blocklist / passlist'
+
+Exceptions for introducing new usage is to maintain a userspace ABI/API,
+or when updating code for an existing (as of 2020) hardware or protocol
+specification that mandates those terms. For new specifications
+translate specification usage of the terminology to the kernel coding
+standard where possible.
 
 5) Typedefs
 -----------
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 426f945..320788f8 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -4339,14 +4339,15 @@
 #define KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE 0x00000001
 
   struct kvm_vmx_nested_state_hdr {
-	__u32 flags;
 	__u64 vmxon_pa;
 	__u64 vmcs12_pa;
-	__u64 preemption_timer_deadline;
 
 	struct {
 		__u16 flags;
 	} smm;
+
+	__u32 flags;
+	__u64 preemption_timer_deadline;
   };
 
   struct kvm_vmx_nested_state_data {
diff --git a/MAINTAINERS b/MAINTAINERS
index 7b5ffd6..b8d6c55 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1425,7 +1425,7 @@
 F:	arch/arm*/kernel/hw_breakpoint.c
 F:	arch/arm*/kernel/perf_*
 F:	arch/arm/oprofile/common.c
-F:	drivers/perf/*
+F:	drivers/perf/
 F:	include/linux/perf/arm_pmu.h
 
 ARM PORT
@@ -2929,6 +2929,7 @@
 
 ATMEL MACB ETHERNET DRIVER
 M:	Nicolas Ferre <nicolas.ferre@microchip.com>
+M:	Claudiu Beznea <claudiu.beznea@microchip.com>
 S:	Supported
 F:	drivers/net/ethernet/cadence/
 
@@ -3306,7 +3307,7 @@
 
 BPF JIT for S390
 M:	Ilya Leoshkevich <iii@linux.ibm.com>
-M:	Heiko Carstens <heiko.carstens@de.ibm.com>
+M:	Heiko Carstens <hca@linux.ibm.com>
 M:	Vasily Gorbik <gor@linux.ibm.com>
 L:	netdev@vger.kernel.org
 L:	bpf@vger.kernel.org
@@ -3946,7 +3947,7 @@
 S:	Supported
 F:	drivers/char/hw_random/cctrng.c
 F:	drivers/char/hw_random/cctrng.h
-F:	Documentation/devicetree/bindings/rng/arm-cctrng.txt
+F:	Documentation/devicetree/bindings/rng/arm-cctrng.yaml
 W:	https://developer.arm.com/products/system-ip/trustzone-cryptocell/cryptocell-700-family
 
 CEC FRAMEWORK
@@ -5021,7 +5022,6 @@
 F:	drivers/pinctrl/pinctrl-da90??.c
 F:	drivers/power/supply/da9052-battery.c
 F:	drivers/power/supply/da91??-*.c
-F:	drivers/regulator/da903x.c
 F:	drivers/regulator/da9???-regulator.[ch]
 F:	drivers/regulator/slg51000-regulator.[ch]
 F:	drivers/rtc/rtc-da90??.c
@@ -5111,7 +5111,7 @@
 L:	dmaengine@vger.kernel.org
 S:	Maintained
 Q:	https://patchwork.kernel.org/project/linux-dmaengine/list/
-T:	git git://git.infradead.org/users/vkoul/slave-dma.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine.git
 F:	Documentation/devicetree/bindings/dma/
 F:	Documentation/driver-api/dmaengine/
 F:	drivers/dma/
@@ -5490,7 +5490,7 @@
 DRM DRIVER FOR RAYDIUM RM67191 PANELS
 M:	Robert Chiras <robert.chiras@nxp.com>
 S:	Maintained
-F:	Documentation/devicetree/bindings/display/panel/raydium,rm67191.txt
+F:	Documentation/devicetree/bindings/display/panel/raydium,rm67191.yaml
 F:	drivers/gpu/drm/panel/panel-raydium-rm67191.c
 
 DRM DRIVER FOR ROCKTECH JH057N00900 PANELS
@@ -6956,6 +6956,7 @@
 M:	Nicolin Chen <nicoleotsuka@gmail.com>
 M:	Xiubo Li <Xiubo.Lee@gmail.com>
 R:	Fabio Estevam <festevam@gmail.com>
+R:	Shengjiu Wang <shengjiu.wang@gmail.com>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 L:	linuxppc-dev@lists.ozlabs.org
 S:	Maintained
@@ -8333,7 +8334,7 @@
 M:	Stefan Schmidt <stefan@datenfreihafen.org>
 L:	linux-wpan@vger.kernel.org
 S:	Maintained
-W:	http://wpan.cakelab.org/
+W:	https://linux-wpan.org/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sschmidt/wpan.git
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sschmidt/wpan-next.git
 F:	Documentation/networking/ieee802154.rst
@@ -9305,6 +9306,17 @@
 F:	scripts/Kconfig.include
 F:	scripts/kconfig/
 
+KCOV
+R:	Dmitry Vyukov <dvyukov@google.com>
+R:	Andrey Konovalov <andreyknvl@google.com>
+L:	kasan-dev@googlegroups.com
+S:	Maintained
+F:	Documentation/dev-tools/kcov.rst
+F:	include/linux/kcov.h
+F:	include/uapi/linux/kcov.h
+F:	kernel/kcov.c
+F:	scripts/Makefile.kcov
+
 KCSAN
 M:	Marco Elver <elver@google.com>
 R:	Dmitry Vyukov <dvyukov@google.com>
@@ -10808,7 +10820,7 @@
 F:	drivers/dma/mediatek/
 
 MEDIATEK ETHERNET DRIVER
-M:	Felix Fietkau <nbd@openwrt.org>
+M:	Felix Fietkau <nbd@nbd.name>
 M:	John Crispin <john@phrozen.org>
 M:	Sean Wang <sean.wang@mediatek.com>
 M:	Mark Lee <Mark-MC.Lee@mediatek.com>
@@ -11240,7 +11252,7 @@
 F:	drivers/crypto/atmel-ecc.*
 
 MICROCHIP I2C DRIVER
-M:	Ludovic Desroches <ludovic.desroches@microchip.com>
+M:	Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
 L:	linux-i2c@vger.kernel.org
 S:	Supported
 F:	drivers/i2c/busses/i2c-at91-*.c
@@ -11333,17 +11345,17 @@
 F:	include/dt-bindings/iio/adc/at91-sama5d2_adc.h
 
 MICROCHIP SAMA5D2-COMPATIBLE SHUTDOWN CONTROLLER
-M:	Nicolas Ferre <nicolas.ferre@microchip.com>
+M:	Claudiu Beznea <claudiu.beznea@microchip.com>
 S:	Supported
 F:	drivers/power/reset/at91-sama5d2_shdwc.c
 
 MICROCHIP SPI DRIVER
-M:	Nicolas Ferre <nicolas.ferre@microchip.com>
+M:	Tudor Ambarus <tudor.ambarus@microchip.com>
 S:	Supported
 F:	drivers/spi/spi-atmel.*
 
 MICROCHIP SSC DRIVER
-M:	Nicolas Ferre <nicolas.ferre@microchip.com>
+M:	Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Supported
 F:	drivers/misc/atmel-ssc.c
@@ -12695,13 +12707,13 @@
 
 OP-TEE DRIVER
 M:	Jens Wiklander <jens.wiklander@linaro.org>
-L:	tee-dev@lists.linaro.org
+L:	op-tee@lists.trustedfirmware.org
 S:	Maintained
 F:	drivers/tee/optee/
 
 OP-TEE RANDOM NUMBER GENERATOR (RNG) DRIVER
 M:	Sumit Garg <sumit.garg@linaro.org>
-L:	tee-dev@lists.linaro.org
+L:	op-tee@lists.trustedfirmware.org
 S:	Maintained
 F:	drivers/char/hw_random/optee-rng.c
 
@@ -14574,8 +14586,8 @@
 M:	Niklas Söderlund <niklas.soderlund@ragnatech.se>
 L:	linux-renesas-soc@vger.kernel.org
 S:	Supported
-F:	Documentation/devicetree/bindings/thermal/rcar-gen3-thermal.txt
-F:	Documentation/devicetree/bindings/thermal/rcar-thermal.txt
+F:	Documentation/devicetree/bindings/thermal/rcar-gen3-thermal.yaml
+F:	Documentation/devicetree/bindings/thermal/rcar-thermal.yaml
 F:	drivers/thermal/rcar_gen3_thermal.c
 F:	drivers/thermal/rcar_thermal.c
 
@@ -14831,7 +14843,7 @@
 F:	drivers/video/fbdev/savage/
 
 S390
-M:	Heiko Carstens <heiko.carstens@de.ibm.com>
+M:	Heiko Carstens <hca@linux.ibm.com>
 M:	Vasily Gorbik <gor@linux.ibm.com>
 M:	Christian Borntraeger <borntraeger@de.ibm.com>
 L:	linux-s390@vger.kernel.org
@@ -14862,7 +14874,8 @@
 F:	include/linux/dasd_mod.h
 
 S390 IOMMU (PCI)
-M:	Gerald Schaefer <gerald.schaefer@de.ibm.com>
+M:	Matthew Rosato <mjrosato@linux.ibm.com>
+M:	Gerald Schaefer <gerald.schaefer@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 S:	Supported
 W:	http://www.ibm.com/developerworks/linux/linux390/
@@ -14890,7 +14903,7 @@
 
 S390 PCI SUBSYSTEM
 M:	Niklas Schnelle <schnelle@linux.ibm.com>
-M:	Gerald Schaefer <gerald.schaefer@de.ibm.com>
+M:	Gerald Schaefer <gerald.schaefer@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 S:	Supported
 W:	http://www.ibm.com/developerworks/linux/linux390/
@@ -16058,8 +16071,10 @@
 M:	"Luc Van Oostenryck" <luc.vanoostenryck@gmail.com>
 L:	linux-sparse@vger.kernel.org
 S:	Maintained
-W:	https://sparse.wiki.kernel.org/
+W:	https://sparse.docs.kernel.org/
 T:	git git://git.kernel.org/pub/scm/devel/sparse/sparse.git
+Q:	https://patchwork.kernel.org/project/linux-sparse/list/
+B:	https://bugzilla.kernel.org/enter_bug.cgi?component=Sparse&product=Tools
 F:	include/linux/compiler.h
 
 SPEAR CLOCK FRAMEWORK SUPPORT
@@ -16772,7 +16787,7 @@
 
 TEE SUBSYSTEM
 M:	Jens Wiklander <jens.wiklander@linaro.org>
-L:	tee-dev@lists.linaro.org
+L:	op-tee@lists.trustedfirmware.org
 S:	Maintained
 F:	Documentation/tee.txt
 F:	drivers/tee/
@@ -17511,7 +17526,7 @@
 F:	fs/ufs/
 
 UHID USERSPACE HID IO DRIVER
-M:	David Herrmann <dh.herrmann@googlemail.com>
+M:	David Rheinsberg <david.rheinsberg@gmail.com>
 L:	linux-input@vger.kernel.org
 S:	Maintained
 F:	drivers/hid/uhid.c
@@ -18470,7 +18485,7 @@
 F:	drivers/rtc/rtc-sd3078.c
 
 WIIMOTE HID DRIVER
-M:	David Herrmann <dh.herrmann@googlemail.com>
+M:	David Rheinsberg <david.rheinsberg@gmail.com>
 L:	linux-input@vger.kernel.org
 S:	Maintained
 F:	drivers/hid/hid-wiimote*
diff --git a/Makefile b/Makefile
index ac2c61c..229e67f 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 8
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc7
 NAME = Kleptomaniac Octopus
 
 # *DOCUMENTATION*
@@ -567,7 +567,7 @@
 ifneq ($(CROSS_COMPILE),)
 CLANG_FLAGS	+= --target=$(notdir $(CROSS_COMPILE:%-=%))
 GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)elfedit))
-CLANG_FLAGS	+= --prefix=$(GCC_TOOLCHAIN_DIR)
+CLANG_FLAGS	+= --prefix=$(GCC_TOOLCHAIN_DIR)$(notdir $(CROSS_COMPILE))
 GCC_TOOLCHAIN	:= $(realpath $(GCC_TOOLCHAIN_DIR)/..)
 endif
 ifneq ($(GCC_TOOLCHAIN),)
@@ -970,8 +970,8 @@
 endif
 
 # Align the bit size of userspace programs with the kernel
-KBUILD_USERCFLAGS  += $(filter -m32 -m64, $(KBUILD_CFLAGS))
-KBUILD_USERLDFLAGS += $(filter -m32 -m64, $(KBUILD_CFLAGS))
+KBUILD_USERCFLAGS  += $(filter -m32 -m64 --target=%, $(KBUILD_CFLAGS))
+KBUILD_USERLDFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CFLAGS))
 
 # make the checker run with the right architecture
 CHECKFLAGS += --arch=$(ARCH)
@@ -1754,7 +1754,7 @@
 descend: $(build-dirs)
 $(build-dirs): prepare
 	$(Q)$(MAKE) $(build)=$@ \
-	single-build=$(if $(filter-out $@/, $(filter $@/%, $(single-no-ko))),1) \
+	single-build=$(if $(filter-out $@/, $(filter $@/%, $(KBUILD_SINGLE_TARGETS))),1) \
 	need-builtin=1 need-modorder=1
 
 clean-dirs := $(addprefix _clean_, $(clean-dirs))
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index fddc700..197896c 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -170,6 +170,15 @@
 
 endchoice
 
+config ARC_TUNE_MCPU
+	string "Override default -mcpu compiler flag"
+	default ""
+	help
+	  Override default -mcpu=xxx compiler flag (which is set depending on
+	  the ISA version) with the specified value.
+	  NOTE: If specified flag isn't supported by current compiler the
+	  ISA default value will be used as a fallback.
+
 config CPU_BIG_ENDIAN
 	bool "Enable Big Endian Mode"
 	help
@@ -465,6 +474,12 @@
 	  This is programmable and can be optionally disabled in which case
 	  software INTERRUPT_PROLOGUE/EPILGUE do the needed work
 
+config ARC_LPB_DISABLE
+	bool "Disable loop buffer (LPB)"
+	help
+	  On HS cores, loop buffer (LPB) is programmable in runtime and can
+	  be optionally disabled.
+
 endif # ISA_ARCV2
 
 endmenu   # "ARC CPU Configuration"
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index 20e9ab6..d00f8b8 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -10,8 +10,25 @@
 endif
 
 cflags-y	+= -fno-common -pipe -fno-builtin -mmedium-calls -D__linux__
-cflags-$(CONFIG_ISA_ARCOMPACT)	+= -mA7
-cflags-$(CONFIG_ISA_ARCV2)	+= -mcpu=hs38
+
+tune-mcpu-def-$(CONFIG_ISA_ARCOMPACT)	:= -mcpu=arc700
+tune-mcpu-def-$(CONFIG_ISA_ARCV2)	:= -mcpu=hs38
+
+ifeq ($(CONFIG_ARC_TUNE_MCPU),"")
+cflags-y				+= $(tune-mcpu-def-y)
+else
+tune-mcpu				:= $(shell echo $(CONFIG_ARC_TUNE_MCPU))
+tune-mcpu-ok 				:= $(call cc-option-yn, $(tune-mcpu))
+ifeq ($(tune-mcpu-ok),y)
+cflags-y				+= $(tune-mcpu)
+else
+# The flag provided by 'CONFIG_ARC_TUNE_MCPU' option isn't known by this compiler
+# (probably the compiler is too old). Use ISA default mcpu flag instead as a safe option.
+$(warning ** WARNING ** CONFIG_ARC_TUNE_MCPU flag '$(tune-mcpu)' is unknown, fallback to '$(tune-mcpu-def-y)')
+cflags-y				+= $(tune-mcpu-def-y)
+endif
+endif
+
 
 ifdef CONFIG_ARC_CURR_IN_REG
 # For a global register defintion, make sure it gets passed to every file
diff --git a/arch/arc/include/asm/elf.h b/arch/arc/include/asm/elf.h
index c77a0e3..0284ace 100644
--- a/arch/arc/include/asm/elf.h
+++ b/arch/arc/include/asm/elf.h
@@ -19,7 +19,7 @@
 #define  R_ARC_32_PCREL		0x31
 
 /*to set parameters in the core dumps */
-#define ELF_ARCH		EM_ARCOMPACT
+#define ELF_ARCH		EM_ARC_INUSE
 #define ELF_CLASS		ELFCLASS32
 
 #ifdef CONFIG_CPU_BIG_ENDIAN
diff --git a/arch/arc/include/asm/irqflags-compact.h b/arch/arc/include/asm/irqflags-compact.h
index 7fc73fe..863d63a 100644
--- a/arch/arc/include/asm/irqflags-compact.h
+++ b/arch/arc/include/asm/irqflags-compact.h
@@ -90,6 +90,9 @@
 /*
  * Unconditionally Enable IRQs
  */
+#ifdef CONFIG_ARC_COMPACT_IRQ_LEVELS
+extern void arch_local_irq_enable(void);
+#else
 static inline void arch_local_irq_enable(void)
 {
 	unsigned long temp;
@@ -102,7 +105,7 @@
 	: "n"((STATUS_E1_MASK | STATUS_E2_MASK))
 	: "cc", "memory");
 }
-
+#endif
 
 /*
  * Unconditionally Disable IRQs
diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S
index 60406ec..ea00c8a 100644
--- a/arch/arc/kernel/entry.S
+++ b/arch/arc/kernel/entry.S
@@ -165,7 +165,6 @@
 tracesys:
 	; save EFA in case tracer wants the PC of traced task
 	; using ERET won't work since next-PC has already committed
-	lr  r12, [efa]
 	GET_CURR_TASK_FIELD_PTR   TASK_THREAD, r11
 	st  r12, [r11, THREAD_FAULT_ADDR]	; thread.fault_address
 
@@ -208,15 +207,9 @@
 ; Breakpoint TRAP
 ; ---------------------------------------------
 trap_with_param:
-
-	; stop_pc info by gdb needs this info
-	lr  r0, [efa]
+	mov r0, r12	; EFA in case ptracer/gdb wants stop_pc
 	mov r1, sp
 
-	; Now that we have read EFA, it is safe to do "fake" rtie
-	;   and get out of CPU exception mode
-	FAKE_RET_FROM_EXCPN
-
 	; Save callee regs in case gdb wants to have a look
 	; SP will grow up by size of CALLEE Reg-File
 	; NOTE: clobbers r12
@@ -243,6 +236,10 @@
 
 	EXCEPTION_PROLOGUE
 
+	lr  r12, [efa]
+
+	FAKE_RET_FROM_EXCPN
+
 	;============ TRAP 1   :breakpoints
 	; Check ECR for trap with arg (PROLOGUE ensures r10 has ECR)
 	bmsk.f 0, r10, 7
@@ -250,9 +247,6 @@
 
 	;============ TRAP  (no param): syscall top level
 
-	; First return from Exception to pure K mode (Exception/IRQs renabled)
-	FAKE_RET_FROM_EXCPN
-
 	; If syscall tracing ongoing, invoke pre-post-hooks
 	GET_CURR_THR_INFO_FLAGS   r10
 	btst r10, TIF_SYSCALL_TRACE
diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S
index 6eb23f1..17fd1ed 100644
--- a/arch/arc/kernel/head.S
+++ b/arch/arc/kernel/head.S
@@ -59,6 +59,14 @@
 	bclr	r5, r5, STATUS_AD_BIT
 #endif
 	kflag	r5
+
+#ifdef CONFIG_ARC_LPB_DISABLE
+	lr	r5, [ARC_REG_LPB_BUILD]
+	breq    r5, 0, 1f		; LPB doesn't exist
+	mov	r5, 1
+	sr	r5, [ARC_REG_LPB_CTRL]
+1:
+#endif /* CONFIG_ARC_LPB_DISABLE */
 #endif
 	; Config DSP_CTRL properly, so kernel may use integer multiply,
 	; multiply-accumulate, and divide operations
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index dad8a65..41f07b3 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -58,10 +58,12 @@
 	{ 0x00,		NULL   }
 };
 
-static const struct id_to_str arc_cpu_rel[] = {
+static const struct id_to_str arc_hs_ver54_rel[] = {
 	/* UARCH.MAJOR,	Release */
 	{  0,		"R3.10a"},
 	{  1,		"R3.50a"},
+	{  2,		"R3.60a"},
+	{  3,		"R4.00a"},
 	{  0xFF,	NULL   }
 };
 
@@ -117,12 +119,6 @@
 	struct bcr_uarch_build_arcv2 uarch;
 	const struct id_to_str *tbl;
 
-	/*
-	 * Up until (including) the first core4 release (0x54) things were
-	 * simple: AUX IDENTITY.ARCVER was sufficient to identify arc family
-	 * and release: 0x50 to 0x53 was HS38, 0x54 was HS48 (dual issue)
-	 */
-
 	if (cpu->core.family < 0x54) { /* includes arc700 */
 
 		for (tbl = &arc_legacy_rel[0]; tbl->id != 0; tbl++) {
@@ -143,11 +139,10 @@
 	}
 
 	/*
-	 * However the subsequent HS release (same 0x54) allow HS38 or HS48
-	 * configurations and encode this info in a different BCR.
-	 * The BCR was introduced in 0x54 so can't be read unconditionally.
+	 * Initial HS cores bumped AUX IDENTITY.ARCVER for each release until
+	 * ARCVER 0x54 which introduced AUX MICRO_ARCH_BUILD and subsequent
+	 * releases only update it.
 	 */
-
 	READ_BCR(ARC_REG_MICRO_ARCH_BCR, uarch);
 
 	if (uarch.prod == 4) {
@@ -158,7 +153,7 @@
 		cpu->name = "HS38";
 	}
 
-	for (tbl = &arc_cpu_rel[0]; tbl->id != 0xFF; tbl++) {
+	for (tbl = &arc_hs_ver54_rel[0]; tbl->id != 0xFF; tbl++) {
 		if (uarch.maj == tbl->id) {
 			cpu->release = tbl->str;
 			break;
diff --git a/arch/arm/boot/dts/am335x-baltos.dtsi b/arch/arm/boot/dts/am335x-baltos.dtsi
index 05e7b5d..04f0b12 100644
--- a/arch/arm/boot/dts/am335x-baltos.dtsi
+++ b/arch/arm/boot/dts/am335x-baltos.dtsi
@@ -369,7 +369,7 @@
 &mmc2 {
 	status = "okay";
 	vmmc-supply = <&wl12xx_vmmc>;
-	ti,non-removable;
+	non-removable;
 	bus-width = <4>;
 	cap-power-off-card;
 	pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/am335x-boneblack-common.dtsi b/arch/arm/boot/dts/am335x-boneblack-common.dtsi
index 91f93bc..dd93222 100644
--- a/arch/arm/boot/dts/am335x-boneblack-common.dtsi
+++ b/arch/arm/boot/dts/am335x-boneblack-common.dtsi
@@ -22,6 +22,7 @@
 	pinctrl-0 = <&emmc_pins>;
 	bus-width = <8>;
 	status = "okay";
+	non-removable;
 };
 
 &am33xx_pinmux {
diff --git a/arch/arm/boot/dts/am335x-boneblack-wireless.dts b/arch/arm/boot/dts/am335x-boneblack-wireless.dts
index 3124d94..e07dd79 100644
--- a/arch/arm/boot/dts/am335x-boneblack-wireless.dts
+++ b/arch/arm/boot/dts/am335x-boneblack-wireless.dts
@@ -75,7 +75,6 @@
 	bus-width = <4>;
 	non-removable;
 	cap-power-off-card;
-	ti,needs-special-hs-handling;
 	keep-power-in-suspend;
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc3_pins &wl18xx_pins>;
diff --git a/arch/arm/boot/dts/am335x-boneblue.dts b/arch/arm/boot/dts/am335x-boneblue.dts
index 5811fb8..83f9452 100644
--- a/arch/arm/boot/dts/am335x-boneblue.dts
+++ b/arch/arm/boot/dts/am335x-boneblue.dts
@@ -367,7 +367,6 @@
 	bus-width = <4>;
 	non-removable;
 	cap-power-off-card;
-	ti,needs-special-hs-handling;
 	keep-power-in-suspend;
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc3_pins &wl18xx_pins>;
diff --git a/arch/arm/boot/dts/am335x-bonegreen-wireless.dts b/arch/arm/boot/dts/am335x-bonegreen-wireless.dts
index 4092cd1..609c8db 100644
--- a/arch/arm/boot/dts/am335x-bonegreen-wireless.dts
+++ b/arch/arm/boot/dts/am335x-bonegreen-wireless.dts
@@ -75,7 +75,6 @@
 	bus-width = <4>;
 	non-removable;
 	cap-power-off-card;
-	ti,needs-special-hs-handling;
 	keep-power-in-suspend;
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc3_pins &wl18xx_pins>;
diff --git a/arch/arm/boot/dts/am335x-evm.dts b/arch/arm/boot/dts/am335x-evm.dts
index 68252da..a4fc6b1 100644
--- a/arch/arm/boot/dts/am335x-evm.dts
+++ b/arch/arm/boot/dts/am335x-evm.dts
@@ -743,8 +743,7 @@
 	bus-width = <4>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&mmc3_pins &wlan_pins>;
-	ti,non-removable;
-	ti,needs-special-hs-handling;
+	non-removable;
 	cap-power-off-card;
 	keep-power-in-suspend;
 
diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts
index 32f515a..78b6e1f 100644
--- a/arch/arm/boot/dts/am335x-evmsk.dts
+++ b/arch/arm/boot/dts/am335x-evmsk.dts
@@ -655,7 +655,7 @@
 &mmc2 {
 	status = "okay";
 	vmmc-supply = <&wl12xx_vmmc>;
-	ti,non-removable;
+	non-removable;
 	bus-width = <4>;
 	cap-power-off-card;
 	keep-power-in-suspend;
diff --git a/arch/arm/boot/dts/am335x-lxm.dts b/arch/arm/boot/dts/am335x-lxm.dts
index fef5828..dbedf72 100644
--- a/arch/arm/boot/dts/am335x-lxm.dts
+++ b/arch/arm/boot/dts/am335x-lxm.dts
@@ -339,7 +339,7 @@
 	pinctrl-0 = <&emmc_pins>;
 	vmmc-supply = <&vmmcsd_fixed>;
 	bus-width = <8>;
-	ti,non-removable;
+	non-removable;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/am335x-moxa-uc-2100-common.dtsi b/arch/arm/boot/dts/am335x-moxa-uc-2100-common.dtsi
index 6495a12..4e90f9c 100644
--- a/arch/arm/boot/dts/am335x-moxa-uc-2100-common.dtsi
+++ b/arch/arm/boot/dts/am335x-moxa-uc-2100-common.dtsi
@@ -159,7 +159,7 @@
 	vmmc-supply = <&vmmcsd_fixed>;
 	bus-width = <8>;
 	pinctrl-0 = <&mmc1_pins_default>;
-	ti,non-removable;
+	non-removable;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/am335x-moxa-uc-8100-me-t.dts b/arch/arm/boot/dts/am335x-moxa-uc-8100-me-t.dts
index 244df9c..f03e72c 100644
--- a/arch/arm/boot/dts/am335x-moxa-uc-8100-me-t.dts
+++ b/arch/arm/boot/dts/am335x-moxa-uc-8100-me-t.dts
@@ -451,7 +451,7 @@
 	vmmc-supply = <&vmmcsd_fixed>;
 	bus-width = <8>;
 	pinctrl-0 = <&mmc2_pins_default>;
-	ti,non-removable;
+	non-removable;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/am335x-pepper.dts b/arch/arm/boot/dts/am335x-pepper.dts
index 6d7608d..f9a027b 100644
--- a/arch/arm/boot/dts/am335x-pepper.dts
+++ b/arch/arm/boot/dts/am335x-pepper.dts
@@ -341,7 +341,7 @@
 	pinctrl-0 = <&emmc_pins>;
 	vmmc-supply = <&ldo3_reg>;
 	bus-width = <8>;
-	ti,non-removable;
+	non-removable;
 };
 
 &mmc3 {
@@ -351,7 +351,7 @@
 	pinctrl-0 = <&wireless_pins>;
 	vmmmc-supply = <&v3v3c_reg>;
 	bus-width = <4>;
-	ti,non-removable;
+	non-removable;
 	dmas = <&edma_xbar 12 0 1
 		&edma_xbar 13 0 2>;
 	dma-names = "tx", "rx";
diff --git a/arch/arm/boot/dts/am335x-phycore-som.dtsi b/arch/arm/boot/dts/am335x-phycore-som.dtsi
index 3d0672b..7e46b4c 100644
--- a/arch/arm/boot/dts/am335x-phycore-som.dtsi
+++ b/arch/arm/boot/dts/am335x-phycore-som.dtsi
@@ -69,7 +69,7 @@
 	pinctrl-0 = <&emmc_pins>;
 	vmmc-supply = <&vmmc_reg>;
 	bus-width = <8>;
-	ti,non-removable;
+	non-removable;
 	status = "disabled";
 };
 
diff --git a/arch/arm/boot/dts/am335x-pocketbeagle.dts b/arch/arm/boot/dts/am335x-pocketbeagle.dts
index 4da7190..f0b2222 100644
--- a/arch/arm/boot/dts/am335x-pocketbeagle.dts
+++ b/arch/arm/boot/dts/am335x-pocketbeagle.dts
@@ -88,7 +88,6 @@
 			AM33XX_PADCONF(AM335X_PIN_MMC0_DAT3, PIN_INPUT_PULLUP, MUX_MODE0)
 			AM33XX_PADCONF(AM335X_PIN_MMC0_CMD, PIN_INPUT_PULLUP, MUX_MODE0)
 			AM33XX_PADCONF(AM335X_PIN_MMC0_CLK, PIN_INPUT_PULLUP, MUX_MODE0)
-			AM33XX_PADCONF(AM335X_PIN_MCASP0_ACLKR, PIN_INPUT, MUX_MODE4)		/* (B12) mcasp0_aclkr.mmc0_sdwp */
 		>;
 	};
 
diff --git a/arch/arm/boot/dts/am33xx-l4.dtsi b/arch/arm/boot/dts/am33xx-l4.dtsi
index 7ff11d6..a9cbefc 100644
--- a/arch/arm/boot/dts/am33xx-l4.dtsi
+++ b/arch/arm/boot/dts/am33xx-l4.dtsi
@@ -1335,10 +1335,8 @@
 			ranges = <0x0 0x60000 0x1000>;
 
 			mmc1: mmc@0 {
-				compatible = "ti,omap4-hsmmc";
-				ti,dual-volt;
+				compatible = "ti,am335-sdhci";
 				ti,needs-special-reset;
-				ti,needs-special-hs-handling;
 				dmas = <&edma_xbar 24 0 0
 					&edma_xbar 25 0 0>;
 				dma-names = "tx", "rx";
@@ -1816,7 +1814,7 @@
 			ranges = <0x0 0xd8000 0x1000>;
 
 			mmc2: mmc@0 {
-				compatible = "ti,omap4-hsmmc";
+				compatible = "ti,am335-sdhci";
 				ti,needs-special-reset;
 				dmas = <&edma 2 0
 					&edma 3 0>;
diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
index 3b177c9..5fdce10 100644
--- a/arch/arm/boot/dts/am33xx.dtsi
+++ b/arch/arm/boot/dts/am33xx.dtsi
@@ -322,10 +322,11 @@
 			ranges = <0x0 0x47810000 0x1000>;
 
 			mmc3: mmc@0 {
-				compatible = "ti,omap4-hsmmc";
+				compatible = "ti,am335-sdhci";
 				ti,needs-special-reset;
 				interrupts = <29>;
 				reg = <0x0 0x1000>;
+				status = "disabled";
 			};
 		};
 
@@ -335,7 +336,7 @@
 			      <0x47400010 0x4>;
 			reg-names = "rev", "sysc";
 			ti,sysc-mask = <(SYSC_OMAP4_FREEEMU |
-					 SYSC_OMAP2_SOFTRESET)>;
+					 SYSC_OMAP4_SOFTRESET)>;
 			ti,sysc-midle = <SYSC_IDLE_FORCE>,
 					<SYSC_IDLE_NO>,
 					<SYSC_IDLE_SMART>;
@@ -347,7 +348,7 @@
 			clock-names = "fck";
 			#address-cells = <1>;
 			#size-cells = <1>;
-			ranges = <0x0 0x47400000 0x5000>;
+			ranges = <0x0 0x47400000 0x8000>;
 
 			usb0_phy: usb-phy@1300 {
 				compatible = "ti,am335x-usb-phy";
diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi
index b4861f7..51ad9e8 100644
--- a/arch/arm/boot/dts/am4372.dtsi
+++ b/arch/arm/boot/dts/am4372.dtsi
@@ -316,10 +316,11 @@
 			ranges = <0x0 0x47810000 0x1000>;
 
 			mmc3: mmc@0 {
-				compatible = "ti,omap4-hsmmc";
+				compatible = "ti,am437-sdhci";
 				ti,needs-special-reset;
 				interrupts = <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>;
 				reg = <0x0 0x1000>;
+				status = "disabled";
 			};
 		};
 
diff --git a/arch/arm/boot/dts/am437x-cm-t43.dts b/arch/arm/boot/dts/am437x-cm-t43.dts
index 063113a..a6b4fca 100644
--- a/arch/arm/boot/dts/am437x-cm-t43.dts
+++ b/arch/arm/boot/dts/am437x-cm-t43.dts
@@ -291,7 +291,7 @@
 	pinctrl-0 = <&emmc_pins>;
 	vmmc-supply = <&vmmc_3v3>;
 	bus-width = <8>;
-	ti,non-removable;
+	non-removable;
 };
 
 &spi0 {
diff --git a/arch/arm/boot/dts/am437x-gp-evm.dts b/arch/arm/boot/dts/am437x-gp-evm.dts
index d692e3b..7737863 100644
--- a/arch/arm/boot/dts/am437x-gp-evm.dts
+++ b/arch/arm/boot/dts/am437x-gp-evm.dts
@@ -91,22 +91,6 @@
 
 		backlight = <&lcd_bl>;
 
-		panel-timing {
-			clock-frequency = <33000000>;
-			hactive = <800>;
-			vactive = <480>;
-			hfront-porch = <210>;
-			hback-porch = <16>;
-			hsync-len = <30>;
-			vback-porch = <10>;
-			vfront-porch = <22>;
-			vsync-len = <13>;
-			hsync-active = <0>;
-			vsync-active = <0>;
-			de-active = <1>;
-			pixelclk-active = <1>;
-		};
-
 		port {
 			lcd_in: endpoint {
 				remote-endpoint = <&dpi_out>;
@@ -869,7 +853,7 @@
 	pinctrl-names = "default", "sleep";
 	pinctrl-0 = <&emmc_pins_default>;
 	pinctrl-1 = <&emmc_pins_sleep>;
-	ti,non-removable;
+	non-removable;
 };
 
 &mmc3 {
@@ -886,7 +870,7 @@
 	pinctrl-1 = <&mmc3_pins_sleep>;
 	cap-power-off-card;
 	keep-power-in-suspend;
-	ti,non-removable;
+	non-removable;
 
 	#address-cells = <1>;
 	#size-cells = <0>;
diff --git a/arch/arm/boot/dts/am437x-l4.dtsi b/arch/arm/boot/dts/am437x-l4.dtsi
index 0d0f9fe..906ac29 100644
--- a/arch/arm/boot/dts/am437x-l4.dtsi
+++ b/arch/arm/boot/dts/am437x-l4.dtsi
@@ -1083,9 +1083,8 @@
 			ranges = <0x0 0x60000 0x1000>;
 
 			mmc1: mmc@0 {
-				compatible = "ti,omap4-hsmmc";
+				compatible = "ti,am437-sdhci";
 				reg = <0x0 0x1000>;
-				ti,dual-volt;
 				ti,needs-special-reset;
 				dmas = <&edma 24 0>,
 					<&edma 25 0>;
@@ -1541,8 +1540,9 @@
 			reg = <0xcc020 0x4>;
 			reg-names = "rev";
 			/* Domains (P, C): per_pwrdm, l4ls_clkdm */
-			clocks = <&l4ls_clkctrl AM4_L4LS_D_CAN0_CLKCTRL 0>;
-			clock-names = "fck";
+			clocks = <&l4ls_clkctrl AM4_L4LS_D_CAN0_CLKCTRL 0>,
+			<&dcan0_fck>;
+			clock-names = "fck", "osc";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x0 0xcc000 0x2000>;
@@ -1550,6 +1550,8 @@
 			dcan0: can@0 {
 				compatible = "ti,am4372-d_can", "ti,am3352-d_can";
 				reg = <0x0 0x2000>;
+				clocks = <&dcan0_fck>;
+				clock-names = "fck";
 				syscon-raminit = <&scm_conf 0x644 0>;
 				interrupts = <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>;
 				status = "disabled";
@@ -1561,8 +1563,9 @@
 			reg = <0xd0020 0x4>;
 			reg-names = "rev";
 			/* Domains (P, C): per_pwrdm, l4ls_clkdm */
-			clocks = <&l4ls_clkctrl AM4_L4LS_D_CAN1_CLKCTRL 0>;
-			clock-names = "fck";
+			clocks = <&l4ls_clkctrl AM4_L4LS_D_CAN1_CLKCTRL 0>,
+			<&dcan1_fck>;
+			clock-names = "fck", "osc";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x0 0xd0000 0x2000>;
@@ -1570,6 +1573,8 @@
 			dcan1: can@0 {
 				compatible = "ti,am4372-d_can", "ti,am3352-d_can";
 				reg = <0x0 0x2000>;
+				clocks = <&dcan1_fck>;
+				clock-name = "fck";
 				syscon-raminit = <&scm_conf 0x644 1>;
 				interrupts = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>;
 				status = "disabled";
@@ -1598,7 +1603,7 @@
 			ranges = <0x0 0xd8000 0x1000>;
 
 			mmc2: mmc@0 {
-				compatible = "ti,omap4-hsmmc";
+				compatible = "ti,am437-sdhci";
 				reg = <0x0 0x1000>;
 				ti,needs-special-reset;
 				dmas = <&edma 2 0>,
diff --git a/arch/arm/boot/dts/am437x-sk-evm.dts b/arch/arm/boot/dts/am437x-sk-evm.dts
index 4d5a7ca..08eabf0 100644
--- a/arch/arm/boot/dts/am437x-sk-evm.dts
+++ b/arch/arm/boot/dts/am437x-sk-evm.dts
@@ -134,22 +134,6 @@
 
 		enable-gpios = <&gpio1 7 GPIO_ACTIVE_HIGH>;
 
-		panel-timing {
-			clock-frequency = <9000000>;
-			hactive = <480>;
-			vactive = <272>;
-			hfront-porch = <2>;
-			hback-porch = <2>;
-			hsync-len = <41>;
-			vfront-porch = <2>;
-			vback-porch = <2>;
-			vsync-len = <10>;
-			hsync-active = <0>;
-			vsync-active = <0>;
-			de-active = <1>;
-			pixelclk-active = <1>;
-		};
-
 		port {
 			lcd_in: endpoint {
 				remote-endpoint = <&dpi_out>;
@@ -719,7 +703,7 @@
 	pinctrl-1 = <&mmc3_pins_sleep>;
 	cap-power-off-card;
 	keep-power-in-suspend;
-	ti,non-removable;
+	non-removable;
 
 	#address-cells = <1>;
 	#size-cells = <0>;
diff --git a/arch/arm/boot/dts/am43x-epos-evm.dts b/arch/arm/boot/dts/am43x-epos-evm.dts
index 27259fd..7d4e0df 100644
--- a/arch/arm/boot/dts/am43x-epos-evm.dts
+++ b/arch/arm/boot/dts/am43x-epos-evm.dts
@@ -47,22 +47,6 @@
 
 		backlight = <&lcd_bl>;
 
-		panel-timing {
-			clock-frequency = <33000000>;
-			hactive = <800>;
-			vactive = <480>;
-			hfront-porch = <210>;
-			hback-porch = <16>;
-			hsync-len = <30>;
-			vback-porch = <10>;
-			vfront-porch = <22>;
-			vsync-len = <13>;
-			hsync-active = <0>;
-			vsync-active = <0>;
-			de-active = <1>;
-			pixelclk-active = <1>;
-		};
-
 		port {
 			lcd_in: endpoint {
 				remote-endpoint = <&dpi_out>;
diff --git a/arch/arm/boot/dts/am5729-beagleboneai.dts b/arch/arm/boot/dts/am5729-beagleboneai.dts
index 9877d77..4c51c6b 100644
--- a/arch/arm/boot/dts/am5729-beagleboneai.dts
+++ b/arch/arm/boot/dts/am5729-beagleboneai.dts
@@ -505,7 +505,7 @@
 
 &cpsw_emac0 {
 	phy-handle = <&phy0>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-rxid";
 };
 
 &ocp {
diff --git a/arch/arm/boot/dts/armada-38x.dtsi b/arch/arm/boot/dts/armada-38x.dtsi
index 3481165..9b1a24c 100644
--- a/arch/arm/boot/dts/armada-38x.dtsi
+++ b/arch/arm/boot/dts/armada-38x.dtsi
@@ -342,7 +342,8 @@
 
 			comphy: phy@18300 {
 				compatible = "marvell,armada-380-comphy";
-				reg = <0x18300 0x100>;
+				reg-names = "comphy", "conf";
+				reg = <0x18300 0x100>, <0x18460 4>;
 				#address-cells = <1>;
 				#size-cells = <0>;
 
diff --git a/arch/arm/boot/dts/bcm-nsp.dtsi b/arch/arm/boot/dts/bcm-nsp.dtsi
index da6d70f..3175266 100644
--- a/arch/arm/boot/dts/bcm-nsp.dtsi
+++ b/arch/arm/boot/dts/bcm-nsp.dtsi
@@ -200,7 +200,7 @@
 			status = "disabled";
 		};
 
-		dma@20000 {
+		dma: dma@20000 {
 			compatible = "arm,pl330", "arm,primecell";
 			reg = <0x20000 0x1000>;
 			interrupts = <GIC_SPI 47 IRQ_TYPE_LEVEL_HIGH>,
@@ -215,6 +215,8 @@
 			clocks = <&iprocslow>;
 			clock-names = "apb_pclk";
 			#dma-cells = <1>;
+			dma-coherent;
+			status = "disabled";
 		};
 
 		sdio: sdhci@21000 {
@@ -257,10 +259,10 @@
 			status = "disabled";
 		};
 
-		mailbox: mailbox@25000 {
+		mailbox: mailbox@25c00 {
 			compatible = "brcm,iproc-fa2-mbox";
-			reg = <0x25000 0x445>;
-			interrupts = <GIC_SPI 150 IRQ_TYPE_LEVEL_HIGH>;
+			reg = <0x25c00 0x400>;
+			interrupts = <GIC_SPI 151 IRQ_TYPE_LEVEL_HIGH>;
 			#mbox-cells = <1>;
 			brcm,rx-status-len = <32>;
 			brcm,use-bcm-hdr;
diff --git a/arch/arm/boot/dts/bcm47094-luxul-xwc-2000.dts b/arch/arm/boot/dts/bcm47094-luxul-xwc-2000.dts
index 3343253..29bbecd 100644
--- a/arch/arm/boot/dts/bcm47094-luxul-xwc-2000.dts
+++ b/arch/arm/boot/dts/bcm47094-luxul-xwc-2000.dts
@@ -17,6 +17,7 @@
 	};
 
 	memory {
+		device_type = "memory";
 		reg = <0x00000000 0x08000000
 		       0x88000000 0x18000000>;
 	};
diff --git a/arch/arm/boot/dts/bcm958522er.dts b/arch/arm/boot/dts/bcm958522er.dts
index 8c388eb..7be4c4e 100644
--- a/arch/arm/boot/dts/bcm958522er.dts
+++ b/arch/arm/boot/dts/bcm958522er.dts
@@ -58,6 +58,10 @@
 
 /* USB 3 support needed to be complete */
 
+&dma {
+	status = "okay";
+};
+
 &amac0 {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/bcm958525er.dts b/arch/arm/boot/dts/bcm958525er.dts
index c339771..e58ed7e 100644
--- a/arch/arm/boot/dts/bcm958525er.dts
+++ b/arch/arm/boot/dts/bcm958525er.dts
@@ -58,6 +58,10 @@
 
 /* USB 3 support needed to be complete */
 
+&dma {
+	status = "okay";
+};
+
 &amac0 {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/bcm958525xmc.dts b/arch/arm/boot/dts/bcm958525xmc.dts
index 1c72ec8..716da62 100644
--- a/arch/arm/boot/dts/bcm958525xmc.dts
+++ b/arch/arm/boot/dts/bcm958525xmc.dts
@@ -58,6 +58,10 @@
 
 /* XHCI support needed to be complete */
 
+&dma {
+	status = "okay";
+};
+
 &amac0 {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/bcm958622hr.dts b/arch/arm/boot/dts/bcm958622hr.dts
index 96a021c..a49c2fd 100644
--- a/arch/arm/boot/dts/bcm958622hr.dts
+++ b/arch/arm/boot/dts/bcm958622hr.dts
@@ -58,6 +58,10 @@
 
 /* USB 3 and SLIC support needed to be complete */
 
+&dma {
+	status = "okay";
+};
+
 &amac0 {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/bcm958623hr.dts b/arch/arm/boot/dts/bcm958623hr.dts
index b2c7f21..dd6dff6 100644
--- a/arch/arm/boot/dts/bcm958623hr.dts
+++ b/arch/arm/boot/dts/bcm958623hr.dts
@@ -58,6 +58,10 @@
 
 /* USB 3 and SLIC support needed to be complete */
 
+&dma {
+	status = "okay";
+};
+
 &amac0 {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/bcm958625hr.dts b/arch/arm/boot/dts/bcm958625hr.dts
index 536fb24..a71371b 100644
--- a/arch/arm/boot/dts/bcm958625hr.dts
+++ b/arch/arm/boot/dts/bcm958625hr.dts
@@ -69,6 +69,10 @@
 	status = "okay";
 };
 
+&dma {
+	status = "okay";
+};
+
 &amac0 {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/bcm958625k.dts b/arch/arm/boot/dts/bcm958625k.dts
index 3fcca12..7b84b54 100644
--- a/arch/arm/boot/dts/bcm958625k.dts
+++ b/arch/arm/boot/dts/bcm958625k.dts
@@ -48,6 +48,10 @@
 	};
 };
 
+&dma {
+	status = "okay";
+};
+
 &amac0 {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/dra7-evm-common.dtsi b/arch/arm/boot/dts/dra7-evm-common.dtsi
index f89a64c..2cf6a52 100644
--- a/arch/arm/boot/dts/dra7-evm-common.dtsi
+++ b/arch/arm/boot/dts/dra7-evm-common.dtsi
@@ -245,26 +245,6 @@
 	rx-num-evt = <32>;
 };
 
-&mailbox5 {
-	status = "okay";
-	mbox_ipu1_ipc3x: mbox_ipu1_ipc3x {
-		status = "okay";
-	};
-	mbox_dsp1_ipc3x: mbox_dsp1_ipc3x {
-		status = "okay";
-	};
-};
-
-&mailbox6 {
-	status = "okay";
-	mbox_ipu2_ipc3x: mbox_ipu2_ipc3x {
-		status = "okay";
-	};
-	mbox_dsp2_ipc3x: mbox_dsp2_ipc3x {
-		status = "okay";
-	};
-};
-
 &pcie1_rc {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/dra7-l4.dtsi b/arch/arm/boot/dts/dra7-l4.dtsi
index 62ca895..0c6f266 100644
--- a/arch/arm/boot/dts/dra7-l4.dtsi
+++ b/arch/arm/boot/dts/dra7-l4.dtsi
@@ -1207,9 +1207,8 @@
 					<SYSC_IDLE_SMART>,
 					<SYSC_IDLE_SMART_WKUP>;
 			/* Domains (P, C): l4per_pwrdm, l4per_clkdm */
-			clocks = <&l4per_clkctrl DRA7_L4PER_TIMER4_CLKCTRL 0>,
-				 <&timer_sys_clk_div>;
-			clock-names = "fck", "timer_sys_ck";
+			clocks = <&l4per_clkctrl DRA7_L4PER_TIMER4_CLKCTRL 0>;
+			clock-names = "fck";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x0 0x36000 0x1000>;
@@ -3352,8 +3351,8 @@
 					<SYSC_IDLE_SMART>,
 					<SYSC_IDLE_SMART_WKUP>;
 			/* Domains (P, C): ipu_pwrdm, ipu_clkdm */
-			clocks = <&ipu_clkctrl DRA7_IPU_TIMER5_CLKCTRL 0>, <&timer_sys_clk_div>;
-			clock-names = "fck", "timer_sys_ck";
+			clocks = <&ipu_clkctrl DRA7_IPU_TIMER5_CLKCTRL 0>;
+			clock-names = "fck";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x0 0x20000 0x1000>;
@@ -3361,8 +3360,8 @@
 			timer5: timer@0 {
 				compatible = "ti,omap5430-timer";
 				reg = <0x0 0x80>;
-				clocks = <&ipu_clkctrl DRA7_IPU_TIMER5_CLKCTRL 24>;
-				clock-names = "fck";
+				clocks = <&ipu_clkctrl DRA7_IPU_TIMER5_CLKCTRL 24>, <&timer_sys_clk_div>;
+				clock-names = "fck", "timer_sys_ck";
 				interrupts = <GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>;
 			};
 		};
@@ -3379,9 +3378,8 @@
 					<SYSC_IDLE_SMART>,
 					<SYSC_IDLE_SMART_WKUP>;
 			/* Domains (P, C): ipu_pwrdm, ipu_clkdm */
-			clocks = <&ipu_clkctrl DRA7_IPU_TIMER6_CLKCTRL 0>,
-				 <&timer_sys_clk_div>;
-			clock-names = "fck", "timer_sys_ck";
+			clocks = <&ipu_clkctrl DRA7_IPU_TIMER6_CLKCTRL 0>;
+			clock-names = "fck";
 			#address-cells = <1>;
 			#size-cells = <1>;
 			ranges = <0x0 0x22000 0x1000>;
@@ -3389,8 +3387,8 @@
 			timer6: timer@0 {
 				compatible = "ti,omap5430-timer";
 				reg = <0x0 0x80>;
-				clocks = <&ipu_clkctrl DRA7_IPU_TIMER6_CLKCTRL 24>;
-				clock-names = "fck";
+				clocks = <&ipu_clkctrl DRA7_IPU_TIMER6_CLKCTRL 24>, <&timer_sys_clk_div>;
+				clock-names = "fck", "timer_sys_ck";
 				interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>;
 			};
 		};
@@ -3498,8 +3496,8 @@
 			timer14: timer@0 {
 				compatible = "ti,omap5430-timer";
 				reg = <0x0 0x80>;
-				clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER14_CLKCTRL 24>;
-				clock-names = "fck";
+				clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER14_CLKCTRL 24>, <&timer_sys_clk_div>;
+				clock-names = "fck", "timer_sys_ck";
 				interrupts = <GIC_SPI 340 IRQ_TYPE_LEVEL_HIGH>;
 				ti,timer-pwm;
 			};
@@ -3526,8 +3524,8 @@
 			timer15: timer@0 {
 				compatible = "ti,omap5430-timer";
 				reg = <0x0 0x80>;
-				clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER15_CLKCTRL 24>;
-				clock-names = "fck";
+				clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER15_CLKCTRL 24>, <&timer_sys_clk_div>;
+				clock-names = "fck", "timer_sys_ck";
 				interrupts = <GIC_SPI 341 IRQ_TYPE_LEVEL_HIGH>;
 				ti,timer-pwm;
 			};
@@ -3554,8 +3552,8 @@
 			timer16: timer@0 {
 				compatible = "ti,omap5430-timer";
 				reg = <0x0 0x80>;
-				clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER16_CLKCTRL 24>;
-				clock-names = "fck";
+				clocks = <&l4per3_clkctrl DRA7_L4PER3_TIMER16_CLKCTRL 24>, <&timer_sys_clk_div>;
+				clock-names = "fck", "timer_sys_ck";
 				interrupts = <GIC_SPI 342 IRQ_TYPE_LEVEL_HIGH>;
 				ti,timer-pwm;
 			};
diff --git a/arch/arm/boot/dts/imx6qdl-gw551x.dtsi b/arch/arm/boot/dts/imx6qdl-gw551x.dtsi
index c38e86e..8c33510 100644
--- a/arch/arm/boot/dts/imx6qdl-gw551x.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-gw551x.dtsi
@@ -110,7 +110,7 @@
 		simple-audio-card,frame-master = <&sound_codec>;
 
 		sound_cpu: simple-audio-card,cpu {
-			sound-dai = <&ssi2>;
+			sound-dai = <&ssi1>;
 		};
 
 		sound_codec: simple-audio-card,codec {
diff --git a/arch/arm/boot/dts/imx6qdl-icore.dtsi b/arch/arm/boot/dts/imx6qdl-icore.dtsi
index 756f3a9..12997da 100644
--- a/arch/arm/boot/dts/imx6qdl-icore.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-icore.dtsi
@@ -397,7 +397,7 @@
 
 	pinctrl_usbotg: usbotggrp {
 		fsl,pins = <
-			MX6QDL_PAD_GPIO_1__USB_OTG_ID 0x17059
+			MX6QDL_PAD_ENET_RX_ER__USB_OTG_ID 0x17059
 		>;
 	};
 
@@ -409,6 +409,7 @@
 			MX6QDL_PAD_SD1_DAT1__SD1_DATA1 0x17070
 			MX6QDL_PAD_SD1_DAT2__SD1_DATA2 0x17070
 			MX6QDL_PAD_SD1_DAT3__SD1_DATA3 0x17070
+			MX6QDL_PAD_GPIO_1__GPIO1_IO01  0x1b0b0
 		>;
 	};
 
diff --git a/arch/arm/boot/dts/imx6sx-sabreauto.dts b/arch/arm/boot/dts/imx6sx-sabreauto.dts
index 8259244..14fd1de 100644
--- a/arch/arm/boot/dts/imx6sx-sabreauto.dts
+++ b/arch/arm/boot/dts/imx6sx-sabreauto.dts
@@ -99,7 +99,7 @@
 &fec2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_enet2>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-handle = <&ethphy0>;
 	fsl,magic-packet;
 	status = "okay";
diff --git a/arch/arm/boot/dts/imx6sx-sdb.dtsi b/arch/arm/boot/dts/imx6sx-sdb.dtsi
index 3e5fb72..c99aa27 100644
--- a/arch/arm/boot/dts/imx6sx-sdb.dtsi
+++ b/arch/arm/boot/dts/imx6sx-sdb.dtsi
@@ -213,7 +213,7 @@
 &fec2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_enet2>;
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-handle = <&ethphy2>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6ul-kontron-n6x1x-s.dtsi b/arch/arm/boot/dts/imx6ul-kontron-n6x1x-s.dtsi
index f05e918..53a25fb 100644
--- a/arch/arm/boot/dts/imx6ul-kontron-n6x1x-s.dtsi
+++ b/arch/arm/boot/dts/imx6ul-kontron-n6x1x-s.dtsi
@@ -232,13 +232,6 @@
 	status = "okay";
 };
 
-&wdog1 {
-	pinctrl-names = "default";
-	pinctrl-0 = <&pinctrl_wdog>;
-	fsl,ext-reset-output;
-	status = "okay";
-};
-
 &iomuxc {
 	pinctrl-0 = <&pinctrl_reset_out &pinctrl_gpio>;
 
@@ -409,10 +402,4 @@
 			MX6UL_PAD_NAND_DATA03__USDHC2_DATA3	0x170f9
 		>;
 	};
-
-	pinctrl_wdog: wdoggrp {
-		fsl,pins = <
-			MX6UL_PAD_GPIO1_IO09__WDOG1_WDOG_ANY	0x30b0
-		>;
-	};
 };
diff --git a/arch/arm/boot/dts/imx6ul-kontron-n6x1x-som-common.dtsi b/arch/arm/boot/dts/imx6ul-kontron-n6x1x-som-common.dtsi
index a17af4d..61ba21a 100644
--- a/arch/arm/boot/dts/imx6ul-kontron-n6x1x-som-common.dtsi
+++ b/arch/arm/boot/dts/imx6ul-kontron-n6x1x-som-common.dtsi
@@ -57,6 +57,13 @@
 	status = "okay";
 };
 
+&wdog1 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_wdog>;
+	fsl,ext-reset-output;
+	status = "okay";
+};
+
 &iomuxc {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_reset_out>;
@@ -106,4 +113,10 @@
 			MX6UL_PAD_SNVS_TAMPER9__GPIO5_IO09      0x1b0b0
 		>;
 	};
+
+	pinctrl_wdog: wdoggrp {
+		fsl,pins = <
+			MX6UL_PAD_GPIO1_IO09__WDOG1_WDOG_ANY    0x18b0
+		>;
+	};
 };
diff --git a/arch/arm/boot/dts/keystone-k2g-evm.dts b/arch/arm/boot/dts/keystone-k2g-evm.dts
index db640ba..8b3d64c 100644
--- a/arch/arm/boot/dts/keystone-k2g-evm.dts
+++ b/arch/arm/boot/dts/keystone-k2g-evm.dts
@@ -402,7 +402,7 @@
 
 &gbe0 {
 	phy-handle = <&ethphy0>;
-	phy-mode = "rgmii-id";
+	phy-mode = "rgmii-rxid";
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/meson.dtsi b/arch/arm/boot/dts/meson.dtsi
index ae89dea..91129dc 100644
--- a/arch/arm/boot/dts/meson.dtsi
+++ b/arch/arm/boot/dts/meson.dtsi
@@ -11,7 +11,7 @@
 	#size-cells = <1>;
 	interrupt-parent = <&gic>;
 
-	L2: l2-cache-controller@c4200000 {
+	L2: cache-controller@c4200000 {
 		compatible = "arm,pl310-cache";
 		reg = <0xc4200000 0x1000>;
 		cache-unified;
diff --git a/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi b/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi
index e39eee6..08a7d3c 100644
--- a/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi
+++ b/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi
@@ -13,8 +13,10 @@
 		#interrupt-cells = <2>;
 		#address-cells = <1>;
 		#size-cells = <0>;
-		spi-max-frequency = <3000000>;
+		spi-max-frequency = <9600000>;
 		spi-cs-high;
+		spi-cpol;
+		spi-cpha;
 
 		cpcap_adc: adc {
 			compatible = "motorola,mapphone-cpcap-adc";
diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts
index 4089d97..3dbcae3 100644
--- a/arch/arm/boot/dts/omap3-n900.dts
+++ b/arch/arm/boot/dts/omap3-n900.dts
@@ -105,6 +105,14 @@
 			linux,code = <SW_FRONT_PROXIMITY>;
 			linux,can-disable;
 		};
+
+		machine_cover {
+			label = "Machine Cover";
+			gpios = <&gpio6 0 GPIO_ACTIVE_LOW>; /* 160 */
+			linux,input-type = <EV_SW>;
+			linux,code = <SW_MACHINE_COVER>;
+			linux,can-disable;
+		};
 	};
 
 	isp1707: isp1707 {
@@ -819,10 +827,6 @@
 	pinctrl-0 = <&mmc1_pins>;
 	vmmc-supply = <&vmmc1>;
 	bus-width = <4>;
-	/* For debugging, it is often good idea to remove this GPIO.
-	   It means you can remove back cover (to reboot by removing
-	   battery) and still use the MMC card. */
-	cd-gpios = <&gpio6 0 GPIO_ACTIVE_LOW>; /* 160 */
 };
 
 /* most boards use vaux3, only some old versions use vmmc2 instead */
diff --git a/arch/arm/boot/dts/omap4-duovero-parlor.dts b/arch/arm/boot/dts/omap4-duovero-parlor.dts
index 8047e8c..4548d87 100644
--- a/arch/arm/boot/dts/omap4-duovero-parlor.dts
+++ b/arch/arm/boot/dts/omap4-duovero-parlor.dts
@@ -139,7 +139,7 @@
 	ethernet@gpmc {
 		reg = <5 0 0xff>;
 		interrupt-parent = <&gpio2>;
-		interrupts = <12 IRQ_TYPE_EDGE_FALLING>;	/* gpio_44 */
+		interrupts = <12 IRQ_TYPE_LEVEL_LOW>;		/* gpio_44 */
 
 		phy-mode = "mii";
 
diff --git a/arch/arm/boot/dts/omap4.dtsi b/arch/arm/boot/dts/omap4.dtsi
index 6c2b07f..4400f5f 100644
--- a/arch/arm/boot/dts/omap4.dtsi
+++ b/arch/arm/boot/dts/omap4.dtsi
@@ -662,6 +662,6 @@
 	ti,no-idle;
 	timer@0 {
 		assigned-clocks = <&l4_wkup_clkctrl OMAP4_TIMER1_CLKCTRL 24>;
-		assigned-clock-parents = <&sys_clkin_ck>;
+		assigned-clock-parents = <&sys_32k_ck>;
 	};
 };
diff --git a/arch/arm/boot/dts/socfpga.dtsi b/arch/arm/boot/dts/socfpga.dtsi
index c2b54af..78f3267 100644
--- a/arch/arm/boot/dts/socfpga.dtsi
+++ b/arch/arm/boot/dts/socfpga.dtsi
@@ -726,7 +726,7 @@
 			};
 		};
 
-		L2: l2-cache@fffef000 {
+		L2: cache-controller@fffef000 {
 			compatible = "arm,pl310-cache";
 			reg = <0xfffef000 0x1000>;
 			interrupts = <0 38 0x04>;
diff --git a/arch/arm/boot/dts/socfpga_arria10.dtsi b/arch/arm/boot/dts/socfpga_arria10.dtsi
index 3b8571b..8f614c4 100644
--- a/arch/arm/boot/dts/socfpga_arria10.dtsi
+++ b/arch/arm/boot/dts/socfpga_arria10.dtsi
@@ -636,7 +636,7 @@
 			reg = <0xffcfb100 0x80>;
 		};
 
-		L2: l2-cache@fffff000 {
+		L2: cache-controller@fffff000 {
 			compatible = "arm,pl310-cache";
 			reg = <0xfffff000 0x1000>;
 			interrupts = <0 18 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi
index bf531ef..0f95a6e 100644
--- a/arch/arm/boot/dts/sun4i-a10.dtsi
+++ b/arch/arm/boot/dts/sun4i-a10.dtsi
@@ -198,7 +198,7 @@
 		default-pool {
 			compatible = "shared-dma-pool";
 			size = <0x6000000>;
-			alloc-ranges = <0x4a000000 0x6000000>;
+			alloc-ranges = <0x40000000 0x10000000>;
 			reusable;
 			linux,cma-default;
 		};
diff --git a/arch/arm/boot/dts/sun5i.dtsi b/arch/arm/boot/dts/sun5i.dtsi
index e6b0367..c2b4fbf 100644
--- a/arch/arm/boot/dts/sun5i.dtsi
+++ b/arch/arm/boot/dts/sun5i.dtsi
@@ -117,7 +117,7 @@
 		default-pool {
 			compatible = "shared-dma-pool";
 			size = <0x6000000>;
-			alloc-ranges = <0x4a000000 0x6000000>;
+			alloc-ranges = <0x40000000 0x10000000>;
 			reusable;
 			linux,cma-default;
 		};
diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
index ffe1d10..6d6a379 100644
--- a/arch/arm/boot/dts/sun7i-a20.dtsi
+++ b/arch/arm/boot/dts/sun7i-a20.dtsi
@@ -181,7 +181,7 @@
 		default-pool {
 			compatible = "shared-dma-pool";
 			size = <0x6000000>;
-			alloc-ranges = <0x4a000000 0x6000000>;
+			alloc-ranges = <0x40000000 0x10000000>;
 			reusable;
 			linux,cma-default;
 		};
diff --git a/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi
index e6308fb..a88ee52 100644
--- a/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi
+++ b/arch/arm/boot/dts/vexpress-v2m-rs1.dtsi
@@ -100,79 +100,6 @@
 		};
 	};
 
-	mcc {
-		compatible = "arm,vexpress,config-bus";
-		arm,vexpress,config-bridge = <&v2m_sysreg>;
-
-		oscclk0 {
-			/* MCC static memory clock */
-			compatible = "arm,vexpress-osc";
-			arm,vexpress-sysreg,func = <1 0>;
-			freq-range = <25000000 60000000>;
-			#clock-cells = <0>;
-			clock-output-names = "v2m:oscclk0";
-		};
-
-		v2m_oscclk1: oscclk1 {
-			/* CLCD clock */
-			compatible = "arm,vexpress-osc";
-			arm,vexpress-sysreg,func = <1 1>;
-			freq-range = <23750000 65000000>;
-			#clock-cells = <0>;
-			clock-output-names = "v2m:oscclk1";
-		};
-
-		v2m_oscclk2: oscclk2 {
-			/* IO FPGA peripheral clock */
-			compatible = "arm,vexpress-osc";
-			arm,vexpress-sysreg,func = <1 2>;
-			freq-range = <24000000 24000000>;
-			#clock-cells = <0>;
-			clock-output-names = "v2m:oscclk2";
-		};
-
-		volt-vio {
-			/* Logic level voltage */
-			compatible = "arm,vexpress-volt";
-			arm,vexpress-sysreg,func = <2 0>;
-			regulator-name = "VIO";
-			regulator-always-on;
-			label = "VIO";
-		};
-
-		temp-mcc {
-			/* MCC internal operating temperature */
-			compatible = "arm,vexpress-temp";
-			arm,vexpress-sysreg,func = <4 0>;
-			label = "MCC";
-		};
-
-		reset {
-			compatible = "arm,vexpress-reset";
-			arm,vexpress-sysreg,func = <5 0>;
-		};
-
-		muxfpga {
-			compatible = "arm,vexpress-muxfpga";
-			arm,vexpress-sysreg,func = <7 0>;
-		};
-
-		shutdown {
-			compatible = "arm,vexpress-shutdown";
-			arm,vexpress-sysreg,func = <8 0>;
-		};
-
-		reboot {
-			compatible = "arm,vexpress-reboot";
-			arm,vexpress-sysreg,func = <9 0>;
-		};
-
-		dvimode {
-			compatible = "arm,vexpress-dvimode";
-			arm,vexpress-sysreg,func = <11 0>;
-		};
-	};
-
 	bus@8000000 {
 		motherboard-bus {
 			model = "V2M-P1";
@@ -435,6 +362,79 @@
 						};
 					};
 				};
+
+				mcc {
+					compatible = "arm,vexpress,config-bus";
+					arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+					oscclk0 {
+						/* MCC static memory clock */
+						compatible = "arm,vexpress-osc";
+						arm,vexpress-sysreg,func = <1 0>;
+						freq-range = <25000000 60000000>;
+						#clock-cells = <0>;
+						clock-output-names = "v2m:oscclk0";
+					};
+
+					v2m_oscclk1: oscclk1 {
+						/* CLCD clock */
+						compatible = "arm,vexpress-osc";
+						arm,vexpress-sysreg,func = <1 1>;
+						freq-range = <23750000 65000000>;
+						#clock-cells = <0>;
+						clock-output-names = "v2m:oscclk1";
+					};
+
+					v2m_oscclk2: oscclk2 {
+						/* IO FPGA peripheral clock */
+						compatible = "arm,vexpress-osc";
+						arm,vexpress-sysreg,func = <1 2>;
+						freq-range = <24000000 24000000>;
+						#clock-cells = <0>;
+						clock-output-names = "v2m:oscclk2";
+					};
+
+					volt-vio {
+						/* Logic level voltage */
+						compatible = "arm,vexpress-volt";
+						arm,vexpress-sysreg,func = <2 0>;
+						regulator-name = "VIO";
+						regulator-always-on;
+						label = "VIO";
+					};
+
+					temp-mcc {
+						/* MCC internal operating temperature */
+						compatible = "arm,vexpress-temp";
+						arm,vexpress-sysreg,func = <4 0>;
+						label = "MCC";
+					};
+
+					reset {
+						compatible = "arm,vexpress-reset";
+						arm,vexpress-sysreg,func = <5 0>;
+					};
+
+					muxfpga {
+						compatible = "arm,vexpress-muxfpga";
+						arm,vexpress-sysreg,func = <7 0>;
+					};
+
+					shutdown {
+						compatible = "arm,vexpress-shutdown";
+						arm,vexpress-sysreg,func = <8 0>;
+					};
+
+					reboot {
+						compatible = "arm,vexpress-reboot";
+						arm,vexpress-sysreg,func = <9 0>;
+					};
+
+					dvimode {
+						compatible = "arm,vexpress-dvimode";
+						arm,vexpress-sysreg,func = <11 0>;
+					};
+				};
 			};
 		};
 	};
diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h
index 84dc0ba..5dcf3c6 100644
--- a/arch/arm/include/asm/efi.h
+++ b/arch/arm/include/asm/efi.h
@@ -87,4 +87,11 @@
 	return dram_base + SZ_512M;
 }
 
+struct efi_arm_entry_state {
+	u32	cpsr_before_ebs;
+	u32	sctlr_before_ebs;
+	u32	cpsr_after_ebs;
+	u32	sctlr_after_ebs;
+};
+
 #endif /* _ASM_ARM_EFI_H */
diff --git a/arch/arm/include/asm/percpu.h b/arch/arm/include/asm/percpu.h
index f44f448..1a3eedb 100644
--- a/arch/arm/include/asm/percpu.h
+++ b/arch/arm/include/asm/percpu.h
@@ -5,6 +5,8 @@
 #ifndef _ASM_ARM_PERCPU_H_
 #define _ASM_ARM_PERCPU_H_
 
+#include <asm/thread_info.h>
+
 /*
  * Same as asm-generic/percpu.h, except that we store the per cpu offset
  * in the TPIDRPRW. TPIDRPRW only exists on V6K and V7
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index c036a4a..a1570c8 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -31,15 +31,6 @@
 #if defined(__APCS_26__)
 #error Sorry, your compiler targets APCS-26 but this kernel requires APCS-32
 #endif
-/*
- * GCC 4.8.0-4.8.2: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58854
- *	      miscompiles find_get_entry(), and can result in EXT3 and EXT4
- *	      filesystem corruption (possibly other FS too).
- */
-#if defined(GCC_VERSION) && GCC_VERSION >= 40800 && GCC_VERSION < 40803
-#error Your compiler is too buggy; it is known to miscompile kernels
-#error and result in filesystem corruption and oopses.
-#endif
 
 int main(void)
 {
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index 02ca7ad..7fff88e 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -683,6 +683,12 @@
 	arch_install_hw_breakpoint(bp);
 }
 
+static int watchpoint_fault_on_uaccess(struct pt_regs *regs,
+				       struct arch_hw_breakpoint *info)
+{
+	return !user_mode(regs) && info->ctrl.privilege == ARM_BREAKPOINT_USER;
+}
+
 static void watchpoint_handler(unsigned long addr, unsigned int fsr,
 			       struct pt_regs *regs)
 {
@@ -742,16 +748,27 @@
 		}
 
 		pr_debug("watchpoint fired: address = 0x%x\n", info->trigger);
+
+		/*
+		 * If we triggered a user watchpoint from a uaccess routine,
+		 * then handle the stepping ourselves since userspace really
+		 * can't help us with this.
+		 */
+		if (watchpoint_fault_on_uaccess(regs, info))
+			goto step;
+
 		perf_bp_event(wp, regs);
 
 		/*
-		 * If no overflow handler is present, insert a temporary
-		 * mismatch breakpoint so we can single-step over the
-		 * watchpoint trigger.
+		 * Defer stepping to the overflow handler if one is installed.
+		 * Otherwise, insert a temporary mismatch breakpoint so that
+		 * we can single-step over the watchpoint trigger.
 		 */
-		if (is_default_overflow_handler(wp))
-			enable_single_step(wp, instruction_pointer(regs));
+		if (!is_default_overflow_handler(wp))
+			goto unlock;
 
+step:
+		enable_single_step(wp, instruction_pointer(regs));
 unlock:
 		rcu_read_unlock();
 	}
diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c
index 6bfdca4..fddd08a 100644
--- a/arch/arm/kernel/vdso.c
+++ b/arch/arm/kernel/vdso.c
@@ -184,6 +184,7 @@
 	if (!cntvct_ok) {
 		vdso_nullpatch_one(&einfo, "__vdso_gettimeofday");
 		vdso_nullpatch_one(&einfo, "__vdso_clock_gettime");
+		vdso_nullpatch_one(&einfo, "__vdso_clock_gettime64");
 	}
 }
 
diff --git a/arch/arm/mach-bcm/Kconfig b/arch/arm/mach-bcm/Kconfig
index 6aa938b..1df0ee0 100644
--- a/arch/arm/mach-bcm/Kconfig
+++ b/arch/arm/mach-bcm/Kconfig
@@ -53,6 +53,7 @@
 	select ARM_ERRATA_754322
 	select ARM_ERRATA_775420
 	select ARM_ERRATA_764369 if SMP
+	select ARM_TIMER_SP804
 	select THERMAL
 	select THERMAL_OF
 	help
diff --git a/arch/arm/mach-imx/devices/devices-common.h b/arch/arm/mach-imx/devices/devices-common.h
index 2a685ad..ae84c08 100644
--- a/arch/arm/mach-imx/devices/devices-common.h
+++ b/arch/arm/mach-imx/devices/devices-common.h
@@ -289,6 +289,6 @@
 		const struct spi_imx_master *pdata);
 
 struct platform_device *imx_add_imx_dma(char *name, resource_size_t iobase,
-					int irq, int irq_err);
+					int irq);
 struct platform_device *imx_add_imx_sdma(char *name,
 	resource_size_t iobase, int irq, struct sdma_platform_data *pdata);
diff --git a/arch/arm/mach-imx/devices/platform-gpio-mxc.c b/arch/arm/mach-imx/devices/platform-gpio-mxc.c
index 78628ef..355de84 100644
--- a/arch/arm/mach-imx/devices/platform-gpio-mxc.c
+++ b/arch/arm/mach-imx/devices/platform-gpio-mxc.c
@@ -24,7 +24,8 @@
 			.flags = IORESOURCE_IRQ,
 		},
 	};
+	unsigned int nres;
 
-	return platform_device_register_resndata(&mxc_aips_bus,
-			name, id, res, ARRAY_SIZE(res), NULL, 0);
+	nres = irq_high ? ARRAY_SIZE(res) : ARRAY_SIZE(res) - 1;
+	return platform_device_register_resndata(&mxc_aips_bus, name, id, res, nres, NULL, 0);
 }
diff --git a/arch/arm/mach-imx/devices/platform-imx-dma.c b/arch/arm/mach-imx/devices/platform-imx-dma.c
index 26b47b3..12656f2 100644
--- a/arch/arm/mach-imx/devices/platform-imx-dma.c
+++ b/arch/arm/mach-imx/devices/platform-imx-dma.c
@@ -6,7 +6,7 @@
 #include "devices-common.h"
 
 struct platform_device __init __maybe_unused *imx_add_imx_dma(char *name,
-	resource_size_t iobase, int irq, int irq_err)
+	resource_size_t iobase, int irq)
 {
 	struct resource res[] = {
 		{
@@ -17,10 +17,6 @@
 			.start = irq,
 			.end = irq,
 			.flags = IORESOURCE_IRQ,
-		}, {
-			.start = irq_err,
-			.end = irq_err,
-			.flags = IORESOURCE_IRQ,
 		},
 	};
 
diff --git a/arch/arm/mach-imx/mm-imx21.c b/arch/arm/mach-imx/mm-imx21.c
index 50a2eda..b834026 100644
--- a/arch/arm/mach-imx/mm-imx21.c
+++ b/arch/arm/mach-imx/mm-imx21.c
@@ -78,8 +78,7 @@
 	mxc_register_gpio("imx21-gpio", 5, MX21_GPIO6_BASE_ADDR, SZ_256, MX21_INT_GPIO, 0);
 
 	pinctrl_provide_dummies();
-	imx_add_imx_dma("imx21-dma", MX21_DMA_BASE_ADDR,
-			MX21_INT_DMACH0, 0); /* No ERR irq */
+	imx_add_imx_dma("imx21-dma", MX21_DMA_BASE_ADDR, MX21_INT_DMACH0);
 	platform_device_register_simple("imx21-audmux", 0, imx21_audmux_res,
 					ARRAY_SIZE(imx21_audmux_res));
 }
diff --git a/arch/arm/mach-imx/mm-imx27.c b/arch/arm/mach-imx/mm-imx27.c
index 4e41251..2717614 100644
--- a/arch/arm/mach-imx/mm-imx27.c
+++ b/arch/arm/mach-imx/mm-imx27.c
@@ -79,8 +79,7 @@
 	mxc_register_gpio("imx21-gpio", 5, MX27_GPIO6_BASE_ADDR, SZ_256, MX27_INT_GPIO, 0);
 
 	pinctrl_provide_dummies();
-	imx_add_imx_dma("imx27-dma", MX27_DMA_BASE_ADDR,
-			MX27_INT_DMACH0, 0); /* No ERR irq */
+	imx_add_imx_dma("imx27-dma", MX27_DMA_BASE_ADDR, MX27_INT_DMACH0);
 	/* imx27 has the imx21 type audmux */
 	platform_device_register_simple("imx21-audmux", 0, imx27_audmux_res,
 					ARRAY_SIZE(imx27_audmux_res));
diff --git a/arch/arm/mach-imx/pm-imx5.c b/arch/arm/mach-imx/pm-imx5.c
index f057df8..e9962b4 100644
--- a/arch/arm/mach-imx/pm-imx5.c
+++ b/arch/arm/mach-imx/pm-imx5.c
@@ -295,14 +295,14 @@
 	if (!ocram_pool) {
 		pr_warn("%s: ocram pool unavailable!\n", __func__);
 		ret = -ENODEV;
-		goto put_node;
+		goto put_device;
 	}
 
 	ocram_base = gen_pool_alloc(ocram_pool, size);
 	if (!ocram_base) {
 		pr_warn("%s: unable to alloc ocram!\n", __func__);
 		ret = -ENOMEM;
-		goto put_node;
+		goto put_device;
 	}
 
 	phys = gen_pool_virt_to_phys(ocram_pool, ocram_base);
@@ -312,6 +312,8 @@
 	if (virt_out)
 		*virt_out = virt;
 
+put_device:
+	put_device(&pdev->dev);
 put_node:
 	of_node_put(node);
 
diff --git a/arch/arm/mach-imx/pm-imx6.c b/arch/arm/mach-imx/pm-imx6.c
index dd34dff..40c74b4 100644
--- a/arch/arm/mach-imx/pm-imx6.c
+++ b/arch/arm/mach-imx/pm-imx6.c
@@ -493,14 +493,14 @@
 	if (!ocram_pool) {
 		pr_warn("%s: ocram pool unavailable!\n", __func__);
 		ret = -ENODEV;
-		goto put_node;
+		goto put_device;
 	}
 
 	ocram_base = gen_pool_alloc(ocram_pool, MX6Q_SUSPEND_OCRAM_SIZE);
 	if (!ocram_base) {
 		pr_warn("%s: unable to alloc ocram!\n", __func__);
 		ret = -ENOMEM;
-		goto put_node;
+		goto put_device;
 	}
 
 	ocram_pbase = gen_pool_virt_to_phys(ocram_pool, ocram_base);
@@ -523,7 +523,7 @@
 	ret = imx6_pm_get_base(&pm_info->mmdc_base, socdata->mmdc_compat);
 	if (ret) {
 		pr_warn("%s: failed to get mmdc base %d!\n", __func__, ret);
-		goto put_node;
+		goto put_device;
 	}
 
 	ret = imx6_pm_get_base(&pm_info->src_base, socdata->src_compat);
@@ -570,7 +570,7 @@
 		&imx6_suspend,
 		MX6Q_SUSPEND_OCRAM_SIZE - sizeof(*pm_info));
 
-	goto put_node;
+	goto put_device;
 
 pl310_cache_map_failed:
 	iounmap(pm_info->gpc_base.vbase);
@@ -580,6 +580,8 @@
 	iounmap(pm_info->src_base.vbase);
 src_map_failed:
 	iounmap(pm_info->mmdc_base.vbase);
+put_device:
+	put_device(&pdev->dev);
 put_node:
 	of_node_put(node);
 
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 82706af..15b29a1 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -3435,7 +3435,7 @@
 		regs = ioremap(data->module_pa,
 			       data->module_size);
 		if (!regs)
-			return -ENOMEM;
+			goto out_free_sysc;
 	}
 
 	/*
@@ -3445,13 +3445,13 @@
 	if (oh->class->name && strcmp(oh->class->name, data->name)) {
 		class = kmemdup(oh->class, sizeof(*oh->class), GFP_KERNEL);
 		if (!class)
-			return -ENOMEM;
+			goto out_unmap;
 	}
 
 	if (list_empty(&oh->slave_ports)) {
 		oi = kcalloc(1, sizeof(*oi), GFP_KERNEL);
 		if (!oi)
-			return -ENOMEM;
+			goto out_free_class;
 
 		/*
 		 * Note that we assume interconnect interface clocks will be
@@ -3478,6 +3478,14 @@
 	spin_unlock_irqrestore(&oh->_lock, flags);
 
 	return 0;
+
+out_free_class:
+	kfree(class);
+out_unmap:
+	iounmap(regs);
+out_free_sysc:
+	kfree(sysc);
+	return -ENOMEM;
 }
 
 static const struct omap_hwmod_reset omap24xx_reset_quirks[] = {
@@ -3489,7 +3497,7 @@
 };
 
 static const struct omap_hwmod_reset omap_reset_quirks[] = {
-	{ .match = "dss", .len = 3, .reset = omap_dss_reset, },
+	{ .match = "dss_core", .len = 8, .reset = omap_dss_reset, },
 	{ .match = "hdq1w", .len = 5, .reset = omap_hdq1w_reset, },
 	{ .match = "i2c", .len = 3, .reset = omap_i2c_reset, },
 	{ .match = "wd_timer", .len = 8, .reset = omap2_wd_timer_reset, },
diff --git a/arch/arm/mach-sti/board-dt.c b/arch/arm/mach-sti/board-dt.c
index dcb9893..ffecbf2 100644
--- a/arch/arm/mach-sti/board-dt.c
+++ b/arch/arm/mach-sti/board-dt.c
@@ -20,14 +20,6 @@
 	NULL
 };
 
-static void sti_l2_write_sec(unsigned long val, unsigned reg)
-{
-	/*
-	 * We can't write to secure registers as we are in non-secure
-	 * mode, until we have some SMI service available.
-	 */
-}
-
 DT_MACHINE_START(STM, "STi SoC with Flattened Device Tree")
 	.dt_compat	= stih41x_dt_match,
 	.l2c_aux_val	= L2C_AUX_CTRL_SHARED_OVERRIDE |
@@ -36,5 +28,4 @@
 			  L2C_AUX_CTRL_WAY_SIZE(4),
 	.l2c_aux_mask	= 0xc0000fff,
 	.smp		= smp_ops(sti_smp_ops),
-	.l2c_write_sec	= sti_l2_write_sec,
 MACHINE_END
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 628028b..bcd8261 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -966,7 +966,7 @@
 	pud_t *pud;
 
 	p4d = p4d_alloc(mm, pgd_offset(mm, md->virtual), md->virtual);
-	if (!WARN_ON(!p4d))
+	if (WARN_ON(!p4d))
 		return;
 	pud = pud_alloc(mm, p4d, md->virtual);
 	if (WARN_ON(!pud))
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index fd4e1ce1..e93145d 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -241,7 +241,6 @@
  * see Documentation/devicetree/bindings/arm/xen.txt for the
  * documentation of the Xen Device Tree format.
  */
-#define GRANT_TABLE_PHYSADDR 0
 void __init xen_early_init(void)
 {
 	of_scan_flat_dt(fdt_find_hyper_node, NULL);
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index a4a094b..66dc41f 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1518,9 +1518,9 @@
 	default y
 	depends on !KVM || ARM64_VHE
 	depends on (CC_HAS_SIGN_RETURN_ADDRESS || CC_HAS_BRANCH_PROT_PAC_RET) && AS_HAS_PAC
-	# GCC 9.1 and later inserts a .note.gnu.property section note for PAC
+	# Modern compilers insert a .note.gnu.property section note for PAC
 	# which is only understood by binutils starting with version 2.33.1.
-	depends on !CC_IS_GCC || GCC_VERSION < 90100 || LD_VERSION >= 233010000
+	depends on LD_IS_LLD || LD_VERSION >= 233010000 || (CC_IS_GCC && GCC_VERSION < 90100)
 	depends on !CC_IS_CLANG || AS_HAS_CFI_NEGATE_RA_STATE
 	depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_REGS)
 	help
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index a0d94d0..70f59059 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -137,7 +137,7 @@
 
 core-y		+= arch/arm64/
 libs-y		:= arch/arm64/lib/ $(libs-y)
-core-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a
+libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a
 
 # Default target when executing plain make
 boot		:= arch/arm64/boot
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi
index 78b1361..9ce78a7 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi
@@ -161,6 +161,7 @@
 			resets = <&ccu RST_BUS_VE>;
 			interrupts = <GIC_SPI 89 IRQ_TYPE_LEVEL_HIGH>;
 			allwinner,sram = <&ve_sram 1>;
+			iommus = <&iommu 3>;
 		};
 
 		gpu: gpu@1800000 {
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
index d1fc9c2..9498d1d 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
@@ -77,7 +77,7 @@
 		method = "smc";
 	};
 
-	intc: intc@fffc1000 {
+	intc: interrupt-controller@fffc1000 {
 		compatible = "arm,gic-400", "arm,cortex-a15-gic";
 		#interrupt-cells = <3>;
 		interrupt-controller;
@@ -302,7 +302,7 @@
 			status = "disabled";
 		};
 
-		nand: nand@ffb90000 {
+		nand: nand-controller@ffb90000 {
 			#address-cells = <1>;
 			#size-cells = <0>;
 			compatible = "altr,socfpga-denali-nand";
@@ -445,7 +445,7 @@
 			clock-names = "timer";
 		};
 
-		uart0: serial0@ffc02000 {
+		uart0: serial@ffc02000 {
 			compatible = "snps,dw-apb-uart";
 			reg = <0xffc02000 0x100>;
 			interrupts = <0 108 4>;
@@ -456,7 +456,7 @@
 			status = "disabled";
 		};
 
-		uart1: serial1@ffc02100 {
+		uart1: serial@ffc02100 {
 			compatible = "snps,dw-apb-uart";
 			reg = <0xffc02100 0x100>;
 			interrupts = <0 109 4>;
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts
index f6c4a15..feadd21 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts
@@ -155,6 +155,7 @@
 };
 
 &qspi {
+	status = "okay";
 	flash@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts
index 9946515..c079667 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk_nand.dts
@@ -188,6 +188,7 @@
 };
 
 &qspi {
+	status = "okay";
 	flash@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
@@ -211,12 +212,12 @@
 
 			qspi_boot: partition@0 {
 				label = "Boot and fpga data";
-				reg = <0x0 0x034B0000>;
+				reg = <0x0 0x03FE0000>;
 			};
 
-			qspi_rootfs: partition@4000000 {
+			qspi_rootfs: partition@3FE0000 {
 				label = "Root Filesystem - JFFS2";
-				reg = <0x034B0000 0x0EB50000>;
+				reg = <0x03FE0000 0x0C020000>;
 			};
 		};
 	};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-libretech-ac.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-libretech-ac.dts
index 6a226fa..9e43f4d 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-libretech-ac.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-libretech-ac.dts
@@ -10,7 +10,7 @@
 #include <dt-bindings/input/input.h>
 #include <dt-bindings/sound/meson-aiu.h>
 
-#include "meson-gxl-s905x.dtsi"
+#include "meson-gxl-s805x.dtsi"
 
 / {
 	compatible = "libretech,aml-s805x-ac", "amlogic,s805x",
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-p241.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-p241.dts
index 867e30f..eb7f5a3 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-p241.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x-p241.dts
@@ -9,7 +9,7 @@
 
 #include <dt-bindings/input/input.h>
 
-#include "meson-gxl-s905x.dtsi"
+#include "meson-gxl-s805x.dtsi"
 
 / {
 	compatible = "amlogic,p241", "amlogic,s805x", "amlogic,meson-gxl";
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s805x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x.dtsi
new file mode 100644
index 0000000..f9d7056
--- /dev/null
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s805x.dtsi
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
+/*
+ * Copyright (c) 2020 BayLibre SAS
+ * Author: Neil Armstrong <narmstrong@baylibre.com>
+ */
+
+#include "meson-gxl-s905x.dtsi"
+
+/ {
+	compatible = "amlogic,s805x", "amlogic,meson-gxl";
+};
+
+/* The S805X Package doesn't seem to handle the 744MHz OPP correctly */
+&mali {
+	assigned-clocks = <&clkc CLKID_MALI_0_SEL>,
+			  <&clkc CLKID_MALI_0>,
+			  <&clkc CLKID_MALI>; /* Glitch free mux */
+	assigned-clock-parents = <&clkc CLKID_FCLK_DIV3>,
+				 <0>, /* Do Nothing */
+				 <&clkc CLKID_MALI_0>;
+	assigned-clock-rates = <0>, /* Do Nothing */
+			       <666666666>,
+			       <0>; /* Do Nothing */
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
index fc59c85..6c8b189 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
@@ -337,6 +337,11 @@
 	};
 };
 
+&hwrng {
+	clocks = <&clkc CLKID_RNG0>;
+	clock-names = "core";
+};
+
 &i2c_A {
 	clocks = <&clkc CLKID_I2C>;
 };
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi
index fb0137a..94911b1 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-beacon-som.dtsi
@@ -136,7 +136,7 @@
 
 			ldo1_reg: LDO1 {
 				regulator-name = "LDO1";
-				regulator-min-microvolt = <3000000>;
+				regulator-min-microvolt = <1600000>;
 				regulator-max-microvolt = <3300000>;
 				regulator-boot-on;
 				regulator-always-on;
@@ -144,7 +144,7 @@
 
 			ldo2_reg: LDO2 {
 				regulator-name = "LDO2";
-				regulator-min-microvolt = <900000>;
+				regulator-min-microvolt = <800000>;
 				regulator-max-microvolt = <900000>;
 				regulator-boot-on;
 				regulator-always-on;
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-evk.dts b/arch/arm64/boot/dts/freescale/imx8mm-evk.dts
index e5ec832..0f1d7f8 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-evk.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mm-evk.dts
@@ -208,7 +208,7 @@
 
 			ldo1_reg: LDO1 {
 				regulator-name = "LDO1";
-				regulator-min-microvolt = <3000000>;
+				regulator-min-microvolt = <1600000>;
 				regulator-max-microvolt = <3300000>;
 				regulator-boot-on;
 				regulator-always-on;
@@ -216,7 +216,7 @@
 
 			ldo2_reg: LDO2 {
 				regulator-name = "LDO2";
-				regulator-min-microvolt = <900000>;
+				regulator-min-microvolt = <800000>;
 				regulator-max-microvolt = <900000>;
 				regulator-boot-on;
 				regulator-always-on;
diff --git a/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts b/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts
index d07e0e6..a1e5483 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mn-ddr4-evk.dts
@@ -113,7 +113,7 @@
 
 			ldo1_reg: LDO1 {
 				regulator-name = "LDO1";
-				regulator-min-microvolt = <3000000>;
+				regulator-min-microvolt = <1600000>;
 				regulator-max-microvolt = <3300000>;
 				regulator-boot-on;
 				regulator-always-on;
@@ -121,7 +121,7 @@
 
 			ldo2_reg: LDO2 {
 				regulator-name = "LDO2";
-				regulator-min-microvolt = <900000>;
+				regulator-min-microvolt = <800000>;
 				regulator-max-microvolt = <900000>;
 				regulator-boot-on;
 				regulator-always-on;
diff --git a/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts b/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts
index 51d9483..92f478d 100644
--- a/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts
+++ b/arch/arm64/boot/dts/intel/socfpga_agilex_socdk.dts
@@ -98,6 +98,7 @@
 };
 
 &qspi {
+	status = "okay";
 	flash@0 {
 		#address-cells = <1>;
 		#size-cells = <1>;
diff --git a/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts b/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts
index c8243da..eb01cc9 100644
--- a/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts
+++ b/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts
@@ -454,10 +454,7 @@
 	status = "okay";
 	phy-mode = "2500base-x";
 	phys = <&cp1_comphy5 2>;
-	fixed-link {
-		speed = <2500>;
-		full-duplex;
-	};
+	managed = "in-band-status";
 };
 
 &cp1_spi1 {
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 883e8ba..2ca7ba6 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -194,7 +194,7 @@
 CONFIG_HOTPLUG_PCI_ACPI=y
 CONFIG_PCI_AARDVARK=y
 CONFIG_PCI_TEGRA=y
-CONFIG_PCIE_RCAR=y
+CONFIG_PCIE_RCAR_HOST=y
 CONFIG_PCI_HOST_GENERIC=y
 CONFIG_PCI_XGENE=y
 CONFIG_PCIE_ALTERA=y
diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h
index 5e5dc05..619db9b 100644
--- a/arch/arm64/include/asm/alternative.h
+++ b/arch/arm64/include/asm/alternative.h
@@ -73,13 +73,13 @@
 	".pushsection .altinstructions,\"a\"\n"				\
 	ALTINSTR_ENTRY(feature)						\
 	".popsection\n"							\
-	".pushsection .altinstr_replacement, \"a\"\n"			\
+	".subsection 1\n"						\
 	"663:\n\t"							\
 	newinstr "\n"							\
 	"664:\n\t"							\
-	".popsection\n\t"						\
 	".org	. - (664b-663b) + (662b-661b)\n\t"			\
-	".org	. - (662b-661b) + (664b-663b)\n"			\
+	".org	. - (662b-661b) + (664b-663b)\n\t"			\
+	".previous\n"							\
 	".endif\n"
 
 #define __ALTERNATIVE_CFG_CB(oldinstr, feature, cfg_enabled, cb)	\
@@ -117,9 +117,9 @@
 662:	.pushsection .altinstructions, "a"
 	altinstruction_entry 661b, 663f, \cap, 662b-661b, 664f-663f
 	.popsection
-	.pushsection .altinstr_replacement, "ax"
+	.subsection 1
 663:	\insn2
-664:	.popsection
+664:	.previous
 	.org	. - (664b-663b) + (662b-661b)
 	.org	. - (662b-661b) + (664b-663b)
 	.endif
@@ -160,7 +160,7 @@
 	.pushsection .altinstructions, "a"
 	altinstruction_entry 663f, 661f, \cap, 664f-663f, 662f-661f
 	.popsection
-	.pushsection .altinstr_replacement, "ax"
+	.subsection 1
 	.align 2	/* So GAS knows label 661 is suitably aligned */
 661:
 .endm
@@ -179,9 +179,9 @@
 .macro alternative_else
 662:
 	.if .Lasm_alt_mode==0
-	.pushsection .altinstr_replacement, "ax"
+	.subsection 1
 	.else
-	.popsection
+	.previous
 	.endif
 663:
 .endm
@@ -192,7 +192,7 @@
 .macro alternative_endif
 664:
 	.if .Lasm_alt_mode==0
-	.popsection
+	.previous
 	.endif
 	.org	. - (664b-663b) + (662b-661b)
 	.org	. - (662b-661b) + (664b-663b)
diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h
index a358e97..6647ae4 100644
--- a/arch/arm64/include/asm/arch_gicv3.h
+++ b/arch/arm64/include/asm/arch_gicv3.h
@@ -109,7 +109,7 @@
 	return read_sysreg_s(SYS_ICC_PMR_EL1);
 }
 
-static inline void gic_write_pmr(u32 val)
+static __always_inline void gic_write_pmr(u32 val)
 {
 	write_sysreg_s(val, SYS_ICC_PMR_EL1);
 }
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index 7ae54d7..9f0ec21 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -58,6 +58,7 @@
 	u64 (*read_cntvct_el0)(void);
 	int (*set_next_event_phys)(unsigned long, struct clock_event_device *);
 	int (*set_next_event_virt)(unsigned long, struct clock_event_device *);
+	bool disable_compat_vdso;
 };
 
 DECLARE_PER_CPU(const struct arch_timer_erratum_workaround *,
diff --git a/arch/arm64/include/asm/checksum.h b/arch/arm64/include/asm/checksum.h
index b6f7bc6..93a161b 100644
--- a/arch/arm64/include/asm/checksum.h
+++ b/arch/arm64/include/asm/checksum.h
@@ -24,16 +24,17 @@
 {
 	__uint128_t tmp;
 	u64 sum;
+	int n = ihl; /* we want it signed */
 
 	tmp = *(const __uint128_t *)iph;
 	iph += 16;
-	ihl -= 4;
+	n -= 4;
 	tmp += ((tmp >> 64) | (tmp << 64));
 	sum = tmp >> 64;
 	do {
 		sum += *(const u32 *)iph;
 		iph += 4;
-	} while (--ihl);
+	} while (--n > 0);
 
 	sum += ((sum >> 32) | (sum << 32));
 	return csum_fold((__force u32)(sum >> 32));
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 5d1f4ae..f7c3d1f 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -675,7 +675,7 @@
 		cpus_have_const_cap(ARM64_HAS_GENERIC_AUTH);
 }
 
-static inline bool system_uses_irq_prio_masking(void)
+static __always_inline bool system_uses_irq_prio_masking(void)
 {
 	return IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) &&
 	       cpus_have_const_cap(ARM64_HAS_IRQ_PRIO_MASKING);
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index a87a93f..7219cdd 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -86,6 +86,7 @@
 #define QCOM_CPU_PART_FALKOR		0xC00
 #define QCOM_CPU_PART_KRYO		0x200
 #define QCOM_CPU_PART_KRYO_3XX_SILVER	0x803
+#define QCOM_CPU_PART_KRYO_4XX_GOLD	0x804
 #define QCOM_CPU_PART_KRYO_4XX_SILVER	0x805
 
 #define NVIDIA_CPU_PART_DENVER		0x003
@@ -114,6 +115,7 @@
 #define MIDR_QCOM_FALKOR MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR)
 #define MIDR_QCOM_KRYO MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO)
 #define MIDR_QCOM_KRYO_3XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_3XX_SILVER)
+#define MIDR_QCOM_KRYO_4XX_GOLD MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_GOLD)
 #define MIDR_QCOM_KRYO_4XX_SILVER MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO_4XX_SILVER)
 #define MIDR_NVIDIA_DENVER MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_DENVER)
 #define MIDR_NVIDIA_CARMEL MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_CARMEL)
diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h
index e5ceea2..0b298f4 100644
--- a/arch/arm64/include/asm/debug-monitors.h
+++ b/arch/arm64/include/asm/debug-monitors.h
@@ -109,6 +109,8 @@
 
 void user_rewind_single_step(struct task_struct *task);
 void user_fastforward_single_step(struct task_struct *task);
+void user_regs_reset_single_step(struct user_pt_regs *regs,
+				 struct task_struct *task);
 
 void kernel_enable_single_step(struct pt_regs *regs);
 void kernel_disable_single_step(void);
diff --git a/arch/arm64/include/asm/linkage.h b/arch/arm64/include/asm/linkage.h
index 81fefd2..ba89a9a 100644
--- a/arch/arm64/include/asm/linkage.h
+++ b/arch/arm64/include/asm/linkage.h
@@ -12,7 +12,6 @@
  * instead.
  */
 #define BTI_C hint 34 ;
-#define BTI_J hint 36 ;
 
 /*
  * When using in-kernel BTI we need to ensure that PCS-conformant assembly
@@ -43,11 +42,6 @@
 	SYM_START(name, SYM_L_WEAK, SYM_A_NONE)		\
 	BTI_C
 
-#define SYM_INNER_LABEL(name, linkage)			\
-	.type name SYM_T_NONE ASM_NL			\
-	SYM_ENTRY(name, linkage, SYM_A_NONE)		\
-	BTI_J
-
 #endif
 
 /*
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 68140fd..8444df0 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -19,6 +19,9 @@
 
 typedef struct {
 	atomic64_t	id;
+#ifdef CONFIG_COMPAT
+	void		*sigpage;
+#endif
 	void		*vdso;
 	unsigned long	flags;
 } mm_context_t;
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 2e7e0f4..4d867c6 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -67,7 +67,7 @@
 #define PAGE_HYP		__pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_HYP_XN)
 #define PAGE_HYP_EXEC		__pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY)
 #define PAGE_HYP_RO		__pgprot(_HYP_PAGE_DEFAULT | PTE_HYP | PTE_RDONLY | PTE_HYP_XN)
-#define PAGE_HYP_DEVICE		__pgprot(PROT_DEVICE_nGnRE | PTE_HYP)
+#define PAGE_HYP_DEVICE		__pgprot(_PROT_DEFAULT | PTE_ATTRINDX(MT_DEVICE_nGnRE) | PTE_HYP | PTE_HYP_XN)
 
 #define PAGE_S2_MEMATTR(attr)						\
 	({								\
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index ea268d8..a0c8a0b 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -30,7 +30,6 @@
 #include <linux/threads.h>
 #include <linux/cpumask.h>
 #include <linux/thread_info.h>
-#include <asm/pointer_auth.h>
 
 DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number);
 
diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h
index 65299a2..cfc0672 100644
--- a/arch/arm64/include/asm/syscall.h
+++ b/arch/arm64/include/asm/syscall.h
@@ -34,6 +34,10 @@
 				     struct pt_regs *regs)
 {
 	unsigned long error = regs->regs[0];
+
+	if (is_compat_thread(task_thread_info(task)))
+		error = sign_extend64(error, 31);
+
 	return IS_ERR_VALUE(error) ? error : 0;
 }
 
@@ -47,7 +51,13 @@
 					    struct pt_regs *regs,
 					    int error, long val)
 {
-	regs->regs[0] = (long) error ? error : val;
+	if (error)
+		val = error;
+
+	if (is_compat_thread(task_thread_info(task)))
+		val = lower_32_bits(val);
+
+	regs->regs[0] = val;
 }
 
 #define SYSCALL_MAX_ARGS 6
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 6ea8b6a..5e784e1 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -93,6 +93,7 @@
 #define _TIF_SYSCALL_EMU	(1 << TIF_SYSCALL_EMU)
 #define _TIF_UPROBE		(1 << TIF_UPROBE)
 #define _TIF_FSCHECK		(1 << TIF_FSCHECK)
+#define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
 #define _TIF_32BIT		(1 << TIF_32BIT)
 #define _TIF_SVE		(1 << TIF_SVE)
 
diff --git a/arch/arm64/include/asm/vdso/clocksource.h b/arch/arm64/include/asm/vdso/clocksource.h
index df6ea65..b054d9f 100644
--- a/arch/arm64/include/asm/vdso/clocksource.h
+++ b/arch/arm64/include/asm/vdso/clocksource.h
@@ -2,7 +2,10 @@
 #ifndef __ASM_VDSOCLOCKSOURCE_H
 #define __ASM_VDSOCLOCKSOURCE_H
 
-#define VDSO_ARCH_CLOCKMODES	\
-	VDSO_CLOCKMODE_ARCHTIMER
+#define VDSO_ARCH_CLOCKMODES					\
+	/* vdso clocksource for both 32 and 64bit tasks */	\
+	VDSO_CLOCKMODE_ARCHTIMER,				\
+	/* vdso clocksource for 64bit tasks only */		\
+	VDSO_CLOCKMODE_ARCHTIMER_NOCOMPAT
 
 #endif
diff --git a/arch/arm64/include/asm/vdso/compat_gettimeofday.h b/arch/arm64/include/asm/vdso/compat_gettimeofday.h
index b6907ae..9a625e8 100644
--- a/arch/arm64/include/asm/vdso/compat_gettimeofday.h
+++ b/arch/arm64/include/asm/vdso/compat_gettimeofday.h
@@ -111,7 +111,7 @@
 	 * update. Return something. Core will do another round and then
 	 * see the mode change and fallback to the syscall.
 	 */
-	if (clock_mode == VDSO_CLOCKMODE_NONE)
+	if (clock_mode != VDSO_CLOCKMODE_ARCHTIMER)
 		return 0;
 
 	/*
@@ -152,6 +152,12 @@
 	return ret;
 }
 
+static inline bool vdso_clocksource_ok(const struct vdso_data *vd)
+{
+	return vd->clock_mode == VDSO_CLOCKMODE_ARCHTIMER;
+}
+#define vdso_clocksource_ok	vdso_clocksource_ok
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_VDSO_GETTIMEOFDAY_H */
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 151f285..a561cbb 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -29,9 +29,7 @@
 
 obj-$(CONFIG_COMPAT)			+= sys32.o signal32.o			\
 					   sys_compat.o
-ifneq ($(CONFIG_COMPAT_VDSO), y)
 obj-$(CONFIG_COMPAT)			+= sigreturn32.o
-endif
 obj-$(CONFIG_KUSER_HELPERS)		+= kuser32.o
 obj-$(CONFIG_FUNCTION_TRACER)		+= ftrace.o entry-ftrace.o
 obj-$(CONFIG_MODULES)			+= module.o
diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index d1757ef..7303994 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -43,20 +43,8 @@
  */
 static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc)
 {
-	unsigned long replptr;
-
-	if (kernel_text_address(pc))
-		return true;
-
-	replptr = (unsigned long)ALT_REPL_PTR(alt);
-	if (pc >= replptr && pc <= (replptr + alt->alt_len))
-		return false;
-
-	/*
-	 * Branching into *another* alternate sequence is doomed, and
-	 * we're not even trying to fix it up.
-	 */
-	BUG();
+	unsigned long replptr = (unsigned long)ALT_REPL_PTR(alt);
+	return !(pc >= replptr && pc <= (replptr + alt->alt_len));
 }
 
 #define align_down(x, a)	((unsigned long)(x) & ~(((unsigned long)(a)) - 1))
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index ad06d68..79728bf 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -460,6 +460,8 @@
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A53),
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
 	MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53),
+	MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER),
+	MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER),
 	{},
 };
 
@@ -470,12 +472,7 @@
 has_cortex_a76_erratum_1463225(const struct arm64_cpu_capabilities *entry,
 			       int scope)
 {
-	u32 midr = read_cpuid_id();
-	/* Cortex-A76 r0p0 - r3p1 */
-	struct midr_range range = MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 1);
-
-	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
-	return is_midr_in_range(midr, &range) && is_kernel_in_hyp_mode();
+	return is_affected_midr_range_list(entry, scope) && is_kernel_in_hyp_mode();
 }
 #endif
 
@@ -726,6 +723,8 @@
 	MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 1),
 	/* Neoverse-N1 r0p0 to r3p1 */
 	MIDR_RANGE(MIDR_NEOVERSE_N1, 0, 0, 3, 1),
+	/* Kryo4xx Gold (rcpe to rfpf) => (r0p0 to r3p1) */
+	MIDR_RANGE(MIDR_QCOM_KRYO_4XX_GOLD, 0xc, 0xe, 0xf, 0xf),
 	{},
 };
 #endif
@@ -770,11 +769,23 @@
 #ifdef CONFIG_ARM64_ERRATUM_1530923
 	/* Cortex A55 r0p0 to r2p0 */
 	MIDR_RANGE(MIDR_CORTEX_A55, 0, 0, 2, 0),
+	/* Kryo4xx Silver (rdpe => r1p0) */
+	MIDR_REV(MIDR_QCOM_KRYO_4XX_SILVER, 0xd, 0xe),
 #endif
 	{},
 };
 #endif
 
+#ifdef CONFIG_ARM64_ERRATUM_1463225
+static const struct midr_range erratum_1463225[] = {
+	/* Cortex-A76 r0p0 - r3p1 */
+	MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 1),
+	/* Kryo4xx Gold (rcpe to rfpf) => (r0p0 to r3p1) */
+	MIDR_RANGE(MIDR_QCOM_KRYO_4XX_GOLD, 0xc, 0xe, 0xf, 0xf),
+	{},
+};
+#endif
+
 const struct arm64_cpu_capabilities arm64_errata[] = {
 #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE
 	{
@@ -914,6 +925,7 @@
 		.capability = ARM64_WORKAROUND_1463225,
 		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
 		.matches = has_cortex_a76_erratum_1463225,
+		.midr_range_list = erratum_1463225,
 	},
 #endif
 #ifdef CONFIG_CAVIUM_TX2_ERRATUM_219
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 4ae4167..9fae0ef 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1290,6 +1290,8 @@
 		MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
 		MIDR_ALL_VERSIONS(MIDR_HISI_TSV110),
 		MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL),
+		MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER),
+		MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER),
 		{ /* sentinel */ }
 	};
 	char const *str = "kpti command line option";
@@ -1406,6 +1408,8 @@
 	static const struct midr_range cpus[] = {
 #ifdef CONFIG_ARM64_ERRATUM_1024718
 		MIDR_RANGE(MIDR_CORTEX_A55, 0, 0, 1, 0),  // A55 r0p0 -r1p0
+		/* Kryo4xx Silver (rdpe => r1p0) */
+		MIDR_REV(MIDR_QCOM_KRYO_4XX_SILVER, 0xd, 0xe),
 #endif
 		{},
 	};
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 5df4936..7310a4f 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -141,17 +141,20 @@
 /*
  * Single step API and exception handling.
  */
-static void set_regs_spsr_ss(struct pt_regs *regs)
+static void set_user_regs_spsr_ss(struct user_pt_regs *regs)
 {
 	regs->pstate |= DBG_SPSR_SS;
 }
-NOKPROBE_SYMBOL(set_regs_spsr_ss);
+NOKPROBE_SYMBOL(set_user_regs_spsr_ss);
 
-static void clear_regs_spsr_ss(struct pt_regs *regs)
+static void clear_user_regs_spsr_ss(struct user_pt_regs *regs)
 {
 	regs->pstate &= ~DBG_SPSR_SS;
 }
-NOKPROBE_SYMBOL(clear_regs_spsr_ss);
+NOKPROBE_SYMBOL(clear_user_regs_spsr_ss);
+
+#define set_regs_spsr_ss(r)	set_user_regs_spsr_ss(&(r)->user_regs)
+#define clear_regs_spsr_ss(r)	clear_user_regs_spsr_ss(&(r)->user_regs)
 
 static DEFINE_SPINLOCK(debug_hook_lock);
 static LIST_HEAD(user_step_hook);
@@ -391,17 +394,26 @@
 	 * If single step is active for this thread, then set SPSR.SS
 	 * to 1 to avoid returning to the active-pending state.
 	 */
-	if (test_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP))
+	if (test_tsk_thread_flag(task, TIF_SINGLESTEP))
 		set_regs_spsr_ss(task_pt_regs(task));
 }
 NOKPROBE_SYMBOL(user_rewind_single_step);
 
 void user_fastforward_single_step(struct task_struct *task)
 {
-	if (test_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP))
+	if (test_tsk_thread_flag(task, TIF_SINGLESTEP))
 		clear_regs_spsr_ss(task_pt_regs(task));
 }
 
+void user_regs_reset_single_step(struct user_pt_regs *regs,
+				 struct task_struct *task)
+{
+	if (test_tsk_thread_flag(task, TIF_SINGLESTEP))
+		set_user_regs_spsr_ss(regs);
+	else
+		clear_user_regs_spsr_ss(regs);
+}
+
 /* Kernel API */
 void kernel_enable_single_step(struct pt_regs *regs)
 {
diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index 3dbdf97..d3be9db 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -57,7 +57,7 @@
 	/*
 	 * The CPU masked interrupts, and we are leaving them masked during
 	 * do_debug_exception(). Update PMR as if we had called
-	 * local_mask_daif().
+	 * local_daif_mask().
 	 */
 	if (system_uses_irq_prio_masking())
 		gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 5304d19..35de8ba 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -126,8 +126,10 @@
 	add	\dst, \dst, #(\sym - .entry.tramp.text)
 	.endm
 
-	// This macro corrupts x0-x3. It is the caller's duty
-	// to save/restore them if required.
+	/*
+	 * This macro corrupts x0-x3. It is the caller's duty  to save/restore
+	 * them if required.
+	 */
 	.macro	apply_ssbd, state, tmp1, tmp2
 #ifdef CONFIG_ARM64_SSBD
 alternative_cb	arm64_enable_wa2_handling
@@ -167,13 +169,28 @@
 	stp	x28, x29, [sp, #16 * 14]
 
 	.if	\el == 0
+	.if	\regsize == 32
+	/*
+	 * If we're returning from a 32-bit task on a system affected by
+	 * 1418040 then re-enable userspace access to the virtual counter.
+	 */
+#ifdef CONFIG_ARM64_ERRATUM_1418040
+alternative_if ARM64_WORKAROUND_1418040
+	mrs	x0, cntkctl_el1
+	orr	x0, x0, #2	// ARCH_TIMER_USR_VCT_ACCESS_EN
+	msr	cntkctl_el1, x0
+alternative_else_nop_endif
+#endif
+	.endif
 	clear_gp_regs
 	mrs	x21, sp_el0
 	ldr_this_cpu	tsk, __entry_task, x20
 	msr	sp_el0, tsk
 
-	// Ensure MDSCR_EL1.SS is clear, since we can unmask debug exceptions
-	// when scheduling.
+	/*
+	 * Ensure MDSCR_EL1.SS is clear, since we can unmask debug exceptions
+	 * when scheduling.
+	 */
 	ldr	x19, [tsk, #TSK_TI_FLAGS]
 	disable_step_tsk x19, x20
 
@@ -320,6 +337,14 @@
 	tst	x22, #PSR_MODE32_BIT		// native task?
 	b.eq	3f
 
+#ifdef CONFIG_ARM64_ERRATUM_1418040
+alternative_if ARM64_WORKAROUND_1418040
+	mrs	x0, cntkctl_el1
+	bic	x0, x0, #2			// ARCH_TIMER_USR_VCT_ACCESS_EN
+	msr	cntkctl_el1, x0
+alternative_else_nop_endif
+#endif
+
 #ifdef CONFIG_ARM64_ERRATUM_845719
 alternative_if ARM64_WORKAROUND_845719
 #ifdef CONFIG_PID_IN_CONTEXTIDR
@@ -331,21 +356,6 @@
 alternative_else_nop_endif
 #endif
 3:
-#ifdef CONFIG_ARM64_ERRATUM_1418040
-alternative_if_not ARM64_WORKAROUND_1418040
-	b	4f
-alternative_else_nop_endif
-	/*
-	 * if (x22.mode32 == cntkctl_el1.el0vcten)
-	 *     cntkctl_el1.el0vcten = ~cntkctl_el1.el0vcten
-	 */
-	mrs	x1, cntkctl_el1
-	eon	x0, x1, x22, lsr #3
-	tbz	x0, #1, 4f
-	eor	x1, x1, #2	// ARCH_TIMER_USR_VCT_ACCESS_EN
-	msr	cntkctl_el1, x1
-4:
-#endif
 	scs_save tsk, x0
 
 	/* No kernel C function calls after this as user keys are set. */
@@ -377,11 +387,11 @@
 	.if	\el == 0
 alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
-	bne	5f
+	bne	4f
 	msr	far_el1, x30
 	tramp_alias	x30, tramp_exit_native
 	br	x30
-5:
+4:
 	tramp_alias	x30, tramp_exit_compat
 	br	x30
 #endif
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
index 4311992..1a157ca3 100644
--- a/arch/arm64/kernel/kgdb.c
+++ b/arch/arm64/kernel/kgdb.c
@@ -252,7 +252,7 @@
 	if (!kgdb_single_step)
 		return DBG_HOOK_ERROR;
 
-	kgdb_handle_exception(1, SIGTRAP, 0, regs);
+	kgdb_handle_exception(0, SIGTRAP, 0, regs);
 	return DBG_HOOK_HANDLED;
 }
 NOKPROBE_SYMBOL(kgdb_step_brk_fn);
diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c
index 0bbac61..666b225 100644
--- a/arch/arm64/kernel/perf_regs.c
+++ b/arch/arm64/kernel/perf_regs.c
@@ -15,15 +15,34 @@
 		return 0;
 
 	/*
-	 * Compat (i.e. 32 bit) mode:
-	 * - PC has been set in the pt_regs struct in kernel_entry,
-	 * - Handle SP and LR here.
+	 * Our handling of compat tasks (PERF_SAMPLE_REGS_ABI_32) is weird, but
+	 * we're stuck with it for ABI compatability reasons.
+	 *
+	 * For a 32-bit consumer inspecting a 32-bit task, then it will look at
+	 * the first 16 registers (see arch/arm/include/uapi/asm/perf_regs.h).
+	 * These correspond directly to a prefix of the registers saved in our
+	 * 'struct pt_regs', with the exception of the PC, so we copy that down
+	 * (x15 corresponds to SP_hyp in the architecture).
+	 *
+	 * So far, so good.
+	 *
+	 * The oddity arises when a 64-bit consumer looks at a 32-bit task and
+	 * asks for registers beyond PERF_REG_ARM_MAX. In this case, we return
+	 * SP_usr, LR_usr and PC in the positions where the AArch64 SP, LR and
+	 * PC registers would normally live. The initial idea was to allow a
+	 * 64-bit unwinder to unwind a 32-bit task and, although it's not clear
+	 * how well that works in practice, somebody might be relying on it.
+	 *
+	 * At the time we make a sample, we don't know whether the consumer is
+	 * 32-bit or 64-bit, so we have to cater for both possibilities.
 	 */
 	if (compat_user_mode(regs)) {
 		if ((u32)idx == PERF_REG_ARM64_SP)
 			return regs->compat_sp;
 		if ((u32)idx == PERF_REG_ARM64_LR)
 			return regs->compat_lr;
+		if (idx == 15)
+			return regs->pc;
 	}
 
 	if ((u32)idx == PERF_REG_ARM64_SP)
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index d1c95dc..5290f17 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -120,15 +120,9 @@
 
 void *alloc_insn_page(void)
 {
-	void *page;
-
-	page = vmalloc_exec(PAGE_SIZE);
-	if (page) {
-		set_memory_ro((unsigned long)page, 1);
-		set_vm_flush_reset_perms(page);
-	}
-
-	return page;
+	return __vmalloc_node_range(PAGE_SIZE, 1, VMALLOC_START, VMALLOC_END,
+			GFP_KERNEL, PAGE_KERNEL_ROX, VM_FLUSH_RESET_PERMS,
+			NUMA_NO_NODE, __builtin_return_address(0));
 }
 
 /* arm kprobe: install breakpoint in text */
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 68b7f34..1e02e98 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1811,19 +1811,42 @@
 	unsigned long saved_reg;
 
 	/*
-	 * A scratch register (ip(r12) on AArch32, x7 on AArch64) is
-	 * used to denote syscall entry/exit:
+	 * We have some ABI weirdness here in the way that we handle syscall
+	 * exit stops because we indicate whether or not the stop has been
+	 * signalled from syscall entry or syscall exit by clobbering a general
+	 * purpose register (ip/r12 for AArch32, x7 for AArch64) in the tracee
+	 * and restoring its old value after the stop. This means that:
+	 *
+	 * - Any writes by the tracer to this register during the stop are
+	 *   ignored/discarded.
+	 *
+	 * - The actual value of the register is not available during the stop,
+	 *   so the tracer cannot save it and restore it later.
+	 *
+	 * - Syscall stops behave differently to seccomp and pseudo-step traps
+	 *   (the latter do not nobble any registers).
 	 */
 	regno = (is_compat_task() ? 12 : 7);
 	saved_reg = regs->regs[regno];
 	regs->regs[regno] = dir;
 
-	if (dir == PTRACE_SYSCALL_EXIT)
+	if (dir == PTRACE_SYSCALL_ENTER) {
+		if (tracehook_report_syscall_entry(regs))
+			forget_syscall(regs);
+		regs->regs[regno] = saved_reg;
+	} else if (!test_thread_flag(TIF_SINGLESTEP)) {
 		tracehook_report_syscall_exit(regs, 0);
-	else if (tracehook_report_syscall_entry(regs))
-		forget_syscall(regs);
+		regs->regs[regno] = saved_reg;
+	} else {
+		regs->regs[regno] = saved_reg;
 
-	regs->regs[regno] = saved_reg;
+		/*
+		 * Signal a pseudo-step exception since we are stepping but
+		 * tracer modifications to the registers may have rewound the
+		 * state machine.
+		 */
+		tracehook_report_syscall_exit(regs, 1);
+	}
 }
 
 int syscall_trace_enter(struct pt_regs *regs)
@@ -1833,12 +1856,12 @@
 	if (flags & (_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE)) {
 		tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER);
 		if (!in_syscall(regs) || (flags & _TIF_SYSCALL_EMU))
-			return -1;
+			return NO_SYSCALL;
 	}
 
 	/* Do the secure computing after ptrace; failures should be fast. */
 	if (secure_computing() == -1)
-		return -1;
+		return NO_SYSCALL;
 
 	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
 		trace_sys_enter(regs, regs->syscallno);
@@ -1851,12 +1874,14 @@
 
 void syscall_trace_exit(struct pt_regs *regs)
 {
+	unsigned long flags = READ_ONCE(current_thread_info()->flags);
+
 	audit_syscall_exit(regs);
 
-	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+	if (flags & _TIF_SYSCALL_TRACEPOINT)
 		trace_sys_exit(regs, regs_return_value(regs));
 
-	if (test_thread_flag(TIF_SYSCALL_TRACE))
+	if (flags & (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP))
 		tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT);
 
 	rseq_syscall(regs);
@@ -1934,8 +1959,8 @@
  */
 int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task)
 {
-	if (!test_tsk_thread_flag(task, TIF_SINGLESTEP))
-		regs->pstate &= ~DBG_SPSR_SS;
+	/* https://lore.kernel.org/lkml/20191118131525.GA4180@willie-the-truck */
+	user_regs_reset_single_step(regs, task);
 
 	if (is_compat_thread(task_thread_info(task)))
 		return valid_compat_regs(regs);
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 801d56c..3b4f31f 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -800,7 +800,6 @@
  */
 static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 {
-	struct task_struct *tsk = current;
 	sigset_t *oldset = sigmask_to_save();
 	int usig = ksig->sig;
 	int ret;
@@ -824,14 +823,8 @@
 	 */
 	ret |= !valid_user_regs(&regs->user_regs, current);
 
-	/*
-	 * Fast forward the stepping logic so we step into the signal
-	 * handler.
-	 */
-	if (!ret)
-		user_fastforward_single_step(tsk);
-
-	signal_setup_done(ret, ksig, 0);
+	/* Step into the signal handler if we are stepping */
+	signal_setup_done(ret, ksig, test_thread_flag(TIF_SINGLESTEP));
 }
 
 /*
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index 82feca6..2f507f5 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -342,38 +342,13 @@
 		retcode = ptr_to_compat(ka->sa.sa_restorer);
 	} else {
 		/* Set up sigreturn pointer */
-#ifdef CONFIG_COMPAT_VDSO
-		void *vdso_base = current->mm->context.vdso;
-		void *vdso_trampoline;
-
-		if (ka->sa.sa_flags & SA_SIGINFO) {
-			if (thumb) {
-				vdso_trampoline = VDSO_SYMBOL(vdso_base,
-							compat_rt_sigreturn_thumb);
-			} else {
-				vdso_trampoline = VDSO_SYMBOL(vdso_base,
-							compat_rt_sigreturn_arm);
-			}
-		} else {
-			if (thumb) {
-				vdso_trampoline = VDSO_SYMBOL(vdso_base,
-							compat_sigreturn_thumb);
-			} else {
-				vdso_trampoline = VDSO_SYMBOL(vdso_base,
-							compat_sigreturn_arm);
-			}
-		}
-
-		retcode = ptr_to_compat(vdso_trampoline) + thumb;
-#else
 		unsigned int idx = thumb << 1;
 
 		if (ka->sa.sa_flags & SA_SIGINFO)
 			idx += 3;
 
-		retcode = (unsigned long)current->mm->context.vdso +
+		retcode = (unsigned long)current->mm->context.sigpage +
 			  (idx << 2) + thumb;
-#endif
 	}
 
 	regs->regs[0]	= usig;
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index 5f5b868..5f0c048 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -50,6 +50,9 @@
 		ret = do_ni_syscall(regs, scno);
 	}
 
+	if (is_compat_task())
+		ret = lower_32_bits(ret);
+
 	regs->regs[0] = ret;
 }
 
@@ -121,7 +124,21 @@
 	user_exit();
 
 	if (has_syscall_work(flags)) {
-		/* set default errno for user-issued syscall(-1) */
+		/*
+		 * The de-facto standard way to skip a system call using ptrace
+		 * is to set the system call to -1 (NO_SYSCALL) and set x0 to a
+		 * suitable error code for consumption by userspace. However,
+		 * this cannot be distinguished from a user-issued syscall(-1)
+		 * and so we must set x0 to -ENOSYS here in case the tracer doesn't
+		 * issue the skip and we fall into trace_exit with x0 preserved.
+		 *
+		 * This is slightly odd because it also means that if a tracer
+		 * sets the system call number to -1 but does not initialise x0,
+		 * then x0 will be preserved for all system calls apart from a
+		 * user-issued syscall(-1). However, requesting a skip and not
+		 * setting the return value is unlikely to do anything sensible
+		 * anyway.
+		 */
 		if (scno == NO_SYSCALL)
 			regs->regs[0] = -ENOSYS;
 		scno = syscall_trace_enter(regs);
@@ -139,7 +156,7 @@
 	if (!has_syscall_work(flags) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) {
 		local_daif_mask();
 		flags = current_thread_info()->flags;
-		if (!has_syscall_work(flags)) {
+		if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP)) {
 			/*
 			 * We're off to userspace, where interrupts are
 			 * always enabled after we restore the flags from
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 4e01657..e546df0 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -191,15 +191,12 @@
 #ifdef CONFIG_COMPAT_VDSO
 	AA32_MAP_VVAR,
 	AA32_MAP_VDSO,
-#else
-	AA32_MAP_SIGPAGE
 #endif
+	AA32_MAP_SIGPAGE
 };
 
 static struct page *aarch32_vectors_page __ro_after_init;
-#ifndef CONFIG_COMPAT_VDSO
 static struct page *aarch32_sig_page __ro_after_init;
-#endif
 
 static struct vm_special_mapping aarch32_vdso_maps[] = {
 	[AA32_MAP_VECTORS] = {
@@ -214,12 +211,11 @@
 		.name = "[vdso]",
 		.mremap = aarch32_vdso_mremap,
 	},
-#else
+#endif /* CONFIG_COMPAT_VDSO */
 	[AA32_MAP_SIGPAGE] = {
 		.name	= "[sigpage]", /* ABI */
 		.pages	= &aarch32_sig_page,
 	},
-#endif /* CONFIG_COMPAT_VDSO */
 };
 
 static int aarch32_alloc_kuser_vdso_page(void)
@@ -242,27 +238,11 @@
 	return 0;
 }
 
-#ifdef CONFIG_COMPAT_VDSO
-static int __aarch32_alloc_vdso_pages(void)
-{
-	int ret;
-
-	vdso_info[VDSO_ABI_AA32].dm = &aarch32_vdso_maps[AA32_MAP_VVAR];
-	vdso_info[VDSO_ABI_AA32].cm = &aarch32_vdso_maps[AA32_MAP_VDSO];
-
-	ret = __vdso_init(VDSO_ABI_AA32);
-	if (ret)
-		return ret;
-
-	return aarch32_alloc_kuser_vdso_page();
-}
-#else
-static int __aarch32_alloc_vdso_pages(void)
+static int aarch32_alloc_sigpage(void)
 {
 	extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[];
 	int sigret_sz = __aarch32_sigret_code_end - __aarch32_sigret_code_start;
 	unsigned long sigpage;
-	int ret;
 
 	sigpage = get_zeroed_page(GFP_ATOMIC);
 	if (!sigpage)
@@ -271,18 +251,34 @@
 	memcpy((void *)sigpage, __aarch32_sigret_code_start, sigret_sz);
 	aarch32_sig_page = virt_to_page(sigpage);
 	flush_dcache_page(aarch32_sig_page);
+	return 0;
+}
 
-	ret = aarch32_alloc_kuser_vdso_page();
-	if (ret)
-		free_page(sigpage);
+#ifdef CONFIG_COMPAT_VDSO
+static int __aarch32_alloc_vdso_pages(void)
+{
+	vdso_info[VDSO_ABI_AA32].dm = &aarch32_vdso_maps[AA32_MAP_VVAR];
+	vdso_info[VDSO_ABI_AA32].cm = &aarch32_vdso_maps[AA32_MAP_VDSO];
 
-	return ret;
+	return __vdso_init(VDSO_ABI_AA32);
 }
 #endif /* CONFIG_COMPAT_VDSO */
 
 static int __init aarch32_alloc_vdso_pages(void)
 {
-	return __aarch32_alloc_vdso_pages();
+	int ret;
+
+#ifdef CONFIG_COMPAT_VDSO
+	ret = __aarch32_alloc_vdso_pages();
+	if (ret)
+		return ret;
+#endif
+
+	ret = aarch32_alloc_sigpage();
+	if (ret)
+		return ret;
+
+	return aarch32_alloc_kuser_vdso_page();
 }
 arch_initcall(aarch32_alloc_vdso_pages);
 
@@ -305,7 +301,6 @@
 	return PTR_ERR_OR_ZERO(ret);
 }
 
-#ifndef CONFIG_COMPAT_VDSO
 static int aarch32_sigreturn_setup(struct mm_struct *mm)
 {
 	unsigned long addr;
@@ -328,12 +323,11 @@
 	if (IS_ERR(ret))
 		goto out;
 
-	mm->context.vdso = (void *)addr;
+	mm->context.sigpage = (void *)addr;
 
 out:
 	return PTR_ERR_OR_ZERO(ret);
 }
-#endif /* !CONFIG_COMPAT_VDSO */
 
 int aarch32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 {
@@ -352,10 +346,11 @@
 				       mm,
 				       bprm,
 				       uses_interp);
-#else
-	ret = aarch32_sigreturn_setup(mm);
+	if (ret)
+		goto out;
 #endif /* CONFIG_COMPAT_VDSO */
 
+	ret = aarch32_sigreturn_setup(mm);
 out:
 	mmap_write_unlock(mm);
 	return ret;
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index 556d424..45d5cfe 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -23,13 +23,14 @@
 # potential future proofing if we end up with internal calls to the exported
 # routines, as x86 does (see 6f121e548f83 ("x86, vdso: Reimplement vdso.so
 # preparation in build-time C")).
-ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv \
-		-Bsymbolic --eh-frame-hdr --build-id -n $(btildflags-y) -T
+ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv	\
+	     -Bsymbolic $(call ld-option, --no-eh-frame-hdr) --build-id -n	\
+	     $(btildflags-y) -T
 
 ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18
 ccflags-y += -DDISABLE_BRANCH_PROFILING
 
-CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS)
+CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS) $(GCC_PLUGINS_CFLAGS)
 KBUILD_CFLAGS			+= $(DISABLE_LTO)
 KASAN_SANITIZE			:= n
 UBSAN_SANITIZE			:= n
diff --git a/arch/arm64/kernel/vdso/sigreturn.S b/arch/arm64/kernel/vdso/sigreturn.S
index 620a3ef..0e18729 100644
--- a/arch/arm64/kernel/vdso/sigreturn.S
+++ b/arch/arm64/kernel/vdso/sigreturn.S
@@ -18,29 +18,40 @@
 
 	.text
 
+/*
+ * NOTE!!!  You may notice that all of the .cfi directives in this file have
+ * been commented out. This is because they have been shown to trigger segfaults
+ * in libgcc when unwinding out of a SIGCANCEL handler to invoke pthread
+ * cleanup handlers during the thread cancellation dance. By omitting the
+ * directives, we trigger an arm64-specific fallback path in the unwinder which
+ * recognises the signal frame and restores many of the registers directly from
+ * the sigcontext. Re-enabling the cfi directives here therefore needs to be
+ * much more comprehensive to reduce the risk of further regressions.
+ */
+
 /* Ensure that the mysterious NOP can be associated with a function. */
-	.cfi_startproc
+//	.cfi_startproc
 
 /*
- * .cfi_signal_frame causes the corresponding Frame Description Entry in the
- * .eh_frame section to be annotated as a signal frame. This allows DWARF
- * unwinders (e.g. libstdc++) to implement _Unwind_GetIPInfo(), which permits
- * unwinding out of the signal trampoline without the need for the mysterious
- * NOP.
+ * .cfi_signal_frame causes the corresponding Frame Description Entry (FDE) in
+ * the .eh_frame section to be annotated as a signal frame. This allows DWARF
+ * unwinders (e.g. libstdc++) to implement _Unwind_GetIPInfo() and identify
+ * the next frame using the unmodified return address instead of subtracting 1,
+ * which may yield the wrong FDE.
  */
-	.cfi_signal_frame
+//	.cfi_signal_frame
 
 /*
  * Tell the unwinder where to locate the frame record linking back to the
- * interrupted context. We don't provide unwind info for registers other
- * than the frame pointer and the link register here; in practice, this
- * is sufficient for unwinding in C/C++ based runtimes and the values in
- * the sigcontext may have been modified by this point anyway. Debuggers
+ * interrupted context. We don't provide unwind info for registers other than
+ * the frame pointer and the link register here; in practice, this is likely to
+ * be insufficient for unwinding in C/C++ based runtimes, especially without a
+ * means to restore the stack pointer. Thankfully, unwinders and debuggers
  * already have baked-in strategies for attempting to unwind out of signals.
  */
-	.cfi_def_cfa    x29, 0
-	.cfi_offset     x29, 0 * 8
-	.cfi_offset     x30, 1 * 8
+//	.cfi_def_cfa    x29, 0
+//	.cfi_offset     x29, 0 * 8
+//	.cfi_offset     x30, 1 * 8
 
 /*
  * This mysterious NOP is required for some unwinders (e.g. libc++) that
@@ -51,16 +62,19 @@
 	nop	// Mysterious NOP
 
 /*
- * GDB relies on being able to identify the sigreturn instruction sequence to
- * unwind from signal handlers. We cannot, therefore, use SYM_FUNC_START()
- * here, as it will emit a BTI C instruction and break the unwinder. Thankfully,
- * this function is only ever called from a RET and so omitting the landing pad
- * is perfectly fine.
+ * GDB, libgcc and libunwind rely on being able to identify the sigreturn
+ * instruction sequence to unwind from signal handlers. We cannot, therefore,
+ * use SYM_FUNC_START() here, as it will emit a BTI C instruction and break the
+ * unwinder. Thankfully, this function is only ever called from a RET and so
+ * omitting the landing pad is perfectly fine.
  */
 SYM_CODE_START(__kernel_rt_sigreturn)
+//	PLEASE DO NOT MODIFY
 	mov	x8, #__NR_rt_sigreturn
+//	PLEASE DO NOT MODIFY
 	svc	#0
-	.cfi_endproc
+//	PLEASE DO NOT MODIFY
+//	.cfi_endproc
 SYM_CODE_END(__kernel_rt_sigreturn)
 
 emit_aarch64_feature_1_and
diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile
index 7ea1e82..5139a5f 100644
--- a/arch/arm64/kernel/vdso32/Makefile
+++ b/arch/arm64/kernel/vdso32/Makefile
@@ -14,7 +14,7 @@
 COMPAT_GCC_TOOLCHAIN := $(realpath $(COMPAT_GCC_TOOLCHAIN_DIR)/..)
 
 CC_COMPAT_CLANG_FLAGS := --target=$(notdir $(CROSS_COMPILE_COMPAT:%-=%))
-CC_COMPAT_CLANG_FLAGS += --prefix=$(COMPAT_GCC_TOOLCHAIN_DIR)
+CC_COMPAT_CLANG_FLAGS += --prefix=$(COMPAT_GCC_TOOLCHAIN_DIR)$(notdir $(CROSS_COMPILE_COMPAT))
 CC_COMPAT_CLANG_FLAGS += -no-integrated-as -Qunused-arguments
 ifneq ($(COMPAT_GCC_TOOLCHAIN),)
 CC_COMPAT_CLANG_FLAGS += --gcc-toolchain=$(COMPAT_GCC_TOOLCHAIN)
@@ -140,7 +140,6 @@
 
 c-obj-vdso := note.o
 c-obj-vdso-gettimeofday := vgettimeofday.o
-asm-obj-vdso := sigreturn.o
 
 ifneq ($(c-gettimeofday-y),)
 VDSO_CFLAGS_gettimeofday_o += -include $(c-gettimeofday-y)
diff --git a/arch/arm64/kernel/vdso32/sigreturn.S b/arch/arm64/kernel/vdso32/sigreturn.S
deleted file mode 100644
index b0091064..0000000
--- a/arch/arm64/kernel/vdso32/sigreturn.S
+++ /dev/null
@@ -1,58 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * This file provides both A32 and T32 versions, in accordance with the
- * arm sigreturn code.
- *
- * Please read the comments in arch/arm64/kernel/vdso/sigreturn.S to
- * understand some of the craziness in here.
- *
- * Copyright (C) 2018 ARM Limited
- */
-
-#include <linux/linkage.h>
-#include <asm/asm-offsets.h>
-#include <asm/unistd.h>
-
-	.text
-
-	.arm
-	.fnstart
-	.save {r0-r15}
-	.pad #COMPAT_SIGFRAME_REGS_OFFSET
-	nop
-SYM_CODE_START(__kernel_sigreturn_arm)
-	mov r7, #__NR_compat_sigreturn
-	svc #0
-	.fnend
-SYM_CODE_END(__kernel_sigreturn_arm)
-
-	.fnstart
-	.save {r0-r15}
-	.pad #COMPAT_RT_SIGFRAME_REGS_OFFSET
-	nop
-SYM_CODE_START(__kernel_rt_sigreturn_arm)
-	mov r7, #__NR_compat_rt_sigreturn
-	svc #0
-	.fnend
-SYM_CODE_END(__kernel_rt_sigreturn_arm)
-
-	.thumb
-	.fnstart
-	.save {r0-r15}
-	.pad #COMPAT_SIGFRAME_REGS_OFFSET
-	nop
-SYM_CODE_START(__kernel_sigreturn_thumb)
-	mov r7, #__NR_compat_sigreturn
-	svc #0
-	.fnend
-SYM_CODE_END(__kernel_sigreturn_thumb)
-
-	.fnstart
-	.save {r0-r15}
-	.pad #COMPAT_RT_SIGFRAME_REGS_OFFSET
-	nop
-SYM_CODE_START(__kernel_rt_sigreturn_thumb)
-	mov r7, #__NR_compat_rt_sigreturn
-	svc #0
-	.fnend
-SYM_CODE_END(__kernel_rt_sigreturn_thumb)
diff --git a/arch/arm64/kernel/vdso32/vdso.lds.S b/arch/arm64/kernel/vdso32/vdso.lds.S
index a3944927e..337d035 100644
--- a/arch/arm64/kernel/vdso32/vdso.lds.S
+++ b/arch/arm64/kernel/vdso32/vdso.lds.S
@@ -64,19 +64,7 @@
 		__vdso_clock_gettime;
 		__vdso_gettimeofday;
 		__vdso_clock_getres;
-		__kernel_sigreturn_arm;
-		__kernel_sigreturn_thumb;
-		__kernel_rt_sigreturn_arm;
-		__kernel_rt_sigreturn_thumb;
 		__vdso_clock_gettime64;
 	local: *;
 	};
 }
-
-/*
- * Make the sigreturn code visible to the kernel.
- */
-VDSO_compat_sigreturn_arm	= __kernel_sigreturn_arm;
-VDSO_compat_sigreturn_thumb	= __kernel_sigreturn_thumb;
-VDSO_compat_rt_sigreturn_arm	= __kernel_rt_sigreturn_arm;
-VDSO_compat_rt_sigreturn_thumb	= __kernel_rt_sigreturn_thumb;
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 6827da7..5423ffe 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -165,9 +165,6 @@
 		*(.altinstructions)
 		__alt_instructions_end = .;
 	}
-	.altinstr_replacement : {
-		*(.altinstr_replacement)
-	}
 
 	. = ALIGN(SEGMENT_ALIGN);
 	__inittext_end = .;
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index 6e6ed55..e76c0e8 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -136,11 +136,15 @@
 
 1:	cmp	x0, #HVC_RESET_VECTORS
 	b.ne	1f
-reset:
+
 	/*
-	 * Reset kvm back to the hyp stub. Do not clobber x0-x4 in
-	 * case we coming via HVC_SOFT_RESTART.
+	 * Set the HVC_RESET_VECTORS return code before entering the common
+	 * path so that we do not clobber x0-x2 in case we are coming via
+	 * HVC_SOFT_RESTART.
 	 */
+	mov	x0, xzr
+reset:
+	/* Reset kvm back to the hyp stub. */
 	mrs	x5, sctlr_el2
 	mov_q	x6, SCTLR_ELx_FLAGS
 	bic	x5, x5, x6		// Clear SCTL_M and etc
@@ -151,7 +155,6 @@
 	/* Install stub vectors */
 	adr_l	x5, __hyp_stub_vectors
 	msr	vbar_el2, x5
-	mov	x0, xzr
 	eret
 
 1:	/* Bad stub call */
diff --git a/arch/arm64/kvm/pmu.c b/arch/arm64/kvm/pmu.c
index b5ae3a5..3c22416 100644
--- a/arch/arm64/kvm/pmu.c
+++ b/arch/arm64/kvm/pmu.c
@@ -159,7 +159,10 @@
 }
 
 /*
- * On VHE ensure that only guest events have EL0 counting enabled
+ * On VHE ensure that only guest events have EL0 counting enabled.
+ * This is called from both vcpu_{load,put} and the sysreg handling.
+ * Since the latter is preemptible, special care must be taken to
+ * disable preemption.
  */
 void kvm_vcpu_pmu_restore_guest(struct kvm_vcpu *vcpu)
 {
@@ -169,12 +172,14 @@
 	if (!has_vhe())
 		return;
 
+	preempt_disable();
 	host = this_cpu_ptr(&kvm_host_data);
 	events_guest = host->pmu_events.events_guest;
 	events_host = host->pmu_events.events_host;
 
 	kvm_vcpu_pmu_enable_el0(events_guest);
 	kvm_vcpu_pmu_disable_el0(events_host);
+	preempt_enable();
 }
 
 /*
diff --git a/arch/arm64/kvm/pvtime.c b/arch/arm64/kvm/pvtime.c
index 1e0f4c2..f7b52ce 100644
--- a/arch/arm64/kvm/pvtime.c
+++ b/arch/arm64/kvm/pvtime.c
@@ -3,6 +3,7 @@
 
 #include <linux/arm-smccc.h>
 #include <linux/kvm_host.h>
+#include <linux/sched/stat.h>
 
 #include <asm/kvm_mmu.h>
 #include <asm/pvclock-abi.h>
@@ -73,6 +74,11 @@
 	return base;
 }
 
+static bool kvm_arm_pvtime_supported(void)
+{
+	return !!sched_info_on();
+}
+
 int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu,
 			    struct kvm_device_attr *attr)
 {
@@ -82,7 +88,8 @@
 	int ret = 0;
 	int idx;
 
-	if (attr->attr != KVM_ARM_VCPU_PVTIME_IPA)
+	if (!kvm_arm_pvtime_supported() ||
+	    attr->attr != KVM_ARM_VCPU_PVTIME_IPA)
 		return -ENXIO;
 
 	if (get_user(ipa, user))
@@ -110,7 +117,8 @@
 	u64 __user *user = (u64 __user *)attr->addr;
 	u64 ipa;
 
-	if (attr->attr != KVM_ARM_VCPU_PVTIME_IPA)
+	if (!kvm_arm_pvtime_supported() ||
+	    attr->attr != KVM_ARM_VCPU_PVTIME_IPA)
 		return -ENXIO;
 
 	ipa = vcpu->arch.steal.base;
@@ -125,7 +133,8 @@
 {
 	switch (attr->attr) {
 	case KVM_ARM_VCPU_PVTIME_IPA:
-		return 0;
+		if (kvm_arm_pvtime_supported())
+			return 0;
 	}
 	return -ENXIO;
 }
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index d3b2090..6ed36be5 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -245,7 +245,7 @@
  */
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 {
-	int ret = -EINVAL;
+	int ret;
 	bool loaded;
 	u32 pstate;
 
@@ -269,15 +269,19 @@
 
 	if (test_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, vcpu->arch.features) ||
 	    test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features)) {
-		if (kvm_vcpu_enable_ptrauth(vcpu))
+		if (kvm_vcpu_enable_ptrauth(vcpu)) {
+			ret = -EINVAL;
 			goto out;
+		}
 	}
 
 	switch (vcpu->arch.target) {
 	default:
 		if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) {
-			if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1))
+			if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1)) {
+				ret = -EINVAL;
 				goto out;
+			}
 			pstate = VCPU_RESET_PSTATE_SVC;
 		} else {
 			pstate = VCPU_RESET_PSTATE_EL1;
diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c
index 27ac833..b5fa73c 100644
--- a/arch/arm64/kvm/vgic/vgic-v4.c
+++ b/arch/arm64/kvm/vgic/vgic-v4.c
@@ -90,7 +90,15 @@
 	    !irqd_irq_disabled(&irq_to_desc(irq)->irq_data))
 		disable_irq_nosync(irq);
 
+	/*
+	 * The v4.1 doorbell can fire concurrently with the vPE being
+	 * made non-resident. Ensure we only update pending_last
+	 * *after* the non-residency sequence has completed.
+	 */
+	raw_spin_lock(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vpe_lock);
 	vcpu->arch.vgic_cpu.vgic_v3.its_vpe.pending_last = true;
+	raw_spin_unlock(&vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vpe_lock);
+
 	kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
 	kvm_vcpu_kick(vcpu);
 
diff --git a/arch/m68k/kernel/setup_no.c b/arch/m68k/kernel/setup_no.c
index e779b19..f66f4b1 100644
--- a/arch/m68k/kernel/setup_no.c
+++ b/arch/m68k/kernel/setup_no.c
@@ -138,7 +138,8 @@
 	pr_debug("MEMORY -> ROMFS=0x%p-0x%06lx MEM=0x%06lx-0x%06lx\n ",
 		 __bss_stop, memory_start, memory_start, memory_end);
 
-	memblock_add(memory_start, memory_end - memory_start);
+	memblock_add(_rambase, memory_end - _rambase);
+	memblock_reserve(_rambase, memory_start - _rambase);
 
 	/* Keep a copy of command line */
 	*cmdline_p = &command_line[0];
diff --git a/arch/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c
index 29f4792..7d04210 100644
--- a/arch/m68k/mm/mcfmmu.c
+++ b/arch/m68k/mm/mcfmmu.c
@@ -174,7 +174,7 @@
 	m68k_memory[0].addr = _rambase;
 	m68k_memory[0].size = _ramend - _rambase;
 
-	memblock_add(m68k_memory[0].addr, m68k_memory[0].size);
+	memblock_add_node(m68k_memory[0].addr, m68k_memory[0].size, 0);
 
 	/* compute total pages in system */
 	num_pages = PFN_DOWN(_ramend - _rambase);
diff --git a/arch/mips/boot/dts/ingenic/gcw0.dts b/arch/mips/boot/dts/ingenic/gcw0.dts
index 8d22828..bc72304 100644
--- a/arch/mips/boot/dts/ingenic/gcw0.dts
+++ b/arch/mips/boot/dts/ingenic/gcw0.dts
@@ -92,7 +92,7 @@
 			"MIC1N", "Built-in Mic";
 		simple-audio-card,pin-switches = "Speaker", "Headphones";
 
-		simple-audio-card,hp-det-gpio = <&gpf 21 GPIO_ACTIVE_HIGH>;
+		simple-audio-card,hp-det-gpio = <&gpf 21 GPIO_ACTIVE_LOW>;
 		simple-audio-card,aux-devs = <&speaker_amp>, <&headphones_amp>;
 
 		simple-audio-card,bitclock-master = <&dai_codec>;
diff --git a/arch/mips/include/asm/unroll.h b/arch/mips/include/asm/unroll.h
index c628747..7dd4a80 100644
--- a/arch/mips/include/asm/unroll.h
+++ b/arch/mips/include/asm/unroll.h
@@ -19,15 +19,13 @@
 								\
 	/*							\
 	 * We can't unroll if the number of iterations isn't	\
-	 * compile-time constant. Unfortunately GCC versions	\
-	 * up until 4.6 tend to miss obvious constants & cause	\
+	 * compile-time constant. Unfortunately clang versions	\
+	 * up until 8.0 tend to miss obvious constants & cause	\
 	 * this check to fail, even though they go on to	\
 	 * generate reasonable code for the switch statement,	\
 	 * so we skip the sanity check for those compilers.	\
 	 */							\
-	BUILD_BUG_ON((CONFIG_GCC_VERSION >= 40700 ||		\
-		      CONFIG_CLANG_VERSION >= 80000) &&		\
-		     !__builtin_constant_p(times));		\
+	BUILD_BUG_ON(!__builtin_constant_p(times));		\
 								\
 	switch (times) {					\
 	case 32: fn(__VA_ARGS__); /* fall through */		\
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 7c32c95..f655af6 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -723,12 +723,14 @@
 		perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, 0);
 
 		/* Do not emulate on unsupported core models. */
-		if (!loongson3_cpucfg_emulation_enabled(&current_cpu_data))
+		preempt_disable();
+		if (!loongson3_cpucfg_emulation_enabled(&current_cpu_data)) {
+			preempt_enable();
 			return -1;
-
+		}
 		regs->regs[rd] = loongson3_cpucfg_read_synthesized(
 			&current_cpu_data, sel);
-
+		preempt_enable();
 		return 0;
 	}
 
@@ -2169,6 +2171,7 @@
 
 	change_c0_status(ST0_CU|ST0_MX|ST0_RE|ST0_FR|ST0_BEV|ST0_TS|ST0_KX|ST0_SX|ST0_UX,
 			 status_set);
+	back_to_back_c0_hazard();
 }
 
 unsigned int hwrena;
diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c
index 5ae82d9..d242300c 100644
--- a/arch/mips/kvm/emulate.c
+++ b/arch/mips/kvm/emulate.c
@@ -1722,6 +1722,7 @@
 			  vcpu->arch.gprs[rt], *(u32 *)data);
 		break;
 
+#if defined(CONFIG_64BIT) && defined(CONFIG_KVM_MIPS_VZ)
 	case sdl_op:
 		run->mmio.phys_addr = kvm_mips_callbacks->gva_to_gpa(
 					vcpu->arch.host_cp0_badvaddr) & (~0x7);
@@ -1815,6 +1816,7 @@
 			  vcpu->arch.pc, vcpu->arch.host_cp0_badvaddr,
 			  vcpu->arch.gprs[rt], *(u64 *)data);
 		break;
+#endif
 
 #ifdef CONFIG_CPU_LOONGSON64
 	case sdc2_op:
@@ -2002,6 +2004,7 @@
 		}
 		break;
 
+#if defined(CONFIG_64BIT) && defined(CONFIG_KVM_MIPS_VZ)
 	case ldl_op:
 		run->mmio.phys_addr = kvm_mips_callbacks->gva_to_gpa(
 					vcpu->arch.host_cp0_badvaddr) & (~0x7);
@@ -2073,6 +2076,7 @@
 			break;
 		}
 		break;
+#endif
 
 #ifdef CONFIG_CPU_LOONGSON64
 	case ldc2_op:
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 521bd58..666d335 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -67,8 +67,10 @@
 	VCPU_STAT("vz_ghfc", vz_ghfc_exits),
 	VCPU_STAT("vz_gpa", vz_gpa_exits),
 	VCPU_STAT("vz_resvd", vz_resvd_exits),
+#ifdef CONFIG_CPU_LOONGSON64
 	VCPU_STAT("vz_cpucfg", vz_cpucfg_exits),
 #endif
+#endif
 	VCPU_STAT("halt_successful_poll", halt_successful_poll),
 	VCPU_STAT("halt_attempted_poll", halt_attempted_poll),
 	VCPU_STAT("halt_poll_invalid", halt_poll_invalid),
diff --git a/arch/mips/lantiq/xway/sysctrl.c b/arch/mips/lantiq/xway/sysctrl.c
index aa37545..b103420 100644
--- a/arch/mips/lantiq/xway/sysctrl.c
+++ b/arch/mips/lantiq/xway/sysctrl.c
@@ -514,8 +514,8 @@
 		clkdev_add_pmu("1e10b308.eth", NULL, 0, 0, PMU_SWITCH |
 			       PMU_PPE_DP | PMU_PPE_TC);
 		clkdev_add_pmu("1da00000.usif", "NULL", 1, 0, PMU_USIF);
-		clkdev_add_pmu("1e108000.gswip", "gphy0", 0, 0, PMU_GPHY);
-		clkdev_add_pmu("1e108000.gswip", "gphy1", 0, 0, PMU_GPHY);
+		clkdev_add_pmu("1e108000.switch", "gphy0", 0, 0, PMU_GPHY);
+		clkdev_add_pmu("1e108000.switch", "gphy1", 0, 0, PMU_GPHY);
 		clkdev_add_pmu("1e103100.deu", NULL, 1, 0, PMU_DEU);
 		clkdev_add_pmu("1e116000.mei", "afe", 1, 2, PMU_ANALOG_DSL_AFE);
 		clkdev_add_pmu("1e116000.mei", "dfe", 1, 0, PMU_DFE);
@@ -538,8 +538,8 @@
 				PMU_SWITCH | PMU_PPE_DPLUS | PMU_PPE_DPLUM |
 				PMU_PPE_EMA | PMU_PPE_TC | PMU_PPE_SLL01 |
 				PMU_PPE_QSB | PMU_PPE_TOP);
-		clkdev_add_pmu("1e108000.gswip", "gphy0", 0, 0, PMU_GPHY);
-		clkdev_add_pmu("1e108000.gswip", "gphy1", 0, 0, PMU_GPHY);
+		clkdev_add_pmu("1e108000.switch", "gphy0", 0, 0, PMU_GPHY);
+		clkdev_add_pmu("1e108000.switch", "gphy1", 0, 0, PMU_GPHY);
 		clkdev_add_pmu("1e103000.sdio", NULL, 1, 0, PMU_SDIO);
 		clkdev_add_pmu("1e103100.deu", NULL, 1, 0, PMU_DEU);
 		clkdev_add_pmu("1e116000.mei", "dfe", 1, 0, PMU_DFE);
diff --git a/arch/mips/pci/pci-xtalk-bridge.c b/arch/mips/pci/pci-xtalk-bridge.c
index 3b2552f..5958217 100644
--- a/arch/mips/pci/pci-xtalk-bridge.c
+++ b/arch/mips/pci/pci-xtalk-bridge.c
@@ -627,9 +627,10 @@
 		return -ENOMEM;
 	domain = irq_domain_create_hierarchy(parent, 0, 8, fn,
 					     &bridge_domain_ops, NULL);
-	irq_domain_free_fwnode(fn);
-	if (!domain)
+	if (!domain) {
+		irq_domain_free_fwnode(fn);
 		return -ENOMEM;
+	}
 
 	pci_set_flags(PCI_PROBE_ONLY);
 
diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c
index c152a68..3457276 100644
--- a/arch/openrisc/kernel/dma.c
+++ b/arch/openrisc/kernel/dma.c
@@ -74,8 +74,11 @@
 	 * We need to iterate through the pages, clearing the dcache for
 	 * them and setting the cache-inhibit bit.
 	 */
+	mmap_read_lock(&init_mm);
 	error = walk_page_range(&init_mm, va, va + size, &set_nocache_walk_ops,
 			NULL);
+	mmap_read_unlock(&init_mm);
+
 	if (error)
 		return ERR_PTR(error);
 	return cpu_addr;
@@ -85,9 +88,11 @@
 {
 	unsigned long va = (unsigned long)cpu_addr;
 
+	mmap_read_lock(&init_mm);
 	/* walk_page_range shouldn't be able to fail here */
 	WARN_ON(walk_page_range(&init_mm, va, va + size,
 			&clear_nocache_walk_ops, NULL));
+	mmap_read_unlock(&init_mm);
 }
 
 void arch_sync_dma_for_device(phys_addr_t addr, size_t size,
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index 118953d..6dd4171 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -212,6 +212,8 @@
 	_atomic_spin_unlock_irqrestore(v, flags);
 }
 
+#define atomic64_set_release(v, i)	atomic64_set((v), (i))
+
 static __inline__ s64
 atomic64_read(const atomic64_t *v)
 {
diff --git a/arch/parisc/include/asm/cmpxchg.h b/arch/parisc/include/asm/cmpxchg.h
index ab5c215..0689585 100644
--- a/arch/parisc/include/asm/cmpxchg.h
+++ b/arch/parisc/include/asm/cmpxchg.h
@@ -60,6 +60,7 @@
 extern unsigned long __cmpxchg_u32(volatile unsigned int *m, unsigned int old,
 				   unsigned int new_);
 extern u64 __cmpxchg_u64(volatile u64 *ptr, u64 old, u64 new_);
+extern u8 __cmpxchg_u8(volatile u8 *ptr, u8 old, u8 new_);
 
 /* don't worry...optimizer will get rid of most of this */
 static inline unsigned long
@@ -71,6 +72,7 @@
 #endif
 	case 4: return __cmpxchg_u32((unsigned int *)ptr,
 				     (unsigned int)old, (unsigned int)new_);
+	case 1: return __cmpxchg_u8((u8 *)ptr, (u8)old, (u8)new_);
 	}
 	__cmpxchg_called_with_bad_pointer();
 	return old;
diff --git a/arch/parisc/lib/bitops.c b/arch/parisc/lib/bitops.c
index 70ffbcf..2e4d1f0 100644
--- a/arch/parisc/lib/bitops.c
+++ b/arch/parisc/lib/bitops.c
@@ -79,3 +79,15 @@
 	_atomic_spin_unlock_irqrestore(ptr, flags);
 	return (unsigned long)prev;
 }
+
+u8 __cmpxchg_u8(volatile u8 *ptr, u8 old, u8 new)
+{
+	unsigned long flags;
+	u8 prev;
+
+	_atomic_spin_lock_irqsave(ptr, flags);
+	if ((prev = *ptr) == old)
+		*ptr = new;
+	_atomic_spin_unlock_irqrestore(ptr, flags);
+	return prev;
+}
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 128192e..3230c1d 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -23,6 +23,8 @@
 	select ARCH_HAS_SET_DIRECT_MAP
 	select ARCH_HAS_SET_MEMORY
 	select ARCH_HAS_STRICT_KERNEL_RWX if MMU
+	select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX
+	select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU
 	select ARCH_WANT_FRAME_POINTERS
 	select ARCH_WANT_HUGE_PMD_SHARE if 64BIT
diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h
index 3f1737f..d0e24aa 100644
--- a/arch/riscv/include/asm/barrier.h
+++ b/arch/riscv/include/asm/barrier.h
@@ -58,8 +58,16 @@
  * The AQ/RL pair provides a RCpc critical section, but there's not really any
  * way we can take advantage of that here because the ordering is only enforced
  * on that one lock.  Thus, we're just doing a full fence.
+ *
+ * Since we allow writeX to be called from preemptive regions we need at least
+ * an "o" in the predecessor set to ensure device writes are visible before the
+ * task is marked as available for scheduling on a new hart.  While I don't see
+ * any concrete reason we need a full IO fence, it seems safer to just upgrade
+ * this in order to avoid any IO crossing a scheduling boundary.  In both
+ * instances the scheduler pairs this with an mb(), so nothing is necessary on
+ * the new hart.
  */
-#define smp_mb__after_spinlock()	RISCV_FENCE(rw,rw)
+#define smp_mb__after_spinlock()	RISCV_FENCE(iorw,iorw)
 
 #include <asm-generic/barrier.h>
 
diff --git a/arch/riscv/include/asm/gdb_xml.h b/arch/riscv/include/asm/gdb_xml.h
index 041b45f..0934211 100644
--- a/arch/riscv/include/asm/gdb_xml.h
+++ b/arch/riscv/include/asm/gdb_xml.h
@@ -3,8 +3,7 @@
 #ifndef __ASM_GDB_XML_H_
 #define __ASM_GDB_XML_H_
 
-#define kgdb_arch_gdb_stub_feature riscv_gdb_stub_feature
-static const char riscv_gdb_stub_feature[64] =
+const char riscv_gdb_stub_feature[64] =
 			"PacketSize=800;qXfer:features:read+;";
 
 static const char gdb_xfer_read_target[31] = "qXfer:features:read:target.xml:";
diff --git a/arch/riscv/include/asm/kgdb.h b/arch/riscv/include/asm/kgdb.h
index 8177a45..46677da 100644
--- a/arch/riscv/include/asm/kgdb.h
+++ b/arch/riscv/include/asm/kgdb.h
@@ -19,7 +19,6 @@
 
 #ifndef	__ASSEMBLY__
 
-extern int kgdb_has_hit_break(unsigned long addr);
 extern unsigned long kgdb_compiled_break;
 
 static inline void arch_kgdb_breakpoint(void)
@@ -106,7 +105,9 @@
 #define DBG_REG_BADADDR_OFF 34
 #define DBG_REG_CAUSE_OFF 35
 
-#include <asm/gdb_xml.h>
+extern const char riscv_gdb_stub_feature[64];
+
+#define kgdb_arch_gdb_stub_feature riscv_gdb_stub_feature
 
 #endif
 #endif
diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h
index 1dd12a0..464a2bb 100644
--- a/arch/riscv/include/asm/thread_info.h
+++ b/arch/riscv/include/asm/thread_info.h
@@ -12,7 +12,11 @@
 #include <linux/const.h>
 
 /* thread information allocation */
+#ifdef CONFIG_64BIT
+#define THREAD_SIZE_ORDER	(2)
+#else
 #define THREAD_SIZE_ORDER	(1)
+#endif
 #define THREAD_SIZE		(PAGE_SIZE << THREAD_SIZE_ORDER)
 
 #ifndef __ASSEMBLY__
diff --git a/arch/riscv/kernel/kgdb.c b/arch/riscv/kernel/kgdb.c
index c3275f4..963ed7e 100644
--- a/arch/riscv/kernel/kgdb.c
+++ b/arch/riscv/kernel/kgdb.c
@@ -44,18 +44,18 @@
 DECLARE_INSN(c_bnez, MATCH_C_BNEZ, MASK_C_BNEZ)
 DECLARE_INSN(sret, MATCH_SRET, MASK_SRET)
 
-int decode_register_index(unsigned long opcode, int offset)
+static int decode_register_index(unsigned long opcode, int offset)
 {
 	return (opcode >> offset) & 0x1F;
 }
 
-int decode_register_index_short(unsigned long opcode, int offset)
+static int decode_register_index_short(unsigned long opcode, int offset)
 {
 	return ((opcode >> offset) & 0x7) + 8;
 }
 
 /* Calculate the new address for after a step */
-int get_step_address(struct pt_regs *regs, unsigned long *next_addr)
+static int get_step_address(struct pt_regs *regs, unsigned long *next_addr)
 {
 	unsigned long pc = regs->epc;
 	unsigned long *regs_ptr = (unsigned long *)regs;
@@ -136,7 +136,7 @@
 	return 0;
 }
 
-int do_single_step(struct pt_regs *regs)
+static int do_single_step(struct pt_regs *regs)
 {
 	/* Determine where the target instruction will send us to */
 	unsigned long addr = 0;
@@ -320,7 +320,7 @@
 	return err;
 }
 
-int kgdb_riscv_kgdbbreak(unsigned long addr)
+static int kgdb_riscv_kgdbbreak(unsigned long addr)
 {
 	if (stepped_address == addr)
 		return KGDB_SW_SINGLE_STEP;
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
index 38ba55b..e4c7c2c 100644
--- a/arch/riscv/kernel/vdso/Makefile
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -17,7 +17,7 @@
 obj-vdso = $(patsubst %, %.o, $(vdso-syms)) note.o
 
 ifneq ($(c-gettimeofday-y),)
-  CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y)
+  CFLAGS_vgettimeofday.o += -fPIC -include $(c-gettimeofday-y)
 endif
 
 # Build rules
@@ -27,6 +27,9 @@
 obj-y += vdso.o vdso-syms.o
 CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
 
+# Disable -pg to prevent insert call site
+CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os
+
 # Disable gcov profiling for VDSO code
 GCOV_PROFILE := n
 
diff --git a/arch/riscv/kernel/vdso/vgettimeofday.c b/arch/riscv/kernel/vdso/vgettimeofday.c
index d264943..cc0d806 100644
--- a/arch/riscv/kernel/vdso/vgettimeofday.c
+++ b/arch/riscv/kernel/vdso/vgettimeofday.c
@@ -9,16 +9,22 @@
 #include <linux/time.h>
 #include <linux/types.h>
 
+extern
+int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts);
 int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts)
 {
 	return __cvdso_clock_gettime(clock, ts);
 }
 
+extern
+int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz);
 int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
 {
 	return __cvdso_gettimeofday(tv, tz);
 }
 
+extern
+int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res);
 int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res)
 {
 	return __cvdso_clock_getres(clock_id, res);
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index f4adb36..79e9d55 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -95,19 +95,40 @@
 #ifdef CONFIG_BLK_DEV_INITRD
 static void __init setup_initrd(void)
 {
+	phys_addr_t start;
 	unsigned long size;
 
-	if (initrd_start >= initrd_end) {
-		pr_info("initrd not found or empty");
-		goto disable;
-	}
-	if (__pa_symbol(initrd_end) > PFN_PHYS(max_low_pfn)) {
-		pr_err("initrd extends beyond end of memory");
+	/* Ignore the virtul address computed during device tree parsing */
+	initrd_start = initrd_end = 0;
+
+	if (!phys_initrd_size)
+		return;
+	/*
+	 * Round the memory region to page boundaries as per free_initrd_mem()
+	 * This allows us to detect whether the pages overlapping the initrd
+	 * are in use, but more importantly, reserves the entire set of pages
+	 * as we don't want these pages allocated for other purposes.
+	 */
+	start = round_down(phys_initrd_start, PAGE_SIZE);
+	size = phys_initrd_size + (phys_initrd_start - start);
+	size = round_up(size, PAGE_SIZE);
+
+	if (!memblock_is_region_memory(start, size)) {
+		pr_err("INITRD: 0x%08llx+0x%08lx is not a memory region",
+		       (u64)start, size);
 		goto disable;
 	}
 
-	size = initrd_end - initrd_start;
-	memblock_reserve(__pa_symbol(initrd_start), size);
+	if (memblock_is_region_reserved(start, size)) {
+		pr_err("INITRD: 0x%08llx+0x%08lx overlaps in-use memory region\n",
+		       (u64)start, size);
+		goto disable;
+	}
+
+	memblock_reserve(start, size);
+	/* Now convert initrd to virtual addresses */
+	initrd_start = (unsigned long)__va(phys_initrd_start);
+	initrd_end = initrd_start + phys_initrd_size;
 	initrd_below_start_ok = 1;
 
 	pr_info("Initial ramdisk at: 0x%p (%lu bytes)\n",
@@ -126,33 +147,36 @@
 {
 	struct memblock_region *reg;
 	phys_addr_t mem_size = 0;
+	phys_addr_t total_mem = 0;
+	phys_addr_t mem_start, end = 0;
 	phys_addr_t vmlinux_end = __pa_symbol(&_end);
 	phys_addr_t vmlinux_start = __pa_symbol(&_start);
 
 	/* Find the memory region containing the kernel */
 	for_each_memblock(memory, reg) {
-		phys_addr_t end = reg->base + reg->size;
-
-		if (reg->base <= vmlinux_start && vmlinux_end <= end) {
-			mem_size = min(reg->size, (phys_addr_t)-PAGE_OFFSET);
-
-			/*
-			 * Remove memblock from the end of usable area to the
-			 * end of region
-			 */
-			if (reg->base + mem_size < end)
-				memblock_remove(reg->base + mem_size,
-						end - reg->base - mem_size);
-		}
+		end = reg->base + reg->size;
+		if (!total_mem)
+			mem_start = reg->base;
+		if (reg->base <= vmlinux_start && vmlinux_end <= end)
+			BUG_ON(reg->size == 0);
+		total_mem = total_mem + reg->size;
 	}
-	BUG_ON(mem_size == 0);
+
+	/*
+	 * Remove memblock from the end of usable area to the
+	 * end of region
+	 */
+	mem_size = min(total_mem, (phys_addr_t)-PAGE_OFFSET);
+	if (mem_start + mem_size < end)
+		memblock_remove(mem_start + mem_size,
+				end - mem_start - mem_size);
 
 	/* Reserve from the start of the kernel to the end of the kernel */
 	memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start);
 
-	set_max_mapnr(PFN_DOWN(mem_size));
 	max_pfn = PFN_DOWN(memblock_end_of_DRAM());
 	max_low_pfn = max_pfn;
+	set_max_mapnr(max_low_pfn);
 
 #ifdef CONFIG_BLK_DEV_INITRD
 	setup_initrd();
diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c
index 4a8b618..87b4ab3 100644
--- a/arch/riscv/mm/kasan_init.c
+++ b/arch/riscv/mm/kasan_init.c
@@ -44,7 +44,7 @@
 				(__pa(((uintptr_t) kasan_early_shadow_pmd))),
 				__pgprot(_PAGE_TABLE)));
 
-	flush_tlb_all();
+	local_flush_tlb_all();
 }
 
 static void __init populate(void *start, void *end)
@@ -79,7 +79,7 @@
 			pfn_pgd(PFN_DOWN(__pa(&pmd[offset])),
 				__pgprot(_PAGE_TABLE)));
 
-	flush_tlb_all();
+	local_flush_tlb_all();
 	memset(start, 0, end - start);
 }
 
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 46038bc..0cf9a82 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -1,5 +1,6 @@
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_WATCH_QUEUE=y
 CONFIG_AUDIT=y
 CONFIG_NO_HZ_IDLE=y
 CONFIG_HIGH_RES_TIMERS=y
@@ -14,7 +15,6 @@
 CONFIG_IKCONFIG_PROC=y
 CONFIG_NUMA_BALANCING=y
 CONFIG_MEMCG=y
-CONFIG_MEMCG_SWAP=y
 CONFIG_BLK_CGROUP=y
 CONFIG_CFS_BANDWIDTH=y
 CONFIG_RT_GROUP_SCHED=y
@@ -31,9 +31,9 @@
 CONFIG_USER_NS=y
 CONFIG_CHECKPOINT_RESTORE=y
 CONFIG_SCHED_AUTOGROUP=y
-CONFIG_BLK_DEV_INITRD=y
 CONFIG_EXPERT=y
 # CONFIG_SYSFS_SYSCALL is not set
+CONFIG_BPF_LSM=y
 CONFIG_BPF_SYSCALL=y
 CONFIG_USERFAULTFD=y
 # CONFIG_COMPAT_BRK is not set
@@ -51,14 +51,11 @@
 CONFIG_VFIO_CCW=m
 CONFIG_VFIO_AP=m
 CONFIG_CRASH_DUMP=y
-CONFIG_HIBERNATION=y
-CONFIG_PM_DEBUG=y
 CONFIG_PROTECTED_VIRTUALIZATION_GUEST=y
 CONFIG_CMM=m
 CONFIG_APPLDATA_BASE=y
 CONFIG_KVM=m
-CONFIG_VHOST_NET=m
-CONFIG_VHOST_VSOCK=m
+CONFIG_S390_UNWIND_SELFTEST=y
 CONFIG_OPROFILE=m
 CONFIG_KPROBES=y
 CONFIG_JUMP_LABEL=y
@@ -77,6 +74,8 @@
 CONFIG_BLK_WBT=y
 CONFIG_BLK_CGROUP_IOLATENCY=y
 CONFIG_BLK_CGROUP_IOCOST=y
+CONFIG_BLK_INLINE_ENCRYPTION=y
+CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_IBM_PARTITION=y
 CONFIG_BSD_DISKLABEL=y
@@ -96,7 +95,6 @@
 CONFIG_CMA_DEBUGFS=y
 CONFIG_MEM_SOFT_DIRTY=y
 CONFIG_ZSWAP=y
-CONFIG_ZBUD=m
 CONFIG_ZSMALLOC=m
 CONFIG_ZSMALLOC_STAT=y
 CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
@@ -130,6 +128,7 @@
 CONFIG_NET_IPVTI=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
+CONFIG_INET_ESPINTCP=y
 CONFIG_INET_IPCOMP=m
 CONFIG_INET_DIAG=m
 CONFIG_INET_UDP_DIAG=m
@@ -144,6 +143,7 @@
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
+CONFIG_INET6_ESPINTCP=y
 CONFIG_INET6_IPCOMP=m
 CONFIG_IPV6_MIP6=m
 CONFIG_IPV6_VTI=m
@@ -151,7 +151,10 @@
 CONFIG_IPV6_GRE=m
 CONFIG_IPV6_MULTIPLE_TABLES=y
 CONFIG_IPV6_SUBTREES=y
+CONFIG_IPV6_RPL_LWTUNNEL=y
+CONFIG_MPTCP=y
 CONFIG_NETFILTER=y
+CONFIG_BRIDGE_NETFILTER=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_SECMARK=y
 CONFIG_NF_CONNTRACK_EVENTS=y
@@ -317,6 +320,7 @@
 CONFIG_L2TP_IP=m
 CONFIG_L2TP_ETH=m
 CONFIG_BRIDGE=m
+CONFIG_BRIDGE_MRP=y
 CONFIG_VLAN_8021Q=m
 CONFIG_VLAN_8021Q_GVRP=y
 CONFIG_NET_SCHED=y
@@ -341,6 +345,7 @@
 CONFIG_NET_SCH_FQ_CODEL=m
 CONFIG_NET_SCH_INGRESS=m
 CONFIG_NET_SCH_PLUG=m
+CONFIG_NET_SCH_ETS=m
 CONFIG_NET_CLS_BASIC=m
 CONFIG_NET_CLS_TCINDEX=m
 CONFIG_NET_CLS_ROUTE4=m
@@ -364,6 +369,7 @@
 CONFIG_NET_ACT_SIMP=m
 CONFIG_NET_ACT_SKBEDIT=m
 CONFIG_NET_ACT_CSUM=m
+CONFIG_NET_ACT_GATE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_OPENVSWITCH=m
 CONFIG_VSOCKETS=m
@@ -374,6 +380,7 @@
 CONFIG_NET_PKTGEN=m
 # CONFIG_NET_DROP_MONITOR is not set
 CONFIG_PCI=y
+# CONFIG_PCIEASPM is not set
 CONFIG_PCI_DEBUG=y
 CONFIG_HOTPLUG_PCI=y
 CONFIG_HOTPLUG_PCI_S390=y
@@ -435,6 +442,7 @@
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_MULTIPATH_QL=m
 CONFIG_DM_MULTIPATH_ST=m
+CONFIG_DM_MULTIPATH_HST=m
 CONFIG_DM_DELAY=m
 CONFIG_DM_UEVENT=y
 CONFIG_DM_FLAKEY=m
@@ -448,6 +456,8 @@
 CONFIG_IFB=m
 CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
+CONFIG_VXLAN=m
+CONFIG_BAREUDP=m
 CONFIG_TUN=m
 CONFIG_VETH=m
 CONFIG_VIRTIO_NET=m
@@ -481,7 +491,6 @@
 CONFIG_MLX4_EN=m
 CONFIG_MLX5_CORE=m
 CONFIG_MLX5_CORE_EN=y
-# CONFIG_MLXFW is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_MICROCHIP is not set
 # CONFIG_NET_VENDOR_MICROSEMI is not set
@@ -514,6 +523,7 @@
 # CONFIG_NET_VENDOR_TI is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
+# CONFIG_NET_VENDOR_XILINX is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -561,6 +571,8 @@
 CONFIG_VIRTIO_PCI=m
 CONFIG_VIRTIO_BALLOON=m
 CONFIG_VIRTIO_INPUT=y
+CONFIG_VHOST_NET=m
+CONFIG_VHOST_VSOCK=m
 CONFIG_S390_CCW_IOMMU=y
 CONFIG_S390_AP_IOMMU=y
 CONFIG_EXT4_FS=y
@@ -608,6 +620,7 @@
 CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
+CONFIG_EXFAT_FS=m
 CONFIG_NTFS_FS=m
 CONFIG_NTFS_RW=y
 CONFIG_PROC_KCORE=y
@@ -650,8 +663,8 @@
 CONFIG_DLM=m
 CONFIG_UNICODE=y
 CONFIG_PERSISTENT_KEYRINGS=y
-CONFIG_BIG_KEYS=y
 CONFIG_ENCRYPTED_KEYS=m
+CONFIG_KEY_NOTIFICATIONS=y
 CONFIG_SECURITY=y
 CONFIG_SECURITY_NETWORK=y
 CONFIG_FORTIFY_SOURCE=y
@@ -675,8 +688,11 @@
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
+CONFIG_CRYPTO_CURVE25519=m
+CONFIG_CRYPTO_GCM=y
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_SEQIV=y
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -685,6 +701,7 @@
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_CRC32=m
+CONFIG_CRYPTO_BLAKE2S=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_RMD128=m
 CONFIG_CRYPTO_RMD160=m
@@ -701,6 +718,7 @@
 CONFIG_CRYPTO_CAMELLIA=m
 CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
+CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SALSA20=m
@@ -719,6 +737,9 @@
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 CONFIG_CRYPTO_STATS=y
+CONFIG_CRYPTO_LIB_BLAKE2S=m
+CONFIG_CRYPTO_LIB_CURVE25519=m
+CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m
 CONFIG_ZCRYPT=m
 CONFIG_PKEY=m
 CONFIG_CRYPTO_PAES_S390=m
@@ -774,6 +795,7 @@
 CONFIG_PANIC_ON_OOPS=y
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_WQ_WATCHDOG=y
+CONFIG_TEST_LOCKUP=m
 CONFIG_DEBUG_TIMEKEEPING=y
 CONFIG_PROVE_LOCKING=y
 CONFIG_LOCK_STAT=y
@@ -786,7 +808,9 @@
 CONFIG_DEBUG_CREDENTIALS=y
 CONFIG_RCU_TORTURE_TEST=m
 CONFIG_RCU_CPU_STALL_TIMEOUT=300
+# CONFIG_RCU_TRACE is not set
 CONFIG_LATENCYTOP=y
+CONFIG_BOOTTIME_TRACING=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_STACK_TRACER=y
 CONFIG_IRQSOFF_TRACER=y
@@ -808,10 +832,12 @@
 CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y
 CONFIG_LKDTM=m
 CONFIG_TEST_LIST_SORT=y
+CONFIG_TEST_MIN_HEAP=y
 CONFIG_TEST_SORT=y
 CONFIG_KPROBES_SANITY_TEST=y
 CONFIG_RBTREE_TEST=y
 CONFIG_INTERVAL_TREE_TEST=m
 CONFIG_PERCPU_TEST=m
 CONFIG_ATOMIC64_SELFTEST=y
+CONFIG_TEST_BITOPS=m
 CONFIG_TEST_BPF=m
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index 7cd0648..5df9759 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -1,5 +1,6 @@
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_WATCH_QUEUE=y
 CONFIG_AUDIT=y
 CONFIG_NO_HZ_IDLE=y
 CONFIG_HIGH_RES_TIMERS=y
@@ -13,7 +14,6 @@
 CONFIG_IKCONFIG_PROC=y
 CONFIG_NUMA_BALANCING=y
 CONFIG_MEMCG=y
-CONFIG_MEMCG_SWAP=y
 CONFIG_BLK_CGROUP=y
 CONFIG_CFS_BANDWIDTH=y
 CONFIG_RT_GROUP_SCHED=y
@@ -30,9 +30,9 @@
 CONFIG_USER_NS=y
 CONFIG_CHECKPOINT_RESTORE=y
 CONFIG_SCHED_AUTOGROUP=y
-CONFIG_BLK_DEV_INITRD=y
 CONFIG_EXPERT=y
 # CONFIG_SYSFS_SYSCALL is not set
+CONFIG_BPF_LSM=y
 CONFIG_BPF_SYSCALL=y
 CONFIG_USERFAULTFD=y
 # CONFIG_COMPAT_BRK is not set
@@ -41,7 +41,6 @@
 CONFIG_TUNE_ZEC12=y
 CONFIG_NR_CPUS=512
 CONFIG_NUMA=y
-# CONFIG_NUMA_EMU is not set
 CONFIG_HZ_100=y
 CONFIG_KEXEC_FILE=y
 CONFIG_KEXEC_SIG=y
@@ -51,14 +50,11 @@
 CONFIG_VFIO_CCW=m
 CONFIG_VFIO_AP=m
 CONFIG_CRASH_DUMP=y
-CONFIG_HIBERNATION=y
-CONFIG_PM_DEBUG=y
 CONFIG_PROTECTED_VIRTUALIZATION_GUEST=y
 CONFIG_CMM=m
 CONFIG_APPLDATA_BASE=y
 CONFIG_KVM=m
-CONFIG_VHOST_NET=m
-CONFIG_VHOST_VSOCK=m
+CONFIG_S390_UNWIND_SELFTEST=m
 CONFIG_OPROFILE=m
 CONFIG_KPROBES=y
 CONFIG_JUMP_LABEL=y
@@ -74,6 +70,8 @@
 CONFIG_BLK_WBT=y
 CONFIG_BLK_CGROUP_IOLATENCY=y
 CONFIG_BLK_CGROUP_IOCOST=y
+CONFIG_BLK_INLINE_ENCRYPTION=y
+CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_IBM_PARTITION=y
 CONFIG_BSD_DISKLABEL=y
@@ -91,7 +89,6 @@
 CONFIG_FRONTSWAP=y
 CONFIG_MEM_SOFT_DIRTY=y
 CONFIG_ZSWAP=y
-CONFIG_ZBUD=m
 CONFIG_ZSMALLOC=m
 CONFIG_ZSMALLOC_STAT=y
 CONFIG_DEFERRED_STRUCT_PAGE_INIT=y
@@ -125,6 +122,7 @@
 CONFIG_NET_IPVTI=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
+CONFIG_INET_ESPINTCP=y
 CONFIG_INET_IPCOMP=m
 CONFIG_INET_DIAG=m
 CONFIG_INET_UDP_DIAG=m
@@ -139,6 +137,7 @@
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
+CONFIG_INET6_ESPINTCP=y
 CONFIG_INET6_IPCOMP=m
 CONFIG_IPV6_MIP6=m
 CONFIG_IPV6_VTI=m
@@ -146,7 +145,10 @@
 CONFIG_IPV6_GRE=m
 CONFIG_IPV6_MULTIPLE_TABLES=y
 CONFIG_IPV6_SUBTREES=y
+CONFIG_IPV6_RPL_LWTUNNEL=y
+CONFIG_MPTCP=y
 CONFIG_NETFILTER=y
+CONFIG_BRIDGE_NETFILTER=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_SECMARK=y
 CONFIG_NF_CONNTRACK_EVENTS=y
@@ -311,6 +313,7 @@
 CONFIG_L2TP_IP=m
 CONFIG_L2TP_ETH=m
 CONFIG_BRIDGE=m
+CONFIG_BRIDGE_MRP=y
 CONFIG_VLAN_8021Q=m
 CONFIG_VLAN_8021Q_GVRP=y
 CONFIG_NET_SCHED=y
@@ -335,6 +338,7 @@
 CONFIG_NET_SCH_FQ_CODEL=m
 CONFIG_NET_SCH_INGRESS=m
 CONFIG_NET_SCH_PLUG=m
+CONFIG_NET_SCH_ETS=m
 CONFIG_NET_CLS_BASIC=m
 CONFIG_NET_CLS_TCINDEX=m
 CONFIG_NET_CLS_ROUTE4=m
@@ -358,6 +362,7 @@
 CONFIG_NET_ACT_SIMP=m
 CONFIG_NET_ACT_SKBEDIT=m
 CONFIG_NET_ACT_CSUM=m
+CONFIG_NET_ACT_GATE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_OPENVSWITCH=m
 CONFIG_VSOCKETS=m
@@ -368,6 +373,7 @@
 CONFIG_NET_PKTGEN=m
 # CONFIG_NET_DROP_MONITOR is not set
 CONFIG_PCI=y
+# CONFIG_PCIEASPM is not set
 CONFIG_HOTPLUG_PCI=y
 CONFIG_HOTPLUG_PCI_S390=y
 CONFIG_UEVENT_HELPER=y
@@ -430,6 +436,7 @@
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_MULTIPATH_QL=m
 CONFIG_DM_MULTIPATH_ST=m
+CONFIG_DM_MULTIPATH_HST=m
 CONFIG_DM_DELAY=m
 CONFIG_DM_UEVENT=y
 CONFIG_DM_FLAKEY=m
@@ -444,6 +451,8 @@
 CONFIG_IFB=m
 CONFIG_MACVLAN=m
 CONFIG_MACVTAP=m
+CONFIG_VXLAN=m
+CONFIG_BAREUDP=m
 CONFIG_TUN=m
 CONFIG_VETH=m
 CONFIG_VIRTIO_NET=m
@@ -477,7 +486,6 @@
 CONFIG_MLX4_EN=m
 CONFIG_MLX5_CORE=m
 CONFIG_MLX5_CORE_EN=y
-# CONFIG_MLXFW is not set
 # CONFIG_NET_VENDOR_MICREL is not set
 # CONFIG_NET_VENDOR_MICROCHIP is not set
 # CONFIG_NET_VENDOR_MICROSEMI is not set
@@ -510,6 +518,7 @@
 # CONFIG_NET_VENDOR_TI is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
+# CONFIG_NET_VENDOR_XILINX is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -557,6 +566,8 @@
 CONFIG_VIRTIO_PCI=m
 CONFIG_VIRTIO_BALLOON=m
 CONFIG_VIRTIO_INPUT=y
+CONFIG_VHOST_NET=m
+CONFIG_VHOST_VSOCK=m
 CONFIG_S390_CCW_IOMMU=y
 CONFIG_S390_AP_IOMMU=y
 CONFIG_EXT4_FS=y
@@ -600,6 +611,7 @@
 CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
+CONFIG_EXFAT_FS=m
 CONFIG_NTFS_FS=m
 CONFIG_NTFS_RW=y
 CONFIG_PROC_KCORE=y
@@ -642,8 +654,8 @@
 CONFIG_DLM=m
 CONFIG_UNICODE=y
 CONFIG_PERSISTENT_KEYRINGS=y
-CONFIG_BIG_KEYS=y
 CONFIG_ENCRYPTED_KEYS=m
+CONFIG_KEY_NOTIFICATIONS=y
 CONFIG_SECURITY=y
 CONFIG_SECURITY_NETWORK=y
 CONFIG_SECURITY_SELINUX=y
@@ -667,8 +679,11 @@
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
+CONFIG_CRYPTO_CURVE25519=m
+CONFIG_CRYPTO_GCM=y
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_SEQIV=y
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_OFB=m
@@ -678,6 +693,7 @@
 CONFIG_CRYPTO_XCBC=m
 CONFIG_CRYPTO_VMAC=m
 CONFIG_CRYPTO_CRC32=m
+CONFIG_CRYPTO_BLAKE2S=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_RMD128=m
 CONFIG_CRYPTO_RMD160=m
@@ -694,6 +710,7 @@
 CONFIG_CRYPTO_CAMELLIA=m
 CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
+CONFIG_CRYPTO_DES=m
 CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
 CONFIG_CRYPTO_SALSA20=m
@@ -712,6 +729,9 @@
 CONFIG_CRYPTO_USER_API_RNG=m
 CONFIG_CRYPTO_USER_API_AEAD=m
 CONFIG_CRYPTO_STATS=y
+CONFIG_CRYPTO_LIB_BLAKE2S=m
+CONFIG_CRYPTO_LIB_CURVE25519=m
+CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m
 CONFIG_ZCRYPT=m
 CONFIG_PKEY=m
 CONFIG_CRYPTO_PAES_S390=m
@@ -725,6 +745,7 @@
 CONFIG_CRYPTO_GHASH_S390=m
 CONFIG_CRYPTO_CRC32_S390=y
 CONFIG_CORDIC=m
+CONFIG_PRIME_NUMBERS=m
 CONFIG_CRC4=m
 CONFIG_CRC7=m
 CONFIG_CRC8=m
@@ -739,10 +760,12 @@
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_MEMORY_INIT=y
 CONFIG_PANIC_ON_OOPS=y
+CONFIG_TEST_LOCKUP=m
 CONFIG_BUG_ON_DATA_CORRUPTION=y
 CONFIG_RCU_TORTURE_TEST=m
 CONFIG_RCU_CPU_STALL_TIMEOUT=60
 CONFIG_LATENCYTOP=y
+CONFIG_BOOTTIME_TRACING=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_STACK_TRACER=y
 CONFIG_SCHED_TRACER=y
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index 20c51e5..4091c50 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -30,6 +30,7 @@
 # CONFIG_BOUNCE is not set
 CONFIG_NET=y
 # CONFIG_IUCV is not set
+# CONFIG_ETHTOOL_NETLINK is not set
 CONFIG_DEVTMPFS=y
 CONFIG_BLK_DEV_RAM=y
 # CONFIG_BLK_DEV_XPRAM is not set
@@ -55,6 +56,8 @@
 # CONFIG_MONWRITER is not set
 # CONFIG_S390_VMUR is not set
 # CONFIG_HID is not set
+# CONFIG_VIRTIO_MENU is not set
+# CONFIG_VHOST_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 # CONFIG_DNOTIFY is not set
 # CONFIG_INOTIFY_USER is not set
@@ -62,7 +65,9 @@
 # CONFIG_MISC_FILESYSTEMS is not set
 # CONFIG_NETWORK_FILESYSTEMS is not set
 CONFIG_LSM="yama,loadpin,safesetid,integrity"
+# CONFIG_ZLIB_DFLTCC is not set
 CONFIG_PRINTK_TIME=y
+# CONFIG_SYMBOLIC_ERRNAME is not set
 CONFIG_DEBUG_INFO=y
 CONFIG_DEBUG_FS=y
 CONFIG_DEBUG_KERNEL=y
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index cee3cb6..6ea0820 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -31,12 +31,12 @@
 #define KVM_USER_MEM_SLOTS 32
 
 /*
- * These seem to be used for allocating ->chip in the routing table,
- * which we don't use. 4096 is an out-of-thin-air value. If we need
- * to look at ->chip later on, we'll need to revisit this.
+ * These seem to be used for allocating ->chip in the routing table, which we
+ * don't use. 1 is as small as we can get to reduce the needed memory. If we
+ * need to look at ->chip later on, we'll need to revisit this.
  */
 #define KVM_NR_IRQCHIPS 1
-#define KVM_IRQCHIP_NUM_PINS 4096
+#define KVM_IRQCHIP_NUM_PINS 1
 #define KVM_HALT_POLL_NS_DEFAULT 50000
 
 /* s390-specific vcpu->requests bit members */
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index 63644600..263075a 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -198,9 +198,10 @@
 	if (!areas)
 		goto fail_malloc_areas;
 	for (i = 0; i < nr_areas; i++) {
+		/* GFP_NOWARN to avoid user triggerable WARN, we handle fails */
 		areas[i] = kmalloc_array(pages_per_area,
 					 sizeof(debug_entry_t *),
-					 GFP_KERNEL);
+					 GFP_KERNEL | __GFP_NOWARN);
 		if (!areas[i])
 			goto fail_malloc_areas2;
 		for (j = 0; j < pages_per_area; j++) {
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index cd241ee..0782772 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -170,6 +170,8 @@
 	psw_t psw;
 
 	psw.mask = PSW_MASK_BASE | PSW_DEFAULT_KEY | PSW_MASK_EA | PSW_MASK_BA;
+	if (IS_ENABLED(CONFIG_KASAN))
+		psw.mask |= PSW_MASK_DAT;
 	psw.addr = (unsigned long) s390_base_ext_handler;
 	S390_lowcore.external_new_psw = psw;
 	psw.addr = (unsigned long) s390_base_pgm_handler;
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 496f74d..969b35b 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -378,9 +378,9 @@
 	stmg	%r8,%r15,__LC_SAVE_AREA_SYNC
 	BPOFF
 	lg	%r12,__LC_CURRENT
-	lghi	%r13,__TASK_thread
 	lghi	%r14,_PIF_SYSCALL
 .Lsysc_per:
+	lghi	%r13,__TASK_thread
 	lg	%r15,__LC_KERNEL_STACK
 	la	%r11,STACK_FRAME_OVERHEAD(%r15)	# pointer to pt_regs
 	UPDATE_VTIME %r8,%r9,__LC_SYNC_ENTER_TIMER
diff --git a/arch/s390/kernel/perf_cpum_cf_events.c b/arch/s390/kernel/perf_cpum_cf_events.c
index 1e3df52..37265f5 100644
--- a/arch/s390/kernel/perf_cpum_cf_events.c
+++ b/arch/s390/kernel/perf_cpum_cf_events.c
@@ -292,7 +292,7 @@
 CPUMF_EVENT_ATTR(cf_z15, DFLT_ACCESS, 0x00f7);
 CPUMF_EVENT_ATTR(cf_z15, DFLT_CYCLES, 0x00fc);
 CPUMF_EVENT_ATTR(cf_z15, DFLT_CC, 0x00108);
-CPUMF_EVENT_ATTR(cf_z15, DFLT_CCERROR, 0x00109);
+CPUMF_EVENT_ATTR(cf_z15, DFLT_CCFINISH, 0x00109);
 CPUMF_EVENT_ATTR(cf_z15, MT_DIAG_CYCLES_ONE_THR_ACTIVE, 0x01c0);
 CPUMF_EVENT_ATTR(cf_z15, MT_DIAG_CYCLES_TWO_THR_ACTIVE, 0x01c1);
 
@@ -629,7 +629,7 @@
 	CPUMF_EVENT_PTR(cf_z15, DFLT_ACCESS),
 	CPUMF_EVENT_PTR(cf_z15, DFLT_CYCLES),
 	CPUMF_EVENT_PTR(cf_z15, DFLT_CC),
-	CPUMF_EVENT_PTR(cf_z15, DFLT_CCERROR),
+	CPUMF_EVENT_PTR(cf_z15, DFLT_CCFINISH),
 	CPUMF_EVENT_PTR(cf_z15, MT_DIAG_CYCLES_ONE_THR_ACTIVE),
 	CPUMF_EVENT_PTR(cf_z15, MT_DIAG_CYCLES_TWO_THR_ACTIVE),
 	NULL,
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 85a711d..4f9e462 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -881,12 +881,21 @@
 	return err;
 }
 
+static bool is_callchain_event(struct perf_event *event)
+{
+	u64 sample_type = event->attr.sample_type;
+
+	return sample_type & (PERF_SAMPLE_CALLCHAIN | PERF_SAMPLE_REGS_USER |
+			      PERF_SAMPLE_STACK_USER);
+}
+
 static int cpumsf_pmu_event_init(struct perf_event *event)
 {
 	int err;
 
 	/* No support for taken branch sampling */
-	if (has_branch_stack(event))
+	/* No support for callchain, stacks and registers */
+	if (has_branch_stack(event) || is_callchain_event(event))
 		return -EOPNOTSUPP;
 
 	switch (event->attr.type) {
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 5853c98..07aa15b 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -1100,6 +1100,7 @@
 	if (IS_ENABLED(CONFIG_EXPOLINE_AUTO))
 		nospec_auto_detect();
 
+	jump_label_init();
 	parse_early_param();
 #ifdef CONFIG_CRASH_DUMP
 	/* Deactivate elfcorehdr= kernel parameter */
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index 82df06d..3b5a4d2 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -117,7 +117,7 @@
 					     _PAGE_YOUNG);
 #ifdef CONFIG_MEM_SOFT_DIRTY
 		pte_val(pte) |= move_set_bit(rste, _SEGMENT_ENTRY_SOFT_DIRTY,
-					     _PAGE_DIRTY);
+					     _PAGE_SOFT_DIRTY);
 #endif
 		pte_val(pte) |= move_set_bit(rste, _SEGMENT_ENTRY_NOEXEC,
 					     _PAGE_NOEXEC);
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index 22a0be6..1d17413 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -62,11 +62,15 @@
 	long copied;
 
 	spin_lock_irqsave(&s390_kernel_write_lock, flags);
-	while (size) {
-		copied = s390_kernel_write_odd(tmp, src, size);
-		tmp += copied;
-		src += copied;
-		size -= copied;
+	if (!(flags & PSW_MASK_DAT)) {
+		memcpy(dst, src, size);
+	} else {
+		while (size) {
+			copied = s390_kernel_write_odd(tmp, src, size);
+			tmp += copied;
+			src += copied;
+			size -= copied;
+		}
 	}
 	spin_unlock_irqrestore(&s390_kernel_write_lock, flags);
 
diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c
index 08e1d61..fdebd28 100644
--- a/arch/s390/pci/pci_event.c
+++ b/arch/s390/pci/pci_event.c
@@ -94,7 +94,18 @@
 		}
 		zdev->fh = ccdf->fh;
 		zdev->state = ZPCI_FN_STATE_CONFIGURED;
-		zpci_create_device(zdev);
+		ret = zpci_enable_device(zdev);
+		if (ret)
+			break;
+
+		pdev = pci_scan_single_device(zdev->zbus->bus, zdev->devfn);
+		if (!pdev)
+			break;
+
+		pci_bus_add_device(pdev);
+		pci_lock_rescan_remove();
+		pci_bus_add_devices(zdev->zbus->bus);
+		pci_unlock_rescan_remove();
 		break;
 	case 0x0302: /* Reserved -> Standby */
 		if (!zdev) {
diff --git a/arch/sh/include/asm/pgalloc.h b/arch/sh/include/asm/pgalloc.h
index 22d968b..d770da3 100644
--- a/arch/sh/include/asm/pgalloc.h
+++ b/arch/sh/include/asm/pgalloc.h
@@ -12,6 +12,7 @@
 extern void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd);
 extern pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address);
 extern void pmd_free(struct mm_struct *mm, pmd_t *pmd);
+#define __pmd_free_tlb(tlb, pmdp, addr)		pmd_free((tlb)->mm, (pmdp))
 #endif
 
 static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
@@ -33,13 +34,4 @@
 	tlb_remove_page((tlb), (pte));			\
 } while (0)
 
-#if CONFIG_PGTABLE_LEVELS > 2
-#define __pmd_free_tlb(tlb, pmdp, addr)			\
-do {							\
-	struct page *page = virt_to_page(pmdp);		\
-	pgtable_pmd_page_dtor(page);			\
-	tlb_remove_page((tlb), page);			\
-} while (0);
-#endif
-
 #endif /* __ASM_SH_PGALLOC_H */
diff --git a/arch/sh/kernel/entry-common.S b/arch/sh/kernel/entry-common.S
index 956a7a0..9bac5bb 100644
--- a/arch/sh/kernel/entry-common.S
+++ b/arch/sh/kernel/entry-common.S
@@ -199,7 +199,7 @@
 	mov.l	@(OFF_R7,r15), r7   ! arg3
 	mov.l	@(OFF_R3,r15), r3   ! syscall_nr
 	!
-	mov.l	2f, r10			! Number of syscalls
+	mov.l	6f, r10			! Number of syscalls
 	cmp/hs	r10, r3
 	bf	syscall_call
 	mov	#-ENOSYS, r0
@@ -353,7 +353,7 @@
 	tst	r9, r8
 	bf	syscall_trace_entry
 	!
-	mov.l	2f, r8			! Number of syscalls
+	mov.l	6f, r8			! Number of syscalls
 	cmp/hs	r8, r3
 	bt	syscall_badsys
 	!
@@ -392,7 +392,7 @@
 #if !defined(CONFIG_CPU_SH2)
 1:	.long	TRA
 #endif
-2:	.long	NR_syscalls
+6:	.long	NR_syscalls
 3:	.long	sys_call_table
 7:	.long	do_syscall_trace_enter
 8:	.long	do_syscall_trace_leave
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 6a0cc52..883da0a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -67,7 +67,7 @@
 	select ARCH_HAS_FILTER_PGPROT
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
-	select ARCH_HAS_KCOV			if X86_64
+	select ARCH_HAS_KCOV			if X86_64 && STACK_VALIDATION
 	select ARCH_HAS_MEM_ENCRYPT
 	select ARCH_HAS_MEMBARRIER_SYNC_CORE
 	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 7619742..5a828fd 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -90,8 +90,8 @@
 
 vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o
 
-vmlinux-objs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a
 vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o
+efi-obj-$(CONFIG_EFI_STUB) = $(objtree)/drivers/firmware/efi/libstub/lib.a
 
 # The compressed kernel is built with -fPIC/-fPIE so that a boot loader
 # can place it anywhere in memory and it will still run. However, since
@@ -115,7 +115,7 @@
 quiet_cmd_check-and-link-vmlinux = LD      $@
       cmd_check-and-link-vmlinux = $(cmd_check_data_rel); $(cmd_ld)
 
-$(obj)/vmlinux: $(vmlinux-objs-y) FORCE
+$(obj)/vmlinux: $(vmlinux-objs-y) $(efi-obj-y) FORCE
 	$(call if_changed,check-and-link-vmlinux)
 
 OBJCOPYFLAGS_vmlinux.bin :=  -R .comment -S
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index e821a7d..97d37f0 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -213,7 +213,6 @@
 	 * We place all of the values on our mini stack so lret can
 	 * used to perform that far jump.
 	 */
-	pushl	$__KERNEL_CS
 	leal	startup_64(%ebp), %eax
 #ifdef CONFIG_EFI_MIXED
 	movl	efi32_boot_args(%ebp), %edi
@@ -224,11 +223,20 @@
 	movl	efi32_boot_args+8(%ebp), %edx	// saved bootparams pointer
 	cmpl	$0, %edx
 	jnz	1f
+	/*
+	 * efi_pe_entry uses MS calling convention, which requires 32 bytes of
+	 * shadow space on the stack even if all arguments are passed in
+	 * registers. We also need an additional 8 bytes for the space that
+	 * would be occupied by the return address, and this also results in
+	 * the correct stack alignment for entry.
+	 */
+	subl	$40, %esp
 	leal	efi_pe_entry(%ebp), %eax
 	movl	%edi, %ecx			// MS calling convention
 	movl	%esi, %edx
 1:
 #endif
+	pushl	$__KERNEL_CS
 	pushl	%eax
 
 	/* Enter paged protected Mode, activating Long Mode */
@@ -784,6 +792,7 @@
 
 SYM_DATA_START_LOCAL(boot_stack)
 	.fill BOOT_STACK_SIZE, 1, 0
+	.balign 16
 SYM_DATA_END_LABEL(boot_stack, SYM_L_LOCAL, boot_stack_end)
 
 /*
diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile
index b7a5790..08bf95d 100644
--- a/arch/x86/entry/Makefile
+++ b/arch/x86/entry/Makefile
@@ -7,12 +7,20 @@
 UBSAN_SANITIZE := n
 KCOV_INSTRUMENT := n
 
-CFLAGS_REMOVE_common.o = $(CC_FLAGS_FTRACE) -fstack-protector -fstack-protector-strong
-CFLAGS_REMOVE_syscall_32.o = $(CC_FLAGS_FTRACE) -fstack-protector -fstack-protector-strong
-CFLAGS_REMOVE_syscall_64.o = $(CC_FLAGS_FTRACE) -fstack-protector -fstack-protector-strong
+CFLAGS_REMOVE_common.o		= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_syscall_64.o	= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_syscall_32.o	= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_syscall_x32.o	= $(CC_FLAGS_FTRACE)
+
+CFLAGS_common.o			+= -fno-stack-protector
+CFLAGS_syscall_64.o		+= -fno-stack-protector
+CFLAGS_syscall_32.o		+= -fno-stack-protector
+CFLAGS_syscall_x32.o		+= -fno-stack-protector
 
 CFLAGS_syscall_64.o		+= $(call cc-option,-Wno-override-init,)
 CFLAGS_syscall_32.o		+= $(call cc-option,-Wno-override-init,)
+CFLAGS_syscall_x32.o		+= $(call cc-option,-Wno-override-init,)
+
 obj-y				:= entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o
 obj-y				+= common.o
 
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index bd3f141..f092884 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -45,6 +45,32 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
 
+/* Check that the stack and regs on entry from user mode are sane. */
+static noinstr void check_user_regs(struct pt_regs *regs)
+{
+	if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) {
+		/*
+		 * Make sure that the entry code gave us a sensible EFLAGS
+		 * register.  Native because we want to check the actual CPU
+		 * state, not the interrupt state as imagined by Xen.
+		 */
+		unsigned long flags = native_save_fl();
+		WARN_ON_ONCE(flags & (X86_EFLAGS_AC | X86_EFLAGS_DF |
+				      X86_EFLAGS_NT));
+
+		/* We think we came from user mode. Make sure pt_regs agrees. */
+		WARN_ON_ONCE(!user_mode(regs));
+
+		/*
+		 * All entries from user mode (except #DF) should be on the
+		 * normal thread stack and should have user pt_regs in the
+		 * correct location.
+		 */
+		WARN_ON_ONCE(!on_thread_stack());
+		WARN_ON_ONCE(regs != task_pt_regs(current));
+	}
+}
+
 #ifdef CONFIG_CONTEXT_TRACKING
 /**
  * enter_from_user_mode - Establish state when coming from user mode
@@ -127,9 +153,6 @@
 	unsigned long ret = 0;
 	u32 work;
 
-	if (IS_ENABLED(CONFIG_DEBUG_ENTRY))
-		BUG_ON(regs != task_pt_regs(current));
-
 	work = READ_ONCE(ti->flags);
 
 	if (work & (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU)) {
@@ -271,7 +294,7 @@
 #endif
 }
 
-__visible noinstr void prepare_exit_to_usermode(struct pt_regs *regs)
+static noinstr void prepare_exit_to_usermode(struct pt_regs *regs)
 {
 	instrumentation_begin();
 	__prepare_exit_to_usermode(regs);
@@ -346,6 +369,8 @@
 {
 	struct thread_info *ti;
 
+	check_user_regs(regs);
+
 	enter_from_user_mode();
 	instrumentation_begin();
 
@@ -409,6 +434,8 @@
 /* Handles int $0x80 */
 __visible noinstr void do_int80_syscall_32(struct pt_regs *regs)
 {
+	check_user_regs(regs);
+
 	enter_from_user_mode();
 	instrumentation_begin();
 
@@ -460,6 +487,8 @@
 					vdso_image_32.sym_int80_landing_pad;
 	bool success;
 
+	check_user_regs(regs);
+
 	/*
 	 * SYSENTER loses EIP, and even SYSCALL32 needs us to skip forward
 	 * so that 'regs->ip -= 2' lands back on an int $0x80 instruction.
@@ -510,6 +539,18 @@
 		(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF | X86_EFLAGS_VM)) == 0;
 #endif
 }
+
+/* Returns 0 to return using IRET or 1 to return using SYSEXIT/SYSRETL. */
+__visible noinstr long do_SYSENTER_32(struct pt_regs *regs)
+{
+	/* SYSENTER loses RSP, but the vDSO saved it in RBP. */
+	regs->sp = regs->bp;
+
+	/* SYSENTER clobbers EFLAGS.IF.  Assume it was set in usermode. */
+	regs->flags |= X86_EFLAGS_IF;
+
+	return do_fast_syscall_32(regs);
+}
 #endif
 
 SYSCALL_DEFINE0(ni_syscall)
@@ -553,6 +594,7 @@
 bool noinstr idtentry_enter_cond_rcu(struct pt_regs *regs)
 {
 	if (user_mode(regs)) {
+		check_user_regs(regs);
 		enter_from_user_mode();
 		return false;
 	}
@@ -686,6 +728,7 @@
  */
 void noinstr idtentry_enter_user(struct pt_regs *regs)
 {
+	check_user_regs(regs);
 	enter_from_user_mode();
 }
 
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 024d7d2..2d0bd5d 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -933,9 +933,8 @@
 
 .Lsysenter_past_esp:
 	pushl	$__USER_DS		/* pt_regs->ss */
-	pushl	%ebp			/* pt_regs->sp (stashed in bp) */
+	pushl	$0			/* pt_regs->sp (placeholder) */
 	pushfl				/* pt_regs->flags (except IF = 0) */
-	orl	$X86_EFLAGS_IF, (%esp)	/* Fix IF */
 	pushl	$__USER_CS		/* pt_regs->cs */
 	pushl	$0			/* pt_regs->ip = 0 (placeholder) */
 	pushl	%eax			/* pt_regs->orig_ax */
@@ -965,7 +964,7 @@
 .Lsysenter_flags_fixed:
 
 	movl	%esp, %eax
-	call	do_fast_syscall_32
+	call	do_SYSENTER_32
 	/* XEN PV guests always use IRET path */
 	ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \
 		    "jmp .Lsyscall_32_done", X86_FEATURE_XENPV
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 0f974ae..541fdaf 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -57,6 +57,21 @@
 
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
+	/* Construct struct pt_regs on stack */
+	pushq	$__USER32_DS		/* pt_regs->ss */
+	pushq	$0			/* pt_regs->sp = 0 (placeholder) */
+
+	/*
+	 * Push flags.  This is nasty.  First, interrupts are currently
+	 * off, but we need pt_regs->flags to have IF set.  Second, if TS
+	 * was set in usermode, it's still set, and we're singlestepping
+	 * through this code.  do_SYSENTER_32() will fix up IF.
+	 */
+	pushfq				/* pt_regs->flags (except IF = 0) */
+	pushq	$__USER32_CS		/* pt_regs->cs */
+	pushq	$0			/* pt_regs->ip = 0 (placeholder) */
+SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL)
+
 	/*
 	 * User tracing code (ptrace or signal handlers) might assume that
 	 * the saved RAX contains a 32-bit number when we're invoking a 32-bit
@@ -66,20 +81,6 @@
 	 */
 	movl	%eax, %eax
 
-	/* Construct struct pt_regs on stack */
-	pushq	$__USER32_DS		/* pt_regs->ss */
-	pushq	%rbp			/* pt_regs->sp (stashed in bp) */
-
-	/*
-	 * Push flags.  This is nasty.  First, interrupts are currently
-	 * off, but we need pt_regs->flags to have IF set.  Second, even
-	 * if TF was set when SYSENTER started, it's clear by now.  We fix
-	 * that later using TIF_SINGLESTEP.
-	 */
-	pushfq				/* pt_regs->flags (except IF = 0) */
-	orl	$X86_EFLAGS_IF, (%rsp)	/* Fix saved flags */
-	pushq	$__USER32_CS		/* pt_regs->cs */
-	pushq	$0			/* pt_regs->ip = 0 (placeholder) */
 	pushq	%rax			/* pt_regs->orig_ax */
 	pushq	%rdi			/* pt_regs->di */
 	pushq	%rsi			/* pt_regs->si */
@@ -135,7 +136,7 @@
 .Lsysenter_flags_fixed:
 
 	movq	%rsp, %rdi
-	call	do_fast_syscall_32
+	call	do_SYSENTER_32
 	/* XEN PV guests always use IRET path */
 	ALTERNATIVE "testl %eax, %eax; jz swapgs_restore_regs_and_return_to_usermode", \
 		    "jmp swapgs_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
diff --git a/arch/x86/events/Makefile b/arch/x86/events/Makefile
index 12c42eb..9933c0e 100644
--- a/arch/x86/events/Makefile
+++ b/arch/x86/events/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-y					+= core.o probe.o
-obj-$(PERF_EVENTS_INTEL_RAPL)		+= rapl.o
+obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL)	+= rapl.o
 obj-y					+= amd/
 obj-$(CONFIG_X86_LOCAL_APIC)            += msr.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= intel/
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index a54c6a4..6035df1 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -375,7 +375,10 @@
 	guest_id = generate_guest_id(0, LINUX_VERSION_CODE, 0);
 	wrmsrl(HV_X64_MSR_GUEST_OS_ID, guest_id);
 
-	hv_hypercall_pg = vmalloc_exec(PAGE_SIZE);
+	hv_hypercall_pg = __vmalloc_node_range(PAGE_SIZE, 1, VMALLOC_START,
+			VMALLOC_END, GFP_KERNEL, PAGE_KERNEL_ROX,
+			VM_FLUSH_RESET_PERMS, NUMA_NO_NODE,
+			__builtin_return_address(0));
 	if (hv_hypercall_pg == NULL) {
 		wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
 		goto remove_cpuhp_state;
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 35460fe..0367efd 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -201,12 +201,8 @@
 	return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc), *addr, c, "Ir", nr);
 }
 
-static __no_kcsan_or_inline bool constant_test_bit(long nr, const volatile unsigned long *addr)
+static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr)
 {
-	/*
-	 * Because this is a plain access, we need to disable KCSAN here to
-	 * avoid double instrumentation via instrumented bitops.
-	 */
 	return ((1UL << (nr & (BITS_PER_LONG-1))) &
 		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index fb34ff6..0281895 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -75,6 +75,12 @@
 	unreachable();						\
 } while (0)
 
+/*
+ * This instrumentation_begin() is strictly speaking incorrect; but it
+ * suppresses the complaints from WARN()s in noinstr code. If such a WARN()
+ * were to trigger, we'd rather wreck the machine in an attempt to get the
+ * message out than not know about it.
+ */
 #define __WARN_FLAGS(flags)					\
 do {								\
 	instrumentation_begin();				\
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index dd17c2d..da78ccb 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -58,4 +58,9 @@
 	return false;
 }
 #endif
+#ifdef CONFIG_IA32_FEAT_CTL
+void init_ia32_feat_ctl(struct cpuinfo_x86 *c);
+#else
+static inline void init_ia32_feat_ctl(struct cpuinfo_x86 *c) {}
+#endif
 #endif /* _ASM_X86_CPU_H */
diff --git a/arch/x86/include/asm/cpumask.h b/arch/x86/include/asm/cpumask.h
index 6722ffc..3afa990 100644
--- a/arch/x86/include/asm/cpumask.h
+++ b/arch/x86/include/asm/cpumask.h
@@ -11,5 +11,23 @@
 
 extern void setup_cpu_local_masks(void);
 
+/*
+ * NMI and MCE exceptions need cpu_is_offline() _really_ early,
+ * provide an arch_ special for them to avoid instrumentation.
+ */
+#if NR_CPUS > 1
+static __always_inline bool arch_cpu_online(int cpu)
+{
+	return arch_test_bit(cpu, cpumask_bits(cpu_online_mask));
+}
+#else
+static __always_inline bool arch_cpu_online(int cpu)
+{
+	return cpu == 0;
+}
+#endif
+
+#define arch_cpu_is_offline(cpu)	unlikely(!arch_cpu_online(cpu))
+
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_X86_CPUMASK_H */
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 42159f4..845e748 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -623,6 +623,11 @@
  * MXCSR and XCR definitions:
  */
 
+static inline void ldmxcsr(u32 mxcsr)
+{
+	asm volatile("ldmxcsr %0" :: "m" (mxcsr));
+}
+
 extern unsigned int mxcsr_feature_mask;
 
 #define XCR_XFEATURE_ENABLED_MASK	0x00000000
diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index cf51c50..80d3b30 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -353,10 +353,6 @@
 
 #else	/* CONFIG_X86_64 */
 
-/* Maps to a regular IDTENTRY on 32bit for now */
-# define DECLARE_IDTENTRY_IST		DECLARE_IDTENTRY
-# define DEFINE_IDTENTRY_IST		DEFINE_IDTENTRY
-
 /**
  * DECLARE_IDTENTRY_DF - Declare functions for double fault 32bit variant
  * @vector:	Vector number (ignored for C)
@@ -387,28 +383,18 @@
 #endif	/* !CONFIG_X86_64 */
 
 /* C-Code mapping */
+#define DECLARE_IDTENTRY_NMI		DECLARE_IDTENTRY_RAW
+#define DEFINE_IDTENTRY_NMI		DEFINE_IDTENTRY_RAW
+
+#ifdef CONFIG_X86_64
 #define DECLARE_IDTENTRY_MCE		DECLARE_IDTENTRY_IST
 #define DEFINE_IDTENTRY_MCE		DEFINE_IDTENTRY_IST
 #define DEFINE_IDTENTRY_MCE_USER	DEFINE_IDTENTRY_NOIST
 
-#define DECLARE_IDTENTRY_NMI		DECLARE_IDTENTRY_RAW
-#define DEFINE_IDTENTRY_NMI		DEFINE_IDTENTRY_RAW
-
 #define DECLARE_IDTENTRY_DEBUG		DECLARE_IDTENTRY_IST
 #define DEFINE_IDTENTRY_DEBUG		DEFINE_IDTENTRY_IST
 #define DEFINE_IDTENTRY_DEBUG_USER	DEFINE_IDTENTRY_NOIST
-
-/**
- * DECLARE_IDTENTRY_XEN - Declare functions for XEN redirect IDT entry points
- * @vector:	Vector number (ignored for C)
- * @func:	Function name of the entry point
- *
- * Used for xennmi and xendebug redirections. No DEFINE as this is all ASM
- * indirection magic.
- */
-#define DECLARE_IDTENTRY_XEN(vector, func)				\
-	asmlinkage void xen_asm_exc_xen##func(void);			\
-	asmlinkage void asm_exc_xen##func(void)
+#endif
 
 #else /* !__ASSEMBLY__ */
 
@@ -455,9 +441,6 @@
 # define DECLARE_IDTENTRY_MCE(vector, func)				\
 	DECLARE_IDTENTRY(vector, func)
 
-# define DECLARE_IDTENTRY_DEBUG(vector, func)				\
-	DECLARE_IDTENTRY(vector, func)
-
 /* No ASM emitted for DF as this goes through a C shim */
 # define DECLARE_IDTENTRY_DF(vector, func)
 
@@ -469,10 +452,6 @@
 /* No ASM code emitted for NMI */
 #define DECLARE_IDTENTRY_NMI(vector, func)
 
-/* XEN NMI and DB wrapper */
-#define DECLARE_IDTENTRY_XEN(vector, func)				\
-	idtentry vector asm_exc_xen##func exc_##func has_error_code=0
-
 /*
  * ASM code to emit the common vector entry stubs where each stub is
  * packed into 8 bytes.
@@ -490,16 +469,15 @@
 	.align 8
 SYM_CODE_START(irq_entries_start)
     vector=FIRST_EXTERNAL_VECTOR
-    pos = .
     .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
 	UNWIND_HINT_IRET_REGS
+0 :
 	.byte	0x6a, vector
 	jmp	asm_common_interrupt
 	nop
 	/* Ensure that the above is 8 bytes max */
-	. = pos + 8
-    pos=pos+8
-    vector=vector+1
+	. = 0b + 8
+	vector = vector+1
     .endr
 SYM_CODE_END(irq_entries_start)
 
@@ -507,16 +485,15 @@
 	.align 8
 SYM_CODE_START(spurious_entries_start)
     vector=FIRST_SYSTEM_VECTOR
-    pos = .
     .rept (NR_VECTORS - FIRST_SYSTEM_VECTOR)
 	UNWIND_HINT_IRET_REGS
+0 :
 	.byte	0x6a, vector
 	jmp	asm_spurious_interrupt
 	nop
 	/* Ensure that the above is 8 bytes max */
-	. = pos + 8
-    pos=pos+8
-    vector=vector+1
+	. = 0b + 8
+	vector = vector+1
     .endr
 SYM_CODE_END(spurious_entries_start)
 #endif
@@ -565,16 +542,28 @@
 DECLARE_IDTENTRY_RAW_ERRORCODE(X86_TRAP_PF,	exc_page_fault);
 
 #ifdef CONFIG_X86_MCE
+#ifdef CONFIG_X86_64
 DECLARE_IDTENTRY_MCE(X86_TRAP_MC,	exc_machine_check);
+#else
+DECLARE_IDTENTRY_RAW(X86_TRAP_MC,	exc_machine_check);
+#endif
 #endif
 
 /* NMI */
 DECLARE_IDTENTRY_NMI(X86_TRAP_NMI,	exc_nmi);
-DECLARE_IDTENTRY_XEN(X86_TRAP_NMI,	nmi);
+#if defined(CONFIG_XEN_PV) && defined(CONFIG_X86_64)
+DECLARE_IDTENTRY_RAW(X86_TRAP_NMI,	xenpv_exc_nmi);
+#endif
 
 /* #DB */
+#ifdef CONFIG_X86_64
 DECLARE_IDTENTRY_DEBUG(X86_TRAP_DB,	exc_debug);
-DECLARE_IDTENTRY_XEN(X86_TRAP_DB,	debug);
+#else
+DECLARE_IDTENTRY_RAW(X86_TRAP_DB,	exc_debug);
+#endif
+#if defined(CONFIG_XEN_PV) && defined(CONFIG_X86_64)
+DECLARE_IDTENTRY_RAW(X86_TRAP_DB,	xenpv_exc_debug);
+#endif
 
 /* #DF */
 DECLARE_IDTENTRY_DF(X86_TRAP_DF,	exc_double_fault);
@@ -635,8 +624,8 @@
 
 #if IS_ENABLED(CONFIG_HYPERV)
 DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_CALLBACK_VECTOR,	sysvec_hyperv_callback);
-DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_REENLIGHTENMENT_VECTOR,	sysvec_hyperv_reenlightenment);
-DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_STIMER0_VECTOR,	sysvec_hyperv_stimer0);
+DECLARE_IDTENTRY_SYSVEC(HYPERV_REENLIGHTENMENT_VECTOR,	sysvec_hyperv_reenlightenment);
+DECLARE_IDTENTRY_SYSVEC(HYPERV_STIMER0_VECTOR,	sysvec_hyperv_stimer0);
 #endif
 
 #if IS_ENABLED(CONFIG_ACRN_GUEST)
diff --git a/arch/x86/include/asm/io_bitmap.h b/arch/x86/include/asm/io_bitmap.h
index ac1a99f..7f080f5 100644
--- a/arch/x86/include/asm/io_bitmap.h
+++ b/arch/x86/include/asm/io_bitmap.h
@@ -19,12 +19,28 @@
 void io_bitmap_share(struct task_struct *tsk);
 void io_bitmap_exit(struct task_struct *tsk);
 
+static inline void native_tss_invalidate_io_bitmap(void)
+{
+	/*
+	 * Invalidate the I/O bitmap by moving io_bitmap_base outside the
+	 * TSS limit so any subsequent I/O access from user space will
+	 * trigger a #GP.
+	 *
+	 * This is correct even when VMEXIT rewrites the TSS limit
+	 * to 0x67 as the only requirement is that the base points
+	 * outside the limit.
+	 */
+	this_cpu_write(cpu_tss_rw.x86_tss.io_bitmap_base,
+		       IO_BITMAP_OFFSET_INVALID);
+}
+
 void native_tss_update_io_bitmap(void);
 
 #ifdef CONFIG_PARAVIRT_XXL
 #include <asm/paravirt.h>
 #else
 #define tss_update_io_bitmap native_tss_update_io_bitmap
+#define tss_invalidate_io_bitmap native_tss_invalidate_io_bitmap
 #endif
 
 #else
diff --git a/arch/x86/include/asm/iosf_mbi.h b/arch/x86/include/asm/iosf_mbi.h
index 5270ff3..a1911fe 100644
--- a/arch/x86/include/asm/iosf_mbi.h
+++ b/arch/x86/include/asm/iosf_mbi.h
@@ -39,6 +39,7 @@
 #define BT_MBI_UNIT_PMC		0x04
 #define BT_MBI_UNIT_GFX		0x06
 #define BT_MBI_UNIT_SMI		0x0C
+#define BT_MBI_UNIT_CCK		0x14
 #define BT_MBI_UNIT_USB		0x43
 #define BT_MBI_UNIT_SATA	0xA3
 #define BT_MBI_UNIT_PCIE	0xA6
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index f8998e9..be5363b 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -943,7 +943,7 @@
 	atomic_t vapics_in_nmi_mode;
 	struct mutex apic_map_lock;
 	struct kvm_apic_map *apic_map;
-	bool apic_map_dirty;
+	atomic_t apic_map_dirty;
 
 	bool apic_access_page_done;
 	unsigned long apicv_inhibit_reasons;
@@ -1220,7 +1220,7 @@
 	void (*enable_log_dirty_pt_masked)(struct kvm *kvm,
 					   struct kvm_memory_slot *slot,
 					   gfn_t offset, unsigned long mask);
-	int (*write_log_dirty)(struct kvm_vcpu *vcpu);
+	int (*write_log_dirty)(struct kvm_vcpu *vcpu, gpa_t l2_gpa);
 
 	/* pmu operations of sub-arch */
 	const struct kvm_pmu_ops *pmu_ops;
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index 73d997a..e039a93 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -25,8 +25,6 @@
 #define TPAUSE_C01_STATE		1
 #define TPAUSE_C02_STATE		0
 
-u32 get_umwait_control_msr(void);
-
 static inline void __monitor(const void *eax, unsigned long ecx,
 			     unsigned long edx)
 {
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 5ca5d29..3d2afec 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -302,6 +302,11 @@
 }
 
 #ifdef CONFIG_X86_IOPL_IOPERM
+static inline void tss_invalidate_io_bitmap(void)
+{
+	PVOP_VCALL0(cpu.invalidate_io_bitmap);
+}
+
 static inline void tss_update_io_bitmap(void)
 {
 	PVOP_VCALL0(cpu.update_io_bitmap);
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 732f62e..8dfcb25 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -141,6 +141,7 @@
 	void (*load_sp0)(unsigned long sp0);
 
 #ifdef CONFIG_X86_IOPL_IOPERM
+	void (*invalidate_io_bitmap)(void);
 	void (*update_io_bitmap)(void);
 #endif
 
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 2da1f95..816b31c 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -194,6 +194,7 @@
 #define _PAGE_TABLE_NOENC	 (__PP|__RW|_USR|___A|   0|___D|   0|   0)
 #define _PAGE_TABLE		 (__PP|__RW|_USR|___A|   0|___D|   0|   0| _ENC)
 #define __PAGE_KERNEL_RO	 (__PP|   0|   0|___A|__NX|___D|   0|___G)
+#define __PAGE_KERNEL_ROX	 (__PP|   0|   0|___A|   0|___D|   0|___G)
 #define __PAGE_KERNEL_NOCACHE	 (__PP|__RW|   0|___A|__NX|___D|   0|___G| __NC)
 #define __PAGE_KERNEL_VVAR	 (__PP|   0|_USR|___A|__NX|___D|   0|___G)
 #define __PAGE_KERNEL_LARGE	 (__PP|__RW|   0|___A|__NX|___D|_PSE|___G)
@@ -219,6 +220,7 @@
 #define PAGE_KERNEL_RO		__pgprot_mask(__PAGE_KERNEL_RO         | _ENC)
 #define PAGE_KERNEL_EXEC	__pgprot_mask(__PAGE_KERNEL_EXEC       | _ENC)
 #define PAGE_KERNEL_EXEC_NOENC	__pgprot_mask(__PAGE_KERNEL_EXEC       |    0)
+#define PAGE_KERNEL_ROX		__pgprot_mask(__PAGE_KERNEL_ROX        | _ENC)
 #define PAGE_KERNEL_NOCACHE	__pgprot_mask(__PAGE_KERNEL_NOCACHE    | _ENC)
 #define PAGE_KERNEL_LARGE	__pgprot_mask(__PAGE_KERNEL_LARGE      | _ENC)
 #define PAGE_KERNEL_LARGE_EXEC	__pgprot_mask(__PAGE_KERNEL_LARGE_EXEC | _ENC)
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 42cd333..03b7c4c 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -370,7 +370,7 @@
 #define IO_BITMAP_OFFSET_INVALID	(__KERNEL_TSS_LIMIT + 1)
 
 struct entry_stack {
-	unsigned long		words[64];
+	char	stack[PAGE_SIZE];
 };
 
 struct entry_stack_page {
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 17c5a03..0780f97 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -408,14 +408,15 @@
 };
 
 struct kvm_vmx_nested_state_hdr {
-	__u32 flags;
 	__u64 vmxon_pa;
 	__u64 vmcs12_pa;
-	__u64 preemption_timer_deadline;
 
 	struct {
 		__u16 flags;
 	} smm;
+
+	__u32 flags;
+	__u64 preemption_timer_deadline;
 };
 
 struct kvm_svm_nested_state_data {
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index ce61e3e..81ffcfb 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2316,12 +2316,12 @@
 	ip->irqdomain = irq_domain_create_linear(fn, hwirqs, cfg->ops,
 						 (void *)(long)ioapic);
 
-	/* Release fw handle if it was allocated above */
-	if (!cfg->dev)
-		irq_domain_free_fwnode(fn);
-
-	if (!ip->irqdomain)
+	if (!ip->irqdomain) {
+		/* Release fw handle if it was allocated above */
+		if (!cfg->dev)
+			irq_domain_free_fwnode(fn);
 		return -ENOMEM;
+	}
 
 	ip->irqdomain->parent = parent;
 
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index 5cbaca5..c2b2911 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -263,12 +263,13 @@
 		msi_default_domain =
 			pci_msi_create_irq_domain(fn, &pci_msi_domain_info,
 						  parent);
-		irq_domain_free_fwnode(fn);
 	}
-	if (!msi_default_domain)
+	if (!msi_default_domain) {
+		irq_domain_free_fwnode(fn);
 		pr_warn("failed to initialize irqdomain for MSI/MSI-x.\n");
-	else
+	} else {
 		msi_default_domain->flags |= IRQ_DOMAIN_MSI_NOMASK_QUIRK;
+	}
 }
 
 #ifdef CONFIG_IRQ_REMAP
@@ -301,7 +302,8 @@
 	if (!fn)
 		return NULL;
 	d = pci_msi_create_irq_domain(fn, &pci_msi_ir_domain_info, parent);
-	irq_domain_free_fwnode(fn);
+	if (!d)
+		irq_domain_free_fwnode(fn);
 	return d;
 }
 #endif
@@ -364,7 +366,8 @@
 	if (fn) {
 		dmar_domain = msi_create_irq_domain(fn, &dmar_msi_domain_info,
 						    x86_vector_domain);
-		irq_domain_free_fwnode(fn);
+		if (!dmar_domain)
+			irq_domain_free_fwnode(fn);
 	}
 out:
 	mutex_unlock(&dmar_lock);
@@ -489,7 +492,10 @@
 	}
 
 	d = msi_create_irq_domain(fn, domain_info, parent);
-	irq_domain_free_fwnode(fn);
+	if (!d) {
+		irq_domain_free_fwnode(fn);
+		kfree(domain_info);
+	}
 	return d;
 }
 
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index c48be6e..7649da2 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -446,12 +446,10 @@
 	trace_vector_activate(irqd->irq, apicd->is_managed,
 			      apicd->can_reserve, reserve);
 
-	/* Nothing to do for fixed assigned vectors */
-	if (!apicd->can_reserve && !apicd->is_managed)
-		return 0;
-
 	raw_spin_lock_irqsave(&vector_lock, flags);
-	if (reserve || irqd_is_managed_and_shutdown(irqd))
+	if (!apicd->can_reserve && !apicd->is_managed)
+		assign_irq_vector_any_locked(irqd);
+	else if (reserve || irqd_is_managed_and_shutdown(irqd))
 		vector_assign_managed_shutdown(irqd);
 	else if (apicd->is_managed)
 		ret = activate_managed(irqd);
@@ -709,7 +707,6 @@
 	x86_vector_domain = irq_domain_create_tree(fn, &x86_vector_domain_ops,
 						   NULL);
 	BUG_ON(x86_vector_domain == NULL);
-	irq_domain_free_fwnode(fn);
 	irq_set_default_host(x86_vector_domain);
 
 	arch_init_msi_domain(x86_vector_domain);
@@ -775,20 +772,10 @@
 static int apic_set_affinity(struct irq_data *irqd,
 			     const struct cpumask *dest, bool force)
 {
-	struct apic_chip_data *apicd = apic_chip_data(irqd);
 	int err;
 
-	/*
-	 * Core code can call here for inactive interrupts. For inactive
-	 * interrupts which use managed or reservation mode there is no
-	 * point in going through the vector assignment right now as the
-	 * activation will assign a vector which fits the destination
-	 * cpumask. Let the core code store the destination mask and be
-	 * done with it.
-	 */
-	if (!irqd_is_activated(irqd) &&
-	    (apicd->is_managed || apicd->can_reserve))
-		return IRQ_SET_MASK_OK;
+	if (WARN_ON_ONCE(!irqd_is_activated(irqd)))
+		return -EIO;
 
 	raw_spin_lock(&vector_lock);
 	cpumask_and(vector_searchmask, dest, cpu_online_mask);
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index 4267925..c5cf336 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -3,6 +3,7 @@
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
 
+#include <asm/cpu.h>
 #include <asm/cpufeature.h>
 #include <asm/e820/api.h>
 #include <asm/mtrr.h>
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 043d93c..95c090a 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -347,6 +347,9 @@
 	cr4_clear_bits(X86_CR4_UMIP);
 }
 
+/* These bits should not change their value after CPU init is finished. */
+static const unsigned long cr4_pinned_mask =
+	X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP | X86_CR4_FSGSBASE;
 static DEFINE_STATIC_KEY_FALSE_RO(cr_pinning);
 static unsigned long cr4_pinned_bits __ro_after_init;
 
@@ -371,20 +374,20 @@
 
 void native_write_cr4(unsigned long val)
 {
-	unsigned long bits_missing = 0;
+	unsigned long bits_changed = 0;
 
 set_register:
 	asm volatile("mov %0,%%cr4": "+r" (val), "+m" (cr4_pinned_bits));
 
 	if (static_branch_likely(&cr_pinning)) {
-		if (unlikely((val & cr4_pinned_bits) != cr4_pinned_bits)) {
-			bits_missing = ~val & cr4_pinned_bits;
-			val |= bits_missing;
+		if (unlikely((val & cr4_pinned_mask) != cr4_pinned_bits)) {
+			bits_changed = (val & cr4_pinned_mask) ^ cr4_pinned_bits;
+			val = (val & ~cr4_pinned_mask) | cr4_pinned_bits;
 			goto set_register;
 		}
-		/* Warn after we've set the missing bits. */
-		WARN_ONCE(bits_missing, "CR4 bits went missing: %lx!?\n",
-			  bits_missing);
+		/* Warn after we've corrected the changed bits. */
+		WARN_ONCE(bits_changed, "pinned CR4 bits changed: 0x%lx!?\n",
+			  bits_changed);
 	}
 }
 #if IS_MODULE(CONFIG_LKDTM)
@@ -419,7 +422,7 @@
 	if (boot_cpu_has(X86_FEATURE_PCID))
 		cr4 |= X86_CR4_PCIDE;
 	if (static_branch_likely(&cr_pinning))
-		cr4 |= cr4_pinned_bits;
+		cr4 = (cr4 & ~cr4_pinned_mask) | cr4_pinned_bits;
 
 	__write_cr4(cr4);
 
@@ -434,10 +437,7 @@
  */
 static void __init setup_cr_pinning(void)
 {
-	unsigned long mask;
-
-	mask = (X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP);
-	cr4_pinned_bits = this_cpu_read(cpu_tlbstate.cr4) & mask;
+	cr4_pinned_bits = this_cpu_read(cpu_tlbstate.cr4) & cr4_pinned_mask;
 	static_key_enable(&cr_pinning.key);
 }
 
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index fb538fc..9d03369 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -81,8 +81,4 @@
 
 extern u64 x86_read_arch_cap_msr(void);
 
-#ifdef CONFIG_IA32_FEAT_CTL
-void init_ia32_feat_ctl(struct cpuinfo_x86 *c);
-#endif
-
 #endif /* ARCH_X86_CPU_H */
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index c25a67a..0ab48f1c 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -50,6 +50,13 @@
 static u64 msr_test_ctrl_cache __ro_after_init;
 
 /*
+ * With a name like MSR_TEST_CTL it should go without saying, but don't touch
+ * MSR_TEST_CTL unless the CPU is one of the whitelisted models.  Writing it
+ * on CPUs that do not support SLD can cause fireworks, even when writing '0'.
+ */
+static bool cpu_model_supports_sld __ro_after_init;
+
+/*
  * Processors which have self-snooping capability can handle conflicting
  * memory type across CPUs by snooping its own cache. However, there exists
  * CPU models in which having conflicting memory types still leads to
@@ -1071,7 +1078,8 @@
 
 static void split_lock_init(void)
 {
-	split_lock_verify_msr(sld_state != sld_off);
+	if (cpu_model_supports_sld)
+		split_lock_verify_msr(sld_state != sld_off);
 }
 
 static void split_lock_warn(unsigned long ip)
@@ -1177,5 +1185,6 @@
 		return;
 	}
 
+	cpu_model_supports_sld = true;
 	split_lock_setup();
 }
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index ce9120c..14e4b4d 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1083,7 +1083,7 @@
 {
 	unsigned int cpu = smp_processor_id();
 
-	if (cpu_is_offline(cpu) ||
+	if (arch_cpu_is_offline(cpu) ||
 	    (crashing_cpu != -1 && crashing_cpu != cpu)) {
 		u64 mcgstatus;
 
@@ -1901,6 +1901,8 @@
 
 static __always_inline void exc_machine_check_kernel(struct pt_regs *regs)
 {
+	WARN_ON_ONCE(user_mode(regs));
+
 	/*
 	 * Only required when from kernel mode. See
 	 * mce_check_crashing_cpu() for details.
@@ -1954,7 +1956,7 @@
 }
 #else
 /* 32bit unified entry point */
-DEFINE_IDTENTRY_MCE(exc_machine_check)
+DEFINE_IDTENTRY_RAW(exc_machine_check)
 {
 	unsigned long dr7;
 
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 12f967c..6a9df71 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -981,10 +981,10 @@
 
 		c->x86_cache_max_rmid  = ecx;
 		c->x86_cache_occ_scale = ebx;
-		if (c->x86_vendor == X86_VENDOR_INTEL)
-			c->x86_cache_mbm_width_offset = eax & 0xff;
-		else
-			c->x86_cache_mbm_width_offset = -1;
+		c->x86_cache_mbm_width_offset = eax & 0xff;
+
+		if (c->x86_vendor == X86_VENDOR_AMD && !c->x86_cache_mbm_width_offset)
+			c->x86_cache_mbm_width_offset = MBM_CNTR_WIDTH_OFFSET_AMD;
 	}
 }
 
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index f20a47d..5ffa322 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -37,6 +37,7 @@
 #define MBA_IS_LINEAR			0x4
 #define MBA_MAX_MBPS			U32_MAX
 #define MAX_MBA_BW_AMD			0x800
+#define MBM_CNTR_WIDTH_OFFSET_AMD	20
 
 #define RMID_VAL_ERROR			BIT_ULL(63)
 #define RMID_VAL_UNAVAIL		BIT_ULL(62)
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 23b4b61..3f844f1 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -1117,6 +1117,7 @@
 	_d_cdp = rdt_find_domain(_r_cdp, d->id, NULL);
 	if (WARN_ON(IS_ERR_OR_NULL(_d_cdp))) {
 		_r_cdp = NULL;
+		_d_cdp = NULL;
 		ret = -EINVAL;
 	}
 
diff --git a/arch/x86/kernel/cpu/umwait.c b/arch/x86/kernel/cpu/umwait.c
index 300e3fd..ec8064c 100644
--- a/arch/x86/kernel/cpu/umwait.c
+++ b/arch/x86/kernel/cpu/umwait.c
@@ -18,12 +18,6 @@
  */
 static u32 umwait_control_cached = UMWAIT_CTRL_VAL(100000, UMWAIT_C02_ENABLE);
 
-u32 get_umwait_control_msr(void)
-{
-	return umwait_control_cached;
-}
-EXPORT_SYMBOL_GPL(get_umwait_control_msr);
-
 /*
  * Cache the original IA32_UMWAIT_CONTROL MSR value which is configured by
  * hardware or BIOS before kernel boot.
diff --git a/arch/x86/kernel/cpu/zhaoxin.c b/arch/x86/kernel/cpu/zhaoxin.c
index df1358b..05fa4ef 100644
--- a/arch/x86/kernel/cpu/zhaoxin.c
+++ b/arch/x86/kernel/cpu/zhaoxin.c
@@ -2,6 +2,7 @@
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
 
+#include <asm/cpu.h>
 #include <asm/cpufeature.h>
 
 #include "cpu.h"
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index b037cfa..7401cc1 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -71,6 +71,22 @@
 	printk("%s %s%pB\n", log_lvl, reliable ? "" : "? ", (void *)address);
 }
 
+static int copy_code(struct pt_regs *regs, u8 *buf, unsigned long src,
+		     unsigned int nbytes)
+{
+	if (!user_mode(regs))
+		return copy_from_kernel_nofault(buf, (u8 *)src, nbytes);
+
+	/*
+	 * Make sure userspace isn't trying to trick us into dumping kernel
+	 * memory by pointing the userspace instruction pointer at it.
+	 */
+	if (__chk_range_not_ok(src, nbytes, TASK_SIZE_MAX))
+		return -EINVAL;
+
+	return copy_from_user_nmi(buf, (void __user *)src, nbytes);
+}
+
 /*
  * There are a couple of reasons for the 2/3rd prologue, courtesy of Linus:
  *
@@ -97,17 +113,8 @@
 #define OPCODE_BUFSIZE (PROLOGUE_SIZE + 1 + EPILOGUE_SIZE)
 	u8 opcodes[OPCODE_BUFSIZE];
 	unsigned long prologue = regs->ip - PROLOGUE_SIZE;
-	bool bad_ip;
 
-	/*
-	 * Make sure userspace isn't trying to trick us into dumping kernel
-	 * memory by pointing the userspace instruction pointer at it.
-	 */
-	bad_ip = user_mode(regs) &&
-		__chk_range_not_ok(prologue, OPCODE_BUFSIZE, TASK_SIZE_MAX);
-
-	if (bad_ip || copy_from_kernel_nofault(opcodes, (u8 *)prologue,
-					OPCODE_BUFSIZE)) {
+	if (copy_code(regs, opcodes, prologue, sizeof(opcodes))) {
 		printk("%sCode: Bad RIP value.\n", loglvl);
 	} else {
 		printk("%sCode: %" __stringify(PROLOGUE_SIZE) "ph <%02x> %"
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 06c8189..15247b9 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -101,6 +101,12 @@
 		copy_fpregs_to_fpstate(&current->thread.fpu);
 	}
 	__cpu_invalidate_fpregs_state();
+
+	if (boot_cpu_has(X86_FEATURE_XMM))
+		ldmxcsr(MXCSR_DEFAULT);
+
+	if (boot_cpu_has(X86_FEATURE_FPU))
+		asm volatile ("fninit");
 }
 EXPORT_SYMBOL_GPL(kernel_fpu_begin);
 
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index bda2e5e..ad3a2b3 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -1074,7 +1074,7 @@
 		copy_part(offsetof(struct fxregs_state, st_space), 128,
 			  &xsave->i387.st_space, &kbuf, &offset_start, &count);
 	if (header.xfeatures & XFEATURE_MASK_SSE)
-		copy_part(xstate_offsets[XFEATURE_MASK_SSE], 256,
+		copy_part(xstate_offsets[XFEATURE_SSE], 256,
 			  &xsave->i387.xmm_space, &kbuf, &offset_start, &count);
 	/*
 	 * Fill xsave->i387.sw_reserved value for ptrace frame:
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index 8748321..b8aee71 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -29,6 +29,8 @@
 #include <asm/mmu_context.h>
 #include <asm/pgtable_areas.h>
 
+#include <xen/xen.h>
+
 /* This is a multiple of PAGE_SIZE. */
 #define LDT_SLOT_STRIDE (LDT_ENTRIES * LDT_ENTRY_SIZE)
 
@@ -543,6 +545,28 @@
 	return bytecount;
 }
 
+static bool allow_16bit_segments(void)
+{
+	if (!IS_ENABLED(CONFIG_X86_16BIT))
+		return false;
+
+#ifdef CONFIG_XEN_PV
+	/*
+	 * Xen PV does not implement ESPFIX64, which means that 16-bit
+	 * segments will not work correctly.  Until either Xen PV implements
+	 * ESPFIX64 and can signal this fact to the guest or unless someone
+	 * provides compelling evidence that allowing broken 16-bit segments
+	 * is worthwhile, disallow 16-bit segments under Xen PV.
+	 */
+	if (xen_pv_domain()) {
+		pr_info_once("Warning: 16-bit segments do not work correctly in a Xen PV guest\n");
+		return false;
+	}
+#endif
+
+	return true;
+}
+
 static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 {
 	struct mm_struct *mm = current->mm;
@@ -574,7 +598,7 @@
 		/* The user wants to clear the entry. */
 		memset(&ldt, 0, sizeof(ldt));
 	} else {
-		if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) {
+		if (!ldt_info.seg_32bit && !allow_16bit_segments()) {
 			error = -EINVAL;
 			goto out;
 		}
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 2de365f..d7c5e44 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -478,7 +478,7 @@
 
 DEFINE_IDTENTRY_RAW(exc_nmi)
 {
-	if (IS_ENABLED(CONFIG_SMP) && cpu_is_offline(smp_processor_id()))
+	if (IS_ENABLED(CONFIG_SMP) && arch_cpu_is_offline(smp_processor_id()))
 		return;
 
 	if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) {
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 674a7d6..de2138b 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -324,7 +324,8 @@
 	.cpu.swapgs		= native_swapgs,
 
 #ifdef CONFIG_X86_IOPL_IOPERM
-	.cpu.update_io_bitmap	= native_tss_update_io_bitmap,
+	.cpu.invalidate_io_bitmap	= native_tss_invalidate_io_bitmap,
+	.cpu.update_io_bitmap		= native_tss_update_io_bitmap,
 #endif
 
 	.cpu.start_context_switch	= paravirt_nop,
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index f362ce0..fe67dbd 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -322,20 +322,6 @@
 }
 
 #ifdef CONFIG_X86_IOPL_IOPERM
-static inline void tss_invalidate_io_bitmap(struct tss_struct *tss)
-{
-	/*
-	 * Invalidate the I/O bitmap by moving io_bitmap_base outside the
-	 * TSS limit so any subsequent I/O access from user space will
-	 * trigger a #GP.
-	 *
-	 * This is correct even when VMEXIT rewrites the TSS limit
-	 * to 0x67 as the only requirement is that the base points
-	 * outside the limit.
-	 */
-	tss->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET_INVALID;
-}
-
 static inline void switch_to_bitmap(unsigned long tifp)
 {
 	/*
@@ -346,7 +332,7 @@
 	 * user mode.
 	 */
 	if (tifp & _TIF_IO_BITMAP)
-		tss_invalidate_io_bitmap(this_cpu_ptr(&cpu_tss_rw));
+		tss_invalidate_io_bitmap();
 }
 
 static void tss_copy_io_bitmap(struct tss_struct *tss, struct io_bitmap *iobm)
@@ -380,7 +366,7 @@
 	u16 *base = &tss->x86_tss.io_bitmap_base;
 
 	if (!test_thread_flag(TIF_IO_BITMAP)) {
-		tss_invalidate_io_bitmap(tss);
+		native_tss_invalidate_io_bitmap();
 		return;
 	}
 
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 6ad43fc..2fd698e 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -58,7 +58,6 @@
 			 * or a page fault), which can make frame pointers
 			 * unreliable.
 			 */
-
 			if (IS_ENABLED(CONFIG_FRAME_POINTER))
 				return -EINVAL;
 		}
@@ -81,10 +80,6 @@
 	if (unwind_error(&state))
 		return -EINVAL;
 
-	/* Success path for non-user tasks, i.e. kthreads and idle tasks */
-	if (!(task->flags & (PF_KTHREAD | PF_IDLE)))
-		return -EINVAL;
-
 	return 0;
 }
 
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index f9727b9..b7cb3e0 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -84,17 +84,16 @@
 		local_irq_disable();
 }
 
-int is_valid_bugaddr(unsigned long addr)
+__always_inline int is_valid_bugaddr(unsigned long addr)
 {
-	unsigned short ud;
-
 	if (addr < TASK_SIZE_MAX)
 		return 0;
 
-	if (get_kernel_nofault(ud, (unsigned short *)addr))
-		return 0;
-
-	return ud == INSN_UD0 || ud == INSN_UD2;
+	/*
+	 * We got #UD, if the text isn't readable we'd have gotten
+	 * a different exception.
+	 */
+	return *(unsigned short *)addr == INSN_UD2;
 }
 
 static nokprobe_inline int
@@ -216,40 +215,45 @@
 		      ILL_ILLOPN, error_get_trap_addr(regs));
 }
 
+static noinstr bool handle_bug(struct pt_regs *regs)
+{
+	bool handled = false;
+
+	if (!is_valid_bugaddr(regs->ip))
+		return handled;
+
+	/*
+	 * All lies, just get the WARN/BUG out.
+	 */
+	instrumentation_begin();
+	/*
+	 * Since we're emulating a CALL with exceptions, restore the interrupt
+	 * state to what it was at the exception site.
+	 */
+	if (regs->flags & X86_EFLAGS_IF)
+		raw_local_irq_enable();
+	if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN) {
+		regs->ip += LEN_UD2;
+		handled = true;
+	}
+	if (regs->flags & X86_EFLAGS_IF)
+		raw_local_irq_disable();
+	instrumentation_end();
+
+	return handled;
+}
+
 DEFINE_IDTENTRY_RAW(exc_invalid_op)
 {
 	bool rcu_exit;
 
 	/*
-	 * Handle BUG/WARN like NMIs instead of like normal idtentries:
-	 * if we bugged/warned in a bad RCU context, for example, the last
-	 * thing we want is to BUG/WARN again in the idtentry code, ad
-	 * infinitum.
+	 * We use UD2 as a short encoding for 'CALL __WARN', as such
+	 * handle it before exception entry to avoid recursive WARN
+	 * in case exception entry is the one triggering WARNs.
 	 */
-	if (!user_mode(regs) && is_valid_bugaddr(regs->ip)) {
-		enum bug_trap_type type;
-
-		nmi_enter();
-		instrumentation_begin();
-		trace_hardirqs_off_finish();
-		type = report_bug(regs->ip, regs);
-		if (regs->flags & X86_EFLAGS_IF)
-			trace_hardirqs_on_prepare();
-		instrumentation_end();
-		nmi_exit();
-
-		if (type == BUG_TRAP_TYPE_WARN) {
-			/* Skip the ud2. */
-			regs->ip += LEN_UD2;
-			return;
-		}
-
-		/*
-		 * Else, if this was a BUG and report_bug returns or if this
-		 * was just a normal #UD, we want to continue onward and
-		 * crash.
-		 */
-	}
+	if (!user_mode(regs) && handle_bug(regs))
+		return;
 
 	rcu_exit = idtentry_enter_cond_rcu(regs);
 	instrumentation_begin();
@@ -299,6 +303,8 @@
 
 	do_trap(X86_TRAP_AC, SIGBUS, "alignment check", regs,
 		error_code, BUS_ADRALN, NULL);
+
+	local_irq_disable();
 }
 
 #ifdef CONFIG_VMAP_STACK
@@ -691,13 +697,13 @@
 		(struct bad_iret_stack *)__this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1;
 
 	/* Copy the IRET target to the temporary storage. */
-	memcpy(&tmp.regs.ip, (void *)s->regs.sp, 5*8);
+	__memcpy(&tmp.regs.ip, (void *)s->regs.sp, 5*8);
 
 	/* Copy the remainder of the stack from the current stack. */
-	memcpy(&tmp, s, offsetof(struct bad_iret_stack, regs.ip));
+	__memcpy(&tmp, s, offsetof(struct bad_iret_stack, regs.ip));
 
 	/* Update the entry stack */
-	memcpy(new_stack, &tmp, sizeof(tmp));
+	__memcpy(new_stack, &tmp, sizeof(tmp));
 
 	BUG_ON(!user_mode(&new_stack->regs));
 	return new_stack;
@@ -866,6 +872,12 @@
 	trace_hardirqs_off_finish();
 
 	/*
+	 * If something gets miswired and we end up here for a user mode
+	 * #DB, we will malfunction.
+	 */
+	WARN_ON_ONCE(user_mode(regs));
+
+	/*
 	 * Catch SYSENTER with TF set and clear DR_STEP. If this hit a
 	 * watchpoint at the same time then that will still be handled.
 	 */
@@ -883,6 +895,12 @@
 static __always_inline void exc_debug_user(struct pt_regs *regs,
 					   unsigned long dr6)
 {
+	/*
+	 * If something gets miswired and we end up here for a kernel mode
+	 * #DB, we will malfunction.
+	 */
+	WARN_ON_ONCE(!user_mode(regs));
+
 	idtentry_enter_user(regs);
 	instrumentation_begin();
 
@@ -913,7 +931,7 @@
 }
 #else
 /* 32 bit does not have separate entry points. */
-DEFINE_IDTENTRY_DEBUG(exc_debug)
+DEFINE_IDTENTRY_RAW(exc_debug)
 {
 	unsigned long dr6, dr7;
 
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 7f969b2..ec88bbe 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -440,8 +440,11 @@
 	/*
 	 * Find the orc_entry associated with the text address.
 	 *
-	 * Decrement call return addresses by one so they work for sibling
-	 * calls and calls to noreturn functions.
+	 * For a call frame (as opposed to a signal frame), state->ip points to
+	 * the instruction after the call.  That instruction's stack layout
+	 * could be different from the call instruction's layout, for example
+	 * if the call was to a noreturn function.  So get the ORC data for the
+	 * call instruction itself.
 	 */
 	orc = orc_find(state->signal ? state->ip : state->ip - 1);
 	if (!orc) {
@@ -662,6 +665,7 @@
 		state->sp = task->thread.sp;
 		state->bp = READ_ONCE_NOCHECK(frame->bp);
 		state->ip = READ_ONCE_NOCHECK(frame->ret_addr);
+		state->signal = (void *)state->ip == ret_from_fork;
 	}
 
 	if (get_stack_info((unsigned long *)state->sp, state->task,
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 3bfc8dd..9a03e5b 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -358,6 +358,7 @@
 	.bss : AT(ADDR(.bss) - LOAD_OFFSET) {
 		__bss_start = .;
 		*(.bss..page_aligned)
+		. = ALIGN(PAGE_SIZE);
 		*(BSS_MAIN)
 		BSS_DECRYPTED
 		. = ALIGN(PAGE_SIZE);
diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h
index ff2d0e9..cfe83d4 100644
--- a/arch/x86/kvm/kvm_cache_regs.h
+++ b/arch/x86/kvm/kvm_cache_regs.h
@@ -7,7 +7,7 @@
 #define KVM_POSSIBLE_CR0_GUEST_BITS X86_CR0_TS
 #define KVM_POSSIBLE_CR4_GUEST_BITS				  \
 	(X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR  \
-	 | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE)
+	 | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE | X86_CR4_TSD)
 
 #define BUILD_KVM_GPR_ACCESSORS(lname, uname)				      \
 static __always_inline unsigned long kvm_##lname##_read(struct kvm_vcpu *vcpu)\
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 34a7e05..5bf72fc 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -169,6 +169,18 @@
 	kvfree(map);
 }
 
+/*
+ * CLEAN -> DIRTY and UPDATE_IN_PROGRESS -> DIRTY changes happen without a lock.
+ *
+ * DIRTY -> UPDATE_IN_PROGRESS and UPDATE_IN_PROGRESS -> CLEAN happen with
+ * apic_map_lock_held.
+ */
+enum {
+	CLEAN,
+	UPDATE_IN_PROGRESS,
+	DIRTY
+};
+
 void kvm_recalculate_apic_map(struct kvm *kvm)
 {
 	struct kvm_apic_map *new, *old = NULL;
@@ -176,17 +188,17 @@
 	int i;
 	u32 max_id = 255; /* enough space for any xAPIC ID */
 
-	if (!kvm->arch.apic_map_dirty) {
-		/*
-		 * Read kvm->arch.apic_map_dirty before
-		 * kvm->arch.apic_map
-		 */
-		smp_rmb();
+	/* Read kvm->arch.apic_map_dirty before kvm->arch.apic_map.  */
+	if (atomic_read_acquire(&kvm->arch.apic_map_dirty) == CLEAN)
 		return;
-	}
 
 	mutex_lock(&kvm->arch.apic_map_lock);
-	if (!kvm->arch.apic_map_dirty) {
+	/*
+	 * Read kvm->arch.apic_map_dirty before kvm->arch.apic_map
+	 * (if clean) or the APIC registers (if dirty).
+	 */
+	if (atomic_cmpxchg_acquire(&kvm->arch.apic_map_dirty,
+				   DIRTY, UPDATE_IN_PROGRESS) == CLEAN) {
 		/* Someone else has updated the map. */
 		mutex_unlock(&kvm->arch.apic_map_lock);
 		return;
@@ -256,11 +268,11 @@
 			lockdep_is_held(&kvm->arch.apic_map_lock));
 	rcu_assign_pointer(kvm->arch.apic_map, new);
 	/*
-	 * Write kvm->arch.apic_map before
-	 * clearing apic->apic_map_dirty
+	 * Write kvm->arch.apic_map before clearing apic->apic_map_dirty.
+	 * If another update has come in, leave it DIRTY.
 	 */
-	smp_wmb();
-	kvm->arch.apic_map_dirty = false;
+	atomic_cmpxchg_release(&kvm->arch.apic_map_dirty,
+			       UPDATE_IN_PROGRESS, CLEAN);
 	mutex_unlock(&kvm->arch.apic_map_lock);
 
 	if (old)
@@ -282,20 +294,20 @@
 		else
 			static_key_slow_inc(&apic_sw_disabled.key);
 
-		apic->vcpu->kvm->arch.apic_map_dirty = true;
+		atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
 	}
 }
 
 static inline void kvm_apic_set_xapic_id(struct kvm_lapic *apic, u8 id)
 {
 	kvm_lapic_set_reg(apic, APIC_ID, id << 24);
-	apic->vcpu->kvm->arch.apic_map_dirty = true;
+	atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
 }
 
 static inline void kvm_apic_set_ldr(struct kvm_lapic *apic, u32 id)
 {
 	kvm_lapic_set_reg(apic, APIC_LDR, id);
-	apic->vcpu->kvm->arch.apic_map_dirty = true;
+	atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
 }
 
 static inline u32 kvm_apic_calc_x2apic_ldr(u32 id)
@@ -311,7 +323,7 @@
 
 	kvm_lapic_set_reg(apic, APIC_ID, id);
 	kvm_lapic_set_reg(apic, APIC_LDR, ldr);
-	apic->vcpu->kvm->arch.apic_map_dirty = true;
+	atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
 }
 
 static inline int apic_lvt_enabled(struct kvm_lapic *apic, int lvt_type)
@@ -1976,7 +1988,7 @@
 	case APIC_DFR:
 		if (!apic_x2apic_mode(apic)) {
 			kvm_lapic_set_reg(apic, APIC_DFR, val | 0x0FFFFFFF);
-			apic->vcpu->kvm->arch.apic_map_dirty = true;
+			atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
 		} else
 			ret = 1;
 		break;
@@ -2232,7 +2244,7 @@
 			static_key_slow_dec_deferred(&apic_hw_disabled);
 		} else {
 			static_key_slow_inc(&apic_hw_disabled.key);
-			vcpu->kvm->arch.apic_map_dirty = true;
+			atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
 		}
 	}
 
@@ -2273,7 +2285,6 @@
 	if (!apic)
 		return;
 
-	vcpu->kvm->arch.apic_map_dirty = false;
 	/* Stop the timer in case it's a reset to an active apic */
 	hrtimer_cancel(&apic->lapic_timer.timer);
 
@@ -2567,6 +2578,7 @@
 	}
 	memcpy(vcpu->arch.apic->regs, s->regs, sizeof(*s));
 
+	atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
 	kvm_recalculate_apic_map(vcpu->kvm);
 	kvm_apic_set_version(vcpu);
 
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 0ad06bf..444bb9c 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -222,7 +222,7 @@
 void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn);
 bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
 				    struct kvm_memory_slot *slot, u64 gfn);
-int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu);
+int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu, gpa_t l2_gpa);
 
 int kvm_mmu_post_init_vm(struct kvm *kvm);
 void kvm_mmu_pre_destroy_vm(struct kvm *kvm);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index fdd05c2..6d6a0ae 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1745,10 +1745,10 @@
  * Emulate arch specific page modification logging for the
  * nested hypervisor
  */
-int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu)
+int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu, gpa_t l2_gpa)
 {
 	if (kvm_x86_ops.write_log_dirty)
-		return kvm_x86_ops.write_log_dirty(vcpu);
+		return kvm_x86_ops.write_log_dirty(vcpu, l2_gpa);
 
 	return 0;
 }
@@ -4449,7 +4449,7 @@
 			nonleaf_bit8_rsvd | rsvd_bits(7, 7) |
 			rsvd_bits(maxphyaddr, 51);
 		rsvd_check->rsvd_bits_mask[0][2] = exb_bit_rsvd |
-			nonleaf_bit8_rsvd | gbpages_bit_rsvd |
+			gbpages_bit_rsvd |
 			rsvd_bits(maxphyaddr, 51);
 		rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd |
 			rsvd_bits(maxphyaddr, 51);
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index a6d484e..bd70ece1 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -235,7 +235,7 @@
 static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
 					     struct kvm_mmu *mmu,
 					     struct guest_walker *walker,
-					     int write_fault)
+					     gpa_t addr, int write_fault)
 {
 	unsigned level, index;
 	pt_element_t pte, orig_pte;
@@ -260,7 +260,7 @@
 				!(pte & PT_GUEST_DIRTY_MASK)) {
 			trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte));
 #if PTTYPE == PTTYPE_EPT
-			if (kvm_arch_write_log_dirty(vcpu))
+			if (kvm_arch_write_log_dirty(vcpu, addr))
 				return -EINVAL;
 #endif
 			pte |= PT_GUEST_DIRTY_MASK;
@@ -360,7 +360,6 @@
 	++walker->level;
 
 	do {
-		gfn_t real_gfn;
 		unsigned long host_addr;
 
 		pt_access = pte_access;
@@ -375,7 +374,7 @@
 		walker->table_gfn[walker->level - 1] = table_gfn;
 		walker->pte_gpa[walker->level - 1] = pte_gpa;
 
-		real_gfn = mmu->translate_gpa(vcpu, gfn_to_gpa(table_gfn),
+		real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(table_gfn),
 					      nested_access,
 					      &walker->fault);
 
@@ -389,12 +388,10 @@
 		 * information to fix the exit_qualification or exit_info_1
 		 * fields.
 		 */
-		if (unlikely(real_gfn == UNMAPPED_GVA))
+		if (unlikely(real_gpa == UNMAPPED_GVA))
 			return 0;
 
-		real_gfn = gpa_to_gfn(real_gfn);
-
-		host_addr = kvm_vcpu_gfn_to_hva_prot(vcpu, real_gfn,
+		host_addr = kvm_vcpu_gfn_to_hva_prot(vcpu, gpa_to_gfn(real_gpa),
 					    &walker->pte_writable[walker->level - 1]);
 		if (unlikely(kvm_is_error_hva(host_addr)))
 			goto error;
@@ -457,7 +454,8 @@
 			(PT_GUEST_DIRTY_SHIFT - PT_GUEST_ACCESSED_SHIFT);
 
 	if (unlikely(!accessed_dirty)) {
-		ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, write_fault);
+		ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker,
+							addr, write_fault);
 		if (unlikely(ret < 0))
 			goto error;
 		else if (ret)
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 8ccfa41..c0da4dd 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3344,7 +3344,7 @@
 
 void __svm_vcpu_run(unsigned long vmcb_pa, unsigned long *regs);
 
-static fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
+static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
 {
 	fastpath_t exit_fastpath;
 	struct vcpu_svm *svm = to_svm(vcpu);
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index d1af20b..d4a4cec 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -4109,7 +4109,7 @@
 	 * CR0_GUEST_HOST_MASK is already set in the original vmcs01
 	 * (KVM doesn't change it);
 	 */
-	vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS;
+	vcpu->arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS;
 	vmx_set_cr0(vcpu, vmcs12->host_cr0);
 
 	/* Same as above - no reason to call set_cr4_guest_host_mask().  */
@@ -4259,7 +4259,7 @@
 	 */
 	vmx_set_efer(vcpu, nested_vmx_get_vmcs01_guest_efer(vmx));
 
-	vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS;
+	vcpu->arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS;
 	vmx_set_cr0(vcpu, vmcs_readl(CR0_READ_SHADOW));
 
 	vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
@@ -6176,6 +6176,7 @@
 			goto error_guest_mode;
 	}
 
+	vmx->nested.has_preemption_timer_deadline = false;
 	if (kvm_state->hdr.vmx.flags & KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE) {
 		vmx->nested.has_preemption_timer_deadline = true;
 		vmx->nested.preemption_timer_deadline =
diff --git a/arch/x86/kvm/vmx/vmcs.h b/arch/x86/kvm/vmx/vmcs.h
index 5c0ff80..7a3675f 100644
--- a/arch/x86/kvm/vmx/vmcs.h
+++ b/arch/x86/kvm/vmx/vmcs.h
@@ -72,11 +72,24 @@
 	struct vmcs_controls_shadow controls_shadow;
 };
 
+static inline bool is_intr_type(u32 intr_info, u32 type)
+{
+	const u32 mask = INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK;
+
+	return (intr_info & mask) == (INTR_INFO_VALID_MASK | type);
+}
+
+static inline bool is_intr_type_n(u32 intr_info, u32 type, u8 vector)
+{
+	const u32 mask = INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK |
+			 INTR_INFO_VECTOR_MASK;
+
+	return (intr_info & mask) == (INTR_INFO_VALID_MASK | type | vector);
+}
+
 static inline bool is_exception_n(u32 intr_info, u8 vector)
 {
-	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
-			     INTR_INFO_VALID_MASK)) ==
-		(INTR_TYPE_HARD_EXCEPTION | vector | INTR_INFO_VALID_MASK);
+	return is_intr_type_n(intr_info, INTR_TYPE_HARD_EXCEPTION, vector);
 }
 
 static inline bool is_debug(u32 intr_info)
@@ -106,28 +119,23 @@
 
 static inline bool is_machine_check(u32 intr_info)
 {
-	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
-			     INTR_INFO_VALID_MASK)) ==
-		(INTR_TYPE_HARD_EXCEPTION | MC_VECTOR | INTR_INFO_VALID_MASK);
+	return is_exception_n(intr_info, MC_VECTOR);
 }
 
 /* Undocumented: icebp/int1 */
 static inline bool is_icebp(u32 intr_info)
 {
-	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
-		== (INTR_TYPE_PRIV_SW_EXCEPTION | INTR_INFO_VALID_MASK);
+	return is_intr_type(intr_info, INTR_TYPE_PRIV_SW_EXCEPTION);
 }
 
 static inline bool is_nmi(u32 intr_info)
 {
-	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
-		== (INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK);
+	return is_intr_type(intr_info, INTR_TYPE_NMI_INTR);
 }
 
 static inline bool is_external_intr(u32 intr_info)
 {
-	return (intr_info & (INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK))
-		== (INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR);
+	return is_intr_type(intr_info, INTR_TYPE_EXT_INTR);
 }
 
 enum vmcs_field_width {
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 36c7717..13745f2 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -133,9 +133,6 @@
 #define KVM_VM_CR0_ALWAYS_ON				\
 	(KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | 	\
 	 X86_CR0_WP | X86_CR0_PG | X86_CR0_PE)
-#define KVM_CR4_GUEST_OWNED_BITS				      \
-	(X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR      \
-	 | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_TSD)
 
 #define KVM_VM_CR4_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR4_VMXE
 #define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE)
@@ -4034,9 +4031,9 @@
 
 void set_cr4_guest_host_mask(struct vcpu_vmx *vmx)
 {
-	vmx->vcpu.arch.cr4_guest_owned_bits = KVM_CR4_GUEST_OWNED_BITS;
-	if (enable_ept)
-		vmx->vcpu.arch.cr4_guest_owned_bits |= X86_CR4_PGE;
+	vmx->vcpu.arch.cr4_guest_owned_bits = KVM_POSSIBLE_CR4_GUEST_BITS;
+	if (!enable_ept)
+		vmx->vcpu.arch.cr4_guest_owned_bits &= ~X86_CR4_PGE;
 	if (is_guest_mode(&vmx->vcpu))
 		vmx->vcpu.arch.cr4_guest_owned_bits &=
 			~get_vmcs12(&vmx->vcpu)->cr4_guest_host_mask;
@@ -4333,8 +4330,8 @@
 	/* 22.2.1, 20.8.1 */
 	vm_entry_controls_set(vmx, vmx_vmentry_ctrl());
 
-	vmx->vcpu.arch.cr0_guest_owned_bits = X86_CR0_TS;
-	vmcs_writel(CR0_GUEST_HOST_MASK, ~X86_CR0_TS);
+	vmx->vcpu.arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS;
+	vmcs_writel(CR0_GUEST_HOST_MASK, ~vmx->vcpu.arch.cr0_guest_owned_bits);
 
 	set_cr4_guest_host_mask(vmx);
 
@@ -6606,23 +6603,6 @@
 					msrs[i].host, false);
 }
 
-static void atomic_switch_umwait_control_msr(struct vcpu_vmx *vmx)
-{
-	u32 host_umwait_control;
-
-	if (!vmx_has_waitpkg(vmx))
-		return;
-
-	host_umwait_control = get_umwait_control_msr();
-
-	if (vmx->msr_ia32_umwait_control != host_umwait_control)
-		add_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL,
-			vmx->msr_ia32_umwait_control,
-			host_umwait_control, false);
-	else
-		clear_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL);
-}
-
 static void vmx_update_hv_timer(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -6728,9 +6708,7 @@
 
 	pt_guest_enter(vmx);
 
-	if (vcpu_to_pmu(vcpu)->version)
-		atomic_switch_perf_msrs(vmx);
-	atomic_switch_umwait_control_msr(vmx);
+	atomic_switch_perf_msrs(vmx);
 
 	if (enable_preemption_timer)
 		vmx_update_hv_timer(vcpu);
@@ -7501,11 +7479,11 @@
 	kvm_flush_pml_buffers(kvm);
 }
 
-static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu)
+static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu, gpa_t gpa)
 {
 	struct vmcs12 *vmcs12;
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	gpa_t gpa, dst;
+	gpa_t dst;
 
 	if (is_guest_mode(vcpu)) {
 		WARN_ON_ONCE(vmx->nested.pml_full);
@@ -7524,7 +7502,7 @@
 			return 1;
 		}
 
-		gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS) & ~0xFFFull;
+		gpa &= ~0xFFFull;
 		dst = vmcs12->pml_address + sizeof(u64) * vmcs12->guest_pml_index;
 
 		if (kvm_write_guest_page(vcpu->kvm, gpa_to_gfn(dst), &gpa,
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 8a83b5e..639798e 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -288,8 +288,6 @@
 
 	u64 current_tsc_ratio;
 
-	u32 host_pkru;
-
 	unsigned long host_debugctlmsr;
 
 	/*
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 00c88c2..88c593f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -975,6 +975,8 @@
 	if (is_long_mode(vcpu)) {
 		if (!(cr4 & X86_CR4_PAE))
 			return 1;
+		if ((cr4 ^ old_cr4) & X86_CR4_LA57)
+			return 1;
 	} else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE)
 		   && ((cr4 ^ old_cr4) & pdptr_bits)
 		   && !load_pdptrs(vcpu, vcpu->arch.walk_mmu,
@@ -2693,6 +2695,9 @@
 	if (data & 0x30)
 		return 1;
 
+	if (!lapic_in_kernel(vcpu))
+		return 1;
+
 	vcpu->arch.apf.msr_en_val = data;
 
 	if (!kvm_pv_async_pf_enabled(vcpu)) {
@@ -2856,7 +2861,7 @@
 		return kvm_mtrr_set_msr(vcpu, msr, data);
 	case MSR_IA32_APICBASE:
 		return kvm_set_apic_base(vcpu, msr_info);
-	case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff:
+	case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff:
 		return kvm_x2apic_msr_write(vcpu, msr, data);
 	case MSR_IA32_TSCDEADLINE:
 		kvm_set_lapic_tscdeadline_msr(vcpu, data);
@@ -3196,7 +3201,7 @@
 	case MSR_IA32_APICBASE:
 		msr_info->data = kvm_get_apic_base(vcpu);
 		break;
-	case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff:
+	case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff:
 		return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data);
 	case MSR_IA32_TSCDEADLINE:
 		msr_info->data = kvm_get_lapic_tscdeadline_msr(vcpu);
@@ -4603,7 +4608,8 @@
 		r = -EINVAL;
 		user_tsc_khz = (u32)arg;
 
-		if (user_tsc_khz >= kvm_max_guest_tsc_khz)
+		if (kvm_has_tsc_control &&
+		    user_tsc_khz >= kvm_max_guest_tsc_khz)
 			goto out;
 
 		if (user_tsc_khz == 0)
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 56b243b..bbcc05b 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -8,6 +8,8 @@
 #include <asm/alternative-asm.h>
 #include <asm/export.h>
 
+.pushsection .noinstr.text, "ax"
+
 /*
  * We build a jump to memcpy_orig by default which gets NOPped out on
  * the majority of x86 CPUs which set REP_GOOD. In addition, CPUs which
@@ -184,6 +186,8 @@
 	retq
 SYM_FUNC_END(memcpy_orig)
 
+.popsection
+
 #ifndef CONFIG_UML
 
 MCSAFE_TEST_CTL
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index fff28c6..b0dfac3 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -24,6 +24,7 @@
 	asm volatile(
 		"	testq  %[size8],%[size8]\n"
 		"	jz     4f\n"
+		"	.align 16\n"
 		"0:	movq $0,(%[dst])\n"
 		"	addq   $8,%[dst]\n"
 		"	decl %%ecx ; jnz   0b\n"
diff --git a/arch/x86/math-emu/wm_sqrt.S b/arch/x86/math-emu/wm_sqrt.S
index 3b2b581..40526dd 100644
--- a/arch/x86/math-emu/wm_sqrt.S
+++ b/arch/x86/math-emu/wm_sqrt.S
@@ -209,7 +209,7 @@
 
 #ifdef PARANOID
 /* It should be possible to get here only if the arg is ffff....ffff */
-	cmp	$0xffffffff,FPU_fsqrt_arg_1
+	cmpl	$0xffffffff,FPU_fsqrt_arg_1
 	jnz	sqrt_stage_2_error
 #endif /* PARANOID */
 
diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c
index fc13cbb..abb6075 100644
--- a/arch/x86/platform/uv/uv_irq.c
+++ b/arch/x86/platform/uv/uv_irq.c
@@ -167,9 +167,10 @@
 		goto out;
 
 	uv_domain = irq_domain_create_tree(fn, &uv_domain_ops, NULL);
-	irq_domain_free_fwnode(fn);
 	if (uv_domain)
 		uv_domain->parent = x86_vector_domain;
+	else
+		irq_domain_free_fwnode(fn);
 out:
 	mutex_unlock(&uv_lock);
 
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 7c65102..db1378c 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -193,6 +193,8 @@
  */
 static void notrace __restore_processor_state(struct saved_context *ctxt)
 {
+	struct cpuinfo_x86 *c;
+
 	if (ctxt->misc_enable_saved)
 		wrmsrl(MSR_IA32_MISC_ENABLE, ctxt->misc_enable);
 	/*
@@ -263,6 +265,10 @@
 	mtrr_bp_restore();
 	perf_restore_debug_store();
 	msr_restore_context(ctxt);
+
+	c = &cpu_data(smp_processor_id());
+	if (cpu_has(c, X86_FEATURE_MSR_IA32_FEAT_CTL))
+		init_ia32_feat_ctl(c);
 }
 
 /* Needed by apm.c */
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index acc49fa..c46b9f2 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -598,6 +598,26 @@
 }
 
 #ifdef CONFIG_X86_64
+void noist_exc_debug(struct pt_regs *regs);
+
+DEFINE_IDTENTRY_RAW(xenpv_exc_nmi)
+{
+	/* On Xen PV, NMI doesn't use IST.  The C part is the sane as native. */
+	exc_nmi(regs);
+}
+
+DEFINE_IDTENTRY_RAW(xenpv_exc_debug)
+{
+	/*
+	 * There's no IST on Xen PV, but we still need to dispatch
+	 * to the correct handler.
+	 */
+	if (user_mode(regs))
+		noist_exc_debug(regs);
+	else
+		exc_debug(regs);
+}
+
 struct trap_array_entry {
 	void (*orig)(void);
 	void (*xen)(void);
@@ -609,18 +629,18 @@
 	.xen		= xen_asm_##func,		\
 	.ist_okay	= ist_ok }
 
-#define TRAP_ENTRY_REDIR(func, xenfunc, ist_ok) {	\
+#define TRAP_ENTRY_REDIR(func, ist_ok) {		\
 	.orig		= asm_##func,			\
-	.xen		= xen_asm_##xenfunc,		\
+	.xen		= xen_asm_xenpv_##func,		\
 	.ist_okay	= ist_ok }
 
 static struct trap_array_entry trap_array[] = {
-	TRAP_ENTRY_REDIR(exc_debug, exc_xendebug,	true  ),
+	TRAP_ENTRY_REDIR(exc_debug,			true  ),
 	TRAP_ENTRY(exc_double_fault,			true  ),
 #ifdef CONFIG_X86_MCE
 	TRAP_ENTRY(exc_machine_check,			true  ),
 #endif
-	TRAP_ENTRY_REDIR(exc_nmi, exc_xennmi,		true  ),
+	TRAP_ENTRY_REDIR(exc_nmi,			true  ),
 	TRAP_ENTRY(exc_int3,				false ),
 	TRAP_ENTRY(exc_overflow,			false ),
 #ifdef CONFIG_IA32_EMULATION
@@ -850,6 +870,17 @@
 }
 
 #ifdef CONFIG_X86_IOPL_IOPERM
+static void xen_invalidate_io_bitmap(void)
+{
+	struct physdev_set_iobitmap iobitmap = {
+		.bitmap = 0,
+		.nr_ports = 0,
+	};
+
+	native_tss_invalidate_io_bitmap();
+	HYPERVISOR_physdev_op(PHYSDEVOP_set_iobitmap, &iobitmap);
+}
+
 static void xen_update_io_bitmap(void)
 {
 	struct physdev_set_iobitmap iobitmap;
@@ -1079,6 +1110,7 @@
 	.load_sp0 = xen_load_sp0,
 
 #ifdef CONFIG_X86_IOPL_IOPERM
+	.invalidate_io_bitmap = xen_invalidate_io_bitmap,
 	.update_io_bitmap = xen_update_io_bitmap,
 #endif
 	.io_delay = xen_io_delay,
diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S
index 5d252aa..aab1d99 100644
--- a/arch/x86/xen/xen-asm_64.S
+++ b/arch/x86/xen/xen-asm_64.S
@@ -29,10 +29,9 @@
 .endm
 
 xen_pv_trap asm_exc_divide_error
-xen_pv_trap asm_exc_debug
-xen_pv_trap asm_exc_xendebug
+xen_pv_trap asm_xenpv_exc_debug
 xen_pv_trap asm_exc_int3
-xen_pv_trap asm_exc_xennmi
+xen_pv_trap asm_xenpv_exc_nmi
 xen_pv_trap asm_exc_overflow
 xen_pv_trap asm_exc_bounds
 xen_pv_trap asm_exc_invalid_op
@@ -161,10 +160,22 @@
 
 /* 32-bit compat sysenter target */
 SYM_FUNC_START(xen_sysenter_target)
-	mov 0*8(%rsp), %rcx
-	mov 1*8(%rsp), %r11
-	mov 5*8(%rsp), %rsp
-	jmp entry_SYSENTER_compat
+	/*
+	 * NB: Xen is polite and clears TF from EFLAGS for us.  This means
+	 * that we don't need to guard against single step exceptions here.
+	 */
+	popq %rcx
+	popq %r11
+
+	/*
+	 * Neither Xen nor the kernel really knows what the old SS and
+	 * CS were.  The kernel expects __USER32_DS and __USER32_CS, so
+	 * report those values even though Xen will guess its own values.
+	 */
+	movq $__USER32_DS, 4*8(%rsp)
+	movq $__USER32_CS, 1*8(%rsp)
+
+	jmp entry_SYSENTER_compat_after_hwframe
 SYM_FUNC_END(xen_sysenter_target)
 
 #else /* !CONFIG_IA32_EMULATION */
diff --git a/arch/xtensa/include/asm/checksum.h b/arch/xtensa/include/asm/checksum.h
index d8292cc..243a5fe 100644
--- a/arch/xtensa/include/asm/checksum.h
+++ b/arch/xtensa/include/asm/checksum.h
@@ -57,7 +57,7 @@
 __wsum csum_and_copy_from_user(const void __user *src, void *dst,
 				   int len, __wsum sum, int *err_ptr)
 {
-	if (access_ok(dst, len))
+	if (access_ok(src, len))
 		return csum_partial_copy_generic((__force const void *)src, dst,
 					len, sum, err_ptr, NULL);
 	if (len)
diff --git a/arch/xtensa/kernel/perf_event.c b/arch/xtensa/kernel/perf_event.c
index 9bae79f..99fcd63 100644
--- a/arch/xtensa/kernel/perf_event.c
+++ b/arch/xtensa/kernel/perf_event.c
@@ -362,9 +362,7 @@
 	struct xtensa_pmu_events *ev = this_cpu_ptr(&xtensa_pmu_events);
 	unsigned i;
 
-	for (i = find_first_bit(ev->used_mask, XCHAL_NUM_PERF_COUNTERS);
-	     i < XCHAL_NUM_PERF_COUNTERS;
-	     i = find_next_bit(ev->used_mask, XCHAL_NUM_PERF_COUNTERS, i + 1)) {
+	for_each_set_bit(i, ev->used_mask, XCHAL_NUM_PERF_COUNTERS) {
 		uint32_t v = get_er(XTENSA_PMU_PMSTAT(i));
 		struct perf_event *event = ev->event[i];
 		struct hw_perf_event *hwc = &event->hw;
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index d9204dc2..be2c78f 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -724,7 +724,8 @@
 static void *
 c_next(struct seq_file *f, void *v, loff_t *pos)
 {
-	return NULL;
+	++*pos;
+	return c_start(f, pos);
 }
 
 static void
diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c
index 4092555..24cf697 100644
--- a/arch/xtensa/kernel/xtensa_ksyms.c
+++ b/arch/xtensa/kernel/xtensa_ksyms.c
@@ -87,13 +87,13 @@
 }
 EXPORT_SYMBOL(__xtensa_libgcc_window_spill);
 
-unsigned long __sync_fetch_and_and_4(unsigned long *p, unsigned long v)
+unsigned int __sync_fetch_and_and_4(volatile void *p, unsigned int v)
 {
 	BUG();
 }
 EXPORT_SYMBOL(__sync_fetch_and_and_4);
 
-unsigned long __sync_fetch_and_or_4(unsigned long *p, unsigned long v)
+unsigned int __sync_fetch_and_or_4(volatile void *p, unsigned int v)
 {
 	BUG();
 }
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 23632a3..9ffd7e2 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -24,6 +24,19 @@
 	flush_workqueue(kintegrityd_wq);
 }
 
+static void __bio_integrity_free(struct bio_set *bs,
+				 struct bio_integrity_payload *bip)
+{
+	if (bs && mempool_initialized(&bs->bio_integrity_pool)) {
+		if (bip->bip_vec)
+			bvec_free(&bs->bvec_integrity_pool, bip->bip_vec,
+				  bip->bip_slab);
+		mempool_free(bip, &bs->bio_integrity_pool);
+	} else {
+		kfree(bip);
+	}
+}
+
 /**
  * bio_integrity_alloc - Allocate integrity payload and attach it to bio
  * @bio:	bio to attach integrity metadata to
@@ -78,7 +91,7 @@
 
 	return bip;
 err:
-	mempool_free(bip, &bs->bio_integrity_pool);
+	__bio_integrity_free(bs, bip);
 	return ERR_PTR(-ENOMEM);
 }
 EXPORT_SYMBOL(bio_integrity_alloc);
@@ -99,14 +112,7 @@
 		kfree(page_address(bip->bip_vec->bv_page) +
 		      bip->bip_vec->bv_offset);
 
-	if (bs && mempool_initialized(&bs->bio_integrity_pool)) {
-		bvec_free(&bs->bvec_integrity_pool, bip->bip_vec, bip->bip_slab);
-
-		mempool_free(bip, &bs->bio_integrity_pool);
-	} else {
-		kfree(bip);
-	}
-
+	__bio_integrity_free(bs, bip);
 	bio->bi_integrity = NULL;
 	bio->bi_opf &= ~REQ_INTEGRITY;
 }
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 15df3a3..e0b2bc1 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -125,6 +125,9 @@
 	QUEUE_FLAG_NAME(REGISTERED),
 	QUEUE_FLAG_NAME(SCSI_PASSTHROUGH),
 	QUEUE_FLAG_NAME(QUIESCED),
+	QUEUE_FLAG_NAME(PCI_P2PDMA),
+	QUEUE_FLAG_NAME(ZONE_RESETALL),
+	QUEUE_FLAG_NAME(RQ_ALLOC_TIME),
 };
 #undef QUEUE_FLAG_NAME
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index a9aa6d1..4e0d173 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -828,10 +828,10 @@
 			       void *priv, bool reserved)
 {
 	/*
-	 * If we find a request that is inflight and the queue matches,
+	 * If we find a request that isn't idle and the queue matches,
 	 * we know the queue is busy. Return false to stop the iteration.
 	 */
-	if (rq->state == MQ_RQ_IN_FLIGHT && rq->q == hctx->queue) {
+	if (blk_mq_request_started(rq) && rq->q == hctx->queue) {
 		bool *busy = priv;
 
 		*busy = true;
diff --git a/block/keyslot-manager.c b/block/keyslot-manager.c
index c2ef41b..35abcb1 100644
--- a/block/keyslot-manager.c
+++ b/block/keyslot-manager.c
@@ -374,8 +374,7 @@
 	if (!ksm)
 		return;
 	kvfree(ksm->slot_hashtable);
-	memzero_explicit(ksm->slots, sizeof(ksm->slots[0]) * ksm->num_slots);
-	kvfree(ksm->slots);
+	kvfree_sensitive(ksm->slots, sizeof(ksm->slots[0]) * ksm->num_slots);
 	memzero_explicit(ksm, sizeof(*ksm));
 }
 EXPORT_SYMBOL_GPL(blk_ksm_destroy);
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index b1cd353..28fc323 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -128,21 +128,15 @@
 void af_alg_release_parent(struct sock *sk)
 {
 	struct alg_sock *ask = alg_sk(sk);
-	unsigned int nokey = ask->nokey_refcnt;
-	bool last = nokey && !ask->refcnt;
+	unsigned int nokey = atomic_read(&ask->nokey_refcnt);
 
 	sk = ask->parent;
 	ask = alg_sk(sk);
 
-	local_bh_disable();
-	bh_lock_sock(sk);
-	ask->nokey_refcnt -= nokey;
-	if (!last)
-		last = !--ask->refcnt;
-	bh_unlock_sock(sk);
-	local_bh_enable();
+	if (nokey)
+		atomic_dec(&ask->nokey_refcnt);
 
-	if (last)
+	if (atomic_dec_and_test(&ask->refcnt))
 		sock_put(sk);
 }
 EXPORT_SYMBOL_GPL(af_alg_release_parent);
@@ -187,7 +181,7 @@
 
 	err = -EBUSY;
 	lock_sock(sk);
-	if (ask->refcnt | ask->nokey_refcnt)
+	if (atomic_read(&ask->refcnt))
 		goto unlock;
 
 	swap(ask->type, type);
@@ -236,7 +230,7 @@
 	int err = -EBUSY;
 
 	lock_sock(sk);
-	if (ask->refcnt)
+	if (atomic_read(&ask->refcnt) != atomic_read(&ask->nokey_refcnt))
 		goto unlock;
 
 	type = ask->type;
@@ -301,12 +295,14 @@
 	if (err)
 		goto unlock;
 
-	if (nokey || !ask->refcnt++)
+	if (atomic_inc_return_relaxed(&ask->refcnt) == 1)
 		sock_hold(sk);
-	ask->nokey_refcnt += nokey;
+	if (nokey) {
+		atomic_inc(&ask->nokey_refcnt);
+		atomic_set(&alg_sk(sk2)->nokey_refcnt, 1);
+	}
 	alg_sk(sk2)->parent = sk;
 	alg_sk(sk2)->type = type;
-	alg_sk(sk2)->nokey_refcnt = nokey;
 
 	newsock->ops = type->ops;
 	newsock->state = SS_CONNECTED;
diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c
index eb1910b..0ae000a 100644
--- a/crypto/algif_aead.c
+++ b/crypto/algif_aead.c
@@ -384,7 +384,7 @@
 	struct alg_sock *ask = alg_sk(sk);
 
 	lock_sock(sk);
-	if (ask->refcnt)
+	if (!atomic_read(&ask->nokey_refcnt))
 		goto unlock_child;
 
 	psk = ask->parent;
@@ -396,11 +396,8 @@
 	if (crypto_aead_get_flags(tfm->aead) & CRYPTO_TFM_NEED_KEY)
 		goto unlock;
 
-	if (!pask->refcnt++)
-		sock_hold(psk);
-
-	ask->refcnt = 1;
-	sock_put(psk);
+	atomic_dec(&pask->nokey_refcnt);
+	atomic_set(&ask->nokey_refcnt, 0);
 
 	err = 0;
 
diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
index da1ffa4..e71727c 100644
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -301,7 +301,7 @@
 	struct alg_sock *ask = alg_sk(sk);
 
 	lock_sock(sk);
-	if (ask->refcnt)
+	if (!atomic_read(&ask->nokey_refcnt))
 		goto unlock_child;
 
 	psk = ask->parent;
@@ -313,11 +313,8 @@
 	if (crypto_ahash_get_flags(tfm) & CRYPTO_TFM_NEED_KEY)
 		goto unlock;
 
-	if (!pask->refcnt++)
-		sock_hold(psk);
-
-	ask->refcnt = 1;
-	sock_put(psk);
+	atomic_dec(&pask->nokey_refcnt);
+	atomic_set(&ask->nokey_refcnt, 0);
 
 	err = 0;
 
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index 4c3bdffe..ec5567c 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -211,7 +211,7 @@
 	struct alg_sock *ask = alg_sk(sk);
 
 	lock_sock(sk);
-	if (ask->refcnt)
+	if (!atomic_read(&ask->nokey_refcnt))
 		goto unlock_child;
 
 	psk = ask->parent;
@@ -223,11 +223,8 @@
 	if (crypto_skcipher_get_flags(tfm) & CRYPTO_TFM_NEED_KEY)
 		goto unlock;
 
-	if (!pask->refcnt++)
-		sock_hold(psk);
-
-	ask->refcnt = 1;
-	sock_put(psk);
+	atomic_dec(&pask->nokey_refcnt);
+	atomic_set(&ask->nokey_refcnt, 0);
 
 	err = 0;
 
diff --git a/crypto/asymmetric_keys/public_key.c b/crypto/asymmetric_keys/public_key.c
index d7f43d4..e5fae4e 100644
--- a/crypto/asymmetric_keys/public_key.c
+++ b/crypto/asymmetric_keys/public_key.c
@@ -119,6 +119,7 @@
 	if (IS_ERR(tfm))
 		return PTR_ERR(tfm);
 
+	ret = -ENOMEM;
 	key = kmalloc(pkey->keylen + sizeof(u32) * 2 + pkey->paramlen,
 		      GFP_KERNEL);
 	if (!key)
diff --git a/drivers/acpi/acpi_configfs.c b/drivers/acpi/acpi_configfs.c
index ece8c1a..88c8af4 100644
--- a/drivers/acpi/acpi_configfs.c
+++ b/drivers/acpi/acpi_configfs.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/configfs.h>
 #include <linux/acpi.h>
+#include <linux/security.h>
 
 #include "acpica/accommon.h"
 #include "acpica/actables.h"
@@ -28,7 +29,10 @@
 {
 	const struct acpi_table_header *header = data;
 	struct acpi_table *table;
-	int ret;
+	int ret = security_locked_down(LOCKDOWN_ACPI_TABLES);
+
+	if (ret)
+		return ret;
 
 	table = container_of(cfg, struct acpi_table, cfg);
 
diff --git a/drivers/acpi/dptf/dptf_power.c b/drivers/acpi/dptf/dptf_power.c
index 5fab7e3..92b996a 100644
--- a/drivers/acpi/dptf/dptf_power.c
+++ b/drivers/acpi/dptf/dptf_power.c
@@ -228,6 +228,7 @@
 	{"INT3407", 0},
 	{"INT3532", 0},
 	{"INTC1047", 0},
+	{"INTC1050", 0},
 	{"", 0},
 };
 MODULE_DEVICE_TABLE(acpi, int3407_device_ids);
diff --git a/drivers/acpi/fan.c b/drivers/acpi/fan.c
index 873e039..6287338 100644
--- a/drivers/acpi/fan.c
+++ b/drivers/acpi/fan.c
@@ -25,8 +25,8 @@
 
 static const struct acpi_device_id fan_device_ids[] = {
 	{"PNP0C0B", 0},
-	{"INT1044", 0},
 	{"INT3404", 0},
+	{"INTC1044", 0},
 	{"", 0},
 };
 MODULE_DEVICE_TABLE(acpi, fan_device_ids);
diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c
index 3a89909..76c668c 100644
--- a/drivers/acpi/sysfs.c
+++ b/drivers/acpi/sysfs.c
@@ -938,13 +938,13 @@
 }
 
 static ssize_t
-acpi_show_profile(struct device *dev, struct device_attribute *attr,
+acpi_show_profile(struct kobject *kobj, struct kobj_attribute *attr,
 		  char *buf)
 {
 	return sprintf(buf, "%d\n", acpi_gbl_FADT.preferred_profile);
 }
 
-static const struct device_attribute pm_profile_attr =
+static const struct kobj_attribute pm_profile_attr =
 	__ATTR(pm_profile, S_IRUGO, acpi_show_profile, NULL);
 
 static ssize_t hotplug_enabled_show(struct kobject *kobj,
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index e47c8a4..f50c5f1 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -4686,8 +4686,15 @@
 
 static void binder_free_proc(struct binder_proc *proc)
 {
+	struct binder_device *device;
+
 	BUG_ON(!list_empty(&proc->todo));
 	BUG_ON(!list_empty(&proc->delivered_death));
+	device = container_of(proc->context, struct binder_device, context);
+	if (refcount_dec_and_test(&device->ref)) {
+		kfree(proc->context->name);
+		kfree(device);
+	}
 	binder_alloc_deferred_release(&proc->alloc);
 	put_task_struct(proc->tsk);
 	binder_stats_deleted(BINDER_STAT_PROC);
@@ -5406,7 +5413,6 @@
 static void binder_deferred_release(struct binder_proc *proc)
 {
 	struct binder_context *context = proc->context;
-	struct binder_device *device;
 	struct rb_node *n;
 	int threads, nodes, incoming_refs, outgoing_refs, active_transactions;
 
@@ -5423,12 +5429,6 @@
 		context->binder_context_mgr_node = NULL;
 	}
 	mutex_unlock(&context->context_mgr_node_lock);
-	device = container_of(proc->context, struct binder_device, context);
-	if (refcount_dec_and_test(&device->ref)) {
-		kfree(context->name);
-		kfree(device);
-	}
-	proc->context = NULL;
 	binder_inner_proc_lock(proc);
 	/*
 	 * Make sure proc stays alive after we
diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 42c672f..cbe6aa7 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -947,7 +947,7 @@
 		trace_binder_unmap_user_end(alloc, index);
 	}
 	mmap_read_unlock(mm);
-	mmput(mm);
+	mmput_async(mm);
 
 	trace_binder_unmap_kernel_start(alloc, index);
 
diff --git a/drivers/base/base.h b/drivers/base/base.h
index 95c22c0..40fb069 100644
--- a/drivers/base/base.h
+++ b/drivers/base/base.h
@@ -153,7 +153,6 @@
 extern int devres_release_all(struct device *dev);
 extern void device_block_probing(void);
 extern void device_unblock_probing(void);
-extern void driver_deferred_probe_force_trigger(void);
 
 /* /sys/devices directory */
 extern struct kset *devices_kset;
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 67d39a9..05d414e 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -50,6 +50,7 @@
 static LIST_HEAD(deferred_sync);
 static unsigned int defer_sync_state_count = 1;
 static unsigned int defer_fw_devlink_count;
+static LIST_HEAD(deferred_fw_devlink);
 static DEFINE_MUTEX(defer_fw_devlink_lock);
 static bool fw_devlink_is_permissive(void);
 
@@ -754,11 +755,11 @@
 	 */
 	dev->state_synced = true;
 
-	if (WARN_ON(!list_empty(&dev->links.defer_sync)))
+	if (WARN_ON(!list_empty(&dev->links.defer_hook)))
 		return;
 
 	get_device(dev);
-	list_add_tail(&dev->links.defer_sync, list);
+	list_add_tail(&dev->links.defer_hook, list);
 }
 
 /**
@@ -776,8 +777,8 @@
 {
 	struct device *dev, *tmp;
 
-	list_for_each_entry_safe(dev, tmp, list, links.defer_sync) {
-		list_del_init(&dev->links.defer_sync);
+	list_for_each_entry_safe(dev, tmp, list, links.defer_hook) {
+		list_del_init(&dev->links.defer_hook);
 
 		if (dev != dont_lock_dev)
 			device_lock(dev);
@@ -815,12 +816,12 @@
 	if (defer_sync_state_count)
 		goto out;
 
-	list_for_each_entry_safe(dev, tmp, &deferred_sync, links.defer_sync) {
+	list_for_each_entry_safe(dev, tmp, &deferred_sync, links.defer_hook) {
 		/*
 		 * Delete from deferred_sync list before queuing it to
-		 * sync_list because defer_sync is used for both lists.
+		 * sync_list because defer_hook is used for both lists.
 		 */
-		list_del_init(&dev->links.defer_sync);
+		list_del_init(&dev->links.defer_hook);
 		__device_links_queue_sync_state(dev, &sync_list);
 	}
 out:
@@ -838,8 +839,8 @@
 
 static void __device_links_supplier_defer_sync(struct device *sup)
 {
-	if (list_empty(&sup->links.defer_sync) && dev_has_sync_state(sup))
-		list_add_tail(&sup->links.defer_sync, &deferred_sync);
+	if (list_empty(&sup->links.defer_hook) && dev_has_sync_state(sup))
+		list_add_tail(&sup->links.defer_hook, &deferred_sync);
 }
 
 static void device_link_drop_managed(struct device_link *link)
@@ -1052,7 +1053,7 @@
 		WRITE_ONCE(link->status, DL_STATE_DORMANT);
 	}
 
-	list_del_init(&dev->links.defer_sync);
+	list_del_init(&dev->links.defer_hook);
 	__device_links_no_driver(dev);
 
 	device_links_write_unlock();
@@ -1244,6 +1245,12 @@
 			fw_ret = -EAGAIN;
 	} else {
 		fw_ret = -ENODEV;
+		/*
+		 * defer_hook is not used to add device to deferred_sync list
+		 * until device is bound. Since deferred fw devlink also blocks
+		 * probing, same list hook can be used for deferred_fw_devlink.
+		 */
+		list_add_tail(&dev->links.defer_hook, &deferred_fw_devlink);
 	}
 
 	if (fw_ret == -ENODEV)
@@ -1312,6 +1319,9 @@
  */
 void fw_devlink_resume(void)
 {
+	struct device *dev, *tmp;
+	LIST_HEAD(probe_list);
+
 	mutex_lock(&defer_fw_devlink_lock);
 	if (!defer_fw_devlink_count) {
 		WARN(true, "Unmatched fw_devlink pause/resume!");
@@ -1323,9 +1333,19 @@
 		goto out;
 
 	device_link_add_missing_supplier_links();
-	driver_deferred_probe_force_trigger();
+	list_splice_tail_init(&deferred_fw_devlink, &probe_list);
 out:
 	mutex_unlock(&defer_fw_devlink_lock);
+
+	/*
+	 * bus_probe_device() can cause new devices to get added and they'll
+	 * try to grab defer_fw_devlink_lock. So, this needs to be done outside
+	 * the defer_fw_devlink_lock.
+	 */
+	list_for_each_entry_safe(dev, tmp, &probe_list, links.defer_hook) {
+		list_del_init(&dev->links.defer_hook);
+		bus_probe_device(dev);
+	}
 }
 /* Device links support end. */
 
@@ -2172,7 +2192,7 @@
 	INIT_LIST_HEAD(&dev->links.consumers);
 	INIT_LIST_HEAD(&dev->links.suppliers);
 	INIT_LIST_HEAD(&dev->links.needs_suppliers);
-	INIT_LIST_HEAD(&dev->links.defer_sync);
+	INIT_LIST_HEAD(&dev->links.defer_hook);
 	dev->links.status = DL_DEV_NO_DRIVER;
 }
 EXPORT_SYMBOL_GPL(device_initialize);
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index 9a1d940..48ca81c 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -164,11 +164,6 @@
 	if (!driver_deferred_probe_enable)
 		return;
 
-	driver_deferred_probe_force_trigger();
-}
-
-void driver_deferred_probe_force_trigger(void)
-{
 	/*
 	 * A successful probe means that all the devices in the pending list
 	 * should be triggered to be reprobed.  Move all the deferred devices
diff --git a/drivers/base/power/trace.c b/drivers/base/power/trace.c
index 977d27b..a97f33d 100644
--- a/drivers/base/power/trace.c
+++ b/drivers/base/power/trace.c
@@ -265,14 +265,14 @@
 	.notifier_call = pm_trace_notify,
 };
 
-static int early_resume_init(void)
+static int __init early_resume_init(void)
 {
 	hash_value_early_read = read_magic_time();
 	register_pm_notifier(&pm_trace_nb);
 	return 0;
 }
 
-static int late_resume_init(void)
+static int __init late_resume_init(void)
 {
 	unsigned int val = hash_value_early_read;
 	unsigned int user, file, dev;
diff --git a/drivers/base/property.c b/drivers/base/property.c
index 1e6d75e..d58aa98 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -721,7 +721,7 @@
 		return next;
 
 	/* When no more children in primary, continue with secondary */
-	if (!IS_ERR_OR_NULL(fwnode->secondary))
+	if (fwnode && !IS_ERR_OR_NULL(fwnode->secondary))
 		next = fwnode_get_next_child_node(fwnode->secondary, child);
 
 	return next;
diff --git a/drivers/base/regmap/Kconfig b/drivers/base/regmap/Kconfig
index 0fd6f97..1d1d26b 100644
--- a/drivers/base/regmap/Kconfig
+++ b/drivers/base/regmap/Kconfig
@@ -4,7 +4,7 @@
 # subsystems should select the appropriate symbols.
 
 config REGMAP
-	default y if (REGMAP_I2C || REGMAP_SPI || REGMAP_SPMI || REGMAP_W1 || REGMAP_AC97 || REGMAP_MMIO || REGMAP_IRQ || REGMAP_SCCB || REGMAP_I3C)
+	default y if (REGMAP_I2C || REGMAP_SPI || REGMAP_SPMI || REGMAP_W1 || REGMAP_AC97 || REGMAP_MMIO || REGMAP_IRQ || REGMAP_SOUNDWIRE || REGMAP_SCCB || REGMAP_I3C)
 	select IRQ_DOMAIN if REGMAP_IRQ
 	bool
 
diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c
index 089e5dc..f58baff 100644
--- a/drivers/base/regmap/regmap-debugfs.c
+++ b/drivers/base/regmap/regmap-debugfs.c
@@ -463,29 +463,31 @@
 {
 	struct regmap *map = container_of(file->private_data,
 					  struct regmap, cache_only);
-	ssize_t result;
-	bool was_enabled, require_sync = false;
+	bool new_val, require_sync = false;
 	int err;
 
+	err = kstrtobool_from_user(user_buf, count, &new_val);
+	/* Ignore malforned data like debugfs_write_file_bool() */
+	if (err)
+		return count;
+
+	err = debugfs_file_get(file->f_path.dentry);
+	if (err)
+		return err;
+
 	map->lock(map->lock_arg);
 
-	was_enabled = map->cache_only;
-
-	result = debugfs_write_file_bool(file, user_buf, count, ppos);
-	if (result < 0) {
-		map->unlock(map->lock_arg);
-		return result;
-	}
-
-	if (map->cache_only && !was_enabled) {
+	if (new_val && !map->cache_only) {
 		dev_warn(map->dev, "debugfs cache_only=Y forced\n");
 		add_taint(TAINT_USER, LOCKDEP_STILL_OK);
-	} else if (!map->cache_only && was_enabled) {
+	} else if (!new_val && map->cache_only) {
 		dev_warn(map->dev, "debugfs cache_only=N forced: syncing cache\n");
 		require_sync = true;
 	}
+	map->cache_only = new_val;
 
 	map->unlock(map->lock_arg);
+	debugfs_file_put(file->f_path.dentry);
 
 	if (require_sync) {
 		err = regcache_sync(map);
@@ -493,7 +495,7 @@
 			dev_err(map->dev, "Failed to sync cache %d\n", err);
 	}
 
-	return result;
+	return count;
 }
 
 static const struct file_operations regmap_cache_only_fops = {
@@ -508,28 +510,32 @@
 {
 	struct regmap *map = container_of(file->private_data,
 					  struct regmap, cache_bypass);
-	ssize_t result;
-	bool was_enabled;
+	bool new_val;
+	int err;
+
+	err = kstrtobool_from_user(user_buf, count, &new_val);
+	/* Ignore malforned data like debugfs_write_file_bool() */
+	if (err)
+		return count;
+
+	err = debugfs_file_get(file->f_path.dentry);
+	if (err)
+		return err;
 
 	map->lock(map->lock_arg);
 
-	was_enabled = map->cache_bypass;
-
-	result = debugfs_write_file_bool(file, user_buf, count, ppos);
-	if (result < 0)
-		goto out;
-
-	if (map->cache_bypass && !was_enabled) {
+	if (new_val && !map->cache_bypass) {
 		dev_warn(map->dev, "debugfs cache_bypass=Y forced\n");
 		add_taint(TAINT_USER, LOCKDEP_STILL_OK);
-	} else if (!map->cache_bypass && was_enabled) {
+	} else if (!new_val && map->cache_bypass) {
 		dev_warn(map->dev, "debugfs cache_bypass=N forced\n");
 	}
+	map->cache_bypass = new_val;
 
-out:
 	map->unlock(map->lock_arg);
+	debugfs_file_put(file->f_path.dentry);
 
-	return result;
+	return count;
 }
 
 static const struct file_operations regmap_cache_bypass_fops = {
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index c472f62..795a62a 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -17,6 +17,7 @@
 #include <linux/delay.h>
 #include <linux/log2.h>
 #include <linux/hwspinlock.h>
+#include <asm/unaligned.h>
 
 #define CREATE_TRACE_POINTS
 #include "trace.h"
@@ -249,22 +250,20 @@
 
 static void regmap_format_16_be(void *buf, unsigned int val, unsigned int shift)
 {
-	__be16 *b = buf;
-
-	b[0] = cpu_to_be16(val << shift);
+	put_unaligned_be16(val << shift, buf);
 }
 
 static void regmap_format_16_le(void *buf, unsigned int val, unsigned int shift)
 {
-	__le16 *b = buf;
-
-	b[0] = cpu_to_le16(val << shift);
+	put_unaligned_le16(val << shift, buf);
 }
 
 static void regmap_format_16_native(void *buf, unsigned int val,
 				    unsigned int shift)
 {
-	*(u16 *)buf = val << shift;
+	u16 v = val << shift;
+
+	memcpy(buf, &v, sizeof(v));
 }
 
 static void regmap_format_24(void *buf, unsigned int val, unsigned int shift)
@@ -280,43 +279,39 @@
 
 static void regmap_format_32_be(void *buf, unsigned int val, unsigned int shift)
 {
-	__be32 *b = buf;
-
-	b[0] = cpu_to_be32(val << shift);
+	put_unaligned_be32(val << shift, buf);
 }
 
 static void regmap_format_32_le(void *buf, unsigned int val, unsigned int shift)
 {
-	__le32 *b = buf;
-
-	b[0] = cpu_to_le32(val << shift);
+	put_unaligned_le32(val << shift, buf);
 }
 
 static void regmap_format_32_native(void *buf, unsigned int val,
 				    unsigned int shift)
 {
-	*(u32 *)buf = val << shift;
+	u32 v = val << shift;
+
+	memcpy(buf, &v, sizeof(v));
 }
 
 #ifdef CONFIG_64BIT
 static void regmap_format_64_be(void *buf, unsigned int val, unsigned int shift)
 {
-	__be64 *b = buf;
-
-	b[0] = cpu_to_be64((u64)val << shift);
+	put_unaligned_be64((u64) val << shift, buf);
 }
 
 static void regmap_format_64_le(void *buf, unsigned int val, unsigned int shift)
 {
-	__le64 *b = buf;
-
-	b[0] = cpu_to_le64((u64)val << shift);
+	put_unaligned_le64((u64) val << shift, buf);
 }
 
 static void regmap_format_64_native(void *buf, unsigned int val,
 				    unsigned int shift)
 {
-	*(u64 *)buf = (u64)val << shift;
+	u64 v = (u64) val << shift;
+
+	memcpy(buf, &v, sizeof(v));
 }
 #endif
 
@@ -333,35 +328,34 @@
 
 static unsigned int regmap_parse_16_be(const void *buf)
 {
-	const __be16 *b = buf;
-
-	return be16_to_cpu(b[0]);
+	return get_unaligned_be16(buf);
 }
 
 static unsigned int regmap_parse_16_le(const void *buf)
 {
-	const __le16 *b = buf;
-
-	return le16_to_cpu(b[0]);
+	return get_unaligned_le16(buf);
 }
 
 static void regmap_parse_16_be_inplace(void *buf)
 {
-	__be16 *b = buf;
+	u16 v = get_unaligned_be16(buf);
 
-	b[0] = be16_to_cpu(b[0]);
+	memcpy(buf, &v, sizeof(v));
 }
 
 static void regmap_parse_16_le_inplace(void *buf)
 {
-	__le16 *b = buf;
+	u16 v = get_unaligned_le16(buf);
 
-	b[0] = le16_to_cpu(b[0]);
+	memcpy(buf, &v, sizeof(v));
 }
 
 static unsigned int regmap_parse_16_native(const void *buf)
 {
-	return *(u16 *)buf;
+	u16 v;
+
+	memcpy(&v, buf, sizeof(v));
+	return v;
 }
 
 static unsigned int regmap_parse_24(const void *buf)
@@ -376,69 +370,67 @@
 
 static unsigned int regmap_parse_32_be(const void *buf)
 {
-	const __be32 *b = buf;
-
-	return be32_to_cpu(b[0]);
+	return get_unaligned_be32(buf);
 }
 
 static unsigned int regmap_parse_32_le(const void *buf)
 {
-	const __le32 *b = buf;
-
-	return le32_to_cpu(b[0]);
+	return get_unaligned_le32(buf);
 }
 
 static void regmap_parse_32_be_inplace(void *buf)
 {
-	__be32 *b = buf;
+	u32 v = get_unaligned_be32(buf);
 
-	b[0] = be32_to_cpu(b[0]);
+	memcpy(buf, &v, sizeof(v));
 }
 
 static void regmap_parse_32_le_inplace(void *buf)
 {
-	__le32 *b = buf;
+	u32 v = get_unaligned_le32(buf);
 
-	b[0] = le32_to_cpu(b[0]);
+	memcpy(buf, &v, sizeof(v));
 }
 
 static unsigned int regmap_parse_32_native(const void *buf)
 {
-	return *(u32 *)buf;
+	u32 v;
+
+	memcpy(&v, buf, sizeof(v));
+	return v;
 }
 
 #ifdef CONFIG_64BIT
 static unsigned int regmap_parse_64_be(const void *buf)
 {
-	const __be64 *b = buf;
-
-	return be64_to_cpu(b[0]);
+	return get_unaligned_be64(buf);
 }
 
 static unsigned int regmap_parse_64_le(const void *buf)
 {
-	const __le64 *b = buf;
-
-	return le64_to_cpu(b[0]);
+	return get_unaligned_le64(buf);
 }
 
 static void regmap_parse_64_be_inplace(void *buf)
 {
-	__be64 *b = buf;
+	u64 v =  get_unaligned_be64(buf);
 
-	b[0] = be64_to_cpu(b[0]);
+	memcpy(buf, &v, sizeof(v));
 }
 
 static void regmap_parse_64_le_inplace(void *buf)
 {
-	__le64 *b = buf;
+	u64 v = get_unaligned_le64(buf);
 
-	b[0] = le64_to_cpu(b[0]);
+	memcpy(buf, &v, sizeof(v));
 }
 
 static unsigned int regmap_parse_64_native(const void *buf)
 {
-	return *(u64 *)buf;
+	u64 v;
+
+	memcpy(&v, buf, sizeof(v));
+	return v;
 }
 #endif
 
@@ -1357,6 +1349,7 @@
 	if (map->hwlock)
 		hwspin_lock_free(map->hwlock);
 	kfree_const(map->name);
+	kfree(map->patch);
 	kfree(map);
 }
 EXPORT_SYMBOL_GPL(regmap_exit);
@@ -1371,7 +1364,7 @@
 
 	/* If the user didn't specify a name match any */
 	if (data)
-		return (*r)->name == data;
+		return !strcmp((*r)->name, data);
 	else
 		return 1;
 }
@@ -2944,8 +2937,9 @@
  * @reg: Register to read from
  * @bits: Bits to test
  *
- * Returns -1 if the underlying regmap_read() fails, 0 if at least one of the
- * tested bits is not set and 1 if all tested bits are set.
+ * Returns 0 if at least one of the tested bits is not set, 1 if all tested
+ * bits are set and a negative error number if the underlying regmap_read()
+ * fails.
  */
 int regmap_test_bits(struct regmap *map, unsigned int reg, unsigned int bits)
 {
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 43cff01..ce7e9f22 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -1033,25 +1033,26 @@
 	     test_bit(NBD_RT_BOUND, &config->runtime_flags))) {
 		dev_err(disk_to_dev(nbd->disk),
 			"Device being setup by another task");
-		sockfd_put(sock);
-		return -EBUSY;
+		err = -EBUSY;
+		goto put_socket;
+	}
+
+	nsock = kzalloc(sizeof(*nsock), GFP_KERNEL);
+	if (!nsock) {
+		err = -ENOMEM;
+		goto put_socket;
 	}
 
 	socks = krealloc(config->socks, (config->num_connections + 1) *
 			 sizeof(struct nbd_sock *), GFP_KERNEL);
 	if (!socks) {
-		sockfd_put(sock);
-		return -ENOMEM;
+		kfree(nsock);
+		err = -ENOMEM;
+		goto put_socket;
 	}
 
 	config->socks = socks;
 
-	nsock = kzalloc(sizeof(struct nbd_sock), GFP_KERNEL);
-	if (!nsock) {
-		sockfd_put(sock);
-		return -ENOMEM;
-	}
-
 	nsock->fallback_index = -1;
 	nsock->dead = false;
 	mutex_init(&nsock->tx_lock);
@@ -1063,6 +1064,10 @@
 	atomic_inc(&config->live_connections);
 
 	return 0;
+
+put_socket:
+	sockfd_put(sock);
+	return err;
 }
 
 static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg)
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 9d21bf0..980df85 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -878,6 +878,7 @@
 	put_disk(vblk->disk);
 out_free_vq:
 	vdev->config->del_vqs(vdev);
+	kfree(vblk->vqs);
 out_free_vblk:
 	kfree(vblk);
 out_free_index:
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 6e2ad90..270dd81 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -2021,7 +2021,8 @@
 		return ret;
 	return scnprintf(buf, PAGE_SIZE, "%d\n", ret);
 }
-static CLASS_ATTR_RO(hot_add);
+static struct class_attribute class_attr_hot_add =
+	__ATTR(hot_add, 0400, hot_add_show, NULL);
 
 static ssize_t hot_remove_store(struct class *class,
 			struct class_attribute *attr,
diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c
index 3affd18..191c97b 100644
--- a/drivers/bus/ti-sysc.c
+++ b/drivers/bus/ti-sysc.c
@@ -221,6 +221,34 @@
 	return sysc_read(ddata, offset);
 }
 
+/* Poll on reset status */
+static int sysc_wait_softreset(struct sysc *ddata)
+{
+	u32 sysc_mask, syss_done, rstval;
+	int syss_offset, error = 0;
+
+	syss_offset = ddata->offsets[SYSC_SYSSTATUS];
+	sysc_mask = BIT(ddata->cap->regbits->srst_shift);
+
+	if (ddata->cfg.quirks & SYSS_QUIRK_RESETDONE_INVERTED)
+		syss_done = 0;
+	else
+		syss_done = ddata->cfg.syss_mask;
+
+	if (syss_offset >= 0) {
+		error = readx_poll_timeout_atomic(sysc_read_sysstatus, ddata,
+				rstval, (rstval & ddata->cfg.syss_mask) ==
+				syss_done, 100, MAX_MODULE_SOFTRESET_WAIT);
+
+	} else if (ddata->cfg.quirks & SYSC_QUIRK_RESET_STATUS) {
+		error = readx_poll_timeout_atomic(sysc_read_sysconfig, ddata,
+				rstval, !(rstval & sysc_mask),
+				100, MAX_MODULE_SOFTRESET_WAIT);
+	}
+
+	return error;
+}
+
 static int sysc_add_named_clock_from_child(struct sysc *ddata,
 					   const char *name,
 					   const char *optfck_name)
@@ -925,18 +953,47 @@
 	struct sysc *ddata;
 	const struct sysc_regbits *regbits;
 	u32 reg, idlemodes, best_mode;
+	int error;
 
 	ddata = dev_get_drvdata(dev);
+
+	/*
+	 * Some modules like DSS reset automatically on idle. Enable optional
+	 * reset clocks and wait for OCP softreset to complete.
+	 */
+	if (ddata->cfg.quirks & SYSC_QUIRK_OPT_CLKS_IN_RESET) {
+		error = sysc_enable_opt_clocks(ddata);
+		if (error) {
+			dev_err(ddata->dev,
+				"Optional clocks failed for enable: %i\n",
+				error);
+			return error;
+		}
+	}
+	error = sysc_wait_softreset(ddata);
+	if (error)
+		dev_warn(ddata->dev, "OCP softreset timed out\n");
+	if (ddata->cfg.quirks & SYSC_QUIRK_OPT_CLKS_IN_RESET)
+		sysc_disable_opt_clocks(ddata);
+
+	/*
+	 * Some subsystem private interconnects, like DSS top level module,
+	 * need only the automatic OCP softreset handling with no sysconfig
+	 * register bits to configure.
+	 */
 	if (ddata->offsets[SYSC_SYSCONFIG] == -ENODEV)
 		return 0;
 
 	regbits = ddata->cap->regbits;
 	reg = sysc_read(ddata, ddata->offsets[SYSC_SYSCONFIG]);
 
-	/* Set CLOCKACTIVITY, we only use it for ick */
+	/*
+	 * Set CLOCKACTIVITY, we only use it for ick. And we only configure it
+	 * based on the SYSC_QUIRK_USE_CLOCKACT flag, not based on the hardware
+	 * capabilities. See the old HWMOD_SET_DEFAULT_CLOCKACT flag.
+	 */
 	if (regbits->clkact_shift >= 0 &&
-	    (ddata->cfg.quirks & SYSC_QUIRK_USE_CLOCKACT ||
-	     ddata->cfg.sysc_val & BIT(regbits->clkact_shift)))
+	    (ddata->cfg.quirks & SYSC_QUIRK_USE_CLOCKACT))
 		reg |= SYSC_CLOCACT_ICK << regbits->clkact_shift;
 
 	/* Set SIDLE mode */
@@ -991,6 +1048,9 @@
 		sysc_write_sysconfig(ddata, reg);
 	}
 
+	/* Flush posted write */
+	sysc_read(ddata, ddata->offsets[SYSC_SYSCONFIG]);
+
 	if (ddata->module_enable_quirk)
 		ddata->module_enable_quirk(ddata);
 
@@ -1071,6 +1131,9 @@
 		reg |= 1 << regbits->autoidle_shift;
 	sysc_write_sysconfig(ddata, reg);
 
+	/* Flush posted write */
+	sysc_read(ddata, ddata->offsets[SYSC_SYSCONFIG]);
+
 	return 0;
 }
 
@@ -1215,7 +1278,8 @@
 
 	ddata = dev_get_drvdata(dev);
 
-	if (ddata->cfg.quirks & SYSC_QUIRK_LEGACY_IDLE)
+	if (ddata->cfg.quirks &
+	    (SYSC_QUIRK_LEGACY_IDLE | SYSC_QUIRK_NO_IDLE))
 		return 0;
 
 	return pm_runtime_force_suspend(dev);
@@ -1227,7 +1291,8 @@
 
 	ddata = dev_get_drvdata(dev);
 
-	if (ddata->cfg.quirks & SYSC_QUIRK_LEGACY_IDLE)
+	if (ddata->cfg.quirks &
+	    (SYSC_QUIRK_LEGACY_IDLE | SYSC_QUIRK_NO_IDLE))
 		return 0;
 
 	return pm_runtime_force_resume(dev);
@@ -1488,7 +1553,7 @@
 	bool lcd_en, digit_en, lcd2_en = false, lcd3_en = false;
 	const int lcd_en_mask = BIT(0), digit_en_mask = BIT(1);
 	int manager_count;
-	bool framedonetv_irq;
+	bool framedonetv_irq = true;
 	u32 val, irq_mask = 0;
 
 	switch (sysc_soc->soc) {
@@ -1505,6 +1570,7 @@
 		break;
 	case SOC_AM4:
 		manager_count = 1;
+		framedonetv_irq = false;
 		break;
 	case SOC_UNKNOWN:
 	default:
@@ -1663,8 +1729,8 @@
 
 	local_irq_save(flags);
 	/* RTC_STATUS BUSY bit may stay active for 1/32768 seconds (~30 usec) */
-	error = readl_poll_timeout(ddata->module_va + 0x44, val,
-				   !(val & BIT(0)), 100, 50);
+	error = readl_poll_timeout_atomic(ddata->module_va + 0x44, val,
+					  !(val & BIT(0)), 100, 50);
 	if (error)
 		dev_warn(ddata->dev, "rtc busy timeout\n");
 	/* Now we have ~15 microseconds to read/write various registers */
@@ -1822,11 +1888,10 @@
  */
 static int sysc_reset(struct sysc *ddata)
 {
-	int sysc_offset, syss_offset, sysc_val, rstval, error = 0;
-	u32 sysc_mask, syss_done;
+	int sysc_offset, sysc_val, error;
+	u32 sysc_mask;
 
 	sysc_offset = ddata->offsets[SYSC_SYSCONFIG];
-	syss_offset = ddata->offsets[SYSC_SYSSTATUS];
 
 	if (ddata->legacy_mode ||
 	    ddata->cap->regbits->srst_shift < 0 ||
@@ -1835,11 +1900,6 @@
 
 	sysc_mask = BIT(ddata->cap->regbits->srst_shift);
 
-	if (ddata->cfg.quirks & SYSS_QUIRK_RESETDONE_INVERTED)
-		syss_done = 0;
-	else
-		syss_done = ddata->cfg.syss_mask;
-
 	if (ddata->pre_reset_quirk)
 		ddata->pre_reset_quirk(ddata);
 
@@ -1856,18 +1916,9 @@
 	if (ddata->post_reset_quirk)
 		ddata->post_reset_quirk(ddata);
 
-	/* Poll on reset status */
-	if (syss_offset >= 0) {
-		error = readx_poll_timeout(sysc_read_sysstatus, ddata, rstval,
-					   (rstval & ddata->cfg.syss_mask) ==
-					   syss_done,
-					   100, MAX_MODULE_SOFTRESET_WAIT);
-
-	} else if (ddata->cfg.quirks & SYSC_QUIRK_RESET_STATUS) {
-		error = readx_poll_timeout(sysc_read_sysconfig, ddata, rstval,
-					   !(rstval & sysc_mask),
-					   100, MAX_MODULE_SOFTRESET_WAIT);
-	}
+	error = sysc_wait_softreset(ddata);
+	if (error)
+		dev_warn(ddata->dev, "OCP softreset timed out\n");
 
 	if (ddata->reset_done_quirk)
 		ddata->reset_done_quirk(ddata);
@@ -2814,6 +2865,24 @@
 	return error;
 }
 
+/*
+ * Ignore timers tagged with no-reset and no-idle. These are likely in use,
+ * for example by drivers/clocksource/timer-ti-dm-systimer.c. If more checks
+ * are needed, we could also look at the timer register configuration.
+ */
+static int sysc_check_active_timer(struct sysc *ddata)
+{
+	if (ddata->cap->type != TI_SYSC_OMAP2_TIMER &&
+	    ddata->cap->type != TI_SYSC_OMAP4_TIMER)
+		return 0;
+
+	if ((ddata->cfg.quirks & SYSC_QUIRK_NO_RESET_ON_INIT) &&
+	    (ddata->cfg.quirks & SYSC_QUIRK_NO_IDLE))
+		return -EBUSY;
+
+	return 0;
+}
+
 static const struct of_device_id sysc_match_table[] = {
 	{ .compatible = "simple-bus", },
 	{ /* sentinel */ },
@@ -2870,6 +2939,10 @@
 	if (error)
 		return error;
 
+	error = sysc_check_active_timer(ddata);
+	if (error)
+		return error;
+
 	error = sysc_get_clocks(ddata);
 	if (error)
 		return error;
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 934c92d..687d4af 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -814,7 +814,8 @@
 #ifdef CONFIG_IO_STRICT_DEVMEM
 void revoke_devmem(struct resource *res)
 {
-	struct inode *inode = READ_ONCE(devmem_inode);
+	/* pairs with smp_store_release() in devmem_init_inode() */
+	struct inode *inode = smp_load_acquire(&devmem_inode);
 
 	/*
 	 * Check that the initialization has completed. Losing the race
@@ -1028,8 +1029,11 @@
 		return rc;
 	}
 
-	/* publish /dev/mem initialized */
-	WRITE_ONCE(devmem_inode, inode);
+	/*
+	 * Publish /dev/mem initialized.
+	 * Pairs with smp_load_acquire() in revoke_devmem().
+	 */
+	smp_store_release(&devmem_inode, inode);
 
 	return 0;
 }
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 2a41b21..d20ba1b 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -1277,6 +1277,7 @@
 
 	fast_mix(fast_pool);
 	add_interrupt_bench(cycles);
+	this_cpu_add(net_rand_state.s1, fast_pool->pool[cycles & 3]);
 
 	if (unlikely(crng_init == 0)) {
 		if ((fast_pool->count >= 64) &&
diff --git a/drivers/char/tpm/st33zp24/i2c.c b/drivers/char/tpm/st33zp24/i2c.c
index 35333b6..7c617ed 100644
--- a/drivers/char/tpm/st33zp24/i2c.c
+++ b/drivers/char/tpm/st33zp24/i2c.c
@@ -210,7 +210,7 @@
 
 /*
  * st33zp24_i2c_probe initialize the TPM device
- * @param: client, the i2c_client drescription (TPM I2C description).
+ * @param: client, the i2c_client description (TPM I2C description).
  * @param: id, the i2c_device_id struct.
  * @return: 0 in case of success.
  *	 -1 in other case.
diff --git a/drivers/char/tpm/st33zp24/spi.c b/drivers/char/tpm/st33zp24/spi.c
index 26e09de..a75dafd 100644
--- a/drivers/char/tpm/st33zp24/spi.c
+++ b/drivers/char/tpm/st33zp24/spi.c
@@ -329,7 +329,7 @@
 
 /*
  * st33zp24_spi_probe initialize the TPM device
- * @param: dev, the spi_device drescription (TPM SPI description).
+ * @param: dev, the spi_device description (TPM SPI description).
  * @return: 0 in case of success.
  *	 or a negative value describing the error.
  */
@@ -378,7 +378,7 @@
 
 /*
  * st33zp24_spi_remove remove the TPM device
- * @param: client, the spi_device drescription (TPM SPI description).
+ * @param: client, the spi_device description (TPM SPI description).
  * @return: 0 in case of success.
  */
 static int st33zp24_spi_remove(struct spi_device *dev)
diff --git a/drivers/char/tpm/st33zp24/st33zp24.c b/drivers/char/tpm/st33zp24/st33zp24.c
index 37bb13f..4ec10ab 100644
--- a/drivers/char/tpm/st33zp24/st33zp24.c
+++ b/drivers/char/tpm/st33zp24/st33zp24.c
@@ -502,7 +502,7 @@
 
 /*
  * st33zp24_probe initialize the TPM device
- * @param: client, the i2c_client drescription (TPM I2C description).
+ * @param: client, the i2c_client description (TPM I2C description).
  * @param: id, the i2c_device_id struct.
  * @return: 0 in case of success.
  *	 -1 in other case.
diff --git a/drivers/char/tpm/tpm-dev-common.c b/drivers/char/tpm/tpm-dev-common.c
index 87f4493..1784530 100644
--- a/drivers/char/tpm/tpm-dev-common.c
+++ b/drivers/char/tpm/tpm-dev-common.c
@@ -189,15 +189,6 @@
 		goto out;
 	}
 
-	/* atomic tpm command send and result receive. We only hold the ops
-	 * lock during this period so that the tpm can be unregistered even if
-	 * the char dev is held open.
-	 */
-	if (tpm_try_get_ops(priv->chip)) {
-		ret = -EPIPE;
-		goto out;
-	}
-
 	priv->response_length = 0;
 	priv->response_read = false;
 	*off = 0;
@@ -211,11 +202,19 @@
 	if (file->f_flags & O_NONBLOCK) {
 		priv->command_enqueued = true;
 		queue_work(tpm_dev_wq, &priv->async_work);
-		tpm_put_ops(priv->chip);
 		mutex_unlock(&priv->buffer_mutex);
 		return size;
 	}
 
+	/* atomic tpm command send and result receive. We only hold the ops
+	 * lock during this period so that the tpm can be unregistered even if
+	 * the char dev is held open.
+	 */
+	if (tpm_try_get_ops(priv->chip)) {
+		ret = -EPIPE;
+		goto out;
+	}
+
 	ret = tpm_dev_transmit(priv->chip, priv->space, priv->data_buffer,
 			       sizeof(priv->data_buffer));
 	tpm_put_ops(priv->chip);
diff --git a/drivers/char/tpm/tpm_ibmvtpm.c b/drivers/char/tpm/tpm_ibmvtpm.c
index 09fe452..994385b 100644
--- a/drivers/char/tpm/tpm_ibmvtpm.c
+++ b/drivers/char/tpm/tpm_ibmvtpm.c
@@ -683,13 +683,6 @@
 	if (rc)
 		goto init_irq_cleanup;
 
-	if (!strcmp(id->compat, "IBM,vtpm20")) {
-		chip->flags |= TPM_CHIP_FLAG_TPM2;
-		rc = tpm2_get_cc_attrs_tbl(chip);
-		if (rc)
-			goto init_irq_cleanup;
-	}
-
 	if (!wait_event_timeout(ibmvtpm->crq_queue.wq,
 				ibmvtpm->rtce_buf != NULL,
 				HZ)) {
@@ -697,6 +690,13 @@
 		goto init_irq_cleanup;
 	}
 
+	if (!strcmp(id->compat, "IBM,vtpm20")) {
+		chip->flags |= TPM_CHIP_FLAG_TPM2;
+		rc = tpm2_get_cc_attrs_tbl(chip);
+		if (rc)
+			goto init_irq_cleanup;
+	}
+
 	return tpm_chip_register(chip);
 init_irq_cleanup:
 	do {
diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c
index e7df342..0b21496 100644
--- a/drivers/char/tpm/tpm_tis.c
+++ b/drivers/char/tpm/tpm_tis.c
@@ -235,6 +235,13 @@
 	return tpm_tis_init(&pnp_dev->dev, &tpm_info);
 }
 
+/*
+ * There is a known bug caused by 93e1b7d42e1e ("[PATCH] tpm: add HID module
+ * parameter"). This commit added IFX0102 device ID, which is also used by
+ * tpm_infineon but ignored to add quirks to probe which driver ought to be
+ * used.
+ */
+
 static struct pnp_device_id tpm_pnp_tbl[] = {
 	{"PNP0C31", 0},		/* TPM */
 	{"ATM1200", 0},		/* Atmel */
diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c
index 2435216..65ab1b0 100644
--- a/drivers/char/tpm/tpm_tis_core.c
+++ b/drivers/char/tpm/tpm_tis_core.c
@@ -1085,7 +1085,7 @@
 
 	return 0;
 out_err:
-	if ((chip->ops != NULL) && (chip->ops->clk_enable != NULL))
+	if (chip->ops->clk_enable != NULL)
 		chip->ops->clk_enable(chip, false);
 
 	tpm_tis_remove(chip);
diff --git a/drivers/char/tpm/tpm_tis_spi_main.c b/drivers/char/tpm/tpm_tis_spi_main.c
index d967559..3856f6e 100644
--- a/drivers/char/tpm/tpm_tis_spi_main.c
+++ b/drivers/char/tpm/tpm_tis_spi_main.c
@@ -53,8 +53,6 @@
 
 	if ((phy->iobuf[3] & 0x01) == 0) {
 		// handle SPI wait states
-		phy->iobuf[0] = 0;
-
 		for (i = 0; i < TPM_RETRY; i++) {
 			spi_xfer->len = 1;
 			spi_message_init(&m);
@@ -104,6 +102,8 @@
 		if (ret < 0)
 			goto exit;
 
+		/* Flow control transfers are receive only */
+		spi_xfer.tx_buf = NULL;
 		ret = phy->flow_control(phy, &spi_xfer);
 		if (ret < 0)
 			goto exit;
@@ -113,9 +113,8 @@
 		spi_xfer.delay.value = 5;
 		spi_xfer.delay.unit = SPI_DELAY_UNIT_USECS;
 
-		if (in) {
-			spi_xfer.tx_buf = NULL;
-		} else if (out) {
+		if (out) {
+			spi_xfer.tx_buf = phy->iobuf;
 			spi_xfer.rx_buf = NULL;
 			memcpy(phy->iobuf, out, transfer_len);
 			out += transfer_len;
@@ -288,6 +287,7 @@
 		.pm = &tpm_tis_pm,
 		.of_match_table = of_match_ptr(of_tis_spi_match),
 		.acpi_match_table = ACPI_PTR(acpi_tis_spi_match),
+		.probe_type = PROBE_PREFER_ASYNCHRONOUS,
 	},
 	.probe = tpm_tis_spi_driver_probe,
 	.remove = tpm_tis_spi_remove,
diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 00c5e3a..ca691bc 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -2116,6 +2116,7 @@
 	{ VIRTIO_ID_CONSOLE, VIRTIO_DEV_ANY_ID },
 	{ 0 },
 };
+MODULE_DEVICE_TABLE(virtio, id_table);
 
 static unsigned int features[] = {
 	VIRTIO_CONSOLE_F_SIZE,
@@ -2128,6 +2129,7 @@
 #endif
 	{ 0 },
 };
+MODULE_DEVICE_TABLE(virtio, rproc_serial_id_table);
 
 static unsigned int rproc_serial_features[] = {
 };
@@ -2280,6 +2282,5 @@
 module_init(init);
 module_exit(fini);
 
-MODULE_DEVICE_TABLE(virtio, id_table);
 MODULE_DESCRIPTION("Virtio console driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig
index 69934c0..326f91b 100644
--- a/drivers/clk/Kconfig
+++ b/drivers/clk/Kconfig
@@ -50,6 +50,7 @@
 config CLK_HSDK
 	bool "PLL Driver for HSDK platform"
 	depends on OF || COMPILE_TEST
+	depends on IOMEM
 	help
 	  This driver supports the HSDK core, system, ddr, tunnel and hdmi PLLs
 	  control.
diff --git a/drivers/clk/clk-ast2600.c b/drivers/clk/clk-ast2600.c
index 99afc94..177368c 100644
--- a/drivers/clk/clk-ast2600.c
+++ b/drivers/clk/clk-ast2600.c
@@ -131,6 +131,18 @@
 	{ 0 }
 };
 
+static const struct clk_div_table ast2600_emmc_extclk_div_table[] = {
+	{ 0x0, 2 },
+	{ 0x1, 4 },
+	{ 0x2, 6 },
+	{ 0x3, 8 },
+	{ 0x4, 10 },
+	{ 0x5, 12 },
+	{ 0x6, 14 },
+	{ 0x7, 16 },
+	{ 0 }
+};
+
 static const struct clk_div_table ast2600_mac_div_table[] = {
 	{ 0x0, 4 },
 	{ 0x1, 4 },
@@ -390,6 +402,11 @@
 	return hw;
 }
 
+static const char *const emmc_extclk_parent_names[] = {
+	"emmc_extclk_hpll_in",
+	"mpll",
+};
+
 static const char * const vclk_parent_names[] = {
 	"dpll",
 	"d1pll",
@@ -459,16 +476,32 @@
 		return PTR_ERR(hw);
 	aspeed_g6_clk_data->hws[ASPEED_CLK_UARTX] = hw;
 
-	/* EMMC ext clock divider */
-	hw = clk_hw_register_gate(dev, "emmc_extclk_gate", "hpll", 0,
-			scu_g6_base + ASPEED_G6_CLK_SELECTION1, 15, 0,
-			&aspeed_g6_clk_lock);
+	/* EMMC ext clock */
+	hw = clk_hw_register_fixed_factor(dev, "emmc_extclk_hpll_in", "hpll",
+					  0, 1, 2);
 	if (IS_ERR(hw))
 		return PTR_ERR(hw);
-	hw = clk_hw_register_divider_table(dev, "emmc_extclk", "emmc_extclk_gate", 0,
-			scu_g6_base + ASPEED_G6_CLK_SELECTION1, 12, 3, 0,
-			ast2600_div_table,
-			&aspeed_g6_clk_lock);
+
+	hw = clk_hw_register_mux(dev, "emmc_extclk_mux",
+				 emmc_extclk_parent_names,
+				 ARRAY_SIZE(emmc_extclk_parent_names), 0,
+				 scu_g6_base + ASPEED_G6_CLK_SELECTION1, 11, 1,
+				 0, &aspeed_g6_clk_lock);
+	if (IS_ERR(hw))
+		return PTR_ERR(hw);
+
+	hw = clk_hw_register_gate(dev, "emmc_extclk_gate", "emmc_extclk_mux",
+				  0, scu_g6_base + ASPEED_G6_CLK_SELECTION1,
+				  15, 0, &aspeed_g6_clk_lock);
+	if (IS_ERR(hw))
+		return PTR_ERR(hw);
+
+	hw = clk_hw_register_divider_table(dev, "emmc_extclk",
+					   "emmc_extclk_gate", 0,
+					   scu_g6_base +
+						ASPEED_G6_CLK_SELECTION1, 12,
+					   3, 0, ast2600_emmc_extclk_div_table,
+					   &aspeed_g6_clk_lock);
 	if (IS_ERR(hw))
 		return PTR_ERR(hw);
 	aspeed_g6_clk_data->hws[ASPEED_CLK_EMMC] = hw;
diff --git a/drivers/clk/mvebu/Kconfig b/drivers/clk/mvebu/Kconfig
index ded07b0..557d621 100644
--- a/drivers/clk/mvebu/Kconfig
+++ b/drivers/clk/mvebu/Kconfig
@@ -42,6 +42,7 @@
 
 config ARMADA_AP_CPU_CLK
 	bool
+	select ARMADA_AP_CP_HELPER
 
 config ARMADA_CP110_SYSCON
 	bool
diff --git a/drivers/clk/sifive/fu540-prci.c b/drivers/clk/sifive/fu540-prci.c
index 6282ee2..a8901f9 100644
--- a/drivers/clk/sifive/fu540-prci.c
+++ b/drivers/clk/sifive/fu540-prci.c
@@ -586,7 +586,10 @@
 	struct __prci_data *pd;
 	int r;
 
-	pd = devm_kzalloc(dev, sizeof(*pd), GFP_KERNEL);
+	pd = devm_kzalloc(dev,
+			  struct_size(pd, hw_clks.hws,
+				      ARRAY_SIZE(__prci_init_clocks)),
+			  GFP_KERNEL);
 	if (!pd)
 		return -ENOMEM;
 
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index ecf7b7d..6c3e841 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -480,6 +480,14 @@
 		.set_next_event_virt = erratum_set_next_event_tval_virt,
 	},
 #endif
+#ifdef CONFIG_ARM64_ERRATUM_1418040
+	{
+		.match_type = ate_match_local_cap_id,
+		.id = (void *)ARM64_WORKAROUND_1418040,
+		.desc = "ARM erratum 1418040",
+		.disable_compat_vdso = true,
+	},
+#endif
 };
 
 typedef bool (*ate_match_fn_t)(const struct arch_timer_erratum_workaround *,
@@ -566,6 +574,9 @@
 	if (wa->read_cntvct_el0) {
 		clocksource_counter.vdso_clock_mode = VDSO_CLOCKMODE_NONE;
 		vdso_default = VDSO_CLOCKMODE_NONE;
+	} else if (wa->disable_compat_vdso && vdso_default != VDSO_CLOCKMODE_NONE) {
+		vdso_default = VDSO_CLOCKMODE_ARCHTIMER_NOCOMPAT;
+		clocksource_counter.vdso_clock_mode = vdso_default;
 	}
 }
 
diff --git a/drivers/clocksource/timer-ti-dm-systimer.c b/drivers/clocksource/timer-ti-dm-systimer.c
index 6fd1f21..f6fd1c1 100644
--- a/drivers/clocksource/timer-ti-dm-systimer.c
+++ b/drivers/clocksource/timer-ti-dm-systimer.c
@@ -19,7 +19,7 @@
 /* For type1, set SYSC_OMAP2_CLOCKACTIVITY for fck off on idle, l4 clock on */
 #define DMTIMER_TYPE1_ENABLE	((1 << 9) | (SYSC_IDLE_SMART << 3) | \
 				 SYSC_OMAP2_ENAWAKEUP | SYSC_OMAP2_AUTOIDLE)
-
+#define DMTIMER_TYPE1_DISABLE	(SYSC_OMAP2_SOFTRESET | SYSC_OMAP2_AUTOIDLE)
 #define DMTIMER_TYPE2_ENABLE	(SYSC_IDLE_SMART_WKUP << 2)
 #define DMTIMER_RESET_WAIT	100000
 
@@ -44,6 +44,8 @@
 	u8 ctrl;
 	u8 wakeup;
 	u8 ifctrl;
+	struct clk *fck;
+	struct clk *ick;
 	unsigned long rate;
 };
 
@@ -298,16 +300,20 @@
 }
 
 /* Interface clocks are only available on some SoCs variants */
-static int __init dmtimer_systimer_init_clock(struct device_node *np,
+static int __init dmtimer_systimer_init_clock(struct dmtimer_systimer *t,
+					      struct device_node *np,
 					      const char *name,
 					      unsigned long *rate)
 {
 	struct clk *clock;
 	unsigned long r;
+	bool is_ick = false;
 	int error;
 
+	is_ick = !strncmp(name, "ick", 3);
+
 	clock = of_clk_get_by_name(np, name);
-	if ((PTR_ERR(clock) == -EINVAL) && !strncmp(name, "ick", 3))
+	if ((PTR_ERR(clock) == -EINVAL) && is_ick)
 		return 0;
 	else if (IS_ERR(clock))
 		return PTR_ERR(clock);
@@ -320,6 +326,11 @@
 	if (!r)
 		return -ENODEV;
 
+	if (is_ick)
+		t->ick = clock;
+	else
+		t->fck = clock;
+
 	*rate = r;
 
 	return 0;
@@ -339,7 +350,10 @@
 
 static void dmtimer_systimer_disable(struct dmtimer_systimer *t)
 {
-	writel_relaxed(0, t->base + t->sysc);
+	if (!dmtimer_systimer_revision1(t))
+		return;
+
+	writel_relaxed(DMTIMER_TYPE1_DISABLE, t->base + t->sysc);
 }
 
 static int __init dmtimer_systimer_setup(struct device_node *np,
@@ -366,13 +380,13 @@
 		pr_err("%s: clock source init failed: %i\n", __func__, error);
 
 	/* For ti-sysc, we have timer clocks at the parent module level */
-	error = dmtimer_systimer_init_clock(np->parent, "fck", &rate);
+	error = dmtimer_systimer_init_clock(t, np->parent, "fck", &rate);
 	if (error)
 		goto err_unmap;
 
 	t->rate = rate;
 
-	error = dmtimer_systimer_init_clock(np->parent, "ick", &rate);
+	error = dmtimer_systimer_init_clock(t, np->parent, "ick", &rate);
 	if (error)
 		goto err_unmap;
 
@@ -496,12 +510,18 @@
 	struct dmtimer_systimer *t = &clkevt->t;
 
 	dmtimer_systimer_disable(t);
+	clk_disable(t->fck);
 }
 
 static void omap_clockevent_unidle(struct clock_event_device *evt)
 {
 	struct dmtimer_clockevent *clkevt = to_dmtimer_clockevent(evt);
 	struct dmtimer_systimer *t = &clkevt->t;
+	int error;
+
+	error = clk_enable(t->fck);
+	if (error)
+		pr_err("could not enable timer fck on resume: %i\n", error);
 
 	dmtimer_systimer_enable(t);
 	writel_relaxed(OMAP_TIMER_INT_OVERFLOW, t->base + t->irq_ena);
@@ -570,8 +590,8 @@
 					3, /* Timer internal resynch latency */
 					0xffffffff);
 
-	if (of_device_is_compatible(np, "ti,am33xx") ||
-	    of_device_is_compatible(np, "ti,am43")) {
+	if (of_machine_is_compatible("ti,am33xx") ||
+	    of_machine_is_compatible("ti,am43")) {
 		dev->suspend = omap_clockevent_idle;
 		dev->resume = omap_clockevent_unidle;
 	}
@@ -616,12 +636,18 @@
 
 	clksrc->loadval = readl_relaxed(t->base + t->counter);
 	dmtimer_systimer_disable(t);
+	clk_disable(t->fck);
 }
 
 static void dmtimer_clocksource_resume(struct clocksource *cs)
 {
 	struct dmtimer_clocksource *clksrc = to_dmtimer_clocksource(cs);
 	struct dmtimer_systimer *t = &clksrc->t;
+	int error;
+
+	error = clk_enable(t->fck);
+	if (error)
+		pr_err("could not enable timer fck on resume: %i\n", error);
 
 	dmtimer_systimer_enable(t);
 	writel_relaxed(clksrc->loadval, t->base + t->counter);
@@ -653,8 +679,8 @@
 	dev->mask = CLOCKSOURCE_MASK(32);
 	dev->flags = CLOCK_SOURCE_IS_CONTINUOUS;
 
-	if (of_device_is_compatible(np, "ti,am33xx") ||
-	    of_device_is_compatible(np, "ti,am43")) {
+	/* Unlike for clockevent, legacy code sets suspend only for am4 */
+	if (of_machine_is_compatible("ti,am43")) {
 		dev->suspend = dmtimer_clocksource_suspend;
 		dev->resume = dmtimer_clocksource_resume;
 	}
diff --git a/drivers/counter/104-quad-8.c b/drivers/counter/104-quad-8.c
index aa13708..d22cfae 100644
--- a/drivers/counter/104-quad-8.c
+++ b/drivers/counter/104-quad-8.c
@@ -1274,18 +1274,26 @@
 					     struct counter_signal *signal,
 					     void *private, char *buf)
 {
-	const struct quad8_iio *const priv = counter->priv;
+	struct quad8_iio *const priv = counter->priv;
 	const size_t channel_id = signal->id / 2;
-	const bool disabled = !(priv->cable_fault_enable & BIT(channel_id));
+	bool disabled;
 	unsigned int status;
 	unsigned int fault;
 
-	if (disabled)
+	mutex_lock(&priv->lock);
+
+	disabled = !(priv->cable_fault_enable & BIT(channel_id));
+
+	if (disabled) {
+		mutex_unlock(&priv->lock);
 		return -EINVAL;
+	}
 
 	/* Logic 0 = cable fault */
 	status = inb(priv->base + QUAD8_DIFF_ENCODER_CABLE_STATUS);
 
+	mutex_unlock(&priv->lock);
+
 	/* Mask respective channel and invert logic */
 	fault = !(status & BIT(channel_id));
 
@@ -1317,6 +1325,8 @@
 	if (ret)
 		return ret;
 
+	mutex_lock(&priv->lock);
+
 	if (enable)
 		priv->cable_fault_enable |= BIT(channel_id);
 	else
@@ -1327,6 +1337,8 @@
 
 	outb(cable_fault_enable, priv->base + QUAD8_DIFF_ENCODER_CABLE_STATUS);
 
+	mutex_unlock(&priv->lock);
+
 	return len;
 }
 
@@ -1353,6 +1365,8 @@
 	if (ret)
 		return ret;
 
+	mutex_lock(&priv->lock);
+
 	priv->fck_prescaler[channel_id] = prescaler;
 
 	/* Reset Byte Pointer */
@@ -1363,6 +1377,8 @@
 	outb(QUAD8_CTR_RLD | QUAD8_RLD_RESET_BP | QUAD8_RLD_PRESET_PSC,
 	     base_offset + 1);
 
+	mutex_unlock(&priv->lock);
+
 	return len;
 }
 
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 8e23a69..7e0f7880 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -2464,7 +2464,7 @@
 	.name		= "intel_cpufreq",
 };
 
-static struct cpufreq_driver *default_driver = &intel_pstate;
+static struct cpufreq_driver *default_driver;
 
 static void intel_pstate_driver_cleanup(void)
 {
@@ -2677,6 +2677,8 @@
 	{ } /* End */
 };
 
+#define BITMASK_OOB	(BIT(8) | BIT(18))
+
 static bool __init intel_pstate_platform_pwr_mgmt_exists(void)
 {
 	const struct x86_cpu_id *id;
@@ -2686,8 +2688,9 @@
 	id = x86_match_cpu(intel_pstate_cpu_oob_ids);
 	if (id) {
 		rdmsrl(MSR_MISC_PWR_MGMT, misc_pwr);
-		if (misc_pwr & (1 << 8)) {
-			pr_debug("Bit 8 in the MISC_PWR_MGMT MSR set\n");
+		if (misc_pwr & BITMASK_OOB) {
+			pr_debug("Bit 8 or 18 in the MISC_PWR_MGMT MSR set\n");
+			pr_debug("P states are controlled in Out of Band mode by the firmware/hardware\n");
 			return true;
 		}
 	}
@@ -2755,6 +2758,7 @@
 			hwp_active++;
 			hwp_mode_bdw = id->driver_data;
 			intel_pstate.attr = hwp_cpufreq_attrs;
+			default_driver = &intel_pstate;
 			goto hwp_cpu_matched;
 		}
 	} else {
@@ -2772,7 +2776,8 @@
 		return -ENODEV;
 	}
 	/* Without HWP start in the passive mode. */
-	default_driver = &intel_cpufreq;
+	if (!default_driver)
+		default_driver = &intel_cpufreq;
 
 hwp_cpu_matched:
 	/*
@@ -2817,6 +2822,8 @@
 
 	if (!strcmp(str, "disable")) {
 		no_load = 1;
+	} else if (!strcmp(str, "active")) {
+		default_driver = &intel_pstate;
 	} else if (!strcmp(str, "passive")) {
 		default_driver = &intel_cpufreq;
 		no_hwp = 1;
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index c149d9e..8719731 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -186,9 +186,10 @@
 	 * be frozen safely.
 	 */
 	index = find_deepest_state(drv, dev, U64_MAX, 0, true);
-	if (index > 0)
+	if (index > 0) {
 		enter_s2idle_proper(drv, dev, index);
-
+		local_irq_enable();
+	}
 	return index;
 }
 #endif /* CONFIG_SUSPEND */
diff --git a/drivers/crypto/chelsio/chtls/chtls_cm.c b/drivers/crypto/chelsio/chtls/chtls_cm.c
index f200fae..5409311 100644
--- a/drivers/crypto/chelsio/chtls/chtls_cm.c
+++ b/drivers/crypto/chelsio/chtls/chtls_cm.c
@@ -102,7 +102,7 @@
 	case PF_INET:
 		if (likely(!inet_sk(sk)->inet_rcv_saddr))
 			return ndev;
-		ndev = ip_dev_find(&init_net, inet_sk(sk)->inet_rcv_saddr);
+		ndev = __ip_dev_find(&init_net, inet_sk(sk)->inet_rcv_saddr, false);
 		break;
 #if IS_ENABLED(CONFIG_IPV6)
 	case PF_INET6:
diff --git a/drivers/crypto/chelsio/chtls/chtls_io.c b/drivers/crypto/chelsio/chtls/chtls_io.c
index e1401d9..2e9acae 100644
--- a/drivers/crypto/chelsio/chtls/chtls_io.c
+++ b/drivers/crypto/chelsio/chtls/chtls_io.c
@@ -1052,14 +1052,15 @@
 							  &record_type);
 				if (err)
 					goto out_err;
+
+				/* Avoid appending tls handshake, alert to tls data */
+				if (skb)
+					tx_skb_finalize(skb);
 			}
 
 			recordsz = size;
 			csk->tlshws.txleft = recordsz;
 			csk->tlshws.type = record_type;
-
-			if (skb)
-				ULP_SKB_CB(skb)->ulp.tls.type = record_type;
 		}
 
 		if (!skb || (ULP_SKB_CB(skb)->flags & ULPCB_FLAG_NO_APPEND) ||
diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index 01ce125..1ca609f 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -45,46 +45,20 @@
 	size_t ret = 0;
 
 	dmabuf = dentry->d_fsdata;
-	dma_resv_lock(dmabuf->resv, NULL);
+	spin_lock(&dmabuf->name_lock);
 	if (dmabuf->name)
 		ret = strlcpy(name, dmabuf->name, DMA_BUF_NAME_LEN);
-	dma_resv_unlock(dmabuf->resv);
+	spin_unlock(&dmabuf->name_lock);
 
 	return dynamic_dname(dentry, buffer, buflen, "/%s:%s",
 			     dentry->d_name.name, ret > 0 ? name : "");
 }
 
-static const struct dentry_operations dma_buf_dentry_ops = {
-	.d_dname = dmabuffs_dname,
-};
-
-static struct vfsmount *dma_buf_mnt;
-
-static int dma_buf_fs_init_context(struct fs_context *fc)
-{
-	struct pseudo_fs_context *ctx;
-
-	ctx = init_pseudo(fc, DMA_BUF_MAGIC);
-	if (!ctx)
-		return -ENOMEM;
-	ctx->dops = &dma_buf_dentry_ops;
-	return 0;
-}
-
-static struct file_system_type dma_buf_fs_type = {
-	.name = "dmabuf",
-	.init_fs_context = dma_buf_fs_init_context,
-	.kill_sb = kill_anon_super,
-};
-
-static int dma_buf_release(struct inode *inode, struct file *file)
+static void dma_buf_release(struct dentry *dentry)
 {
 	struct dma_buf *dmabuf;
 
-	if (!is_dma_buf_file(file))
-		return -EINVAL;
-
-	dmabuf = file->private_data;
+	dmabuf = dentry->d_fsdata;
 
 	BUG_ON(dmabuf->vmapping_counter);
 
@@ -110,9 +84,32 @@
 	module_put(dmabuf->owner);
 	kfree(dmabuf->name);
 	kfree(dmabuf);
+}
+
+static const struct dentry_operations dma_buf_dentry_ops = {
+	.d_dname = dmabuffs_dname,
+	.d_release = dma_buf_release,
+};
+
+static struct vfsmount *dma_buf_mnt;
+
+static int dma_buf_fs_init_context(struct fs_context *fc)
+{
+	struct pseudo_fs_context *ctx;
+
+	ctx = init_pseudo(fc, DMA_BUF_MAGIC);
+	if (!ctx)
+		return -ENOMEM;
+	ctx->dops = &dma_buf_dentry_ops;
 	return 0;
 }
 
+static struct file_system_type dma_buf_fs_type = {
+	.name = "dmabuf",
+	.init_fs_context = dma_buf_fs_init_context,
+	.kill_sb = kill_anon_super,
+};
+
 static int dma_buf_mmap_internal(struct file *file, struct vm_area_struct *vma)
 {
 	struct dma_buf *dmabuf;
@@ -341,8 +338,10 @@
 		kfree(name);
 		goto out_unlock;
 	}
+	spin_lock(&dmabuf->name_lock);
 	kfree(dmabuf->name);
 	dmabuf->name = name;
+	spin_unlock(&dmabuf->name_lock);
 
 out_unlock:
 	dma_resv_unlock(dmabuf->resv);
@@ -405,14 +404,13 @@
 	/* Don't count the temporary reference taken inside procfs seq_show */
 	seq_printf(m, "count:\t%ld\n", file_count(dmabuf->file) - 1);
 	seq_printf(m, "exp_name:\t%s\n", dmabuf->exp_name);
-	dma_resv_lock(dmabuf->resv, NULL);
+	spin_lock(&dmabuf->name_lock);
 	if (dmabuf->name)
 		seq_printf(m, "name:\t%s\n", dmabuf->name);
-	dma_resv_unlock(dmabuf->resv);
+	spin_unlock(&dmabuf->name_lock);
 }
 
 static const struct file_operations dma_buf_fops = {
-	.release	= dma_buf_release,
 	.mmap		= dma_buf_mmap_internal,
 	.llseek		= dma_buf_llseek,
 	.poll		= dma_buf_poll,
@@ -546,6 +544,7 @@
 	dmabuf->size = exp_info->size;
 	dmabuf->exp_name = exp_info->exp_name;
 	dmabuf->owner = exp_info->owner;
+	spin_lock_init(&dmabuf->name_lock);
 	init_waitqueue_head(&dmabuf->poll);
 	dmabuf->cb_excl.poll = dmabuf->cb_shared.poll = &dmabuf->poll;
 	dmabuf->cb_excl.active = dmabuf->cb_shared.active = 0;
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index b175229..604f803 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -1176,6 +1176,8 @@
 	} else if (dmatest_run) {
 		if (!is_threaded_test_pending(info)) {
 			pr_info("No channels configured, continue with any\n");
+			if (!is_threaded_test_run(info))
+				stop_threaded_test(info);
 			add_threaded_test(info);
 		}
 		start_threaded_tests(info);
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index 21cb2a5..a1b56f5 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -118,16 +118,11 @@
 {
 	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
 
-	if (test_bit(DW_DMA_IS_INITIALIZED, &dwc->flags))
-		return;
-
 	dw->initialize_chan(dwc);
 
 	/* Enable interrupts */
 	channel_set_bit(dw, MASK.XFER, dwc->mask);
 	channel_set_bit(dw, MASK.ERROR, dwc->mask);
-
-	set_bit(DW_DMA_IS_INITIALIZED, &dwc->flags);
 }
 
 /*----------------------------------------------------------------------*/
@@ -954,8 +949,6 @@
 
 void do_dw_dma_off(struct dw_dma *dw)
 {
-	unsigned int i;
-
 	dma_writel(dw, CFG, 0);
 
 	channel_clear_bit(dw, MASK.XFER, dw->all_chan_mask);
@@ -966,9 +959,6 @@
 
 	while (dma_readl(dw, CFG) & DW_CFG_DMA_EN)
 		cpu_relax();
-
-	for (i = 0; i < dw->dma.chancnt; i++)
-		clear_bit(DW_DMA_IS_INITIALIZED, &dw->chan[i].flags);
 }
 
 void do_dw_dma_on(struct dw_dma *dw)
@@ -1032,8 +1022,6 @@
 	/* Clear custom channel configuration */
 	memset(&dwc->dws, 0, sizeof(struct dw_dma_slave));
 
-	clear_bit(DW_DMA_IS_INITIALIZED, &dwc->flags);
-
 	/* Disable interrupts */
 	channel_clear_bit(dw, MASK.XFER, dwc->mask);
 	channel_clear_bit(dw, MASK.BLOCK, dwc->mask);
diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c
index 5697c36..930ae26 100644
--- a/drivers/dma/fsl-edma-common.c
+++ b/drivers/dma/fsl-edma-common.c
@@ -352,26 +352,28 @@
 	/*
 	 * TCD parameters are stored in struct fsl_edma_hw_tcd in little
 	 * endian format. However, we need to load the TCD registers in
-	 * big- or little-endian obeying the eDMA engine model endian.
+	 * big- or little-endian obeying the eDMA engine model endian,
+	 * and this is performed from specific edma_write functions
 	 */
 	edma_writew(edma, 0,  &regs->tcd[ch].csr);
-	edma_writel(edma, le32_to_cpu(tcd->saddr), &regs->tcd[ch].saddr);
-	edma_writel(edma, le32_to_cpu(tcd->daddr), &regs->tcd[ch].daddr);
 
-	edma_writew(edma, le16_to_cpu(tcd->attr), &regs->tcd[ch].attr);
-	edma_writew(edma, le16_to_cpu(tcd->soff), &regs->tcd[ch].soff);
+	edma_writel(edma, (s32)tcd->saddr, &regs->tcd[ch].saddr);
+	edma_writel(edma, (s32)tcd->daddr, &regs->tcd[ch].daddr);
 
-	edma_writel(edma, le32_to_cpu(tcd->nbytes), &regs->tcd[ch].nbytes);
-	edma_writel(edma, le32_to_cpu(tcd->slast), &regs->tcd[ch].slast);
+	edma_writew(edma, (s16)tcd->attr, &regs->tcd[ch].attr);
+	edma_writew(edma, tcd->soff, &regs->tcd[ch].soff);
 
-	edma_writew(edma, le16_to_cpu(tcd->citer), &regs->tcd[ch].citer);
-	edma_writew(edma, le16_to_cpu(tcd->biter), &regs->tcd[ch].biter);
-	edma_writew(edma, le16_to_cpu(tcd->doff), &regs->tcd[ch].doff);
+	edma_writel(edma, (s32)tcd->nbytes, &regs->tcd[ch].nbytes);
+	edma_writel(edma, (s32)tcd->slast, &regs->tcd[ch].slast);
 
-	edma_writel(edma, le32_to_cpu(tcd->dlast_sga),
+	edma_writew(edma, (s16)tcd->citer, &regs->tcd[ch].citer);
+	edma_writew(edma, (s16)tcd->biter, &regs->tcd[ch].biter);
+	edma_writew(edma, (s16)tcd->doff, &regs->tcd[ch].doff);
+
+	edma_writel(edma, (s32)tcd->dlast_sga,
 			&regs->tcd[ch].dlast_sga);
 
-	edma_writew(edma, le16_to_cpu(tcd->csr), &regs->tcd[ch].csr);
+	edma_writew(edma, (s16)tcd->csr, &regs->tcd[ch].csr);
 }
 
 static inline
@@ -589,6 +591,8 @@
 {
 	struct virt_dma_desc *vdesc;
 
+	lockdep_assert_held(&fsl_chan->vchan.lock);
+
 	vdesc = vchan_next_desc(&fsl_chan->vchan);
 	if (!vdesc)
 		return;
diff --git a/drivers/dma/fsl-edma-common.h b/drivers/dma/fsl-edma-common.h
index 67e4225..ec11697 100644
--- a/drivers/dma/fsl-edma-common.h
+++ b/drivers/dma/fsl-edma-common.h
@@ -33,7 +33,7 @@
 #define EDMA_TCD_ATTR_DSIZE_16BIT	BIT(0)
 #define EDMA_TCD_ATTR_DSIZE_32BIT	BIT(1)
 #define EDMA_TCD_ATTR_DSIZE_64BIT	(BIT(0) | BIT(1))
-#define EDMA_TCD_ATTR_DSIZE_32BYTE	(BIT(3) | BIT(0))
+#define EDMA_TCD_ATTR_DSIZE_32BYTE	(BIT(2) | BIT(0))
 #define EDMA_TCD_ATTR_SSIZE_8BIT	0
 #define EDMA_TCD_ATTR_SSIZE_16BIT	(EDMA_TCD_ATTR_DSIZE_16BIT << 8)
 #define EDMA_TCD_ATTR_SSIZE_32BIT	(EDMA_TCD_ATTR_DSIZE_32BIT << 8)
diff --git a/drivers/dma/fsl-edma.c b/drivers/dma/fsl-edma.c
index eff7ebd..90bb72a 100644
--- a/drivers/dma/fsl-edma.c
+++ b/drivers/dma/fsl-edma.c
@@ -45,6 +45,13 @@
 			fsl_chan = &fsl_edma->chans[ch];
 
 			spin_lock(&fsl_chan->vchan.lock);
+
+			if (!fsl_chan->edesc) {
+				/* terminate_all called before */
+				spin_unlock(&fsl_chan->vchan.lock);
+				continue;
+			}
+
 			if (!fsl_chan->edesc->iscyclic) {
 				list_del(&fsl_chan->edesc->vdesc.node);
 				vchan_cookie_complete(&fsl_chan->edesc->vdesc);
diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c
index ff49847e..cb376cf 100644
--- a/drivers/dma/idxd/cdev.c
+++ b/drivers/dma/idxd/cdev.c
@@ -74,6 +74,7 @@
 	struct idxd_device *idxd;
 	struct idxd_wq *wq;
 	struct device *dev;
+	int rc = 0;
 
 	wq = inode_wq(inode);
 	idxd = wq->idxd;
@@ -81,17 +82,27 @@
 
 	dev_dbg(dev, "%s called: %d\n", __func__, idxd_wq_refcount(wq));
 
-	if (idxd_wq_refcount(wq) > 0 && wq_dedicated(wq))
-		return -EBUSY;
-
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
 		return -ENOMEM;
 
+	mutex_lock(&wq->wq_lock);
+
+	if (idxd_wq_refcount(wq) > 0 && wq_dedicated(wq)) {
+		rc = -EBUSY;
+		goto failed;
+	}
+
 	ctx->wq = wq;
 	filp->private_data = ctx;
 	idxd_wq_get(wq);
+	mutex_unlock(&wq->wq_lock);
 	return 0;
+
+ failed:
+	mutex_unlock(&wq->wq_lock);
+	kfree(ctx);
+	return rc;
 }
 
 static int idxd_cdev_release(struct inode *node, struct file *filep)
@@ -105,7 +116,9 @@
 	filep->private_data = NULL;
 
 	kfree(ctx);
+	mutex_lock(&wq->wq_lock);
 	idxd_wq_put(wq);
+	mutex_unlock(&wq->wq_lock);
 	return 0;
 }
 
diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index 8d79a878..8d2718c5 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -320,6 +320,31 @@
 	devm_iounmap(dev, wq->dportal);
 }
 
+void idxd_wq_disable_cleanup(struct idxd_wq *wq)
+{
+	struct idxd_device *idxd = wq->idxd;
+	struct device *dev = &idxd->pdev->dev;
+	int i, wq_offset;
+
+	lockdep_assert_held(&idxd->dev_lock);
+	memset(&wq->wqcfg, 0, sizeof(wq->wqcfg));
+	wq->type = IDXD_WQT_NONE;
+	wq->size = 0;
+	wq->group = NULL;
+	wq->threshold = 0;
+	wq->priority = 0;
+	clear_bit(WQ_FLAG_DEDICATED, &wq->flags);
+	memset(wq->name, 0, WQ_NAME_SIZE);
+
+	for (i = 0; i < 8; i++) {
+		wq_offset = idxd->wqcfg_offset + wq->id * 32 + i * sizeof(u32);
+		iowrite32(0, idxd->reg_base + wq_offset);
+		dev_dbg(dev, "WQ[%d][%d][%#x]: %#x\n",
+			wq->id, i, wq_offset,
+			ioread32(idxd->reg_base + wq_offset));
+	}
+}
+
 /* Device control bits */
 static inline bool idxd_is_enabled(struct idxd_device *idxd)
 {
diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h
index b8f8a36..908c8d0 100644
--- a/drivers/dma/idxd/idxd.h
+++ b/drivers/dma/idxd/idxd.h
@@ -290,6 +290,7 @@
 int idxd_wq_disable(struct idxd_wq *wq);
 int idxd_wq_map_portal(struct idxd_wq *wq);
 void idxd_wq_unmap_portal(struct idxd_wq *wq);
+void idxd_wq_disable_cleanup(struct idxd_wq *wq);
 
 /* submission */
 int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc);
diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c
index 6510791..8a35f58 100644
--- a/drivers/dma/idxd/irq.c
+++ b/drivers/dma/idxd/irq.c
@@ -141,7 +141,7 @@
 
 	iowrite32(cause, idxd->reg_base + IDXD_INTCAUSE_OFFSET);
 	if (!err)
-		return IRQ_HANDLED;
+		goto out;
 
 	gensts.bits = ioread32(idxd->reg_base + IDXD_GENSTATS_OFFSET);
 	if (gensts.state == IDXD_DEVICE_STATE_HALT) {
@@ -162,6 +162,7 @@
 		spin_unlock_bh(&idxd->dev_lock);
 	}
 
+ out:
 	idxd_unmask_msix_vector(idxd, irq_entry->id);
 	return IRQ_HANDLED;
 }
diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c
index 052dae5..2e2c5082 100644
--- a/drivers/dma/idxd/sysfs.c
+++ b/drivers/dma/idxd/sysfs.c
@@ -315,6 +315,11 @@
 		idxd_unregister_dma_device(idxd);
 		spin_lock_irqsave(&idxd->dev_lock, flags);
 		rc = idxd_device_disable(idxd);
+		for (i = 0; i < idxd->max_wqs; i++) {
+			struct idxd_wq *wq = &idxd->wqs[i];
+
+			idxd_wq_disable_cleanup(wq);
+		}
 		spin_unlock_irqrestore(&idxd->dev_lock, flags);
 		module_put(THIS_MODULE);
 		if (rc < 0)
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 9177403..270992c 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -1331,8 +1331,7 @@
 
 	sdma_channel_synchronize(chan);
 
-	if (sdmac->event_id0 >= 0)
-		sdma_event_disable(sdmac, sdmac->event_id0);
+	sdma_event_disable(sdmac, sdmac->event_id0);
 	if (sdmac->event_id1)
 		sdma_event_disable(sdmac, sdmac->event_id1);
 
@@ -1632,11 +1631,9 @@
 	memcpy(&sdmac->slave_config, dmaengine_cfg, sizeof(*dmaengine_cfg));
 
 	/* Set ENBLn earlier to make sure dma request triggered after that */
-	if (sdmac->event_id0 >= 0) {
-		if (sdmac->event_id0 >= sdmac->sdma->drvdata->num_events)
-			return -EINVAL;
-		sdma_event_enable(sdmac, sdmac->event_id0);
-	}
+	if (sdmac->event_id0 >= sdmac->sdma->drvdata->num_events)
+		return -EINVAL;
+	sdma_event_enable(sdmac, sdmac->event_id0);
 
 	if (sdmac->event_id1) {
 		if (sdmac->event_id1 >= sdmac->sdma->drvdata->num_events)
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index 8ad0ad8..fd782ae 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -26,6 +26,18 @@
 
 #include "../dmaengine.h"
 
+int completion_timeout = 200;
+module_param(completion_timeout, int, 0644);
+MODULE_PARM_DESC(completion_timeout,
+		"set ioat completion timeout [msec] (default 200 [msec])");
+int idle_timeout = 2000;
+module_param(idle_timeout, int, 0644);
+MODULE_PARM_DESC(idle_timeout,
+		"set ioat idel timeout [msec] (default 2000 [msec])");
+
+#define IDLE_TIMEOUT msecs_to_jiffies(idle_timeout)
+#define COMPLETION_TIMEOUT msecs_to_jiffies(completion_timeout)
+
 static char *chanerr_str[] = {
 	"DMA Transfer Source Address Error",
 	"DMA Transfer Destination Address Error",
diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h
index e6b622e..f7f31fd 100644
--- a/drivers/dma/ioat/dma.h
+++ b/drivers/dma/ioat/dma.h
@@ -104,8 +104,6 @@
 	#define IOAT_RUN 5
 	#define IOAT_CHAN_ACTIVE 6
 	struct timer_list timer;
-	#define COMPLETION_TIMEOUT msecs_to_jiffies(100)
-	#define IDLE_TIMEOUT msecs_to_jiffies(2000)
 	#define RESET_DELAY msecs_to_jiffies(100)
 	struct ioatdma_device *ioat_dma;
 	dma_addr_t completion_dma;
diff --git a/drivers/dma/mcf-edma.c b/drivers/dma/mcf-edma.c
index e15bd15..e12b754 100644
--- a/drivers/dma/mcf-edma.c
+++ b/drivers/dma/mcf-edma.c
@@ -35,6 +35,13 @@
 			mcf_chan = &mcf_edma->chans[ch];
 
 			spin_lock(&mcf_chan->vchan.lock);
+
+			if (!mcf_chan->edesc) {
+				/* terminate_all called before */
+				spin_unlock(&mcf_chan->vchan.lock);
+				continue;
+			}
+
 			if (!mcf_chan->edesc->iscyclic) {
 				list_del(&mcf_chan->edesc->vdesc.node);
 				vchan_cookie_complete(&mcf_chan->edesc->vdesc);
diff --git a/drivers/dma/sh/usb-dmac.c b/drivers/dma/sh/usb-dmac.c
index b218a01..8f7ceb6 100644
--- a/drivers/dma/sh/usb-dmac.c
+++ b/drivers/dma/sh/usb-dmac.c
@@ -586,6 +586,8 @@
 		desc->residue = usb_dmac_get_current_residue(chan, desc,
 							desc->sg_index - 1);
 		desc->done_cookie = desc->vd.tx.cookie;
+		desc->vd.tx_result.result = DMA_TRANS_NOERROR;
+		desc->vd.tx_result.residue = desc->residue;
 		vchan_cookie_complete(&desc->vd);
 
 		/* Restart the next transfer if this driver has a next desc */
diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c
index db58d7e..c5fa2ef 100644
--- a/drivers/dma/tegra210-adma.c
+++ b/drivers/dma/tegra210-adma.c
@@ -658,6 +658,7 @@
 
 	ret = pm_runtime_get_sync(tdc2dev(tdc));
 	if (ret < 0) {
+		pm_runtime_put_noidle(tdc2dev(tdc));
 		free_irq(tdc->irq, tdc);
 		return ret;
 	}
@@ -869,8 +870,10 @@
 	pm_runtime_enable(&pdev->dev);
 
 	ret = pm_runtime_get_sync(&pdev->dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put_noidle(&pdev->dev);
 		goto rpm_disable;
+	}
 
 	ret = tegra_adma_init(tdma);
 	if (ret)
diff --git a/drivers/dma/ti/k3-udma-private.c b/drivers/dma/ti/k3-udma-private.c
index 0b8f3dd..77e8e67 100644
--- a/drivers/dma/ti/k3-udma-private.c
+++ b/drivers/dma/ti/k3-udma-private.c
@@ -42,6 +42,7 @@
 	ud = platform_get_drvdata(pdev);
 	if (!ud) {
 		pr_debug("UDMA has not been probed\n");
+		put_device(&pdev->dev);
 		return ERR_PTR(-EPROBE_DEFER);
 	}
 
diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c
index c91e2dc..6c879a7 100644
--- a/drivers/dma/ti/k3-udma.c
+++ b/drivers/dma/ti/k3-udma.c
@@ -1753,7 +1753,8 @@
 			dev_err(ud->ddev.dev,
 				"Descriptor pool allocation failed\n");
 			uc->use_dma_pool = false;
-			return -ENOMEM;
+			ret = -ENOMEM;
+			goto err_cleanup;
 		}
 	}
 
@@ -1773,16 +1774,18 @@
 
 		ret = udma_get_chan_pair(uc);
 		if (ret)
-			return ret;
+			goto err_cleanup;
 
 		ret = udma_alloc_tx_resources(uc);
-		if (ret)
-			return ret;
+		if (ret) {
+			udma_put_rchan(uc);
+			goto err_cleanup;
+		}
 
 		ret = udma_alloc_rx_resources(uc);
 		if (ret) {
 			udma_free_tx_resources(uc);
-			return ret;
+			goto err_cleanup;
 		}
 
 		uc->config.src_thread = ud->psil_base + uc->tchan->id;
@@ -1800,10 +1803,8 @@
 			uc->id);
 
 		ret = udma_alloc_tx_resources(uc);
-		if (ret) {
-			uc->config.remote_thread_id = -1;
-			return ret;
-		}
+		if (ret)
+			goto err_cleanup;
 
 		uc->config.src_thread = ud->psil_base + uc->tchan->id;
 		uc->config.dst_thread = uc->config.remote_thread_id;
@@ -1820,10 +1821,8 @@
 			uc->id);
 
 		ret = udma_alloc_rx_resources(uc);
-		if (ret) {
-			uc->config.remote_thread_id = -1;
-			return ret;
-		}
+		if (ret)
+			goto err_cleanup;
 
 		uc->config.src_thread = uc->config.remote_thread_id;
 		uc->config.dst_thread = (ud->psil_base + uc->rchan->id) |
@@ -1838,7 +1837,9 @@
 		/* Can not happen */
 		dev_err(uc->ud->dev, "%s: chan%d invalid direction (%u)\n",
 			__func__, uc->id, uc->config.dir);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto err_cleanup;
+
 	}
 
 	/* check if the channel configuration was successful */
@@ -1847,7 +1848,7 @@
 
 	if (udma_is_chan_running(uc)) {
 		dev_warn(ud->dev, "chan%d: is running!\n", uc->id);
-		udma_stop(uc);
+		udma_reset_chan(uc, false);
 		if (udma_is_chan_running(uc)) {
 			dev_err(ud->dev, "chan%d: won't stop!\n", uc->id);
 			ret = -EBUSY;
@@ -1906,8 +1907,6 @@
 
 	udma_reset_rings(uc);
 
-	INIT_DELAYED_WORK_ONSTACK(&uc->tx_drain.work,
-				  udma_check_tx_completion);
 	return 0;
 
 err_irq_free:
@@ -1919,7 +1918,7 @@
 err_res_free:
 	udma_free_tx_resources(uc);
 	udma_free_rx_resources(uc);
-
+err_cleanup:
 	udma_reset_uchan(uc);
 
 	if (uc->use_dma_pool) {
@@ -3019,7 +3018,6 @@
 	}
 
 	cancel_delayed_work_sync(&uc->tx_drain.work);
-	destroy_delayed_work_on_stack(&uc->tx_drain.work);
 
 	if (uc->irq_num_ring > 0) {
 		free_irq(uc->irq_num_ring, uc);
@@ -3593,7 +3591,7 @@
 		return ret;
 	}
 
-	ret = of_property_read_u32(navss_node, "ti,udma-atype", &ud->atype);
+	ret = of_property_read_u32(dev->of_node, "ti,udma-atype", &ud->atype);
 	if (!ret && ud->atype > 2) {
 		dev_err(dev, "Invalid atype: %u\n", ud->atype);
 		return -EINVAL;
@@ -3711,6 +3709,7 @@
 		tasklet_init(&uc->vc.task, udma_vchan_complete,
 			     (unsigned long)&uc->vc);
 		init_completion(&uc->teardown_completed);
+		INIT_DELAYED_WORK(&uc->tx_drain.work, udma_check_tx_completion);
 	}
 
 	ret = dma_async_device_register(&ud->ddev);
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index ef90070..6262f63 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -269,6 +269,8 @@
 
 		if (pvt->model == 0x60)
 			amd64_read_pci_cfg(pvt->F2, F15H_M60H_SCRCTRL, &scrubval);
+		else
+			amd64_read_pci_cfg(pvt->F3, SCRCTRL, &scrubval);
 	} else {
 		amd64_read_pci_cfg(pvt->F3, SCRCTRL, &scrubval);
 	}
diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index e6fc022..3939699 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/drivers/firmware/efi/Kconfig
@@ -278,3 +278,14 @@
 	depends on SERIAL_EARLYCON && !ARM && !IA64
 	select FONT_SUPPORT
 	select ARCH_USE_MEMREMAP_PROT
+
+config EFI_CUSTOM_SSDT_OVERLAYS
+	bool "Load custom ACPI SSDT overlay from an EFI variable"
+	depends on EFI_VARS && ACPI
+	default ACPI_TABLE_UPGRADE
+	help
+	  Allow loading of an ACPI SSDT overlay from an EFI variable specified
+	  by a kernel command line option.
+
+	  See Documentation/admin-guide/acpi/ssdt-overlays.rst for more
+	  information.
diff --git a/drivers/firmware/efi/arm-init.c b/drivers/firmware/efi/arm-init.c
index c697e70..71c445d 100644
--- a/drivers/firmware/efi/arm-init.c
+++ b/drivers/firmware/efi/arm-init.c
@@ -52,9 +52,11 @@
 }
 
 static __initdata unsigned long screen_info_table = EFI_INVALID_TABLE_ADDR;
+static __initdata unsigned long cpu_state_table = EFI_INVALID_TABLE_ADDR;
 
 static const efi_config_table_type_t arch_tables[] __initconst = {
 	{LINUX_EFI_ARM_SCREEN_INFO_TABLE_GUID, &screen_info_table},
+	{LINUX_EFI_ARM_CPU_STATE_TABLE_GUID, &cpu_state_table},
 	{}
 };
 
@@ -62,7 +64,8 @@
 {
 	struct screen_info *si;
 
-	if (screen_info_table != EFI_INVALID_TABLE_ADDR) {
+	if (IS_ENABLED(CONFIG_ARM) &&
+	    screen_info_table != EFI_INVALID_TABLE_ADDR) {
 		si = early_memremap_ro(screen_info_table, sizeof(*si));
 		if (!si) {
 			pr_err("Could not map screen_info config table\n");
@@ -116,7 +119,8 @@
 		goto out;
 	}
 	retval = efi_config_parse_tables(config_tables, systab->nr_tables,
-					 arch_tables);
+					 IS_ENABLED(CONFIG_ARM) ? arch_tables
+								: NULL);
 
 	early_memunmap(config_tables, table_size);
 out:
@@ -238,9 +242,37 @@
 
 	init_screen_info();
 
+#ifdef CONFIG_ARM
 	/* ARM does not permit early mappings to persist across paging_init() */
-	if (IS_ENABLED(CONFIG_ARM))
-		efi_memmap_unmap();
+	efi_memmap_unmap();
+
+	if (cpu_state_table != EFI_INVALID_TABLE_ADDR) {
+		struct efi_arm_entry_state *state;
+		bool dump_state = true;
+
+		state = early_memremap_ro(cpu_state_table,
+					  sizeof(struct efi_arm_entry_state));
+		if (state == NULL) {
+			pr_warn("Unable to map CPU entry state table.\n");
+			return;
+		}
+
+		if ((state->sctlr_before_ebs & 1) == 0)
+			pr_warn(FW_BUG "EFI stub was entered with MMU and Dcache disabled, please fix your firmware!\n");
+		else if ((state->sctlr_after_ebs & 1) == 0)
+			pr_warn(FW_BUG "ExitBootServices() returned with MMU and Dcache disabled, please fix your firmware!\n");
+		else
+			dump_state = false;
+
+		if (dump_state || efi_enabled(EFI_DBG)) {
+			pr_info("CPSR at EFI stub entry        : 0x%08x\n", state->cpsr_before_ebs);
+			pr_info("SCTLR at EFI stub entry       : 0x%08x\n", state->sctlr_before_ebs);
+			pr_info("CPSR after ExitBootServices() : 0x%08x\n", state->cpsr_after_ebs);
+			pr_info("SCTLR after ExitBootServices(): 0x%08x\n", state->sctlr_after_ebs);
+		}
+		early_memunmap(state, sizeof(struct efi_arm_entry_state));
+	}
+#endif
 }
 
 static bool efifb_overlaps_pci_range(const struct of_pci_range *range)
diff --git a/drivers/firmware/efi/efi-pstore.c b/drivers/firmware/efi/efi-pstore.c
index c2f1d4e..feb7fe6 100644
--- a/drivers/firmware/efi/efi-pstore.c
+++ b/drivers/firmware/efi/efi-pstore.c
@@ -356,10 +356,7 @@
 
 static __init int efivars_pstore_init(void)
 {
-	if (!efi_rt_services_supported(EFI_RT_SUPPORTED_VARIABLE_SERVICES))
-		return 0;
-
-	if (!efivars_kobject())
+	if (!efivars_kobject() || !efivar_supports_writes())
 		return 0;
 
 	if (efivars_pstore_disable)
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 7f1657b..fdd1db0 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -176,11 +176,13 @@
 static int generic_ops_register(void)
 {
 	generic_ops.get_variable = efi.get_variable;
-	generic_ops.set_variable = efi.set_variable;
-	generic_ops.set_variable_nonblocking = efi.set_variable_nonblocking;
 	generic_ops.get_next_variable = efi.get_next_variable;
 	generic_ops.query_variable_store = efi_query_variable_store;
 
+	if (efi_rt_services_supported(EFI_RT_SUPPORTED_SET_VARIABLE)) {
+		generic_ops.set_variable = efi.set_variable;
+		generic_ops.set_variable_nonblocking = efi.set_variable_nonblocking;
+	}
 	return efivars_register(&generic_efivars, &generic_ops, efi_kobj);
 }
 
@@ -189,7 +191,7 @@
 	efivars_unregister(&generic_efivars);
 }
 
-#if IS_ENABLED(CONFIG_ACPI)
+#ifdef CONFIG_EFI_CUSTOM_SSDT_OVERLAYS
 #define EFIVAR_SSDT_NAME_MAX	16
 static char efivar_ssdt[EFIVAR_SSDT_NAME_MAX] __initdata;
 static int __init efivar_ssdt_setup(char *str)
@@ -382,7 +384,8 @@
 		return -ENOMEM;
 	}
 
-	if (efi_rt_services_supported(EFI_RT_SUPPORTED_VARIABLE_SERVICES)) {
+	if (efi_rt_services_supported(EFI_RT_SUPPORTED_GET_VARIABLE |
+				      EFI_RT_SUPPORTED_GET_NEXT_VARIABLE_NAME)) {
 		efivar_ssdt_load();
 		error = generic_ops_register();
 		if (error)
@@ -416,7 +419,8 @@
 err_remove_group:
 	sysfs_remove_group(efi_kobj, &efi_subsys_attr_group);
 err_unregister:
-	if (efi_rt_services_supported(EFI_RT_SUPPORTED_VARIABLE_SERVICES))
+	if (efi_rt_services_supported(EFI_RT_SUPPORTED_GET_VARIABLE |
+				      EFI_RT_SUPPORTED_GET_NEXT_VARIABLE_NAME))
 		generic_ops_unregister();
 err_put:
 	kobject_put(efi_kobj);
@@ -622,7 +626,8 @@
 			rsv = (void *)(p + prsv % PAGE_SIZE);
 
 			/* reserve the entry itself */
-			memblock_reserve(prsv, EFI_MEMRESERVE_SIZE(rsv->size));
+			memblock_reserve(prsv,
+					 struct_size(rsv, entry, rsv->size));
 
 			for (i = 0; i < atomic_read(&rsv->count); i++) {
 				memblock_reserve(rsv->entry[i].base,
diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c
index 26528a4..dcea137 100644
--- a/drivers/firmware/efi/efivars.c
+++ b/drivers/firmware/efi/efivars.c
@@ -680,11 +680,8 @@
 	struct kobject *parent_kobj = efivars_kobject();
 	int error = 0;
 
-	if (!efi_rt_services_supported(EFI_RT_SUPPORTED_VARIABLE_SERVICES))
-		return -ENODEV;
-
 	/* No efivars has been registered yet */
-	if (!parent_kobj)
+	if (!parent_kobj || !efivar_supports_writes())
 		return 0;
 
 	printk(KERN_INFO "EFI Variables Facility v%s %s\n", EFIVARS_VERSION,
diff --git a/drivers/firmware/efi/esrt.c b/drivers/firmware/efi/esrt.c
index e3d6926..d591527 100644
--- a/drivers/firmware/efi/esrt.c
+++ b/drivers/firmware/efi/esrt.c
@@ -181,7 +181,7 @@
 		rc = kobject_init_and_add(&entry->kobj, &esre1_ktype, NULL,
 					  "entry%d", entry_num);
 		if (rc) {
-			kfree(entry);
+			kobject_put(&entry->kobj);
 			return rc;
 		}
 	}
diff --git a/drivers/firmware/efi/libstub/alignedmem.c b/drivers/firmware/efi/libstub/alignedmem.c
index cc89c4d..1de9878 100644
--- a/drivers/firmware/efi/libstub/alignedmem.c
+++ b/drivers/firmware/efi/libstub/alignedmem.c
@@ -44,7 +44,7 @@
 	*addr = ALIGN((unsigned long)alloc_addr, align);
 
 	if (slack > 0) {
-		int l = (alloc_addr % align) / EFI_PAGE_SIZE;
+		int l = (alloc_addr & (align - 1)) / EFI_PAGE_SIZE;
 
 		if (l) {
 			efi_bs_call(free_pages, alloc_addr, slack - l + 1);
diff --git a/drivers/firmware/efi/libstub/arm32-stub.c b/drivers/firmware/efi/libstub/arm32-stub.c
index 40243f5..d08e5d5 100644
--- a/drivers/firmware/efi/libstub/arm32-stub.c
+++ b/drivers/firmware/efi/libstub/arm32-stub.c
@@ -7,10 +7,49 @@
 
 #include "efistub.h"
 
+static efi_guid_t cpu_state_guid = LINUX_EFI_ARM_CPU_STATE_TABLE_GUID;
+
+struct efi_arm_entry_state *efi_entry_state;
+
+static void get_cpu_state(u32 *cpsr, u32 *sctlr)
+{
+	asm("mrs %0, cpsr" : "=r"(*cpsr));
+	if ((*cpsr & MODE_MASK) == HYP_MODE)
+		asm("mrc p15, 4, %0, c1, c0, 0" : "=r"(*sctlr));
+	else
+		asm("mrc p15, 0, %0, c1, c0, 0" : "=r"(*sctlr));
+}
+
 efi_status_t check_platform_features(void)
 {
+	efi_status_t status;
+	u32 cpsr, sctlr;
 	int block;
 
+	get_cpu_state(&cpsr, &sctlr);
+
+	efi_info("Entering in %s mode with MMU %sabled\n",
+		 ((cpsr & MODE_MASK) == HYP_MODE) ? "HYP" : "SVC",
+		 (sctlr & 1) ? "en" : "dis");
+
+	status = efi_bs_call(allocate_pool, EFI_LOADER_DATA,
+			     sizeof(*efi_entry_state),
+			     (void **)&efi_entry_state);
+	if (status != EFI_SUCCESS) {
+		efi_err("allocate_pool() failed\n");
+		return status;
+	}
+
+	efi_entry_state->cpsr_before_ebs = cpsr;
+	efi_entry_state->sctlr_before_ebs = sctlr;
+
+	status = efi_bs_call(install_configuration_table, &cpu_state_guid,
+			     efi_entry_state);
+	if (status != EFI_SUCCESS) {
+		efi_err("install_configuration_table() failed\n");
+		goto free_state;
+	}
+
 	/* non-LPAE kernels can run anywhere */
 	if (!IS_ENABLED(CONFIG_ARM_LPAE))
 		return EFI_SUCCESS;
@@ -19,9 +58,22 @@
 	block = cpuid_feature_extract(CPUID_EXT_MMFR0, 0);
 	if (block < 5) {
 		efi_err("This LPAE kernel is not supported by your CPU\n");
-		return EFI_UNSUPPORTED;
+		status = EFI_UNSUPPORTED;
+		goto drop_table;
 	}
 	return EFI_SUCCESS;
+
+drop_table:
+	efi_bs_call(install_configuration_table, &cpu_state_guid, NULL);
+free_state:
+	efi_bs_call(free_pool, efi_entry_state);
+	return status;
+}
+
+void efi_handle_post_ebs_state(void)
+{
+	get_cpu_state(&efi_entry_state->cpsr_after_ebs,
+		      &efi_entry_state->sctlr_after_ebs);
 }
 
 static efi_guid_t screen_info_guid = LINUX_EFI_ARM_SCREEN_INFO_TABLE_GUID;
diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c
index 7f6a57d..e5bfac7 100644
--- a/drivers/firmware/efi/libstub/arm64-stub.c
+++ b/drivers/firmware/efi/libstub/arm64-stub.c
@@ -35,13 +35,16 @@
 }
 
 /*
- * Relocatable kernels can fix up the misalignment with respect to
- * MIN_KIMG_ALIGN, so they only require a minimum alignment of EFI_KIMG_ALIGN
- * (which accounts for the alignment of statically allocated objects such as
- * the swapper stack.)
+ * Although relocatable kernels can fix up the misalignment with respect to
+ * MIN_KIMG_ALIGN, the resulting virtual text addresses are subtly out of
+ * sync with those recorded in the vmlinux when kaslr is disabled but the
+ * image required relocation anyway. Therefore retain 2M alignment unless
+ * KASLR is in use.
  */
-static const u64 min_kimg_align = IS_ENABLED(CONFIG_RELOCATABLE) ? EFI_KIMG_ALIGN
-								 : MIN_KIMG_ALIGN;
+static u64 min_kimg_align(void)
+{
+	return efi_nokaslr ? MIN_KIMG_ALIGN : EFI_KIMG_ALIGN;
+}
 
 efi_status_t handle_kernel_image(unsigned long *image_addr,
 				 unsigned long *image_size,
@@ -74,21 +77,21 @@
 
 	kernel_size = _edata - _text;
 	kernel_memsize = kernel_size + (_end - _edata);
-	*reserve_size = kernel_memsize + TEXT_OFFSET % min_kimg_align;
+	*reserve_size = kernel_memsize + TEXT_OFFSET % min_kimg_align();
 
 	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && phys_seed != 0) {
 		/*
 		 * If KASLR is enabled, and we have some randomness available,
 		 * locate the kernel at a randomized offset in physical memory.
 		 */
-		status = efi_random_alloc(*reserve_size, min_kimg_align,
+		status = efi_random_alloc(*reserve_size, min_kimg_align(),
 					  reserve_addr, phys_seed);
 	} else {
 		status = EFI_OUT_OF_RESOURCES;
 	}
 
 	if (status != EFI_SUCCESS) {
-		if (IS_ALIGNED((u64)_text - TEXT_OFFSET, min_kimg_align)) {
+		if (IS_ALIGNED((u64)_text - TEXT_OFFSET, min_kimg_align())) {
 			/*
 			 * Just execute from wherever we were loaded by the
 			 * UEFI PE/COFF loader if the alignment is suitable.
@@ -99,7 +102,7 @@
 		}
 
 		status = efi_allocate_pages_aligned(*reserve_size, reserve_addr,
-						    ULONG_MAX, min_kimg_align);
+						    ULONG_MAX, min_kimg_align());
 
 		if (status != EFI_SUCCESS) {
 			efi_err("Failed to relocate kernel\n");
@@ -108,7 +111,7 @@
 		}
 	}
 
-	*image_addr = *reserve_addr + TEXT_OFFSET % min_kimg_align;
+	*image_addr = *reserve_addr + TEXT_OFFSET % min_kimg_align();
 	memcpy((void *)*image_addr, _text, kernel_size);
 
 	return EFI_SUCCESS;
diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index 89f0752..6bca70b 100644
--- a/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -19,7 +19,7 @@
 #include "efistub.h"
 
 bool efi_nochunk;
-bool efi_nokaslr;
+bool efi_nokaslr = !IS_ENABLED(CONFIG_RANDOMIZE_BASE);
 bool efi_noinitrd;
 int efi_loglevel = CONSOLE_LOGLEVEL_DEFAULT;
 bool efi_novamap;
@@ -32,6 +32,10 @@
 	return !efi_nosoftreserve;
 }
 
+/**
+ * efi_char16_puts() - Write a UCS-2 encoded string to the console
+ * @str:	UCS-2 encoded string
+ */
 void efi_char16_puts(efi_char16_t *str)
 {
 	efi_call_proto(efi_table_attr(efi_system_table, con_out),
@@ -83,6 +87,10 @@
 	return c32;
 }
 
+/**
+ * efi_puts() - Write a UTF-8 encoded string to the console
+ * @str:	UTF-8 encoded string
+ */
 void efi_puts(const char *str)
 {
 	efi_char16_t buf[128];
@@ -113,6 +121,16 @@
 	}
 }
 
+/**
+ * efi_printk() - Print a kernel message
+ * @fmt:	format string
+ *
+ * The first letter of the format string is used to determine the logging level
+ * of the message. If the level is less then the current EFI logging level, the
+ * message is suppressed. The message will be truncated to 255 bytes.
+ *
+ * Return:	number of printed characters
+ */
 int efi_printk(const char *fmt, ...)
 {
 	char printf_buf[256];
@@ -154,13 +172,18 @@
 	return printed;
 }
 
-/*
- * Parse the ASCII string 'cmdline' for EFI options, denoted by the efi=
+/**
+ * efi_parse_options() - Parse EFI command line options
+ * @cmdline:	kernel command line
+ *
+ * Parse the ASCII string @cmdline for EFI options, denoted by the efi=
  * option, e.g. efi=nochunk.
  *
  * It should be noted that efi= is parsed in two very different
  * environments, first in the early boot environment of the EFI boot
  * stub, and subsequently during the kernel boot.
+ *
+ * Return:	status code
  */
 efi_status_t efi_parse_options(char const *cmdline)
 {
@@ -286,13 +309,21 @@
 	return (char *)cmdline_addr;
 }
 
-/*
+/**
+ * efi_exit_boot_services() - Exit boot services
+ * @handle:	handle of the exiting image
+ * @map:	pointer to receive the memory map
+ * @priv:	argument to be passed to @priv_func
+ * @priv_func:	function to process the memory map before exiting boot services
+ *
  * Handle calling ExitBootServices according to the requirements set out by the
  * spec.  Obtains the current memory map, and returns that info after calling
  * ExitBootServices.  The client must specify a function to perform any
  * processing of the memory map data prior to ExitBootServices.  A client
  * specific structure may be passed to the function via priv.  The client
  * function may be called multiple times.
+ *
+ * Return:	status code
  */
 efi_status_t efi_exit_boot_services(void *handle,
 				    struct efi_boot_memmap *map,
@@ -361,6 +392,11 @@
 	return status;
 }
 
+/**
+ * get_efi_config_table() - retrieve UEFI configuration table
+ * @guid:	GUID of the configuration table to be retrieved
+ * Return:	pointer to the configuration table or NULL
+ */
 void *get_efi_config_table(efi_guid_t guid)
 {
 	unsigned long tables = efi_table_attr(efi_system_table, tables);
@@ -408,17 +444,18 @@
 };
 
 /**
- * efi_load_initrd_dev_path - load the initrd from the Linux initrd device path
+ * efi_load_initrd_dev_path() - load the initrd from the Linux initrd device path
  * @load_addr:	pointer to store the address where the initrd was loaded
  * @load_size:	pointer to store the size of the loaded initrd
  * @max:	upper limit for the initrd memory allocation
- * @return:	%EFI_SUCCESS if the initrd was loaded successfully, in which
- *		case @load_addr and @load_size are assigned accordingly
- *		%EFI_NOT_FOUND if no LoadFile2 protocol exists on the initrd
- *		device path
- *		%EFI_INVALID_PARAMETER if load_addr == NULL or load_size == NULL
- *		%EFI_OUT_OF_RESOURCES if memory allocation failed
- *		%EFI_LOAD_ERROR in all other cases
+ *
+ * Return:
+ * * %EFI_SUCCESS if the initrd was loaded successfully, in which
+ *   case @load_addr and @load_size are assigned accordingly
+ * * %EFI_NOT_FOUND if no LoadFile2 protocol exists on the initrd device path
+ * * %EFI_INVALID_PARAMETER if load_addr == NULL or load_size == NULL
+ * * %EFI_OUT_OF_RESOURCES if memory allocation failed
+ * * %EFI_LOAD_ERROR in all other cases
  */
 static
 efi_status_t efi_load_initrd_dev_path(unsigned long *load_addr,
@@ -481,6 +518,16 @@
 				    load_addr, load_size);
 }
 
+/**
+ * efi_load_initrd() - Load initial RAM disk
+ * @image:	EFI loaded image protocol
+ * @load_addr:	pointer to loaded initrd
+ * @load_size:	size of loaded initrd
+ * @soft_limit:	preferred size of allocated memory for loading the initrd
+ * @hard_limit:	minimum size of allocated memory
+ *
+ * Return:	status code
+ */
 efi_status_t efi_load_initrd(efi_loaded_image_t *image,
 			     unsigned long *load_addr,
 			     unsigned long *load_size,
@@ -505,6 +552,15 @@
 	return status;
 }
 
+/**
+ * efi_wait_for_key() - Wait for key stroke
+ * @usec:	number of microseconds to wait for key stroke
+ * @key:	key entered
+ *
+ * Wait for up to @usec microseconds for a key stroke.
+ *
+ * Return:	status code, EFI_SUCCESS if key received
+ */
 efi_status_t efi_wait_for_key(unsigned long usec, efi_input_key_t *key)
 {
 	efi_event_t events[2], timer;
diff --git a/drivers/firmware/efi/libstub/efi-stub.c b/drivers/firmware/efi/libstub/efi-stub.c
index e97370b..a5a405d 100644
--- a/drivers/firmware/efi/libstub/efi-stub.c
+++ b/drivers/firmware/efi/libstub/efi-stub.c
@@ -122,23 +122,6 @@
 }
 
 /*
- * This function handles the architcture specific differences between arm and
- * arm64 regarding where the kernel image must be loaded and any memory that
- * must be reserved. On failure it is required to free all
- * all allocations it has made.
- */
-efi_status_t handle_kernel_image(unsigned long *image_addr,
-				 unsigned long *image_size,
-				 unsigned long *reserve_addr,
-				 unsigned long *reserve_size,
-				 unsigned long dram_base,
-				 efi_loaded_image_t *image);
-
-asmlinkage void __noreturn efi_enter_kernel(unsigned long entrypoint,
-					    unsigned long fdt_addr,
-					    unsigned long fdt_size);
-
-/*
  * EFI entry point for the arm/arm64 EFI stubs.  This is the entrypoint
  * that is described in the PE/COFF header.  Most of the code is the same
  * for both archictectures, with the arch-specific code provided in the
@@ -329,6 +312,9 @@
 	if (status != EFI_SUCCESS)
 		goto fail_free_initrd;
 
+	if (IS_ENABLED(CONFIG_ARM))
+		efi_handle_post_ebs_state();
+
 	efi_enter_kernel(image_addr, fdt_addr, fdt_totalsize((void *)fdt_addr));
 	/* not reached */
 
diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h
index bcd8c0a..85050f5 100644
--- a/drivers/firmware/efi/libstub/efistub.h
+++ b/drivers/firmware/efi/libstub/efistub.h
@@ -157,8 +157,14 @@
 #define EFI_EVT_NOTIFY_WAIT	0x00000100U
 #define EFI_EVT_NOTIFY_SIGNAL	0x00000200U
 
-/*
- * boottime->wait_for_event takes an array of events as input.
+/**
+ * efi_set_event_at() - add event to events array
+ *
+ * @events:	array of UEFI events
+ * @ids:	index where to put the event in the array
+ * @event:	event to add to the aray
+ *
+ * boottime->wait_for_event() takes an array of events as input.
  * Provide a helper to set it up correctly for mixed mode.
  */
 static inline
@@ -770,5 +776,23 @@
 			     unsigned long *load_size,
 			     unsigned long soft_limit,
 			     unsigned long hard_limit);
+/*
+ * This function handles the architcture specific differences between arm and
+ * arm64 regarding where the kernel image must be loaded and any memory that
+ * must be reserved. On failure it is required to free all
+ * all allocations it has made.
+ */
+efi_status_t handle_kernel_image(unsigned long *image_addr,
+				 unsigned long *image_size,
+				 unsigned long *reserve_addr,
+				 unsigned long *reserve_size,
+				 unsigned long dram_base,
+				 efi_loaded_image_t *image);
+
+asmlinkage void __noreturn efi_enter_kernel(unsigned long entrypoint,
+					    unsigned long fdt_addr,
+					    unsigned long fdt_size);
+
+void efi_handle_post_ebs_state(void);
 
 #endif
diff --git a/drivers/firmware/efi/libstub/file.c b/drivers/firmware/efi/libstub/file.c
index 2005e33..630caa6 100644
--- a/drivers/firmware/efi/libstub/file.c
+++ b/drivers/firmware/efi/libstub/file.c
@@ -102,12 +102,20 @@
 	if (!found)
 		return 0;
 
+	/* Skip any leading slashes */
+	while (cmdline[i] == L'/' || cmdline[i] == L'\\')
+		i++;
+
 	while (--result_len > 0 && i < cmdline_len) {
-		if (cmdline[i] == L'\0' ||
-		    cmdline[i] == L'\n' ||
-		    cmdline[i] == L' ')
+		efi_char16_t c = cmdline[i++];
+
+		if (c == L'\0' || c == L'\n' || c == L' ')
 			break;
-		*result++ = cmdline[i++];
+		else if (c == L'/')
+			/* Replace UNIX dir separators with EFI standard ones */
+			*result++ = L'\\';
+		else
+			*result++ = c;
 	}
 	*result = L'\0';
 	return i;
diff --git a/drivers/firmware/efi/libstub/skip_spaces.c b/drivers/firmware/efi/libstub/skip_spaces.c
index a700b3c..159fb4e 100644
--- a/drivers/firmware/efi/libstub/skip_spaces.c
+++ b/drivers/firmware/efi/libstub/skip_spaces.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
 #include <linux/ctype.h>
+#include <linux/string.h>
 #include <linux/types.h>
 
 char *skip_spaces(const char *str)
diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c
index 5a48d99..3672539 100644
--- a/drivers/firmware/efi/libstub/x86-stub.c
+++ b/drivers/firmware/efi/libstub/x86-stub.c
@@ -8,6 +8,7 @@
 
 #include <linux/efi.h>
 #include <linux/pci.h>
+#include <linux/stddef.h>
 
 #include <asm/efi.h>
 #include <asm/e820/types.h>
@@ -361,8 +362,6 @@
 	int options_size = 0;
 	efi_status_t status;
 	char *cmdline_ptr;
-	unsigned long ramdisk_addr;
-	unsigned long ramdisk_size;
 
 	efi_system_table = sys_table_arg;
 
@@ -390,8 +389,9 @@
 
 	hdr = &boot_params->hdr;
 
-	/* Copy the second sector to boot_params */
-	memcpy(&hdr->jump, image_base + 512, 512);
+	/* Copy the setup header from the second sector to boot_params */
+	memcpy(&hdr->jump, image_base + 512,
+	       sizeof(struct setup_header) - offsetof(struct setup_header, jump));
 
 	/*
 	 * Fill out some of the header fields ourselves because the
diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c
index 5f2a4d1..973eef2 100644
--- a/drivers/firmware/efi/vars.c
+++ b/drivers/firmware/efi/vars.c
@@ -1229,3 +1229,9 @@
 	return rv;
 }
 EXPORT_SYMBOL_GPL(efivars_unregister);
+
+int efivar_supports_writes(void)
+{
+	return __efivars && __efivars->ops->set_variable;
+}
+EXPORT_SYMBOL_GPL(efivar_supports_writes);
diff --git a/drivers/firmware/psci/psci_checker.c b/drivers/firmware/psci/psci_checker.c
index 873841a..3d6ba42 100644
--- a/drivers/firmware/psci/psci_checker.c
+++ b/drivers/firmware/psci/psci_checker.c
@@ -157,8 +157,10 @@
 
 	cpu_groups = kcalloc(nb_available_cpus, sizeof(cpu_groups),
 			     GFP_KERNEL);
-	if (!cpu_groups)
+	if (!cpu_groups) {
+		free_cpumask_var(tmp);
 		return -ENOMEM;
+	}
 
 	cpumask_copy(tmp, cpu_online_mask);
 
@@ -167,6 +169,7 @@
 			topology_core_cpumask(cpumask_any(tmp));
 
 		if (!alloc_cpumask_var(&cpu_groups[num_groups], GFP_KERNEL)) {
+			free_cpumask_var(tmp);
 			free_cpu_groups(num_groups, &cpu_groups);
 			return -ENOMEM;
 		}
@@ -196,13 +199,12 @@
 	if (!page_buf)
 		goto out_free_cpu_groups;
 
-	err = 0;
 	/*
 	 * Of course the last CPU cannot be powered down and cpu_down() should
 	 * refuse doing that.
 	 */
 	pr_info("Trying to turn off and on again all CPUs\n");
-	err += down_and_up_cpus(cpu_online_mask, offlined_cpus);
+	err = down_and_up_cpus(cpu_online_mask, offlined_cpus);
 
 	/*
 	 * Take down CPUs by cpu group this time. When the last CPU is turned
diff --git a/drivers/firmware/qemu_fw_cfg.c b/drivers/firmware/qemu_fw_cfg.c
index 039e0f9..6945c3c 100644
--- a/drivers/firmware/qemu_fw_cfg.c
+++ b/drivers/firmware/qemu_fw_cfg.c
@@ -605,8 +605,10 @@
 	/* register entry under "/sys/firmware/qemu_fw_cfg/by_key/" */
 	err = kobject_init_and_add(&entry->kobj, &fw_cfg_sysfs_entry_ktype,
 				   fw_cfg_sel_ko, "%d", entry->select);
-	if (err)
-		goto err_register;
+	if (err) {
+		kobject_put(&entry->kobj);
+		return err;
+	}
 
 	/* add raw binary content access */
 	err = sysfs_create_bin_file(&entry->kobj, &fw_cfg_sysfs_attr_raw);
@@ -622,7 +624,6 @@
 
 err_add_raw:
 	kobject_del(&entry->kobj);
-err_register:
 	kfree(entry);
 	return err;
 }
diff --git a/drivers/firmware/raspberrypi.c b/drivers/firmware/raspberrypi.c
index ef80988..625c8fd 100644
--- a/drivers/firmware/raspberrypi.c
+++ b/drivers/firmware/raspberrypi.c
@@ -181,6 +181,7 @@
 static void
 rpi_firmware_print_firmware_revision(struct rpi_firmware *fw)
 {
+	time64_t date_and_time;
 	u32 packet;
 	int ret = rpi_firmware_property(fw,
 					RPI_FIRMWARE_GET_FIRMWARE_REVISION,
@@ -189,7 +190,9 @@
 	if (ret)
 		return;
 
-	dev_info(fw->cl.dev, "Attached to firmware from %ptT\n", &packet);
+	/* This is not compatible with y2038 */
+	date_and_time = packet;
+	dev_info(fw->cl.dev, "Attached to firmware from %ptT\n", &date_and_time);
 }
 
 static void
diff --git a/drivers/fpga/Kconfig b/drivers/fpga/Kconfig
index b2408a7..7cd5a29 100644
--- a/drivers/fpga/Kconfig
+++ b/drivers/fpga/Kconfig
@@ -208,7 +208,7 @@
 
 config FPGA_MGR_ZYNQMP_FPGA
 	tristate "Xilinx ZynqMP FPGA"
-	depends on ARCH_ZYNQMP || COMPILE_TEST
+	depends on ZYNQMP_FIRMWARE || (!ZYNQMP_FIRMWARE && COMPILE_TEST)
 	help
 	  FPGA manager driver support for Xilinx ZynqMP FPGAs.
 	  This driver uses the processor configuration port(PCAP)
diff --git a/drivers/fpga/dfl-afu-main.c b/drivers/fpga/dfl-afu-main.c
index b0c3178..3fa2c59 100644
--- a/drivers/fpga/dfl-afu-main.c
+++ b/drivers/fpga/dfl-afu-main.c
@@ -83,7 +83,8 @@
 	 * on this port and minimum soft reset pulse width has elapsed.
 	 * Driver polls port_soft_reset_ack to determine if reset done by HW.
 	 */
-	if (readq_poll_timeout(base + PORT_HDR_CTRL, v, v & PORT_CTRL_SFTRST,
+	if (readq_poll_timeout(base + PORT_HDR_CTRL, v,
+			       v & PORT_CTRL_SFTRST_ACK,
 			       RST_POLL_INVL, RST_POLL_TIMEOUT)) {
 		dev_err(&pdev->dev, "timeout, fail to reset device\n");
 		return -ETIMEDOUT;
diff --git a/drivers/fpga/dfl-pci.c b/drivers/fpga/dfl-pci.c
index 5387550..a78c409 100644
--- a/drivers/fpga/dfl-pci.c
+++ b/drivers/fpga/dfl-pci.c
@@ -227,7 +227,6 @@
 {
 	struct cci_drvdata *drvdata = pci_get_drvdata(pcidev);
 	struct dfl_fpga_cdev *cdev = drvdata->cdev;
-	int ret = 0;
 
 	if (!num_vfs) {
 		/*
@@ -239,6 +238,8 @@
 		dfl_fpga_cdev_config_ports_pf(cdev);
 
 	} else {
+		int ret;
+
 		/*
 		 * before enable SRIOV, put released ports into VF access mode
 		 * first of all.
diff --git a/drivers/gpio/gpio-arizona.c b/drivers/gpio/gpio-arizona.c
index 5640efe..5bda38e 100644
--- a/drivers/gpio/gpio-arizona.c
+++ b/drivers/gpio/gpio-arizona.c
@@ -64,6 +64,7 @@
 		ret = pm_runtime_get_sync(chip->parent);
 		if (ret < 0) {
 			dev_err(chip->parent, "Failed to resume: %d\n", ret);
+			pm_runtime_put_autosuspend(chip->parent);
 			return ret;
 		}
 
@@ -72,12 +73,15 @@
 		if (ret < 0) {
 			dev_err(chip->parent, "Failed to drop cache: %d\n",
 				ret);
+			pm_runtime_put_autosuspend(chip->parent);
 			return ret;
 		}
 
 		ret = regmap_read(arizona->regmap, reg, &val);
-		if (ret < 0)
+		if (ret < 0) {
+			pm_runtime_put_autosuspend(chip->parent);
 			return ret;
+		}
 
 		pm_runtime_mark_last_busy(chip->parent);
 		pm_runtime_put_autosuspend(chip->parent);
@@ -106,6 +110,7 @@
 		ret = pm_runtime_get_sync(chip->parent);
 		if (ret < 0) {
 			dev_err(chip->parent, "Failed to resume: %d\n", ret);
+			pm_runtime_put(chip->parent);
 			return ret;
 		}
 	}
diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c
index 1fca8dd..a3b9bde 100644
--- a/drivers/gpio/gpio-pca953x.c
+++ b/drivers/gpio/gpio-pca953x.c
@@ -107,6 +107,84 @@
 };
 MODULE_DEVICE_TABLE(i2c, pca953x_id);
 
+#ifdef CONFIG_GPIO_PCA953X_IRQ
+
+#include <linux/dmi.h>
+#include <linux/gpio.h>
+#include <linux/list.h>
+
+static const struct dmi_system_id pca953x_dmi_acpi_irq_info[] = {
+	{
+		/*
+		 * On Intel Galileo Gen 2 board the IRQ pin of one of
+		 * the I²C GPIO expanders, which has GpioInt() resource,
+		 * is provided as an absolute number instead of being
+		 * relative. Since first controller (gpio-sch.c) and
+		 * second (gpio-dwapb.c) are at the fixed bases, we may
+		 * safely refer to the number in the global space to get
+		 * an IRQ out of it.
+		 */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_BOARD_NAME, "GalileoGen2"),
+		},
+	},
+	{}
+};
+
+#ifdef CONFIG_ACPI
+static int pca953x_acpi_get_pin(struct acpi_resource *ares, void *data)
+{
+	struct acpi_resource_gpio *agpio;
+	int *pin = data;
+
+	if (acpi_gpio_get_irq_resource(ares, &agpio))
+		*pin = agpio->pin_table[0];
+	return 1;
+}
+
+static int pca953x_acpi_find_pin(struct device *dev)
+{
+	struct acpi_device *adev = ACPI_COMPANION(dev);
+	int pin = -ENOENT, ret;
+	LIST_HEAD(r);
+
+	ret = acpi_dev_get_resources(adev, &r, pca953x_acpi_get_pin, &pin);
+	acpi_dev_free_resource_list(&r);
+	if (ret < 0)
+		return ret;
+
+	return pin;
+}
+#else
+static inline int pca953x_acpi_find_pin(struct device *dev) { return -ENXIO; }
+#endif
+
+static int pca953x_acpi_get_irq(struct device *dev)
+{
+	int pin, ret;
+
+	pin = pca953x_acpi_find_pin(dev);
+	if (pin < 0)
+		return pin;
+
+	dev_info(dev, "Applying ACPI interrupt quirk (GPIO %d)\n", pin);
+
+	if (!gpio_is_valid(pin))
+		return -EINVAL;
+
+	ret = gpio_request(pin, "pca953x interrupt");
+	if (ret)
+		return ret;
+
+	ret = gpio_to_irq(pin);
+
+	/* When pin is used as an IRQ, no need to keep it requested */
+	gpio_free(pin);
+
+	return ret;
+}
+#endif
+
 static const struct acpi_device_id pca953x_acpi_ids[] = {
 	{ "INT3491", 16 | PCA953X_TYPE | PCA_LATCH_INT, },
 	{ }
@@ -322,6 +400,7 @@
 	.writeable_reg = pca953x_writeable_register,
 	.volatile_reg = pca953x_volatile_register,
 
+	.disable_locking = true,
 	.cache_type = REGCACHE_RBTREE,
 	.max_register = 0x7f,
 };
@@ -623,8 +702,6 @@
 	DECLARE_BITMAP(reg_direction, MAX_LINE);
 	int level;
 
-	pca953x_read_regs(chip, chip->regs->direction, reg_direction);
-
 	if (chip->driver_data & PCA_PCAL) {
 		/* Enable latch on interrupt-enabled inputs */
 		pca953x_write_regs(chip, PCAL953X_IN_LATCH, chip->irq_mask);
@@ -635,7 +712,11 @@
 		pca953x_write_regs(chip, PCAL953X_INT_MASK, irq_mask);
 	}
 
+	/* Switch direction to input if needed */
+	pca953x_read_regs(chip, chip->regs->direction, reg_direction);
+
 	bitmap_or(irq_mask, chip->irq_trig_fall, chip->irq_trig_raise, gc->ngpio);
+	bitmap_complement(reg_direction, reg_direction, gc->ngpio);
 	bitmap_and(irq_mask, irq_mask, reg_direction, gc->ngpio);
 
 	/* Look for any newly setup interrupt */
@@ -734,14 +815,16 @@
 	struct gpio_chip *gc = &chip->gpio_chip;
 	DECLARE_BITMAP(pending, MAX_LINE);
 	int level;
+	bool ret;
 
-	if (!pca953x_irq_pending(chip, pending))
-		return IRQ_NONE;
+	mutex_lock(&chip->i2c_lock);
+	ret = pca953x_irq_pending(chip, pending);
+	mutex_unlock(&chip->i2c_lock);
 
 	for_each_set_bit(level, pending, gc->ngpio)
 		handle_nested_irq(irq_find_mapping(gc->irq.domain, level));
 
-	return IRQ_HANDLED;
+	return IRQ_RETVAL(ret);
 }
 
 static int pca953x_irq_setup(struct pca953x_chip *chip, int irq_base)
@@ -752,6 +835,12 @@
 	DECLARE_BITMAP(irq_stat, MAX_LINE);
 	int ret;
 
+	if (dmi_first_match(pca953x_dmi_acpi_irq_info)) {
+		ret = pca953x_acpi_get_irq(&client->dev);
+		if (ret > 0)
+			client->irq = ret;
+	}
+
 	if (!client->irq)
 		return 0;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
index 58f9d8c..44f9276 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
@@ -204,6 +204,7 @@
 				(mode_info->atom_context->bios + data_offset);
 			switch (crev) {
 			case 11:
+			case 12:
 				mem_channel_number = igp_info->v11.umachannelnumber;
 				/* channel width is 64 */
 				if (vram_width)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index d33cb34..a414da2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -1295,27 +1295,37 @@
 static void amdgpu_ib_preempt_mark_partial_job(struct amdgpu_ring *ring)
 {
 	struct amdgpu_job *job;
-	struct drm_sched_job *s_job;
+	struct drm_sched_job *s_job, *tmp;
 	uint32_t preempt_seq;
 	struct dma_fence *fence, **ptr;
 	struct amdgpu_fence_driver *drv = &ring->fence_drv;
 	struct drm_gpu_scheduler *sched = &ring->sched;
+	bool preempted = true;
 
 	if (ring->funcs->type != AMDGPU_RING_TYPE_GFX)
 		return;
 
 	preempt_seq = le32_to_cpu(*(drv->cpu_addr + 2));
-	if (preempt_seq <= atomic_read(&drv->last_seq))
-		return;
+	if (preempt_seq <= atomic_read(&drv->last_seq)) {
+		preempted = false;
+		goto no_preempt;
+	}
 
 	preempt_seq &= drv->num_fences_mask;
 	ptr = &drv->fences[preempt_seq];
 	fence = rcu_dereference_protected(*ptr, 1);
 
+no_preempt:
 	spin_lock(&sched->job_list_lock);
-	list_for_each_entry(s_job, &sched->ring_mirror_list, node) {
+	list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
+		if (dma_fence_is_signaled(&s_job->s_fence->finished)) {
+			/* remove job from ring_mirror_list */
+			list_del_init(&s_job->node);
+			sched->ops->free_job(s_job);
+			continue;
+		}
 		job = to_amdgpu_job(s_job);
-		if (job->fence == fence)
+		if (preempted && job->fence == fence)
 			/* mark the job as preempted */
 			job->preemption_status |= AMDGPU_IB_PREEMPTED;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 4720718..4fb4c3b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -37,7 +37,8 @@
 
 	memset(&ti, 0, sizeof(struct amdgpu_task_info));
 
-	if (amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) {
+	if (amdgpu_gpu_recovery &&
+	    amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) {
 		DRM_ERROR("ring %s timeout, but soft recovered\n",
 			  s_job->sched->name);
 		return;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index d7e17e3..2129209 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -692,9 +692,10 @@
 		return n ? -EFAULT : 0;
 	}
 	case AMDGPU_INFO_DEV_INFO: {
-		struct drm_amdgpu_info_device dev_info = {};
+		struct drm_amdgpu_info_device dev_info;
 		uint64_t vm_size;
 
+		memset(&dev_info, 0, sizeof(dev_info));
 		dev_info.device_id = dev->pdev->device;
 		dev_info.chip_rev = adev->rev_id;
 		dev_info.external_rev = adev->external_rev_id;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index 16596a9..02e6f8c4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -2784,7 +2784,7 @@
 	if (r)
 		return r;
 
-	return snprintf(buf, PAGE_SIZE, "%d\n", sclk * 10 * 1000);
+	return snprintf(buf, PAGE_SIZE, "%u\n", sclk * 10 * 1000);
 }
 
 static ssize_t amdgpu_hwmon_show_sclk_label(struct device *dev,
@@ -2819,7 +2819,7 @@
 	if (r)
 		return r;
 
-	return snprintf(buf, PAGE_SIZE, "%d\n", mclk * 10 * 1000);
+	return snprintf(buf, PAGE_SIZE, "%u\n", mclk * 10 * 1000);
 }
 
 static ssize_t amdgpu_hwmon_show_mclk_label(struct device *dev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 7301fdc..ef3269c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -372,6 +372,52 @@
 	return ret;
 }
 
+static void psp_prep_tmr_unload_cmd_buf(struct psp_context *psp,
+					struct psp_gfx_cmd_resp *cmd)
+{
+	if (amdgpu_sriov_vf(psp->adev))
+		cmd->cmd_id = GFX_CMD_ID_DESTROY_VMR;
+	else
+		cmd->cmd_id = GFX_CMD_ID_DESTROY_TMR;
+}
+
+static int psp_tmr_unload(struct psp_context *psp)
+{
+	int ret;
+	struct psp_gfx_cmd_resp *cmd;
+
+	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	psp_prep_tmr_unload_cmd_buf(psp, cmd);
+	DRM_INFO("free PSP TMR buffer\n");
+
+	ret = psp_cmd_submit_buf(psp, NULL, cmd,
+				 psp->fence_buf_mc_addr);
+
+	kfree(cmd);
+
+	return ret;
+}
+
+static int psp_tmr_terminate(struct psp_context *psp)
+{
+	int ret;
+	void *tmr_buf;
+	void **pptr;
+
+	ret = psp_tmr_unload(psp);
+	if (ret)
+		return ret;
+
+	/* free TMR memory buffer */
+	pptr = amdgpu_sriov_vf(psp->adev) ? &tmr_buf : NULL;
+	amdgpu_bo_free_kernel(&psp->tmr_bo, &psp->tmr_mc_addr, pptr);
+
+	return 0;
+}
+
 static void psp_prep_asd_load_cmd_buf(struct psp_gfx_cmd_resp *cmd,
 				uint64_t asd_mc, uint32_t size)
 {
@@ -1779,8 +1825,6 @@
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	struct psp_context *psp = &adev->psp;
-	void *tmr_buf;
-	void **pptr;
 
 	if (psp->adev->psp.ta_fw) {
 		psp_ras_terminate(psp);
@@ -1790,10 +1834,9 @@
 
 	psp_asd_unload(psp);
 
+	psp_tmr_terminate(psp);
 	psp_ring_destroy(psp, PSP_RING_TYPE__KM);
 
-	pptr = amdgpu_sriov_vf(psp->adev) ? &tmr_buf : NULL;
-	amdgpu_bo_free_kernel(&psp->tmr_bo, &psp->tmr_mc_addr, pptr);
 	amdgpu_bo_free_kernel(&psp->fw_pri_bo,
 			      &psp->fw_pri_mc_addr, &psp->fw_pri_buf);
 	amdgpu_bo_free_kernel(&psp->fence_buf_bo,
@@ -1840,6 +1883,18 @@
 		}
 	}
 
+	ret = psp_asd_unload(psp);
+	if (ret) {
+		DRM_ERROR("Failed to unload asd\n");
+		return ret;
+	}
+
+	ret = psp_tmr_terminate(psp);
+	if (ret) {
+		DRM_ERROR("Falied to terminate tmr\n");
+		return ret;
+	}
+
 	ret = psp_ring_stop(psp, PSP_RING_TYPE__KM);
 	if (ret) {
 		DRM_ERROR("PSP ring stop failed\n");
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index bd5dd4f..fac77a8 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -7513,12 +7513,17 @@
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
 	struct amdgpu_ring *kiq_ring = &kiq->ring;
+	unsigned long flags;
 
 	if (!kiq->pmf || !kiq->pmf->kiq_unmap_queues)
 		return -EINVAL;
 
-	if (amdgpu_ring_alloc(kiq_ring, kiq->pmf->unmap_queues_size))
+	spin_lock_irqsave(&kiq->ring_lock, flags);
+
+	if (amdgpu_ring_alloc(kiq_ring, kiq->pmf->unmap_queues_size)) {
+		spin_unlock_irqrestore(&kiq->ring_lock, flags);
 		return -ENOMEM;
+	}
 
 	/* assert preemption condition */
 	amdgpu_ring_set_preempt_cond_exec(ring, false);
@@ -7529,6 +7534,8 @@
 				   ++ring->trail_seq);
 	amdgpu_ring_commit(kiq_ring);
 
+	spin_unlock_irqrestore(&kiq->ring_lock, flags);
+
 	/* poll the trailing fence */
 	for (i = 0; i < adev->usec_timeout; i++) {
 		if (ring->trail_seq ==
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
index b544baf..8fb66e5 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
@@ -314,30 +314,20 @@
 static uint64_t sdma_v5_0_ring_get_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
-	u64 *wptr = NULL;
-	uint64_t local_wptr = 0;
+	u64 wptr;
 
 	if (ring->use_doorbell) {
 		/* XXX check if swapping is necessary on BE */
-		wptr = ((u64 *)&adev->wb.wb[ring->wptr_offs]);
-		DRM_DEBUG("wptr/doorbell before shift == 0x%016llx\n", *wptr);
-		*wptr = (*wptr) >> 2;
-		DRM_DEBUG("wptr/doorbell after shift == 0x%016llx\n", *wptr);
+		wptr = READ_ONCE(*((u64 *)&adev->wb.wb[ring->wptr_offs]));
+		DRM_DEBUG("wptr/doorbell before shift == 0x%016llx\n", wptr);
 	} else {
-		u32 lowbit, highbit;
-
-		wptr = &local_wptr;
-		lowbit = RREG32(sdma_v5_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR)) >> 2;
-		highbit = RREG32(sdma_v5_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI)) >> 2;
-
-		DRM_DEBUG("wptr [%i]high== 0x%08x low==0x%08x\n",
-				ring->me, highbit, lowbit);
-		*wptr = highbit;
-		*wptr = (*wptr) << 32;
-		*wptr |= lowbit;
+		wptr = RREG32(sdma_v5_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI));
+		wptr = wptr << 32;
+		wptr |= RREG32(sdma_v5_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR));
+		DRM_DEBUG("wptr before shift [%i] wptr == 0x%016llx\n", ring->me, wptr);
 	}
 
-	return *wptr;
+	return wptr >> 2;
 }
 
 /**
@@ -1298,8 +1288,12 @@
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	int i;
 
-	for (i = 0; i < adev->sdma.num_instances; i++)
+	for (i = 0; i < adev->sdma.num_instances; i++) {
+		if (adev->sdma.instance[i].fw != NULL)
+			release_firmware(adev->sdma.instance[i].fw);
+
 		amdgpu_ring_fini(&adev->sdma.instance[i].ring);
+	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index d27221d..0e0c42e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -428,6 +428,7 @@
 					   (int)process->lead_thread->pid);
 		if (ret) {
 			pr_warn("Creating procfs pid directory failed");
+			kobject_put(process->kobj);
 			goto out;
 		}
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 7ced9f8..710edc7 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -974,6 +974,9 @@
 	/* Update the actual used number of crtc */
 	adev->mode_info.num_crtc = adev->dm.display_indexes_num;
 
+	/* create fake encoders for MST */
+	dm_dp_create_fake_mst_encoders(adev);
+
 	/* TODO: Add_display_info? */
 
 	/* TODO use dynamic cursor width */
@@ -997,6 +1000,12 @@
 
 static void amdgpu_dm_fini(struct amdgpu_device *adev)
 {
+	int i;
+
+	for (i = 0; i < adev->dm.display_indexes_num; i++) {
+		drm_encoder_cleanup(&adev->dm.mst_encoders[i].base);
+	}
+
 	amdgpu_dm_audio_fini(adev);
 
 	amdgpu_dm_destroy_drm_device(&adev->dm);
@@ -1358,7 +1367,7 @@
 	struct dmcu *dmcu = NULL;
 	bool ret;
 
-	if (!adev->dm.fw_dmcu)
+	if (!adev->dm.fw_dmcu && !adev->dm.dmub_fw)
 		return detect_mst_link_for_all_connectors(adev->ddev);
 
 	dmcu = adev->dm.dc->res_pool->dmcu;
@@ -2010,6 +2019,7 @@
 	struct amdgpu_display_manager *dm;
 	struct drm_connector *conn_base;
 	struct amdgpu_device *adev;
+	struct dc_link *link = NULL;
 	static const u8 pre_computed_values[] = {
 		50, 51, 52, 53, 55, 56, 57, 58, 59, 61, 62, 63, 65, 66, 68, 69,
 		71, 72, 74, 75, 77, 79, 81, 82, 84, 86, 88, 90, 92, 94, 96, 98};
@@ -2017,6 +2027,10 @@
 	if (!aconnector || !aconnector->dc_link)
 		return;
 
+	link = aconnector->dc_link;
+	if (link->connector_signal != SIGNAL_TYPE_EDP)
+		return;
+
 	conn_base = &aconnector->base;
 	adev = conn_base->dev->dev_private;
 	dm = &adev->dm;
@@ -5024,7 +5038,8 @@
 	struct drm_connector *connector = &aconnector->base;
 	struct amdgpu_device *adev = connector->dev->dev_private;
 	struct dc_stream_state *stream;
-	int requested_bpc = connector->state ? connector->state->max_requested_bpc : 8;
+	const struct drm_connector_state *drm_state = dm_state ? &dm_state->base : NULL;
+	int requested_bpc = drm_state ? drm_state->max_requested_bpc : 8;
 	enum dc_status dc_result = DC_OK;
 
 	do {
@@ -8702,20 +8717,38 @@
 		 * the same resource. If we have a new DC context as part of
 		 * the DM atomic state from validation we need to free it and
 		 * retain the existing one instead.
+		 *
+		 * Furthermore, since the DM atomic state only contains the DC
+		 * context and can safely be annulled, we can free the state
+		 * and clear the associated private object now to free
+		 * some memory and avoid a possible use-after-free later.
 		 */
-		struct dm_atomic_state *new_dm_state, *old_dm_state;
 
-		new_dm_state = dm_atomic_get_new_state(state);
-		old_dm_state = dm_atomic_get_old_state(state);
+		for (i = 0; i < state->num_private_objs; i++) {
+			struct drm_private_obj *obj = state->private_objs[i].ptr;
 
-		if (new_dm_state && old_dm_state) {
-			if (new_dm_state->context)
-				dc_release_state(new_dm_state->context);
+			if (obj->funcs == adev->dm.atomic_obj.funcs) {
+				int j = state->num_private_objs-1;
 
-			new_dm_state->context = old_dm_state->context;
+				dm_atomic_destroy_state(obj,
+						state->private_objs[i].state);
 
-			if (old_dm_state->context)
-				dc_retain_state(old_dm_state->context);
+				/* If i is not at the end of the array then the
+				 * last element needs to be moved to where i was
+				 * before the array can safely be truncated.
+				 */
+				if (i != j)
+					state->private_objs[i] =
+						state->private_objs[j];
+
+				state->private_objs[j].ptr = NULL;
+				state->private_objs[j].state = NULL;
+				state->private_objs[j].old_state = NULL;
+				state->private_objs[j].new_state = NULL;
+
+				state->num_private_objs = j;
+				break;
+			}
 		}
 	}
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index d61186f..648180c 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -43,6 +43,9 @@
  */
 
 #define AMDGPU_DM_MAX_DISPLAY_INDEX 31
+
+#define AMDGPU_DM_MAX_CRTC 6
+
 /*
 #include "include/amdgpu_dal_power_if.h"
 #include "amdgpu_dm_irq.h"
@@ -328,6 +331,13 @@
 	 * available in FW
 	 */
 	const struct gpu_info_soc_bounding_box_v1_0 *soc_bounding_box;
+
+	/**
+	 * @mst_encoders:
+	 *
+	 * fake encoders used for DP MST.
+	 */
+	struct amdgpu_encoder mst_encoders[AMDGPU_DM_MAX_CRTC];
 };
 
 struct amdgpu_dm_connector {
@@ -356,7 +366,6 @@
 	struct amdgpu_dm_dp_aux dm_dp_aux;
 	struct drm_dp_mst_port *port;
 	struct amdgpu_dm_connector *mst_port;
-	struct amdgpu_encoder *mst_encoder;
 	struct drm_dp_aux *dsc_aux;
 
 	/* TODO see if we can merge with ddc_bus or make a dm_connector */
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
index 076af26..1d692f4 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -1058,7 +1058,6 @@
 		{"link_settings", &dp_link_settings_debugfs_fops},
 		{"phy_settings", &dp_phy_settings_debugfs_fop},
 		{"test_pattern", &dp_phy_test_pattern_fops},
-		{"output_bpc", &output_bpc_fops},
 		{"vrr_range", &vrr_range_fops},
 #ifdef CONFIG_DRM_AMD_DC_HDCP
 		{"hdcp_sink_capability", &hdcp_sink_capability_fops},
@@ -1142,6 +1141,9 @@
 	debugfs_create_file_unsafe("force_yuv420_output", 0644, dir, connector,
 				   &force_yuv420_output_fops);
 
+	debugfs_create_file("output_bpc", 0644, dir, connector,
+			    &output_bpc_fops);
+
 	connector->debugfs_dpcd_address = 0;
 	connector->debugfs_dpcd_size = 0;
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
index dcf84a6..949d10e 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
@@ -510,8 +510,10 @@
 
 	srm = psp_get_srm(work->hdcp.config.psp.handle, &srm_version, &srm_size);
 
-	if (!srm)
-		return -EINVAL;
+	if (!srm) {
+		ret = -EINVAL;
+		goto ret;
+	}
 
 	if (pos >= srm_size)
 		ret = 0;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index ae0a7ef..e5ecc5a 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -95,7 +95,6 @@
 {
 	struct amdgpu_dm_connector *aconnector =
 		to_amdgpu_dm_connector(connector);
-	struct amdgpu_encoder *amdgpu_encoder = aconnector->mst_encoder;
 
 	if (aconnector->dc_sink) {
 		dc_link_remove_remote_sink(aconnector->dc_link,
@@ -105,8 +104,6 @@
 
 	kfree(aconnector->edid);
 
-	drm_encoder_cleanup(&amdgpu_encoder->base);
-	kfree(amdgpu_encoder);
 	drm_connector_cleanup(connector);
 	drm_dp_mst_put_port_malloc(aconnector->port);
 	kfree(aconnector);
@@ -243,7 +240,11 @@
 dm_mst_atomic_best_encoder(struct drm_connector *connector,
 			   struct drm_connector_state *connector_state)
 {
-	return &to_amdgpu_dm_connector(connector)->mst_encoder->base;
+	struct drm_device *dev = connector->dev;
+	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_crtc *acrtc = to_amdgpu_crtc(connector_state->crtc);
+
+	return &adev->dm.mst_encoders[acrtc->crtc_id].base;
 }
 
 static int
@@ -306,31 +307,27 @@
 	.destroy = amdgpu_dm_encoder_destroy,
 };
 
-static struct amdgpu_encoder *
-dm_dp_create_fake_mst_encoder(struct amdgpu_dm_connector *connector)
+void
+dm_dp_create_fake_mst_encoders(struct amdgpu_device *adev)
 {
-	struct drm_device *dev = connector->base.dev;
-	struct amdgpu_device *adev = dev->dev_private;
-	struct amdgpu_encoder *amdgpu_encoder;
-	struct drm_encoder *encoder;
+	struct drm_device *dev = adev->ddev;
+	int i;
 
-	amdgpu_encoder = kzalloc(sizeof(*amdgpu_encoder), GFP_KERNEL);
-	if (!amdgpu_encoder)
-		return NULL;
+	for (i = 0; i < adev->dm.display_indexes_num; i++) {
+		struct amdgpu_encoder *amdgpu_encoder = &adev->dm.mst_encoders[i];
+		struct drm_encoder *encoder = &amdgpu_encoder->base;
 
-	encoder = &amdgpu_encoder->base;
-	encoder->possible_crtcs = amdgpu_dm_get_encoder_crtc_mask(adev);
+		encoder->possible_crtcs = amdgpu_dm_get_encoder_crtc_mask(adev);
 
-	drm_encoder_init(
-		dev,
-		&amdgpu_encoder->base,
-		&amdgpu_dm_encoder_funcs,
-		DRM_MODE_ENCODER_DPMST,
-		NULL);
+		drm_encoder_init(
+			dev,
+			&amdgpu_encoder->base,
+			&amdgpu_dm_encoder_funcs,
+			DRM_MODE_ENCODER_DPMST,
+			NULL);
 
-	drm_encoder_helper_add(encoder, &amdgpu_dm_encoder_helper_funcs);
-
-	return amdgpu_encoder;
+		drm_encoder_helper_add(encoder, &amdgpu_dm_encoder_helper_funcs);
+	}
 }
 
 static struct drm_connector *
@@ -343,6 +340,7 @@
 	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_dm_connector *aconnector;
 	struct drm_connector *connector;
+	int i;
 
 	aconnector = kzalloc(sizeof(*aconnector), GFP_KERNEL);
 	if (!aconnector)
@@ -369,9 +367,10 @@
 		master->dc_link,
 		master->connector_id);
 
-	aconnector->mst_encoder = dm_dp_create_fake_mst_encoder(master);
-	drm_connector_attach_encoder(&aconnector->base,
-				     &aconnector->mst_encoder->base);
+	for (i = 0; i < adev->dm.display_indexes_num; i++) {
+		drm_connector_attach_encoder(&aconnector->base,
+					     &adev->dm.mst_encoders[i].base);
+	}
 
 	connector->max_bpc_property = master->base.max_bpc_property;
 	if (connector->max_bpc_property)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
index d2c5657..b38bd68 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h
@@ -35,6 +35,9 @@
 				       struct amdgpu_dm_connector *aconnector,
 				       int link_index);
 
+void
+dm_dp_create_fake_mst_encoders(struct amdgpu_device *adev);
+
 #if defined(CONFIG_DRM_AMD_DC_DCN)
 bool compute_mst_dsc_configs_for_state(struct drm_atomic_state *state,
 				       struct dc_state *dc_state);
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 6f93a6c..d016f50 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -2538,10 +2538,12 @@
 
 	copy_stream_update_to_stream(dc, context, stream, stream_update);
 
-	if (!dc->res_pool->funcs->validate_bandwidth(dc, context, false)) {
-		DC_ERROR("Mode validation failed for stream update!\n");
-		dc_release_state(context);
-		return;
+	if (update_type > UPDATE_TYPE_FAST) {
+		if (!dc->res_pool->funcs->validate_bandwidth(dc, context, false)) {
+			DC_ERROR("Mode validation failed for stream update!\n");
+			dc_release_state(context);
+			return;
+		}
 	}
 
 	commit_planes_for_stream(
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
index 4f0e720..470c827 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
@@ -56,7 +56,7 @@
 	}
 }
 
-static void dc_stream_construct(struct dc_stream_state *stream,
+static bool dc_stream_construct(struct dc_stream_state *stream,
 	struct dc_sink *dc_sink_data)
 {
 	uint32_t i = 0;
@@ -118,11 +118,17 @@
 	update_stream_signal(stream, dc_sink_data);
 
 	stream->out_transfer_func = dc_create_transfer_func();
+	if (stream->out_transfer_func == NULL) {
+		dc_sink_release(dc_sink_data);
+		return false;
+	}
 	stream->out_transfer_func->type = TF_TYPE_BYPASS;
 	stream->out_transfer_func->ctx = stream->ctx;
 
 	stream->stream_id = stream->ctx->dc_stream_id_count;
 	stream->ctx->dc_stream_id_count++;
+
+	return true;
 }
 
 static void dc_stream_destruct(struct dc_stream_state *stream)
@@ -164,13 +170,20 @@
 
 	stream = kzalloc(sizeof(struct dc_stream_state), GFP_KERNEL);
 	if (stream == NULL)
-		return NULL;
+		goto alloc_fail;
 
-	dc_stream_construct(stream, sink);
+	if (dc_stream_construct(stream, sink) == false)
+		goto construct_fail;
 
 	kref_init(&stream->refcount);
 
 	return stream;
+
+construct_fail:
+	kfree(stream);
+
+alloc_fail:
+	return NULL;
 }
 
 struct dc_stream_state *dc_copy_stream(const struct dc_stream_state *stream)
diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
index 6747604..fbb3f3a 100644
--- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
@@ -689,7 +689,7 @@
 		return -EINVAL;
 	}
 
-	ret = smu_send_smc_msg_with_param(smu, SMU_MSG_SetWorkloadMask,
+	ret = smu_send_smc_msg_with_param(smu, SMU_MSG_ActiveProcessNotify,
 				    1 << workload_type,
 				    NULL);
 	if (ret) {
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.c
index 2fb9755..c2e0fbb 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.c
@@ -522,9 +522,11 @@
 	priv->smu_tables.entry[TABLE_ACTIVITY_MONITOR_COEFF].version = 0x01;
 	priv->smu_tables.entry[TABLE_ACTIVITY_MONITOR_COEFF].size = sizeof(DpmActivityMonitorCoeffInt_t);
 
-	ret = smu_v11_0_i2c_eeprom_control_init(&adev->pm.smu_i2c);
-	if (ret)
-		goto err4;
+	if (adev->psp.ras.ras) {
+		ret = smu_v11_0_i2c_eeprom_control_init(&adev->pm.smu_i2c);
+		if (ret)
+			goto err4;
+	}
 
 	return 0;
 
@@ -560,7 +562,8 @@
 			(struct vega20_smumgr *)(hwmgr->smu_backend);
 	struct amdgpu_device *adev = hwmgr->adev;
 
-	smu_v11_0_i2c_eeprom_control_fini(&adev->pm.smu_i2c);
+	if (adev->psp.ras.ras)
+		smu_v11_0_i2c_eeprom_control_fini(&adev->pm.smu_i2c);
 
 	if (priv) {
 		amdgpu_bo_free_kernel(&priv->smu_tables.entry[TABLE_PPTABLE].handle,
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
index 3da71a0..0ecc18b 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
@@ -644,9 +644,6 @@
 
 	/* sclk is bigger than max sclk in the dependence table */
 	*voltage |= (dep_table->entries[i - 1].vddc * VOLTAGE_SCALE) << VDDC_SHIFT;
-	vddci = phm_find_closest_vddci(&(data->vddci_voltage_table),
-			(dep_table->entries[i - 1].vddc -
-					(uint16_t)VDDC_VDDCI_DELTA));
 
 	if (SMU7_VOLTAGE_CONTROL_NONE == data->vddci_control)
 		*voltage |= (data->vbios_boot_state.vddci_bootup_value *
@@ -654,8 +651,13 @@
 	else if (dep_table->entries[i - 1].vddci)
 		*voltage |= (dep_table->entries[i - 1].vddci *
 				VOLTAGE_SCALE) << VDDC_SHIFT;
-	else
+	else {
+		vddci = phm_find_closest_vddci(&(data->vddci_voltage_table),
+				(dep_table->entries[i - 1].vddc -
+						(uint16_t)VDDC_VDDCI_DELTA));
+
 		*voltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT;
+	}
 
 	if (SMU7_VOLTAGE_CONTROL_NONE == data->mvdd_control)
 		*mvdd = data->vbios_boot_state.mvdd_bootup_value * VOLTAGE_SCALE;
diff --git a/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c b/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c
index 6b27242..bca3fcf 100644
--- a/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c
+++ b/drivers/gpu/drm/aspeed/aspeed_gfx_drv.c
@@ -173,8 +173,6 @@
 
 	drm_mode_config_reset(drm);
 
-	drm_fbdev_generic_setup(drm, 32);
-
 	return 0;
 }
 
@@ -225,6 +223,7 @@
 	if (ret)
 		goto err_unload;
 
+	drm_fbdev_generic_setup(&priv->drm, 32);
 	return 0;
 
 err_unload:
diff --git a/drivers/gpu/drm/bochs/bochs_kms.c b/drivers/gpu/drm/bochs/bochs_kms.c
index 05d8373..079f46f 100644
--- a/drivers/gpu/drm/bochs/bochs_kms.c
+++ b/drivers/gpu/drm/bochs/bochs_kms.c
@@ -146,6 +146,7 @@
 	bochs->dev->mode_config.preferred_depth = 24;
 	bochs->dev->mode_config.prefer_shadow = 0;
 	bochs->dev->mode_config.prefer_shadow_fbdev = 1;
+	bochs->dev->mode_config.fbdev_use_iomem = true;
 	bochs->dev->mode_config.quirk_addfb_prefer_host_byte_order = true;
 
 	bochs->dev->mode_config.funcs = &bochs_mode_funcs;
diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
index 87b58c1..648eb23d 100644
--- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
+++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
@@ -1224,6 +1224,7 @@
 
 	adv7511->bridge.funcs = &adv7511_bridge_funcs;
 	adv7511->bridge.of_node = dev->of_node;
+	adv7511->bridge.type = DRM_MODE_CONNECTOR_HDMIA;
 
 	drm_bridge_add(&adv7511->bridge);
 
diff --git a/drivers/gpu/drm/bridge/nwl-dsi.c b/drivers/gpu/drm/bridge/nwl-dsi.c
index b14d725..c7bc194 100644
--- a/drivers/gpu/drm/bridge/nwl-dsi.c
+++ b/drivers/gpu/drm/bridge/nwl-dsi.c
@@ -917,11 +917,6 @@
 	struct drm_panel *panel;
 	int ret;
 
-	if (flags & DRM_BRIDGE_ATTACH_NO_CONNECTOR) {
-		DRM_ERROR("Fix bridge driver to make connector optional!");
-		return -EINVAL;
-	}
-
 	ret = drm_of_find_panel_or_bridge(dsi->dev->of_node, 1, 0, &panel,
 					  &panel_bridge);
 	if (ret)
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 170aa76..89cfd68 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -227,6 +227,42 @@
 }
 EXPORT_SYMBOL(drm_fb_helper_debug_leave);
 
+static int
+__drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper,
+					    bool force)
+{
+	bool do_delayed;
+	int ret;
+
+	if (!drm_fbdev_emulation || !fb_helper)
+		return -ENODEV;
+
+	if (READ_ONCE(fb_helper->deferred_setup))
+		return 0;
+
+	mutex_lock(&fb_helper->lock);
+	if (force) {
+		/*
+		 * Yes this is the _locked version which expects the master lock
+		 * to be held. But for forced restores we're intentionally
+		 * racing here, see drm_fb_helper_set_par().
+		 */
+		ret = drm_client_modeset_commit_locked(&fb_helper->client);
+	} else {
+		ret = drm_client_modeset_commit(&fb_helper->client);
+	}
+
+	do_delayed = fb_helper->delayed_hotplug;
+	if (do_delayed)
+		fb_helper->delayed_hotplug = false;
+	mutex_unlock(&fb_helper->lock);
+
+	if (do_delayed)
+		drm_fb_helper_hotplug_event(fb_helper);
+
+	return ret;
+}
+
 /**
  * drm_fb_helper_restore_fbdev_mode_unlocked - restore fbdev configuration
  * @fb_helper: driver-allocated fbdev helper, can be NULL
@@ -240,27 +276,7 @@
  */
 int drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper)
 {
-	bool do_delayed;
-	int ret;
-
-	if (!drm_fbdev_emulation || !fb_helper)
-		return -ENODEV;
-
-	if (READ_ONCE(fb_helper->deferred_setup))
-		return 0;
-
-	mutex_lock(&fb_helper->lock);
-	ret = drm_client_modeset_commit(&fb_helper->client);
-
-	do_delayed = fb_helper->delayed_hotplug;
-	if (do_delayed)
-		fb_helper->delayed_hotplug = false;
-	mutex_unlock(&fb_helper->lock);
-
-	if (do_delayed)
-		drm_fb_helper_hotplug_event(fb_helper);
-
-	return ret;
+	return __drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper, false);
 }
 EXPORT_SYMBOL(drm_fb_helper_restore_fbdev_mode_unlocked);
 
@@ -383,7 +399,11 @@
 	unsigned int y;
 
 	for (y = clip->y1; y < clip->y2; y++) {
-		memcpy(dst, src, len);
+		if (!fb_helper->dev->mode_config.fbdev_use_iomem)
+			memcpy(dst, src, len);
+		else
+			memcpy_toio((void __iomem *)dst, src, len);
+
 		src += fb->pitches[0];
 		dst += fb->pitches[0];
 	}
@@ -1318,6 +1338,7 @@
 {
 	struct drm_fb_helper *fb_helper = info->par;
 	struct fb_var_screeninfo *var = &info->var;
+	bool force;
 
 	if (oops_in_progress)
 		return -EBUSY;
@@ -1327,7 +1348,25 @@
 		return -EINVAL;
 	}
 
-	drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper);
+	/*
+	 * Normally we want to make sure that a kms master takes precedence over
+	 * fbdev, to avoid fbdev flickering and occasionally stealing the
+	 * display status. But Xorg first sets the vt back to text mode using
+	 * the KDSET IOCTL with KD_TEXT, and only after that drops the master
+	 * status when exiting.
+	 *
+	 * In the past this was caught by drm_fb_helper_lastclose(), but on
+	 * modern systems where logind always keeps a drm fd open to orchestrate
+	 * the vt switching, this doesn't work.
+	 *
+	 * To not break the userspace ABI we have this special case here, which
+	 * is only used for the above case. Everything else uses the normal
+	 * commit function, which ensures that we never steal the display from
+	 * an active drm master.
+	 */
+	force = var->activate & FB_ACTIVATE_KD_TEXT;
+
+	__drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper, force);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index 7bf628e..ee2058a 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -871,9 +871,6 @@
  * @file_priv: drm file-private structure
  *
  * Open an object using the global name, returning a handle and the size.
- *
- * This handle (of course) holds a reference to the object, so the object
- * will not go away until the handle is deleted.
  */
 int
 drm_gem_open_ioctl(struct drm_device *dev, void *data,
@@ -898,14 +895,15 @@
 
 	/* drm_gem_handle_create_tail unlocks dev->object_name_lock. */
 	ret = drm_gem_handle_create_tail(file_priv, obj, &handle);
-	drm_gem_object_put_unlocked(obj);
 	if (ret)
-		return ret;
+		goto err;
 
 	args->handle = handle;
 	args->size = obj->size;
 
-	return 0;
+err:
+	drm_gem_object_put_unlocked(obj);
+	return ret;
 }
 
 /**
diff --git a/drivers/gpu/drm/drm_mipi_dbi.c b/drivers/gpu/drm/drm_mipi_dbi.c
index bb27c82..bf7888a 100644
--- a/drivers/gpu/drm/drm_mipi_dbi.c
+++ b/drivers/gpu/drm/drm_mipi_dbi.c
@@ -923,7 +923,7 @@
 			}
 		}
 
-		tr.len = chunk;
+		tr.len = chunk * 2;
 		len -= chunk;
 
 		ret = spi_sync(spi, &m);
diff --git a/drivers/gpu/drm/drm_of.c b/drivers/gpu/drm/drm_of.c
index b50b44e..8fc3f67 100644
--- a/drivers/gpu/drm/drm_of.c
+++ b/drivers/gpu/drm/drm_of.c
@@ -322,10 +322,8 @@
 		 * configurations by passing the endpoints explicitly to
 		 * drm_of_lvds_get_dual_link_pixel_order().
 		 */
-		if (!current_pt || pixels_type != current_pt) {
-			of_node_put(remote_port);
+		if (!current_pt || pixels_type != current_pt)
 			return -EINVAL;
-		}
 	}
 
 	return pixels_type;
diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c
index ffd95bf..d00ea38 100644
--- a/drivers/gpu/drm/drm_panel_orientation_quirks.c
+++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c
@@ -30,12 +30,6 @@
 	int orientation;
 };
 
-static const struct drm_dmi_panel_orientation_data acer_s1003 = {
-	.width = 800,
-	.height = 1280,
-	.orientation = DRM_MODE_PANEL_ORIENTATION_RIGHT_UP,
-};
-
 static const struct drm_dmi_panel_orientation_data asus_t100ha = {
 	.width = 800,
 	.height = 1280,
@@ -114,13 +108,19 @@
 		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Acer"),
 		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "One S1003"),
 		},
-		.driver_data = (void *)&acer_s1003,
+		.driver_data = (void *)&lcd800x1280_rightside_up,
 	}, {	/* Asus T100HA */
 		.matches = {
 		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
 		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100HAN"),
 		},
 		.driver_data = (void *)&asus_t100ha,
+	}, {	/* Asus T101HA */
+		.matches = {
+		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+		  DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T101HA"),
+		},
+		.driver_data = (void *)&lcd800x1280_rightside_up,
 	}, {	/* GPD MicroPC (generic strings, also match on bios date) */
 		.matches = {
 		  DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Default string"),
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dma.c b/drivers/gpu/drm/exynos/exynos_drm_dma.c
index 619f814..58b89ec 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dma.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dma.c
@@ -61,7 +61,7 @@
 				struct device *subdrv_dev, void **dma_priv)
 {
 	struct exynos_drm_private *priv = drm_dev->dev_private;
-	int ret;
+	int ret = 0;
 
 	if (get_dma_ops(priv->dma_dev) != get_dma_ops(subdrv_dev)) {
 		DRM_DEV_ERROR(subdrv_dev, "Device %s lacks support for IOMMU\n",
@@ -92,7 +92,7 @@
 	if (ret)
 		clear_dma_max_seg_size(subdrv_dev);
 
-	return 0;
+	return ret;
 }
 
 /*
diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
index fcee33a..03be314 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
@@ -1498,7 +1498,6 @@
 
 	g2d->irq = platform_get_irq(pdev, 0);
 	if (g2d->irq < 0) {
-		dev_err(dev, "failed to get irq\n");
 		ret = g2d->irq;
 		goto err_put_clk;
 	}
diff --git a/drivers/gpu/drm/exynos/exynos_drm_mic.c b/drivers/gpu/drm/exynos/exynos_drm_mic.c
index a86abc1..3821ea7 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_mic.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_mic.c
@@ -269,8 +269,10 @@
 		goto unlock;
 
 	ret = pm_runtime_get_sync(mic->dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put_noidle(mic->dev);
 		goto unlock;
+	}
 
 	mic_set_path(mic, 1);
 
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
index a6fd0c2..544b999 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_drv.c
@@ -307,8 +307,6 @@
 	/* reset all the states of crtc/plane/encoder/connector */
 	drm_mode_config_reset(dev);
 
-	drm_fbdev_generic_setup(dev, dev->mode_config.preferred_depth);
-
 	return 0;
 
 err:
@@ -355,6 +353,9 @@
 			  ret);
 		goto err_unload;
 	}
+
+	drm_fbdev_generic_setup(dev, dev->mode_config.preferred_depth);
+
 	return 0;
 
 err_unload:
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 9ea1a39..26996e1 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -3822,6 +3822,17 @@
 	return true;
 }
 
+unsigned int
+intel_plane_fence_y_offset(const struct intel_plane_state *plane_state)
+{
+	int x = 0, y = 0;
+
+	intel_plane_adjust_aligned_offset(&x, &y, plane_state, 0,
+					  plane_state->color_plane[0].offset, 0);
+
+	return y;
+}
+
 static int skl_check_main_surface(struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(plane_state->uapi.plane->dev);
diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h
index efb4da2..3a06f72 100644
--- a/drivers/gpu/drm/i915/display/intel_display.h
+++ b/drivers/gpu/drm/i915/display/intel_display.h
@@ -608,6 +608,7 @@
 				   u32 pixel_format, u64 modifier,
 				   unsigned int rotation);
 int bdw_get_pipemisc_bpp(struct intel_crtc *crtc);
+unsigned int intel_plane_fence_y_offset(const struct intel_plane_state *plane_state);
 
 struct intel_display_error_state *
 intel_display_capture_error_state(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c
index 1c26673..412572f 100644
--- a/drivers/gpu/drm/i915/display/intel_fbc.c
+++ b/drivers/gpu/drm/i915/display/intel_fbc.c
@@ -48,19 +48,6 @@
 #include "intel_frontbuffer.h"
 
 /*
- * In some platforms where the CRTC's x:0/y:0 coordinates doesn't match the
- * frontbuffer's x:0/y:0 coordinates we lie to the hardware about the plane's
- * origin so the x and y offsets can actually fit the registers. As a
- * consequence, the fence doesn't really start exactly at the display plane
- * address we program because it starts at the real start of the buffer, so we
- * have to take this into consideration here.
- */
-static unsigned int get_crtc_fence_y_offset(struct intel_fbc *fbc)
-{
-	return fbc->state_cache.plane.y - fbc->state_cache.plane.adjusted_y;
-}
-
-/*
  * For SKL+, the plane source size used by the hardware is based on the value we
  * write to the PLANE_SIZE register. For BDW-, the hardware looks at the value
  * we wrote to PIPESRC.
@@ -141,7 +128,7 @@
 			fbc_ctl2 |= FBC_CTL_CPU_FENCE;
 		intel_de_write(dev_priv, FBC_CONTROL2, fbc_ctl2);
 		intel_de_write(dev_priv, FBC_FENCE_OFF,
-			       params->crtc.fence_y_offset);
+			       params->fence_y_offset);
 	}
 
 	/* enable it... */
@@ -175,7 +162,7 @@
 	if (params->fence_id >= 0) {
 		dpfc_ctl |= DPFC_CTL_FENCE_EN | params->fence_id;
 		intel_de_write(dev_priv, DPFC_FENCE_YOFF,
-			       params->crtc.fence_y_offset);
+			       params->fence_y_offset);
 	} else {
 		intel_de_write(dev_priv, DPFC_FENCE_YOFF, 0);
 	}
@@ -243,7 +230,7 @@
 			intel_de_write(dev_priv, SNB_DPFC_CTL_SA,
 				       SNB_CPU_FENCE_ENABLE | params->fence_id);
 			intel_de_write(dev_priv, DPFC_CPU_FENCE_OFFSET,
-				       params->crtc.fence_y_offset);
+				       params->fence_y_offset);
 		}
 	} else {
 		if (IS_GEN(dev_priv, 6)) {
@@ -253,7 +240,7 @@
 	}
 
 	intel_de_write(dev_priv, ILK_DPFC_FENCE_YOFF,
-		       params->crtc.fence_y_offset);
+		       params->fence_y_offset);
 	/* enable it... */
 	intel_de_write(dev_priv, ILK_DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN);
 
@@ -320,7 +307,7 @@
 		intel_de_write(dev_priv, SNB_DPFC_CTL_SA,
 			       SNB_CPU_FENCE_ENABLE | params->fence_id);
 		intel_de_write(dev_priv, DPFC_CPU_FENCE_OFFSET,
-			       params->crtc.fence_y_offset);
+			       params->fence_y_offset);
 	} else if (dev_priv->ggtt.num_fences) {
 		intel_de_write(dev_priv, SNB_DPFC_CTL_SA, 0);
 		intel_de_write(dev_priv, DPFC_CPU_FENCE_OFFSET, 0);
@@ -631,8 +618,8 @@
 /*
  * For some reason, the hardware tracking starts looking at whatever we
  * programmed as the display plane base address register. It does not look at
- * the X and Y offset registers. That's why we look at the crtc->adjusted{x,y}
- * variables instead of just looking at the pipe/plane size.
+ * the X and Y offset registers. That's why we include the src x/y offsets
+ * instead of just looking at the plane size.
  */
 static bool intel_fbc_hw_tracking_covers_screen(struct intel_crtc *crtc)
 {
@@ -705,7 +692,6 @@
 	cache->plane.src_h = drm_rect_height(&plane_state->uapi.src) >> 16;
 	cache->plane.adjusted_x = plane_state->color_plane[0].x;
 	cache->plane.adjusted_y = plane_state->color_plane[0].y;
-	cache->plane.y = plane_state->uapi.src.y1 >> 16;
 
 	cache->plane.pixel_blend_mode = plane_state->hw.pixel_blend_mode;
 
@@ -713,6 +699,8 @@
 	cache->fb.stride = fb->pitches[0];
 	cache->fb.modifier = fb->modifier;
 
+	cache->fence_y_offset = intel_plane_fence_y_offset(plane_state);
+
 	drm_WARN_ON(&dev_priv->drm, plane_state->flags & PLANE_HAS_FENCE &&
 		    !plane_state->vma->fence);
 
@@ -731,6 +719,25 @@
 		fbc->compressed_fb.size * fbc->threshold;
 }
 
+static u16 intel_fbc_gen9_wa_cfb_stride(struct drm_i915_private *dev_priv)
+{
+	struct intel_fbc *fbc = &dev_priv->fbc;
+	struct intel_fbc_state_cache *cache = &fbc->state_cache;
+
+	if ((IS_GEN9_BC(dev_priv) || IS_BROXTON(dev_priv)) &&
+	    cache->fb.modifier != I915_FORMAT_MOD_X_TILED)
+		return DIV_ROUND_UP(cache->plane.src_w, 32 * fbc->threshold) * 8;
+	else
+		return 0;
+}
+
+static bool intel_fbc_gen9_wa_cfb_stride_changed(struct drm_i915_private *dev_priv)
+{
+	struct intel_fbc *fbc = &dev_priv->fbc;
+
+	return fbc->params.gen9_wa_cfb_stride != intel_fbc_gen9_wa_cfb_stride(dev_priv);
+}
+
 static bool intel_fbc_can_enable(struct drm_i915_private *dev_priv)
 {
 	struct intel_fbc *fbc = &dev_priv->fbc;
@@ -883,12 +890,13 @@
 	memset(params, 0, sizeof(*params));
 
 	params->fence_id = cache->fence_id;
+	params->fence_y_offset = cache->fence_y_offset;
 
 	params->crtc.pipe = crtc->pipe;
 	params->crtc.i9xx_plane = to_intel_plane(crtc->base.primary)->i9xx_plane;
-	params->crtc.fence_y_offset = get_crtc_fence_y_offset(fbc);
 
 	params->fb.format = cache->fb.format;
+	params->fb.modifier = cache->fb.modifier;
 	params->fb.stride = cache->fb.stride;
 
 	params->cfb_size = intel_fbc_calculate_cfb_size(dev_priv, cache);
@@ -918,6 +926,9 @@
 	if (params->fb.format != cache->fb.format)
 		return false;
 
+	if (params->fb.modifier != cache->fb.modifier)
+		return false;
+
 	if (params->fb.stride != cache->fb.stride)
 		return false;
 
@@ -1197,7 +1208,8 @@
 
 	if (fbc->crtc) {
 		if (fbc->crtc != crtc ||
-		    !intel_fbc_cfb_size_changed(dev_priv))
+		    (!intel_fbc_cfb_size_changed(dev_priv) &&
+		     !intel_fbc_gen9_wa_cfb_stride_changed(dev_priv)))
 			goto out;
 
 		__intel_fbc_disable(dev_priv);
@@ -1219,12 +1231,7 @@
 		goto out;
 	}
 
-	if ((IS_GEN9_BC(dev_priv) || IS_BROXTON(dev_priv)) &&
-	    plane_state->hw.fb->modifier != I915_FORMAT_MOD_X_TILED)
-		cache->gen9_wa_cfb_stride =
-			DIV_ROUND_UP(cache->plane.src_w, 32 * fbc->threshold) * 8;
-	else
-		cache->gen9_wa_cfb_stride = 0;
+	cache->gen9_wa_cfb_stride = intel_fbc_gen9_wa_cfb_stride(dev_priv);
 
 	drm_dbg_kms(&dev_priv->drm, "Enabling FBC on pipe %c\n",
 		    pipe_name(crtc->pipe));
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index 010f372..95b6d94 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -2867,19 +2867,13 @@
 	return ret;
 }
 
-static void intel_hdmi_destroy(struct drm_connector *connector)
+static void intel_hdmi_connector_unregister(struct drm_connector *connector)
 {
 	struct cec_notifier *n = intel_attached_hdmi(to_intel_connector(connector))->cec_notifier;
 
 	cec_notifier_conn_unregister(n);
 
-	intel_connector_destroy(connector);
-}
-
-static void intel_hdmi_connector_unregister(struct drm_connector *connector)
-{
 	intel_hdmi_remove_i2c_symlink(connector);
-
 	intel_connector_unregister(connector);
 }
 
@@ -2891,7 +2885,7 @@
 	.atomic_set_property = intel_digital_connector_atomic_set_property,
 	.late_register = intel_hdmi_connector_register,
 	.early_unregister = intel_hdmi_connector_unregister,
-	.destroy = intel_hdmi_destroy,
+	.destroy = intel_connector_destroy,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
 	.atomic_duplicate_state = intel_digital_connector_duplicate_state,
 };
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index e4aece2..52db2bd 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -204,25 +204,25 @@
 {
 	int err;
 
-	err = i915_active_acquire(&ring->vma->active);
+	err = intel_ring_pin(ring);
 	if (err)
 		return err;
 
-	err = intel_ring_pin(ring);
+	err = i915_active_acquire(&ring->vma->active);
 	if (err)
-		goto err_active;
+		goto err_pin;
 
 	return 0;
 
-err_active:
-	i915_active_release(&ring->vma->active);
+err_pin:
+	intel_ring_unpin(ring);
 	return err;
 }
 
 static void __ring_retire(struct intel_ring *ring)
 {
-	intel_ring_unpin(ring);
 	i915_active_release(&ring->vma->active);
+	intel_ring_unpin(ring);
 }
 
 __i915_active_call
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 7c3d8ef..cb07e1d 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -5396,13 +5396,8 @@
 	 * typically be the first we inspect for submission.
 	 */
 	swp = prandom_u32_max(ve->num_siblings);
-	if (!swp)
-		return;
-
-	swap(ve->siblings[swp], ve->siblings[0]);
-	if (!intel_engine_has_relative_mmio(ve->siblings[0]))
-		virtual_update_register_offsets(ve->context.lrc_reg_state,
-						ve->siblings[0]);
+	if (swp)
+		swap(ve->siblings[swp], ve->siblings[0]);
 }
 
 static int virtual_context_alloc(struct intel_context *ce)
@@ -5415,15 +5410,9 @@
 static int virtual_context_pin(struct intel_context *ce)
 {
 	struct virtual_engine *ve = container_of(ce, typeof(*ve), context);
-	int err;
 
 	/* Note: we must use a real engine class for setting up reg state */
-	err = __execlists_context_pin(ce, ve->siblings[0]);
-	if (err)
-		return err;
-
-	virtual_engine_initial_hint(ve);
-	return 0;
+	return __execlists_context_pin(ce, ve->siblings[0]);
 }
 
 static void virtual_context_enter(struct intel_context *ce)
@@ -5688,6 +5677,7 @@
 	intel_engine_init_active(&ve->base, ENGINE_VIRTUAL);
 	intel_engine_init_breadcrumbs(&ve->base);
 	intel_engine_init_execlists(&ve->base);
+	ve->base.breadcrumbs.irq_armed = true; /* fake HW, used for irq_work */
 
 	ve->base.cops = &virtual_context_ops;
 	ve->base.request_alloc = execlists_request_alloc;
@@ -5769,6 +5759,7 @@
 
 	ve->base.flags |= I915_ENGINE_IS_VIRTUAL;
 
+	virtual_engine_initial_hint(ve);
 	return &ve->context;
 
 err_put:
diff --git a/drivers/gpu/drm/i915/gt/selftest_rps.c b/drivers/gpu/drm/i915/gt/selftest_rps.c
index 5049c3d..c91981e 100644
--- a/drivers/gpu/drm/i915/gt/selftest_rps.c
+++ b/drivers/gpu/drm/i915/gt/selftest_rps.c
@@ -44,9 +44,9 @@
 {
 	const u64 *a = A, *b = B;
 
-	if (a < b)
+	if (*a < *b)
 		return -1;
-	else if (a > b)
+	else if (*a > *b)
 		return 1;
 	else
 		return 0;
@@ -56,9 +56,9 @@
 {
 	const u32 *a = A, *b = B;
 
-	if (a < b)
+	if (*a < *b)
 		return -1;
-	else if (a > b)
+	else if (*a > *b)
 		return 1;
 	else
 		return 0;
diff --git a/drivers/gpu/drm/i915/gt/shaders/README b/drivers/gpu/drm/i915/gt/shaders/README
new file mode 100644
index 0000000..e7e96d7
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/shaders/README
@@ -0,0 +1,46 @@
+ASM sources for auto generated shaders
+======================================
+
+The i915/gt/hsw_clear_kernel.c and i915/gt/ivb_clear_kernel.c files contain
+pre-compiled batch chunks that will clear any residual render cache during
+context switch.
+
+They are generated from their respective platform ASM files present on
+i915/gt/shaders/clear_kernel directory.
+
+The generated .c files should never be modified directly. Instead, any modification
+needs to be done on the on their respective ASM files and build instructions below
+needes to be followed.
+
+Building
+========
+
+Environment
+-----------
+
+IGT GPU tool scripts and the Mesa's i965 instruction assembler tool are used
+on building.
+
+Please make sure your Mesa tool is compiled with "-Dtools=intel" and
+"-Ddri-drivers=i965", and run this script from IGT source root directory"
+
+The instructions bellow assume:
+    *  IGT gpu tools source code is located on your home directory (~) as ~/igt
+    *  Mesa source code is located on your home directory (~) as ~/mesa
+       and built under the ~/mesa/build directory
+    *  Linux kernel source code is under your home directory (~) as ~/linux
+
+Instructions
+------------
+
+~ $ cp ~/linux/drivers/gpu/drm/i915/gt/shaders/clear_kernel/ivb.asm \
+       ~/igt/lib/i915/shaders/clear_kernel/ivb.asm
+~ $ cd ~/igt
+igt $ ./scripts/generate_clear_kernel.sh -g ivb \
+      -m ~/mesa/build/src/intel/tools/i965_asm
+
+~ $ cp ~/linux/drivers/gpu/drm/i915/gt/shaders/clear_kernel/hsw.asm \
+    ~/igt/lib/i915/shaders/clear_kernel/hsw.asm
+~ $ cd ~/igt
+igt $ ./scripts/generate_clear_kernel.sh -g hsw \
+      -m ~/mesa/build/src/intel/tools/i965_asm
\ No newline at end of file
diff --git a/drivers/gpu/drm/i915/gt/shaders/clear_kernel/hsw.asm b/drivers/gpu/drm/i915/gt/shaders/clear_kernel/hsw.asm
new file mode 100644
index 0000000..5fdf384
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/shaders/clear_kernel/hsw.asm
@@ -0,0 +1,119 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+/*
+ * Kernel for PAVP buffer clear.
+ *
+ *	1. Clear all 64 GRF registers assigned to the kernel with designated value;
+ *	2. Write 32x16 block of all "0" to render target buffer which indirectly clears
+ *	   512 bytes of Render Cache.
+ */
+
+/* Store designated "clear GRF" value */
+mov(1)          f0.1<1>UW       g1.2<0,1,0>UW                   { align1 1N };
+
+/**
+ * Curbe Format
+ *
+ * DW 1.0 - Block Offset to write Render Cache
+ * DW 1.1 [15:0] - Clear Word
+ * DW 1.2 - Delay iterations
+ * DW 1.3 - Enable Instrumentation (only for debug)
+ * DW 1.4 - Rsvd (intended for context ID)
+ * DW 1.5 - [31:16]:SliceCount, [15:0]:SubSlicePerSliceCount
+ * DW 1.6 - Rsvd MBZ (intended for Enable Wait on Total Thread Count)
+ * DW 1.7 - Rsvd MBZ (inteded for Total Thread Count)
+ *
+ * Binding Table
+ *
+ * BTI 0: 2D Surface to help clear L3 (Render/Data Cache)
+ * BTI 1: Wait/Instrumentation Buffer
+ *  Size : (SliceCount * SubSliceCount  * 16 EUs/SubSlice) rows * (16 threads/EU) cols (Format R32_UINT)
+ *         Expected to be initialized to 0 by driver/another kernel
+ *  Layout:
+ *          RowN: Histogram for EU-N: (SliceID*SubSlicePerSliceCount + SSID)*16 + EUID [assume max 16 EUs / SS]
+ *          Col-k[DW-k]: Threads Executed on ThreadID-k for EU-N
+ */
+add(1)          g1.2<1>UD       g1.2<0,1,0>UD   0x00000001UD    { align1 1N }; /* Loop count to delay kernel: Init to (g1.2 + 1) */
+cmp.z.f0.0(1)   null<1>UD       g1.3<0,1,0>UD   0x00000000UD    { align1 1N };
+(+f0.0) jmpi(1) 352D                                            { align1 WE_all 1N };
+
+/**
+ * State Register has info on where this thread is running
+ *	IVB: sr0.0 :: [15:13]: MBZ, 12: HSID (Half-Slice ID), [11:8]EUID, [2:0] ThreadSlotID
+ *	HSW: sr0.0 :: 15: MBZ, [14:13]: SliceID, 12: HSID (Half-Slice ID), [11:8]EUID, [2:0] ThreadSlotID
+ */
+mov(8)          g3<1>UD         0x00000000UD                    { align1 1Q };
+shr(1)          g3<1>D          sr0<0,1,0>D     12D             { align1 1N };
+and(1)          g3<1>D          g3<0,1,0>D      1D              { align1 1N }; /* g3 has HSID */
+shr(1)          g3.1<1>D        sr0<0,1,0>D     13D             { align1 1N };
+and(1)          g3.1<1>D        g3.1<0,1,0>D    3D              { align1 1N }; /* g3.1 has sliceID */
+mul(1)          g3.5<1>D        g3.1<0,1,0>D    g1.10<0,1,0>UW  { align1 1N };
+add(1)          g3<1>D          g3<0,1,0>D      g3.5<0,1,0>D    { align1 1N }; /* g3 = sliceID * SubSlicePerSliceCount + HSID */
+shr(1)          g3.2<1>D        sr0<0,1,0>D     8D              { align1 1N };
+and(1)          g3.2<1>D        g3.2<0,1,0>D    15D             { align1 1N }; /* g3.2 = EUID */
+mul(1)          g3.4<1>D        g3<0,1,0>D      16D             { align1 1N };
+add(1)          g3.2<1>D        g3.2<0,1,0>D    g3.4<0,1,0>D    { align1 1N }; /* g3.2 now points to EU row number (Y-pixel = V address )  in instrumentation surf */
+
+mov(8)          g5<1>UD         0x00000000UD                    { align1 1Q };
+and(1)          g3.3<1>D        sr0<0,1,0>D     7D              { align1 1N };
+mul(1)          g3.3<1>D        g3.3<0,1,0>D    4D              { align1 1N };
+
+mov(8)          g4<1>UD         g0<8,8,1>UD                     { align1 1Q }; /* Initialize message header with g0 */
+mov(1)          g4<1>UD         g3.3<0,1,0>UD                   { align1 1N }; /* Block offset */
+mov(1)          g4.1<1>UD       g3.2<0,1,0>UD                   { align1 1N }; /* Block offset */
+mov(1)          g4.2<1>UD       0x00000003UD                    { align1 1N }; /* Block size (1 row x 4 bytes) */
+and(1)          g4.3<1>UD       g4.3<0,1,0>UW   0xffffffffUD    { align1 1N };
+
+/* Media block read to fetch current value at specified location in instrumentation buffer */
+sendc(8)        g5<1>UD         g4<8,8,1>F      0x02190001
+
+                            render MsgDesc: media block read MsgCtrl = 0x0 Surface = 1 mlen 1 rlen 1 { align1 1Q };
+add(1)          g5<1>D          g5<0,1,0>D      1D              { align1 1N };
+
+/* Media block write for updated value at specified location in instrumentation buffer */
+sendc(8)        g5<1>UD         g4<8,8,1>F      0x040a8001
+                            render MsgDesc: media block write MsgCtrl = 0x0 Surface = 1 mlen 2 rlen 0 { align1 1Q };
+
+/* Delay thread for specified parameter */
+add.nz.f0.0(1)  g1.2<1>UD       g1.2<0,1,0>UD   -1D             { align1 1N };
+(+f0.0) jmpi(1) -32D                                            { align1 WE_all 1N };
+
+/* Store designated "clear GRF" value */
+mov(1)          f0.1<1>UW       g1.2<0,1,0>UW                   { align1 1N };
+
+/* Initialize looping parameters */
+mov(1)          a0<1>D          0D                              { align1 1N }; /* Initialize a0.0:w=0 */
+mov(1)          a0.4<1>W        127W                            { align1 1N }; /* Loop count. Each loop contains 16 GRF's */
+
+/* Write 32x16 all "0" block */
+mov(8)          g2<1>UD         g0<8,8,1>UD                     { align1 1Q };
+mov(8)          g127<1>UD       g0<8,8,1>UD                     { align1 1Q };
+mov(2)          g2<1>UD         g1<2,2,1>UW                     { align1 1N };
+mov(1)          g2.2<1>UD       0x000f000fUD                    { align1 1N }; /* Block size (16x16) */
+and(1)          g2.3<1>UD       g2.3<0,1,0>UW   0xffffffefUD    { align1 1N };
+mov(16)         g3<1>UD         0x00000000UD                    { align1 1H };
+mov(16)         g4<1>UD         0x00000000UD                    { align1 1H };
+mov(16)         g5<1>UD         0x00000000UD                    { align1 1H };
+mov(16)         g6<1>UD         0x00000000UD                    { align1 1H };
+mov(16)         g7<1>UD         0x00000000UD                    { align1 1H };
+mov(16)         g8<1>UD         0x00000000UD                    { align1 1H };
+mov(16)         g9<1>UD         0x00000000UD                    { align1 1H };
+mov(16)         g10<1>UD        0x00000000UD                    { align1 1H };
+sendc(8)        null<1>UD       g2<8,8,1>F      0x120a8000
+                            render MsgDesc: media block write MsgCtrl = 0x0 Surface = 0 mlen 9 rlen 0 { align1 1Q };
+add(1)          g2<1>UD         g1<0,1,0>UW     0x0010UW        { align1 1N };
+sendc(8)        null<1>UD       g2<8,8,1>F      0x120a8000
+                            render MsgDesc: media block write MsgCtrl = 0x0 Surface = 0 mlen 9 rlen 0 { align1 1Q };
+
+/* Now, clear all GRF registers */
+add.nz.f0.0(1)  a0.4<1>W        a0.4<0,1,0>W    -1W             { align1 1N };
+mov(16)         g[a0]<1>UW      f0.1<0,1,0>UW                   { align1 1H };
+add(1)          a0<1>D          a0<0,1,0>D      32D             { align1 1N };
+(+f0.0) jmpi(1) -64D                                            { align1 WE_all 1N };
+
+/* Terminante the thread */
+sendc(8)        null<1>UD       g127<8,8,1>F    0x82000010
+                            thread_spawner MsgDesc: mlen 1 rlen 0           { align1 1Q EOT };
diff --git a/drivers/gpu/drm/i915/gt/shaders/clear_kernel/ivb.asm b/drivers/gpu/drm/i915/gt/shaders/clear_kernel/ivb.asm
new file mode 100644
index 0000000..97c7ac9
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/shaders/clear_kernel/ivb.asm
@@ -0,0 +1,117 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2020 Intel Corporation
+ */
+
+/*
+ * Kernel for PAVP buffer clear.
+ *
+ *	1. Clear all 64 GRF registers assigned to the kernel with designated value;
+ *	2. Write 32x16 block of all "0" to render target buffer which indirectly clears
+ *	   512 bytes of Render Cache.
+ */
+
+/* Store designated "clear GRF" value */
+mov(1)          f0.1<1>UW       g1.2<0,1,0>UW                   { align1 1N };
+
+/**
+ * Curbe Format
+ *
+ * DW 1.0 - Block Offset to write Render Cache
+ * DW 1.1 [15:0] - Clear Word
+ * DW 1.2 - Delay iterations
+ * DW 1.3 - Enable Instrumentation (only for debug)
+ * DW 1.4 - Rsvd (intended for context ID)
+ * DW 1.5 - [31:16]:SliceCount, [15:0]:SubSlicePerSliceCount
+ * DW 1.6 - Rsvd MBZ (intended for Enable Wait on Total Thread Count)
+ * DW 1.7 - Rsvd MBZ (inteded for Total Thread Count)
+ *
+ * Binding Table
+ *
+ * BTI 0: 2D Surface to help clear L3 (Render/Data Cache)
+ * BTI 1: Wait/Instrumentation Buffer
+ *  Size : (SliceCount * SubSliceCount  * 16 EUs/SubSlice) rows * (16 threads/EU) cols (Format R32_UINT)
+ *         Expected to be initialized to 0 by driver/another kernel
+ *  Layout :
+ *           RowN: Histogram for EU-N: (SliceID*SubSlicePerSliceCount + SSID)*16 + EUID [assume max 16 EUs / SS]
+ *           Col-k[DW-k]: Threads Executed on ThreadID-k for EU-N
+ */
+add(1)          g1.2<1>UD       g1.2<0,1,0>UD   0x00000001UD    { align1 1N }; /* Loop count to delay kernel: Init to (g1.2 + 1) */
+cmp.z.f0.0(1)   null<1>UD       g1.3<0,1,0>UD   0x00000000UD    { align1 1N };
+(+f0.0) jmpi(1) 44D                                             { align1 WE_all 1N };
+
+/**
+ * State Register has info on where this thread is running
+ *	IVB: sr0.0 :: [15:13]: MBZ, 12: HSID (Half-Slice ID), [11:8]EUID, [2:0] ThreadSlotID
+ *	HSW: sr0.0 :: 15: MBZ, [14:13]: SliceID, 12: HSID (Half-Slice ID), [11:8]EUID, [2:0] ThreadSlotID
+ */
+mov(8)          g3<1>UD         0x00000000UD                    { align1 1Q };
+shr(1)          g3<1>D          sr0<0,1,0>D     12D             { align1 1N };
+and(1)          g3<1>D          g3<0,1,0>D      1D              { align1 1N }; /* g3 has HSID */
+shr(1)          g3.1<1>D        sr0<0,1,0>D     13D             { align1 1N };
+and(1)          g3.1<1>D        g3.1<0,1,0>D    3D              { align1 1N }; /* g3.1 has sliceID */
+mul(1)          g3.5<1>D        g3.1<0,1,0>D    g1.10<0,1,0>UW  { align1 1N };
+add(1)          g3<1>D          g3<0,1,0>D      g3.5<0,1,0>D    { align1 1N }; /* g3 = sliceID * SubSlicePerSliceCount + HSID */
+shr(1)          g3.2<1>D        sr0<0,1,0>D     8D              { align1 1N };
+and(1)          g3.2<1>D        g3.2<0,1,0>D    15D             { align1 1N }; /* g3.2 = EUID */
+mul(1)          g3.4<1>D        g3<0,1,0>D      16D             { align1 1N };
+add(1)          g3.2<1>D        g3.2<0,1,0>D    g3.4<0,1,0>D    { align1 1N }; /* g3.2 now points to EU row number (Y-pixel = V address )  in instrumentation surf */
+
+mov(8)          g5<1>UD         0x00000000UD                    { align1 1Q };
+and(1)          g3.3<1>D        sr0<0,1,0>D     7D              { align1 1N };
+mul(1)          g3.3<1>D        g3.3<0,1,0>D    4D              { align1 1N };
+
+mov(8)          g4<1>UD         g0<8,8,1>UD                     { align1 1Q }; /* Initialize message header with g0 */
+mov(1)          g4<1>UD         g3.3<0,1,0>UD                   { align1 1N }; /* Block offset */
+mov(1)          g4.1<1>UD       g3.2<0,1,0>UD                   { align1 1N }; /* Block offset */
+mov(1)          g4.2<1>UD       0x00000003UD                    { align1 1N }; /* Block size (1 row x 4 bytes) */
+and(1)          g4.3<1>UD       g4.3<0,1,0>UW   0xffffffffUD    { align1 1N };
+
+/* Media block read to fetch current value at specified location in instrumentation buffer */
+sendc(8)        g5<1>UD         g4<8,8,1>F      0x02190001
+                            render MsgDesc: media block read MsgCtrl = 0x0 Surface = 1 mlen 1 rlen 1 { align1 1Q };
+add(1)          g5<1>D          g5<0,1,0>D      1D              { align1 1N };
+
+/* Media block write for updated value at specified location in instrumentation buffer */
+sendc(8)        g5<1>UD         g4<8,8,1>F      0x040a8001
+                            render MsgDesc: media block write MsgCtrl = 0x0 Surface = 1 mlen 2 rlen 0 { align1 1Q };
+/* Delay thread for specified parameter */
+add.nz.f0.0(1)  g1.2<1>UD       g1.2<0,1,0>UD   -1D             { align1 1N };
+(+f0.0) jmpi(1) -4D                                             { align1 WE_all 1N };
+
+/* Store designated "clear GRF" value */
+mov(1)          f0.1<1>UW       g1.2<0,1,0>UW                   { align1 1N };
+
+/* Initialize looping parameters */
+mov(1)          a0<1>D          0D                              { align1 1N }; /* Initialize a0.0:w=0 */
+mov(1)          a0.4<1>W        127W                            { align1 1N }; /* Loop count. Each loop contains 16 GRF's */
+
+/* Write 32x16 all "0" block */
+mov(8)          g2<1>UD         g0<8,8,1>UD                     { align1 1Q };
+mov(8)          g127<1>UD       g0<8,8,1>UD                     { align1 1Q };
+mov(2)          g2<1>UD         g1<2,2,1>UW                     { align1 1N };
+mov(1)          g2.2<1>UD       0x000f000fUD                    { align1 1N }; /* Block size (16x16) */
+and(1)          g2.3<1>UD       g2.3<0,1,0>UW   0xffffffefUD    { align1 1N };
+mov(16)         g3<1>UD         0x00000000UD                    { align1 1H };
+mov(16)         g4<1>UD         0x00000000UD                    { align1 1H };
+mov(16)         g5<1>UD         0x00000000UD                    { align1 1H };
+mov(16)         g6<1>UD         0x00000000UD                    { align1 1H };
+mov(16)         g7<1>UD         0x00000000UD                    { align1 1H };
+mov(16)         g8<1>UD         0x00000000UD                    { align1 1H };
+mov(16)         g9<1>UD         0x00000000UD                    { align1 1H };
+mov(16)         g10<1>UD        0x00000000UD                    { align1 1H };
+sendc(8)        null<1>UD       g2<8,8,1>F      0x120a8000
+                            render MsgDesc: media block write MsgCtrl = 0x0 Surface = 0 mlen 9 rlen 0 { align1 1Q };
+add(1)          g2<1>UD         g1<0,1,0>UW     0x0010UW        { align1 1N };
+sendc(8)        null<1>UD       g2<8,8,1>F      0x120a8000
+                            render MsgDesc: media block write MsgCtrl = 0x0 Surface = 0 mlen 9 rlen 0 { align1 1Q };
+
+/* Now, clear all GRF registers */
+add.nz.f0.0(1)  a0.4<1>W        a0.4<0,1,0>W    -1W             { align1 1N };
+mov(16)         g[a0]<1>UW      f0.1<0,1,0>UW                   { align1 1H };
+add(1)          a0<1>D          a0<0,1,0>D      32D             { align1 1N };
+(+f0.0) jmpi(1) -8D                                             { align1 WE_all 1N };
+
+/* Terminante the thread */
+sendc(8)        null<1>UD       g127<8,8,1>F    0x82000010
+                            thread_spawner MsgDesc: mlen 1 rlen 0           { align1 1Q EOT };
diff --git a/drivers/gpu/drm/i915/gvt/debugfs.c b/drivers/gpu/drm/i915/gvt/debugfs.c
index ec47d41..62e6a14 100644
--- a/drivers/gpu/drm/i915/gvt/debugfs.c
+++ b/drivers/gpu/drm/i915/gvt/debugfs.c
@@ -66,7 +66,7 @@
 	vreg = vgpu_vreg(param->vgpu, offset);
 
 	if (preg != vreg) {
-		node = kmalloc(sizeof(*node), GFP_KERNEL);
+		node = kmalloc(sizeof(*node), GFP_ATOMIC);
 		if (!node)
 			return -ENOMEM;
 
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 3e88e3b..fadd2ad 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -1726,13 +1726,13 @@
 		(*(u32 *)p_data) &= ~_MASKED_BIT_ENABLE(2);
 	write_vreg(vgpu, offset, p_data, bytes);
 
-	if (data & _MASKED_BIT_ENABLE(1)) {
+	if (IS_MASKED_BITS_ENABLED(data, 1)) {
 		enter_failsafe_mode(vgpu, GVT_FAILSAFE_UNSUPPORTED_GUEST);
 		return 0;
 	}
 
 	if (IS_COFFEELAKE(vgpu->gvt->gt->i915) &&
-	    data & _MASKED_BIT_ENABLE(2)) {
+	    IS_MASKED_BITS_ENABLED(data, 2)) {
 		enter_failsafe_mode(vgpu, GVT_FAILSAFE_UNSUPPORTED_GUEST);
 		return 0;
 	}
@@ -1741,14 +1741,14 @@
 	 * pvinfo, if not, we will treat this guest as non-gvtg-aware
 	 * guest, and stop emulating its cfg space, mmio, gtt, etc.
 	 */
-	if (((data & _MASKED_BIT_ENABLE(GFX_PPGTT_ENABLE)) ||
-			(data & _MASKED_BIT_ENABLE(GFX_RUN_LIST_ENABLE)))
-			&& !vgpu->pv_notified) {
+	if ((IS_MASKED_BITS_ENABLED(data, GFX_PPGTT_ENABLE) ||
+	    IS_MASKED_BITS_ENABLED(data, GFX_RUN_LIST_ENABLE)) &&
+	    !vgpu->pv_notified) {
 		enter_failsafe_mode(vgpu, GVT_FAILSAFE_UNSUPPORTED_GUEST);
 		return 0;
 	}
-	if ((data & _MASKED_BIT_ENABLE(GFX_RUN_LIST_ENABLE))
-			|| (data & _MASKED_BIT_DISABLE(GFX_RUN_LIST_ENABLE))) {
+	if (IS_MASKED_BITS_ENABLED(data, GFX_RUN_LIST_ENABLE) ||
+	    IS_MASKED_BITS_DISABLED(data, GFX_RUN_LIST_ENABLE)) {
 		enable_execlist = !!(data & GFX_RUN_LIST_ENABLE);
 
 		gvt_dbg_core("EXECLIST %s on ring %s\n",
@@ -1809,7 +1809,7 @@
 	write_vreg(vgpu, offset, p_data, bytes);
 	data = vgpu_vreg(vgpu, offset);
 
-	if (data & _MASKED_BIT_ENABLE(RESET_CTL_REQUEST_RESET))
+	if (IS_MASKED_BITS_ENABLED(data, RESET_CTL_REQUEST_RESET))
 		data |= RESET_CTL_READY_TO_RESET;
 	else if (data & _MASKED_BIT_DISABLE(RESET_CTL_REQUEST_RESET))
 		data &= ~RESET_CTL_READY_TO_RESET;
@@ -1827,7 +1827,8 @@
 	(*(u32 *)p_data) &= ~_MASKED_BIT_ENABLE(0x18);
 	write_vreg(vgpu, offset, p_data, bytes);
 
-	if (data & _MASKED_BIT_ENABLE(0x10) || data & _MASKED_BIT_ENABLE(0x8))
+	if (IS_MASKED_BITS_ENABLED(data, 0x10) ||
+	    IS_MASKED_BITS_ENABLED(data, 0x8))
 		enter_failsafe_mode(vgpu, GVT_FAILSAFE_UNSUPPORTED_GUEST);
 
 	return 0;
@@ -3055,6 +3056,7 @@
 	MMIO_D(_MMIO(0x72380), D_SKL_PLUS);
 	MMIO_D(_MMIO(0x7239c), D_SKL_PLUS);
 	MMIO_D(_MMIO(_PLANE_SURF_3_A), D_SKL_PLUS);
+	MMIO_D(_MMIO(_PLANE_SURF_3_B), D_SKL_PLUS);
 
 	MMIO_D(CSR_SSP_BASE, D_SKL_PLUS);
 	MMIO_D(CSR_HTP_SKL, D_SKL_PLUS);
@@ -3131,8 +3133,8 @@
 	MMIO_DFH(GEN9_WM_CHICKEN3, D_SKL_PLUS, F_MODE_MASK | F_CMD_ACCESS,
 		 NULL, NULL);
 
-	MMIO_D(GAMT_CHKN_BIT_REG, D_KBL);
-	MMIO_D(GEN9_CTX_PREEMPT_REG, D_KBL | D_SKL);
+	MMIO_D(GAMT_CHKN_BIT_REG, D_KBL | D_CFL);
+	MMIO_D(GEN9_CTX_PREEMPT_REG, D_SKL_PLUS);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.h b/drivers/gpu/drm/i915/gvt/mmio_context.h
index 970704b..3b25e7f 100644
--- a/drivers/gpu/drm/i915/gvt/mmio_context.h
+++ b/drivers/gpu/drm/i915/gvt/mmio_context.h
@@ -54,8 +54,8 @@
 
 int intel_vgpu_restore_inhibit_context(struct intel_vgpu *vgpu,
 				       struct i915_request *req);
-#define IS_RESTORE_INHIBIT(a)	\
-	(_MASKED_BIT_ENABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT) == \
-	((a) & _MASKED_BIT_ENABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT)))
+
+#define IS_RESTORE_INHIBIT(a) \
+	IS_MASKED_BITS_ENABLED(a, CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT)
 
 #endif
diff --git a/drivers/gpu/drm/i915/gvt/reg.h b/drivers/gpu/drm/i915/gvt/reg.h
index 5b66e14..b88e033 100644
--- a/drivers/gpu/drm/i915/gvt/reg.h
+++ b/drivers/gpu/drm/i915/gvt/reg.h
@@ -94,6 +94,11 @@
 #define GFX_MODE_BIT_SET_IN_MASK(val, bit) \
 		((((bit) & 0xffff0000) == 0) && !!((val) & (((bit) << 16))))
 
+#define IS_MASKED_BITS_ENABLED(_val, _b) \
+		(((_val) & _MASKED_BIT_ENABLE(_b)) == _MASKED_BIT_ENABLE(_b))
+#define IS_MASKED_BITS_DISABLED(_val, _b) \
+		((_val) & _MASKED_BIT_DISABLE(_b))
+
 #define FORCEWAKE_RENDER_GEN9_REG 0xa278
 #define FORCEWAKE_ACK_RENDER_GEN9_REG 0x0D84
 #define FORCEWAKE_BLITTER_GEN9_REG 0xa188
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index bca036a..e7532e7 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -230,7 +230,7 @@
 	struct file_stats *stats = data;
 	struct i915_vma *vma;
 
-	if (!kref_get_unless_zero(&obj->base.refcount))
+	if (IS_ERR_OR_NULL(obj) || !kref_get_unless_zero(&obj->base.refcount))
 		return 0;
 
 	stats->count++;
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index adb9bf3..ae99a91 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -410,8 +410,6 @@
 			int adjusted_x;
 			int adjusted_y;
 
-			int y;
-
 			u16 pixel_blend_mode;
 		} plane;
 
@@ -420,6 +418,8 @@
 			unsigned int stride;
 			u64 modifier;
 		} fb;
+
+		unsigned int fence_y_offset;
 		u16 gen9_wa_cfb_stride;
 		s8 fence_id;
 	} state_cache;
@@ -435,15 +435,16 @@
 		struct {
 			enum pipe pipe;
 			enum i9xx_plane_id i9xx_plane;
-			unsigned int fence_y_offset;
 		} crtc;
 
 		struct {