Linux 6.1-rc3

-----BEGIN PGP SIGNATURE-----
 
 iQFSBAABCAA8FiEEq68RxlopcLEwq+PEeb4+QwBBGIYFAmNe+HAeHHRvcnZhbGRz
 QGxpbnV4LWZvdW5kYXRpb24ub3JnAAoJEHm+PkMAQRiGrFwH/jYeSZl8ACW2GR7r
 8zsyHK/qy7tOmwV99QZjS94b1KK1hfi2L93Ro8LXohqI3HDvk6eBXWApz3jSicFW
 OeTCq1vu2Bw1iimhUThVqVCWF8EaVwdYYobvNqIznA2QCkOO+oTG+3oIiWJaEOVE
 xKJypq95b16D0KAGXrgZznjdBi2DlOUzdsjNT3E8xSXeEjvX7y7optHhuMlCgir4
 19kEgelGAOp28rd5l0qZ2pt0ltMN+COx4EF8LCNvsD2kvXPbyDN/V2Ql04mYBMde
 hriWyP5W0WDOCvjrcxV4CgyosZ2UgkfAdZ1JTJQi3RkfJ1B52BpyfRiBkfQeqcC+
 RoHbW7w=
 =RWs8
 -----END PGP SIGNATURE-----

Merge 6.1-rc3 into usb-next

We need the USB fixes in here as well.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

.mailmap

@@ -104,6 +104,7 @@ Christoph Hellwig <hch@lst.de>
 Colin Ian King <colin.i.king@gmail.com> <colin.king@canonical.com>
 Corey Minyard <minyard@acm.org>
 Damian Hobson-Garcia <dhobsong@igel.co.jp>
+Dan Carpenter <error27@gmail.com> <dan.carpenter@oracle.com>
 Daniel Borkmann <daniel@iogearbox.net> <danborkmann@googlemail.com>
 Daniel Borkmann <daniel@iogearbox.net> <danborkmann@iogearbox.net>
 Daniel Borkmann <daniel@iogearbox.net> <daniel.borkmann@tik.ee.ethz.ch>
@@ -353,7 +354,8 @@ Peter Oruba <peter@oruba.de>
 Pratyush Anand <pratyush.anand@gmail.com> <pratyush.anand@st.com>
 Praveen BP <praveenbp@ti.com>
 Punit Agrawal <punitagrawal@gmail.com> <punit.agrawal@arm.com>
-Qais Yousef <qsyousef@gmail.com> <qais.yousef@imgtec.com>
+Qais Yousef <qyousef@layalina.io> <qais.yousef@imgtec.com>
+Qais Yousef <qyousef@layalina.io> <qais.yousef@arm.com>
 Quentin Monnet <quentin@isovalent.com> <quentin.monnet@netronome.com>
 Quentin Perret <qperret@qperret.net> <quentin.perret@arm.com>
 Rafael J. Wysocki <rjw@rjwysocki.net> <rjw@sisk.pl>

Documentation/ABI/testing/sysfs-kernel-mm-memory-tiers

@@ -10,7 +10,7 @@ Description:	A collection of all the memory tiers allocated.
 
 
 What:		/sys/devices/virtual/memory_tiering/memory_tierN/
-		/sys/devices/virtual/memory_tiering/memory_tierN/nodes
+		/sys/devices/virtual/memory_tiering/memory_tierN/nodelist
 Date:		August 2022
 Contact:	Linux memory management mailing list <linux-mm@kvack.org>
 Description:	Directory with details of a specific memory tier
@@ -21,5 +21,5 @@ Description:	Directory with details of a specific memory tier
 		A smaller value of N implies a higher (faster) memory tier in the
 		hierarchy.
 
-		nodes: NUMA nodes that are part of this memory tier.
+		nodelist: NUMA nodes that are part of this memory tier.
 

Documentation/admin-guide/acpi/index.rst

@@ -9,7 +9,6 @@ the Linux ACPI support.
    :maxdepth: 1
 
    initrd_table_override
-   dsdt-override
    ssdt-overlays
    cppc_sysfs
    fan_performance_states

Documentation/admin-guide/device-mapper/verity.rst

@@ -141,6 +141,10 @@ root_hash_sig_key_desc <key_description>
     also gain new certificates at run time if they are signed by a certificate
     already in the secondary trusted keyring.
 
+try_verify_in_tasklet
+    If verity hashes are in cache, verify data blocks in kernel tasklet instead
+    of workqueue. This option can reduce IO latency.
+
 Theory of operation
 ===================
 

Documentation/admin-guide/media/vivid.rst

@@ -1318,7 +1318,7 @@ instance. This setup would require the following commands:
 	$ v4l2-ctl -d2 -i2
 	$ v4l2-ctl -d2 -c horizontal_movement=4
 	$ v4l2-ctl -d1 --overlay=1
-	$ v4l2-ctl -d1 -c loop_video=1
+	$ v4l2-ctl -d0 -c loop_video=1
 	$ v4l2-ctl -d2 --stream-mmap --overlay=1
 
 And from another console:

Documentation/block/ublk.rst

@@ -144,6 +144,42 @@ managing and controlling ublk devices with help of several control commands:
   For retrieving device info via ``ublksrv_ctrl_dev_info``. It is the server's
   responsibility to save IO target specific info in userspace.
 
+- ``UBLK_CMD_START_USER_RECOVERY``
+
+  This command is valid if ``UBLK_F_USER_RECOVERY`` feature is enabled. This
+  command is accepted after the old process has exited, ublk device is quiesced
+  and ``/dev/ublkc*`` is released. User should send this command before he starts
+  a new process which re-opens ``/dev/ublkc*``. When this command returns, the
+  ublk device is ready for the new process.
+
+- ``UBLK_CMD_END_USER_RECOVERY``
+
+  This command is valid if ``UBLK_F_USER_RECOVERY`` feature is enabled. This
+  command is accepted after ublk device is quiesced and a new process has
+  opened ``/dev/ublkc*`` and get all ublk queues be ready. When this command
+  returns, ublk device is unquiesced and new I/O requests are passed to the
+  new process.
+
+- user recovery feature description
+
+  Two new features are added for user recovery: ``UBLK_F_USER_RECOVERY`` and
+  ``UBLK_F_USER_RECOVERY_REISSUE``.
+
+  With ``UBLK_F_USER_RECOVERY`` set, after one ubq_daemon(ublk server's io
+  handler) is dying, ublk does not delete ``/dev/ublkb*`` during the whole
+  recovery stage and ublk device ID is kept. It is ublk server's
+  responsibility to recover the device context by its own knowledge.
+  Requests which have not been issued to userspace are requeued. Requests
+  which have been issued to userspace are aborted.
+
+  With ``UBLK_F_USER_RECOVERY_REISSUE`` set, after one ubq_daemon(ublk
+  server's io handler) is dying, contrary to ``UBLK_F_USER_RECOVERY``,
+  requests which have been issued to userspace are requeued and will be
+  re-issued to the new process after handling ``UBLK_CMD_END_USER_RECOVERY``.
+  ``UBLK_F_USER_RECOVERY_REISSUE`` is designed for backends who tolerate
+  double-write since the driver may issue the same I/O request twice. It
+  might be useful to a read-only FS or a VM backend.
+
 Data plane
 ----------
 

Documentation/core-api/kernel-api.rst

@@ -118,6 +118,12 @@ Text Searching
 CRC and Math Functions in Linux
 ===============================
 
+Arithmetic Overflow Checking
+----------------------------
+
+.. kernel-doc:: include/linux/overflow.h
+   :internal:
+
 CRC Functions
 -------------
 

Documentation/devicetree/bindings/media/i2c/dongwoon,dw9714.txt

@@ -1,9 +0,0 @@
-Dongwoon Anatech DW9714 camera voice coil lens driver
-
-DW9174 is a 10-bit DAC with current sink capability. It is intended
-for driving voice coil lenses in camera modules.
-
-Mandatory properties:
-
-- compatible: "dongwoon,dw9714"
-- reg: I²C slave address

Documentation/devicetree/bindings/media/i2c/dongwoon,dw9714.yaml

@@ -0,0 +1,47 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/media/i2c/dongwoon,dw9714.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Dongwoon Anatech DW9714 camera voice coil lens driver
+
+maintainers:
+  - Krzysztof Kozlowski <krzk@kernel.org>
+
+description:
+  DW9174 is a 10-bit DAC with current sink capability. It is intended for
+  driving voice coil lenses in camera modules.
+
+properties:
+  compatible:
+    const: dongwoon,dw9714
+
+  reg:
+    maxItems: 1
+
+  powerdown-gpios:
+    description:
+      XSD pin for shutdown (active low)
+
+  vcc-supply:
+    description: VDD power supply
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        camera-lens@c {
+            compatible = "dongwoon,dw9714";
+            reg = <0x0c>;
+            vcc-supply = <&reg_csi_1v8>;
+        };
+    };

Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml

@@ -8,7 +8,6 @@ title: Samsung S3FWRN5 NCI NFC Controller
 
 maintainers:
   - Krzysztof Kozlowski <krzk@kernel.org>
-  - Krzysztof Opasiak <k.opasiak@samsung.com>
 
 properties:
   compatible:

Documentation/devicetree/bindings/pinctrl/xlnx,zynqmp-pinctrl.yaml

@@ -274,10 +274,6 @@ patternProperties:
           slew-rate:
             enum: [0, 1]
 
-          output-enable:
-            description:
-              This will internally disable the tri-state for MIO pins.
-
           drive-strength:
             description:
               Selects the drive strength for MIO pins, in mA.

Documentation/driver-api/basics.rst

@@ -107,9 +107,6 @@ Kernel utility functions
 .. kernel-doc:: kernel/panic.c
    :export:
 
-.. kernel-doc:: include/linux/overflow.h
-   :internal:
-
 Device Resource Management
 --------------------------
 

Documentation/driver-api/media/mc-core.rst

@@ -214,18 +214,29 @@ Link properties can be modified at runtime by calling
 Pipelines and media streams
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
+A media stream is a stream of pixels or metadata originating from one or more
+source devices (such as a sensors) and flowing through media entity pads
+towards the final sinks. The stream can be modified on the route by the
+devices (e.g. scaling or pixel format conversions), or it can be split into
+multiple branches, or multiple branches can be merged.
+
+A media pipeline is a set of media streams which are interdependent. This
+interdependency can be caused by the hardware (e.g. configuration of a second
+stream cannot be changed if the first stream has been enabled) or by the driver
+due to the software design. Most commonly a media pipeline consists of a single
+stream which does not branch.
+
 When starting streaming, drivers must notify all entities in the pipeline to
 prevent link states from being modified during streaming by calling
 :c:func:`media_pipeline_start()`.
 
-The function will mark all entities connected to the given entity through
+The function will mark all the pads which are part of the pipeline as streaming.
-enabled links, either directly or indirectly, as streaming.
 
 The struct media_pipeline instance pointed to by
-the pipe argument will be stored in every entity in the pipeline.
+the pipe argument will be stored in every pad in the pipeline.
 Drivers should embed the struct media_pipeline
 in higher-level pipeline structures and can then access the
-pipeline through the struct media_entity
+pipeline through the struct media_pad
 pipe field.
 
 Calls to :c:func:`media_pipeline_start()` can be nested.

Documentation/hwmon/corsair-psu.rst

@@ -19,6 +19,8 @@ Supported devices:
 
   Corsair HX1200i
 
+  Corsair HX1500i
+
   Corsair RM550i
 
   Corsair RM650i

Documentation/process/maintainer-netdev.rst

@@ -319,3 +319,13 @@ unpatched tree to confirm infrastructure didn't mangle it.
 Finally, go back and read
 :ref:`Documentation/process/submitting-patches.rst <submittingpatches>`
 to be sure you are not repeating some common mistake documented there.
+
+My company uses peer feedback in employee performance reviews. Can I ask netdev maintainers for feedback?
+---------------------------------------------------------------------------------------------------------
+
+Yes, especially if you spend significant amount of time reviewing code
+and go out of your way to improve shared infrastructure.
+
+The feedback must be requested by you, the contributor, and will always
+be shared with you (even if you request for it to be submitted to your
+manager).

Documentation/userspace-api/media/cec.h.rst.exceptions

@@ -239,6 +239,7 @@ ignore define CEC_OP_FEAT_DEV_HAS_DECK_CONTROL
 ignore define CEC_OP_FEAT_DEV_HAS_SET_AUDIO_RATE
 ignore define CEC_OP_FEAT_DEV_SINK_HAS_ARC_TX
 ignore define CEC_OP_FEAT_DEV_SOURCE_HAS_ARC_RX
+ignore define CEC_OP_FEAT_DEV_HAS_SET_AUDIO_VOLUME_LEVEL
 
 ignore define CEC_MSG_GIVE_FEATURES
 
@@ -487,6 +488,7 @@ ignore define CEC_OP_SYS_AUD_STATUS_ON
 
 ignore define CEC_MSG_SYSTEM_AUDIO_MODE_REQUEST
 ignore define CEC_MSG_SYSTEM_AUDIO_MODE_STATUS
+ignore define CEC_MSG_SET_AUDIO_VOLUME_LEVEL
 
 ignore define CEC_OP_AUD_FMT_ID_CEA861
 ignore define CEC_OP_AUD_FMT_ID_CEA861_CXT

Documentation/userspace-api/media/v4l/libv4l-introduction.rst

@@ -136,9 +136,9 @@ V4L2 functions
 
    operates like the :c:func:`read()` function.
 
-.. c:function:: void v4l2_mmap(void *start, size_t length, int prot, int flags, int fd, int64_t offset);
+.. c:function:: void *v4l2_mmap(void *start, size_t length, int prot, int flags, int fd, int64_t offset);
 
-   operates like the :c:func:`munmap()` function.
+   operates like the :c:func:`mmap()` function.
 
 .. c:function:: int v4l2_munmap(void *_start, size_t length);
 

MAINTAINERS

@@ -4101,6 +4101,7 @@ N:	bcm7038
 N:	bcm7120
 
 BROADCOM BDC DRIVER
+M:	Justin Chen <justinpopo6@gmail.com>
 M:	Al Cooper <alcooperx@gmail.com>
 L:	linux-usb@vger.kernel.org
 R:	Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
@@ -4207,6 +4208,7 @@ F:	Documentation/devicetree/bindings/serial/brcm,bcm7271-uart.yaml
 F:	drivers/tty/serial/8250/8250_bcm7271.c
 
 BROADCOM BRCMSTB USB EHCI DRIVER
+M:	Justin Chen <justinpopo6@gmail.com>
 M:	Al Cooper <alcooperx@gmail.com>
 R:	Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
 L:	linux-usb@vger.kernel.org
@@ -4223,6 +4225,7 @@ F:	Documentation/devicetree/bindings/usb/brcm,usb-pinmap.yaml
 F:	drivers/usb/misc/brcmstb-usb-pinmap.c
 
 BROADCOM BRCMSTB USB2 and USB3 PHY DRIVER
+M:	Justin Chen <justinpopo6@gmail.com>
 M:	Al Cooper <alcooperx@gmail.com>
 R:	Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
 L:	linux-kernel@vger.kernel.org
@@ -4459,13 +4462,15 @@ M:	Josef Bacik <josef@toxicpanda.com>
 M:	David Sterba <dsterba@suse.com>
 L:	linux-btrfs@vger.kernel.org
 S:	Maintained
-W:	http://btrfs.wiki.kernel.org/
+W:	https://btrfs.readthedocs.io
-Q:	http://patchwork.kernel.org/project/linux-btrfs/list/
+W:	https://btrfs.wiki.kernel.org/
+Q:	https://patchwork.kernel.org/project/linux-btrfs/list/
 C:	irc://irc.libera.chat/btrfs
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux.git
 F:	Documentation/filesystems/btrfs.rst
 F:	fs/btrfs/
 F:	include/linux/btrfs*
+F:	include/trace/events/btrfs.h
 F:	include/uapi/linux/btrfs*
 
 BTTV VIDEO4LINUX DRIVER
@@ -5266,6 +5271,7 @@ F:	tools/testing/selftests/cgroup/
 
 CONTROL GROUP - BLOCK IO CONTROLLER (BLKIO)
 M:	Tejun Heo <tj@kernel.org>
+M:	Josef Bacik <josef@toxicpanda.com>
 M:	Jens Axboe <axboe@kernel.dk>
 L:	cgroups@vger.kernel.org
 L:	linux-block@vger.kernel.org
@@ -5273,6 +5279,7 @@ T:	git git://git.kernel.dk/linux-block
 F:	Documentation/admin-guide/cgroup-v1/blkio-controller.rst
 F:	block/bfq-cgroup.c
 F:	block/blk-cgroup.c
+F:	block/blk-iocost.c
 F:	block/blk-iolatency.c
 F:	block/blk-throttle.c
 F:	include/linux/blk-cgroup.h
@@ -6280,7 +6287,7 @@ M:	Sakari Ailus <sakari.ailus@linux.intel.com>
 L:	linux-media@vger.kernel.org
 S:	Maintained
 T:	git git://linuxtv.org/media_tree.git
-F:	Documentation/devicetree/bindings/media/i2c/dongwoon,dw9714.txt
+F:	Documentation/devicetree/bindings/media/i2c/dongwoon,dw9714.yaml
 F:	drivers/media/i2c/dw9714.c
 
 DONGWOON DW9768 LENS VOICE COIL DRIVER
@@ -11254,7 +11261,6 @@ M:	Claudio Imbrenda <imbrenda@linux.ibm.com>
 R:	David Hildenbrand <david@redhat.com>
 L:	kvm@vger.kernel.org
 S:	Supported
-W:	http://www.ibm.com/developerworks/linux/linux390/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux.git
 F:	Documentation/virt/kvm/s390*
 F:	arch/s390/include/asm/gmap.h
@@ -14520,7 +14526,7 @@ L:	linux-nilfs@vger.kernel.org
 S:	Supported
 W:	https://nilfs.sourceforge.io/
 W:	https://nilfs.osdn.jp/
-T:	git git://github.com/konis/nilfs2.git
+T:	git https://github.com/konis/nilfs2.git
 F:	Documentation/filesystems/nilfs2.rst
 F:	fs/nilfs2/
 F:	include/trace/events/nilfs2.h
@@ -14709,6 +14715,12 @@ F:	drivers/nvme/target/auth.c
 F:	drivers/nvme/target/fabrics-cmd-auth.c
 F:	include/linux/nvme-auth.h
 
+NVM EXPRESS HARDWARE MONITORING SUPPORT
+M:	Guenter Roeck <linux@roeck-us.net>
+L:	linux-nvme@lists.infradead.org
+S:	Supported
+F:	drivers/nvme/host/hwmon.c
+
 NVM EXPRESS FC TRANSPORT DRIVERS
 M:	James Smart <james.smart@broadcom.com>
 L:	linux-nvme@lists.infradead.org
@@ -15426,6 +15438,7 @@ S:	Maintained
 W:	http://openvswitch.org
 F:	include/uapi/linux/openvswitch.h
 F:	net/openvswitch/
+F:	tools/testing/selftests/net/openvswitch/
 
 OPERATING PERFORMANCE POINTS (OPP)
 M:	Viresh Kumar <vireshk@kernel.org>
@@ -15839,7 +15852,7 @@ F:	Documentation/devicetree/bindings/pci/snps,dw-pcie-ep.yaml
 F:	drivers/pci/controller/dwc/*designware*
 
 PCI DRIVER FOR TI DRA7XX/J721E
-M:	Kishon Vijay Abraham I <kishon@ti.com>
+M:	Vignesh Raghavendra <vigneshr@ti.com>
 L:	linux-omap@vger.kernel.org
 L:	linux-pci@vger.kernel.org
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -15856,10 +15869,10 @@ F:	Documentation/devicetree/bindings/pci/v3-v360epc-pci.txt
 F:	drivers/pci/controller/pci-v3-semi.c
 
 PCI ENDPOINT SUBSYSTEM
-M:	Kishon Vijay Abraham I <kishon@ti.com>
 M:	Lorenzo Pieralisi <lpieralisi@kernel.org>
 R:	Krzysztof Wilczyński <kw@linux.com>
 R:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+R:	Kishon Vijay Abraham I <kishon@kernel.org>
 L:	linux-pci@vger.kernel.org
 S:	Supported
 Q:	https://patchwork.kernel.org/project/linux-pci/list/
@@ -16665,6 +16678,7 @@ F:	Documentation/driver-api/ptp.rst
 F:	drivers/net/phy/dp83640*
 F:	drivers/ptp/*
 F:	include/linux/ptp_cl*
+K:	(?:\b|_)ptp(?:\b|_)
 
 PTP VIRTUAL CLOCK SUPPORT
 M:	Yangbo Lu <yangbo.lu@nxp.com>
@@ -17801,7 +17815,7 @@ S:	Odd Fixes
 F:	drivers/tty/serial/rp2.*
 
 ROHM BD99954 CHARGER IC
-R:	Matti Vaittinen <mazziesaccount@gmail.com>
+M:	Matti Vaittinen <mazziesaccount@gmail.com>
 S:	Supported
 F:	drivers/power/supply/bd99954-charger.c
 F:	drivers/power/supply/bd99954-charger.h
@@ -17824,7 +17838,7 @@ F:	drivers/regulator/bd9571mwv-regulator.c
 F:	include/linux/mfd/bd9571mwv.h
 
 ROHM POWER MANAGEMENT IC DEVICE DRIVERS
-R:	Matti Vaittinen <mazziesaccount@gmail.com>
+M:	Matti Vaittinen <mazziesaccount@gmail.com>
 S:	Supported
 F:	drivers/clk/clk-bd718x7.c
 F:	drivers/gpio/gpio-bd71815.c
@@ -17986,7 +18000,6 @@ R:	Christian Borntraeger <borntraeger@linux.ibm.com>
 R:	Sven Schnelle <svens@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 S:	Supported
-W:	http://www.ibm.com/developerworks/linux/linux390/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux.git
 F:	Documentation/driver-api/s390-drivers.rst
 F:	Documentation/s390/
@@ -17998,7 +18011,6 @@ M:	Vineeth Vijayan <vneethv@linux.ibm.com>
 M:	Peter Oberparleiter <oberpar@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 S:	Supported
-W:	http://www.ibm.com/developerworks/linux/linux390/
 F:	drivers/s390/cio/
 
 S390 DASD DRIVER
@@ -18006,7 +18018,6 @@ M:	Stefan Haberland <sth@linux.ibm.com>
 M:	Jan Hoeppner <hoeppner@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 S:	Supported
-W:	http://www.ibm.com/developerworks/linux/linux390/
 F:	block/partitions/ibm.c
 F:	drivers/s390/block/dasd*
 F:	include/linux/dasd_mod.h
@@ -18016,7 +18027,6 @@ 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/
 F:	drivers/iommu/s390-iommu.c
 
 S390 IUCV NETWORK LAYER
@@ -18025,7 +18035,6 @@ M:	Wenjia Zhang <wenjia@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 L:	netdev@vger.kernel.org
 S:	Supported
-W:	http://www.ibm.com/developerworks/linux/linux390/
 F:	drivers/s390/net/*iucv*
 F:	include/net/iucv/
 F:	net/iucv/
@@ -18036,7 +18045,6 @@ M:	Wenjia Zhang <wenjia@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 L:	netdev@vger.kernel.org
 S:	Supported
-W:	http://www.ibm.com/developerworks/linux/linux390/
 F:	drivers/s390/net/
 
 S390 PCI SUBSYSTEM
@@ -18044,7 +18052,6 @@ M:	Niklas Schnelle <schnelle@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/
 F:	arch/s390/pci/
 F:	drivers/pci/hotplug/s390_pci_hpc.c
 F:	Documentation/s390/pci.rst
@@ -18055,7 +18062,6 @@ M:	Halil Pasic <pasic@linux.ibm.com>
 M:	Jason Herne <jjherne@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 S:	Supported
-W:	http://www.ibm.com/developerworks/linux/linux390/
 F:	Documentation/s390/vfio-ap*
 F:	drivers/s390/crypto/vfio_ap*
 
@@ -18084,7 +18090,6 @@ S390 ZCRYPT DRIVER
 M:	Harald Freudenberger <freude@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 S:	Supported
-W:	http://www.ibm.com/developerworks/linux/linux390/
 F:	drivers/s390/crypto/
 
 S390 ZFCP DRIVER
@@ -18092,7 +18097,6 @@ M:	Steffen Maier <maier@linux.ibm.com>
 M:	Benjamin Block <bblock@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 S:	Supported
-W:	http://www.ibm.com/developerworks/linux/linux390/
 F:	drivers/s390/scsi/zfcp_*
 
 S3C ADC BATTERY DRIVER
@@ -18131,7 +18135,6 @@ L:	linux-media@vger.kernel.org
 S:	Maintained
 T:	git git://linuxtv.org/media_tree.git
 F:	drivers/staging/media/deprecated/saa7146/
-F:	include/media/drv-intf/saa7146*
 
 SAFESETID SECURITY MODULE
 M:	Micah Morton <mortonm@chromium.org>
@@ -18211,7 +18214,6 @@ F:	include/media/drv-intf/s3c_camif.h
 
 SAMSUNG S3FWRN5 NFC DRIVER
 M:	Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
-M:	Krzysztof Opasiak <k.opasiak@samsung.com>
 L:	linux-nfc@lists.01.org (subscribers-only)
 S:	Maintained
 F:	Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml
@@ -18666,7 +18668,6 @@ M:	Wenjia Zhang <wenjia@linux.ibm.com>
 M:	Jan Karcher <jaka@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 S:	Supported
-W:	http://www.ibm.com/developerworks/linux/linux390/
 F:	net/smc/
 
 SHARP GP2AP002A00F/GP2AP002S00F SENSOR DRIVER
@@ -18777,7 +18778,7 @@ M:	Palmer Dabbelt <palmer@dabbelt.com>
 M:	Paul Walmsley <paul.walmsley@sifive.com>
 L:	linux-riscv@lists.infradead.org
 S:	Supported
-T:	git git://github.com/sifive/riscv-linux.git
+T:	git https://github.com/sifive/riscv-linux.git
 N:	sifive
 K:	[^@]sifive
 
@@ -21181,15 +21182,6 @@ S:	Maintained
 F:	Documentation/usb/ehci.rst
 F:	drivers/usb/host/ehci*
 
-USB GADGET/PERIPHERAL SUBSYSTEM
-M:	Felipe Balbi <balbi@kernel.org>
-L:	linux-usb@vger.kernel.org
-S:	Maintained
-W:	http://www.linux-usb.org/gadget
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb.git
-F:	drivers/usb/gadget/
-F:	include/linux/usb/gadget*
-
 USB HID/HIDBP DRIVERS (USB KEYBOARDS, MICE, REMOTE CONTROLS, ...)
 M:	Jiri Kosina <jikos@kernel.org>
 M:	Benjamin Tissoires <benjamin.tissoires@redhat.com>
@@ -21293,16 +21285,9 @@ L:	linux-usb@vger.kernel.org
 L:	netdev@vger.kernel.org
 S:	Maintained
 W:	https://github.com/petkan/pegasus
-T:	git git://github.com/petkan/pegasus.git
+T:	git https://github.com/petkan/pegasus.git
 F:	drivers/net/usb/pegasus.*
 
-USB PHY LAYER
-M:	Felipe Balbi <balbi@kernel.org>
-L:	linux-usb@vger.kernel.org
-S:	Maintained
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb.git
-F:	drivers/usb/phy/
-
 USB PRINTER DRIVER (usblp)
 M:	Pete Zaitcev <zaitcev@redhat.com>
 L:	linux-usb@vger.kernel.org
@@ -21330,7 +21315,7 @@ L:	linux-usb@vger.kernel.org
 L:	netdev@vger.kernel.org
 S:	Maintained
 W:	https://github.com/petkan/rtl8150
-T:	git git://github.com/petkan/rtl8150.git
+T:	git https://github.com/petkan/rtl8150.git
 F:	drivers/net/usb/rtl8150.c
 
 USB SERIAL SUBSYSTEM
@@ -22121,6 +22106,7 @@ F:	Documentation/watchdog/
 F:	drivers/watchdog/
 F:	include/linux/watchdog.h
 F:	include/uapi/linux/watchdog.h
+F:	include/trace/events/watchdog.h
 
 WHISKEYCOVE PMIC GPIO DRIVER
 M:	Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
@@ -22761,7 +22747,7 @@ S:	Maintained
 W:	http://mjpeg.sourceforge.net/driver-zoran/
 Q:	https://patchwork.linuxtv.org/project/linux-media/list/
 F:	Documentation/driver-api/media/drivers/zoran.rst
-F:	drivers/staging/media/zoran/
+F:	drivers/media/pci/zoran/
 
 ZRAM COMPRESSED RAM BLOCK DEVICE DRVIER
 M:	Minchan Kim <minchan@kernel.org>

Makefile

@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 1
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc3
 NAME = Hurr durr I'ma ninja sloth
 
 # *DOCUMENTATION*

arch/arc/boot/dts/axc003.dtsi

@@ -103,11 +103,11 @@
 			dma-coherent;
 		};
 
-		ehci@40000 {
+		usb@40000 {
 			dma-coherent;
 		};
 
-		ohci@60000 {
+		usb@60000 {
 			dma-coherent;
 		};
 

arch/arc/boot/dts/axc003_idu.dtsi

@@ -110,11 +110,11 @@
 			dma-coherent;
 		};
 
-		ehci@40000 {
+		usb@40000 {
 			dma-coherent;
 		};
 
-		ohci@60000 {
+		usb@60000 {
 			dma-coherent;
 		};
 

arch/arc/boot/dts/axs10x_mb.dtsi

@@ -87,13 +87,13 @@
 			mac-address = [00 00 00 00 00 00]; /* Filled in by U-Boot */
 		};
 
-		ehci@40000 {
+		usb@40000 {
 			compatible = "generic-ehci";
 			reg = < 0x40000 0x100 >;
 			interrupts = < 8 >;
 		};
 
-		ohci@60000 {
+		usb@60000 {
 			compatible = "generic-ohci";
 			reg = < 0x60000 0x100 >;
 			interrupts = < 8 >;

arch/arc/boot/dts/hsdk.dts

@@ -234,7 +234,7 @@
 			};
 		};
 
-		ohci@60000 {
+		usb@60000 {
 			compatible = "snps,hsdk-v1.0-ohci", "generic-ohci";
 			reg = <0x60000 0x100>;
 			interrupts = <15>;
@@ -242,7 +242,7 @@
 			dma-coherent;
 		};
 
-		ehci@40000 {
+		usb@40000 {
 			compatible = "snps,hsdk-v1.0-ehci", "generic-ehci";
 			reg = <0x40000 0x100>;
 			interrupts = <15>;

arch/arc/boot/dts/vdk_axs10x_mb.dtsi

@@ -46,7 +46,7 @@
 			clock-names = "stmmaceth";
 		};
 
-		ehci@40000 {
+		usb@40000 {
 			compatible = "generic-ehci";
 			reg = < 0x40000 0x100 >;
 			interrupts = < 8 >;

arch/arc/configs/axs101_defconfig

@@ -35,9 +35,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_IP_PNP_RARP=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
 CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
@@ -99,7 +96,6 @@ CONFIG_NFS_FS=y
 CONFIG_NFS_V3_ACL=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
-# CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_STRIP_ASM_SYMS=y
 CONFIG_SOFTLOCKUP_DETECTOR=y
 CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10

arch/arc/configs/axs103_defconfig

@@ -34,9 +34,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_IP_PNP_RARP=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
 CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
@@ -97,7 +94,6 @@ CONFIG_NFS_FS=y
 CONFIG_NFS_V3_ACL=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
-# CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_STRIP_ASM_SYMS=y
 CONFIG_SOFTLOCKUP_DETECTOR=y
 CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10

arch/arc/configs/axs103_smp_defconfig

@@ -35,9 +35,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_IP_PNP_RARP=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
 CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
@@ -100,7 +97,6 @@ CONFIG_NFS_FS=y
 CONFIG_NFS_V3_ACL=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
-# CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_STRIP_ASM_SYMS=y
 CONFIG_SOFTLOCKUP_DETECTOR=y
 CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10

arch/arc/configs/haps_hs_defconfig

@@ -59,6 +59,5 @@ CONFIG_EXT2_FS_XATTR=y
 CONFIG_TMPFS=y
 # CONFIG_MISC_FILESYSTEMS is not set
 CONFIG_NFS_FS=y
-# CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_DEBUG_MEMORY_INIT=y
 # CONFIG_DEBUG_PREEMPT is not set

arch/arc/configs/haps_hs_smp_defconfig

@@ -59,6 +59,5 @@ CONFIG_EXT2_FS_XATTR=y
 CONFIG_TMPFS=y
 # CONFIG_MISC_FILESYSTEMS is not set
 CONFIG_NFS_FS=y
-# CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_SOFTLOCKUP_DETECTOR=y
 # CONFIG_DEBUG_PREEMPT is not set

arch/arc/configs/hsdk_defconfig

@@ -85,7 +85,6 @@ CONFIG_NFS_FS=y
 CONFIG_NFS_V3_ACL=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
-# CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_STRIP_ASM_SYMS=y
 CONFIG_SOFTLOCKUP_DETECTOR=y
 CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10

arch/arc/configs/nsim_700_defconfig

@@ -56,5 +56,4 @@ CONFIG_EXT2_FS_XATTR=y
 CONFIG_TMPFS=y
 # CONFIG_MISC_FILESYSTEMS is not set
 CONFIG_NFS_FS=y
-# CONFIG_ENABLE_MUST_CHECK is not set
 # CONFIG_DEBUG_PREEMPT is not set

arch/arc/configs/nsimosci_defconfig

@@ -65,4 +65,3 @@ CONFIG_TMPFS=y
 # CONFIG_MISC_FILESYSTEMS is not set
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3_ACL=y
-# CONFIG_ENABLE_MUST_CHECK is not set

arch/arc/configs/nsimosci_hs_defconfig

@@ -63,4 +63,3 @@ CONFIG_TMPFS=y
 # CONFIG_MISC_FILESYSTEMS is not set
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3_ACL=y
-# CONFIG_ENABLE_MUST_CHECK is not set

arch/arc/configs/nsimosci_hs_smp_defconfig

@@ -26,9 +26,6 @@ CONFIG_UNIX=y
 CONFIG_UNIX_DIAG=y
 CONFIG_NET_KEY=y
 CONFIG_INET=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_IPV6 is not set
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
@@ -37,7 +34,6 @@ CONFIG_DEVTMPFS=y
 # CONFIG_BLK_DEV is not set
 CONFIG_NETDEVICES=y
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 CONFIG_EZCHIP_NPS_MANAGEMENT_ENET=y
 # CONFIG_NET_VENDOR_INTEL is not set
@@ -74,5 +70,5 @@ CONFIG_TMPFS=y
 # CONFIG_MISC_FILESYSTEMS is not set
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3_ACL=y
-# CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_FTRACE=y
+# CONFIG_NET_VENDOR_CADENCE is not set

arch/arc/configs/tb10x_defconfig

@@ -35,15 +35,11 @@ CONFIG_PACKET=y
 CONFIG_UNIX=y
 CONFIG_INET=y
 CONFIG_IP_MULTICAST=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
 # CONFIG_INET_DIAG is not set
 # CONFIG_IPV6 is not set
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
 CONFIG_NETDEVICES=y
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
@@ -94,12 +90,11 @@ CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
 CONFIG_STRIP_ASM_SYMS=y
 CONFIG_DEBUG_FS=y
 CONFIG_HEADERS_INSTALL=y
-CONFIG_HEADERS_CHECK=y
 CONFIG_DEBUG_SECTION_MISMATCH=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_MEMORY_INIT=y
 CONFIG_DEBUG_STACKOVERFLOW=y
 CONFIG_DETECT_HUNG_TASK=y
 CONFIG_SCHEDSTATS=y
-CONFIG_TIMER_STATS=y
 # CONFIG_CRYPTO_HW is not set
+# CONFIG_NET_VENDOR_CADENCE is not set

arch/arc/configs/vdk_hs38_defconfig

@@ -58,8 +58,6 @@ CONFIG_SERIAL_OF_PLATFORM=y
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
 CONFIG_FB=y
-CONFIG_ARCPGU_RGB888=y
-CONFIG_ARCPGU_DISPTYPE=0
 # CONFIG_VGA_CONSOLE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
@@ -87,7 +85,6 @@ CONFIG_NFS_FS=y
 CONFIG_NFS_V3_ACL=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
-# CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_STRIP_ASM_SYMS=y
 CONFIG_DEBUG_SHIRQ=y
 CONFIG_SOFTLOCKUP_DETECTOR=y

arch/arc/configs/vdk_hs38_smp_defconfig

@@ -91,7 +91,6 @@ CONFIG_NFS_FS=y
 CONFIG_NFS_V3_ACL=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
-# CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_STRIP_ASM_SYMS=y
 CONFIG_DEBUG_SHIRQ=y
 CONFIG_SOFTLOCKUP_DETECTOR=y

arch/arc/include/asm/bitops.h

@@ -82,7 +82,7 @@ static inline __attribute__ ((const)) int fls(unsigned int x)
 /*
  * __fls: Similar to fls, but zero based (0-31)
  */
-static inline __attribute__ ((const)) int __fls(unsigned long x)
+static inline __attribute__ ((const)) unsigned long __fls(unsigned long x)
 {
 	if (!x)
 		return 0;
@@ -131,7 +131,7 @@ static inline __attribute__ ((const)) int fls(unsigned int x)
 /*
  * __fls: Similar to fls, but zero based (0-31). Also 0 if no bit set
  */
-static inline __attribute__ ((const)) int __fls(unsigned long x)
+static inline __attribute__ ((const)) unsigned long __fls(unsigned long x)
 {
 	/* FLS insn has exactly same semantics as the API */
 	return	__builtin_arc_fls(x);

arch/arc/include/asm/entry-compact.h

@@ -21,7 +21,7 @@
  *      r25 contains the kernel current task ptr
  *  - Defined Stack Switching Macro to be reused in all intr/excp hdlrs
  *  - Shaved off 11 instructions from RESTORE_ALL_INT1 by using the
- *      address Write back load ld.ab instead of seperate ld/add instn
+ *      address Write back load ld.ab instead of separate ld/add instn
  *
  * Amit Bhor, Sameer Dhavale: Codito Technologies 2004
  */

arch/arc/include/asm/io.h

@@ -32,7 +32,7 @@ static inline void ioport_unmap(void __iomem *addr)
 {
 }
 
-extern void iounmap(const void __iomem *addr);
+extern void iounmap(const volatile void __iomem *addr);
 
 /*
  * io{read,write}{16,32}be() macros

arch/arc/include/asm/pgtable-levels.h

@@ -161,7 +161,7 @@
 #define pmd_pfn(pmd)		((pmd_val(pmd) & PAGE_MASK) >> PAGE_SHIFT)
 #define pmd_page(pmd)		virt_to_page(pmd_page_vaddr(pmd))
 #define set_pmd(pmdp, pmd)	(*(pmdp) = pmd)
-#define pmd_pgtable(pmd)	((pgtable_t) pmd_page_vaddr(pmd))
+#define pmd_pgtable(pmd)	((pgtable_t) pmd_page(pmd))
 
 /*
  * 4th level paging: pte

arch/arc/kernel/smp.c

@@ -385,7 +385,7 @@ irqreturn_t do_IPI(int irq, void *dev_id)
  * API called by platform code to hookup arch-common ISR to their IPI IRQ
  *
  * Note: If IPI is provided by platform (vs. say ARC MCIP), their intc setup/map
- * function needs to call call irq_set_percpu_devid() for IPI IRQ, otherwise
+ * function needs to call irq_set_percpu_devid() for IPI IRQ, otherwise
  * request_percpu_irq() below will fail
  */
 static DEFINE_PER_CPU(int, ipi_dev);

arch/arc/mm/cache.c

@@ -750,7 +750,7 @@ static inline void arc_slc_enable(void)
  *  -In SMP, if hardware caches are coherent
  *
  * There's a corollary case, where kernel READs from a userspace mapped page.
- * If the U-mapping is not congruent to to K-mapping, former needs flushing.
+ * If the U-mapping is not congruent to K-mapping, former needs flushing.
  */
 void flush_dcache_page(struct page *page)
 {
@@ -910,7 +910,7 @@ EXPORT_SYMBOL(flush_icache_range);
  * @vaddr is typically user vaddr (breakpoint) or kernel vaddr (vmalloc)
  *    However in one instance, when called by kprobe (for a breakpt in
  *    builtin kernel code) @vaddr will be paddr only, meaning CDU operation will
- *    use a paddr to index the cache (despite VIPT). This is fine since since a
+ *    use a paddr to index the cache (despite VIPT). This is fine since a
  *    builtin kernel page will not have any virtual mappings.
  *    kprobe on loadable module will be kernel vaddr.
  */

arch/arc/mm/ioremap.c

@@ -94,7 +94,7 @@ void __iomem *ioremap_prot(phys_addr_t paddr, unsigned long size,
 EXPORT_SYMBOL(ioremap_prot);
 
 
-void iounmap(const void __iomem *addr)
+void iounmap(const volatile void __iomem *addr)
 {
 	/* weird double cast to handle phys_addr_t > 32 bits */
 	if (arc_uncached_addr_space((phys_addr_t)(u32)addr))

arch/arm64/include/asm/kvm_pgtable.h

@@ -13,6 +13,18 @@
 
 #define KVM_PGTABLE_MAX_LEVELS		4U
 
+/*
+ * The largest supported block sizes for KVM (no 52-bit PA support):
+ *  - 4K (level 1):	1GB
+ *  - 16K (level 2):	32MB
+ *  - 64K (level 2):	512MB
+ */
+#ifdef CONFIG_ARM64_4K_PAGES
+#define KVM_PGTABLE_MIN_BLOCK_LEVEL	1U
+#else
+#define KVM_PGTABLE_MIN_BLOCK_LEVEL	2U
+#endif
+
 static inline u64 kvm_get_parange(u64 mmfr0)
 {
 	u64 parange = cpuid_feature_extract_unsigned_field(mmfr0,
@@ -58,11 +70,7 @@ static inline u64 kvm_granule_size(u32 level)
 
 static inline bool kvm_level_supports_block_mapping(u32 level)
 {
-	/*
+	return level >= KVM_PGTABLE_MIN_BLOCK_LEVEL;
-	 * Reject invalid block mappings and don't bother with 4TB mappings for
-	 * 52-bit PAs.
-	 */
-	return !(level == 0 || (PAGE_SIZE != SZ_4K && level == 1));
 }
 
 /**

arch/arm64/include/asm/stage2_pgtable.h

@@ -10,13 +10,6 @@
 
 #include <linux/pgtable.h>
 
-/*
- * PGDIR_SHIFT determines the size a top-level page table entry can map
- * and depends on the number of levels in the page table. Compute the
- * PGDIR_SHIFT for a given number of levels.
- */
-#define pt_levels_pgdir_shift(lvls)	ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - (lvls))
-
 /*
  * The hardware supports concatenation of up to 16 tables at stage2 entry
  * level and we use the feature whenever possible, which means we resolve 4
@@ -30,11 +23,6 @@
 #define stage2_pgtable_levels(ipa)	ARM64_HW_PGTABLE_LEVELS((ipa) - 4)
 #define kvm_stage2_levels(kvm)		VTCR_EL2_LVLS(kvm->arch.vtcr)
 
-/* stage2_pgdir_shift() is the size mapped by top-level stage2 entry for the VM */
-#define stage2_pgdir_shift(kvm)		pt_levels_pgdir_shift(kvm_stage2_levels(kvm))
-#define stage2_pgdir_size(kvm)		(1ULL << stage2_pgdir_shift(kvm))
-#define stage2_pgdir_mask(kvm)		~(stage2_pgdir_size(kvm) - 1)
-
 /*
  * kvm_mmmu_cache_min_pages() is the number of pages required to install
  * a stage-2 translation. We pre-allocate the entry level page table at
@@ -42,12 +30,4 @@
  */
 #define kvm_mmu_cache_min_pages(kvm)	(kvm_stage2_levels(kvm) - 1)
 
-static inline phys_addr_t
-stage2_pgd_addr_end(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
-{
-	phys_addr_t boundary = (addr + stage2_pgdir_size(kvm)) & stage2_pgdir_mask(kvm);
-
-	return (boundary - 1 < end - 1) ? boundary : end;
-}
-
 #endif	/* __ARM64_S2_PGTABLE_H_ */

arch/arm64/kernel/entry-ftrace.S

@@ -7,6 +7,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/asm-offsets.h>
 #include <asm/assembler.h>
 #include <asm/ftrace.h>
@@ -294,10 +295,14 @@ SYM_FUNC_END(ftrace_graph_caller)
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 
-SYM_FUNC_START(ftrace_stub)
+SYM_TYPED_FUNC_START(ftrace_stub)
 	ret
 SYM_FUNC_END(ftrace_stub)
 
+SYM_TYPED_FUNC_START(ftrace_stub_graph)
+	ret
+SYM_FUNC_END(ftrace_stub_graph)
+
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 /*
  * void return_to_handler(void)

arch/arm64/kvm/hyp/Makefile

@@ -5,9 +5,6 @@
 
 incdir := $(srctree)/$(src)/include
 subdir-asflags-y := -I$(incdir)
-subdir-ccflags-y := -I$(incdir)				\
+subdir-ccflags-y := -I$(incdir)
-		    -fno-stack-protector		\
-		    -DDISABLE_BRANCH_PROFILING		\
-		    $(DISABLE_STACKLEAK_PLUGIN)
 
 obj-$(CONFIG_KVM) += vhe/ nvhe/ pgtable.o

arch/arm64/kvm/hyp/nvhe/Makefile

@@ -10,6 +10,9 @@ asflags-y := -D__KVM_NVHE_HYPERVISOR__ -D__DISABLE_EXPORTS
 # will explode instantly (Words of Marc Zyngier). So introduce a generic flag
 # __DISABLE_TRACE_MMIO__ to disable MMIO tracing for nVHE KVM.
 ccflags-y := -D__KVM_NVHE_HYPERVISOR__ -D__DISABLE_EXPORTS -D__DISABLE_TRACE_MMIO__
+ccflags-y += -fno-stack-protector	\
+	     -DDISABLE_BRANCH_PROFILING	\
+	     $(DISABLE_STACKLEAK_PLUGIN)
 
 hostprogs := gen-hyprel
 HOST_EXTRACFLAGS += -I$(objtree)/include
@@ -89,6 +92,10 @@ quiet_cmd_hypcopy = HYPCOPY $@
 # Remove ftrace, Shadow Call Stack, and CFI CFLAGS.
 # This is equivalent to the 'notrace', '__noscs', and '__nocfi' annotations.
 KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) $(CC_FLAGS_CFI), $(KBUILD_CFLAGS))
+# Starting from 13.0.0 llvm emits SHT_REL section '.llvm.call-graph-profile'
+# when profile optimization is applied. gen-hyprel does not support SHT_REL and
+# causes a build failure. Remove profile optimization flags.
+KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%, $(KBUILD_CFLAGS))
 
 # KVM nVHE code is run at a different exception code with a different map, so
 # compiler instrumentation that inserts callbacks or checks into the code may

arch/arm64/kvm/mmu.c

@@ -31,6 +31,13 @@ static phys_addr_t hyp_idmap_vector;
 
 static unsigned long io_map_base;
 
+static phys_addr_t stage2_range_addr_end(phys_addr_t addr, phys_addr_t end)
+{
+	phys_addr_t size = kvm_granule_size(KVM_PGTABLE_MIN_BLOCK_LEVEL);
+	phys_addr_t boundary = ALIGN_DOWN(addr + size, size);
+
+	return (boundary - 1 < end - 1) ? boundary : end;
+}
 
 /*
  * Release kvm_mmu_lock periodically if the memory region is large. Otherwise,
@@ -52,7 +59,7 @@ static int stage2_apply_range(struct kvm *kvm, phys_addr_t addr,
 		if (!pgt)
 			return -EINVAL;
 
-		next = stage2_pgd_addr_end(kvm, addr, end);
+		next = stage2_range_addr_end(addr, end);
 		ret = fn(pgt, addr, next - addr);
 		if (ret)
 			break;

arch/arm64/kvm/vgic/vgic-its.c

@@ -2149,7 +2149,7 @@ static int scan_its_table(struct vgic_its *its, gpa_t base, int size, u32 esz,
 
 	memset(entry, 0, esz);
 
-	while (len > 0) {
+	while (true) {
 		int next_offset;
 		size_t byte_offset;
 
@@ -2162,6 +2162,9 @@ static int scan_its_table(struct vgic_its *its, gpa_t base, int size, u32 esz,
 			return next_offset;
 
 		byte_offset = next_offset * esz;
+		if (byte_offset >= len)
+			break;
+
 		id += next_offset;
 		gpa += byte_offset;
 		len -= byte_offset;

arch/loongarch/include/asm/processor.h

@@ -191,7 +191,7 @@ static inline void flush_thread(void)
 unsigned long __get_wchan(struct task_struct *p);
 
 #define __KSTK_TOS(tsk) ((unsigned long)task_stack_page(tsk) + \
-			 THREAD_SIZE - 32 - sizeof(struct pt_regs))
+			 THREAD_SIZE - sizeof(struct pt_regs))
 #define task_pt_regs(tsk) ((struct pt_regs *)__KSTK_TOS(tsk))
 #define KSTK_EIP(tsk) (task_pt_regs(tsk)->csr_era)
 #define KSTK_ESP(tsk) (task_pt_regs(tsk)->regs[3])

arch/loongarch/include/asm/ptrace.h

@@ -29,7 +29,7 @@ struct pt_regs {
 	unsigned long csr_euen;
 	unsigned long csr_ecfg;
 	unsigned long csr_estat;
-	unsigned long __last[0];
+	unsigned long __last[];
 } __aligned(8);
 
 static inline int regs_irqs_disabled(struct pt_regs *regs)
@@ -133,7 +133,7 @@ static inline void die_if_kernel(const char *str, struct pt_regs *regs)
 #define current_pt_regs()						\
 ({									\
 	unsigned long sp = (unsigned long)__builtin_frame_address(0);	\
-	(struct pt_regs *)((sp | (THREAD_SIZE - 1)) + 1 - 32) - 1;	\
+	(struct pt_regs *)((sp | (THREAD_SIZE - 1)) + 1) - 1;		\
 })
 
 /* Helpers for working with the user stack pointer */

arch/loongarch/kernel/head.S

@@ -84,10 +84,9 @@ SYM_CODE_START(kernel_entry)			# kernel entry point
 
 	la.pcrel	tp, init_thread_union
 	/* Set the SP after an empty pt_regs.  */
-	PTR_LI		sp, (_THREAD_SIZE - 32 - PT_SIZE)
+	PTR_LI		sp, (_THREAD_SIZE - PT_SIZE)
 	PTR_ADD		sp, sp, tp
 	set_saved_sp	sp, t0, t1
-	PTR_ADDI	sp, sp, -4 * SZREG	# init stack pointer
 
 	bl		start_kernel
 	ASM_BUG()

arch/loongarch/kernel/process.c

@@ -129,7 +129,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	unsigned long clone_flags = args->flags;
 	struct pt_regs *childregs, *regs = current_pt_regs();
 
-	childksp = (unsigned long)task_stack_page(p) + THREAD_SIZE - 32;
+	childksp = (unsigned long)task_stack_page(p) + THREAD_SIZE;
 
 	/* set up new TSS. */
 	childregs = (struct pt_regs *) childksp - 1;
@@ -236,7 +236,7 @@ bool in_task_stack(unsigned long stack, struct task_struct *task,
 			struct stack_info *info)
 {
 	unsigned long begin = (unsigned long)task_stack_page(task);
-	unsigned long end = begin + THREAD_SIZE - 32;
+	unsigned long end = begin + THREAD_SIZE;
 
 	if (stack < begin || stack >= end)
 		return false;

arch/loongarch/kernel/switch.S

@@ -26,7 +26,7 @@ SYM_FUNC_START(__switch_to)
 	move	tp, a2
 	cpu_restore_nonscratch a1
 
-	li.w		t0, _THREAD_SIZE - 32
+	li.w		t0, _THREAD_SIZE
 	PTR_ADD		t0, t0, tp
 	set_saved_sp	t0, t1, t2
 

arch/loongarch/net/bpf_jit.c

@@ -279,6 +279,7 @@ static void emit_atomic(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	const u8 t1 = LOONGARCH_GPR_T1;
 	const u8 t2 = LOONGARCH_GPR_T2;
 	const u8 t3 = LOONGARCH_GPR_T3;
+	const u8 r0 = regmap[BPF_REG_0];
 	const u8 src = regmap[insn->src_reg];
 	const u8 dst = regmap[insn->dst_reg];
 	const s16 off = insn->off;
@@ -359,8 +360,6 @@ static void emit_atomic(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		break;
 	/* r0 = atomic_cmpxchg(dst + off, r0, src); */
 	case BPF_CMPXCHG:
-		u8 r0 = regmap[BPF_REG_0];
-
 		move_reg(ctx, t2, r0);
 		if (isdw) {
 			emit_insn(ctx, lld, r0, t1, 0);
@@ -390,8 +389,11 @@ static bool is_signed_bpf_cond(u8 cond)
 
 static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool extra_pass)
 {
-	const bool is32 = BPF_CLASS(insn->code) == BPF_ALU ||
+	u8 tm = -1;
-			  BPF_CLASS(insn->code) == BPF_JMP32;
+	u64 func_addr;
+	bool func_addr_fixed;
+	int i = insn - ctx->prog->insnsi;
+	int ret, jmp_offset;
 	const u8 code = insn->code;
 	const u8 cond = BPF_OP(code);
 	const u8 t1 = LOONGARCH_GPR_T1;
@@ -400,8 +402,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
 	const u8 dst = regmap[insn->dst_reg];
 	const s16 off = insn->off;
 	const s32 imm = insn->imm;
-	int jmp_offset;
+	const u64 imm64 = (u64)(insn + 1)->imm << 32 | (u32)insn->imm;
-	int i = insn - ctx->prog->insnsi;
+	const bool is32 = BPF_CLASS(insn->code) == BPF_ALU || BPF_CLASS(insn->code) == BPF_JMP32;
 
 	switch (code) {
 	/* dst = src */
@@ -724,24 +726,23 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
 	case BPF_JMP32 | BPF_JSGE | BPF_K:
 	case BPF_JMP32 | BPF_JSLT | BPF_K:
 	case BPF_JMP32 | BPF_JSLE | BPF_K:
-		u8 t7 = -1;
 		jmp_offset = bpf2la_offset(i, off, ctx);
 		if (imm) {
 			move_imm(ctx, t1, imm, false);
-			t7 = t1;
+			tm = t1;
 		} else {
 			/* If imm is 0, simply use zero register. */
-			t7 = LOONGARCH_GPR_ZERO;
+			tm = LOONGARCH_GPR_ZERO;
 		}
 		move_reg(ctx, t2, dst);
 		if (is_signed_bpf_cond(BPF_OP(code))) {
-			emit_sext_32(ctx, t7, is32);
+			emit_sext_32(ctx, tm, is32);
 			emit_sext_32(ctx, t2, is32);
 		} else {
-			emit_zext_32(ctx, t7, is32);
+			emit_zext_32(ctx, tm, is32);
 			emit_zext_32(ctx, t2, is32);
 		}
-		if (emit_cond_jmp(ctx, cond, t2, t7, jmp_offset) < 0)
+		if (emit_cond_jmp(ctx, cond, t2, tm, jmp_offset) < 0)
 			goto toofar;
 		break;
 
@@ -775,10 +776,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
 
 	/* function call */
 	case BPF_JMP | BPF_CALL:
-		int ret;
-		u64 func_addr;
-		bool func_addr_fixed;
-
 		mark_call(ctx);
 		ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass,
 					    &func_addr, &func_addr_fixed);
@@ -811,8 +808,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
 
 	/* dst = imm64 */
 	case BPF_LD | BPF_IMM | BPF_DW:
-		u64 imm64 = (u64)(insn + 1)->imm << 32 | (u32)insn->imm;
-
 		move_imm(ctx, dst, imm64, is32);
 		return 1;
 

arch/powerpc/include/asm/book3s/64/tlbflush-hash.h

@@ -32,6 +32,11 @@ static inline void arch_enter_lazy_mmu_mode(void)
 
 	if (radix_enabled())
 		return;
+	/*
+	 * apply_to_page_range can call us this preempt enabled when
+	 * operating on kernel page tables.
+	 */
+	preempt_disable();
 	batch = this_cpu_ptr(&ppc64_tlb_batch);
 	batch->active = 1;
 }
@@ -47,6 +52,7 @@ static inline void arch_leave_lazy_mmu_mode(void)
 	if (batch->index)
 		__flush_tlb_pending(batch);
 	batch->active = 0;
+	preempt_enable();
 }
 
 #define arch_flush_lazy_mmu_mode()      do {} while (0)

arch/powerpc/kernel/exceptions-64e.S

@@ -813,6 +813,13 @@ kernel_dbg_exc:
 	EXCEPTION_COMMON(0x260)
 	CHECK_NAPPING()
 	addi	r3,r1,STACK_FRAME_OVERHEAD
+	/*
+	 * XXX: Returning from performance_monitor_exception taken as a
+	 * soft-NMI (Linux irqs disabled) may be risky to use interrupt_return
+	 * and could cause bugs in return or elsewhere. That case should just
+	 * restore registers and return. There is a workaround for one known
+	 * problem in interrupt_exit_kernel_prepare().
+	 */
 	bl	performance_monitor_exception
 	b	interrupt_return
 

arch/powerpc/kernel/exceptions-64s.S

@@ -2357,9 +2357,21 @@ EXC_VIRT_END(performance_monitor, 0x4f00, 0x20)
 EXC_COMMON_BEGIN(performance_monitor_common)
 	GEN_COMMON performance_monitor
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	performance_monitor_exception
+	lbz	r4,PACAIRQSOFTMASK(r13)
+	cmpdi	r4,IRQS_ENABLED
+	bne	1f
+	bl	performance_monitor_exception_async
 	b	interrupt_return_srr
+1:
+	bl	performance_monitor_exception_nmi
+	/* Clear MSR_RI before setting SRR0 and SRR1. */
+	li	r9,0
+	mtmsrd	r9,1
 
+	kuap_kernel_restore r9, r10
+
+	EXCEPTION_RESTORE_REGS hsrr=0
+	RFI_TO_KERNEL
 
 /**
  * Interrupt 0xf20 - Vector Unavailable Interrupt.

arch/powerpc/kernel/interrupt.c

@@ -374,10 +374,18 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs)
 	if (regs_is_unrecoverable(regs))
 		unrecoverable_exception(regs);
 	/*
-	 * CT_WARN_ON comes here via program_check_exception,
+	 * CT_WARN_ON comes here via program_check_exception, so avoid
-	 * so avoid recursion.
+	 * recursion.
+	 *
+	 * Skip the assertion on PMIs on 64e to work around a problem caused
+	 * by NMI PMIs incorrectly taking this interrupt return path, it's
+	 * possible for this to hit after interrupt exit to user switches
+	 * context to user. See also the comment in the performance monitor
+	 * handler in exceptions-64e.S
 	 */
-	if (TRAP(regs) != INTERRUPT_PROGRAM)
+	if (!IS_ENABLED(CONFIG_PPC_BOOK3E_64) &&
+	    TRAP(regs) != INTERRUPT_PROGRAM &&
+	    TRAP(regs) != INTERRUPT_PERFMON)
 		CT_WARN_ON(ct_state() == CONTEXT_USER);
 
 	kuap = kuap_get_and_assert_locked();

arch/powerpc/kernel/interrupt_64.S

@@ -532,15 +532,24 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_kernel)
 	 * Returning to soft-disabled context.
 	 * Check if a MUST_HARD_MASK interrupt has become pending, in which
 	 * case we need to disable MSR[EE] in the return context.
+	 *
+	 * The MSR[EE] check catches among other things the short incoherency
+	 * in hard_irq_disable() between clearing MSR[EE] and setting
+	 * PACA_IRQ_HARD_DIS.
 	 */
 	ld	r12,_MSR(r1)
 	andi.	r10,r12,MSR_EE
 	beq	.Lfast_kernel_interrupt_return_\srr\() // EE already disabled
 	lbz	r11,PACAIRQHAPPENED(r13)
 	andi.	r10,r11,PACA_IRQ_MUST_HARD_MASK
-	beq	.Lfast_kernel_interrupt_return_\srr\() // No HARD_MASK pending
+	bne	1f // HARD_MASK is pending
+	// No HARD_MASK pending, clear possible HARD_DIS set by interrupt
+	andi.	r11,r11,(~PACA_IRQ_HARD_DIS)@l
+	stb	r11,PACAIRQHAPPENED(r13)
+	b	.Lfast_kernel_interrupt_return_\srr\()
 
-	/* Must clear MSR_EE from _MSR */
+
+1:	/* Must clear MSR_EE from _MSR */
 #ifdef CONFIG_PPC_BOOK3S
 	li	r10,0
 	/* Clear valid before changing _MSR */

arch/powerpc/kvm/Kconfig

@@ -51,6 +51,7 @@ config KVM_BOOK3S_HV_POSSIBLE
 config KVM_BOOK3S_32
 	tristate "KVM support for PowerPC book3s_32 processors"
 	depends on PPC_BOOK3S_32 && !SMP && !PTE_64BIT
+	depends on !CONTEXT_TRACKING_USER
 	select KVM
 	select KVM_BOOK3S_32_HANDLER
 	select KVM_BOOK3S_PR_POSSIBLE
@@ -105,6 +106,7 @@ config KVM_BOOK3S_64_HV
 config KVM_BOOK3S_64_PR
 	tristate "KVM support without using hypervisor mode in host"
 	depends on KVM_BOOK3S_64
+	depends on !CONTEXT_TRACKING_USER
 	select KVM_BOOK3S_PR_POSSIBLE
 	help
 	  Support running guest kernels in virtual machines on processors
@@ -190,6 +192,7 @@ config KVM_EXIT_TIMING
 config KVM_E500V2
 	bool "KVM support for PowerPC E500v2 processors"
 	depends on PPC_E500 && !PPC_E500MC
+	depends on !CONTEXT_TRACKING_USER
 	select KVM
 	select KVM_MMIO
 	select MMU_NOTIFIER
@@ -205,6 +208,7 @@ config KVM_E500V2
 config KVM_E500MC
 	bool "KVM support for PowerPC E500MC/E5500/E6500 processors"
 	depends on PPC_E500MC
+	depends on !CONTEXT_TRACKING_USER
 	select KVM
 	select KVM_MMIO
 	select KVM_BOOKE_HV

arch/powerpc/lib/vmx-helper.c

@@ -36,7 +36,17 @@ int exit_vmx_usercopy(void)
 {
 	disable_kernel_altivec();
 	pagefault_enable();
-	preempt_enable();
+	preempt_enable_no_resched();
+	/*
+	 * Must never explicitly call schedule (including preempt_enable())
+	 * while in a kuap-unlocked user copy, because the AMR register will
+	 * not be saved and restored across context switch. However preempt
+	 * kernels need to be preempted as soon as possible if need_resched is
+	 * set and we are preemptible. The hack here is to schedule a
+	 * decrementer to fire here and reschedule for us if necessary.
+	 */
+	if (IS_ENABLED(CONFIG_PREEMPT) && need_resched())
+		set_dec(1);
 	return 0;
 }
 

arch/powerpc/mm/book3s64/hash_native.c

@@ -43,6 +43,29 @@
 
 static DEFINE_RAW_SPINLOCK(native_tlbie_lock);
 
+#ifdef CONFIG_LOCKDEP
+static struct lockdep_map hpte_lock_map =
+	STATIC_LOCKDEP_MAP_INIT("hpte_lock", &hpte_lock_map);
+
+static void acquire_hpte_lock(void)
+{
+	lock_map_acquire(&hpte_lock_map);
+}
+
+static void release_hpte_lock(void)
+{
+	lock_map_release(&hpte_lock_map);
+}
+#else
+static void acquire_hpte_lock(void)
+{
+}
+
+static void release_hpte_lock(void)
+{
+}
+#endif
+
 static inline unsigned long  ___tlbie(unsigned long vpn, int psize,
 						int apsize, int ssize)
 {
@@ -220,6 +243,7 @@ static inline void native_lock_hpte(struct hash_pte *hptep)
 {
 	unsigned long *word = (unsigned long *)&hptep->v;
 
+	acquire_hpte_lock();
 	while (1) {
 		if (!test_and_set_bit_lock(HPTE_LOCK_BIT, word))
 			break;
@@ -234,6 +258,7 @@ static inline void native_unlock_hpte(struct hash_pte *hptep)
 {
 	unsigned long *word = (unsigned long *)&hptep->v;
 
+	release_hpte_lock();
 	clear_bit_unlock(HPTE_LOCK_BIT, word);
 }
 
@@ -243,8 +268,11 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn,
 {
 	struct hash_pte *hptep = htab_address + hpte_group;
 	unsigned long hpte_v, hpte_r;
+	unsigned long flags;
 	int i;
 
+	local_irq_save(flags);
+
 	if (!(vflags & HPTE_V_BOLTED)) {
 		DBG_LOW("    insert(group=%lx, vpn=%016lx, pa=%016lx,"
 			" rflags=%lx, vflags=%lx, psize=%d)\n",
@@ -263,8 +291,10 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn,
 		hptep++;
 	}
 
-	if (i == HPTES_PER_GROUP)
+	if (i == HPTES_PER_GROUP) {
+		local_irq_restore(flags);
 		return -1;
+	}
 
 	hpte_v = hpte_encode_v(vpn, psize, apsize, ssize) | vflags | HPTE_V_VALID;
 	hpte_r = hpte_encode_r(pa, psize, apsize) | rflags;
@@ -286,10 +316,13 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn,
 	 * Now set the first dword including the valid bit
 	 * NOTE: this also unlocks the hpte
 	 */
+	release_hpte_lock();
 	hptep->v = cpu_to_be64(hpte_v);
 
 	__asm__ __volatile__ ("ptesync" : : : "memory");
 
+	local_irq_restore(flags);
+
 	return i | (!!(vflags & HPTE_V_SECONDARY) << 3);
 }
 
@@ -327,6 +360,7 @@ static long native_hpte_remove(unsigned long hpte_group)
 		return -1;
 
 	/* Invalidate the hpte. NOTE: this also unlocks it */
+	release_hpte_lock();
 	hptep->v = 0;
 
 	return i;
@@ -339,6 +373,9 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 	struct hash_pte *hptep = htab_address + slot;
 	unsigned long hpte_v, want_v;
 	int ret = 0, local = 0;
+	unsigned long irqflags;
+
+	local_irq_save(irqflags);
 
 	want_v = hpte_encode_avpn(vpn, bpsize, ssize);
 
@@ -382,6 +419,8 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 	if (!(flags & HPTE_NOHPTE_UPDATE))
 		tlbie(vpn, bpsize, apsize, ssize, local);
 
+	local_irq_restore(irqflags);
+
 	return ret;
 }
 
@@ -445,6 +484,9 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
 	unsigned long vsid;
 	long slot;
 	struct hash_pte *hptep;
+	unsigned long flags;
+
+	local_irq_save(flags);
 
 	vsid = get_kernel_vsid(ea, ssize);
 	vpn = hpt_vpn(ea, vsid, ssize);
@@ -463,6 +505,8 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
 	 * actual page size will be same.
 	 */
 	tlbie(vpn, psize, psize, ssize, 0);
+
+	local_irq_restore(flags);
 }
 
 /*
@@ -476,6 +520,9 @@ static int native_hpte_removebolted(unsigned long ea, int psize, int ssize)
 	unsigned long vsid;
 	long slot;
 	struct hash_pte *hptep;
+	unsigned long flags;
+
+	local_irq_save(flags);
 
 	vsid = get_kernel_vsid(ea, ssize);
 	vpn = hpt_vpn(ea, vsid, ssize);
@@ -493,6 +540,9 @@ static int native_hpte_removebolted(unsigned long ea, int psize, int ssize)
 
 	/* Invalidate the TLB */
 	tlbie(vpn, psize, psize, ssize, 0);
+
+	local_irq_restore(flags);
+
 	return 0;
 }
 
@@ -517,10 +567,11 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
 		/* recheck with locks held */
 		hpte_v = hpte_get_old_v(hptep);
 
-		if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID))
+		if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID)) {
 			/* Invalidate the hpte. NOTE: this also unlocks it */
+			release_hpte_lock();
 			hptep->v = 0;
-		else
+		} else
 			native_unlock_hpte(hptep);
 	}
 	/*
@@ -580,10 +631,8 @@ static void native_hugepage_invalidate(unsigned long vsid,
 			hpte_v = hpte_get_old_v(hptep);
 
 			if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID)) {
-				/*
+				/* Invalidate the hpte. NOTE: this also unlocks it */
-				 * Invalidate the hpte. NOTE: this also unlocks it
+				release_hpte_lock();
-				 */
-
 				hptep->v = 0;
 			} else
 				native_unlock_hpte(hptep);
@@ -765,8 +814,10 @@ static void native_flush_hash_range(unsigned long number, int local)
 
 			if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID))
 				native_unlock_hpte(hptep);
-			else
+			else {
+				release_hpte_lock();
 				hptep->v = 0;
+			}
 
 		} pte_iterate_hashed_end();
 	}

arch/powerpc/mm/book3s64/hash_pgtable.c

@@ -404,7 +404,8 @@ EXPORT_SYMBOL_GPL(hash__has_transparent_hugepage);
 
 struct change_memory_parms {
 	unsigned long start, end, newpp;
-	unsigned int step, nr_cpus, master_cpu;
+	unsigned int step, nr_cpus;
+	atomic_t master_cpu;
 	atomic_t cpu_counter;
 };
 
@@ -478,7 +479,8 @@ static int change_memory_range_fn(void *data)
 {
 	struct change_memory_parms *parms = data;
 
-	if (parms->master_cpu != smp_processor_id())
+	// First CPU goes through, all others wait.
+	if (atomic_xchg(&parms->master_cpu, 1) == 1)
 		return chmem_secondary_loop(parms);
 
 	// Wait for all but one CPU (this one) to call-in
@@ -516,7 +518,7 @@ static bool hash__change_memory_range(unsigned long start, unsigned long end,
 		chmem_parms.end = end;
 		chmem_parms.step = step;
 		chmem_parms.newpp = newpp;
-		chmem_parms.master_cpu = smp_processor_id();
+		atomic_set(&chmem_parms.master_cpu, 0);
 
 		cpus_read_lock();
 

arch/powerpc/mm/book3s64/hash_utils.c

@@ -1981,7 +1981,7 @@ repeat:
 }
 
 #if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE)
-static DEFINE_SPINLOCK(linear_map_hash_lock);
+static DEFINE_RAW_SPINLOCK(linear_map_hash_lock);
 
 static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi)
 {
@@ -2005,10 +2005,10 @@ static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi)
 				    mmu_linear_psize, mmu_kernel_ssize);
 
 	BUG_ON (ret < 0);
-	spin_lock(&linear_map_hash_lock);
+	raw_spin_lock(&linear_map_hash_lock);
 	BUG_ON(linear_map_hash_slots[lmi] & 0x80);
 	linear_map_hash_slots[lmi] = ret | 0x80;
-	spin_unlock(&linear_map_hash_lock);
+	raw_spin_unlock(&linear_map_hash_lock);
 }
 
 static void kernel_unmap_linear_page(unsigned long vaddr, unsigned long lmi)
@@ -2018,14 +2018,14 @@ static void kernel_unmap_linear_page(unsigned long vaddr, unsigned long lmi)
 	unsigned long vpn = hpt_vpn(vaddr, vsid, mmu_kernel_ssize);
 
 	hash = hpt_hash(vpn, PAGE_SHIFT, mmu_kernel_ssize);
-	spin_lock(&linear_map_hash_lock);
+	raw_spin_lock(&linear_map_hash_lock);
 	if (!(linear_map_hash_slots[lmi] & 0x80)) {
-		spin_unlock(&linear_map_hash_lock);
+		raw_spin_unlock(&linear_map_hash_lock);
 		return;
 	}
 	hidx = linear_map_hash_slots[lmi] & 0x7f;
 	linear_map_hash_slots[lmi] = 0;
-	spin_unlock(&linear_map_hash_lock);
+	raw_spin_unlock(&linear_map_hash_lock);
 	if (hidx & _PTEIDX_SECONDARY)
 		hash = ~hash;
 	slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;

arch/powerpc/platforms/pseries/lparcfg.c

@@ -35,6 +35,7 @@
 #include <asm/drmem.h>
 
 #include "pseries.h"
+#include "vas.h"	/* pseries_vas_dlpar_cpu() */
 
 /*
  * This isn't a module but we expose that to userspace
@@ -748,6 +749,16 @@ static ssize_t lparcfg_write(struct file *file, const char __user * buf,
 			return -EINVAL;
 
 		retval = update_ppp(new_entitled_ptr, NULL);
+
+		if (retval == H_SUCCESS || retval == H_CONSTRAINED) {
+			/*
+			 * The hypervisor assigns VAS resources based
+			 * on entitled capacity for shared mode.
+			 * Reconfig VAS windows based on DLPAR CPU events.
+			 */
+			if (pseries_vas_dlpar_cpu() != 0)
+				retval = H_HARDWARE;
+		}
 	} else if (!strcmp(kbuf, "capacity_weight")) {
 		char *endp;
 		*new_weight_ptr = (u8) simple_strtoul(tmp, &endp, 10);

arch/powerpc/platforms/pseries/vas.c

@@ -200,16 +200,41 @@ static irqreturn_t pseries_vas_fault_thread_fn(int irq, void *data)
 	struct vas_user_win_ref *tsk_ref;
 	int rc;
 
-	rc = h_get_nx_fault(txwin->vas_win.winid, (u64)virt_to_phys(&crb));
+	while (atomic_read(&txwin->pending_faults)) {
-	if (!rc) {
+		rc = h_get_nx_fault(txwin->vas_win.winid, (u64)virt_to_phys(&crb));
-		tsk_ref = &txwin->vas_win.task_ref;
+		if (!rc) {
-		vas_dump_crb(&crb);
+			tsk_ref = &txwin->vas_win.task_ref;
-		vas_update_csb(&crb, tsk_ref);
+			vas_dump_crb(&crb);
+			vas_update_csb(&crb, tsk_ref);
+		}
+		atomic_dec(&txwin->pending_faults);
 	}
 
 	return IRQ_HANDLED;
 }
 
+/*
+ * irq_default_primary_handler() can be used only with IRQF_ONESHOT
+ * which disables IRQ before executing the thread handler and enables
+ * it after. But this disabling interrupt sets the VAS IRQ OFF
+ * state in the hypervisor. If the NX generates fault interrupt
+ * during this window, the hypervisor will not deliver this
+ * interrupt to the LPAR. So use VAS specific IRQ handler instead
+ * of calling the default primary handler.
+ */
+static irqreturn_t pseries_vas_irq_handler(int irq, void *data)
+{
+	struct pseries_vas_window *txwin = data;
+
+	/*
+	 * The thread hanlder will process this interrupt if it is
+	 * already running.
+	 */
+	atomic_inc(&txwin->pending_faults);
+
+	return IRQ_WAKE_THREAD;
+}
+
 /*
  * Allocate window and setup IRQ mapping.
  */
@@ -240,8 +265,9 @@ static int allocate_setup_window(struct pseries_vas_window *txwin,
 		goto out_irq;
 	}
 
-	rc = request_threaded_irq(txwin->fault_virq, NULL,
+	rc = request_threaded_irq(txwin->fault_virq,
-				  pseries_vas_fault_thread_fn, IRQF_ONESHOT,
+				  pseries_vas_irq_handler,
+				  pseries_vas_fault_thread_fn, 0,
 				  txwin->name, txwin);
 	if (rc) {
 		pr_err("VAS-Window[%d]: Request IRQ(%u) failed with %d\n",
@@ -826,6 +852,25 @@ int vas_reconfig_capabilties(u8 type, int new_nr_creds)
 	mutex_unlock(&vas_pseries_mutex);
 	return rc;
 }
+
+int pseries_vas_dlpar_cpu(void)
+{
+	int new_nr_creds, rc;
+
+	rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES,
+				      vascaps[VAS_GZIP_DEF_FEAT_TYPE].feat,
+				      (u64)virt_to_phys(&hv_cop_caps));
+	if (!rc) {
+		new_nr_creds = be16_to_cpu(hv_cop_caps.target_lpar_creds);
+		rc = vas_reconfig_capabilties(VAS_GZIP_DEF_FEAT_TYPE, new_nr_creds);
+	}
+
+	if (rc)
+		pr_err("Failed reconfig VAS capabilities with DLPAR\n");
+
+	return rc;
+}
+
 /*
  * Total number of default credits available (target_credits)
  * in LPAR depends on number of cores configured. It varies based on
@@ -840,7 +885,15 @@ static int pseries_vas_notifier(struct notifier_block *nb,
 	struct of_reconfig_data *rd = data;
 	struct device_node *dn = rd->dn;
 	const __be32 *intserv = NULL;
-	int new_nr_creds, len, rc = 0;
+	int len;
+
+	/*
+	 * For shared CPU partition, the hypervisor assigns total credits
+	 * based on entitled core capacity. So updating VAS windows will
+	 * be called from lparcfg_write().
+	 */
+	if (is_shared_processor())
+		return NOTIFY_OK;
 
 	if ((action == OF_RECONFIG_ATTACH_NODE) ||
 		(action == OF_RECONFIG_DETACH_NODE))
@@ -852,19 +905,7 @@ static int pseries_vas_notifier(struct notifier_block *nb,
 	if (!intserv)
 		return NOTIFY_OK;
 
-	rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES,
+	return pseries_vas_dlpar_cpu();
-					vascaps[VAS_GZIP_DEF_FEAT_TYPE].feat,
-					(u64)virt_to_phys(&hv_cop_caps));
-	if (!rc) {
-		new_nr_creds = be16_to_cpu(hv_cop_caps.target_lpar_creds);
-		rc = vas_reconfig_capabilties(VAS_GZIP_DEF_FEAT_TYPE,
-						new_nr_creds);
-	}
-
-	if (rc)
-		pr_err("Failed reconfig VAS capabilities with DLPAR\n");
-
-	return rc;
 }
 
 static struct notifier_block pseries_vas_nb = {

arch/powerpc/platforms/pseries/vas.h

@@ -132,6 +132,7 @@ struct pseries_vas_window {
 	u64 flags;
 	char *name;
 	int fault_virq;
+	atomic_t pending_faults; /* Number of pending faults */
 };
 
 int sysfs_add_vas_caps(struct vas_cop_feat_caps *caps);
@@ -140,10 +141,15 @@ int __init sysfs_pseries_vas_init(struct vas_all_caps *vas_caps);
 
 #ifdef CONFIG_PPC_VAS
 int vas_migration_handler(int action);
+int pseries_vas_dlpar_cpu(void);
 #else
 static inline int vas_migration_handler(int action)
 {
 	return 0;
 }
+static inline int pseries_vas_dlpar_cpu(void)
+{
+	return 0;
+}
 #endif
 #endif /* _VAS_H */

arch/riscv/Kconfig

@@ -411,14 +411,16 @@ config RISCV_ISA_SVPBMT
 
 	   If you don't know what to do here, say Y.
 
-config CC_HAS_ZICBOM
+config TOOLCHAIN_HAS_ZICBOM
 	bool
-	default y if 64BIT && $(cc-option,-mabi=lp64 -march=rv64ima_zicbom)
+	default y
-	default y if 32BIT && $(cc-option,-mabi=ilp32 -march=rv32ima_zicbom)
+	depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64ima_zicbom)
+	depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32ima_zicbom)
+	depends on LLD_VERSION >= 150000 || LD_VERSION >= 23800
 
 config RISCV_ISA_ZICBOM
 	bool "Zicbom extension support for non-coherent DMA operation"
-	depends on CC_HAS_ZICBOM
+	depends on TOOLCHAIN_HAS_ZICBOM
 	depends on !XIP_KERNEL && MMU
 	select RISCV_DMA_NONCOHERENT
 	select RISCV_ALTERNATIVE
@@ -433,6 +435,13 @@ config RISCV_ISA_ZICBOM
 
 	   If you don't know what to do here, say Y.
 
+config TOOLCHAIN_HAS_ZIHINTPAUSE
+	bool
+	default y
+	depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64ima_zihintpause)
+	depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32ima_zihintpause)
+	depends on LLD_VERSION >= 150000 || LD_VERSION >= 23600
+
 config FPU
 	bool "FPU support"
 	default y

arch/riscv/Makefile

@@ -59,12 +59,10 @@ toolchain-need-zicsr-zifencei := $(call cc-option-yn, -march=$(riscv-march-y)_zi
 riscv-march-$(toolchain-need-zicsr-zifencei) := $(riscv-march-y)_zicsr_zifencei
 
 # Check if the toolchain supports Zicbom extension
-toolchain-supports-zicbom := $(call cc-option-yn, -march=$(riscv-march-y)_zicbom)
+riscv-march-$(CONFIG_TOOLCHAIN_HAS_ZICBOM) := $(riscv-march-y)_zicbom
-riscv-march-$(toolchain-supports-zicbom) := $(riscv-march-y)_zicbom
 
 # Check if the toolchain supports Zihintpause extension
-toolchain-supports-zihintpause := $(call cc-option-yn, -march=$(riscv-march-y)_zihintpause)
+riscv-march-$(CONFIG_TOOLCHAIN_HAS_ZIHINTPAUSE) := $(riscv-march-y)_zihintpause
-riscv-march-$(toolchain-supports-zihintpause) := $(riscv-march-y)_zihintpause
 
 KBUILD_CFLAGS += -march=$(subst fd,,$(riscv-march-y))
 KBUILD_AFLAGS += -march=$(riscv-march-y)

arch/riscv/include/asm/cacheflush.h

@@ -42,16 +42,8 @@ void flush_icache_mm(struct mm_struct *mm, bool local);
 
 #endif /* CONFIG_SMP */
 
-/*
- * The T-Head CMO errata internally probe the CBOM block size, but otherwise
- * don't depend on Zicbom.
- */
 extern unsigned int riscv_cbom_block_size;
-#ifdef CONFIG_RISCV_ISA_ZICBOM
 void riscv_init_cbom_blocksize(void);
-#else
-static inline void riscv_init_cbom_blocksize(void) { }
-#endif
 
 #ifdef CONFIG_RISCV_DMA_NONCOHERENT
 void riscv_noncoherent_supported(void);

arch/riscv/include/asm/jump_label.h

@@ -14,8 +14,8 @@
 
 #define JUMP_LABEL_NOP_SIZE 4
 
-static __always_inline bool arch_static_branch(struct static_key *key,
+static __always_inline bool arch_static_branch(struct static_key * const key,
-					       bool branch)
+					       const bool branch)
 {
 	asm_volatile_goto(
 		"	.option push				\n\t"
@@ -35,8 +35,8 @@ label:
 	return true;
 }
 
-static __always_inline bool arch_static_branch_jump(struct static_key *key,
+static __always_inline bool arch_static_branch_jump(struct static_key * const key,
-						    bool branch)
+						    const bool branch)
 {
 	asm_volatile_goto(
 		"	.option push				\n\t"

arch/riscv/include/asm/kvm_vcpu_timer.h

@@ -45,6 +45,7 @@ int kvm_riscv_vcpu_timer_deinit(struct kvm_vcpu *vcpu);
 int kvm_riscv_vcpu_timer_reset(struct kvm_vcpu *vcpu);
 void kvm_riscv_vcpu_timer_restore(struct kvm_vcpu *vcpu);
 void kvm_riscv_guest_timer_init(struct kvm *kvm);
+void kvm_riscv_vcpu_timer_sync(struct kvm_vcpu *vcpu);
 void kvm_riscv_vcpu_timer_save(struct kvm_vcpu *vcpu);
 bool kvm_riscv_vcpu_timer_pending(struct kvm_vcpu *vcpu);
 

arch/riscv/include/asm/vdso/processor.h

@@ -21,7 +21,7 @@ static inline void cpu_relax(void)
 		 * Reduce instruction retirement.
 		 * This assumes the PC changes.
 		 */
-#ifdef __riscv_zihintpause
+#ifdef CONFIG_TOOLCHAIN_HAS_ZIHINTPAUSE
 		__asm__ __volatile__ ("pause");
 #else
 		/* Encoding of the pause instruction */

arch/riscv/kernel/cpu.c

@@ -213,6 +213,9 @@ static void print_mmu(struct seq_file *f)
 
 static void *c_start(struct seq_file *m, loff_t *pos)
 {
+	if (*pos == nr_cpu_ids)
+		return NULL;
+
 	*pos = cpumask_next(*pos - 1, cpu_online_mask);
 	if ((*pos) < nr_cpu_ids)
 		return (void *)(uintptr_t)(1 + *pos);

arch/riscv/kvm/vcpu.c

@@ -708,6 +708,9 @@ void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu)
 				clear_bit(IRQ_VS_SOFT, &v->irqs_pending);
 		}
 	}
+
+	/* Sync-up timer CSRs */
+	kvm_riscv_vcpu_timer_sync(vcpu);
 }
 
 int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq)

arch/riscv/kvm/vcpu_timer.c

@@ -320,6 +320,21 @@ void kvm_riscv_vcpu_timer_restore(struct kvm_vcpu *vcpu)
 	kvm_riscv_vcpu_timer_unblocking(vcpu);
 }
 
+void kvm_riscv_vcpu_timer_sync(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu_timer *t = &vcpu->arch.timer;
+
+	if (!t->sstc_enabled)
+		return;
+
+#if defined(CONFIG_32BIT)
+	t->next_cycles = csr_read(CSR_VSTIMECMP);
+	t->next_cycles |= (u64)csr_read(CSR_VSTIMECMPH) << 32;
+#else
+	t->next_cycles = csr_read(CSR_VSTIMECMP);
+#endif
+}
+
 void kvm_riscv_vcpu_timer_save(struct kvm_vcpu *vcpu)
 {
 	struct kvm_vcpu_timer *t = &vcpu->arch.timer;
@@ -327,13 +342,11 @@ void kvm_riscv_vcpu_timer_save(struct kvm_vcpu *vcpu)
 	if (!t->sstc_enabled)
 		return;
 
-	t = &vcpu->arch.timer;
+	/*
-#if defined(CONFIG_32BIT)
+	 * The vstimecmp CSRs are saved by kvm_riscv_vcpu_timer_sync()
-	t->next_cycles = csr_read(CSR_VSTIMECMP);
+	 * upon every VM exit so no need to save here.
-	t->next_cycles |= (u64)csr_read(CSR_VSTIMECMPH) << 32;
+	 */
-#else
+
-	t->next_cycles = csr_read(CSR_VSTIMECMP);
-#endif
 	/* timer should be enabled for the remaining operations */
 	if (unlikely(!t->init_done))
 		return;

arch/riscv/mm/cacheflush.c

@@ -3,6 +3,7 @@
  * Copyright (C) 2017 SiFive
  */
 
+#include <linux/of.h>
 #include <asm/cacheflush.h>
 
 #ifdef CONFIG_SMP
@@ -86,3 +87,40 @@ void flush_icache_pte(pte_t pte)
 		flush_icache_all();
 }
 #endif /* CONFIG_MMU */
+
+unsigned int riscv_cbom_block_size;
+EXPORT_SYMBOL_GPL(riscv_cbom_block_size);
+
+void riscv_init_cbom_blocksize(void)
+{
+	struct device_node *node;
+	unsigned long cbom_hartid;
+	u32 val, probed_block_size;
+	int ret;
+
+	probed_block_size = 0;
+	for_each_of_cpu_node(node) {
+		unsigned long hartid;
+
+		ret = riscv_of_processor_hartid(node, &hartid);
+		if (ret)
+			continue;
+
+		/* set block-size for cbom extension if available */
+		ret = of_property_read_u32(node, "riscv,cbom-block-size", &val);
+		if (ret)
+			continue;
+
+		if (!probed_block_size) {
+			probed_block_size = val;
+			cbom_hartid = hartid;
+		} else {
+			if (probed_block_size != val)
+				pr_warn("cbom-block-size mismatched between harts %lu and %lu\n",
+					cbom_hartid, hartid);
+		}
+	}
+
+	if (probed_block_size)
+		riscv_cbom_block_size = probed_block_size;
+}

arch/riscv/mm/dma-noncoherent.c

@@ -8,13 +8,8 @@
 #include <linux/dma-direct.h>
 #include <linux/dma-map-ops.h>
 #include <linux/mm.h>
-#include <linux/of.h>
-#include <linux/of_device.h>
 #include <asm/cacheflush.h>
 
-unsigned int riscv_cbom_block_size;
-EXPORT_SYMBOL_GPL(riscv_cbom_block_size);
-
 static bool noncoherent_supported;
 
 void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
@@ -77,42 +72,6 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 	dev->dma_coherent = coherent;
 }
 
-#ifdef CONFIG_RISCV_ISA_ZICBOM
-void riscv_init_cbom_blocksize(void)
-{
-	struct device_node *node;
-	unsigned long cbom_hartid;
-	u32 val, probed_block_size;
-	int ret;
-
-	probed_block_size = 0;
-	for_each_of_cpu_node(node) {
-		unsigned long hartid;
-
-		ret = riscv_of_processor_hartid(node, &hartid);
-		if (ret)
-			continue;
-
-		/* set block-size for cbom extension if available */
-		ret = of_property_read_u32(node, "riscv,cbom-block-size", &val);
-		if (ret)
-			continue;
-
-		if (!probed_block_size) {
-			probed_block_size = val;
-			cbom_hartid = hartid;
-		} else {
-			if (probed_block_size != val)
-				pr_warn("cbom-block-size mismatched between harts %lu and %lu\n",
-					cbom_hartid, hartid);
-		}
-	}
-
-	if (probed_block_size)
-		riscv_cbom_block_size = probed_block_size;
-}
-#endif
-
 void riscv_noncoherent_supported(void)
 {
 	WARN(!riscv_cbom_block_size,

arch/riscv/mm/kasan_init.c

@@ -113,6 +113,8 @@ static void __init kasan_populate_pud(pgd_t *pgd,
 		base_pud = pt_ops.get_pud_virt(pfn_to_phys(_pgd_pfn(*pgd)));
 	} else if (pgd_none(*pgd)) {
 		base_pud = memblock_alloc(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE);
+		memcpy(base_pud, (void *)kasan_early_shadow_pud,
+			sizeof(pud_t) * PTRS_PER_PUD);
 	} else {
 		base_pud = (pud_t *)pgd_page_vaddr(*pgd);
 		if (base_pud == lm_alias(kasan_early_shadow_pud)) {
@@ -173,8 +175,11 @@ static void __init kasan_populate_p4d(pgd_t *pgd,
 		base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(*pgd)));
 	} else {
 		base_p4d = (p4d_t *)pgd_page_vaddr(*pgd);
-		if (base_p4d == lm_alias(kasan_early_shadow_p4d))
+		if (base_p4d == lm_alias(kasan_early_shadow_p4d)) {
 			base_p4d = memblock_alloc(PTRS_PER_PUD * sizeof(p4d_t), PAGE_SIZE);
+			memcpy(base_p4d, (void *)kasan_early_shadow_p4d,
+				sizeof(p4d_t) * PTRS_PER_P4D);
+		}
 	}
 
 	p4dp = base_p4d + p4d_index(vaddr);

arch/s390/boot/vmlinux.lds.S

@@ -102,8 +102,17 @@ SECTIONS
 		_compressed_start = .;
 		*(.vmlinux.bin.compressed)
 		_compressed_end = .;
-		FILL(0xff);
+	}
-		. = ALIGN(4096);
+
+#define SB_TRAILER_SIZE 32
+	/* Trailer needed for Secure Boot */
+	. += SB_TRAILER_SIZE; /* make sure .sb.trailer does not overwrite the previous section */
+	. = ALIGN(4096) - SB_TRAILER_SIZE;
+	.sb.trailer : {
+		QUAD(0)
+		QUAD(0)
+		QUAD(0)
+		QUAD(0x000000207a49504c)
 	}
 	_end = .;
 

arch/s390/include/asm/futex.h

@@ -17,7 +17,8 @@
 		"3: jl    1b\n"						\
 		"   lhi   %0,0\n"					\
 		"4: sacf  768\n"					\
-		EX_TABLE(0b,4b) EX_TABLE(2b,4b) EX_TABLE(3b,4b)		\
+		EX_TABLE(0b,4b) EX_TABLE(1b,4b)				\
+		EX_TABLE(2b,4b) EX_TABLE(3b,4b)				\
 		: "=d" (ret), "=&d" (oldval), "=&d" (newval),		\
 		  "=m" (*uaddr)						\
 		: "0" (-EFAULT), "d" (oparg), "a" (uaddr),		\

arch/s390/kernel/perf_pai_ext.c

@@ -459,6 +459,7 @@ static int paiext_push_sample(void)
 		raw.frag.data = cpump->save;
 		raw.size = raw.frag.size;
 		data.raw = &raw;
+		data.sample_flags |= PERF_SAMPLE_RAW;
 	}
 
 	overflow = perf_event_overflow(event, &data, &regs);

arch/s390/lib/uaccess.c

@@ -157,7 +157,7 @@ unsigned long __clear_user(void __user *to, unsigned long size)
 	asm volatile(
 		"   lr	  0,%[spec]\n"
 		"0: mvcos 0(%1),0(%4),%0\n"
-		"   jz	  4f\n"
+		"6: jz	  4f\n"
 		"1: algr  %0,%2\n"
 		"   slgr  %1,%2\n"
 		"   j	  0b\n"
@@ -167,11 +167,11 @@ unsigned long __clear_user(void __user *to, unsigned long size)
 		"   clgr  %0,%3\n"	/* copy crosses next page boundary? */
 		"   jnh	  5f\n"
 		"3: mvcos 0(%1),0(%4),%3\n"
-		"   slgr  %0,%3\n"
+		"7: slgr  %0,%3\n"
 		"   j	  5f\n"
 		"4: slgr  %0,%0\n"
 		"5:\n"
-		EX_TABLE(0b,2b) EX_TABLE(3b,5b)
+		EX_TABLE(0b,2b) EX_TABLE(6b,2b) EX_TABLE(3b,5b) EX_TABLE(7b,5b)
 		: "+a" (size), "+a" (to), "+a" (tmp1), "=a" (tmp2)
 		: "a" (empty_zero_page), [spec] "d" (spec.val)
 		: "cc", "memory", "0");

arch/s390/pci/pci_mmio.c

@@ -64,7 +64,7 @@ static inline int __pcistg_mio_inuser(
 	asm volatile (
 		"       sacf    256\n"
 		"0:     llgc    %[tmp],0(%[src])\n"
-		"       sllg    %[val],%[val],8\n"
+		"4:	sllg	%[val],%[val],8\n"
 		"       aghi    %[src],1\n"
 		"       ogr     %[val],%[tmp]\n"
 		"       brctg   %[cnt],0b\n"
@@ -72,7 +72,7 @@ static inline int __pcistg_mio_inuser(
 		"2:     ipm     %[cc]\n"
 		"       srl     %[cc],28\n"
 		"3:     sacf    768\n"
-		EX_TABLE(0b, 3b) EX_TABLE(1b, 3b) EX_TABLE(2b, 3b)
+		EX_TABLE(0b, 3b) EX_TABLE(4b, 3b) EX_TABLE(1b, 3b) EX_TABLE(2b, 3b)
 		:
 		[src] "+a" (src), [cnt] "+d" (cnt),
 		[val] "+d" (val), [tmp] "=d" (tmp),
@@ -215,10 +215,10 @@ static inline int __pcilg_mio_inuser(
 		"2:     ahi     %[shift],-8\n"
 		"       srlg    %[tmp],%[val],0(%[shift])\n"
 		"3:     stc     %[tmp],0(%[dst])\n"
-		"       aghi    %[dst],1\n"
+		"5:	aghi	%[dst],1\n"
 		"       brctg   %[cnt],2b\n"
 		"4:     sacf    768\n"
-		EX_TABLE(0b, 4b) EX_TABLE(1b, 4b) EX_TABLE(3b, 4b)
+		EX_TABLE(0b, 4b) EX_TABLE(1b, 4b) EX_TABLE(3b, 4b) EX_TABLE(5b, 4b)
 		:
 		[ioaddr_len] "+&d" (ioaddr_len.pair),
 		[cc] "+d" (cc), [val] "=d" (val),

arch/x86/Kconfig

@@ -1973,7 +1973,6 @@ config EFI
 config EFI_STUB
 	bool "EFI stub support"
 	depends on EFI
-	depends on $(cc-option,-mabi=ms) || X86_32
 	select RELOCATABLE
 	help
 	  This kernel feature allows a bzImage to be loaded directly

arch/x86/crypto/polyval-clmulni_glue.c

@@ -27,13 +27,17 @@
 #include <asm/cpu_device_id.h>
 #include <asm/simd.h>
 
+#define POLYVAL_ALIGN	16
+#define POLYVAL_ALIGN_ATTR __aligned(POLYVAL_ALIGN)
+#define POLYVAL_ALIGN_EXTRA ((POLYVAL_ALIGN - 1) & ~(CRYPTO_MINALIGN - 1))
+#define POLYVAL_CTX_SIZE (sizeof(struct polyval_tfm_ctx) + POLYVAL_ALIGN_EXTRA)
 #define NUM_KEY_POWERS	8
 
 struct polyval_tfm_ctx {
 	/*
 	 * These powers must be in the order h^8, ..., h^1.
 	 */
-	u8 key_powers[NUM_KEY_POWERS][POLYVAL_BLOCK_SIZE];
+	u8 key_powers[NUM_KEY_POWERS][POLYVAL_BLOCK_SIZE] POLYVAL_ALIGN_ATTR;
 };
 
 struct polyval_desc_ctx {
@@ -45,6 +49,11 @@ asmlinkage void clmul_polyval_update(const struct polyval_tfm_ctx *keys,
 	const u8 *in, size_t nblocks, u8 *accumulator);
 asmlinkage void clmul_polyval_mul(u8 *op1, const u8 *op2);
 
+static inline struct polyval_tfm_ctx *polyval_tfm_ctx(struct crypto_shash *tfm)
+{
+	return PTR_ALIGN(crypto_shash_ctx(tfm), POLYVAL_ALIGN);
+}
+
 static void internal_polyval_update(const struct polyval_tfm_ctx *keys,
 	const u8 *in, size_t nblocks, u8 *accumulator)
 {
@@ -72,7 +81,7 @@ static void internal_polyval_mul(u8 *op1, const u8 *op2)
 static int polyval_x86_setkey(struct crypto_shash *tfm,
 			const u8 *key, unsigned int keylen)
 {
-	struct polyval_tfm_ctx *tctx = crypto_shash_ctx(tfm);
+	struct polyval_tfm_ctx *tctx = polyval_tfm_ctx(tfm);
 	int i;
 
 	if (keylen != POLYVAL_BLOCK_SIZE)
@@ -102,7 +111,7 @@ static int polyval_x86_update(struct shash_desc *desc,
 			 const u8 *src, unsigned int srclen)
 {
 	struct polyval_desc_ctx *dctx = shash_desc_ctx(desc);
-	const struct polyval_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
+	const struct polyval_tfm_ctx *tctx = polyval_tfm_ctx(desc->tfm);
 	u8 *pos;
 	unsigned int nblocks;
 	unsigned int n;
@@ -143,7 +152,7 @@ static int polyval_x86_update(struct shash_desc *desc,
 static int polyval_x86_final(struct shash_desc *desc, u8 *dst)
 {
 	struct polyval_desc_ctx *dctx = shash_desc_ctx(desc);
-	const struct polyval_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
+	const struct polyval_tfm_ctx *tctx = polyval_tfm_ctx(desc->tfm);
 
 	if (dctx->bytes) {
 		internal_polyval_mul(dctx->buffer,
@@ -167,7 +176,7 @@ static struct shash_alg polyval_alg = {
 		.cra_driver_name	= "polyval-clmulni",
 		.cra_priority		= 200,
 		.cra_blocksize		= POLYVAL_BLOCK_SIZE,
-		.cra_ctxsize		= sizeof(struct polyval_tfm_ctx),
+		.cra_ctxsize		= POLYVAL_CTX_SIZE,
 		.cra_module		= THIS_MODULE,
 	},
 };

arch/x86/events/amd/ibs.c

@@ -801,7 +801,7 @@ static void perf_ibs_get_mem_lvl(union ibs_op_data2 *op_data2,
 	/* Extension Memory */
 	if (ibs_caps & IBS_CAPS_ZEN4 &&
 	    ibs_data_src == IBS_DATA_SRC_EXT_EXT_MEM) {
-		data_src->mem_lvl_num = PERF_MEM_LVLNUM_EXTN_MEM;
+		data_src->mem_lvl_num = PERF_MEM_LVLNUM_CXL;
 		if (op_data2->rmt_node) {
 			data_src->mem_remote = PERF_MEM_REMOTE_REMOTE;
 			/* IBS doesn't provide Remote socket detail */

arch/x86/events/intel/lbr.c

@@ -1596,7 +1596,7 @@ void __init intel_pmu_arch_lbr_init(void)
 	return;
 
 clear_arch_lbr:
-	clear_cpu_cap(&boot_cpu_data, X86_FEATURE_ARCH_LBR);
+	setup_clear_cpu_cap(X86_FEATURE_ARCH_LBR);
 }
 
 /**

arch/x86/events/rapl.c

@@ -806,7 +806,11 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE,		&model_skl),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE,		&model_skl),
 	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L,		&model_skl),
+	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N,		&model_skl),
 	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X,	&model_spr),
+	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE,		&model_skl),
+	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P,	&model_skl),
+	X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S,	&model_skl),
 	{},
 };
 MODULE_DEVICE_TABLE(x86cpu, rapl_model_match);

arch/x86/include/asm/iommu.h

@@ -25,8 +25,10 @@ arch_rmrr_sanity_check(struct acpi_dmar_reserved_memory *rmrr)
 {
 	u64 start = rmrr->base_address;
 	u64 end = rmrr->end_address + 1;
+	int entry_type;
 
-	if (e820__mapped_all(start, end, E820_TYPE_RESERVED))
+	entry_type = e820__get_entry_type(start, end);
+	if (entry_type == E820_TYPE_RESERVED || entry_type == E820_TYPE_NVS)
 		return 0;
 
 	pr_err(FW_BUG "No firmware reserved region can cover this RMRR [%#018Lx-%#018Lx], contact BIOS vendor for fixes\n",

arch/x86/include/asm/string_64.h

@@ -10,10 +10,13 @@
 /* Even with __builtin_ the compiler may decide to use the out of line
    function. */
 
+#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY)
+#include <linux/kmsan_string.h>
+#endif
+
 #define __HAVE_ARCH_MEMCPY 1
-#if defined(__SANITIZE_MEMORY__)
+#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY)
 #undef memcpy
-void *__msan_memcpy(void *dst, const void *src, size_t size);
 #define memcpy __msan_memcpy
 #else
 extern void *memcpy(void *to, const void *from, size_t len);
@@ -21,7 +24,7 @@ extern void *memcpy(void *to, const void *from, size_t len);
 extern void *__memcpy(void *to, const void *from, size_t len);
 
 #define __HAVE_ARCH_MEMSET
-#if defined(__SANITIZE_MEMORY__)
+#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY)
 extern void *__msan_memset(void *s, int c, size_t n);
 #undef memset
 #define memset __msan_memset
@@ -67,7 +70,7 @@ static inline void *memset64(uint64_t *s, uint64_t v, size_t n)
 }
 
 #define __HAVE_ARCH_MEMMOVE
-#if defined(__SANITIZE_MEMORY__)
+#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY)
 #undef memmove
 void *__msan_memmove(void *dest, const void *src, size_t len);
 #define memmove __msan_memmove

arch/x86/include/asm/uaccess.h

@@ -254,24 +254,25 @@ extern void __put_user_nocheck_8(void);
 #define __put_user_size(x, ptr, size, label)				\
 do {									\
 	__typeof__(*(ptr)) __x = (x); /* eval x once */			\
-	__chk_user_ptr(ptr);						\
+	__typeof__(ptr) __ptr = (ptr); /* eval ptr once */		\
+	__chk_user_ptr(__ptr);						\
 	switch (size) {							\
 	case 1:								\
-		__put_user_goto(__x, ptr, "b", "iq", label);		\
+		__put_user_goto(__x, __ptr, "b", "iq", label);		\
 		break;							\
 	case 2:								\
-		__put_user_goto(__x, ptr, "w", "ir", label);		\
+		__put_user_goto(__x, __ptr, "w", "ir", label);		\
 		break;							\
 	case 4:								\
-		__put_user_goto(__x, ptr, "l", "ir", label);		\
+		__put_user_goto(__x, __ptr, "l", "ir", label);		\
 		break;							\
 	case 8:								\
-		__put_user_goto_u64(__x, ptr, label);			\
+		__put_user_goto_u64(__x, __ptr, label);			\
 		break;							\
 	default:							\
 		__put_user_bad();					\
 	}								\
-	instrument_put_user(__x, ptr, size);				\
+	instrument_put_user(__x, __ptr, size);				\
 } while (0)
 
 #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT

arch/x86/kernel/cpu/microcode/amd.c

@@ -440,7 +440,13 @@ apply_microcode_early_amd(u32 cpuid_1_eax, void *ucode, size_t size, bool save_p
 		return ret;
 
 	native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
-	if (rev >= mc->hdr.patch_id)
+
+	/*
+	 * Allow application of the same revision to pick up SMT-specific
+	 * changes even if the revision of the other SMT thread is already
+	 * up-to-date.
+	 */
+	if (rev > mc->hdr.patch_id)
 		return ret;
 
 	if (!__apply_microcode_amd(mc)) {
@@ -528,8 +534,12 @@ void load_ucode_amd_ap(unsigned int cpuid_1_eax)
 
 	native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
 
-	/* Check whether we have saved a new patch already: */
+	/*
-	if (*new_rev && rev < mc->hdr.patch_id) {
+	 * Check whether a new patch has been saved already. Also, allow application of
+	 * the same revision in order to pick up SMT-thread-specific configuration even
+	 * if the sibling SMT thread already has an up-to-date revision.
+	 */
+	if (*new_rev && rev <= mc->hdr.patch_id) {
 		if (!__apply_microcode_amd(mc)) {
 			*new_rev = mc->hdr.patch_id;
 			return;

arch/x86/kernel/cpu/resctrl/core.c

@@ -66,9 +66,6 @@ struct rdt_hw_resource rdt_resources_all[] = {
 			.rid			= RDT_RESOURCE_L3,
 			.name			= "L3",
 			.cache_level		= 3,
-			.cache = {
-				.min_cbm_bits	= 1,
-			},
 			.domains		= domain_init(RDT_RESOURCE_L3),
 			.parse_ctrlval		= parse_cbm,
 			.format_str		= "%d=%0*x",
@@ -83,9 +80,6 @@ struct rdt_hw_resource rdt_resources_all[] = {
 			.rid			= RDT_RESOURCE_L2,
 			.name			= "L2",
 			.cache_level		= 2,
-			.cache = {
-				.min_cbm_bits	= 1,
-			},
 			.domains		= domain_init(RDT_RESOURCE_L2),
 			.parse_ctrlval		= parse_cbm,
 			.format_str		= "%d=%0*x",
@@ -836,6 +830,7 @@ static __init void rdt_init_res_defs_intel(void)
 			r->cache.arch_has_sparse_bitmaps = false;
 			r->cache.arch_has_empty_bitmaps = false;
 			r->cache.arch_has_per_cpu_cfg = false;
+			r->cache.min_cbm_bits = 1;
 		} else if (r->rid == RDT_RESOURCE_MBA) {
 			hw_res->msr_base = MSR_IA32_MBA_THRTL_BASE;
 			hw_res->msr_update = mba_wrmsr_intel;
@@ -856,6 +851,7 @@ static __init void rdt_init_res_defs_amd(void)
 			r->cache.arch_has_sparse_bitmaps = true;
 			r->cache.arch_has_empty_bitmaps = true;
 			r->cache.arch_has_per_cpu_cfg = true;
+			r->cache.min_cbm_bits = 0;
 		} else if (r->rid == RDT_RESOURCE_MBA) {
 			hw_res->msr_base = MSR_IA32_MBA_BW_BASE;
 			hw_res->msr_update = mba_wrmsr_amd;

arch/x86/kernel/cpu/topology.c

@@ -96,6 +96,7 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
 	unsigned int ht_mask_width, core_plus_mask_width, die_plus_mask_width;
 	unsigned int core_select_mask, core_level_siblings;
 	unsigned int die_select_mask, die_level_siblings;
+	unsigned int pkg_mask_width;
 	bool die_level_present = false;
 	int leaf;
 
@@ -111,10 +112,10 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
 	core_level_siblings = smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx);
 	core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
 	die_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
-	die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
+	pkg_mask_width = die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
 
 	sub_index = 1;
-	do {
+	while (true) {
 		cpuid_count(leaf, sub_index, &eax, &ebx, &ecx, &edx);
 
 		/*
@@ -132,10 +133,15 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
 			die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
 		}
 
-		sub_index++;
+		if (LEAFB_SUBTYPE(ecx) != INVALID_TYPE)
-	} while (LEAFB_SUBTYPE(ecx) != INVALID_TYPE);
+			pkg_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
+		else
+			break;
 
-	core_select_mask = (~(-1 << core_plus_mask_width)) >> ht_mask_width;
+		sub_index++;
+	}
+
+	core_select_mask = (~(-1 << pkg_mask_width)) >> ht_mask_width;
 	die_select_mask = (~(-1 << die_plus_mask_width)) >>
 				core_plus_mask_width;
 
@@ -148,7 +154,7 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
 	}
 
 	c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid,
-				die_plus_mask_width);
+				pkg_mask_width);
 	/*
 	 * Reinit the apicid, now that we have extended initial_apicid.
 	 */

arch/x86/kernel/fpu/init.c

@@ -210,13 +210,6 @@ static void __init fpu__init_system_xstate_size_legacy(void)
 	fpstate_reset(&current->thread.fpu);
 }
 
-static void __init fpu__init_init_fpstate(void)
-{
-	/* Bring init_fpstate size and features up to date */
-	init_fpstate.size		= fpu_kernel_cfg.max_size;
-	init_fpstate.xfeatures		= fpu_kernel_cfg.max_features;
-}
-
 /*
  * Called on the boot CPU once per system bootup, to set up the initial
  * FPU state that is later cloned into all processes:
@@ -236,5 +229,4 @@ void __init fpu__init_system(struct cpuinfo_x86 *c)
 	fpu__init_system_xstate_size_legacy();
 	fpu__init_system_xstate(fpu_kernel_cfg.max_size);
 	fpu__init_task_struct_size();
-	fpu__init_init_fpstate();
 }

arch/x86/kernel/fpu/xstate.c

@@ -360,7 +360,7 @@ static void __init setup_init_fpu_buf(void)
 
 	print_xstate_features();
 
-	xstate_init_xcomp_bv(&init_fpstate.regs.xsave, fpu_kernel_cfg.max_features);
+	xstate_init_xcomp_bv(&init_fpstate.regs.xsave, init_fpstate.xfeatures);
 
 	/*
 	 * Init all the features state with header.xfeatures being 0x0
@@ -678,20 +678,6 @@ static unsigned int __init get_xsave_size_user(void)
 	return ebx;
 }
 
-/*
- * Will the runtime-enumerated 'xstate_size' fit in the init
- * task's statically-allocated buffer?
- */
-static bool __init is_supported_xstate_size(unsigned int test_xstate_size)
-{
-	if (test_xstate_size <= sizeof(init_fpstate.regs))
-		return true;
-
-	pr_warn("x86/fpu: xstate buffer too small (%zu < %d), disabling xsave\n",
-			sizeof(init_fpstate.regs), test_xstate_size);
-	return false;
-}
-
 static int __init init_xstate_size(void)
 {
 	/* Recompute the context size for enabled features: */
@@ -717,10 +703,6 @@ static int __init init_xstate_size(void)
 	kernel_default_size =
 		xstate_calculate_size(fpu_kernel_cfg.default_features, compacted);
 
-	/* Ensure we have the space to store all default enabled features. */
-	if (!is_supported_xstate_size(kernel_default_size))
-		return -EINVAL;
-
 	if (!paranoid_xstate_size_valid(kernel_size))
 		return -EINVAL;
 
@@ -875,6 +857,19 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
 	update_regset_xstate_info(fpu_user_cfg.max_size,
 				  fpu_user_cfg.max_features);
 
+	/*
+	 * init_fpstate excludes dynamic states as they are large but init
+	 * state is zero.
+	 */
+	init_fpstate.size		= fpu_kernel_cfg.default_size;
+	init_fpstate.xfeatures		= fpu_kernel_cfg.default_features;
+
+	if (init_fpstate.size > sizeof(init_fpstate.regs)) {
+		pr_warn("x86/fpu: init_fpstate buffer too small (%zu < %d), disabling XSAVE\n",
+			sizeof(init_fpstate.regs), init_fpstate.size);
+		goto out_disable;
+	}
+
 	setup_init_fpu_buf();
 
 	/*
@@ -1130,6 +1125,15 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
 	 */
 	mask = fpstate->user_xfeatures;
 
+	/*
+	 * Dynamic features are not present in init_fpstate. When they are
+	 * in an all zeros init state, remove those from 'mask' to zero
+	 * those features in the user buffer instead of retrieving them
+	 * from init_fpstate.
+	 */
+	if (fpu_state_size_dynamic())
+		mask &= (header.xfeatures | xinit->header.xcomp_bv);
+
 	for_each_extended_xfeature(i, mask) {
 		/*
 		 * If there was a feature or alignment gap, zero the space