Linux 6.10-rc6

-----BEGIN PGP SIGNATURE-----
 
 iQFSBAABCAA8FiEEq68RxlopcLEwq+PEeb4+QwBBGIYFAmaB0NweHHRvcnZhbGRz
 QGxpbnV4LWZvdW5kYXRpb24ub3JnAAoJEHm+PkMAQRiGkvwH/36UJRk/o6wvXnyH
 E6QjCSWo2226APyWks22NjtC3I/8Iqdvkneuh6wG0qL2sXAB078EMjUq5R81bF8H
 wWFBJwetjYTp8GEyLioMEb2wCH/J3R29dLFC4UYTplafXRGP6//xcpJaKmTxcgdR
 31IzvTPXbApZ7L3k1U6rA2bK9PNKcFCOvZlrNMUCuwMrabymHsDfOUt1DqXyg2xp
 zjqiWYBwlklozmgawSWt/mdEgkWuTcAbg+KyqDVQF59s9aj/OOwZ0j+HACq5V8CM
 quTPIAYL6CC9p7uxa69lGr/sgC0Is/BZLPX7RTZAwCgarGvnX+1HUsjDcaFCtrVg
 O6fPUV8=
 =pgUx
 -----END PGP SIGNATURE-----

Merge v6.10-rc6 into drm-next

The exynos-next pull is based on a newer -rc than drm-next. hence
backmerge first to make sure the unrelated conflicts we accumulated
don't end up randomly in the exynos merge pull, but are separated out.

Conflicts are all benign: Adjacent changes in amdgpu and fbdev-dma
code, and cherry-pick conflict in xe.

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

.editorconfig

@@ -5,7 +5,6 @@ root = true
 [{*.{awk,c,dts,dtsi,dtso,h,mk,s,S},Kconfig,Makefile,Makefile.*}]
 charset = utf-8
 end_of_line = lf
-trim_trailing_whitespace = true
 insert_final_newline = true
 indent_style = tab
 indent_size = 8
@@ -13,7 +12,6 @@ indent_size = 8
 [*.{json,py,rs}]
 charset = utf-8
 end_of_line = lf
-trim_trailing_whitespace = true
 insert_final_newline = true
 indent_style = space
 indent_size = 4
@@ -26,7 +24,6 @@ indent_size = 8
 [*.yaml]
 charset = utf-8
 end_of_line = lf
-trim_trailing_whitespace = unset
 insert_final_newline = true
 indent_style = space
 indent_size = 2

.mailmap

@@ -72,6 +72,8 @@ Andrey Ryabinin <ryabinin.a.a@gmail.com> <aryabinin@virtuozzo.com>
 Andrzej Hajda <andrzej.hajda@intel.com> <a.hajda@samsung.com>
 André Almeida <andrealmeid@igalia.com> <andrealmeid@collabora.com>
 Andy Adamson <andros@citi.umich.edu>
+Andy Shevchenko <andy@kernel.org> <andy@smile.org.ua>
+Andy Shevchenko <andy@kernel.org> <ext-andriy.shevchenko@nokia.com>
 Anilkumar Kolli <quic_akolli@quicinc.com> <akolli@codeaurora.org>
 Anirudh Ghayal <quic_aghayal@quicinc.com> <aghayal@codeaurora.org>
 Antoine Tenart <atenart@kernel.org> <antoine.tenart@bootlin.com>
@@ -217,6 +219,7 @@ Geliang Tang <geliang@kernel.org> <geliang.tang@suse.com>
 Geliang Tang <geliang@kernel.org> <geliangtang@xiaomi.com>
 Geliang Tang <geliang@kernel.org> <geliangtang@gmail.com>
 Geliang Tang <geliang@kernel.org> <geliangtang@163.com>
+Geliang Tang <geliang@kernel.org> <tanggeliang@kylinos.cn>
 Georgi Djakov <djakov@kernel.org> <georgi.djakov@linaro.org>
 Gerald Schaefer <gerald.schaefer@linux.ibm.com> <geraldsc@de.ibm.com>
 Gerald Schaefer <gerald.schaefer@linux.ibm.com> <gerald.schaefer@de.ibm.com>
@@ -605,6 +608,7 @@ Simon Kelley <simon@thekelleys.org.uk>
 Sricharan Ramabadhran <quic_srichara@quicinc.com> <sricharan@codeaurora.org>
 Srinivas Ramana <quic_sramana@quicinc.com> <sramana@codeaurora.org>
 Sriram R <quic_srirrama@quicinc.com> <srirrama@codeaurora.org>
+Stanislav Fomichev <sdf@fomichev.me> <sdf@google.com>
 Stefan Wahren <wahrenst@gmx.net> <stefan.wahren@i2se.com>
 Stéphane Witzmann <stephane.witzmann@ubpmes.univ-bpclermont.fr>
 Stephen Hemminger <stephen@networkplumber.org> <shemminger@linux-foundation.org>

Documentation/admin-guide/kernel-parameters.txt

@@ -788,25 +788,6 @@
 			Documentation/networking/netconsole.rst for an
 			alternative.
 
-		<DEVNAME>:<n>.<n>[,options]
-			Use the specified serial port on the serial core bus.
-			The addressing uses DEVNAME of the physical serial port
-			device, followed by the serial core controller instance,
-			and the serial port instance. The options are the same
-			as documented for the ttyS addressing above.
-
-			The mapping of the serial ports to the tty instances
-			can be viewed with:
-
-			$ ls -d /sys/bus/serial-base/devices/*:*.*/tty/*
-			/sys/bus/serial-base/devices/00:04:0.0/tty/ttyS0
-
-			In the above example, the console can be addressed with
-			console=00:04:0.0. Note that a console addressed this
-			way will only get added when the related device driver
-			is ready. The use of an earlycon parameter in addition to
-			the console may be desired for console output early on.
-
 		uart[8250],io,<addr>[,options]
 		uart[8250],mmio,<addr>[,options]
 		uart[8250],mmio16,<addr>[,options]
@@ -2192,12 +2173,6 @@
 			Format: 0 | 1
 			Default set by CONFIG_INIT_ON_FREE_DEFAULT_ON.
 
-	init_mlocked_on_free=	[MM] Fill freed userspace memory with zeroes if
-				it was mlock'ed and not explicitly munlock'ed
-				afterwards.
-				Format: 0 | 1
-				Default set by CONFIG_INIT_MLOCKED_ON_FREE_DEFAULT_ON
-
 	init_pkru=	[X86] Specify the default memory protection keys rights
 			register contents for all processes.  0x55555554 by
 			default (disallow access to all but pkey 0).  Can

Documentation/devicetree/bindings/dma/fsl,edma.yaml

@@ -59,8 +59,8 @@ properties:
       - 3
 
   dma-channels:
-    minItems: 1
+    minimum: 1
-    maxItems: 64
+    maximum: 64
 
   clocks:
     minItems: 1

Documentation/devicetree/bindings/i2c/atmel,at91sam-i2c.yaml

@@ -77,7 +77,7 @@ required:
   - clocks
 
 allOf:
-  - $ref: i2c-controller.yaml
+  - $ref: /schemas/i2c/i2c-controller.yaml#
   - if:
       properties:
         compatible:

Documentation/devicetree/bindings/i2c/google,cros-ec-i2c-tunnel.yaml

@@ -21,7 +21,7 @@ description: |
   google,cros-ec-spi or google,cros-ec-i2c.
 
 allOf:
-  - $ref: i2c-controller.yaml#
+  - $ref: /schemas/i2c/i2c-controller.yaml#
 
 properties:
   compatible:

Documentation/devicetree/bindings/iio/dac/adi,ad3552r.yaml

@@ -139,7 +139,7 @@ allOf:
                 Voltage output range of the channel as <minimum, maximum>
                 Required connections:
                   Rfb1x for: 0 to 2.5 V; 0 to 3V; 0 to 5 V;
-                  Rfb2x for: 0 to 10 V; 2.5 to 7.5V; -5 to 5 V;
+                  Rfb2x for: 0 to 10 V; -2.5 to 7.5V; -5 to 5 V;
               oneOf:
                 - items:
                     - const: 0

Documentation/devicetree/bindings/net/fsl,fman-dtsec.yaml

@@ -128,7 +128,6 @@ required:
   - cell-index
   - reg
   - fsl,fman-ports
-  - ptp-timer
 
 dependencies:
   pcs-handle-names:

Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.yaml

@@ -29,7 +29,6 @@ properties:
           - qcom,pm7325-gpio
           - qcom,pm7550ba-gpio
           - qcom,pm8005-gpio
-          - qcom,pm8008-gpio
           - qcom,pm8018-gpio
           - qcom,pm8019-gpio
           - qcom,pm8038-gpio
@@ -126,7 +125,6 @@ allOf:
         compatible:
           contains:
             enum:
-              - qcom,pm8008-gpio
               - qcom,pmi8950-gpio
               - qcom,pmr735d-gpio
     then:
@@ -448,7 +446,6 @@ $defs:
                  - gpio1-gpio10 for pm7325
                  - gpio1-gpio8 for pm7550ba
                  - gpio1-gpio4 for pm8005
-                 - gpio1-gpio2 for pm8008
                  - gpio1-gpio6 for pm8018
                  - gpio1-gpio12 for pm8038
                  - gpio1-gpio40 for pm8058

Documentation/devicetree/bindings/usb/realtek,rts5411.yaml

@@ -65,6 +65,7 @@ patternProperties:
     description: The hard wired USB devices
     type: object
     $ref: /schemas/usb/usb-device.yaml
+    additionalProperties: true
 
 required:
   - peer-hub

Documentation/filesystems/proc.rst

@@ -571,6 +571,7 @@ encoded manner. The codes are the following:
     um    userfaultfd missing tracking
     uw    userfaultfd wr-protect tracking
     ss    shadow stack page
+    sl    sealed
     ==    =======================================
 
 Note that there is no guarantee that every flag and associated mnemonic will

Documentation/i2c/i2c_bus.svg

@@ -1,5 +1,6 @@
 <?xml version="1.0" encoding="UTF-8" standalone="no"?>
 <!-- Created with Inkscape (http://www.inkscape.org/) -->
+<!-- Updated to inclusive terminology by Wolfram Sang -->
 
 <svg
    xmlns:dc="http://purl.org/dc/elements/1.1/"
@@ -1120,7 +1121,7 @@
     <rect
        style="opacity:1;fill:#ffb9b9;fill-opacity:1;stroke:#f00000;stroke-width:2.8125;stroke-linecap:round;stroke-linejoin:round;stroke-miterlimit:4;stroke-dasharray:none;stroke-opacity:1"
        id="rect4424-3-2-9-7"
-       width="112.5"
+       width="134.5"
        height="113.75008"
        x="112.5"
        y="471.11221"
@@ -1133,15 +1134,15 @@
        y="521.46259"
        id="text4349"><tspan
          sodipodi:role="line"
-         x="167.5354"
+         x="178.5354"
          y="521.46259"
          style="font-size:25px;line-height:1.25;font-family:sans-serif;text-align:center;text-anchor:middle"
          id="tspan1273">I2C</tspan><tspan
          sodipodi:role="line"
-         x="167.5354"
+         x="178.5354"
          y="552.71259"
          style="font-size:25px;line-height:1.25;font-family:sans-serif;text-align:center;text-anchor:middle"
-         id="tspan1285">Master</tspan></text>
+         id="tspan1285">Controller</tspan></text>
     <rect
        style="color:#000000;clip-rule:nonzero;display:inline;overflow:visible;visibility:visible;opacity:1;isolation:auto;mix-blend-mode:normal;color-interpolation:sRGB;color-interpolation-filters:linearRGB;solid-color:#000000;solid-opacity:1;fill:#b9ffb9;fill-opacity:1;fill-rule:nonzero;stroke:#006400;stroke-width:2.8125;stroke-linecap:round;stroke-linejoin:round;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;color-rendering:auto;image-rendering:auto;shape-rendering:auto;text-rendering:auto;enable-background:accumulate"
        id="rect4424-3-2-9-7-3-3-5-3"
@@ -1171,7 +1172,7 @@
          x="318.59131"
          y="552.08752"
          style="font-size:25.00000191px;line-height:1.25;font-family:sans-serif;text-align:center;text-anchor:middle;stroke-width:1px"
-         id="tspan1287">Slave</tspan></text>
+         id="tspan1287">Target</tspan></text>
     <path
        style="fill:none;fill-rule:evenodd;stroke:#000000;stroke-width:1.99968767;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-opacity:1"
        d="m 112.49995,677.36223 c 712.50005,0 712.50005,0 712.50005,0"
@@ -1233,7 +1234,7 @@
          x="468.59131"
          y="552.08746"
          style="font-size:25.00000191px;line-height:1.25;font-family:sans-serif;text-align:center;text-anchor:middle;stroke-width:1px"
-         id="tspan1287-6">Slave</tspan></text>
+         id="tspan1287-6">Target</tspan></text>
     <rect
        style="color:#000000;clip-rule:nonzero;display:inline;overflow:visible;visibility:visible;opacity:1;isolation:auto;mix-blend-mode:normal;color-interpolation:sRGB;color-interpolation-filters:linearRGB;solid-color:#000000;solid-opacity:1;vector-effect:none;fill:#b9ffb9;fill-opacity:1;fill-rule:nonzero;stroke:#006400;stroke-width:2.8125;stroke-linecap:round;stroke-linejoin:round;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;color-rendering:auto;image-rendering:auto;shape-rendering:auto;text-rendering:auto;enable-background:accumulate"
        id="rect4424-3-2-9-7-3-3-5-3-1"
@@ -1258,7 +1259,7 @@
          x="618.59131"
          y="552.08746"
          style="font-size:25.00000191px;line-height:1.25;font-family:sans-serif;text-align:center;text-anchor:middle;stroke-width:1px"
-         id="tspan1287-9">Slave</tspan></text>
+         id="tspan1287-9">Target</tspan></text>
     <path
        style="fill:none;fill-rule:evenodd;stroke:#000000;stroke-width:1.99968743;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-opacity:1;marker-end:url(#DotM)"
        d="m 150,583.61221 v 93.75"

Documentation/i2c/summary.rst

@@ -3,29 +3,27 @@ Introduction to I2C and SMBus
 =============================
 
 I²C (pronounce: I squared C and written I2C in the kernel documentation) is
-a protocol developed by Philips. It is a slow two-wire protocol (variable
+a protocol developed by Philips. It is a two-wire protocol with variable
-speed, up to 400 kHz), with a high speed extension (3.4 MHz).  It provides
+speed (typically up to 400 kHz, high speed modes up to 5 MHz). It provides
 an inexpensive bus for connecting many types of devices with infrequent or
-low bandwidth communications needs.  I2C is widely used with embedded
+low bandwidth communications needs. I2C is widely used with embedded
-systems.  Some systems use variants that don't meet branding requirements,
+systems. Some systems use variants that don't meet branding requirements,
 and so are not advertised as being I2C but come under different names,
 e.g. TWI (Two Wire Interface), IIC.
 
-The latest official I2C specification is the `"I2C-bus specification and user
+The latest official I2C specification is the `"I²C-bus specification and user
-manual" (UM10204) <https://www.nxp.com/webapp/Download?colCode=UM10204>`_
+manual" (UM10204) <https://www.nxp.com/docs/en/user-guide/UM10204.pdf>`_
-published by NXP Semiconductors. However, you need to log-in to the site to
+published by NXP Semiconductors, version 7 as of this writing.
-access the PDF. An older version of the specification (revision 6) is archived
-`here <https://web.archive.org/web/20210813122132/https://www.nxp.com/docs/en/user-guide/UM10204.pdf>`_.
 
 SMBus (System Management Bus) is based on the I2C protocol, and is mostly
-a subset of I2C protocols and signaling.  Many I2C devices will work on an
+a subset of I2C protocols and signaling. Many I2C devices will work on an
 SMBus, but some SMBus protocols add semantics beyond what is required to
-achieve I2C branding.  Modern PC mainboards rely on SMBus.  The most common
+achieve I2C branding. Modern PC mainboards rely on SMBus. The most common
 devices connected through SMBus are RAM modules configured using I2C EEPROMs,
 and hardware monitoring chips.
 
 Because the SMBus is mostly a subset of the generalized I2C bus, we can
-use its protocols on many I2C systems.  However, there are systems that don't
+use its protocols on many I2C systems. However, there are systems that don't
 meet both SMBus and I2C electrical constraints; and others which can't
 implement all the common SMBus protocol semantics or messages.
 
@@ -33,29 +31,52 @@ implement all the common SMBus protocol semantics or messages.
 Terminology
 ===========
 
-Using the terminology from the official documentation, the I2C bus connects
+The I2C bus connects one or more controller chips and one or more target chips.
-one or more *master* chips and one or more *slave* chips.
 
 .. kernel-figure::  i2c_bus.svg
-   :alt:    Simple I2C bus with one master and 3 slaves
+   :alt:    Simple I2C bus with one controller and 3 targets
 
    Simple I2C bus
 
-A **master** chip is a node that starts communications with slaves. In the
+A **controller** chip is a node that starts communications with targets. In the
-Linux kernel implementation it is called an **adapter** or bus. Adapter
+Linux kernel implementation it is also called an "adapter" or "bus". Controller
-drivers are in the ``drivers/i2c/busses/`` subdirectory.
+drivers are usually in the ``drivers/i2c/busses/`` subdirectory.
 
-An **algorithm** contains general code that can be used to implement a
+An **algorithm** contains general code that can be used to implement a whole
-whole class of I2C adapters. Each specific adapter driver either depends on
+class of I2C controllers. Each specific controller driver either depends on an
-an algorithm driver in the ``drivers/i2c/algos/`` subdirectory, or includes
+algorithm driver in the ``drivers/i2c/algos/`` subdirectory, or includes its
-its own implementation.
+own implementation.
 
-A **slave** chip is a node that responds to communications when addressed
+A **target** chip is a node that responds to communications when addressed by a
-by the master. In Linux it is called a **client**. Client drivers are kept
+controller. In the Linux kernel implementation it is also called a "client".
-in a directory specific to the feature they provide, for example
+While targets are usually separate external chips, Linux can also act as a
-``drivers/media/gpio/`` for GPIO expanders and ``drivers/media/i2c/`` for
+target (needs hardware support) and respond to another controller on the bus.
+This is then called a **local target**. In contrast, an external chip is called
+a **remote target**.
+
+Target drivers are kept in a directory specific to the feature they provide,
+for example ``drivers/gpio/`` for GPIO expanders and ``drivers/media/i2c/`` for
 video-related chips.
 
-For the example configuration in figure, you will need a driver for your
+For the example configuration in the figure above, you will need one driver for
-I2C adapter, and drivers for your I2C devices (usually one driver for each
+the I2C controller, and drivers for your I2C targets. Usually one driver for
-device).
+each target.
+
+Synonyms
+--------
+
+As mentioned above, the Linux I2C implementation historically uses the terms
+"adapter" for controller and "client" for target. A number of data structures
+have these synonyms in their name. So, when discussing implementation details,
+you should be aware of these terms as well. The official wording is preferred,
+though.
+
+Outdated terminology
+--------------------
+
+In earlier I2C specifications, controller was named "master" and target was
+named "slave". These terms have been obsoleted with v7 of the specification and
+their use is also discouraged by the Linux Kernel Code of Conduct. You may
+still find them in references to documentation which has not been updated. The
+general attitude, however, is to use the inclusive terms: controller and
+target. Work to replace the old terminology in the Linux Kernel is on-going.

Documentation/kbuild/modules.rst

@@ -128,7 +128,7 @@ executed to make module versioning work.
 
 	modules_install
 		Install the external module(s). The default location is
-		/lib/modules/<kernel_release>/extra/, but a prefix may
+		/lib/modules/<kernel_release>/updates/, but a prefix may
 		be added with INSTALL_MOD_PATH (discussed in section 5).
 
 	clean
@@ -417,7 +417,7 @@ directory:
 
 And external modules are installed in:
 
-	/lib/modules/$(KERNELRELEASE)/extra/
+	/lib/modules/$(KERNELRELEASE)/updates/
 
 5.1 INSTALL_MOD_PATH
 --------------------
@@ -438,10 +438,10 @@ And external modules are installed in:
 -------------------
 
 	External modules are by default installed to a directory under
-	/lib/modules/$(KERNELRELEASE)/extra/, but you may wish to
+	/lib/modules/$(KERNELRELEASE)/updates/, but you may wish to
 	locate modules for a specific functionality in a separate
 	directory. For this purpose, use INSTALL_MOD_DIR to specify an
-	alternative name to "extra."::
+	alternative name to "updates."::
 
 		$ make INSTALL_MOD_DIR=gandalf -C $KDIR \
 		       M=$PWD modules_install

Documentation/netlink/specs/ethtool.yaml

@@ -1603,7 +1603,7 @@ operations:
           attributes:
             - header
         reply:
-          attributes: &pse
+          attributes:
             - header
             - podl-pse-admin-state
             - podl-pse-admin-control
@@ -1620,7 +1620,10 @@ operations:
 
       do:
         request:
-          attributes: *pse
+          attributes:
+            - header
+            - podl-pse-admin-control
+            - c33-pse-admin-control
     -
       name: rss-get
       doc: Get RSS params.

Documentation/netlink/specs/nfsd.yaml

@@ -123,8 +123,6 @@ operations:
       doc: dump pending nfsd rpc
       attribute-set: rpc-status
       dump:
-        pre: nfsd-nl-rpc-status-get-start
-        post: nfsd-nl-rpc-status-get-done
         reply:
           attributes:
             - xid

Documentation/userspace-api/index.rst

@@ -32,6 +32,7 @@ Security-related interfaces
    seccomp_filter
    landlock
    lsm
+   mfd_noexec
    spec_ctrl
    tee
 

Documentation/userspace-api/mfd_noexec.rst

@@ -0,0 +1,86 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==================================
+Introduction of non-executable mfd
+==================================
+:Author:
+    Daniel Verkamp <dverkamp@chromium.org>
+    Jeff Xu <jeffxu@chromium.org>
+
+:Contributor:
+	Aleksa Sarai <cyphar@cyphar.com>
+
+Since Linux introduced the memfd feature, memfds have always had their
+execute bit set, and the memfd_create() syscall doesn't allow setting
+it differently.
+
+However, in a secure-by-default system, such as ChromeOS, (where all
+executables should come from the rootfs, which is protected by verified
+boot), this executable nature of memfd opens a door for NoExec bypass
+and enables “confused deputy attack”.  E.g, in VRP bug [1]: cros_vm
+process created a memfd to share the content with an external process,
+however the memfd is overwritten and used for executing arbitrary code
+and root escalation. [2] lists more VRP of this kind.
+
+On the other hand, executable memfd has its legit use: runc uses memfd’s
+seal and executable feature to copy the contents of the binary then
+execute them. For such a system, we need a solution to differentiate runc's
+use of executable memfds and an attacker's [3].
+
+To address those above:
+ - Let memfd_create() set X bit at creation time.
+ - Let memfd be sealed for modifying X bit when NX is set.
+ - Add a new pid namespace sysctl: vm.memfd_noexec to help applications in
+   migrating and enforcing non-executable MFD.
+
+User API
+========
+``int memfd_create(const char *name, unsigned int flags)``
+
+``MFD_NOEXEC_SEAL``
+	When MFD_NOEXEC_SEAL bit is set in the ``flags``, memfd is created
+	with NX. F_SEAL_EXEC is set and the memfd can't be modified to
+	add X later. MFD_ALLOW_SEALING is also implied.
+	This is the most common case for the application to use memfd.
+
+``MFD_EXEC``
+	When MFD_EXEC bit is set in the ``flags``, memfd is created with X.
+
+Note:
+	``MFD_NOEXEC_SEAL`` implies ``MFD_ALLOW_SEALING``. In case that
+	an app doesn't want sealing, it can add F_SEAL_SEAL after creation.
+
+
+Sysctl:
+========
+``pid namespaced sysctl vm.memfd_noexec``
+
+The new pid namespaced sysctl vm.memfd_noexec has 3 values:
+
+ - 0: MEMFD_NOEXEC_SCOPE_EXEC
+	memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL acts like
+	MFD_EXEC was set.
+
+ - 1: MEMFD_NOEXEC_SCOPE_NOEXEC_SEAL
+	memfd_create() without MFD_EXEC nor MFD_NOEXEC_SEAL acts like
+	MFD_NOEXEC_SEAL was set.
+
+ - 2: MEMFD_NOEXEC_SCOPE_NOEXEC_ENFORCED
+	memfd_create() without MFD_NOEXEC_SEAL will be rejected.
+
+The sysctl allows finer control of memfd_create for old software that
+doesn't set the executable bit; for example, a container with
+vm.memfd_noexec=1 means the old software will create non-executable memfd
+by default while new software can create executable memfd by setting
+MFD_EXEC.
+
+The value of vm.memfd_noexec is passed to child namespace at creation
+time. In addition, the setting is hierarchical, i.e. during memfd_create,
+we will search from current ns to root ns and use the most restrictive
+setting.
+
+[1] https://crbug.com/1305267
+
+[2] https://bugs.chromium.org/p/chromium/issues/list?q=type%3Dbug-security%20memfd%20escalation&can=1
+
+[3] https://lwn.net/Articles/781013/

Documentation/virt/hyperv/clocks.rst

@@ -62,12 +62,21 @@ shared page with scale and offset values into user space.  User
 space code performs the same algorithm of reading the TSC and
 applying the scale and offset to get the constant 10 MHz clock.
 
-Linux clockevents are based on Hyper-V synthetic timer 0. While
+Linux clockevents are based on Hyper-V synthetic timer 0 (stimer0).
-Hyper-V offers 4 synthetic timers for each CPU, Linux only uses
+While Hyper-V offers 4 synthetic timers for each CPU, Linux only uses
-timer 0. Interrupts from stimer0 are recorded on the "HVS" line in
+timer 0. In older versions of Hyper-V, an interrupt from stimer0
-/proc/interrupts.  Clockevents based on the virtualized PIT and
+results in a VMBus control message that is demultiplexed by
-local APIC timer also work, but the Hyper-V synthetic timer is
+vmbus_isr() as described in the Documentation/virt/hyperv/vmbus.rst
-preferred.
+documentation. In newer versions of Hyper-V, stimer0 interrupts can
+be mapped to an architectural interrupt, which is referred to as
+"Direct Mode". Linux prefers to use Direct Mode when available. Since
+x86/x64 doesn't support per-CPU interrupts, Direct Mode statically
+allocates an x86 interrupt vector (HYPERV_STIMER0_VECTOR) across all CPUs
+and explicitly codes it to call the stimer0 interrupt handler. Hence
+interrupts from stimer0 are recorded on the "HVS" line in /proc/interrupts
+rather than being associated with a Linux IRQ. Clockevents based on the
+virtualized PIT and local APIC timer also work, but Hyper-V stimer0
+is preferred.
 
 The driver for the Hyper-V synthetic system clock and timers is
 drivers/clocksource/hyperv_timer.c.

Documentation/virt/hyperv/overview.rst

@@ -40,7 +40,7 @@ Linux guests communicate with Hyper-V in four different ways:
   arm64, these synthetic registers must be accessed using explicit
   hypercalls.
 
-* VMbus: VMbus is a higher-level software construct that is built on
+* VMBus: VMBus is a higher-level software construct that is built on
   the other 3 mechanisms.  It is a message passing interface between
   the Hyper-V host and the Linux guest.  It uses memory that is shared
   between Hyper-V and the guest, along with various signaling
@@ -54,8 +54,8 @@ x86/x64 architecture only.
 
 .. _Hyper-V Top Level Functional Spec (TLFS): https://docs.microsoft.com/en-us/virtualization/hyper-v-on-windows/tlfs/tlfs
 
-VMbus is not documented.  This documentation provides a high-level
+VMBus is not documented.  This documentation provides a high-level
-overview of VMbus and how it works, but the details can be discerned
+overview of VMBus and how it works, but the details can be discerned
 only from the code.
 
 Sharing Memory
@@ -74,7 +74,7 @@ follows:
   physical address space.  How Hyper-V is told about the GPA or list
   of GPAs varies.  In some cases, a single GPA is written to a
   synthetic register.  In other cases, a GPA or list of GPAs is sent
-  in a VMbus message.
+  in a VMBus message.
 
 * Hyper-V translates the GPAs into "real" physical memory addresses,
   and creates a virtual mapping that it can use to access the memory.
@@ -133,9 +133,9 @@ only the CPUs actually present in the VM, so Linux does not report
 any hot-add CPUs.
 
 A Linux guest CPU may be taken offline using the normal Linux
-mechanisms, provided no VMbus channel interrupts are assigned to
+mechanisms, provided no VMBus channel interrupts are assigned to
-the CPU.  See the section on VMbus Interrupts for more details
+the CPU.  See the section on VMBus Interrupts for more details
-on how VMbus channel interrupts can be re-assigned to permit
+on how VMBus channel interrupts can be re-assigned to permit
 taking a CPU offline.
 
 32-bit and 64-bit
@@ -169,14 +169,14 @@ and functionality. Hyper-V indicates feature/function availability
 via flags in synthetic MSRs that Hyper-V provides to the guest,
 and the guest code tests these flags.
 
-VMbus has its own protocol version that is negotiated during the
+VMBus has its own protocol version that is negotiated during the
-initial VMbus connection from the guest to Hyper-V. This version
+initial VMBus connection from the guest to Hyper-V. This version
 number is also output to dmesg during boot.  This version number
 is checked in a few places in the code to determine if specific
 functionality is present.
 
-Furthermore, each synthetic device on VMbus also has a protocol
+Furthermore, each synthetic device on VMBus also has a protocol
-version that is separate from the VMbus protocol version. Device
+version that is separate from the VMBus protocol version. Device
 drivers for these synthetic devices typically negotiate the device
 protocol version, and may test that protocol version to determine
 if specific device functionality is present.

Documentation/virt/hyperv/vmbus.rst

@@ -1,8 +1,8 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-VMbus
+VMBus
 =====
-VMbus is a software construct provided by Hyper-V to guest VMs.  It
+VMBus is a software construct provided by Hyper-V to guest VMs.  It
 consists of a control path and common facilities used by synthetic
 devices that Hyper-V presents to guest VMs.   The control path is
 used to offer synthetic devices to the guest VM and, in some cases,
@@ -12,9 +12,9 @@ and the synthetic device implementation that is part of Hyper-V, and
 signaling primitives to allow Hyper-V and the guest to interrupt
 each other.
 
-VMbus is modeled in Linux as a bus, with the expected /sys/bus/vmbus
+VMBus is modeled in Linux as a bus, with the expected /sys/bus/vmbus
-entry in a running Linux guest.  The VMbus driver (drivers/hv/vmbus_drv.c)
+entry in a running Linux guest.  The VMBus driver (drivers/hv/vmbus_drv.c)
-establishes the VMbus control path with the Hyper-V host, then
+establishes the VMBus control path with the Hyper-V host, then
 registers itself as a Linux bus driver.  It implements the standard
 bus functions for adding and removing devices to/from the bus.
 
@@ -49,9 +49,9 @@ synthetic NIC is referred to as "netvsc" and the Linux driver for
 the synthetic SCSI controller is "storvsc".  These drivers contain
 functions with names like "storvsc_connect_to_vsp".
 
-VMbus channels
+VMBus channels
 --------------
-An instance of a synthetic device uses VMbus channels to communicate
+An instance of a synthetic device uses VMBus channels to communicate
 between the VSP and the VSC.  Channels are bi-directional and used
 for passing messages.   Most synthetic devices use a single channel,
 but the synthetic SCSI controller and synthetic NIC may use multiple
@@ -73,7 +73,7 @@ write indices and some control flags, followed by the memory for the
 actual ring.  The size of the ring is determined by the VSC in the
 guest and is specific to each synthetic device.   The list of GPAs
 making up the ring is communicated to the Hyper-V host over the
-VMbus control path as a GPA Descriptor List (GPADL).  See function
+VMBus control path as a GPA Descriptor List (GPADL).  See function
 vmbus_establish_gpadl().
 
 Each ring buffer is mapped into contiguous Linux kernel virtual
@@ -102,10 +102,10 @@ resources.  For Windows Server 2019 and later, this limit is
 approximately 1280 Mbytes.  For versions prior to Windows Server
 2019, the limit is approximately 384 Mbytes.
 
-VMbus messages
+VMBus channel messages
---------------
+----------------------
-All VMbus messages have a standard header that includes the message
+All messages sent in a VMBus channel have a standard header that includes
-length, the offset of the message payload, some flags, and a
+the message length, the offset of the message payload, some flags, and a
 transactionID.  The portion of the message after the header is
 unique to each VSP/VSC pair.
 
@@ -137,7 +137,7 @@ control message contains a list of GPAs that describe the data
 buffer.  For example, the storvsc driver uses this approach to
 specify the data buffers to/from which disk I/O is done.
 
-Three functions exist to send VMbus messages:
+Three functions exist to send VMBus channel messages:
 
 1. vmbus_sendpacket():  Control-only messages and messages with
    embedded data -- no GPAs
@@ -154,20 +154,51 @@ Historically, Linux guests have trusted Hyper-V to send well-formed
 and valid messages, and Linux drivers for synthetic devices did not
 fully validate messages.  With the introduction of processor
 technologies that fully encrypt guest memory and that allow the
-guest to not trust the hypervisor (AMD SNP-SEV, Intel TDX), trusting
+guest to not trust the hypervisor (AMD SEV-SNP, Intel TDX), trusting
 the Hyper-V host is no longer a valid assumption.  The drivers for
-VMbus synthetic devices are being updated to fully validate any
+VMBus synthetic devices are being updated to fully validate any
 values read from memory that is shared with Hyper-V, which includes
-messages from VMbus devices.  To facilitate such validation,
+messages from VMBus devices.  To facilitate such validation,
 messages read by the guest from the "in" ring buffer are copied to a
 temporary buffer that is not shared with Hyper-V.  Validation is
 performed in this temporary buffer without the risk of Hyper-V
 maliciously modifying the message after it is validated but before
 it is used.
 
-VMbus interrupts
+Synthetic Interrupt Controller (synic)
+--------------------------------------
+Hyper-V provides each guest CPU with a synthetic interrupt controller
+that is used by VMBus for host-guest communication. While each synic
+defines 16 synthetic interrupts (SINT), Linux uses only one of the 16
+(VMBUS_MESSAGE_SINT). All interrupts related to communication between
+the Hyper-V host and a guest CPU use that SINT.
+
+The SINT is mapped to a single per-CPU architectural interrupt (i.e,
+an 8-bit x86/x64 interrupt vector, or an arm64 PPI INTID). Because
+each CPU in the guest has a synic and may receive VMBus interrupts,
+they are best modeled in Linux as per-CPU interrupts. This model works
+well on arm64 where a single per-CPU Linux IRQ is allocated for
+VMBUS_MESSAGE_SINT. This IRQ appears in /proc/interrupts as an IRQ labelled
+"Hyper-V VMbus". Since x86/x64 lacks support for per-CPU IRQs, an x86
+interrupt vector is statically allocated (HYPERVISOR_CALLBACK_VECTOR)
+across all CPUs and explicitly coded to call vmbus_isr(). In this case,
+there's no Linux IRQ, and the interrupts are visible in aggregate in
+/proc/interrupts on the "HYP" line.
+
+The synic provides the means to demultiplex the architectural interrupt into
+one or more logical interrupts and route the logical interrupt to the proper
+VMBus handler in Linux. This demultiplexing is done by vmbus_isr() and
+related functions that access synic data structures.
+
+The synic is not modeled in Linux as an irq chip or irq domain,
+and the demultiplexed logical interrupts are not Linux IRQs. As such,
+they don't appear in /proc/interrupts or /proc/irq. The CPU
+affinity for one of these logical interrupts is controlled via an
+entry under /sys/bus/vmbus as described below.
+
+VMBus interrupts
 ----------------
-VMbus provides a mechanism for the guest to interrupt the host when
+VMBus provides a mechanism for the guest to interrupt the host when
 the guest has queued new messages in a ring buffer.  The host
 expects that the guest will send an interrupt only when an "out"
 ring buffer transitions from empty to non-empty.  If the guest sends
@@ -176,63 +207,55 @@ unnecessary.  If a guest sends an excessive number of unnecessary
 interrupts, the host may throttle that guest by suspending its
 execution for a few seconds to prevent a denial-of-service attack.
 
-Similarly, the host will interrupt the guest when it sends a new
+Similarly, the host will interrupt the guest via the synic when
-message on the VMbus control path, or when a VMbus channel "in" ring
+it sends a new message on the VMBus control path, or when a VMBus
-buffer transitions from empty to non-empty.  Each CPU in the guest
+channel "in" ring buffer transitions from empty to non-empty due to
-may receive VMbus interrupts, so they are best modeled as per-CPU
+the host inserting a new VMBus channel message. The control message stream
-interrupts in Linux.  This model works well on arm64 where a single
+and each VMBus channel "in" ring buffer are separate logical interrupts
-per-CPU IRQ is allocated for VMbus.  Since x86/x64 lacks support for
+that are demultiplexed by vmbus_isr(). It demultiplexes by first checking
-per-CPU IRQs, an x86 interrupt vector is statically allocated (see
+for channel interrupts by calling vmbus_chan_sched(), which looks at a synic
-HYPERVISOR_CALLBACK_VECTOR) across all CPUs and explicitly coded to
+bitmap to determine which channels have pending interrupts on this CPU.
-call the VMbus interrupt service routine.  These interrupts are
+If multiple channels have pending interrupts for this CPU, they are
-visible in /proc/interrupts on the "HYP" line.
+processed sequentially.  When all channel interrupts have been processed,
+vmbus_isr() checks for and processes any messages received on the VMBus
+control path.
 
-The guest CPU that a VMbus channel will interrupt is selected by the
+The guest CPU that a VMBus channel will interrupt is selected by the
 guest when the channel is created, and the host is informed of that
-selection.  VMbus devices are broadly grouped into two categories:
+selection.  VMBus devices are broadly grouped into two categories:
 
-1. "Slow" devices that need only one VMbus channel.  The devices
+1. "Slow" devices that need only one VMBus channel.  The devices
    (such as keyboard, mouse, heartbeat, and timesync) generate
-   relatively few interrupts.  Their VMbus channels are all
+   relatively few interrupts.  Their VMBus channels are all
    assigned to interrupt the VMBUS_CONNECT_CPU, which is always
    CPU 0.
 
-2. "High speed" devices that may use multiple VMbus channels for
+2. "High speed" devices that may use multiple VMBus channels for
    higher parallelism and performance.  These devices include the
-   synthetic SCSI controller and synthetic NIC.  Their VMbus
+   synthetic SCSI controller and synthetic NIC.  Their VMBus
    channels interrupts are assigned to CPUs that are spread out
    among the available CPUs in the VM so that interrupts on
    multiple channels can be processed in parallel.
 
-The assignment of VMbus channel interrupts to CPUs is done in the
+The assignment of VMBus channel interrupts to CPUs is done in the
 function init_vp_index().  This assignment is done outside of the
 normal Linux interrupt affinity mechanism, so the interrupts are
 neither "unmanaged" nor "managed" interrupts.
 
-The CPU that a VMbus channel will interrupt can be seen in
+The CPU that a VMBus channel will interrupt can be seen in
 /sys/bus/vmbus/devices/<deviceGUID>/ channels/<channelRelID>/cpu.
 When running on later versions of Hyper-V, the CPU can be changed
-by writing a new value to this sysfs entry.  Because the interrupt
+by writing a new value to this sysfs entry. Because VMBus channel
-assignment is done outside of the normal Linux affinity mechanism,
+interrupts are not Linux IRQs, there are no entries in /proc/interrupts
-there are no entries in /proc/irq corresponding to individual
+or /proc/irq corresponding to individual VMBus channel interrupts.
-VMbus channel interrupts.
 
 An online CPU in a Linux guest may not be taken offline if it has
-VMbus channel interrupts assigned to it.  Any such channel
+VMBus channel interrupts assigned to it.  Any such channel
 interrupts must first be manually reassigned to another CPU as
 described above.  When no channel interrupts are assigned to the
 CPU, it can be taken offline.
 
-When a guest CPU receives a VMbus interrupt from the host, the
+The VMBus channel interrupt handling code is designed to work
-function vmbus_isr() handles the interrupt.  It first checks for
-channel interrupts by calling vmbus_chan_sched(), which looks at a
-bitmap setup by the host to determine which channels have pending
-interrupts on this CPU.  If multiple channels have pending
-interrupts for this CPU, they are processed sequentially.  When all
-channel interrupts have been processed, vmbus_isr() checks for and
-processes any message received on the VMbus control path.
-
-The VMbus channel interrupt handling code is designed to work
 correctly even if an interrupt is received on a CPU other than the
 CPU assigned to the channel.  Specifically, the code does not use
 CPU-based exclusion for correctness.  In normal operation, Hyper-V
@@ -242,23 +265,23 @@ when Hyper-V will make the transition.  The code must work correctly
 even if there is a time lag before Hyper-V starts interrupting the
 new CPU.  See comments in target_cpu_store().
 
-VMbus device creation/deletion
+VMBus device creation/deletion
 ------------------------------
 Hyper-V and the Linux guest have a separate message-passing path
 that is used for synthetic device creation and deletion. This
-path does not use a VMbus channel.  See vmbus_post_msg() and
+path does not use a VMBus channel.  See vmbus_post_msg() and
 vmbus_on_msg_dpc().
 
 The first step is for the guest to connect to the generic
-Hyper-V VMbus mechanism.  As part of establishing this connection,
+Hyper-V VMBus mechanism.  As part of establishing this connection,
-the guest and Hyper-V agree on a VMbus protocol version they will
+the guest and Hyper-V agree on a VMBus protocol version they will
 use.  This negotiation allows newer Linux kernels to run on older
 Hyper-V versions, and vice versa.
 
 The guest then tells Hyper-V to "send offers".  Hyper-V sends an
 offer message to the guest for each synthetic device that the VM
-is configured to have. Each VMbus device type has a fixed GUID
+is configured to have. Each VMBus device type has a fixed GUID
-known as the "class ID", and each VMbus device instance is also
+known as the "class ID", and each VMBus device instance is also
 identified by a GUID. The offer message from Hyper-V contains
 both GUIDs to uniquely (within the VM) identify the device.
 There is one offer message for each device instance, so a VM with
@@ -275,7 +298,7 @@ type based on the class ID, and invokes the correct driver to set up
 the device.  Driver/device matching is performed using the standard
 Linux mechanism.
 
-The device driver probe function opens the primary VMbus channel to
+The device driver probe function opens the primary VMBus channel to
 the corresponding VSP. It allocates guest memory for the channel
 ring buffers and shares the ring buffer with the Hyper-V host by
 giving the host a list of GPAs for the ring buffer memory.  See
@@ -285,7 +308,7 @@ Once the ring buffer is set up, the device driver and VSP exchange
 setup messages via the primary channel.  These messages may include
 negotiating the device protocol version to be used between the Linux
 VSC and the VSP on the Hyper-V host.  The setup messages may also
-include creating additional VMbus channels, which are somewhat
+include creating additional VMBus channels, which are somewhat
 mis-named as "sub-channels" since they are functionally
 equivalent to the primary channel once they are created.
 

MAINTAINERS

@@ -1044,7 +1044,7 @@ M:	Joerg Roedel <joro@8bytes.org>
 R:	Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
 L:	iommu@lists.linux.dev
 S:	Maintained
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/iommu/linux.git
 F:	drivers/iommu/amd/
 F:	include/linux/amd-iommu.h
 
@@ -3980,7 +3980,7 @@ R:	Song Liu <song@kernel.org>
 R:	Yonghong Song <yonghong.song@linux.dev>
 R:	John Fastabend <john.fastabend@gmail.com>
 R:	KP Singh <kpsingh@kernel.org>
-R:	Stanislav Fomichev <sdf@google.com>
+R:	Stanislav Fomichev <sdf@fomichev.me>
 R:	Hao Luo <haoluo@google.com>
 R:	Jiri Olsa <jolsa@kernel.org>
 L:	bpf@vger.kernel.org
@@ -4083,12 +4083,13 @@ F:	kernel/bpf/ringbuf.c
 
 BPF [SECURITY & LSM] (Security Audit and Enforcement using BPF)
 M:	KP Singh <kpsingh@kernel.org>
-R:	Matt Bobrowski <mattbobrowski@google.com>
+M:	Matt Bobrowski <mattbobrowski@google.com>
 L:	bpf@vger.kernel.org
 S:	Maintained
 F:	Documentation/bpf/prog_lsm.rst
 F:	include/linux/bpf_lsm.h
 F:	kernel/bpf/bpf_lsm.c
+F:	kernel/trace/bpf_trace.c
 F:	security/bpf/
 
 BPF [SELFTESTS] (Test Runners & Infrastructure)
@@ -5295,7 +5296,7 @@ F:	drivers/infiniband/hw/usnic/
 
 CLANG CONTROL FLOW INTEGRITY SUPPORT
 M:	Sami Tolvanen <samitolvanen@google.com>
-M:	Kees Cook <keescook@chromium.org>
+M:	Kees Cook <kees@kernel.org>
 R:	Nathan Chancellor <nathan@kernel.org>
 L:	llvm@lists.linux.dev
 S:	Supported
@@ -8217,7 +8218,7 @@ F:	rust/kernel/net/phy.rs
 
 EXEC & BINFMT API, ELF
 R:	Eric Biederman <ebiederm@xmission.com>
-R:	Kees Cook <keescook@chromium.org>
+R:	Kees Cook <kees@kernel.org>
 L:	linux-mm@kvack.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/execve
@@ -8618,7 +8619,7 @@ S:	Maintained
 F:	drivers/net/ethernet/nvidia/*
 
 FORTIFY_SOURCE
-M:	Kees Cook <keescook@chromium.org>
+M:	Kees Cook <kees@kernel.org>
 L:	linux-hardening@vger.kernel.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/hardening
@@ -9108,7 +9109,7 @@ F:	include/linux/mfd/gsc.h
 F:	include/linux/platform_data/gsc_hwmon.h
 
 GCC PLUGINS
-M:	Kees Cook <keescook@chromium.org>
+M:	Kees Cook <kees@kernel.org>
 L:	linux-hardening@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/hardening
@@ -9242,7 +9243,7 @@ S:	Maintained
 F:	drivers/input/touchscreen/resistive-adc-touch.c
 
 GENERIC STRING LIBRARY
-M:	Kees Cook <keescook@chromium.org>
+M:	Kees Cook <kees@kernel.org>
 R:	Andy Shevchenko <andy@kernel.org>
 L:	linux-hardening@vger.kernel.org
 S:	Supported
@@ -11042,6 +11043,7 @@ F:	include/uapi/drm/i915_drm.h
 INTEL DRM XE DRIVER (Lunar Lake and newer)
 M:	Lucas De Marchi <lucas.demarchi@intel.com>
 M:	Thomas Hellström <thomas.hellstrom@linux.intel.com>
+M:	Rodrigo Vivi <rodrigo.vivi@intel.com>
 L:	intel-xe@lists.freedesktop.org
 S:	Supported
 W:	https://drm.pages.freedesktop.org/intel-docs/
@@ -11162,7 +11164,7 @@ M:	David Woodhouse <dwmw2@infradead.org>
 M:	Lu Baolu <baolu.lu@linux.intel.com>
 L:	iommu@lists.linux.dev
 S:	Supported
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/iommu/linux.git
 F:	drivers/iommu/intel/
 
 INTEL IPU3 CSI-2 CIO2 DRIVER
@@ -11535,7 +11537,7 @@ IOMMU DMA-API LAYER
 M:	Robin Murphy <robin.murphy@arm.com>
 L:	iommu@lists.linux.dev
 S:	Maintained
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/iommu/linux.git
 F:	drivers/iommu/dma-iommu.c
 F:	drivers/iommu/dma-iommu.h
 F:	drivers/iommu/iova.c
@@ -11547,7 +11549,7 @@ M:	Will Deacon <will@kernel.org>
 R:	Robin Murphy <robin.murphy@arm.com>
 L:	iommu@lists.linux.dev
 S:	Maintained
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/iommu/linux.git
 F:	Documentation/devicetree/bindings/iommu/
 F:	Documentation/userspace-api/iommu.rst
 F:	drivers/iommu/
@@ -11956,7 +11958,7 @@ F:	scripts/package/
 F:	usr/
 
 KERNEL HARDENING (not covered by other areas)
-M:	Kees Cook <keescook@chromium.org>
+M:	Kees Cook <kees@kernel.org>
 R:	Gustavo A. R. Silva <gustavoars@kernel.org>
 L:	linux-hardening@vger.kernel.org
 S:	Supported
@@ -12388,7 +12390,6 @@ F:	drivers/video/backlight/ktz8866.c
 
 KVM PARAVIRT (KVM/paravirt)
 M:	Paolo Bonzini <pbonzini@redhat.com>
-R:	Wanpeng Li <wanpengli@tencent.com>
 R:	Vitaly Kuznetsov <vkuznets@redhat.com>
 L:	kvm@vger.kernel.org
 S:	Supported
@@ -12484,7 +12485,7 @@ F:	drivers/scsi/53c700*
 
 LEAKING_ADDRESSES
 M:	Tycho Andersen <tycho@tycho.pizza>
-R:	Kees Cook <keescook@chromium.org>
+R:	Kees Cook <kees@kernel.org>
 L:	linux-hardening@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/hardening
@@ -12780,7 +12781,7 @@ F:	arch/powerpc/platforms/8xx/
 F:	arch/powerpc/platforms/83xx/
 
 LINUX KERNEL DUMP TEST MODULE (LKDTM)
-M:	Kees Cook <keescook@chromium.org>
+M:	Kees Cook <kees@kernel.org>
 S:	Maintained
 F:	drivers/misc/lkdtm/*
 F:	tools/testing/selftests/lkdtm/*
@@ -12910,7 +12911,7 @@ Q:	http://patchwork.linuxtv.org/project/linux-media/list/
 F:	drivers/media/usb/dvb-usb-v2/lmedm04*
 
 LOADPIN SECURITY MODULE
-M:	Kees Cook <keescook@chromium.org>
+M:	Kees Cook <kees@kernel.org>
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/hardening
 F:	Documentation/admin-guide/LSM/LoadPin.rst
@@ -15831,7 +15832,7 @@ F:	drivers/nfc/virtual_ncidev.c
 F:	tools/testing/selftests/nci/
 
 NFS, SUNRPC, AND LOCKD CLIENTS
-M:	Trond Myklebust <trond.myklebust@hammerspace.com>
+M:	Trond Myklebust <trondmy@kernel.org>
 M:	Anna Schumaker <anna@kernel.org>
 L:	linux-nfs@vger.kernel.org
 S:	Maintained
@@ -17538,7 +17539,6 @@ F:	include/linux/peci.h
 PENSANDO ETHERNET DRIVERS
 M:	Shannon Nelson <shannon.nelson@amd.com>
 M:	Brett Creeley <brett.creeley@amd.com>
-M:	drivers@pensando.io
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	Documentation/networking/device_drivers/ethernet/pensando/ionic.rst
@@ -18002,7 +18002,7 @@ F:	tools/testing/selftests/proc/
 
 PROC SYSCTL
 M:	Luis Chamberlain <mcgrof@kernel.org>
-M:	Kees Cook <keescook@chromium.org>
+M:	Kees Cook <kees@kernel.org>
 M:	Joel Granados <j.granados@samsung.com>
 L:	linux-kernel@vger.kernel.org
 L:	linux-fsdevel@vger.kernel.org
@@ -18058,7 +18058,7 @@ F:	Documentation/devicetree/bindings/net/pse-pd/
 F:	drivers/net/pse-pd/
 
 PSTORE FILESYSTEM
-M:	Kees Cook <keescook@chromium.org>
+M:	Kees Cook <kees@kernel.org>
 R:	Tony Luck <tony.luck@intel.com>
 R:	Guilherme G. Piccoli <gpiccoli@igalia.com>
 L:	linux-hardening@vger.kernel.org
@@ -18216,6 +18216,7 @@ QCOM AUDIO (ASoC) DRIVERS
 M:	Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
 M:	Banajit Goswami <bgoswami@quicinc.com>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
+L:	linux-arm-msm@vger.kernel.org
 S:	Supported
 F:	Documentation/devicetree/bindings/soc/qcom/qcom,apr*
 F:	Documentation/devicetree/bindings/sound/qcom,*
@@ -20064,7 +20065,7 @@ F:	drivers/media/cec/platform/seco/seco-cec.c
 F:	drivers/media/cec/platform/seco/seco-cec.h
 
 SECURE COMPUTING
-M:	Kees Cook <keescook@chromium.org>
+M:	Kees Cook <kees@kernel.org>
 R:	Andy Lutomirski <luto@amacapital.net>
 R:	Will Drewry <wad@chromium.org>
 S:	Supported
@@ -22752,7 +22753,7 @@ M:	Jarkko Sakkinen <jarkko@kernel.org>
 R:	Jason Gunthorpe <jgg@ziepe.ca>
 L:	linux-integrity@vger.kernel.org
 S:	Maintained
-W:	https://gitlab.com/jarkkojs/linux-tpmdd-test
+W:	https://codeberg.org/jarkko/linux-tpmdd-test
 Q:	https://patchwork.kernel.org/project/linux-integrity/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jarkko/linux-tpmdd.git
 F:	Documentation/devicetree/bindings/tpm/
@@ -22978,7 +22979,7 @@ F:	drivers/block/ublk_drv.c
 F:	include/uapi/linux/ublk_cmd.h
 
 UBSAN
-M:	Kees Cook <keescook@chromium.org>
+M:	Kees Cook <kees@kernel.org>
 R:	Marco Elver <elver@google.com>
 R:	Andrey Konovalov <andreyknvl@gmail.com>
 R:	Andrey Ryabinin <ryabinin.a.a@gmail.com>
@@ -23980,7 +23981,6 @@ VMALLOC
 M:	Andrew Morton <akpm@linux-foundation.org>
 R:	Uladzislau Rezki <urezki@gmail.com>
 R:	Christoph Hellwig <hch@infradead.org>
-R:	Lorenzo Stoakes <lstoakes@gmail.com>
 L:	linux-mm@kvack.org
 S:	Maintained
 W:	http://www.linux-mm.org
@@ -24816,7 +24816,7 @@ F:	drivers/net/hamradio/yam*
 F:	include/linux/yam.h
 
 YAMA SECURITY MODULE
-M:	Kees Cook <keescook@chromium.org>
+M:	Kees Cook <kees@kernel.org>
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/hardening
 F:	Documentation/admin-guide/LSM/Yama.rst

Makefile

@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 10
 SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc6
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*

arch/arm/boot/dts/nxp/imx/imx53-qsb-common.dtsi

@@ -85,7 +85,7 @@
 		};
 	};
 
-	panel {
+	panel_dpi: panel {
 		compatible = "sii,43wvf1g";
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_display_power>;

arch/arm/boot/dts/nxp/imx/imx53-qsb-hdmi.dtso

@@ -10,8 +10,6 @@
 /plugin/;
 
 &{/} {
-	/delete-node/ panel;
-
 	hdmi: connector-hdmi {
 		compatible = "hdmi-connector";
 		label = "hdmi";
@@ -82,6 +80,10 @@
 	};
 };
 
+&panel_dpi {
+	status = "disabled";
+};
+
 &tve {
 	status = "disabled";
 };

arch/arm/include/asm/efi.h

@@ -14,6 +14,7 @@
 #include <asm/mach/map.h>
 #include <asm/mmu_context.h>
 #include <asm/ptrace.h>
+#include <asm/uaccess.h>
 
 #ifdef CONFIG_EFI
 void efi_init(void);
@@ -25,6 +26,18 @@ int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md, boo
 #define arch_efi_call_virt_setup()	efi_virtmap_load()
 #define arch_efi_call_virt_teardown()	efi_virtmap_unload()
 
+#ifdef CONFIG_CPU_TTBR0_PAN
+#undef arch_efi_call_virt
+#define arch_efi_call_virt(p, f, args...) ({				\
+	unsigned int flags = uaccess_save_and_enable();			\
+	efi_status_t res = _Generic((p)->f(args),			\
+			efi_status_t:	(p)->f(args),			\
+			default:	((p)->f(args), EFI_ABORTED));	\
+	uaccess_restore(flags);						\
+	res;								\
+})
+#endif
+
 #define ARCH_EFI_IRQ_FLAGS_MASK \
 	(PSR_J_BIT | PSR_E_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT | \
 	 PSR_T_BIT | MODE_MASK)

arch/arm/kernel/ftrace.c

@@ -232,11 +232,24 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 	unsigned long old;
 
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
+err_out:
 		return;
 
 	if (IS_ENABLED(CONFIG_UNWINDER_FRAME_POINTER)) {
-		/* FP points one word below parent's top of stack */
+		/*
-		frame_pointer += 4;
+		 * Usually, the stack frames are contiguous in memory but cases
+		 * have been observed where the next stack frame does not live
+		 * at 'frame_pointer + 4' as this code used to assume.
+		 *
+		 * Instead, dereference the field in the stack frame that
+		 * stores the SP of the calling frame: to avoid unbounded
+		 * recursion, this cannot involve any ftrace instrumented
+		 * functions, so use the __get_kernel_nofault() primitive
+		 * directly.
+		 */
+		__get_kernel_nofault(&frame_pointer,
+				     (unsigned long *)(frame_pointer - 8),
+				     unsigned long, err_out);
 	} else {
 		struct stackframe frame = {
 			.fp = frame_pointer,

arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi

@@ -6,6 +6,7 @@
 #include <dt-bindings/phy/phy-imx8-pcie.h>
 #include <dt-bindings/pwm/pwm.h>
 #include "imx8mm.dtsi"
+#include "imx8mm-overdrive.dtsi"
 
 / {
 	chosen {
@@ -935,7 +936,7 @@
 	/* Verdin GPIO_9_DSI (pulled-up as active-low) */
 	pinctrl_gpio_9_dsi: gpio9dsigrp {
 		fsl,pins =
-			<MX8MM_IOMUXC_NAND_RE_B_GPIO3_IO15		0x146>;	/* SODIMM 17 */
+			<MX8MM_IOMUXC_NAND_RE_B_GPIO3_IO15		0x1c6>;	/* SODIMM 17 */
 	};
 
 	/* Verdin GPIO_10_DSI (pulled-up as active-low) */

arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi

@@ -254,7 +254,7 @@
 				  <&clk IMX8MP_CLK_CLKOUT2>,
 				  <&clk IMX8MP_AUDIO_PLL2_OUT>;
 		assigned-clock-parents = <&clk IMX8MP_AUDIO_PLL2_OUT>;
-		assigned-clock-rates = <13000000>, <13000000>, <156000000>;
+		assigned-clock-rates = <13000000>, <13000000>, <208000000>;
 		reset-gpios = <&gpio4 1 GPIO_ACTIVE_HIGH>;
 		status = "disabled";
 

arch/arm64/boot/dts/freescale/imx8mp-venice-gw73xx.dtsi

@@ -219,7 +219,7 @@
 
 	bluetooth {
 		compatible = "brcm,bcm4330-bt";
-		shutdown-gpios = <&gpio4 16 GPIO_ACTIVE_HIGH>;
+		shutdown-gpios = <&gpio1 3 GPIO_ACTIVE_HIGH>;
 	};
 };
 

arch/arm64/boot/dts/freescale/imx8qm-mek.dts

@@ -36,7 +36,7 @@
 		regulator-name = "SD1_SPWR";
 		regulator-min-microvolt = <3000000>;
 		regulator-max-microvolt = <3000000>;
-		gpio = <&lsio_gpio4 19 GPIO_ACTIVE_HIGH>;
+		gpio = <&lsio_gpio4 7 GPIO_ACTIVE_HIGH>;
 		enable-active-high;
 	};
 

arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts

@@ -296,7 +296,6 @@
 	vmmc-supply = <&reg_usdhc2_vmmc>;
 	bus-width = <4>;
 	status = "okay";
-	no-sdio;
 	no-mmc;
 };
 

arch/arm64/include/asm/pgtable-hwdef.h

@@ -170,6 +170,7 @@
 #define PTE_CONT		(_AT(pteval_t, 1) << 52)	/* Contiguous range */
 #define PTE_PXN			(_AT(pteval_t, 1) << 53)	/* Privileged XN */
 #define PTE_UXN			(_AT(pteval_t, 1) << 54)	/* User XN */
+#define PTE_SWBITS_MASK		_AT(pteval_t, (BIT(63) | GENMASK(58, 55)))
 
 #define PTE_ADDR_LOW		(((_AT(pteval_t, 1) << (50 - PAGE_SHIFT)) - 1) << PAGE_SHIFT)
 #ifdef CONFIG_ARM64_PA_BITS_52

arch/arm64/include/asm/unistd32.h

@@ -840,7 +840,7 @@ __SYSCALL(__NR_pselect6_time64, compat_sys_pselect6_time64)
 #define __NR_ppoll_time64 414
 __SYSCALL(__NR_ppoll_time64, compat_sys_ppoll_time64)
 #define __NR_io_pgetevents_time64 416
-__SYSCALL(__NR_io_pgetevents_time64, sys_io_pgetevents)
+__SYSCALL(__NR_io_pgetevents_time64, compat_sys_io_pgetevents_time64)
 #define __NR_recvmmsg_time64 417
 __SYSCALL(__NR_recvmmsg_time64, compat_sys_recvmmsg_time64)
 #define __NR_mq_timedsend_time64 418

arch/arm64/kernel/efi.c

@@ -9,6 +9,7 @@
 
 #include <linux/efi.h>
 #include <linux/init.h>
+#include <linux/kmemleak.h>
 #include <linux/screen_info.h>
 #include <linux/vmalloc.h>
 
@@ -213,6 +214,7 @@ l:	if (!p) {
 		return -ENOMEM;
 	}
 
+	kmemleak_not_leak(p);
 	efi_rt_stack_top = p + THREAD_SIZE;
 	return 0;
 }

arch/arm64/kernel/pi/map_kernel.c

@@ -173,7 +173,7 @@ static void __init remap_idmap_for_lpa2(void)
 	 * Don't bother with the FDT, we no longer need it after this.
 	 */
 	memset(init_idmap_pg_dir, 0,
-	       (u64)init_idmap_pg_dir - (u64)init_idmap_pg_end);
+	       (u64)init_idmap_pg_end - (u64)init_idmap_pg_dir);
 
 	create_init_idmap(init_idmap_pg_dir, mask);
 	dsb(ishst);

arch/arm64/kernel/syscall.c

@@ -53,17 +53,15 @@ static void invoke_syscall(struct pt_regs *regs, unsigned int scno,
 	syscall_set_return_value(current, regs, 0, ret);
 
 	/*
-	 * Ultimately, this value will get limited by KSTACK_OFFSET_MAX(),
+	 * This value will get limited by KSTACK_OFFSET_MAX(), which is 10
-	 * but not enough for arm64 stack utilization comfort. To keep
+	 * bits. The actual entropy will be further reduced by the compiler
-	 * reasonable stack head room, reduce the maximum offset to 9 bits.
+	 * when applying stack alignment constraints: the AAPCS mandates a
+	 * 16-byte aligned SP at function boundaries, which will remove the
+	 * 4 low bits from any entropy chosen here.
 	 *
-	 * The actual entropy will be further reduced by the compiler when
+	 * The resulting 6 bits of entropy is seen in SP[9:4].
-	 * applying stack alignment constraints: the AAPCS mandates a
-	 * 16-byte (i.e. 4-bit) aligned SP at function boundaries.
-	 *
-	 * The resulting 5 bits of entropy is seen in SP[8:4].
 	 */
-	choose_random_kstack_offset(get_random_u16() & 0x1FF);
+	choose_random_kstack_offset(get_random_u16());
 }
 
 static inline bool has_syscall_work(unsigned long flags)

arch/arm64/kvm/hyp/nvhe/ffa.c

@@ -177,6 +177,14 @@ static void ffa_retrieve_req(struct arm_smccc_res *res, u32 len)
 			  res);
 }
 
+static void ffa_rx_release(struct arm_smccc_res *res)
+{
+	arm_smccc_1_1_smc(FFA_RX_RELEASE,
+			  0, 0,
+			  0, 0, 0, 0, 0,
+			  res);
+}
+
 static void do_ffa_rxtx_map(struct arm_smccc_res *res,
 			    struct kvm_cpu_context *ctxt)
 {
@@ -543,16 +551,19 @@ static void do_ffa_mem_reclaim(struct arm_smccc_res *res,
 	if (WARN_ON(offset > len ||
 		    fraglen > KVM_FFA_MBOX_NR_PAGES * PAGE_SIZE)) {
 		ret = FFA_RET_ABORTED;
+		ffa_rx_release(res);
 		goto out_unlock;
 	}
 
 	if (len > ffa_desc_buf.len) {
 		ret = FFA_RET_NO_MEMORY;
+		ffa_rx_release(res);
 		goto out_unlock;
 	}
 
 	buf = ffa_desc_buf.buf;
 	memcpy(buf, hyp_buffers.rx, fraglen);
+	ffa_rx_release(res);
 
 	for (fragoff = fraglen; fragoff < len; fragoff += fraglen) {
 		ffa_mem_frag_rx(res, handle_lo, handle_hi, fragoff);
@@ -563,6 +574,7 @@ static void do_ffa_mem_reclaim(struct arm_smccc_res *res,
 
 		fraglen = res->a3;
 		memcpy((void *)buf + fragoff, hyp_buffers.rx, fraglen);
+		ffa_rx_release(res);
 	}
 
 	ffa_mem_reclaim(res, handle_lo, handle_hi, flags);

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

@@ -391,7 +391,7 @@ static void kvm_vgic_dist_destroy(struct kvm *kvm)
 
 	if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
 		list_for_each_entry_safe(rdreg, next, &dist->rd_regions, list)
-			vgic_v3_free_redist_region(rdreg);
+			vgic_v3_free_redist_region(kvm, rdreg);
 		INIT_LIST_HEAD(&dist->rd_regions);
 	} else {
 		dist->vgic_cpu_base = VGIC_ADDR_UNDEF;

arch/arm64/kvm/vgic/vgic-mmio-v3.c

@@ -919,8 +919,19 @@ free:
 	return ret;
 }
 
-void vgic_v3_free_redist_region(struct vgic_redist_region *rdreg)
+void vgic_v3_free_redist_region(struct kvm *kvm, struct vgic_redist_region *rdreg)
 {
+	struct kvm_vcpu *vcpu;
+	unsigned long c;
+
+	lockdep_assert_held(&kvm->arch.config_lock);
+
+	/* Garbage collect the region */
+	kvm_for_each_vcpu(c, vcpu, kvm) {
+		if (vcpu->arch.vgic_cpu.rdreg == rdreg)
+			vcpu->arch.vgic_cpu.rdreg = NULL;
+	}
+
 	list_del(&rdreg->list);
 	kfree(rdreg);
 }
@@ -945,7 +956,7 @@ int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count)
 
 		mutex_lock(&kvm->arch.config_lock);
 		rdreg = vgic_v3_rdist_region_from_index(kvm, index);
-		vgic_v3_free_redist_region(rdreg);
+		vgic_v3_free_redist_region(kvm, rdreg);
 		mutex_unlock(&kvm->arch.config_lock);
 		return ret;
 	}

arch/arm64/kvm/vgic/vgic.h

@@ -316,7 +316,7 @@ vgic_v3_rd_region_size(struct kvm *kvm, struct vgic_redist_region *rdreg)
 
 struct vgic_redist_region *vgic_v3_rdist_region_from_index(struct kvm *kvm,
 							   u32 index);
-void vgic_v3_free_redist_region(struct vgic_redist_region *rdreg);
+void vgic_v3_free_redist_region(struct kvm *kvm, struct vgic_redist_region *rdreg);
 
 bool vgic_v3_rdist_overlap(struct kvm *kvm, gpa_t base, size_t size);
 

arch/arm64/mm/mmu.c

@@ -124,7 +124,8 @@ bool pgattr_change_is_safe(u64 old, u64 new)
 	 * The following mapping attributes may be updated in live
 	 * kernel mappings without the need for break-before-make.
 	 */
-	pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE | PTE_NG;
+	pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE | PTE_NG |
+			PTE_SWBITS_MASK;
 
 	/* creating or taking down mappings is always safe */
 	if (!pte_valid(__pte(old)) || !pte_valid(__pte(new)))

arch/csky/include/uapi/asm/unistd.h

@@ -6,6 +6,7 @@
 #define __ARCH_WANT_SYS_CLONE3
 #define __ARCH_WANT_SET_GET_RLIMIT
 #define __ARCH_WANT_TIME32_SYSCALLS
+#define __ARCH_WANT_SYNC_FILE_RANGE2
 #include <asm-generic/unistd.h>
 
 #define __NR_set_thread_area	(__NR_arch_specific_syscall + 0)

arch/csky/kernel/syscall.c

@@ -20,7 +20,7 @@ SYSCALL_DEFINE6(mmap2,
 	unsigned long, prot,
 	unsigned long, flags,
 	unsigned long, fd,
-	off_t, offset)
+	unsigned long, offset)
 {
 	if (unlikely(offset & (~PAGE_MASK >> 12)))
 		return -EINVAL;

arch/hexagon/include/asm/syscalls.h

@@ -0,0 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <asm-generic/syscalls.h>
+
+asmlinkage long sys_hexagon_fadvise64_64(int fd, int advice,
+	                                  u32 a2, u32 a3, u32 a4, u32 a5);

arch/hexagon/include/uapi/asm/unistd.h

@@ -36,5 +36,6 @@
 #define __ARCH_WANT_SYS_VFORK
 #define __ARCH_WANT_SYS_FORK
 #define __ARCH_WANT_TIME32_SYSCALLS
+#define __ARCH_WANT_SYNC_FILE_RANGE2
 
 #include <asm-generic/unistd.h>

arch/hexagon/kernel/syscalltab.c

@@ -14,6 +14,13 @@
 #undef __SYSCALL
 #define __SYSCALL(nr, call) [nr] = (call),
 
+SYSCALL_DEFINE6(hexagon_fadvise64_64, int, fd, int, advice,
+		SC_ARG64(offset), SC_ARG64(len))
+{
+	return ksys_fadvise64_64(fd, SC_VAL64(loff_t, offset), SC_VAL64(loff_t, len), advice);
+}
+#define sys_fadvise64_64 sys_hexagon_fadvise64_64
+
 void *sys_call_table[__NR_syscalls] = {
 #include <asm/unistd.h>
 };

arch/loongarch/Kconfig

@@ -143,7 +143,7 @@ config LOONGARCH
 	select HAVE_LIVEPATCH
 	select HAVE_MOD_ARCH_SPECIFIC
 	select HAVE_NMI
-	select HAVE_OBJTOOL if AS_HAS_EXPLICIT_RELOCS
+	select HAVE_OBJTOOL if AS_HAS_EXPLICIT_RELOCS && AS_HAS_THIN_ADD_SUB && !CC_IS_CLANG
 	select HAVE_PCI
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
@@ -261,6 +261,9 @@ config AS_HAS_EXPLICIT_RELOCS
 config AS_HAS_FCSR_CLASS
 	def_bool $(as-instr,movfcsr2gr \$t0$(comma)\$fcsr0)
 
+config AS_HAS_THIN_ADD_SUB
+	def_bool $(cc-option,-Wa$(comma)-mthin-add-sub)
+
 config AS_HAS_LSX_EXTENSION
 	def_bool $(as-instr,vld \$vr0$(comma)\$a0$(comma)0)
 

arch/loongarch/Kconfig.debug

@@ -28,6 +28,7 @@ config UNWINDER_PROLOGUE
 
 config UNWINDER_ORC
 	bool "ORC unwinder"
+	depends on HAVE_OBJTOOL
 	select OBJTOOL
 	help
 	  This option enables the ORC (Oops Rewind Capability) unwinder for

arch/loongarch/include/asm/hw_breakpoint.h

@@ -75,6 +75,8 @@ do {								\
 #define CSR_MWPC_NUM		0x3f
 
 #define CTRL_PLV_ENABLE		0x1e
+#define CTRL_PLV0_ENABLE	0x02
+#define CTRL_PLV3_ENABLE	0x10
 
 #define MWPnCFG3_LoadEn		8
 #define MWPnCFG3_StoreEn	9
@@ -101,7 +103,7 @@ struct perf_event;
 struct perf_event_attr;
 
 extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
-				  int *gen_len, int *gen_type, int *offset);
+				  int *gen_len, int *gen_type);
 extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
 extern int hw_breakpoint_arch_parse(struct perf_event *bp,
 				    const struct perf_event_attr *attr,

arch/loongarch/kernel/hw_breakpoint.c

@@ -174,11 +174,21 @@ void flush_ptrace_hw_breakpoint(struct task_struct *tsk)
 static int hw_breakpoint_control(struct perf_event *bp,
 				 enum hw_breakpoint_ops ops)
 {
-	u32 ctrl;
+	u32 ctrl, privilege;
 	int i, max_slots, enable;
+	struct pt_regs *regs;
 	struct perf_event **slots;
 	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 
+	if (arch_check_bp_in_kernelspace(info))
+		privilege = CTRL_PLV0_ENABLE;
+	else
+		privilege = CTRL_PLV3_ENABLE;
+
+	/*  Whether bp belongs to a task. */
+	if (bp->hw.target)
+		regs = task_pt_regs(bp->hw.target);
+
 	if (info->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) {
 		/* Breakpoint */
 		slots = this_cpu_ptr(bp_on_reg);
@@ -197,31 +207,38 @@ static int hw_breakpoint_control(struct perf_event *bp,
 	switch (ops) {
 	case HW_BREAKPOINT_INSTALL:
 		/* Set the FWPnCFG/MWPnCFG 1~4 register. */
-		write_wb_reg(CSR_CFG_ADDR, i, 0, info->address);
-		write_wb_reg(CSR_CFG_ADDR, i, 1, info->address);
-		write_wb_reg(CSR_CFG_MASK, i, 0, info->mask);
-		write_wb_reg(CSR_CFG_MASK, i, 1, info->mask);
-		write_wb_reg(CSR_CFG_ASID, i, 0, 0);
-		write_wb_reg(CSR_CFG_ASID, i, 1, 0);
 		if (info->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) {
-			write_wb_reg(CSR_CFG_CTRL, i, 0, CTRL_PLV_ENABLE);
+			write_wb_reg(CSR_CFG_ADDR, i, 0, info->address);
+			write_wb_reg(CSR_CFG_MASK, i, 0, info->mask);
+			write_wb_reg(CSR_CFG_ASID, i, 0, 0);
+			write_wb_reg(CSR_CFG_CTRL, i, 0, privilege);
 		} else {
+			write_wb_reg(CSR_CFG_ADDR, i, 1, info->address);
+			write_wb_reg(CSR_CFG_MASK, i, 1, info->mask);
+			write_wb_reg(CSR_CFG_ASID, i, 1, 0);
 			ctrl = encode_ctrl_reg(info->ctrl);
-			write_wb_reg(CSR_CFG_CTRL, i, 1, ctrl | CTRL_PLV_ENABLE);
+			write_wb_reg(CSR_CFG_CTRL, i, 1, ctrl | privilege);
 		}
 		enable = csr_read64(LOONGARCH_CSR_CRMD);
 		csr_write64(CSR_CRMD_WE | enable, LOONGARCH_CSR_CRMD);
+		if (bp->hw.target)
+			regs->csr_prmd |= CSR_PRMD_PWE;
 		break;
 	case HW_BREAKPOINT_UNINSTALL:
 		/* Reset the FWPnCFG/MWPnCFG 1~4 register. */
-		write_wb_reg(CSR_CFG_ADDR, i, 0, 0);
+		if (info->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) {
-		write_wb_reg(CSR_CFG_ADDR, i, 1, 0);
+			write_wb_reg(CSR_CFG_ADDR, i, 0, 0);
-		write_wb_reg(CSR_CFG_MASK, i, 0, 0);
+			write_wb_reg(CSR_CFG_MASK, i, 0, 0);
-		write_wb_reg(CSR_CFG_MASK, i, 1, 0);
+			write_wb_reg(CSR_CFG_CTRL, i, 0, 0);
-		write_wb_reg(CSR_CFG_CTRL, i, 0, 0);
+			write_wb_reg(CSR_CFG_ASID, i, 0, 0);
-		write_wb_reg(CSR_CFG_CTRL, i, 1, 0);
+		} else {
-		write_wb_reg(CSR_CFG_ASID, i, 0, 0);
+			write_wb_reg(CSR_CFG_ADDR, i, 1, 0);
-		write_wb_reg(CSR_CFG_ASID, i, 1, 0);
+			write_wb_reg(CSR_CFG_MASK, i, 1, 0);
+			write_wb_reg(CSR_CFG_CTRL, i, 1, 0);
+			write_wb_reg(CSR_CFG_ASID, i, 1, 0);
+		}
+		if (bp->hw.target)
+			regs->csr_prmd &= ~CSR_PRMD_PWE;
 		break;
 	}
 
@@ -283,7 +300,7 @@ int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
  * to generic breakpoint descriptions.
  */
 int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
-			   int *gen_len, int *gen_type, int *offset)
+			   int *gen_len, int *gen_type)
 {
 	/* Type */
 	switch (ctrl.type) {
@@ -303,11 +320,6 @@ int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
 		return -EINVAL;
 	}
 
-	if (!ctrl.len)
-		return -EINVAL;
-
-	*offset = __ffs(ctrl.len);
-
 	/* Len */
 	switch (ctrl.len) {
 	case LOONGARCH_BREAKPOINT_LEN_1:
@@ -386,21 +398,17 @@ int hw_breakpoint_arch_parse(struct perf_event *bp,
 			     struct arch_hw_breakpoint *hw)
 {
 	int ret;
-	u64 alignment_mask, offset;
+	u64 alignment_mask;
 
 	/* Build the arch_hw_breakpoint. */
 	ret = arch_build_bp_info(bp, attr, hw);
 	if (ret)
 		return ret;
 
-	if (hw->ctrl.type != LOONGARCH_BREAKPOINT_EXECUTE)
+	if (hw->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) {
-		alignment_mask = 0x7;
-	else
 		alignment_mask = 0x3;
-	offset = hw->address & alignment_mask;
+		hw->address &= ~alignment_mask;
-
+	}
-	hw->address &= ~alignment_mask;
-	hw->ctrl.len <<= offset;
 
 	return 0;
 }
@@ -471,12 +479,15 @@ void breakpoint_handler(struct pt_regs *regs)
 	slots = this_cpu_ptr(bp_on_reg);
 
 	for (i = 0; i < boot_cpu_data.watch_ireg_count; ++i) {
-		bp = slots[i];
+		if ((csr_read32(LOONGARCH_CSR_FWPS) & (0x1 << i))) {
-		if (bp == NULL)
+			bp = slots[i];
-			continue;
+			if (bp == NULL)
-		perf_bp_event(bp, regs);
+				continue;
+			perf_bp_event(bp, regs);
+			csr_write32(0x1 << i, LOONGARCH_CSR_FWPS);
+			update_bp_registers(regs, 0, 0);
+		}
 	}
-	update_bp_registers(regs, 0, 0);
 }
 NOKPROBE_SYMBOL(breakpoint_handler);
 
@@ -488,12 +499,15 @@ void watchpoint_handler(struct pt_regs *regs)
 	slots = this_cpu_ptr(wp_on_reg);
 
 	for (i = 0; i < boot_cpu_data.watch_dreg_count; ++i) {
-		wp = slots[i];
+		if ((csr_read32(LOONGARCH_CSR_MWPS) & (0x1 << i))) {
-		if (wp == NULL)
+			wp = slots[i];
-			continue;
+			if (wp == NULL)
-		perf_bp_event(wp, regs);
+				continue;
+			perf_bp_event(wp, regs);
+			csr_write32(0x1 << i, LOONGARCH_CSR_MWPS);
+			update_bp_registers(regs, 0, 1);
+		}
 	}
-	update_bp_registers(regs, 0, 1);
 }
 NOKPROBE_SYMBOL(watchpoint_handler);
 

arch/loongarch/kernel/ptrace.c

@@ -494,28 +494,14 @@ static int ptrace_hbp_fill_attr_ctrl(unsigned int note_type,
 				     struct arch_hw_breakpoint_ctrl ctrl,
 				     struct perf_event_attr *attr)
 {
-	int err, len, type, offset;
+	int err, len, type;
 
-	err = arch_bp_generic_fields(ctrl, &len, &type, &offset);
+	err = arch_bp_generic_fields(ctrl, &len, &type);
 	if (err)
 		return err;
 
-	switch (note_type) {
-	case NT_LOONGARCH_HW_BREAK:
-		if ((type & HW_BREAKPOINT_X) != type)
-			return -EINVAL;
-		break;
-	case NT_LOONGARCH_HW_WATCH:
-		if ((type & HW_BREAKPOINT_RW) != type)
-			return -EINVAL;
-		break;
-	default:
-		return -EINVAL;
-	}
-
 	attr->bp_len	= len;
 	attr->bp_type	= type;
-	attr->bp_addr	+= offset;
 
 	return 0;
 }
@@ -609,10 +595,27 @@ static int ptrace_hbp_set_ctrl(unsigned int note_type,
 		return PTR_ERR(bp);
 
 	attr = bp->attr;
-	decode_ctrl_reg(uctrl, &ctrl);
+
-	err = ptrace_hbp_fill_attr_ctrl(note_type, ctrl, &attr);
+	switch (note_type) {
-	if (err)
+	case NT_LOONGARCH_HW_BREAK:
-		return err;
+		ctrl.type = LOONGARCH_BREAKPOINT_EXECUTE;
+		ctrl.len = LOONGARCH_BREAKPOINT_LEN_4;
+		break;
+	case NT_LOONGARCH_HW_WATCH:
+		decode_ctrl_reg(uctrl, &ctrl);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (uctrl & CTRL_PLV_ENABLE) {
+		err = ptrace_hbp_fill_attr_ctrl(note_type, ctrl, &attr);
+		if (err)
+			return err;
+		attr.disabled = 0;
+	} else {
+		attr.disabled = 1;
+	}
 
 	return modify_user_hw_breakpoint(bp, &attr);
 }
@@ -643,6 +646,10 @@ static int ptrace_hbp_set_addr(unsigned int note_type,
 	struct perf_event *bp;
 	struct perf_event_attr attr;
 
+	/* Kernel-space address cannot be monitored by user-space */
+	if ((unsigned long)addr >= XKPRANGE)
+		return -EINVAL;
+
 	bp = ptrace_hbp_get_initialised_bp(note_type, tsk, idx);
 	if (IS_ERR(bp))
 		return PTR_ERR(bp);

arch/loongarch/kernel/syscall.c

@@ -22,7 +22,7 @@
 #define __SYSCALL(nr, call)	[nr] = (call),
 
 SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, unsigned long,
-		prot, unsigned long, flags, unsigned long, fd, off_t, offset)
+		prot, unsigned long, flags, unsigned long, fd, unsigned long, offset)
 {
 	if (offset & ~PAGE_MASK)
 		return -EINVAL;

arch/loongarch/kvm/exit.c

@@ -761,7 +761,7 @@ static void kvm_handle_service(struct kvm_vcpu *vcpu)
 	default:
 		ret = KVM_HCALL_INVALID_CODE;
 		break;
-	};
+	}
 
 	kvm_write_reg(vcpu, LOONGARCH_GPR_A0, ret);
 }

arch/microblaze/kernel/sys_microblaze.c

@@ -35,7 +35,7 @@
 
 SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
 		unsigned long, prot, unsigned long, flags, unsigned long, fd,
-		off_t, pgoff)
+		unsigned long, pgoff)
 {
 	if (pgoff & ~PAGE_MASK)
 		return -EINVAL;

arch/mips/bmips/setup.c

@@ -110,7 +110,8 @@ static void bcm6358_quirks(void)
 	 * RAC flush causes kernel panics on BCM6358 when booting from TP1
 	 * because the bootloader is not initializing it properly.
 	 */
-	bmips_rac_flush_disable = !!(read_c0_brcm_cmt_local() & (1 << 31));
+	bmips_rac_flush_disable = !!(read_c0_brcm_cmt_local() & (1 << 31)) ||
+				  !!BMIPS_GET_CBR();
 }
 
 static void bcm6368_quirks(void)

arch/mips/include/asm/mipsmtregs.h

@@ -322,7 +322,7 @@ static inline void ehb(void)
 	"	.set	push				\n"	\
 	"	.set	"MIPS_ISA_LEVEL"		\n"	\
 	_ASM_SET_MFTC0							\
-	"	mftc0	$1, " #rt ", " #sel "		\n"	\
+	"	mftc0	%0, " #rt ", " #sel "		\n"	\
 	_ASM_UNSET_MFTC0						\
 	"	.set	pop				\n"	\
 	: "=r" (__res));						\

arch/mips/kernel/syscalls/syscall_n32.tbl

@@ -354,7 +354,7 @@
 412	n32	utimensat_time64		sys_utimensat
 413	n32	pselect6_time64			compat_sys_pselect6_time64
 414	n32	ppoll_time64			compat_sys_ppoll_time64
-416	n32	io_pgetevents_time64		sys_io_pgetevents
+416	n32	io_pgetevents_time64		compat_sys_io_pgetevents_time64
 417	n32	recvmmsg_time64			compat_sys_recvmmsg_time64
 418	n32	mq_timedsend_time64		sys_mq_timedsend
 419	n32	mq_timedreceive_time64		sys_mq_timedreceive

arch/mips/kernel/syscalls/syscall_o32.tbl

@@ -27,7 +27,7 @@
 17	o32	break				sys_ni_syscall
 # 18 was sys_stat
 18	o32	unused18			sys_ni_syscall
-19	o32	lseek				sys_lseek
+19	o32	lseek				sys_lseek			compat_sys_lseek
 20	o32	getpid				sys_getpid
 21	o32	mount				sys_mount
 22	o32	umount				sys_oldumount
@@ -403,7 +403,7 @@
 412	o32	utimensat_time64		sys_utimensat			sys_utimensat
 413	o32	pselect6_time64			sys_pselect6			compat_sys_pselect6_time64
 414	o32	ppoll_time64			sys_ppoll			compat_sys_ppoll_time64
-416	o32	io_pgetevents_time64		sys_io_pgetevents		sys_io_pgetevents
+416	o32	io_pgetevents_time64		sys_io_pgetevents		compat_sys_io_pgetevents_time64
 417	o32	recvmmsg_time64			sys_recvmmsg			compat_sys_recvmmsg_time64
 418	o32	mq_timedsend_time64		sys_mq_timedsend		sys_mq_timedsend
 419	o32	mq_timedreceive_time64		sys_mq_timedreceive		sys_mq_timedreceive

arch/mips/pci/ops-rc32434.c

@@ -112,8 +112,8 @@ retry:
 	 * gives them time to settle
 	 */
 	if (where == PCI_VENDOR_ID) {
-		if (ret == 0xffffffff || ret == 0x00000000 ||
+		if (*val == 0xffffffff || *val == 0x00000000 ||
-		    ret == 0x0000ffff || ret == 0xffff0000) {
+		    *val == 0x0000ffff || *val == 0xffff0000) {
 			if (delay > 4)
 				return 0;
 			delay *= 2;

arch/parisc/Kconfig

@@ -16,6 +16,7 @@ config PARISC
 	select ARCH_HAS_UBSAN
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_NO_SG_CHAIN
+	select ARCH_SPLIT_ARG64 if !64BIT
 	select ARCH_SUPPORTS_HUGETLBFS if PA20
 	select ARCH_SUPPORTS_MEMORY_FAILURE
 	select ARCH_STACKWALK

arch/parisc/include/asm/cacheflush.h

@@ -31,18 +31,17 @@ void flush_cache_all_local(void);
 void flush_cache_all(void);
 void flush_cache_mm(struct mm_struct *mm);
 
-void flush_kernel_dcache_page_addr(const void *addr);
-
 #define flush_kernel_dcache_range(start,size) \
 	flush_kernel_dcache_range_asm((start), (start)+(size));
 
+/* The only way to flush a vmap range is to flush whole cache */
 #define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1
 void flush_kernel_vmap_range(void *vaddr, int size);
 void invalidate_kernel_vmap_range(void *vaddr, int size);
 
-#define flush_cache_vmap(start, end)		flush_cache_all()
+void flush_cache_vmap(unsigned long start, unsigned long end);
 #define flush_cache_vmap_early(start, end)	do { } while (0)
-#define flush_cache_vunmap(start, end)		flush_cache_all()
+void flush_cache_vunmap(unsigned long start, unsigned long end);
 
 void flush_dcache_folio(struct folio *folio);
 #define flush_dcache_folio flush_dcache_folio
@@ -77,17 +76,11 @@ void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr,
 void flush_cache_range(struct vm_area_struct *vma,
 		unsigned long start, unsigned long end);
 
-/* defined in pacache.S exported in cache.c used by flush_anon_page */
-void flush_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr);
-
 #define ARCH_HAS_FLUSH_ANON_PAGE
 void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr);
 
 #define ARCH_HAS_FLUSH_ON_KUNMAP
-static inline void kunmap_flush_on_unmap(const void *addr)
+void kunmap_flush_on_unmap(const void *addr);
-{
-	flush_kernel_dcache_page_addr(addr);
-}
 
 #endif /* _PARISC_CACHEFLUSH_H */
 

arch/parisc/include/asm/pgtable.h

@@ -448,14 +448,17 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
 	return pte;
 }
 
+static inline pte_t ptep_get(pte_t *ptep)
+{
+	return READ_ONCE(*ptep);
+}
+#define ptep_get ptep_get
+
 static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
 {
 	pte_t pte;
 
-	if (!pte_young(*ptep))
+	pte = ptep_get(ptep);
-		return 0;
-
-	pte = *ptep;
 	if (!pte_young(pte)) {
 		return 0;
 	}
@@ -463,17 +466,10 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned
 	return 1;
 }
 
+int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep);
+pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep);
+
 struct mm_struct;
-static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
-{
-	pte_t old_pte;
-
-	old_pte = *ptep;
-	set_pte(ptep, __pte(0));
-
-	return old_pte;
-}
-
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
 	set_pte(ptep, pte_wrprotect(*ptep));
@@ -511,7 +507,8 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
 
 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
-#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
+#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
+#define __HAVE_ARCH_PTEP_CLEAR_FLUSH
 #define __HAVE_ARCH_PTEP_SET_WRPROTECT
 #define __HAVE_ARCH_PTE_SAME
 

arch/parisc/kernel/cache.c

@@ -20,6 +20,7 @@
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
 #include <linux/syscalls.h>
+#include <linux/vmalloc.h>
 #include <asm/pdc.h>
 #include <asm/cache.h>
 #include <asm/cacheflush.h>
@@ -31,20 +32,31 @@
 #include <asm/mmu_context.h>
 #include <asm/cachectl.h>
 
+#define PTR_PAGE_ALIGN_DOWN(addr) PTR_ALIGN_DOWN(addr, PAGE_SIZE)
+
+/*
+ * When nonzero, use _PAGE_ACCESSED bit to try to reduce the number
+ * of page flushes done flush_cache_page_if_present. There are some
+ * pros and cons in using this option. It may increase the risk of
+ * random segmentation faults.
+ */
+#define CONFIG_FLUSH_PAGE_ACCESSED	0
+
 int split_tlb __ro_after_init;
 int dcache_stride __ro_after_init;
 int icache_stride __ro_after_init;
 EXPORT_SYMBOL(dcache_stride);
 
+/* Internal implementation in arch/parisc/kernel/pacache.S */
 void flush_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr);
 EXPORT_SYMBOL(flush_dcache_page_asm);
 void purge_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr);
 void flush_icache_page_asm(unsigned long phys_addr, unsigned long vaddr);
-
-/* Internal implementation in arch/parisc/kernel/pacache.S */
 void flush_data_cache_local(void *);  /* flushes local data-cache only */
 void flush_instruction_cache_local(void); /* flushes local code-cache only */
 
+static void flush_kernel_dcache_page_addr(const void *addr);
+
 /* On some machines (i.e., ones with the Merced bus), there can be
  * only a single PxTLB broadcast at a time; this must be guaranteed
  * by software. We need a spinlock around all TLB flushes to ensure
@@ -321,6 +333,18 @@ __flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr,
 {
 	if (!static_branch_likely(&parisc_has_cache))
 		return;
+
+	/*
+	 * The TLB is the engine of coherence on parisc.  The CPU is
+	 * entitled to speculate any page with a TLB mapping, so here
+	 * we kill the mapping then flush the page along a special flush
+	 * only alias mapping. This guarantees that the page is no-longer
+	 * in the cache for any process and nor may it be speculatively
+	 * read in (until the user or kernel specifically accesses it,
+	 * of course).
+	 */
+	flush_tlb_page(vma, vmaddr);
+
 	preempt_disable();
 	flush_dcache_page_asm(physaddr, vmaddr);
 	if (vma->vm_flags & VM_EXEC)
@@ -328,46 +352,44 @@ __flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr,
 	preempt_enable();
 }
 
-static void flush_user_cache_page(struct vm_area_struct *vma, unsigned long vmaddr)
+static void flush_kernel_dcache_page_addr(const void *addr)
 {
-	unsigned long flags, space, pgd, prot;
+	unsigned long vaddr = (unsigned long)addr;
-#ifdef CONFIG_TLB_PTLOCK
+	unsigned long flags;
-	unsigned long pgd_lock;
-#endif
 
-	vmaddr &= PAGE_MASK;
+	/* Purge TLB entry to remove translation on all CPUs */
+	purge_tlb_start(flags);
+	pdtlb(SR_KERNEL, addr);
+	purge_tlb_end(flags);
 
+	/* Use tmpalias flush to prevent data cache move-in */
 	preempt_disable();
-
+	flush_dcache_page_asm(__pa(vaddr), vaddr);
-	/* Set context for flush */
-	local_irq_save(flags);
-	prot = mfctl(8);
-	space = mfsp(SR_USER);
-	pgd = mfctl(25);
-#ifdef CONFIG_TLB_PTLOCK
-	pgd_lock = mfctl(28);
-#endif
-	switch_mm_irqs_off(NULL, vma->vm_mm, NULL);
-	local_irq_restore(flags);
-
-	flush_user_dcache_range_asm(vmaddr, vmaddr + PAGE_SIZE);
-	if (vma->vm_flags & VM_EXEC)
-		flush_user_icache_range_asm(vmaddr, vmaddr + PAGE_SIZE);
-	flush_tlb_page(vma, vmaddr);
-
-	/* Restore previous context */
-	local_irq_save(flags);
-#ifdef CONFIG_TLB_PTLOCK
-	mtctl(pgd_lock, 28);
-#endif
-	mtctl(pgd, 25);
-	mtsp(space, SR_USER);
-	mtctl(prot, 8);
-	local_irq_restore(flags);
-
 	preempt_enable();
 }
 
+static void flush_kernel_icache_page_addr(const void *addr)
+{
+	unsigned long vaddr = (unsigned long)addr;
+	unsigned long flags;
+
+	/* Purge TLB entry to remove translation on all CPUs */
+	purge_tlb_start(flags);
+	pdtlb(SR_KERNEL, addr);
+	purge_tlb_end(flags);
+
+	/* Use tmpalias flush to prevent instruction cache move-in */
+	preempt_disable();
+	flush_icache_page_asm(__pa(vaddr), vaddr);
+	preempt_enable();
+}
+
+void kunmap_flush_on_unmap(const void *addr)
+{
+	flush_kernel_dcache_page_addr(addr);
+}
+EXPORT_SYMBOL(kunmap_flush_on_unmap);
+
 void flush_icache_pages(struct vm_area_struct *vma, struct page *page,
 		unsigned int nr)
 {
@@ -375,13 +397,16 @@ void flush_icache_pages(struct vm_area_struct *vma, struct page *page,
 
 	for (;;) {
 		flush_kernel_dcache_page_addr(kaddr);
-		flush_kernel_icache_page(kaddr);
+		flush_kernel_icache_page_addr(kaddr);
 		if (--nr == 0)
 			break;
 		kaddr += PAGE_SIZE;
 	}
 }
 
+/*
+ * Walk page directory for MM to find PTEP pointer for address ADDR.
+ */
 static inline pte_t *get_ptep(struct mm_struct *mm, unsigned long addr)
 {
 	pte_t *ptep = NULL;
@@ -410,6 +435,41 @@ static inline bool pte_needs_flush(pte_t pte)
 		== (_PAGE_PRESENT | _PAGE_ACCESSED);
 }
 
+/*
+ * Return user physical address. Returns 0 if page is not present.
+ */
+static inline unsigned long get_upa(struct mm_struct *mm, unsigned long addr)
+{
+	unsigned long flags, space, pgd, prot, pa;
+#ifdef CONFIG_TLB_PTLOCK
+	unsigned long pgd_lock;
+#endif
+
+	/* Save context */
+	local_irq_save(flags);
+	prot = mfctl(8);
+	space = mfsp(SR_USER);
+	pgd = mfctl(25);
+#ifdef CONFIG_TLB_PTLOCK
+	pgd_lock = mfctl(28);
+#endif
+
+	/* Set context for lpa_user */
+	switch_mm_irqs_off(NULL, mm, NULL);
+	pa = lpa_user(addr);
+
+	/* Restore previous context */
+#ifdef CONFIG_TLB_PTLOCK
+	mtctl(pgd_lock, 28);
+#endif
+	mtctl(pgd, 25);
+	mtsp(space, SR_USER);
+	mtctl(prot, 8);
+	local_irq_restore(flags);
+
+	return pa;
+}
+
 void flush_dcache_folio(struct folio *folio)
 {
 	struct address_space *mapping = folio_flush_mapping(folio);
@@ -458,50 +518,23 @@ void flush_dcache_folio(struct folio *folio)
 		if (addr + nr * PAGE_SIZE > vma->vm_end)
 			nr = (vma->vm_end - addr) / PAGE_SIZE;
 
-		if (parisc_requires_coherency()) {
+		if (old_addr == 0 || (old_addr & (SHM_COLOUR - 1))
-			for (i = 0; i < nr; i++) {
-				pte_t *ptep = get_ptep(vma->vm_mm,
-							addr + i * PAGE_SIZE);
-				if (!ptep)
-					continue;
-				if (pte_needs_flush(*ptep))
-					flush_user_cache_page(vma,
-							addr + i * PAGE_SIZE);
-				/* Optimise accesses to the same table? */
-				pte_unmap(ptep);
-			}
-		} else {
-			/*
-			 * The TLB is the engine of coherence on parisc:
-			 * The CPU is entitled to speculate any page
-			 * with a TLB mapping, so here we kill the
-			 * mapping then flush the page along a special
-			 * flush only alias mapping. This guarantees that
-			 * the page is no-longer in the cache for any
-			 * process and nor may it be speculatively read
-			 * in (until the user or kernel specifically
-			 * accesses it, of course)
-			 */
-			for (i = 0; i < nr; i++)
-				flush_tlb_page(vma, addr + i * PAGE_SIZE);
-			if (old_addr == 0 || (old_addr & (SHM_COLOUR - 1))
 					!= (addr & (SHM_COLOUR - 1))) {
-				for (i = 0; i < nr; i++)
+			for (i = 0; i < nr; i++)
-					__flush_cache_page(vma,
+				__flush_cache_page(vma,
-						addr + i * PAGE_SIZE,
+					addr + i * PAGE_SIZE,
-						(pfn + i) * PAGE_SIZE);
+					(pfn + i) * PAGE_SIZE);
-				/*
+			/*
-				 * Software is allowed to have any number
+			 * Software is allowed to have any number
-				 * of private mappings to a page.
+			 * of private mappings to a page.
-				 */
+			 */
-				if (!(vma->vm_flags & VM_SHARED))
+			if (!(vma->vm_flags & VM_SHARED))
-					continue;
+				continue;
-				if (old_addr)
+			if (old_addr)
-					pr_err("INEQUIVALENT ALIASES 0x%lx and 0x%lx in file %pD\n",
+				pr_err("INEQUIVALENT ALIASES 0x%lx and 0x%lx in file %pD\n",
-						old_addr, addr, vma->vm_file);
+					old_addr, addr, vma->vm_file);
-				if (nr == folio_nr_pages(folio))
+			if (nr == folio_nr_pages(folio))
-					old_addr = addr;
+				old_addr = addr;
-			}
 		}
 		WARN_ON(++count == 4096);
 	}
@@ -591,35 +624,28 @@ extern void purge_kernel_dcache_page_asm(unsigned long);
 extern void clear_user_page_asm(void *, unsigned long);
 extern void copy_user_page_asm(void *, void *, unsigned long);
 
-void flush_kernel_dcache_page_addr(const void *addr)
-{
-	unsigned long flags;
-
-	flush_kernel_dcache_page_asm(addr);
-	purge_tlb_start(flags);
-	pdtlb(SR_KERNEL, addr);
-	purge_tlb_end(flags);
-}
-EXPORT_SYMBOL(flush_kernel_dcache_page_addr);
-
 static void flush_cache_page_if_present(struct vm_area_struct *vma,
-	unsigned long vmaddr, unsigned long pfn)
+	unsigned long vmaddr)
 {
+#if CONFIG_FLUSH_PAGE_ACCESSED
 	bool needs_flush = false;
-	pte_t *ptep;
+	pte_t *ptep, pte;
 
-	/*
-	 * The pte check is racy and sometimes the flush will trigger
-	 * a non-access TLB miss. Hopefully, the page has already been
-	 * flushed.
-	 */
 	ptep = get_ptep(vma->vm_mm, vmaddr);
 	if (ptep) {
-		needs_flush = pte_needs_flush(*ptep);
+		pte = ptep_get(ptep);
+		needs_flush = pte_needs_flush(pte);
 		pte_unmap(ptep);
 	}
 	if (needs_flush)
-		flush_cache_page(vma, vmaddr, pfn);
+		__flush_cache_page(vma, vmaddr, PFN_PHYS(pte_pfn(pte)));
+#else
+	struct mm_struct *mm = vma->vm_mm;
+	unsigned long physaddr = get_upa(mm, vmaddr);
+
+	if (physaddr)
+		__flush_cache_page(vma, vmaddr, PAGE_ALIGN_DOWN(physaddr));
+#endif
 }
 
 void copy_user_highpage(struct page *to, struct page *from,
@@ -629,7 +655,7 @@ void copy_user_highpage(struct page *to, struct page *from,
 
 	kfrom = kmap_local_page(from);
 	kto = kmap_local_page(to);
-	flush_cache_page_if_present(vma, vaddr, page_to_pfn(from));
+	__flush_cache_page(vma, vaddr, PFN_PHYS(page_to_pfn(from)));
 	copy_page_asm(kto, kfrom);
 	kunmap_local(kto);
 	kunmap_local(kfrom);
@@ -638,16 +664,17 @@ void copy_user_highpage(struct page *to, struct page *from,
 void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
 		unsigned long user_vaddr, void *dst, void *src, int len)
 {
-	flush_cache_page_if_present(vma, user_vaddr, page_to_pfn(page));
+	__flush_cache_page(vma, user_vaddr, PFN_PHYS(page_to_pfn(page)));
 	memcpy(dst, src, len);
-	flush_kernel_dcache_range_asm((unsigned long)dst, (unsigned long)dst + len);
+	flush_kernel_dcache_page_addr(PTR_PAGE_ALIGN_DOWN(dst));
 }
 
 void copy_from_user_page(struct vm_area_struct *vma, struct page *page,
 		unsigned long user_vaddr, void *dst, void *src, int len)
 {
-	flush_cache_page_if_present(vma, user_vaddr, page_to_pfn(page));
+	__flush_cache_page(vma, user_vaddr, PFN_PHYS(page_to_pfn(page)));
 	memcpy(dst, src, len);
+	flush_kernel_dcache_page_addr(PTR_PAGE_ALIGN_DOWN(src));
 }
 
 /* __flush_tlb_range()
@@ -681,32 +708,10 @@ int __flush_tlb_range(unsigned long sid, unsigned long start,
 
 static void flush_cache_pages(struct vm_area_struct *vma, unsigned long start, unsigned long end)
 {
-	unsigned long addr, pfn;
+	unsigned long addr;
-	pte_t *ptep;
 
-	for (addr = start; addr < end; addr += PAGE_SIZE) {
+	for (addr = start; addr < end; addr += PAGE_SIZE)
-		bool needs_flush = false;
+		flush_cache_page_if_present(vma, addr);
-		/*
-		 * The vma can contain pages that aren't present. Although
-		 * the pte search is expensive, we need the pte to find the
-		 * page pfn and to check whether the page should be flushed.
-		 */
-		ptep = get_ptep(vma->vm_mm, addr);
-		if (ptep) {
-			needs_flush = pte_needs_flush(*ptep);
-			pfn = pte_pfn(*ptep);
-			pte_unmap(ptep);
-		}
-		if (needs_flush) {
-			if (parisc_requires_coherency()) {
-				flush_user_cache_page(vma, addr);
-			} else {
-				if (WARN_ON(!pfn_valid(pfn)))
-					return;
-				__flush_cache_page(vma, addr, PFN_PHYS(pfn));
-			}
-		}
-	}
 }
 
 static inline unsigned long mm_total_size(struct mm_struct *mm)
@@ -757,21 +762,19 @@ void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned
 		if (WARN_ON(IS_ENABLED(CONFIG_SMP) && arch_irqs_disabled()))
 			return;
 		flush_tlb_range(vma, start, end);
-		flush_cache_all();
+		if (vma->vm_flags & VM_EXEC)
+			flush_cache_all();
+		else
+			flush_data_cache();
 		return;
 	}
 
-	flush_cache_pages(vma, start, end);
+	flush_cache_pages(vma, start & PAGE_MASK, end);
 }
 
 void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn)
 {
-	if (WARN_ON(!pfn_valid(pfn)))
+	__flush_cache_page(vma, vmaddr, PFN_PHYS(pfn));
-		return;
-	if (parisc_requires_coherency())
-		flush_user_cache_page(vma, vmaddr);
-	else
-		__flush_cache_page(vma, vmaddr, PFN_PHYS(pfn));
 }
 
 void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr)
@@ -779,34 +782,133 @@ void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned lon
 	if (!PageAnon(page))
 		return;
 
-	if (parisc_requires_coherency()) {
+	__flush_cache_page(vma, vmaddr, PFN_PHYS(page_to_pfn(page)));
-		if (vma->vm_flags & VM_SHARED)
+}
-			flush_data_cache();
+
-		else
+int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr,
-			flush_user_cache_page(vma, vmaddr);
+			   pte_t *ptep)
+{
+	pte_t pte = ptep_get(ptep);
+
+	if (!pte_young(pte))
+		return 0;
+	set_pte(ptep, pte_mkold(pte));
+#if CONFIG_FLUSH_PAGE_ACCESSED
+	__flush_cache_page(vma, addr, PFN_PHYS(pte_pfn(pte)));
+#endif
+	return 1;
+}
+
+/*
+ * After a PTE is cleared, we have no way to flush the cache for
+ * the physical page. On PA8800 and PA8900 processors, these lines
+ * can cause random cache corruption. Thus, we must flush the cache
+ * as well as the TLB when clearing a PTE that's valid.
+ */
+pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr,
+		       pte_t *ptep)
+{
+	struct mm_struct *mm = (vma)->vm_mm;
+	pte_t pte = ptep_get_and_clear(mm, addr, ptep);
+	unsigned long pfn = pte_pfn(pte);
+
+	if (pfn_valid(pfn))
+		__flush_cache_page(vma, addr, PFN_PHYS(pfn));
+	else if (pte_accessible(mm, pte))
+		flush_tlb_page(vma, addr);
+
+	return pte;
+}
+
+/*
+ * The physical address for pages in the ioremap case can be obtained
+ * from the vm_struct struct. I wasn't able to successfully handle the
+ * vmalloc and vmap cases. We have an array of struct page pointers in
+ * the uninitialized vmalloc case but the flush failed using page_to_pfn.
+ */
+void flush_cache_vmap(unsigned long start, unsigned long end)
+{
+	unsigned long addr, physaddr;
+	struct vm_struct *vm;
+
+	/* Prevent cache move-in */
+	flush_tlb_kernel_range(start, end);
+
+	if (end - start >= parisc_cache_flush_threshold) {
+		flush_cache_all();
 		return;
 	}
 
-	flush_tlb_page(vma, vmaddr);
+	if (WARN_ON_ONCE(!is_vmalloc_addr((void *)start))) {
-	preempt_disable();
+		flush_cache_all();
-	flush_dcache_page_asm(page_to_phys(page), vmaddr);
+		return;
-	preempt_enable();
+	}
-}
 
+	vm = find_vm_area((void *)start);
+	if (WARN_ON_ONCE(!vm)) {
+		flush_cache_all();
+		return;
+	}
+
+	/* The physical addresses of IOREMAP regions are contiguous */
+	if (vm->flags & VM_IOREMAP) {
+		physaddr = vm->phys_addr;
+		for (addr = start; addr < end; addr += PAGE_SIZE) {
+			preempt_disable();
+			flush_dcache_page_asm(physaddr, start);
+			flush_icache_page_asm(physaddr, start);
+			preempt_enable();
+			physaddr += PAGE_SIZE;
+		}
+		return;
+	}
+
+	flush_cache_all();
+}
+EXPORT_SYMBOL(flush_cache_vmap);
+
+/*
+ * The vm_struct has been retired and the page table is set up. The
+ * last page in the range is a guard page. Its physical address can't
+ * be determined using lpa, so there is no way to flush the range
+ * using flush_dcache_page_asm.
+ */
+void flush_cache_vunmap(unsigned long start, unsigned long end)
+{
+	/* Prevent cache move-in */
+	flush_tlb_kernel_range(start, end);
+	flush_data_cache();
+}
+EXPORT_SYMBOL(flush_cache_vunmap);
+
+/*
+ * On systems with PA8800/PA8900 processors, there is no way to flush
+ * a vmap range other than using the architected loop to flush the
+ * entire cache. The page directory is not set up, so we can't use
+ * fdc, etc. FDCE/FICE don't work to flush a portion of the cache.
+ * L2 is physically indexed but FDCE/FICE instructions in virtual
+ * mode output their virtual address on the core bus, not their
+ * real address. As a result, the L2 cache index formed from the
+ * virtual address will most likely not be the same as the L2 index
+ * formed from the real address.
+ */
 void flush_kernel_vmap_range(void *vaddr, int size)
 {
 	unsigned long start = (unsigned long)vaddr;
 	unsigned long end = start + size;
 
-	if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
+	flush_tlb_kernel_range(start, end);
-	    (unsigned long)size >= parisc_cache_flush_threshold) {
+
-		flush_tlb_kernel_range(start, end);
+	if (!static_branch_likely(&parisc_has_dcache))
-		flush_data_cache();
+		return;
+
+	/* If interrupts are disabled, we can only do local flush */
+	if (WARN_ON(IS_ENABLED(CONFIG_SMP) && arch_irqs_disabled())) {
+		flush_data_cache_local(NULL);
 		return;
 	}
 
-	flush_kernel_dcache_range_asm(start, end);
+	flush_data_cache();
-	flush_tlb_kernel_range(start, end);
 }
 EXPORT_SYMBOL(flush_kernel_vmap_range);
 
@@ -818,15 +920,18 @@ void invalidate_kernel_vmap_range(void *vaddr, int size)
 	/* Ensure DMA is complete */
 	asm_syncdma();
 
-	if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
+	flush_tlb_kernel_range(start, end);
-	    (unsigned long)size >= parisc_cache_flush_threshold) {
+
-		flush_tlb_kernel_range(start, end);
+	if (!static_branch_likely(&parisc_has_dcache))
-		flush_data_cache();
+		return;
+
+	/* If interrupts are disabled, we can only do local flush */
+	if (WARN_ON(IS_ENABLED(CONFIG_SMP) && arch_irqs_disabled())) {
+		flush_data_cache_local(NULL);
 		return;
 	}
 
-	purge_kernel_dcache_range_asm(start, end);
+	flush_data_cache();
-	flush_tlb_kernel_range(start, end);
 }
 EXPORT_SYMBOL(invalidate_kernel_vmap_range);
 

arch/parisc/kernel/sys_parisc32.c

@@ -23,12 +23,3 @@ asmlinkage long sys32_unimplemented(int r26, int r25, int r24, int r23,
     	current->comm, current->pid, r20);
     return -ENOSYS;
 }
-
-asmlinkage long sys32_fanotify_mark(compat_int_t fanotify_fd, compat_uint_t flags,
-	compat_uint_t mask0, compat_uint_t mask1, compat_int_t dfd,
-	const char  __user * pathname)
-{
-	return sys_fanotify_mark(fanotify_fd, flags,
-			((__u64)mask1 << 32) | mask0,
-			 dfd, pathname);
-}

arch/parisc/kernel/syscalls/syscall.tbl

@@ -108,7 +108,7 @@
 95	common	fchown			sys_fchown
 96	common	getpriority		sys_getpriority
 97	common	setpriority		sys_setpriority
-98	common	recv			sys_recv
+98	common	recv			sys_recv			compat_sys_recv
 99	common	statfs			sys_statfs			compat_sys_statfs
 100	common	fstatfs			sys_fstatfs			compat_sys_fstatfs
 101	common	stat64			sys_stat64
@@ -135,7 +135,7 @@
 120	common	clone			sys_clone_wrapper
 121	common	setdomainname		sys_setdomainname
 122	common	sendfile		sys_sendfile			compat_sys_sendfile
-123	common	recvfrom		sys_recvfrom
+123	common	recvfrom		sys_recvfrom			compat_sys_recvfrom
 124	32	adjtimex		sys_adjtimex_time32
 124	64	adjtimex		sys_adjtimex
 125	common	mprotect		sys_mprotect
@@ -364,7 +364,7 @@
 320	common	accept4			sys_accept4
 321	common	prlimit64		sys_prlimit64
 322	common	fanotify_init		sys_fanotify_init
-323	common	fanotify_mark		sys_fanotify_mark		sys32_fanotify_mark
+323	common	fanotify_mark		sys_fanotify_mark		compat_sys_fanotify_mark
 324	32	clock_adjtime		sys_clock_adjtime32
 324	64	clock_adjtime		sys_clock_adjtime
 325	common	name_to_handle_at	sys_name_to_handle_at

arch/powerpc/crypto/.gitignore

@@ -1,3 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
 aesp10-ppc.S
+aesp8-ppc.S
 ghashp10-ppc.S
+ghashp8-ppc.S

arch/powerpc/kernel/syscalls/syscall.tbl

@@ -230,8 +230,10 @@
 178	nospu 	rt_sigsuspend			sys_rt_sigsuspend		compat_sys_rt_sigsuspend
 179	32	pread64				sys_ppc_pread64			compat_sys_ppc_pread64
 179	64	pread64				sys_pread64
+179	spu	pread64				sys_pread64
 180	32	pwrite64			sys_ppc_pwrite64		compat_sys_ppc_pwrite64
 180	64	pwrite64			sys_pwrite64
+180	spu	pwrite64			sys_pwrite64
 181	common	chown				sys_chown
 182	common	getcwd				sys_getcwd
 183	common	capget				sys_capget
@@ -246,6 +248,7 @@
 190	common	ugetrlimit			sys_getrlimit			compat_sys_getrlimit
 191	32	readahead			sys_ppc_readahead		compat_sys_ppc_readahead
 191	64	readahead			sys_readahead
+191	spu	readahead			sys_readahead
 192	32	mmap2				sys_mmap2			compat_sys_mmap2
 193	32	truncate64			sys_ppc_truncate64		compat_sys_ppc_truncate64
 194	32	ftruncate64			sys_ppc_ftruncate64		compat_sys_ppc_ftruncate64
@@ -293,6 +296,7 @@
 232	nospu	set_tid_address			sys_set_tid_address
 233	32	fadvise64			sys_ppc32_fadvise64		compat_sys_ppc32_fadvise64
 233	64	fadvise64			sys_fadvise64
+233	spu	fadvise64			sys_fadvise64
 234	nospu	exit_group			sys_exit_group
 235	nospu	lookup_dcookie			sys_ni_syscall
 236	common	epoll_create			sys_epoll_create
@@ -502,7 +506,7 @@
 412	32	utimensat_time64		sys_utimensat			sys_utimensat
 413	32	pselect6_time64			sys_pselect6			compat_sys_pselect6_time64
 414	32	ppoll_time64			sys_ppoll			compat_sys_ppoll_time64
-416	32	io_pgetevents_time64		sys_io_pgetevents		sys_io_pgetevents
+416	32	io_pgetevents_time64		sys_io_pgetevents		compat_sys_io_pgetevents_time64
 417	32	recvmmsg_time64			sys_recvmmsg			compat_sys_recvmmsg_time64
 418	32	mq_timedsend_time64		sys_mq_timedsend		sys_mq_timedsend
 419	32	mq_timedreceive_time64		sys_mq_timedreceive		sys_mq_timedreceive

arch/powerpc/kvm/book3s_64_vio.c

@@ -130,14 +130,16 @@ long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
 	}
 	rcu_read_unlock();
 
-	fdput(f);
+	if (!found) {
-
+		fdput(f);
-	if (!found)
 		return -EINVAL;
+	}
 
 	table_group = iommu_group_get_iommudata(grp);
-	if (WARN_ON(!table_group))
+	if (WARN_ON(!table_group)) {
+		fdput(f);
 		return -EFAULT;
+	}
 
 	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
 		struct iommu_table *tbltmp = table_group->tables[i];
@@ -158,8 +160,10 @@ long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
 			break;
 		}
 	}
-	if (!tbl)
+	if (!tbl) {
+		fdput(f);
 		return -EINVAL;
+	}
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(stit, &stt->iommu_tables, next) {
@@ -170,6 +174,7 @@ long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
 			/* stit is being destroyed */
 			iommu_tce_table_put(tbl);
 			rcu_read_unlock();
+			fdput(f);
 			return -ENOTTY;
 		}
 		/*
@@ -177,6 +182,7 @@ long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
 		 * its KVM reference counter and can return.
 		 */
 		rcu_read_unlock();
+		fdput(f);
 		return 0;
 	}
 	rcu_read_unlock();
@@ -184,6 +190,7 @@ long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
 	stit = kzalloc(sizeof(*stit), GFP_KERNEL);
 	if (!stit) {
 		iommu_tce_table_put(tbl);
+		fdput(f);
 		return -ENOMEM;
 	}
 
@@ -192,6 +199,7 @@ long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd,
 
 	list_add_rcu(&stit->next, &stt->iommu_tables);
 
+	fdput(f);
 	return 0;
 }
 

arch/riscv/boot/dts/sophgo/cv1800b-milkv-duo.dts

@@ -45,6 +45,7 @@
 	no-1-8-v;
 	no-mmc;
 	no-sdio;
+	disable-wp;
 };
 
 &uart0 {

arch/riscv/include/asm/insn.h

@@ -145,7 +145,7 @@
 
 /* parts of opcode for RVF, RVD and RVQ */
 #define RVFDQ_FL_FS_WIDTH_OFF	12
-#define RVFDQ_FL_FS_WIDTH_MASK	GENMASK(3, 0)
+#define RVFDQ_FL_FS_WIDTH_MASK	GENMASK(2, 0)
 #define RVFDQ_FL_FS_WIDTH_W	2
 #define RVFDQ_FL_FS_WIDTH_D	3
 #define RVFDQ_LS_FS_WIDTH_Q	4

arch/riscv/kernel/ftrace.c

@@ -120,9 +120,6 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
 	out = ftrace_make_nop(mod, rec, MCOUNT_ADDR);
 	mutex_unlock(&text_mutex);
 
-	if (!mod)
-		local_flush_icache_range(rec->ip, rec->ip + MCOUNT_INSN_SIZE);
-
 	return out;
 }
 
@@ -156,9 +153,9 @@ static int __ftrace_modify_code(void *data)
 	} else {
 		while (atomic_read(&param->cpu_count) <= num_online_cpus())
 			cpu_relax();
-	}
 
-	local_flush_icache_all();
+		local_flush_icache_all();
+	}
 
 	return 0;
 }

arch/riscv/kernel/patch.c

@@ -89,6 +89,14 @@ static int __patch_insn_set(void *addr, u8 c, size_t len)
 
 	memset(waddr, c, len);
 
+	/*
+	 * We could have just patched a function that is about to be
+	 * called so make sure we don't execute partially patched
+	 * instructions by flushing the icache as soon as possible.
+	 */
+	local_flush_icache_range((unsigned long)waddr,
+				 (unsigned long)waddr + len);
+
 	patch_unmap(FIX_TEXT_POKE0);
 
 	if (across_pages)
@@ -135,6 +143,14 @@ static int __patch_insn_write(void *addr, const void *insn, size_t len)
 
 	ret = copy_to_kernel_nofault(waddr, insn, len);
 
+	/*
+	 * We could have just patched a function that is about to be
+	 * called so make sure we don't execute partially patched
+	 * instructions by flushing the icache as soon as possible.
+	 */
+	local_flush_icache_range((unsigned long)waddr,
+				 (unsigned long)waddr + len);
+
 	patch_unmap(FIX_TEXT_POKE0);
 
 	if (across_pages)
@@ -189,9 +205,6 @@ int patch_text_set_nosync(void *addr, u8 c, size_t len)
 
 	ret = patch_insn_set(tp, c, len);
 
-	if (!ret)
-		flush_icache_range((uintptr_t)tp, (uintptr_t)tp + len);
-
 	return ret;
 }
 NOKPROBE_SYMBOL(patch_text_set_nosync);
@@ -224,9 +237,6 @@ int patch_text_nosync(void *addr, const void *insns, size_t len)
 
 	ret = patch_insn_write(tp, insns, len);
 
-	if (!ret)
-		flush_icache_range((uintptr_t) tp, (uintptr_t) tp + len);
-
 	return ret;
 }
 NOKPROBE_SYMBOL(patch_text_nosync);
@@ -253,9 +263,9 @@ static int patch_text_cb(void *data)
 	} else {
 		while (atomic_read(&patch->cpu_count) <= num_online_cpus())
 			cpu_relax();
-	}
 
-	local_flush_icache_all();
+		local_flush_icache_all();
+	}
 
 	return ret;
 }

arch/riscv/kernel/stacktrace.c

@@ -156,7 +156,7 @@ unsigned long __get_wchan(struct task_struct *task)
 	return pc;
 }
 
-noinline void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
+noinline noinstr void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
 		     struct task_struct *task, struct pt_regs *regs)
 {
 	walk_stackframe(task, regs, consume_entry, cookie);

arch/riscv/kernel/sys_riscv.c

@@ -23,7 +23,7 @@ static long riscv_sys_mmap(unsigned long addr, unsigned long len,
 #ifdef CONFIG_64BIT
 SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
 	unsigned long, prot, unsigned long, flags,
-	unsigned long, fd, off_t, offset)
+	unsigned long, fd, unsigned long, offset)
 {
 	return riscv_sys_mmap(addr, len, prot, flags, fd, offset, 0);
 }
@@ -32,7 +32,7 @@ SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
 #if defined(CONFIG_32BIT) || defined(CONFIG_COMPAT)
 SYSCALL_DEFINE6(mmap2, unsigned long, addr, unsigned long, len,
 	unsigned long, prot, unsigned long, flags,
-	unsigned long, fd, off_t, offset)
+	unsigned long, fd, unsigned long, offset)
 {
 	/*
 	 * Note that the shift for mmap2 is constant (12),

arch/s390/boot/startup.c

@@ -170,11 +170,14 @@ static void kaslr_adjust_got(unsigned long offset)
 	u64 *entry;
 
 	/*
-	 * Even without -fPIE, Clang still uses a global offset table for some
+	 * Adjust GOT entries, except for ones for undefined weak symbols
-	 * reason. Adjust the GOT entries.
+	 * that resolved to zero. This also skips the first three reserved
+	 * entries on s390x that are zero.
 	 */
-	for (entry = (u64 *)vmlinux.got_start; entry < (u64 *)vmlinux.got_end; entry++)
+	for (entry = (u64 *)vmlinux.got_start; entry < (u64 *)vmlinux.got_end; entry++) {
-		*entry += offset - __START_KERNEL;
+		if (*entry)
+			*entry += offset - __START_KERNEL;
+	}
 }
 
 /*
@@ -384,7 +387,7 @@ static void fixup_vmlinux_info(void)
 void startup_kernel(void)
 {
 	unsigned long kernel_size = vmlinux.image_size + vmlinux.bss_size;
-	unsigned long nokaslr_offset_phys = mem_safe_offset();
+	unsigned long nokaslr_offset_phys, kaslr_large_page_offset;
 	unsigned long amode31_lma = 0;
 	unsigned long max_physmem_end;
 	unsigned long asce_limit;
@@ -393,6 +396,12 @@ void startup_kernel(void)
 
 	fixup_vmlinux_info();
 	setup_lpp();
+
+	/*
+	 * Non-randomized kernel physical start address must be _SEGMENT_SIZE
+	 * aligned (see blow).
+	 */
+	nokaslr_offset_phys = ALIGN(mem_safe_offset(), _SEGMENT_SIZE);
 	safe_addr = PAGE_ALIGN(nokaslr_offset_phys + kernel_size);
 
 	/*
@@ -425,10 +434,25 @@ void startup_kernel(void)
 	save_ipl_cert_comp_list();
 	rescue_initrd(safe_addr, ident_map_size);
 
-	if (kaslr_enabled())
+	/*
-		__kaslr_offset_phys = randomize_within_range(kernel_size, THREAD_SIZE, 0, ident_map_size);
+	 * __kaslr_offset_phys must be _SEGMENT_SIZE aligned, so the lower
+	 * 20 bits (the offset within a large page) are zero. Copy the last
+	 * 20 bits of __kaslr_offset, which is THREAD_SIZE aligned, to
+	 * __kaslr_offset_phys.
+	 *
+	 * With this the last 20 bits of __kaslr_offset_phys and __kaslr_offset
+	 * are identical, which is required to allow for large mappings of the
+	 * kernel image.
+	 */
+	kaslr_large_page_offset = __kaslr_offset & ~_SEGMENT_MASK;
+	if (kaslr_enabled()) {
+		unsigned long end = ident_map_size - kaslr_large_page_offset;
+
+		__kaslr_offset_phys = randomize_within_range(kernel_size, _SEGMENT_SIZE, 0, end);
+	}
 	if (!__kaslr_offset_phys)
 		__kaslr_offset_phys = nokaslr_offset_phys;
+	__kaslr_offset_phys |= kaslr_large_page_offset;
 	kaslr_adjust_vmlinux_info(__kaslr_offset_phys);
 	physmem_reserve(RR_VMLINUX, __kaslr_offset_phys, kernel_size);
 	deploy_kernel((void *)__kaslr_offset_phys);

arch/s390/boot/vmem.c

@@ -261,21 +261,27 @@ static unsigned long _pa(unsigned long addr, unsigned long size, enum populate_m
 
 static bool large_allowed(enum populate_mode mode)
 {
-	return (mode == POPULATE_DIRECT) || (mode == POPULATE_IDENTITY);
+	return (mode == POPULATE_DIRECT) || (mode == POPULATE_IDENTITY) || (mode == POPULATE_KERNEL);
 }
 
 static bool can_large_pud(pud_t *pu_dir, unsigned long addr, unsigned long end,
 			  enum populate_mode mode)
 {
+	unsigned long size = end - addr;
+
 	return machine.has_edat2 && large_allowed(mode) &&
-	       IS_ALIGNED(addr, PUD_SIZE) && (end - addr) >= PUD_SIZE;
+	       IS_ALIGNED(addr, PUD_SIZE) && (size >= PUD_SIZE) &&
+	       IS_ALIGNED(_pa(addr, size, mode), PUD_SIZE);
 }
 
 static bool can_large_pmd(pmd_t *pm_dir, unsigned long addr, unsigned long end,
 			  enum populate_mode mode)
 {
+	unsigned long size = end - addr;
+
 	return machine.has_edat1 && large_allowed(mode) &&
-	       IS_ALIGNED(addr, PMD_SIZE) && (end - addr) >= PMD_SIZE;
+	       IS_ALIGNED(addr, PMD_SIZE) && (size >= PMD_SIZE) &&
+	       IS_ALIGNED(_pa(addr, size, mode), PMD_SIZE);
 }
 
 static void pgtable_pte_populate(pmd_t *pmd, unsigned long addr, unsigned long end,

arch/s390/boot/vmlinux.lds.S

@@ -109,6 +109,7 @@ SECTIONS
 #ifdef CONFIG_KERNEL_UNCOMPRESSED
 	. = ALIGN(PAGE_SIZE);
 	. += AMODE31_SIZE;		/* .amode31 section */
+	. = ALIGN(1 << 20);		/* _SEGMENT_SIZE */
 #else
 	. = ALIGN(8);
 #endif

arch/s390/configs/debug_defconfig

@@ -43,7 +43,6 @@ CONFIG_PROFILING=y
 CONFIG_KEXEC=y
 CONFIG_KEXEC_FILE=y
 CONFIG_KEXEC_SIG=y
-CONFIG_CRASH_DUMP=y
 CONFIG_LIVEPATCH=y
 CONFIG_MARCH_Z13=y
 CONFIG_NR_CPUS=512
@@ -51,6 +50,7 @@ CONFIG_NUMA=y
 CONFIG_HZ_100=y
 CONFIG_CERT_STORE=y
 CONFIG_EXPOLINE=y
+# CONFIG_EXPOLINE_EXTERN is not set
 CONFIG_EXPOLINE_AUTO=y
 CONFIG_CHSC_SCH=y
 CONFIG_VFIO_CCW=m
@@ -76,6 +76,7 @@ CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_MODULE_UNLOAD_TAINT_TRACKING=y
 CONFIG_MODVERSIONS=y
 CONFIG_MODULE_SRCVERSION_ALL=y
+CONFIG_MODULE_SIG_SHA256=y
 CONFIG_BLK_DEV_THROTTLING=y
 CONFIG_BLK_WBT=y
 CONFIG_BLK_CGROUP_IOLATENCY=y
@@ -100,7 +101,6 @@ CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
 CONFIG_KSM=y
 CONFIG_TRANSPARENT_HUGEPAGE=y
-CONFIG_CMA_DEBUG=y
 CONFIG_CMA_DEBUGFS=y
 CONFIG_CMA_SYSFS=y
 CONFIG_CMA_AREAS=7
@@ -119,6 +119,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_XFRM_USER=m
 CONFIG_NET_KEY=m
 CONFIG_SMC_DIAG=m
+CONFIG_SMC_LO=y
 CONFIG_INET=y
 CONFIG_IP_MULTICAST=y
 CONFIG_IP_ADVANCED_ROUTER=y
@@ -133,7 +134,6 @@ CONFIG_IP_MROUTE=y
 CONFIG_IP_MROUTE_MULTIPLE_TABLES=y
 CONFIG_IP_PIMSM_V1=y
 CONFIG_IP_PIMSM_V2=y
-CONFIG_SYN_COOKIES=y
 CONFIG_NET_IPVTI=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
@@ -167,6 +167,7 @@ CONFIG_BRIDGE_NETFILTER=m
 CONFIG_NETFILTER_NETLINK_HOOK=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_SECMARK=y
+CONFIG_NF_CONNTRACK_ZONES=y
 CONFIG_NF_CONNTRACK_PROCFS=y
 CONFIG_NF_CONNTRACK_EVENTS=y
 CONFIG_NF_CONNTRACK_TIMEOUT=y
@@ -183,17 +184,39 @@ CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_CT_NETLINK=m
 CONFIG_NF_CT_NETLINK_TIMEOUT=m
+CONFIG_NF_CT_NETLINK_HELPER=m
+CONFIG_NETFILTER_NETLINK_GLUE_CT=y
 CONFIG_NF_TABLES=m
 CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
+CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
+CONFIG_NFT_FLOW_OFFLOAD=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
+CONFIG_NFT_MASQ=m
+CONFIG_NFT_REDIR=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_TUNNEL=m
+CONFIG_NFT_QUEUE=m
+CONFIG_NFT_QUOTA=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
-CONFIG_NETFILTER_XTABLES_COMPAT=y
+CONFIG_NFT_XFRM=m
+CONFIG_NFT_SOCKET=m
+CONFIG_NFT_OSF=m
+CONFIG_NFT_TPROXY=m
+CONFIG_NFT_SYNPROXY=m
+CONFIG_NFT_DUP_NETDEV=m
+CONFIG_NFT_FWD_NETDEV=m
+CONFIG_NFT_FIB_NETDEV=m
+CONFIG_NFT_REJECT_NETDEV=m
+CONFIG_NF_FLOW_TABLE_INET=m
+CONFIG_NF_FLOW_TABLE=m
+CONFIG_NF_FLOW_TABLE_PROCFS=y
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_AUDIT=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -206,8 +229,10 @@ CONFIG_NETFILTER_XT_TARGET_HMARK=m
 CONFIG_NETFILTER_XT_TARGET_IDLETIMER=m
 CONFIG_NETFILTER_XT_TARGET_LOG=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
+CONFIG_NETFILTER_XT_TARGET_NETMAP=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
+CONFIG_NETFILTER_XT_TARGET_REDIRECT=m
 CONFIG_NETFILTER_XT_TARGET_TEE=m
 CONFIG_NETFILTER_XT_TARGET_TPROXY=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
@@ -216,6 +241,7 @@ CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
 CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=m
 CONFIG_NETFILTER_XT_MATCH_BPF=m
+CONFIG_NETFILTER_XT_MATCH_CGROUP=m
 CONFIG_NETFILTER_XT_MATCH_CLUSTER=m
 CONFIG_NETFILTER_XT_MATCH_COMMENT=m
 CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m
@@ -230,6 +256,7 @@ CONFIG_NETFILTER_XT_MATCH_DSCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPCOMP=m
 CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_IPVS=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
@@ -247,6 +274,7 @@ CONFIG_NETFILTER_XT_MATCH_QUOTA=m
 CONFIG_NETFILTER_XT_MATCH_RATEEST=m
 CONFIG_NETFILTER_XT_MATCH_REALM=m
 CONFIG_NETFILTER_XT_MATCH_RECENT=m
+CONFIG_NETFILTER_XT_MATCH_SOCKET=m
 CONFIG_NETFILTER_XT_MATCH_STATE=m
 CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
 CONFIG_NETFILTER_XT_MATCH_STRING=m
@@ -302,7 +330,6 @@ CONFIG_IP_NF_TARGET_ECN=m
 CONFIG_IP_NF_TARGET_TTL=m
 CONFIG_IP_NF_RAW=m
 CONFIG_IP_NF_SECURITY=m
-CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NFT_FIB_IPV6=m
@@ -373,7 +400,6 @@ CONFIG_NET_ACT_POLICE=m
 CONFIG_NET_ACT_GACT=m
 CONFIG_GACT_PROB=y
 CONFIG_NET_ACT_MIRRED=m
-CONFIG_NET_ACT_IPT=m
 CONFIG_NET_ACT_NAT=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
@@ -462,6 +488,7 @@ CONFIG_DM_VERITY=m
 CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG=y
 CONFIG_DM_SWITCH=m
 CONFIG_DM_INTEGRITY=m
+CONFIG_DM_VDO=m
 CONFIG_NETDEVICES=y
 CONFIG_BONDING=m
 CONFIG_DUMMY=m
@@ -574,7 +601,6 @@ CONFIG_WATCHDOG=y
 CONFIG_WATCHDOG_NOWAYOUT=y
 CONFIG_SOFT_WATCHDOG=m
 CONFIG_DIAG288_WATCHDOG=m
-# CONFIG_DRM_DEBUG_MODESET_LOCK is not set
 CONFIG_FB=y
 # CONFIG_FB_DEVICE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
@@ -645,7 +671,6 @@ CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
 CONFIG_EXFAT_FS=m
 CONFIG_NTFS_FS=m
-CONFIG_NTFS_RW=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
@@ -663,6 +688,7 @@ CONFIG_SQUASHFS_XZ=y
 CONFIG_SQUASHFS_ZSTD=y
 CONFIG_ROMFS_FS=m
 CONFIG_NFS_FS=m
+CONFIG_NFS_V2=m
 CONFIG_NFS_V3_ACL=y
 CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y
@@ -879,6 +905,5 @@ CONFIG_RBTREE_TEST=y
 CONFIG_INTERVAL_TREE_TEST=m
 CONFIG_PERCPU_TEST=m
 CONFIG_ATOMIC64_SELFTEST=y
-CONFIG_STRING_SELFTEST=y
 CONFIG_TEST_BITOPS=m
 CONFIG_TEST_BPF=m

arch/s390/configs/defconfig

@@ -41,7 +41,6 @@ CONFIG_PROFILING=y
 CONFIG_KEXEC=y
 CONFIG_KEXEC_FILE=y
 CONFIG_KEXEC_SIG=y
-CONFIG_CRASH_DUMP=y
 CONFIG_LIVEPATCH=y
 CONFIG_MARCH_Z13=y
 CONFIG_NR_CPUS=512
@@ -49,6 +48,7 @@ CONFIG_NUMA=y
 CONFIG_HZ_100=y
 CONFIG_CERT_STORE=y
 CONFIG_EXPOLINE=y
+# CONFIG_EXPOLINE_EXTERN is not set
 CONFIG_EXPOLINE_AUTO=y
 CONFIG_CHSC_SCH=y
 CONFIG_VFIO_CCW=m
@@ -71,6 +71,7 @@ CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_MODULE_UNLOAD_TAINT_TRACKING=y
 CONFIG_MODVERSIONS=y
 CONFIG_MODULE_SRCVERSION_ALL=y
+CONFIG_MODULE_SIG_SHA256=y
 CONFIG_BLK_DEV_THROTTLING=y
 CONFIG_BLK_WBT=y
 CONFIG_BLK_CGROUP_IOLATENCY=y
@@ -110,6 +111,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_XFRM_USER=m
 CONFIG_NET_KEY=m
 CONFIG_SMC_DIAG=m
+CONFIG_SMC_LO=y
 CONFIG_INET=y
 CONFIG_IP_MULTICAST=y
 CONFIG_IP_ADVANCED_ROUTER=y
@@ -124,7 +126,6 @@ CONFIG_IP_MROUTE=y
 CONFIG_IP_MROUTE_MULTIPLE_TABLES=y
 CONFIG_IP_PIMSM_V1=y
 CONFIG_IP_PIMSM_V2=y
-CONFIG_SYN_COOKIES=y
 CONFIG_NET_IPVTI=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
@@ -158,6 +159,7 @@ CONFIG_BRIDGE_NETFILTER=m
 CONFIG_NETFILTER_NETLINK_HOOK=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_SECMARK=y
+CONFIG_NF_CONNTRACK_ZONES=y
 CONFIG_NF_CONNTRACK_PROCFS=y
 CONFIG_NF_CONNTRACK_EVENTS=y
 CONFIG_NF_CONNTRACK_TIMEOUT=y
@@ -174,17 +176,39 @@ CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_CT_NETLINK=m
 CONFIG_NF_CT_NETLINK_TIMEOUT=m
+CONFIG_NF_CT_NETLINK_HELPER=m
+CONFIG_NETFILTER_NETLINK_GLUE_CT=y
 CONFIG_NF_TABLES=m
 CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
+CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
+CONFIG_NFT_FLOW_OFFLOAD=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
+CONFIG_NFT_MASQ=m
+CONFIG_NFT_REDIR=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_TUNNEL=m
+CONFIG_NFT_QUEUE=m
+CONFIG_NFT_QUOTA=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
-CONFIG_NETFILTER_XTABLES_COMPAT=y
+CONFIG_NFT_XFRM=m
+CONFIG_NFT_SOCKET=m
+CONFIG_NFT_OSF=m
+CONFIG_NFT_TPROXY=m
+CONFIG_NFT_SYNPROXY=m
+CONFIG_NFT_DUP_NETDEV=m
+CONFIG_NFT_FWD_NETDEV=m
+CONFIG_NFT_FIB_NETDEV=m
+CONFIG_NFT_REJECT_NETDEV=m
+CONFIG_NF_FLOW_TABLE_INET=m
+CONFIG_NF_FLOW_TABLE=m
+CONFIG_NF_FLOW_TABLE_PROCFS=y
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_AUDIT=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -197,8 +221,10 @@ CONFIG_NETFILTER_XT_TARGET_HMARK=m
 CONFIG_NETFILTER_XT_TARGET_IDLETIMER=m
 CONFIG_NETFILTER_XT_TARGET_LOG=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
+CONFIG_NETFILTER_XT_TARGET_NETMAP=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
+CONFIG_NETFILTER_XT_TARGET_REDIRECT=m
 CONFIG_NETFILTER_XT_TARGET_TEE=m
 CONFIG_NETFILTER_XT_TARGET_TPROXY=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
@@ -207,6 +233,7 @@ CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
 CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=m
 CONFIG_NETFILTER_XT_MATCH_BPF=m
+CONFIG_NETFILTER_XT_MATCH_CGROUP=m
 CONFIG_NETFILTER_XT_MATCH_CLUSTER=m
 CONFIG_NETFILTER_XT_MATCH_COMMENT=m
 CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m
@@ -221,6 +248,7 @@ CONFIG_NETFILTER_XT_MATCH_DSCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPCOMP=m
 CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_IPVS=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
@@ -238,6 +266,7 @@ CONFIG_NETFILTER_XT_MATCH_QUOTA=m
 CONFIG_NETFILTER_XT_MATCH_RATEEST=m
 CONFIG_NETFILTER_XT_MATCH_REALM=m
 CONFIG_NETFILTER_XT_MATCH_RECENT=m
+CONFIG_NETFILTER_XT_MATCH_SOCKET=m
 CONFIG_NETFILTER_XT_MATCH_STATE=m
 CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
 CONFIG_NETFILTER_XT_MATCH_STRING=m
@@ -293,7 +322,6 @@ CONFIG_IP_NF_TARGET_ECN=m
 CONFIG_IP_NF_TARGET_TTL=m
 CONFIG_IP_NF_RAW=m
 CONFIG_IP_NF_SECURITY=m
-CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NFT_FIB_IPV6=m
@@ -363,7 +391,6 @@ CONFIG_NET_ACT_POLICE=m
 CONFIG_NET_ACT_GACT=m
 CONFIG_GACT_PROB=y
 CONFIG_NET_ACT_MIRRED=m
-CONFIG_NET_ACT_IPT=m
 CONFIG_NET_ACT_NAT=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
@@ -452,6 +479,7 @@ CONFIG_DM_VERITY=m
 CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG=y
 CONFIG_DM_SWITCH=m
 CONFIG_DM_INTEGRITY=m
+CONFIG_DM_VDO=m
 CONFIG_NETDEVICES=y
 CONFIG_BONDING=m
 CONFIG_DUMMY=m
@@ -630,7 +658,6 @@ CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
 CONFIG_EXFAT_FS=m
 CONFIG_NTFS_FS=m
-CONFIG_NTFS_RW=y
 CONFIG_PROC_KCORE=y
 CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
@@ -649,6 +676,7 @@ CONFIG_SQUASHFS_XZ=y
 CONFIG_SQUASHFS_ZSTD=y
 CONFIG_ROMFS_FS=m
 CONFIG_NFS_FS=m
+CONFIG_NFS_V2=m
 CONFIG_NFS_V3_ACL=y
 CONFIG_NFS_V4=m
 CONFIG_NFS_SWAP=y

arch/s390/configs/zfcpdump_defconfig

@@ -9,25 +9,22 @@ CONFIG_BPF_SYSCALL=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_KEXEC=y
-CONFIG_CRASH_DUMP=y
 CONFIG_MARCH_Z13=y
 CONFIG_NR_CPUS=2
 CONFIG_HZ_100=y
 # CONFIG_CHSC_SCH is not set
 # CONFIG_SCM_BUS is not set
+# CONFIG_AP is not set
 # CONFIG_PFAULT is not set
 # CONFIG_S390_HYPFS is not set
 # CONFIG_VIRTUALIZATION is not set
 # CONFIG_S390_GUEST is not set
 # CONFIG_SECCOMP is not set
-# CONFIG_GCC_PLUGINS is not set
 # CONFIG_BLOCK_LEGACY_AUTOLOAD is not set
 CONFIG_PARTITION_ADVANCED=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 # CONFIG_SWAP is not set
 # CONFIG_COMPAT_BRK is not set
-# CONFIG_COMPACTION is not set
-# CONFIG_MIGRATION is not set
 CONFIG_NET=y
 # CONFIG_IUCV is not set
 # CONFIG_PCPU_DEV_REFCNT is not set

arch/s390/include/asm/entry-common.h

@@ -54,7 +54,7 @@ static __always_inline void arch_exit_to_user_mode(void)
 static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
 						  unsigned long ti_work)
 {
-	choose_random_kstack_offset(get_tod_clock_fast() & 0xff);
+	choose_random_kstack_offset(get_tod_clock_fast());
 }
 
 #define arch_exit_to_user_mode_prepare arch_exit_to_user_mode_prepare

arch/s390/kernel/syscall.c

@@ -38,33 +38,6 @@
 
 #include "entry.h"
 
-/*
- * Perform the mmap() system call. Linux for S/390 isn't able to handle more
- * than 5 system call parameters, so this system call uses a memory block
- * for parameter passing.
- */
-
-struct s390_mmap_arg_struct {
-	unsigned long addr;
-	unsigned long len;
-	unsigned long prot;
-	unsigned long flags;
-	unsigned long fd;
-	unsigned long offset;
-};
-
-SYSCALL_DEFINE1(mmap2, struct s390_mmap_arg_struct __user *, arg)
-{
-	struct s390_mmap_arg_struct a;
-	int error = -EFAULT;
-
-	if (copy_from_user(&a, arg, sizeof(a)))
-		goto out;
-	error = ksys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset);
-out:
-	return error;
-}
-
 #ifdef CONFIG_SYSVIPC
 /*
  * sys_ipc() is the de-multiplexer for the SysV IPC calls.

arch/s390/kernel/syscalls/syscall.tbl

@@ -418,7 +418,7 @@
 412	32	utimensat_time64	-				sys_utimensat
 413	32	pselect6_time64		-				compat_sys_pselect6_time64
 414	32	ppoll_time64		-				compat_sys_ppoll_time64
-416	32	io_pgetevents_time64	-				sys_io_pgetevents
+416	32	io_pgetevents_time64	-				compat_sys_io_pgetevents_time64
 417	32	recvmmsg_time64		-				compat_sys_recvmmsg_time64
 418	32	mq_timedsend_time64	-				sys_mq_timedsend
 419	32	mq_timedreceive_time64	-				sys_mq_timedreceive

arch/s390/pci/pci_irq.c

@@ -410,7 +410,7 @@ static void __init cpu_enable_directed_irq(void *unused)
 	union zpci_sic_iib iib = {{0}};
 	union zpci_sic_iib ziib = {{0}};
 
-	iib.cdiib.dibv_addr = (u64) zpci_ibv[smp_processor_id()]->vector;
+	iib.cdiib.dibv_addr = virt_to_phys(zpci_ibv[smp_processor_id()]->vector);
 
 	zpci_set_irq_ctrl(SIC_IRQ_MODE_SET_CPU, 0, &iib);
 	zpci_set_irq_ctrl(SIC_IRQ_MODE_D_SINGLE, PCI_ISC, &ziib);

arch/sh/kernel/sys_sh32.c

@@ -59,3 +59,14 @@ asmlinkage int sys_fadvise64_64_wrapper(int fd, u32 offset0, u32 offset1,
 				 (u64)len0 << 32 | len1, advice);
 #endif
 }
+
+/*
+ * swap the arguments the way that libc wants them instead of
+ * moving flags ahead of the 64-bit nbytes argument
+ */
+SYSCALL_DEFINE6(sh_sync_file_range6, int, fd, SC_ARG64(offset),
+                SC_ARG64(nbytes), unsigned int, flags)
+{
+        return ksys_sync_file_range(fd, SC_VAL64(loff_t, offset),
+                                    SC_VAL64(loff_t, nbytes), flags);
+}

arch/sh/kernel/syscalls/syscall.tbl

@@ -321,7 +321,7 @@
 311	common	set_robust_list			sys_set_robust_list
 312	common	get_robust_list			sys_get_robust_list
 313	common	splice				sys_splice
-314	common	sync_file_range			sys_sync_file_range
+314	common	sync_file_range			sys_sh_sync_file_range6
 315	common	tee				sys_tee
 316	common	vmsplice			sys_vmsplice
 317	common	move_pages			sys_move_pages
@@ -395,6 +395,7 @@
 385	common	pkey_alloc			sys_pkey_alloc
 386	common	pkey_free			sys_pkey_free
 387	common	rseq				sys_rseq
+388	common	sync_file_range2		sys_sync_file_range2
 # room for arch specific syscalls
 393	common	semget				sys_semget
 394	common	semctl				sys_semctl

arch/sparc/kernel/sys32.S

@@ -18,224 +18,3 @@ sys32_mmap2:
 	sethi		%hi(sys_mmap), %g1
 	jmpl		%g1 + %lo(sys_mmap), %g0
 	 sllx		%o5, 12, %o5
-
-	.align		32
-	.globl		sys32_socketcall
-sys32_socketcall:	/* %o0=call, %o1=args */
-	cmp		%o0, 1
-	bl,pn		%xcc, do_einval
-	 cmp		%o0, 18
-	bg,pn		%xcc, do_einval
-	 sub		%o0, 1, %o0
-	sllx		%o0, 5, %o0
-	sethi		%hi(__socketcall_table_begin), %g2
-	or		%g2, %lo(__socketcall_table_begin), %g2
-	jmpl		%g2 + %o0, %g0
-	 nop
-do_einval:
-	retl
-	 mov		-EINVAL, %o0
-
-	.align		32
-__socketcall_table_begin:
-
-	/* Each entry is exactly 32 bytes. */
-do_sys_socket: /* sys_socket(int, int, int) */
-1:	ldswa		[%o1 + 0x0] %asi, %o0
-	sethi		%hi(sys_socket), %g1
-2:	ldswa		[%o1 + 0x8] %asi, %o2
-	jmpl		%g1 + %lo(sys_socket), %g0
-3:	 ldswa		[%o1 + 0x4] %asi, %o1
-	nop
-	nop
-	nop
-do_sys_bind: /* sys_bind(int fd, struct sockaddr *, int) */
-4:	ldswa		[%o1 + 0x0] %asi, %o0
-	sethi		%hi(sys_bind), %g1
-5:	ldswa		[%o1 + 0x8] %asi, %o2
-	jmpl		%g1 + %lo(sys_bind), %g0
-6:	 lduwa		[%o1 + 0x4] %asi, %o1
-	nop
-	nop
-	nop
-do_sys_connect: /* sys_connect(int, struct sockaddr *, int) */
-7:	ldswa		[%o1 + 0x0] %asi, %o0
-	sethi		%hi(sys_connect), %g1
-8:	ldswa		[%o1 + 0x8] %asi, %o2
-	jmpl		%g1 + %lo(sys_connect), %g0
-9:	 lduwa		[%o1 + 0x4] %asi, %o1
-	nop
-	nop
-	nop
-do_sys_listen: /* sys_listen(int, int) */
-10:	ldswa		[%o1 + 0x0] %asi, %o0
-	sethi		%hi(sys_listen), %g1
-	jmpl		%g1 + %lo(sys_listen), %g0
-11:	 ldswa		[%o1 + 0x4] %asi, %o1
-	nop
-	nop
-	nop
-	nop
-do_sys_accept: /* sys_accept(int, struct sockaddr *, int *) */
-12:	ldswa		[%o1 + 0x0] %asi, %o0
-	sethi		%hi(sys_accept), %g1
-13:	lduwa		[%o1 + 0x8] %asi, %o2
-	jmpl		%g1 + %lo(sys_accept), %g0
-14:	 lduwa		[%o1 + 0x4] %asi, %o1
-	nop
-	nop
-	nop
-do_sys_getsockname: /* sys_getsockname(int, struct sockaddr *, int *) */
-15:	ldswa		[%o1 + 0x0] %asi, %o0
-	sethi		%hi(sys_getsockname), %g1
-16:	lduwa		[%o1 + 0x8] %asi, %o2
-	jmpl		%g1 + %lo(sys_getsockname), %g0
-17:	 lduwa		[%o1 + 0x4] %asi, %o1
-	nop
-	nop
-	nop
-do_sys_getpeername: /* sys_getpeername(int, struct sockaddr *, int *) */
-18:	ldswa		[%o1 + 0x0] %asi, %o0
-	sethi		%hi(sys_getpeername), %g1
-19:	lduwa		[%o1 + 0x8] %asi, %o2
-	jmpl		%g1 + %lo(sys_getpeername), %g0
-20:	 lduwa		[%o1 + 0x4] %asi, %o1
-	nop
-	nop
-	nop
-do_sys_socketpair: /* sys_socketpair(int, int, int, int *) */
-21:	ldswa		[%o1 + 0x0] %asi, %o0
-	sethi		%hi(sys_socketpair), %g1
-22:	ldswa		[%o1 + 0x8] %asi, %o2
-23:	lduwa		[%o1 + 0xc] %asi, %o3
-	jmpl		%g1 + %lo(sys_socketpair), %g0
-24:	 ldswa		[%o1 + 0x4] %asi, %o1
-	nop
-	nop
-do_sys_send: /* sys_send(int, void *, size_t, unsigned int) */
-25:	ldswa		[%o1 + 0x0] %asi, %o0
-	sethi		%hi(sys_send), %g1
-26:	lduwa		[%o1 + 0x8] %asi, %o2
-27:	lduwa		[%o1 + 0xc] %asi, %o3
-	jmpl		%g1 + %lo(sys_send), %g0
-28:	 lduwa		[%o1 + 0x4] %asi, %o1
-	nop
-	nop
-do_sys_recv: /* sys_recv(int, void *, size_t, unsigned int) */
-29:	ldswa		[%o1 + 0x0] %asi, %o0
-	sethi		%hi(sys_recv), %g1
-30:	lduwa		[%o1 + 0x8] %asi, %o2
-31:	lduwa		[%o1 + 0xc] %asi, %o3
-	jmpl		%g1 + %lo(sys_recv), %g0
-32:	 lduwa		[%o1 + 0x4] %asi, %o1
-	nop
-	nop
-do_sys_sendto: /* sys_sendto(int, u32, compat_size_t, unsigned int, u32, int) */
-33:	ldswa		[%o1 + 0x0] %asi, %o0
-	sethi		%hi(sys_sendto), %g1
-34:	lduwa		[%o1 + 0x8] %asi, %o2
-35:	lduwa		[%o1 + 0xc] %asi, %o3
-36:	lduwa		[%o1 + 0x10] %asi, %o4
-37:	ldswa		[%o1 + 0x14] %asi, %o5
-	jmpl		%g1 + %lo(sys_sendto), %g0
-38:	 lduwa		[%o1 + 0x4] %asi, %o1
-do_sys_recvfrom: /* sys_recvfrom(int, u32, compat_size_t, unsigned int, u32, u32) */
-39:	ldswa		[%o1 + 0x0] %asi, %o0
-	sethi		%hi(sys_recvfrom), %g1
-40:	lduwa		[%o1 + 0x8] %asi, %o2
-41:	lduwa		[%o1 + 0xc] %asi, %o3
-42:	lduwa		[%o1 + 0x10] %asi, %o4
-43:	lduwa		[%o1 + 0x14] %asi, %o5
-	jmpl		%g1 + %lo(sys_recvfrom), %g0
-44:	 lduwa		[%o1 + 0x4] %asi, %o1
-do_sys_shutdown: /* sys_shutdown(int, int) */
-45:	ldswa		[%o1 + 0x0] %asi, %o0
-	sethi		%hi(sys_shutdown), %g1
-	jmpl		%g1 + %lo(sys_shutdown), %g0
-46:	 ldswa		[%o1 + 0x4] %asi, %o1
-	nop
-	nop
-	nop
-	nop
-do_sys_setsockopt: /* sys_setsockopt(int, int, int, char *, int) */
-47:	ldswa		[%o1 + 0x0] %asi, %o0
-	sethi		%hi(sys_setsockopt), %g1
-48:	ldswa		[%o1 + 0x8] %asi, %o2
-49:	lduwa		[%o1 + 0xc] %asi, %o3
-50:	ldswa		[%o1 + 0x10] %asi, %o4
-	jmpl		%g1 + %lo(sys_setsockopt), %g0
-51:	 ldswa		[%o1 + 0x4] %asi, %o1
-	nop
-do_sys_getsockopt: /* sys_getsockopt(int, int, int, u32, u32) */
-52:	ldswa		[%o1 + 0x0] %asi, %o0
-	sethi		%hi(sys_getsockopt), %g1
-53:	ldswa		[%o1 + 0x8] %asi, %o2
-54:	lduwa		[%o1 + 0xc] %asi, %o3
-55:	lduwa		[%o1 + 0x10] %asi, %o4
-	jmpl		%g1 + %lo(sys_getsockopt), %g0
-56:	 ldswa		[%o1 + 0x4] %asi, %o1
-	nop
-do_sys_sendmsg: /* compat_sys_sendmsg(int, struct compat_msghdr *, unsigned int) */
-57:	ldswa		[%o1 + 0x0] %asi, %o0
-	sethi		%hi(compat_sys_sendmsg), %g1
-58:	lduwa		[%o1 + 0x8] %asi, %o2
-	jmpl		%g1 + %lo(compat_sys_sendmsg), %g0
-59:	 lduwa		[%o1 + 0x4] %asi, %o1
-	nop
-	nop
-	nop
-do_sys_recvmsg: /* compat_sys_recvmsg(int, struct compat_msghdr *, unsigned int) */
-60:	ldswa		[%o1 + 0x0] %asi, %o0
-	sethi		%hi(compat_sys_recvmsg), %g1
-61:	lduwa		[%o1 + 0x8] %asi, %o2
-	jmpl		%g1 + %lo(compat_sys_recvmsg), %g0
-62:	 lduwa		[%o1 + 0x4] %asi, %o1
-	nop
-	nop
-	nop
-do_sys_accept4: /* sys_accept4(int, struct sockaddr *, int *, int) */
-63:	ldswa		[%o1 + 0x0] %asi, %o0
-	sethi		%hi(sys_accept4), %g1
-64:	lduwa		[%o1 + 0x8] %asi, %o2
-65:	ldswa		[%o1 + 0xc] %asi, %o3
-	jmpl		%g1 + %lo(sys_accept4), %g0
-66:	 lduwa		[%o1 + 0x4] %asi, %o1
-	nop
-	nop
-
-	.section	__ex_table,"a"
-	.align		4
-	.word		1b, __retl_efault, 2b, __retl_efault
-	.word		3b, __retl_efault, 4b, __retl_efault
-	.word		5b, __retl_efault, 6b, __retl_efault
-	.word		7b, __retl_efault, 8b, __retl_efault
-	.word		9b, __retl_efault, 10b, __retl_efault
-	.word		11b, __retl_efault, 12b, __retl_efault
-	.word		13b, __retl_efault, 14b, __retl_efault
-	.word		15b, __retl_efault, 16b, __retl_efault
-	.word		17b, __retl_efault, 18b, __retl_efault
-	.word		19b, __retl_efault, 20b, __retl_efault
-	.word		21b, __retl_efault, 22b, __retl_efault
-	.word		23b, __retl_efault, 24b, __retl_efault
-	.word		25b, __retl_efault, 26b, __retl_efault
-	.word		27b, __retl_efault, 28b, __retl_efault
-	.word		29b, __retl_efault, 30b, __retl_efault
-	.word		31b, __retl_efault, 32b, __retl_efault
-	.word		33b, __retl_efault, 34b, __retl_efault
-	.word		35b, __retl_efault, 36b, __retl_efault
-	.word		37b, __retl_efault, 38b, __retl_efault
-	.word		39b, __retl_efault, 40b, __retl_efault
-	.word		41b, __retl_efault, 42b, __retl_efault
-	.word		43b, __retl_efault, 44b, __retl_efault
-	.word		45b, __retl_efault, 46b, __retl_efault
-	.word		47b, __retl_efault, 48b, __retl_efault
-	.word		49b, __retl_efault, 50b, __retl_efault
-	.word		51b, __retl_efault, 52b, __retl_efault
-	.word		53b, __retl_efault, 54b, __retl_efault
-	.word		55b, __retl_efault, 56b, __retl_efault
-	.word		57b, __retl_efault, 58b, __retl_efault
-	.word		59b, __retl_efault, 60b, __retl_efault
-	.word		61b, __retl_efault, 62b, __retl_efault
-	.word		63b, __retl_efault, 64b, __retl_efault
-	.word		65b, __retl_efault, 66b, __retl_efault
-	.previous

arch/sparc/kernel/syscalls/syscall.tbl

@@ -117,7 +117,7 @@
 90	common	dup2			sys_dup2
 91	32	setfsuid32		sys_setfsuid
 92	common	fcntl			sys_fcntl			compat_sys_fcntl
-93	common	select			sys_select
+93	common	select			sys_select			compat_sys_select
 94	32	setfsgid32		sys_setfsgid
 95	common	fsync			sys_fsync
 96	common	setpriority		sys_setpriority
@@ -155,7 +155,7 @@
 123	32	fchown			sys_fchown16
 123	64	fchown			sys_fchown
 124	common	fchmod			sys_fchmod
-125	common	recvfrom		sys_recvfrom
+125	common	recvfrom		sys_recvfrom			compat_sys_recvfrom
 126	32	setreuid		sys_setreuid16
 126	64	setreuid		sys_setreuid
 127	32	setregid		sys_setregid16
@@ -247,7 +247,7 @@
 204	32	readdir			sys_old_readdir			compat_sys_old_readdir
 204	64	readdir			sys_nis_syscall
 205	common	readahead		sys_readahead			compat_sys_readahead
-206	common	socketcall		sys_socketcall			sys32_socketcall
+206	common	socketcall		sys_socketcall			compat_sys_socketcall
 207	common	syslog			sys_syslog
 208	common	lookup_dcookie		sys_ni_syscall
 209	common	fadvise64		sys_fadvise64			compat_sys_fadvise64
@@ -461,7 +461,7 @@
 412	32	utimensat_time64		sys_utimensat			sys_utimensat
 413	32	pselect6_time64			sys_pselect6			compat_sys_pselect6_time64
 414	32	ppoll_time64			sys_ppoll			compat_sys_ppoll_time64
-416	32	io_pgetevents_time64		sys_io_pgetevents		sys_io_pgetevents
+416	32	io_pgetevents_time64		sys_io_pgetevents		compat_sys_io_pgetevents_time64
 417	32	recvmmsg_time64			sys_recvmmsg			compat_sys_recvmmsg_time64
 418	32	mq_timedsend_time64		sys_mq_timedsend		sys_mq_timedsend
 419	32	mq_timedreceive_time64		sys_mq_timedreceive		sys_mq_timedreceive

arch/x86/boot/compressed/Makefile

@@ -105,9 +105,9 @@ vmlinux-objs-$(CONFIG_UNACCEPTED_MEMORY) += $(obj)/mem.o
 
 vmlinux-objs-$(CONFIG_EFI) += $(obj)/efi.o
 vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_mixed.o
-vmlinux-objs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a
+vmlinux-libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a
 
-$(obj)/vmlinux: $(vmlinux-objs-y) FORCE
+$(obj)/vmlinux: $(vmlinux-objs-y) $(vmlinux-libs-y) FORCE
 	$(call if_changed,ld)
 
 OBJCOPYFLAGS_vmlinux.bin :=  -R .comment -S

arch/x86/entry/syscalls/syscall_32.tbl

@@ -420,7 +420,7 @@
 412	i386	utimensat_time64	sys_utimensat
 413	i386	pselect6_time64		sys_pselect6			compat_sys_pselect6_time64
 414	i386	ppoll_time64		sys_ppoll			compat_sys_ppoll_time64
-416	i386	io_pgetevents_time64	sys_io_pgetevents
+416	i386	io_pgetevents_time64	sys_io_pgetevents		compat_sys_io_pgetevents_time64
 417	i386	recvmmsg_time64		sys_recvmmsg			compat_sys_recvmmsg_time64
 418	i386	mq_timedsend_time64	sys_mq_timedsend
 419	i386	mq_timedreceive_time64	sys_mq_timedreceive

arch/x86/include/asm/cmpxchg_32.h

@@ -93,10 +93,9 @@ static __always_inline bool __try_cmpxchg64_local(volatile u64 *ptr, u64 *oldp,
 									\
 	asm volatile(ALTERNATIVE(_lock_loc				\
 				 "call cmpxchg8b_emu",			\
-				 _lock "cmpxchg8b %[ptr]", X86_FEATURE_CX8) \
+				 _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \
-		     : [ptr] "+m" (*(_ptr)),				\
+		     : "+a" (o.low), "+d" (o.high)			\
-		       "+a" (o.low), "+d" (o.high)			\
+		     : "b" (n.low), "c" (n.high), [ptr] "S" (_ptr)	\
-		     : "b" (n.low), "c" (n.high), "S" (_ptr)		\
 		     : "memory");					\
 									\
 	o.full;								\
@@ -122,12 +121,11 @@ static __always_inline u64 arch_cmpxchg64_local(volatile u64 *ptr, u64 old, u64
 									\
 	asm volatile(ALTERNATIVE(_lock_loc				\
 				 "call cmpxchg8b_emu",			\
-				 _lock "cmpxchg8b %[ptr]", X86_FEATURE_CX8) \
+				 _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \
 		     CC_SET(e)						\
 		     : CC_OUT(e) (ret),					\
-		       [ptr] "+m" (*(_ptr)),				\
 		       "+a" (o.low), "+d" (o.high)			\
-		     : "b" (n.low), "c" (n.high), "S" (_ptr)		\
+		     : "b" (n.low), "c" (n.high), [ptr] "S" (_ptr)	\
 		     : "memory");					\
 									\
 	if (unlikely(!ret))						\

arch/x86/include/asm/efi.h

@@ -401,7 +401,6 @@ extern int __init efi_memmap_alloc(unsigned int num_entries,
 				   struct efi_memory_map_data *data);
 extern void __efi_memmap_free(u64 phys, unsigned long size,
 			      unsigned long flags);
-#define __efi_memmap_free __efi_memmap_free
 
 extern int __init efi_memmap_install(struct efi_memory_map_data *data);
 extern int __init efi_memmap_split_count(efi_memory_desc_t *md,

arch/x86/include/asm/entry-common.h

@@ -73,19 +73,16 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
 #endif
 
 	/*
-	 * Ultimately, this value will get limited by KSTACK_OFFSET_MAX(),
+	 * This value will get limited by KSTACK_OFFSET_MAX(), which is 10
-	 * but not enough for x86 stack utilization comfort. To keep
+	 * bits. The actual entropy will be further reduced by the compiler
-	 * reasonable stack head room, reduce the maximum offset to 8 bits.
+	 * when applying stack alignment constraints (see cc_stack_align4/8 in
-	 *
-	 * The actual entropy will be further reduced by the compiler when
-	 * applying stack alignment constraints (see cc_stack_align4/8 in
 	 * arch/x86/Makefile), which will remove the 3 (x86_64) or 2 (ia32)
 	 * low bits from any entropy chosen here.
 	 *
-	 * Therefore, final stack offset entropy will be 5 (x86_64) or
+	 * Therefore, final stack offset entropy will be 7 (x86_64) or
-	 * 6 (ia32) bits.
+	 * 8 (ia32) bits.
 	 */
-	choose_random_kstack_offset(rdtsc() & 0xFF);
+	choose_random_kstack_offset(rdtsc());
 }
 #define arch_exit_to_user_mode_prepare arch_exit_to_user_mode_prepare
 

arch/x86/include/asm/uaccess.h

@@ -78,10 +78,10 @@ extern int __get_user_bad(void);
 	int __ret_gu;							\
 	register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX);		\
 	__chk_user_ptr(ptr);						\
-	asm volatile("call __" #fn "_%c4"				\
+	asm volatile("call __" #fn "_%c[size]"				\
 		     : "=a" (__ret_gu), "=r" (__val_gu),		\
 			ASM_CALL_CONSTRAINT				\
-		     : "0" (ptr), "i" (sizeof(*(ptr))));		\
+		     : "0" (ptr), [size] "i" (sizeof(*(ptr))));		\
 	instrument_get_user(__val_gu);					\
 	(x) = (__force __typeof__(*(ptr))) __val_gu;			\
 	__builtin_expect(__ret_gu, 0);					\

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

@@ -519,7 +519,8 @@ void free_rmid(u32 closid, u32 rmid)
 	 * allows architectures that ignore the closid parameter to avoid an
 	 * unnecessary check.
 	 */
-	if (idx == resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID,
+	if (!resctrl_arch_mon_capable() ||
+	    idx == resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID,
 						RESCTRL_RESERVED_RMID))
 		return;
 

arch/x86/kernel/time.c

@@ -27,25 +27,7 @@
 
 unsigned long profile_pc(struct pt_regs *regs)
 {
-	unsigned long pc = instruction_pointer(regs);
+	return instruction_pointer(regs);
-
-	if (!user_mode(regs) && in_lock_functions(pc)) {
-#ifdef CONFIG_FRAME_POINTER
-		return *(unsigned long *)(regs->bp + sizeof(long));
-#else
-		unsigned long *sp = (unsigned long *)regs->sp;
-		/*
-		 * Return address is either directly at stack pointer
-		 * or above a saved flags. Eflags has bits 22-31 zero,
-		 * kernel addresses don't.
-		 */
-		if (sp[0] >> 22)
-			return sp[0];
-		if (sp[1] >> 22)
-			return sp[1];
-#endif
-	}
-	return pc;
 }
 EXPORT_SYMBOL(profile_pc);
 

arch/x86/kvm/svm/svm.c

@@ -2843,7 +2843,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 
 	if (sev_es_prevent_msr_access(vcpu, msr_info)) {
 		msr_info->data = 0;
-		return -EINVAL;
+		return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0;
 	}
 
 	switch (msr_info->index) {
@@ -2998,7 +2998,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	u64 data = msr->data;
 
 	if (sev_es_prevent_msr_access(vcpu, msr))
-		return -EINVAL;
+		return vcpu->kvm->arch.has_protected_state ? -EINVAL : 0;
 
 	switch (ecx) {
 	case MSR_AMD64_TSC_RATIO:

arch/x86/kvm/x86.c

@@ -10718,13 +10718,12 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
 
 	bitmap_zero(vcpu->arch.ioapic_handled_vectors, 256);
 
+	static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
+
 	if (irqchip_split(vcpu->kvm))
 		kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors);
-	else {
+	else if (ioapic_in_kernel(vcpu->kvm))
-		static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
+		kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors);
-		if (ioapic_in_kernel(vcpu->kvm))
-			kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors);
-	}
 
 	if (is_guest_mode(vcpu))
 		vcpu->arch.load_eoi_exitmap_pending = true;

arch/x86/lib/getuser.S

@@ -44,7 +44,11 @@
 	or %rdx, %rax
 .else
 	cmp $TASK_SIZE_MAX-\size+1, %eax
+.if \size != 8
 	jae .Lbad_get_user
+.else
+	jae .Lbad_get_user_8
+.endif
 	sbb %edx, %edx		/* array_index_mask_nospec() */
 	and %edx, %eax
 .endif
@@ -154,7 +158,7 @@ SYM_CODE_END(__get_user_handle_exception)
 #ifdef CONFIG_X86_32
 SYM_CODE_START_LOCAL(__get_user_8_handle_exception)
 	ASM_CLAC
-bad_get_user_8:
+.Lbad_get_user_8:
 	xor %edx,%edx
 	xor %ecx,%ecx
 	mov $(-EFAULT),%_ASM_AX