Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Cross-merge networking fixes after downstream PR (net-6.16-rc3).

No conflicts or adjacent changes.

Signed-off-by: Jakub Kicinski <[e-mail]>

.mailmap

···
 Daniel Borkmann <[e-mail]> <[e-mail]>
 Daniel Borkmann <[e-mail]> <[e-mail]>
 Daniel Borkmann <[e-mail]> <[e-mail]>
+Danilo Krummrich <[e-mail]> <[e-mail]>
 David Brownell <[e-mail]>
 David Collins <[e-mail]> <[e-mail]>
 David Heidelberg <[e-mail]> <[e-mail]>
···
 Gustavo Padovan <[e-mail]>
 Hamza Mahfooz <[e-mail]> <[e-mail]>
 Hanjun Guo <[e-mail]> <[e-mail]>
+Hans de Goede <[e-mail]> <[e-mail]>
 Hans Verkuil <[e-mail]> <[e-mail]>
 Hans Verkuil <[e-mail]> <[e-mail]>
 Harry Yoo <[e-mail]> <[e-mail]>
···
 Serge Hallyn <[e-mail]> <[e-mail]>
 Seth Forshee <[e-mail]> <[e-mail]>
 Shakeel Butt <[e-mail]> <[e-mail]>
-Shannon Nelson <[e-mail]> <[e-mail]>
-Shannon Nelson <[e-mail]> <[e-mail]>
-Shannon Nelson <[e-mail]> <[e-mail]>
+Shannon Nelson <[e-mail]> <[e-mail]>
+Shannon Nelson <[e-mail]> <[e-mail]>
+Shannon Nelson <[e-mail]> <[e-mail]>
+Shannon Nelson <[e-mail]> <[e-mail]>
 Sharath Chandra Vurukala <[e-mail]> <[e-mail]>
 Shiraz Hashim <[e-mail]> <[e-mail]>
 Shuah Khan <[e-mail]> <[e-mail]>

Documentation/admin-guide/cifs/usage.rst

···
 illegal Windows/NTFS/SMB characters to a remap range (this mount parameter
 is the default for SMB3). This remap (``mapposix``) range is also
 compatible with Mac (and "Services for Mac" on some older Windows).
+When POSIX Extensions for SMB 3.1.1 are negotiated, remapping is automatically
+disabled.
 
 CIFS VFS Mount Options
 ======================

Documentation/block/ublk.rst

···
 parameter of `struct ublk_param_segment` with backend for avoiding
 unnecessary IO split, which usually hurts io_uring performance.
 
+Auto Buffer Registration
+------------------------
+
+The ``UBLK_F_AUTO_BUF_REG`` feature automatically handles buffer registration
+and unregistration for I/O requests, which simplifies the buffer management
+process and reduces overhead in the ublk server implementation.
+
+This is another feature flag for using zero copy, and it is compatible with
+``UBLK_F_SUPPORT_ZERO_COPY``.
+
+Feature Overview
+~~~~~~~~~~~~~~~~
+
+This feature automatically registers request buffers to the io_uring context
+before delivering I/O commands to the ublk server and unregisters them when
+completing I/O commands. This eliminates the need for manual buffer
+registration/unregistration via ``UBLK_IO_REGISTER_IO_BUF`` and
+``UBLK_IO_UNREGISTER_IO_BUF`` commands, then IO handling in ublk server
+can avoid dependency on the two uring_cmd operations.
+
+IOs can't be issued concurrently to io_uring if there is any dependency
+among these IOs. So this way not only simplifies ublk server implementation,
+but also makes concurrent IO handling becomes possible by removing the
+dependency on buffer registration & unregistration commands.
+
+Usage Requirements
+~~~~~~~~~~~~~~~~~~
+
+1. The ublk server must create a sparse buffer table on the same ``io_ring_ctx``
+   used for ``UBLK_IO_FETCH_REQ`` and ``UBLK_IO_COMMIT_AND_FETCH_REQ``. If
+   uring_cmd is issued on a different ``io_ring_ctx``, manual buffer
+   unregistration is required.
+
+2. Buffer registration data must be passed via uring_cmd's ``sqe->addr`` with the
+   following structure::
+
+    struct ublk_auto_buf_reg {
+        __u16 index;      /* Buffer index for registration */
+        __u8 flags;       /* Registration flags */
+        __u8 reserved0;   /* Reserved for future use */
+        __u32 reserved1;  /* Reserved for future use */
+    };
+
+   ublk_auto_buf_reg_to_sqe_addr() is for converting the above structure into
+   ``sqe->addr``.
+
+3. All reserved fields in ``ublk_auto_buf_reg`` must be zeroed.
+
+4. Optional flags can be passed via ``ublk_auto_buf_reg.flags``.
+
+Fallback Behavior
+~~~~~~~~~~~~~~~~~
+
+If auto buffer registration fails:
+
+1. When ``UBLK_AUTO_BUF_REG_FALLBACK`` is enabled:
+
+   - The uring_cmd is completed
+   - ``UBLK_IO_F_NEED_REG_BUF`` is set in ``ublksrv_io_desc.op_flags``
+   - The ublk server must manually deal with the failure, such as, register
+     the buffer manually, or using user copy feature for retrieving the data
+     for handling ublk IO
+
+2. If fallback is not enabled:
+
+   - The ublk I/O request fails silently
+   - The uring_cmd won't be completed
+
+Limitations
+~~~~~~~~~~~
+
+- Requires same ``io_ring_ctx`` for all operations
+- May require manual buffer management in fallback cases
+- io_ring_ctx buffer table has a max size of 16K, which may not be enough
+  in case that too many ublk devices are handled by this single io_ring_ctx
+  and each one has very large queue depth
+
 References
 ==========
 

Documentation/devicetree/bindings/pmem/pmem-region.txt

···
-Device-tree bindings for persistent memory regions
------------------------------------------------------
-
-Persistent memory refers to a class of memory devices that are:
-
-	a) Usable as main system memory (i.e. cacheable), and
-	b) Retain their contents across power failure.
-
-Given b) it is best to think of persistent memory as a kind of memory mapped
-storage device. To ensure data integrity the operating system needs to manage
-persistent regions separately to the normal memory pool. To aid with that this
-binding provides a standardised interface for discovering where persistent
-memory regions exist inside the physical address space.
-
-Bindings for the region nodes:
------------------------------
-
-Required properties:
-	- compatible = "pmem-region"
-
-	- reg = <base, size>;
-		The reg property should specify an address range that is
-		translatable to a system physical address range. This address
-		range should be mappable as normal system memory would be
-		(i.e cacheable).
-
-		If the reg property contains multiple address ranges
-		each address range will be treated as though it was specified
-		in a separate device node. Having multiple address ranges in a
-		node implies no special relationship between the two ranges.
-
-Optional properties:
-	- Any relevant NUMA associativity properties for the target platform.
-
-	- volatile; This property indicates that this region is actually
-	  backed by non-persistent memory. This lets the OS know that it
-	  may skip the cache flushes required to ensure data is made
-	  persistent after a write.
-
-	  If this property is absent then the OS must assume that the region
-	  is backed by non-volatile memory.
-
-Examples:
---------------------
-
-	/*
-	 * This node specifies one 4KB region spanning from
-	 * 0x5000 to 0x5fff that is backed by non-volatile memory.
-	 */
-	pmem@5000 {
-		compatible = "pmem-region";
-		reg = <0x00005000 0x00001000>;
-	};
-
-	/*
-	 * This node specifies two 4KB regions that are backed by
-	 * volatile (normal) memory.
-	 */
-	pmem@6000 {
-		compatible = "pmem-region";
-		reg = < 0x00006000 0x00001000
-			0x00008000 0x00001000 >;
-		volatile;
-	};
-

Documentation/devicetree/bindings/pmem/pmem-region.yaml

···
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pmem-region.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+maintainers:
+  - Oliver O'Halloran <[e-mail]>
+
+title: Persistent Memory Regions
+
+description: |
+  Persistent memory refers to a class of memory devices that are:
+
+    a) Usable as main system memory (i.e. cacheable), and
+    b) Retain their contents across power failure.
+
+  Given b) it is best to think of persistent memory as a kind of memory mapped
+  storage device. To ensure data integrity the operating system needs to manage
+  persistent regions separately to the normal memory pool. To aid with that this
+  binding provides a standardised interface for discovering where persistent
+  memory regions exist inside the physical address space.
+
+properties:
+  compatible:
+    const: pmem-region
+
+  reg:
+    maxItems: 1
+
+  volatile:
+    description:
+      Indicates the region is volatile (non-persistent) and the OS can skip
+      cache flushes for writes
+    type: boolean
+
+required:
+  - compatible
+  - reg
+
+additionalProperties: false
+
+examples:
+  - |
+    pmem@5000 {
+        compatible = "pmem-region";
+        reg = <0x00005000 0x00001000>;
+    };

Documentation/filesystems/proc.rst

···
     ms    may share
     gd    stack segment growns down
     pf    pure PFN range
-    dw    disabled write to the mapped file
     lo    pages are locked in memory
     io    memory mapped I/O area
     sr    sequential read advise provided
···
     mt    arm64 MTE allocation tags are enabled
     um    userfaultfd missing tracking
     uw    userfaultfd wr-protect tracking
+    ui    userfaultfd minor fault
     ss    shadow/guarded control stack page
     sl    sealed
+    lf    lock on fault pages
+    dp    always lazily freeable mapping
     ==    =======================================
 
 Note that there is no guarantee that every flag and associated mnemonic will

Documentation/netlink/specs/ethtool.yaml

···
 doc: Partial family for Ethtool Netlink.
 uapi-header: linux/ethtool_netlink_generated.h
 
+c-family-name: ethtool-genl-name
+c-version-name: ethtool-genl-version
+
 definitions:
   -
     name: udp-tunnel-type

Documentation/process/embargoed-hardware-issues.rst

···
   AMD		Tom Lendacky <[e-mail]>
   Ampere	Darren Hart <[e-mail]>
   ARM		Catalin Marinas <[e-mail]>
+  IBM Power	Madhavan Srinivasan <[e-mail]>
   IBM Z		Christian Borntraeger <[e-mail]>
   Intel		Tony Luck <[e-mail]>
   Qualcomm	Trilok Soni <[e-mail]>

MAINTAINERS

···
 X:	include/uapi/
 
 ABIT UGURU 1,2 HARDWARE MONITOR DRIVER
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 L:	[e-mail]
 S:	Maintained
 F:	drivers/hwmon/abituguru.c
···
 F:	drivers/platform/x86/quickstart.c
 
 ACPI SERIAL MULTI INSTANTIATE DRIVER
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 L:	[e-mail]
 S:	Maintained
 F:	drivers/platform/x86/serial-multi-instantiate.c
···
 F:	arch/x86/kernel/amd_node.c
 
 AMD PDS CORE DRIVER
-M:	Shannon Nelson <[e-mail]>
 M:	Brett Creeley <[e-mail]>
 L:	[e-mail]
 S:	Maintained
···
 F:	scripts/make_fit.py
 
 ARM64 PLATFORM DRIVERS
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 M:	Ilpo Järvinen <[e-mail]>
 R:	Bryan O'Donoghue <[e-mail]>
 L:	[e-mail]
···
 F:	drivers/platform/x86/eeepc*.c
 
 ASUS TF103C DOCK DRIVER
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 L:	[e-mail]
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/pdx86/platform-drivers-x86.git
···
 F:	drivers/usb/chipidea/
 
 CHIPONE ICN8318 I2C TOUCHSCREEN DRIVER
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 L:	[e-mail]
 S:	Maintained
 F:	Documentation/devicetree/bindings/input/touchscreen/chipone,icn8318.yaml
 F:	drivers/input/touchscreen/chipone_icn8318.c
 
 CHIPONE ICN8505 I2C TOUCHSCREEN DRIVER
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 L:	[e-mail]
 S:	Maintained
 F:	drivers/input/touchscreen/chipone_icn8505.c
···
 F:	include/linux/smpboot.h
 F:	kernel/cpu.c
 F:	kernel/smpboot.*
+F:	rust/helper/cpu.c
 F:	rust/kernel/cpu.rs
 
 CPU IDLE TIME MANAGEMENT FRAMEWORK
···
 F:	include/linux/devfreq-event.h
 
 DEVICE RESOURCE MANAGEMENT HELPERS
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 R:	Matti Vaittinen <[e-mail]>
 S:	Maintained
 F:	include/linux/devm-helpers.h
···
 F:	include/drm/gud.h
 
 DRM DRIVER FOR GRAIN MEDIA GM12U320 PROJECTORS
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 S:	Maintained
 T:	git https://gitlab.freedesktop.org/drm/misc/kernel.git
 F:	drivers/gpu/drm/tiny/gm12u320.c
···
 F:	drivers/gpu/drm/vkms/
 
 DRM DRIVER FOR VIRTUALBOX VIRTUAL GPU
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 L:	[e-mail]
 S:	Maintained
 T:	git https://gitlab.freedesktop.org/drm/misc/kernel.git
···
 F:	include/drm/drm_panel.h
 
 DRM PRIVACY-SCREEN CLASS
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 L:	[e-mail]
 S:	Maintained
 T:	git https://gitlab.freedesktop.org/drm/misc/kernel.git
···
 
 FWCTL PDS DRIVER
 M:	Brett Creeley <[e-mail]>
-R:	Shannon Nelson <[e-mail]>
 L:	[e-mail]
 S:	Maintained
 F:	drivers/fwctl/pds/
···
 F:	Documentation/devicetree/bindings/connector/gocontroll,moduline-module-slot.yaml
 
 GOODIX TOUCHSCREEN
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 L:	[e-mail]
 S:	Maintained
 F:	drivers/input/touchscreen/goodix*
···
 K:	[gG]oogle.?[tT]ensor
 
 GPD POCKET FAN DRIVER
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 L:	[e-mail]
 S:	Maintained
 F:	drivers/platform/x86/gpd-pocket-fan.c
···
 F:	drivers/i2c/busses/i2c-viapro.c
 
 I2C/SMBUS INTEL CHT WHISKEY COVE PMIC DRIVER
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 L:	[e-mail]
 S:	Maintained
 F:	drivers/i2c/busses/i2c-cht-wc.c
···
 F:	sound/soc/intel/
 
 INTEL ATOMISP2 DUMMY / POWER-MANAGEMENT DRIVER
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 L:	[e-mail]
 S:	Maintained
 F:	drivers/platform/x86/intel/atomisp2/pm.c
 
 INTEL ATOMISP2 LED DRIVER
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 L:	[e-mail]
 S:	Maintained
 F:	drivers/platform/x86/intel/atomisp2/led.c
···
 F:	drivers/platform/x86/lenovo-wmi-hotkey-utilities.c
 
 LETSKETCH HID TABLET DRIVER
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 L:	[e-mail]
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/hid/hid.git
···
 F:	drivers/ata/sata_gemini.h
 
 LIBATA SATA AHCI PLATFORM devices support
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 L:	[e-mail]
 S:	Maintained
 F:	drivers/ata/ahci_platform.c
···
 L:	[e-mail]
 S:	Supported
 Q:	https://patchwork.kernel.org/project/linux-nvdimm/list/
-F:	Documentation/devicetree/bindings/pmem/pmem-region.txt
+F:	Documentation/devicetree/bindings/pmem/pmem-region.yaml
 F:	drivers/nvdimm/of_pmem.c
 
 LIBNVDIMM: NON-VOLATILE MEMORY DEVICE SUBSYSTEM
···
 F:	block/partitions/ldm.*
 
 LOGITECH HID GAMING KEYBOARDS
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 L:	[e-mail]
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/hid/hid.git
···
 F:	drivers/power/supply/max17040_battery.c
 
 MAXIM MAX17042 FAMILY FUEL GAUGE DRIVERS
-R:	Hans de Goede <[e-mail]>
+R:	Hans de Goede <[e-mail]>
 R:	Krzysztof Kozlowski <[e-mail]>
 R:	Marek Szyprowski <[e-mail]>
 R:	Sebastian Krzyszkowiak <[e-mail]>
···
 F:	drivers/net/ethernet/mellanox/mlxfw/
 
 MELLANOX HARDWARE PLATFORM SUPPORT
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 M:	Ilpo Järvinen <[e-mail]>
 M:	Vadim Pasternak <[e-mail]>
 L:	[e-mail]
···
 R:	Nico Pache <[e-mail]>
 R:	Ryan Roberts <[e-mail]>
 R:	Dev Jain <[e-mail]>
+R:	Barry Song <[e-mail]>
 L:	[e-mail]
 S:	Maintained
 W:	http://www.linux-mm.org
···
 F:	drivers/platform/surface/surface_gpe.c
 
 MICROSOFT SURFACE HARDWARE PLATFORM SUPPORT
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 M:	Ilpo Järvinen <[e-mail]>
 M:	Maximilian Luz <[e-mail]>
 L:	[e-mail]
···
 F:	tools/testing/selftests/nolibc/
 
 NOVATEK NVT-TS I2C TOUCHSCREEN DRIVER
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 L:	[e-mail]
 S:	Maintained
 F:	Documentation/devicetree/bindings/input/touchscreen/novatek,nvt-ts.yaml
···
 F:	include/crypto/pcrypt.h
 
 PDS DSC VIRTIO DATA PATH ACCELERATOR
-R:	Shannon Nelson <[e-mail]>
+R:	Brett Creeley <[e-mail]>
 F:	drivers/vdpa/pds/
 
 PECI HARDWARE MONITORING DRIVERS
···
 F:	include/linux/peci.h
 
 PENSANDO ETHERNET DRIVERS
-M:	Shannon Nelson <[e-mail]>
 M:	Brett Creeley <[e-mail]>
 L:	[e-mail]
 S:	Maintained
···
 R:	David Vernet <[e-mail]>
 R:	Andrea Righi <[e-mail]>
 R:	Changwoo Min <[e-mail]>
-L:	[e-mail]
+L:	[e-mail]
 S:	Maintained
 W:	https://github.com/sched-ext/scx
 T:	git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext.git
···
 K:	[^@]sifive
 
 SILEAD TOUCHSCREEN DRIVER
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 L:	[e-mail]
 L:	[e-mail]
 S:	Maintained
···
 F:	drivers/i3c/master/svc-i3c-master.c
 
 SIMPLEFB FB DRIVER
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 L:	[e-mail]
 S:	Maintained
 F:	Documentation/devicetree/bindings/display/simple-framebuffer.yaml
···
 F:	drivers/hwmon/emc2103.c
 
 SMSC SCH5627 HARDWARE MONITOR DRIVER
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 L:	[e-mail]
 S:	Supported
 F:	Documentation/hwmon/sch5627.rst
···
 F:	Documentation/process/stable-kernel-rules.rst
 
 STAGING - ATOMISP DRIVER
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 M:	Mauro Carvalho Chehab <[e-mail]>
 R:	Sakari Ailus <[e-mail]>
 L:	[e-mail]
···
 F:	drivers/net/ethernet/i825xx/sun3*
 
 SUN4I LOW RES ADC ATTACHED TABLET KEYS DRIVER
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 L:	[e-mail]
 S:	Maintained
 F:	Documentation/devicetree/bindings/input/allwinner,sun4i-a10-lradc-keys.yaml
···
 F:	drivers/hid/usbhid/
 
 USB INTEL XHCI ROLE MUX DRIVER
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 L:	[e-mail]
 S:	Maintained
 F:	drivers/usb/roles/intel-xhci-usb-role-switch.c
···
 F:	drivers/usb/typec/mux/intel_pmc_mux.c
 
 USB TYPEC PI3USB30532 MUX DRIVER
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 L:	[e-mail]
 S:	Maintained
 F:	drivers/usb/typec/mux/pi3usb30532.c
···
 
 USB VIDEO CLASS
 M:	Laurent Pinchart <[e-mail]>
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 L:	[e-mail]
 S:	Maintained
 W:	http://www.ideasonboard.org/uvc/
···
 F:	sound/virtio/*
 
 VIRTUAL BOX GUEST DEVICE DRIVER
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 M:	Arnd Bergmann <[e-mail]>
 M:	Greg Kroah-Hartman <[e-mail]>
 S:	Maintained
···
 F:	include/uapi/linux/vbox*.h
 
 VIRTUAL BOX SHARED FOLDER VFS DRIVER
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 L:	[e-mail]
 S:	Maintained
 F:	fs/vboxsf/*
···
 
 WACOM PROTOCOL 4 SERIAL TABLETS
 M:	Julian Squires <[e-mail]>
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 L:	[e-mail]
 S:	Maintained
 F:	drivers/input/tablet/wacom_serial4.c
···
 F:	include/uapi/linux/wwan.h
 
 X-POWERS AXP288 PMIC DRIVERS
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 S:	Maintained
 F:	drivers/acpi/pmic/intel_pmic_xpower.c
 N:	axp288
···
 F:	arch/x86/mm/
 
 X86 PLATFORM ANDROID TABLETS DSDT FIXUP DRIVER
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 L:	[e-mail]
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/pdx86/platform-drivers-x86.git
 F:	drivers/platform/x86/x86-android-tablets/
 
 X86 PLATFORM DRIVERS
-M:	Hans de Goede <[e-mail]>
+M:	Hans de Goede <[e-mail]>
 M:	Ilpo Järvinen <[e-mail]>
 L:	[e-mail]
 S:	Maintained

Makefile

···
 VERSION = 6
 PATCHLEVEL = 16
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*
···
 # Misc
 # ---------------------------------------------------------------------------
 
-# Run misc checks when ${KBUILD_EXTRA_WARN} contains 1
 PHONY += misc-check
-ifneq ($(findstring 1,$(KBUILD_EXTRA_WARN)),)
 misc-check:
 	$(Q)$(srctree)/scripts/misc-check
-endif
 
 all: misc-check
 

arch/arm64/include/asm/kvm_host.h

···
 #define ctxt_sys_reg(c,r)	(*__ctxt_sys_reg(c,r))
 
 u64 kvm_vcpu_apply_reg_masks(const struct kvm_vcpu *, enum vcpu_sysreg, u64);
-#define __vcpu_sys_reg(v,r)						\
-	(*({								\
+
+#define __vcpu_assign_sys_reg(v, r, val)				\
+	do {								\
 		const struct kvm_cpu_context *ctxt = &(v)->arch.ctxt;	\
-		u64 *__r = __ctxt_sys_reg(ctxt, (r));			\
+		u64 __v = (val);					\
 		if (vcpu_has_nv((v)) && (r) >= __SANITISED_REG_START__)	\
-			*__r = kvm_vcpu_apply_reg_masks((v), (r), *__r);\
-		__r;							\
-	}))
+			__v = kvm_vcpu_apply_reg_masks((v), (r), __v);	\
+									\
+		ctxt_sys_reg(ctxt, (r)) = __v;				\
+	} while (0)
+
+#define __vcpu_rmw_sys_reg(v, r, op, val)				\
+	do {								\
+		const struct kvm_cpu_context *ctxt = &(v)->arch.ctxt;	\
+		u64 __v = ctxt_sys_reg(ctxt, (r));			\
+		__v op (val);						\
+		if (vcpu_has_nv((v)) && (r) >= __SANITISED_REG_START__)	\
+			__v = kvm_vcpu_apply_reg_masks((v), (r), __v);	\
+									\
+		ctxt_sys_reg(ctxt, (r)) = __v;				\
+	} while (0)
+
+#define __vcpu_sys_reg(v,r)						\
+	({								\
+		const struct kvm_cpu_context *ctxt = &(v)->arch.ctxt;	\
+		u64 __v = ctxt_sys_reg(ctxt, (r));			\
+		if (vcpu_has_nv((v)) && (r) >= __SANITISED_REG_START__)	\
+			__v = kvm_vcpu_apply_reg_masks((v), (r), __v);	\
+		__v;							\
+	})
 
 u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg);
 void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg);

arch/arm64/kvm/arch_timer.c

···
 
 	switch(arch_timer_ctx_index(ctxt)) {
 	case TIMER_VTIMER:
-		__vcpu_sys_reg(vcpu, CNTV_CTL_EL0) = ctl;
+		__vcpu_assign_sys_reg(vcpu, CNTV_CTL_EL0, ctl);
 		break;
 	case TIMER_PTIMER:
-		__vcpu_sys_reg(vcpu, CNTP_CTL_EL0) = ctl;
+		__vcpu_assign_sys_reg(vcpu, CNTP_CTL_EL0, ctl);
 		break;
 	case TIMER_HVTIMER:
-		__vcpu_sys_reg(vcpu, CNTHV_CTL_EL2) = ctl;
+		__vcpu_assign_sys_reg(vcpu, CNTHV_CTL_EL2, ctl);
 		break;
 	case TIMER_HPTIMER:
-		__vcpu_sys_reg(vcpu, CNTHP_CTL_EL2) = ctl;
+		__vcpu_assign_sys_reg(vcpu, CNTHP_CTL_EL2, ctl);
 		break;
 	default:
 		WARN_ON(1);
···
 
 	switch(arch_timer_ctx_index(ctxt)) {
 	case TIMER_VTIMER:
-		__vcpu_sys_reg(vcpu, CNTV_CVAL_EL0) = cval;
+		__vcpu_assign_sys_reg(vcpu, CNTV_CVAL_EL0, cval);
 		break;
 	case TIMER_PTIMER:
-		__vcpu_sys_reg(vcpu, CNTP_CVAL_EL0) = cval;
+		__vcpu_assign_sys_reg(vcpu, CNTP_CVAL_EL0, cval);
 		break;
 	case TIMER_HVTIMER:
-		__vcpu_sys_reg(vcpu, CNTHV_CVAL_EL2) = cval;
+		__vcpu_assign_sys_reg(vcpu, CNTHV_CVAL_EL2, cval);
 		break;
 	case TIMER_HPTIMER:
-		__vcpu_sys_reg(vcpu, CNTHP_CVAL_EL2) = cval;
+		__vcpu_assign_sys_reg(vcpu, CNTHP_CVAL_EL2, cval);
 		break;
 	default:
 		WARN_ON(1);
···
 	if (vcpu_has_nv(vcpu)) {
 		struct arch_timer_offset *offs = &vcpu_vtimer(vcpu)->offset;
 
-		offs->vcpu_offset = &__vcpu_sys_reg(vcpu, CNTVOFF_EL2);
+		offs->vcpu_offset = __ctxt_sys_reg(&vcpu->arch.ctxt, CNTVOFF_EL2);
 		offs->vm_offset = &vcpu->kvm->arch.timer_data.poffset;
 	}
 

arch/arm64/kvm/debug.c

···
 void kvm_debug_handle_oslar(struct kvm_vcpu *vcpu, u64 val)
 {
 	if (val & OSLAR_EL1_OSLK)
-		__vcpu_sys_reg(vcpu, OSLSR_EL1) |= OSLSR_EL1_OSLK;
+		__vcpu_rmw_sys_reg(vcpu, OSLSR_EL1, |=, OSLSR_EL1_OSLK);
 	else
-		__vcpu_sys_reg(vcpu, OSLSR_EL1) &= ~OSLSR_EL1_OSLK;
+		__vcpu_rmw_sys_reg(vcpu, OSLSR_EL1, &=, ~OSLSR_EL1_OSLK);
 
 	preempt_disable();
 	kvm_arch_vcpu_put(vcpu);

arch/arm64/kvm/fpsimd.c

···
 		fp_state.sve_state = vcpu->arch.sve_state;
 		fp_state.sve_vl = vcpu->arch.sve_max_vl;
 		fp_state.sme_state = NULL;
-		fp_state.svcr = &__vcpu_sys_reg(vcpu, SVCR);
-		fp_state.fpmr = &__vcpu_sys_reg(vcpu, FPMR);
+		fp_state.svcr = __ctxt_sys_reg(&vcpu->arch.ctxt, SVCR);
+		fp_state.fpmr = __ctxt_sys_reg(&vcpu->arch.ctxt, FPMR);
 		fp_state.fp_type = &vcpu->arch.fp_type;
 
 		if (vcpu_has_sve(vcpu))

arch/arm64/kvm/hyp/exception.c

···
 	if (unlikely(vcpu_has_nv(vcpu)))
 		vcpu_write_sys_reg(vcpu, val, reg);
 	else if (!__vcpu_write_sys_reg_to_cpu(val, reg))
-		__vcpu_sys_reg(vcpu, reg) = val;
+		__vcpu_assign_sys_reg(vcpu, reg, val);
 }
 
 static void __vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long target_mode,
···
 	} else if (has_vhe()) {
 		write_sysreg_el1(val, SYS_SPSR);
 	} else {
-		__vcpu_sys_reg(vcpu, SPSR_EL1) = val;
+		__vcpu_assign_sys_reg(vcpu, SPSR_EL1, val);
 	}
 }
 

arch/arm64/kvm/hyp/include/hyp/switch.h

···
 	if (!vcpu_el1_is_32bit(vcpu))
 		return;
 
-	__vcpu_sys_reg(vcpu, FPEXC32_EL2) = read_sysreg(fpexc32_el2);
+	__vcpu_assign_sys_reg(vcpu, FPEXC32_EL2, read_sysreg(fpexc32_el2));
 }
 
 static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
···
 	 */
 	if (vcpu_has_sve(vcpu)) {
 		zcr_el1 = read_sysreg_el1(SYS_ZCR);
-		__vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)) = zcr_el1;
+		__vcpu_assign_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu), zcr_el1);
 
 		/*
 		 * The guest's state is always saved using the guest's max VL.

arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h

···
 	vcpu->arch.ctxt.spsr_irq = read_sysreg(spsr_irq);
 	vcpu->arch.ctxt.spsr_fiq = read_sysreg(spsr_fiq);
 
-	__vcpu_sys_reg(vcpu, DACR32_EL2) = read_sysreg(dacr32_el2);
-	__vcpu_sys_reg(vcpu, IFSR32_EL2) = read_sysreg(ifsr32_el2);
+	__vcpu_assign_sys_reg(vcpu, DACR32_EL2, read_sysreg(dacr32_el2));
+	__vcpu_assign_sys_reg(vcpu, IFSR32_EL2, read_sysreg(ifsr32_el2));
 
 	if (has_vhe() || kvm_debug_regs_in_use(vcpu))
-		__vcpu_sys_reg(vcpu, DBGVCR32_EL2) = read_sysreg(dbgvcr32_el2);
+		__vcpu_assign_sys_reg(vcpu, DBGVCR32_EL2, read_sysreg(dbgvcr32_el2));
 }
 
 static inline void __sysreg32_restore_state(struct kvm_vcpu *vcpu)

arch/arm64/kvm/hyp/nvhe/hyp-main.c

···
 
 static void __hyp_sve_save_guest(struct kvm_vcpu *vcpu)
 {
-	__vcpu_sys_reg(vcpu, ZCR_EL1) = read_sysreg_el1(SYS_ZCR);
+	__vcpu_assign_sys_reg(vcpu, ZCR_EL1, read_sysreg_el1(SYS_ZCR));
 	/*
 	 * On saving/restoring guest sve state, always use the maximum VL for
 	 * the guest. The layout of the data when saving the sve state depends
···
 
 	has_fpmr = kvm_has_fpmr(kern_hyp_va(vcpu->kvm));
 	if (has_fpmr)
-		__vcpu_sys_reg(vcpu, FPMR) = read_sysreg_s(SYS_FPMR);
+		__vcpu_assign_sys_reg(vcpu, FPMR, read_sysreg_s(SYS_FPMR));
 
 	if (system_supports_sve())
 		__hyp_sve_restore_host();

arch/arm64/kvm/hyp/vhe/switch.c

···
 		 */
 		val = read_sysreg_el0(SYS_CNTP_CVAL);
 		if (map.direct_ptimer == vcpu_ptimer(vcpu))
-			__vcpu_sys_reg(vcpu, CNTP_CVAL_EL0) = val;
+			__vcpu_assign_sys_reg(vcpu, CNTP_CVAL_EL0, val);
 		if (map.direct_ptimer == vcpu_hptimer(vcpu))
-			__vcpu_sys_reg(vcpu, CNTHP_CVAL_EL2) = val;
+			__vcpu_assign_sys_reg(vcpu, CNTHP_CVAL_EL2, val);
 
 		offset = read_sysreg_s(SYS_CNTPOFF_EL2);
 

arch/arm64/kvm/hyp/vhe/sysreg-sr.c

···
 static void __sysreg_save_vel2_state(struct kvm_vcpu *vcpu)
 {
 	/* These registers are common with EL1 */
-	__vcpu_sys_reg(vcpu, PAR_EL1)	= read_sysreg(par_el1);
-	__vcpu_sys_reg(vcpu, TPIDR_EL1)	= read_sysreg(tpidr_el1);
+	__vcpu_assign_sys_reg(vcpu, PAR_EL1,	 read_sysreg(par_el1));
+	__vcpu_assign_sys_reg(vcpu, TPIDR_EL1,	 read_sysreg(tpidr_el1));
 
-	__vcpu_sys_reg(vcpu, ESR_EL2)	= read_sysreg_el1(SYS_ESR);
-	__vcpu_sys_reg(vcpu, AFSR0_EL2)	= read_sysreg_el1(SYS_AFSR0);
-	__vcpu_sys_reg(vcpu, AFSR1_EL2)	= read_sysreg_el1(SYS_AFSR1);
-	__vcpu_sys_reg(vcpu, FAR_EL2)	= read_sysreg_el1(SYS_FAR);
-	__vcpu_sys_reg(vcpu, MAIR_EL2)	= read_sysreg_el1(SYS_MAIR);
-	__vcpu_sys_reg(vcpu, VBAR_EL2)	= read_sysreg_el1(SYS_VBAR);
-	__vcpu_sys_reg(vcpu, CONTEXTIDR_EL2) = read_sysreg_el1(SYS_CONTEXTIDR);
-	__vcpu_sys_reg(vcpu, AMAIR_EL2)	= read_sysreg_el1(SYS_AMAIR);
+	__vcpu_assign_sys_reg(vcpu, ESR_EL2,	 read_sysreg_el1(SYS_ESR));
+	__vcpu_assign_sys_reg(vcpu, AFSR0_EL2,	 read_sysreg_el1(SYS_AFSR0));
+	__vcpu_assign_sys_reg(vcpu, AFSR1_EL2,	 read_sysreg_el1(SYS_AFSR1));
+	__vcpu_assign_sys_reg(vcpu, FAR_EL2,	 read_sysreg_el1(SYS_FAR));
+	__vcpu_assign_sys_reg(vcpu, MAIR_EL2,	 read_sysreg_el1(SYS_MAIR));
+	__vcpu_assign_sys_reg(vcpu, VBAR_EL2,	 read_sysreg_el1(SYS_VBAR));
+	__vcpu_assign_sys_reg(vcpu, CONTEXTIDR_EL2, read_sysreg_el1(SYS_CONTEXTIDR));
+	__vcpu_assign_sys_reg(vcpu, AMAIR_EL2,	 read_sysreg_el1(SYS_AMAIR));
 
 	/*
 	 * In VHE mode those registers are compatible between EL1 and EL2,
···
 		 * are always trapped, ensuring that the in-memory
 		 * copy is always up-to-date. A small blessing...
 		 */
-		__vcpu_sys_reg(vcpu, SCTLR_EL2)	= read_sysreg_el1(SYS_SCTLR);
-		__vcpu_sys_reg(vcpu, TTBR0_EL2)	= read_sysreg_el1(SYS_TTBR0);
-		__vcpu_sys_reg(vcpu, TTBR1_EL2)	= read_sysreg_el1(SYS_TTBR1);
-		__vcpu_sys_reg(vcpu, TCR_EL2)	= read_sysreg_el1(SYS_TCR);
+		__vcpu_assign_sys_reg(vcpu, SCTLR_EL2,	 read_sysreg_el1(SYS_SCTLR));
+		__vcpu_assign_sys_reg(vcpu, TTBR0_EL2,	 read_sysreg_el1(SYS_TTBR0));
+		__vcpu_assign_sys_reg(vcpu, TTBR1_EL2,	 read_sysreg_el1(SYS_TTBR1));
+		__vcpu_assign_sys_reg(vcpu, TCR_EL2,	 read_sysreg_el1(SYS_TCR));
 
 		if (ctxt_has_tcrx(&vcpu->arch.ctxt)) {
-			__vcpu_sys_reg(vcpu, TCR2_EL2) = read_sysreg_el1(SYS_TCR2);
+			__vcpu_assign_sys_reg(vcpu, TCR2_EL2, read_sysreg_el1(SYS_TCR2));
 
 			if (ctxt_has_s1pie(&vcpu->arch.ctxt)) {
-				__vcpu_sys_reg(vcpu, PIRE0_EL2) = read_sysreg_el1(SYS_PIRE0);
-				__vcpu_sys_reg(vcpu, PIR_EL2) = read_sysreg_el1(SYS_PIR);
+				__vcpu_assign_sys_reg(vcpu, PIRE0_EL2, read_sysreg_el1(SYS_PIRE0));
+				__vcpu_assign_sys_reg(vcpu, PIR_EL2, read_sysreg_el1(SYS_PIR));
 			}
 
 			if (ctxt_has_s1poe(&vcpu->arch.ctxt))
-				__vcpu_sys_reg(vcpu, POR_EL2) = read_sysreg_el1(SYS_POR);
+				__vcpu_assign_sys_reg(vcpu, POR_EL2, read_sysreg_el1(SYS_POR));
 		}
 
 		/*
···
 		 */
 		val = read_sysreg_el1(SYS_CNTKCTL);
 		val &= CNTKCTL_VALID_BITS;
-		__vcpu_sys_reg(vcpu, CNTHCTL_EL2) &= ~CNTKCTL_VALID_BITS;
-		__vcpu_sys_reg(vcpu, CNTHCTL_EL2) |= val;
+		__vcpu_rmw_sys_reg(vcpu, CNTHCTL_EL2, &=, ~CNTKCTL_VALID_BITS);
+		__vcpu_rmw_sys_reg(vcpu, CNTHCTL_EL2, |=, val);
 	}
 
-	__vcpu_sys_reg(vcpu, SP_EL2)	= read_sysreg(sp_el1);
-	__vcpu_sys_reg(vcpu, ELR_EL2)	= read_sysreg_el1(SYS_ELR);
-	__vcpu_sys_reg(vcpu, SPSR_EL2)	= read_sysreg_el1(SYS_SPSR);
+	__vcpu_assign_sys_reg(vcpu, SP_EL2,	 read_sysreg(sp_el1));
+	__vcpu_assign_sys_reg(vcpu, ELR_EL2,	 read_sysreg_el1(SYS_ELR));
+	__vcpu_assign_sys_reg(vcpu, SPSR_EL2,	 read_sysreg_el1(SYS_SPSR));
 }
 
 static void __sysreg_restore_vel2_state(struct kvm_vcpu *vcpu)

arch/arm64/kvm/nested.c

···
 
 out:
 	for (enum vcpu_sysreg sr = __SANITISED_REG_START__; sr < NR_SYS_REGS; sr++)
-		(void)__vcpu_sys_reg(vcpu, sr);
+		__vcpu_rmw_sys_reg(vcpu, sr, |=, 0);
 
 	return 0;
 }

arch/arm64/kvm/pmu-emul.c

···
 		val |= lower_32_bits(val);
 	}
 
-	__vcpu_sys_reg(vcpu, reg) = val;
+	__vcpu_assign_sys_reg(vcpu, reg, val);
 
 	/* Recreate the perf event to reflect the updated sample_period */
 	kvm_pmu_create_perf_event(pmc);
···
 void kvm_pmu_set_counter_value_user(struct kvm_vcpu *vcpu, u64 select_idx, u64 val)
 {
 	kvm_pmu_release_perf_event(kvm_vcpu_idx_to_pmc(vcpu, select_idx));
-	__vcpu_sys_reg(vcpu, counter_index_to_reg(select_idx)) = val;
+	__vcpu_assign_sys_reg(vcpu, counter_index_to_reg(select_idx), val);
 	kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu);
 }
 
···
 
 	reg = counter_index_to_reg(pmc->idx);
 
-	__vcpu_sys_reg(vcpu, reg) = val;
+	__vcpu_assign_sys_reg(vcpu, reg, val);
 
 	kvm_pmu_release_perf_event(pmc);
 }
···
 		reg = __vcpu_sys_reg(vcpu, counter_index_to_reg(i)) + 1;
 		if (!kvm_pmc_is_64bit(pmc))
 			reg = lower_32_bits(reg);
-		__vcpu_sys_reg(vcpu, counter_index_to_reg(i)) = reg;
+		__vcpu_assign_sys_reg(vcpu, counter_index_to_reg(i), reg);
 
 		/* No overflow? move on */
 		if (kvm_pmc_has_64bit_overflow(pmc) ? reg : lower_32_bits(reg))
 			continue;
 
 		/* Mark overflow */
-		__vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(i);
+		__vcpu_rmw_sys_reg(vcpu, PMOVSSET_EL0, |=, BIT(i));
 
 		if (kvm_pmu_counter_can_chain(pmc))
 			kvm_pmu_counter_increment(vcpu, BIT(i + 1),
···
 	perf_event->attr.sample_period = period;
 	perf_event->hw.sample_period = period;
 
-	__vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(idx);
+	__vcpu_rmw_sys_reg(vcpu, PMOVSSET_EL0, |=, BIT(idx));
 
 	if (kvm_pmu_counter_can_chain(pmc))
 		kvm_pmu_counter_increment(vcpu, BIT(idx + 1),
···
 		kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu);
 
 	/* The reset bits don't indicate any state, and shouldn't be saved. */
-	__vcpu_sys_reg(vcpu, PMCR_EL0) = val & ~(ARMV8_PMU_PMCR_C | ARMV8_PMU_PMCR_P);
+	__vcpu_assign_sys_reg(vcpu, PMCR_EL0, (val & ~(ARMV8_PMU_PMCR_C | ARMV8_PMU_PMCR_P)));
 
 	if (val & ARMV8_PMU_PMCR_C)
 		kvm_pmu_set_counter_value(vcpu, ARMV8_PMU_CYCLE_IDX, 0);
···
 	u64 reg;
 
 	reg = counter_index_to_evtreg(pmc->idx);
-	__vcpu_sys_reg(vcpu, reg) = data & kvm_pmu_evtyper_mask(vcpu->kvm);
+	__vcpu_assign_sys_reg(vcpu, reg, (data & kvm_pmu_evtyper_mask(vcpu->kvm)));
 
 	kvm_pmu_create_perf_event(pmc);
 }
···
 {
 	u64 mask = kvm_pmu_implemented_counter_mask(vcpu);
 
-	__vcpu_sys_reg(vcpu, PMOVSSET_EL0) &= mask;
-	__vcpu_sys_reg(vcpu, PMINTENSET_EL1) &= mask;
-	__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= mask;
+	__vcpu_rmw_sys_reg(vcpu, PMOVSSET_EL0, &=, mask);
+	__vcpu_rmw_sys_reg(vcpu, PMINTENSET_EL1, &=, mask);
+	__vcpu_rmw_sys_reg(vcpu, PMCNTENSET_EL0, &=, mask);
 
 	kvm_pmu_reprogram_counter_mask(vcpu, mask);
 }
···
 			u64 val = __vcpu_sys_reg(vcpu, MDCR_EL2);
 			val &= ~MDCR_EL2_HPMN;
 			val |= FIELD_PREP(MDCR_EL2_HPMN, kvm->arch.nr_pmu_counters);
-			__vcpu_sys_reg(vcpu, MDCR_EL2) = val;
+			__vcpu_assign_sys_reg(vcpu, MDCR_EL2, val);
 		}
 	}
 }

arch/arm64/kvm/sys_regs.c

···
 		 * to reverse-translate virtual EL2 system registers for a
 		 * non-VHE guest hypervisor.
 		 */
-		__vcpu_sys_reg(vcpu, reg) = val;
+		__vcpu_assign_sys_reg(vcpu, reg, val);
 
 		switch (reg) {
 		case CNTHCTL_EL2:
···
 		return;
 
 memory_write:
-	 __vcpu_sys_reg(vcpu, reg) = val;
+	__vcpu_assign_sys_reg(vcpu, reg, val);
 }
 
 /* CSSELR values; used to index KVM_REG_ARM_DEMUX_ID_CCSIDR */
···
 	if ((val ^ rd->val) & ~OSLSR_EL1_OSLK)
 		return -EINVAL;
 
-	__vcpu_sys_reg(vcpu, rd->reg) = val;
+	__vcpu_assign_sys_reg(vcpu, rd->reg, val);
 	return 0;
 }
 
···
 		mask |= GENMASK(n - 1, 0);
 
 	reset_unknown(vcpu, r);
-	__vcpu_sys_reg(vcpu, r->reg) &= mask;
+	__vcpu_rmw_sys_reg(vcpu, r->reg, &=, mask);
 
 	return __vcpu_sys_reg(vcpu, r->reg);
 }
···
 static u64 reset_pmevcntr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
 	reset_unknown(vcpu, r);
-	__vcpu_sys_reg(vcpu, r->reg) &= GENMASK(31, 0);
+	__vcpu_rmw_sys_reg(vcpu, r->reg, &=, GENMASK(31, 0));
 
 	return __vcpu_sys_reg(vcpu, r->reg);
 }
···
 		return 0;
 
 	reset_unknown(vcpu, r);
-	__vcpu_sys_reg(vcpu, r->reg) &= kvm_pmu_evtyper_mask(vcpu->kvm);
+	__vcpu_rmw_sys_reg(vcpu, r->reg, &=, kvm_pmu_evtyper_mask(vcpu->kvm));
 
 	return __vcpu_sys_reg(vcpu, r->reg);
 }
···
 static u64 reset_pmselr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
 	reset_unknown(vcpu, r);
-	__vcpu_sys_reg(vcpu, r->reg) &= PMSELR_EL0_SEL_MASK;
+	__vcpu_rmw_sys_reg(vcpu, r->reg, &=, PMSELR_EL0_SEL_MASK);
 
 	return __vcpu_sys_reg(vcpu, r->reg);
 }
···
 	 * The value of PMCR.N field is included when the
 	 * vCPU register is read via kvm_vcpu_read_pmcr().
 	 */
-	__vcpu_sys_reg(vcpu, r->reg) = pmcr;
+	__vcpu_assign_sys_reg(vcpu, r->reg, pmcr);
 
 	return __vcpu_sys_reg(vcpu, r->reg);
 }
···
 		return false;
 
 	if (p->is_write)
-		__vcpu_sys_reg(vcpu, PMSELR_EL0) = p->regval;
+		__vcpu_assign_sys_reg(vcpu, PMSELR_EL0, p->regval);
 	else
 		/* return PMSELR.SEL field */
 		p->regval = __vcpu_sys_reg(vcpu, PMSELR_EL0)
···
 {
 	u64 mask = kvm_pmu_accessible_counter_mask(vcpu);
 
-	__vcpu_sys_reg(vcpu, r->reg) = val & mask;
+	__vcpu_assign_sys_reg(vcpu, r->reg, val & mask);
 	kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu);
 
 	return 0;
···
 		val = p->regval & mask;
 		if (r->Op2 & 0x1)
 			/* accessing PMCNTENSET_EL0 */
-			__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) |= val;
+			__vcpu_rmw_sys_reg(vcpu, PMCNTENSET_EL0, |=, val);
 		else
 			/* accessing PMCNTENCLR_EL0 */
-			__vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= ~val;
+			__vcpu_rmw_sys_reg(vcpu, PMCNTENSET_EL0, &=, ~val);
 
 		kvm_pmu_reprogram_counter_mask(vcpu, val);
 	} else {
···
 
 		if (r->Op2 & 0x1)
 			/* accessing PMINTENSET_EL1 */
-			__vcpu_sys_reg(vcpu, PMINTENSET_EL1) |= val;
+			__vcpu_rmw_sys_reg(vcpu, PMINTENSET_EL1, |=, val);
 		else
 			/* accessing PMINTENCLR_EL1 */
-			__vcpu_sys_reg(vcpu, PMINTENSET_EL1) &= ~val;
+			__vcpu_rmw_sys_reg(vcpu, PMINTENSET_EL1, &=, ~val);
 	} else {
 		p->regval = __vcpu_sys_reg(vcpu, PMINTENSET_EL1);
 	}
···
 	if (p->is_write) {
 		if (r->CRm & 0x2)
 			/* accessing PMOVSSET_EL0 */
-			__vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= (p->regval & mask);
+			__vcpu_rmw_sys_reg(vcpu, PMOVSSET_EL0, |=, (p->regval & mask));
 		else
 			/* accessing PMOVSCLR_EL0 */
-			__vcpu_sys_reg(vcpu, PMOVSSET_EL0) &= ~(p->regval & mask);
+			__vcpu_rmw_sys_reg(vcpu, PMOVSSET_EL0, &=, ~(p->regval & mask));
 	} else {
 		p->regval = __vcpu_sys_reg(vcpu, PMOVSSET_EL0);
 	}
···
 		if (!vcpu_mode_priv(vcpu))
 			return undef_access(vcpu, p, r);
 
-		__vcpu_sys_reg(vcpu, PMUSERENR_EL0) =
-			       p->regval & ARMV8_PMU_USERENR_MASK;
+		__vcpu_assign_sys_reg(vcpu, PMUSERENR_EL0,
+				      (p->regval & ARMV8_PMU_USERENR_MASK));
 	} else {
 		p->regval = __vcpu_sys_reg(vcpu, PMUSERENR_EL0)
 			    & ARMV8_PMU_USERENR_MASK;
···
 	if (!kvm_supports_32bit_el0())
 		val |= ARMV8_PMU_PMCR_LC;
 
-	__vcpu_sys_reg(vcpu, r->reg) = val;
+	__vcpu_assign_sys_reg(vcpu, r->reg, val);
 	kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu);
 
 	return 0;
···
 	if (kvm_has_mte(vcpu->kvm))
 		clidr |= 2ULL << CLIDR_TTYPE_SHIFT(loc);
 
-	__vcpu_sys_reg(vcpu, r->reg) = clidr;
+	__vcpu_assign_sys_reg(vcpu, r->reg, clidr);
 
 	return __vcpu_sys_reg(vcpu, r->reg);
 }
···
 	if ((val & CLIDR_EL1_RES0) || (!(ctr_el0 & CTR_EL0_IDC) && idc))
 		return -EINVAL;
 
-	__vcpu_sys_reg(vcpu, rd->reg) = val;
+	__vcpu_assign_sys_reg(vcpu, rd->reg, val);
 
 	return 0;
 }
···
 			  const struct sys_reg_desc *r)
 {
 	if (p->is_write)
-		__vcpu_sys_reg(vcpu, SP_EL1) = p->regval;
+		__vcpu_assign_sys_reg(vcpu, SP_EL1, p->regval);
 	else
 		p->regval = __vcpu_sys_reg(vcpu, SP_EL1);
 
···
 			const struct sys_reg_desc *r)
 {
 	if (p->is_write)
-		__vcpu_sys_reg(vcpu, SPSR_EL1) = p->regval;
+		__vcpu_assign_sys_reg(vcpu, SPSR_EL1, p->regval);
 	else
 		p->regval = __vcpu_sys_reg(vcpu, SPSR_EL1);
 
···
 				const struct sys_reg_desc *r)
 {
 	if (p->is_write)
-		__vcpu_sys_reg(vcpu, CNTKCTL_EL1) = p->regval;
+		__vcpu_assign_sys_reg(vcpu, CNTKCTL_EL1, p->regval);
 	else
 		p->regval = __vcpu_sys_reg(vcpu, CNTKCTL_EL1);
 
···
 	if (!cpus_have_final_cap(ARM64_HAS_HCR_NV1))
 		val |= HCR_E2H;
 
-	return __vcpu_sys_reg(vcpu, r->reg) = val;
+	__vcpu_assign_sys_reg(vcpu, r->reg, val);
+
+	return __vcpu_sys_reg(vcpu, r->reg);
 }
 
 static unsigned int __el2_visibility(const struct kvm_vcpu *vcpu,
···
 		u64_replace_bits(val, hpmn, MDCR_EL2_HPMN);
 	}
 
-	__vcpu_sys_reg(vcpu, MDCR_EL2) = val;
+	__vcpu_assign_sys_reg(vcpu, MDCR_EL2, val);
 
 	/*
 	 * Request a reload of the PMU to enable/disable the counters
···
 
 static u64 reset_mdcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
-	__vcpu_sys_reg(vcpu, r->reg) = vcpu->kvm->arch.nr_pmu_counters;
+	__vcpu_assign_sys_reg(vcpu, r->reg, vcpu->kvm->arch.nr_pmu_counters);
 	return vcpu->kvm->arch.nr_pmu_counters;
 }
 
···
 			r->reset(vcpu, r);
 
 		if (r->reg >= __SANITISED_REG_START__ && r->reg < NR_SYS_REGS)
-			(void)__vcpu_sys_reg(vcpu, r->reg);
+			__vcpu_rmw_sys_reg(vcpu, r->reg, |=, 0);
 	}
 
 	set_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &kvm->arch.flags);
···
 	if (r->set_user) {
 		ret = (r->set_user)(vcpu, r, val);
 	} else {
-		__vcpu_sys_reg(vcpu, r->reg) = val;
+		__vcpu_assign_sys_reg(vcpu, r->reg, val);
 		ret = 0;
 	}
 

arch/arm64/kvm/sys_regs.h

···
 {
 	BUG_ON(!r->reg);
 	BUG_ON(r->reg >= NR_SYS_REGS);
-	__vcpu_sys_reg(vcpu, r->reg) = 0x1de7ec7edbadc0deULL;
+	__vcpu_assign_sys_reg(vcpu, r->reg, 0x1de7ec7edbadc0deULL);
 	return __vcpu_sys_reg(vcpu, r->reg);
 }
 
···
 {
 	BUG_ON(!r->reg);
 	BUG_ON(r->reg >= NR_SYS_REGS);
-	__vcpu_sys_reg(vcpu, r->reg) = r->val;
+	__vcpu_assign_sys_reg(vcpu, r->reg, r->val);
 	return __vcpu_sys_reg(vcpu, r->reg);
 }
 

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

···
 	val = __vcpu_sys_reg(vcpu, ICH_HCR_EL2);
 	val &= ~ICH_HCR_EL2_EOIcount_MASK;
 	val |= (s_cpu_if->vgic_hcr & ICH_HCR_EL2_EOIcount_MASK);
-	__vcpu_sys_reg(vcpu, ICH_HCR_EL2) = val;
-	__vcpu_sys_reg(vcpu, ICH_VMCR_EL2) = s_cpu_if->vgic_vmcr;
+	__vcpu_assign_sys_reg(vcpu, ICH_HCR_EL2, val);
+	__vcpu_assign_sys_reg(vcpu, ICH_VMCR_EL2, s_cpu_if->vgic_vmcr);
 
 	for (i = 0; i < 4; i++) {
-		__vcpu_sys_reg(vcpu, ICH_AP0RN(i)) = s_cpu_if->vgic_ap0r[i];
-		__vcpu_sys_reg(vcpu, ICH_AP1RN(i)) = s_cpu_if->vgic_ap1r[i];
+		__vcpu_assign_sys_reg(vcpu, ICH_AP0RN(i), s_cpu_if->vgic_ap0r[i]);
+		__vcpu_assign_sys_reg(vcpu, ICH_AP1RN(i), s_cpu_if->vgic_ap1r[i]);
 	}
 
 	for_each_set_bit(i, &shadow_if->lr_map, kvm_vgic_global_state.nr_lr) {
···
 		val &= ~ICH_LR_STATE;
 		val |= s_cpu_if->vgic_lr[i] & ICH_LR_STATE;
 
-		__vcpu_sys_reg(vcpu, ICH_LRN(i)) = val;
+		__vcpu_assign_sys_reg(vcpu, ICH_LRN(i), val);
 		s_cpu_if->vgic_lr[i] = 0;
 	}
 

arch/arm64/lib/crypto/poly1305-glue.c

···
 			unsigned int todo = min_t(unsigned int, len, SZ_4K);
 
 			kernel_neon_begin();
-			poly1305_blocks_neon(state, src, todo, 1);
+			poly1305_blocks_neon(state, src, todo, padbit);
 			kernel_neon_end();
 
 			len -= todo;
 			src += todo;
 		} while (len);
 	} else
-		poly1305_blocks(state, src, len, 1);
+		poly1305_blocks(state, src, len, padbit);
 }
 EXPORT_SYMBOL_GPL(poly1305_blocks_arch);
 

arch/powerpc/boot/dts/microwatt.dts

···
 / {
 	#size-cells = <0x02>;
 	#address-cells = <0x02>;
-	model-name = "microwatt";
+	model = "microwatt";
 	compatible = "microwatt-soc";
 
 	aliases {

arch/powerpc/boot/dts/mpc8315erdb.dts

···
  */
 
 /dts-v1/;
+#include <dt-bindings/interrupt-controller/irq.h>
 
 / {
 	compatible = "fsl,mpc8315erdb";
···
 			interrupts = <80 8>;
 			interrupt-parent = <&ipic>;
 			fsl,mpc8313-wakeup-timer = <&gtm1>;
+		};
+
+		gpio: gpio-controller@c00 {
+			compatible = "fsl,mpc8314-gpio";
+			reg = <0xc00 0x100>;
+			interrupts = <74 IRQ_TYPE_LEVEL_LOW>;
+			interrupt-parent = <&ipic>;
+			gpio-controller;
+			#gpio-cells = <2>;
 		};
 	};
 

arch/powerpc/include/asm/ppc_asm.h

···
 /*
  * Used to name C functions called from asm
  */
-#ifdef CONFIG_PPC_KERNEL_PCREL
+#if defined(__powerpc64__) && defined(CONFIG_PPC_KERNEL_PCREL)
 #define CFUNC(name) name@notoc
 #else
 #define CFUNC(name) name

arch/powerpc/include/uapi/asm/ioctls.h

···
 #define TCSETSW		_IOW('t', 21, struct termios)
 #define TCSETSF		_IOW('t', 22, struct termios)
 
-#define TCGETA		_IOR('t', 23, struct termio)
-#define TCSETA		_IOW('t', 24, struct termio)
-#define TCSETAW		_IOW('t', 25, struct termio)
-#define TCSETAF		_IOW('t', 28, struct termio)
+#define TCGETA		0x40147417 /* _IOR('t', 23, struct termio) */
+#define TCSETA		0x80147418 /* _IOW('t', 24, struct termio) */
+#define TCSETAW		0x80147419 /* _IOW('t', 25, struct termio) */
+#define TCSETAF		0x8014741c /* _IOW('t', 28, struct termio) */
 
 #define TCSBRK		_IO('t', 29)
 #define TCXONC		_IO('t', 30)

arch/powerpc/kernel/eeh.c

···
 	/* Invalid PE ? */
 	if (!pe)
 		return -ENODEV;
+	else
+		ret = eeh_ops->configure_bridge(pe);
 
 	return ret;
 }

arch/powerpc/kernel/vdso/Makefile

···
 ldflags-y += $(filter-out $(CC_AUTO_VAR_INIT_ZERO_ENABLER) $(CC_FLAGS_FTRACE) -Wa$(comma)%, $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS))
 
 CC32FLAGS := -m32
-CC32FLAGSREMOVE := -mcmodel=medium -mabi=elfv1 -mabi=elfv2 -mcall-aixdesc
+CC32FLAGSREMOVE := -mcmodel=medium -mabi=elfv1 -mabi=elfv2 -mcall-aixdesc -mpcrel
 ifdef CONFIG_CC_IS_CLANG
 # This flag is supported by clang for 64-bit but not 32-bit so it will cause
 # an unused command line flag warning for this file.

arch/x86/Kconfig

···
 	select ARCH_HAS_DMA_OPS			if GART_IOMMU || XEN
 	select ARCH_HAS_EARLY_DEBUG		if KGDB
 	select ARCH_HAS_ELF_RANDOMIZE
-	select ARCH_HAS_EXECMEM_ROX		if X86_64
+	select ARCH_HAS_EXECMEM_ROX		if X86_64 && STRICT_MODULE_RWX
 	select ARCH_HAS_FAST_MULTIPLIER
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL

arch/x86/include/asm/module.h

···
 #include <asm-generic/module.h>
 #include <asm/orc_types.h>
 
+struct its_array {
+#ifdef CONFIG_MITIGATION_ITS
+	void **pages;
+	int num;
+#endif
+};
+
 struct mod_arch_specific {
 #ifdef CONFIG_UNWINDER_ORC
 	unsigned int num_orcs;
 	int *orc_unwind_ip;
 	struct orc_entry *orc_unwind;
 #endif
+	struct its_array its_pages;
 };
 
 #endif /* _ASM_X86_MODULE_H */

arch/x86/include/asm/sighandling.h

···
 int x64_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs);
 int x32_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs);
 
+/*
+ * To prevent immediate repeat of single step trap on return from SIGTRAP
+ * handler if the trap flag (TF) is set without an external debugger attached,
+ * clear the software event flag in the augmented SS, ensuring no single-step
+ * trap is pending upon ERETU completion.
+ *
+ * Note, this function should be called in sigreturn() before the original
+ * state is restored to make sure the TF is read from the entry frame.
+ */
+static __always_inline void prevent_single_step_upon_eretu(struct pt_regs *regs)
+{
+	/*
+	 * If the trap flag (TF) is set, i.e., the sigreturn() SYSCALL instruction
+	 * is being single-stepped, do not clear the software event flag in the
+	 * augmented SS, thus a debugger won't skip over the following instruction.
+	 */
+#ifdef CONFIG_X86_FRED
+	if (!(regs->flags & X86_EFLAGS_TF))
+		regs->fred_ss.swevent = 0;
+#endif
+}
+
 #endif /* _ASM_X86_SIGHANDLING_H */

arch/x86/include/asm/tdx.h

···
 
 typedef u64 (*sc_func_t)(u64 fn, struct tdx_module_args *args);
 
-static inline u64 sc_retry(sc_func_t func, u64 fn,
+static __always_inline u64 sc_retry(sc_func_t func, u64 fn,
 			   struct tdx_module_args *args)
 {
 	int retry = RDRAND_RETRY_LOOPS;

arch/x86/kernel/alternative.c

···
 #endif
 static void *its_page;
 static unsigned int its_offset;
+struct its_array its_pages;
+
+static void *__its_alloc(struct its_array *pages)
+{
+	void *page __free(execmem) = execmem_alloc(EXECMEM_MODULE_TEXT, PAGE_SIZE);
+	if (!page)
+		return NULL;
+
+	void *tmp = krealloc(pages->pages, (pages->num+1) * sizeof(void *),
+			     GFP_KERNEL);
+	if (!tmp)
+		return NULL;
+
+	pages->pages = tmp;
+	pages->pages[pages->num++] = page;
+
+	return no_free_ptr(page);
+}
 
 /* Initialize a thunk with the "jmp *reg; int3" instructions. */
 static void *its_init_thunk(void *thunk, int reg)
···
 	return thunk + offset;
 }
 
+static void its_pages_protect(struct its_array *pages)
+{
+	for (int i = 0; i < pages->num; i++) {
+		void *page = pages->pages[i];
+		execmem_restore_rox(page, PAGE_SIZE);
+	}
+}
+
+static void its_fini_core(void)
+{
+	if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX))
+		its_pages_protect(&its_pages);
+	kfree(its_pages.pages);
+}
+
 #ifdef CONFIG_MODULES
 void its_init_mod(struct module *mod)
 {
···
 	its_page = NULL;
 	mutex_unlock(&text_mutex);
 
-	for (int i = 0; i < mod->its_num_pages; i++) {
-		void *page = mod->its_page_array[i];
-		execmem_restore_rox(page, PAGE_SIZE);
-	}
+	if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
+		its_pages_protect(&mod->arch.its_pages);
 }
 
 void its_free_mod(struct module *mod)
···
 	if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS))
 		return;
 
-	for (int i = 0; i < mod->its_num_pages; i++) {
-		void *page = mod->its_page_array[i];
+	for (int i = 0; i < mod->arch.its_pages.num; i++) {
+		void *page = mod->arch.its_pages.pages[i];
 		execmem_free(page);
 	}
-	kfree(mod->its_page_array);
+	kfree(mod->arch.its_pages.pages);
 }
 #endif /* CONFIG_MODULES */
 
 static void *its_alloc(void)
 {
-	void *page __free(execmem) = execmem_alloc(EXECMEM_MODULE_TEXT, PAGE_SIZE);
+	struct its_array *pages = &its_pages;
+	void *page;
 
+#ifdef CONFIG_MODULE
+	if (its_mod)
+		pages = &its_mod->arch.its_pages;
+#endif
+
+	page = __its_alloc(pages);
 	if (!page)
 		return NULL;
 
-#ifdef CONFIG_MODULES
-	if (its_mod) {
-		void *tmp = krealloc(its_mod->its_page_array,
-				     (its_mod->its_num_pages+1) * sizeof(void *),
-				     GFP_KERNEL);
-		if (!tmp)
-			return NULL;
+	execmem_make_temp_rw(page, PAGE_SIZE);
+	if (pages == &its_pages)
+		set_memory_x((unsigned long)page, 1);
 
-		its_mod->its_page_array = tmp;
-		its_mod->its_page_array[its_mod->its_num_pages++] = page;
-
-		execmem_make_temp_rw(page, PAGE_SIZE);
-	}
-#endif /* CONFIG_MODULES */
-
-	return no_free_ptr(page);
+	return page;
 }
 
 static void *its_allocate_thunk(int reg)
···
 	return thunk;
 }
 
-#endif
+#else
+static inline void its_fini_core(void) {}
+#endif /* CONFIG_MITIGATION_ITS */
 
 /*
  * Nomenclature for variable names to simplify and clarify this code and ease
···
 	 */
 	apply_retpolines(__retpoline_sites, __retpoline_sites_end);
 	apply_returns(__return_sites, __return_sites_end);
+
+	its_fini_core();
 
 	/*
 	 * Adjust all CALL instructions to point to func()-10, including

arch/x86/kernel/signal_32.c

···
 	struct sigframe_ia32 __user *frame = (struct sigframe_ia32 __user *)(regs->sp-8);
 	sigset_t set;
 
+	prevent_single_step_upon_eretu(regs);
+
 	if (!access_ok(frame, sizeof(*frame)))
 		goto badframe;
 	if (__get_user(set.sig[0], &frame->sc.oldmask)
···
 	struct pt_regs *regs = current_pt_regs();
 	struct rt_sigframe_ia32 __user *frame;
 	sigset_t set;
+
+	prevent_single_step_upon_eretu(regs);
 
 	frame = (struct rt_sigframe_ia32 __user *)(regs->sp - 4);
 

arch/x86/kernel/signal_64.c

···
 	sigset_t set;
 	unsigned long uc_flags;
 
+	prevent_single_step_upon_eretu(regs);
+
 	frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long));
 	if (!access_ok(frame, sizeof(*frame)))
 		goto badframe;
···
 	struct rt_sigframe_x32 __user *frame;
 	sigset_t set;
 	unsigned long uc_flags;
+
+	prevent_single_step_upon_eretu(regs);
 
 	frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8);
 

arch/x86/kernel/smp.c

···
 	.send_call_func_single_ipi = native_send_call_func_single_ipi,
 };
 EXPORT_SYMBOL_GPL(smp_ops);
+
+int arch_cpu_rescan_dead_smt_siblings(void)
+{
+	enum cpuhp_smt_control old = cpu_smt_control;
+	int ret;
+
+	/*
+	 * If SMT has been disabled and SMT siblings are in HLT, bring them back
+	 * online and offline them again so that they end up in MWAIT proper.
+	 *
+	 * Called with hotplug enabled.
+	 */
+	if (old != CPU_SMT_DISABLED && old != CPU_SMT_FORCE_DISABLED)
+		return 0;
+
+	ret = cpuhp_smt_enable();
+	if (ret)
+		return ret;
+
+	ret = cpuhp_smt_disable(old);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(arch_cpu_rescan_dead_smt_siblings);

arch/x86/kernel/smpboot.c

···
 	local_irq_disable();
 }
 
+/*
+ * We need to flush the caches before going to sleep, lest we have
+ * dirty data in our caches when we come back up.
+ */
 void __noreturn mwait_play_dead(unsigned int eax_hint)
 {
 	struct mwait_cpu_dead *md = this_cpu_ptr(&mwait_cpu_dead);
···
 				native_halt();
 		}
 	}
-}
-
-/*
- * We need to flush the caches before going to sleep, lest we have
- * dirty data in our caches when we come back up.
- */
-static inline void mwait_play_dead_cpuid_hint(void)
-{
-	unsigned int eax, ebx, ecx, edx;
-	unsigned int highest_cstate = 0;
-	unsigned int highest_subcstate = 0;
-	int i;
-
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
-	    boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
-		return;
-	if (!this_cpu_has(X86_FEATURE_MWAIT))
-		return;
-	if (!this_cpu_has(X86_FEATURE_CLFLUSH))
-		return;
-
-	eax = CPUID_LEAF_MWAIT;
-	ecx = 0;
-	native_cpuid(&eax, &ebx, &ecx, &edx);
-
-	/*
-	 * eax will be 0 if EDX enumeration is not valid.
-	 * Initialized below to cstate, sub_cstate value when EDX is valid.
-	 */
-	if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED)) {
-		eax = 0;
-	} else {
-		edx >>= MWAIT_SUBSTATE_SIZE;
-		for (i = 0; i < 7 && edx; i++, edx >>= MWAIT_SUBSTATE_SIZE) {
-			if (edx & MWAIT_SUBSTATE_MASK) {
-				highest_cstate = i;
-				highest_subcstate = edx & MWAIT_SUBSTATE_MASK;
-			}
-		}
-		eax = (highest_cstate << MWAIT_SUBSTATE_SIZE) |
-			(highest_subcstate - 1);
-	}
-
-	mwait_play_dead(eax);
 }
 
 /*
···
 	play_dead_common();
 	tboot_shutdown(TB_SHUTDOWN_WFS);
 
-	mwait_play_dead_cpuid_hint();
-	if (cpuidle_play_dead())
-		hlt_play_dead();
+	/* Below returns only on error. */
+	cpuidle_play_dead();
+	hlt_play_dead();
 }
 
 #else /* ... !CONFIG_HOTPLUG_CPU */

arch/x86/kvm/mmu/mmu.c

···
 {
 	u64 error_code = PFERR_GUEST_FINAL_MASK;
 	u8 level = PG_LEVEL_4K;
+	u64 direct_bits;
 	u64 end;
 	int r;
 
 	if (!vcpu->kvm->arch.pre_fault_allowed)
 		return -EOPNOTSUPP;
+
+	if (kvm_is_gfn_alias(vcpu->kvm, gpa_to_gfn(range->gpa)))
+		return -EINVAL;
 
 	/*
 	 * reload is efficient when called repeatedly, so we can do it on
···
 	if (r)
 		return r;
 
+	direct_bits = 0;
 	if (kvm_arch_has_private_mem(vcpu->kvm) &&
 	    kvm_mem_is_private(vcpu->kvm, gpa_to_gfn(range->gpa)))
 		error_code |= PFERR_PRIVATE_ACCESS;
+	else
+		direct_bits = gfn_to_gpa(kvm_gfn_direct_bits(vcpu->kvm));
 
 	/*
 	 * Shadow paging uses GVA for kvm page fault, so restrict to
 	 * two-dimensional paging.
 	 */
-	r = kvm_tdp_map_page(vcpu, range->gpa, error_code, &level);
+	r = kvm_tdp_map_page(vcpu, range->gpa | direct_bits, error_code, &level);
 	if (r < 0)
 		return r;
 

arch/x86/kvm/svm/sev.c

···
 	}
 }
 
+static bool is_sev_snp_initialized(void)
+{
+	struct sev_user_data_snp_status *status;
+	struct sev_data_snp_addr buf;
+	bool initialized = false;
+	int ret, error = 0;
+
+	status = snp_alloc_firmware_page(GFP_KERNEL | __GFP_ZERO);
+	if (!status)
+		return false;
+
+	buf.address = __psp_pa(status);
+	ret = sev_do_cmd(SEV_CMD_SNP_PLATFORM_STATUS, &buf, &error);
+	if (ret) {
+		pr_err("SEV: SNP_PLATFORM_STATUS failed ret=%d, fw_error=%d (%#x)\n",
+		       ret, error, error);
+		goto out;
+	}
+
+	initialized = !!status->state;
+
+out:
+	snp_free_firmware_page(status);
+
+	return initialized;
+}
+
 void __init sev_hardware_setup(void)
 {
 	unsigned int eax, ebx, ecx, edx, sev_asid_count, sev_es_asid_count;
···
 	sev_snp_supported = sev_snp_enabled && cc_platform_has(CC_ATTR_HOST_SEV_SNP);
 
 out:
+	if (sev_enabled) {
+		init_args.probe = true;
+		if (sev_platform_init(&init_args))
+			sev_supported = sev_es_supported = sev_snp_supported = false;
+		else if (sev_snp_supported)
+			sev_snp_supported = is_sev_snp_initialized();
+	}
+
 	if (boot_cpu_has(X86_FEATURE_SEV))
 		pr_info("SEV %s (ASIDs %u - %u)\n",
 			sev_supported ? min_sev_asid <= max_sev_asid ? "enabled" :
···
 	sev_supported_vmsa_features = 0;
 	if (sev_es_debug_swap_enabled)
 		sev_supported_vmsa_features |= SVM_SEV_FEAT_DEBUG_SWAP;
-
-	if (!sev_enabled)
-		return;
-
-	/*
-	 * Do both SNP and SEV initialization at KVM module load.
-	 */
-	init_args.probe = true;
-	sev_platform_init(&init_args);
 }
 
 void sev_hardware_unsetup(void)

arch/x86/mm/init_32.c

···
 #include <linux/initrd.h>
 #include <linux/cpumask.h>
 #include <linux/gfp.h>
-#include <linux/execmem.h>
 
 #include <asm/asm.h>
 #include <asm/bios_ebda.h>
···
 	set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
 	pr_info("Write protecting kernel text and read-only data: %luk\n",
 		size >> 10);
-
-	execmem_cache_make_ro();
 
 	kernel_set_to_readonly = 1;
 

arch/x86/mm/init_64.c

···
 #include <linux/gfp.h>
 #include <linux/kcore.h>
 #include <linux/bootmem_info.h>
-#include <linux/execmem.h>
 
 #include <asm/processor.h>
 #include <asm/bios_ebda.h>
···
 	printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
 	       (end - start) >> 10);
 	set_memory_ro(start, (end - start) >> PAGE_SHIFT);
-
-	execmem_cache_make_ro();
 
 	kernel_set_to_readonly = 1;
 

arch/x86/mm/pat/set_memory.c

···
 	pgprot_t pgprot;
 	int i = 0;
 
+	if (!cpu_feature_enabled(X86_FEATURE_PSE))
+		return 0;
+
 	addr &= PMD_MASK;
 	pte = pte_offset_kernel(pmd, addr);
 	first = *pte;

arch/x86/power/hibernate.c

···
 
 int arch_resume_nosmt(void)
 {
-	int ret = 0;
+	int ret;
+
 	/*
 	 * We reached this while coming out of hibernation. This means
 	 * that SMT siblings are sleeping in hlt, as mwait is not safe
···
 	 * Called with hotplug disabled.
 	 */
 	cpu_hotplug_enable();
-	if (cpu_smt_control == CPU_SMT_DISABLED ||
-			cpu_smt_control == CPU_SMT_FORCE_DISABLED) {
-		enum cpuhp_smt_control old = cpu_smt_control;
 
-		ret = cpuhp_smt_enable();
-		if (ret)
-			goto out;
-		ret = cpuhp_smt_disable(old);
-		if (ret)
-			goto out;
-	}
-out:
+	ret = arch_cpu_rescan_dead_smt_siblings();
+
 	cpu_hotplug_disable();
+
 	return ret;
 }

arch/x86/virt/vmx/tdx/tdx.c

···
 			args->r9, args->r10, args->r11);
 }
 
-static inline int sc_retry_prerr(sc_func_t func, sc_err_func_t err_func,
-				 u64 fn, struct tdx_module_args *args)
+static __always_inline int sc_retry_prerr(sc_func_t func,
+					  sc_err_func_t err_func,
+					  u64 fn, struct tdx_module_args *args)
 {
 	u64 sret = sc_retry(func, fn, args);
 

block/blk-merge.c

···
 	if (!plug || rq_list_empty(&plug->mq_list))
 		return false;
 
-	rq_list_for_each(&plug->mq_list, rq) {
-		if (rq->q == q) {
-			if (blk_attempt_bio_merge(q, rq, bio, nr_segs, false) ==
-			    BIO_MERGE_OK)
-				return true;
-			break;
-		}
+	rq = plug->mq_list.tail;
+	if (rq->q == q)
+		return blk_attempt_bio_merge(q, rq, bio, nr_segs, false) ==
+			BIO_MERGE_OK;
+	else if (!plug->multiple_queues)
+		return false;
 
-		/*
-		 * Only keep iterating plug list for merges if we have multiple
-		 * queues
-		 */
-		if (!plug->multiple_queues)
-			break;
+	rq_list_for_each(&plug->mq_list, rq) {
+		if (rq->q != q)
+			continue;
+		if (blk_attempt_bio_merge(q, rq, bio, nr_segs, false) ==
+		    BIO_MERGE_OK)
+			return true;
+		break;
 	}
 	return false;
 }

block/blk-zoned.c

···
 	if (bio_flagged(bio, BIO_EMULATES_ZONE_APPEND)) {
 		bio->bi_opf &= ~REQ_OP_MASK;
 		bio->bi_opf |= REQ_OP_ZONE_APPEND;
+		bio_clear_flag(bio, BIO_EMULATES_ZONE_APPEND);
 	}
 
 	/*
···
 	spin_unlock_irqrestore(&zwplug->lock, flags);
 
 	bdev = bio->bi_bdev;
-	submit_bio_noacct_nocheck(bio);
 
 	/*
 	 * blk-mq devices will reuse the extra reference on the request queue
···
 	 * path for BIO-based devices will not do that. So drop this extra
 	 * reference here.
 	 */
-	if (bdev_test_flag(bdev, BD_HAS_SUBMIT_BIO))
+	if (bdev_test_flag(bdev, BD_HAS_SUBMIT_BIO)) {
+		bdev->bd_disk->fops->submit_bio(bio);
 		blk_queue_exit(bdev->bd_disk->queue);
+	} else {
+		blk_mq_submit_bio(bio);
+	}
 
 put_zwplug:
 	/* Drop the reference we took in disk_zone_wplug_schedule_bio_work(). */

crypto/hkdf.c

···
 
 static void __exit crypto_hkdf_module_exit(void) {}
 
-module_init(crypto_hkdf_module_init);
+late_initcall(crypto_hkdf_module_init);
 module_exit(crypto_hkdf_module_exit);
 
 MODULE_LICENSE("GPL");

drivers/accel/amdxdna/aie2_psp.c

···
 	psp->ddev = ddev;
 	memcpy(psp->psp_regs, conf->psp_regs, sizeof(psp->psp_regs));
 
-	psp->fw_buf_sz = ALIGN(conf->fw_size, PSP_FW_ALIGN) + PSP_FW_ALIGN;
-	psp->fw_buffer = drmm_kmalloc(ddev, psp->fw_buf_sz, GFP_KERNEL);
+	psp->fw_buf_sz = ALIGN(conf->fw_size, PSP_FW_ALIGN);
+	psp->fw_buffer = drmm_kmalloc(ddev, psp->fw_buf_sz + PSP_FW_ALIGN, GFP_KERNEL);
 	if (!psp->fw_buffer) {
 		drm_err(ddev, "no memory for fw buffer");
 		return NULL;

drivers/acpi/acpi_pad.c

···
 static DEFINE_MUTEX(isolated_cpus_lock);
 static DEFINE_MUTEX(round_robin_lock);
 
-static unsigned long power_saving_mwait_eax;
+static unsigned int power_saving_mwait_eax;
 
 static unsigned char tsc_detected_unstable;
 static unsigned char tsc_marked_unstable;

drivers/acpi/apei/einj-core.c

···
 	}
 
 	einj_dev = faux_device_create("acpi-einj", NULL, &einj_device_ops);
-	if (!einj_dev)
-		return -ENODEV;
 
-	einj_initialized = true;
+	if (einj_dev)
+		einj_initialized = true;
 
 	return 0;
 }
 
 static void __exit einj_exit(void)
 {
-	if (einj_initialized)
-		faux_device_destroy(einj_dev);
-
+	faux_device_destroy(einj_dev);
 }
 
 module_init(einj_init);

drivers/acpi/cppc_acpi.c

···
 	struct cpc_desc *cpc_ptr;
 	int cpu;
 
-	for_each_possible_cpu(cpu) {
+	for_each_present_cpu(cpu) {
 		cpc_ptr = per_cpu(cpc_desc_ptr, cpu);
 		desired_reg = &cpc_ptr->cpc_regs[DESIRED_PERF];
 		if (!CPC_IN_SYSTEM_MEMORY(desired_reg) &&

drivers/acpi/ec.c

···
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/list.h>
+#include <linux/printk.h>
 #include <linux/spinlock.h>
 #include <linux/slab.h>
+#include <linux/string.h>
 #include <linux/suspend.h>
 #include <linux/acpi.h>
 #include <linux/dmi.h>
···
 		 * Asus X50GL:
 		 * https://bugzilla.kernel.org/show_bug.cgi?id=11880
 		 */
+		goto out;
+	}
+
+	if (!strstarts(ecdt_ptr->id, "\\")) {
+		/*
+		 * The ECDT table on some MSI notebooks contains invalid data, together
+		 * with an empty ID string ("").
+		 *
+		 * Section 5.2.15 of the ACPI specification requires the ID string to be
+		 * a "fully qualified reference to the (...) embedded controller device",
+		 * so this string always has to start with a backslash.
+		 *
+		 * By verifying this we can avoid such faulty ECDT tables in a safe way.
+		 */
+		pr_err(FW_BUG "Ignoring ECDT due to invalid ID string \"%s\"\n", ecdt_ptr->id);
 		goto out;
 	}
 

drivers/acpi/internal.h

···
 static inline void acpi_early_processor_control_setup(void) {}
 #endif
 
+#ifdef CONFIG_ACPI_PROCESSOR_CSTATE
+void acpi_idle_rescan_dead_smt_siblings(void);
+#else
+static inline void acpi_idle_rescan_dead_smt_siblings(void) {}
+#endif
+
 /* --------------------------------------------------------------------------
                                   Embedded Controller
    -------------------------------------------------------------------------- */

drivers/acpi/processor_driver.c

···
 	 * after acpi_cppc_processor_probe() has been called for all online CPUs
 	 */
 	acpi_processor_init_invariance_cppc();
+
+	acpi_idle_rescan_dead_smt_siblings();
+
 	return 0;
 err:
 	driver_unregister(&acpi_processor_driver);

drivers/acpi/processor_idle.c

···
 #include <acpi/processor.h>
 #include <linux/context_tracking.h>
 
+#include "internal.h"
+
 /*
  * Include the apic definitions for x86 to have the APIC timer related defines
  * available also for UP (on SMP it gets magically included via linux/smp.h).
···
 };
 
 #ifdef CONFIG_ACPI_PROCESSOR_CSTATE
+void acpi_idle_rescan_dead_smt_siblings(void)
+{
+	if (cpuidle_get_driver() == &acpi_idle_driver)
+		arch_cpu_rescan_dead_smt_siblings();
+}
+
 static
 DEFINE_PER_CPU(struct acpi_processor_cx * [CPUIDLE_STATE_MAX], acpi_cstate);
 

drivers/acpi/resource.c

···
 		},
 	},
 	{
+		/* MACHENIKE L16P/L16P */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "MACHENIKE"),
+			DMI_MATCH(DMI_BOARD_NAME, "L16P"),
+		},
+	},
+	{
 		/*
 		 * TongFang GM5HG0A in case of the SKIKK Vanaheim relabel the
 		 * board-name is changed, so check OEM strings instead. Note

drivers/ata/ahci.c

···
 
 static bool ahci_broken_lpm(struct pci_dev *pdev)
 {
+	/*
+	 * Platforms with LPM problems.
+	 * If driver_data is NULL, there is no existing BIOS version with
+	 * functioning LPM.
+	 * If driver_data is non-NULL, then driver_data contains the DMI BIOS
+	 * build date of the first BIOS version with functioning LPM (i.e. older
+	 * BIOS versions have broken LPM).
+	 */
 	static const struct dmi_system_id sysids[] = {
-		/* Various Lenovo 50 series have LPM issues with older BIOSen */
 		{
 			.matches = {
 				DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
···
 				DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
 				DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad W541"),
 			},
+			.driver_data = "20180409", /* 2.35 */
+		},
+		{
+			.matches = {
+				DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+				DMI_MATCH(DMI_PRODUCT_VERSION, "ASUSPRO D840MB_M840SA"),
+			},
+			/* 320 is broken, there is no known good version. */
+		},
+		{
 			/*
-			 * Note date based on release notes, 2.35 has been
-			 * reported to be good, but I've been unable to get
-			 * a hold of the reporter to get the DMI BIOS date.
-			 * TODO: fix this.
+			 * AMD 500 Series Chipset SATA Controller [1022:43eb]
+			 * on this motherboard timeouts on ports 5 and 6 when
+			 * LPM is enabled, at least with WDC WD20EFAX-68FB5N0
+			 * hard drives. LPM with the same drive works fine on
+			 * all other ports on the same controller.
 			 */
-			.driver_data = "20180310", /* 2.35 */
+			.matches = {
+				DMI_MATCH(DMI_BOARD_VENDOR,
+					  "ASUSTeK COMPUTER INC."),
+				DMI_MATCH(DMI_BOARD_NAME,
+					  "ROG STRIX B550-F GAMING (WI-FI)"),
+			},
+			/* 3621 is broken, there is no known good version. */
 		},
 		{ }	/* terminate list */
 	};
···
 
 	if (!dmi)
 		return false;
+
+	if (!dmi->driver_data)
+		return true;
 
 	dmi_get_date(DMI_BIOS_DATE, &year, &month, &date);
 	snprintf(buf, sizeof(buf), "%04d%02d%02d", year, month, date);

drivers/ata/libata-acpi.c

···
 EXPORT_SYMBOL_GPL(ata_acpi_gtm_xfermask);
 
 /**
- * ata_acpi_cbl_80wire		-	Check for 80 wire cable
+ * ata_acpi_cbl_pata_type - Return PATA cable type
  * @ap: Port to check
- * @gtm: GTM data to use
  *
- * Return 1 if the @gtm indicates the BIOS selected an 80wire mode.
+ * Return ATA_CBL_PATA* according to the transfer mode selected by BIOS
  */
-int ata_acpi_cbl_80wire(struct ata_port *ap, const struct ata_acpi_gtm *gtm)
+int ata_acpi_cbl_pata_type(struct ata_port *ap)
 {
 	struct ata_device *dev;
+	int ret = ATA_CBL_PATA_UNK;
+	const struct ata_acpi_gtm *gtm = ata_acpi_init_gtm(ap);
+
+	if (!gtm)
+		return ATA_CBL_PATA40;
 
 	ata_for_each_dev(dev, &ap->link, ENABLED) {
 		unsigned int xfer_mask, udma_mask;
···
 		xfer_mask = ata_acpi_gtm_xfermask(dev, gtm);
 		ata_unpack_xfermask(xfer_mask, NULL, NULL, &udma_mask);
 
-		if (udma_mask & ~ATA_UDMA_MASK_40C)
-			return 1;
+		ret = ATA_CBL_PATA40;
+
+		if (udma_mask & ~ATA_UDMA_MASK_40C) {
+			ret = ATA_CBL_PATA80;
+			break;
+		}
 	}
 
-	return 0;
+	return ret;
 }
-EXPORT_SYMBOL_GPL(ata_acpi_cbl_80wire);
+EXPORT_SYMBOL_GPL(ata_acpi_cbl_pata_type);
 
 static void ata_acpi_gtf_to_tf(struct ata_device *dev,
 			       const struct ata_acpi_gtf *gtf,

drivers/ata/pata_cs5536.c

···
 #include <scsi/scsi_host.h>
 #include <linux/dmi.h>
 
-#ifdef CONFIG_X86_32
+#if defined(CONFIG_X86) && defined(CONFIG_X86_32)
 #include <asm/msr.h>
 static int use_msr;
 module_param_named(msr, use_msr, int, 0644);

drivers/ata/pata_macio.c

···
 	priv->dev = &pdev->dev;
 
 	/* Get MMIO regions */
-	if (pci_request_regions(pdev, "pata-macio")) {
+	if (pcim_request_all_regions(pdev, "pata-macio")) {
 		dev_err(&pdev->dev,
 			"Cannot obtain PCI resources\n");
 		return -EBUSY;

drivers/ata/pata_via.c

···
 	   two drives */
 	if (ata66 & (0x10100000 >> (16 * ap->port_no)))
 		return ATA_CBL_PATA80;
+
 	/* Check with ACPI so we can spot BIOS reported SATA bridges */
-	if (ata_acpi_init_gtm(ap) &&
-	    ata_acpi_cbl_80wire(ap, ata_acpi_init_gtm(ap)))
-		return ATA_CBL_PATA80;
-	return ATA_CBL_PATA40;
+	return ata_acpi_cbl_pata_type(ap);
 }
 
 static int via_pre_reset(struct ata_link *link, unsigned long deadline)
···
 	}
 
 	if (dev->class == ATA_DEV_ATAPI &&
-	    dmi_check_system(no_atapi_dma_dmi_table)) {
+	    (dmi_check_system(no_atapi_dma_dmi_table) ||
+	     config->id == PCI_DEVICE_ID_VIA_6415)) {
 		ata_dev_warn(dev, "controller locks up on ATAPI DMA, forcing PIO\n");
 		mask &= ATA_MASK_PIO;
 	}

drivers/atm/atmtcp.c

···
 	struct sk_buff *new_skb;
 	int result = 0;
 
-	if (!skb->len) return 0;
+	if (skb->len < sizeof(struct atmtcp_hdr))
+		goto done;
+
 	dev = vcc->dev_data;
 	hdr = (struct atmtcp_hdr *) skb->data;
 	if (hdr->length == ATMTCP_HDR_MAGIC) {

drivers/base/faux.c

···
 	.name		= "faux_driver",
 	.bus		= &faux_bus_type,
 	.probe_type	= PROBE_FORCE_SYNCHRONOUS,
+	.suppress_bind_attrs = true,
 };
 
 static void faux_device_release(struct device *dev)
···
 	 * successful is almost impossible to determine by the caller.
 	 */
 	if (!dev->driver) {
-		dev_err(dev, "probe did not succeed, tearing down the device\n");
+		dev_dbg(dev, "probe did not succeed, tearing down the device\n");
 		faux_device_destroy(faux_dev);
 		faux_dev = NULL;
 	}

drivers/block/loop.c

···
 	lo->lo_flags &= ~LOOP_SET_STATUS_CLEARABLE_FLAGS;
 	lo->lo_flags |= (info->lo_flags & LOOP_SET_STATUS_SETTABLE_FLAGS);
 
-	if (size_changed) {
-		loff_t new_size = get_size(lo->lo_offset, lo->lo_sizelimit,
-					   lo->lo_backing_file);
-		loop_set_size(lo, new_size);
-	}
-
 	/* update the direct I/O flag if lo_offset changed */
 	loop_update_dio(lo);
 
···
 	blk_mq_unfreeze_queue(lo->lo_queue, memflags);
 	if (partscan)
 		clear_bit(GD_SUPPRESS_PART_SCAN, &lo->lo_disk->state);
+	if (!err && size_changed) {
+		loff_t new_size = get_size(lo->lo_offset, lo->lo_sizelimit,
+					   lo->lo_backing_file);
+		loop_set_size(lo, new_size);
+	}
 out_unlock:
 	mutex_unlock(&lo->lo_mutex);
 	if (partscan)

drivers/cpufreq/rcpufreq_dt.rs

···
 }
 
 /// Finds supply name for the CPU from DT.
-fn find_supply_names(dev: &Device, cpu: u32) -> Option<KVec<CString>> {
+fn find_supply_names(dev: &Device, cpu: cpu::CpuId) -> Option<KVec<CString>> {
     // Try "cpu0" for older DTs, fallback to "cpu".
-    let name = (cpu == 0)
+    let name = (cpu.as_u32() == 0)
         .then(|| find_supply_name_exact(dev, "cpu0"))
         .flatten()
         .or_else(|| find_supply_name_exact(dev, "cpu"))?;

drivers/dma-buf/dma-buf.c

···
 		 * Catch exporters making buffers inaccessible even when
 		 * attachments preventing that exist.
 		 */
-		WARN_ON_ONCE(ret == EBUSY);
+		WARN_ON_ONCE(ret == -EBUSY);
 		if (ret)
 			return ERR_PTR(ret);
 	}

drivers/dma-buf/udmabuf.c

···
 			ubuf->sg = NULL;
 		}
 	} else {
-		dma_sync_sg_for_cpu(dev, ubuf->sg->sgl, ubuf->sg->nents,
-				    direction);
+		dma_sync_sgtable_for_cpu(dev, ubuf->sg, direction);
 	}
 
 	return ret;
···
 	if (!ubuf->sg)
 		return -EINVAL;
 
-	dma_sync_sg_for_device(dev, ubuf->sg->sgl, ubuf->sg->nents, direction);
+	dma_sync_sgtable_for_device(dev, ubuf->sg, direction);
 	return 0;
 }
 

drivers/gpu/drm/meson/meson_encoder_hdmi.c

···
 		venc_freq /= 2;
 
 	dev_dbg(priv->dev,
-		"vclk:%lluHz phy=%lluHz venc=%lluHz hdmi=%lluHz enci=%d\n",
+		"phy:%lluHz vclk=%lluHz venc=%lluHz hdmi=%lluHz enci=%d\n",
 		phy_freq, vclk_freq, venc_freq, hdmi_freq,
 		priv->venc.hdmi_use_enci);
 

drivers/gpu/drm/meson/meson_vclk.c

···
 #define HDMI_PLL_LOCK		BIT(31)
 #define HDMI_PLL_LOCK_G12A	(3 << 30)
 
-#define PIXEL_FREQ_1000_1001(_freq)	\
-	DIV_ROUND_CLOSEST_ULL((_freq) * 1000ULL, 1001ULL)
-#define PHY_FREQ_1000_1001(_freq)	\
-	(PIXEL_FREQ_1000_1001(DIV_ROUND_DOWN_ULL(_freq, 10ULL)) * 10)
+#define FREQ_1000_1001(_freq)	DIV_ROUND_CLOSEST_ULL((_freq) * 1000ULL, 1001ULL)
 
 /* VID PLL Dividers */
 enum {
···
 		  pll_freq);
 }
 
+static bool meson_vclk_freqs_are_matching_param(unsigned int idx,
+						unsigned long long phy_freq,
+						unsigned long long vclk_freq)
+{
+	DRM_DEBUG_DRIVER("i = %d vclk_freq = %lluHz alt = %lluHz\n",
+			 idx, params[idx].vclk_freq,
+			 FREQ_1000_1001(params[idx].vclk_freq));
+	DRM_DEBUG_DRIVER("i = %d phy_freq = %lluHz alt = %lluHz\n",
+			 idx, params[idx].phy_freq,
+			 FREQ_1000_1001(params[idx].phy_freq));
+
+	/* Match strict frequency */
+	if (phy_freq == params[idx].phy_freq &&
+	    vclk_freq == params[idx].vclk_freq)
+		return true;
+
+	/* Match 1000/1001 variant: vclk deviation has to be less than 1kHz
+	 * (drm EDID is defined in 1kHz steps, so everything smaller must be
+	 * rounding error) and the PHY freq deviation has to be less than
+	 * 10kHz (as the TMDS clock is 10 times the pixel clock, so anything
+	 * smaller must be rounding error as well).
+	 */
+	if (abs(vclk_freq - FREQ_1000_1001(params[idx].vclk_freq)) < 1000 &&
+	    abs(phy_freq - FREQ_1000_1001(params[idx].phy_freq)) < 10000)
+		return true;
+
+	/* no match */
+	return false;
+}
+
 enum drm_mode_status
 meson_vclk_vic_supported_freq(struct meson_drm *priv,
 			      unsigned long long phy_freq,
···
 	}
 
 	for (i = 0 ; params[i].pixel_freq ; ++i) {
-		DRM_DEBUG_DRIVER("i = %d pixel_freq = %lluHz alt = %lluHz\n",
-				 i, params[i].pixel_freq,
-				 PIXEL_FREQ_1000_1001(params[i].pixel_freq));
-		DRM_DEBUG_DRIVER("i = %d phy_freq = %lluHz alt = %lluHz\n",
-				 i, params[i].phy_freq,
-				 PHY_FREQ_1000_1001(params[i].phy_freq));
-		/* Match strict frequency */
-		if (phy_freq == params[i].phy_freq &&
-		    vclk_freq == params[i].vclk_freq)
-			return MODE_OK;
-		/* Match 1000/1001 variant */
-		if (phy_freq == PHY_FREQ_1000_1001(params[i].phy_freq) &&
-		    vclk_freq == PIXEL_FREQ_1000_1001(params[i].vclk_freq))
+		if (meson_vclk_freqs_are_matching_param(i, phy_freq, vclk_freq))
 			return MODE_OK;
 	}
 
···
 	}
 
 	for (freq = 0 ; params[freq].pixel_freq ; ++freq) {
-		if ((phy_freq == params[freq].phy_freq ||
-		     phy_freq == PHY_FREQ_1000_1001(params[freq].phy_freq)) &&
-		    (vclk_freq == params[freq].vclk_freq ||
-		     vclk_freq == PIXEL_FREQ_1000_1001(params[freq].vclk_freq))) {
+		if (meson_vclk_freqs_are_matching_param(freq, phy_freq,
+							vclk_freq)) {
 			if (vclk_freq != params[freq].vclk_freq)
 				vic_alternate_clock = true;
 			else

drivers/gpu/drm/sitronix/Kconfig

···
 	select DRM_GEM_SHMEM_HELPER
 	select DRM_KMS_HELPER
 	select REGMAP_I2C
+	select VIDEOMODE_HELPERS
 	help
 	  DRM driver for Sitronix ST7571 panels controlled over I2C.
 

drivers/gpu/drm/vc4/vc4_hdmi.c

···
 	if (ret)
 		return ret;
 
-	ret = drm_connector_hdmi_audio_init(connector, dev->dev,
-					    &vc4_hdmi_audio_funcs,
-					    8, false, -1);
-	if (ret)
-		return ret;
-
 	drm_connector_helper_add(connector, &vc4_hdmi_connector_helper_funcs);
 
 	/*
···
 		dev_err(dev, "Could not register CPU DAI: %d\n", ret);
 		return ret;
 	}
+
+	ret = drm_connector_hdmi_audio_init(&vc4_hdmi->connector, dev,
+					    &vc4_hdmi_audio_funcs, 8, false,
+					    -1);
+	if (ret)
+		return ret;
 
 	dai_link->cpus		= &vc4_hdmi->audio.cpu;
 	dai_link->codecs	= &vc4_hdmi->audio.codec;

drivers/gpu/drm/xe/xe_lrc.c

···
  * store it in the PPHSWP.
  */
 #define CONTEXT_ACTIVE 1ULL
-static void xe_lrc_setup_utilization(struct xe_lrc *lrc)
+static int xe_lrc_setup_utilization(struct xe_lrc *lrc)
 {
-	u32 *cmd;
+	u32 *cmd, *buf = NULL;
 
-	cmd = lrc->bb_per_ctx_bo->vmap.vaddr;
+	if (lrc->bb_per_ctx_bo->vmap.is_iomem) {
+		buf = kmalloc(lrc->bb_per_ctx_bo->size, GFP_KERNEL);
+		if (!buf)
+			return -ENOMEM;
+		cmd = buf;
+	} else {
+		cmd = lrc->bb_per_ctx_bo->vmap.vaddr;
+	}
 
 	*cmd++ = MI_STORE_REGISTER_MEM | MI_SRM_USE_GGTT | MI_SRM_ADD_CS_OFFSET;
 	*cmd++ = ENGINE_ID(0).addr;
···
 
 	*cmd++ = MI_BATCH_BUFFER_END;
 
+	if (buf) {
+		xe_map_memcpy_to(gt_to_xe(lrc->gt), &lrc->bb_per_ctx_bo->vmap, 0,
+				 buf, (cmd - buf) * sizeof(*cmd));
+		kfree(buf);
+	}
+
 	xe_lrc_write_ctx_reg(lrc, CTX_BB_PER_CTX_PTR,
 			     xe_bo_ggtt_addr(lrc->bb_per_ctx_bo) | 1);
 
+	return 0;
 }
 
 #define PVC_CTX_ASID		(0x2e + 1)
···
 	map = __xe_lrc_start_seqno_map(lrc);
 	xe_map_write32(lrc_to_xe(lrc), &map, lrc->fence_ctx.next_seqno - 1);
 
-	xe_lrc_setup_utilization(lrc);
+	err = xe_lrc_setup_utilization(lrc);
+	if (err)
+		goto err_lrc_finish;
 
 	return 0;
 

drivers/gpu/drm/xe/xe_svm.c

···
 		return false;
 	}
 
-	if (range_size <= SZ_64K && !supports_4K_migration(vm->xe)) {
+	if (range_size < SZ_64K && !supports_4K_migration(vm->xe)) {
 		drm_dbg(&vm->xe->drm, "Platform doesn't support SZ_4K range migration\n");
 		return false;
 	}

drivers/hwmon/ftsteutates.c

···
 		break;
 	case hwmon_pwm:
 		switch (attr) {
-		case hwmon_pwm_auto_channels_temp:
-			if (data->fan_source[channel] == FTS_FAN_SOURCE_INVALID)
+		case hwmon_pwm_auto_channels_temp: {
+			u8 fan_source = data->fan_source[channel];
+
+			if (fan_source == FTS_FAN_SOURCE_INVALID || fan_source >= BITS_PER_LONG)
 				*val = 0;
 			else
-				*val = BIT(data->fan_source[channel]);
+				*val = BIT(fan_source);
 
 			return 0;
+		}
 		default:
 			break;
 		}

drivers/hwmon/ltc4282.c

···
 	}
 
 	if (device_property_read_bool(dev, "adi,fault-log-enable")) {
-		ret = regmap_set_bits(st->map, LTC4282_ADC_CTRL,
-				      LTC4282_FAULT_LOG_EN_MASK);
-		if (ret)
-			return ret;
-	}
-
-	if (device_property_read_bool(dev, "adi,fault-log-enable")) {
 		ret = regmap_set_bits(st->map, LTC4282_ADC_CTRL, LTC4282_FAULT_LOG_EN_MASK);
 		if (ret)
 			return ret;

drivers/hwmon/occ/common.c

···
 	return sysfs_emit(buf, "%llu\n", val);
 }
 
-static u64 occ_get_powr_avg(u64 *accum, u32 *samples)
+static u64 occ_get_powr_avg(u64 accum, u32 samples)
 {
-	u64 divisor = get_unaligned_be32(samples);
-
-	return (divisor == 0) ? 0 :
-		div64_u64(get_unaligned_be64(accum) * 1000000ULL, divisor);
+	return (samples == 0) ? 0 :
+		mul_u64_u32_div(accum, 1000000UL, samples);
 }
 
 static ssize_t occ_show_power_2(struct device *dev,
···
 				  get_unaligned_be32(&power->sensor_id),
 				  power->function_id, power->apss_channel);
 	case 1:
-		val = occ_get_powr_avg(&power->accumulator,
-				       &power->update_tag);
+		val = occ_get_powr_avg(get_unaligned_be64(&power->accumulator),
+				       get_unaligned_be32(&power->update_tag));
 		break;
 	case 2:
 		val = (u64)get_unaligned_be32(&power->update_tag) *
···
 		return sysfs_emit(buf, "%u_system\n",
 				  get_unaligned_be32(&power->sensor_id));
 	case 1:
-		val = occ_get_powr_avg(&power->system.accumulator,
-				       &power->system.update_tag);
+		val = occ_get_powr_avg(get_unaligned_be64(&power->system.accumulator),
+				       get_unaligned_be32(&power->system.update_tag));
 		break;
 	case 2:
 		val = (u64)get_unaligned_be32(&power->system.update_tag) *
···
 		return sysfs_emit(buf, "%u_proc\n",
 				  get_unaligned_be32(&power->sensor_id));
 	case 5:
-		val = occ_get_powr_avg(&power->proc.accumulator,
-				       &power->proc.update_tag);
+		val = occ_get_powr_avg(get_unaligned_be64(&power->proc.accumulator),
+				       get_unaligned_be32(&power->proc.update_tag));
 		break;
 	case 6:
 		val = (u64)get_unaligned_be32(&power->proc.update_tag) *
···
 		return sysfs_emit(buf, "%u_vdd\n",
 				  get_unaligned_be32(&power->sensor_id));
 	case 9:
-		val = occ_get_powr_avg(&power->vdd.accumulator,
-				       &power->vdd.update_tag);
+		val = occ_get_powr_avg(get_unaligned_be64(&power->vdd.accumulator),
+				       get_unaligned_be32(&power->vdd.update_tag));
 		break;
 	case 10:
 		val = (u64)get_unaligned_be32(&power->vdd.update_tag) *
···
 		return sysfs_emit(buf, "%u_vdn\n",
 				  get_unaligned_be32(&power->sensor_id));
 	case 13:
-		val = occ_get_powr_avg(&power->vdn.accumulator,
-				       &power->vdn.update_tag);
+		val = occ_get_powr_avg(get_unaligned_be64(&power->vdn.accumulator),
+				       get_unaligned_be32(&power->vdn.update_tag));
 		break;
 	case 14:
 		val = (u64)get_unaligned_be32(&power->vdn.update_tag) *
···
 }
 
 /*
- * Some helper macros to make it easier to define an occ_attribute. Since these
- * are dynamically allocated, we shouldn't use the existing kernel macros which
+ * A helper to make it easier to define an occ_attribute. Since these
+ * are dynamically allocated, we cannot use the existing kernel macros which
  * stringify the name argument.
  */
-#define ATTR_OCC(_name, _mode, _show, _store) {				\
-	.attr	= {							\
-		.name = _name,						\
-		.mode = VERIFY_OCTAL_PERMISSIONS(_mode),		\
-	},								\
-	.show	= _show,						\
-	.store	= _store,						\
-}
+static void occ_init_attribute(struct occ_attribute *attr, int mode,
+	ssize_t (*show)(struct device *dev, struct device_attribute *attr, char *buf),
+	ssize_t (*store)(struct device *dev, struct device_attribute *attr,
+				   const char *buf, size_t count),
+	int nr, int index, const char *fmt, ...)
+{
+	va_list args;
 
-#define SENSOR_ATTR_OCC(_name, _mode, _show, _store, _nr, _index) {	\
-	.dev_attr	= ATTR_OCC(_name, _mode, _show, _store),	\
-	.index		= _index,					\
-	.nr		= _nr,						\
-}
+	va_start(args, fmt);
+	vsnprintf(attr->name, sizeof(attr->name), fmt, args);
+	va_end(args);
 
-#define OCC_INIT_ATTR(_name, _mode, _show, _store, _nr, _index)		\
-	((struct sensor_device_attribute_2)				\
-		SENSOR_ATTR_OCC(_name, _mode, _show, _store, _nr, _index))
+	attr->sensor.dev_attr.attr.name = attr->name;
+	attr->sensor.dev_attr.attr.mode = mode;
+	attr->sensor.dev_attr.show = show;
+	attr->sensor.dev_attr.store = store;
+	attr->sensor.index = index;
+	attr->sensor.nr = nr;
+}
 
 /*
  * Allocate and instatiate sensor_device_attribute_2s. It's most efficient to
···
 		sensors->extended.num_sensors = 0;
 	}
 
-	occ->attrs = devm_kzalloc(dev, sizeof(*occ->attrs) * num_attrs,
+	occ->attrs = devm_kcalloc(dev, num_attrs, sizeof(*occ->attrs),
 				  GFP_KERNEL);
 	if (!occ->attrs)
 		return -ENOMEM;
 
 	/* null-terminated list */
-	occ->group.attrs = devm_kzalloc(dev, sizeof(*occ->group.attrs) *
-					num_attrs + 1, GFP_KERNEL);
+	occ->group.attrs = devm_kcalloc(dev, num_attrs + 1,
+					sizeof(*occ->group.attrs),
+					GFP_KERNEL);
 	if (!occ->group.attrs)
 		return -ENOMEM;
 
···
 		s = i + 1;
 		temp = ((struct temp_sensor_2 *)sensors->temp.data) + i;
 
-		snprintf(attr->name, sizeof(attr->name), "temp%d_label", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_temp, NULL,
-					     0, i);
+		occ_init_attribute(attr, 0444, show_temp, NULL,
+				   0, i, "temp%d_label", s);
 		attr++;
 
 		if (sensors->temp.version == 2 &&
 		    temp->fru_type == OCC_FRU_TYPE_VRM) {
-			snprintf(attr->name, sizeof(attr->name),
-				 "temp%d_alarm", s);
+			occ_init_attribute(attr, 0444, show_temp, NULL,
+					   1, i, "temp%d_alarm", s);
 		} else {
-			snprintf(attr->name, sizeof(attr->name),
-				 "temp%d_input", s);
+			occ_init_attribute(attr, 0444, show_temp, NULL,
+					   1, i, "temp%d_input", s);
 		}
 
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_temp, NULL,
-					     1, i);
 		attr++;
 
 		if (sensors->temp.version > 1) {
-			snprintf(attr->name, sizeof(attr->name),
-				 "temp%d_fru_type", s);
-			attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-						     show_temp, NULL, 2, i);
+			occ_init_attribute(attr, 0444, show_temp, NULL,
+					   2, i, "temp%d_fru_type", s);
 			attr++;
 
-			snprintf(attr->name, sizeof(attr->name),
-				 "temp%d_fault", s);
-			attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-						     show_temp, NULL, 3, i);
+			occ_init_attribute(attr, 0444, show_temp, NULL,
+					   3, i, "temp%d_fault", s);
 			attr++;
 
 			if (sensors->temp.version == 0x10) {
-				snprintf(attr->name, sizeof(attr->name),
-					 "temp%d_max", s);
-				attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-							     show_temp, NULL,
-							     4, i);
+				occ_init_attribute(attr, 0444, show_temp, NULL,
+						   4, i, "temp%d_max", s);
 				attr++;
 			}
 		}
···
 	for (i = 0; i < sensors->freq.num_sensors; ++i) {
 		s = i + 1;
 
-		snprintf(attr->name, sizeof(attr->name), "freq%d_label", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_freq, NULL,
-					     0, i);
+		occ_init_attribute(attr, 0444, show_freq, NULL,
+				   0, i, "freq%d_label", s);
 		attr++;
 
-		snprintf(attr->name, sizeof(attr->name), "freq%d_input", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_freq, NULL,
-					     1, i);
+		occ_init_attribute(attr, 0444, show_freq, NULL,
+				   1, i, "freq%d_input", s);
 		attr++;
 	}
 
···
 			s = (i * 4) + 1;
 
 			for (j = 0; j < 4; ++j) {
-				snprintf(attr->name, sizeof(attr->name),
-					 "power%d_label", s);
-				attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-							     show_power, NULL,
-							     nr++, i);
+				occ_init_attribute(attr, 0444, show_power,
+						   NULL, nr++, i,
+						   "power%d_label", s);
 				attr++;
 
-				snprintf(attr->name, sizeof(attr->name),
-					 "power%d_average", s);
-				attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-							     show_power, NULL,
-							     nr++, i);
+				occ_init_attribute(attr, 0444, show_power,
+						   NULL, nr++, i,
+						   "power%d_average", s);
 				attr++;
 
-				snprintf(attr->name, sizeof(attr->name),
-					 "power%d_average_interval", s);
-				attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-							     show_power, NULL,
-							     nr++, i);
+				occ_init_attribute(attr, 0444, show_power,
+						   NULL, nr++, i,
+						   "power%d_average_interval", s);
 				attr++;
 
-				snprintf(attr->name, sizeof(attr->name),
-					 "power%d_input", s);
-				attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-							     show_power, NULL,
-							     nr++, i);
+				occ_init_attribute(attr, 0444, show_power,
+						   NULL, nr++, i,
+						   "power%d_input", s);
 				attr++;
 
 				s++;
···
 		for (i = 0; i < sensors->power.num_sensors; ++i) {
 			s = i + 1;
 
-			snprintf(attr->name, sizeof(attr->name),
-				 "power%d_label", s);
-			attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-						     show_power, NULL, 0, i);
+			occ_init_attribute(attr, 0444, show_power, NULL,
+					   0, i, "power%d_label", s);
 			attr++;
 
-			snprintf(attr->name, sizeof(attr->name),
-				 "power%d_average", s);
-			attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-						     show_power, NULL, 1, i);
+			occ_init_attribute(attr, 0444, show_power, NULL,
+					   1, i, "power%d_average", s);
 			attr++;
 
-			snprintf(attr->name, sizeof(attr->name),
-				 "power%d_average_interval", s);
-			attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-						     show_power, NULL, 2, i);
+			occ_init_attribute(attr, 0444, show_power, NULL,
+					   2, i, "power%d_average_interval", s);
 			attr++;
 
-			snprintf(attr->name, sizeof(attr->name),
-				 "power%d_input", s);
-			attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-						     show_power, NULL, 3, i);
+			occ_init_attribute(attr, 0444, show_power, NULL,
+					   3, i, "power%d_input", s);
 			attr++;
 		}
 
···
 	}
 
 	if (sensors->caps.num_sensors >= 1) {
-		snprintf(attr->name, sizeof(attr->name), "power%d_label", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_caps, NULL,
-					     0, 0);
+		occ_init_attribute(attr, 0444, show_caps, NULL,
+				   0, 0, "power%d_label", s);
 		attr++;
 
-		snprintf(attr->name, sizeof(attr->name), "power%d_cap", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_caps, NULL,
-					     1, 0);
+		occ_init_attribute(attr, 0444, show_caps, NULL,
+				   1, 0, "power%d_cap", s);
 		attr++;
 
-		snprintf(attr->name, sizeof(attr->name), "power%d_input", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_caps, NULL,
-					     2, 0);
+		occ_init_attribute(attr, 0444, show_caps, NULL,
+				   2, 0, "power%d_input", s);
 		attr++;
 
-		snprintf(attr->name, sizeof(attr->name),
-			 "power%d_cap_not_redundant", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_caps, NULL,
-					     3, 0);
+		occ_init_attribute(attr, 0444, show_caps, NULL,
+				   3, 0, "power%d_cap_not_redundant", s);
 		attr++;
 
-		snprintf(attr->name, sizeof(attr->name), "power%d_cap_max", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_caps, NULL,
-					     4, 0);
+		occ_init_attribute(attr, 0444, show_caps, NULL,
+				   4, 0, "power%d_cap_max", s);
 		attr++;
 
-		snprintf(attr->name, sizeof(attr->name), "power%d_cap_min", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_caps, NULL,
-					     5, 0);
+		occ_init_attribute(attr, 0444, show_caps, NULL,
+				   5, 0, "power%d_cap_min", s);
 		attr++;
 
-		snprintf(attr->name, sizeof(attr->name), "power%d_cap_user",
-			 s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0644, show_caps,
-					     occ_store_caps_user, 6, 0);
+		occ_init_attribute(attr, 0644, show_caps, occ_store_caps_user,
+				   6, 0, "power%d_cap_user", s);
 		attr++;
 
 		if (sensors->caps.version > 1) {
-			snprintf(attr->name, sizeof(attr->name),
-				 "power%d_cap_user_source", s);
-			attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-						     show_caps, NULL, 7, 0);
+			occ_init_attribute(attr, 0444, show_caps, NULL,
+					   7, 0, "power%d_cap_user_source", s);
 			attr++;
 
 			if (sensors->caps.version > 2) {
-				snprintf(attr->name, sizeof(attr->name),
-					 "power%d_cap_min_soft", s);
-				attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-							     show_caps, NULL,
-							     8, 0);
+				occ_init_attribute(attr, 0444, show_caps, NULL,
+						   8, 0,
+						   "power%d_cap_min_soft", s);
 				attr++;
 			}
 		}
···
 	for (i = 0; i < sensors->extended.num_sensors; ++i) {
 		s = i + 1;
 
-		snprintf(attr->name, sizeof(attr->name), "extn%d_label", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-					     occ_show_extended, NULL, 0, i);
+		occ_init_attribute(attr, 0444, occ_show_extended, NULL,
+				   0, i, "extn%d_label", s);
 		attr++;
 
-		snprintf(attr->name, sizeof(attr->name), "extn%d_flags", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-					     occ_show_extended, NULL, 1, i);
+		occ_init_attribute(attr, 0444, occ_show_extended, NULL,
+				   1, i, "extn%d_flags", s);
 		attr++;
 
-		snprintf(attr->name, sizeof(attr->name), "extn%d_input", s);
-		attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
-					     occ_show_extended, NULL, 2, i);
+		occ_init_attribute(attr, 0444, occ_show_extended, NULL,
+				   2, i, "extn%d_input", s);
 		attr++;
 	}
 

drivers/idle/intel_idle.c

···
 					int index, bool irqoff)
 {
 	struct cpuidle_state *state = &drv->states[index];
-	unsigned long eax = flg2MWAIT(state->flags);
-	unsigned long ecx = 1*irqoff; /* break on interrupt flag */
+	unsigned int eax = flg2MWAIT(state->flags);
+	unsigned int ecx = 1*irqoff; /* break on interrupt flag */
 
 	mwait_idle_with_hints(eax, ecx);
 
···
 static __cpuidle int intel_idle_s2idle(struct cpuidle_device *dev,
 				       struct cpuidle_driver *drv, int index)
 {
-	unsigned long ecx = 1; /* break on interrupt flag */
 	struct cpuidle_state *state = &drv->states[index];
-	unsigned long eax = flg2MWAIT(state->flags);
+	unsigned int eax = flg2MWAIT(state->flags);
+	unsigned int ecx = 1; /* break on interrupt flag */
 
 	if (state->flags & CPUIDLE_FLAG_INIT_XSTATE)
 		fpu_idle_fpregs();
···
 	pr_debug("Local APIC timer is reliable in %s\n",
 		 boot_cpu_has(X86_FEATURE_ARAT) ? "all C-states" : "C1");
 
+	arch_cpu_rescan_dead_smt_siblings();
+
 	return 0;
 
 hp_setup_fail:
···
 	return retval;
 
 }
-device_initcall(intel_idle_init);
+subsys_initcall_sync(intel_idle_init);
 
 /*
  * We are not really modular, but we used to support that.  Meaning we also

drivers/iommu/tegra-smmu.c

···
 {
 	unsigned int pd_index = iova_pd_index(iova);
 	struct tegra_smmu *smmu = as->smmu;
-	struct tegra_pd *pd = as->pd;
+	u32 *pd = &as->pd->val[pd_index];
 	unsigned long offset = pd_index * sizeof(*pd);
 
 	/* Set the page directory entry first */
-	pd->val[pd_index] = value;
+	*pd = value;
 
 	/* The flush the page directory entry from caches */
 	dma_sync_single_range_for_device(smmu->dev, as->pd_dma, offset,

drivers/net/can/m_can/tcan4x5x-core.c

···
 	priv = cdev_to_priv(mcan_class);
 
 	priv->power = devm_regulator_get_optional(&spi->dev, "vsup");
-	if (PTR_ERR(priv->power) == -EPROBE_DEFER) {
-		ret = -EPROBE_DEFER;
-		goto out_m_can_class_free_dev;
-	} else {
+	if (IS_ERR(priv->power)) {
+		if (PTR_ERR(priv->power) == -EPROBE_DEFER) {
+			ret = -EPROBE_DEFER;
+			goto out_m_can_class_free_dev;
+		}
 		priv->power = NULL;
 	}
 

drivers/net/ethernet/airoha/airoha_eth.c

···
 
 static int airoha_qdma_init_hfwd_queues(struct airoha_qdma *qdma)
 {
+	int size, index, num_desc = HW_DSCP_NUM;
 	struct airoha_eth *eth = qdma->eth;
 	int id = qdma - &eth->qdma[0];
+	u32 status, buf_size;
 	dma_addr_t dma_addr;
 	const char *name;
-	int size, index;
-	u32 status;
-
-	size = HW_DSCP_NUM * sizeof(struct airoha_qdma_fwd_desc);
-	if (!dmam_alloc_coherent(eth->dev, size, &dma_addr, GFP_KERNEL))
-		return -ENOMEM;
-
-	airoha_qdma_wr(qdma, REG_FWD_DSCP_BASE, dma_addr);
 
 	name = devm_kasprintf(eth->dev, GFP_KERNEL, "qdma%d-buf", id);
 	if (!name)
 		return -ENOMEM;
 
+	buf_size = id ? AIROHA_MAX_PACKET_SIZE / 2 : AIROHA_MAX_PACKET_SIZE;
 	index = of_property_match_string(eth->dev->of_node,
 					 "memory-region-names", name);
 	if (index >= 0) {
···
 		rmem = of_reserved_mem_lookup(np);
 		of_node_put(np);
 		dma_addr = rmem->base;
+		/* Compute the number of hw descriptors according to the
+		 * reserved memory size and the payload buffer size
+		 */
+		num_desc = div_u64(rmem->size, buf_size);
 	} else {
-		size = AIROHA_MAX_PACKET_SIZE * HW_DSCP_NUM;
+		size = buf_size * num_desc;
 		if (!dmam_alloc_coherent(eth->dev, size, &dma_addr,
 					 GFP_KERNEL))
 			return -ENOMEM;
···
 
 	airoha_qdma_wr(qdma, REG_FWD_BUF_BASE, dma_addr);
 
+	size = num_desc * sizeof(struct airoha_qdma_fwd_desc);
+	if (!dmam_alloc_coherent(eth->dev, size, &dma_addr, GFP_KERNEL))
+		return -ENOMEM;
+
+	airoha_qdma_wr(qdma, REG_FWD_DSCP_BASE, dma_addr);
+	/* QDMA0: 2KB. QDMA1: 1KB */
 	airoha_qdma_rmw(qdma, REG_HW_FWD_DSCP_CFG,
 			HW_FWD_DSCP_PAYLOAD_SIZE_MASK,
-			FIELD_PREP(HW_FWD_DSCP_PAYLOAD_SIZE_MASK, 0));
+			FIELD_PREP(HW_FWD_DSCP_PAYLOAD_SIZE_MASK, !!id));
 	airoha_qdma_rmw(qdma, REG_FWD_DSCP_LOW_THR, FWD_DSCP_LOW_THR_MASK,
 			FIELD_PREP(FWD_DSCP_LOW_THR_MASK, 128));
 	airoha_qdma_rmw(qdma, REG_LMGR_INIT_CFG,
 			LMGR_INIT_START | LMGR_SRAM_MODE_MASK |
 			HW_FWD_DESC_NUM_MASK,
-			FIELD_PREP(HW_FWD_DESC_NUM_MASK, HW_DSCP_NUM) |
+			FIELD_PREP(HW_FWD_DESC_NUM_MASK, num_desc) |
 			LMGR_INIT_START | LMGR_SRAM_MODE_MASK);
 
 	return read_poll_timeout(airoha_qdma_rr, status,

drivers/net/ethernet/airoha/airoha_ppe.c

···
 		int idle;
 
 		hwe = airoha_ppe_foe_get_entry(ppe, iter->hash);
-		ib1 = READ_ONCE(hwe->ib1);
+		if (!hwe)
+			continue;
 
+		ib1 = READ_ONCE(hwe->ib1);
 		state = FIELD_GET(AIROHA_FOE_IB1_BIND_STATE, ib1);
 		if (state != AIROHA_FOE_STATE_BIND) {
 			iter->hash = 0xffff;

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

···
 	bp->num_rss_ctx--;
 }
 
+static bool bnxt_vnic_has_rx_ring(struct bnxt *bp, struct bnxt_vnic_info *vnic,
+				  int rxr_id)
+{
+	u16 tbl_size = bnxt_get_rxfh_indir_size(bp->dev);
+	int i, vnic_rx;
+
+	/* Ntuple VNIC always has all the rx rings. Any change of ring id
+	 * must be updated because a future filter may use it.
+	 */
+	if (vnic->flags & BNXT_VNIC_NTUPLE_FLAG)
+		return true;
+
+	for (i = 0; i < tbl_size; i++) {
+		if (vnic->flags & BNXT_VNIC_RSSCTX_FLAG)
+			vnic_rx = ethtool_rxfh_context_indir(vnic->rss_ctx)[i];
+		else
+			vnic_rx = bp->rss_indir_tbl[i];
+
+		if (rxr_id == vnic_rx)
+			return true;
+	}
+
+	return false;
+}
+
+static int bnxt_set_vnic_mru_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic,
+				u16 mru, int rxr_id)
+{
+	int rc;
+
+	if (!bnxt_vnic_has_rx_ring(bp, vnic, rxr_id))
+		return 0;
+
+	if (mru) {
+		rc = bnxt_hwrm_vnic_set_rss_p5(bp, vnic, true);
+		if (rc) {
+			netdev_err(bp->dev, "hwrm vnic %d set rss failure rc: %d\n",
+				   vnic->vnic_id, rc);
+			return rc;
+		}
+	}
+	vnic->mru = mru;
+	bnxt_hwrm_vnic_update(bp, vnic,
+			      VNIC_UPDATE_REQ_ENABLES_MRU_VALID);
+
+	return 0;
+}
+
+static int bnxt_set_rss_ctx_vnic_mru(struct bnxt *bp, u16 mru, int rxr_id)
+{
+	struct ethtool_rxfh_context *ctx;
+	unsigned long context;
+	int rc;
+
+	xa_for_each(&bp->dev->ethtool->rss_ctx, context, ctx) {
+		struct bnxt_rss_ctx *rss_ctx = ethtool_rxfh_context_priv(ctx);
+		struct bnxt_vnic_info *vnic = &rss_ctx->vnic;
+
+		rc = bnxt_set_vnic_mru_p5(bp, vnic, mru, rxr_id);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
 static void bnxt_hwrm_realloc_rss_ctx_vnic(struct bnxt *bp)
 {
 	bool set_tpa = !!(bp->flags & BNXT_FLAG_TPA);
···
 	struct bnxt_vnic_info *vnic;
 	struct bnxt_napi *bnapi;
 	int i, rc;
+	u16 mru;
 
 	rxr = &bp->rx_ring[idx];
 	clone = qmem;
···
 	napi_enable_locked(&bnapi->napi);
 	bnxt_db_nq_arm(bp, &cpr->cp_db, cpr->cp_raw_cons);
 
+	mru = bp->dev->mtu + ETH_HLEN + VLAN_HLEN;
 	for (i = 0; i < bp->nr_vnics; i++) {
 		vnic = &bp->vnic_info[i];
 
-		rc = bnxt_hwrm_vnic_set_rss_p5(bp, vnic, true);
-		if (rc) {
-			netdev_err(bp->dev, "hwrm vnic %d set rss failure rc: %d\n",
-				   vnic->vnic_id, rc);
+		rc = bnxt_set_vnic_mru_p5(bp, vnic, mru, idx);
+		if (rc)
 			return rc;
-		}
-		vnic->mru = bp->dev->mtu + ETH_HLEN + VLAN_HLEN;
-		bnxt_hwrm_vnic_update(bp, vnic,
-				      VNIC_UPDATE_REQ_ENABLES_MRU_VALID);
 	}
-
-	return 0;
+	return bnxt_set_rss_ctx_vnic_mru(bp, mru, idx);
 
 err_reset:
 	netdev_err(bp->dev, "Unexpected HWRM error during queue start rc: %d\n",
···
 
 	for (i = 0; i < bp->nr_vnics; i++) {
 		vnic = &bp->vnic_info[i];
-		vnic->mru = 0;
-		bnxt_hwrm_vnic_update(bp, vnic,
-				      VNIC_UPDATE_REQ_ENABLES_MRU_VALID);
+
+		bnxt_set_vnic_mru_p5(bp, vnic, 0, idx);
 	}
+	bnxt_set_rss_ctx_vnic_mru(bp, 0, idx);
 	/* Make sure NAPI sees that the VNIC is disabled */
 	synchronize_net();
 	rxr = &bp->rx_ring[idx];

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

···
 		return;
 
 	mutex_lock(&edev->en_dev_lock);
-	if (!bnxt_ulp_registered(edev)) {
-		mutex_unlock(&edev->en_dev_lock);
-		return;
-	}
+	if (!bnxt_ulp_registered(edev) ||
+	    (edev->flags & BNXT_EN_FLAG_ULP_STOPPED))
+		goto ulp_stop_exit;
 
 	edev->flags |= BNXT_EN_FLAG_ULP_STOPPED;
 	if (aux_priv) {
···
 			adrv->suspend(adev, pm);
 		}
 	}
+ulp_stop_exit:
 	mutex_unlock(&edev->en_dev_lock);
 }
 
···
 	struct bnxt_aux_priv *aux_priv = bp->aux_priv;
 	struct bnxt_en_dev *edev = bp->edev;
 
-	if (!edev)
-		return;
-
-	edev->flags &= ~BNXT_EN_FLAG_ULP_STOPPED;
-
-	if (err)
+	if (!edev || err)
 		return;
 
 	mutex_lock(&edev->en_dev_lock);
-	if (!bnxt_ulp_registered(edev)) {
-		mutex_unlock(&edev->en_dev_lock);
-		return;
-	}
+	if (!bnxt_ulp_registered(edev) ||
+	    !(edev->flags & BNXT_EN_FLAG_ULP_STOPPED))
+		goto ulp_start_exit;
 
 	if (edev->ulp_tbl->msix_requested)
 		bnxt_fill_msix_vecs(bp, edev->msix_entries);
···
 			adrv->resume(adev);
 		}
 	}
+ulp_start_exit:
+	edev->flags &= ~BNXT_EN_FLAG_ULP_STOPPED;
 	mutex_unlock(&edev->en_dev_lock);
 }
 

drivers/net/ethernet/faraday/Kconfig

···
 	depends on ARM || COMPILE_TEST
 	depends on !64BIT || BROKEN
 	select PHYLIB
+	select FIXED_PHY
 	select MDIO_ASPEED if MACH_ASPEED_G6
 	select CRC32
 	help

drivers/net/ethernet/intel/e1000e/netdev.c

···
 	case e1000_pch_cnp:
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
-	case e1000_pch_mtp:
-	case e1000_pch_lnp:
-	case e1000_pch_ptp:
 	case e1000_pch_nvp:
 		if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) {
 			/* Stable 24MHz frequency */
···
 			shift = INCVALUE_SHIFT_38400KHZ;
 			adapter->cc.shift = shift;
 		}
+		break;
+	case e1000_pch_mtp:
+	case e1000_pch_lnp:
+	case e1000_pch_ptp:
+		/* System firmware can misreport this value, so set it to a
+		 * stable 38400KHz frequency.
+		 */
+		incperiod = INCPERIOD_38400KHZ;
+		incvalue = INCVALUE_38400KHZ;
+		shift = INCVALUE_SHIFT_38400KHZ;
+		adapter->cc.shift = shift;
 		break;
 	case e1000_82574:
 	case e1000_82583:

drivers/net/ethernet/intel/e1000e/ptp.c

···
 	case e1000_pch_cnp:
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
-	case e1000_pch_mtp:
-	case e1000_pch_lnp:
-	case e1000_pch_ptp:
 	case e1000_pch_nvp:
 		if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)
 			adapter->ptp_clock_info.max_adj = MAX_PPB_24MHZ;
 		else
 			adapter->ptp_clock_info.max_adj = MAX_PPB_38400KHZ;
+		break;
+	case e1000_pch_mtp:
+	case e1000_pch_lnp:
+	case e1000_pch_ptp:
+		adapter->ptp_clock_info.max_adj = MAX_PPB_38400KHZ;
 		break;
 	case e1000_82574:
 	case e1000_82583:

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

···
 }
 
 /**
+ * ice_arfs_cmp - Check if aRFS filter matches this flow.
+ * @fltr_info: filter info of the saved ARFS entry.
+ * @fk: flow dissector keys.
+ * @n_proto:  One of htons(ETH_P_IP) or htons(ETH_P_IPV6).
+ * @ip_proto: One of IPPROTO_TCP or IPPROTO_UDP.
+ *
+ * Since this function assumes limited values for n_proto and ip_proto, it
+ * is meant to be called only from ice_rx_flow_steer().
+ *
+ * Return:
+ * * true	- fltr_info refers to the same flow as fk.
+ * * false	- fltr_info and fk refer to different flows.
+ */
+static bool
+ice_arfs_cmp(const struct ice_fdir_fltr *fltr_info, const struct flow_keys *fk,
+	     __be16 n_proto, u8 ip_proto)
+{
+	/* Determine if the filter is for IPv4 or IPv6 based on flow_type,
+	 * which is one of ICE_FLTR_PTYPE_NONF_IPV{4,6}_{TCP,UDP}.
+	 */
+	bool is_v4 = fltr_info->flow_type == ICE_FLTR_PTYPE_NONF_IPV4_TCP ||
+		     fltr_info->flow_type == ICE_FLTR_PTYPE_NONF_IPV4_UDP;
+
+	/* Following checks are arranged in the quickest and most discriminative
+	 * fields first for early failure.
+	 */
+	if (is_v4)
+		return n_proto == htons(ETH_P_IP) &&
+			fltr_info->ip.v4.src_port == fk->ports.src &&
+			fltr_info->ip.v4.dst_port == fk->ports.dst &&
+			fltr_info->ip.v4.src_ip == fk->addrs.v4addrs.src &&
+			fltr_info->ip.v4.dst_ip == fk->addrs.v4addrs.dst &&
+			fltr_info->ip.v4.proto == ip_proto;
+
+	return fltr_info->ip.v6.src_port == fk->ports.src &&
+		fltr_info->ip.v6.dst_port == fk->ports.dst &&
+		fltr_info->ip.v6.proto == ip_proto &&
+		!memcmp(&fltr_info->ip.v6.src_ip, &fk->addrs.v6addrs.src,
+			sizeof(struct in6_addr)) &&
+		!memcmp(&fltr_info->ip.v6.dst_ip, &fk->addrs.v6addrs.dst,
+			sizeof(struct in6_addr));
+}
+
+/**
  * ice_rx_flow_steer - steer the Rx flow to where application is being run
  * @netdev: ptr to the netdev being adjusted
  * @skb: buffer with required header information
···
 			continue;
 
 		fltr_info = &arfs_entry->fltr_info;
+
+		if (!ice_arfs_cmp(fltr_info, &fk, n_proto, ip_proto))
+			continue;
+
 		ret = fltr_info->fltr_id;
 
 		if (fltr_info->q_index == rxq_idx ||

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

···
  */
 int ice_eswitch_attach_vf(struct ice_pf *pf, struct ice_vf *vf)
 {
-	struct ice_repr *repr = ice_repr_create_vf(vf);
 	struct devlink *devlink = priv_to_devlink(pf);
+	struct ice_repr *repr;
 	int err;
 
+	if (!ice_is_eswitch_mode_switchdev(pf))
+		return 0;
+
+	repr = ice_repr_create_vf(vf);
 	if (IS_ERR(repr))
 		return PTR_ERR(repr);
 

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

···
 		req->chan_cnt = IEEE_8021QAZ_MAX_TCS;
 		req->bpid_per_chan = 1;
 	} else {
-		req->chan_cnt = 1;
+		req->chan_cnt = pfvf->hw.rx_chan_cnt;
 		req->bpid_per_chan = 0;
 	}
 
···
 		req->chan_cnt = IEEE_8021QAZ_MAX_TCS;
 		req->bpid_per_chan = 1;
 	} else {
-		req->chan_cnt = 1;
+		req->chan_cnt = pfvf->hw.rx_chan_cnt;
 		req->bpid_per_chan = 0;
 	}
 

drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c

···
 	priv->llu_plu_irq = platform_get_irq(pdev, MLXBF_GIGE_LLU_PLU_INTR_IDX);
 
 	phy_irq = acpi_dev_gpio_irq_get_by(ACPI_COMPANION(&pdev->dev), "phy", 0);
-	if (phy_irq < 0) {
-		dev_err(&pdev->dev, "Error getting PHY irq. Use polling instead");
+	if (phy_irq == -EPROBE_DEFER) {
+		err = -EPROBE_DEFER;
+		goto out;
+	} else if (phy_irq < 0) {
 		phy_irq = PHY_POLL;
 	}
 

drivers/net/ethernet/meta/fbnic/fbnic_fw.c

···
 		return -EBUSY;
 
 	addr = dma_map_single(fbd->dev, msg, PAGE_SIZE, direction);
-	if (dma_mapping_error(fbd->dev, addr)) {
-		free_page((unsigned long)msg);
-
+	if (dma_mapping_error(fbd->dev, addr))
 		return -ENOSPC;
-	}
 
 	mbx->buf_info[tail].msg = msg;
 	mbx->buf_info[tail].addr = addr;

drivers/net/ethernet/microchip/lan743x_ptp.h

···
  */
 #define LAN743X_PTP_N_EVENT_CHAN	2
 #define LAN743X_PTP_N_PEROUT		LAN743X_PTP_N_EVENT_CHAN
-#define LAN743X_PTP_N_EXTTS		4
-#define LAN743X_PTP_N_PPS		0
 #define PCI11X1X_PTP_IO_MAX_CHANNELS	8
+#define LAN743X_PTP_N_EXTTS		PCI11X1X_PTP_IO_MAX_CHANNELS
+#define LAN743X_PTP_N_PPS		0
 #define PTP_CMD_CTL_TIMEOUT_CNT		50
 
 struct lan743x_adapter;

drivers/net/ethernet/pensando/ionic/ionic_main.c

···
 	unsigned long start_time;
 	unsigned long max_wait;
 	unsigned long duration;
-	int done = 0;
 	bool fw_up;
 	int opcode;
+	bool done;
 	int err;
 
 	/* Wait for dev cmd to complete, retrying if we get EAGAIN,
···
 	 */
 	max_wait = jiffies + (max_seconds * HZ);
 try_again:
+	done = false;
 	opcode = idev->opcode;
 	start_time = jiffies;
 	for (fw_up = ionic_is_fw_running(idev);

drivers/net/ethernet/ti/icssg/icssg_common.c

···
 {
 	struct cppi5_host_desc_t *first_desc, *next_desc;
 	dma_addr_t buf_dma, next_desc_dma;
-	struct prueth_swdata *swdata;
-	struct page *page;
 	u32 buf_dma_len;
 
 	first_desc = desc;
 	next_desc = first_desc;
-
-	swdata = cppi5_hdesc_get_swdata(desc);
-	if (swdata->type == PRUETH_SWDATA_PAGE) {
-		page = swdata->data.page;
-		page_pool_recycle_direct(page->pp, swdata->data.page);
-		goto free_desc;
-	}
 
 	cppi5_hdesc_get_obuf(first_desc, &buf_dma, &buf_dma_len);
 	k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &buf_dma);
···
 		k3_cppi_desc_pool_free(tx_chn->desc_pool, next_desc);
 	}
 
-free_desc:
 	k3_cppi_desc_pool_free(tx_chn->desc_pool, first_desc);
 }
 EXPORT_SYMBOL_GPL(prueth_xmit_free);
···
 	k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &buf_dma);
 	cppi5_hdesc_attach_buf(first_desc, buf_dma, xdpf->len, buf_dma, xdpf->len);
 	swdata = cppi5_hdesc_get_swdata(first_desc);
-	if (page) {
-		swdata->type = PRUETH_SWDATA_PAGE;
-		swdata->data.page = page;
-	} else {
-		swdata->type = PRUETH_SWDATA_XDPF;
-		swdata->data.xdpf = xdpf;
-	}
+	swdata->type = PRUETH_SWDATA_XDPF;
+	swdata->data.xdpf = xdpf;
 
 	/* Report BQL before sending the packet */
 	netif_txq = netdev_get_tx_queue(ndev, tx_chn->id);

drivers/net/wireless/ath/ath12k/core.c

···
 	INIT_LIST_HEAD(&ar->fw_stats.pdevs);
 	INIT_LIST_HEAD(&ar->fw_stats.bcn);
 	init_completion(&ar->fw_stats_complete);
+	init_completion(&ar->fw_stats_done);
 }
 
 void ath12k_fw_stats_free(struct ath12k_fw_stats *stats)
···
 void ath12k_fw_stats_reset(struct ath12k *ar)
 {
 	spin_lock_bh(&ar->data_lock);
-	ar->fw_stats.fw_stats_done = false;
 	ath12k_fw_stats_free(&ar->fw_stats);
+	ar->fw_stats.num_vdev_recvd = 0;
+	ar->fw_stats.num_bcn_recvd = 0;
 	spin_unlock_bh(&ar->data_lock);
 }
 

drivers/net/wireless/ath/ath12k/core.h

···
 #define ATH12K_NUM_CHANS 101
 #define ATH12K_MAX_5GHZ_CHAN 173
 
+static inline bool ath12k_is_2ghz_channel_freq(u32 freq)
+{
+	return freq >= ATH12K_MIN_2GHZ_FREQ &&
+	       freq <= ATH12K_MAX_2GHZ_FREQ;
+}
+
 enum ath12k_hw_state {
 	ATH12K_HW_STATE_OFF,
 	ATH12K_HW_STATE_ON,
···
 	struct list_head pdevs;
 	struct list_head vdevs;
 	struct list_head bcn;
-	bool fw_stats_done;
+	u32 num_vdev_recvd;
+	u32 num_bcn_recvd;
 };
 
 struct ath12k_dbg_htt_stats {
···
 	bool regdom_set_by_user;
 
 	struct completion fw_stats_complete;
+	struct completion fw_stats_done;
 
 	struct completion mlo_setup_done;
 	u32 mlo_setup_status;

drivers/net/wireless/ath/ath12k/debugfs.c

···
 	 */
 }
 
-void
-ath12k_debugfs_fw_stats_process(struct ath12k *ar,
-				struct ath12k_fw_stats *stats)
-{
-	struct ath12k_base *ab = ar->ab;
-	struct ath12k_pdev *pdev;
-	bool is_end;
-	static unsigned int num_vdev, num_bcn;
-	size_t total_vdevs_started = 0;
-	int i;
-
-	if (stats->stats_id == WMI_REQUEST_VDEV_STAT) {
-		if (list_empty(&stats->vdevs)) {
-			ath12k_warn(ab, "empty vdev stats");
-			return;
-		}
-		/* FW sends all the active VDEV stats irrespective of PDEV,
-		 * hence limit until the count of all VDEVs started
-		 */
-		rcu_read_lock();
-		for (i = 0; i < ab->num_radios; i++) {
-			pdev = rcu_dereference(ab->pdevs_active[i]);
-			if (pdev && pdev->ar)
-				total_vdevs_started += pdev->ar->num_started_vdevs;
-		}
-		rcu_read_unlock();
-
-		is_end = ((++num_vdev) == total_vdevs_started);
-
-		list_splice_tail_init(&stats->vdevs,
-				      &ar->fw_stats.vdevs);
-
-		if (is_end) {
-			ar->fw_stats.fw_stats_done = true;
-			num_vdev = 0;
-		}
-		return;
-	}
-	if (stats->stats_id == WMI_REQUEST_BCN_STAT) {
-		if (list_empty(&stats->bcn)) {
-			ath12k_warn(ab, "empty beacon stats");
-			return;
-		}
-		/* Mark end until we reached the count of all started VDEVs
-		 * within the PDEV
-		 */
-		is_end = ((++num_bcn) == ar->num_started_vdevs);
-
-		list_splice_tail_init(&stats->bcn,
-				      &ar->fw_stats.bcn);
-
-		if (is_end) {
-			ar->fw_stats.fw_stats_done = true;
-			num_bcn = 0;
-		}
-	}
-}
-
 static int ath12k_open_vdev_stats(struct inode *inode, struct file *file)
 {
 	struct ath12k *ar = inode->i_private;

drivers/net/wireless/ath/ath12k/debugfs.h

···
 void ath12k_debugfs_soc_destroy(struct ath12k_base *ab);
 void ath12k_debugfs_register(struct ath12k *ar);
 void ath12k_debugfs_unregister(struct ath12k *ar);
-void ath12k_debugfs_fw_stats_process(struct ath12k *ar,
-				     struct ath12k_fw_stats *stats);
 void ath12k_debugfs_op_vif_add(struct ieee80211_hw *hw,
 			       struct ieee80211_vif *vif);
 void ath12k_debugfs_pdev_create(struct ath12k_base *ab);
···
 }
 
 static inline void ath12k_debugfs_unregister(struct ath12k *ar)
-{
-}
-
-static inline void ath12k_debugfs_fw_stats_process(struct ath12k *ar,
-						   struct ath12k_fw_stats *stats)
 {
 }
 

drivers/net/wireless/ath/ath12k/mac.c

···
 {
 	struct ath12k_base *ab = ar->ab;
 	struct ath12k_hw *ah = ath12k_ar_to_ah(ar);
-	unsigned long timeout, time_left;
+	unsigned long time_left;
 	int ret;
 
 	guard(mutex)(&ah->hw_mutex);
···
 	if (ah->state != ATH12K_HW_STATE_ON)
 		return -ENETDOWN;
 
-	/* FW stats can get split when exceeding the stats data buffer limit.
-	 * In that case, since there is no end marking for the back-to-back
-	 * received 'update stats' event, we keep a 3 seconds timeout in case,
-	 * fw_stats_done is not marked yet
-	 */
-	timeout = jiffies + msecs_to_jiffies(3 * 1000);
 	ath12k_fw_stats_reset(ar);
 
 	reinit_completion(&ar->fw_stats_complete);
+	reinit_completion(&ar->fw_stats_done);
 
 	ret = ath12k_wmi_send_stats_request_cmd(ar, param->stats_id,
 						param->vdev_id, param->pdev_id);
-
 	if (ret) {
 		ath12k_warn(ab, "failed to request fw stats: %d\n", ret);
 		return ret;
···
 		   param->pdev_id, param->vdev_id, param->stats_id);
 
 	time_left = wait_for_completion_timeout(&ar->fw_stats_complete, 1 * HZ);
-
 	if (!time_left) {
 		ath12k_warn(ab, "time out while waiting for get fw stats\n");
 		return -ETIMEDOUT;
···
 	/* Firmware sends WMI_UPDATE_STATS_EVENTID back-to-back
 	 * when stats data buffer limit is reached. fw_stats_complete
 	 * is completed once host receives first event from firmware, but
-	 * still end might not be marked in the TLV.
-	 * Below loop is to confirm that firmware completed sending all the event
-	 * and fw_stats_done is marked true when end is marked in the TLV.
+	 * still there could be more events following. Below is to wait
+	 * until firmware completes sending all the events.
 	 */
-	for (;;) {
-		if (time_after(jiffies, timeout))
-			break;
-		spin_lock_bh(&ar->data_lock);
-		if (ar->fw_stats.fw_stats_done) {
-			spin_unlock_bh(&ar->data_lock);
-			break;
-		}
-		spin_unlock_bh(&ar->data_lock);
+	time_left = wait_for_completion_timeout(&ar->fw_stats_done, 3 * HZ);
+	if (!time_left) {
+		ath12k_warn(ab, "time out while waiting for fw stats done\n");
+		return -ETIMEDOUT;
 	}
+
 	return 0;
 }
 
···
 	return ret;
 }
 
+static bool ath12k_mac_is_freq_on_mac(struct ath12k_hw_mode_freq_range_arg *freq_range,
+				      u32 freq, u8 mac_id)
+{
+	return (freq >= freq_range[mac_id].low_2ghz_freq &&
+		freq <= freq_range[mac_id].high_2ghz_freq) ||
+	       (freq >= freq_range[mac_id].low_5ghz_freq &&
+		freq <= freq_range[mac_id].high_5ghz_freq);
+}
+
+static bool
+ath12k_mac_2_freq_same_mac_in_freq_range(struct ath12k_base *ab,
+					 struct ath12k_hw_mode_freq_range_arg *freq_range,
+					 u32 freq_link1, u32 freq_link2)
+{
+	u8 i;
+
+	for (i = 0; i < MAX_RADIOS; i++) {
+		if (ath12k_mac_is_freq_on_mac(freq_range, freq_link1, i) &&
+		    ath12k_mac_is_freq_on_mac(freq_range, freq_link2, i))
+			return true;
+	}
+
+	return false;
+}
+
+static bool ath12k_mac_is_hw_dbs_capable(struct ath12k_base *ab)
+{
+	return test_bit(WMI_TLV_SERVICE_DUAL_BAND_SIMULTANEOUS_SUPPORT,
+			ab->wmi_ab.svc_map) &&
+	       ab->wmi_ab.hw_mode_info.support_dbs;
+}
+
+static bool ath12k_mac_2_freq_same_mac_in_dbs(struct ath12k_base *ab,
+					      u32 freq_link1, u32 freq_link2)
+{
+	struct ath12k_hw_mode_freq_range_arg *freq_range;
+
+	if (!ath12k_mac_is_hw_dbs_capable(ab))
+		return true;
+
+	freq_range = ab->wmi_ab.hw_mode_info.freq_range_caps[ATH12K_HW_MODE_DBS];
+	return ath12k_mac_2_freq_same_mac_in_freq_range(ab, freq_range,
+							freq_link1, freq_link2);
+}
+
+static bool ath12k_mac_is_hw_sbs_capable(struct ath12k_base *ab)
+{
+	return test_bit(WMI_TLV_SERVICE_DUAL_BAND_SIMULTANEOUS_SUPPORT,
+			ab->wmi_ab.svc_map) &&
+	       ab->wmi_ab.hw_mode_info.support_sbs;
+}
+
+static bool ath12k_mac_2_freq_same_mac_in_sbs(struct ath12k_base *ab,
+					      u32 freq_link1, u32 freq_link2)
+{
+	struct ath12k_hw_mode_info *info = &ab->wmi_ab.hw_mode_info;
+	struct ath12k_hw_mode_freq_range_arg *sbs_uppr_share;
+	struct ath12k_hw_mode_freq_range_arg *sbs_low_share;
+	struct ath12k_hw_mode_freq_range_arg *sbs_range;
+
+	if (!ath12k_mac_is_hw_sbs_capable(ab))
+		return true;
+
+	if (ab->wmi_ab.sbs_lower_band_end_freq) {
+		sbs_uppr_share = info->freq_range_caps[ATH12K_HW_MODE_SBS_UPPER_SHARE];
+		sbs_low_share = info->freq_range_caps[ATH12K_HW_MODE_SBS_LOWER_SHARE];
+
+		return ath12k_mac_2_freq_same_mac_in_freq_range(ab, sbs_low_share,
+								freq_link1, freq_link2) ||
+		       ath12k_mac_2_freq_same_mac_in_freq_range(ab, sbs_uppr_share,
+								freq_link1, freq_link2);
+	}
+
+	sbs_range = info->freq_range_caps[ATH12K_HW_MODE_SBS];
+	return ath12k_mac_2_freq_same_mac_in_freq_range(ab, sbs_range,
+							freq_link1, freq_link2);
+}
+
+static bool ath12k_mac_freqs_on_same_mac(struct ath12k_base *ab,
+					 u32 freq_link1, u32 freq_link2)
+{
+	return ath12k_mac_2_freq_same_mac_in_dbs(ab, freq_link1, freq_link2) &&
+	       ath12k_mac_2_freq_same_mac_in_sbs(ab, freq_link1, freq_link2);
+}
+
+static int ath12k_mac_mlo_sta_set_link_active(struct ath12k_base *ab,
+					      enum wmi_mlo_link_force_reason reason,
+					      enum wmi_mlo_link_force_mode mode,
+					      u8 *mlo_vdev_id_lst,
+					      u8 num_mlo_vdev,
+					      u8 *mlo_inactive_vdev_lst,
+					      u8 num_mlo_inactive_vdev)
+{
+	struct wmi_mlo_link_set_active_arg param = {0};
+	u32 entry_idx, entry_offset, vdev_idx;
+	u8 vdev_id;
+
+	param.reason = reason;
+	param.force_mode = mode;
+
+	for (vdev_idx = 0; vdev_idx < num_mlo_vdev; vdev_idx++) {
+		vdev_id = mlo_vdev_id_lst[vdev_idx];
+		entry_idx = vdev_id / 32;
+		entry_offset = vdev_id % 32;
+		if (entry_idx >= WMI_MLO_LINK_NUM_SZ) {
+			ath12k_warn(ab, "Invalid entry_idx %d num_mlo_vdev %d vdev %d",
+				    entry_idx, num_mlo_vdev, vdev_id);
+			return -EINVAL;
+		}
+		param.vdev_bitmap[entry_idx] |= 1 << entry_offset;
+		/* update entry number if entry index changed */
+		if (param.num_vdev_bitmap < entry_idx + 1)
+			param.num_vdev_bitmap = entry_idx + 1;
+	}
+
+	ath12k_dbg(ab, ATH12K_DBG_MAC,
+		   "num_vdev_bitmap %d vdev_bitmap[0] = 0x%x, vdev_bitmap[1] = 0x%x",
+		   param.num_vdev_bitmap, param.vdev_bitmap[0], param.vdev_bitmap[1]);
+
+	if (mode == WMI_MLO_LINK_FORCE_MODE_ACTIVE_INACTIVE) {
+		for (vdev_idx = 0; vdev_idx < num_mlo_inactive_vdev; vdev_idx++) {
+			vdev_id = mlo_inactive_vdev_lst[vdev_idx];
+			entry_idx = vdev_id / 32;
+			entry_offset = vdev_id % 32;
+			if (entry_idx >= WMI_MLO_LINK_NUM_SZ) {
+				ath12k_warn(ab, "Invalid entry_idx %d num_mlo_vdev %d vdev %d",
+					    entry_idx, num_mlo_inactive_vdev, vdev_id);
+				return -EINVAL;
+			}
+			param.inactive_vdev_bitmap[entry_idx] |= 1 << entry_offset;
+			/* update entry number if entry index changed */
+			if (param.num_inactive_vdev_bitmap < entry_idx + 1)
+				param.num_inactive_vdev_bitmap = entry_idx + 1;
+		}
+
+		ath12k_dbg(ab, ATH12K_DBG_MAC,
+			   "num_vdev_bitmap %d inactive_vdev_bitmap[0] = 0x%x, inactive_vdev_bitmap[1] = 0x%x",
+			   param.num_inactive_vdev_bitmap,
+			   param.inactive_vdev_bitmap[0],
+			   param.inactive_vdev_bitmap[1]);
+	}
+
+	if (mode == WMI_MLO_LINK_FORCE_MODE_ACTIVE_LINK_NUM ||
+	    mode == WMI_MLO_LINK_FORCE_MODE_INACTIVE_LINK_NUM) {
+		param.num_link_entry = 1;
+		param.link_num[0].num_of_link = num_mlo_vdev - 1;
+	}
+
+	return ath12k_wmi_send_mlo_link_set_active_cmd(ab, &param);
+}
+
+static int ath12k_mac_mlo_sta_update_link_active(struct ath12k_base *ab,
+						 struct ieee80211_hw *hw,
+						 struct ath12k_vif *ahvif)
+{
+	u8 mlo_vdev_id_lst[IEEE80211_MLD_MAX_NUM_LINKS] = {0};
+	u32 mlo_freq_list[IEEE80211_MLD_MAX_NUM_LINKS] = {0};
+	unsigned long links = ahvif->links_map;
+	enum wmi_mlo_link_force_reason reason;
+	struct ieee80211_chanctx_conf *conf;
+	enum wmi_mlo_link_force_mode mode;
+	struct ieee80211_bss_conf *info;
+	struct ath12k_link_vif *arvif;
+	u8 num_mlo_vdev = 0;
+	u8 link_id;
+
+	for_each_set_bit(link_id, &links, IEEE80211_MLD_MAX_NUM_LINKS) {
+		arvif = wiphy_dereference(hw->wiphy, ahvif->link[link_id]);
+		/* make sure vdev is created on this device */
+		if (!arvif || !arvif->is_created || arvif->ar->ab != ab)
+			continue;
+
+		info = ath12k_mac_get_link_bss_conf(arvif);
+		conf = wiphy_dereference(hw->wiphy, info->chanctx_conf);
+		mlo_freq_list[num_mlo_vdev] = conf->def.chan->center_freq;
+
+		mlo_vdev_id_lst[num_mlo_vdev] = arvif->vdev_id;
+		num_mlo_vdev++;
+	}
+
+	/* It is not allowed to activate more links than a single device
+	 * supported. Something goes wrong if we reach here.
+	 */
+	if (num_mlo_vdev > ATH12K_NUM_MAX_ACTIVE_LINKS_PER_DEVICE) {
+		WARN_ON_ONCE(1);
+		return -EINVAL;
+	}
+
+	/* if 2 links are established and both link channels fall on the
+	 * same hardware MAC, send command to firmware to deactivate one
+	 * of them.
+	 */
+	if (num_mlo_vdev == 2 &&
+	    ath12k_mac_freqs_on_same_mac(ab, mlo_freq_list[0],
+					 mlo_freq_list[1])) {
+		mode = WMI_MLO_LINK_FORCE_MODE_INACTIVE_LINK_NUM;
+		reason = WMI_MLO_LINK_FORCE_REASON_NEW_CONNECT;
+		return ath12k_mac_mlo_sta_set_link_active(ab, reason, mode,
+							  mlo_vdev_id_lst, num_mlo_vdev,
+							  NULL, 0);
+	}
+
+	return 0;
+}
+
+static bool ath12k_mac_are_sbs_chan(struct ath12k_base *ab, u32 freq_1, u32 freq_2)
+{
+	if (!ath12k_mac_is_hw_sbs_capable(ab))
+		return false;
+
+	if (ath12k_is_2ghz_channel_freq(freq_1) ||
+	    ath12k_is_2ghz_channel_freq(freq_2))
+		return false;
+
+	return !ath12k_mac_2_freq_same_mac_in_sbs(ab, freq_1, freq_2);
+}
+
+static bool ath12k_mac_are_dbs_chan(struct ath12k_base *ab, u32 freq_1, u32 freq_2)
+{
+	if (!ath12k_mac_is_hw_dbs_capable(ab))
+		return false;
+
+	return !ath12k_mac_2_freq_same_mac_in_dbs(ab, freq_1, freq_2);
+}
+
+static int ath12k_mac_select_links(struct ath12k_base *ab,
+				   struct ieee80211_vif *vif,
+				   struct ieee80211_hw *hw,
+				   u16 *selected_links)
+{
+	unsigned long useful_links = ieee80211_vif_usable_links(vif);
+	struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif);
+	u8 num_useful_links = hweight_long(useful_links);
+	struct ieee80211_chanctx_conf *chanctx;
+	struct ath12k_link_vif *assoc_arvif;
+	u32 assoc_link_freq, partner_freq;
+	u16 sbs_links = 0, dbs_links = 0;
+	struct ieee80211_bss_conf *info;
+	struct ieee80211_channel *chan;
+	struct ieee80211_sta *sta;
+	struct ath12k_sta *ahsta;
+	u8 link_id;
+
+	/* activate all useful links if less than max supported */
+	if (num_useful_links <= ATH12K_NUM_MAX_ACTIVE_LINKS_PER_DEVICE) {
+		*selected_links = useful_links;
+		return 0;
+	}
+
+	/* only in station mode we can get here, so it's safe
+	 * to use ap_addr
+	 */
+	rcu_read_lock();
+	sta = ieee80211_find_sta(vif, vif->cfg.ap_addr);
+	if (!sta) {
+		rcu_read_unlock();
+		ath12k_warn(ab, "failed to find sta with addr %pM\n", vif->cfg.ap_addr);
+		return -EINVAL;
+	}
+
+	ahsta = ath12k_sta_to_ahsta(sta);
+	assoc_arvif = wiphy_dereference(hw->wiphy, ahvif->link[ahsta->assoc_link_id]);
+	info = ath12k_mac_get_link_bss_conf(assoc_arvif);
+	chanctx = rcu_dereference(info->chanctx_conf);
+	assoc_link_freq = chanctx->def.chan->center_freq;
+	rcu_read_unlock();
+	ath12k_dbg(ab, ATH12K_DBG_MAC, "assoc link %u freq %u\n",
+		   assoc_arvif->link_id, assoc_link_freq);
+
+	/* assoc link is already activated and has to be kept active,
+	 * only need to select a partner link from others.
+	 */
+	useful_links &= ~BIT(assoc_arvif->link_id);
+	for_each_set_bit(link_id, &useful_links, IEEE80211_MLD_MAX_NUM_LINKS) {
+		info = wiphy_dereference(hw->wiphy, vif->link_conf[link_id]);
+		if (!info) {
+			ath12k_warn(ab, "failed to get link info for link: %u\n",
+				    link_id);
+			return -ENOLINK;
+		}
+
+		chan = info->chanreq.oper.chan;
+		if (!chan) {
+			ath12k_warn(ab, "failed to get chan for link: %u\n", link_id);
+			return -EINVAL;
+		}
+
+		partner_freq = chan->center_freq;
+		if (ath12k_mac_are_sbs_chan(ab, assoc_link_freq, partner_freq)) {
+			sbs_links |= BIT(link_id);
+			ath12k_dbg(ab, ATH12K_DBG_MAC, "new SBS link %u freq %u\n",
+				   link_id, partner_freq);
+			continue;
+		}
+
+		if (ath12k_mac_are_dbs_chan(ab, assoc_link_freq, partner_freq)) {
+			dbs_links |= BIT(link_id);
+			ath12k_dbg(ab, ATH12K_DBG_MAC, "new DBS link %u freq %u\n",
+				   link_id, partner_freq);
+			continue;
+		}
+
+		ath12k_dbg(ab, ATH12K_DBG_MAC, "non DBS/SBS link %u freq %u\n",
+			   link_id, partner_freq);
+	}
+
+	/* choose the first candidate no matter how many is in the list */
+	if (sbs_links)
+		link_id = __ffs(sbs_links);
+	else if (dbs_links)
+		link_id = __ffs(dbs_links);
+	else
+		link_id = ffs(useful_links) - 1;
+
+	ath12k_dbg(ab, ATH12K_DBG_MAC, "select partner link %u\n", link_id);
+
+	*selected_links = BIT(assoc_arvif->link_id) | BIT(link_id);
+
+	return 0;
+}
+
 static int ath12k_mac_op_sta_state(struct ieee80211_hw *hw,
 				   struct ieee80211_vif *vif,
 				   struct ieee80211_sta *sta,
···
 	struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif);
 	struct ath12k_sta *ahsta = ath12k_sta_to_ahsta(sta);
 	struct ath12k_hw *ah = ath12k_hw_to_ah(hw);
+	struct ath12k_base *prev_ab = NULL, *ab;
 	struct ath12k_link_vif *arvif;
 	struct ath12k_link_sta *arsta;
 	unsigned long valid_links;
-	u8 link_id = 0;
+	u16 selected_links = 0;
+	u8 link_id = 0, i;
+	struct ath12k *ar;
 	int ret;
 
 	lockdep_assert_wiphy(hw->wiphy);
···
 	 * about to move to the associated state.
 	 */
 	if (ieee80211_vif_is_mld(vif) && vif->type == NL80211_IFTYPE_STATION &&
-	    old_state == IEEE80211_STA_AUTH && new_state == IEEE80211_STA_ASSOC)
-		ieee80211_set_active_links(vif, ieee80211_vif_usable_links(vif));
+	    old_state == IEEE80211_STA_AUTH && new_state == IEEE80211_STA_ASSOC) {
+		/* TODO: for now only do link selection for single device
+		 * MLO case. Other cases would be handled in the future.
+		 */
+		ab = ah->radio[0].ab;
+		if (ab->ag->num_devices == 1) {
+			ret = ath12k_mac_select_links(ab, vif, hw, &selected_links);
+			if (ret) {
+				ath12k_warn(ab,
+					    "failed to get selected links: %d\n", ret);
+				goto exit;
+			}
+		} else {
+			selected_links = ieee80211_vif_usable_links(vif);
+		}
+
+		ieee80211_set_active_links(vif, selected_links);
+	}
 
 	/* Handle all the other state transitions in generic way */
 	valid_links = ahsta->links_map;
···
 		}
 	}
 
+	if (ieee80211_vif_is_mld(vif) && vif->type == NL80211_IFTYPE_STATION &&
+	    old_state == IEEE80211_STA_ASSOC && new_state == IEEE80211_STA_AUTHORIZED) {
+		for_each_ar(ah, ar, i) {
+			ab = ar->ab;
+			if (prev_ab == ab)
+				continue;
+
+			ret = ath12k_mac_mlo_sta_update_link_active(ab, hw, ahvif);
+			if (ret) {
+				ath12k_warn(ab,
+					    "failed to update link active state on connect %d\n",
+					    ret);
+				goto exit;
+			}
+
+			prev_ab = ab;
+		}
+	}
 	/* IEEE80211_STA_NONE -> IEEE80211_STA_NOTEXIST:
 	 * Remove the station from driver (handle ML sta here since that
 	 * needs special handling. Normal sta will be handled in generic

drivers/net/wireless/ath/ath12k/mac.h

···
 #define ATH12K_DEFAULT_SCAN_LINK	IEEE80211_MLD_MAX_NUM_LINKS
 #define ATH12K_NUM_MAX_LINKS		(IEEE80211_MLD_MAX_NUM_LINKS + 1)
 
+#define ATH12K_NUM_MAX_ACTIVE_LINKS_PER_DEVICE	2
+
 enum ath12k_supported_bw {
 	ATH12K_BW_20    = 0,
 	ATH12K_BW_40    = 1,

drivers/net/wireless/ath/ath12k/wmi.c

···
 	bool dma_ring_cap_done;
 	bool spectral_bin_scaling_done;
 	bool mac_phy_caps_ext_done;
+	bool hal_reg_caps_ext2_done;
+	bool scan_radio_caps_ext2_done;
+	bool twt_caps_done;
+	bool htt_msdu_idx_to_qtype_map_done;
+	bool dbs_or_sbs_cap_ext_done;
 };
 
 struct ath12k_wmi_rdy_parse {
···
 static int ath12k_wmi_hw_mode_caps(struct ath12k_base *soc,
 				   u16 len, const void *ptr, void *data)
 {
+	struct ath12k_svc_ext_info *svc_ext_info = &soc->wmi_ab.svc_ext_info;
 	struct ath12k_wmi_svc_rdy_ext_parse *svc_rdy_ext = data;
 	const struct ath12k_wmi_hw_mode_cap_params *hw_mode_caps;
 	enum wmi_host_hw_mode_config_type mode, pref;
···
 		}
 	}
 
-	ath12k_dbg(soc, ATH12K_DBG_WMI, "preferred_hw_mode:%d\n",
-		   soc->wmi_ab.preferred_hw_mode);
+	svc_ext_info->num_hw_modes = svc_rdy_ext->n_hw_mode_caps;
+
+	ath12k_dbg(soc, ATH12K_DBG_WMI, "num hw modes %u preferred_hw_mode %d\n",
+		   svc_ext_info->num_hw_modes, soc->wmi_ab.preferred_hw_mode);
+
 	if (soc->wmi_ab.preferred_hw_mode == WMI_HOST_HW_MODE_MAX)
 		return -EINVAL;
 
···
 	return ret;
 }
 
+static void
+ath12k_wmi_save_mac_phy_info(struct ath12k_base *ab,
+			     const struct ath12k_wmi_mac_phy_caps_params *mac_phy_cap,
+			     struct ath12k_svc_ext_mac_phy_info *mac_phy_info)
+{
+	mac_phy_info->phy_id = __le32_to_cpu(mac_phy_cap->phy_id);
+	mac_phy_info->supported_bands = __le32_to_cpu(mac_phy_cap->supported_bands);
+	mac_phy_info->hw_freq_range.low_2ghz_freq =
+					__le32_to_cpu(mac_phy_cap->low_2ghz_chan_freq);
+	mac_phy_info->hw_freq_range.high_2ghz_freq =
+					__le32_to_cpu(mac_phy_cap->high_2ghz_chan_freq);
+	mac_phy_info->hw_freq_range.low_5ghz_freq =
+					__le32_to_cpu(mac_phy_cap->low_5ghz_chan_freq);
+	mac_phy_info->hw_freq_range.high_5ghz_freq =
+					__le32_to_cpu(mac_phy_cap->high_5ghz_chan_freq);
+}
+
+static void
+ath12k_wmi_save_all_mac_phy_info(struct ath12k_base *ab,
+				 struct ath12k_wmi_svc_rdy_ext_parse *svc_rdy_ext)
+{
+	struct ath12k_svc_ext_info *svc_ext_info = &ab->wmi_ab.svc_ext_info;
+	const struct ath12k_wmi_mac_phy_caps_params *mac_phy_cap;
+	const struct ath12k_wmi_hw_mode_cap_params *hw_mode_cap;
+	struct ath12k_svc_ext_mac_phy_info *mac_phy_info;
+	u32 hw_mode_id, phy_bit_map;
+	u8 hw_idx;
+
+	mac_phy_info = &svc_ext_info->mac_phy_info[0];
+	mac_phy_cap = svc_rdy_ext->mac_phy_caps;
+
+	for (hw_idx = 0; hw_idx < svc_ext_info->num_hw_modes; hw_idx++) {
+		hw_mode_cap = &svc_rdy_ext->hw_mode_caps[hw_idx];
+		hw_mode_id = __le32_to_cpu(hw_mode_cap->hw_mode_id);
+		phy_bit_map = __le32_to_cpu(hw_mode_cap->phy_id_map);
+
+		while (phy_bit_map) {
+			ath12k_wmi_save_mac_phy_info(ab, mac_phy_cap, mac_phy_info);
+			mac_phy_info->hw_mode_config_type =
+					le32_get_bits(hw_mode_cap->hw_mode_config_type,
+						      WMI_HW_MODE_CAP_CFG_TYPE);
+			ath12k_dbg(ab, ATH12K_DBG_WMI,
+				   "hw_idx %u hw_mode_id %u hw_mode_config_type %u supported_bands %u phy_id %u 2 GHz [%u - %u] 5 GHz [%u - %u]\n",
+				   hw_idx, hw_mode_id,
+				   mac_phy_info->hw_mode_config_type,
+				   mac_phy_info->supported_bands, mac_phy_info->phy_id,
+				   mac_phy_info->hw_freq_range.low_2ghz_freq,
+				   mac_phy_info->hw_freq_range.high_2ghz_freq,
+				   mac_phy_info->hw_freq_range.low_5ghz_freq,
+				   mac_phy_info->hw_freq_range.high_5ghz_freq);
+
+			mac_phy_cap++;
+			mac_phy_info++;
+
+			phy_bit_map >>= 1;
+		}
+	}
+}
+
 static int ath12k_wmi_svc_rdy_ext_parse(struct ath12k_base *ab,
 					u16 tag, u16 len,
 					const void *ptr, void *data)
···
 				ath12k_warn(ab, "failed to parse tlv %d\n", ret);
 				return ret;
 			}
+
+			ath12k_wmi_save_all_mac_phy_info(ab, svc_rdy_ext);
 
 			svc_rdy_ext->mac_phy_done = true;
 		} else if (!svc_rdy_ext->ext_hal_reg_done) {
···
 	return 0;
 }
 
+static void
+ath12k_wmi_update_freq_info(struct ath12k_base *ab,
+			    struct ath12k_svc_ext_mac_phy_info *mac_cap,
+			    enum ath12k_hw_mode mode,
+			    u32 phy_id)
+{
+	struct ath12k_hw_mode_info *hw_mode_info = &ab->wmi_ab.hw_mode_info;
+	struct ath12k_hw_mode_freq_range_arg *mac_range;
+
+	mac_range = &hw_mode_info->freq_range_caps[mode][phy_id];
+
+	if (mac_cap->supported_bands & WMI_HOST_WLAN_2GHZ_CAP) {
+		mac_range->low_2ghz_freq = max_t(u32,
+						 mac_cap->hw_freq_range.low_2ghz_freq,
+						 ATH12K_MIN_2GHZ_FREQ);
+		mac_range->high_2ghz_freq = mac_cap->hw_freq_range.high_2ghz_freq ?
+					    min_t(u32,
+						  mac_cap->hw_freq_range.high_2ghz_freq,
+						  ATH12K_MAX_2GHZ_FREQ) :
+					    ATH12K_MAX_2GHZ_FREQ;
+	}
+
+	if (mac_cap->supported_bands & WMI_HOST_WLAN_5GHZ_CAP) {
+		mac_range->low_5ghz_freq = max_t(u32,
+						 mac_cap->hw_freq_range.low_5ghz_freq,
+						 ATH12K_MIN_5GHZ_FREQ);
+		mac_range->high_5ghz_freq = mac_cap->hw_freq_range.high_5ghz_freq ?
+					    min_t(u32,
+						  mac_cap->hw_freq_range.high_5ghz_freq,
+						  ATH12K_MAX_6GHZ_FREQ) :
+					    ATH12K_MAX_6GHZ_FREQ;
+	}
+}
+
+static bool
+ath12k_wmi_all_phy_range_updated(struct ath12k_base *ab,
+				 enum ath12k_hw_mode hwmode)
+{
+	struct ath12k_hw_mode_info *hw_mode_info = &ab->wmi_ab.hw_mode_info;
+	struct ath12k_hw_mode_freq_range_arg *mac_range;
+	u8 phy_id;
+
+	for (phy_id = 0; phy_id < MAX_RADIOS; phy_id++) {
+		mac_range = &hw_mode_info->freq_range_caps[hwmode][phy_id];
+		/* modify SBS/DBS range only when both phy for DBS are filled */
+		if (!mac_range->low_2ghz_freq && !mac_range->low_5ghz_freq)
+			return false;
+	}
+
+	return true;
+}
+
+static void ath12k_wmi_update_dbs_freq_info(struct ath12k_base *ab)
+{
+	struct ath12k_hw_mode_info *hw_mode_info = &ab->wmi_ab.hw_mode_info;
+	struct ath12k_hw_mode_freq_range_arg *mac_range;
+	u8 phy_id;
+
+	mac_range = hw_mode_info->freq_range_caps[ATH12K_HW_MODE_DBS];
+	/* Reset 5 GHz range for shared mac for DBS */
+	for (phy_id = 0; phy_id < MAX_RADIOS; phy_id++) {
+		if (mac_range[phy_id].low_2ghz_freq &&
+		    mac_range[phy_id].low_5ghz_freq) {
+			mac_range[phy_id].low_5ghz_freq = 0;
+			mac_range[phy_id].high_5ghz_freq = 0;
+		}
+	}
+}
+
+static u32
+ath12k_wmi_get_highest_5ghz_freq_from_range(struct ath12k_hw_mode_freq_range_arg *range)
+{
+	u32 highest_freq = 0;
+	u8 phy_id;
+
+	for (phy_id = 0; phy_id < MAX_RADIOS; phy_id++) {
+		if (range[phy_id].high_5ghz_freq > highest_freq)
+			highest_freq = range[phy_id].high_5ghz_freq;
+	}
+
+	return highest_freq ? highest_freq : ATH12K_MAX_6GHZ_FREQ;
+}
+
+static u32
+ath12k_wmi_get_lowest_5ghz_freq_from_range(struct ath12k_hw_mode_freq_range_arg *range)
+{
+	u32 lowest_freq = 0;
+	u8 phy_id;
+
+	for (phy_id = 0; phy_id < MAX_RADIOS; phy_id++) {
+		if ((!lowest_freq && range[phy_id].low_5ghz_freq) ||
+		    range[phy_id].low_5ghz_freq < lowest_freq)
+			lowest_freq = range[phy_id].low_5ghz_freq;
+	}
+
+	return lowest_freq ? lowest_freq : ATH12K_MIN_5GHZ_FREQ;
+}
+
+static void
+ath12k_wmi_fill_upper_share_sbs_freq(struct ath12k_base *ab,
+				     u16 sbs_range_sep,
+				     struct ath12k_hw_mode_freq_range_arg *ref_freq)
+{
+	struct ath12k_hw_mode_info *hw_mode_info = &ab->wmi_ab.hw_mode_info;
+	struct ath12k_hw_mode_freq_range_arg *upper_sbs_freq_range;
+	u8 phy_id;
+
+	upper_sbs_freq_range =
+			hw_mode_info->freq_range_caps[ATH12K_HW_MODE_SBS_UPPER_SHARE];
+
+	for (phy_id = 0; phy_id < MAX_RADIOS; phy_id++) {
+		upper_sbs_freq_range[phy_id].low_2ghz_freq =
+						ref_freq[phy_id].low_2ghz_freq;
+		upper_sbs_freq_range[phy_id].high_2ghz_freq =
+						ref_freq[phy_id].high_2ghz_freq;
+
+		/* update for shared mac */
+		if (upper_sbs_freq_range[phy_id].low_2ghz_freq) {
+			upper_sbs_freq_range[phy_id].low_5ghz_freq = sbs_range_sep + 10;
+			upper_sbs_freq_range[phy_id].high_5ghz_freq =
+				ath12k_wmi_get_highest_5ghz_freq_from_range(ref_freq);
+		} else {
+			upper_sbs_freq_range[phy_id].low_5ghz_freq =
+				ath12k_wmi_get_lowest_5ghz_freq_from_range(ref_freq);
+			upper_sbs_freq_range[phy_id].high_5ghz_freq = sbs_range_sep;
+		}
+	}
+}
+
+static void
+ath12k_wmi_fill_lower_share_sbs_freq(struct ath12k_base *ab,
+				     u16 sbs_range_sep,
+				     struct ath12k_hw_mode_freq_range_arg *ref_freq)
+{
+	struct ath12k_hw_mode_info *hw_mode_info = &ab->wmi_ab.hw_mode_info;
+	struct ath12k_hw_mode_freq_range_arg *lower_sbs_freq_range;
+	u8 phy_id;
+
+	lower_sbs_freq_range =
+			hw_mode_info->freq_range_caps[ATH12K_HW_MODE_SBS_LOWER_SHARE];
+
+	for (phy_id = 0; phy_id < MAX_RADIOS; phy_id++) {
+		lower_sbs_freq_range[phy_id].low_2ghz_freq =
+						ref_freq[phy_id].low_2ghz_freq;
+		lower_sbs_freq_range[phy_id].high_2ghz_freq =
+						ref_freq[phy_id].high_2ghz_freq;
+
+		/* update for shared mac */
+		if (lower_sbs_freq_range[phy_id].low_2ghz_freq) {
+			lower_sbs_freq_range[phy_id].low_5ghz_freq =
+				ath12k_wmi_get_lowest_5ghz_freq_from_range(ref_freq);
+			lower_sbs_freq_range[phy_id].high_5ghz_freq = sbs_range_sep;
+		} else {
+			lower_sbs_freq_range[phy_id].low_5ghz_freq = sbs_range_sep + 10;
+			lower_sbs_freq_range[phy_id].high_5ghz_freq =
+				ath12k_wmi_get_highest_5ghz_freq_from_range(ref_freq);
+		}
+	}
+}
+
+static const char *ath12k_wmi_hw_mode_to_str(enum ath12k_hw_mode hw_mode)
+{
+	static const char * const mode_str[] = {
+		[ATH12K_HW_MODE_SMM] = "SMM",
+		[ATH12K_HW_MODE_DBS] = "DBS",
+		[ATH12K_HW_MODE_SBS] = "SBS",
+		[ATH12K_HW_MODE_SBS_UPPER_SHARE] = "SBS_UPPER_SHARE",
+		[ATH12K_HW_MODE_SBS_LOWER_SHARE] = "SBS_LOWER_SHARE",
+	};
+
+	if (hw_mode >= ARRAY_SIZE(mode_str))
+		return "Unknown";
+
+	return mode_str[hw_mode];
+}
+
+static void
+ath12k_wmi_dump_freq_range_per_mac(struct ath12k_base *ab,
+				   struct ath12k_hw_mode_freq_range_arg *freq_range,
+				   enum ath12k_hw_mode hw_mode)
+{
+	u8 i;
+
+	for (i = 0; i < MAX_RADIOS; i++)
+		if (freq_range[i].low_2ghz_freq || freq_range[i].low_5ghz_freq)
+			ath12k_dbg(ab, ATH12K_DBG_WMI,
+				   "frequency range: %s(%d) mac %d 2 GHz [%d - %d] 5 GHz [%d - %d]",
+				   ath12k_wmi_hw_mode_to_str(hw_mode),
+				   hw_mode, i,
+				   freq_range[i].low_2ghz_freq,
+				   freq_range[i].high_2ghz_freq,
+				   freq_range[i].low_5ghz_freq,
+				   freq_range[i].high_5ghz_freq);
+}
+
+static void ath12k_wmi_dump_freq_range(struct ath12k_base *ab)
+{
+	struct ath12k_hw_mode_freq_range_arg *freq_range;
+	u8 i;
+
+	for (i = ATH12K_HW_MODE_SMM; i < ATH12K_HW_MODE_MAX; i++) {
+		freq_range = ab->wmi_ab.hw_mode_info.freq_range_caps[i];
+		ath12k_wmi_dump_freq_range_per_mac(ab, freq_range, i);
+	}
+}
+
+static int ath12k_wmi_modify_sbs_freq(struct ath12k_base *ab, u8 phy_id)
+{
+	struct ath12k_hw_mode_info *hw_mode_info = &ab->wmi_ab.hw_mode_info;
+	struct ath12k_hw_mode_freq_range_arg *sbs_mac_range, *shared_mac_range;
+	struct ath12k_hw_mode_freq_range_arg *non_shared_range;
+	u8 shared_phy_id;
+
+	sbs_mac_range = &hw_mode_info->freq_range_caps[ATH12K_HW_MODE_SBS][phy_id];
+
+	/* if SBS mac range has both 2.4 and 5 GHz ranges, i.e. shared phy_id
+	 * keep the range as it is in SBS
+	 */
+	if (sbs_mac_range->low_2ghz_freq && sbs_mac_range->low_5ghz_freq)
+		return 0;
+
+	if (sbs_mac_range->low_2ghz_freq && !sbs_mac_range->low_5ghz_freq) {
+		ath12k_err(ab, "Invalid DBS/SBS mode with only 2.4Ghz");
+		ath12k_wmi_dump_freq_range_per_mac(ab, sbs_mac_range, ATH12K_HW_MODE_SBS);
+		return -EINVAL;
+	}
+
+	non_shared_range = sbs_mac_range;
+	/* if SBS mac range has only 5 GHz then it's the non-shared phy, so
+	 * modify the range as per the shared mac.
+	 */
+	shared_phy_id = phy_id ? 0 : 1;
+	shared_mac_range =
+		&hw_mode_info->freq_range_caps[ATH12K_HW_MODE_SBS][shared_phy_id];
+
+	if (shared_mac_range->low_5ghz_freq > non_shared_range->low_5ghz_freq) {
+		ath12k_dbg(ab, ATH12K_DBG_WMI, "high 5 GHz shared");
+		/* If the shared mac lower 5 GHz frequency is greater than
+		 * non-shared mac lower 5 GHz frequency then the shared mac has
+		 * high 5 GHz shared with 2.4 GHz. So non-shared mac's 5 GHz high
+		 * freq should be less than the shared mac's low 5 GHz freq.
+		 */
+		if (non_shared_range->high_5ghz_freq >=
+		    shared_mac_range->low_5ghz_freq)
+			non_shared_range->high_5ghz_freq =
+				max_t(u32, shared_mac_range->low_5ghz_freq - 10,
+				      non_shared_range->low_5ghz_freq);
+	} else if (shared_mac_range->high_5ghz_freq <
+		   non_shared_range->high_5ghz_freq) {
+		ath12k_dbg(ab, ATH12K_DBG_WMI, "low 5 GHz shared");
+		/* If the shared mac high 5 GHz frequency is less than
+		 * non-shared mac high 5 GHz frequency then the shared mac has
+		 * low 5 GHz shared with 2.4 GHz. So non-shared mac's 5 GHz low
+		 * freq should be greater than the shared mac's high 5 GHz freq.
+		 */
+		if (shared_mac_range->high_5ghz_freq >=
+		    non_shared_range->low_5ghz_freq)
+			non_shared_range->low_5ghz_freq =
+				min_t(u32, shared_mac_range->high_5ghz_freq + 10,
+				      non_shared_range->high_5ghz_freq);
+	} else {
+		ath12k_warn(ab, "invalid SBS range with all 5 GHz shared");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void ath12k_wmi_update_sbs_freq_info(struct ath12k_base *ab)
+{
+	struct ath12k_hw_mode_info *hw_mode_info = &ab->wmi_ab.hw_mode_info;
+	struct ath12k_hw_mode_freq_range_arg *mac_range;
+	u16 sbs_range_sep;
+	u8 phy_id;
+	int ret;
+
+	mac_range = hw_mode_info->freq_range_caps[ATH12K_HW_MODE_SBS];
+
+	/* If sbs_lower_band_end_freq has a value, then the frequency range
+	 * will be split using that value.
+	 */
+	sbs_range_sep = ab->wmi_ab.sbs_lower_band_end_freq;
+	if (sbs_range_sep) {
+		ath12k_wmi_fill_upper_share_sbs_freq(ab, sbs_range_sep,
+						     mac_range);
+		ath12k_wmi_fill_lower_share_sbs_freq(ab, sbs_range_sep,
+						     mac_range);
+		/* Hardware specifies the range boundary with sbs_range_sep,
+		 * (i.e. the boundary between 5 GHz high and 5 GHz low),
+		 * reset the original one to make sure it will not get used.
+		 */
+		memset(mac_range, 0, sizeof(*mac_range) * MAX_RADIOS);
+		return;
+	}
+
+	/* If sbs_lower_band_end_freq is not set that means firmware will send one
+	 * shared mac range and one non-shared mac range. so update that freq.
+	 */
+	for (phy_id = 0; phy_id < MAX_RADIOS; phy_id++) {
+		ret = ath12k_wmi_modify_sbs_freq(ab, phy_id);
+		if (ret) {
+			memset(mac_range, 0, sizeof(*mac_range) * MAX_RADIOS);
+			break;
+		}
+	}
+}
+
+static void
+ath12k_wmi_update_mac_freq_info(struct ath12k_base *ab,
+				enum wmi_host_hw_mode_config_type hw_config_type,
+				u32 phy_id,
+				struct ath12k_svc_ext_mac_phy_info *mac_cap)
+{
+	if (phy_id >= MAX_RADIOS) {
+		ath12k_err(ab, "mac more than two not supported: %d", phy_id);
+		return;
+	}
+
+	ath12k_dbg(ab, ATH12K_DBG_WMI,
+		   "hw_mode_cfg %d mac %d band 0x%x SBS cutoff freq %d 2 GHz [%d - %d] 5 GHz [%d - %d]",
+		   hw_config_type, phy_id, mac_cap->supported_bands,
+		   ab->wmi_ab.sbs_lower_band_end_freq,
+		   mac_cap->hw_freq_range.low_2ghz_freq,
+		   mac_cap->hw_freq_range.high_2ghz_freq,
+		   mac_cap->hw_freq_range.low_5ghz_freq,
+		   mac_cap->hw_freq_range.high_5ghz_freq);
+
+	switch (hw_config_type) {
+	case WMI_HOST_HW_MODE_SINGLE:
+		if (phy_id) {
+			ath12k_dbg(ab, ATH12K_DBG_WMI, "mac phy 1 is not supported");
+			break;
+		}
+		ath12k_wmi_update_freq_info(ab, mac_cap, ATH12K_HW_MODE_SMM, phy_id);
+		break;
+
+	case WMI_HOST_HW_MODE_DBS:
+		if (!ath12k_wmi_all_phy_range_updated(ab, ATH12K_HW_MODE_DBS))
+			ath12k_wmi_update_freq_info(ab, mac_cap,
+						    ATH12K_HW_MODE_DBS, phy_id);
+		break;
+	case WMI_HOST_HW_MODE_DBS_SBS:
+	case WMI_HOST_HW_MODE_DBS_OR_SBS:
+		ath12k_wmi_update_freq_info(ab, mac_cap, ATH12K_HW_MODE_DBS, phy_id);
+		if (ab->wmi_ab.sbs_lower_band_end_freq ||
+		    mac_cap->hw_freq_range.low_5ghz_freq ||
+		    mac_cap->hw_freq_range.low_2ghz_freq)
+			ath12k_wmi_update_freq_info(ab, mac_cap, ATH12K_HW_MODE_SBS,
+						    phy_id);
+
+		if (ath12k_wmi_all_phy_range_updated(ab, ATH12K_HW_MODE_DBS))
+			ath12k_wmi_update_dbs_freq_info(ab);
+		if (ath12k_wmi_all_phy_range_updated(ab, ATH12K_HW_MODE_SBS))
+			ath12k_wmi_update_sbs_freq_info(ab);
+		break;
+	case WMI_HOST_HW_MODE_SBS:
+	case WMI_HOST_HW_MODE_SBS_PASSIVE:
+		ath12k_wmi_update_freq_info(ab, mac_cap, ATH12K_HW_MODE_SBS, phy_id);
+		if (ath12k_wmi_all_phy_range_updated(ab, ATH12K_HW_MODE_SBS))
+			ath12k_wmi_update_sbs_freq_info(ab);
+
+		break;
+	default:
+		break;
+	}
+}
+
+static bool ath12k_wmi_sbs_range_present(struct ath12k_base *ab)
+{
+	if (ath12k_wmi_all_phy_range_updated(ab, ATH12K_HW_MODE_SBS) ||
+	    (ab->wmi_ab.sbs_lower_band_end_freq &&
+	     ath12k_wmi_all_phy_range_updated(ab, ATH12K_HW_MODE_SBS_LOWER_SHARE) &&
+	     ath12k_wmi_all_phy_range_updated(ab, ATH12K_HW_MODE_SBS_UPPER_SHARE)))
+		return true;
+
+	return false;
+}
+
+static int ath12k_wmi_update_hw_mode_list(struct ath12k_base *ab)
+{
+	struct ath12k_svc_ext_info *svc_ext_info = &ab->wmi_ab.svc_ext_info;
+	struct ath12k_hw_mode_info *info = &ab->wmi_ab.hw_mode_info;
+	enum wmi_host_hw_mode_config_type hw_config_type;
+	struct ath12k_svc_ext_mac_phy_info *tmp;
+	bool dbs_mode = false, sbs_mode = false;
+	u32 i, j = 0;
+
+	if (!svc_ext_info->num_hw_modes) {
+		ath12k_err(ab, "invalid number of hw modes");
+		return -EINVAL;
+	}
+
+	ath12k_dbg(ab, ATH12K_DBG_WMI, "updated HW mode list: num modes %d",
+		   svc_ext_info->num_hw_modes);
+
+	memset(info->freq_range_caps, 0, sizeof(info->freq_range_caps));
+
+	for (i = 0; i < svc_ext_info->num_hw_modes; i++) {
+		if (j >= ATH12K_MAX_MAC_PHY_CAP)
+			return -EINVAL;
+
+		/* Update for MAC0 */
+		tmp = &svc_ext_info->mac_phy_info[j++];
+		hw_config_type = tmp->hw_mode_config_type;
+		ath12k_wmi_update_mac_freq_info(ab, hw_config_type, tmp->phy_id, tmp);
+
+		/* SBS and DBS have dual MAC. Up to 2 MACs are considered. */
+		if (hw_config_type == WMI_HOST_HW_MODE_DBS ||
+		    hw_config_type == WMI_HOST_HW_MODE_SBS_PASSIVE ||
+		    hw_config_type == WMI_HOST_HW_MODE_SBS ||
+		    hw_config_type == WMI_HOST_HW_MODE_DBS_OR_SBS) {
+			if (j >= ATH12K_MAX_MAC_PHY_CAP)
+				return -EINVAL;
+			/* Update for MAC1 */
+			tmp = &svc_ext_info->mac_phy_info[j++];
+			ath12k_wmi_update_mac_freq_info(ab, hw_config_type,
+							tmp->phy_id, tmp);
+
+			if (hw_config_type == WMI_HOST_HW_MODE_DBS ||
+			    hw_config_type == WMI_HOST_HW_MODE_DBS_OR_SBS)
+				dbs_mode = true;
+
+			if (ath12k_wmi_sbs_range_present(ab) &&
+			    (hw_config_type == WMI_HOST_HW_MODE_SBS_PASSIVE ||
+			     hw_config_type == WMI_HOST_HW_MODE_SBS ||
+			     hw_config_type == WMI_HOST_HW_MODE_DBS_OR_SBS))
+				sbs_mode = true;
+		}
+	}
+
+	info->support_dbs = dbs_mode;
+	info->support_sbs = sbs_mode;
+
+	ath12k_wmi_dump_freq_range(ab);
+
+	return 0;
+}
+
 static int ath12k_wmi_svc_rdy_ext2_parse(struct ath12k_base *ab,
 					 u16 tag, u16 len,
 					 const void *ptr, void *data)
 {
+	const struct ath12k_wmi_dbs_or_sbs_cap_params *dbs_or_sbs_caps;
 	struct ath12k_wmi_pdev *wmi_handle = &ab->wmi_ab.wmi[0];
 	struct ath12k_wmi_svc_rdy_ext2_parse *parse = data;
 	int ret;
···
 			}
 
 			parse->mac_phy_caps_ext_done = true;
+		} else if (!parse->hal_reg_caps_ext2_done) {
+			parse->hal_reg_caps_ext2_done = true;
+		} else if (!parse->scan_radio_caps_ext2_done) {
+			parse->scan_radio_caps_ext2_done = true;
+		} else if (!parse->twt_caps_done) {
+			parse->twt_caps_done = true;
+		} else if (!parse->htt_msdu_idx_to_qtype_map_done) {
+			parse->htt_msdu_idx_to_qtype_map_done = true;
+		} else if (!parse->dbs_or_sbs_cap_ext_done) {
+			dbs_or_sbs_caps = ptr;
+			ab->wmi_ab.sbs_lower_band_end_freq =
+				__le32_to_cpu(dbs_or_sbs_caps->sbs_lower_band_end_freq);
+
+			ath12k_dbg(ab, ATH12K_DBG_WMI, "sbs_lower_band_end_freq %u\n",
+				   ab->wmi_ab.sbs_lower_band_end_freq);
+
+			ret = ath12k_wmi_update_hw_mode_list(ab);
+			if (ret) {
+				ath12k_warn(ab, "failed to update hw mode list: %d\n",
+					    ret);
+				return ret;
+			}
+
+			parse->dbs_or_sbs_cap_ext_done = true;
 		}
+
 		break;
 	default:
 		break;
···
 				   &parse);
 }
 
+static void ath12k_wmi_fw_stats_process(struct ath12k *ar,
+					struct ath12k_fw_stats *stats)
+{
+	struct ath12k_base *ab = ar->ab;
+	struct ath12k_pdev *pdev;
+	bool is_end = true;
+	size_t total_vdevs_started = 0;
+	int i;
+
+	if (stats->stats_id == WMI_REQUEST_VDEV_STAT) {
+		if (list_empty(&stats->vdevs)) {
+			ath12k_warn(ab, "empty vdev stats");
+			return;
+		}
+		/* FW sends all the active VDEV stats irrespective of PDEV,
+		 * hence limit until the count of all VDEVs started
+		 */
+		rcu_read_lock();
+		for (i = 0; i < ab->num_radios; i++) {
+			pdev = rcu_dereference(ab->pdevs_active[i]);
+			if (pdev && pdev->ar)
+				total_vdevs_started += pdev->ar->num_started_vdevs;
+		}
+		rcu_read_unlock();
+
+		if (total_vdevs_started)
+			is_end = ((++ar->fw_stats.num_vdev_recvd) ==
+				  total_vdevs_started);
+
+		list_splice_tail_init(&stats->vdevs,
+				      &ar->fw_stats.vdevs);
+
+		if (is_end)
+			complete(&ar->fw_stats_done);
+
+		return;
+	}
+
+	if (stats->stats_id == WMI_REQUEST_BCN_STAT) {
+		if (list_empty(&stats->bcn)) {
+			ath12k_warn(ab, "empty beacon stats");
+			return;
+		}
+		/* Mark end until we reached the count of all started VDEVs
+		 * within the PDEV
+		 */
+		if (ar->num_started_vdevs)
+			is_end = ((++ar->fw_stats.num_bcn_recvd) ==
+				  ar->num_started_vdevs);
+
+		list_splice_tail_init(&stats->bcn,
+				      &ar->fw_stats.bcn);
+
+		if (is_end)
+			complete(&ar->fw_stats_done);
+	}
+}
+
 static void ath12k_update_stats_event(struct ath12k_base *ab, struct sk_buff *skb)
 {
 	struct ath12k_fw_stats stats = {};
···
 
 	spin_lock_bh(&ar->data_lock);
 
-	/* WMI_REQUEST_PDEV_STAT can be requested via .get_txpower mac ops or via
-	 * debugfs fw stats. Therefore, processing it separately.
-	 */
+	/* Handle WMI_REQUEST_PDEV_STAT status update */
 	if (stats.stats_id == WMI_REQUEST_PDEV_STAT) {
 		list_splice_tail_init(&stats.pdevs, &ar->fw_stats.pdevs);
-		ar->fw_stats.fw_stats_done = true;
+		complete(&ar->fw_stats_done);
 		goto complete;
 	}
 
-	/* WMI_REQUEST_VDEV_STAT and WMI_REQUEST_BCN_STAT are currently requested only
-	 * via debugfs fw stats. Hence, processing these in debugfs context.
-	 */
-	ath12k_debugfs_fw_stats_process(ar, &stats);
+	/* Handle WMI_REQUEST_VDEV_STAT and WMI_REQUEST_BCN_STAT updates. */
+	ath12k_wmi_fw_stats_process(ar, &stats);
 
 complete:
 	complete(&ar->fw_stats_complete);
···
 	}
 
 	return 0;
+}
+
+static int
+ath12k_wmi_fill_disallowed_bmap(struct ath12k_base *ab,
+				struct wmi_disallowed_mlo_mode_bitmap_params *dislw_bmap,
+				struct wmi_mlo_link_set_active_arg *arg)
+{
+	struct wmi_ml_disallow_mode_bmap_arg *dislw_bmap_arg;
+	u8 i;
+
+	if (arg->num_disallow_mode_comb >
+	    ARRAY_SIZE(arg->disallow_bmap)) {
+		ath12k_warn(ab, "invalid num_disallow_mode_comb: %d",
+			    arg->num_disallow_mode_comb);
+		return -EINVAL;
+	}
+
+	dislw_bmap_arg = &arg->disallow_bmap[0];
+	for (i = 0; i < arg->num_disallow_mode_comb; i++) {
+		dislw_bmap->tlv_header =
+				ath12k_wmi_tlv_cmd_hdr(0, sizeof(*dislw_bmap));
+		dislw_bmap->disallowed_mode_bitmap =
+				cpu_to_le32(dislw_bmap_arg->disallowed_mode);
+		dislw_bmap->ieee_link_id_comb =
+			le32_encode_bits(dislw_bmap_arg->ieee_link_id[0],
+					 WMI_DISALW_MLO_MODE_BMAP_IEEE_LINK_ID_COMB_1) |
+			le32_encode_bits(dislw_bmap_arg->ieee_link_id[1],
+					 WMI_DISALW_MLO_MODE_BMAP_IEEE_LINK_ID_COMB_2) |
+			le32_encode_bits(dislw_bmap_arg->ieee_link_id[2],
+					 WMI_DISALW_MLO_MODE_BMAP_IEEE_LINK_ID_COMB_3) |
+			le32_encode_bits(dislw_bmap_arg->ieee_link_id[3],
+					 WMI_DISALW_MLO_MODE_BMAP_IEEE_LINK_ID_COMB_4);
+
+		ath12k_dbg(ab, ATH12K_DBG_WMI,
+			   "entry %d disallowed_mode %d ieee_link_id_comb 0x%x",
+			   i, dislw_bmap_arg->disallowed_mode,
+			   dislw_bmap_arg->ieee_link_id_comb);
+		dislw_bmap++;
+		dislw_bmap_arg++;
+	}
+
+	return 0;
+}
+
+int ath12k_wmi_send_mlo_link_set_active_cmd(struct ath12k_base *ab,
+					    struct wmi_mlo_link_set_active_arg *arg)
+{
+	struct wmi_disallowed_mlo_mode_bitmap_params *disallowed_mode_bmap;
+	struct wmi_mlo_set_active_link_number_params *link_num_param;
+	u32 num_link_num_param = 0, num_vdev_bitmap = 0;
+	struct ath12k_wmi_base *wmi_ab = &ab->wmi_ab;
+	struct wmi_mlo_link_set_active_cmd *cmd;
+	u32 num_inactive_vdev_bitmap = 0;
+	u32 num_disallow_mode_comb = 0;
+	struct wmi_tlv *tlv;
+	struct sk_buff *skb;
+	__le32 *vdev_bitmap;
+	void *buf_ptr;
+	int i, ret;
+	u32 len;
+
+	if (!arg->num_vdev_bitmap && !arg->num_link_entry) {
+		ath12k_warn(ab, "Invalid num_vdev_bitmap and num_link_entry");
+		return -EINVAL;
+	}
+
+	switch (arg->force_mode) {
+	case WMI_MLO_LINK_FORCE_MODE_ACTIVE_LINK_NUM:
+	case WMI_MLO_LINK_FORCE_MODE_INACTIVE_LINK_NUM:
+		num_link_num_param = arg->num_link_entry;
+		fallthrough;
+	case WMI_MLO_LINK_FORCE_MODE_ACTIVE:
+	case WMI_MLO_LINK_FORCE_MODE_INACTIVE:
+	case WMI_MLO_LINK_FORCE_MODE_NO_FORCE:
+		num_vdev_bitmap = arg->num_vdev_bitmap;
+		break;
+	case WMI_MLO_LINK_FORCE_MODE_ACTIVE_INACTIVE:
+		num_vdev_bitmap = arg->num_vdev_bitmap;
+		num_inactive_vdev_bitmap = arg->num_inactive_vdev_bitmap;
+		break;
+	default:
+		ath12k_warn(ab, "Invalid force mode: %u", arg->force_mode);
+		return -EINVAL;
+	}
+
+	num_disallow_mode_comb = arg->num_disallow_mode_comb;
+	len = sizeof(*cmd) +
+	      TLV_HDR_SIZE + sizeof(*link_num_param) * num_link_num_param +
+	      TLV_HDR_SIZE + sizeof(*vdev_bitmap) * num_vdev_bitmap +
+	      TLV_HDR_SIZE + TLV_HDR_SIZE + TLV_HDR_SIZE +
+	      TLV_HDR_SIZE + sizeof(*disallowed_mode_bmap) * num_disallow_mode_comb;
+	if (arg->force_mode == WMI_MLO_LINK_FORCE_MODE_ACTIVE_INACTIVE)
+		len += sizeof(*vdev_bitmap) * num_inactive_vdev_bitmap;
+
+	skb = ath12k_wmi_alloc_skb(wmi_ab, len);
+	if (!skb)
+		return -ENOMEM;
+
+	cmd = (struct wmi_mlo_link_set_active_cmd *)skb->data;
+	cmd->tlv_header = ath12k_wmi_tlv_cmd_hdr(WMI_TAG_MLO_LINK_SET_ACTIVE_CMD,
+						 sizeof(*cmd));
+	cmd->force_mode = cpu_to_le32(arg->force_mode);
+	cmd->reason = cpu_to_le32(arg->reason);
+	ath12k_dbg(ab, ATH12K_DBG_WMI,
+		   "mode %d reason %d num_link_num_param %d num_vdev_bitmap %d inactive %d num_disallow_mode_comb %d",
+		   arg->force_mode, arg->reason, num_link_num_param,
+		   num_vdev_bitmap, num_inactive_vdev_bitmap,
+		   num_disallow_mode_comb);
+
+	buf_ptr = skb->data + sizeof(*cmd);
+	tlv = buf_ptr;
+	tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_STRUCT,
+					 sizeof(*link_num_param) * num_link_num_param);
+	buf_ptr += TLV_HDR_SIZE;
+
+	if (num_link_num_param) {
+		cmd->ctrl_flags =
+			le32_encode_bits(arg->ctrl_flags.dync_force_link_num ? 1 : 0,
+					 CRTL_F_DYNC_FORCE_LINK_NUM);
+
+		link_num_param = buf_ptr;
+		for (i = 0; i < num_link_num_param; i++) {
+			link_num_param->tlv_header =
+				ath12k_wmi_tlv_cmd_hdr(0, sizeof(*link_num_param));
+			link_num_param->num_of_link =
+				cpu_to_le32(arg->link_num[i].num_of_link);
+			link_num_param->vdev_type =
+				cpu_to_le32(arg->link_num[i].vdev_type);
+			link_num_param->vdev_subtype =
+				cpu_to_le32(arg->link_num[i].vdev_subtype);
+			link_num_param->home_freq =
+				cpu_to_le32(arg->link_num[i].home_freq);
+			ath12k_dbg(ab, ATH12K_DBG_WMI,
+				   "entry %d num_of_link %d vdev type %d subtype %d freq %d control_flags %d",
+				   i, arg->link_num[i].num_of_link,
+				   arg->link_num[i].vdev_type,
+				   arg->link_num[i].vdev_subtype,
+				   arg->link_num[i].home_freq,
+				   __le32_to_cpu(cmd->ctrl_flags));
+			link_num_param++;
+		}
+
+		buf_ptr += sizeof(*link_num_param) * num_link_num_param;
+	}
+
+	tlv = buf_ptr;
+	tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_UINT32,
+					 sizeof(*vdev_bitmap) * num_vdev_bitmap);
+	buf_ptr += TLV_HDR_SIZE;
+
+	if (num_vdev_bitmap) {
+		vdev_bitmap = buf_ptr;
+		for (i = 0; i < num_vdev_bitmap; i++) {
+			vdev_bitmap[i] = cpu_to_le32(arg->vdev_bitmap[i]);
+			ath12k_dbg(ab, ATH12K_DBG_WMI, "entry %d vdev_id_bitmap 0x%x",
+				   i, arg->vdev_bitmap[i]);
+		}
+
+		buf_ptr += sizeof(*vdev_bitmap) * num_vdev_bitmap;
+	}
+
+	if (arg->force_mode == WMI_MLO_LINK_FORCE_MODE_ACTIVE_INACTIVE) {
+		tlv = buf_ptr;
+		tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_UINT32,
+						 sizeof(*vdev_bitmap) *
+						 num_inactive_vdev_bitmap);
+		buf_ptr += TLV_HDR_SIZE;
+
+		if (num_inactive_vdev_bitmap) {
+			vdev_bitmap = buf_ptr;
+			for (i = 0; i < num_inactive_vdev_bitmap; i++) {
+				vdev_bitmap[i] =
+					cpu_to_le32(arg->inactive_vdev_bitmap[i]);
+				ath12k_dbg(ab, ATH12K_DBG_WMI,
+					   "entry %d inactive_vdev_id_bitmap 0x%x",
+					    i, arg->inactive_vdev_bitmap[i]);
+			}
+
+			buf_ptr += sizeof(*vdev_bitmap) * num_inactive_vdev_bitmap;
+		}
+	} else {
+		/* add empty vdev bitmap2 tlv */
+		tlv = buf_ptr;
+		tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_UINT32, 0);
+		buf_ptr += TLV_HDR_SIZE;
+	}
+
+	/* add empty ieee_link_id_bitmap tlv */
+	tlv = buf_ptr;
+	tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_UINT32, 0);
+	buf_ptr += TLV_HDR_SIZE;
+
+	/* add empty ieee_link_id_bitmap2 tlv */
+	tlv = buf_ptr;
+	tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_UINT32, 0);
+	buf_ptr += TLV_HDR_SIZE;
+
+	tlv = buf_ptr;
+	tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_STRUCT,
+					 sizeof(*disallowed_mode_bmap) *
+					 arg->num_disallow_mode_comb);
+	buf_ptr += TLV_HDR_SIZE;
+
+	ret = ath12k_wmi_fill_disallowed_bmap(ab, buf_ptr, arg);
+	if (ret)
+		goto free_skb;
+
+	ret = ath12k_wmi_cmd_send(&wmi_ab->wmi[0], skb, WMI_MLO_LINK_SET_ACTIVE_CMDID);
+	if (ret) {
+		ath12k_warn(ab,
+			    "failed to send WMI_MLO_LINK_SET_ACTIVE_CMDID: %d\n", ret);
+		goto free_skb;
+	}
+
+	ath12k_dbg(ab, ATH12K_DBG_WMI, "WMI mlo link set active cmd");
+
+	return ret;
+
+free_skb:
+	dev_kfree_skb(skb);
+	return ret;
 }

drivers/net/wireless/ath/ath12k/wmi.h

···
 	WMI_TAG_TPC_STATS_CTL_PWR_TABLE_EVENT,
 	WMI_TAG_VDEV_SET_TPC_POWER_CMD = 0x3B5,
 	WMI_TAG_VDEV_CH_POWER_INFO,
+	WMI_TAG_MLO_LINK_SET_ACTIVE_CMD = 0x3BE,
 	WMI_TAG_EHT_RATE_SET = 0x3C4,
 	WMI_TAG_DCS_AWGN_INT_TYPE = 0x3C5,
 	WMI_TAG_MLO_TX_SEND_PARAMS,
···
 	__le32 num_chainmask_tables;
 } __packed;
 
+#define WMI_HW_MODE_CAP_CFG_TYPE	GENMASK(27, 0)
+
 struct ath12k_wmi_hw_mode_cap_params {
 	__le32 tlv_header;
 	__le32 hw_mode_id;
···
 	__le32 he_cap_info_2g_ext;
 	__le32 he_cap_info_5g_ext;
 	__le32 he_cap_info_internal;
+	__le32 wireless_modes;
+	__le32 low_2ghz_chan_freq;
+	__le32 high_2ghz_chan_freq;
+	__le32 low_5ghz_chan_freq;
+	__le32 high_5ghz_chan_freq;
+	__le32 nss_ratio;
 } __packed;
 
 struct ath12k_wmi_hal_reg_caps_ext_params {
···
 	__le32 max_num_linkview_peers;
 	__le32 max_num_msduq_supported_per_tid;
 	__le32 default_num_msduq_supported_per_tid;
+} __packed;
+
+struct ath12k_wmi_dbs_or_sbs_cap_params {
+	__le32 hw_mode_id;
+	__le32 sbs_lower_band_end_freq;
 } __packed;
 
 struct ath12k_wmi_caps_ext_params {
···
 	u32 rx_decap_mode;
 };
 
+struct ath12k_hw_mode_freq_range_arg {
+	u32 low_2ghz_freq;
+	u32 high_2ghz_freq;
+	u32 low_5ghz_freq;
+	u32 high_5ghz_freq;
+};
+
+struct ath12k_svc_ext_mac_phy_info {
+	enum wmi_host_hw_mode_config_type hw_mode_config_type;
+	u32 phy_id;
+	u32 supported_bands;
+	struct ath12k_hw_mode_freq_range_arg hw_freq_range;
+};
+
+#define ATH12K_MAX_MAC_PHY_CAP	8
+
+struct ath12k_svc_ext_info {
+	u32 num_hw_modes;
+	struct ath12k_svc_ext_mac_phy_info mac_phy_info[ATH12K_MAX_MAC_PHY_CAP];
+};
+
+/**
+ * enum ath12k_hw_mode - enum for host mode
+ * @ATH12K_HW_MODE_SMM: Single mac mode
+ * @ATH12K_HW_MODE_DBS: DBS mode
+ * @ATH12K_HW_MODE_SBS: SBS mode with either high share or low share
+ * @ATH12K_HW_MODE_SBS_UPPER_SHARE: Higher 5 GHz shared with 2.4 GHz
+ * @ATH12K_HW_MODE_SBS_LOWER_SHARE: Lower 5 GHz shared with 2.4 GHz
+ * @ATH12K_HW_MODE_MAX: Max, used to indicate invalid mode
+ */
+enum ath12k_hw_mode {
+	ATH12K_HW_MODE_SMM,
+	ATH12K_HW_MODE_DBS,
+	ATH12K_HW_MODE_SBS,
+	ATH12K_HW_MODE_SBS_UPPER_SHARE,
+	ATH12K_HW_MODE_SBS_LOWER_SHARE,
+	ATH12K_HW_MODE_MAX,
+};
+
+struct ath12k_hw_mode_info {
+	bool support_dbs:1;
+	bool support_sbs:1;
+
+	struct ath12k_hw_mode_freq_range_arg freq_range_caps[ATH12K_HW_MODE_MAX]
+							    [MAX_RADIOS];
+};
+
 struct ath12k_wmi_base {
 	struct ath12k_base *ab;
 	struct ath12k_wmi_pdev wmi[MAX_RADIOS];
···
 	enum wmi_host_hw_mode_config_type preferred_hw_mode;
 
 	struct ath12k_wmi_target_cap_arg *targ_cap;
+
+	struct ath12k_svc_ext_info svc_ext_info;
+	u32 sbs_lower_band_end_freq;
+	struct ath12k_hw_mode_info hw_mode_info;
 };
 
 struct wmi_pdev_set_bios_interface_cmd {
···
 	 */
 } __packed;
 
+#define CRTL_F_DYNC_FORCE_LINK_NUM GENMASK(3, 2)
+
+struct wmi_mlo_link_set_active_cmd {
+	__le32 tlv_header;
+	__le32 force_mode;
+	__le32 reason;
+	__le32 use_ieee_link_id_bitmap;
+	struct ath12k_wmi_mac_addr_params ap_mld_mac_addr;
+	__le32 ctrl_flags;
+} __packed;
+
+struct wmi_mlo_set_active_link_number_params {
+	__le32 tlv_header;
+	__le32 num_of_link;
+	__le32 vdev_type;
+	__le32 vdev_subtype;
+	__le32 home_freq;
+} __packed;
+
+#define WMI_DISALW_MLO_MODE_BMAP_IEEE_LINK_ID_COMB_1 GENMASK(7, 0)
+#define WMI_DISALW_MLO_MODE_BMAP_IEEE_LINK_ID_COMB_2 GENMASK(15, 8)
+#define WMI_DISALW_MLO_MODE_BMAP_IEEE_LINK_ID_COMB_3 GENMASK(23, 16)
+#define WMI_DISALW_MLO_MODE_BMAP_IEEE_LINK_ID_COMB_4 GENMASK(31, 24)
+
+struct wmi_disallowed_mlo_mode_bitmap_params {
+	__le32 tlv_header;
+	__le32 disallowed_mode_bitmap;
+	__le32 ieee_link_id_comb;
+} __packed;
+
+enum wmi_mlo_link_force_mode {
+	WMI_MLO_LINK_FORCE_MODE_ACTIVE			= 1,
+	WMI_MLO_LINK_FORCE_MODE_INACTIVE		= 2,
+	WMI_MLO_LINK_FORCE_MODE_ACTIVE_LINK_NUM		= 3,
+	WMI_MLO_LINK_FORCE_MODE_INACTIVE_LINK_NUM	= 4,
+	WMI_MLO_LINK_FORCE_MODE_NO_FORCE		= 5,
+	WMI_MLO_LINK_FORCE_MODE_ACTIVE_INACTIVE		= 6,
+	WMI_MLO_LINK_FORCE_MODE_NON_FORCE_UPDATE	= 7,
+};
+
+enum wmi_mlo_link_force_reason {
+	WMI_MLO_LINK_FORCE_REASON_NEW_CONNECT		= 1,
+	WMI_MLO_LINK_FORCE_REASON_NEW_DISCONNECT	= 2,
+	WMI_MLO_LINK_FORCE_REASON_LINK_REMOVAL		= 3,
+	WMI_MLO_LINK_FORCE_REASON_TDLS			= 4,
+	WMI_MLO_LINK_FORCE_REASON_REVERT_FAILURE	= 5,
+	WMI_MLO_LINK_FORCE_REASON_LINK_DELETE		= 6,
+	WMI_MLO_LINK_FORCE_REASON_SINGLE_LINK_EMLSR_OP	= 7,
+};
+
+struct wmi_mlo_link_num_arg {
+	u32 num_of_link;
+	u32 vdev_type;
+	u32 vdev_subtype;
+	u32 home_freq;
+};
+
+struct wmi_mlo_control_flags_arg {
+	bool overwrite_force_active_bitmap;
+	bool overwrite_force_inactive_bitmap;
+	bool dync_force_link_num;
+	bool post_re_evaluate;
+	u8 post_re_evaluate_loops;
+	bool dont_reschedule_workqueue;
+};
+
+struct wmi_ml_link_force_cmd_arg {
+	u8 ap_mld_mac_addr[ETH_ALEN];
+	u16 ieee_link_id_bitmap;
+	u16 ieee_link_id_bitmap2;
+	u8 link_num;
+};
+
+struct wmi_ml_disallow_mode_bmap_arg {
+	u32 disallowed_mode;
+	union {
+		u32 ieee_link_id_comb;
+		u8 ieee_link_id[4];
+	};
+};
+
+/* maximum size of link number param array
+ * for MLO link set active command
+ */
+#define WMI_MLO_LINK_NUM_SZ 2
+
+/* maximum size of vdev bitmap array for
+ * MLO link set active command
+ */
+#define WMI_MLO_VDEV_BITMAP_SZ 2
+
+/* Max number of disallowed bitmap combination
+ * sent to firmware
+ */
+#define WMI_ML_MAX_DISALLOW_BMAP_COMB 4
+
+struct wmi_mlo_link_set_active_arg {
+	enum wmi_mlo_link_force_mode force_mode;
+	enum wmi_mlo_link_force_reason reason;
+	u32 num_link_entry;
+	u32 num_vdev_bitmap;
+	u32 num_inactive_vdev_bitmap;
+	struct wmi_mlo_link_num_arg link_num[WMI_MLO_LINK_NUM_SZ];
+	u32 vdev_bitmap[WMI_MLO_VDEV_BITMAP_SZ];
+	u32 inactive_vdev_bitmap[WMI_MLO_VDEV_BITMAP_SZ];
+	struct wmi_mlo_control_flags_arg ctrl_flags;
+	bool use_ieee_link_id;
+	struct wmi_ml_link_force_cmd_arg force_cmd;
+	u32 num_disallow_mode_comb;
+	struct wmi_ml_disallow_mode_bmap_arg disallow_bmap[WMI_ML_MAX_DISALLOW_BMAP_COMB];
+};
+
 void ath12k_wmi_init_qcn9274(struct ath12k_base *ab,
 			     struct ath12k_wmi_resource_config_arg *config);
 void ath12k_wmi_init_wcn7850(struct ath12k_base *ab,
···
 int ath12k_wmi_send_vdev_set_tpc_power(struct ath12k *ar,
 				       u32 vdev_id,
 				       struct ath12k_reg_tpc_power_info *param);
-
+int ath12k_wmi_send_mlo_link_set_active_cmd(struct ath12k_base *ab,
+					    struct wmi_mlo_link_set_active_arg *param);
 #endif

drivers/net/wireless/ath/ath6kl/bmi.c

···
 		 * We need to do some backwards compatibility to make this work.
 		 */
 		if (le32_to_cpu(targ_info->byte_count) != sizeof(*targ_info)) {
-			WARN_ON(1);
+			ath6kl_err("mismatched byte count %d vs. expected %zd\n",
+				   le32_to_cpu(targ_info->byte_count),
+				   sizeof(*targ_info));
 			return -EINVAL;
 		}
 

drivers/net/wireless/ath/carl9170/usb.c

···
 
 		if (atomic_read(&ar->rx_anch_urbs) == 0) {
 			/*
-			 * The system is too slow to cope with
-			 * the enormous workload. We have simply
-			 * run out of active rx urbs and this
-			 * unfortunately leads to an unpredictable
-			 * device.
+			 * At this point, either the system is too slow to
+			 * cope with the enormous workload (so we have simply
+			 * run out of active rx urbs and this unfortunately
+			 * leads to an unpredictable device), or the device
+			 * is not fully functional after an unsuccessful
+			 * firmware loading attempts (so it doesn't pass
+			 * ieee80211_register_hw() and there is no internal
+			 * workqueue at all).
 			 */
 
-			ieee80211_queue_work(ar->hw, &ar->ping_work);
+			if (ar->registered)
+				ieee80211_queue_work(ar->hw, &ar->ping_work);
+			else
+				pr_warn_once("device %s is not registered\n",
+					     dev_name(&ar->udev->dev));
 		}
 	} else {
 		/*

drivers/net/wireless/intel/iwlwifi/dvm/main.c

···
 		     sizeof(trans->conf.no_reclaim_cmds));
 	memcpy(trans->conf.no_reclaim_cmds, no_reclaim_cmds,
 	       sizeof(no_reclaim_cmds));
+	trans->conf.n_no_reclaim_cmds = ARRAY_SIZE(no_reclaim_cmds);
 
 	switch (iwlwifi_mod_params.amsdu_size) {
 	case IWL_AMSDU_DEF:

drivers/net/wireless/intel/iwlwifi/mld/mld.c

···
 
 	/* Setup async RX handling */
 	spin_lock_init(&mld->async_handlers_lock);
+	INIT_LIST_HEAD(&mld->async_handlers_list);
 	wiphy_work_init(&mld->async_handlers_wk,
 			iwl_mld_async_handlers_wk);
 

drivers/net/wireless/intel/iwlwifi/mvm/mld-mac.c

···
 					    WIDE_ID(MAC_CONF_GROUP,
 						    MAC_CONFIG_CMD), 0);
 
-	if (WARN_ON(cmd_ver < 1 && cmd_ver > 3))
+	if (WARN_ON(cmd_ver < 1 || cmd_ver > 3))
 		return;
 
 	cmd->id_and_color = cpu_to_le32(mvmvif->id);

drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c

···
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_context_info *ctxt_info;
 	struct iwl_context_info_rbd_cfg *rx_cfg;
-	u32 control_flags = 0, rb_size;
+	u32 control_flags = 0, rb_size, cb_size;
 	dma_addr_t phys;
 	int ret;
 
···
 		rb_size = IWL_CTXT_INFO_RB_SIZE_4K;
 	}
 
-	WARN_ON(RX_QUEUE_CB_SIZE(iwl_trans_get_num_rbds(trans)) > 12);
+	cb_size = RX_QUEUE_CB_SIZE(iwl_trans_get_num_rbds(trans));
+	if (WARN_ON(cb_size > 12))
+		cb_size = 12;
+
 	control_flags = IWL_CTXT_INFO_TFD_FORMAT_LONG;
-	control_flags |=
-		u32_encode_bits(RX_QUEUE_CB_SIZE(iwl_trans_get_num_rbds(trans)),
-				IWL_CTXT_INFO_RB_CB_SIZE);
+	control_flags |= u32_encode_bits(cb_size, IWL_CTXT_INFO_RB_CB_SIZE);
 	control_flags |= u32_encode_bits(rb_size, IWL_CTXT_INFO_RB_SIZE);
 	ctxt_info->control.control_flags = cpu_to_le32(control_flags);
 

drivers/nvme/host/ioctl.c

···
 	pdu->result = le64_to_cpu(nvme_req(req)->result.u64);
 
 	/*
-	 * For iopoll, complete it directly. Note that using the uring_cmd
-	 * helper for this is safe only because we check blk_rq_is_poll().
-	 * As that returns false if we're NOT on a polled queue, then it's
-	 * safe to use the polled completion helper.
-	 *
-	 * Otherwise, move the completion to task work.
+	 * IOPOLL could potentially complete this request directly, but
+	 * if multiple rings are polling on the same queue, then it's possible
+	 * for one ring to find completions for another ring. Punting the
+	 * completion via task_work will always direct it to the right
+	 * location, rather than potentially complete requests for ringA
+	 * under iopoll invocations from ringB.
 	 */
-	if (blk_rq_is_poll(req)) {
-		if (pdu->bio)
-			blk_rq_unmap_user(pdu->bio);
-		io_uring_cmd_iopoll_done(ioucmd, pdu->result, pdu->status);
-	} else {
-		io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb);
-	}
-
+	io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb);
 	return RQ_END_IO_FREE;
 }
 

drivers/platform/x86/amd/hsmp/hsmp.c

···
 	short_sleep = jiffies + msecs_to_jiffies(HSMP_SHORT_SLEEP);
 	timeout	= jiffies + msecs_to_jiffies(HSMP_MSG_TIMEOUT);
 
-	while (time_before(jiffies, timeout)) {
+	while (true) {
 		ret = sock->amd_hsmp_rdwr(sock, mbinfo->msg_resp_off, &mbox_status, HSMP_RD);
 		if (ret) {
 			dev_err(sock->dev, "Error %d reading mailbox status\n", ret);
···
 
 		if (mbox_status != HSMP_STATUS_NOT_READY)
 			break;
+
+		if (!time_before(jiffies, timeout))
+			break;
+
 		if (time_before(jiffies, short_sleep))
 			usleep_range(50, 100);
 		else
···
 		return -ENODEV;
 	sock = &hsmp_pdev.sock[msg->sock_ind];
 
-	/*
-	 * The time taken by smu operation to complete is between
-	 * 10us to 1ms. Sometime it may take more time.
-	 * In SMP system timeout of 100 millisecs should
-	 * be enough for the previous thread to finish the operation
-	 */
-	ret = down_timeout(&sock->hsmp_sem, msecs_to_jiffies(HSMP_MSG_TIMEOUT));
+	ret = down_interruptible(&sock->hsmp_sem);
 	if (ret < 0)
 		return ret;
 

drivers/platform/x86/amd/pmc/pmc-quirks.c

···
 			DMI_MATCH(DMI_BOARD_NAME, "WUJIE14-GX4HRXL"),
 		}
 	},
+	/* https://bugzilla.kernel.org/show_bug.cgi?id=220116 */
+	{
+		.ident = "PCSpecialist Lafite Pro V 14M",
+		.driver_data = &quirk_spurious_8042,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "PCSpecialist"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Lafite Pro V 14M"),
+		}
+	},
 	{}
 };
 

drivers/platform/x86/amd/pmc/pmc.c

···
 			return -ENOMEM;
 	}
 
+	memset_io(dev->smu_virt_addr, 0, sizeof(struct smu_metrics));
+
 	/* Start the logging */
 	amd_pmc_send_cmd(dev, 0, NULL, SMU_MSG_LOG_RESET, false);
 	amd_pmc_send_cmd(dev, 0, NULL, SMU_MSG_LOG_START, false);

drivers/platform/x86/amd/pmf/core.c

···
 			dev_err(dev->dev, "Invalid CPU id: 0x%x", dev->cpu_id);
 		}
 
-		dev->buf = kzalloc(dev->mtable_size, GFP_KERNEL);
+		dev->buf = devm_kzalloc(dev->dev, dev->mtable_size, GFP_KERNEL);
 		if (!dev->buf)
 			return -ENOMEM;
 	}
···
 	mutex_destroy(&dev->lock);
 	mutex_destroy(&dev->update_mutex);
 	mutex_destroy(&dev->cb_mutex);
-	kfree(dev->buf);
 }
 
 static const struct attribute_group *amd_pmf_driver_groups[] = {

drivers/platform/x86/amd/pmf/tee-if.c

···
 		return -EINVAL;
 
 	/* re-alloc to the new buffer length of the policy binary */
-	new_policy_buf = memdup_user(buf, length);
-	if (IS_ERR(new_policy_buf))
-		return PTR_ERR(new_policy_buf);
+	new_policy_buf = devm_kzalloc(dev->dev, length, GFP_KERNEL);
+	if (!new_policy_buf)
+		return -ENOMEM;
 
-	kfree(dev->policy_buf);
+	if (copy_from_user(new_policy_buf, buf, length)) {
+		devm_kfree(dev->dev, new_policy_buf);
+		return -EFAULT;
+	}
+
+	devm_kfree(dev->dev, dev->policy_buf);
 	dev->policy_buf = new_policy_buf;
 	dev->policy_sz = length;
 
-	if (!amd_pmf_pb_valid(dev)) {
-		ret = -EINVAL;
-		goto cleanup;
-	}
+	if (!amd_pmf_pb_valid(dev))
+		return -EINVAL;
 
 	amd_pmf_hex_dump_pb(dev);
 	ret = amd_pmf_start_policy_engine(dev);
 	if (ret < 0)
-		goto cleanup;
+		return ret;
 
 	return length;
-
-cleanup:
-	kfree(dev->policy_buf);
-	dev->policy_buf = NULL;
-	return ret;
 }
 
 static const struct file_operations pb_fops = {
···
 	rc = tee_client_open_session(ctx, &sess_arg, NULL);
 	if (rc < 0 || sess_arg.ret != 0) {
 		pr_err("Failed to open TEE session err:%#x, rc:%d\n", sess_arg.ret, rc);
-		return rc;
+		return rc ?: -EINVAL;
 	}
 
 	*id = sess_arg.session;
 
-	return rc;
+	return 0;
 }
 
 static int amd_pmf_register_input_device(struct amd_pmf_dev *dev)
···
 	dev->tee_ctx = tee_client_open_context(NULL, amd_pmf_amdtee_ta_match, NULL, NULL);
 	if (IS_ERR(dev->tee_ctx)) {
 		dev_err(dev->dev, "Failed to open TEE context\n");
-		return PTR_ERR(dev->tee_ctx);
+		ret = PTR_ERR(dev->tee_ctx);
+		dev->tee_ctx = NULL;
+		return ret;
 	}
 
 	ret = amd_pmf_ta_open_session(dev->tee_ctx, &dev->session_id, uuid);
···
 
 static void amd_pmf_tee_deinit(struct amd_pmf_dev *dev)
 {
+	if (!dev->tee_ctx)
+		return;
 	tee_shm_free(dev->fw_shm_pool);
 	tee_client_close_session(dev->tee_ctx, dev->session_id);
 	tee_client_close_context(dev->tee_ctx);
+	dev->tee_ctx = NULL;
 }
 
 int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev)
···
 
 	ret = amd_pmf_set_dram_addr(dev, true);
 	if (ret)
-		goto err_cancel_work;
+		return ret;
 
 	dev->policy_base = devm_ioremap_resource(dev->dev, dev->res);
-	if (IS_ERR(dev->policy_base)) {
-		ret = PTR_ERR(dev->policy_base);
-		goto err_free_dram_buf;
-	}
+	if (IS_ERR(dev->policy_base))
+		return PTR_ERR(dev->policy_base);
 
-	dev->policy_buf = kzalloc(dev->policy_sz, GFP_KERNEL);
-	if (!dev->policy_buf) {
-		ret = -ENOMEM;
-		goto err_free_dram_buf;
-	}
+	dev->policy_buf = devm_kzalloc(dev->dev, dev->policy_sz, GFP_KERNEL);
+	if (!dev->policy_buf)
+		return -ENOMEM;
 
 	memcpy_fromio(dev->policy_buf, dev->policy_base, dev->policy_sz);
 
 	if (!amd_pmf_pb_valid(dev)) {
 		dev_info(dev->dev, "No Smart PC policy present\n");
-		ret = -EINVAL;
-		goto err_free_policy;
+		return -EINVAL;
 	}
 
 	amd_pmf_hex_dump_pb(dev);
 
-	dev->prev_data = kzalloc(sizeof(*dev->prev_data), GFP_KERNEL);
-	if (!dev->prev_data) {
-		ret = -ENOMEM;
-		goto err_free_policy;
-	}
+	dev->prev_data = devm_kzalloc(dev->dev, sizeof(*dev->prev_data), GFP_KERNEL);
+	if (!dev->prev_data)
+		return -ENOMEM;
 
 	for (i = 0; i < ARRAY_SIZE(amd_pmf_ta_uuid); i++) {
 		ret = amd_pmf_tee_init(dev, &amd_pmf_ta_uuid[i]);
 		if (ret)
-			goto err_free_prev_data;
+			return ret;
 
 		ret = amd_pmf_start_policy_engine(dev);
-		switch (ret) {
-		case TA_PMF_TYPE_SUCCESS:
-			status = true;
-			break;
-		case TA_ERROR_CRYPTO_INVALID_PARAM:
-		case TA_ERROR_CRYPTO_BIN_TOO_LARGE:
-			amd_pmf_tee_deinit(dev);
-			status = false;
-			break;
-		default:
-			ret = -EINVAL;
-			amd_pmf_tee_deinit(dev);
-			goto err_free_prev_data;
-		}
-
+		dev_dbg(dev->dev, "start policy engine ret: %d\n", ret);
+		status = ret == TA_PMF_TYPE_SUCCESS;
 		if (status)
 			break;
+		amd_pmf_tee_deinit(dev);
 	}
 
 	if (!status && !pb_side_load) {
 		ret = -EINVAL;
-		goto err_free_prev_data;
+		goto err;
 	}
 
 	if (pb_side_load)
···
 
 	ret = amd_pmf_register_input_device(dev);
 	if (ret)
-		goto err_pmf_remove_pb;
+		goto err;
 
 	return 0;
 
-err_pmf_remove_pb:
-	if (pb_side_load && dev->esbin)
-		amd_pmf_remove_pb(dev);
-	amd_pmf_tee_deinit(dev);
-err_free_prev_data:
-	kfree(dev->prev_data);
-err_free_policy:
-	kfree(dev->policy_buf);
-err_free_dram_buf:
-	kfree(dev->buf);
-err_cancel_work:
-	cancel_delayed_work_sync(&dev->pb_work);
+err:
+	amd_pmf_deinit_smart_pc(dev);
 
 	return ret;
 }
···
 		amd_pmf_remove_pb(dev);
 
 	cancel_delayed_work_sync(&dev->pb_work);
-	kfree(dev->prev_data);
-	dev->prev_data = NULL;
-	kfree(dev->policy_buf);
-	dev->policy_buf = NULL;
-	kfree(dev->buf);
-	dev->buf = NULL;
 	amd_pmf_tee_deinit(dev);
 }

drivers/platform/x86/dell/alienware-wmi-wmax.c

···
 			DMI_MATCH(DMI_SYS_VENDOR, "Alienware"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m16 R1 AMD"),
 		},
-		.driver_data = &g_series_quirks,
+		.driver_data = &generic_quirks,
 	},
 	{
 		.ident = "Alienware m16 R2",

drivers/platform/x86/dell/dell_rbu.c

···
 MODULE_AUTHOR("Abhay Salunke <[e-mail]>");
 MODULE_DESCRIPTION("Driver for updating BIOS image on DELL systems");
 MODULE_LICENSE("GPL");
-MODULE_VERSION("3.2");
+MODULE_VERSION("3.3");
 
 #define BIOS_SCAN_LIMIT 0xffffffff
 #define MAX_IMAGE_LENGTH 16
···
 	rbu_data.imagesize = 0;
 }
 
-static int create_packet(void *data, size_t length)
+static int create_packet(void *data, size_t length) __must_hold(&rbu_data.lock)
 {
 	struct packet_data *newpacket;
 	int ordernum = 0;
···
 	remaining_bytes = *pread_length;
 	bytes_read = rbu_data.packet_read_count;
 
-	list_for_each_entry(newpacket, (&packet_data_head.list)->next, list) {
+	list_for_each_entry(newpacket, &packet_data_head.list, list) {
 		bytes_copied = do_packet_read(pdest, newpacket,
 			remaining_bytes, bytes_read, &temp_count);
 		remaining_bytes -= bytes_copied;
···
 {
 	struct packet_data *newpacket, *tmp;
 
-	list_for_each_entry_safe(newpacket, tmp, (&packet_data_head.list)->next, list) {
+	list_for_each_entry_safe(newpacket, tmp, &packet_data_head.list, list) {
 		list_del(&newpacket->list);
 
 		/*
 		 * zero out the RBU packet memory before freeing
 		 * to make sure there are no stale RBU packets left in memory
 		 */
-		memset(newpacket->data, 0, rbu_data.packetsize);
+		memset(newpacket->data, 0, newpacket->length);
 		set_memory_wb((unsigned long)newpacket->data,
 			1 << newpacket->ordernum);
 		free_pages((unsigned long) newpacket->data,

drivers/platform/x86/ideapad-laptop.c

···
 #include <linux/bug.h>
 #include <linux/cleanup.h>
 #include <linux/debugfs.h>
+#include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/dmi.h>
 #include <linux/i8042.h>
···
  */
 #define IDEAPAD_EC_TIMEOUT 200 /* in ms */
 
+/*
+ * Some models (e.g., ThinkBook since 2024) have a low tolerance for being
+ * polled too frequently. Doing so may break the state machine in the EC,
+ * resulting in a hard shutdown.
+ *
+ * It is also observed that frequent polls may disturb the ongoing operation
+ * and notably delay the availability of EC response.
+ *
+ * These values are used as the delay before the first poll and the interval
+ * between subsequent polls to solve the above issues.
+ */
+#define IDEAPAD_EC_POLL_MIN_US 150
+#define IDEAPAD_EC_POLL_MAX_US 300
+
 static int eval_int(acpi_handle handle, const char *name, unsigned long *res)
 {
 	unsigned long long result;
···
 	end_jiffies = jiffies + msecs_to_jiffies(IDEAPAD_EC_TIMEOUT) + 1;
 
 	while (time_before(jiffies, end_jiffies)) {
-		schedule();
+		usleep_range(IDEAPAD_EC_POLL_MIN_US, IDEAPAD_EC_POLL_MAX_US);
 
 		err = eval_vpcr(handle, 1, &val);
 		if (err)
···
 	end_jiffies = jiffies + msecs_to_jiffies(IDEAPAD_EC_TIMEOUT) + 1;
 
 	while (time_before(jiffies, end_jiffies)) {
-		schedule();
+		usleep_range(IDEAPAD_EC_POLL_MIN_US, IDEAPAD_EC_POLL_MAX_US);
 
 		err = eval_vpcr(handle, 1, &val);
 		if (err)

drivers/platform/x86/intel/pmc/core.h

···
 #define PTL_PCD_PMC_MMIO_REG_LEN		0x31A8
 
 /* SSRAM PMC Device ID */
+/* LNL */
+#define PMC_DEVID_LNL_SOCM	0xa87f
+
+/* PTL */
+#define PMC_DEVID_PTL_PCDH	0xe37f
+#define PMC_DEVID_PTL_PCDP	0xe47f
+
 /* ARL */
 #define PMC_DEVID_ARL_SOCM	0x777f
 #define PMC_DEVID_ARL_SOCS	0xae7f

drivers/platform/x86/intel/pmc/ssram_telemetry.c

···
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PMC_DEVID_MTL_SOCM) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PMC_DEVID_ARL_SOCS) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PMC_DEVID_ARL_SOCM) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PMC_DEVID_LNL_SOCM) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PMC_DEVID_PTL_PCDH) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PMC_DEVID_PTL_PCDP) },
 	{ }
 };
 MODULE_DEVICE_TABLE(pci, intel_pmc_ssram_telemetry_pci_ids);

drivers/platform/x86/intel/tpmi_power_domains.c

···
 
 	domain_die_map = kcalloc(size_mul(topology_max_packages(), MAX_POWER_DOMAINS),
 				 sizeof(*domain_die_map), GFP_KERNEL);
-	if (!domain_die_map)
+	if (!domain_die_map) {
+		ret = -ENOMEM;
 		goto free_domain_mask;
+	}
 
 	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
 				"platform/x86/tpmi_power_domains:online",

drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c

···
 		if (length)
 			length += sysfs_emit_at(buf, length, " ");
 
-		length += sysfs_emit_at(buf, length, agent_name[agent]);
+		length += sysfs_emit_at(buf, length, "%s", agent_name[agent]);
 	}
 
 	length += sysfs_emit_at(buf, length, "\n");

drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c

···
 
 	/* Get the package ID from the TPMI core */
 	plat_info = tpmi_get_platform_data(auxdev);
-	if (plat_info)
-		pkg = plat_info->package_id;
-	else
+	if (unlikely(!plat_info)) {
 		dev_info(&auxdev->dev, "Platform information is NULL\n");
+		ret = -ENODEV;
+		goto err_rem_common;
+	}
+
+	pkg = plat_info->package_id;
 
 	for (i = 0; i < num_resources; ++i) {
 		struct tpmi_uncore_power_domain_info *pd_info;

drivers/platform/x86/samsung-galaxybook.c

···
 }
 
 static const struct acpi_device_id galaxybook_device_ids[] = {
+	{ "SAM0426" },
 	{ "SAM0427" },
 	{ "SAM0428" },
 	{ "SAM0429" },

drivers/ptp/ptp_clock.c

···
 	struct ptp_clock_info *ops;
 	int err = -EOPNOTSUPP;
 
-	if (ptp_clock_freerun(ptp)) {
+	if (tx->modes & (ADJ_SETOFFSET | ADJ_FREQUENCY | ADJ_OFFSET) &&
+	    ptp_clock_freerun(ptp)) {
 		pr_err("ptp: physical clock is free running\n");
 		return -EBUSY;
 	}

drivers/ptp/ptp_private.h

···
 /* Check if ptp virtual clock is in use */
 static inline bool ptp_vclock_in_use(struct ptp_clock *ptp)
 {
-	return !ptp->is_virtual_clock;
+	bool in_use = false;
+
+	/* Virtual clocks can't be stacked on top of virtual clocks.
+	 * Avoid acquiring the n_vclocks_mux on virtual clocks, to allow this
+	 * function to be called from code paths where the n_vclocks_mux of the
+	 * parent physical clock is already held. Functionally that's not an
+	 * issue, but lockdep would complain, because they have the same lock
+	 * class.
+	 */
+	if (ptp->is_virtual_clock)
+		return false;
+
+	if (mutex_lock_interruptible(&ptp->n_vclocks_mux))
+		return true;
+
+	if (ptp->n_vclocks)
+		in_use = true;
+
+	mutex_unlock(&ptp->n_vclocks_mux);
+
+	return in_use;
 }
 
 /* Check if ptp clock shall be free running */

drivers/rapidio/rio_cm.c

···
 	if (buf == NULL || ch_id == 0 || len == 0 || len > RIO_MAX_MSG_SIZE)
 		return -EINVAL;
 
+	if (len < sizeof(struct rio_ch_chan_hdr))
+		return -EINVAL;		/* insufficient data from user */
+
 	ch = riocm_get_channel(ch_id);
 	if (!ch) {
 		riocm_error("%s(%d) ch_%d not found", current->comm,

drivers/regulator/max20086-regulator.c

···
 // Copyright (C) 2022 Laurent Pinchart <[e-mail]>
 // Copyright (C) 2018 Avnet, Inc.
 
+#include <linux/cleanup.h>
 #include <linux/err.h>
 #include <linux/gpio/consumer.h>
 #include <linux/i2c.h>
···
 static int max20086_parse_regulators_dt(struct max20086 *chip, bool *boot_on)
 {
 	struct of_regulator_match *matches;
-	struct device_node *node;
 	unsigned int i;
 	int ret;
 
-	node = of_get_child_by_name(chip->dev->of_node, "regulators");
+	struct device_node *node __free(device_node) =
+		of_get_child_by_name(chip->dev->of_node, "regulators");
 	if (!node) {
 		dev_err(chip->dev, "regulators node not found\n");
 		return -ENODEV;
···
 
 	ret = of_regulator_match(chip->dev, node, matches,
 				 chip->info->num_outputs);
-	of_node_put(node);
 	if (ret < 0) {
 		dev_err(chip->dev, "Failed to match regulators\n");
 		return -EINVAL;

drivers/s390/scsi/zfcp_sysfs.c

···
 	if (kstrtoull(buf, 0, (unsigned long long *) &fcp_lun))
 		return -EINVAL;
 
+	flush_work(&port->rport_work);
+
 	retval = zfcp_unit_add(port, fcp_lun);
 	if (retval)
 		return retval;

drivers/scsi/mvsas/mv_defs.h

···
 
 	/* MVS_Px_INT_STAT, MVS_Px_INT_MASK (per-phy events) */
 	PHYEV_DEC_ERR		= (1U << 24),	/* Phy Decoding Error */
-	PHYEV_DCDR_ERR		= (1U << 23),	/* STP Deocder Error */
+	PHYEV_DCDR_ERR		= (1U << 23),	/* STP Decoder Error */
 	PHYEV_CRC_ERR		= (1U << 22),	/* STP CRC Error */
 	PHYEV_UNASSOC_FIS	= (1U << 19),	/* unassociated FIS rx'd */
 	PHYEV_AN		= (1U << 18),	/* SATA async notification */
···
 	CMD_SATA_PORT_MEM_CTL0	= 0x158, /* SATA Port Memory Control 0 */
 	CMD_SATA_PORT_MEM_CTL1	= 0x15c, /* SATA Port Memory Control 1 */
 	CMD_XOR_MEM_BIST_CTL	= 0x160, /* XOR Memory BIST Control */
-	CMD_XOR_MEM_BIST_STAT	= 0x164, /* XOR Memroy BIST Status */
+	CMD_XOR_MEM_BIST_STAT	= 0x164, /* XOR Memory BIST Status */
 	CMD_DMA_MEM_BIST_CTL	= 0x168, /* DMA Memory BIST Control */
 	CMD_DMA_MEM_BIST_STAT	= 0x16c, /* DMA Memory BIST Status */
 	CMD_PORT_MEM_BIST_CTL	= 0x170, /* Port Memory BIST Control */

drivers/scsi/scsi_error.c

···
 		 * if the device is in the process of becoming ready, we
 		 * should retry.
 		 */
-		if ((sshdr.asc == 0x04) && (sshdr.ascq == 0x01))
+		if ((sshdr.asc == 0x04) &&
+		    (sshdr.ascq == 0x01 || sshdr.ascq == 0x0a))
 			return NEEDS_RETRY;
 		/*
 		 * if the device is not started, we need to wake

drivers/scsi/scsi_transport_iscsi.c

···
 		pr_err("%s could not find host no %u\n",
 		       __func__, ev->u.new_flashnode.host_no);
 		err = -ENODEV;
-		goto put_host;
+		goto exit_new_fnode;
 	}
 
 	index = transport->new_flashnode(shost, data, len);
···
 	else
 		err = -EIO;
 
-put_host:
 	scsi_host_put(shost);
 
 exit_new_fnode:
···
 		pr_err("%s could not find host no %u\n",
 		       __func__, ev->u.del_flashnode.host_no);
 		err = -ENODEV;
-		goto put_host;
+		goto exit_del_fnode;
 	}
 
 	idx = ev->u.del_flashnode.flashnode_idx;
···
 		pr_err("%s could not find host no %u\n",
 		       __func__, ev->u.login_flashnode.host_no);
 		err = -ENODEV;
-		goto put_host;
+		goto exit_login_fnode;
 	}
 
 	idx = ev->u.login_flashnode.flashnode_idx;
···
 		pr_err("%s could not find host no %u\n",
 		       __func__, ev->u.logout_flashnode.host_no);
 		err = -ENODEV;
-		goto put_host;
+		goto exit_logout_fnode;
 	}
 
 	idx = ev->u.logout_flashnode.flashnode_idx;
···
 		pr_err("%s could not find host no %u\n",
 		       __func__, ev->u.logout_flashnode.host_no);
 		err = -ENODEV;
-		goto put_host;
+		goto exit_logout_sid;
 	}
 
 	session = iscsi_session_lookup(ev->u.logout_flashnode_sid.sid);

drivers/scsi/storvsc_drv.c

···
 /*
  * Timeout in seconds for all devices managed by this driver.
  */
-static int storvsc_timeout = 180;
+static const int storvsc_timeout = 180;
 
 #if IS_ENABLED(CONFIG_SCSI_FC_ATTRS)
 static struct scsi_transport_template *fc_transport_template;
···
 		return;
 	}
 
-	t = wait_for_completion_timeout(&request->wait_event, 10*HZ);
+	t = wait_for_completion_timeout(&request->wait_event, storvsc_timeout * HZ);
 	if (t == 0) {
 		dev_err(dev, "Failed to create sub-channel: timed out\n");
 		return;
···
 	if (ret != 0)
 		return ret;
 
-	t = wait_for_completion_timeout(&request->wait_event, 5*HZ);
+	t = wait_for_completion_timeout(&request->wait_event, storvsc_timeout * HZ);
 	if (t == 0)
 		return -ETIMEDOUT;
 
···
 		return ret;
 
 	ret = storvsc_channel_init(device, is_fc);
+	if (ret)
+		vmbus_close(device->channel);
 
 	return ret;
 }
···
 	if (ret != 0)
 		return FAILED;
 
-	t = wait_for_completion_timeout(&request->wait_event, 5*HZ);
+	t = wait_for_completion_timeout(&request->wait_event, storvsc_timeout * HZ);
 	if (t == 0)
 		return TIMEOUT_ERROR;
 

drivers/spi/spi-loongson-core.c

···
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/err.h>
+#include <linux/export.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>

drivers/spi/spi-offload.c

···
 	if (trigger->ops->enable) {
 		ret = trigger->ops->enable(trigger, config);
 		if (ret) {
-			if (offload->ops->trigger_disable)
+			if (offload->ops && offload->ops->trigger_disable)
 				offload->ops->trigger_disable(offload);
 			return ret;
 		}

drivers/spi/spi-omap2-mcspi.c

···
 	size_t			max_xfer_len;
 	u32			ref_clk_hz;
 	bool			use_multi_mode;
+	bool			last_msg_kept_cs;
 };
 
 struct omap2_mcspi_cs {
···
 	 * multi-mode is applicable.
 	 */
 	mcspi->use_multi_mode = true;
+
+	if (mcspi->last_msg_kept_cs)
+		mcspi->use_multi_mode = false;
+
 	list_for_each_entry(tr, &msg->transfers, transfer_list) {
 		if (!tr->bits_per_word)
 			bits_per_word = msg->spi->bits_per_word;
···
 			mcspi->use_multi_mode = false;
 		}
 
-		/* Check if transfer asks to change the CS status after the transfer */
-		if (!tr->cs_change)
-			mcspi->use_multi_mode = false;
-
-		/*
-		 * If at least one message is not compatible, switch back to single mode
-		 *
-		 * The bits_per_word of certain transfer can be different, but it will have no
-		 * impact on the signal itself.
-		 */
-		if (!mcspi->use_multi_mode)
-			break;
+		if (list_is_last(&tr->transfer_list, &msg->transfers)) {
+			/* Check if transfer asks to keep the CS status after the whole message */
+			if (tr->cs_change) {
+				mcspi->use_multi_mode = false;
+				mcspi->last_msg_kept_cs = true;
+			} else {
+				mcspi->last_msg_kept_cs = false;
+			}
+		} else {
+			/* Check if transfer asks to change the CS status after the transfer */
+			if (!tr->cs_change)
+				mcspi->use_multi_mode = false;
+		}
 	}
 
 	omap2_mcspi_set_mode(ctlr);

drivers/spi/spi-pci1xxxx.c

···
 				return -EINVAL;
 
 			num_vector = pci_alloc_irq_vectors(pdev, 1, hw_inst_cnt,
-							   PCI_IRQ_ALL_TYPES);
+							   PCI_IRQ_INTX | PCI_IRQ_MSI);
 			if (num_vector < 0) {
 				dev_err(&pdev->dev, "Error allocating MSI vectors\n");
-				return ret;
+				return num_vector;
 			}
 
 			init_completion(&spi_sub_ptr->spi_xfer_done);

drivers/spi/spi-stm32-ospi.c

···
 		return ret;
 	}
 
-	ospi->rstc = devm_reset_control_array_get_exclusive(dev);
+	ospi->rstc = devm_reset_control_array_get_exclusive_released(dev);
 	if (IS_ERR(ospi->rstc))
 		return dev_err_probe(dev, PTR_ERR(ospi->rstc),
 				     "Can't get reset\n");
···
 	if (ret < 0)
 		goto err_pm_enable;
 
-	if (ospi->rstc) {
-		reset_control_assert(ospi->rstc);
-		udelay(2);
-		reset_control_deassert(ospi->rstc);
+	ret = reset_control_acquire(ospi->rstc);
+	if (ret) {
+		dev_err_probe(dev, ret, "Can not acquire reset %d\n", ret);
+		goto err_pm_resume;
 	}
+
+	reset_control_assert(ospi->rstc);
+	udelay(2);
+	reset_control_deassert(ospi->rstc);
 
 	ret = spi_register_controller(ctrl);
 	if (ret) {
···
 	if (ospi->dma_chrx)
 		dma_release_channel(ospi->dma_chrx);
 
+	reset_control_release(ospi->rstc);
+
 	pm_runtime_put_sync_suspend(ospi->dev);
 	pm_runtime_force_suspend(ospi->dev);
 }
···
 	struct stm32_ospi *ospi = dev_get_drvdata(dev);
 
 	pinctrl_pm_select_sleep_state(dev);
+
+	reset_control_release(ospi->rstc);
 
 	return pm_runtime_force_suspend(ospi->dev);
 }
···
 	ret = pm_runtime_resume_and_get(ospi->dev);
 	if (ret < 0)
 		return ret;
+
+	ret = reset_control_acquire(ospi->rstc);
+	if (ret) {
+		dev_err(dev, "Can not acquire reset\n");
+		return ret;
+	}
 
 	writel_relaxed(ospi->cr_reg, regs_base + OSPI_CR);
 	writel_relaxed(ospi->dcr_reg, regs_base + OSPI_DCR1);

drivers/ufs/core/ufshcd.c

···
 		up(&hba->host_sem);
 		return;
 	}
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
+
+	ufshcd_err_handling_prepare(hba);
+
+	spin_lock_irqsave(hba->host->host_lock, flags);
 	ufshcd_set_eh_in_progress(hba);
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
-	ufshcd_err_handling_prepare(hba);
+
 	/* Complete requests that have door-bell cleared by h/w */
 	ufshcd_complete_requests(hba, false);
 	spin_lock_irqsave(hba->host->host_lock, flags);

fs/bcachefs/bcachefs.h

···
 #define bch2_fmt(_c, fmt)		bch2_log_msg(_c, fmt "\n")
 
 void bch2_print_str(struct bch_fs *, const char *, const char *);
-void bch2_print_str_nonblocking(struct bch_fs *, const char *, const char *);
 
 __printf(2, 3)
 void bch2_print_opts(struct bch_opts *, const char *, ...);

fs/bcachefs/btree_gc.c

···
 			continue;
 		}
 
-		ret = btree_check_node_boundaries(trans, b, prev, cur, pulled_from_scan);
+		ret = lockrestart_do(trans,
+			btree_check_node_boundaries(trans, b, prev, cur, pulled_from_scan));
+		if (ret < 0)
+			goto err;
+
 		if (ret == DID_FILL_FROM_SCAN) {
 			new_pass = true;
 			ret = 0;
···
 
 	if (!ret && !IS_ERR_OR_NULL(prev)) {
 		BUG_ON(cur);
-		ret = btree_repair_node_end(trans, b, prev, pulled_from_scan);
+		ret = lockrestart_do(trans,
+			btree_repair_node_end(trans, b, prev, pulled_from_scan));
 		if (ret == DID_FILL_FROM_SCAN) {
 			new_pass = true;
 			ret = 0;
···
 	bch2_bkey_buf_exit(&prev_k, c);
 	bch2_bkey_buf_exit(&cur_k, c);
 	printbuf_exit(&buf);
+	bch_err_fn(c, ret);
+	return ret;
+}
+
+static int bch2_check_root(struct btree_trans *trans, enum btree_id i,
+			   bool *reconstructed_root)
+{
+	struct bch_fs *c = trans->c;
+	struct btree_root *r = bch2_btree_id_root(c, i);
+	struct printbuf buf = PRINTBUF;
+	int ret = 0;
+
+	bch2_btree_id_to_text(&buf, i);
+
+	if (r->error) {
+		bch_info(c, "btree root %s unreadable, must recover from scan", buf.buf);
+
+		r->alive = false;
+		r->error = 0;
+
+		if (!bch2_btree_has_scanned_nodes(c, i)) {
+			__fsck_err(trans,
+				   FSCK_CAN_FIX|(!btree_id_important(i) ? FSCK_AUTOFIX : 0),
+				   btree_root_unreadable_and_scan_found_nothing,
+				   "no nodes found for btree %s, continue?", buf.buf);
+			bch2_btree_root_alloc_fake_trans(trans, i, 0);
+		} else {
+			bch2_btree_root_alloc_fake_trans(trans, i, 1);
+			bch2_shoot_down_journal_keys(c, i, 1, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX);
+			ret = bch2_get_scanned_nodes(c, i, 0, POS_MIN, SPOS_MAX);
+			if (ret)
+				goto err;
+		}
+
+		*reconstructed_root = true;
+	}
+err:
+fsck_err:
+	printbuf_exit(&buf);
+	bch_err_fn(c, ret);
 	return ret;
 }
 
···
 {
 	struct btree_trans *trans = bch2_trans_get(c);
 	struct bpos pulled_from_scan = POS_MIN;
-	struct printbuf buf = PRINTBUF;
 	int ret = 0;
 
 	bch2_trans_srcu_unlock(trans);
 
 	for (unsigned i = 0; i < btree_id_nr_alive(c) && !ret; i++) {
-		struct btree_root *r = bch2_btree_id_root(c, i);
 		bool reconstructed_root = false;
+recover:
+		ret = lockrestart_do(trans, bch2_check_root(trans, i, &reconstructed_root));
+		if (ret)
+			break;
 
-		printbuf_reset(&buf);
-		bch2_btree_id_to_text(&buf, i);
-
-		if (r->error) {
-reconstruct_root:
-			bch_info(c, "btree root %s unreadable, must recover from scan", buf.buf);
-
-			r->alive = false;
-			r->error = 0;
-
-			if (!bch2_btree_has_scanned_nodes(c, i)) {
-				__fsck_err(trans,
-					   FSCK_CAN_FIX|(!btree_id_important(i) ? FSCK_AUTOFIX : 0),
-					   btree_root_unreadable_and_scan_found_nothing,
-					   "no nodes found for btree %s, continue?", buf.buf);
-				bch2_btree_root_alloc_fake_trans(trans, i, 0);
-			} else {
-				bch2_btree_root_alloc_fake_trans(trans, i, 1);
-				bch2_shoot_down_journal_keys(c, i, 1, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX);
-				ret = bch2_get_scanned_nodes(c, i, 0, POS_MIN, SPOS_MAX);
-				if (ret)
-					break;
-			}
-
-			reconstructed_root = true;
-		}
-
+		struct btree_root *r = bch2_btree_id_root(c, i);
 		struct btree *b = r->b;
 
 		btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_read);
···
 
 			r->b = NULL;
 
-			if (!reconstructed_root)
-				goto reconstruct_root;
+			if (!reconstructed_root) {
+				r->error = -EIO;
+				goto recover;
+			}
 
+			struct printbuf buf = PRINTBUF;
+			bch2_btree_id_to_text(&buf, i);
 			bch_err(c, "empty btree root %s", buf.buf);
+			printbuf_exit(&buf);
 			bch2_btree_root_alloc_fake_trans(trans, i, 0);
 			r->alive = false;
 			ret = 0;
 		}
 	}
-fsck_err:
-	printbuf_exit(&buf);
+
 	bch2_trans_put(trans);
 	return ret;
 }

fs/bcachefs/btree_io.c

···
 		     BCH_VERSION_MAJOR(version),
 		     BCH_VERSION_MINOR(version));
 
-	if (btree_err_on(version < c->sb.version_min,
+	if (c->recovery.curr_pass != BCH_RECOVERY_PASS_scan_for_btree_nodes &&
+	    btree_err_on(version < c->sb.version_min,
 			 -BCH_ERR_btree_node_read_err_fixable,
 			 c, NULL, b, i, NULL,
 			 btree_node_bset_older_than_sb_min,
 			 "bset version %u older than superblock version_min %u",
 			 version, c->sb.version_min)) {
-		mutex_lock(&c->sb_lock);
-		c->disk_sb.sb->version_min = cpu_to_le16(version);
-		bch2_write_super(c);
-		mutex_unlock(&c->sb_lock);
+		if (bch2_version_compatible(version)) {
+			mutex_lock(&c->sb_lock);
+			c->disk_sb.sb->version_min = cpu_to_le16(version);
+			bch2_write_super(c);
+			mutex_unlock(&c->sb_lock);
+		} else {
+			/* We have no idea what's going on: */
+			i->version = cpu_to_le16(c->sb.version);
+		}
 	}
 
 	if (btree_err_on(BCH_VERSION_MAJOR(version) >
···
 		le16_add_cpu(&i->u64s, -next_good_key);
 		memmove_u64s_down(k, (u64 *) k + next_good_key, (u64 *) vstruct_end(i) - (u64 *) k);
 		set_btree_node_need_rewrite(b);
+		set_btree_node_need_rewrite_error(b);
 	}
 fsck_err:
 	printbuf_exit(&buf);
···
 					  (u64 *) vstruct_end(i) - (u64 *) k);
 			set_btree_bset_end(b, b->set);
 			set_btree_node_need_rewrite(b);
+			set_btree_node_need_rewrite_error(b);
 			continue;
 		}
 		if (ret)
···
 		bkey_for_each_ptr(bch2_bkey_ptrs(bkey_i_to_s(&b->key)), ptr) {
 			struct bch_dev *ca2 = bch2_dev_rcu(c, ptr->dev);
 
-			if (!ca2 || ca2->mi.state != BCH_MEMBER_STATE_rw)
+			if (!ca2 || ca2->mi.state != BCH_MEMBER_STATE_rw) {
 				set_btree_node_need_rewrite(b);
+				set_btree_node_need_rewrite_degraded(b);
+			}
 		}
 
-	if (!ptr_written)
+	if (!ptr_written) {
 		set_btree_node_need_rewrite(b);
+		set_btree_node_need_rewrite_ptr_written_zero(b);
+	}
 fsck_err:
 	mempool_free(iter, &c->fill_iter);
 	printbuf_exit(&buf);

fs/bcachefs/btree_locking.c

···
 		prt_newline(&buf);
 	}
 
-	bch2_print_str_nonblocking(g->g->trans->c, KERN_ERR, buf.buf);
+	bch2_print_str(g->g->trans->c, KERN_ERR, buf.buf);
 	printbuf_exit(&buf);
 	BUG();
 }

fs/bcachefs/btree_locking.h

···
 	EBUG_ON(!btree_node_locked(path, path->level));
 	EBUG_ON(path->uptodate);
 
-	path->should_be_locked = true;
-	trace_btree_path_should_be_locked(trans, path);
+	if (!path->should_be_locked) {
+		path->should_be_locked = true;
+		trace_btree_path_should_be_locked(trans, path);
+	}
 }
 
 static inline void __btree_path_set_level_up(struct btree_trans *trans,

fs/bcachefs/btree_types.h

···
 	x(dying)							\
 	x(fake)								\
 	x(need_rewrite)							\
+	x(need_rewrite_error)						\
+	x(need_rewrite_degraded)					\
+	x(need_rewrite_ptr_written_zero)				\
 	x(never_write)							\
 	x(pinned)
 
···
 
 BTREE_FLAGS()
 #undef x
+
+#define BTREE_NODE_REWRITE_REASON()					\
+	x(none)								\
+	x(unknown)							\
+	x(error)							\
+	x(degraded)							\
+	x(ptr_written_zero)
+
+enum btree_node_rewrite_reason {
+#define x(n)	BTREE_NODE_REWRITE_##n,
+	BTREE_NODE_REWRITE_REASON()
+#undef x
+};
+
+static inline enum btree_node_rewrite_reason btree_node_rewrite_reason(struct btree *b)
+{
+	if (btree_node_need_rewrite_ptr_written_zero(b))
+		return BTREE_NODE_REWRITE_ptr_written_zero;
+	if (btree_node_need_rewrite_degraded(b))
+		return BTREE_NODE_REWRITE_degraded;
+	if (btree_node_need_rewrite_error(b))
+		return BTREE_NODE_REWRITE_error;
+	if (btree_node_need_rewrite(b))
+		return BTREE_NODE_REWRITE_unknown;
+	return BTREE_NODE_REWRITE_none;
+}
 
 static inline struct btree_write *btree_current_write(struct btree *b)
 {

fs/bcachefs/btree_update_interior.c

···
 			       start_time);
 }
 
+static const char * const btree_node_reawrite_reason_strs[] = {
+#define x(n)	#n,
+	BTREE_NODE_REWRITE_REASON()
+#undef x
+	NULL,
+};
+
 static struct btree_update *
 bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path,
 			unsigned level_start, bool split,
···
 	mutex_lock(&c->btree_interior_update_lock);
 	list_add_tail(&as->list, &c->btree_interior_update_list);
 	mutex_unlock(&c->btree_interior_update_lock);
+
+	struct btree *b = btree_path_node(path, path->level);
+	as->node_start	= b->data->min_key;
+	as->node_end	= b->data->max_key;
+	as->node_needed_rewrite = btree_node_rewrite_reason(b);
+	as->node_written = b->written;
+	as->node_sectors = btree_buf_bytes(b) >> 9;
+	as->node_remaining = __bch2_btree_u64s_remaining(b,
+				btree_bkey_last(b, bset_tree_last(b)));
 
 	/*
 	 * We don't want to allocate if we're in an error state, that can cause
···
 	if (ret)
 		goto err;
 
+	as->node_start	= prev->data->min_key;
+	as->node_end	= next->data->max_key;
+
 	trace_and_count(c, btree_node_merge, trans, b);
 
 	n = bch2_btree_node_alloc(as, trans, b->c.level);
···
 
 	prt_str(out, " ");
 	bch2_btree_id_to_text(out, as->btree_id);
-	prt_printf(out, " l=%u-%u mode=%s nodes_written=%u cl.remaining=%u journal_seq=%llu\n",
+	prt_printf(out, " l=%u-%u ",
 		   as->update_level_start,
-		   as->update_level_end,
+		   as->update_level_end);
+	bch2_bpos_to_text(out, as->node_start);
+	prt_char(out, ' ');
+	bch2_bpos_to_text(out, as->node_end);
+	prt_printf(out, "\nwritten %u/%u u64s_remaining %u need_rewrite %s",
+		   as->node_written,
+		   as->node_sectors,
+		   as->node_remaining,
+		   btree_node_reawrite_reason_strs[as->node_needed_rewrite]);
+
+	prt_printf(out, "\nmode=%s nodes_written=%u cl.remaining=%u journal_seq=%llu\n",
 		   bch2_btree_update_modes[as->mode],
 		   as->nodes_written,
 		   closure_nr_remaining(&as->cl),

fs/bcachefs/btree_update_interior.h

···
 	unsigned			took_gc_lock:1;
 
 	enum btree_id			btree_id;
+	struct bpos			node_start;
+	struct bpos			node_end;
+	enum btree_node_rewrite_reason	node_needed_rewrite;
+	u16				node_written;
+	u16				node_sectors;
+	u16				node_remaining;
+
 	unsigned			update_level_start;
 	unsigned			update_level_end;
 

fs/bcachefs/chardev.c

···
 	return ret;
 }
 
-static long bch2_ioctl_fs_usage(struct bch_fs *c,
+static noinline_for_stack long bch2_ioctl_fs_usage(struct bch_fs *c,
 				struct bch_ioctl_fs_usage __user *user_arg)
 {
 	struct bch_ioctl_fs_usage arg = {};
···
 }
 
 /* obsolete, didn't allow for new data types: */
-static long bch2_ioctl_dev_usage(struct bch_fs *c,
+static noinline_for_stack long bch2_ioctl_dev_usage(struct bch_fs *c,
 				 struct bch_ioctl_dev_usage __user *user_arg)
 {
 	struct bch_ioctl_dev_usage arg;

fs/bcachefs/disk_accounting.c

···
 			for (unsigned j = 0; j < nr; j++)
 				src_v[j] -= dst_v[j];
 
-			if (fsck_err(trans, accounting_mismatch, "%s", buf.buf)) {
+			bch2_trans_unlock_long(trans);
+
+			if (fsck_err(c, accounting_mismatch, "%s", buf.buf)) {
 				percpu_up_write(&c->mark_lock);
 				ret = commit_do(trans, NULL, NULL, 0,
 						bch2_disk_accounting_mod(trans, &acc_k, src_v, nr, false));

fs/bcachefs/error.c

···
 	if (trans)
 		bch2_trans_updates_to_text(&buf, trans);
 	bool ret = __bch2_inconsistent_error(c, &buf);
-	bch2_print_str_nonblocking(c, KERN_ERR, buf.buf);
+	bch2_print_str(c, KERN_ERR, buf.buf);
 
 	printbuf_exit(&buf);
 	return ret;
···
 
 	if (s)
 		s->ret = ret;
+
+	if (trans)
+		ret = bch2_trans_log_str(trans, bch2_sb_error_strs[err]) ?: ret;
 err_unlock:
 	mutex_unlock(&c->fsck_error_msgs_lock);
 err:

fs/bcachefs/fs.c

···
 	if (ret)
 		goto err_stop_fs;
 
+	/*
+	 * We might be doing a RO mount because other options required it, or we
+	 * have no alloc info and it's a small image with no room to regenerate
+	 * it
+	 */
+	if (c->opts.read_only)
+		fc->sb_flags |= SB_RDONLY;
+
 	sb = sget(fc->fs_type, NULL, bch2_set_super, fc->sb_flags|SB_NOSEC, c);
 	ret = PTR_ERR_OR_ZERO(sb);
 	if (ret)

fs/bcachefs/io_read.c

···
 
 	*bounce		= true;
 	*read_full	= promote_full;
+
+	if (have_io_error(failed))
+		orig->self_healing = true;
+
 	return promote;
 nopromote:
 	trace_io_read_nopromote(c, ret);
···
 			prt_str(&buf, "(internal move) ");
 
 		prt_str(&buf, "data read error, ");
-		if (!ret)
+		if (!ret) {
 			prt_str(&buf, "successful retry");
-		else
+			if (rbio->self_healing)
+				prt_str(&buf, ", self healing");
+		} else
 			prt_str(&buf, bch2_err_str(ret));
 		prt_newline(&buf);
+
 
 		if (!bkey_deleted(&sk.k->k)) {
 			bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(sk.k));

fs/bcachefs/io_read.h

···
 				have_ioref:1,
 				narrow_crcs:1,
 				saw_error:1,
+				self_healing:1,
 				context:2;
 	};
 	u16			_state;

fs/bcachefs/movinggc.c

···
 #include <linux/wait.h>
 
 struct buckets_in_flight {
-	struct rhashtable	table;
+	struct rhashtable	*table;
 	struct move_bucket	*first;
 	struct move_bucket	*last;
 	size_t			nr;
···
 static void move_bucket_free(struct buckets_in_flight *list,
 			     struct move_bucket *b)
 {
-	int ret = rhashtable_remove_fast(&list->table, &b->hash,
+	int ret = rhashtable_remove_fast(list->table, &b->hash,
 					 bch_move_bucket_params);
 	BUG_ON(ret);
 	kfree(b);
···
 static bool bucket_in_flight(struct buckets_in_flight *list,
 			     struct move_bucket_key k)
 {
-	return rhashtable_lookup_fast(&list->table, &k, bch_move_bucket_params);
+	return rhashtable_lookup_fast(list->table, &k, bch_move_bucket_params);
 }
 
 static int bch2_copygc_get_buckets(struct moving_context *ctxt,
···
 				goto err;
 			}
 
-			ret2 = rhashtable_lookup_insert_fast(&buckets_in_flight->table, &b_i->hash,
+			ret2 = rhashtable_lookup_insert_fast(buckets_in_flight->table, &b_i->hash,
 							     bch_move_bucket_params);
 			BUG_ON(ret2);
 
···
 	struct buckets_in_flight buckets = {};
 	u64 last, wait;
 
-	int ret = rhashtable_init(&buckets.table, &bch_move_bucket_params);
+	buckets.table = kzalloc(sizeof(*buckets.table), GFP_KERNEL);
+	int ret = !buckets.table
+		? -ENOMEM
+		: rhashtable_init(buckets.table, &bch_move_bucket_params);
 	bch_err_msg(c, ret, "allocating copygc buckets in flight");
 	if (ret)
-		return ret;
+		goto err;
 
 	set_freezable();
 
···
 	}
 
 	move_buckets_wait(&ctxt, &buckets, true);
-	rhashtable_destroy(&buckets.table);
+	rhashtable_destroy(buckets.table);
 	bch2_moving_ctxt_exit(&ctxt);
 	bch2_move_stats_exit(&move_stats, c);
-
-	return 0;
+err:
+	kfree(buckets.table);
+	return ret;
 }
 
 void bch2_copygc_stop(struct bch_fs *c)

fs/bcachefs/namei.c

···
 		new_inode->bi_dir_offset	= dir_offset;
 	}
 
+	if (S_ISDIR(mode)) {
+		ret = bch2_maybe_propagate_has_case_insensitive(trans,
+				(subvol_inum) {
+					new_inode->bi_subvol ?: dir.subvol,
+					new_inode->bi_inum },
+				new_inode);
+		if (ret)
+			goto err;
+	}
+
 	if (S_ISDIR(mode) &&
 	    !new_inode->bi_subvol)
 		new_inode->bi_depth = dir_u->bi_depth + 1;

fs/bcachefs/rcu_pending.c

···
 	while (nr--)
 		kfree(*p);
 }
-
-#define local_irq_save(flags)		\
-do {					\
-	flags = 0;			\
-} while (0)
 #endif
 
 static noinline void __process_finished_items(struct rcu_pending *pending,
···
 
 	BUG_ON((ptr != NULL) != (pending->process == RCU_PENDING_KVFREE_FN));
 
-	local_irq_save(flags);
-	p = this_cpu_ptr(pending->p);
-	spin_lock(&p->lock);
+	/* We could technically be scheduled before taking the lock and end up
+	 * using a different cpu's rcu_pending_pcpu: that's ok, it needs a lock
+	 * anyways
+	 *
+	 * And we have to do it this way to avoid breaking PREEMPT_RT, which
+	 * redefines how spinlocks work:
+	 */
+	p = raw_cpu_ptr(pending->p);
+	spin_lock_irqsave(&p->lock, flags);
 	rcu_gp_poll_state_t seq = __get_state_synchronize_rcu(pending->srcu);
 restart:
 	if (may_sleep &&
···
 		goto free_node;
 	}
 
-	local_irq_save(flags);
-	p = this_cpu_ptr(pending->p);
-	spin_lock(&p->lock);
+	p = raw_cpu_ptr(pending->p);
+	spin_lock_irqsave(&p->lock, flags);
 	goto restart;
 }
 

fs/bcachefs/recovery.c

···
 		goto out;
 	case BTREE_ID_snapshots:
 		ret = __bch2_run_explicit_recovery_pass(c, msg, BCH_RECOVERY_PASS_reconstruct_snapshots, 0) ?: ret;
+		ret = __bch2_run_explicit_recovery_pass(c, msg, BCH_RECOVERY_PASS_check_topology, 0) ?: ret;
 		ret = __bch2_run_explicit_recovery_pass(c, msg, BCH_RECOVERY_PASS_scan_for_btree_nodes, 0) ?: ret;
 		goto out;
 	default:
+		ret = __bch2_run_explicit_recovery_pass(c, msg, BCH_RECOVERY_PASS_check_topology, 0) ?: ret;
 		ret = __bch2_run_explicit_recovery_pass(c, msg, BCH_RECOVERY_PASS_scan_for_btree_nodes, 0) ?: ret;
 		goto out;
 	}
···
 		goto out;
 
 	struct btree_path *path = btree_iter_path(trans, &iter);
-	if (unlikely(!btree_path_node(path, k->level))) {
+	if (unlikely(!btree_path_node(path, k->level) &&
+		     !k->allocated)) {
+		struct bch_fs *c = trans->c;
+
+		if (!(c->recovery.passes_complete & (BIT_ULL(BCH_RECOVERY_PASS_scan_for_btree_nodes)|
+						     BIT_ULL(BCH_RECOVERY_PASS_check_topology)))) {
+			bch_err(c, "have key in journal replay for btree depth that does not exist, confused");
+			ret = -EINVAL;
+		}
+#if 0
 		bch2_trans_iter_exit(trans, &iter);
 		bch2_trans_node_iter_init(trans, &iter, k->btree_id, k->k->k.p,
 					  BTREE_MAX_DEPTH, 0, iter_flags);
 		ret =   bch2_btree_iter_traverse(trans, &iter) ?:
 			bch2_btree_increase_depth(trans, iter.path, 0) ?:
 			-BCH_ERR_transaction_restart_nested;
+#endif
+		k->overwritten = true;
 		goto out;
 	}
 
···
 			? min(c->opts.recovery_pass_last, BCH_RECOVERY_PASS_snapshots_read)
 			: BCH_RECOVERY_PASS_snapshots_read;
 		c->opts.nochanges = true;
-		c->opts.read_only = true;
 	}
+
+	if (c->opts.nochanges)
+		c->opts.read_only = true;
 
 	mutex_lock(&c->sb_lock);
 	struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext);
···
 out:
 	bch2_flush_fsck_errs(c);
 
-	if (!IS_ERR(clean))
-		kfree(clean);
-
 	if (!ret &&
 	    test_bit(BCH_FS_need_delete_dead_snapshots, &c->flags) &&
 	    !c->opts.nochanges) {
···
 	}
 
 	bch_err_fn(c, ret);
+final_out:
+	if (!IS_ERR(clean))
+		kfree(clean);
 	return ret;
 err:
 fsck_err:
···
 		bch2_print_str(c, KERN_ERR, buf.buf);
 		printbuf_exit(&buf);
 	}
-	return ret;
+	goto final_out;
 }
 
 int bch2_fs_initialize(struct bch_fs *c)

fs/bcachefs/recovery_passes.c

···
 				    enum bch_run_recovery_pass_flags *flags)
 {
 	struct bch_fs_recovery *r = &c->recovery;
-	bool in_recovery = test_bit(BCH_FS_in_recovery, &c->flags);
-	bool persistent = !in_recovery || !(*flags & RUN_RECOVERY_PASS_nopersistent);
+
+	/*
+	 * Never run scan_for_btree_nodes persistently: check_topology will run
+	 * it if required
+	 */
+	if (pass == BCH_RECOVERY_PASS_scan_for_btree_nodes)
+		*flags |= RUN_RECOVERY_PASS_nopersistent;
 
 	if ((*flags & RUN_RECOVERY_PASS_ratelimit) &&
 	    !bch2_recovery_pass_want_ratelimit(c, pass))
···
 	 * Otherwise, we run run_explicit_recovery_pass when we find damage, so
 	 * it should run again even if it's already run:
 	 */
+	bool in_recovery = test_bit(BCH_FS_in_recovery, &c->flags);
+	bool persistent = !in_recovery || !(*flags & RUN_RECOVERY_PASS_nopersistent);
 
 	if (persistent
 	    ? !(c->sb.recovery_passes_required & BIT_ULL(pass))
···
 {
 	struct bch_fs_recovery *r = &c->recovery;
 	int ret = 0;
+
 
 	lockdep_assert_held(&c->sb_lock);
 
···
 
 int bch2_run_print_explicit_recovery_pass(struct bch_fs *c, enum bch_recovery_pass pass)
 {
-	enum bch_run_recovery_pass_flags flags = RUN_RECOVERY_PASS_nopersistent;
+	enum bch_run_recovery_pass_flags flags = 0;
 
 	if (!recovery_pass_needs_set(c, pass, &flags))
 		return 0;

fs/bcachefs/sb-downgrade.c

···
 
 static int downgrade_table_extra(struct bch_fs *c, darray_char *table)
 {
+	unsigned dst_offset = table->nr;
 	struct bch_sb_field_downgrade_entry *dst = (void *) &darray_top(*table);
 	unsigned bytes = sizeof(*dst) + sizeof(dst->errors[0]) * le16_to_cpu(dst->nr_errors);
 	int ret = 0;
···
 			if (ret)
 				return ret;
 
+			dst = (void *) &table->data[dst_offset];
+			dst->nr_errors = cpu_to_le16(nr_errors + 1);
+
 			/* open coded __set_bit_le64, as dst is packed and
 			 * dst->recovery_passes is misaligned */
 			unsigned b = BCH_RECOVERY_PASS_STABLE_check_allocations;
···
 		break;
 	}
 
-	dst->nr_errors = cpu_to_le16(nr_errors);
 	return ret;
 }
 

fs/bcachefs/sb-errors_format.h

···
 	x(bucket_gens_to_invalid_buckets,			121,	FSCK_AUTOFIX)	\
 	x(bucket_gens_nonzero_for_invalid_buckets,		122,	FSCK_AUTOFIX)	\
 	x(need_discard_freespace_key_to_invalid_dev_bucket,	123,	0)		\
-	x(need_discard_freespace_key_bad,			124,	0)		\
+	x(need_discard_freespace_key_bad,			124,	FSCK_AUTOFIX)	\
 	x(discarding_bucket_not_in_need_discard_btree,		291,	0)		\
 	x(backpointer_bucket_offset_wrong,			125,	0)		\
 	x(backpointer_level_bad,				294,	0)		\
···
 	x(ptr_to_missing_replicas_entry,			149,	FSCK_AUTOFIX)	\
 	x(ptr_to_missing_stripe,				150,	0)		\
 	x(ptr_to_incorrect_stripe,				151,	0)		\
-	x(ptr_gen_newer_than_bucket_gen,			152,	0)		\
+	x(ptr_gen_newer_than_bucket_gen,			152,	FSCK_AUTOFIX)		\
 	x(ptr_too_stale,					153,	0)		\
 	x(stale_dirty_ptr,					154,	FSCK_AUTOFIX)	\
 	x(ptr_bucket_data_type_mismatch,			155,	0)		\
···
 	x(inode_multiple_links_but_nlink_0,			207,	FSCK_AUTOFIX)	\
 	x(inode_wrong_backpointer,				208,	FSCK_AUTOFIX)	\
 	x(inode_wrong_nlink,					209,	FSCK_AUTOFIX)	\
-	x(inode_has_child_snapshots_wrong,			287,	0)		\
+	x(inode_has_child_snapshots_wrong,			287,	FSCK_AUTOFIX)	\
 	x(inode_unreachable,					210,	FSCK_AUTOFIX)	\
 	x(inode_journal_seq_in_future,				299,	FSCK_AUTOFIX)	\
 	x(inode_i_sectors_underflow,				312,	FSCK_AUTOFIX)	\
···
 	x(root_dir_missing,					239,	0)		\
 	x(root_inode_not_dir,					240,	0)		\
 	x(dir_loop,						241,	0)		\
-	x(hash_table_key_duplicate,				242,	0)		\
-	x(hash_table_key_wrong_offset,				243,	0)		\
+	x(hash_table_key_duplicate,				242,	FSCK_AUTOFIX)	\
+	x(hash_table_key_wrong_offset,				243,	FSCK_AUTOFIX)	\
 	x(unlinked_inode_not_on_deleted_list,			244,	FSCK_AUTOFIX)	\
 	x(reflink_p_front_pad_bad,				245,	0)		\
 	x(journal_entry_dup_same_device,			246,	0)		\

fs/bcachefs/sb-members.c

···
 {
 	struct bch_sb_field_members_v1 *mi = field_to_type(f, members_v1);
 	struct bch_sb_field_disk_groups *gi = bch2_sb_field_get(sb, disk_groups);
-	unsigned i;
 
-	for (i = 0; i < sb->nr_devices; i++)
+	if (vstruct_end(&mi->field) <= (void *) &mi->_members[0]) {
+		prt_printf(out, "field ends before start of entries");
+		return;
+	}
+
+	unsigned nr = (vstruct_end(&mi->field) - (void *) &mi->_members[0]) / sizeof(mi->_members[0]);
+	if (nr != sb->nr_devices)
+		prt_printf(out, "nr_devices mismatch: have %i entries, should be %u", nr, sb->nr_devices);
+
+	for (unsigned i = 0; i < min(sb->nr_devices, nr); i++)
 		member_to_text(out, members_v1_get(mi, i), gi, sb, i);
 }
 
···
 {
 	struct bch_sb_field_members_v2 *mi = field_to_type(f, members_v2);
 	struct bch_sb_field_disk_groups *gi = bch2_sb_field_get(sb, disk_groups);
-	unsigned i;
 
-	for (i = 0; i < sb->nr_devices; i++)
+	if (vstruct_end(&mi->field) <= (void *) &mi->_members[0]) {
+		prt_printf(out, "field ends before start of entries");
+		return;
+	}
+
+	if (!le16_to_cpu(mi->member_bytes)) {
+		prt_printf(out, "member_bytes 0");
+		return;
+	}
+
+	unsigned nr = (vstruct_end(&mi->field) - (void *) &mi->_members[0]) / le16_to_cpu(mi->member_bytes);
+	if (nr != sb->nr_devices)
+		prt_printf(out, "nr_devices mismatch: have %i entries, should be %u", nr, sb->nr_devices);
+
+	/*
+	 * We call to_text() on superblock sections that haven't passed
+	 * validate, so we can't trust sb->nr_devices.
+	 */
+
+	for (unsigned i = 0; i < min(sb->nr_devices, nr); i++)
 		member_to_text(out, members_v2_get(mi, i), gi, sb, i);
 }
 

fs/bcachefs/super.c

···
 #undef x
 
 static void __bch2_print_str(struct bch_fs *c, const char *prefix,
-			     const char *str, bool nonblocking)
+			     const char *str)
 {
 #ifdef __KERNEL__
 	struct stdio_redirect *stdio = bch2_fs_stdio_redirect(c);
···
 		return;
 	}
 #endif
-	bch2_print_string_as_lines(KERN_ERR, str, nonblocking);
+	bch2_print_string_as_lines(KERN_ERR, str);
 }
 
 void bch2_print_str(struct bch_fs *c, const char *prefix, const char *str)
 {
-	__bch2_print_str(c, prefix, str, false);
-}
-
-void bch2_print_str_nonblocking(struct bch_fs *c, const char *prefix, const char *str)
-{
-	__bch2_print_str(c, prefix, str, true);
+	__bch2_print_str(c, prefix, str);
 }
 
 __printf(2, 0)
···
 static void print_mount_opts(struct bch_fs *c)
 {
 	enum bch_opt_id i;
-	struct printbuf p = PRINTBUF;
-	bool first = true;
+	CLASS(printbuf, p)();
+	bch2_log_msg_start(c, &p);
 
 	prt_str(&p, "starting version ");
 	bch2_version_to_text(&p, c->sb.version);
 
+	bool first = true;
 	for (i = 0; i < bch2_opts_nr; i++) {
 		const struct bch_option *opt = &bch2_opt_table[i];
 		u64 v = bch2_opt_get_by_id(&c->opts, i);
···
 	}
 
 	if (c->sb.version_incompat_allowed != c->sb.version) {
-		prt_printf(&p, "\n  allowing incompatible features above ");
+		prt_printf(&p, "\nallowing incompatible features above ");
 		bch2_version_to_text(&p, c->sb.version_incompat_allowed);
 	}
 
 	if (c->opts.verbose) {
-		prt_printf(&p, "\n  features: ");
+		prt_printf(&p, "\nfeatures: ");
 		prt_bitflags(&p, bch2_sb_features, c->sb.features);
 	}
 
-	bch_info(c, "%s", p.buf);
-	printbuf_exit(&p);
+	if (c->sb.multi_device) {
+		prt_printf(&p, "\nwith devices");
+		for_each_online_member(c, ca, BCH_DEV_READ_REF_bch2_online_devs) {
+			prt_char(&p, ' ');
+			prt_str(&p, ca->name);
+		}
+	}
+
+	bch2_print_str(c, KERN_INFO, p.buf);
 }
 
 static bool bch2_fs_may_start(struct bch_fs *c)
···
 		if (ret)
 			goto err_late;
 	}
+
+	/*
+	 * We just changed the superblock UUID, invalidate cache and send a
+	 * uevent to update /dev/disk/by-uuid
+	 */
+	invalidate_bdev(ca->disk_sb.bdev);
+
+	char uuid_str[37];
+	snprintf(uuid_str, sizeof(uuid_str), "UUID=%pUb", &c->sb.uuid);
+
+	char *envp[] = {
+		"CHANGE=uuid",
+		uuid_str,
+		NULL,
+	};
+	kobject_uevent_env(&ca->disk_sb.bdev->bd_device.kobj, KOBJ_CHANGE, envp);
 
 	up_write(&c->state_lock);
 out:

fs/bcachefs/util.c

···
 	return true;
 }
 
-void bch2_print_string_as_lines(const char *prefix, const char *lines,
-				bool nonblocking)
+void bch2_print_string_as_lines(const char *prefix, const char *lines)
 {
 	bool locked = false;
 	const char *p;
···
 		return;
 	}
 
-	if (!nonblocking) {
-		console_lock();
-		locked = true;
-	} else {
-		locked = console_trylock();
-	}
+	locked = console_trylock();
 
 	while (*lines) {
 		p = strchrnul(lines, '\n');

fs/bcachefs/util.h

···
 void bch2_prt_u64_base2_nbits(struct printbuf *, u64, unsigned);
 void bch2_prt_u64_base2(struct printbuf *, u64);
 
-void bch2_print_string_as_lines(const char *, const char *, bool);
+void bch2_print_string_as_lines(const char *, const char *);
 
 typedef DARRAY(unsigned long) bch_stacktrace;
 int bch2_save_backtrace(bch_stacktrace *stack, struct task_struct *, unsigned, gfp_t);

fs/file.c

···
 	if (!(file->f_mode & FMODE_ATOMIC_POS) && !file->f_op->iterate_shared)
 		return false;
 
-	VFS_WARN_ON_ONCE((file_count(file) > 1) &&
-			 !mutex_is_locked(&file->f_pos_lock));
+	/*
+	 * Note that we are not guaranteed to be called after fdget_pos() on
+	 * this file obj, in which case the caller is expected to provide the
+	 * appropriate locking.
+	 */
+
 	return true;
 }
 

fs/namei.c

···
  * @base:	base directory to lookup from
  *
  * Look up a dentry by name in the dcache, returning NULL if it does not
- * currently exist.  The function does not try to create a dentry.
+ * currently exist.  The function does not try to create a dentry and if one
+ * is found it doesn't try to revalidate it.
  *
  * Note that this routine is purely a helper for filesystem usage and should
  * not be called by generic code.  It does no permission checking.
···
 	if (err)
 		return ERR_PTR(err);
 
-	return lookup_dcache(name, base, 0);
+	return d_lookup(base, name);
 }
 EXPORT_SYMBOL(try_lookup_noperm);
 
···
  * Note that this routine is purely a helper for filesystem usage and should
  * not be called by generic code. It does no permission checking.
  *
- * Unlike lookup_noperm, it should be called without the parent
+ * Unlike lookup_noperm(), it should be called without the parent
  * i_rwsem held, and will take the i_rwsem itself if necessary.
+ *
+ * Unlike try_lookup_noperm() it *does* revalidate the dentry if it already
+ * existed.
  */
 struct dentry *lookup_noperm_unlocked(struct qstr *name, struct dentry *base)
 {
 	struct dentry *ret;
+	int err;
 
-	ret = try_lookup_noperm(name, base);
+	err = lookup_noperm_common(name, base);
+	if (err)
+		return ERR_PTR(err);
+
+	ret = lookup_dcache(name, base, 0);
 	if (!ret)
 		ret = lookup_slow(name, base, 0);
 	return ret;

fs/overlayfs/namei.c

···
 bool ovl_lower_positive(struct dentry *dentry)
 {
 	struct ovl_entry *poe = OVL_E(dentry->d_parent);
-	struct qstr *name = &dentry->d_name;
+	const struct qstr *name = &dentry->d_name;
 	const struct cred *old_cred;
 	unsigned int i;
 	bool positive = false;
···
 		struct dentry *this;
 		struct ovl_path *parentpath = &ovl_lowerstack(poe)[i];
 
+		/*
+		 * We need to make a non-const copy of dentry->d_name,
+		 * because lookup_one_positive_unlocked() will hash name
+		 * with parentpath base, which is on another (lower fs).
+		 */
 		this = lookup_one_positive_unlocked(
 				mnt_idmap(parentpath->layer->mnt),
-				name, parentpath->dentry);
+				&QSTR_LEN(name->name, name->len),
+				parentpath->dentry);
 		if (IS_ERR(this)) {
 			switch (PTR_ERR(this)) {
 			case -ENOENT:

fs/overlayfs/overlayfs.h

···
 					  struct dentry *dentry,
 					  umode_t mode)
 {
-	dentry = vfs_mkdir(ovl_upper_mnt_idmap(ofs), dir, dentry, mode);
-	pr_debug("mkdir(%pd2, 0%o) = %i\n", dentry, mode, PTR_ERR_OR_ZERO(dentry));
-	return dentry;
+	struct dentry *ret;
+
+	ret = vfs_mkdir(ovl_upper_mnt_idmap(ofs), dir, dentry, mode);
+	pr_debug("mkdir(%pd2, 0%o) = %i\n", dentry, mode, PTR_ERR_OR_ZERO(ret));
+	return ret;
 }
 
 static inline int ovl_do_mknod(struct ovl_fs *ofs,

fs/pidfs.c

···
 	kinfo.pid = task_pid_vnr(task);
 	kinfo.mask |= PIDFD_INFO_PID;
 
-	if (kinfo.pid == 0 || kinfo.tgid == 0 || (kinfo.ppid == 0 && kinfo.pid != 1))
+	if (kinfo.pid == 0 || kinfo.tgid == 0)
 		return -ESRCH;
 
 copy_out:

fs/smb/client/cached_dir.h

···
 struct cached_dirents {
 	bool is_valid:1;
 	bool is_failed:1;
-	struct dir_context *ctx; /*
-				  * Only used to make sure we only take entries
-				  * from a single context. Never dereferenced.
-				  */
+	struct file *file; /*
+			    * Used to associate the cache with a single
+			    * open file instance.
+			    */
 	struct mutex de_mutex;
 	int pos;		 /* Expected ctx->pos */
 	struct list_head entries;

fs/smb/client/connect.c

···
 		goto out;
 	}
 
-	/* if new SMB3.11 POSIX extensions are supported do not remap / and \ */
-	if (tcon->posix_extensions)
+	/*
+	 * if new SMB3.11 POSIX extensions are supported, do not change anything in the
+	 * path (i.e., do not remap / and \ and do not map any special characters)
+	 */
+	if (tcon->posix_extensions) {
 		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_POSIX_PATHS;
+		cifs_sb->mnt_cifs_flags &= ~(CIFS_MOUNT_MAP_SFM_CHR |
+					     CIFS_MOUNT_MAP_SPECIAL_CHR);
+	}
 
 #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
 	/* tell server which Unix caps we support */

fs/smb/client/file.c

···
 		rc = cifs_get_readable_path(tcon, full_path, &cfile);
 	}
 	if (rc == 0) {
-		if (file->f_flags == cfile->f_flags) {
+		unsigned int oflags = file->f_flags & ~(O_CREAT|O_EXCL|O_TRUNC);
+		unsigned int cflags = cfile->f_flags & ~(O_CREAT|O_EXCL|O_TRUNC);
+
+		if (cifs_convert_flags(oflags, 0) == cifs_convert_flags(cflags, 0) &&
+		    (oflags & (O_SYNC|O_DIRECT)) == (cflags & (O_SYNC|O_DIRECT))) {
 			file->private_data = cfile;
 			spin_lock(&CIFS_I(inode)->deferred_lock);
 			cifs_del_deferred_close(cfile);
 			spin_unlock(&CIFS_I(inode)->deferred_lock);
 			goto use_cache;
-		} else {
-			_cifsFileInfo_put(cfile, true, false);
 		}
+		_cifsFileInfo_put(cfile, true, false);
 	} else {
 		/* hard link on the defeered close file */
 		rc = cifs_get_hardlink_path(tcon, inode, file);

fs/smb/client/readdir.c

···
 }
 
 static void update_cached_dirents_count(struct cached_dirents *cde,
-					struct dir_context *ctx)
+					struct file *file)
 {
-	if (cde->ctx != ctx)
+	if (cde->file != file)
 		return;
 	if (cde->is_valid || cde->is_failed)
 		return;
···
 }
 
 static void finished_cached_dirents_count(struct cached_dirents *cde,
-					struct dir_context *ctx)
+					struct dir_context *ctx, struct file *file)
 {
-	if (cde->ctx != ctx)
+	if (cde->file != file)
 		return;
 	if (cde->is_valid || cde->is_failed)
 		return;
···
 static void add_cached_dirent(struct cached_dirents *cde,
 			      struct dir_context *ctx,
 			      const char *name, int namelen,
-			      struct cifs_fattr *fattr)
+			      struct cifs_fattr *fattr,
+				  struct file *file)
 {
 	struct cached_dirent *de;
 
-	if (cde->ctx != ctx)
+	if (cde->file != file)
 		return;
 	if (cde->is_valid || cde->is_failed)
 		return;
···
 static bool cifs_dir_emit(struct dir_context *ctx,
 			  const char *name, int namelen,
 			  struct cifs_fattr *fattr,
-			  struct cached_fid *cfid)
+			  struct cached_fid *cfid,
+			  struct file *file)
 {
 	bool rc;
 	ino_t ino = cifs_uniqueid_to_ino_t(fattr->cf_uniqueid);
···
 	if (cfid) {
 		mutex_lock(&cfid->dirents.de_mutex);
 		add_cached_dirent(&cfid->dirents, ctx, name, namelen,
-				  fattr);
+				  fattr, file);
 		mutex_unlock(&cfid->dirents.de_mutex);
 	}
 
···
 	cifs_prime_dcache(file_dentry(file), &name, &fattr);
 
 	return !cifs_dir_emit(ctx, name.name, name.len,
-			      &fattr, cfid);
+			      &fattr, cfid, file);
 }
 
 
···
 	 * we need to initialize scanning and storing the
 	 * directory content.
 	 */
-	if (ctx->pos == 0 && cfid->dirents.ctx == NULL) {
-		cfid->dirents.ctx = ctx;
+	if (ctx->pos == 0 && cfid->dirents.file == NULL) {
+		cfid->dirents.file = file;
 		cfid->dirents.pos = 2;
 	}
 	/*
···
 	} else {
 		if (cfid) {
 			mutex_lock(&cfid->dirents.de_mutex);
-			finished_cached_dirents_count(&cfid->dirents, ctx);
+			finished_cached_dirents_count(&cfid->dirents, ctx, file);
 			mutex_unlock(&cfid->dirents.de_mutex);
 		}
 		cifs_dbg(FYI, "Could not find entry\n");
···
 		ctx->pos++;
 		if (cfid) {
 			mutex_lock(&cfid->dirents.de_mutex);
-			update_cached_dirents_count(&cfid->dirents, ctx);
+			update_cached_dirents_count(&cfid->dirents, file);
 			mutex_unlock(&cfid->dirents.de_mutex);
 		}
 

fs/smb/server/connection.c

···
 	kvfree(conn->request_buf);
 	kfree(conn->preauth_info);
 	if (atomic_dec_and_test(&conn->refcnt)) {
-		ksmbd_free_transport(conn->transport);
+		conn->transport->ops->free_transport(conn->transport);
 		kfree(conn);
 	}
 }

fs/smb/server/connection.h

···
 			  void *buf, unsigned int len,
 			  struct smb2_buffer_desc_v1 *desc,
 			  unsigned int desc_len);
+	void (*free_transport)(struct ksmbd_transport *kt);
 };
 
 struct ksmbd_transport {

fs/smb/server/smb2pdu.c

···
 	out_len = work->response_sz -
 		(le16_to_cpu(rsp->SecurityBufferOffset) + 4);
 
-	/* Check previous session */
-	prev_sess_id = le64_to_cpu(req->PreviousSessionId);
-	if (prev_sess_id && prev_sess_id != sess->id)
-		destroy_previous_session(conn, sess->user, prev_sess_id);
-
 	retval = ksmbd_krb5_authenticate(sess, in_blob, in_len,
 					 out_blob, &out_len);
 	if (retval) {
 		ksmbd_debug(SMB, "krb5 authentication failed\n");
 		return -EINVAL;
 	}
+
+	/* Check previous session */
+	prev_sess_id = le64_to_cpu(req->PreviousSessionId);
+	if (prev_sess_id && prev_sess_id != sess->id)
+		destroy_previous_session(conn, sess->user, prev_sess_id);
+
 	rsp->SecurityBufferLength = cpu_to_le16(out_len);
 
 	if ((conn->sign || server_conf.enforced_signing) ||
···
 	sinfo = (struct smb2_file_standard_info *)rsp->Buffer;
 	delete_pending = ksmbd_inode_pending_delete(fp);
 
-	sinfo->AllocationSize = cpu_to_le64(stat.blocks << 9);
-	sinfo->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size);
+	if (ksmbd_stream_fd(fp) == false) {
+		sinfo->AllocationSize = cpu_to_le64(stat.blocks << 9);
+		sinfo->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size);
+	} else {
+		sinfo->AllocationSize = cpu_to_le64(fp->stream.size);
+		sinfo->EndOfFile = cpu_to_le64(fp->stream.size);
+	}
 	sinfo->NumberOfLinks = cpu_to_le32(get_nlink(&stat) - delete_pending);
 	sinfo->DeletePending = delete_pending;
 	sinfo->Directory = S_ISDIR(stat.mode) ? 1 : 0;
···
 	file_info->ChangeTime = cpu_to_le64(time);
 	file_info->Attributes = fp->f_ci->m_fattr;
 	file_info->Pad1 = 0;
-	file_info->AllocationSize =
-		cpu_to_le64(stat.blocks << 9);
-	file_info->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size);
+	if (ksmbd_stream_fd(fp) == false) {
+		file_info->AllocationSize =
+			cpu_to_le64(stat.blocks << 9);
+		file_info->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size);
+	} else {
+		file_info->AllocationSize = cpu_to_le64(fp->stream.size);
+		file_info->EndOfFile = cpu_to_le64(fp->stream.size);
+	}
 	file_info->NumberOfLinks =
 			cpu_to_le32(get_nlink(&stat) - delete_pending);
 	file_info->DeletePending = delete_pending;
···
 	file_info->IndexNumber = cpu_to_le64(stat.ino);
 	file_info->EASize = 0;
 	file_info->AccessFlags = fp->daccess;
-	file_info->CurrentByteOffset = cpu_to_le64(fp->filp->f_pos);
+	if (ksmbd_stream_fd(fp) == false)
+		file_info->CurrentByteOffset = cpu_to_le64(fp->filp->f_pos);
+	else
+		file_info->CurrentByteOffset = cpu_to_le64(fp->stream.pos);
 	file_info->Mode = fp->coption;
 	file_info->AlignmentRequirement = 0;
 	conv_len = smbConvertToUTF16((__le16 *)file_info->FileName, filename,
···
 	time = ksmbd_UnixTimeToNT(stat.ctime);
 	file_info->ChangeTime = cpu_to_le64(time);
 	file_info->Attributes = fp->f_ci->m_fattr;
-	file_info->AllocationSize = cpu_to_le64(stat.blocks << 9);
-	file_info->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size);
+	if (ksmbd_stream_fd(fp) == false) {
+		file_info->AllocationSize = cpu_to_le64(stat.blocks << 9);
+		file_info->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size);
+	} else {
+		file_info->AllocationSize = cpu_to_le64(fp->stream.size);
+		file_info->EndOfFile = cpu_to_le64(fp->stream.size);
+	}
 	file_info->Reserved = cpu_to_le32(0);
 	rsp->OutputBufferLength =
 		cpu_to_le32(sizeof(struct smb2_file_ntwrk_info));
···
 	struct smb2_file_pos_info *file_info;
 
 	file_info = (struct smb2_file_pos_info *)rsp->Buffer;
-	file_info->CurrentByteOffset = cpu_to_le64(fp->filp->f_pos);
+	if (ksmbd_stream_fd(fp) == false)
+		file_info->CurrentByteOffset = cpu_to_le64(fp->filp->f_pos);
+	else
+		file_info->CurrentByteOffset = cpu_to_le64(fp->stream.pos);
+
 	rsp->OutputBufferLength =
 		cpu_to_le32(sizeof(struct smb2_file_pos_info));
 }
···
 	file_info->ChangeTime = cpu_to_le64(time);
 	file_info->DosAttributes = fp->f_ci->m_fattr;
 	file_info->Inode = cpu_to_le64(stat.ino);
-	file_info->EndOfFile = cpu_to_le64(stat.size);
-	file_info->AllocationSize = cpu_to_le64(stat.blocks << 9);
+	if (ksmbd_stream_fd(fp) == false) {
+		file_info->EndOfFile = cpu_to_le64(stat.size);
+		file_info->AllocationSize = cpu_to_le64(stat.blocks << 9);
+	} else {
+		file_info->EndOfFile = cpu_to_le64(fp->stream.size);
+		file_info->AllocationSize = cpu_to_le64(fp->stream.size);
+	}
 	file_info->HardLinks = cpu_to_le32(stat.nlink);
 	file_info->Mode = cpu_to_le32(stat.mode & 0777);
 	switch (stat.mode & S_IFMT) {
···
 	if (!(fp->daccess & FILE_WRITE_DATA_LE))
 		return -EACCES;
 
+	if (ksmbd_stream_fd(fp) == true)
+		return 0;
+
 	rc = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS,
 			 AT_STATX_SYNC_AS_STAT);
 	if (rc)
···
 	 * truncate of some filesystem like FAT32 fill zero data in
 	 * truncated range.
 	 */
-	if (inode->i_sb->s_magic != MSDOS_SUPER_MAGIC) {
+	if (inode->i_sb->s_magic != MSDOS_SUPER_MAGIC &&
+	    ksmbd_stream_fd(fp) == false) {
 		ksmbd_debug(SMB, "truncated to newsize %lld\n", newsize);
 		rc = ksmbd_vfs_truncate(work, fp, newsize);
 		if (rc) {
···
 		return -EINVAL;
 	}
 
-	fp->filp->f_pos = current_byte_offset;
+	if (ksmbd_stream_fd(fp) == false)
+		fp->filp->f_pos = current_byte_offset;
+	else {
+		if (current_byte_offset > XATTR_SIZE_MAX)
+			current_byte_offset = XATTR_SIZE_MAX;
+		fp->stream.pos = current_byte_offset;
+	}
 	return 0;
 }
 

fs/smb/server/transport_rdma.c

···
 };
 
 #define KSMBD_TRANS(t) ((struct ksmbd_transport *)&((t)->transport))
-
+#define SMBD_TRANS(t)	((struct smb_direct_transport *)container_of(t, \
+				struct smb_direct_transport, transport))
 enum {
 	SMB_DIRECT_MSG_NEGOTIATE_REQ = 0,
 	SMB_DIRECT_MSG_DATA_TRANSFER
···
 	return NULL;
 }
 
+static void smb_direct_free_transport(struct ksmbd_transport *kt)
+{
+	kfree(SMBD_TRANS(kt));
+}
+
 static void free_transport(struct smb_direct_transport *t)
 {
 	struct smb_direct_recvmsg *recvmsg;
···
 
 	smb_direct_destroy_pools(t);
 	ksmbd_conn_free(KSMBD_TRANS(t)->conn);
-	kfree(t);
 }
 
 static struct smb_direct_sendmsg
···
 	.read		= smb_direct_read,
 	.rdma_read	= smb_direct_rdma_read,
 	.rdma_write	= smb_direct_rdma_write,
+	.free_transport = smb_direct_free_transport,
 };

fs/smb/server/transport_tcp.c

···
 	return t;
 }
 
-void ksmbd_free_transport(struct ksmbd_transport *kt)
+static void ksmbd_tcp_free_transport(struct ksmbd_transport *kt)
 {
 	struct tcp_transport *t = TCP_TRANS(kt);
 
···
 	.read		= ksmbd_tcp_read,
 	.writev		= ksmbd_tcp_writev,
 	.disconnect	= ksmbd_tcp_disconnect,
+	.free_transport = ksmbd_tcp_free_transport,
 };

fs/smb/server/vfs.c

···
 
 	if (v_len - *pos < count)
 		count = v_len - *pos;
+	fp->stream.pos = v_len;
 
 	memcpy(buf, &stream_buf[*pos], count);
 
···
 				 true);
 	if (err < 0)
 		goto out;
-
-	fp->filp->f_pos = *pos;
+	else
+		fp->stream.pos = size;
 	err = 0;
 out:
 	kvfree(stream_buf);

fs/smb/server/vfs_cache.h

···
 struct stream {
 	char *name;
 	ssize_t size;
+	loff_t pos;
 };
 
 struct ksmbd_inode {

fs/super.c

···
 		spin_unlock(&sb_lock);
 
 		locked = super_lock_shared(sb);
-		if (locked)
+		if (locked) {
 			f(sb, arg);
+			super_unlock_shared(sb);
+		}
 
 		spin_lock(&sb_lock);
 		if (p)

fs/xattr.c

···
 		buffer += err;
 	}
 	remaining_size -= err;
+	err = 0;
 
 	read_lock(&xattrs->lock);
 	for (rbp = rb_first(&xattrs->rb_root); rbp; rbp = rb_next(rbp)) {

include/linux/atmdev.h

···
 	ATM_SKB(skb)->atm_options = vcc->atm_options;
 }
 
+static inline void atm_return_tx(struct atm_vcc *vcc, struct sk_buff *skb)
+{
+	WARN_ON_ONCE(refcount_sub_and_test(ATM_SKB(skb)->acct_truesize,
+					   &sk_atm(vcc)->sk_wmem_alloc));
+}
+
 static inline void atm_force_charge(struct atm_vcc *vcc,int truesize)
 {
 	atomic_add(truesize, &sk_atm(vcc)->sk_rmem_alloc);

include/linux/bio.h

···
 
 	fi->folio = page_folio(bvec->bv_page);
 	fi->offset = bvec->bv_offset +
-			PAGE_SIZE * (bvec->bv_page - &fi->folio->page);
+			PAGE_SIZE * folio_page_idx(fi->folio, bvec->bv_page);
 	fi->_seg_count = bvec->bv_len;
 	fi->length = min(folio_size(fi->folio) - fi->offset, fi->_seg_count);
 	fi->_next = folio_next(fi->folio);

include/linux/bvec.h

···
  * @offset:	offset into the folio
  */
 static inline void bvec_set_folio(struct bio_vec *bv, struct folio *folio,
-		unsigned int len, unsigned int offset)
+		size_t len, size_t offset)
 {
-	bvec_set_page(bv, &folio->page, len, offset);
+	unsigned long nr = offset / PAGE_SIZE;
+
+	WARN_ON_ONCE(len > UINT_MAX);
+	bvec_set_page(bv, folio_page(folio, nr), len, offset % PAGE_SIZE);
 }
 
 /**

include/linux/cpu.h

···
 extern void cpu_maps_update_done(void);
 int bringup_hibernate_cpu(unsigned int sleep_cpu);
 void bringup_nonboot_cpus(unsigned int max_cpus);
+int arch_cpu_rescan_dead_smt_siblings(void);
 
 #else	/* CONFIG_SMP */
 #define cpuhp_tasks_frozen	0
···
 }
 
 static inline int add_cpu(unsigned int cpu) { return 0;}
+
+static inline int arch_cpu_rescan_dead_smt_siblings(void) { return 0; }
 
 #endif /* CONFIG_SMP */
 extern const struct bus_type cpu_subsys;

include/linux/execmem.h

···
 	EXECMEM_ROX_CACHE	= (1 << 1),
 };
 
-#if defined(CONFIG_ARCH_HAS_EXECMEM_ROX) && defined(CONFIG_EXECMEM)
+#ifdef CONFIG_ARCH_HAS_EXECMEM_ROX
 /**
  * execmem_fill_trapping_insns - set memory to contain instructions that
  *				 will trap
···
  * Return: 0 on success or negative error code on failure.
  */
 int execmem_restore_rox(void *ptr, size_t size);
-
-/*
- * Called from mark_readonly(), where the system transitions to ROX.
- */
-void execmem_cache_make_ro(void);
 #else
 static inline int execmem_make_temp_rw(void *ptr, size_t size) { return 0; }
 static inline int execmem_restore_rox(void *ptr, size_t size) { return 0; }
-static inline void execmem_cache_make_ro(void) { }
 #endif
 
 /**

include/linux/fs.h

···
 	{ IOCB_WAITQ,		"WAITQ" }, \
 	{ IOCB_NOIO,		"NOIO" }, \
 	{ IOCB_ALLOC_CACHE,	"ALLOC_CACHE" }, \
-	{ IOCB_DIO_CALLER_COMP,	"CALLER_COMP" }
+	{ IOCB_DIO_CALLER_COMP,	"CALLER_COMP" }, \
+	{ IOCB_AIO_RW,		"AIO_RW" }, \
+	{ IOCB_HAS_METADATA,	"AIO_HAS_METADATA" }
 
 struct kiocb {
 	struct file		*ki_filp;
···
 	return true;
 }
 
+int compat_vma_mmap_prepare(struct file *file, struct vm_area_struct *vma);
+
 static inline int call_mmap(struct file *file, struct vm_area_struct *vma)
 {
-	if (WARN_ON_ONCE(file->f_op->mmap_prepare))
-		return -EINVAL;
+	if (file->f_op->mmap_prepare)
+		return compat_vma_mmap_prepare(file, vma);
 
 	return file->f_op->mmap(file, vma);
 }

include/linux/ieee80211.h

···
 			u8 sa[ETH_ALEN];
 			__le32 timestamp;
 			u8 change_seq;
-			u8 variable[0];
+			u8 variable[];
 		} __packed s1g_beacon;
 	} u;
 } __packed __aligned(2);
···
 					u8 action_code;
 					u8 dialog_token;
 					__le16 capability;
-					u8 variable[0];
+					u8 variable[];
 				} __packed tdls_discover_resp;
 				struct {
 					u8 action_code;
···
 		struct {
 			u8 dialog_token;
 			__le16 capability;
-			u8 variable[0];
+			u8 variable[];
 		} __packed setup_req;
 		struct {
 			__le16 status_code;
 			u8 dialog_token;
 			__le16 capability;
-			u8 variable[0];
+			u8 variable[];
 		} __packed setup_resp;
 		struct {
 			__le16 status_code;
 			u8 dialog_token;
-			u8 variable[0];
+			u8 variable[];
 		} __packed setup_cfm;
 		struct {
 			__le16 reason_code;
-			u8 variable[0];
+			u8 variable[];
 		} __packed teardown;
 		struct {
 			u8 dialog_token;
-			u8 variable[0];
+			u8 variable[];
 		} __packed discover_req;
 		struct {
 			u8 target_channel;
 			u8 oper_class;
-			u8 variable[0];
+			u8 variable[];
 		} __packed chan_switch_req;
 		struct {
 			__le16 status_code;
-			u8 variable[0];
+			u8 variable[];
 		} __packed chan_switch_resp;
 	} u;
 } __packed;

include/linux/libata.h

···
 int ata_acpi_gtm(struct ata_port *ap, struct ata_acpi_gtm *stm);
 unsigned int ata_acpi_gtm_xfermask(struct ata_device *dev,
 				   const struct ata_acpi_gtm *gtm);
-int ata_acpi_cbl_80wire(struct ata_port *ap, const struct ata_acpi_gtm *gtm);
+int ata_acpi_cbl_pata_type(struct ata_port *ap);
 #else
 static inline const struct ata_acpi_gtm *ata_acpi_init_gtm(struct ata_port *ap)
 {
···
 	return 0;
 }
 
-static inline int ata_acpi_cbl_80wire(struct ata_port *ap,
-				      const struct ata_acpi_gtm *gtm)
+static inline int ata_acpi_cbl_pata_type(struct ata_port *ap)
 {
-	return 0;
+	return ATA_CBL_PATA40;
 }
 #endif
 

include/linux/module.h

···
 	atomic_t refcnt;
 #endif
 
-#ifdef CONFIG_MITIGATION_ITS
-	int its_num_pages;
-	void **its_page_array;
-#endif
-
 #ifdef CONFIG_CONSTRUCTORS
 	/* Constructor functions. */
 	ctor_fn_t *ctors;

include/linux/scatterlist.h

···
  * @sg:		The current sg entry
  *
  * Description:
- *   Usually the next entry will be @sg@ + 1, but if this sg element is part
+ *   Usually the next entry will be @sg + 1, but if this sg element is part
  *   of a chained scatterlist, it could jump to the start of a new
  *   scatterlist array.
  *
···
  * @sgl:	Second scatterlist
  *
  * Description:
- *   Links @prv@ and @sgl@ together, to form a longer scatterlist.
+ *   Links @prv and @sgl together, to form a longer scatterlist.
  *
  **/
 static inline void sg_chain(struct scatterlist *prv, unsigned int prv_nents,

include/uapi/linux/bits.h

···
 #ifndef _UAPI_LINUX_BITS_H
 #define _UAPI_LINUX_BITS_H
 
-#define __GENMASK(h, l) (((~_UL(0)) << (l)) & (~_UL(0) >> (BITS_PER_LONG - 1 - (h))))
+#define __GENMASK(h, l) (((~_UL(0)) << (l)) & (~_UL(0) >> (__BITS_PER_LONG - 1 - (h))))
 
-#define __GENMASK_ULL(h, l) (((~_ULL(0)) << (l)) & (~_ULL(0) >> (BITS_PER_LONG_LONG - 1 - (h))))
+#define __GENMASK_ULL(h, l) (((~_ULL(0)) << (l)) & (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h))))
 
 #define __GENMASK_U128(h, l) \
 	((_BIT128((h)) << 1) - (_BIT128(l)))

include/uapi/linux/ethtool_netlink.h

···
 	ETHTOOL_A_STATS_PHY_MAX = (__ETHTOOL_A_STATS_PHY_CNT - 1)
 };
 
-/* generic netlink info */
-#define ETHTOOL_GENL_NAME "ethtool"
-#define ETHTOOL_GENL_VERSION 1
-
 #define ETHTOOL_MCGRP_MONITOR_NAME "monitor"
 
 #endif /* _UAPI_LINUX_ETHTOOL_NETLINK_H_ */

include/uapi/linux/ethtool_netlink_generated.h

···
 #ifndef _UAPI_LINUX_ETHTOOL_NETLINK_GENERATED_H
 #define _UAPI_LINUX_ETHTOOL_NETLINK_GENERATED_H
 
-#define ETHTOOL_FAMILY_NAME	"ethtool"
-#define ETHTOOL_FAMILY_VERSION	1
+#define ETHTOOL_GENL_NAME	"ethtool"
+#define ETHTOOL_GENL_VERSION	1
 
 enum {
 	ETHTOOL_UDP_TUNNEL_TYPE_VXLAN,

init/initramfs.c

···
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/init.h>
 #include <linux/async.h>
+#include <linux/export.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
 #include <linux/types.h>

init/main.c

···
 #define DEBUG		/* Enable initcall_debug */
 
 #include <linux/types.h>
+#include <linux/export.h>
 #include <linux/extable.h>
 #include <linux/module.h>
 #include <linux/proc_fs.h>

io_uring/fdinfo.c

···
 
 	if (ctx->flags & IORING_SETUP_SQPOLL) {
 		struct io_sq_data *sq = ctx->sq_data;
+		struct task_struct *tsk;
 
+		rcu_read_lock();
+		tsk = rcu_dereference(sq->thread);
 		/*
 		 * sq->thread might be NULL if we raced with the sqpoll
 		 * thread termination.
 		 */
-		if (sq->thread) {
+		if (tsk) {
+			get_task_struct(tsk);
+			rcu_read_unlock();
+			getrusage(tsk, RUSAGE_SELF, &sq_usage);
+			put_task_struct(tsk);
 			sq_pid = sq->task_pid;
 			sq_cpu = sq->sq_cpu;
-			getrusage(sq->thread, RUSAGE_SELF, &sq_usage);
 			sq_total_time = (sq_usage.ru_stime.tv_sec * 1000000
 					 + sq_usage.ru_stime.tv_usec);
 			sq_work_time = sq->work_time;
+		} else {
+			rcu_read_unlock();
 		}
 	}
 

io_uring/io_uring.c

···
 		}
 	}
 	mutex_unlock(&ctx->uring_lock);
+
+	if (ctx->flags & IORING_SETUP_DEFER_TASKRUN)
+		io_move_task_work_from_local(ctx);
 }
 
 static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned int min_events)
···
 			struct task_struct *tsk;
 
 			io_sq_thread_park(sqd);
-			tsk = sqd->thread;
+			tsk = sqpoll_task_locked(sqd);
 			if (tsk && tsk->io_uring && tsk->io_uring->io_wq)
 				io_wq_cancel_cb(tsk->io_uring->io_wq,
 						io_cancel_ctx_cb, ctx, true);
···
 	s64 inflight;
 	DEFINE_WAIT(wait);
 
-	WARN_ON_ONCE(sqd && sqd->thread != current);
+	WARN_ON_ONCE(sqd && sqpoll_task_locked(sqd) != current);
 
 	if (!current->io_uring)
 		return;

io_uring/kbuf.c

···
 		/* truncate end piece, if needed, for non partial buffers */
 		if (len > arg->max_len) {
 			len = arg->max_len;
-			if (!(bl->flags & IOBL_INC))
+			if (!(bl->flags & IOBL_INC)) {
+				if (iov != arg->iovs)
+					break;
 				buf->len = len;
+			}
 		}
 
 		iov->iov_base = u64_to_user_ptr(buf->addr);

io_uring/register.c

···
 	if (ctx->flags & IORING_SETUP_SQPOLL) {
 		sqd = ctx->sq_data;
 		if (sqd) {
+			struct task_struct *tsk;
+
 			/*
 			 * Observe the correct sqd->lock -> ctx->uring_lock
 			 * ordering. Fine to drop uring_lock here, we hold
···
 			mutex_unlock(&ctx->uring_lock);
 			mutex_lock(&sqd->lock);
 			mutex_lock(&ctx->uring_lock);
-			if (sqd->thread)
-				tctx = sqd->thread->io_uring;
+			tsk = sqpoll_task_locked(sqd);
+			if (tsk)
+				tctx = tsk->io_uring;
 		}
 	} else {
 		tctx = current->io_uring;

io_uring/sqpoll.c

···
 void io_sq_thread_unpark(struct io_sq_data *sqd)
 	__releases(&sqd->lock)
 {
-	WARN_ON_ONCE(sqd->thread == current);
+	WARN_ON_ONCE(sqpoll_task_locked(sqd) == current);
 
 	/*
 	 * Do the dance but not conditional clear_bit() because it'd race with
···
 void io_sq_thread_park(struct io_sq_data *sqd)
 	__acquires(&sqd->lock)
 {
-	WARN_ON_ONCE(data_race(sqd->thread) == current);
+	struct task_struct *tsk;
 
 	atomic_inc(&sqd->park_pending);
 	set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
 	mutex_lock(&sqd->lock);
-	if (sqd->thread)
-		wake_up_process(sqd->thread);
+
+	tsk = sqpoll_task_locked(sqd);
+	if (tsk) {
+		WARN_ON_ONCE(tsk == current);
+		wake_up_process(tsk);
+	}
 }
 
 void io_sq_thread_stop(struct io_sq_data *sqd)
 {
-	WARN_ON_ONCE(sqd->thread == current);
+	struct task_struct *tsk;
+
 	WARN_ON_ONCE(test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state));
 
 	set_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
 	mutex_lock(&sqd->lock);
-	if (sqd->thread)
-		wake_up_process(sqd->thread);
+	tsk = sqpoll_task_locked(sqd);
+	if (tsk) {
+		WARN_ON_ONCE(tsk == current);
+		wake_up_process(tsk);
+	}
 	mutex_unlock(&sqd->lock);
 	wait_for_completion(&sqd->exited);
 }
···
 	/* offload context creation failed, just exit */
 	if (!current->io_uring) {
 		mutex_lock(&sqd->lock);
-		sqd->thread = NULL;
+		rcu_assign_pointer(sqd->thread, NULL);
+		put_task_struct(current);
 		mutex_unlock(&sqd->lock);
 		goto err_out;
 	}
···
 		io_sq_tw(&retry_list, UINT_MAX);
 
 	io_uring_cancel_generic(true, sqd);
-	sqd->thread = NULL;
+	rcu_assign_pointer(sqd->thread, NULL);
+	put_task_struct(current);
 	list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
 		atomic_or(IORING_SQ_NEED_WAKEUP, &ctx->rings->sq_flags);
 	io_run_task_work();
···
 			goto err_sqpoll;
 		}
 
-		sqd->thread = tsk;
+		mutex_lock(&sqd->lock);
+		rcu_assign_pointer(sqd->thread, tsk);
+		mutex_unlock(&sqd->lock);
+
 		task_to_put = get_task_struct(tsk);
 		ret = io_uring_alloc_task_context(tsk, ctx);
 		wake_up_new_task(tsk);
···
 		ret = -EINVAL;
 		goto err;
 	}
-
-	if (task_to_put)
-		put_task_struct(task_to_put);
 	return 0;
 err_sqpoll:
 	complete(&ctx->sq_data->exited);
···
 	int ret = -EINVAL;
 
 	if (sqd) {
+		struct task_struct *tsk;
+
 		io_sq_thread_park(sqd);
 		/* Don't set affinity for a dying thread */
-		if (sqd->thread)
-			ret = io_wq_cpu_affinity(sqd->thread->io_uring, mask);
+		tsk = sqpoll_task_locked(sqd);
+		if (tsk)
+			ret = io_wq_cpu_affinity(tsk->io_uring, mask);
 		io_sq_thread_unpark(sqd);
 	}
 

io_uring/sqpoll.h

···
 	/* ctx's that are using this sqd */
 	struct list_head	ctx_list;
 
-	struct task_struct	*thread;
+	struct task_struct __rcu *thread;
 	struct wait_queue_head	wait;
 
 	unsigned		sq_thread_idle;
···
 void io_put_sq_data(struct io_sq_data *sqd);
 void io_sqpoll_wait_sq(struct io_ring_ctx *ctx);
 int io_sqpoll_wq_cpu_affinity(struct io_ring_ctx *ctx, cpumask_var_t mask);
+
+static inline struct task_struct *sqpoll_task_locked(struct io_sq_data *sqd)
+{
+	return rcu_dereference_protected(sqd->thread,
+					 lockdep_is_held(&sqd->lock));
+}

kernel/cgroup/legacy_freezer.c

···
 		if (!(freezer->state & CGROUP_FREEZING)) {
 			__thaw_task(task);
 		} else {
-			freeze_task(task);
-
 			/* clear FROZEN and propagate upwards */
 			while (freezer && (freezer->state & CGROUP_FROZEN)) {
 				freezer->state &= ~CGROUP_FROZEN;
 				freezer = parent_freezer(freezer);
 			}
+			freeze_task(task);
 		}
 	}
 

kernel/sched/core.c

···
 		init_cfs_bandwidth(&root_task_group.cfs_bandwidth, NULL);
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 #ifdef CONFIG_EXT_GROUP_SCHED
-		root_task_group.scx_weight = CGROUP_WEIGHT_DFL;
+		scx_tg_init(&root_task_group);
 #endif /* CONFIG_EXT_GROUP_SCHED */
 #ifdef CONFIG_RT_GROUP_SCHED
 		root_task_group.rt_se = (struct sched_rt_entity **)ptr;
···
 	if (!alloc_rt_sched_group(tg, parent))
 		goto err;
 
-	scx_group_set_weight(tg, CGROUP_WEIGHT_DFL);
+	scx_tg_init(tg);
 	alloc_uclamp_sched_group(tg, parent);
 
 	return tg;

kernel/sched/ext.c

···
 DEFINE_STATIC_PERCPU_RWSEM(scx_cgroup_rwsem);
 static bool scx_cgroup_enabled;
 
+void scx_tg_init(struct task_group *tg)
+{
+	tg->scx_weight = CGROUP_WEIGHT_DFL;
+}
+
 int scx_tg_online(struct task_group *tg)
 {
 	struct scx_sched *sch = scx_root;
···
 
 	percpu_down_read(&scx_cgroup_rwsem);
 
-	if (scx_cgroup_enabled && tg->scx_weight != weight) {
-		if (SCX_HAS_OP(sch, cgroup_set_weight))
-			SCX_CALL_OP(sch, SCX_KF_UNLOCKED, cgroup_set_weight, NULL,
-				    tg_cgrp(tg), weight);
-		tg->scx_weight = weight;
-	}
+	if (scx_cgroup_enabled && SCX_HAS_OP(sch, cgroup_set_weight) &&
+	    tg->scx_weight != weight)
+		SCX_CALL_OP(sch, SCX_KF_UNLOCKED, cgroup_set_weight, NULL,
+			    tg_cgrp(tg), weight);
+
+	tg->scx_weight = weight;
 
 	percpu_up_read(&scx_cgroup_rwsem);
 }

kernel/sched/ext.h

···
 
 #ifdef CONFIG_CGROUP_SCHED
 #ifdef CONFIG_EXT_GROUP_SCHED
+void scx_tg_init(struct task_group *tg);
 int scx_tg_online(struct task_group *tg);
 void scx_tg_offline(struct task_group *tg);
 int scx_cgroup_can_attach(struct cgroup_taskset *tset);
···
 void scx_group_set_weight(struct task_group *tg, unsigned long cgrp_weight);
 void scx_group_set_idle(struct task_group *tg, bool idle);
 #else	/* CONFIG_EXT_GROUP_SCHED */
+static inline void scx_tg_init(struct task_group *tg) {}
 static inline int scx_tg_online(struct task_group *tg) { return 0; }
 static inline void scx_tg_offline(struct task_group *tg) {}
 static inline int scx_cgroup_can_attach(struct cgroup_taskset *tset) { return 0; }

kernel/time/posix-cpu-timers.c

···
 	lockdep_assert_irqs_disabled();
 
 	/*
+	 * Ensure that release_task(tsk) can't happen while
+	 * handle_posix_cpu_timers() is running. Otherwise, a concurrent
+	 * posix_cpu_timer_del() may fail to lock_task_sighand(tsk) and
+	 * miss timer->it.cpu.firing != 0.
+	 */
+	if (tsk->exit_state)
+		return;
+
+	/*
 	 * If the actual expiry is deferred to task work context and the
 	 * work is already scheduled there is no point to do anything here.
 	 */

kernel/trace/trace_events_filter.c

···
 	INIT_LIST_HEAD(&head->list);
 
 	item = kmalloc(sizeof(*item), GFP_KERNEL);
-	if (!item) {
-		kfree(head);
+	if (!item)
 		goto free_now;
-	}
 
 	item->filter = filter;
 	list_add_tail(&item->list, &head->list);

kernel/trace/trace_functions_graph.c

···
 	return 0;
 }
 
+static struct tracer graph_trace;
+
 static int ftrace_graph_trace_args(struct trace_array *tr, int set)
 {
 	trace_func_graph_ent_t entry;
+
+	/* Do nothing if the current tracer is not this tracer */
+	if (tr->current_trace != &graph_trace)
+		return 0;
 
 	if (set)
 		entry = trace_graph_entry_args;

kernel/workqueue.c

···
 		restrict_unbound_cpumask("workqueue.unbound_cpus", &wq_cmdline_cpumask);
 
 	cpumask_copy(wq_requested_unbound_cpumask, wq_unbound_cpumask);
-
+	cpumask_andnot(wq_isolated_cpumask, cpu_possible_mask,
+						housekeeping_cpumask(HK_TYPE_DOMAIN));
 	pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC);
 
 	unbound_wq_update_pwq_attrs_buf = alloc_workqueue_attrs();

lib/Kconfig

···
 
 config PLDMFW
 	bool
+	select CRC32
 	default n
 
 config ASN1_ENCODER

lib/crypto/Makefile

···
 libcurve25519-generic-y				:= curve25519-fiat32.o
 libcurve25519-generic-$(CONFIG_ARCH_SUPPORTS_INT128)	:= curve25519-hacl64.o
 libcurve25519-generic-y				+= curve25519-generic.o
+# clang versions prior to 18 may blow out the stack with KASAN
+ifeq ($(call clang-min-version, 180000),)
+KASAN_SANITIZE_curve25519-hacl64.o := n
+endif
 
 obj-$(CONFIG_CRYPTO_LIB_CURVE25519)		+= libcurve25519.o
 libcurve25519-y					+= curve25519.o

lib/crypto/aescfb.c

···
  */
 
 static struct {
-	u8	ptext[64];
-	u8	ctext[64];
+	u8	ptext[64] __nonstring;
+	u8	ctext[64] __nonstring;
 
-	u8	key[AES_MAX_KEY_SIZE];
-	u8	iv[AES_BLOCK_SIZE];
+	u8	key[AES_MAX_KEY_SIZE] __nonstring;
+	u8	iv[AES_BLOCK_SIZE] __nonstring;
 
 	int	klen;
 	int	len;

lib/crypto/aesgcm.c

···
  * Test code below. Vectors taken from crypto/testmgr.h
  */
 
-static const u8 __initconst ctext0[16] =
+static const u8 __initconst ctext0[16] __nonstring =
 	"\x58\xe2\xfc\xce\xfa\x7e\x30\x61"
 	"\x36\x7f\x1d\x57\xa4\xe7\x45\x5a";
 
 static const u8 __initconst ptext1[16];
 
-static const u8 __initconst ctext1[32] =
+static const u8 __initconst ctext1[32] __nonstring =
 	"\x03\x88\xda\xce\x60\xb6\xa3\x92"
 	"\xf3\x28\xc2\xb9\x71\xb2\xfe\x78"
 	"\xab\x6e\x47\xd4\x2c\xec\x13\xbd"
 	"\xf5\x3a\x67\xb2\x12\x57\xbd\xdf";
 
-static const u8 __initconst ptext2[64] =
+static const u8 __initconst ptext2[64] __nonstring =
 	"\xd9\x31\x32\x25\xf8\x84\x06\xe5"
 	"\xa5\x59\x09\xc5\xaf\xf5\x26\x9a"
 	"\x86\xa7\xa9\x53\x15\x34\xf7\xda"
···
 	"\xb1\x6a\xed\xf5\xaa\x0d\xe6\x57"
 	"\xba\x63\x7b\x39\x1a\xaf\xd2\x55";
 
-static const u8 __initconst ctext2[80] =
+static const u8 __initconst ctext2[80] __nonstring =
 	"\x42\x83\x1e\xc2\x21\x77\x74\x24"
 	"\x4b\x72\x21\xb7\x84\xd0\xd4\x9c"
 	"\xe3\xaa\x21\x2f\x2c\x02\xa4\xe0"
···
 	"\x4d\x5c\x2a\xf3\x27\xcd\x64\xa6"
 	"\x2c\xf3\x5a\xbd\x2b\xa6\xfa\xb4";
 
-static const u8 __initconst ptext3[60] =
+static const u8 __initconst ptext3[60] __nonstring =
 	"\xd9\x31\x32\x25\xf8\x84\x06\xe5"
 	"\xa5\x59\x09\xc5\xaf\xf5\x26\x9a"
 	"\x86\xa7\xa9\x53\x15\x34\xf7\xda"
···
 	"\xb1\x6a\xed\xf5\xaa\x0d\xe6\x57"
 	"\xba\x63\x7b\x39";
 
-static const u8 __initconst ctext3[76] =
+static const u8 __initconst ctext3[76] __nonstring =
 	"\x42\x83\x1e\xc2\x21\x77\x74\x24"
 	"\x4b\x72\x21\xb7\x84\xd0\xd4\x9c"
 	"\xe3\xaa\x21\x2f\x2c\x02\xa4\xe0"
···
 	"\x5b\xc9\x4f\xbc\x32\x21\xa5\xdb"
 	"\x94\xfa\xe9\x5a\xe7\x12\x1a\x47";
 
-static const u8 __initconst ctext4[16] =
+static const u8 __initconst ctext4[16] __nonstring =
 	"\xcd\x33\xb2\x8a\xc7\x73\xf7\x4b"
 	"\xa0\x0e\xd1\xf3\x12\x57\x24\x35";
 
-static const u8 __initconst ctext5[32] =
+static const u8 __initconst ctext5[32] __nonstring =
 	"\x98\xe7\x24\x7c\x07\xf0\xfe\x41"
 	"\x1c\x26\x7e\x43\x84\xb0\xf6\x00"
 	"\x2f\xf5\x8d\x80\x03\x39\x27\xab"
 	"\x8e\xf4\xd4\x58\x75\x14\xf0\xfb";
 
-static const u8 __initconst ptext6[64] =
+static const u8 __initconst ptext6[64] __nonstring =
 	"\xd9\x31\x32\x25\xf8\x84\x06\xe5"
 	"\xa5\x59\x09\xc5\xaf\xf5\x26\x9a"
 	"\x86\xa7\xa9\x53\x15\x34\xf7\xda"
···
 	"\xb1\x6a\xed\xf5\xaa\x0d\xe6\x57"
 	"\xba\x63\x7b\x39\x1a\xaf\xd2\x55";
 
-static const u8 __initconst ctext6[80] =
+static const u8 __initconst ctext6[80] __nonstring =
 	"\x39\x80\xca\x0b\x3c\x00\xe8\x41"
 	"\xeb\x06\xfa\xc4\x87\x2a\x27\x57"
 	"\x85\x9e\x1c\xea\xa6\xef\xd9\x84"
···
 	"\x99\x24\xa7\xc8\x58\x73\x36\xbf"
 	"\xb1\x18\x02\x4d\xb8\x67\x4a\x14";
 
-static const u8 __initconst ctext7[16] =
+static const u8 __initconst ctext7[16] __nonstring =
 	"\x53\x0f\x8a\xfb\xc7\x45\x36\xb9"
 	"\xa9\x63\xb4\xf1\xc4\xcb\x73\x8b";
 
-static const u8 __initconst ctext8[32] =
+static const u8 __initconst ctext8[32] __nonstring =
 	"\xce\xa7\x40\x3d\x4d\x60\x6b\x6e"
 	"\x07\x4e\xc5\xd3\xba\xf3\x9d\x18"
 	"\xd0\xd1\xc8\xa7\x99\x99\x6b\xf0"
 	"\x26\x5b\x98\xb5\xd4\x8a\xb9\x19";
 
-static const u8 __initconst ptext9[64] =
+static const u8 __initconst ptext9[64] __nonstring =
 	"\xd9\x31\x32\x25\xf8\x84\x06\xe5"
 	"\xa5\x59\x09\xc5\xaf\xf5\x26\x9a"
 	"\x86\xa7\xa9\x53\x15\x34\xf7\xda"
···
 	"\xb1\x6a\xed\xf5\xaa\x0d\xe6\x57"
 	"\xba\x63\x7b\x39\x1a\xaf\xd2\x55";
 
-static const u8 __initconst ctext9[80] =
+static const u8 __initconst ctext9[80] __nonstring =
 	"\x52\x2d\xc1\xf0\x99\x56\x7d\x07"
 	"\xf4\x7f\x37\xa3\x2a\x84\x42\x7d"
 	"\x64\x3a\x8c\xdc\xbf\xe5\xc0\xc9"
···
 	"\xb0\x94\xda\xc5\xd9\x34\x71\xbd"
 	"\xec\x1a\x50\x22\x70\xe3\xcc\x6c";
 
-static const u8 __initconst ptext10[60] =
+static const u8 __initconst ptext10[60] __nonstring =
 	"\xd9\x31\x32\x25\xf8\x84\x06\xe5"
 	"\xa5\x59\x09\xc5\xaf\xf5\x26\x9a"
 	"\x86\xa7\xa9\x53\x15\x34\xf7\xda"
···
 	"\xb1\x6a\xed\xf5\xaa\x0d\xe6\x57"
 	"\xba\x63\x7b\x39";
 
-static const u8 __initconst ctext10[76] =
+static const u8 __initconst ctext10[76] __nonstring =
 	"\x52\x2d\xc1\xf0\x99\x56\x7d\x07"
 	"\xf4\x7f\x37\xa3\x2a\x84\x42\x7d"
 	"\x64\x3a\x8c\xdc\xbf\xe5\xc0\xc9"
···
 	"\x76\xfc\x6e\xce\x0f\x4e\x17\x68"
 	"\xcd\xdf\x88\x53\xbb\x2d\x55\x1b";
 
-static const u8 __initconst ptext11[60] =
+static const u8 __initconst ptext11[60] __nonstring =
 	"\xd9\x31\x32\x25\xf8\x84\x06\xe5"
 	"\xa5\x59\x09\xc5\xaf\xf5\x26\x9a"
 	"\x86\xa7\xa9\x53\x15\x34\xf7\xda"
···
 	"\xb1\x6a\xed\xf5\xaa\x0d\xe6\x57"
 	"\xba\x63\x7b\x39";
 
-static const u8 __initconst ctext11[76] =
+static const u8 __initconst ctext11[76] __nonstring =
 	"\x39\x80\xca\x0b\x3c\x00\xe8\x41"
 	"\xeb\x06\xfa\xc4\x87\x2a\x27\x57"
 	"\x85\x9e\x1c\xea\xa6\xef\xd9\x84"
···
 	"\x25\x19\x49\x8e\x80\xf1\x47\x8f"
 	"\x37\xba\x55\xbd\x6d\x27\x61\x8c";
 
-static const u8 __initconst ptext12[719] =
+static const u8 __initconst ptext12[719] __nonstring =
 	"\x42\xc1\xcc\x08\x48\x6f\x41\x3f"
 	"\x2f\x11\x66\x8b\x2a\x16\xf0\xe0"
 	"\x58\x83\xf0\xc3\x70\x14\xc0\x5b"
···
 	"\x59\xfa\xfa\xaa\x44\x04\x01\xa7"
 	"\xa4\x78\xdb\x74\x3d\x8b\xb5";
 
-static const u8 __initconst ctext12[735] =
+static const u8 __initconst ctext12[735] __nonstring =
 	"\x84\x0b\xdb\xd5\xb7\xa8\xfe\x20"
 	"\xbb\xb1\x12\x7f\x41\xea\xb3\xc0"
 	"\xa2\xb4\x37\x19\x11\x58\xb6\x0b"
···
 	const u8	*ptext;
 	const u8	*ctext;
 
-	u8		key[AES_MAX_KEY_SIZE];
-	u8		iv[GCM_AES_IV_SIZE];
-	u8		assoc[20];
+	u8		key[AES_MAX_KEY_SIZE] __nonstring;
+	u8		iv[GCM_AES_IV_SIZE] __nonstring;
+	u8		assoc[20] __nonstring;
 
 	int		klen;
 	int		clen;

lib/scatterlist.c

···
  *   Should only be used casually, it (currently) scans the entire list
  *   to get the last entry.
  *
- *   Note that the @sgl@ pointer passed in need not be the first one,
- *   the important bit is that @nents@ denotes the number of entries that
- *   exist from @sgl@.
+ *   Note that the @sgl pointer passed in need not be the first one,
+ *   the important bit is that @nents denotes the number of entries that
+ *   exist from @sgl.
  *
  **/
 struct scatterlist *sg_last(struct scatterlist *sgl, unsigned int nents)
···
  * @gfp_mask:	GFP allocation mask
  *
  *  Description:
- *    Allocate and initialize an sg table. If @nents@ is larger than
+ *    Allocate and initialize an sg table. If @nents is larger than
  *    SG_MAX_SINGLE_ALLOC a chained sg table will be setup.
  *
  **/

mm/execmem.c

···
 	return ptr;
 }
 
-static bool execmem_cache_rox = false;
-
-void execmem_cache_make_ro(void)
-{
-	struct maple_tree *free_areas = &execmem_cache.free_areas;
-	struct maple_tree *busy_areas = &execmem_cache.busy_areas;
-	MA_STATE(mas_free, free_areas, 0, ULONG_MAX);
-	MA_STATE(mas_busy, busy_areas, 0, ULONG_MAX);
-	struct mutex *mutex = &execmem_cache.mutex;
-	void *area;
-
-	execmem_cache_rox = true;
-
-	mutex_lock(mutex);
-
-	mas_for_each(&mas_free, area, ULONG_MAX) {
-		unsigned long pages = mas_range_len(&mas_free) >> PAGE_SHIFT;
-		set_memory_ro(mas_free.index, pages);
-	}
-
-	mas_for_each(&mas_busy, area, ULONG_MAX) {
-		unsigned long pages = mas_range_len(&mas_busy) >> PAGE_SHIFT;
-		set_memory_ro(mas_busy.index, pages);
-	}
-
-	mutex_unlock(mutex);
-}
-
 static int execmem_cache_populate(struct execmem_range *range, size_t size)
 {
 	unsigned long vm_flags = VM_ALLOW_HUGE_VMAP;
···
 	/* fill memory with instructions that will trap */
 	execmem_fill_trapping_insns(p, alloc_size, /* writable = */ true);
 
-	if (execmem_cache_rox) {
-		err = set_memory_rox((unsigned long)p, vm->nr_pages);
-		if (err)
-			goto err_free_mem;
-	} else {
-		err = set_memory_x((unsigned long)p, vm->nr_pages);
-		if (err)
-			goto err_free_mem;
-	}
+	err = set_memory_rox((unsigned long)p, vm->nr_pages);
+	if (err)
+		goto err_free_mem;
 
 	err = execmem_cache_add(p, alloc_size);
 	if (err)

mm/madvise.c

···
 					pte_offset_map_lock(mm, pmd, addr, &ptl);
 				if (!start_pte)
 					break;
+				flush_tlb_batched_pending(mm);
 				arch_enter_lazy_mmu_mode();
 				if (!err)
 					nr = 0;
···
 				start_pte = pte;
 				if (!start_pte)
 					break;
+				flush_tlb_batched_pending(mm);
 				arch_enter_lazy_mmu_mode();
 				if (!err)
 					nr = 0;

mm/util.c

···
 }
 EXPORT_SYMBOL(flush_dcache_folio);
 #endif
+
+/**
+ * compat_vma_mmap_prepare() - Apply the file's .mmap_prepare() hook to an
+ * existing VMA
+ * @file: The file which possesss an f_op->mmap_prepare() hook
+ * @vma: The VMA to apply the .mmap_prepare() hook to.
+ *
+ * Ordinarily, .mmap_prepare() is invoked directly upon mmap(). However, certain
+ * 'wrapper' file systems invoke a nested mmap hook of an underlying file.
+ *
+ * Until all filesystems are converted to use .mmap_prepare(), we must be
+ * conservative and continue to invoke these 'wrapper' filesystems using the
+ * deprecated .mmap() hook.
+ *
+ * However we have a problem if the underlying file system possesses an
+ * .mmap_prepare() hook, as we are in a different context when we invoke the
+ * .mmap() hook, already having a VMA to deal with.
+ *
+ * compat_vma_mmap_prepare() is a compatibility function that takes VMA state,
+ * establishes a struct vm_area_desc descriptor, passes to the underlying
+ * .mmap_prepare() hook and applies any changes performed by it.
+ *
+ * Once the conversion of filesystems is complete this function will no longer
+ * be required and will be removed.
+ *
+ * Returns: 0 on success or error.
+ */
+int compat_vma_mmap_prepare(struct file *file, struct vm_area_struct *vma)
+{
+	struct vm_area_desc desc;
+	int err;
+
+	err = file->f_op->mmap_prepare(vma_to_desc(vma, &desc));
+	if (err)
+		return err;
+	set_vma_from_desc(vma, &desc);
+
+	return 0;
+}
+EXPORT_SYMBOL(compat_vma_mmap_prepare);

mm/vma.c

···
 		err = dup_anon_vma(next, middle, &anon_dup);
 	}
 
-	if (err)
+	if (err || commit_merge(vmg))
 		goto abort;
-
-	err = commit_merge(vmg);
-	if (err) {
-		VM_WARN_ON(err != -ENOMEM);
-
-		if (anon_dup)
-			unlink_anon_vmas(anon_dup);
-
-		/*
-		 * We've cleaned up any cloned anon_vma's, no VMAs have been
-		 * modified, no harm no foul if the user requests that we not
-		 * report this and just give up, leaving the VMAs unmerged.
-		 */
-		if (!vmg->give_up_on_oom)
-			vmg->state = VMA_MERGE_ERROR_NOMEM;
-		return NULL;
-	}
 
 	khugepaged_enter_vma(vmg->target, vmg->flags);
 	vmg->state = VMA_MERGE_SUCCESS;
···
 abort:
 	vma_iter_set(vmg->vmi, start);
 	vma_iter_load(vmg->vmi);
+
+	if (anon_dup)
+		unlink_anon_vmas(anon_dup);
 
 	/*
 	 * This means we have failed to clone anon_vma's correctly, but no
···
 	userfaultfd_unmap_complete(mm, &uf);
 	return ret;
 }
-
 
 /* Insert vm structure into process list sorted by address
  * and into the inode's i_mmap tree.  If vm_file is non-NULL

mm/vma.h

···
 	return 0;
 }
 
+
+/*
+ * Temporary helper functions for file systems which wrap an invocation of
+ * f_op->mmap() but which might have an underlying file system which implements
+ * f_op->mmap_prepare().
+ */
+
+static inline struct vm_area_desc *vma_to_desc(struct vm_area_struct *vma,
+		struct vm_area_desc *desc)
+{
+	desc->mm = vma->vm_mm;
+	desc->start = vma->vm_start;
+	desc->end = vma->vm_end;
+
+	desc->pgoff = vma->vm_pgoff;
+	desc->file = vma->vm_file;
+	desc->vm_flags = vma->vm_flags;
+	desc->page_prot = vma->vm_page_prot;
+
+	desc->vm_ops = NULL;
+	desc->private_data = NULL;
+
+	return desc;
+}
+
+static inline void set_vma_from_desc(struct vm_area_struct *vma,
+		struct vm_area_desc *desc)
+{
+	/*
+	 * Since we're invoking .mmap_prepare() despite having a partially
+	 * established VMA, we must take care to handle setting fields
+	 * correctly.
+	 */
+
+	/* Mutable fields. Populated with initial state. */
+	vma->vm_pgoff = desc->pgoff;
+	if (vma->vm_file != desc->file)
+		vma_set_file(vma, desc->file);
+	if (vma->vm_flags != desc->vm_flags)
+		vm_flags_set(vma, desc->vm_flags);
+	vma->vm_page_prot = desc->page_prot;
+
+	/* User-defined fields. */
+	vma->vm_ops = desc->vm_ops;
+	vma->vm_private_data = desc->private_data;
+}
+
 int
 do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma,
 		    struct mm_struct *mm, unsigned long start,

net/atm/common.c

···
 
 	skb->dev = NULL; /* for paths shared with net_device interfaces */
 	if (!copy_from_iter_full(skb_put(skb, size), size, &m->msg_iter)) {
+		atm_return_tx(vcc, skb);
 		kfree_skb(skb);
 		error = -EFAULT;
 		goto out;

net/atm/lec.c

···
 
 /* Device structures */
 static struct net_device *dev_lec[MAX_LEC_ITF];
+static DEFINE_MUTEX(lec_mutex);
 
 #if IS_ENABLED(CONFIG_BRIDGE)
 static void lec_handle_bridge(struct sk_buff *skb, struct net_device *dev)
···
 	int bytes_left;
 	struct atmlec_ioc ioc_data;
 
+	lockdep_assert_held(&lec_mutex);
 	/* Lecd must be up in this case */
 	bytes_left = copy_from_user(&ioc_data, arg, sizeof(struct atmlec_ioc));
 	if (bytes_left != 0)
···
 
 static int lec_mcast_attach(struct atm_vcc *vcc, int arg)
 {
+	lockdep_assert_held(&lec_mutex);
 	if (arg < 0 || arg >= MAX_LEC_ITF)
 		return -EINVAL;
 	arg = array_index_nospec(arg, MAX_LEC_ITF);
···
 	int i;
 	struct lec_priv *priv;
 
+	lockdep_assert_held(&lec_mutex);
 	if (arg < 0)
 		arg = 0;
 	if (arg >= MAX_LEC_ITF)
···
 		snprintf(dev_lec[i]->name, IFNAMSIZ, "lec%d", i);
 		if (register_netdev(dev_lec[i])) {
 			free_netdev(dev_lec[i]);
+			dev_lec[i] = NULL;
 			return -EINVAL;
 		}
 
···
 	v = (dev && netdev_priv(dev)) ?
 		lec_priv_walk(state, l, netdev_priv(dev)) : NULL;
 	if (!v && dev) {
-		dev_put(dev);
 		/* Partial state reset for the next time we get called */
 		dev = NULL;
 	}
···
 {
 	struct lec_state *state = seq->private;
 
+	mutex_lock(&lec_mutex);
 	state->itf = 0;
 	state->dev = NULL;
 	state->locked = NULL;
···
 	if (state->dev) {
 		spin_unlock_irqrestore(&state->locked->lec_arp_lock,
 				       state->flags);
-		dev_put(state->dev);
+		state->dev = NULL;
 	}
+	mutex_unlock(&lec_mutex);
 }
 
 static void *lec_seq_next(struct seq_file *seq, void *v, loff_t *pos)
···
 		return -ENOIOCTLCMD;
 	}
 
+	mutex_lock(&lec_mutex);
 	switch (cmd) {
 	case ATMLEC_CTRL:
 		err = lecd_attach(vcc, (int)arg);
···
 		break;
 	}
 
+	mutex_unlock(&lec_mutex);
 	return err;
 }
 

net/atm/raw.c

···
 
 	pr_debug("(%d) %d -= %d\n",
 		 vcc->vci, sk_wmem_alloc_get(sk), ATM_SKB(skb)->acct_truesize);
-	WARN_ON(refcount_sub_and_test(ATM_SKB(skb)->acct_truesize, &sk->sk_wmem_alloc));
+	atm_return_tx(vcc, skb);
 	dev_kfree_skb_any(skb);
 	sk->sk_write_space(sk);
 }

net/core/skbuff.c

···
 	if (!pskb_may_pull(skb, write_len))
 		return -ENOMEM;
 
-	if (!skb_frags_readable(skb))
-		return -EFAULT;
-
 	if (!skb_cloned(skb) || skb_clone_writable(skb, write_len))
 		return 0;
 

net/ipv4/tcp_fastopen.c

···
 #include <linux/tcp.h>
 #include <linux/rcupdate.h>
 #include <net/tcp.h>
+#include <net/busy_poll.h>
 
 void tcp_fastopen_init_key_once(struct net *net)
 {
···
 			     req->timeout, false);
 
 	refcount_set(&req->rsk_refcnt, 2);
+
+	sk_mark_napi_id_set(child, skb);
 
 	/* Now finish processing the fastopen child socket. */
 	tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB, skb);

net/ipv4/tcp_input.c

···
 {
 	const struct sock *sk = (const struct sock *)tp;
 
-	if (tp->retrans_stamp &&
-	    tcp_tsopt_ecr_before(tp, tp->retrans_stamp))
-		return true;  /* got echoed TS before first retransmission */
+	/* Received an echoed timestamp before the first retransmission? */
+	if (tp->retrans_stamp)
+		return tcp_tsopt_ecr_before(tp, tp->retrans_stamp);
 
-	/* Check if nothing was retransmitted (retrans_stamp==0), which may
-	 * happen in fast recovery due to TSQ. But we ignore zero retrans_stamp
-	 * in TCP_SYN_SENT, since when we set FLAG_SYN_ACKED we also clear
-	 * retrans_stamp even if we had retransmitted the SYN.
+	/* We set tp->retrans_stamp upon the first retransmission of a loss
+	 * recovery episode, so normally if tp->retrans_stamp is 0 then no
+	 * retransmission has happened yet (likely due to TSQ, which can cause
+	 * fast retransmits to be delayed). So if snd_una advanced while
+	 * (tp->retrans_stamp is 0 then apparently a packet was merely delayed,
+	 * not lost. But there are exceptions where we retransmit but then
+	 * clear tp->retrans_stamp, so we check for those exceptions.
 	 */
-	if (!tp->retrans_stamp &&	   /* no record of a retransmit/SYN? */
-	    sk->sk_state != TCP_SYN_SENT)  /* not the FLAG_SYN_ACKED case? */
-		return true;  /* nothing was retransmitted */
 
-	return false;
+	/* (1) For non-SACK connections, tcp_is_non_sack_preventing_reopen()
+	 * clears tp->retrans_stamp when snd_una == high_seq.
+	 */
+	if (!tcp_is_sack(tp) && !before(tp->snd_una, tp->high_seq))
+		return false;
+
+	/* (2) In TCP_SYN_SENT tcp_clean_rtx_queue() clears tp->retrans_stamp
+	 * when setting FLAG_SYN_ACKED is set, even if the SYN was
+	 * retransmitted.
+	 */
+	if (sk->sk_state == TCP_SYN_SENT)
+		return false;
+
+	return true;	/* tp->retrans_stamp is zero; no retransmit yet */
 }
 
 /* Undo procedures. */

net/ipv6/calipso.c

···
 	struct ipv6_opt_hdr *old, *new;
 	struct sock *sk = sk_to_full_sk(req_to_sk(req));
 
+	/* sk is NULL for SYN+ACK w/ SYN Cookie */
+	if (!sk)
+		return -ENOMEM;
+
 	if (req_inet->ipv6_opt && req_inet->ipv6_opt->hopopt)
 		old = req_inet->ipv6_opt->hopopt;
 	else
···
 	struct ipv6_opt_hdr *new;
 	struct ipv6_txoptions *txopts;
 	struct sock *sk = sk_to_full_sk(req_to_sk(req));
+
+	/* sk is NULL for SYN+ACK w/ SYN Cookie */
+	if (!sk)
+		return;
 
 	if (!req_inet->ipv6_opt || !req_inet->ipv6_opt->hopopt)
 		return;

net/mac80211/debug.h

···
 /* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Portions
- * Copyright (C) 2022 - 2024 Intel Corporation
+ * Copyright (C) 2022 - 2025 Intel Corporation
  */
 #ifndef __MAC80211_DEBUG_H
 #define __MAC80211_DEBUG_H
+#include <linux/once_lite.h>
 #include <net/cfg80211.h>
 
 #ifdef CONFIG_MAC80211_OCB_DEBUG
···
 		else							\
 			_sdata_err((link)->sdata, fmt, ##__VA_ARGS__);	\
 	} while (0)
+#define link_err_once(link, fmt, ...)					\
+	DO_ONCE_LITE(link_err, link, fmt, ##__VA_ARGS__)
 #define link_id_info(sdata, link_id, fmt, ...)				\
 	do {								\
 		if (ieee80211_vif_is_mld(&sdata->vif))			\

net/mac80211/rx.c

···
 		if (!multicast &&
 		    !ether_addr_equal(sdata->dev->dev_addr, hdr->addr1))
 			return false;
+		/* reject invalid/our STA address */
+		if (!is_valid_ether_addr(hdr->addr2) ||
+		    ether_addr_equal(sdata->dev->dev_addr, hdr->addr2))
+			return false;
 		if (!rx->sta) {
 			int rate_idx;
 			if (status->encoding != RX_ENC_LEGACY)

net/mac80211/tx.c

···
  * Copyright 2006-2007	Jiri Benc <[e-mail]>
  * Copyright 2007	Johannes Berg <[e-mail]>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
- * Copyright (C) 2018-2024 Intel Corporation
+ * Copyright (C) 2018-2025 Intel Corporation
  *
  * Transmit and frame generation functions.
  */
···
 	}
 }
 
-static u8 __ieee80211_beacon_update_cntdwn(struct beacon_data *beacon)
+static u8 __ieee80211_beacon_update_cntdwn(struct ieee80211_link_data *link,
+					   struct beacon_data *beacon)
 {
-	beacon->cntdwn_current_counter--;
+	if (beacon->cntdwn_current_counter == 1) {
+		/*
+		 * Channel switch handling is done by a worker thread while
+		 * beacons get pulled from hardware timers. It's therefore
+		 * possible that software threads are slow enough to not be
+		 * able to complete CSA handling in a single beacon interval,
+		 * in which case we get here. There isn't much to do about
+		 * it, other than letting the user know that the AP isn't
+		 * behaving correctly.
+		 */
+		link_err_once(link,
+			      "beacon TX faster than countdown (channel/color switch) completion\n");
+		return 0;
+	}
 
-	/* the counter should never reach 0 */
-	WARN_ON_ONCE(!beacon->cntdwn_current_counter);
+	beacon->cntdwn_current_counter--;
 
 	return beacon->cntdwn_current_counter;
 }
···
 	if (!beacon)
 		goto unlock;
 
-	count = __ieee80211_beacon_update_cntdwn(beacon);
+	count = __ieee80211_beacon_update_cntdwn(link, beacon);
 
 unlock:
 	rcu_read_unlock();
···
 
 		if (beacon->cntdwn_counter_offsets[0]) {
 			if (!is_template)
-				__ieee80211_beacon_update_cntdwn(beacon);
+				__ieee80211_beacon_update_cntdwn(link, beacon);
 
 			ieee80211_set_beacon_cntdwn(sdata, beacon, link);
 		}
···
 				 * for now we leave it consistent with overall
 				 * mac80211's behavior.
 				 */
-				__ieee80211_beacon_update_cntdwn(beacon);
+				__ieee80211_beacon_update_cntdwn(link, beacon);
 
 			ieee80211_set_beacon_cntdwn(sdata, beacon, link);
 		}

net/mpls/af_mpls.c

···
 
 	if (index < net->mpls.platform_labels) {
 		struct mpls_route __rcu **platform_label =
-			rcu_dereference(net->mpls.platform_label);
-		rt = rcu_dereference(platform_label[index]);
+			rcu_dereference_rtnl(net->mpls.platform_label);
+		rt = rcu_dereference_rtnl(platform_label[index]);
 	}
 	return rt;
 }

net/nfc/nci/uart.c

···
 
 	memcpy(nu, nci_uart_drivers[driver], sizeof(struct nci_uart));
 	nu->tty = tty;
-	tty->disc_data = nu;
 	skb_queue_head_init(&nu->tx_q);
 	INIT_WORK(&nu->write_work, nci_uart_write_work);
 	spin_lock_init(&nu->rx_lock);
 
 	ret = nu->ops.open(nu);
 	if (ret) {
-		tty->disc_data = NULL;
 		kfree(nu);
+		return ret;
 	} else if (!try_module_get(nu->owner)) {
 		nu->ops.close(nu);
-		tty->disc_data = NULL;
 		kfree(nu);
 		return -ENOENT;
 	}
-	return ret;
+	tty->disc_data = nu;
+
+	return 0;
 }
 
 /* ------ LDISC part ------ */

net/openvswitch/actions.c

···
 #include "flow_netlink.h"
 #include "openvswitch_trace.h"
 
-DEFINE_PER_CPU(struct ovs_pcpu_storage, ovs_pcpu_storage) = {
-	.bh_lock = INIT_LOCAL_LOCK(bh_lock),
-};
+struct ovs_pcpu_storage __percpu *ovs_pcpu_storage;
 
 /* Make a clone of the 'key', using the pre-allocated percpu 'flow_keys'
  * space. Return NULL if out of key spaces.
  */
 static struct sw_flow_key *clone_key(const struct sw_flow_key *key_)
 {
-	struct ovs_pcpu_storage *ovs_pcpu = this_cpu_ptr(&ovs_pcpu_storage);
+	struct ovs_pcpu_storage *ovs_pcpu = this_cpu_ptr(ovs_pcpu_storage);
 	struct action_flow_keys *keys = &ovs_pcpu->flow_keys;
 	int level = ovs_pcpu->exec_level;
 	struct sw_flow_key *key = NULL;
···
 				    const struct nlattr *actions,
 				    const int actions_len)
 {
-	struct action_fifo *fifo = this_cpu_ptr(&ovs_pcpu_storage.action_fifos);
+	struct action_fifo *fifo = this_cpu_ptr(&ovs_pcpu_storage->action_fifos);
 	struct deferred_action *da;
 
 	da = action_fifo_put(fifo);
···
 static int ovs_vport_output(struct net *net, struct sock *sk,
 			    struct sk_buff *skb)
 {
-	struct ovs_frag_data *data = this_cpu_ptr(&ovs_pcpu_storage.frag_data);
+	struct ovs_frag_data *data = this_cpu_ptr(&ovs_pcpu_storage->frag_data);
 	struct vport *vport = data->vport;
 
 	if (skb_cow_head(skb, data->l2_len) < 0) {
···
 	unsigned int hlen = skb_network_offset(skb);
 	struct ovs_frag_data *data;
 
-	data = this_cpu_ptr(&ovs_pcpu_storage.frag_data);
+	data = this_cpu_ptr(&ovs_pcpu_storage->frag_data);
 	data->dst = skb->_skb_refdst;
 	data->vport = vport;
 	data->cb = *OVS_CB(skb);
···
 	clone = clone_flow_key ? clone_key(key) : key;
 	if (clone) {
 		int err = 0;
-
 		if (actions) { /* Sample action */
 			if (clone_flow_key)
-				__this_cpu_inc(ovs_pcpu_storage.exec_level);
+				__this_cpu_inc(ovs_pcpu_storage->exec_level);
 
 			err = do_execute_actions(dp, skb, clone,
 						 actions, len);
 
 			if (clone_flow_key)
-				__this_cpu_dec(ovs_pcpu_storage.exec_level);
+				__this_cpu_dec(ovs_pcpu_storage->exec_level);
 		} else { /* Recirc action */
 			clone->recirc_id = recirc_id;
 			ovs_dp_process_packet(skb, clone);
···
 
 static void process_deferred_actions(struct datapath *dp)
 {
-	struct action_fifo *fifo = this_cpu_ptr(&ovs_pcpu_storage.action_fifos);
+	struct action_fifo *fifo = this_cpu_ptr(&ovs_pcpu_storage->action_fifos);
 
 	/* Do not touch the FIFO in case there is no deferred actions. */
 	if (action_fifo_is_empty(fifo))
···
 {
 	int err, level;
 
-	level = __this_cpu_inc_return(ovs_pcpu_storage.exec_level);
+	level = __this_cpu_inc_return(ovs_pcpu_storage->exec_level);
 	if (unlikely(level > OVS_RECURSION_LIMIT)) {
 		net_crit_ratelimited("ovs: recursion limit reached on datapath %s, probable configuration error\n",
 				     ovs_dp_name(dp));
···
 		process_deferred_actions(dp);
 
 out:
-	__this_cpu_dec(ovs_pcpu_storage.exec_level);
+	__this_cpu_dec(ovs_pcpu_storage->exec_level);
 	return err;
 }

net/openvswitch/datapath.c

···
 /* Must be called with rcu_read_lock. */
 void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key)
 {
-	struct ovs_pcpu_storage *ovs_pcpu = this_cpu_ptr(&ovs_pcpu_storage);
+	struct ovs_pcpu_storage *ovs_pcpu = this_cpu_ptr(ovs_pcpu_storage);
 	const struct vport *p = OVS_CB(skb)->input_vport;
 	struct datapath *dp = p->dp;
 	struct sw_flow *flow;
···
 	 * avoided.
 	 */
 	if (IS_ENABLED(CONFIG_PREEMPT_RT) && ovs_pcpu->owner != current) {
-		local_lock_nested_bh(&ovs_pcpu_storage.bh_lock);
+		local_lock_nested_bh(&ovs_pcpu_storage->bh_lock);
 		ovs_pcpu->owner = current;
 		ovs_pcpu_locked = true;
 	}
···
 				    ovs_dp_name(dp), error);
 	if (ovs_pcpu_locked) {
 		ovs_pcpu->owner = NULL;
-		local_unlock_nested_bh(&ovs_pcpu_storage.bh_lock);
+		local_unlock_nested_bh(&ovs_pcpu_storage->bh_lock);
 	}
 
 	stats_counter = &stats->n_hit;
···
 	sf_acts = rcu_dereference(flow->sf_acts);
 
 	local_bh_disable();
-	local_lock_nested_bh(&ovs_pcpu_storage.bh_lock);
+	local_lock_nested_bh(&ovs_pcpu_storage->bh_lock);
 	if (IS_ENABLED(CONFIG_PREEMPT_RT))
-		this_cpu_write(ovs_pcpu_storage.owner, current);
+		this_cpu_write(ovs_pcpu_storage->owner, current);
 	err = ovs_execute_actions(dp, packet, sf_acts, &flow->key);
 	if (IS_ENABLED(CONFIG_PREEMPT_RT))
-		this_cpu_write(ovs_pcpu_storage.owner, NULL);
-	local_unlock_nested_bh(&ovs_pcpu_storage.bh_lock);
+		this_cpu_write(ovs_pcpu_storage->owner, NULL);
+	local_unlock_nested_bh(&ovs_pcpu_storage->bh_lock);
 	local_bh_enable();
 	rcu_read_unlock();
 
···
 	.n_reasons = ARRAY_SIZE(ovs_drop_reasons),
 };
 
+static int __init ovs_alloc_percpu_storage(void)
+{
+	unsigned int cpu;
+
+	ovs_pcpu_storage = alloc_percpu(*ovs_pcpu_storage);
+	if (!ovs_pcpu_storage)
+		return -ENOMEM;
+
+	for_each_possible_cpu(cpu) {
+		struct ovs_pcpu_storage *ovs_pcpu;
+
+		ovs_pcpu = per_cpu_ptr(ovs_pcpu_storage, cpu);
+		local_lock_init(&ovs_pcpu->bh_lock);
+	}
+	return 0;
+}
+
+static void ovs_free_percpu_storage(void)
+{
+	free_percpu(ovs_pcpu_storage);
+}
+
 static int __init dp_init(void)
 {
 	int err;
···
 		     sizeof_field(struct sk_buff, cb));
 
 	pr_info("Open vSwitch switching datapath\n");
+
+	err = ovs_alloc_percpu_storage();
+	if (err)
+		goto error;
 
 	err = ovs_internal_dev_rtnl_link_register();
 	if (err)
···
 error_unreg_rtnl_link:
 	ovs_internal_dev_rtnl_link_unregister();
 error:
+	ovs_free_percpu_storage();
 	return err;
 }
 
···
 	ovs_vport_exit();
 	ovs_flow_exit();
 	ovs_internal_dev_rtnl_link_unregister();
+	ovs_free_percpu_storage();
 }
 
 module_init(dp_init);

net/openvswitch/datapath.h

···
 	struct task_struct *owner;
 	local_lock_t bh_lock;
 };
-DECLARE_PER_CPU(struct ovs_pcpu_storage, ovs_pcpu_storage);
+
+extern struct ovs_pcpu_storage __percpu *ovs_pcpu_storage;
 
 /**
  * enum ovs_pkt_hash_types - hash info to include with a packet

net/sched/sch_taprio.c

···
 
 		stab = rtnl_dereference(q->root->stab);
 
-		oper = rtnl_dereference(q->oper_sched);
+		rcu_read_lock();
+		oper = rcu_dereference(q->oper_sched);
 		if (oper)
 			taprio_update_queue_max_sdu(q, oper, stab);
 
-		admin = rtnl_dereference(q->admin_sched);
+		admin = rcu_dereference(q->admin_sched);
 		if (admin)
 			taprio_update_queue_max_sdu(q, admin, stab);
+		rcu_read_unlock();
 
 		break;
 	}

net/tipc/udp_media.c

···
 
 		rtnl_lock();
 		b = tipc_bearer_find(net, bname);
-		if (!b) {
+		if (!b || b->bcast_addr.media_id != TIPC_MEDIA_TYPE_UDP) {
 			rtnl_unlock();
 			return -EINVAL;
 		}
···
 
 		rtnl_lock();
 		b = rtnl_dereference(tn->bearer_list[bid]);
-		if (!b) {
+		if (!b || b->bcast_addr.media_id != TIPC_MEDIA_TYPE_UDP) {
 			rtnl_unlock();
 			return -EINVAL;
 		}

rust/bindings/bindings_helper.h

···
 #include <linux/blk_types.h>
 #include <linux/blkdev.h>
 #include <linux/clk.h>
+#include <linux/completion.h>
 #include <linux/configfs.h>
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>

rust/helpers/completion.c

···
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/completion.h>
+
+void rust_helper_init_completion(struct completion *x)
+{
+	init_completion(x);
+}

rust/helpers/cpu.c

···
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/smp.h>
+
+unsigned int rust_helper_raw_smp_processor_id(void)
+{
+	return raw_smp_processor_id();
+}

rust/helpers/helpers.c

···
 #include "build_assert.c"
 #include "build_bug.c"
 #include "clk.c"
+#include "completion.c"
+#include "cpu.c"
 #include "cpufreq.c"
 #include "cpumask.c"
 #include "cred.c"

rust/kernel/cpu.rs

···
 
 use crate::{bindings, device::Device, error::Result, prelude::ENODEV};
 
+/// Returns the maximum number of possible CPUs in the current system configuration.
+#[inline]
+pub fn nr_cpu_ids() -> u32 {
+    #[cfg(any(NR_CPUS_1, CONFIG_FORCE_NR_CPUS))]
+    {
+        bindings::NR_CPUS
+    }
+
+    #[cfg(not(any(NR_CPUS_1, CONFIG_FORCE_NR_CPUS)))]
+    // SAFETY: `nr_cpu_ids` is a valid global provided by the kernel.
+    unsafe {
+        bindings::nr_cpu_ids
+    }
+}
+
+/// The CPU ID.
+///
+/// Represents a CPU identifier as a wrapper around an [`u32`].
+///
+/// # Invariants
+///
+/// The CPU ID lies within the range `[0, nr_cpu_ids())`.
+///
+/// # Examples
+///
+/// ```
+/// use kernel::cpu::CpuId;
+///
+/// let cpu = 0;
+///
+/// // SAFETY: 0 is always a valid CPU number.
+/// let id = unsafe { CpuId::from_u32_unchecked(cpu) };
+///
+/// assert_eq!(id.as_u32(), cpu);
+/// assert!(CpuId::from_i32(0).is_some());
+/// assert!(CpuId::from_i32(-1).is_none());
+/// ```
+#[derive(Copy, Clone, PartialEq, Eq, Debug)]
+pub struct CpuId(u32);
+
+impl CpuId {
+    /// Creates a new [`CpuId`] from the given `id` without checking bounds.
+    ///
+    /// # Safety
+    ///
+    /// The caller must ensure that `id` is a valid CPU ID (i.e., `0 <= id < nr_cpu_ids()`).
+    #[inline]
+    pub unsafe fn from_i32_unchecked(id: i32) -> Self {
+        debug_assert!(id >= 0);
+        debug_assert!((id as u32) < nr_cpu_ids());
+
+        // INVARIANT: The function safety guarantees `id` is a valid CPU id.
+        Self(id as u32)
+    }
+
+    /// Creates a new [`CpuId`] from the given `id`, checking that it is valid.
+    pub fn from_i32(id: i32) -> Option<Self> {
+        if id < 0 || id as u32 >= nr_cpu_ids() {
+            None
+        } else {
+            // INVARIANT: `id` has just been checked as a valid CPU ID.
+            Some(Self(id as u32))
+        }
+    }
+
+    /// Creates a new [`CpuId`] from the given `id` without checking bounds.
+    ///
+    /// # Safety
+    ///
+    /// The caller must ensure that `id` is a valid CPU ID (i.e., `0 <= id < nr_cpu_ids()`).
+    #[inline]
+    pub unsafe fn from_u32_unchecked(id: u32) -> Self {
+        debug_assert!(id < nr_cpu_ids());
+
+        // Ensure the `id` fits in an [`i32`] as it's also representable that way.
+        debug_assert!(id <= i32::MAX as u32);
+
+        // INVARIANT: The function safety guarantees `id` is a valid CPU id.
+        Self(id)
+    }
+
+    /// Creates a new [`CpuId`] from the given `id`, checking that it is valid.
+    pub fn from_u32(id: u32) -> Option<Self> {
+        if id >= nr_cpu_ids() {
+            None
+        } else {
+            // INVARIANT: `id` has just been checked as a valid CPU ID.
+            Some(Self(id))
+        }
+    }
+
+    /// Returns CPU number.
+    #[inline]
+    pub fn as_u32(&self) -> u32 {
+        self.0
+    }
+
+    /// Returns the ID of the CPU the code is currently running on.
+    ///
+    /// The returned value is considered unstable because it may change
+    /// unexpectedly due to preemption or CPU migration. It should only be
+    /// used when the context ensures that the task remains on the same CPU
+    /// or the users could use a stale (yet valid) CPU ID.
+    pub fn current() -> Self {
+        // SAFETY: raw_smp_processor_id() always returns a valid CPU ID.
+        unsafe { Self::from_u32_unchecked(bindings::raw_smp_processor_id()) }
+    }
+}
+
+impl From<CpuId> for u32 {
+    fn from(id: CpuId) -> Self {
+        id.as_u32()
+    }
+}
+
+impl From<CpuId> for i32 {
+    fn from(id: CpuId) -> Self {
+        id.as_u32() as i32
+    }
+}
+
 /// Creates a new instance of CPU's device.
 ///
 /// # Safety
···
 /// Callers must ensure that the CPU device is not used after it has been unregistered.
 /// This can be achieved, for example, by registering a CPU hotplug notifier and removing
 /// any references to the CPU device within the notifier's callback.
-pub unsafe fn from_cpu(cpu: u32) -> Result<&'static Device> {
+pub unsafe fn from_cpu(cpu: CpuId) -> Result<&'static Device> {
     // SAFETY: It is safe to call `get_cpu_device()` for any CPU.
-    let ptr = unsafe { bindings::get_cpu_device(cpu) };
+    let ptr = unsafe { bindings::get_cpu_device(u32::from(cpu)) };
     if ptr.is_null() {
         return Err(ENODEV);
     }

rust/kernel/cpufreq.rs

···
 
 use crate::{
     clk::Hertz,
+    cpu::CpuId,
     cpumask,
     device::{Bound, Device},
     devres::Devres,
···
 
     /// Returns the primary CPU for the [`Policy`].
     #[inline]
-    pub fn cpu(&self) -> u32 {
-        self.as_ref().cpu
+    pub fn cpu(&self) -> CpuId {
+        // SAFETY: The C API guarantees that `cpu` refers to a valid CPU number.
+        unsafe { CpuId::from_u32_unchecked(self.as_ref().cpu) }
     }
 
     /// Returns the minimum frequency for the [`Policy`].
···
     #[inline]
     pub fn generic_get(&self) -> Result<u32> {
         // SAFETY: By the type invariant, the pointer stored in `self` is valid.
-        Ok(unsafe { bindings::cpufreq_generic_get(self.cpu()) })
+        Ok(unsafe { bindings::cpufreq_generic_get(u32::from(self.cpu())) })
     }
 
     /// Provides a wrapper to the register with energy model using the OPP core.
···
 struct PolicyCpu<'a>(&'a mut Policy);
 
 impl<'a> PolicyCpu<'a> {
-    fn from_cpu(cpu: u32) -> Result<Self> {
+    fn from_cpu(cpu: CpuId) -> Result<Self> {
         // SAFETY: It is safe to call `cpufreq_cpu_get` for any valid CPU.
-        let ptr = from_err_ptr(unsafe { bindings::cpufreq_cpu_get(cpu) })?;
+        let ptr = from_err_ptr(unsafe { bindings::cpufreq_cpu_get(u32::from(cpu)) })?;
 
         Ok(Self(
             // SAFETY: The `ptr` is guaranteed to be valid and remains valid for the lifetime of
···
 impl<T: Driver> Registration<T> {
     /// Driver's `init` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn init_callback(ptr: *mut bindings::cpufreq_policy) -> kernel::ffi::c_int {
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn init_callback(ptr: *mut bindings::cpufreq_policy) -> kernel::ffi::c_int {
         from_result(|| {
             // SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
             // lifetime of `policy`.
···
 
     /// Driver's `exit` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn exit_callback(ptr: *mut bindings::cpufreq_policy) {
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn exit_callback(ptr: *mut bindings::cpufreq_policy) {
         // SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
         // lifetime of `policy`.
         let policy = unsafe { Policy::from_raw_mut(ptr) };
···
 
     /// Driver's `online` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn online_callback(ptr: *mut bindings::cpufreq_policy) -> kernel::ffi::c_int {
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn online_callback(ptr: *mut bindings::cpufreq_policy) -> kernel::ffi::c_int {
         from_result(|| {
             // SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
             // lifetime of `policy`.
···
 
     /// Driver's `offline` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn offline_callback(ptr: *mut bindings::cpufreq_policy) -> kernel::ffi::c_int {
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn offline_callback(
+        ptr: *mut bindings::cpufreq_policy,
+    ) -> kernel::ffi::c_int {
         from_result(|| {
             // SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
             // lifetime of `policy`.
···
 
     /// Driver's `suspend` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn suspend_callback(ptr: *mut bindings::cpufreq_policy) -> kernel::ffi::c_int {
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn suspend_callback(
+        ptr: *mut bindings::cpufreq_policy,
+    ) -> kernel::ffi::c_int {
         from_result(|| {
             // SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
             // lifetime of `policy`.
···
 
     /// Driver's `resume` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn resume_callback(ptr: *mut bindings::cpufreq_policy) -> kernel::ffi::c_int {
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn resume_callback(ptr: *mut bindings::cpufreq_policy) -> kernel::ffi::c_int {
         from_result(|| {
             // SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
             // lifetime of `policy`.
···
 
     /// Driver's `ready` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn ready_callback(ptr: *mut bindings::cpufreq_policy) {
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn ready_callback(ptr: *mut bindings::cpufreq_policy) {
         // SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
         // lifetime of `policy`.
         let policy = unsafe { Policy::from_raw_mut(ptr) };
···
 
     /// Driver's `verify` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn verify_callback(ptr: *mut bindings::cpufreq_policy_data) -> kernel::ffi::c_int {
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn verify_callback(
+        ptr: *mut bindings::cpufreq_policy_data,
+    ) -> kernel::ffi::c_int {
         from_result(|| {
             // SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
             // lifetime of `policy`.
···
 
     /// Driver's `setpolicy` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn setpolicy_callback(ptr: *mut bindings::cpufreq_policy) -> kernel::ffi::c_int {
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn setpolicy_callback(
+        ptr: *mut bindings::cpufreq_policy,
+    ) -> kernel::ffi::c_int {
         from_result(|| {
             // SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
             // lifetime of `policy`.
···
 
     /// Driver's `target` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn target_callback(
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn target_callback(
         ptr: *mut bindings::cpufreq_policy,
         target_freq: u32,
         relation: u32,
···
 
     /// Driver's `target_index` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn target_index_callback(
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn target_index_callback(
         ptr: *mut bindings::cpufreq_policy,
         index: u32,
     ) -> kernel::ffi::c_int {
···
 
     /// Driver's `fast_switch` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn fast_switch_callback(
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn fast_switch_callback(
         ptr: *mut bindings::cpufreq_policy,
         target_freq: u32,
     ) -> kernel::ffi::c_uint {
···
     }
 
     /// Driver's `adjust_perf` callback.
-    extern "C" fn adjust_perf_callback(
+    ///
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    unsafe extern "C" fn adjust_perf_callback(
         cpu: u32,
         min_perf: usize,
         target_perf: usize,
         capacity: usize,
     ) {
-        if let Ok(mut policy) = PolicyCpu::from_cpu(cpu) {
+        // SAFETY: The C API guarantees that `cpu` refers to a valid CPU number.
+        let cpu_id = unsafe { CpuId::from_u32_unchecked(cpu) };
+
+        if let Ok(mut policy) = PolicyCpu::from_cpu(cpu_id) {
             T::adjust_perf(&mut policy, min_perf, target_perf, capacity);
         }
     }
 
     /// Driver's `get_intermediate` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn get_intermediate_callback(
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn get_intermediate_callback(
         ptr: *mut bindings::cpufreq_policy,
         index: u32,
     ) -> kernel::ffi::c_uint {
···
 
     /// Driver's `target_intermediate` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn target_intermediate_callback(
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn target_intermediate_callback(
         ptr: *mut bindings::cpufreq_policy,
         index: u32,
     ) -> kernel::ffi::c_int {
···
     }
 
     /// Driver's `get` callback.
-    extern "C" fn get_callback(cpu: u32) -> kernel::ffi::c_uint {
-        PolicyCpu::from_cpu(cpu).map_or(0, |mut policy| T::get(&mut policy).map_or(0, |f| f))
+    ///
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    unsafe extern "C" fn get_callback(cpu: u32) -> kernel::ffi::c_uint {
+        // SAFETY: The C API guarantees that `cpu` refers to a valid CPU number.
+        let cpu_id = unsafe { CpuId::from_u32_unchecked(cpu) };
+
+        PolicyCpu::from_cpu(cpu_id).map_or(0, |mut policy| T::get(&mut policy).map_or(0, |f| f))
     }
 
     /// Driver's `update_limit` callback.
-    extern "C" fn update_limits_callback(ptr: *mut bindings::cpufreq_policy) {
+    ///
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn update_limits_callback(ptr: *mut bindings::cpufreq_policy) {
         // SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
         // lifetime of `policy`.
         let policy = unsafe { Policy::from_raw_mut(ptr) };
···
 
     /// Driver's `bios_limit` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn bios_limit_callback(cpu: i32, limit: *mut u32) -> kernel::ffi::c_int {
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn bios_limit_callback(cpu: i32, limit: *mut u32) -> kernel::ffi::c_int {
+        // SAFETY: The C API guarantees that `cpu` refers to a valid CPU number.
+        let cpu_id = unsafe { CpuId::from_i32_unchecked(cpu) };
+
         from_result(|| {
-            let mut policy = PolicyCpu::from_cpu(cpu as u32)?;
+            let mut policy = PolicyCpu::from_cpu(cpu_id)?;
 
             // SAFETY: `limit` is guaranteed by the C code to be valid.
             T::bios_limit(&mut policy, &mut (unsafe { *limit })).map(|()| 0)
···
 
     /// Driver's `set_boost` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn set_boost_callback(
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn set_boost_callback(
         ptr: *mut bindings::cpufreq_policy,
         state: i32,
     ) -> kernel::ffi::c_int {
···
 
     /// Driver's `register_em` callback.
     ///
-    /// SAFETY: Called from C. Inputs must be valid pointers.
-    extern "C" fn register_em_callback(ptr: *mut bindings::cpufreq_policy) {
+    /// # Safety
+    ///
+    /// - This function may only be called from the cpufreq C infrastructure.
+    /// - The pointer arguments must be valid pointers.
+    unsafe extern "C" fn register_em_callback(ptr: *mut bindings::cpufreq_policy) {
         // SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
         // lifetime of `policy`.
         let policy = unsafe { Policy::from_raw_mut(ptr) };

rust/kernel/cpumask.rs

···
 
 use crate::{
     alloc::{AllocError, Flags},
+    cpu::CpuId,
     prelude::*,
     types::Opaque,
 };
···
 ///
 /// ```
 /// use kernel::bindings;
+/// use kernel::cpu::CpuId;
 /// use kernel::cpumask::Cpumask;
 ///
-/// fn set_clear_cpu(ptr: *mut bindings::cpumask, set_cpu: u32, clear_cpu: i32) {
+/// fn set_clear_cpu(ptr: *mut bindings::cpumask, set_cpu: CpuId, clear_cpu: CpuId) {
 ///     // SAFETY: The `ptr` is valid for writing and remains valid for the lifetime of the
 ///     // returned reference.
 ///     let mask = unsafe { Cpumask::as_mut_ref(ptr) };
···
     /// This mismatches kernel naming convention and corresponds to the C
     /// function `__cpumask_set_cpu()`.
     #[inline]
-    pub fn set(&mut self, cpu: u32) {
+    pub fn set(&mut self, cpu: CpuId) {
         // SAFETY: By the type invariant, `self.as_raw` is a valid argument to `__cpumask_set_cpu`.
-        unsafe { bindings::__cpumask_set_cpu(cpu, self.as_raw()) };
+        unsafe { bindings::__cpumask_set_cpu(u32::from(cpu), self.as_raw()) };
     }
 
     /// Clear `cpu` in the cpumask.
···
     /// This mismatches kernel naming convention and corresponds to the C
     /// function `__cpumask_clear_cpu()`.
     #[inline]
-    pub fn clear(&mut self, cpu: i32) {
+    pub fn clear(&mut self, cpu: CpuId) {
         // SAFETY: By the type invariant, `self.as_raw` is a valid argument to
         // `__cpumask_clear_cpu`.
-        unsafe { bindings::__cpumask_clear_cpu(cpu, self.as_raw()) };
+        unsafe { bindings::__cpumask_clear_cpu(i32::from(cpu), self.as_raw()) };
     }
 
     /// Test `cpu` in the cpumask.
     ///
     /// Equivalent to the kernel's `cpumask_test_cpu` API.
     #[inline]
-    pub fn test(&self, cpu: i32) -> bool {
+    pub fn test(&self, cpu: CpuId) -> bool {
         // SAFETY: By the type invariant, `self.as_raw` is a valid argument to `cpumask_test_cpu`.
-        unsafe { bindings::cpumask_test_cpu(cpu, self.as_raw()) }
+        unsafe { bindings::cpumask_test_cpu(i32::from(cpu), self.as_raw()) }
     }
 
     /// Set all CPUs in the cpumask.
···
 /// The following example demonstrates how to create and update a [`CpumaskVar`].
 ///
 /// ```
+/// use kernel::cpu::CpuId;
 /// use kernel::cpumask::CpumaskVar;
 ///
 /// let mut mask = CpumaskVar::new_zero(GFP_KERNEL).unwrap();
 ///
 /// assert!(mask.empty());
-/// mask.set(2);
-/// assert!(mask.test(2));
-/// mask.set(3);
-/// assert!(mask.test(3));
-/// assert_eq!(mask.weight(), 2);
+/// let mut count = 0;
+///
+/// let cpu2 = CpuId::from_u32(2);
+/// if let Some(cpu) = cpu2 {
+///     mask.set(cpu);
+///     assert!(mask.test(cpu));
+///     count += 1;
+/// }
+///
+/// let cpu3 = CpuId::from_u32(3);
+/// if let Some(cpu) = cpu3 {
+///     mask.set(cpu);
+///     assert!(mask.test(cpu));
+///     count += 1;
+/// }
+///
+/// assert_eq!(mask.weight(), count);
 ///
 /// let mask2 = CpumaskVar::try_clone(&mask).unwrap();
-/// assert!(mask2.test(2));
-/// assert!(mask2.test(3));
-/// assert_eq!(mask2.weight(), 2);
+///
+/// if let Some(cpu) = cpu2 {
+///     assert!(mask2.test(cpu));
+/// }
+///
+/// if let Some(cpu) = cpu3 {
+///     assert!(mask2.test(cpu));
+/// }
+/// assert_eq!(mask2.weight(), count);
 /// ```
 pub struct CpumaskVar {
     #[cfg(CONFIG_CPUMASK_OFFSTACK)]

rust/kernel/devres.rs

···
     error::{Error, Result},
     ffi::c_void,
     prelude::*,
-    revocable::Revocable,
-    sync::Arc,
+    revocable::{Revocable, RevocableGuard},
+    sync::{rcu, Arc, Completion},
     types::ARef,
 };
-
-use core::ops::Deref;
 
 #[pin_data]
 struct DevresInner<T> {
···
     callback: unsafe extern "C" fn(*mut c_void),
     #[pin]
     data: Revocable<T>,
+    #[pin]
+    revoke: Completion,
 }
 
 /// This abstraction is meant to be used by subsystems to containerize [`Device`] bound resources to
 /// manage their lifetime.
 ///
 /// [`Device`] bound resources should be freed when either the resource goes out of scope or the
-/// [`Device`] is unbound respectively, depending on what happens first.
+/// [`Device`] is unbound respectively, depending on what happens first. In any case, it is always
+/// guaranteed that revoking the device resource is completed before the corresponding [`Device`]
+/// is unbound.
 ///
 /// To achieve that [`Devres`] registers a devres callback on creation, which is called once the
 /// [`Device`] is unbound, revoking access to the encapsulated resource (see also [`Revocable`]).
···
                 dev: dev.into(),
                 callback: Self::devres_callback,
                 data <- Revocable::new(data),
+                revoke <- Completion::new(),
             }),
             flags,
         )?;
···
         self as _
     }
 
-    fn remove_action(this: &Arc<Self>) {
+    fn remove_action(this: &Arc<Self>) -> bool {
         // SAFETY:
         // - `self.inner.dev` is a valid `Device`,
         // - the `action` and `data` pointers are the exact same ones as given to devm_add_action()
         //   previously,
         // - `self` is always valid, even if the action has been released already.
-        let ret = unsafe {
+        let success = unsafe {
             bindings::devm_remove_action_nowarn(
                 this.dev.as_raw(),
                 Some(this.callback),
                 this.as_ptr() as _,
             )
-        };
+        } == 0;
 
-        if ret == 0 {
+        if success {
             // SAFETY: We leaked an `Arc` reference to devm_add_action() in `DevresInner::new`; if
             // devm_remove_action_nowarn() was successful we can (and have to) claim back ownership
             // of this reference.
             let _ = unsafe { Arc::from_raw(this.as_ptr()) };
         }
+
+        success
     }
 
     #[allow(clippy::missing_safety_doc)]
···
         //         `DevresInner::new`.
         let inner = unsafe { Arc::from_raw(ptr) };
 
-        inner.data.revoke();
+        if !inner.data.revoke() {
+            // If `revoke()` returns false, it means that `Devres::drop` already started revoking
+            // `inner.data` for us. Hence we have to wait until `Devres::drop()` signals that it
+            // completed revoking `inner.data`.
+            inner.revoke.wait_for_completion();
+        }
     }
 }
 
···
         // SAFETY: `dev` being the same device as the device this `Devres` has been created for
         // proves that `self.0.data` hasn't been revoked and is guaranteed to not be revoked as
         // long as `dev` lives; `dev` lives at least as long as `self`.
-        Ok(unsafe { self.deref().access() })
+        Ok(unsafe { self.0.data.access() })
     }
-}
 
-impl<T> Deref for Devres<T> {
-    type Target = Revocable<T>;
+    /// [`Devres`] accessor for [`Revocable::try_access`].
+    pub fn try_access(&self) -> Option<RevocableGuard<'_, T>> {
+        self.0.data.try_access()
+    }
 
-    fn deref(&self) -> &Self::Target {
-        &self.0.data
+    /// [`Devres`] accessor for [`Revocable::try_access_with`].
+    pub fn try_access_with<R, F: FnOnce(&T) -> R>(&self, f: F) -> Option<R> {
+        self.0.data.try_access_with(f)
+    }
+
+    /// [`Devres`] accessor for [`Revocable::try_access_with_guard`].
+    pub fn try_access_with_guard<'a>(&'a self, guard: &'a rcu::Guard) -> Option<&'a T> {
+        self.0.data.try_access_with_guard(guard)
     }
 }
 
 impl<T> Drop for Devres<T> {
     fn drop(&mut self) {
-        DevresInner::remove_action(&self.0);
+        // SAFETY: When `drop` runs, it is guaranteed that nobody is accessing the revocable data
+        // anymore, hence it is safe not to wait for the grace period to finish.
+        if unsafe { self.0.data.revoke_nosync() } {
+            // We revoked `self.0.data` before the devres action did, hence try to remove it.
+            if !DevresInner::remove_action(&self.0) {
+                // We could not remove the devres action, which means that it now runs concurrently,
+                // hence signal that `self.0.data` has been revoked successfully.
+                self.0.revoke.complete_all();
+            }
+        }
     }
 }

rust/kernel/revocable.rs

···
     /// # Safety
     ///
     /// Callers must ensure that there are no more concurrent users of the revocable object.
-    unsafe fn revoke_internal<const SYNC: bool>(&self) {
-        if self.is_available.swap(false, Ordering::Relaxed) {
+    unsafe fn revoke_internal<const SYNC: bool>(&self) -> bool {
+        let revoke = self.is_available.swap(false, Ordering::Relaxed);
+
+        if revoke {
             if SYNC {
                 // SAFETY: Just an FFI call, there are no further requirements.
                 unsafe { bindings::synchronize_rcu() };
···
             // `compare_exchange` above that takes `is_available` from `true` to `false`.
             unsafe { drop_in_place(self.data.get()) };
         }
+
+        revoke
     }
 
     /// Revokes access to and drops the wrapped object.
···
     /// Access to the object is revoked immediately to new callers of [`Revocable::try_access`],
     /// expecting that there are no concurrent users of the object.
     ///
+    /// Returns `true` if `&self` has been revoked with this call, `false` if it was revoked
+    /// already.
+    ///
     /// # Safety
     ///
     /// Callers must ensure that there are no more concurrent users of the revocable object.
-    pub unsafe fn revoke_nosync(&self) {
+    pub unsafe fn revoke_nosync(&self) -> bool {
         // SAFETY: By the safety requirement of this function, the caller ensures that nobody is
         // accessing the data anymore and hence we don't have to wait for the grace period to
         // finish.
···
     /// If there are concurrent users of the object (i.e., ones that called
     /// [`Revocable::try_access`] beforehand and still haven't dropped the returned guard), this
     /// function waits for the concurrent access to complete before dropping the wrapped object.
-    pub fn revoke(&self) {
+    ///
+    /// Returns `true` if `&self` has been revoked with this call, `false` if it was revoked
+    /// already.
+    pub fn revoke(&self) -> bool {
         // SAFETY: By passing `true` we ask `revoke_internal` to wait for the grace period to
         // finish.
         unsafe { self.revoke_internal::<true>() }

rust/kernel/sync.rs

···
 use pin_init;
 
 mod arc;
+pub mod completion;
 mod condvar;
 pub mod lock;
 mod locked_by;
···
 pub mod rcu;
 
 pub use arc::{Arc, ArcBorrow, UniqueArc};
+pub use completion::Completion;
 pub use condvar::{new_condvar, CondVar, CondVarTimeoutResult};
 pub use lock::global::{global_lock, GlobalGuard, GlobalLock, GlobalLockBackend, GlobalLockedBy};
 pub use lock::mutex::{new_mutex, Mutex, MutexGuard};

rust/kernel/sync/completion.rs

···
+// SPDX-License-Identifier: GPL-2.0
+
+//! Completion support.
+//!
+//! Reference: <https://docs.kernel.org/scheduler/completion.html>
+//!
+//! C header: [`include/linux/completion.h`](srctree/include/linux/completion.h)
+
+use crate::{bindings, prelude::*, types::Opaque};
+
+/// Synchronization primitive to signal when a certain task has been completed.
+///
+/// The [`Completion`] synchronization primitive signals when a certain task has been completed by
+/// waking up other tasks that have been queued up to wait for the [`Completion`] to be completed.
+///
+/// # Examples
+///
+/// ```
+/// use kernel::sync::{Arc, Completion};
+/// use kernel::workqueue::{self, impl_has_work, new_work, Work, WorkItem};
+///
+/// #[pin_data]
+/// struct MyTask {
+///     #[pin]
+///     work: Work<MyTask>,
+///     #[pin]
+///     done: Completion,
+/// }
+///
+/// impl_has_work! {
+///     impl HasWork<Self> for MyTask { self.work }
+/// }
+///
+/// impl MyTask {
+///     fn new() -> Result<Arc<Self>> {
+///         let this = Arc::pin_init(pin_init!(MyTask {
+///             work <- new_work!("MyTask::work"),
+///             done <- Completion::new(),
+///         }), GFP_KERNEL)?;
+///
+///         let _ = workqueue::system().enqueue(this.clone());
+///
+///         Ok(this)
+///     }
+///
+///     fn wait_for_completion(&self) {
+///         self.done.wait_for_completion();
+///
+///         pr_info!("Completion: task complete\n");
+///     }
+/// }
+///
+/// impl WorkItem for MyTask {
+///     type Pointer = Arc<MyTask>;
+///
+///     fn run(this: Arc<MyTask>) {
+///         // process this task
+///         this.done.complete_all();
+///     }
+/// }
+///
+/// let task = MyTask::new()?;
+/// task.wait_for_completion();
+/// # Ok::<(), Error>(())
+/// ```
+#[pin_data]
+pub struct Completion {
+    #[pin]
+    inner: Opaque<bindings::completion>,
+}
+
+// SAFETY: `Completion` is safe to be send to any task.
+unsafe impl Send for Completion {}
+
+// SAFETY: `Completion` is safe to be accessed concurrently.
+unsafe impl Sync for Completion {}
+
+impl Completion {
+    /// Create an initializer for a new [`Completion`].
+    pub fn new() -> impl PinInit<Self> {
+        pin_init!(Self {
+            inner <- Opaque::ffi_init(|slot: *mut bindings::completion| {
+                // SAFETY: `slot` is a valid pointer to an uninitialized `struct completion`.
+                unsafe { bindings::init_completion(slot) };
+            }),
+        })
+    }
+
+    fn as_raw(&self) -> *mut bindings::completion {
+        self.inner.get()
+    }
+
+    /// Signal all tasks waiting on this completion.
+    ///
+    /// This method wakes up all tasks waiting on this completion; after this operation the
+    /// completion is permanently done, i.e. signals all current and future waiters.
+    pub fn complete_all(&self) {
+        // SAFETY: `self.as_raw()` is a pointer to a valid `struct completion`.
+        unsafe { bindings::complete_all(self.as_raw()) };
+    }
+
+    /// Wait for completion of a task.
+    ///
+    /// This method waits for the completion of a task; it is not interruptible and there is no
+    /// timeout.
+    ///
+    /// See also [`Completion::complete_all`].
+    pub fn wait_for_completion(&self) {
+        // SAFETY: `self.as_raw()` is a pointer to a valid `struct completion`.
+        unsafe { bindings::wait_for_completion(self.as_raw()) };
+    }
+}

rust/kernel/time/hrtimer.rs

···
             ) -> *mut Self {
                 // SAFETY: As per the safety requirement of this function, `ptr`
                 // is pointing inside a `$timer_type`.
-                unsafe { ::kernel::container_of!(ptr, $timer_type, $field).cast_mut() }
+                unsafe { ::kernel::container_of!(ptr, $timer_type, $field) }
             }
         }
     }

scripts/gendwarfksyms/gendwarfksyms.h

···
 void cache_init(struct cache *cache);
 void cache_free(struct cache *cache);
 
-static inline void __cache_mark_expanded(struct cache *cache, uintptr_t addr)
-{
-	cache_set(cache, addr, 1);
-}
-
-static inline bool __cache_was_expanded(struct cache *cache, uintptr_t addr)
-{
-	return cache_get(cache, addr) == 1;
-}
-
 static inline void cache_mark_expanded(struct cache *cache, void *addr)
 {
-	__cache_mark_expanded(cache, (uintptr_t)addr);
+	cache_set(cache, (unsigned long)addr, 1);
 }
 
 static inline bool cache_was_expanded(struct cache *cache, void *addr)
 {
-	return __cache_was_expanded(cache, (uintptr_t)addr);
+	return cache_get(cache, (unsigned long)addr) == 1;
 }
 
 /*

scripts/gendwarfksyms/types.c

···
 	cache_free(&expansion_cache);
 }
 
-static void __type_expand(struct die *cache, struct type_expansion *type,
-			  bool recursive);
-
-static void type_expand_child(struct die *cache, struct type_expansion *type,
-			      bool recursive)
-{
-	struct type_expansion child;
-	char *name;
-
-	name = get_type_name(cache);
-	if (!name) {
-		__type_expand(cache, type, recursive);
-		return;
-	}
-
-	if (recursive && !__cache_was_expanded(&expansion_cache, cache->addr)) {
-		__cache_mark_expanded(&expansion_cache, cache->addr);
-		type_expansion_init(&child);
-		__type_expand(cache, &child, true);
-		type_map_add(name, &child);
-		type_expansion_free(&child);
-	}
-
-	type_expansion_append(type, name, name);
-}
-
-static void __type_expand(struct die *cache, struct type_expansion *type,
-			  bool recursive)
+static void __type_expand(struct die *cache, struct type_expansion *type)
 {
 	struct die_fragment *df;
 	struct die *child;
+	char *name;
 
 	list_for_each_entry(df, &cache->fragments, list) {
 		switch (df->type) {
···
 				error("unknown child: %" PRIxPTR,
 				      df->data.addr);
 
-			type_expand_child(child, type, recursive);
+			name = get_type_name(child);
+			if (name)
+				type_expansion_append(type, name, name);
+			else
+				__type_expand(child, type);
+
 			break;
 		case FRAGMENT_LINEBREAK:
 			/*
···
 	}
 }
 
-static void type_expand(struct die *cache, struct type_expansion *type,
-			bool recursive)
+static void type_expand(const char *name, struct die *cache,
+			struct type_expansion *type)
 {
+	const char *override;
+
 	type_expansion_init(type);
-	__type_expand(cache, type, recursive);
-	cache_free(&expansion_cache);
+
+	if (stable && kabi_get_type_string(name, &override))
+		type_parse(name, override, type);
+	else
+		__type_expand(cache, type);
 }
 
 static void type_parse(const char *name, const char *str,
···
 
 	if (!*str)
 		error("empty type string override for '%s'", name);
-
-	type_expansion_init(type);
 
 	for (pos = 0; str[pos]; ++pos) {
 		bool empty;
···
 static void expand_type(struct die *cache, void *arg)
 {
 	struct type_expansion type;
-	const char *override;
 	char *name;
 
 	if (cache->mapped)
···
 
 	debug("%s", name);
 
-	if (stable && kabi_get_type_string(name, &override))
-		type_parse(name, override, &type);
-	else
-		type_expand(cache, &type, true);
-
+	type_expand(name, cache, &type);
 	type_map_add(name, &type);
 	type_expansion_free(&type);
 	free(name);
···
 {
 	struct type_expansion type;
 	struct version version;
-	const char *override;
 	struct die *cache;
 
 	/*
···
 	if (__die_map_get(sym->die_addr, DIE_SYMBOL, &cache))
 		return; /* We'll warn about missing CRCs later. */
 
-	if (stable && kabi_get_type_string(sym->name, &override))
-		type_parse(sym->name, override, &type);
-	else
-		type_expand(cache, &type, false);
+	type_expand(sym->name, cache, &type);
 
 	/* If the symbol already has a version, don't calculate it again. */
 	if (sym->state != SYMBOL_PROCESSED) {

scripts/misc-check

···
 	xargs -r printf "%s: warning: EXPORT_SYMBOL() is not used, but #include <linux/export.h> is present\n" >&2
 }
 
-check_tracked_ignored_files
-check_missing_include_linux_export_h
-check_unnecessary_include_linux_export_h
+case "${KBUILD_EXTRA_WARN}" in
+*1*)
+	check_tracked_ignored_files
+	;;
+esac
+
+case "${KBUILD_EXTRA_WARN}" in
+*2*)
+	check_missing_include_linux_export_h
+	check_unnecessary_include_linux_export_h
+	;;
+esac

security/selinux/xfrm.c

···
 
 	ctx->ctx_doi = XFRM_SC_DOI_LSM;
 	ctx->ctx_alg = XFRM_SC_ALG_SELINUX;
-	ctx->ctx_len = str_len;
+	ctx->ctx_len = str_len + 1;
 	memcpy(ctx->ctx_str, &uctx[1], str_len);
 	ctx->ctx_str[str_len] = '\0';
 	rc = security_context_to_sid(ctx->ctx_str, str_len,

tools/net/ynl/pyynl/lib/ynl.py

···
                     self.extack['unknown'].append(extack)
 
             if attr_space:
-                # We don't have the ability to parse nests yet, so only do global
-                if 'miss-type' in self.extack and 'miss-nest' not in self.extack:
-                    miss_type = self.extack['miss-type']
-                    if miss_type in attr_space.attrs_by_val:
-                        spec = attr_space.attrs_by_val[miss_type]
-                        self.extack['miss-type'] = spec['name']
-                        if 'doc' in spec:
-                            self.extack['miss-type-doc'] = spec['doc']
+                self.annotate_extack(attr_space)
 
     def _decode_policy(self, raw):
         policy = {}
···
                 policy['mask'] = attr.as_scalar('u64')
         return policy
 
+    def annotate_extack(self, attr_space):
+        """ Make extack more human friendly with attribute information """
+
+        # We don't have the ability to parse nests yet, so only do global
+        if 'miss-type' in self.extack and 'miss-nest' not in self.extack:
+            miss_type = self.extack['miss-type']
+            if miss_type in attr_space.attrs_by_val:
+                spec = attr_space.attrs_by_val[miss_type]
+                self.extack['miss-type'] = spec['name']
+                if 'doc' in spec:
+                    self.extack['miss-type-doc'] = spec['doc']
+
     def cmd(self):
         return self.nl_type
 
···
 
 
 class NlMsgs:
-    def __init__(self, data, attr_space=None):
+    def __init__(self, data):
         self.msgs = []
 
         offset = 0
         while offset < len(data):
-            msg = NlMsg(data, offset, attr_space=attr_space)
+            msg = NlMsg(data, offset)
             offset += msg.nl_len
             self.msgs.append(msg)
 
···
         op_rsp = []
         while not done:
             reply = self.sock.recv(self._recv_size)
-            nms = NlMsgs(reply, attr_space=op.attr_set)
+            nms = NlMsgs(reply)
             self._recv_dbg_print(reply, nms)
             for nl_msg in nms:
                 if nl_msg.nl_seq in reqs_by_seq:
                     (op, vals, req_msg, req_flags) = reqs_by_seq[nl_msg.nl_seq]
                     if nl_msg.extack:
+                        nl_msg.annotate_extack(op.attr_set)
                         self._decode_extack(req_msg, op, nl_msg.extack, vals)
                 else:
                     op = None

tools/power/cpupower/Makefile

···
 mandir ?=	/usr/man
 libdir ?=	/usr/lib
 libexecdir ?=	/usr/libexec
+unitdir ?=	/usr/lib/systemd/system
 includedir ?=	/usr/include
 localedir ?=	/usr/share/locale
 docdir ?=       /usr/share/doc/packages/cpupower
···
 	$(INSTALL_DATA) cpupower-service.conf '$(DESTDIR)${confdir}'
 	$(INSTALL) -d $(DESTDIR)${libexecdir}
 	$(INSTALL_PROGRAM) cpupower.sh '$(DESTDIR)${libexecdir}/cpupower'
-	$(INSTALL) -d $(DESTDIR)${libdir}/systemd/system
-	sed 's|___CDIR___|${confdir}|; s|___LDIR___|${libexecdir}|' cpupower.service.in > '$(DESTDIR)${libdir}/systemd/system/cpupower.service'
-	$(SETPERM_DATA) '$(DESTDIR)${libdir}/systemd/system/cpupower.service'
+	$(INSTALL) -d $(DESTDIR)${unitdir}
+	sed 's|___CDIR___|${confdir}|; s|___LDIR___|${libexecdir}|' cpupower.service.in > '$(DESTDIR)${unitdir}/cpupower.service'
+	$(SETPERM_DATA) '$(DESTDIR)${unitdir}/cpupower.service'
 
 install-man:
 	$(INSTALL_DATA) -D man/cpupower.1 $(DESTDIR)${mandir}/man1/cpupower.1
···
 	- rm -f $(DESTDIR)${bindir}/utils/cpupower
 	- rm -f $(DESTDIR)${confdir}cpupower-service.conf
 	- rm -f $(DESTDIR)${libexecdir}/cpupower
-	- rm -f $(DESTDIR)${libdir}/systemd/system/cpupower.service
+	- rm -f $(DESTDIR)${unitdir}/cpupower.service
 	- rm -f $(DESTDIR)${mandir}/man1/cpupower.1
 	- rm -f $(DESTDIR)${mandir}/man1/cpupower-frequency-set.1
 	- rm -f $(DESTDIR)${mandir}/man1/cpupower-frequency-info.1

tools/testing/selftests/drivers/net/netdevsim/peer.sh

···
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0-only
 
-source ../../../net/lib.sh
+lib_dir=$(dirname $0)/../../../net
+source $lib_dir/lib.sh
 
 NSIM_DEV_1_ID=$((256 + RANDOM % 256))
 NSIM_DEV_1_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_DEV_1_ID

tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c

···
 #include "gic.h"
 #include "vgic.h"
 
-static const uint64_t CVAL_MAX = ~0ULL;
+/* Depends on counter width. */
+static uint64_t CVAL_MAX;
 /* tval is a signed 32-bit int. */
 static const int32_t TVAL_MAX = INT32_MAX;
 static const int32_t TVAL_MIN = INT32_MIN;
···
 /* After how much time we say there is no IRQ. */
 static const uint32_t TIMEOUT_NO_IRQ_US = 50000;
 
-/* A nice counter value to use as the starting one for most tests. */
-static const uint64_t DEF_CNT = (CVAL_MAX / 2);
+/* Counter value to use as the starting one for most tests. Set to CVAL_MAX/2 */
+static uint64_t DEF_CNT;
 
 /* Number of runs. */
 static const uint32_t NR_TEST_ITERS_DEF = 5;
···
 {
 	atomic_set(&shared_data.handled, 0);
 	atomic_set(&shared_data.spurious, 0);
-	timer_set_ctl(timer, ctl);
 	timer_set_tval(timer, tval_cycles);
+	timer_set_ctl(timer, ctl);
 }
 
 static void set_xval_irq(enum arch_timer timer, uint64_t xval, uint32_t ctl,
···
 		test_set_cnt_after_tval(timer, 0, tval, (uint64_t) tval + 1,
 					wm);
 	}
-
-	for (i = 0; i < ARRAY_SIZE(sleep_method); i++) {
-		sleep_method_t sm = sleep_method[i];
-
-		test_set_cnt_after_cval_no_irq(timer, 0, DEF_CNT, CVAL_MAX, sm);
-	}
 }
 
 /*
···
 	GUEST_DONE();
 }
 
+static cpu_set_t default_cpuset;
+
 static uint32_t next_pcpu(void)
 {
 	uint32_t max = get_nprocs();
 	uint32_t cur = sched_getcpu();
 	uint32_t next = cur;
-	cpu_set_t cpuset;
+	cpu_set_t cpuset = default_cpuset;
 
 	TEST_ASSERT(max > 1, "Need at least two physical cpus");
-
-	sched_getaffinity(0, sizeof(cpuset), &cpuset);
 
 	do {
 		next = (next + 1) % CPU_SETSIZE;
···
 	test_init_timer_irq(*vm, *vcpu);
 	vgic_v3_setup(*vm, 1, 64);
 	sync_global_to_guest(*vm, test_args);
+	sync_global_to_guest(*vm, CVAL_MAX);
+	sync_global_to_guest(*vm, DEF_CNT);
 }
 
 static void test_print_help(char *name)
···
 	pr_info("\t-b: Test both physical and virtual timers (default: true)\n");
 	pr_info("\t-l: Delta (in ms) used for long wait time test (default: %u)\n",
 	     LONG_WAIT_TEST_MS);
-	pr_info("\t-l: Delta (in ms) used for wait times (default: %u)\n",
+	pr_info("\t-w: Delta (in ms) used for wait times (default: %u)\n",
 		WAIT_TEST_MS);
 	pr_info("\t-p: Test physical timer (default: true)\n");
 	pr_info("\t-v: Test virtual timer (default: true)\n");
···
 	return false;
 }
 
+static void set_counter_defaults(void)
+{
+	const uint64_t MIN_ROLLOVER_SECS = 40ULL * 365 * 24 * 3600;
+	uint64_t freq = read_sysreg(CNTFRQ_EL0);
+	uint64_t width = ilog2(MIN_ROLLOVER_SECS * freq);
+
+	width = clamp(width, 56, 64);
+	CVAL_MAX = GENMASK_ULL(width - 1, 0);
+	DEF_CNT = CVAL_MAX / 2;
+}
+
 int main(int argc, char *argv[])
 {
 	struct kvm_vcpu *vcpu;
···
 
 	if (!parse_args(argc, argv))
 		exit(KSFT_SKIP);
+
+	sched_getaffinity(0, sizeof(default_cpuset), &default_cpuset);
+	set_counter_defaults();
 
 	if (test_args.test_virtual) {
 		test_vm_create(&vm, &vcpu, VIRTUAL);

tools/testing/selftests/mm/gup_longterm.c

···
 	log_test_start("%s ... with memfd", desc);
 
 	fd = memfd_create("test", 0);
-	if (fd < 0)
+	if (fd < 0) {
 		ksft_print_msg("memfd_create() failed (%s)\n", strerror(errno));
+		log_test_result(KSFT_SKIP);
+		return;
+	}
 
 	fn(fd, pagesize);
 	close(fd);
···
 	fd = memfd_create("test", flags);
 	if (fd < 0) {
 		ksft_print_msg("memfd_create() failed (%s)\n", strerror(errno));
+		log_test_result(KSFT_SKIP);
+		return;
 	}
 
 	fn(fd, hugetlbsize);

tools/testing/selftests/net/.gitignore

···
 tcp_fastopen_backup_key
 tcp_inq
 tcp_mmap
+tfo
 timestamping
 tls
 toeplitz

tools/testing/selftests/net/Makefile

···
 TEST_PROGS += lwt_dst_cache_ref_loop.sh
 TEST_PROGS += skf_net_off.sh
 TEST_GEN_FILES += skf_net_off
+TEST_GEN_FILES += tfo
+TEST_PROGS += tfo_passive.sh
 
 # YNL files, must be before "include ..lib.mk"
 YNL_GEN_FILES := busy_poller netlink-dumps

tools/testing/selftests/net/tfo.c

···
+// SPDX-License-Identifier: GPL-2.0
+#include <error.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <arpa/inet.h>
+#include <sys/socket.h>
+#include <netinet/tcp.h>
+#include <errno.h>
+
+static int cfg_server;
+static int cfg_client;
+static int cfg_port = 8000;
+static struct sockaddr_in6 cfg_addr;
+static char *cfg_outfile;
+
+static int parse_address(const char *str, int port, struct sockaddr_in6 *sin6)
+{
+	int ret;
+
+	sin6->sin6_family = AF_INET6;
+	sin6->sin6_port = htons(port);
+
+	ret = inet_pton(sin6->sin6_family, str, &sin6->sin6_addr);
+	if (ret != 1) {
+		/* fallback to plain IPv4 */
+		ret = inet_pton(AF_INET, str, &sin6->sin6_addr.s6_addr32[3]);
+		if (ret != 1)
+			return -1;
+
+		/* add ::ffff prefix */
+		sin6->sin6_addr.s6_addr32[0] = 0;
+		sin6->sin6_addr.s6_addr32[1] = 0;
+		sin6->sin6_addr.s6_addr16[4] = 0;
+		sin6->sin6_addr.s6_addr16[5] = 0xffff;
+	}
+
+	return 0;
+}
+
+static void run_server(void)
+{
+	unsigned long qlen = 32;
+	int fd, opt, connfd;
+	socklen_t len;
+	char buf[64];
+	FILE *outfile;
+
+	outfile = fopen(cfg_outfile, "w");
+	if (!outfile)
+		error(1, errno, "fopen() outfile");
+
+	fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (fd == -1)
+		error(1, errno, "socket()");
+
+	opt = 1;
+	if (setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &opt, sizeof(opt)) < 0)
+		error(1, errno, "setsockopt(SO_REUSEADDR)");
+
+	if (setsockopt(fd, SOL_TCP, TCP_FASTOPEN, &qlen, sizeof(qlen)) < 0)
+		error(1, errno, "setsockopt(TCP_FASTOPEN)");
+
+	if (bind(fd, (struct sockaddr *)&cfg_addr, sizeof(cfg_addr)) < 0)
+		error(1, errno, "bind()");
+
+	if (listen(fd, 5) < 0)
+		error(1, errno, "listen()");
+
+	len = sizeof(cfg_addr);
+	connfd = accept(fd, (struct sockaddr *)&cfg_addr, &len);
+	if (connfd < 0)
+		error(1, errno, "accept()");
+
+	len = sizeof(opt);
+	if (getsockopt(connfd, SOL_SOCKET, SO_INCOMING_NAPI_ID, &opt, &len) < 0)
+		error(1, errno, "getsockopt(SO_INCOMING_NAPI_ID)");
+
+	read(connfd, buf, 64);
+	fprintf(outfile, "%d\n", opt);
+
+	fclose(outfile);
+	close(connfd);
+	close(fd);
+}
+
+static void run_client(void)
+{
+	int fd;
+	char *msg = "Hello, world!";
+
+	fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (fd == -1)
+		error(1, errno, "socket()");
+
+	sendto(fd, msg, strlen(msg), MSG_FASTOPEN, (struct sockaddr *)&cfg_addr, sizeof(cfg_addr));
+
+	close(fd);
+}
+
+static void usage(const char *filepath)
+{
+	error(1, 0, "Usage: %s (-s|-c) -h<server_ip> -p<port> -o<outfile> ", filepath);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+	struct sockaddr_in6 *addr6 = (void *) &cfg_addr;
+	char *addr = NULL;
+	int ret;
+	int c;
+
+	if (argc <= 1)
+		usage(argv[0]);
+
+	while ((c = getopt(argc, argv, "sch:p:o:")) != -1) {
+		switch (c) {
+		case 's':
+			if (cfg_client)
+				error(1, 0, "Pass one of -s or -c");
+			cfg_server = 1;
+			break;
+		case 'c':
+			if (cfg_server)
+				error(1, 0, "Pass one of -s or -c");
+			cfg_client = 1;
+			break;
+		case 'h':
+			addr = optarg;
+			break;
+		case 'p':
+			cfg_port = strtoul(optarg, NULL, 0);
+			break;
+		case 'o':
+			cfg_outfile = strdup(optarg);
+			if (!cfg_outfile)
+				error(1, 0, "outfile invalid");
+			break;
+		}
+	}
+
+	if (cfg_server && addr)
+		error(1, 0, "Server cannot have -h specified");
+
+	memset(addr6, 0, sizeof(*addr6));
+	addr6->sin6_family = AF_INET6;
+	addr6->sin6_port = htons(cfg_port);
+	addr6->sin6_addr = in6addr_any;
+	if (addr) {
+		ret = parse_address(addr, cfg_port, addr6);
+		if (ret)
+			error(1, 0, "Client address parse error: %s", addr);
+	}
+}
+
+int main(int argc, char **argv)
+{
+	parse_opts(argc, argv);
+
+	if (cfg_server)
+		run_server();
+	else if (cfg_client)
+		run_client();
+
+	return 0;
+}

tools/testing/selftests/net/tfo_passive.sh

···
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+source lib.sh
+
+NSIM_SV_ID=$((256 + RANDOM % 256))
+NSIM_SV_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_SV_ID
+NSIM_CL_ID=$((512 + RANDOM % 256))
+NSIM_CL_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_CL_ID
+
+NSIM_DEV_SYS_NEW=/sys/bus/netdevsim/new_device
+NSIM_DEV_SYS_DEL=/sys/bus/netdevsim/del_device
+NSIM_DEV_SYS_LINK=/sys/bus/netdevsim/link_device
+NSIM_DEV_SYS_UNLINK=/sys/bus/netdevsim/unlink_device
+
+SERVER_IP=192.168.1.1
+CLIENT_IP=192.168.1.2
+SERVER_PORT=48675
+
+setup_ns()
+{
+	set -e
+	ip netns add nssv
+	ip netns add nscl
+
+	NSIM_SV_NAME=$(find $NSIM_SV_SYS/net -maxdepth 1 -type d ! \
+		-path $NSIM_SV_SYS/net -exec basename {} \;)
+	NSIM_CL_NAME=$(find $NSIM_CL_SYS/net -maxdepth 1 -type d ! \
+		-path $NSIM_CL_SYS/net -exec basename {} \;)
+
+	ip link set $NSIM_SV_NAME netns nssv
+	ip link set $NSIM_CL_NAME netns nscl
+
+	ip netns exec nssv ip addr add "${SERVER_IP}/24" dev $NSIM_SV_NAME
+	ip netns exec nscl ip addr add "${CLIENT_IP}/24" dev $NSIM_CL_NAME
+
+	ip netns exec nssv ip link set dev $NSIM_SV_NAME up
+	ip netns exec nscl ip link set dev $NSIM_CL_NAME up
+
+	# Enable passive TFO
+	ip netns exec nssv sysctl -w net.ipv4.tcp_fastopen=519 > /dev/null
+
+	set +e
+}
+
+cleanup_ns()
+{
+	ip netns del nscl
+	ip netns del nssv
+}
+
+###
+### Code start
+###
+
+modprobe netdevsim
+
+# linking
+
+echo $NSIM_SV_ID > $NSIM_DEV_SYS_NEW
+echo $NSIM_CL_ID > $NSIM_DEV_SYS_NEW
+udevadm settle
+
+setup_ns
+
+NSIM_SV_FD=$((256 + RANDOM % 256))
+exec {NSIM_SV_FD}</var/run/netns/nssv
+NSIM_SV_IFIDX=$(ip netns exec nssv cat /sys/class/net/$NSIM_SV_NAME/ifindex)
+
+NSIM_CL_FD=$((256 + RANDOM % 256))
+exec {NSIM_CL_FD}</var/run/netns/nscl
+NSIM_CL_IFIDX=$(ip netns exec nscl cat /sys/class/net/$NSIM_CL_NAME/ifindex)
+
+echo "$NSIM_SV_FD:$NSIM_SV_IFIDX $NSIM_CL_FD:$NSIM_CL_IFIDX" > \
+     $NSIM_DEV_SYS_LINK
+
+if [ $? -ne 0 ]; then
+	echo "linking netdevsim1 with netdevsim2 should succeed"
+	cleanup_ns
+	exit 1
+fi
+
+out_file=$(mktemp)
+
+timeout -k 1s 30s ip netns exec nssv ./tfo        \
+				-s                \
+				-p ${SERVER_PORT} \
+				-o ${out_file}&
+
+wait_local_port_listen nssv ${SERVER_PORT} tcp
+
+ip netns exec nscl ./tfo -c -h ${SERVER_IP} -p ${SERVER_PORT}
+
+wait
+
+res=$(cat $out_file)
+rm $out_file
+
+if [ $res -eq 0 ]; then
+	echo "got invalid NAPI ID from passive TFO socket"
+	cleanup_ns
+	exit 1
+fi
+
+echo "$NSIM_SV_FD:$NSIM_SV_IFIDX" > $NSIM_DEV_SYS_UNLINK
+
+echo $NSIM_CL_ID > $NSIM_DEV_SYS_DEL
+
+cleanup_ns
+
+modprobe -r netdevsim
+
+exit 0

tools/testing/selftests/x86/Makefile

···
 
 TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap_vdso \
 			check_initial_reg_state sigreturn iopl ioperm \
-			test_vsyscall mov_ss_trap \
+			test_vsyscall mov_ss_trap sigtrap_loop \
 			syscall_arg_fault fsgsbase_restore sigaltstack
 TARGETS_C_BOTHBITS += nx_stack
 TARGETS_C_32BIT_ONLY := entry_from_vm86 test_syscall_vdso unwind_vdso \

tools/testing/selftests/x86/sigtrap_loop.c

···
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2025 Intel Corporation
+ */
+#define _GNU_SOURCE
+
+#include <err.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ucontext.h>
+
+#ifdef __x86_64__
+# define REG_IP REG_RIP
+#else
+# define REG_IP REG_EIP
+#endif
+
+static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), int flags)
+{
+	struct sigaction sa;
+
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_sigaction = handler;
+	sa.sa_flags = SA_SIGINFO | flags;
+	sigemptyset(&sa.sa_mask);
+
+	if (sigaction(sig, &sa, 0))
+		err(1, "sigaction");
+
+	return;
+}
+
+static void sigtrap(int sig, siginfo_t *info, void *ctx_void)
+{
+	ucontext_t *ctx = (ucontext_t *)ctx_void;
+	static unsigned int loop_count_on_same_ip;
+	static unsigned long last_trap_ip;
+
+	if (last_trap_ip == ctx->uc_mcontext.gregs[REG_IP]) {
+		printf("\tTrapped at %016lx\n", last_trap_ip);
+
+		/*
+		 * If the same IP is hit more than 10 times in a row, it is
+		 * _considered_ an infinite loop.
+		 */
+		if (++loop_count_on_same_ip > 10) {
+			printf("[FAIL]\tDetected SIGTRAP infinite loop\n");
+			exit(1);
+		}
+
+		return;
+	}
+
+	loop_count_on_same_ip = 0;
+	last_trap_ip = ctx->uc_mcontext.gregs[REG_IP];
+	printf("\tTrapped at %016lx\n", last_trap_ip);
+}
+
+int main(int argc, char *argv[])
+{
+	sethandler(SIGTRAP, sigtrap, 0);
+
+	/*
+	 * Set the Trap Flag (TF) to single-step the test code, therefore to
+	 * trigger a SIGTRAP signal after each instruction until the TF is
+	 * cleared.
+	 *
+	 * Because the arithmetic flags are not significant here, the TF is
+	 * set by pushing 0x302 onto the stack and then popping it into the
+	 * flags register.
+	 *
+	 * Four instructions in the following asm code are executed with the
+	 * TF set, thus the SIGTRAP handler is expected to run four times.
+	 */
+	printf("[RUN]\tSIGTRAP infinite loop detection\n");
+	asm volatile(
+#ifdef __x86_64__
+		/*
+		 * Avoid clobbering the redzone
+		 *
+		 * Equivalent to "sub $128, %rsp", however -128 can be encoded
+		 * in a single byte immediate while 128 uses 4 bytes.
+		 */
+		"add $-128, %rsp\n\t"
+#endif
+		"push $0x302\n\t"
+		"popf\n\t"
+		"nop\n\t"
+		"nop\n\t"
+		"push $0x202\n\t"
+		"popf\n\t"
+#ifdef __x86_64__
+		"sub $-128, %rsp\n\t"
+#endif
+	);
+
+	printf("[OK]\tNo SIGTRAP infinite loop detected\n");
+	return 0;
+}

tools/testing/vma/vma_internal.h

···
 
 #define ASSERT_EXCLUSIVE_WRITER(x)
 
+/**
+ * swap - swap values of @a and @b
+ * @a: first value
+ * @b: second value
+ */
+#define swap(a, b) \
+	do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
+
 struct kref {
 	refcount_t refcount;
 };
···
 static inline void fixup_hugetlb_reservations(struct vm_area_struct *vma)
 {
 	(void)vma;
+}
+
+static inline void vma_set_file(struct vm_area_struct *vma, struct file *file)
+{
+	/* Changing an anonymous vma with this is illegal */
+	get_file(file);
+	swap(vma->vm_file, file);
+	fput(file);
 }
 
 #endif	/* __MM_VMA_INTERNAL_H */