Thermal control updates for 6.19-rc1

- Add Nova Lake processor thermal device to the int340x
    processor_thermal driver, add DLVR support for Nova Lake to it,
    add Nova Lake support to the ACPI DPTF code, document thermal
    throttling on Intel platforms, and update workload type hint
    interface documentation (Srinivas Pandruvada)
 
  - Remove int340x thermal scan handler from the ACPI DPTF code
    because it turned out to be unnecessary (Slawomir Rosek)
 
  - Clean up the Intel int340x thermal driver (Kaushlendra Kumar)
 
  - Document the RZ/V2H TSU DT bindings (Ovidiu Panait)
 
  - Document the Kaanapali Temperature Sensor (Manaf Meethalavalappu
    Pallikunhi)
 
  - Document R-Car Gen4 and RZ/G2 support in driver comment (Marek Vasut)
 
  - Convert to DEFINE_SIMPLE_DEV_PM_OPS() in R-Car [Gen3] (Geert
    Uytterhoeven)
 
  - Fix format string bug in thermal-engine (Malaya Kumar Rout)
 
  - Make ipq5018 tsens standalone compatible (George Moussalem)
 
  - Add the QCS8300 compatible for QCom Tsens (Gaurav Kohli)
 
  - Add support for the NXP i.MX91 thermal module, including the DT
    bindings (Pengfei Li)
 -----BEGIN PGP SIGNATURE-----
 
 iQFGBAABCAAwFiEEcM8Aw/RY0dgsiRUR7l+9nS/U47UFAmkpt1cSHHJqd0Byand5
 c29ja2kubmV0AAoJEO5fvZ0v1OO1cikH/jW6IUXUvrTy9VEi3wGTzLAcnOuJJtQL
 zKQBzrjtuGngr4xIeE+chr9Gr8+S4EfVcD17twp59I6C3T9fBZngfMxbi7VLdyd7
 gIJs2IxIqfIlQwK32lBOkLM2/YHa0AYU3Dd/YHsgYOU3Y25adSvmiwoTqG3kUmXB
 YnoHUobPskzV/9iKf2sptM7XBLDaBdoPHcDAM2BN4rfKhgOy/1ha7KzigJyuHHyW
 V+b9KR/IlFOVct8OrvhXKT4mzsS9VZv6IJ6KrRsDsCIgVwM/fO1YTmRgfOkuRASZ
 fw6vNNi+49xK0LN8zEvHKuYthBFy+7lIP+MiErMr2Fw5nuY2uXitZA8=
 =OgXe
 -----END PGP SIGNATURE-----

Merge tag 'thermal-6.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull thermal control updates from Rafael Wysocki:
 "These add Nova Lake processor support to the Intel thermal drivers and
  DPTF code, update thermal control documentation, simplify the ACPI
  DPTF code related to thermal control, add QCS8300 compatible to the
  tsens thermal DT bindings, add DT bindings for NXP i.MX91 thermal
  module and add support for it to the imx91 thermal driver, update a
  few other thermal drivers and fix a format string issue in a thermal
  utility:

   - Add Nova Lake processor thermal device to the int340x
     processor_thermal driver, add DLVR support for Nova Lake to it, add
     Nova Lake support to the ACPI DPTF code, document thermal
     throttling on Intel platforms, and update workload type hint
     interface documentation (Srinivas Pandruvada)

   - Remove int340x thermal scan handler from the ACPI DPTF code because
     it turned out to be unnecessary (Slawomir Rosek)

   - Clean up the Intel int340x thermal driver (Kaushlendra Kumar)

   - Document the RZ/V2H TSU DT bindings (Ovidiu Panait)

   - Document the Kaanapali Temperature Sensor (Manaf Meethalavalappu
     Pallikunhi)

   - Document R-Car Gen4 and RZ/G2 support in driver comment (Marek
     Vasut)

   - Convert to DEFINE_SIMPLE_DEV_PM_OPS() in R-Car [Gen3] (Geert
     Uytterhoeven)

   - Fix format string bug in thermal-engine (Malaya Kumar Rout)

   - Make ipq5018 tsens standalone compatible (George Moussalem)

   - Add the QCS8300 compatible for QCom Tsens (Gaurav Kohli)

   - Add support for the NXP i.MX91 thermal module, including the DT
     bindings (Pengfei Li)"

* tag 'thermal-6.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  thermal/drivers/imx91: Add support for i.MX91 thermal monitoring unit
  dt-bindings: thermal: fsl,imx91-tmu: add bindings for NXP i.MX91 thermal module
  dt-bindings: thermal: tsens: Add QCS8300 compatible
  dt-bindings: thermal: qcom-tsens: make ipq5018 tsens standalone compatible
  tools/thermal/thermal-engine: Fix format string bug in thermal-engine
  docs: driver-api/thermal/intel_dptf: Add new workload type hint
  thermal/drivers/rcar_gen3: Convert to DEFINE_SIMPLE_DEV_PM_OPS()
  thermal/drivers/rcar: Convert to DEFINE_SIMPLE_DEV_PM_OPS()
  Documentation: thermal: Document thermal throttling on Intel platforms
  ACPI: DPTF: Support Nova Lake
  thermal: intel: int340x: Add DLVR support for Nova Lake
  thermal: int340x: processor_thermal: Add Nova Lake processor thermal device
  thermal: intel: int340x: Replace sprintf() with sysfs_emit()
  thermal: intel: int340x: Use symbolic constant for UUID comparison
  thermal/drivers/rcar_gen3: Document R-Car Gen4 and RZ/G2 support in driver comment
  dt-bindings: thermal: qcom-tsens: document the Kaanapali Temperature Sensor
  dt-bindings: thermal: r9a09g047-tsu: Document RZ/V2H TSU
  ACPI: DPTF: Remove int340x thermal scan handler
  thermal: intel: Select INT340X_THERMAL from INTEL_SOC_DTS_THERMAL

Documentation/ABI/testing/sysfs-power

@@ -454,3 +454,19 @@ Description:
 		disables it.  Reads from the file return the current value.
 		The default is "1" if the build-time "SUSPEND_SKIP_SYNC" config
 		flag is unset, or "0" otherwise.
+
+What:           /sys/power/hibernate_compression_threads
+Date:           October 2025
+Contact:        <luoxueqin@kylinos.cn>
+Description:
+                Controls the number of threads used for compression
+                and decompression of hibernation images.
+
+                The value can be adjusted at runtime to balance
+                performance and CPU utilization.
+
+                The change takes effect on the next hibernation or
+                resume operation.
+
+                Minimum value: 1
+                Default value: 3

Documentation/admin-guide/RAS/main.rst

@@ -406,24 +406,8 @@ index of the MC::
 		   |->mc2
 		   ....
 
-Under each ``mcX`` directory each ``csrowX`` is again represented by a
-``csrowX``, where ``X`` is the csrow index::
-
-	.../mc/mc0/
-		|
-		|->csrow0
-		|->csrow2
-		|->csrow3
-		....
-
-Notice that there is no csrow1, which indicates that csrow0 is composed
-of a single ranked DIMMs. This should also apply in both Channels, in
-order to have dual-channel mode be operational. Since both csrow2 and
-csrow3 are populated, this indicates a dual ranked set of DIMMs for
-channels 0 and 1.
-
-Within each of the ``mcX`` and ``csrowX`` directories are several EDAC
-control and attribute files.
+Within each of the ``mcX`` directory are several EDAC control and
+attribute files.
 
 ``mcX`` directories
 -------------------
@@ -569,7 +553,7 @@ this ``X`` memory module:
 		- Unbuffered-DDR
 
 .. [#f5] On some systems, the memory controller doesn't have any logic
-  to identify the memory module. On such systems, the directory is called ``rankX`` and works on a similar way as the ``csrowX`` directories.
+  to identify the memory module. On such systems, the directory is called ``rankX``.
   On modern Intel memory controllers, the memory controller identifies the
   memory modules directly. On such systems, the directory is called ``dimmX``.
 
@@ -577,126 +561,6 @@ this ``X`` memory module:
   symlinks inside the sysfs mapping that are automatically created by
   the sysfs subsystem. Currently, they serve no purpose.
 
-``csrowX`` directories
-----------------------
-
-When CONFIG_EDAC_LEGACY_SYSFS is enabled, sysfs will contain the ``csrowX``
-directories. As this API doesn't work properly for Rambus, FB-DIMMs and
-modern Intel Memory Controllers, this is being deprecated in favor of
-``dimmX`` directories.
-
-In the ``csrowX`` directories are EDAC control and attribute files for
-this ``X`` instance of csrow:
-
-
-- ``ue_count`` - Total Uncorrectable Errors count attribute file
-
-	This attribute file displays the total count of uncorrectable
-	errors that have occurred on this csrow. If panic_on_ue is set
-	this counter will not have a chance to increment, since EDAC
-	will panic the system.
-
-
-- ``ce_count`` - Total Correctable Errors count attribute file
-
-	This attribute file displays the total count of correctable
-	errors that have occurred on this csrow. This count is very
-	important to examine. CEs provide early indications that a
-	DIMM is beginning to fail. This count field should be
-	monitored for non-zero values and report such information
-	to the system administrator.
-
-
-- ``size_mb`` - Total memory managed by this csrow attribute file
-
-	This attribute file displays, in count of megabytes, the memory
-	that this csrow contains.
-
-
-- ``mem_type`` - Memory Type attribute file
-
-	This attribute file will display what type of memory is currently
-	on this csrow. Normally, either buffered or unbuffered memory.
-	Examples:
-
-		- Registered-DDR
-		- Unbuffered-DDR
-
-
-- ``edac_mode`` - EDAC Mode of operation attribute file
-
-	This attribute file will display what type of Error detection
-	and correction is being utilized.
-
-
-- ``dev_type`` - Device type attribute file
-
-	This attribute file will display what type of DRAM device is
-	being utilized on this DIMM.
-	Examples:
-
-		- x1
-		- x2
-		- x4
-		- x8
-
-
-- ``ch0_ce_count`` - Channel 0 CE Count attribute file
-
-	This attribute file will display the count of CEs on this
-	DIMM located in channel 0.
-
-
-- ``ch0_ue_count`` - Channel 0 UE Count attribute file
-
-	This attribute file will display the count of UEs on this
-	DIMM located in channel 0.
-
-
-- ``ch0_dimm_label`` - Channel 0 DIMM Label control file
-
-
-	This control file allows this DIMM to have a label assigned
-	to it. With this label in the module, when errors occur
-	the output can provide the DIMM label in the system log.
-	This becomes vital for panic events to isolate the
-	cause of the UE event.
-
-	DIMM Labels must be assigned after booting, with information
-	that correctly identifies the physical slot with its
-	silk screen label. This information is currently very
-	motherboard specific and determination of this information
-	must occur in userland at this time.
-
-
-- ``ch1_ce_count`` - Channel 1 CE Count attribute file
-
-
-	This attribute file will display the count of CEs on this
-	DIMM located in channel 1.
-
-
-- ``ch1_ue_count`` - Channel 1 UE Count attribute file
-
-
-	This attribute file will display the count of UEs on this
-	DIMM located in channel 0.
-
-
-- ``ch1_dimm_label`` - Channel 1 DIMM Label control file
-
-	This control file allows this DIMM to have a label assigned
-	to it. With this label in the module, when errors occur
-	the output can provide the DIMM label in the system log.
-	This becomes vital for panic events to isolate the
-	cause of the UE event.
-
-	DIMM Labels must be assigned after booting, with information
-	that correctly identifies the physical slot with its
-	silk screen label. This information is currently very
-	motherboard specific and determination of this information
-	must occur in userland at this time.
-
 
 System Logging
 --------------

Documentation/admin-guide/kernel-parameters.txt

@@ -1907,6 +1907,16 @@
 			/sys/power/pm_test). Only available when CONFIG_PM_DEBUG
 			is set. Default value is 5.
 
+	hibernate_compression_threads=
+			[HIBERNATION]
+			Set the number of threads used for compressing or decompressing
+			hibernation images.
+
+			Format: <integer>
+			Default: 3
+			Minimum: 1
+			Example: hibernate_compression_threads=4
+
 	highmem=nn[KMG]	[KNL,BOOT,EARLY] forces the highmem zone to have an exact
 			size of <nn>. This works even on boxes that have no
 			highmem otherwise. This also works to reduce highmem
@@ -6207,7 +6217,7 @@
 	rdt=		[HW,X86,RDT]
 			Turn on/off individual RDT features. List is:
 			cmt, mbmtotal, mbmlocal, l3cat, l3cdp, l2cat, l2cdp,
-			mba, smba, bmec, abmc.
+			mba, smba, bmec, abmc, sdciae.
 			E.g. to turn on cmt and turn off mba use:
 				rdt=cmt,!mba
 
@@ -6500,6 +6510,10 @@
 			Memory area to be used by remote processor image,
 			managed by CMA.
 
+	rseq_debug=	[KNL] Enable or disable restartable sequence
+			debug mode. Defaults to CONFIG_RSEQ_DEBUG_DEFAULT_ENABLE.
+			Format: <bool>
+
 	rt_group_sched=	[KNL] Enable or disable SCHED_RR/FIFO group scheduling
 			when CONFIG_RT_GROUP_SCHED=y. Defaults to
 			!CONFIG_RT_GROUP_SCHED_DEFAULT_DISABLED.

Documentation/admin-guide/pm/cpuidle.rst

@@ -580,6 +580,15 @@ the given CPU as the upper limit for the exit latency of the idle states that
 they are allowed to select for that CPU.  They should never select any idle
 states with exit latency beyond that limit.
 
+While the above CPU QoS constraints apply to CPU idle time management, user
+space may also request a CPU system wakeup latency QoS limit, via the
+`cpu_wakeup_latency` file.  This QoS constraint is respected when selecting a
+suitable idle state for the CPUs, while entering the system-wide suspend-to-idle
+sleep state, but also to the regular CPU idle time management.
+
+Note that, the management of the `cpu_wakeup_latency` file works according to
+the 'cpu_dma_latency' file from user space point of view.  Moreover, the unit
+is also microseconds.
 
 Idle States Control Via Kernel Command Line
 ===========================================

Documentation/admin-guide/pm/intel_pstate.rst

@@ -48,8 +48,9 @@ only way to pass early-configuration-time parameters to it is via the kernel
 command line.  However, its configuration can be adjusted via ``sysfs`` to a
 great extent.  In some configurations it even is possible to unregister it via
 ``sysfs`` which allows another ``CPUFreq`` scaling driver to be loaded and
-registered (see `below <status_attr_>`_).
+registered (see :ref:`below <status_attr>`).
 
+.. _operation_modes:
 
 Operation Modes
 ===============
@@ -62,6 +63,8 @@ a certain performance scaling algorithm.  Which of them will be in effect
 depends on what kernel command line options are used and on the capabilities of
 the processor.
 
+.. _active_mode:
+
 Active Mode
 -----------
 
@@ -94,6 +97,8 @@ Which of the P-state selection algorithms is used by default depends on the
 Namely, if that option is set, the ``performance`` algorithm will be used by
 default, and the other one will be used by default if it is not set.
 
+.. _active_mode_hwp:
+
 Active Mode With HWP
 ~~~~~~~~~~~~~~~~~~~~
 
@@ -123,7 +128,7 @@ Energy-Performance Bias (EPB) knob (otherwise), which means that the processor's
 internal P-state selection logic is expected to focus entirely on performance.
 
 This will override the EPP/EPB setting coming from the ``sysfs`` interface
-(see `Energy vs Performance Hints`_ below).  Moreover, any attempts to change
+(see :ref:`energy_performance_hints` below).  Moreover, any attempts to change
 the EPP/EPB to a value different from 0 ("performance") via ``sysfs`` in this
 configuration will be rejected.
 
@@ -192,6 +197,8 @@ This is the default P-state selection algorithm if the
 :c:macro:`CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE` kernel configuration option
 is not set.
 
+.. _passive_mode:
+
 Passive Mode
 ------------
 
@@ -289,12 +296,12 @@ Unlike ``_PSS`` objects in the ACPI tables, ``intel_pstate`` always exposes
 the entire range of available P-states, including the whole turbo range, to the
 ``CPUFreq`` core and (in the passive mode) to generic scaling governors.  This
 generally causes turbo P-states to be set more often when ``intel_pstate`` is
-used relative to ACPI-based CPU performance scaling (see `below <acpi-cpufreq_>`_
-for more information).
+used relative to ACPI-based CPU performance scaling (see
+:ref:`below <acpi-cpufreq>` for more information).
 
 Moreover, since ``intel_pstate`` always knows what the real turbo threshold is
 (even if the Configurable TDP feature is enabled in the processor), its
-``no_turbo`` attribute in ``sysfs`` (described `below <no_turbo_attr_>`_) should
+``no_turbo`` attribute in ``sysfs`` (described :ref:`below <no_turbo_attr>`) should
 work as expected in all cases (that is, if set to disable turbo P-states, it
 always should prevent ``intel_pstate`` from using them).
 
@@ -307,12 +314,12 @@ pieces of information on it to be known, including:
 
  * The minimum supported P-state.
 
- * The maximum supported `non-turbo P-state <turbo_>`_.
+ * The maximum supported :ref:`non-turbo P-state <turbo>`.
 
  * Whether or not turbo P-states are supported at all.
 
- * The maximum supported `one-core turbo P-state <turbo_>`_ (if turbo P-states
-   are supported).
+ * The maximum supported :ref:`one-core turbo P-state <turbo>` (if turbo
+   P-states are supported).
 
  * The scaling formula to translate the driver's internal representation
    of P-states into frequencies and the other way around.
@@ -400,10 +407,10 @@ Energy-Aware Scheduling Support
 
 If ``CONFIG_ENERGY_MODEL`` has been set during kernel configuration and
 ``intel_pstate`` runs on a hybrid processor without SMT, in addition to enabling
-`CAS <CAS_>`_ it registers an Energy Model for the processor.  This allows the
+:ref:`CAS` it registers an Energy Model for the processor.  This allows the
 Energy-Aware Scheduling (EAS) support to be enabled in the CPU scheduler if
 ``schedutil`` is used as the  ``CPUFreq`` governor which requires ``intel_pstate``
-to operate in the `passive mode <Passive Mode_>`_.
+to operate in the :ref:`passive mode <passive_mode>`.
 
 The Energy Model registered by ``intel_pstate`` is artificial (that is, it is
 based on abstract cost values and it does not include any real power numbers)
@@ -432,6 +439,8 @@ the ``energy_model`` directory in ``debugfs`` (typlically mounted on
 User Space Interface in ``sysfs``
 =================================
 
+.. _global_attributes:
+
 Global Attributes
 -----------------
 
@@ -444,8 +453,8 @@ argument is passed to the kernel in the command line.
 
 ``max_perf_pct``
 	Maximum P-state the driver is allowed to set in percent of the
-	maximum supported performance level (the highest supported `turbo
-	P-state <turbo_>`_).
+	maximum supported performance level (the highest supported :ref:`turbo
+	P-state <turbo>`).
 
 	This attribute will not be exposed if the
 	``intel_pstate=per_cpu_perf_limits`` argument is present in the kernel
@@ -453,8 +462,8 @@ argument is passed to the kernel in the command line.
 
 ``min_perf_pct``
 	Minimum P-state the driver is allowed to set in percent of the
-	maximum supported performance level (the highest supported `turbo
-	P-state <turbo_>`_).
+	maximum supported performance level (the highest supported :ref:`turbo
+	P-state <turbo>`).
 
 	This attribute will not be exposed if the
 	``intel_pstate=per_cpu_perf_limits`` argument is present in the kernel
@@ -463,18 +472,18 @@ argument is passed to the kernel in the command line.
 ``num_pstates``
 	Number of P-states supported by the processor (between 0 and 255
 	inclusive) including both turbo and non-turbo P-states (see
-	`Turbo P-states Support`_).
+	:ref:`turbo`).
 
 	This attribute is present only if the value exposed by it is the same
 	for all of the CPUs in the system.
 
 	The value of this attribute is not affected by the ``no_turbo``
-	setting described `below <no_turbo_attr_>`_.
+	setting described :ref:`below <no_turbo_attr>`.
 
 	This attribute is read-only.
 
 ``turbo_pct``
-	Ratio of the `turbo range <turbo_>`_ size to the size of the entire
+	Ratio of the :ref:`turbo range <turbo>` size to the size of the entire
 	range of supported P-states, in percent.
 
 	This attribute is present only if the value exposed by it is the same
@@ -486,7 +495,7 @@ argument is passed to the kernel in the command line.
 
 ``no_turbo``
 	If set (equal to 1), the driver is not allowed to set any turbo P-states
-	(see `Turbo P-states Support`_).  If unset (equal to 0, which is the
+	(see :ref:`turbo`).  If unset (equal to 0, which is the
 	default), turbo P-states can be set by the driver.
 	[Note that ``intel_pstate`` does not support the general ``boost``
 	attribute (supported by some other scaling drivers) which is replaced
@@ -495,11 +504,11 @@ argument is passed to the kernel in the command line.
 	This attribute does not affect the maximum supported frequency value
 	supplied to the ``CPUFreq`` core and exposed via the policy interface,
 	but it affects the maximum possible value of per-policy P-state	limits
-	(see `Interpretation of Policy Attributes`_ below for details).
+	(see :ref:`policy_attributes_interpretation` below for details).
 
 ``hwp_dynamic_boost``
 	This attribute is only present if ``intel_pstate`` works in the
-	`active mode with the HWP feature enabled <Active Mode With HWP_>`_ in
+	:ref:`active mode with the HWP feature enabled <active_mode_hwp>` in
 	the processor.  If set (equal to 1), it causes the minimum P-state limit
 	to be increased dynamically for a short time whenever a task previously
 	waiting on I/O is selected to run on a given logical CPU (the purpose
@@ -514,12 +523,12 @@ argument is passed to the kernel in the command line.
 	Operation mode of the driver: "active", "passive" or "off".
 
 	"active"
-		The driver is functional and in the `active mode
-		<Active Mode_>`_.
+		The driver is functional and in the :ref:`active mode
+		<active_mode>`.
 
 	"passive"
-		The driver is functional and in the `passive mode
-		<Passive Mode_>`_.
+		The driver is functional and in the :ref:`passive mode
+		<passive_mode>`.
 
 	"off"
 		The driver is not functional (it is not registered as a scaling
@@ -547,13 +556,15 @@ argument is passed to the kernel in the command line.
 	attribute to "1" enables the energy-efficiency optimizations and setting
 	to "0" disables them.
 
+.. _policy_attributes_interpretation:
+
 Interpretation of Policy Attributes
 -----------------------------------
 
 The interpretation of some ``CPUFreq`` policy attributes described in
 Documentation/admin-guide/pm/cpufreq.rst is special with ``intel_pstate``
 as the current scaling driver and it generally depends on the driver's
-`operation mode <Operation Modes_>`_.
+:ref:`operation mode <operation_modes>`.
 
 First of all, the values of the ``cpuinfo_max_freq``, ``cpuinfo_min_freq`` and
 ``scaling_cur_freq`` attributes are produced by applying a processor-specific
@@ -562,9 +573,10 @@ Also, the values of the ``scaling_max_freq`` and ``scaling_min_freq``
 attributes are capped by the frequency corresponding to the maximum P-state that
 the driver is allowed to set.
 
-If the ``no_turbo`` `global attribute <no_turbo_attr_>`_ is set, the driver is
-not allowed to use turbo P-states, so the maximum value of ``scaling_max_freq``
-and ``scaling_min_freq`` is limited to the maximum non-turbo P-state frequency.
+If the ``no_turbo`` :ref:`global attribute <no_turbo_attr>` is set, the driver
+is not allowed to use turbo P-states, so the maximum value of
+``scaling_max_freq`` and ``scaling_min_freq`` is limited to the maximum
+non-turbo P-state frequency.
 Accordingly, setting ``no_turbo`` causes ``scaling_max_freq`` and
 ``scaling_min_freq`` to go down to that value if they were above it before.
 However, the old values of ``scaling_max_freq`` and ``scaling_min_freq`` will be
@@ -576,7 +588,7 @@ and ``scaling_min_freq`` corresponds to the maximum supported turbo P-state,
 which also is the value of ``cpuinfo_max_freq`` in either case.
 
 Next, the following policy attributes have special meaning if
-``intel_pstate`` works in the `active mode <Active Mode_>`_:
+``intel_pstate`` works in the :ref:`active mode <active_mode>`:
 
 ``scaling_available_governors``
 	List of P-state selection algorithms provided by ``intel_pstate``.
@@ -597,20 +609,22 @@ processor:
 	Shows the base frequency of the CPU. Any frequency above this will be
 	in the turbo frequency range.
 
-The meaning of these attributes in the `passive mode <Passive Mode_>`_ is the
+The meaning of these attributes in the :ref:`passive mode <passive_mode>` is the
 same as for other scaling drivers.
 
 Additionally, the value of the ``scaling_driver`` attribute for ``intel_pstate``
 depends on the operation mode of the driver.  Namely, it is either
-"intel_pstate" (in the `active mode <Active Mode_>`_) or "intel_cpufreq" (in the
-`passive mode <Passive Mode_>`_).
+"intel_pstate" (in the :ref:`active mode <active_mode>`) or "intel_cpufreq"
+(in the :ref:`passive mode <passive_mode>`).
+
+.. _pstate_limits_coordination:
 
 Coordination of P-State Limits
 ------------------------------
 
 ``intel_pstate`` allows P-state limits to be set in two ways: with the help of
-the ``max_perf_pct`` and ``min_perf_pct`` `global attributes
-<Global Attributes_>`_ or via the ``scaling_max_freq`` and ``scaling_min_freq``
+the ``max_perf_pct`` and ``min_perf_pct`` :ref:`global attributes
+<global_attributes>` or via the ``scaling_max_freq`` and ``scaling_min_freq``
 ``CPUFreq`` policy attributes.  The coordination between those limits is based
 on the following rules, regardless of the current operation mode of the driver:
 
@@ -632,17 +646,18 @@ on the following rules, regardless of the current operation mode of the driver:
 
  3. The global and per-policy limits can be set independently.
 
-In the `active mode with the HWP feature enabled <Active Mode With HWP_>`_, the
+In the :ref:`active mode with the HWP feature enabled <active_mode_hwp>`, the
 resulting effective values are written into hardware registers whenever the
 limits change in order to request its internal P-state selection logic to always
 set P-states within these limits.  Otherwise, the limits are taken into account
-by scaling governors (in the `passive mode <Passive Mode_>`_) and by the driver
-every time before setting a new P-state for a CPU.
+by scaling governors (in the :ref:`passive mode <passive_mode>`) and by the
+driver every time before setting a new P-state for a CPU.
 
 Additionally, if the ``intel_pstate=per_cpu_perf_limits`` command line argument
 is passed to the kernel, ``max_perf_pct`` and ``min_perf_pct`` are not exposed
 at all and the only way to set the limits is by using the policy attributes.
 
+.. _energy_performance_hints:
 
 Energy vs Performance Hints
 ---------------------------
@@ -702,9 +717,9 @@ output.
 On those systems each ``_PSS`` object returns a list of P-states supported by
 the corresponding CPU which basically is a subset of the P-states range that can
 be used by ``intel_pstate`` on the same system, with one exception: the whole
-`turbo range <turbo_>`_ is represented by one item in it (the topmost one).  By
-convention, the frequency returned by ``_PSS`` for that item is greater by 1 MHz
-than the frequency of the highest non-turbo P-state listed by it, but the
+:ref:`turbo range <turbo>` is represented by one item in it (the topmost one).
+By convention, the frequency returned by ``_PSS`` for that item is greater by
+1 MHz than the frequency of the highest non-turbo P-state listed by it, but the
 corresponding P-state representation (following the hardware specification)
 returned for it matches the maximum supported turbo P-state (or is the
 special value 255 meaning essentially "go as high as you can get").
@@ -730,18 +745,18 @@ benefit from running at turbo frequencies will be given non-turbo P-states
 instead.
 
 One more issue related to that may appear on systems supporting the
-`Configurable TDP feature <turbo_>`_ allowing the platform firmware to set the
-turbo threshold.  Namely, if that is not coordinated with the lists of P-states
-returned by ``_PSS`` properly, there may be more than one item corresponding to
-a turbo P-state in those lists and there may be a problem with avoiding the
-turbo range (if desirable or necessary).  Usually, to avoid using turbo
-P-states overall, ``acpi-cpufreq`` simply avoids using the topmost state listed
-by ``_PSS``, but that is not sufficient when there are other turbo P-states in
-the list returned by it.
+:ref:`Configurable TDP feature <turbo>` allowing the platform firmware to set
+the turbo threshold.  Namely, if that is not coordinated with the lists of
+P-states returned by ``_PSS`` properly, there may be more than one item
+corresponding to a turbo P-state in those lists and there may be a problem with
+avoiding the turbo range (if desirable or necessary).  Usually, to avoid using
+turbo P-states overall, ``acpi-cpufreq`` simply avoids using the topmost state
+listed by ``_PSS``, but that is not sufficient when there are other turbo
+P-states in the list returned by it.
 
 Apart from the above, ``acpi-cpufreq`` works like ``intel_pstate`` in the
-`passive mode <Passive Mode_>`_, except that the number of P-states it can set
-is limited to the ones listed by the ACPI ``_PSS`` objects.
+:ref:`passive mode <passive_mode>`, except that the number of P-states it can
+set is limited to the ones listed by the ACPI ``_PSS`` objects.
 
 
 Kernel Command Line Options for ``intel_pstate``
@@ -756,11 +771,11 @@ of them have to be prepended with the ``intel_pstate=`` prefix.
 	processor is supported by it.
 
 ``active``
-	Register ``intel_pstate`` in the `active mode <Active Mode_>`_ to start
-	with.
+	Register ``intel_pstate`` in the :ref:`active mode <active_mode>` to
+        start with.
 
 ``passive``
-	Register ``intel_pstate`` in the `passive mode <Passive Mode_>`_ to
+	Register ``intel_pstate`` in the :ref:`passive mode <passive_mode>` to
 	start with.
 
 ``force``
@@ -793,12 +808,12 @@ of them have to be prepended with the ``intel_pstate=`` prefix.
 	and this option has no effect.
 
 ``per_cpu_perf_limits``
-	Use per-logical-CPU P-State limits (see `Coordination of P-state
-	Limits`_ for details).
+	Use per-logical-CPU P-State limits (see
+        :ref:`pstate_limits_coordination` for details).
 
 ``no_cas``
-	Do not enable `capacity-aware scheduling <CAS_>`_ which is enabled by
-	default on hybrid systems without SMT.
+	Do not enable :ref:`capacity-aware scheduling <CAS>` which is enabled
+        by default on hybrid systems without SMT.
 
 Diagnostics and Tuning
 ======================
@@ -810,7 +825,7 @@ There are two static trace events that can be used for ``intel_pstate``
 diagnostics.  One of them is the ``cpu_frequency`` trace event generally used
 by ``CPUFreq``, and the other one is the ``pstate_sample`` trace event specific
 to ``intel_pstate``.  Both of them are triggered by ``intel_pstate`` only if
-it works in the `active mode <Active Mode_>`_.
+it works in the :ref:`active mode <active_mode>`.
 
 The following sequence of shell commands can be used to enable them and see
 their output (if the kernel is generally configured to support event tracing)::
@@ -822,7 +837,7 @@ their output (if the kernel is generally configured to support event tracing)::
  gnome-terminal--4510  [001] ..s.  1177.680733: pstate_sample: core_busy=107 scaled=94 from=26 to=26 mperf=1143818 aperf=1230607 tsc=29838618 freq=2474476
  cat-5235  [002] ..s.  1177.681723: cpu_frequency: state=2900000 cpu_id=2
 
-If ``intel_pstate`` works in the `passive mode <Passive Mode_>`_, the
+If ``intel_pstate`` works in the :ref:`passive mode <passive_mode>`, the
 ``cpu_frequency`` trace event will be triggered either by the ``schedutil``
 scaling governor (for the policies it is attached to), or by the ``CPUFreq``
 core (for the policies with other scaling governors).

Documentation/admin-guide/thermal/index.rst

@@ -6,3 +6,4 @@ Thermal Subsystem
    :maxdepth: 1
 
    intel_powerclamp
+   intel_thermal_throttle

Documentation/admin-guide/thermal/intel_thermal_throttle.rst

@@ -0,0 +1,91 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
+=======================================
+Intel thermal throttle events reporting
+=======================================
+
+:Author: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
+
+Introduction
+------------
+
+Intel processors have built in automatic and adaptive thermal monitoring
+mechanisms that force the processor to reduce its power consumption in order
+to operate within predetermined temperature limits.
+
+Refer to section "THERMAL MONITORING AND PROTECTION" in the "Intel® 64 and
+IA-32 Architectures Software Developer’s Manual Volume 3 (3A, 3B, 3C, & 3D):
+System Programming Guide" for more details.
+
+In general, there are two mechanisms to control the core temperature of the
+processor. They are called "Thermal Monitor 1 (TM1) and Thermal Monitor 2 (TM2)".
+
+The status of the temperature sensor that triggers the thermal monitor (TM1/TM2)
+is indicated through the "thermal status flag" and "thermal status log flag" in
+MSR_IA32_THERM_STATUS for core level and MSR_IA32_PACKAGE_THERM_STATUS for
+package level.
+
+Thermal Status flag, bit 0 — When set, indicates that the processor core
+temperature is currently at the trip temperature of the thermal monitor and that
+the processor power consumption is being reduced via either TM1 or TM2, depending
+on which is enabled. When clear, the flag indicates that the core temperature is
+below the thermal monitor trip temperature. This flag is read only.
+
+Thermal Status Log flag, bit 1 — When set, indicates that the thermal sensor has
+tripped since the last power-up or reset or since the last time that software
+cleared this flag. This flag is a sticky bit; once set it remains set until
+cleared by software or until a power-up or reset of the processor. The default
+state is clear.
+
+It is possible that when user reads MSR_IA32_THERM_STATUS or
+MSR_IA32_PACKAGE_THERM_STATUS, TM1/TM2 is not active. In this case,
+"Thermal Status flag" will read "0" and the "Thermal Status Log flag" will be set
+to show any previous "TM1/TM2" activation. But since it needs to be cleared by
+the software, it can't show the number of occurrences of "TM1/TM2" activations.
+
+Hence, Linux provides counters of how many times the "Thermal Status flag" was
+set. Also presents how long the "Thermal Status flag" was active in milliseconds.
+Using these counters, users can check if the performance was limited because of
+thermal events. It is recommended to read from sysfs instead of directly reading
+MSRs as the "Thermal Status Log flag" is reset by the driver to implement rate
+control.
+
+Sysfs Interface
+---------------
+
+Thermal throttling events are presented for each CPU under
+"/sys/devices/system/cpu/cpuX/thermal_throttle/", where "X" is the CPU number.
+
+All these counters are read-only. They can't be reset to 0. So, they can potentially
+overflow after reaching the maximum 64 bit unsigned integer.
+
+``core_throttle_count``
+	Shows the number of times "Thermal Status flag" changed from 0 to 1 for this
+	CPU since OS boot and thermal vector is initialized. This is a 64 bit counter.
+
+``package_throttle_count``
+	Shows the number of times "Thermal Status flag" changed from 0 to 1 for the
+	package containing this CPU since OS boot and thermal vector is initialized.
+	Package status is broadcast to all CPUs; all CPUs in the package increment
+	this count. This is a 64-bit counter.
+
+``core_throttle_max_time_ms``
+	Shows the maximum amount of time for which "Thermal Status flag" has been
+	set to 1 for this CPU at the core level since OS boot and thermal vector
+	is initialized.
+
+``package_throttle_max_time_ms``
+	Shows the maximum amount of time for which "Thermal Status flag" has been
+	set to 1 for the package containing this CPU since OS boot and thermal
+	vector is initialized.
+
+``core_throttle_total_time_ms``
+	Shows the cumulative time for which "Thermal Status flag" has been
+	set to 1 for this CPU for core level since OS boot and thermal vector
+	is initialized.
+
+``package_throttle_total_time_ms``
+	Shows the cumulative time for which "Thermal Status flag" has been set
+	to 1 for the package containing this CPU since OS boot and thermal vector
+	is initialized.

Documentation/arch/arm64/booting.rst

@@ -391,13 +391,13 @@ Before jumping into the kernel, the following conditions must be met:
     - SMCR_EL2.LEN must be initialised to the same value for all CPUs the
       kernel will execute on.
 
-    - HWFGRTR_EL2.nTPIDR2_EL0 (bit 55) must be initialised to 0b01.
+    - HFGRTR_EL2.nTPIDR2_EL0 (bit 55) must be initialised to 0b01.
 
-    - HWFGWTR_EL2.nTPIDR2_EL0 (bit 55) must be initialised to 0b01.
+    - HFGWTR_EL2.nTPIDR2_EL0 (bit 55) must be initialised to 0b01.
 
-    - HWFGRTR_EL2.nSMPRI_EL1 (bit 54) must be initialised to 0b01.
+    - HFGRTR_EL2.nSMPRI_EL1 (bit 54) must be initialised to 0b01.
 
-    - HWFGWTR_EL2.nSMPRI_EL1 (bit 54) must be initialised to 0b01.
+    - HFGWTR_EL2.nSMPRI_EL1 (bit 54) must be initialised to 0b01.
 
   For CPUs with the Scalable Matrix Extension FA64 feature (FEAT_SME_FA64):
 

Documentation/arch/arm64/sve.rst

@@ -402,6 +402,11 @@ The regset data starts with struct user_sve_header, containing:
   streaming mode and any SETREGSET of NT_ARM_SSVE will enter streaming mode
   if the target was not in streaming mode.
 
+* On systems that do not support SVE it is permitted to use SETREGSET to
+  write SVE_PT_REGS_FPSIMD formatted data via NT_ARM_SVE, in this case the
+  vector length should be specified as 0. This allows streaming mode to be
+  disabled on systems with SME but not SVE.
+
 * If any register data is provided along with SVE_PT_VL_ONEXEC then the
   registers data will be interpreted with the current vector length, not
   the vector length configured for use on exec.

Documentation/arch/s390/s390dbf.rst

@@ -243,9 +243,8 @@ Examples:
 
 Changing the size of debug areas
 ------------------------------------
-It is possible the change the size of debug areas through piping
-the number of pages to the debugfs file "pages". The resize request will
-also flush the debug areas.
+To resize a debug area, write the desired page count to the "pages" file.
+Existing data is preserved if it fits; otherwise, oldest entries are dropped.
 
 Example:
 

Documentation/devicetree/bindings/interrupt-controller/amlogic,meson-gpio-intc.yaml

@@ -39,6 +39,9 @@ properties:
               - amlogic,a4-gpio-ao-intc
               - amlogic,a5-gpio-intc
               - amlogic,c3-gpio-intc
+              - amlogic,s6-gpio-intc
+              - amlogic,s7-gpio-intc
+              - amlogic,s7d-gpio-intc
               - amlogic,t7-gpio-intc
           - const: amlogic,meson-gpio-intc
 

Documentation/devicetree/bindings/interrupt-controller/aspeed,ast2700-intc.yaml

@@ -25,13 +25,14 @@ properties:
   interrupt-controller: true
 
   '#interrupt-cells':
-    const: 2
+    const: 1
     description:
       The first cell is the IRQ number, the second cell is the trigger
       type as defined in interrupt.txt in this directory.
 
   interrupts:
-    maxItems: 6
+    minItems: 1
+    maxItems: 10
     description: |
       Depend to which INTC0 or INTC1 used.
       INTC0 and INTC1 are two kinds of interrupt controller with enable and raw
@@ -74,13 +75,17 @@ examples:
         interrupt-controller@12101b00 {
             compatible = "aspeed,ast2700-intc-ic";
             reg = <0 0x12101b00 0 0x10>;
-            #interrupt-cells = <2>;
+            #interrupt-cells = <1>;
             interrupt-controller;
             interrupts = <GIC_SPI 192 IRQ_TYPE_LEVEL_HIGH>,
                          <GIC_SPI 193 IRQ_TYPE_LEVEL_HIGH>,
                          <GIC_SPI 194 IRQ_TYPE_LEVEL_HIGH>,
                          <GIC_SPI 195 IRQ_TYPE_LEVEL_HIGH>,
                          <GIC_SPI 196 IRQ_TYPE_LEVEL_HIGH>,
-                         <GIC_SPI 197 IRQ_TYPE_LEVEL_HIGH>;
+                         <GIC_SPI 197 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 198 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 199 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 200 IRQ_TYPE_LEVEL_HIGH>,
+                         <GIC_SPI 201 IRQ_TYPE_LEVEL_HIGH>;
         };
     };

Documentation/devicetree/bindings/interrupt-controller/sifive,plic-1.0.0.yaml

@@ -58,6 +58,7 @@ properties:
           - const: andestech,nceplic100
       - items:
           - enum:
+              - anlogic,dr1v90-plic
               - canaan,k210-plic
               - eswin,eic7700-plic
               - sifive,fu540-c000-plic
@@ -75,6 +76,9 @@ properties:
               - sophgo,sg2044-plic
               - thead,th1520-plic
           - const: thead,c900-plic
+      - items:
+          - const: ultrarisc,dp1000-plic
+          - const: ultrarisc,cp100-plic
       - items:
           - const: sifive,plic-1.0.0
           - const: riscv,plic0

Documentation/devicetree/bindings/interrupt-controller/thead,c900-aclint-mswi.yaml

@@ -4,18 +4,23 @@
 $id: http://devicetree.org/schemas/interrupt-controller/thead,c900-aclint-mswi.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
-title: Sophgo sg2042 CLINT Machine-level Software Interrupt Device
+title: ACLINT Machine-level Software Interrupt Device
 
 maintainers:
   - Inochi Amaoto <inochiama@outlook.com>
 
 properties:
   compatible:
-    items:
-      - enum:
-          - sophgo,sg2042-aclint-mswi
-          - sophgo,sg2044-aclint-mswi
-      - const: thead,c900-aclint-mswi
+    oneOf:
+      - items:
+          - enum:
+              - sophgo,sg2042-aclint-mswi
+              - sophgo,sg2044-aclint-mswi
+          - const: thead,c900-aclint-mswi
+      - items:
+          - enum:
+              - anlogic,dr1v90-aclint-mswi
+          - const: nuclei,ux900-aclint-mswi
 
   reg:
     maxItems: 1

Documentation/devicetree/bindings/interrupt-controller/thead,c900-aclint-sswi.yaml

@@ -30,6 +30,10 @@ properties:
           - const: thead,c900-aclint-sswi
       - items:
           - const: mips,p8700-aclint-sswi
+      - items:
+          - enum:
+              - anlogic,dr1v90-aclint-sswi
+          - const: nuclei,ux900-aclint-sswi
 
   reg:
     maxItems: 1

Documentation/devicetree/bindings/perf/fsl-imx-ddr.yaml

@@ -14,6 +14,7 @@ properties:
     oneOf:
       - enum:
           - fsl,imx8-ddr-pmu
+          - fsl,imx8dxl-db-pmu
           - fsl,imx8m-ddr-pmu
           - fsl,imx8mq-ddr-pmu
           - fsl,imx8mm-ddr-pmu
@@ -28,7 +29,10 @@ properties:
               - fsl,imx8mp-ddr-pmu
           - const: fsl,imx8m-ddr-pmu
       - items:
-          - const: fsl,imx8dxl-ddr-pmu
+          - enum:
+              - fsl,imx8dxl-ddr-pmu
+              - fsl,imx8qm-ddr-pmu
+              - fsl,imx8qxp-ddr-pmu
           - const: fsl,imx8-ddr-pmu
       - items:
           - enum:
@@ -43,6 +47,14 @@ properties:
   interrupts:
     maxItems: 1
 
+  clocks:
+    maxItems: 2
+
+  clock-names:
+    items:
+      - const: ipg
+      - const: cnt
+
 required:
   - compatible
   - reg
@@ -50,6 +62,21 @@ required:
 
 additionalProperties: false
 
+allOf:
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: fsl,imx8dxl-db-pmu
+    then:
+      required:
+        - clocks
+        - clock-names
+    else:
+      properties:
+        clocks: false
+        clock-names: false
+
 examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>

Documentation/devicetree/bindings/thermal/fsl,imx91-tmu.yaml

@@ -0,0 +1,87 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/thermal/fsl,imx91-tmu.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: NXP i.MX91 Thermal
+
+maintainers:
+  - Pengfei Li <pengfei.li_1@nxp.com>
+
+description:
+  i.MX91 features a new temperature sensor. It includes programmable
+  temperature threshold comparators for both normal and privileged
+  accesses and allows a programmable measurement frequency for the
+  Periodic One-Shot Measurement mode. Additionally, it provides
+  status registers for indicating the end of measurement and threshold
+  violation events.
+
+properties:
+  compatible:
+    items:
+      - const: fsl,imx91-tmu
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  interrupts:
+    items:
+      - description: Comparator 1 irq
+      - description: Comparator 2 irq
+      - description: Data ready irq
+
+  interrupt-names:
+    items:
+      - const: thr1
+      - const: thr2
+      - const: ready
+
+  nvmem-cells:
+    items:
+      - description: Phandle to the trim control 1 provided by ocotp
+      - description: Phandle to the trim control 2 provided by ocotp
+
+  nvmem-cell-names:
+    items:
+      - const: trim1
+      - const: trim2
+
+  "#thermal-sensor-cells":
+    const: 0
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - interrupts
+  - interrupt-names
+
+allOf:
+  - $ref: thermal-sensor.yaml
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/clock/imx93-clock.h>
+
+    thermal-sensor@44482000 {
+        compatible = "fsl,imx91-tmu";
+        reg = <0x44482000 0x1000>;
+        #thermal-sensor-cells = <0>;
+        clocks = <&clk IMX93_CLK_TMC_GATE>;
+        interrupt-parent = <&gic>;
+        interrupts = <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 85 IRQ_TYPE_LEVEL_HIGH>;
+        interrupt-names = "thr1", "thr2", "ready";
+        nvmem-cells = <&tmu_trim1>, <&tmu_trim2>;
+        nvmem-cell-names = "trim1", "trim2";
+    };
+
+...

Documentation/devicetree/bindings/thermal/qcom-tsens.yaml

@@ -36,10 +36,15 @@ properties:
               - qcom,msm8974-tsens
           - const: qcom,tsens-v0_1
 
+      - description:
+          v1 of TSENS without RPM which requires to be explicitly reset
+          and enabled in the driver.
+        enum:
+          - qcom,ipq5018-tsens
+
       - description: v1 of TSENS
         items:
           - enum:
-              - qcom,ipq5018-tsens
               - qcom,msm8937-tsens
               - qcom,msm8956-tsens
               - qcom,msm8976-tsens
@@ -50,11 +55,13 @@ properties:
         items:
           - enum:
               - qcom,glymur-tsens
+              - qcom,kaanapali-tsens
               - qcom,milos-tsens
               - qcom,msm8953-tsens
               - qcom,msm8996-tsens
               - qcom,msm8998-tsens
               - qcom,qcm2290-tsens
+	      - qcom,qcs8300-tsens
               - qcom,qcs615-tsens
               - qcom,sa8255p-tsens
               - qcom,sa8775p-tsens

Documentation/devicetree/bindings/thermal/renesas,r9a09g047-tsu.yaml

@@ -16,7 +16,11 @@ description:
 
 properties:
   compatible:
-    const: renesas,r9a09g047-tsu
+    oneOf:
+      - const: renesas,r9a09g047-tsu # RZ/G3E
+      - items:
+          - const: renesas,r9a09g057-tsu # RZ/V2H
+          - const: renesas,r9a09g047-tsu # RZ/G3E
 
   reg:
     maxItems: 1

Documentation/devicetree/bindings/timer/realtek,rtd1625-systimer.yaml

@@ -0,0 +1,47 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/timer/realtek,rtd1625-systimer.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Realtek System Timer
+
+maintainers:
+  - Hao-Wen Ting <haowen.ting@realtek.com>
+
+description:
+  The Realtek SYSTIMER (System Timer) is a 64-bit global hardware counter operating
+  at a fixed 1MHz frequency. Thanks to its compare match interrupt capability,
+  the timer natively supports oneshot mode for tick broadcast functionality.
+
+properties:
+  compatible:
+    oneOf:
+      - const: realtek,rtd1625-systimer
+      - items:
+          - const: realtek,rtd1635-systimer
+          - const: realtek,rtd1625-systimer
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - interrupts
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    timer@89420 {
+        compatible = "realtek,rtd1635-systimer",
+                     "realtek,rtd1625-systimer";
+        reg = <0x89420 0x18>;
+        interrupts = <GIC_SPI 112 IRQ_TYPE_LEVEL_HIGH>;
+    };

Documentation/devicetree/bindings/vendor-prefixes.yaml

@@ -1705,6 +1705,8 @@ patternProperties:
     description: Universal Scientific Industrial Co., Ltd.
   "^usr,.*":
     description: U.S. Robotics Corporation
+  "^ultrarisc,.*":
+    description: UltraRISC Technology Co., Ltd.
   "^ultratronik,.*":
     description: Ultratronik GmbH
   "^utoo,.*":

Documentation/driver-api/thermal/intel_dptf.rst

@@ -409,3 +409,26 @@ based on the processor generation.
 		Limit 1 from being exhausted.
 
 	4 – Unknown: Can't classify.
+
+	On processors starting from Panther Lake additional hints are provided.
+	The hardware analyzes workload residencies over an extended period to
+	determine whether the workload classification tends toward idle/battery
+	life states or sustained/performance states. Based on this long-term
+	analysis, it classifies:
+
+	Power Classification: If the workload exhibits more idle or battery life
+	residencies, it is classified as "power".
+
+	Performance Classification: If the workload exhibits more sustained or
+	performance residencies, it is classified as "performance".
+
+	This approach enables applications to ignore short-term workload
+	fluctuations and instead respond to longer-term power vs. performance
+	trends.
+
+	Residency thresholds for this classification are CPU generation-specific.
+	Classification is reported via bit 4 of the workload_type_index:
+
+	Bit 4 = 1: Power classification
+
+	Bit 4 = 0: Performance classification

Documentation/filesystems/resctrl.rst

@@ -17,17 +17,18 @@ AMD refers to this feature as AMD Platform Quality of Service(AMD QoS).
 This feature is enabled by the CONFIG_X86_CPU_RESCTRL and the x86 /proc/cpuinfo
 flag bits:
 
-===============================================	================================
-RDT (Resource Director Technology) Allocation	"rdt_a"
-CAT (Cache Allocation Technology)		"cat_l3", "cat_l2"
-CDP (Code and Data Prioritization)		"cdp_l3", "cdp_l2"
-CQM (Cache QoS Monitoring)			"cqm_llc", "cqm_occup_llc"
-MBM (Memory Bandwidth Monitoring)		"cqm_mbm_total", "cqm_mbm_local"
-MBA (Memory Bandwidth Allocation)		"mba"
-SMBA (Slow Memory Bandwidth Allocation)         ""
-BMEC (Bandwidth Monitoring Event Configuration) ""
-ABMC (Assignable Bandwidth Monitoring Counters) ""
-===============================================	================================
+=============================================================== ================================
+RDT (Resource Director Technology) Allocation			"rdt_a"
+CAT (Cache Allocation Technology)				"cat_l3", "cat_l2"
+CDP (Code and Data Prioritization)				"cdp_l3", "cdp_l2"
+CQM (Cache QoS Monitoring)					"cqm_llc", "cqm_occup_llc"
+MBM (Memory Bandwidth Monitoring)				"cqm_mbm_total", "cqm_mbm_local"
+MBA (Memory Bandwidth Allocation)				"mba"
+SMBA (Slow Memory Bandwidth Allocation)				""
+BMEC (Bandwidth Monitoring Event Configuration)			""
+ABMC (Assignable Bandwidth Monitoring Counters)			""
+SDCIAE (Smart Data Cache Injection Allocation Enforcement)	""
+=============================================================== ================================
 
 Historically, new features were made visible by default in /proc/cpuinfo. This
 resulted in the feature flags becoming hard to parse by humans. Adding a new
@@ -72,6 +73,11 @@ The 'info' directory contains information about the enabled
 resources. Each resource has its own subdirectory. The subdirectory
 names reflect the resource names.
 
+Most of the files in the resource's subdirectory are read-only, and
+describe properties of the resource. Resources that support global
+configuration options also include writable files that can be used
+to modify those settings.
+
 Each subdirectory contains the following files with respect to
 allocation:
 
@@ -90,12 +96,19 @@ related to allocation:
 		must be set when writing a mask.
 
 "shareable_bits":
-		Bitmask of shareable resource with other executing
-		entities (e.g. I/O). User can use this when
-		setting up exclusive cache partitions. Note that
-		some platforms support devices that have their
-		own settings for cache use which can over-ride
-		these bits.
+		Bitmask of shareable resource with other executing entities
+		(e.g. I/O). Applies to all instances of this resource. User
+		can use this when setting up exclusive cache partitions.
+		Note that some platforms support devices that have their
+		own settings for cache use which can over-ride these bits.
+
+		When "io_alloc" is enabled, a portion of each cache instance can
+		be configured for shared use between hardware and software.
+		"bit_usage" should be used to see which portions of each cache
+		instance is configured for hardware use via "io_alloc" feature
+		because every cache instance can have its "io_alloc" bitmask
+		configured independently via "io_alloc_cbm".
+
 "bit_usage":
 		Annotated capacity bitmasks showing how all
 		instances of the resource are used. The legend is:
@@ -109,16 +122,16 @@ related to allocation:
 			"H":
 			      Corresponding region is used by hardware only
 			      but available for software use. If a resource
-			      has bits set in "shareable_bits" but not all
-			      of these bits appear in the resource groups'
-			      schematas then the bits appearing in
-			      "shareable_bits" but no resource group will
-			      be marked as "H".
+			      has bits set in "shareable_bits" or "io_alloc_cbm"
+			      but not all of these bits appear in the resource
+			      groups' schemata then the bits appearing in
+			      "shareable_bits" or "io_alloc_cbm" but no
+			      resource group will be marked as "H".
 			"X":
 			      Corresponding region is available for sharing and
-			      used by hardware and software. These are the
-			      bits that appear in "shareable_bits" as
-			      well as a resource group's allocation.
+			      used by hardware and software. These are the bits
+			      that appear in "shareable_bits" or "io_alloc_cbm"
+			      as well as a resource group's allocation.
 			"S":
 			      Corresponding region is used by software
 			      and available for sharing.
@@ -136,6 +149,77 @@ related to allocation:
 			"1":
 			      Non-contiguous 1s value in CBM is supported.
 
+"io_alloc":
+		"io_alloc" enables system software to configure the portion of
+		the cache allocated for I/O traffic. File may only exist if the
+		system supports this feature on some of its cache resources.
+
+			"disabled":
+			      Resource supports "io_alloc" but the feature is disabled.
+			      Portions of cache used for allocation of I/O traffic cannot
+			      be configured.
+			"enabled":
+			      Portions of cache used for allocation of I/O traffic
+			      can be configured using "io_alloc_cbm".
+			"not supported":
+			      Support not available for this resource.
+
+		The feature can be modified by writing to the interface, for example:
+
+		To enable::
+
+			# echo 1 > /sys/fs/resctrl/info/L3/io_alloc
+
+		To disable::
+
+			# echo 0 > /sys/fs/resctrl/info/L3/io_alloc
+
+		The underlying implementation may reduce resources available to
+		general (CPU) cache allocation. See architecture specific notes
+		below. Depending on usage requirements the feature can be enabled
+		or disabled.
+
+		On AMD systems, io_alloc feature is supported by the L3 Smart
+		Data Cache Injection Allocation Enforcement (SDCIAE). The CLOSID for
+		io_alloc is the highest CLOSID supported by the resource. When
+		io_alloc is enabled, the highest CLOSID is dedicated to io_alloc and
+		no longer available for general (CPU) cache allocation. When CDP is
+		enabled, io_alloc routes I/O traffic using the highest CLOSID allocated
+		for the instruction cache (CDP_CODE), making this CLOSID no longer
+		available for general (CPU) cache allocation for both the CDP_CODE
+		and CDP_DATA resources.
+
+"io_alloc_cbm":
+		Capacity bitmasks that describe the portions of cache instances to
+		which I/O traffic from supported I/O devices are routed when "io_alloc"
+		is enabled.
+
+		CBMs are displayed in the following format:
+
+			<cache_id0>=<cbm>;<cache_id1>=<cbm>;...
+
+		Example::
+
+			# cat /sys/fs/resctrl/info/L3/io_alloc_cbm
+			0=ffff;1=ffff
+
+		CBMs can be configured by writing to the interface.
+
+		Example::
+
+			# echo 1=ff > /sys/fs/resctrl/info/L3/io_alloc_cbm
+			# cat /sys/fs/resctrl/info/L3/io_alloc_cbm
+			0=ffff;1=00ff
+
+			# echo "0=ff;1=f" > /sys/fs/resctrl/info/L3/io_alloc_cbm
+			# cat /sys/fs/resctrl/info/L3/io_alloc_cbm
+			0=00ff;1=000f
+
+		When CDP is enabled "io_alloc_cbm" associated with the CDP_DATA and CDP_CODE
+		resources may reflect the same values. For example, values read from and
+		written to /sys/fs/resctrl/info/L3DATA/io_alloc_cbm may be reflected by
+		/sys/fs/resctrl/info/L3CODE/io_alloc_cbm and vice versa.
+
 Memory bandwidth(MB) subdirectory contains the following files
 with respect to allocation:
 

Documentation/netlink/specs/em.yaml

@@ -0,0 +1,113 @@
+# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
+
+name: em
+
+doc: |
+  Energy model netlink interface to notify its changes.
+
+protocol: genetlink
+
+uapi-header: linux/energy_model.h
+
+attribute-sets:
+  -
+    name: pds
+    attributes:
+      -
+        name: pd
+        type: nest
+        nested-attributes: pd
+        multi-attr: true
+  -
+    name: pd
+    attributes:
+      -
+        name: pad
+        type: pad
+      -
+        name: pd-id
+        type: u32
+      -
+        name: flags
+        type: u64
+      -
+        name: cpus
+        type: string
+  -
+    name: pd-table
+    attributes:
+      -
+        name: pd-id
+        type: u32
+      -
+        name: ps
+        type: nest
+        nested-attributes: ps
+        multi-attr: true
+  -
+    name: ps
+    attributes:
+      -
+        name: pad
+        type: pad
+      -
+        name: performance
+        type: u64
+      -
+        name: frequency
+        type: u64
+      -
+        name: power
+        type: u64
+      -
+        name: cost
+        type: u64
+      -
+        name: flags
+        type: u64
+
+operations:
+  list:
+    -
+      name: get-pds
+      attribute-set: pds
+      doc: Get the list of information for all performance domains.
+      do:
+        reply:
+          attributes:
+            - pd
+    -
+      name: get-pd-table
+      attribute-set: pd-table
+      doc: Get the energy model table of a performance domain.
+      do:
+        request:
+          attributes:
+            - pd-id
+        reply:
+          attributes:
+            - pd-id
+            - ps
+    -
+      name: pd-created
+      doc: A performance domain is created.
+      notify: get-pd-table
+      mcgrp: event
+    -
+      name: pd-updated
+      doc: A performance domain is updated.
+      notify: get-pd-table
+      mcgrp: event
+    -
+      name: pd-deleted
+      doc: A performance domain is deleted.
+      attribute-set: pd-table
+      event:
+        attributes:
+            - pd-id
+      mcgrp: event
+
+mcast-groups:
+  list:
+    -
+      name: event

Documentation/power/index.rst

@@ -19,6 +19,7 @@ Power Management
     power_supply_class
     runtime_pm
     s2ram
+    shutdown-debugging
     suspend-and-cpuhotplug
     suspend-and-interrupts
     swsusp-and-swap-files

Documentation/power/pm_qos_interface.rst

@@ -55,7 +55,8 @@ int cpu_latency_qos_request_active(handle):
 
 From user space:
 
-The infrastructure exposes one device node, /dev/cpu_dma_latency, for the CPU
+The infrastructure exposes two separate device nodes, /dev/cpu_dma_latency for
+the CPU latency QoS and /dev/cpu_wakeup_latency for the CPU system wakeup
 latency QoS.
 
 Only processes can register a PM QoS request.  To provide for automatic
@@ -63,15 +64,15 @@ cleanup of a process, the interface requires the process to register its
 parameter requests as follows.
 
 To register the default PM QoS target for the CPU latency QoS, the process must
-open /dev/cpu_dma_latency.
+open /dev/cpu_dma_latency.  To register a CPU system wakeup QoS limit, the
+process must open /dev/cpu_wakeup_latency.
 
 As long as the device node is held open that process has a registered
 request on the parameter.
 
 To change the requested target value, the process needs to write an s32 value to
 the open device node.  Alternatively, it can write a hex string for the value
-using the 10 char long format e.g. "0x12345678".  This translates to a
-cpu_latency_qos_update_request() call.
+using the 10 char long format e.g. "0x12345678".
 
 To remove the user mode request for a target value simply close the device
 node.

Documentation/power/runtime_pm.rst

@@ -480,16 +480,6 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
   `bool pm_runtime_status_suspended(struct device *dev);`
     - return true if the device's runtime PM status is 'suspended'
 
-  `void pm_runtime_allow(struct device *dev);`
-    - set the power.runtime_auto flag for the device and decrease its usage
-      counter (used by the /sys/devices/.../power/control interface to
-      effectively allow the device to be power managed at run time)
-
-  `void pm_runtime_forbid(struct device *dev);`
-    - unset the power.runtime_auto flag for the device and increase its usage
-      counter (used by the /sys/devices/.../power/control interface to
-      effectively prevent the device from being power managed at run time)
-
   `void pm_runtime_no_callbacks(struct device *dev);`
     - set the power.no_callbacks flag for the device and remove the runtime
       PM attributes from /sys/devices/.../power (or prevent them from being

Documentation/power/shutdown-debugging.rst

@@ -0,0 +1,53 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Debugging Kernel Shutdown Hangs with pstore
++++++++++++++++++++++++++++++++++++++++++++
+
+Overview
+========
+If the system hangs while shutting down, the kernel logs may need to be
+retrieved to debug the issue.
+
+On systems that have a UART available, it is best to configure the kernel to use
+this UART for kernel console output.
+
+If a UART isn't available, the ``pstore`` subsystem provides a mechanism to
+persist this data across a system reset, allowing it to be retrieved on the next
+boot.
+
+Kernel Configuration
+====================
+To enable ``pstore`` and enable saving kernel ring buffer logs, set the
+following kernel configuration options:
+
+* ``CONFIG_PSTORE=y``
+* ``CONFIG_PSTORE_CONSOLE=y``
+
+Additionally, enable a backend to store the data. Depending upon your platform
+some potential options include:
+
+* ``CONFIG_EFI_VARS_PSTORE=y``
+* ``CONFIG_PSTORE_RAM=y``
+* ``CONFIG_CHROMEOS_PSTORE=y``
+* ``CONFIG_PSTORE_BLK=y``
+
+Kernel Command-line Parameters
+==============================
+Add these parameters to your kernel command line:
+
+* ``printk.always_kmsg_dump=Y``
+	* Forces the kernel to dump the entire message buffer to pstore during
+		shutdown
+* ``efi_pstore.pstore_disable=N``
+	* For EFI-based systems, ensures the EFI backend is active
+
+Userspace Interaction and Log Retrieval
+=======================================
+On the next boot after a hang, pstore logs will be available in the pstore
+filesystem (``/sys/fs/pstore``) and can be retrieved by userspace.
+
+On systemd systems, the ``systemd-pstore`` service will help do the following:
+
+#. Locate pstore data in ``/sys/fs/pstore``
+#. Read and save it to ``/var/lib/systemd/pstore``
+#. Clear pstore data for the next event

MAINTAINERS

@@ -9188,6 +9188,9 @@ S:	Maintained
 F:	kernel/power/energy_model.c
 F:	include/linux/energy_model.h
 F:	Documentation/power/energy-model.rst
+F:	Documentation/netlink/specs/em.yaml
+F:	include/uapi/linux/energy_model.h
+F:	kernel/power/em_netlink*.*
 
 EPAPR HYPERVISOR BYTE CHANNEL DEVICE DRIVER
 M:	Laurentiu Tudor <laurentiu.tudor@nxp.com>
@@ -17470,6 +17473,16 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/leds/backlight/mps,mp3309c.yaml
 F:	drivers/video/backlight/mp3309c.c
 
+MPAM DRIVER
+M:	James Morse <james.morse@arm.com>
+M:	Ben Horgan <ben.horgan@arm.com>
+R:	Reinette Chatre <reinette.chatre@intel.com>
+R:	Fenghua Yu <fenghuay@nvidia.com>
+S:	Maintained
+F:	drivers/resctrl/mpam_*
+F:	drivers/resctrl/test_mpam_*
+F:	include/linux/arm_mpam.h
+
 MPS MP2869 DRIVER
 M:	Wensheng Wang <wenswang@yeah.net>
 L:	linux-hwmon@vger.kernel.org
@@ -21681,6 +21694,11 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/spi/realtek,rtl9301-snand.yaml
 F:	drivers/spi/spi-realtek-rtl-snand.c
 
+REALTEK SYSTIMER DRIVER
+M:	Hao-Wen Ting <haowen.ting@realtek.com>
+S:	Maintained
+F:	drivers/clocksource/timer-realtek.c
+
 REALTEK WIRELESS DRIVER (rtlwifi family)
 M:	Ping-Ke Shih <pkshih@realtek.com>
 L:	linux-wireless@vger.kernel.org

arch/arm/include/asm/uaccess.h

@@ -283,10 +283,17 @@ extern int __put_user_8(void *, unsigned long long);
 	__gu_err;							\
 })
 
+/*
+ * This is a type: either unsigned long, if the argument fits into
+ * that type, or otherwise unsigned long long.
+ */
+#define __long_type(x) \
+	__typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL))
+
 #define __get_user_err(x, ptr, err, __t)				\
 do {									\
 	unsigned long __gu_addr = (unsigned long)(ptr);			\
-	unsigned long __gu_val;						\
+	__long_type(x) __gu_val;					\
 	unsigned int __ua_flags;					\
 	__chk_user_ptr(ptr);						\
 	might_fault();							\
@@ -295,6 +302,7 @@ do {									\
 	case 1:	__get_user_asm_byte(__gu_val, __gu_addr, err, __t); break;	\
 	case 2:	__get_user_asm_half(__gu_val, __gu_addr, err, __t); break;	\
 	case 4:	__get_user_asm_word(__gu_val, __gu_addr, err, __t); break;	\
+	case 8:	__get_user_asm_dword(__gu_val, __gu_addr, err, __t); break;	\
 	default: (__gu_val) = __get_user_bad();				\
 	}								\
 	uaccess_restore(__ua_flags);					\
@@ -353,6 +361,22 @@ do {									\
 #define __get_user_asm_word(x, addr, err, __t)			\
 	__get_user_asm(x, addr, err, "ldr" __t)
 
+#ifdef __ARMEB__
+#define __WORD0_OFFS	4
+#define __WORD1_OFFS	0
+#else
+#define __WORD0_OFFS	0
+#define __WORD1_OFFS	4
+#endif
+
+#define __get_user_asm_dword(x, addr, err, __t)				\
+	({								\
+	unsigned long __w0, __w1;					\
+	__get_user_asm(__w0, addr + __WORD0_OFFS, err, "ldr" __t);	\
+	__get_user_asm(__w1, addr + __WORD1_OFFS, err, "ldr" __t);	\
+	(x) = ((u64)__w1 << 32) | (u64) __w0;				\
+})
+
 #define __put_user_switch(x, ptr, __err, __fn)				\
 	do {								\
 		const __typeof__(*(ptr)) __user *__pu_ptr = (ptr);	\

arch/arm64/Kconfig

@@ -47,7 +47,6 @@ config ARM64
 	select ARCH_HAS_SETUP_DMA_OPS
 	select ARCH_HAS_SET_DIRECT_MAP
 	select ARCH_HAS_SET_MEMORY
-	select ARCH_HAS_MEM_ENCRYPT
 	select ARCH_HAS_FORCE_DMA_UNENCRYPTED
 	select ARCH_STACKWALK
 	select ARCH_HAS_STRICT_KERNEL_RWX
@@ -2023,6 +2022,31 @@ config ARM64_TLB_RANGE
 	  ARMv8.4-TLBI provides TLBI invalidation instruction that apply to a
 	  range of input addresses.
 
+config ARM64_MPAM
+	bool "Enable support for MPAM"
+	select ARM64_MPAM_DRIVER if EXPERT	# does nothing yet
+	select ACPI_MPAM if ACPI
+	help
+	  Memory System Resource Partitioning and Monitoring (MPAM) is an
+	  optional extension to the Arm architecture that allows each
+	  transaction issued to the memory system to be labelled with a
+	  Partition identifier (PARTID) and Performance Monitoring Group
+	  identifier (PMG).
+
+	  Memory system components, such as the caches, can be configured with
+	  policies to control how much of various physical resources (such as
+	  memory bandwidth or cache memory) the transactions labelled with each
+	  PARTID can consume.  Depending on the capabilities of the hardware,
+	  the PARTID and PMG can also be used as filtering criteria to measure
+	  the memory system resource consumption of different parts of a
+	  workload.
+
+	  Use of this extension requires CPU support, support in the
+	  Memory System Components (MSC), and a description from firmware
+	  of where the MSCs are in the address space.
+
+	  MPAM is exposed to user-space via the resctrl pseudo filesystem.
+
 endmenu # "ARMv8.4 architectural features"
 
 menu "ARMv8.5 architectural features"

arch/arm64/include/asm/alternative-macros.h

@@ -19,7 +19,7 @@
 #error "cpucaps have overflown ARM64_CB_BIT"
 #endif
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/stringify.h>
 
@@ -207,7 +207,7 @@ alternative_endif
 #define _ALTERNATIVE_CFG(insn1, insn2, cap, cfg, ...)	\
 	alternative_insn insn1, insn2, cap, IS_ENABLED(cfg)
 
-#endif  /*  __ASSEMBLY__  */
+#endif  /*  __ASSEMBLER__  */
 
 /*
  * Usage: asm(ALTERNATIVE(oldinstr, newinstr, cpucap));
@@ -219,7 +219,7 @@ alternative_endif
 #define ALTERNATIVE(oldinstr, newinstr, ...)   \
 	_ALTERNATIVE_CFG(oldinstr, newinstr, __VA_ARGS__, 1)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/types.h>
 
@@ -263,6 +263,6 @@ alternative_has_cap_unlikely(const unsigned long cpucap)
 	return true;
 }
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __ASM_ALTERNATIVE_MACROS_H */

arch/arm64/include/asm/alternative.h

@@ -4,7 +4,7 @@
 
 #include <asm/alternative-macros.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/init.h>
 #include <linux/types.h>
@@ -37,5 +37,5 @@ static inline int apply_alternatives_module(void *start, size_t length)
 void alt_cb_patch_nops(struct alt_instr *alt, __le32 *origptr,
 		       __le32 *updptr, int nr_inst);
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* __ASM_ALTERNATIVE_H */

arch/arm64/include/asm/arch_gicv3.h

@@ -9,7 +9,7 @@
 
 #include <asm/sysreg.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/irqchip/arm-gic-common.h>
 #include <linux/stringify.h>
@@ -188,5 +188,5 @@ static inline bool gic_has_relaxed_pmr_sync(void)
 	return cpus_have_cap(ARM64_HAS_GIC_PRIO_RELAXED_SYNC);
 }
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* __ASM_ARCH_GICV3_H */

arch/arm64/include/asm/asm-extable.h

@@ -27,7 +27,7 @@
 /* Data fields for EX_TYPE_UACCESS_CPY */
 #define EX_DATA_UACCESS_WRITE	BIT(0)
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 #define __ASM_EXTABLE_RAW(insn, fixup, type, data)	\
 	.pushsection	__ex_table, "a";		\
@@ -77,7 +77,7 @@
 	__ASM_EXTABLE_RAW(\insn, \fixup, EX_TYPE_UACCESS_CPY, \uaccess_is_write)
 	.endm
 
-#else /* __ASSEMBLY__ */
+#else /* __ASSEMBLER__ */
 
 #include <linux/stringify.h>
 
@@ -132,6 +132,6 @@
 			    EX_DATA_REG(ADDR, addr)				\
 			  ")")
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __ASM_ASM_EXTABLE_H */

arch/arm64/include/asm/assembler.h

@@ -5,7 +5,7 @@
  * Copyright (C) 1996-2000 Russell King
  * Copyright (C) 2012 ARM Ltd.
  */
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #error "Only include this from assembly code"
 #endif
 
@@ -325,14 +325,14 @@ alternative_cb_end
  * tcr_set_t0sz - update TCR.T0SZ so that we can load the ID map
  */
 	.macro	tcr_set_t0sz, valreg, t0sz
-	bfi	\valreg, \t0sz, #TCR_T0SZ_OFFSET, #TCR_TxSZ_WIDTH
+	bfi	\valreg, \t0sz, #TCR_EL1_T0SZ_SHIFT, #TCR_EL1_T0SZ_WIDTH
 	.endm
 
 /*
  * tcr_set_t1sz - update TCR.T1SZ
  */
 	.macro	tcr_set_t1sz, valreg, t1sz
-	bfi	\valreg, \t1sz, #TCR_T1SZ_OFFSET, #TCR_TxSZ_WIDTH
+	bfi	\valreg, \t1sz, #TCR_EL1_T1SZ_SHIFT, #TCR_EL1_T1SZ_WIDTH
 	.endm
 
 /*
@@ -371,7 +371,7 @@ alternative_endif
  * [start, end) with dcache line size explicitly provided.
  *
  * 	op:		operation passed to dc instruction
- * 	domain:		domain used in dsb instruciton
+ * 	domain:		domain used in dsb instruction
  * 	start:          starting virtual address of the region
  * 	end:            end virtual address of the region
  *	linesz:		dcache line size
@@ -412,7 +412,7 @@ alternative_endif
  * [start, end)
  *
  * 	op:		operation passed to dc instruction
- * 	domain:		domain used in dsb instruciton
+ * 	domain:		domain used in dsb instruction
  * 	start:          starting virtual address of the region
  * 	end:            end virtual address of the region
  * 	fixup:		optional label to branch to on user fault
@@ -589,7 +589,7 @@ alternative_endif
 	.macro	offset_ttbr1, ttbr, tmp
 #if defined(CONFIG_ARM64_VA_BITS_52) && !defined(CONFIG_ARM64_LPA2)
 	mrs	\tmp, tcr_el1
-	and	\tmp, \tmp, #TCR_T1SZ_MASK
+	and	\tmp, \tmp, #TCR_EL1_T1SZ_MASK
 	cmp	\tmp, #TCR_T1SZ(VA_BITS_MIN)
 	orr	\tmp, \ttbr, #TTBR1_BADDR_4852_OFFSET
 	csel	\ttbr, \tmp, \ttbr, eq

arch/arm64/include/asm/atomic_lse.h

@@ -103,17 +103,17 @@ static __always_inline void __lse_atomic_and(int i, atomic_t *v)
 	return __lse_atomic_andnot(~i, v);
 }
 
-#define ATOMIC_FETCH_OP_AND(name, mb, cl...)				\
+#define ATOMIC_FETCH_OP_AND(name)					\
 static __always_inline int						\
 __lse_atomic_fetch_and##name(int i, atomic_t *v)			\
 {									\
 	return __lse_atomic_fetch_andnot##name(~i, v);			\
 }
 
-ATOMIC_FETCH_OP_AND(_relaxed,   )
-ATOMIC_FETCH_OP_AND(_acquire,  a, "memory")
-ATOMIC_FETCH_OP_AND(_release,  l, "memory")
-ATOMIC_FETCH_OP_AND(        , al, "memory")
+ATOMIC_FETCH_OP_AND(_relaxed)
+ATOMIC_FETCH_OP_AND(_acquire)
+ATOMIC_FETCH_OP_AND(_release)
+ATOMIC_FETCH_OP_AND(        )
 
 #undef ATOMIC_FETCH_OP_AND
 
@@ -210,17 +210,17 @@ static __always_inline void __lse_atomic64_and(s64 i, atomic64_t *v)
 	return __lse_atomic64_andnot(~i, v);
 }
 
-#define ATOMIC64_FETCH_OP_AND(name, mb, cl...)				\
+#define ATOMIC64_FETCH_OP_AND(name)					\
 static __always_inline long						\
 __lse_atomic64_fetch_and##name(s64 i, atomic64_t *v)			\
 {									\
 	return __lse_atomic64_fetch_andnot##name(~i, v);		\
 }
 
-ATOMIC64_FETCH_OP_AND(_relaxed,   )
-ATOMIC64_FETCH_OP_AND(_acquire,  a, "memory")
-ATOMIC64_FETCH_OP_AND(_release,  l, "memory")
-ATOMIC64_FETCH_OP_AND(        , al, "memory")
+ATOMIC64_FETCH_OP_AND(_relaxed)
+ATOMIC64_FETCH_OP_AND(_acquire)
+ATOMIC64_FETCH_OP_AND(_release)
+ATOMIC64_FETCH_OP_AND(        )
 
 #undef ATOMIC64_FETCH_OP_AND
 

arch/arm64/include/asm/barrier.h

@@ -7,7 +7,7 @@
 #ifndef __ASM_BARRIER_H
 #define __ASM_BARRIER_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/kasan-checks.h>
 
@@ -221,6 +221,6 @@ do {									\
 
 #include <asm-generic/barrier.h>
 
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 
 #endif	/* __ASM_BARRIER_H */

arch/arm64/include/asm/cache.h

@@ -35,7 +35,7 @@
 #define ARCH_DMA_MINALIGN	(128)
 #define ARCH_KMALLOC_MINALIGN	(8)
 
-#if !defined(__ASSEMBLY__) && !defined(BUILD_VDSO)
+#if !defined(__ASSEMBLER__) && !defined(BUILD_VDSO)
 
 #include <linux/bitops.h>
 #include <linux/kasan-enabled.h>
@@ -135,6 +135,6 @@ static inline u32 __attribute_const__ read_cpuid_effective_cachetype(void)
 	return ctr;
 }
 
-#endif /* !defined(__ASSEMBLY__) && !defined(BUILD_VDSO) */
+#endif /* !defined(__ASSEMBLER__) && !defined(BUILD_VDSO) */
 
 #endif

arch/arm64/include/asm/cpucaps.h

@@ -5,7 +5,7 @@
 
 #include <asm/cpucap-defs.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/types.h>
 /*
  * Check whether a cpucap is possible at compiletime.
@@ -77,6 +77,6 @@ cpucap_is_possible(const unsigned int cap)
 
 	return true;
 }
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __ASM_CPUCAPS_H */

arch/arm64/include/asm/cpufeature.h

@@ -19,7 +19,7 @@
 #define ARM64_SW_FEATURE_OVERRIDE_HVHE		4
 #define ARM64_SW_FEATURE_OVERRIDE_RODATA_OFF	8
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/bug.h>
 #include <linux/jump_label.h>
@@ -199,7 +199,7 @@ extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0;
  *    registers (e.g, SCTLR, TCR etc.) or patching the kernel via
  *    alternatives. The kernel patching is batched and performed at later
  *    point. The actions are always initiated only after the capability
- *    is finalised. This is usally denoted by "enabling" the capability.
+ *    is finalised. This is usually denoted by "enabling" the capability.
  *    The actions are initiated as follows :
  *	a) Action is triggered on all online CPUs, after the capability is
  *	finalised, invoked within the stop_machine() context from
@@ -251,7 +251,7 @@ extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0;
 #define ARM64_CPUCAP_SCOPE_LOCAL_CPU		((u16)BIT(0))
 #define ARM64_CPUCAP_SCOPE_SYSTEM		((u16)BIT(1))
 /*
- * The capabilitiy is detected on the Boot CPU and is used by kernel
+ * The capability is detected on the Boot CPU and is used by kernel
  * during early boot. i.e, the capability should be "detected" and
  * "enabled" as early as possibly on all booting CPUs.
  */
@@ -1078,6 +1078,6 @@ static inline bool cpu_has_lpa2(void)
 #endif
 }
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif

arch/arm64/include/asm/cputype.h

@@ -247,9 +247,9 @@
 /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */
 #define MIDR_FUJITSU_ERRATUM_010001		MIDR_FUJITSU_A64FX
 #define MIDR_FUJITSU_ERRATUM_010001_MASK	(~MIDR_CPU_VAR_REV(1, 0))
-#define TCR_CLEAR_FUJITSU_ERRATUM_010001	(TCR_NFD1 | TCR_NFD0)
+#define TCR_CLEAR_FUJITSU_ERRATUM_010001	(TCR_EL1_NFD1 | TCR_EL1_NFD0)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/sysreg.h>
 
@@ -328,6 +328,6 @@ static inline u32 __attribute_const__ read_cpuid_cachetype(void)
 {
 	return read_cpuid(CTR_EL0);
 }
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif

arch/arm64/include/asm/current.h

@@ -4,7 +4,7 @@
 
 #include <linux/compiler.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 struct task_struct;
 
@@ -23,7 +23,7 @@ static __always_inline struct task_struct *get_current(void)
 
 #define current get_current()
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __ASM_CURRENT_H */
 

arch/arm64/include/asm/debug-monitors.h

@@ -48,7 +48,7 @@
 #define AARCH32_BREAK_THUMB2_LO	0xf7f0
 #define AARCH32_BREAK_THUMB2_HI	0xa000
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 struct task_struct;
 
 #define DBG_ARCH_ID_RESERVED	0	/* In case of ptrace ABI updates. */
@@ -88,5 +88,5 @@ static inline bool try_step_suspended_breakpoints(struct pt_regs *regs)
 
 bool try_handle_aarch32_break(struct pt_regs *regs);
 
-#endif	/* __ASSEMBLY */
+#endif	/* __ASSEMBLER__ */
 #endif	/* __ASM_DEBUG_MONITORS_H */

arch/arm64/include/asm/efi.h

@@ -126,21 +126,14 @@ static inline void efi_set_pgd(struct mm_struct *mm)
 		if (mm != current->active_mm) {
 			/*
 			 * Update the current thread's saved ttbr0 since it is
-			 * restored as part of a return from exception. Enable
-			 * access to the valid TTBR0_EL1 and invoke the errata
-			 * workaround directly since there is no return from
-			 * exception when invoking the EFI run-time services.
+			 * restored as part of a return from exception.
 			 */
 			update_saved_ttbr0(current, mm);
-			uaccess_ttbr0_enable();
-			post_ttbr_update_workaround();
 		} else {
 			/*
-			 * Defer the switch to the current thread's TTBR0_EL1
-			 * until uaccess_enable(). Restore the current
-			 * thread's saved ttbr0 corresponding to its active_mm
+			 * Restore the current thread's saved ttbr0
+			 * corresponding to its active_mm
 			 */
-			uaccess_ttbr0_disable();
 			update_saved_ttbr0(current, current->active_mm);
 		}
 	}

arch/arm64/include/asm/el2_setup.h

@@ -7,7 +7,7 @@
 #ifndef __ARM_KVM_INIT_H__
 #define __ARM_KVM_INIT_H__
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #error Assembly-only header
 #endif
 
@@ -24,7 +24,7 @@
 	 * ID_AA64MMFR4_EL1.E2H0 < 0. On such CPUs HCR_EL2.E2H is RES1, but it
 	 * can reset into an UNKNOWN state and might not read as 1 until it has
 	 * been initialized explicitly.
-	 * Initalize HCR_EL2.E2H so that later code can rely upon HCR_EL2.E2H
+	 * Initialize HCR_EL2.E2H so that later code can rely upon HCR_EL2.E2H
 	 * indicating whether the CPU is running in E2H mode.
 	 */
 	mrs_s	x1, SYS_ID_AA64MMFR4_EL1

arch/arm64/include/asm/elf.h

@@ -133,7 +133,7 @@
 #define ELF_ET_DYN_BASE		(2 * DEFAULT_MAP_WINDOW_64 / 3)
 #endif /* CONFIG_ARM64_FORCE_52BIT */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <uapi/linux/elf.h>
 #include <linux/bug.h>
@@ -293,6 +293,6 @@ static inline int arch_check_elf(void *ehdr, bool has_interp,
 	return 0;
 }
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif

arch/arm64/include/asm/esr.h

@@ -431,7 +431,7 @@
 #define ESR_ELx_IT_GCSPOPCX		6
 #define ESR_ELx_IT_GCSPOPX		7
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <asm/types.h>
 
 static inline unsigned long esr_brk_comment(unsigned long esr)
@@ -534,6 +534,6 @@ static inline bool esr_iss_is_eretab(unsigned long esr)
 }
 
 const char *esr_get_class_string(unsigned long esr);
-#endif /* __ASSEMBLY */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __ASM_ESR_H */

arch/arm64/include/asm/fixmap.h

@@ -15,7 +15,7 @@
 #ifndef _ASM_ARM64_FIXMAP_H
 #define _ASM_ARM64_FIXMAP_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/kernel.h>
 #include <linux/math.h>
 #include <linux/sizes.h>
@@ -117,5 +117,5 @@ extern void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t pr
 
 #include <asm-generic/fixmap.h>
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 #endif /* _ASM_ARM64_FIXMAP_H */

arch/arm64/include/asm/fpsimd.h

@@ -12,7 +12,7 @@
 #include <asm/sigcontext.h>
 #include <asm/sysreg.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/bitmap.h>
 #include <linux/build_bug.h>

arch/arm64/include/asm/ftrace.h

@@ -37,7 +37,7 @@
  */
 #define ARCH_FTRACE_SHIFT_STACK_TRACER 1
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/compat.h>
 
 extern void _mcount(unsigned long);
@@ -217,9 +217,9 @@ static inline bool arch_syscall_match_sym_name(const char *sym,
 	 */
 	return !strcmp(sym + 8, name);
 }
-#endif /* ifndef __ASSEMBLY__ */
+#endif /* ifndef __ASSEMBLER__ */
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
 void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,

arch/arm64/include/asm/gpr-num.h

@@ -2,7 +2,7 @@
 #ifndef __ASM_GPR_NUM_H
 #define __ASM_GPR_NUM_H
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 	.irp	num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30
 	.equ	.L__gpr_num_x\num, \num
@@ -11,7 +11,7 @@
 	.equ	.L__gpr_num_xzr, 31
 	.equ	.L__gpr_num_wzr, 31
 
-#else /* __ASSEMBLY__ */
+#else /* __ASSEMBLER__ */
 
 #define __DEFINE_ASM_GPR_NUMS					\
 "	.irp	num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30\n" \
@@ -21,6 +21,6 @@
 "	.equ	.L__gpr_num_xzr, 31\n"				\
 "	.equ	.L__gpr_num_wzr, 31\n"
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __ASM_GPR_NUM_H */

arch/arm64/include/asm/hwcap.h

@@ -46,7 +46,7 @@
 #define COMPAT_HWCAP2_SB	(1 << 5)
 #define COMPAT_HWCAP2_SSBS	(1 << 6)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/log2.h>
 
 /*

arch/arm64/include/asm/image.h

@@ -20,7 +20,7 @@
 #define ARM64_IMAGE_FLAG_PAGE_SIZE_64K		3
 #define ARM64_IMAGE_FLAG_PHYS_BASE		1
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #define arm64_image_flag_field(flags, field) \
 				(((flags) >> field##_SHIFT) & field##_MASK)
@@ -54,6 +54,6 @@ struct arm64_image_header {
 	__le32 res5;
 };
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __ASM_IMAGE_H */

arch/arm64/include/asm/insn.h

@@ -12,7 +12,7 @@
 
 #include <asm/insn-def.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 enum aarch64_insn_hint_cr_op {
 	AARCH64_INSN_HINT_NOP	= 0x0 << 5,
@@ -730,6 +730,6 @@ u32 aarch32_insn_mcr_extract_crm(u32 insn);
 typedef bool (pstate_check_t)(unsigned long);
 extern pstate_check_t * const aarch32_opcode_cond_checks[16];
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif	/* __ASM_INSN_H */

arch/arm64/include/asm/jump_label.h

@@ -8,7 +8,7 @@
 #ifndef __ASM_JUMP_LABEL_H
 #define __ASM_JUMP_LABEL_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/types.h>
 #include <asm/insn.h>
@@ -58,5 +58,5 @@ static __always_inline bool arch_static_branch_jump(struct static_key * const ke
 	return true;
 }
 
-#endif  /* __ASSEMBLY__ */
+#endif  /* __ASSEMBLER__ */
 #endif	/* __ASM_JUMP_LABEL_H */

arch/arm64/include/asm/kasan.h

@@ -2,7 +2,7 @@
 #ifndef __ASM_KASAN_H
 #define __ASM_KASAN_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/linkage.h>
 #include <asm/memory.h>

arch/arm64/include/asm/kexec.h

@@ -25,7 +25,7 @@
 
 #define KEXEC_ARCH KEXEC_ARCH_AARCH64
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 /**
  * crash_setup_regs() - save registers for the panic kernel
@@ -130,6 +130,6 @@ extern int load_other_segments(struct kimage *image,
 		char *cmdline);
 #endif
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif

arch/arm64/include/asm/kgdb.h

@@ -14,7 +14,7 @@
 #include <linux/ptrace.h>
 #include <asm/debug-monitors.h>
 
-#ifndef	__ASSEMBLY__
+#ifndef	__ASSEMBLER__
 
 static inline void arch_kgdb_breakpoint(void)
 {
@@ -36,7 +36,7 @@ static inline int kgdb_single_step_handler(struct pt_regs *regs,
 }
 #endif
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 /*
  * gdb remote procotol (well most versions of it) expects the following

arch/arm64/include/asm/kvm_asm.h

@@ -46,7 +46,7 @@
 
 #define __KVM_HOST_SMCCC_FUNC___kvm_hyp_init			0
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/mm.h>
 
@@ -303,7 +303,7 @@ void kvm_compute_final_ctr_el0(struct alt_instr *alt,
 void __noreturn __cold nvhe_hyp_panic_handler(u64 esr, u64 spsr, u64 elr_virt,
 	u64 elr_phys, u64 par, uintptr_t vcpu, u64 far, u64 hpfar);
 
-#else /* __ASSEMBLY__ */
+#else /* __ASSEMBLER__ */
 
 .macro get_host_ctxt reg, tmp
 	adr_this_cpu \reg, kvm_host_data, \tmp

arch/arm64/include/asm/kvm_mmu.h

@@ -49,7 +49,7 @@
  * mappings, and none of this applies in that case.
  */
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 #include <asm/alternative.h>
 
@@ -396,5 +396,5 @@ void kvm_s2_ptdump_create_debugfs(struct kvm *kvm);
 static inline void kvm_s2_ptdump_create_debugfs(struct kvm *kvm) {}
 #endif /* CONFIG_PTDUMP_STAGE2_DEBUGFS */
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* __ARM64_KVM_MMU_H__ */

arch/arm64/include/asm/kvm_mte.h

@@ -5,7 +5,7 @@
 #ifndef __ASM_KVM_MTE_H
 #define __ASM_KVM_MTE_H
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 #include <asm/sysreg.h>
 
@@ -62,5 +62,5 @@ alternative_else_nop_endif
 .endm
 
 #endif /* CONFIG_ARM64_MTE */
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* __ASM_KVM_MTE_H */

arch/arm64/include/asm/kvm_ptrauth.h

@@ -8,7 +8,7 @@
 #ifndef __ASM_KVM_PTRAUTH_H
 #define __ASM_KVM_PTRAUTH_H
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 #include <asm/sysreg.h>
 
@@ -100,7 +100,7 @@ alternative_else_nop_endif
 .endm
 #endif /* CONFIG_ARM64_PTR_AUTH */
 
-#else  /* !__ASSEMBLY */
+#else  /* !__ASSEMBLER__ */
 
 #define __ptrauth_save_key(ctxt, key)					\
 	do {								\
@@ -120,5 +120,5 @@ alternative_else_nop_endif
 		__ptrauth_save_key(ctxt, APGA);				\
 	} while(0)
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* __ASM_KVM_PTRAUTH_H */

arch/arm64/include/asm/linkage.h

@@ -1,7 +1,7 @@
 #ifndef __ASM_LINKAGE_H
 #define __ASM_LINKAGE_H
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #include <asm/assembler.h>
 #endif
 

arch/arm64/include/asm/memory.h

@@ -207,7 +207,7 @@
  */
 #define TRAMP_SWAPPER_OFFSET	(2 * PAGE_SIZE)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/bitops.h>
 #include <linux/compiler.h>
@@ -392,7 +392,6 @@ static inline unsigned long virt_to_pfn(const void *kaddr)
  *  virt_to_page(x)	convert a _valid_ virtual address to struct page *
  *  virt_addr_valid(x)	indicates whether a virtual address is valid
  */
-#define ARCH_PFN_OFFSET		((unsigned long)PHYS_PFN_OFFSET)
 
 #if defined(CONFIG_DEBUG_VIRTUAL)
 #define page_to_virt(x)	({						\
@@ -422,7 +421,7 @@ static inline unsigned long virt_to_pfn(const void *kaddr)
 })
 
 void dump_mem_limit(void);
-#endif /* !ASSEMBLY */
+#endif /* !__ASSEMBLER__ */
 
 /*
  * Given that the GIC architecture permits ITS implementations that can only be

arch/arm64/include/asm/mmu.h

@@ -12,7 +12,7 @@
 #define USER_ASID_FLAG	(UL(1) << USER_ASID_BIT)
 #define TTBR_ASID_MASK	(UL(0xffff) << 48)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/refcount.h>
 #include <asm/cpufeature.h>
@@ -112,5 +112,5 @@ void kpti_install_ng_mappings(void);
 static inline void kpti_install_ng_mappings(void) {}
 #endif
 
-#endif	/* !__ASSEMBLY__ */
+#endif	/* !__ASSEMBLER__ */
 #endif

arch/arm64/include/asm/mmu_context.h

@@ -8,7 +8,7 @@
 #ifndef __ASM_MMU_CONTEXT_H
 #define __ASM_MMU_CONTEXT_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/compiler.h>
 #include <linux/sched.h>
@@ -61,11 +61,6 @@ static inline void cpu_switch_mm(pgd_t *pgd, struct mm_struct *mm)
 	cpu_do_switch_mm(virt_to_phys(pgd),mm);
 }
 
-/*
- * TCR.T0SZ value to use when the ID map is active.
- */
-#define idmap_t0sz	TCR_T0SZ(IDMAP_VA_BITS)
-
 /*
  * Ensure TCR.T0SZ is set to the provided value.
  */
@@ -73,18 +68,15 @@ static inline void __cpu_set_tcr_t0sz(unsigned long t0sz)
 {
 	unsigned long tcr = read_sysreg(tcr_el1);
 
-	if ((tcr & TCR_T0SZ_MASK) == t0sz)
+	if ((tcr & TCR_EL1_T0SZ_MASK) == t0sz)
 		return;
 
-	tcr &= ~TCR_T0SZ_MASK;
+	tcr &= ~TCR_EL1_T0SZ_MASK;
 	tcr |= t0sz;
 	write_sysreg(tcr, tcr_el1);
 	isb();
 }
 
-#define cpu_set_default_tcr_t0sz()	__cpu_set_tcr_t0sz(TCR_T0SZ(vabits_actual))
-#define cpu_set_idmap_tcr_t0sz()	__cpu_set_tcr_t0sz(idmap_t0sz)
-
 /*
  * Remove the idmap from TTBR0_EL1 and install the pgd of the active mm.
  *
@@ -103,7 +95,7 @@ static inline void cpu_uninstall_idmap(void)
 
 	cpu_set_reserved_ttbr0();
 	local_flush_tlb_all();
-	cpu_set_default_tcr_t0sz();
+	__cpu_set_tcr_t0sz(TCR_T0SZ(vabits_actual));
 
 	if (mm != &init_mm && !system_uses_ttbr0_pan())
 		cpu_switch_mm(mm->pgd, mm);
@@ -113,7 +105,7 @@ static inline void cpu_install_idmap(void)
 {
 	cpu_set_reserved_ttbr0();
 	local_flush_tlb_all();
-	cpu_set_idmap_tcr_t0sz();
+	__cpu_set_tcr_t0sz(TCR_T0SZ(IDMAP_VA_BITS));
 
 	cpu_switch_mm(lm_alias(idmap_pg_dir), &init_mm);
 }
@@ -330,6 +322,6 @@ static inline void deactivate_mm(struct task_struct *tsk,
 
 #include <asm-generic/mmu_context.h>
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* !__ASM_MMU_CONTEXT_H */

arch/arm64/include/asm/mte-kasan.h

@@ -9,7 +9,7 @@
 #include <asm/cputype.h>
 #include <asm/mte-def.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/types.h>
 
@@ -259,6 +259,6 @@ static inline int mte_enable_kernel_store_only(void)
 
 #endif /* CONFIG_ARM64_MTE */
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __ASM_MTE_KASAN_H  */

arch/arm64/include/asm/mte.h

@@ -8,7 +8,7 @@
 #include <asm/compiler.h>
 #include <asm/mte-def.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/bitfield.h>
 #include <linux/kasan-enabled.h>
@@ -282,5 +282,5 @@ static inline void mte_check_tfsr_exit(void)
 }
 #endif /* CONFIG_KASAN_HW_TAGS */
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* __ASM_MTE_H  */

arch/arm64/include/asm/page.h

@@ -10,7 +10,7 @@
 
 #include <asm/page-def.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/personality.h> /* for READ_IMPLIES_EXEC */
 #include <linux/types.h> /* for gfp_t */
@@ -45,7 +45,7 @@ int pfn_is_map_memory(unsigned long pfn);
 
 #include <asm/memory.h>
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #define VM_DATA_DEFAULT_FLAGS	(VM_DATA_FLAGS_TSK_EXEC | VM_MTE_ALLOWED)
 

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

@@ -228,102 +228,53 @@
 /*
  * TCR flags.
  */
-#define TCR_T0SZ_OFFSET		0
-#define TCR_T1SZ_OFFSET		16
-#define TCR_T0SZ(x)		((UL(64) - (x)) << TCR_T0SZ_OFFSET)
-#define TCR_T1SZ(x)		((UL(64) - (x)) << TCR_T1SZ_OFFSET)
-#define TCR_TxSZ(x)		(TCR_T0SZ(x) | TCR_T1SZ(x))
-#define TCR_TxSZ_WIDTH		6
-#define TCR_T0SZ_MASK		(((UL(1) << TCR_TxSZ_WIDTH) - 1) << TCR_T0SZ_OFFSET)
-#define TCR_T1SZ_MASK		(((UL(1) << TCR_TxSZ_WIDTH) - 1) << TCR_T1SZ_OFFSET)
+#define TCR_T0SZ(x)		((UL(64) - (x)) << TCR_EL1_T0SZ_SHIFT)
+#define TCR_T1SZ(x)		((UL(64) - (x)) << TCR_EL1_T1SZ_SHIFT)
 
-#define TCR_EPD0_SHIFT		7
-#define TCR_EPD0_MASK		(UL(1) << TCR_EPD0_SHIFT)
-#define TCR_IRGN0_SHIFT		8
-#define TCR_IRGN0_MASK		(UL(3) << TCR_IRGN0_SHIFT)
-#define TCR_IRGN0_NC		(UL(0) << TCR_IRGN0_SHIFT)
-#define TCR_IRGN0_WBWA		(UL(1) << TCR_IRGN0_SHIFT)
-#define TCR_IRGN0_WT		(UL(2) << TCR_IRGN0_SHIFT)
-#define TCR_IRGN0_WBnWA		(UL(3) << TCR_IRGN0_SHIFT)
+#define TCR_T0SZ_MASK		TCR_EL1_T0SZ_MASK
+#define TCR_T1SZ_MASK		TCR_EL1_T1SZ_MASK
 
-#define TCR_EPD1_SHIFT		23
-#define TCR_EPD1_MASK		(UL(1) << TCR_EPD1_SHIFT)
-#define TCR_IRGN1_SHIFT		24
-#define TCR_IRGN1_MASK		(UL(3) << TCR_IRGN1_SHIFT)
-#define TCR_IRGN1_NC		(UL(0) << TCR_IRGN1_SHIFT)
-#define TCR_IRGN1_WBWA		(UL(1) << TCR_IRGN1_SHIFT)
-#define TCR_IRGN1_WT		(UL(2) << TCR_IRGN1_SHIFT)
-#define TCR_IRGN1_WBnWA		(UL(3) << TCR_IRGN1_SHIFT)
+#define TCR_EPD0_MASK		TCR_EL1_EPD0_MASK
+#define TCR_EPD1_MASK		TCR_EL1_EPD1_MASK
 
-#define TCR_IRGN_NC		(TCR_IRGN0_NC | TCR_IRGN1_NC)
-#define TCR_IRGN_WBWA		(TCR_IRGN0_WBWA | TCR_IRGN1_WBWA)
-#define TCR_IRGN_WT		(TCR_IRGN0_WT | TCR_IRGN1_WT)
-#define TCR_IRGN_WBnWA		(TCR_IRGN0_WBnWA | TCR_IRGN1_WBnWA)
-#define TCR_IRGN_MASK		(TCR_IRGN0_MASK | TCR_IRGN1_MASK)
+#define TCR_IRGN0_MASK		TCR_EL1_IRGN0_MASK
+#define TCR_IRGN0_WBWA		(TCR_EL1_IRGN0_WBWA << TCR_EL1_IRGN0_SHIFT)
 
+#define TCR_ORGN0_MASK		TCR_EL1_ORGN0_MASK
+#define TCR_ORGN0_WBWA		(TCR_EL1_ORGN0_WBWA << TCR_EL1_ORGN0_SHIFT)
 
-#define TCR_ORGN0_SHIFT		10
-#define TCR_ORGN0_MASK		(UL(3) << TCR_ORGN0_SHIFT)
-#define TCR_ORGN0_NC		(UL(0) << TCR_ORGN0_SHIFT)
-#define TCR_ORGN0_WBWA		(UL(1) << TCR_ORGN0_SHIFT)
-#define TCR_ORGN0_WT		(UL(2) << TCR_ORGN0_SHIFT)
-#define TCR_ORGN0_WBnWA		(UL(3) << TCR_ORGN0_SHIFT)
+#define TCR_SH0_MASK		TCR_EL1_SH0_MASK
+#define TCR_SH0_INNER		(TCR_EL1_SH0_INNER << TCR_EL1_SH0_SHIFT)
 
-#define TCR_ORGN1_SHIFT		26
-#define TCR_ORGN1_MASK		(UL(3) << TCR_ORGN1_SHIFT)
-#define TCR_ORGN1_NC		(UL(0) << TCR_ORGN1_SHIFT)
-#define TCR_ORGN1_WBWA		(UL(1) << TCR_ORGN1_SHIFT)
-#define TCR_ORGN1_WT		(UL(2) << TCR_ORGN1_SHIFT)
-#define TCR_ORGN1_WBnWA		(UL(3) << TCR_ORGN1_SHIFT)
+#define TCR_SH1_MASK		TCR_EL1_SH1_MASK
 
-#define TCR_ORGN_NC		(TCR_ORGN0_NC | TCR_ORGN1_NC)
-#define TCR_ORGN_WBWA		(TCR_ORGN0_WBWA | TCR_ORGN1_WBWA)
-#define TCR_ORGN_WT		(TCR_ORGN0_WT | TCR_ORGN1_WT)
-#define TCR_ORGN_WBnWA		(TCR_ORGN0_WBnWA | TCR_ORGN1_WBnWA)
-#define TCR_ORGN_MASK		(TCR_ORGN0_MASK | TCR_ORGN1_MASK)
+#define TCR_TG0_SHIFT		TCR_EL1_TG0_SHIFT
+#define TCR_TG0_MASK		TCR_EL1_TG0_MASK
+#define TCR_TG0_4K		(TCR_EL1_TG0_4K << TCR_EL1_TG0_SHIFT)
+#define TCR_TG0_64K		(TCR_EL1_TG0_64K << TCR_EL1_TG0_SHIFT)
+#define TCR_TG0_16K		(TCR_EL1_TG0_16K << TCR_EL1_TG0_SHIFT)
 
-#define TCR_SH0_SHIFT		12
-#define TCR_SH0_MASK		(UL(3) << TCR_SH0_SHIFT)
-#define TCR_SH0_INNER		(UL(3) << TCR_SH0_SHIFT)
+#define TCR_TG1_SHIFT		TCR_EL1_TG1_SHIFT
+#define TCR_TG1_MASK		TCR_EL1_TG1_MASK
+#define TCR_TG1_16K		(TCR_EL1_TG1_16K << TCR_EL1_TG1_SHIFT)
+#define TCR_TG1_4K		(TCR_EL1_TG1_4K << TCR_EL1_TG1_SHIFT)
+#define TCR_TG1_64K		(TCR_EL1_TG1_64K << TCR_EL1_TG1_SHIFT)
 
-#define TCR_SH1_SHIFT		28
-#define TCR_SH1_MASK		(UL(3) << TCR_SH1_SHIFT)
-#define TCR_SH1_INNER		(UL(3) << TCR_SH1_SHIFT)
-#define TCR_SHARED		(TCR_SH0_INNER | TCR_SH1_INNER)
-
-#define TCR_TG0_SHIFT		14
-#define TCR_TG0_MASK		(UL(3) << TCR_TG0_SHIFT)
-#define TCR_TG0_4K		(UL(0) << TCR_TG0_SHIFT)
-#define TCR_TG0_64K		(UL(1) << TCR_TG0_SHIFT)
-#define TCR_TG0_16K		(UL(2) << TCR_TG0_SHIFT)
-
-#define TCR_TG1_SHIFT		30
-#define TCR_TG1_MASK		(UL(3) << TCR_TG1_SHIFT)
-#define TCR_TG1_16K		(UL(1) << TCR_TG1_SHIFT)
-#define TCR_TG1_4K		(UL(2) << TCR_TG1_SHIFT)
-#define TCR_TG1_64K		(UL(3) << TCR_TG1_SHIFT)
-
-#define TCR_IPS_SHIFT		32
-#define TCR_IPS_MASK		(UL(7) << TCR_IPS_SHIFT)
-#define TCR_A1			(UL(1) << 22)
-#define TCR_ASID16		(UL(1) << 36)
-#define TCR_TBI0		(UL(1) << 37)
-#define TCR_TBI1		(UL(1) << 38)
-#define TCR_HA			(UL(1) << 39)
-#define TCR_HD			(UL(1) << 40)
-#define TCR_HPD0_SHIFT		41
-#define TCR_HPD0		(UL(1) << TCR_HPD0_SHIFT)
-#define TCR_HPD1_SHIFT		42
-#define TCR_HPD1		(UL(1) << TCR_HPD1_SHIFT)
-#define TCR_TBID0		(UL(1) << 51)
-#define TCR_TBID1		(UL(1) << 52)
-#define TCR_NFD0		(UL(1) << 53)
-#define TCR_NFD1		(UL(1) << 54)
-#define TCR_E0PD0		(UL(1) << 55)
-#define TCR_E0PD1		(UL(1) << 56)
-#define TCR_TCMA0		(UL(1) << 57)
-#define TCR_TCMA1		(UL(1) << 58)
-#define TCR_DS			(UL(1) << 59)
+#define TCR_IPS_SHIFT		TCR_EL1_IPS_SHIFT
+#define TCR_IPS_MASK		TCR_EL1_IPS_MASK
+#define TCR_A1			TCR_EL1_A1
+#define TCR_ASID16		TCR_EL1_AS
+#define TCR_TBI0		TCR_EL1_TBI0
+#define TCR_TBI1		TCR_EL1_TBI1
+#define TCR_HA			TCR_EL1_HA
+#define TCR_HD			TCR_EL1_HD
+#define TCR_HPD0		TCR_EL1_HPD0
+#define TCR_HPD1		TCR_EL1_HPD1
+#define TCR_TBID0		TCR_EL1_TBID0
+#define TCR_TBID1		TCR_EL1_TBID1
+#define TCR_E0PD0		TCR_EL1_E0PD0
+#define TCR_E0PD1		TCR_EL1_E0PD1
+#define TCR_DS			TCR_EL1_DS
 
 /*
  * TTBR.

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

@@ -62,7 +62,7 @@
 #define _PAGE_READONLY_EXEC	(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN)
 #define _PAGE_EXECONLY		(_PAGE_DEFAULT | PTE_RDONLY | PTE_NG | PTE_PXN)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/cpufeature.h>
 #include <asm/pgtable-types.h>
@@ -84,7 +84,7 @@ extern unsigned long prot_ns_shared;
 #else
 static inline bool __pure lpa2_is_enabled(void)
 {
-	return read_tcr() & TCR_DS;
+	return read_tcr() & TCR_EL1_DS;
 }
 
 #define PTE_MAYBE_SHARED	(lpa2_is_enabled() ? 0 : PTE_SHARED)
@@ -127,7 +127,7 @@ static inline bool __pure lpa2_is_enabled(void)
 #define PAGE_READONLY_EXEC	__pgprot(_PAGE_READONLY_EXEC)
 #define PAGE_EXECONLY		__pgprot(_PAGE_EXECONLY)
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #define pte_pi_index(pte) ( \
 	((pte & BIT(PTE_PI_IDX_3)) >> (PTE_PI_IDX_3 - 3)) | \

arch/arm64/include/asm/pgtable.h

@@ -30,7 +30,7 @@
 
 #define vmemmap			((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT))
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/cmpxchg.h>
 #include <asm/fixmap.h>
@@ -130,12 +130,16 @@ static inline void arch_leave_lazy_mmu_mode(void)
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 /*
- * Outside of a few very special situations (e.g. hibernation), we always
- * use broadcast TLB invalidation instructions, therefore a spurious page
- * fault on one CPU which has been handled concurrently by another CPU
- * does not need to perform additional invalidation.
+ * We use local TLB invalidation instruction when reusing page in
+ * write protection fault handler to avoid TLBI broadcast in the hot
+ * path.  This will cause spurious page faults if stale read-only TLB
+ * entries exist.
  */
-#define flush_tlb_fix_spurious_fault(vma, address, ptep) do { } while (0)
+#define flush_tlb_fix_spurious_fault(vma, address, ptep)	\
+	local_flush_tlb_page_nonotify(vma, address)
+
+#define flush_tlb_fix_spurious_fault_pmd(vma, address, pmdp)	\
+	local_flush_tlb_page_nonotify(vma, address)
 
 /*
  * ZERO_PAGE is a global shared page that is always zero: used
@@ -433,7 +437,7 @@ bool pgattr_change_is_safe(pteval_t old, pteval_t new);
  *   1      0      |   1           0          1
  *   1      1      |   0           1          x
  *
- * When hardware DBM is not present, the sofware PTE_DIRTY bit is updated via
+ * When hardware DBM is not present, the software PTE_DIRTY bit is updated via
  * the page fault mechanism. Checking the dirty status of a pte becomes:
  *
  *   PTE_DIRTY || (PTE_WRITE && !PTE_RDONLY)
@@ -599,7 +603,7 @@ static inline int pte_protnone(pte_t pte)
 	/*
 	 * pte_present_invalid() tells us that the pte is invalid from HW
 	 * perspective but present from SW perspective, so the fields are to be
-	 * interpretted as per the HW layout. The second 2 checks are the unique
+	 * interpreted as per the HW layout. The second 2 checks are the unique
 	 * encoding that we use for PROT_NONE. It is insufficient to only use
 	 * the first check because we share the same encoding scheme with pmds
 	 * which support pmd_mkinvalid(), so can be present-invalid without
@@ -1949,6 +1953,6 @@ static inline void clear_young_dirty_ptes(struct vm_area_struct *vma,
 
 #endif /* CONFIG_ARM64_CONTPTE */
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __ASM_PGTABLE_H */

arch/arm64/include/asm/proc-fns.h

@@ -9,7 +9,7 @@
 #ifndef __ASM_PROCFNS_H
 #define __ASM_PROCFNS_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/page.h>
 
@@ -21,5 +21,5 @@ extern u64 cpu_do_resume(phys_addr_t ptr, u64 idmap_ttbr);
 
 #include <asm/memory.h>
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* __ASM_PROCFNS_H */

arch/arm64/include/asm/processor.h

@@ -25,7 +25,7 @@
 
 #define MTE_CTRL_STORE_ONLY		(1UL << 19)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/build_bug.h>
 #include <linux/cache.h>
@@ -437,5 +437,5 @@ int set_tsc_mode(unsigned int val);
 #define GET_TSC_CTL(adr)        get_tsc_mode((adr))
 #define SET_TSC_CTL(val)        set_tsc_mode((val))
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif /* __ASM_PROCESSOR_H */

arch/arm64/include/asm/ptrace.h

@@ -94,7 +94,7 @@
  */
 #define NO_SYSCALL (-1)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/bug.h>
 #include <linux/types.h>
 
@@ -361,5 +361,5 @@ static inline void procedure_link_pointer_set(struct pt_regs *regs,
 
 extern unsigned long profile_pc(struct pt_regs *regs);
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif

arch/arm64/include/asm/rsi_smc.h

@@ -122,7 +122,7 @@
  */
 #define SMC_RSI_ATTESTATION_TOKEN_CONTINUE	SMC_RSI_FID(0x195)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 struct realm_config {
 	union {
@@ -142,7 +142,7 @@ struct realm_config {
 	 */
 } __aligned(0x1000);
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 /*
  * Read configuration for the current Realm.

arch/arm64/include/asm/rwonce.h

@@ -5,7 +5,7 @@
 #ifndef __ASM_RWONCE_H
 #define __ASM_RWONCE_H
 
-#if defined(CONFIG_LTO) && !defined(__ASSEMBLY__)
+#if defined(CONFIG_LTO) && !defined(__ASSEMBLER__)
 
 #include <linux/compiler_types.h>
 #include <asm/alternative-macros.h>
@@ -62,7 +62,7 @@
 })
 
 #endif	/* !BUILD_VDSO */
-#endif	/* CONFIG_LTO && !__ASSEMBLY__ */
+#endif	/* CONFIG_LTO && !__ASSEMBLER__ */
 
 #include <asm-generic/rwonce.h>
 

arch/arm64/include/asm/scs.h

@@ -2,7 +2,7 @@
 #ifndef _ASM_SCS_H
 #define _ASM_SCS_H
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 #include <asm/asm-offsets.h>
 #include <asm/sysreg.h>
@@ -55,6 +55,6 @@ enum {
 
 int __pi_scs_patch(const u8 eh_frame[], int size, bool skip_dry_run);
 
-#endif /* __ASSEMBLY __ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* _ASM_SCS_H */

arch/arm64/include/asm/sdei.h

@@ -9,7 +9,7 @@
 
 #define SDEI_STACK_SIZE		IRQ_STACK_SIZE
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/linkage.h>
 #include <linux/preempt.h>
@@ -49,5 +49,5 @@ unsigned long do_sdei_event(struct pt_regs *regs,
 unsigned long sdei_arch_get_entry_point(int conduit);
 #define sdei_arch_get_entry_point(x)	sdei_arch_get_entry_point(x)
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 #endif	/* __ASM_SDEI_H */

arch/arm64/include/asm/simd.h

@@ -29,7 +29,7 @@ static __must_check inline bool may_use_simd(void)
 	 */
 	return !WARN_ON(!system_capabilities_finalized()) &&
 	       system_supports_fpsimd() &&
-	       !in_hardirq() && !irqs_disabled() && !in_nmi();
+	       !in_hardirq() && !in_nmi();
 }
 
 #else /* ! CONFIG_KERNEL_MODE_NEON */

arch/arm64/include/asm/smp.h

@@ -23,7 +23,7 @@
 #define CPU_STUCK_REASON_52_BIT_VA	(UL(1) << CPU_STUCK_REASON_SHIFT)
 #define CPU_STUCK_REASON_NO_GRAN	(UL(2) << CPU_STUCK_REASON_SHIFT)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/threads.h>
 #include <linux/cpumask.h>
@@ -155,6 +155,6 @@ bool cpus_are_stuck_in_kernel(void);
 extern void crash_smp_send_stop(void);
 extern bool smp_crash_stop_failed(void);
 
-#endif /* ifndef __ASSEMBLY__ */
+#endif /* ifndef __ASSEMBLER__ */
 
 #endif /* ifndef __ASM_SMP_H */

arch/arm64/include/asm/spectre.h

@@ -12,7 +12,7 @@
 #define BP_HARDEN_EL2_SLOTS 4
 #define __BP_HARDEN_HYP_VECS_SZ	((BP_HARDEN_EL2_SLOTS - 1) * SZ_2K)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/smp.h>
 #include <asm/percpu.h>
 
@@ -119,5 +119,5 @@ void spectre_bhb_patch_clearbhb(struct alt_instr *alt,
 				__le32 *origptr, __le32 *updptr, int nr_inst);
 void spectre_print_disabled_mitigations(void);
 
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 #endif	/* __ASM_SPECTRE_H */

arch/arm64/include/asm/stacktrace/frame.h

@@ -25,7 +25,7 @@
 #define FRAME_META_TYPE_FINAL		1
 #define FRAME_META_TYPE_PT_REGS		2
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 /* 
  * A standard AAPCS64 frame record.
  */
@@ -43,6 +43,6 @@ struct frame_record_meta {
 	struct frame_record record;
 	u64 type;
 };
-#endif /* __ASSEMBLY */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __ASM_STACKTRACE_FRAME_H */

arch/arm64/include/asm/suspend.h

@@ -23,7 +23,7 @@ struct cpu_suspend_ctx {
  * __cpu_suspend_enter()'s caller, and populated by __cpu_suspend_enter().
  * This data must survive until cpu_resume() is called.
  *
- * This struct desribes the size and the layout of the saved cpu state.
+ * This struct describes the size and the layout of the saved cpu state.
  * The layout of the callee_saved_regs is defined by the implementation
  * of __cpu_suspend_enter(), and cpu_resume(). This struct must be passed
  * in by the caller as __cpu_suspend_enter()'s stack-frame is gone once it

arch/arm64/include/asm/sysreg.h

@@ -52,7 +52,7 @@
 
 #ifndef CONFIG_BROKEN_GAS_INST
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 // The space separator is omitted so that __emit_inst(x) can be parsed as
 // either an assembler directive or an assembler macro argument.
 #define __emit_inst(x)			.inst(x)
@@ -71,11 +71,11 @@
 					 (((x) >> 24) & 0x000000ff))
 #endif	/* CONFIG_CPU_BIG_ENDIAN */
 
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 #define __emit_inst(x)			.long __INSTR_BSWAP(x)
-#else  /* __ASSEMBLY__ */
+#else  /* __ASSEMBLER__ */
 #define __emit_inst(x)			".long " __stringify(__INSTR_BSWAP(x)) "\n\t"
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 
 #endif	/* CONFIG_BROKEN_GAS_INST */
 
@@ -1129,9 +1129,7 @@
 #define gicr_insn(insn)			read_sysreg_s(GICV5_OP_GICR_##insn)
 #define gic_insn(v, insn)		write_sysreg_s(v, GICV5_OP_GIC_##insn)
 
-#define ARM64_FEATURE_FIELD_BITS	4
-
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
 
 	.macro	mrs_s, rt, sreg
 	 __emit_inst(0xd5200000|(\sreg)|(.L__gpr_num_\rt))

arch/arm64/include/asm/system_misc.h

@@ -7,7 +7,7 @@
 #ifndef __ASM_SYSTEM_MISC_H
 #define __ASM_SYSTEM_MISC_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/compiler.h>
 #include <linux/linkage.h>
@@ -28,6 +28,6 @@ void arm64_notify_die(const char *str, struct pt_regs *regs,
 struct mm_struct;
 extern void __show_regs(struct pt_regs *);
 
-#endif	/* __ASSEMBLY__ */
+#endif	/* __ASSEMBLER__ */
 
 #endif	/* __ASM_SYSTEM_MISC_H */

arch/arm64/include/asm/thread_info.h

@@ -10,7 +10,7 @@
 
 #include <linux/compiler.h>
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 struct task_struct;
 

arch/arm64/include/asm/tlbflush.h

@@ -8,7 +8,7 @@
 #ifndef __ASM_TLBFLUSH_H
 #define __ASM_TLBFLUSH_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <linux/bitfield.h>
 #include <linux/mm_types.h>
@@ -249,6 +249,19 @@ static inline unsigned long get_trans_granule(void)
  *		cannot be easily determined, the value TLBI_TTL_UNKNOWN will
  *		perform a non-hinted invalidation.
  *
+ *	local_flush_tlb_page(vma, addr)
+ *		Local variant of flush_tlb_page().  Stale TLB entries may
+ *		remain in remote CPUs.
+ *
+ *	local_flush_tlb_page_nonotify(vma, addr)
+ *		Same as local_flush_tlb_page() except MMU notifier will not be
+ *		called.
+ *
+ *	local_flush_tlb_contpte(vma, addr)
+ *		Invalidate the virtual-address range
+ *		'[addr, addr+CONT_PTE_SIZE)' mapped with contpte on local CPU
+ *		for the user address space corresponding to 'vma->mm'.  Stale
+ *		TLB entries may remain in remote CPUs.
  *
  *	Finally, take a look at asm/tlb.h to see how tlb_flush() is implemented
  *	on top of these routines, since that is our interface to the mmu_gather
@@ -282,6 +295,33 @@ static inline void flush_tlb_mm(struct mm_struct *mm)
 	mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL);
 }
 
+static inline void __local_flush_tlb_page_nonotify_nosync(struct mm_struct *mm,
+							  unsigned long uaddr)
+{
+	unsigned long addr;
+
+	dsb(nshst);
+	addr = __TLBI_VADDR(uaddr, ASID(mm));
+	__tlbi(vale1, addr);
+	__tlbi_user(vale1, addr);
+}
+
+static inline void local_flush_tlb_page_nonotify(struct vm_area_struct *vma,
+						 unsigned long uaddr)
+{
+	__local_flush_tlb_page_nonotify_nosync(vma->vm_mm, uaddr);
+	dsb(nsh);
+}
+
+static inline void local_flush_tlb_page(struct vm_area_struct *vma,
+					unsigned long uaddr)
+{
+	__local_flush_tlb_page_nonotify_nosync(vma->vm_mm, uaddr);
+	mmu_notifier_arch_invalidate_secondary_tlbs(vma->vm_mm, uaddr & PAGE_MASK,
+						(uaddr & PAGE_MASK) + PAGE_SIZE);
+	dsb(nsh);
+}
+
 static inline void __flush_tlb_page_nosync(struct mm_struct *mm,
 					   unsigned long uaddr)
 {
@@ -472,6 +512,22 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma,
 	dsb(ish);
 }
 
+static inline void local_flush_tlb_contpte(struct vm_area_struct *vma,
+					   unsigned long addr)
+{
+	unsigned long asid;
+
+	addr = round_down(addr, CONT_PTE_SIZE);
+
+	dsb(nshst);
+	asid = ASID(vma->vm_mm);
+	__flush_tlb_range_op(vale1, addr, CONT_PTES, PAGE_SIZE, asid,
+			     3, true, lpa2_is_enabled());
+	mmu_notifier_arch_invalidate_secondary_tlbs(vma->vm_mm, addr,
+						    addr + CONT_PTE_SIZE);
+	dsb(nsh);
+}
+
 static inline void flush_tlb_range(struct vm_area_struct *vma,
 				   unsigned long start, unsigned long end)
 {
@@ -524,6 +580,33 @@ static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *b
 {
 	__flush_tlb_range_nosync(mm, start, end, PAGE_SIZE, true, 3);
 }
+
+static inline bool __pte_flags_need_flush(ptdesc_t oldval, ptdesc_t newval)
+{
+	ptdesc_t diff = oldval ^ newval;
+
+	/* invalid to valid transition requires no flush */
+	if (!(oldval & PTE_VALID))
+		return false;
+
+	/* Transition in the SW bits requires no flush */
+	diff &= ~PTE_SWBITS_MASK;
+
+	return diff;
+}
+
+static inline bool pte_needs_flush(pte_t oldpte, pte_t newpte)
+{
+	return __pte_flags_need_flush(pte_val(oldpte), pte_val(newpte));
+}
+#define pte_needs_flush pte_needs_flush
+
+static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd)
+{
+	return __pte_flags_need_flush(pmd_val(oldpmd), pmd_val(newpmd));
+}
+#define huge_pmd_needs_flush huge_pmd_needs_flush
+
 #endif
 
 #endif

arch/arm64/include/asm/uaccess.h

@@ -422,9 +422,9 @@ static __must_check __always_inline bool user_access_begin(const void __user *pt
 }
 #define user_access_begin(a,b)	user_access_begin(a,b)
 #define user_access_end()	uaccess_ttbr0_disable()
-#define unsafe_put_user(x, ptr, label) \
+#define arch_unsafe_put_user(x, ptr, label) \
 	__raw_put_mem("sttr", x, uaccess_mask_ptr(ptr), label, U)
-#define unsafe_get_user(x, ptr, label) \
+#define arch_unsafe_get_user(x, ptr, label) \
 	__raw_get_mem("ldtr", x, uaccess_mask_ptr(ptr), label, U)
 
 /*

arch/arm64/include/asm/vdso.h

@@ -7,7 +7,7 @@
 
 #define __VDSO_PAGES    4
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <generated/vdso-offsets.h>
 
@@ -19,6 +19,6 @@
 extern char vdso_start[], vdso_end[];
 extern char vdso32_start[], vdso32_end[];
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __ASM_VDSO_H */

arch/arm64/include/asm/vdso/compat_barrier.h

@@ -5,7 +5,7 @@
 #ifndef __COMPAT_BARRIER_H
 #define __COMPAT_BARRIER_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 /*
  * Warning: This code is meant to be used from the compat vDSO only.
  */
@@ -31,6 +31,6 @@
 #define smp_rmb()	aarch32_smp_rmb()
 #define smp_wmb()	aarch32_smp_wmb()
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __COMPAT_BARRIER_H */

arch/arm64/include/asm/vdso/compat_gettimeofday.h

@@ -5,7 +5,7 @@
 #ifndef __ASM_VDSO_COMPAT_GETTIMEOFDAY_H
 #define __ASM_VDSO_COMPAT_GETTIMEOFDAY_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/barrier.h>
 #include <asm/unistd_compat_32.h>
@@ -161,6 +161,6 @@ static inline bool vdso_clocksource_ok(const struct vdso_clock *vc)
 }
 #define vdso_clocksource_ok	vdso_clocksource_ok
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __ASM_VDSO_COMPAT_GETTIMEOFDAY_H */

arch/arm64/include/asm/vdso/getrandom.h

@@ -3,7 +3,7 @@
 #ifndef __ASM_VDSO_GETRANDOM_H
 #define __ASM_VDSO_GETRANDOM_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/unistd.h>
 #include <asm/vdso/vsyscall.h>
@@ -33,6 +33,6 @@ static __always_inline ssize_t getrandom_syscall(void *_buffer, size_t _len, uns
 	return ret;
 }
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __ASM_VDSO_GETRANDOM_H */

arch/arm64/include/asm/vdso/gettimeofday.h

@@ -7,7 +7,7 @@
 
 #ifdef __aarch64__
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/alternative.h>
 #include <asm/arch_timer.h>
@@ -96,7 +96,7 @@ static __always_inline const struct vdso_time_data *__arch_get_vdso_u_time_data(
 #define __arch_get_vdso_u_time_data __arch_get_vdso_u_time_data
 #endif /* IS_ENABLED(CONFIG_CC_IS_GCC) && IS_ENABLED(CONFIG_PAGE_SIZE_64KB) */
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #else /* !__aarch64__ */
 

arch/arm64/include/asm/vdso/processor.h

@@ -5,13 +5,13 @@
 #ifndef __ASM_VDSO_PROCESSOR_H
 #define __ASM_VDSO_PROCESSOR_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 static inline void cpu_relax(void)
 {
 	asm volatile("yield" ::: "memory");
 }
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* __ASM_VDSO_PROCESSOR_H */

arch/arm64/include/asm/vdso/vsyscall.h

@@ -2,7 +2,7 @@
 #ifndef __ASM_VDSO_VSYSCALL_H
 #define __ASM_VDSO_VSYSCALL_H
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <vdso/datapage.h>
 
@@ -22,6 +22,6 @@ void __arch_update_vdso_clock(struct vdso_clock *vc)
 /* The asm-generic header needs to be included after the definitions above */
 #include <asm-generic/vdso/vsyscall.h>
 
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __ASM_VDSO_VSYSCALL_H */

arch/arm64/include/asm/virt.h

@@ -56,7 +56,7 @@
  */
 #define BOOT_CPU_FLAG_E2H	BIT_ULL(32)
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 
 #include <asm/ptrace.h>
 #include <asm/sections.h>
@@ -161,6 +161,6 @@ static inline bool is_hyp_nvhe(void)
 	return is_hyp_mode_available() && !is_kernel_in_hyp_mode();
 }
 
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
 
 #endif /* ! __ASM__VIRT_H */

arch/arm64/include/asm/vmap_stack.h

@@ -3,9 +3,7 @@
 #ifndef __ASM_VMAP_STACK_H
 #define __ASM_VMAP_STACK_H
 
-#include <linux/bug.h>
 #include <linux/gfp.h>
-#include <linux/kconfig.h>
 #include <linux/vmalloc.h>
 #include <linux/pgtable.h>
 #include <asm/memory.h>
@@ -19,8 +17,6 @@ static inline unsigned long *arch_alloc_vmap_stack(size_t stack_size, int node)
 {
 	void *p;
 
-	BUILD_BUG_ON(!IS_ENABLED(CONFIG_VMAP_STACK));
-
 	p = __vmalloc_node(stack_size, THREAD_ALIGN, THREADINFO_GFP, node,
 			__builtin_return_address(0));
 	return kasan_reset_tag(p);

arch/arm64/include/uapi/asm/kvm.h

@@ -31,7 +31,7 @@
 #define KVM_SPSR_FIQ	4
 #define KVM_NR_SPSR	5
 
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
 #include <linux/psci.h>
 #include <linux/types.h>
 #include <asm/ptrace.h>