Merge drm/drm-next into drm-misc-next

Backmerging 5.2-rc1 to -misc-next for robher

Signed-off-by: Sean Paul <seanpaul@chromium.org>

.clang-format

@@ -387,14 +387,14 @@ ForEachMacros:
   - 'rhl_for_each_entry_rcu'
   - 'rhl_for_each_rcu'
   - 'rht_for_each'
-  - 'rht_for_each_continue'
+  - 'rht_for_each_from'
   - 'rht_for_each_entry'
-  - 'rht_for_each_entry_continue'
+  - 'rht_for_each_entry_from'
   - 'rht_for_each_entry_rcu'
-  - 'rht_for_each_entry_rcu_continue'
+  - 'rht_for_each_entry_rcu_from'
   - 'rht_for_each_entry_safe'
   - 'rht_for_each_rcu'
-  - 'rht_for_each_rcu_continue'
+  - 'rht_for_each_rcu_from'
   - '__rq_for_each_bio'
   - 'rq_for_each_bvec'
   - 'rq_for_each_segment'

.get_maintainer.ignore

@@ -1 +1,2 @@
 Christoph Hellwig <hch@lst.de>
+Marc Gonzalez <marc.w.gonzalez@free.fr>

.gitignore

@@ -58,6 +58,7 @@ modules.builtin
 /vmlinuz
 /System.map
 /Module.markers
+/modules.builtin.modinfo
 
 #
 # RPM spec file (make rpm-pkg)
@@ -80,20 +81,22 @@ modules.builtin
 /tar-install/
 
 #
-# git files that we don't want to ignore even if they are dot-files
+# We don't want to ignore the following even if they are dot-files
 #
+!.clang-format
+!.cocciconfig
+!.get_maintainer.ignore
+!.gitattributes
 !.gitignore
 !.mailmap
-!.cocciconfig
-!.clang-format
 
 #
 # Generated include files
 #
-include/config
+/include/config/
-include/generated
+/include/generated/
-include/ksym
+/include/ksym/
-arch/*/include/generated
+/arch/*/include/generated/
 
 # stgit generated dirs
 patches-*
@@ -129,7 +132,12 @@ signing_key.x509
 x509.genkey
 
 # Kconfig presets
-all.config
+/all.config
+/alldef.config
+/allmod.config
+/allno.config
+/allrandom.config
+/allyes.config
 
 # Kdevelop4
 *.kdev4

.mailmap

@@ -16,6 +16,11 @@ Alan Cox <alan@lxorguk.ukuu.org.uk>
 Alan Cox <root@hraefn.swansea.linux.org.uk>
 Aleksey Gorelov <aleksey_gorelov@phoenix.com>
 Aleksandar Markovic <aleksandar.markovic@mips.com> <aleksandar.markovic@imgtec.com>
+Alex Shi <alex.shi@linux.alibaba.com> <alex.shi@intel.com>
+Alex Shi <alex.shi@linux.alibaba.com> <alex.shi@linaro.org>
+Alexei Starovoitov <ast@kernel.org> <ast@plumgrid.com>
+Alexei Starovoitov <ast@kernel.org> <alexei.starovoitov@gmail.com>
+Alexei Starovoitov <ast@kernel.org> <ast@fb.com>
 Al Viro <viro@ftp.linux.org.uk>
 Al Viro <viro@zenIV.linux.org.uk>
 Andi Shyti <andi@etezian.org> <andi.shyti@samsung.com>
@@ -46,6 +51,12 @@ Christoph Hellwig <hch@lst.de>
 Christophe Ricard <christophe.ricard@gmail.com>
 Corey Minyard <minyard@acm.org>
 Damian Hobson-Garcia <dhobsong@igel.co.jp>
+Daniel Borkmann <daniel@iogearbox.net> <dborkman@redhat.com>
+Daniel Borkmann <daniel@iogearbox.net> <dborkmann@redhat.com>
+Daniel Borkmann <daniel@iogearbox.net> <danborkmann@iogearbox.net>
+Daniel Borkmann <daniel@iogearbox.net> <daniel.borkmann@tik.ee.ethz.ch>
+Daniel Borkmann <daniel@iogearbox.net> <danborkmann@googlemail.com>
+Daniel Borkmann <daniel@iogearbox.net> <dxchgb@gmail.com>
 David Brownell <david-b@pacbell.net>
 David Woodhouse <dwmw2@shinybook.infradead.org>
 Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@mips.com>
@@ -117,6 +128,8 @@ Leonid I Ananiev <leonid.i.ananiev@intel.com>
 Linas Vepstas <linas@austin.ibm.com>
 Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@web.de>
 Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@ascom.ch>
+Li Yang <leoyang.li@nxp.com> <leo@zh-kernel.org>
+Li Yang <leoyang.li@nxp.com> <leoli@freescale.com>
 Maciej W. Rozycki <macro@mips.com> <macro@imgtec.com>
 Marcin Nowakowski <marcin.nowakowski@mips.com> <marcin.nowakowski@imgtec.com>
 Mark Brown <broonie@sirena.org.uk>
@@ -189,6 +202,7 @@ Santosh Shilimkar <ssantosh@kernel.org>
 Santosh Shilimkar <santosh.shilimkar@oracle.org>
 Sascha Hauer <s.hauer@pengutronix.de>
 S.Çağlar Onur <caglar@pardus.org.tr>
+Sean Nyekjaer <sean@geanix.com> <sean.nyekjaer@prevas.dk>
 Sebastian Reichel <sre@kernel.org> <sre@debian.org>
 Sebastian Reichel <sre@kernel.org> <sebastian.reichel@collabora.co.uk>
 Shiraz Hashim <shiraz.linux.kernel@gmail.com> <shiraz.hashim@st.com>
@@ -207,6 +221,8 @@ Tejun Heo <htejun@gmail.com>
 Thomas Graf <tgraf@suug.ch>
 Thomas Pedersen <twp@codeaurora.org>
 Tony Luck <tony.luck@intel.com>
+TripleX Chung <xxx.phy@gmail.com> <zhongyu@18mail.cn>
+TripleX Chung <xxx.phy@gmail.com> <triplex@zh-kernel.org>
 Tsuneo Yoshioka <Tsuneo.Yoshioka@f-secure.com>
 Uwe Kleine-König <ukleinek@informatik.uni-freiburg.de>
 Uwe Kleine-König <ukl@pengutronix.de>

Documentation/ABI/obsolete/sysfs-class-net-batman-adv

@@ -1,3 +1,5 @@
+This ABI is deprecated and will be removed after 2021. It is
+replaced with the batadv generic netlink family.
 
 What:           /sys/class/net/<iface>/batman-adv/elp_interval
 Date:           Feb 2014

Documentation/ABI/obsolete/sysfs-class-net-mesh

@@ -1,3 +1,5 @@
+This ABI is deprecated and will be removed after 2021. It is
+replaced with the batadv generic netlink family.
 
 What:           /sys/class/net/<mesh_iface>/mesh/aggregated_ogms
 Date:           May 2010

Documentation/ABI/stable/sysfs-bus-nvmem

@@ -6,6 +6,8 @@ Description:
 		This file allows user to read/write the raw NVMEM contents.
 		Permissions for write to this file depends on the nvmem
 		provider configuration.
+		Note: This file is only present if CONFIG_NVMEM_SYSFS
+		is enabled
 
 		ex:
 		hexdump /sys/bus/nvmem/devices/qfprom0/nvmem

Documentation/ABI/stable/sysfs-bus-vmbus

@@ -81,7 +81,9 @@ What:		/sys/bus/vmbus/devices/<UUID>/channels/<N>/latency
 Date:		September. 2017
 KernelVersion:	4.14
 Contact:	Stephen Hemminger <sthemmin@microsoft.com>
-Description:	Channel signaling latency
+Description:	Channel signaling latency. This file is available only for
+		performance critical channels (storage, network, etc.) that use
+		the monitor page mechanism.
 Users:		Debugging tools
 
 What:		/sys/bus/vmbus/devices/<UUID>/channels/<N>/out_mask
@@ -95,7 +97,9 @@ What:		/sys/bus/vmbus/devices/<UUID>/channels/<N>/pending
 Date:		September. 2017
 KernelVersion:	4.14
 Contact:	Stephen Hemminger <sthemmin@microsoft.com>
-Description:	Channel interrupt pending state
+Description:	Channel interrupt pending state. This file is available only for
+		performance critical channels (storage, network, etc.) that use
+		the monitor page mechanism.
 Users:		Debugging tools
 
 What:		/sys/bus/vmbus/devices/<UUID>/channels/<N>/read_avail
@@ -137,7 +141,9 @@ What:		/sys/bus/vmbus/devices/<UUID>/channels/<N>/monitor_id
 Date:		January. 2018
 KernelVersion:	4.16
 Contact:	Stephen Hemminger <sthemmin@microsoft.com>
-Description:	Monitor bit associated with channel
+Description:	Monitor bit associated with channel. This file is available only
+		for performance critical channels (storage, network, etc.) that
+		use the monitor page mechanism.
 Users:		Debugging tools and userspace drivers
 
 What:		/sys/bus/vmbus/devices/<UUID>/channels/<N>/ring

Documentation/ABI/stable/sysfs-devices-node

@@ -90,4 +90,89 @@ Date:		December 2009
 Contact:	Lee Schermerhorn <lee.schermerhorn@hp.com>
 Description:
 		The node's huge page size control/query attributes.
-		See Documentation/admin-guide/mm/hugetlbpage.rst
+		See Documentation/admin-guide/mm/hugetlbpage.rst
+
+What:		/sys/devices/system/node/nodeX/accessY/
+Date:		December 2018
+Contact:	Keith Busch <keith.busch@intel.com>
+Description:
+		The node's relationship to other nodes for access class "Y".
+
+What:		/sys/devices/system/node/nodeX/accessY/initiators/
+Date:		December 2018
+Contact:	Keith Busch <keith.busch@intel.com>
+Description:
+		The directory containing symlinks to memory initiator
+		nodes that have class "Y" access to this target node's
+		memory. CPUs and other memory initiators in nodes not in
+		the list accessing this node's memory may have different
+		performance.
+
+What:		/sys/devices/system/node/nodeX/accessY/targets/
+Date:		December 2018
+Contact:	Keith Busch <keith.busch@intel.com>
+Description:
+		The directory containing symlinks to memory targets that
+		this initiator node has class "Y" access.
+
+What:		/sys/devices/system/node/nodeX/accessY/initiators/read_bandwidth
+Date:		December 2018
+Contact:	Keith Busch <keith.busch@intel.com>
+Description:
+		This node's read bandwidth in MB/s when accessed from
+		nodes found in this access class's linked initiators.
+
+What:		/sys/devices/system/node/nodeX/accessY/initiators/read_latency
+Date:		December 2018
+Contact:	Keith Busch <keith.busch@intel.com>
+Description:
+		This node's read latency in nanoseconds when accessed
+		from nodes found in this access class's linked initiators.
+
+What:		/sys/devices/system/node/nodeX/accessY/initiators/write_bandwidth
+Date:		December 2018
+Contact:	Keith Busch <keith.busch@intel.com>
+Description:
+		This node's write bandwidth in MB/s when accessed from
+		found in this access class's linked initiators.
+
+What:		/sys/devices/system/node/nodeX/accessY/initiators/write_latency
+Date:		December 2018
+Contact:	Keith Busch <keith.busch@intel.com>
+Description:
+		This node's write latency in nanoseconds when access
+		from nodes found in this class's linked initiators.
+
+What:		/sys/devices/system/node/nodeX/memory_side_cache/indexY/
+Date:		December 2018
+Contact:	Keith Busch <keith.busch@intel.com>
+Description:
+		The directory containing attributes for the memory-side cache
+		level 'Y'.
+
+What:		/sys/devices/system/node/nodeX/memory_side_cache/indexY/indexing
+Date:		December 2018
+Contact:	Keith Busch <keith.busch@intel.com>
+Description:
+		The caches associativity indexing: 0 for direct mapped,
+		non-zero if indexed.
+
+What:		/sys/devices/system/node/nodeX/memory_side_cache/indexY/line_size
+Date:		December 2018
+Contact:	Keith Busch <keith.busch@intel.com>
+Description:
+		The number of bytes accessed from the next cache level on a
+		cache miss.
+
+What:		/sys/devices/system/node/nodeX/memory_side_cache/indexY/size
+Date:		December 2018
+Contact:	Keith Busch <keith.busch@intel.com>
+Description:
+		The size of this memory side cache in bytes.
+
+What:		/sys/devices/system/node/nodeX/memory_side_cache/indexY/write_policy
+Date:		December 2018
+Contact:	Keith Busch <keith.busch@intel.com>
+Description:
+		The cache write policy: 0 for write-back, 1 for write-through,
+		other or unknown.

Documentation/ABI/testing/debugfs-wilco-ec

@@ -1,23 +1,46 @@
+What:		/sys/kernel/debug/wilco_ec/h1_gpio
+Date:		April 2019
+KernelVersion:	5.2
+Description:
+		As part of Chrome OS's FAFT (Fully Automated Firmware Testing)
+		tests, we need to ensure that the H1 chip is properly setting
+		some GPIO lines. The h1_gpio attribute exposes the state
+		of the lines:
+		- ENTRY_TO_FACT_MODE in BIT(0)
+		- SPI_CHROME_SEL in BIT(1)
+
+		Output will formatted with "0x%02x\n".
+
 What:		/sys/kernel/debug/wilco_ec/raw
 Date:		January 2019
 KernelVersion:	5.1
 Description:
 		Write and read raw mailbox commands to the EC.
 
-		For writing:
+		You can write a hexadecimal sentence to raw, and that series of
-		Bytes 0-1 indicate the message type:
+		bytes will be sent to the EC. Then, you can read the bytes of
-			00 F0 = Execute Legacy Command
+		response by reading from raw.
-			00 F2 = Read/Write NVRAM Property
-		Byte 2 provides the command code
-		Bytes 3+ consist of the data passed in the request
 
-		At least three bytes are required, for the msg type and command,
+		For writing, bytes 0-1 indicate the message type, one of enum
-		with additional bytes optional for additional data.
+		wilco_ec_msg_type. Byte 2+ consist of the data passed in the
+		request, starting at MBOX[0]
+
+		At least three bytes are required for writing, two for the type
+		and at least a single byte of data. Only the first
+		EC_MAILBOX_DATA_SIZE bytes of MBOX will be used.
 
 		Example:
 		// Request EC info type 3 (EC firmware build date)
-		$ echo 00 f0 38 00 03 00 > raw
+		// Corresponds with sending type 0x00f0 with
+		// MBOX = [38, 00, 03, 00]
+		$ echo 00 f0 38 00 03 00 > /sys/kernel/debug/wilco_ec/raw
 		// View the result. The decoded ASCII result "12/21/18" is
 		// included after the raw hex.
-		$ cat raw
+		// Corresponds with MBOX = [00, 00, 31, 32, 2f, 32, 31, 38, ...]
-		00 31 32 2f 32 31 2f 31 38 00 38 00 01 00 2f 00  .12/21/18.8...
+		$ cat /sys/kernel/debug/wilco_ec/raw
+		00 00 31 32 2f 32 31 2f 31 38 00 38 00 01 00 2f 00  ..12/21/18.8...
+
+		Note that the first 32 bytes of the received MBOX[] will be
+		printed, even if some of the data is junk. It is up to you to
+		know how many of the first bytes of data are the actual
+		response.

Documentation/ABI/testing/sysfs-bus-counter

@@ -0,0 +1,230 @@
+What:		/sys/bus/counter/devices/counterX/countY/count
+KernelVersion:	5.2
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Count data of Count Y represented as a string.
+
+What:		/sys/bus/counter/devices/counterX/countY/ceiling
+KernelVersion:	5.2
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Count value ceiling for Count Y. This is the upper limit for the
+		respective counter.
+
+What:		/sys/bus/counter/devices/counterX/countY/floor
+KernelVersion:	5.2
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Count value floor for Count Y. This is the lower limit for the
+		respective counter.
+
+What:		/sys/bus/counter/devices/counterX/countY/count_mode
+KernelVersion:	5.2
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Count mode for channel Y. The ceiling and floor values for
+		Count Y are used by the count mode where required. The following
+		count modes are available:
+
+		normal:
+			Counting is continuous in either direction.
+
+		range limit:
+			An upper or lower limit is set, mimicking limit switches
+			in the mechanical counterpart. The upper limit is set to
+			the Count Y ceiling value, while the lower limit is set
+			to the Count Y floor value. The counter freezes at
+			count = ceiling when counting up, and at count = floor
+			when counting down. At either of these limits, the
+			counting is resumed only when the count direction is
+			reversed.
+
+		non-recycle:
+			The counter is disabled whenever a counter overflow or
+			underflow takes place. The counter is re-enabled when a
+			new count value is loaded to the counter via a preset
+			operation or direct write.
+
+		modulo-n:
+			A count value boundary is set between the Count Y floor
+			value and the Count Y ceiling value. The counter is
+			reset to the Count Y floor value at count = ceiling when
+			counting up, while the counter is set to the Count Y
+			ceiling value at count = floor when counting down; the
+			counter does not freeze at the boundary points, but
+			counts continuously throughout.
+
+What:		/sys/bus/counter/devices/counterX/countY/count_mode_available
+What:		/sys/bus/counter/devices/counterX/countY/error_noise_available
+What:		/sys/bus/counter/devices/counterX/countY/function_available
+What:		/sys/bus/counter/devices/counterX/countY/signalZ_action_available
+KernelVersion:	5.2
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Discrete set of available values for the respective Count Y
+		configuration are listed in this file. Values are delimited by
+		newline characters.
+
+What:		/sys/bus/counter/devices/counterX/countY/direction
+KernelVersion:	5.2
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Read-only attribute that indicates the count direction of Count
+		Y. Two count directions are available: forward and backward.
+
+		Some counter devices are able to determine the direction of
+		their counting. For example, quadrature encoding counters can
+		determine the direction of movement by evaluating the leading
+		phase of the respective A and B quadrature encoding signals.
+		This attribute exposes such count directions.
+
+What:		/sys/bus/counter/devices/counterX/countY/enable
+KernelVersion:	5.2
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Whether channel Y counter is enabled. Valid attribute values are
+		boolean.
+
+		This attribute is intended to serve as a pause/unpause mechanism
+		for Count Y. Suppose a counter device is used to count the total
+		movement of a conveyor belt: this attribute allows an operator
+		to temporarily pause the counter, service the conveyor belt,
+		and then finally unpause the counter to continue where it had
+		left off.
+
+What:		/sys/bus/counter/devices/counterX/countY/error_noise
+KernelVersion:	5.2
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Read-only attribute that indicates whether excessive noise is
+		present at the channel Y counter inputs.
+
+What:		/sys/bus/counter/devices/counterX/countY/function
+KernelVersion:	5.2
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Count function mode of Count Y; count function evaluation is
+		triggered by conditions specified by the Count Y signalZ_action
+		attributes. The following count functions are available:
+
+		increase:
+			Accumulated count is incremented.
+
+		decrease:
+			Accumulated count is decremented.
+
+		pulse-direction:
+			Rising edges on signal A updates the respective count.
+			The input level of signal B determines direction.
+
+		quadrature x1 a:
+			If direction is forward, rising edges on quadrature pair
+			signal A updates the respective count; if the direction
+			is backward, falling edges on quadrature pair signal A
+			updates the respective count. Quadrature encoding
+			determines the direction.
+
+		quadrature x1 b:
+			If direction is forward, rising edges on quadrature pair
+			signal B updates the respective count; if the direction
+			is backward, falling edges on quadrature pair signal B
+			updates the respective count. Quadrature encoding
+			determines the direction.
+
+		quadrature x2 a:
+			Any state transition on quadrature pair signal A updates
+			the respective count. Quadrature encoding determines the
+			direction.
+
+		quadrature x2 b:
+			Any state transition on quadrature pair signal B updates
+			the respective count. Quadrature encoding determines the
+			direction.
+
+		quadrature x4:
+			Any state transition on either quadrature pair signals
+			updates	the respective count. Quadrature encoding
+			determines the direction.
+
+What:		/sys/bus/counter/devices/counterX/countY/name
+KernelVersion:	5.2
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Read-only attribute that indicates the device-specific name of
+		Count Y. If possible, this should match the name of the
+		respective channel as it appears in the device datasheet.
+
+What:		/sys/bus/counter/devices/counterX/countY/preset
+KernelVersion:	5.2
+Contact:	linux-iio@vger.kernel.org
+Description:
+		If the counter device supports preset registers -- registers
+		used to load counter channels to a set count upon device-defined
+		preset operation trigger events -- the preset count for channel
+		Y is provided by this attribute.
+
+What:		/sys/bus/counter/devices/counterX/countY/preset_enable
+KernelVersion:	5.2
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Whether channel Y counter preset operation is enabled. Valid
+		attribute values are boolean.
+
+What:		/sys/bus/counter/devices/counterX/countY/signalZ_action
+KernelVersion:	5.2
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Action mode of Count Y for Signal Z. This attribute indicates
+		the condition of Signal Z that triggers the count function
+		evaluation for Count Y. The following action modes are
+		available:
+
+		none:
+			Signal does not trigger the count function. In
+			Pulse-Direction count function mode, this Signal is
+			evaluated as Direction.
+
+		rising edge:
+			Low state transitions to high state.
+
+		falling edge:
+			High state transitions to low state.
+
+		both edges:
+			Any state transition.
+
+What:		/sys/bus/counter/devices/counterX/name
+KernelVersion:	5.2
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Read-only attribute that indicates the device-specific name of
+		the Counter. This should match the name of the device as it
+		appears in its respective datasheet.
+
+What:		/sys/bus/counter/devices/counterX/num_counts
+KernelVersion:	5.2
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Read-only attribute that indicates the total number of Counts
+		belonging to the Counter.
+
+What:		/sys/bus/counter/devices/counterX/num_signals
+KernelVersion:	5.2
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Read-only attribute that indicates the total number of Signals
+		belonging to the Counter.
+
+What:		/sys/bus/counter/devices/counterX/signalY/signal
+KernelVersion:	5.2
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Signal data of Signal Y represented as a string.
+
+What:		/sys/bus/counter/devices/counterX/signalY/name
+KernelVersion:	5.2
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Read-only attribute that indicates the device-specific name of
+		Signal Y. If possible, this should match the name of the
+		respective signal as it appears in the device datasheet.

Documentation/ABI/testing/sysfs-bus-counter-104-quad-8

@@ -0,0 +1,36 @@
+What:		/sys/bus/counter/devices/counterX/signalY/index_polarity
+KernelVersion:	5.2
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Active level of index input Signal Y; irrelevant in
+		non-synchronous load mode.
+
+What:		/sys/bus/counter/devices/counterX/signalY/index_polarity_available
+What:		/sys/bus/counter/devices/counterX/signalY/synchronous_mode_available
+KernelVersion:	5.2
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Discrete set of available values for the respective Signal Y
+		configuration are listed in this file.
+
+What:		/sys/bus/counter/devices/counterX/signalY/synchronous_mode
+KernelVersion:	5.2
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Configure the counter associated with Signal Y for
+		non-synchronous or synchronous load mode. Synchronous load mode
+		cannot be selected in non-quadrature (Pulse-Direction) clock
+		mode.
+
+		non-synchronous:
+			A logic low level is the active level at this index
+			input. The index function (as enabled via preset_enable)
+			is performed directly on the active level of the index
+			input.
+
+		synchronous:
+			Intended for interfacing with encoder Index output in
+			quadrature clock mode. The active level is configured
+			via index_polarity. The index function (as enabled via
+			preset_enable) is performed synchronously with the
+			quadrature clock on the active level of the index input.

Documentation/ABI/testing/sysfs-bus-counter-ftm-quaddec

@@ -0,0 +1,16 @@
+What:		/sys/bus/counter/devices/counterX/countY/prescaler_available
+KernelVersion:	5.2
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Discrete set of available values for the respective Count Y
+		configuration are listed in this file. Values are delimited by
+		newline characters.
+
+What:		/sys/bus/counter/devices/counterX/countY/prescaler
+KernelVersion:	5.2
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Configure the prescaler value associated with Count Y.
+		On the FlexTimer, the counter clock source passes through a
+		prescaler (i.e. a counter). This acts like a clock
+		divider.

Documentation/ABI/testing/sysfs-bus-i2c-devices-pca954x

@@ -0,0 +1,20 @@
+What:		/sys/bus/i2c/.../idle_state
+Date:		January 2019
+KernelVersion:	5.2
+Contact:	Robert Shearman <robert.shearman@att.com>
+Description:
+		Value that exists only for mux devices that can be
+		written to control the behaviour of the multiplexer on
+		idle. Possible values:
+		-2 - disconnect on idle, i.e. deselect the last used
+		     channel, which is useful when there is a device
+		     with an address that conflicts with another
+		     device on another mux on the same parent bus.
+		-1 - leave the mux as-is, which is the most optimal
+		     setting in terms of I2C operations and is the
+		     default mode.
+		0..<nchans> - set the mux to a predetermined channel,
+		     which is useful if there is one channel that is
+		     used almost always, and you want to reduce the
+		     latency for normal operations after rare
+		     transactions on other channels

Documentation/ABI/testing/sysfs-bus-iio

@@ -1656,6 +1656,8 @@ What:		/sys/bus/iio/devices/iio:deviceX/in_countY_raw
 KernelVersion:	4.10
 Contact:	linux-iio@vger.kernel.org
 Description:
+		This interface is deprecated; please use the Counter subsystem.
+
 		Raw counter device counts from channel Y. For quadrature
 		counters, multiplication by an available [Y]_scale results in
 		the counts of a single quadrature signal phase from channel Y.
@@ -1664,6 +1666,8 @@ What:		/sys/bus/iio/devices/iio:deviceX/in_indexY_raw
 KernelVersion:	4.10
 Contact:	linux-iio@vger.kernel.org
 Description:
+		This interface is deprecated; please use the Counter subsystem.
+
 		Raw counter device index value from channel Y. This attribute
 		provides an absolute positional reference (e.g. a pulse once per
 		revolution) which may be used to home positional systems as
@@ -1673,6 +1677,8 @@ What:		/sys/bus/iio/devices/iio:deviceX/in_count_count_direction_available
 KernelVersion:	4.12
 Contact:	linux-iio@vger.kernel.org
 Description:
+		This interface is deprecated; please use the Counter subsystem.
+
 		A list of possible counting directions which are:
 		- "up"	: counter device is increasing.
 		- "down": counter device is decreasing.
@@ -1681,6 +1687,8 @@ What:		/sys/bus/iio/devices/iio:deviceX/in_countY_count_direction
 KernelVersion:	4.12
 Contact:	linux-iio@vger.kernel.org
 Description:
+		This interface is deprecated; please use the Counter subsystem.
+
 		Raw counter device counters direction for channel Y.
 
 What:		/sys/bus/iio/devices/iio:deviceX/in_phaseY_raw

Documentation/ABI/testing/sysfs-bus-iio-counter-104-quad-8

@@ -6,6 +6,8 @@ What:		/sys/bus/iio/devices/iio:deviceX/in_index_synchronous_mode_available
 KernelVersion:	4.10
 Contact:	linux-iio@vger.kernel.org
 Description:
+		This interface is deprecated; please use the Counter subsystem.
+
 		Discrete set of available values for the respective counter
 		configuration are listed in this file.
 
@@ -13,6 +15,8 @@ What:		/sys/bus/iio/devices/iio:deviceX/in_countY_count_mode
 KernelVersion:	4.10
 Contact:	linux-iio@vger.kernel.org
 Description:
+		This interface is deprecated; please use the Counter subsystem.
+
 		Count mode for channel Y. Four count modes are available:
 		normal, range limit, non-recycle, and modulo-n. The preset value
 		for channel Y is used by the count mode where required.
@@ -47,6 +51,8 @@ What:		/sys/bus/iio/devices/iio:deviceX/in_countY_noise_error
 KernelVersion:	4.10
 Contact:	linux-iio@vger.kernel.org
 Description:
+		This interface is deprecated; please use the Counter subsystem.
+
 		Read-only attribute that indicates whether excessive noise is
 		present at the channel Y count inputs in quadrature clock mode;
 		irrelevant in non-quadrature clock mode.
@@ -55,6 +61,8 @@ What:		/sys/bus/iio/devices/iio:deviceX/in_countY_preset
 KernelVersion:	4.10
 Contact:	linux-iio@vger.kernel.org
 Description:
+		This interface is deprecated; please use the Counter subsystem.
+
 		If the counter device supports preset registers, the preset
 		count for channel Y is provided by this attribute.
 
@@ -62,6 +70,8 @@ What:		/sys/bus/iio/devices/iio:deviceX/in_countY_quadrature_mode
 KernelVersion:	4.10
 Contact:	linux-iio@vger.kernel.org
 Description:
+		This interface is deprecated; please use the Counter subsystem.
+
 		Configure channel Y counter for non-quadrature or quadrature
 		clock mode. Selecting non-quadrature clock mode will disable
 		synchronous load mode. In quadrature clock mode, the channel Y
@@ -83,6 +93,8 @@ What:		/sys/bus/iio/devices/iio:deviceX/in_countY_set_to_preset_on_index
 KernelVersion:	4.10
 Contact:	linux-iio@vger.kernel.org
 Description:
+		This interface is deprecated; please use the Counter subsystem.
+
 		Whether to set channel Y counter with channel Y preset value
 		when channel Y index input is active, or continuously count.
 		Valid attribute values are boolean.
@@ -91,6 +103,8 @@ What:		/sys/bus/iio/devices/iio:deviceX/in_indexY_index_polarity
 KernelVersion:	4.10
 Contact:	linux-iio@vger.kernel.org
 Description:
+		This interface is deprecated; please use the Counter subsystem.
+
 		Active level of channel Y index input; irrelevant in
 		non-synchronous load mode.
 
@@ -98,6 +112,8 @@ What:		/sys/bus/iio/devices/iio:deviceX/in_indexY_synchronous_mode
 KernelVersion:	4.10
 Contact:	linux-iio@vger.kernel.org
 Description:
+		This interface is deprecated; please use the Counter subsystem.
+
 		Configure channel Y counter for non-synchronous or synchronous
 		load mode. Synchronous load mode cannot be selected in
 		non-quadrature clock mode.

Documentation/ABI/testing/sysfs-bus-iio-impedance-analyzer-ad5933

@@ -1,26 +1,31 @@
-What:		/sys/bus/iio/devices/iio:deviceX/outY_freq_start
+What:		/sys/bus/iio/devices/iio:deviceX/out_altvoltageY_frequency_start
+Date:		March 2019
 KernelVersion:	3.1.0
 Contact:	linux-iio@vger.kernel.org
 Description:
 		Frequency sweep start frequency in Hz.
 
-What:		/sys/bus/iio/devices/iio:deviceX/outY_freq_increment
+What:		/sys/bus/iio/devices/iio:deviceX/out_altvoltageY_frequency_increment
+Date:		March 2019
 KernelVersion:	3.1.0
 Contact:	linux-iio@vger.kernel.org
 Description:
 		Frequency increment in Hz (step size) between consecutive
 		frequency points along the sweep.
 
-What:		/sys/bus/iio/devices/iio:deviceX/outY_freq_points
+What:		/sys/bus/iio/devices/iio:deviceX/out_altvoltageY_frequency_points
+Date:		March 2019
 KernelVersion:	3.1.0
 Contact:	linux-iio@vger.kernel.org
 Description:
 		Number of frequency points (steps) in the frequency sweep.
-		This value, in conjunction with the outY_freq_start and the
+		This value, in conjunction with the
-		outY_freq_increment, determines the frequency sweep range
+		out_altvoltageY_frequency_start and the
-		for the sweep operation.
+		out_altvoltageY_frequency_increment, determines the frequency
+		sweep range for the sweep operation.
 
-What:		/sys/bus/iio/devices/iio:deviceX/outY_settling_cycles
+What:		/sys/bus/iio/devices/iio:deviceX/out_altvoltageY_settling_cycles
+Date:		March 2019
 KernelVersion:	3.1.0
 Contact:	linux-iio@vger.kernel.org
 Description:

Documentation/ABI/testing/sysfs-bus-iio-sps30

@@ -1,6 +1,6 @@
 What:		/sys/bus/iio/devices/iio:deviceX/start_cleaning
 Date:		December 2018
-KernelVersion:	4.22
+KernelVersion:	5.0
 Contact:	linux-iio@vger.kernel.org
 Description:
 		Writing 1 starts sensor self cleaning. Internal fan accelerates

Documentation/ABI/testing/sysfs-bus-iio-temperature-max31856

@@ -0,0 +1,24 @@
+What:		/sys/bus/iio/devices/iio:deviceX/fault_oc
+KernelVersion:	5.1
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Open-circuit fault. The detection of open-circuit faults,
+		such as those caused by broken thermocouple wires.
+		Reading returns either '1' or '0'.
+		'1' = An open circuit such as broken thermocouple wires
+		      has been detected.
+		'0' = No open circuit or broken thermocouple wires are detected
+
+What:		/sys/bus/iio/devices/iio:deviceX/fault_ovuv
+KernelVersion:	5.1
+Contact:	linux-iio@vger.kernel.org
+Description:
+		Overvoltage or Undervoltage Input Fault. The internal circuitry
+		is protected from excessive voltages applied to the thermocouple
+		cables by integrated MOSFETs at the T+ and T- inputs, and the
+		BIAS output. These MOSFETs turn off when the input voltage is
+		negative or greater than VDD.
+		Reading returns either '1' or '0'.
+		'1' = The input voltage is negative or greater than VDD.
+		'0' = The input voltage is positive and less than VDD (normal
+		state).

Documentation/ABI/testing/sysfs-bus-intel_th-devices-msc

@@ -30,4 +30,12 @@ Description:	(RW) Configure MSC buffer size for "single" or "multi" modes.
 		there are no active users and tracing is not enabled) and then
 		allocates a new one.
 
+What:		/sys/bus/intel_th/devices/<intel_th_id>-msc<msc-id>/win_switch
+Date:		May 2019
+KernelVersion:	5.2
+Contact:	Alexander Shishkin <alexander.shishkin@linux.intel.com>
+Description:	(RW) Trigger window switch for the MSC's buffer, in
+		multi-window mode. In "multi" mode, accepts writes of "1", thereby
+		triggering a window switch for the buffer. Returns an error in any
+		other operating mode or attempts to write something other than "1".
 

Documentation/ABI/testing/sysfs-class-mei

@@ -65,3 +65,18 @@ Description:	Display the ME firmware version.
 		<platform>:<major>.<minor>.<milestone>.<build_no>.
 		There can be up to three such blocks for different
 		FW components.
+
+What:		/sys/class/mei/meiN/dev_state
+Date:		Mar 2019
+KernelVersion:	5.1
+Contact:	Tomas Winkler <tomas.winkler@intel.com>
+Description:	Display the ME device state.
+
+		The device state can have following values:
+		INITIALIZING
+		INIT_CLIENTS
+		ENABLED
+		RESETTING
+		DISABLED
+		POWER_DOWN
+		POWER_UP

Documentation/ABI/testing/sysfs-class-power

@@ -114,15 +114,60 @@ Description:
 		Access: Read
 		Valid values: Represented in microamps
 
+What:		/sys/class/power_supply/<supply_name>/charge_control_limit
+Date:		Oct 2012
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Maximum allowable charging current. Used for charge rate
+		throttling for thermal cooling or improving battery health.
+
+		Access: Read, Write
+		Valid values: Represented in microamps
+
+What:		/sys/class/power_supply/<supply_name>/charge_control_limit_max
+Date:		Oct 2012
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Maximum legal value for the charge_control_limit property.
+
+		Access: Read
+		Valid values: Represented in microamps
+
+What:		/sys/class/power_supply/<supply_name>/charge_control_start_threshold
+Date:		April 2019
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Represents a battery percentage level, below which charging will
+		begin.
+
+		Access: Read, Write
+		Valid values: 0 - 100 (percent)
+
+What:		/sys/class/power_supply/<supply_name>/charge_control_end_threshold
+Date:		April 2019
+Contact:	linux-pm@vger.kernel.org
+Description:
+		Represents a battery percentage level, above which charging will
+		stop.
+
+		Access: Read, Write
+		Valid values: 0 - 100 (percent)
+
 What:		/sys/class/power_supply/<supply_name>/charge_type
 Date:		July 2009
 Contact:	linux-pm@vger.kernel.org
 Description:
 		Represents the type of charging currently being applied to the
-		battery.
+		battery. "Trickle", "Fast", and "Standard" all mean different
+		charging speeds. "Adaptive" means that the charger uses some
+		algorithm to adjust the charge rate dynamically, without
+		any user configuration required. "Custom" means that the charger
+		uses the charge_control_* properties as configuration for some
+		different algorithm.
 
-		Access: Read
+		Access: Read, Write
-		Valid values: "Unknown", "N/A", "Trickle", "Fast"
+		Valid values: "Unknown", "N/A", "Trickle", "Fast", "Standard",
+			      "Adaptive", "Custom"
 
 What:		/sys/class/power_supply/<supply_name>/charge_term_current
 Date:		July 2014

Documentation/ABI/testing/sysfs-devices-platform-ipmi

@@ -212,7 +212,7 @@ Description:
 					Messages may be broken into parts if
 					they are long.
 
-		receieved_messages:	(RO) Number of message responses
+		received_messages:	(RO) Number of message responses
 					received.
 
 		received_message_parts: (RO) Number of message fragments

Documentation/ABI/testing/sysfs-devices-system-cpu

@@ -484,6 +484,7 @@ What:		/sys/devices/system/cpu/vulnerabilities
 		/sys/devices/system/cpu/vulnerabilities/spectre_v2
 		/sys/devices/system/cpu/vulnerabilities/spec_store_bypass
 		/sys/devices/system/cpu/vulnerabilities/l1tf
+		/sys/devices/system/cpu/vulnerabilities/mds
 Date:		January 2018
 Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
 Description:	Information about CPU vulnerabilities
@@ -496,8 +497,7 @@ Description:	Information about CPU vulnerabilities
 		"Vulnerable"	  CPU is affected and no mitigation in effect
 		"Mitigation: $M"  CPU is affected and mitigation $M is in effect
 
-		Details about the l1tf file can be found in
+		See also: Documentation/admin-guide/hw-vuln/index.rst
-		Documentation/admin-guide/l1tf.rst
 
 What:		/sys/devices/system/cpu/smt
 		/sys/devices/system/cpu/smt/active
@@ -511,10 +511,30 @@ Description:	Control Symetric Multi Threading (SMT)
 		control: Read/write interface to control SMT. Possible
 			 values:
 
-			 "on"		SMT is enabled
+			 "on"		  SMT is enabled
-			 "off"		SMT is disabled
+			 "off"		  SMT is disabled
-			 "forceoff"	SMT is force disabled. Cannot be changed.
+			 "forceoff"	  SMT is force disabled. Cannot be changed.
-			 "notsupported" SMT is not supported by the CPU
+			 "notsupported"   SMT is not supported by the CPU
+			 "notimplemented" SMT runtime toggling is not
+					  implemented for the architecture
 
 			 If control status is "forceoff" or "notsupported" writes
 			 are rejected.
+
+What:		/sys/devices/system/cpu/cpu#/power/energy_perf_bias
+Date:		March 2019
+Contact:	linux-pm@vger.kernel.org
+Description:	Intel Energy and Performance Bias Hint (EPB)
+
+		EPB for the given CPU in a sliding scale 0 - 15, where a value
+		of 0 corresponds to a hint preference for highest performance
+		and a value of 15 corresponds to the maximum energy savings.
+
+		In order to change the EPB value for the CPU, write either
+		a number in the 0 - 15 sliding scale above, or one of the
+		strings: "performance", "balance-performance", "normal",
+		"balance-power", "power" (that represent values reflected by
+		their meaning), to this attribute.
+
+		This attribute is present for all online CPUs supporting the
+		Intel EPB feature.

Documentation/ABI/testing/sysfs-driver-ucsi-ccg

@@ -0,0 +1,6 @@
+What:		/sys/bus/i2c/drivers/ucsi_ccg/.../do_flash
+Date:		May 2019
+Contact:	Ajay Gupta <ajayg@nvidia.com>
+Description:
+		Tell the driver for Cypress CCGx Type-C controller to attempt
+		firmware upgrade by writing [Yy1] to the file.

Documentation/ABI/testing/sysfs-kernel-livepatch

@@ -45,7 +45,7 @@ Description:
 		use this feature without a clearance from a patch
 		distributor. Removal (rmmod) of patch modules is permanently
 		disabled when the feature is used. See
-		Documentation/livepatch/livepatch.txt for more information.
+		Documentation/livepatch/livepatch.rst for more information.
 
 What:		/sys/kernel/livepatch/<patch>/<object>
 Date:		Nov 2014

Documentation/ABI/testing/usb-uevent

@@ -0,0 +1,27 @@
+What:		Raise a uevent when a USB Host Controller has died
+Date:		2019-04-17
+KernelVersion:	5.2
+Contact:	linux-usb@vger.kernel.org
+Description:	When the USB Host Controller has entered a state where it is no
+		longer functional a uevent will be raised. The uevent will
+		contain ACTION=offline and ERROR=DEAD.
+
+		Here is an example taken using udevadm monitor -p:
+
+		KERNEL[130.428945] offline  /devices/pci0000:00/0000:00:10.0/usb2 (usb)
+		ACTION=offline
+		BUSNUM=002
+		DEVNAME=/dev/bus/usb/002/001
+		DEVNUM=001
+		DEVPATH=/devices/pci0000:00/0000:00:10.0/usb2
+		DEVTYPE=usb_device
+		DRIVER=usb
+		ERROR=DEAD
+		MAJOR=189
+		MINOR=128
+		PRODUCT=1d6b/2/414
+		SEQNUM=2168
+		SUBSYSTEM=usb
+		TYPE=9/0/1
+
+Users:		chromium-os-dev@chromium.org

Documentation/DMA-API-HOWTO.txt

@@ -147,7 +147,7 @@ networking subsystems make sure that the buffers they use are valid
 for you to DMA from/to.
 
 DMA addressing capabilities
-==========================
+===========================
 
 By default, the kernel assumes that your device can address 32-bits of DMA
 addressing.  For a 64-bit capable device, this needs to be increased, and for
@@ -365,13 +365,12 @@ __get_free_pages() (but takes size instead of a page order).  If your
 driver needs regions sized smaller than a page, you may prefer using
 the dma_pool interface, described below.
 
-The consistent DMA mapping interfaces, for non-NULL dev, will by
+The consistent DMA mapping interfaces, will by default return a DMA address
-default return a DMA address which is 32-bit addressable.  Even if the
+which is 32-bit addressable.  Even if the device indicates (via the DMA mask)
-device indicates (via DMA mask) that it may address the upper 32-bits,
+that it may address the upper 32-bits, consistent allocation will only
-consistent allocation will only return > 32-bit addresses for DMA if
+return > 32-bit addresses for DMA if the consistent DMA mask has been
-the consistent DMA mask has been explicitly changed via
+explicitly changed via dma_set_coherent_mask().  This is true of the
-dma_set_coherent_mask().  This is true of the dma_pool interface as
+dma_pool interface as well.
-well.
 
 dma_alloc_coherent() returns two values: the virtual address which you
 can use to access it from the CPU and dma_handle which you pass to the

Documentation/Makefile

@@ -28,8 +28,13 @@ ifeq ($(HAVE_SPHINX),0)
 
 else # HAVE_SPHINX
 
-# User-friendly check for pdflatex
+# User-friendly check for pdflatex and latexmk
 HAVE_PDFLATEX := $(shell if which $(PDFLATEX) >/dev/null 2>&1; then echo 1; else echo 0; fi)
+HAVE_LATEXMK := $(shell if which latexmk >/dev/null 2>&1; then echo 1; else echo 0; fi)
+
+ifeq ($(HAVE_LATEXMK),1)
+	PDFLATEX := latexmk -$(PDFLATEX)
+endif #HAVE_LATEXMK
 
 # Internal variables.
 PAPEROPT_a4     = -D latex_paper_size=a4
@@ -82,7 +87,7 @@ pdfdocs:
 else # HAVE_PDFLATEX
 
 pdfdocs: latexdocs
-	$(foreach var,$(SPHINXDIRS), $(MAKE) PDFLATEX=$(PDFLATEX) LATEXOPTS="$(LATEXOPTS)" -C $(BUILDDIR)/$(var)/latex || exit;)
+	$(foreach var,$(SPHINXDIRS), $(MAKE) PDFLATEX="$(PDFLATEX)" LATEXOPTS="$(LATEXOPTS)" -C $(BUILDDIR)/$(var)/latex || exit;)
 
 endif # HAVE_PDFLATEX
 

Documentation/RCU/Design/Data-Structures/Data-Structures.html

@@ -155,8 +155,7 @@ keeping lock contention under control at all tree levels regardless
 of the level of loading on the system.
 
 </p><p>RCU updaters wait for normal grace periods by registering
-RCU callbacks, either directly via <tt>call_rcu()</tt> and
+RCU callbacks, either directly via <tt>call_rcu()</tt>
-friends (namely <tt>call_rcu_bh()</tt> and <tt>call_rcu_sched()</tt>),
 or indirectly via <tt>synchronize_rcu()</tt> and friends.
 RCU callbacks are represented by <tt>rcu_head</tt> structures,
 which are queued on <tt>rcu_data</tt> structures while they are

Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.html

@@ -56,6 +56,7 @@ sections.
 RCU-preempt Expedited Grace Periods</a></h2>
 
 <p>
+<tt>CONFIG_PREEMPT=y</tt> kernels implement RCU-preempt.
 The overall flow of the handling of a given CPU by an RCU-preempt
 expedited grace period is shown in the following diagram:
 
@@ -139,6 +140,7 @@ or offline, among other things.
 RCU-sched Expedited Grace Periods</a></h2>
 
 <p>
+<tt>CONFIG_PREEMPT=n</tt> kernels implement RCU-sched.
 The overall flow of the handling of a given CPU by an RCU-sched
 expedited grace period is shown in the following diagram:
 
@@ -146,7 +148,7 @@ expedited grace period is shown in the following diagram:
 
 <p>
 As with RCU-preempt, RCU-sched's
-<tt>synchronize_sched_expedited()</tt> ignores offline and
+<tt>synchronize_rcu_expedited()</tt> ignores offline and
 idle CPUs, again because they are in remotely detectable
 quiescent states.
 However, because the

Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html

@@ -34,12 +34,11 @@ Similarly, any code that happens before the beginning of a given RCU grace
 period is guaranteed to see the effects of all accesses following the end
 of that grace period that are within RCU read-side critical sections.
 
-<p>This guarantee is particularly pervasive for <tt>synchronize_sched()</tt>,
+<p>Note well that RCU-sched read-side critical sections include any region
-for which RCU-sched read-side critical sections include any region
 of code for which preemption is disabled.
 Given that each individual machine instruction can be thought of as
 an extremely small region of preemption-disabled code, one can think of
-<tt>synchronize_sched()</tt> as <tt>smp_mb()</tt> on steroids.
+<tt>synchronize_rcu()</tt> as <tt>smp_mb()</tt> on steroids.
 
 <p>RCU updaters use this guarantee by splitting their updates into
 two phases, one of which is executed before the grace period and

Documentation/RCU/NMI-RCU.txt

@@ -81,18 +81,19 @@ currently executing on some other CPU.  We therefore cannot free
 up any data structures used by the old NMI handler until execution
 of it completes on all other CPUs.
 
-One way to accomplish this is via synchronize_sched(), perhaps as
+One way to accomplish this is via synchronize_rcu(), perhaps as
 follows:
 
 	unset_nmi_callback();
-	synchronize_sched();
+	synchronize_rcu();
 	kfree(my_nmi_data);
 
-This works because synchronize_sched() blocks until all CPUs complete
+This works because (as of v4.20) synchronize_rcu() blocks until all
-any preemption-disabled segments of code that they were executing.
+CPUs complete any preemption-disabled segments of code that they were
-Since NMI handlers disable preemption, synchronize_sched() is guaranteed
+executing.
+Since NMI handlers disable preemption, synchronize_rcu() is guaranteed
 not to return until all ongoing NMI handlers exit.  It is therefore safe
-to free up the handler's data as soon as synchronize_sched() returns.
+to free up the handler's data as soon as synchronize_rcu() returns.
 
 Important note: for this to work, the architecture in question must
 invoke nmi_enter() and nmi_exit() on NMI entry and exit, respectively.

Documentation/RCU/UP.txt

@@ -86,10 +86,8 @@ even on a UP system.  So do not do it!  Even on a UP system, the RCU
 infrastructure -must- respect grace periods, and -must- invoke callbacks
 from a known environment in which no locks are held.
 
-It -is- safe for synchronize_sched() and synchronize_rcu_bh() to return
+Note that it -is- safe for synchronize_rcu() to return immediately on
-immediately on an UP system.  It is also safe for synchronize_rcu()
+UP systems, including !PREEMPT SMP builds running on UP systems.
-to return immediately on UP systems, except when running preemptable
-RCU.
 
 Quick Quiz #3: Why can't synchronize_rcu() return immediately on
 	UP systems running preemptable RCU?

Documentation/RCU/checklist.txt

@@ -182,16 +182,13 @@ over a rather long period of time, but improvements are always welcome!
 		when publicizing a pointer to a structure that can
 		be traversed by an RCU read-side critical section.
 
-5.	If call_rcu(), or a related primitive such as call_rcu_bh(),
+5.	If call_rcu() or call_srcu() is used, the callback function will
-	call_rcu_sched(), or call_srcu() is used, the callback function
+	be called from softirq context.  In particular, it cannot block.
-	will be called from softirq context.  In particular, it cannot
-	block.
 
-6.	Since synchronize_rcu() can block, it cannot be called from
+6.	Since synchronize_rcu() can block, it cannot be called
-	any sort of irq context.  The same rule applies for
+	from any sort of irq context.  The same rule applies
-	synchronize_rcu_bh(), synchronize_sched(), synchronize_srcu(),
+	for synchronize_srcu(), synchronize_rcu_expedited(), and
-	synchronize_rcu_expedited(), synchronize_rcu_bh_expedited(),
+	synchronize_srcu_expedited().
-	synchronize_sched_expedite(), and synchronize_srcu_expedited().
 
 	The expedited forms of these primitives have the same semantics
 	as the non-expedited forms, but expediting is both expensive and
@@ -212,20 +209,20 @@ over a rather long period of time, but improvements are always welcome!
 	of the system, especially to real-time workloads running on
 	the rest of the system.
 
-7.	If the updater uses call_rcu() or synchronize_rcu(), then the
+7.	As of v4.20, a given kernel implements only one RCU flavor,
-	corresponding readers must use rcu_read_lock() and
+	which is RCU-sched for PREEMPT=n and RCU-preempt for PREEMPT=y.
-	rcu_read_unlock().  If the updater uses call_rcu_bh() or
+	If the updater uses call_rcu() or synchronize_rcu(),
-	synchronize_rcu_bh(), then the corresponding readers must
+	then the corresponding readers my use rcu_read_lock() and
-	use rcu_read_lock_bh() and rcu_read_unlock_bh().  If the
+	rcu_read_unlock(), rcu_read_lock_bh() and rcu_read_unlock_bh(),
-	updater uses call_rcu_sched() or synchronize_sched(), then
+	or any pair of primitives that disables and re-enables preemption,
-	the corresponding readers must disable preemption, possibly
+	for example, rcu_read_lock_sched() and rcu_read_unlock_sched().
-	by calling rcu_read_lock_sched() and rcu_read_unlock_sched().
+	If the updater uses synchronize_srcu() or call_srcu(),
-	If the updater uses synchronize_srcu() or call_srcu(), then
+	then the corresponding readers must use srcu_read_lock() and
-	the corresponding readers must use srcu_read_lock() and
 	srcu_read_unlock(), and with the same srcu_struct.  The rules for
 	the expedited primitives are the same as for their non-expedited
 	counterparts.  Mixing things up will result in confusion and
-	broken kernels.
+	broken kernels, and has even resulted in an exploitable security
+	issue.
 
 	One exception to this rule: rcu_read_lock() and rcu_read_unlock()
 	may be substituted for rcu_read_lock_bh() and rcu_read_unlock_bh()
@@ -288,8 +285,7 @@ over a rather long period of time, but improvements are always welcome!
 	d.	Periodically invoke synchronize_rcu(), permitting a limited
 		number of updates per grace period.
 
-	The same cautions apply to call_rcu_bh(), call_rcu_sched(),
+	The same cautions apply to call_srcu() and kfree_rcu().
-	call_srcu(), and kfree_rcu().
 
 	Note that although these primitives do take action to avoid memory
 	exhaustion when any given CPU has too many callbacks, a determined
@@ -322,7 +318,7 @@ over a rather long period of time, but improvements are always welcome!
 
 11.	Any lock acquired by an RCU callback must be acquired elsewhere
 	with softirq disabled, e.g., via spin_lock_irqsave(),
-	spin_lock_bh(), etc.  Failing to disable irq on a given
+	spin_lock_bh(), etc.  Failing to disable softirq on a given
 	acquisition of that lock will result in deadlock as soon as
 	the RCU softirq handler happens to run your RCU callback while
 	interrupting that acquisition's critical section.
@@ -335,13 +331,16 @@ over a rather long period of time, but improvements are always welcome!
 	must use whatever locking or other synchronization is required
 	to safely access and/or modify that data structure.
 
-	RCU callbacks are -usually- executed on the same CPU that executed
+	Do not assume that RCU callbacks will be executed on the same
-	the corresponding call_rcu(), call_rcu_bh(), or call_rcu_sched(),
+	CPU that executed the corresponding call_rcu() or call_srcu().
-	but are by -no- means guaranteed to be.  For example, if a given
+	For example, if a given CPU goes offline while having an RCU
-	CPU goes offline while having an RCU callback pending, then that
+	callback pending, then that RCU callback will execute on some
-	RCU callback will execute on some surviving CPU.  (If this was
+	surviving CPU.	(If this was not the case, a self-spawning RCU
-	not the case, a self-spawning RCU callback would prevent the
+	callback would prevent the victim CPU from ever going offline.)
-	victim CPU from ever going offline.)
+	Furthermore, CPUs designated by rcu_nocbs= might well -always-
+	have their RCU callbacks executed on some other CPUs, in fact,
+	for some  real-time workloads, this is the whole point of using
+	the rcu_nocbs= kernel boot parameter.
 
 13.	Unlike other forms of RCU, it -is- permissible to block in an
 	SRCU read-side critical section (demarked by srcu_read_lock()
@@ -381,11 +380,11 @@ over a rather long period of time, but improvements are always welcome!
 
 	SRCU's expedited primitive (synchronize_srcu_expedited())
 	never sends IPIs to other CPUs, so it is easier on
-	real-time workloads than is synchronize_rcu_expedited(),
+	real-time workloads than is synchronize_rcu_expedited().
-	synchronize_rcu_bh_expedited() or synchronize_sched_expedited().
 
-	Note that rcu_dereference() and rcu_assign_pointer() relate to
+	Note that rcu_assign_pointer() relates to SRCU just as it does to
-	SRCU just as they do to other forms of RCU.
+	other forms of RCU, but instead of rcu_dereference() you should
+	use srcu_dereference() in order to avoid lockdep splats.
 
 14.	The whole point of call_rcu(), synchronize_rcu(), and friends
 	is to wait until all pre-existing readers have finished before
@@ -405,6 +404,9 @@ over a rather long period of time, but improvements are always welcome!
 	read-side critical sections.  It is the responsibility of the
 	RCU update-side primitives to deal with this.
 
+	For SRCU readers, you can use smp_mb__after_srcu_read_unlock()
+	immediately after an srcu_read_unlock() to get a full barrier.
+
 16.	Use CONFIG_PROVE_LOCKING, CONFIG_DEBUG_OBJECTS_RCU_HEAD, and the
 	__rcu sparse checks to validate your RCU code.	These can help
 	find problems as follows:
@@ -428,22 +430,19 @@ over a rather long period of time, but improvements are always welcome!
 	These debugging aids can help you find problems that are
 	otherwise extremely difficult to spot.
 
-17.	If you register a callback using call_rcu(), call_rcu_bh(),
+17.	If you register a callback using call_rcu() or call_srcu(), and
-	call_rcu_sched(), or call_srcu(), and pass in a function defined
+	pass in a function defined within a loadable module, then it in
-	within a loadable module, then it in necessary to wait for
+	necessary to wait for all pending callbacks to be invoked after
-	all pending callbacks to be invoked after the last invocation
+	the last invocation and before unloading that module.  Note that
-	and before unloading that module.  Note that it is absolutely
+	it is absolutely -not- sufficient to wait for a grace period!
-	-not- sufficient to wait for a grace period!  The current (say)
+	The current (say) synchronize_rcu() implementation is -not-
-	synchronize_rcu() implementation waits only for all previous
+	guaranteed to wait for callbacks registered on other CPUs.
-	callbacks registered on the CPU that synchronize_rcu() is running
+	Or even on the current CPU if that CPU recently went offline
-	on, but it is -not- guaranteed to wait for callbacks registered
+	and came back online.
-	on other CPUs.
 
 	You instead need to use one of the barrier functions:
 
 	o	call_rcu() -> rcu_barrier()
-	o	call_rcu_bh() -> rcu_barrier()
-	o	call_rcu_sched() -> rcu_barrier()
 	o	call_srcu() -> srcu_barrier()
 
 	However, these barrier functions are absolutely -not- guaranteed

Documentation/RCU/rcu.txt

@@ -52,10 +52,10 @@ o	If I am running on a uniprocessor kernel, which can only do one
 o	How can I see where RCU is currently used in the Linux kernel?
 
 	Search for "rcu_read_lock", "rcu_read_unlock", "call_rcu",
-	"rcu_read_lock_bh", "rcu_read_unlock_bh", "call_rcu_bh",
+	"rcu_read_lock_bh", "rcu_read_unlock_bh", "srcu_read_lock",
-	"srcu_read_lock", "srcu_read_unlock", "synchronize_rcu",
+	"srcu_read_unlock", "synchronize_rcu", "synchronize_net",
-	"synchronize_net", "synchronize_srcu", and the other RCU
+	"synchronize_srcu", and the other RCU primitives.  Or grab one
-	primitives.  Or grab one of the cscope databases from:
+	of the cscope databases from:
 
 	http://www.rdrop.com/users/paulmck/RCU/linuxusage/rculocktab.html
 

Documentation/RCU/rcu_dereference.txt

@@ -351,3 +351,106 @@ garbage values.
 
 In short, rcu_dereference() is -not- optional when you are going to
 dereference the resulting pointer.
+
+
+WHICH MEMBER OF THE rcu_dereference() FAMILY SHOULD YOU USE?
+
+First, please avoid using rcu_dereference_raw() and also please avoid
+using rcu_dereference_check() and rcu_dereference_protected() with a
+second argument with a constant value of 1 (or true, for that matter).
+With that caution out of the way, here is some guidance for which
+member of the rcu_dereference() to use in various situations:
+
+1.	If the access needs to be within an RCU read-side critical
+	section, use rcu_dereference().  With the new consolidated
+	RCU flavors, an RCU read-side critical section is entered
+	using rcu_read_lock(), anything that disables bottom halves,
+	anything that disables interrupts, or anything that disables
+	preemption.
+
+2.	If the access might be within an RCU read-side critical section
+	on the one hand, or protected by (say) my_lock on the other,
+	use rcu_dereference_check(), for example:
+
+		p1 = rcu_dereference_check(p->rcu_protected_pointer,
+					   lockdep_is_held(&my_lock));
+
+
+3.	If the access might be within an RCU read-side critical section
+	on the one hand, or protected by either my_lock or your_lock on
+	the other, again use rcu_dereference_check(), for example:
+
+		p1 = rcu_dereference_check(p->rcu_protected_pointer,
+					   lockdep_is_held(&my_lock) ||
+					   lockdep_is_held(&your_lock));
+
+4.	If the access is on the update side, so that it is always protected
+	by my_lock, use rcu_dereference_protected():
+
+		p1 = rcu_dereference_protected(p->rcu_protected_pointer,
+					       lockdep_is_held(&my_lock));
+
+	This can be extended to handle multiple locks as in #3 above,
+	and both can be extended to check other conditions as well.
+
+5.	If the protection is supplied by the caller, and is thus unknown
+	to this code, that is the rare case when rcu_dereference_raw()
+	is appropriate.  In addition, rcu_dereference_raw() might be
+	appropriate when the lockdep expression would be excessively
+	complex, except that a better approach in that case might be to
+	take a long hard look at your synchronization design.  Still,
+	there are data-locking cases where any one of a very large number
+	of locks or reference counters suffices to protect the pointer,
+	so rcu_dereference_raw() does have its place.
+
+	However, its place is probably quite a bit smaller than one
+	might expect given the number of uses in the current kernel.
+	Ditto for its synonym, rcu_dereference_check( ... , 1), and
+	its close relative, rcu_dereference_protected(... , 1).
+
+
+SPARSE CHECKING OF RCU-PROTECTED POINTERS
+
+The sparse static-analysis tool checks for direct access to RCU-protected
+pointers, which can result in "interesting" bugs due to compiler
+optimizations involving invented loads and perhaps also load tearing.
+For example, suppose someone mistakenly does something like this:
+
+	p = q->rcu_protected_pointer;
+	do_something_with(p->a);
+	do_something_else_with(p->b);
+
+If register pressure is high, the compiler might optimize "p" out
+of existence, transforming the code to something like this:
+
+	do_something_with(q->rcu_protected_pointer->a);
+	do_something_else_with(q->rcu_protected_pointer->b);
+
+This could fatally disappoint your code if q->rcu_protected_pointer
+changed in the meantime.  Nor is this a theoretical problem:  Exactly
+this sort of bug cost Paul E. McKenney (and several of his innocent
+colleagues) a three-day weekend back in the early 1990s.
+
+Load tearing could of course result in dereferencing a mashup of a pair
+of pointers, which also might fatally disappoint your code.
+
+These problems could have been avoided simply by making the code instead
+read as follows:
+
+	p = rcu_dereference(q->rcu_protected_pointer);
+	do_something_with(p->a);
+	do_something_else_with(p->b);
+
+Unfortunately, these sorts of bugs can be extremely hard to spot during
+review.  This is where the sparse tool comes into play, along with the
+"__rcu" marker.  If you mark a pointer declaration, whether in a structure
+or as a formal parameter, with "__rcu", which tells sparse to complain if
+this pointer is accessed directly.  It will also cause sparse to complain
+if a pointer not marked with "__rcu" is accessed using rcu_dereference()
+and friends.  For example, ->rcu_protected_pointer might be declared as
+follows:
+
+	struct foo __rcu *rcu_protected_pointer;
+
+Use of "__rcu" is opt-in.  If you choose not to use it, then you should
+ignore the sparse warnings.

Documentation/RCU/rcubarrier.txt

@@ -83,16 +83,15 @@ Pseudo-code using rcu_barrier() is as follows:
    2. Execute rcu_barrier().
    3. Allow the module to be unloaded.
 
-There are also rcu_barrier_bh(), rcu_barrier_sched(), and srcu_barrier()
+There is also an srcu_barrier() function for SRCU, and you of course
-functions for the other flavors of RCU, and you of course must match
+must match the flavor of rcu_barrier() with that of call_rcu().  If your
-the flavor of rcu_barrier() with that of call_rcu().  If your module
+module uses multiple flavors of call_rcu(), then it must also use multiple
-uses multiple flavors of call_rcu(), then it must also use multiple
 flavors of rcu_barrier() when unloading that module.  For example, if
-it uses call_rcu_bh(), call_srcu() on srcu_struct_1, and call_srcu() on
+it uses call_rcu(), call_srcu() on srcu_struct_1, and call_srcu() on
 srcu_struct_2(), then the following three lines of code will be required
 when unloading:
 
- 1 rcu_barrier_bh();
+ 1 rcu_barrier();
  2 srcu_barrier(&srcu_struct_1);
  3 srcu_barrier(&srcu_struct_2);
 
@@ -185,12 +184,12 @@ module invokes call_rcu() from timers, you will need to first cancel all
 the timers, and only then invoke rcu_barrier() to wait for any remaining
 RCU callbacks to complete.
 
-Of course, if you module uses call_rcu_bh(), you will need to invoke
+Of course, if you module uses call_rcu(), you will need to invoke
-rcu_barrier_bh() before unloading.  Similarly, if your module uses
+rcu_barrier() before unloading.  Similarly, if your module uses
-call_rcu_sched(), you will need to invoke rcu_barrier_sched() before
+call_srcu(), you will need to invoke srcu_barrier() before unloading,
-unloading.  If your module uses call_rcu(), call_rcu_bh(), -and-
+and on the same srcu_struct structure.  If your module uses call_rcu()
-call_rcu_sched(), then you will need to invoke each of rcu_barrier(),
+-and- call_srcu(), then you will need to invoke rcu_barrier() -and-
-rcu_barrier_bh(), and rcu_barrier_sched().
+srcu_barrier().
 
 
 Implementing rcu_barrier()
@@ -223,8 +222,8 @@ shown below. Note that the final "1" in on_each_cpu()'s argument list
 ensures that all the calls to rcu_barrier_func() will have completed
 before on_each_cpu() returns. Line 9 then waits for the completion.
 
-This code was rewritten in 2008 to support rcu_barrier_bh() and
+This code was rewritten in 2008 and several times thereafter, but this
-rcu_barrier_sched() in addition to the original rcu_barrier().
+still gives the general idea.
 
 The rcu_barrier_func() runs on each CPU, where it invokes call_rcu()
 to post an RCU callback, as follows:

Documentation/RCU/whatisRCU.txt

@@ -310,7 +310,7 @@ reader, updater, and reclaimer.
 
 
 	    rcu_assign_pointer()
-	    			    +--------+
+	                            +--------+
 	    +---------------------->| reader |---------+
 	    |                       +--------+         |
 	    |                           |              |
@@ -318,12 +318,12 @@ reader, updater, and reclaimer.
 	    |                           |              | rcu_read_lock()
 	    |                           |              | rcu_read_unlock()
 	    |        rcu_dereference()  |              |
-       +---------+                      |              |
+	    +---------+                 |              |
-       | updater |<---------------------+              |
+	    | updater |<----------------+              |
-       +---------+                                     V
+	    +---------+                                V
 	    |                                    +-----------+
 	    +----------------------------------->| reclaimer |
-	    				         +-----------+
+	                                         +-----------+
 	      Defer:
 	      synchronize_rcu() & call_rcu()
 

Documentation/accounting/psi.txt

@@ -63,6 +63,110 @@ as well as medium and long term trends. The total absolute stall time
 spikes which wouldn't necessarily make a dent in the time averages,
 or to average trends over custom time frames.
 
+Monitoring for pressure thresholds
+==================================
+
+Users can register triggers and use poll() to be woken up when resource
+pressure exceeds certain thresholds.
+
+A trigger describes the maximum cumulative stall time over a specific
+time window, e.g. 100ms of total stall time within any 500ms window to
+generate a wakeup event.
+
+To register a trigger user has to open psi interface file under
+/proc/pressure/ representing the resource to be monitored and write the
+desired threshold and time window. The open file descriptor should be
+used to wait for trigger events using select(), poll() or epoll().
+The following format is used:
+
+<some|full> <stall amount in us> <time window in us>
+
+For example writing "some 150000 1000000" into /proc/pressure/memory
+would add 150ms threshold for partial memory stall measured within
+1sec time window. Writing "full 50000 1000000" into /proc/pressure/io
+would add 50ms threshold for full io stall measured within 1sec time window.
+
+Triggers can be set on more than one psi metric and more than one trigger
+for the same psi metric can be specified. However for each trigger a separate
+file descriptor is required to be able to poll it separately from others,
+therefore for each trigger a separate open() syscall should be made even
+when opening the same psi interface file.
+
+Monitors activate only when system enters stall state for the monitored
+psi metric and deactivates upon exit from the stall state. While system is
+in the stall state psi signal growth is monitored at a rate of 10 times per
+tracking window.
+
+The kernel accepts window sizes ranging from 500ms to 10s, therefore min
+monitoring update interval is 50ms and max is 1s. Min limit is set to
+prevent overly frequent polling. Max limit is chosen as a high enough number
+after which monitors are most likely not needed and psi averages can be used
+instead.
+
+When activated, psi monitor stays active for at least the duration of one
+tracking window to avoid repeated activations/deactivations when system is
+bouncing in and out of the stall state.
+
+Notifications to the userspace are rate-limited to one per tracking window.
+
+The trigger will de-register when the file descriptor used to define the
+trigger  is closed.
+
+Userspace monitor usage example
+===============================
+
+#include <errno.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <poll.h>
+#include <string.h>
+#include <unistd.h>
+
+/*
+ * Monitor memory partial stall with 1s tracking window size
+ * and 150ms threshold.
+ */
+int main() {
+	const char trig[] = "some 150000 1000000";
+	struct pollfd fds;
+	int n;
+
+	fds.fd = open("/proc/pressure/memory", O_RDWR | O_NONBLOCK);
+	if (fds.fd < 0) {
+		printf("/proc/pressure/memory open error: %s\n",
+			strerror(errno));
+		return 1;
+	}
+	fds.events = POLLPRI;
+
+	if (write(fds.fd, trig, strlen(trig) + 1) < 0) {
+		printf("/proc/pressure/memory write error: %s\n",
+			strerror(errno));
+		return 1;
+	}
+
+	printf("waiting for events...\n");
+	while (1) {
+		n = poll(&fds, 1, -1);
+		if (n < 0) {
+			printf("poll error: %s\n", strerror(errno));
+			return 1;
+		}
+		if (fds.revents & POLLERR) {
+			printf("got POLLERR, event source is gone\n");
+			return 0;
+		}
+		if (fds.revents & POLLPRI) {
+			printf("event triggered!\n");
+		} else {
+			printf("unknown event received: 0x%x\n", fds.revents);
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
 Cgroup2 interface
 =================
 
@@ -71,3 +175,6 @@ mounted, pressure stall information is also tracked for tasks grouped
 into cgroups. Each subdirectory in the cgroupfs mountpoint contains
 cpu.pressure, memory.pressure, and io.pressure files; the format is
 the same as the /proc/pressure/ files.
+
+Per-cgroup psi monitors can be specified and used the same way as
+system-wide ones.

Documentation/acpi/aml-debugger.txt

@@ -1,66 +0,0 @@
-The AML Debugger
-
-Copyright (C) 2016, Intel Corporation
-Author: Lv Zheng <lv.zheng@intel.com>
-
-
-This document describes the usage of the AML debugger embedded in the Linux
-kernel.
-
-1. Build the debugger
-
-   The following kernel configuration items are required to enable the AML
-   debugger interface from the Linux kernel:
-
-   CONFIG_ACPI_DEBUGGER=y
-   CONFIG_ACPI_DEBUGGER_USER=m
-
-   The userspace utilities can be built from the kernel source tree using
-   the following commands:
-
-   $ cd tools
-   $ make acpi
-
-   The resultant userspace tool binary is then located at:
-
-     tools/power/acpi/acpidbg
-
-   It can be installed to system directories by running "make install" (as a
-   sufficiently privileged user).
-
-2. Start the userspace debugger interface
-
-   After booting the kernel with the debugger built-in, the debugger can be
-   started by using the following commands:
-
-   # mount -t debugfs none /sys/kernel/debug
-   # modprobe acpi_dbg
-   # tools/power/acpi/acpidbg
-
-   That spawns the interactive AML debugger environment where you can execute
-   debugger commands.
-
-   The commands are documented in the "ACPICA Overview and Programmer Reference"
-   that can be downloaded from
-
-   https://acpica.org/documentation
-
-   The detailed debugger commands reference is located in Chapter 12 "ACPICA
-   Debugger Reference".  The "help" command can be used for a quick reference.
-
-3. Stop the userspace debugger interface
-
-   The interactive debugger interface can be closed by pressing Ctrl+C or using
-   the "quit" or "exit" commands.  When finished, unload the module with:
-
-   # rmmod acpi_dbg
-
-   The module unloading may fail if there is an acpidbg instance running.
-
-4. Run the debugger in a script
-
-   It may be useful to run the AML debugger in a test script. "acpidbg" supports
-   this in a special "batch" mode.  For example, the following command outputs
-   the entire ACPI namespace:
-
-   # acpidbg -b "namespace"

Documentation/acpi/apei/output_format.txt

@@ -1,147 +0,0 @@
-                     APEI output format
-                     ~~~~~~~~~~~~~~~~~~
-
-APEI uses printk as hardware error reporting interface, the output
-format is as follow.
-
-<error record> :=
-APEI generic hardware error status
-severity: <integer>, <severity string>
-section: <integer>, severity: <integer>, <severity string>
-flags: <integer>
-<section flags strings>
-fru_id: <uuid string>
-fru_text: <string>
-section_type: <section type string>
-<section data>
-
-<severity string>* := recoverable | fatal | corrected | info
-
-<section flags strings># :=
-[primary][, containment warning][, reset][, threshold exceeded]\
-[, resource not accessible][, latent error]
-
-<section type string> := generic processor error | memory error | \
-PCIe error | unknown, <uuid string>
-
-<section data> :=
-<generic processor section data> | <memory section data> | \
-<pcie section data> | <null>
-
-<generic processor section data> :=
-[processor_type: <integer>, <proc type string>]
-[processor_isa: <integer>, <proc isa string>]
-[error_type: <integer>
-<proc error type strings>]
-[operation: <integer>, <proc operation string>]
-[flags: <integer>
-<proc flags strings>]
-[level: <integer>]
-[version_info: <integer>]
-[processor_id: <integer>]
-[target_address: <integer>]
-[requestor_id: <integer>]
-[responder_id: <integer>]
-[IP: <integer>]
-
-<proc type string>* := IA32/X64 | IA64
-
-<proc isa string>* := IA32 | IA64 | X64
-
-<processor error type strings># :=
-[cache error][, TLB error][, bus error][, micro-architectural error]
-
-<proc operation string>* := unknown or generic | data read | data write | \
-instruction execution
-
-<proc flags strings># :=
-[restartable][, precise IP][, overflow][, corrected]
-
-<memory section data> :=
-[error_status: <integer>]
-[physical_address: <integer>]
-[physical_address_mask: <integer>]
-[node: <integer>]
-[card: <integer>]
-[module: <integer>]
-[bank: <integer>]
-[device: <integer>]
-[row: <integer>]
-[column: <integer>]
-[bit_position: <integer>]
-[requestor_id: <integer>]
-[responder_id: <integer>]
-[target_id: <integer>]
-[error_type: <integer>, <mem error type string>]
-
-<mem error type string>* :=
-unknown | no error | single-bit ECC | multi-bit ECC | \
-single-symbol chipkill ECC | multi-symbol chipkill ECC | master abort | \
-target abort | parity error | watchdog timeout | invalid address | \
-mirror Broken | memory sparing | scrub corrected error | \
-scrub uncorrected error
-
-<pcie section data> :=
-[port_type: <integer>, <pcie port type string>]
-[version: <integer>.<integer>]
-[command: <integer>, status: <integer>]
-[device_id: <integer>:<integer>:<integer>.<integer>
-slot: <integer>
-secondary_bus: <integer>
-vendor_id: <integer>, device_id: <integer>
-class_code: <integer>]
-[serial number: <integer>, <integer>]
-[bridge: secondary_status: <integer>, control: <integer>]
-[aer_status: <integer>, aer_mask: <integer>
-<aer status string>
-[aer_uncor_severity: <integer>]
-aer_layer=<aer layer string>, aer_agent=<aer agent string>
-aer_tlp_header: <integer> <integer> <integer> <integer>]
-
-<pcie port type string>* := PCIe end point | legacy PCI end point | \
-unknown | unknown | root port | upstream switch port | \
-downstream switch port | PCIe to PCI/PCI-X bridge | \
-PCI/PCI-X to PCIe bridge | root complex integrated endpoint device | \
-root complex event collector
-
-if section severity is fatal or recoverable
-<aer status string># :=
-unknown | unknown | unknown | unknown | Data Link Protocol | \
-unknown | unknown | unknown | unknown | unknown | unknown | unknown | \
-Poisoned TLP | Flow Control Protocol | Completion Timeout | \
-Completer Abort | Unexpected Completion | Receiver Overflow | \
-Malformed TLP | ECRC | Unsupported Request
-else
-<aer status string># :=
-Receiver Error | unknown | unknown | unknown | unknown | unknown | \
-Bad TLP | Bad DLLP | RELAY_NUM Rollover | unknown | unknown | unknown | \
-Replay Timer Timeout | Advisory Non-Fatal
-fi
-
-<aer layer string> :=
-Physical Layer | Data Link Layer | Transaction Layer
-
-<aer agent string> :=
-Receiver ID | Requester ID | Completer ID | Transmitter ID
-
-Where, [] designate corresponding content is optional
-
-All <field string> description with * has the following format:
-
-field: <integer>, <field string>
-
-Where value of <integer> should be the position of "string" in <field
-string> description. Otherwise, <field string> will be "unknown".
-
-All <field strings> description with # has the following format:
-
-field: <integer>
-<field strings>
-
-Where each string in <fields strings> corresponding to one set bit of
-<integer>. The bit position is the position of "string" in <field
-strings> description.
-
-For more detailed explanation of every field, please refer to UEFI
-specification version 2.3 or later, section Appendix N: Common
-Platform Error Record.

Documentation/acpi/dsd/leds.txt

@@ -0,0 +1,99 @@
+Describing and referring to LEDs in ACPI
+
+Individual LEDs are described by hierarchical data extension [6] nodes under the
+device node, the LED driver chip. The "reg" property in the LED specific nodes
+tells the numerical ID of each individual LED output to which the LEDs are
+connected. [3] The hierarchical data nodes are named "led@X", where X is the
+number of the LED output.
+
+Referring to LEDs in Device tree is documented in [4], in "flash-leds" property
+documentation. In short, LEDs are directly referred to by using phandles.
+
+While Device tree allows referring to any node in the tree[1], in ACPI
+references are limited to device nodes only [2]. For this reason using the same
+mechanism on ACPI is not possible. A mechanism to refer to non-device ACPI nodes
+is documented in [7].
+
+ACPI allows (as does DT) using integer arguments after the reference. A
+combination of the LED driver device reference and an integer argument,
+referring to the "reg" property of the relevant LED, is used to identify
+individual LEDs. The value of the "reg" property is a contract between the
+firmware and software, it uniquely identifies the LED driver outputs.
+
+Under the LED driver device, The first hierarchical data extension package list
+entry shall contain the string "led@" followed by the number of the LED,
+followed by the referred object name. That object shall be named "LED" followed
+by the number of the LED.
+
+An ASL example of a camera sensor device and a LED driver device for two LEDs.
+Objects not relevant for LEDs or the references to them have been omitted.
+
+	Device (LED)
+	{
+		Name (_DSD, Package () {
+			ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
+			Package () {
+				Package () { "led@0", LED0 },
+				Package () { "led@1", LED1 },
+			}
+		})
+		Name (LED0, Package () {
+			ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+			Package () {
+				Package () { "reg", 0 },
+				Package () { "flash-max-microamp", 1000000 },
+				Package () { "flash-timeout-us", 200000 },
+				Package () { "led-max-microamp", 100000 },
+				Package () { "label", "white:flash" },
+			}
+		})
+		Name (LED1, Package () {
+			ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+			Package () {
+				Package () { "reg", 1 },
+				Package () { "led-max-microamp", 10000 },
+				Package () { "label", "red:indicator" },
+			}
+		})
+	}
+
+	Device (SEN)
+	{
+		Name (_DSD, Package () {
+			ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+			Package () {
+				Package () {
+					"flash-leds",
+					Package () { ^LED, "led@0", ^LED, "led@1" },
+				}
+			}
+		})
+	}
+
+where
+
+	LED	LED driver device
+	LED0	First LED
+	LED1	Second LED
+	SEN	Camera sensor device (or another device the LED is
+		related to)
+
+[1] Device tree. <URL:http://www.devicetree.org>, referenced 2019-02-21.
+
+[2] Advanced Configuration and Power Interface Specification.
+    <URL:https://uefi.org/sites/default/files/resources/ACPI_6_3_final_Jan30.pdf>,
+    referenced 2019-02-21.
+
+[3] Documentation/devicetree/bindings/leds/common.txt
+
+[4] Documentation/devicetree/bindings/media/video-interfaces.txt
+
+[5] Device Properties UUID For _DSD.
+    <URL:http://www.uefi.org/sites/default/files/resources/_DSD-device-properties-UUID.pdf>,
+    referenced 2019-02-21.
+
+[6] Hierarchical Data Extension UUID For _DSD.
+    <URL:http://www.uefi.org/sites/default/files/resources/_DSD-hierarchical-data-extension-UUID-v1.1.pdf>,
+    referenced 2019-02-21.
+
+[7] Documentation/acpi/dsd/data-node-reference.txt

Documentation/acpi/i2c-muxes.txt

@@ -1,58 +0,0 @@
-ACPI I2C Muxes
---------------
-
-Describing an I2C device hierarchy that includes I2C muxes requires an ACPI
-Device () scope per mux channel.
-
-Consider this topology:
-
-+------+   +------+
-| SMB1 |-->| MUX0 |--CH00--> i2c client A (0x50)
-|      |   | 0x70 |--CH01--> i2c client B (0x50)
-+------+   +------+
-
-which corresponds to the following ASL:
-
-Device (SMB1)
-{
-    Name (_HID, ...)
-    Device (MUX0)
-    {
-        Name (_HID, ...)
-        Name (_CRS, ResourceTemplate () {
-            I2cSerialBus (0x70, ControllerInitiated, I2C_SPEED,
-                          AddressingMode7Bit, "^SMB1", 0x00,
-                          ResourceConsumer,,)
-        }
-
-        Device (CH00)
-        {
-            Name (_ADR, 0)
-
-            Device (CLIA)
-            {
-                Name (_HID, ...)
-                Name (_CRS, ResourceTemplate () {
-                    I2cSerialBus (0x50, ControllerInitiated, I2C_SPEED,
-                                  AddressingMode7Bit, "^CH00", 0x00,
-                                  ResourceConsumer,,)
-                }
-            }
-        }
-
-        Device (CH01)
-        {
-            Name (_ADR, 1)
-
-            Device (CLIB)
-            {
-                Name (_HID, ...)
-                Name (_CRS, ResourceTemplate () {
-                    I2cSerialBus (0x50, ControllerInitiated, I2C_SPEED,
-                                  AddressingMode7Bit, "^CH01", 0x00,
-                                  ResourceConsumer,,)
-                }
-            }
-        }
-    }
-}

Documentation/acpi/initrd_table_override.txt

@@ -1,111 +0,0 @@
-Upgrading ACPI tables via initrd
-================================
-
-1) Introduction (What is this about)
-2) What is this for
-3) How does it work
-4) References (Where to retrieve userspace tools)
-
-1) What is this about
----------------------
-
-If the ACPI_TABLE_UPGRADE compile option is true, it is possible to
-upgrade the ACPI execution environment that is defined by the ACPI tables
-via upgrading the ACPI tables provided by the BIOS with an instrumented,
-modified, more recent version one, or installing brand new ACPI tables.
-
-When building initrd with kernel in a single image, option
-ACPI_TABLE_OVERRIDE_VIA_BUILTIN_INITRD should also be true for this
-feature to work.
-
-For a full list of ACPI tables that can be upgraded/installed, take a look
-at the char *table_sigs[MAX_ACPI_SIGNATURE]; definition in
-drivers/acpi/tables.c.
-All ACPI tables iasl (Intel's ACPI compiler and disassembler) knows should
-be overridable, except:
-   - ACPI_SIG_RSDP (has a signature of 6 bytes)
-   - ACPI_SIG_FACS (does not have an ordinary ACPI table header)
-Both could get implemented as well.
-
-
-2) What is this for
--------------------
-
-Complain to your platform/BIOS vendor if you find a bug which is so severe
-that a workaround is not accepted in the Linux kernel. And this facility
-allows you to upgrade the buggy tables before your platform/BIOS vendor
-releases an upgraded BIOS binary.
-
-This facility can be used by platform/BIOS vendors to provide a Linux
-compatible environment without modifying the underlying platform firmware.
-
-This facility also provides a powerful feature to easily debug and test
-ACPI BIOS table compatibility with the Linux kernel by modifying old
-platform provided ACPI tables or inserting new ACPI tables.
-
-It can and should be enabled in any kernel because there is no functional
-change with not instrumented initrds.
-
-
-3) How does it work
--------------------
-
-# Extract the machine's ACPI tables:
-cd /tmp
-acpidump >acpidump
-acpixtract -a acpidump
-# Disassemble, modify and recompile them:
-iasl -d *.dat
-# For example add this statement into a _PRT (PCI Routing Table) function
-# of the DSDT:
-Store("HELLO WORLD", debug)
-# And increase the OEM Revision. For example, before modification:
-DefinitionBlock ("DSDT.aml", "DSDT", 2, "INTEL ", "TEMPLATE", 0x00000000)
-# After modification:
-DefinitionBlock ("DSDT.aml", "DSDT", 2, "INTEL ", "TEMPLATE", 0x00000001)
-iasl -sa dsdt.dsl
-# Add the raw ACPI tables to an uncompressed cpio archive.
-# They must be put into a /kernel/firmware/acpi directory inside the cpio
-# archive. Note that if the table put here matches a platform table
-# (similar Table Signature, and similar OEMID, and similar OEM Table ID)
-# with a more recent OEM Revision, the platform table will be upgraded by
-# this table. If the table put here doesn't match a platform table
-# (dissimilar Table Signature, or dissimilar OEMID, or dissimilar OEM Table
-# ID), this table will be appended.
-mkdir -p kernel/firmware/acpi
-cp dsdt.aml kernel/firmware/acpi
-# A maximum of "NR_ACPI_INITRD_TABLES (64)" tables are currently allowed
-# (see osl.c):
-iasl -sa facp.dsl
-iasl -sa ssdt1.dsl
-cp facp.aml kernel/firmware/acpi
-cp ssdt1.aml kernel/firmware/acpi
-# The uncompressed cpio archive must be the first. Other, typically
-# compressed cpio archives, must be concatenated on top of the uncompressed
-# one. Following command creates the uncompressed cpio archive and
-# concatenates the original initrd on top:
-find kernel | cpio -H newc --create > /boot/instrumented_initrd
-cat /boot/initrd >>/boot/instrumented_initrd
-# reboot with increased acpi debug level, e.g. boot params:
-acpi.debug_level=0x2 acpi.debug_layer=0xFFFFFFFF
-# and check your syslog:
-[    1.268089] ACPI: PCI Interrupt Routing Table [\_SB_.PCI0._PRT]
-[    1.272091] [ACPI Debug]  String [0x0B] "HELLO WORLD"
-
-iasl is able to disassemble and recompile quite a lot different,
-also static ACPI tables.
-
-
-4) Where to retrieve userspace tools
-------------------------------------
-
-iasl and acpixtract are part of Intel's ACPICA project:
-http://acpica.org/
-and should be packaged by distributions (for example in the acpica package
-on SUSE).
-
-acpidump can be found in Len Browns pmtools:
-ftp://kernel.org/pub/linux/kernel/people/lenb/acpi/utils/pmtools/acpidump
-This tool is also part of the acpica package on SUSE.
-Alternatively, used ACPI tables can be retrieved via sysfs in latest kernels:
-/sys/firmware/acpi/tables

Documentation/acpi/method-customizing.txt

@@ -1,73 +0,0 @@
-Linux ACPI Custom Control Method How To
-=======================================
-
-Written by Zhang Rui <rui.zhang@intel.com>
-
-
-Linux supports customizing ACPI control methods at runtime.
-
-Users can use this to
-1. override an existing method which may not work correctly,
-   or just for debugging purposes.
-2. insert a completely new method in order to create a missing
-   method such as _OFF, _ON, _STA, _INI, etc.
-For these cases, it is far simpler to dynamically install a single
-control method rather than override the entire DSDT, because kernel
-rebuild/reboot is not needed and test result can be got in minutes.
-
-Note: Only ACPI METHOD can be overridden, any other object types like
-      "Device", "OperationRegion", are not recognized. Methods
-      declared inside scope operators are also not supported.
-Note: The same ACPI control method can be overridden for many times,
-      and it's always the latest one that used by Linux/kernel.
-Note: To get the ACPI debug object output (Store (AAAA, Debug)),
-      please run "echo 1 > /sys/module/acpi/parameters/aml_debug_output".
-
-1. override an existing method
-   a) get the ACPI table via ACPI sysfs I/F. e.g. to get the DSDT,
-      just run "cat /sys/firmware/acpi/tables/DSDT > /tmp/dsdt.dat"
-   b) disassemble the table by running "iasl -d dsdt.dat".
-   c) rewrite the ASL code of the method and save it in a new file,
-   d) package the new file (psr.asl) to an ACPI table format.
-      Here is an example of a customized \_SB._AC._PSR method,
-
-      DefinitionBlock ("", "SSDT", 1, "", "", 0x20080715)
-      {
-	Method (\_SB_.AC._PSR, 0, NotSerialized)
-	{
-		Store ("In AC _PSR", Debug)
-		Return (ACON)
-	}
-      }
-      Note that the full pathname of the method in ACPI namespace
-      should be used.
-   e) assemble the file to generate the AML code of the method.
-      e.g. "iasl -vw 6084 psr.asl" (psr.aml is generated as a result)
-      If parameter "-vw 6084" is not supported by your iASL compiler,
-      please try a newer version.
-   f) mount debugfs by "mount -t debugfs none /sys/kernel/debug"
-   g) override the old method via the debugfs by running
-      "cat /tmp/psr.aml > /sys/kernel/debug/acpi/custom_method"
-
-2. insert a new method
-   This is easier than overriding an existing method.
-   We just need to create the ASL code of the method we want to
-   insert and then follow the step c) ~ g) in section 1.
-
-3. undo your changes
-   The "undo" operation is not supported for a new inserted method
-   right now, i.e. we can not remove a method currently.
-   For an overridden method, in order to undo your changes, please
-   save a copy of the method original ASL code in step c) section 1,
-   and redo step c) ~ g) to override the method with the original one.
-
-
-Note: We can use a kernel with multiple custom ACPI method running,
-      But each individual write to debugfs can implement a SINGLE
-      method override. i.e. if we want to insert/override multiple
-      ACPI methods, we need to redo step c) ~ g) for multiple times.
-
-Note: Be aware that root can mis-use this driver to modify arbitrary
-      memory and gain additional rights, if root's privileges got
-      restricted (for example if root is not allowed to load additional
-      modules after boot).

Documentation/acpi/method-tracing.txt

@@ -1,192 +0,0 @@
-ACPICA Trace Facility
-
-Copyright (C) 2015, Intel Corporation
-Author: Lv Zheng <lv.zheng@intel.com>
-
-
-Abstract:
-
-This document describes the functions and the interfaces of the method
-tracing facility.
-
-1. Functionalities and usage examples:
-
-   ACPICA provides method tracing capability. And two functions are
-   currently implemented using this capability.
-
-   A. Log reducer
-   ACPICA subsystem provides debugging outputs when CONFIG_ACPI_DEBUG is
-   enabled. The debugging messages which are deployed via
-   ACPI_DEBUG_PRINT() macro can be reduced at 2 levels - per-component
-   level (known as debug layer, configured via
-   /sys/module/acpi/parameters/debug_layer) and per-type level (known as
-   debug level, configured via /sys/module/acpi/parameters/debug_level).
-
-   But when the particular layer/level is applied to the control method
-   evaluations, the quantity of the debugging outputs may still be too
-   large to be put into the kernel log buffer. The idea thus is worked out
-   to only enable the particular debug layer/level (normally more detailed)
-   logs when the control method evaluation is started, and disable the
-   detailed logging when the control method evaluation is stopped.
-
-   The following command examples illustrate the usage of the "log reducer"
-   functionality:
-   a. Filter out the debug layer/level matched logs when control methods
-      are being evaluated:
-      # cd /sys/module/acpi/parameters
-      # echo "0xXXXXXXXX" > trace_debug_layer
-      # echo "0xYYYYYYYY" > trace_debug_level
-      # echo "enable" > trace_state
-   b. Filter out the debug layer/level matched logs when the specified
-      control method is being evaluated:
-      # cd /sys/module/acpi/parameters
-      # echo "0xXXXXXXXX" > trace_debug_layer
-      # echo "0xYYYYYYYY" > trace_debug_level
-      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
-      # echo "method" > /sys/module/acpi/parameters/trace_state
-   c. Filter out the debug layer/level matched logs when the specified
-      control method is being evaluated for the first time:
-      # cd /sys/module/acpi/parameters
-      # echo "0xXXXXXXXX" > trace_debug_layer
-      # echo "0xYYYYYYYY" > trace_debug_level
-      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
-      # echo "method-once" > /sys/module/acpi/parameters/trace_state
-   Where:
-      0xXXXXXXXX/0xYYYYYYYY: Refer to Documentation/acpi/debug.txt for
-			     possible debug layer/level masking values.
-      \PPPP.AAAA.TTTT.HHHH: Full path of a control method that can be found
-			    in the ACPI namespace. It needn't be an entry
-			    of a control method evaluation.
-
-   B. AML tracer
-
-   There are special log entries added by the method tracing facility at
-   the "trace points" the AML interpreter starts/stops to execute a control
-   method, or an AML opcode. Note that the format of the log entries are
-   subject to change:
-     [    0.186427]   exdebug-0398 ex_trace_point        : Method Begin [0xf58394d8:\_SB.PCI0.LPCB.ECOK] execution.
-     [    0.186630]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905c88:If] execution.
-     [    0.186820]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905cc0:LEqual] execution.
-     [    0.187010]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905a20:-NamePath-] execution.
-     [    0.187214]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905a20:-NamePath-] execution.
-     [    0.187407]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905f60:One] execution.
-     [    0.187594]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905f60:One] execution.
-     [    0.187789]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905cc0:LEqual] execution.
-     [    0.187980]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905cc0:Return] execution.
-     [    0.188146]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905f60:One] execution.
-     [    0.188334]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905f60:One] execution.
-     [    0.188524]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905cc0:Return] execution.
-     [    0.188712]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905c88:If] execution.
-     [    0.188903]   exdebug-0398 ex_trace_point        : Method End [0xf58394d8:\_SB.PCI0.LPCB.ECOK] execution.
-
-   Developers can utilize these special log entries to track the AML
-   interpretion, thus can aid issue debugging and performance tuning. Note
-   that, as the "AML tracer" logs are implemented via ACPI_DEBUG_PRINT()
-   macro, CONFIG_ACPI_DEBUG is also required to be enabled for enabling
-   "AML tracer" logs.
-
-   The following command examples illustrate the usage of the "AML tracer"
-   functionality:
-   a. Filter out the method start/stop "AML tracer" logs when control
-      methods are being evaluated:
-      # cd /sys/module/acpi/parameters
-      # echo "0x80" > trace_debug_layer
-      # echo "0x10" > trace_debug_level
-      # echo "enable" > trace_state
-   b. Filter out the method start/stop "AML tracer" when the specified
-      control method is being evaluated:
-      # cd /sys/module/acpi/parameters
-      # echo "0x80" > trace_debug_layer
-      # echo "0x10" > trace_debug_level
-      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
-      # echo "method" > trace_state
-   c. Filter out the method start/stop "AML tracer" logs when the specified
-      control method is being evaluated for the first time:
-      # cd /sys/module/acpi/parameters
-      # echo "0x80" > trace_debug_layer
-      # echo "0x10" > trace_debug_level
-      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
-      # echo "method-once" > trace_state
-   d. Filter out the method/opcode start/stop "AML tracer" when the
-      specified control method is being evaluated:
-      # cd /sys/module/acpi/parameters
-      # echo "0x80" > trace_debug_layer
-      # echo "0x10" > trace_debug_level
-      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
-      # echo "opcode" > trace_state
-   e. Filter out the method/opcode start/stop "AML tracer" when the
-      specified control method is being evaluated for the first time:
-      # cd /sys/module/acpi/parameters
-      # echo "0x80" > trace_debug_layer
-      # echo "0x10" > trace_debug_level
-      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
-      # echo "opcode-opcode" > trace_state
-
-  Note that all above method tracing facility related module parameters can
-  be used as the boot parameters, for example:
-      acpi.trace_debug_layer=0x80 acpi.trace_debug_level=0x10 \
-      acpi.trace_method_name=\_SB.LID0._LID acpi.trace_state=opcode-once
-
-2. Interface descriptions:
-
-   All method tracing functions can be configured via ACPI module
-   parameters that are accessible at /sys/module/acpi/parameters/:
-
-   trace_method_name
-	The full path of the AML method that the user wants to trace.
-	Note that the full path shouldn't contain the trailing "_"s in its
-	name segments but may contain "\" to form an absolute path.
-
-   trace_debug_layer
-	The temporary debug_layer used when the tracing feature is enabled.
-	Using ACPI_EXECUTER (0x80) by default, which is the debug_layer
-	used to match all "AML tracer" logs.
-
-   trace_debug_level
-	The temporary debug_level used when the tracing feature is enabled.
-	Using ACPI_LV_TRACE_POINT (0x10) by default, which is the
-	debug_level used to match all "AML tracer" logs.
-
-   trace_state
-	The status of the tracing feature.
-	Users can enable/disable this debug tracing feature by executing
-	the following command:
-	    # echo string > /sys/module/acpi/parameters/trace_state
-	Where "string" should be one of the following:
-	"disable"
-	    Disable the method tracing feature.
-	"enable"
-	    Enable the method tracing feature.
-	    ACPICA debugging messages matching
-	    "trace_debug_layer/trace_debug_level" during any method
-	    execution will be logged.
-	"method"
-	    Enable the method tracing feature.
-	    ACPICA debugging messages matching
-	    "trace_debug_layer/trace_debug_level" during method execution
-	    of "trace_method_name" will be logged.
-	"method-once"
-	    Enable the method tracing feature.
-	    ACPICA debugging messages matching
-	    "trace_debug_layer/trace_debug_level" during method execution
-	    of "trace_method_name" will be logged only once.
-	"opcode"
-	    Enable the method tracing feature.
-	    ACPICA debugging messages matching
-	    "trace_debug_layer/trace_debug_level" during method/opcode
-	    execution of "trace_method_name" will be logged.
-	"opcode-once"
-	    Enable the method tracing feature.
-	    ACPICA debugging messages matching
-	    "trace_debug_layer/trace_debug_level" during method/opcode
-	    execution of "trace_method_name" will be logged only once.
-	Note that, the difference between the "enable" and other feature
-        enabling options are:
-	1. When "enable" is specified, since
-	   "trace_debug_layer/trace_debug_level" shall apply to all control
-	   method evaluations, after configuring "trace_state" to "enable",
-	   "trace_method_name" will be reset to NULL.
-	2. When "method/opcode" is specified, if
-	   "trace_method_name" is NULL when "trace_state" is configured to
-	   these options, the "trace_debug_layer/trace_debug_level" will
-	   apply to all control method evaluations.

Documentation/acpi/ssdt-overlays.txt

@@ -1,172 +0,0 @@
-
-In order to support ACPI open-ended hardware configurations (e.g. development
-boards) we need a way to augment the ACPI configuration provided by the firmware
-image. A common example is connecting sensors on I2C / SPI buses on development
-boards.
-
-Although this can be accomplished by creating a kernel platform driver or
-recompiling the firmware image with updated ACPI tables, neither is practical:
-the former proliferates board specific kernel code while the latter requires
-access to firmware tools which are often not publicly available.
-
-Because ACPI supports external references in AML code a more practical
-way to augment firmware ACPI configuration is by dynamically loading
-user defined SSDT tables that contain the board specific information.
-
-For example, to enumerate a Bosch BMA222E accelerometer on the I2C bus of the
-Minnowboard MAX development board exposed via the LSE connector [1], the
-following ASL code can be used:
-
-DefinitionBlock ("minnowmax.aml", "SSDT", 1, "Vendor", "Accel", 0x00000003)
-{
-    External (\_SB.I2C6, DeviceObj)
-
-    Scope (\_SB.I2C6)
-    {
-        Device (STAC)
-        {
-            Name (_ADR, Zero)
-            Name (_HID, "BMA222E")
-
-            Method (_CRS, 0, Serialized)
-            {
-                Name (RBUF, ResourceTemplate ()
-                {
-                    I2cSerialBus (0x0018, ControllerInitiated, 0x00061A80,
-                                  AddressingMode7Bit, "\\_SB.I2C6", 0x00,
-                                  ResourceConsumer, ,)
-                    GpioInt (Edge, ActiveHigh, Exclusive, PullDown, 0x0000,
-                             "\\_SB.GPO2", 0x00, ResourceConsumer, , )
-                    { // Pin list
-                        0
-                    }
-                })
-                Return (RBUF)
-            }
-        }
-    }
-}
-
-which can then be compiled to AML binary format:
-
-$ iasl minnowmax.asl
-
-Intel ACPI Component Architecture
-ASL Optimizing Compiler version 20140214-64 [Mar 29 2014]
-Copyright (c) 2000 - 2014 Intel Corporation
-
-ASL Input:     minnomax.asl - 30 lines, 614 bytes, 7 keywords
-AML Output:    minnowmax.aml - 165 bytes, 6 named objects, 1 executable opcodes
-
-[1] http://wiki.minnowboard.org/MinnowBoard_MAX#Low_Speed_Expansion_Connector_.28Top.29
-
-The resulting AML code can then be loaded by the kernel using one of the methods
-below.
-
-== Loading ACPI SSDTs from initrd ==
-
-This option allows loading of user defined SSDTs from initrd and it is useful
-when the system does not support EFI or when there is not enough EFI storage.
-
-It works in a similar way with initrd based ACPI tables override/upgrade: SSDT
-aml code must be placed in the first, uncompressed, initrd under the
-"kernel/firmware/acpi" path. Multiple files can be used and this will translate
-in loading multiple tables. Only SSDT and OEM tables are allowed. See
-initrd_table_override.txt for more details.
-
-Here is an example:
-
-# Add the raw ACPI tables to an uncompressed cpio archive.
-# They must be put into a /kernel/firmware/acpi directory inside the
-# cpio archive.
-# The uncompressed cpio archive must be the first.
-# Other, typically compressed cpio archives, must be
-# concatenated on top of the uncompressed one.
-mkdir -p kernel/firmware/acpi
-cp ssdt.aml kernel/firmware/acpi
-
-# Create the uncompressed cpio archive and concatenate the original initrd
-# on top:
-find kernel | cpio -H newc --create > /boot/instrumented_initrd
-cat /boot/initrd >>/boot/instrumented_initrd
-
-== Loading ACPI SSDTs from EFI variables ==
-
-This is the preferred method, when EFI is supported on the platform, because it
-allows a persistent, OS independent way of storing the user defined SSDTs. There
-is also work underway to implement EFI support for loading user defined SSDTs
-and using this method will make it easier to convert to the EFI loading
-mechanism when that will arrive.
-
-In order to load SSDTs from an EFI variable the efivar_ssdt kernel command line
-parameter can be used. The argument for the option is the variable name to
-use. If there are multiple variables with the same name but with different
-vendor GUIDs, all of them will be loaded.
-
-In order to store the AML code in an EFI variable the efivarfs filesystem can be
-used. It is enabled and mounted by default in /sys/firmware/efi/efivars in all
-recent distribution.
-
-Creating a new file in /sys/firmware/efi/efivars will automatically create a new
-EFI variable. Updating a file in /sys/firmware/efi/efivars will update the EFI
-variable. Please note that the file name needs to be specially formatted as
-"Name-GUID" and that the first 4 bytes in the file (little-endian format)
-represent the attributes of the EFI variable (see EFI_VARIABLE_MASK in
-include/linux/efi.h). Writing to the file must also be done with one write
-operation.
-
-For example, you can use the following bash script to create/update an EFI
-variable with the content from a given file:
-
-#!/bin/sh -e
-
-while ! [ -z "$1" ]; do
-        case "$1" in
-        "-f") filename="$2"; shift;;
-        "-g") guid="$2"; shift;;
-        *) name="$1";;
-        esac
-        shift
-done
-
-usage()
-{
-        echo "Syntax: ${0##*/} -f filename [ -g guid ] name"
-        exit 1
-}
-
-[ -n "$name" -a -f "$filename" ] || usage
-
-EFIVARFS="/sys/firmware/efi/efivars"
-
-[ -d "$EFIVARFS" ] || exit 2
-
-if stat -tf $EFIVARFS | grep -q -v de5e81e4; then
-        mount -t efivarfs none $EFIVARFS
-fi
-
-# try to pick up an existing GUID
-[ -n "$guid" ] || guid=$(find "$EFIVARFS" -name "$name-*" | head -n1 | cut -f2- -d-)
-
-# use a randomly generated GUID
-[ -n "$guid" ] || guid="$(cat /proc/sys/kernel/random/uuid)"
-
-# efivarfs expects all of the data in one write
-tmp=$(mktemp)
-/bin/echo -ne "\007\000\000\000" | cat - $filename > $tmp
-dd if=$tmp of="$EFIVARFS/$name-$guid" bs=$(stat -c %s $tmp)
-rm $tmp
-
-== Loading ACPI SSDTs from configfs ==
-
-This option allows loading of user defined SSDTs from userspace via the configfs
-interface. The CONFIG_ACPI_CONFIGFS option must be select and configfs must be
-mounted. In the following examples, we assume that configfs has been mounted in
-/config.
-
-New tables can be loading by creating new directories in /config/acpi/table/ and
-writing the SSDT aml code in the aml attribute:
-
-cd /config/acpi/table
-mkdir my_ssdt
-cat ~/ssdt.aml > my_ssdt/aml

Documentation/admin-guide/acpi/cppc_sysfs.rst

@@ -1,5 +1,11 @@
+.. SPDX-License-Identifier: GPL-2.0
 
-	Collaborative Processor Performance Control (CPPC)
+==================================================
+Collaborative Processor Performance Control (CPPC)
+==================================================
+
+CPPC
+====
 
 CPPC defined in the ACPI spec describes a mechanism for the OS to manage the
 performance of a logical processor on a contigious and abstract performance
@@ -10,31 +16,28 @@ For more details on CPPC please refer to the ACPI specification at:
 
 http://uefi.org/specifications
 
-Some of the CPPC registers are exposed via sysfs under:
+Some of the CPPC registers are exposed via sysfs under::
 
-/sys/devices/system/cpu/cpuX/acpi_cppc/
+  /sys/devices/system/cpu/cpuX/acpi_cppc/
 
-for each cpu X
+for each cpu X::
 
---------------------------------------------------------------------------------
+  $ ls -lR  /sys/devices/system/cpu/cpu0/acpi_cppc/
-
+  /sys/devices/system/cpu/cpu0/acpi_cppc/:
-$ ls -lR  /sys/devices/system/cpu/cpu0/acpi_cppc/
+  total 0
-/sys/devices/system/cpu/cpu0/acpi_cppc/:
+  -r--r--r-- 1 root root 65536 Mar  5 19:38 feedback_ctrs
-total 0
+  -r--r--r-- 1 root root 65536 Mar  5 19:38 highest_perf
--r--r--r-- 1 root root 65536 Mar  5 19:38 feedback_ctrs
+  -r--r--r-- 1 root root 65536 Mar  5 19:38 lowest_freq
--r--r--r-- 1 root root 65536 Mar  5 19:38 highest_perf
+  -r--r--r-- 1 root root 65536 Mar  5 19:38 lowest_nonlinear_perf
--r--r--r-- 1 root root 65536 Mar  5 19:38 lowest_freq
+  -r--r--r-- 1 root root 65536 Mar  5 19:38 lowest_perf
--r--r--r-- 1 root root 65536 Mar  5 19:38 lowest_nonlinear_perf
+  -r--r--r-- 1 root root 65536 Mar  5 19:38 nominal_freq
--r--r--r-- 1 root root 65536 Mar  5 19:38 lowest_perf
+  -r--r--r-- 1 root root 65536 Mar  5 19:38 nominal_perf
--r--r--r-- 1 root root 65536 Mar  5 19:38 nominal_freq
+  -r--r--r-- 1 root root 65536 Mar  5 19:38 reference_perf
--r--r--r-- 1 root root 65536 Mar  5 19:38 nominal_perf
+  -r--r--r-- 1 root root 65536 Mar  5 19:38 wraparound_time
--r--r--r-- 1 root root 65536 Mar  5 19:38 reference_perf
--r--r--r-- 1 root root 65536 Mar  5 19:38 wraparound_time
-
---------------------------------------------------------------------------------
 
 * highest_perf : Highest performance of this processor (abstract scale).
-* nominal_perf : Highest sustained performance of this processor (abstract scale).
+* nominal_perf : Highest sustained performance of this processor
+  (abstract scale).
 * lowest_nonlinear_perf : Lowest performance of this processor with nonlinear
   power savings (abstract scale).
 * lowest_perf : Lowest performance of this processor (abstract scale).
@@ -48,22 +51,26 @@ total 0
 * feedback_ctrs : Includes both Reference and delivered performance counter.
   Reference counter ticks up proportional to processor's reference performance.
   Delivered counter ticks up proportional to processor's delivered performance.
-* wraparound_time: Minimum time for the feedback counters to wraparound (seconds).
+* wraparound_time: Minimum time for the feedback counters to wraparound
+  (seconds).
 * reference_perf : Performance level at which reference performance counter
   accumulates (abstract scale).
 
---------------------------------------------------------------------------------
 
-		Computing Average Delivered Performance
+Computing Average Delivered Performance
+=======================================
 
-Below describes the steps to compute the average performance delivered by taking
+Below describes the steps to compute the average performance delivered by
-two different snapshots of feedback counters at time T1 and T2.
+taking two different snapshots of feedback counters at time T1 and T2.
 
-T1: Read feedback_ctrs as fbc_t1
+  T1: Read feedback_ctrs as fbc_t1
-    Wait or run some workload
+      Wait or run some workload
-T2: Read feedback_ctrs as fbc_t2
 
-delivered_counter_delta = fbc_t2[del] - fbc_t1[del]
+  T2: Read feedback_ctrs as fbc_t2
-reference_counter_delta = fbc_t2[ref] - fbc_t1[ref]
 
-delivered_perf = (refernce_perf x delivered_counter_delta) / reference_counter_delta
+::
+
+  delivered_counter_delta = fbc_t2[del] - fbc_t1[del]
+  reference_counter_delta = fbc_t2[ref] - fbc_t1[ref]
+
+  delivered_perf = (refernce_perf x delivered_counter_delta) / reference_counter_delta

Documentation/admin-guide/acpi/dsdt-override.rst

@@ -1,6 +1,12 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===============
+Overriding DSDT
+===============
+
 Linux supports a method of overriding the BIOS DSDT:
 
-CONFIG_ACPI_CUSTOM_DSDT builds the image into the kernel.
+CONFIG_ACPI_CUSTOM_DSDT - builds the image into the kernel.
 
 When to use this method is described in detail on the
 Linux/ACPI home page:

Documentation/admin-guide/acpi/index.rst

@@ -0,0 +1,14 @@
+============
+ACPI Support
+============
+
+Here we document in detail how to interact with various mechanisms in
+the Linux ACPI support.
+
+.. toctree::
+   :maxdepth: 1
+
+   initrd_table_override
+   dsdt-override
+   ssdt-overlays
+   cppc_sysfs

Documentation/admin-guide/acpi/initrd_table_override.rst

@@ -0,0 +1,115 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+================================
+Upgrading ACPI tables via initrd
+================================
+
+What is this about
+==================
+
+If the ACPI_TABLE_UPGRADE compile option is true, it is possible to
+upgrade the ACPI execution environment that is defined by the ACPI tables
+via upgrading the ACPI tables provided by the BIOS with an instrumented,
+modified, more recent version one, or installing brand new ACPI tables.
+
+When building initrd with kernel in a single image, option
+ACPI_TABLE_OVERRIDE_VIA_BUILTIN_INITRD should also be true for this
+feature to work.
+
+For a full list of ACPI tables that can be upgraded/installed, take a look
+at the char `*table_sigs[MAX_ACPI_SIGNATURE];` definition in
+drivers/acpi/tables.c.
+
+All ACPI tables iasl (Intel's ACPI compiler and disassembler) knows should
+be overridable, except:
+
+  - ACPI_SIG_RSDP (has a signature of 6 bytes)
+  - ACPI_SIG_FACS (does not have an ordinary ACPI table header)
+
+Both could get implemented as well.
+
+
+What is this for
+================
+
+Complain to your platform/BIOS vendor if you find a bug which is so severe
+that a workaround is not accepted in the Linux kernel. And this facility
+allows you to upgrade the buggy tables before your platform/BIOS vendor
+releases an upgraded BIOS binary.
+
+This facility can be used by platform/BIOS vendors to provide a Linux
+compatible environment without modifying the underlying platform firmware.
+
+This facility also provides a powerful feature to easily debug and test
+ACPI BIOS table compatibility with the Linux kernel by modifying old
+platform provided ACPI tables or inserting new ACPI tables.
+
+It can and should be enabled in any kernel because there is no functional
+change with not instrumented initrds.
+
+
+How does it work
+================
+::
+
+  # Extract the machine's ACPI tables:
+  cd /tmp
+  acpidump >acpidump
+  acpixtract -a acpidump
+  # Disassemble, modify and recompile them:
+  iasl -d *.dat
+  # For example add this statement into a _PRT (PCI Routing Table) function
+  # of the DSDT:
+  Store("HELLO WORLD", debug)
+  # And increase the OEM Revision. For example, before modification:
+  DefinitionBlock ("DSDT.aml", "DSDT", 2, "INTEL ", "TEMPLATE", 0x00000000)
+  # After modification:
+  DefinitionBlock ("DSDT.aml", "DSDT", 2, "INTEL ", "TEMPLATE", 0x00000001)
+  iasl -sa dsdt.dsl
+  # Add the raw ACPI tables to an uncompressed cpio archive.
+  # They must be put into a /kernel/firmware/acpi directory inside the cpio
+  # archive. Note that if the table put here matches a platform table
+  # (similar Table Signature, and similar OEMID, and similar OEM Table ID)
+  # with a more recent OEM Revision, the platform table will be upgraded by
+  # this table. If the table put here doesn't match a platform table
+  # (dissimilar Table Signature, or dissimilar OEMID, or dissimilar OEM Table
+  # ID), this table will be appended.
+  mkdir -p kernel/firmware/acpi
+  cp dsdt.aml kernel/firmware/acpi
+  # A maximum of "NR_ACPI_INITRD_TABLES (64)" tables are currently allowed
+  # (see osl.c):
+  iasl -sa facp.dsl
+  iasl -sa ssdt1.dsl
+  cp facp.aml kernel/firmware/acpi
+  cp ssdt1.aml kernel/firmware/acpi
+  # The uncompressed cpio archive must be the first. Other, typically
+  # compressed cpio archives, must be concatenated on top of the uncompressed
+  # one. Following command creates the uncompressed cpio archive and
+  # concatenates the original initrd on top:
+  find kernel | cpio -H newc --create > /boot/instrumented_initrd
+  cat /boot/initrd >>/boot/instrumented_initrd
+  # reboot with increased acpi debug level, e.g. boot params:
+  acpi.debug_level=0x2 acpi.debug_layer=0xFFFFFFFF
+  # and check your syslog:
+  [    1.268089] ACPI: PCI Interrupt Routing Table [\_SB_.PCI0._PRT]
+  [    1.272091] [ACPI Debug]  String [0x0B] "HELLO WORLD"
+
+iasl is able to disassemble and recompile quite a lot different,
+also static ACPI tables.
+
+
+Where to retrieve userspace tools
+=================================
+
+iasl and acpixtract are part of Intel's ACPICA project:
+http://acpica.org/
+
+and should be packaged by distributions (for example in the acpica package
+on SUSE).
+
+acpidump can be found in Len Browns pmtools:
+ftp://kernel.org/pub/linux/kernel/people/lenb/acpi/utils/pmtools/acpidump
+
+This tool is also part of the acpica package on SUSE.
+Alternatively, used ACPI tables can be retrieved via sysfs in latest kernels:
+/sys/firmware/acpi/tables

Documentation/admin-guide/acpi/ssdt-overlays.rst

@@ -0,0 +1,180 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=============
+SSDT Overlays
+=============
+
+In order to support ACPI open-ended hardware configurations (e.g. development
+boards) we need a way to augment the ACPI configuration provided by the firmware
+image. A common example is connecting sensors on I2C / SPI buses on development
+boards.
+
+Although this can be accomplished by creating a kernel platform driver or
+recompiling the firmware image with updated ACPI tables, neither is practical:
+the former proliferates board specific kernel code while the latter requires
+access to firmware tools which are often not publicly available.
+
+Because ACPI supports external references in AML code a more practical
+way to augment firmware ACPI configuration is by dynamically loading
+user defined SSDT tables that contain the board specific information.
+
+For example, to enumerate a Bosch BMA222E accelerometer on the I2C bus of the
+Minnowboard MAX development board exposed via the LSE connector [1], the
+following ASL code can be used::
+
+    DefinitionBlock ("minnowmax.aml", "SSDT", 1, "Vendor", "Accel", 0x00000003)
+    {
+        External (\_SB.I2C6, DeviceObj)
+
+        Scope (\_SB.I2C6)
+        {
+            Device (STAC)
+            {
+                Name (_ADR, Zero)
+                Name (_HID, "BMA222E")
+
+                Method (_CRS, 0, Serialized)
+                {
+                    Name (RBUF, ResourceTemplate ()
+                    {
+                        I2cSerialBus (0x0018, ControllerInitiated, 0x00061A80,
+                                    AddressingMode7Bit, "\\_SB.I2C6", 0x00,
+                                    ResourceConsumer, ,)
+                        GpioInt (Edge, ActiveHigh, Exclusive, PullDown, 0x0000,
+                                "\\_SB.GPO2", 0x00, ResourceConsumer, , )
+                        { // Pin list
+                            0
+                        }
+                    })
+                    Return (RBUF)
+                }
+            }
+        }
+    }
+
+which can then be compiled to AML binary format::
+
+    $ iasl minnowmax.asl
+
+    Intel ACPI Component Architecture
+    ASL Optimizing Compiler version 20140214-64 [Mar 29 2014]
+    Copyright (c) 2000 - 2014 Intel Corporation
+
+    ASL Input:     minnomax.asl - 30 lines, 614 bytes, 7 keywords
+    AML Output:    minnowmax.aml - 165 bytes, 6 named objects, 1 executable opcodes
+
+[1] http://wiki.minnowboard.org/MinnowBoard_MAX#Low_Speed_Expansion_Connector_.28Top.29
+
+The resulting AML code can then be loaded by the kernel using one of the methods
+below.
+
+Loading ACPI SSDTs from initrd
+==============================
+
+This option allows loading of user defined SSDTs from initrd and it is useful
+when the system does not support EFI or when there is not enough EFI storage.
+
+It works in a similar way with initrd based ACPI tables override/upgrade: SSDT
+aml code must be placed in the first, uncompressed, initrd under the
+"kernel/firmware/acpi" path. Multiple files can be used and this will translate
+in loading multiple tables. Only SSDT and OEM tables are allowed. See
+initrd_table_override.txt for more details.
+
+Here is an example::
+
+    # Add the raw ACPI tables to an uncompressed cpio archive.
+    # They must be put into a /kernel/firmware/acpi directory inside the
+    # cpio archive.
+    # The uncompressed cpio archive must be the first.
+    # Other, typically compressed cpio archives, must be
+    # concatenated on top of the uncompressed one.
+    mkdir -p kernel/firmware/acpi
+    cp ssdt.aml kernel/firmware/acpi
+
+    # Create the uncompressed cpio archive and concatenate the original initrd
+    # on top:
+    find kernel | cpio -H newc --create > /boot/instrumented_initrd
+    cat /boot/initrd >>/boot/instrumented_initrd
+
+Loading ACPI SSDTs from EFI variables
+=====================================
+
+This is the preferred method, when EFI is supported on the platform, because it
+allows a persistent, OS independent way of storing the user defined SSDTs. There
+is also work underway to implement EFI support for loading user defined SSDTs
+and using this method will make it easier to convert to the EFI loading
+mechanism when that will arrive.
+
+In order to load SSDTs from an EFI variable the efivar_ssdt kernel command line
+parameter can be used. The argument for the option is the variable name to
+use. If there are multiple variables with the same name but with different
+vendor GUIDs, all of them will be loaded.
+
+In order to store the AML code in an EFI variable the efivarfs filesystem can be
+used. It is enabled and mounted by default in /sys/firmware/efi/efivars in all
+recent distribution.
+
+Creating a new file in /sys/firmware/efi/efivars will automatically create a new
+EFI variable. Updating a file in /sys/firmware/efi/efivars will update the EFI
+variable. Please note that the file name needs to be specially formatted as
+"Name-GUID" and that the first 4 bytes in the file (little-endian format)
+represent the attributes of the EFI variable (see EFI_VARIABLE_MASK in
+include/linux/efi.h). Writing to the file must also be done with one write
+operation.
+
+For example, you can use the following bash script to create/update an EFI
+variable with the content from a given file::
+
+    #!/bin/sh -e
+
+    while ! [ -z "$1" ]; do
+            case "$1" in
+            "-f") filename="$2"; shift;;
+            "-g") guid="$2"; shift;;
+            *) name="$1";;
+            esac
+            shift
+    done
+
+    usage()
+    {
+            echo "Syntax: ${0##*/} -f filename [ -g guid ] name"
+            exit 1
+    }
+
+    [ -n "$name" -a -f "$filename" ] || usage
+
+    EFIVARFS="/sys/firmware/efi/efivars"
+
+    [ -d "$EFIVARFS" ] || exit 2
+
+    if stat -tf $EFIVARFS | grep -q -v de5e81e4; then
+            mount -t efivarfs none $EFIVARFS
+    fi
+
+    # try to pick up an existing GUID
+    [ -n "$guid" ] || guid=$(find "$EFIVARFS" -name "$name-*" | head -n1 | cut -f2- -d-)
+
+    # use a randomly generated GUID
+    [ -n "$guid" ] || guid="$(cat /proc/sys/kernel/random/uuid)"
+
+    # efivarfs expects all of the data in one write
+    tmp=$(mktemp)
+    /bin/echo -ne "\007\000\000\000" | cat - $filename > $tmp
+    dd if=$tmp of="$EFIVARFS/$name-$guid" bs=$(stat -c %s $tmp)
+    rm $tmp
+
+Loading ACPI SSDTs from configfs
+================================
+
+This option allows loading of user defined SSDTs from userspace via the configfs
+interface. The CONFIG_ACPI_CONFIGFS option must be select and configfs must be
+mounted. In the following examples, we assume that configfs has been mounted in
+/config.
+
+New tables can be loading by creating new directories in /config/acpi/table/ and
+writing the SSDT aml code in the aml attribute::
+
+    cd /config/acpi/table
+    mkdir my_ssdt
+    cat ~/ssdt.aml > my_ssdt/aml

Documentation/admin-guide/cgroup-v2.rst

@@ -864,6 +864,8 @@ All cgroup core files are prefixed with "cgroup."
 	  populated
 		1 if the cgroup or its descendants contains any live
 		processes; otherwise, 0.
+	  frozen
+		1 if the cgroup is frozen; otherwise, 0.
 
   cgroup.max.descendants
 	A read-write single value files.  The default is "max".
@@ -897,6 +899,31 @@ All cgroup core files are prefixed with "cgroup."
 		A dying cgroup can consume system resources not exceeding
 		limits, which were active at the moment of cgroup deletion.
 
+  cgroup.freeze
+	A read-write single value file which exists on non-root cgroups.
+	Allowed values are "0" and "1". The default is "0".
+
+	Writing "1" to the file causes freezing of the cgroup and all
+	descendant cgroups. This means that all belonging processes will
+	be stopped and will not run until the cgroup will be explicitly
+	unfrozen. Freezing of the cgroup may take some time; when this action
+	is completed, the "frozen" value in the cgroup.events control file
+	will be updated to "1" and the corresponding notification will be
+	issued.
+
+	A cgroup can be frozen either by its own settings, or by settings
+	of any ancestor cgroups. If any of ancestor cgroups is frozen, the
+	cgroup will remain frozen.
+
+	Processes in the frozen cgroup can be killed by a fatal signal.
+	They also can enter and leave a frozen cgroup: either by an explicit
+	move by a user, or if freezing of the cgroup races with fork().
+	If a process is moved to a frozen cgroup, it stops. If a process is
+	moved out of a frozen cgroup, it becomes running.
+
+	Frozen status of a cgroup doesn't affect any cgroup tree operations:
+	it's possible to delete a frozen (and empty) cgroup, as well as
+	create new sub-cgroups.
 
 Controllers
 ===========

Documentation/admin-guide/ext4.rst

@@ -91,10 +91,48 @@ Currently Available
 * large block (up to pagesize) support
 * efficient new ordered mode in JBD2 and ext4 (avoid using buffer head to force
   the ordering)
+* Case-insensitive file name lookups
 
 [1] Filesystems with a block size of 1k may see a limit imposed by the
 directory hash tree having a maximum depth of two.
 
+case-insensitive file name lookups
+======================================================
+
+The case-insensitive file name lookup feature is supported on a
+per-directory basis, allowing the user to mix case-insensitive and
+case-sensitive directories in the same filesystem.  It is enabled by
+flipping the +F inode attribute of an empty directory.  The
+case-insensitive string match operation is only defined when we know how
+text in encoded in a byte sequence.  For that reason, in order to enable
+case-insensitive directories, the filesystem must have the
+casefold feature, which stores the filesystem-wide encoding
+model used.  By default, the charset adopted is the latest version of
+Unicode (12.1.0, by the time of this writing), encoded in the UTF-8
+form.  The comparison algorithm is implemented by normalizing the
+strings to the Canonical decomposition form, as defined by Unicode,
+followed by a byte per byte comparison.
+
+The case-awareness is name-preserving on the disk, meaning that the file
+name provided by userspace is a byte-per-byte match to what is actually
+written in the disk.  The Unicode normalization format used by the
+kernel is thus an internal representation, and not exposed to the
+userspace nor to the disk, with the important exception of disk hashes,
+used on large case-insensitive directories with DX feature.  On DX
+directories, the hash must be calculated using the casefolded version of
+the filename, meaning that the normalization format used actually has an
+impact on where the directory entry is stored.
+
+When we change from viewing filenames as opaque byte sequences to seeing
+them as encoded strings we need to address what happens when a program
+tries to create a file with an invalid name.  The Unicode subsystem
+within the kernel leaves the decision of what to do in this case to the
+filesystem, which select its preferred behavior by enabling/disabling
+the strict mode.  When Ext4 encounters one of those strings and the
+filesystem did not require strict mode, it falls back to considering the
+entire string as an opaque byte sequence, which still allows the user to
+operate on that file, but the case-insensitive lookups won't work.
+
 Options
 =======
 

Documentation/admin-guide/hw-vuln/index.rst

@@ -0,0 +1,13 @@
+========================
+Hardware vulnerabilities
+========================
+
+This section describes CPU vulnerabilities and provides an overview of the
+possible mitigations along with guidance for selecting mitigations if they
+are configurable at compile, boot or run time.
+
+.. toctree::
+   :maxdepth: 1
+
+   l1tf
+   mds

Documentation/admin-guide/hw-vuln/l1tf.rst

@@ -445,6 +445,7 @@ The default is 'cond'. If 'l1tf=full,force' is given on the kernel command
 line, then 'always' is enforced and the kvm-intel.vmentry_l1d_flush
 module parameter is ignored and writes to the sysfs file are rejected.
 
+.. _mitigation_selection:
 
 Mitigation selection guide
 --------------------------

Documentation/admin-guide/hw-vuln/mds.rst

@@ -0,0 +1,308 @@
+MDS - Microarchitectural Data Sampling
+======================================
+
+Microarchitectural Data Sampling is a hardware vulnerability which allows
+unprivileged speculative access to data which is available in various CPU
+internal buffers.
+
+Affected processors
+-------------------
+
+This vulnerability affects a wide range of Intel processors. The
+vulnerability is not present on:
+
+   - Processors from AMD, Centaur and other non Intel vendors
+
+   - Older processor models, where the CPU family is < 6
+
+   - Some Atoms (Bonnell, Saltwell, Goldmont, GoldmontPlus)
+
+   - Intel processors which have the ARCH_CAP_MDS_NO bit set in the
+     IA32_ARCH_CAPABILITIES MSR.
+
+Whether a processor is affected or not can be read out from the MDS
+vulnerability file in sysfs. See :ref:`mds_sys_info`.
+
+Not all processors are affected by all variants of MDS, but the mitigation
+is identical for all of them so the kernel treats them as a single
+vulnerability.
+
+Related CVEs
+------------
+
+The following CVE entries are related to the MDS vulnerability:
+
+   ==============  =====  ===================================================
+   CVE-2018-12126  MSBDS  Microarchitectural Store Buffer Data Sampling
+   CVE-2018-12130  MFBDS  Microarchitectural Fill Buffer Data Sampling
+   CVE-2018-12127  MLPDS  Microarchitectural Load Port Data Sampling
+   CVE-2019-11091  MDSUM  Microarchitectural Data Sampling Uncacheable Memory
+   ==============  =====  ===================================================
+
+Problem
+-------
+
+When performing store, load, L1 refill operations, processors write data
+into temporary microarchitectural structures (buffers). The data in the
+buffer can be forwarded to load operations as an optimization.
+
+Under certain conditions, usually a fault/assist caused by a load
+operation, data unrelated to the load memory address can be speculatively
+forwarded from the buffers. Because the load operation causes a fault or
+assist and its result will be discarded, the forwarded data will not cause
+incorrect program execution or state changes. But a malicious operation
+may be able to forward this speculative data to a disclosure gadget which
+allows in turn to infer the value via a cache side channel attack.
+
+Because the buffers are potentially shared between Hyper-Threads cross
+Hyper-Thread attacks are possible.
+
+Deeper technical information is available in the MDS specific x86
+architecture section: :ref:`Documentation/x86/mds.rst <mds>`.
+
+
+Attack scenarios
+----------------
+
+Attacks against the MDS vulnerabilities can be mounted from malicious non
+priviledged user space applications running on hosts or guest. Malicious
+guest OSes can obviously mount attacks as well.
+
+Contrary to other speculation based vulnerabilities the MDS vulnerability
+does not allow the attacker to control the memory target address. As a
+consequence the attacks are purely sampling based, but as demonstrated with
+the TLBleed attack samples can be postprocessed successfully.
+
+Web-Browsers
+^^^^^^^^^^^^
+
+  It's unclear whether attacks through Web-Browsers are possible at
+  all. The exploitation through Java-Script is considered very unlikely,
+  but other widely used web technologies like Webassembly could possibly be
+  abused.
+
+
+.. _mds_sys_info:
+
+MDS system information
+-----------------------
+
+The Linux kernel provides a sysfs interface to enumerate the current MDS
+status of the system: whether the system is vulnerable, and which
+mitigations are active. The relevant sysfs file is:
+
+/sys/devices/system/cpu/vulnerabilities/mds
+
+The possible values in this file are:
+
+  .. list-table::
+
+     * - 'Not affected'
+       - The processor is not vulnerable
+     * - 'Vulnerable'
+       - The processor is vulnerable, but no mitigation enabled
+     * - 'Vulnerable: Clear CPU buffers attempted, no microcode'
+       - The processor is vulnerable but microcode is not updated.
+
+         The mitigation is enabled on a best effort basis. See :ref:`vmwerv`
+     * - 'Mitigation: Clear CPU buffers'
+       - The processor is vulnerable and the CPU buffer clearing mitigation is
+         enabled.
+
+If the processor is vulnerable then the following information is appended
+to the above information:
+
+    ========================  ============================================
+    'SMT vulnerable'          SMT is enabled
+    'SMT mitigated'           SMT is enabled and mitigated
+    'SMT disabled'            SMT is disabled
+    'SMT Host state unknown'  Kernel runs in a VM, Host SMT state unknown
+    ========================  ============================================
+
+.. _vmwerv:
+
+Best effort mitigation mode
+^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+  If the processor is vulnerable, but the availability of the microcode based
+  mitigation mechanism is not advertised via CPUID the kernel selects a best
+  effort mitigation mode.  This mode invokes the mitigation instructions
+  without a guarantee that they clear the CPU buffers.
+
+  This is done to address virtualization scenarios where the host has the
+  microcode update applied, but the hypervisor is not yet updated to expose
+  the CPUID to the guest. If the host has updated microcode the protection
+  takes effect otherwise a few cpu cycles are wasted pointlessly.
+
+  The state in the mds sysfs file reflects this situation accordingly.
+
+
+Mitigation mechanism
+-------------------------
+
+The kernel detects the affected CPUs and the presence of the microcode
+which is required.
+
+If a CPU is affected and the microcode is available, then the kernel
+enables the mitigation by default. The mitigation can be controlled at boot
+time via a kernel command line option. See
+:ref:`mds_mitigation_control_command_line`.
+
+.. _cpu_buffer_clear:
+
+CPU buffer clearing
+^^^^^^^^^^^^^^^^^^^
+
+  The mitigation for MDS clears the affected CPU buffers on return to user
+  space and when entering a guest.
+
+  If SMT is enabled it also clears the buffers on idle entry when the CPU
+  is only affected by MSBDS and not any other MDS variant, because the
+  other variants cannot be protected against cross Hyper-Thread attacks.
+
+  For CPUs which are only affected by MSBDS the user space, guest and idle
+  transition mitigations are sufficient and SMT is not affected.
+
+.. _virt_mechanism:
+
+Virtualization mitigation
+^^^^^^^^^^^^^^^^^^^^^^^^^
+
+  The protection for host to guest transition depends on the L1TF
+  vulnerability of the CPU:
+
+  - CPU is affected by L1TF:
+
+    If the L1D flush mitigation is enabled and up to date microcode is
+    available, the L1D flush mitigation is automatically protecting the
+    guest transition.
+
+    If the L1D flush mitigation is disabled then the MDS mitigation is
+    invoked explicit when the host MDS mitigation is enabled.
+
+    For details on L1TF and virtualization see:
+    :ref:`Documentation/admin-guide/hw-vuln//l1tf.rst <mitigation_control_kvm>`.
+
+  - CPU is not affected by L1TF:
+
+    CPU buffers are flushed before entering the guest when the host MDS
+    mitigation is enabled.
+
+  The resulting MDS protection matrix for the host to guest transition:
+
+  ============ ===== ============= ============ =================
+   L1TF         MDS   VMX-L1FLUSH   Host MDS     MDS-State
+
+   Don't care   No    Don't care    N/A          Not affected
+
+   Yes          Yes   Disabled      Off          Vulnerable
+
+   Yes          Yes   Disabled      Full         Mitigated
+
+   Yes          Yes   Enabled       Don't care   Mitigated
+
+   No           Yes   N/A           Off          Vulnerable
+
+   No           Yes   N/A           Full         Mitigated
+  ============ ===== ============= ============ =================
+
+  This only covers the host to guest transition, i.e. prevents leakage from
+  host to guest, but does not protect the guest internally. Guests need to
+  have their own protections.
+
+.. _xeon_phi:
+
+XEON PHI specific considerations
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+  The XEON PHI processor family is affected by MSBDS which can be exploited
+  cross Hyper-Threads when entering idle states. Some XEON PHI variants allow
+  to use MWAIT in user space (Ring 3) which opens an potential attack vector
+  for malicious user space. The exposure can be disabled on the kernel
+  command line with the 'ring3mwait=disable' command line option.
+
+  XEON PHI is not affected by the other MDS variants and MSBDS is mitigated
+  before the CPU enters a idle state. As XEON PHI is not affected by L1TF
+  either disabling SMT is not required for full protection.
+
+.. _mds_smt_control:
+
+SMT control
+^^^^^^^^^^^
+
+  All MDS variants except MSBDS can be attacked cross Hyper-Threads. That
+  means on CPUs which are affected by MFBDS or MLPDS it is necessary to
+  disable SMT for full protection. These are most of the affected CPUs; the
+  exception is XEON PHI, see :ref:`xeon_phi`.
+
+  Disabling SMT can have a significant performance impact, but the impact
+  depends on the type of workloads.
+
+  See the relevant chapter in the L1TF mitigation documentation for details:
+  :ref:`Documentation/admin-guide/hw-vuln/l1tf.rst <smt_control>`.
+
+
+.. _mds_mitigation_control_command_line:
+
+Mitigation control on the kernel command line
+---------------------------------------------
+
+The kernel command line allows to control the MDS mitigations at boot
+time with the option "mds=". The valid arguments for this option are:
+
+  ============  =============================================================
+  full		If the CPU is vulnerable, enable all available mitigations
+		for the MDS vulnerability, CPU buffer clearing on exit to
+		userspace and when entering a VM. Idle transitions are
+		protected as well if SMT is enabled.
+
+		It does not automatically disable SMT.
+
+  full,nosmt	The same as mds=full, with SMT disabled on vulnerable
+		CPUs.  This is the complete mitigation.
+
+  off		Disables MDS mitigations completely.
+
+  ============  =============================================================
+
+Not specifying this option is equivalent to "mds=full".
+
+
+Mitigation selection guide
+--------------------------
+
+1. Trusted userspace
+^^^^^^^^^^^^^^^^^^^^
+
+   If all userspace applications are from a trusted source and do not
+   execute untrusted code which is supplied externally, then the mitigation
+   can be disabled.
+
+
+2. Virtualization with trusted guests
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+   The same considerations as above versus trusted user space apply.
+
+3. Virtualization with untrusted guests
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+   The protection depends on the state of the L1TF mitigations.
+   See :ref:`virt_mechanism`.
+
+   If the MDS mitigation is enabled and SMT is disabled, guest to host and
+   guest to guest attacks are prevented.
+
+.. _mds_default_mitigations:
+
+Default mitigations
+-------------------
+
+  The kernel default mitigations for vulnerable processors are:
+
+  - Enable CPU buffer clearing
+
+  The kernel does not by default enforce the disabling of SMT, which leaves
+  SMT systems vulnerable when running untrusted code. The same rationale as
+  for L1TF applies.
+  See :ref:`Documentation/admin-guide/hw-vuln//l1tf.rst <default_mitigations>`.

Documentation/admin-guide/index.rst

@@ -17,14 +17,12 @@ etc.
    kernel-parameters
    devices
 
-This section describes CPU vulnerabilities and provides an overview of the
+This section describes CPU vulnerabilities and their mitigations.
-possible mitigations along with guidance for selecting mitigations if they
-are configurable at compile, boot or run time.
 
 .. toctree::
    :maxdepth: 1
 
-   l1tf
+   hw-vuln/index
 
 Here is a set of documents aimed at users who are trying to track down
 problems and bugs in particular.
@@ -77,6 +75,7 @@ configure specific aspects of kernel behavior to your liking.
    LSM/index
    mm/index
    perf-security
+   acpi/index
 
 .. only::  subproject and html
 

Documentation/admin-guide/kernel-parameters.rst

@@ -88,6 +88,7 @@ parameter is applicable::
 	APIC	APIC support is enabled.
 	APM	Advanced Power Management support is enabled.
 	ARM	ARM architecture is enabled.
+	ARM64	ARM64 architecture is enabled.
 	AX25	Appropriate AX.25 support is enabled.
 	CLK	Common clock infrastructure is enabled.
 	CMA	Contiguous Memory Area support is enabled.

Documentation/admin-guide/kernel-parameters.txt

@@ -704,8 +704,11 @@
 			upon panic. This parameter reserves the physical
 			memory region [offset, offset + size] for that kernel
 			image. If '@offset' is omitted, then a suitable offset
-			is selected automatically. Check
+			is selected automatically.
-			Documentation/kdump/kdump.txt for further details.
+			[KNL, x86_64] select a region under 4G first, and
+			fall back to reserve region above 4G when '@offset'
+			hasn't been specified.
+			See Documentation/kdump/kdump.txt for further details.
 
 	crashkernel=range1:size1[,range2:size2,...][@offset]
 			[KNL] Same as above, but depends on the memory
@@ -1585,7 +1588,7 @@
 			Format: { "off" | "enforce" | "fix" | "log" }
 			default: "enforce"
 
-	ima_appraise_tcb [IMA]
+	ima_appraise_tcb [IMA] Deprecated.  Use ima_policy= instead.
 			The builtin appraise policy appraises all files
 			owned by uid=0.
 
@@ -1612,8 +1615,7 @@
 			uid=0.
 
 			The "appraise_tcb" policy appraises the integrity of
-			all files owned by root. (This is the equivalent
+			all files owned by root.
-			of ima_appraise_tcb.)
 
 			The "secure_boot" policy appraises the integrity
 			of files (eg. kexec kernel image, kernel modules,
@@ -1828,6 +1830,9 @@
 	ip=		[IP_PNP]
 			See Documentation/filesystems/nfs/nfsroot.txt.
 
+	ipcmni_extend	[KNL] Extend the maximum number of unique System V
+			IPC identifiers from 32,768 to 16,777,216.
+
 	irqaffinity=	[SMP] Set the default irq affinity mask
 			The argument is a cpu list, as described above.
 
@@ -2141,7 +2146,7 @@
 
 			Default is 'flush'.
 
-			For details see: Documentation/admin-guide/l1tf.rst
+			For details see: Documentation/admin-guide/hw-vuln/l1tf.rst
 
 	l2cr=		[PPC]
 
@@ -2387,6 +2392,32 @@
 			Format: <first>,<last>
 			Specifies range of consoles to be captured by the MDA.
 
+	mds=		[X86,INTEL]
+			Control mitigation for the Micro-architectural Data
+			Sampling (MDS) vulnerability.
+
+			Certain CPUs are vulnerable to an exploit against CPU
+			internal buffers which can forward information to a
+			disclosure gadget under certain conditions.
+
+			In vulnerable processors, the speculatively
+			forwarded data can be used in a cache side channel
+			attack, to access data to which the attacker does
+			not have direct access.
+
+			This parameter controls the MDS mitigation. The
+			options are:
+
+			full       - Enable MDS mitigation on vulnerable CPUs
+			full,nosmt - Enable MDS mitigation and disable
+				     SMT on vulnerable CPUs
+			off        - Unconditionally disable MDS mitigation
+
+			Not specifying this option is equivalent to
+			mds=full.
+
+			For details see: Documentation/admin-guide/hw-vuln/mds.rst
+
 	mem=nn[KMG]	[KNL,BOOT] Force usage of a specific amount of memory
 			Amount of memory to be used when the kernel is not able
 			to see the whole system memory or for test.
@@ -2544,6 +2575,42 @@
 			in the "bleeding edge" mini2440 support kernel at
 			http://repo.or.cz/w/linux-2.6/mini2440.git
 
+	mitigations=
+			[X86,PPC,S390,ARM64] Control optional mitigations for
+			CPU vulnerabilities.  This is a set of curated,
+			arch-independent options, each of which is an
+			aggregation of existing arch-specific options.
+
+			off
+				Disable all optional CPU mitigations.  This
+				improves system performance, but it may also
+				expose users to several CPU vulnerabilities.
+				Equivalent to: nopti [X86,PPC]
+					       kpti=0 [ARM64]
+					       nospectre_v1 [PPC]
+					       nobp=0 [S390]
+					       nospectre_v2 [X86,PPC,S390,ARM64]
+					       spectre_v2_user=off [X86]
+					       spec_store_bypass_disable=off [X86,PPC]
+					       ssbd=force-off [ARM64]
+					       l1tf=off [X86]
+					       mds=off [X86]
+
+			auto (default)
+				Mitigate all CPU vulnerabilities, but leave SMT
+				enabled, even if it's vulnerable.  This is for
+				users who don't want to be surprised by SMT
+				getting disabled across kernel upgrades, or who
+				have other ways of avoiding SMT-based attacks.
+				Equivalent to: (default behavior)
+
+			auto,nosmt
+				Mitigate all CPU vulnerabilities, disabling SMT
+				if needed.  This is for users who always want to
+				be fully mitigated, even if it means losing SMT.
+				Equivalent to: l1tf=flush,nosmt [X86]
+					       mds=full,nosmt [X86]
+
 	mminit_loglevel=
 			[KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this
 			parameter allows control of the logging verbosity for
@@ -2839,11 +2906,11 @@
 			noexec=on: enable non-executable mappings (default)
 			noexec=off: disable non-executable mappings
 
-	nosmap		[X86]
+	nosmap		[X86,PPC]
 			Disable SMAP (Supervisor Mode Access Prevention)
 			even if it is supported by processor.
 
-	nosmep		[X86]
+	nosmep		[X86,PPC]
 			Disable SMEP (Supervisor Mode Execution Prevention)
 			even if it is supported by processor.
 
@@ -2873,10 +2940,10 @@
 			check bypass). With this option data leaks are possible
 			in the system.
 
-	nospectre_v2	[X86,PPC_FSL_BOOK3E] Disable all mitigations for the Spectre variant 2
+	nospectre_v2	[X86,PPC_FSL_BOOK3E,ARM64] Disable all mitigations for
-			(indirect branch prediction) vulnerability. System may
+			the Spectre variant 2 (indirect branch prediction)
-			allow data leaks with this option, which is equivalent
+			vulnerability. System may allow data leaks with this
-			to spectre_v2=off.
+			option.
 
 	nospec_store_bypass_disable
 			[HW] Disable all mitigations for the Speculative Store Bypass vulnerability
@@ -3110,6 +3177,16 @@
 			This will also cause panics on machine check exceptions.
 			Useful together with panic=30 to trigger a reboot.
 
+	page_alloc.shuffle=
+			[KNL] Boolean flag to control whether the page allocator
+			should randomize its free lists. The randomization may
+			be automatically enabled if the kernel detects it is
+			running on a platform with a direct-mapped memory-side
+			cache, and this parameter can be used to
+			override/disable that behavior. The state of the flag
+			can be read from sysfs at:
+			/sys/module/page_alloc/parameters/shuffle.
+
 	page_owner=	[KNL] Boot-time page_owner enabling option.
 			Storage of the information about who allocated
 			each page is disabled in default. With this switch,
@@ -3135,6 +3212,7 @@
 			bit 2: print timer info
 			bit 3: print locks info if CONFIG_LOCKDEP is on
 			bit 4: print ftrace buffer
+			bit 5: print all printk messages in buffer
 
 	panic_on_warn	panic() instead of WARN().  Useful to cause kdump
 			on a WARN().
@@ -3394,6 +3472,8 @@
 				bridges without forcing it upstream. Note:
 				this removes isolation between devices and
 				may put more devices in an IOMMU group.
+		force_floating	[S390] Force usage of floating interrupts.
+		nomio		[S390] Do not use MIO instructions.
 
 	pcie_aspm=	[PCIE] Forcibly enable or disable PCIe Active State Power
 			Management.
@@ -3623,7 +3703,9 @@
 				see CONFIG_RAS_CEC help text.
 
 	rcu_nocbs=	[KNL]
-			The argument is a cpu list, as described above.
+			The argument is a cpu list, as described above,
+			except that the string "all" can be used to
+			specify every CPU on the system.
 
 			In kernels built with CONFIG_RCU_NOCB_CPU=y, set
 			the specified list of CPUs to be no-callback CPUs.
@@ -3986,7 +4068,9 @@
 				[[,]s[mp]#### \
 				[[,]b[ios] | a[cpi] | k[bd] | t[riple] | e[fi] | p[ci]] \
 				[[,]f[orce]
-			Where reboot_mode is one of warm (soft) or cold (hard) or gpio,
+			Where reboot_mode is one of warm (soft) or cold (hard) or gpio
+					(prefix with 'panic_' to set mode for panic
+					reboot only),
 			      reboot_type is one of bios, acpi, kbd, triple, efi, or pci,
 			      reboot_force is either force or not specified,
 			      reboot_cpu is s[mp]#### with #### being the processor
@@ -4703,6 +4787,10 @@
 			[x86] unstable: mark the TSC clocksource as unstable, this
 			marks the TSC unconditionally unstable at bootup and
 			avoids any further wobbles once the TSC watchdog notices.
+			[x86] nowatchdog: disable clocksource watchdog. Used
+			in situations with strict latency requirements (where
+			interruptions from clocksource watchdog are not
+			acceptable).
 
 	turbografx.map[2|3]=	[HW,JOY]
 			TurboGraFX parallel port interface
@@ -5173,6 +5261,13 @@
 			with /sys/devices/system/xen_memory/xen_memory0/scrub_pages.
 			Default value controlled with CONFIG_XEN_SCRUB_PAGES_DEFAULT.
 
+	xen_timer_slop=	[X86-64,XEN]
+			Set the timer slop (in nanoseconds) for the virtual Xen
+			timers (default is 100000). This adjusts the minimum
+			delta of virtualized Xen timers, where lower values
+			improve timer resolution at the expense of processing
+			more timer interrupts.
+
 	xirc2ps_cs=	[NET,PCMCIA]
 			Format:
 			<irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]]

Documentation/admin-guide/mm/numaperf.rst

@@ -0,0 +1,169 @@
+.. _numaperf:
+
+=============
+NUMA Locality
+=============
+
+Some platforms may have multiple types of memory attached to a compute
+node. These disparate memory ranges may share some characteristics, such
+as CPU cache coherence, but may have different performance. For example,
+different media types and buses affect bandwidth and latency.
+
+A system supports such heterogeneous memory by grouping each memory type
+under different domains, or "nodes", based on locality and performance
+characteristics.  Some memory may share the same node as a CPU, and others
+are provided as memory only nodes. While memory only nodes do not provide
+CPUs, they may still be local to one or more compute nodes relative to
+other nodes. The following diagram shows one such example of two compute
+nodes with local memory and a memory only node for each of compute node:
+
+ +------------------+     +------------------+
+ | Compute Node 0   +-----+ Compute Node 1   |
+ | Local Node0 Mem  |     | Local Node1 Mem  |
+ +--------+---------+     +--------+---------+
+          |                        |
+ +--------+---------+     +--------+---------+
+ | Slower Node2 Mem |     | Slower Node3 Mem |
+ +------------------+     +--------+---------+
+
+A "memory initiator" is a node containing one or more devices such as
+CPUs or separate memory I/O devices that can initiate memory requests.
+A "memory target" is a node containing one or more physical address
+ranges accessible from one or more memory initiators.
+
+When multiple memory initiators exist, they may not all have the same
+performance when accessing a given memory target. Each initiator-target
+pair may be organized into different ranked access classes to represent
+this relationship. The highest performing initiator to a given target
+is considered to be one of that target's local initiators, and given
+the highest access class, 0. Any given target may have one or more
+local initiators, and any given initiator may have multiple local
+memory targets.
+
+To aid applications matching memory targets with their initiators, the
+kernel provides symlinks to each other. The following example lists the
+relationship for the access class "0" memory initiators and targets::
+
+	# symlinks -v /sys/devices/system/node/nodeX/access0/targets/
+	relative: /sys/devices/system/node/nodeX/access0/targets/nodeY -> ../../nodeY
+
+	# symlinks -v /sys/devices/system/node/nodeY/access0/initiators/
+	relative: /sys/devices/system/node/nodeY/access0/initiators/nodeX -> ../../nodeX
+
+A memory initiator may have multiple memory targets in the same access
+class. The target memory's initiators in a given class indicate the
+nodes' access characteristics share the same performance relative to other
+linked initiator nodes. Each target within an initiator's access class,
+though, do not necessarily perform the same as each other.
+
+================
+NUMA Performance
+================
+
+Applications may wish to consider which node they want their memory to
+be allocated from based on the node's performance characteristics. If
+the system provides these attributes, the kernel exports them under the
+node sysfs hierarchy by appending the attributes directory under the
+memory node's access class 0 initiators as follows::
+
+	/sys/devices/system/node/nodeY/access0/initiators/
+
+These attributes apply only when accessed from nodes that have the
+are linked under the this access's inititiators.
+
+The performance characteristics the kernel provides for the local initiators
+are exported are as follows::
+
+	# tree -P "read*|write*" /sys/devices/system/node/nodeY/access0/initiators/
+	/sys/devices/system/node/nodeY/access0/initiators/
+	|-- read_bandwidth
+	|-- read_latency
+	|-- write_bandwidth
+	`-- write_latency
+
+The bandwidth attributes are provided in MiB/second.
+
+The latency attributes are provided in nanoseconds.
+
+The values reported here correspond to the rated latency and bandwidth
+for the platform.
+
+==========
+NUMA Cache
+==========
+
+System memory may be constructed in a hierarchy of elements with various
+performance characteristics in order to provide large address space of
+slower performing memory cached by a smaller higher performing memory. The
+system physical addresses memory  initiators are aware of are provided
+by the last memory level in the hierarchy. The system meanwhile uses
+higher performing memory to transparently cache access to progressively
+slower levels.
+
+The term "far memory" is used to denote the last level memory in the
+hierarchy. Each increasing cache level provides higher performing
+initiator access, and the term "near memory" represents the fastest
+cache provided by the system.
+
+This numbering is different than CPU caches where the cache level (ex:
+L1, L2, L3) uses the CPU-side view where each increased level is lower
+performing. In contrast, the memory cache level is centric to the last
+level memory, so the higher numbered cache level corresponds to  memory
+nearer to the CPU, and further from far memory.
+
+The memory-side caches are not directly addressable by software. When
+software accesses a system address, the system will return it from the
+near memory cache if it is present. If it is not present, the system
+accesses the next level of memory until there is either a hit in that
+cache level, or it reaches far memory.
+
+An application does not need to know about caching attributes in order
+to use the system. Software may optionally query the memory cache
+attributes in order to maximize the performance out of such a setup.
+If the system provides a way for the kernel to discover this information,
+for example with ACPI HMAT (Heterogeneous Memory Attribute Table),
+the kernel will append these attributes to the NUMA node memory target.
+
+When the kernel first registers a memory cache with a node, the kernel
+will create the following directory::
+
+	/sys/devices/system/node/nodeX/memory_side_cache/
+
+If that directory is not present, the system either does not not provide
+a memory-side cache, or that information is not accessible to the kernel.
+
+The attributes for each level of cache is provided under its cache
+level index::
+
+	/sys/devices/system/node/nodeX/memory_side_cache/indexA/
+	/sys/devices/system/node/nodeX/memory_side_cache/indexB/
+	/sys/devices/system/node/nodeX/memory_side_cache/indexC/
+
+Each cache level's directory provides its attributes. For example, the
+following shows a single cache level and the attributes available for
+software to query::
+
+	# tree sys/devices/system/node/node0/memory_side_cache/
+	/sys/devices/system/node/node0/memory_side_cache/
+	|-- index1
+	|   |-- indexing
+	|   |-- line_size
+	|   |-- size
+	|   `-- write_policy
+
+The "indexing" will be 0 if it is a direct-mapped cache, and non-zero
+for any other indexed based, multi-way associativity.
+
+The "line_size" is the number of bytes accessed from the next cache
+level on a miss.
+
+The "size" is the number of bytes provided by this cache level.
+
+The "write_policy" will be 0 for write-back, and non-zero for
+write-through caching.
+
+========
+See Also
+========
+.. [1] https://www.uefi.org/sites/default/files/resources/ACPI_6_2.pdf
+       Section 5.2.27

Documentation/admin-guide/pm/cpufreq.rst

@@ -1,3 +1,6 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
 .. |struct cpufreq_policy| replace:: :c:type:`struct cpufreq_policy <cpufreq_policy>`
 .. |intel_pstate| replace:: :doc:`intel_pstate <intel_pstate>`
 
@@ -5,9 +8,10 @@
 CPU Performance Scaling
 =======================
 
-::
+:Copyright: |copy| 2017 Intel Corporation
+
+:Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
 
- Copyright (c) 2017 Intel Corp., Rafael J. Wysocki <rafael.j.wysocki@intel.com>
 
 The Concept of CPU Performance Scaling
 ======================================
@@ -396,8 +400,8 @@ RT or deadline scheduling classes, the governor will increase the frequency to
 the allowed maximum (that is, the ``scaling_max_freq`` policy limit).  In turn,
 if it is invoked by the CFS scheduling class, the governor will use the
 Per-Entity Load Tracking (PELT) metric for the root control group of the
-given CPU as the CPU utilization estimate (see the `Per-entity load tracking`_
+given CPU as the CPU utilization estimate (see the *Per-entity load tracking*
-LWN.net article for a description of the PELT mechanism).  Then, the new
+LWN.net article [1]_ for a description of the PELT mechanism).  Then, the new
 CPU frequency to apply is computed in accordance with the formula
 
 	f = 1.25 * ``f_0`` * ``util`` / ``max``
@@ -698,4 +702,8 @@ hardware feature (e.g. all Intel ones), even if the
 :c:macro:`CONFIG_X86_ACPI_CPUFREQ_CPB` configuration option is set.
 
 
-.. _Per-entity load tracking: https://lwn.net/Articles/531853/
+References
+==========
+
+.. [1] Jonathan Corbet, *Per-entity load tracking*,
+       https://lwn.net/Articles/531853/

Documentation/admin-guide/pm/cpuidle.rst

@@ -1,3 +1,6 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
 .. |struct cpuidle_state| replace:: :c:type:`struct cpuidle_state <cpuidle_state>`
 .. |cpufreq| replace:: :doc:`CPU Performance Scaling <cpufreq>`
 
@@ -5,9 +8,10 @@
 CPU Idle Time Management
 ========================
 
-::
+:Copyright: |copy| 2018 Intel Corporation
+
+:Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
 
- Copyright (c) 2018 Intel Corp., Rafael J. Wysocki <rafael.j.wysocki@intel.com>
 
 Concepts
 ========

Documentation/admin-guide/pm/index.rst

@@ -1,3 +1,5 @@
+.. SPDX-License-Identifier: GPL-2.0
+
 ================
 Power Management
 ================

Documentation/admin-guide/pm/intel_epb.rst

@@ -0,0 +1,41 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
+======================================
+Intel Performance and Energy Bias Hint
+======================================
+
+:Copyright: |copy| 2019 Intel Corporation
+
+:Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+
+
+.. kernel-doc:: arch/x86/kernel/cpu/intel_epb.c
+   :doc: overview
+
+Intel Performance and Energy Bias Attribute in ``sysfs``
+========================================================
+
+The Intel Performance and Energy Bias Hint (EPB) value for a given (logical) CPU
+can be checked or updated through a ``sysfs`` attribute (file) under
+:file:`/sys/devices/system/cpu/cpu<N>/power/`, where the CPU number ``<N>``
+is allocated at the system initialization time:
+
+``energy_perf_bias``
+	Shows the current EPB value for the CPU in a sliding scale 0 - 15, where
+	a value of 0 corresponds to a hint preference for highest performance
+	and a value of 15 corresponds to the maximum energy savings.
+
+	In order to update the EPB value for the CPU, this attribute can be
+	written to, either with a number in the 0 - 15 sliding scale above, or
+	with one of the strings: "performance", "balance-performance", "normal",
+	"balance-power", "power" that represent values reflected by their
+	meaning.
+
+	This attribute is present for all online CPUs supporting the EPB
+	feature.
+
+Note that while the EPB interface to the processor is defined at the logical CPU
+level, the physical register backing it may be shared by multiple CPUs (for
+example, SMT siblings or cores in one package).  For this reason, updating the
+EPB value for one CPU may cause the EPB values for other CPUs to change.

Documentation/admin-guide/pm/intel_pstate.rst

@@ -1,10 +1,13 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
 ===============================================
 ``intel_pstate`` CPU Performance Scaling Driver
 ===============================================
 
-::
+:Copyright: |copy| 2017 Intel Corporation
 
- Copyright (c) 2017 Intel Corp., Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+:Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
 
 
 General Information
@@ -20,11 +23,10 @@ you have not done that yet.]
 
 For the processors supported by ``intel_pstate``, the P-state concept is broader
 than just an operating frequency or an operating performance point (see the
-`LinuxCon Europe 2015 presentation by Kristen Accardi <LCEU2015_>`_ for more
+LinuxCon Europe 2015 presentation by Kristen Accardi [1]_ for more
 information about that).  For this reason, the representation of P-states used
 by ``intel_pstate`` internally follows the hardware specification (for details
-refer to `Intel® 64 and IA-32 Architectures Software Developer’s Manual
+refer to Intel Software Developer’s Manual [2]_).  However, the ``CPUFreq`` core
-Volume 3: System Programming Guide <SDM_>`_).  However, the ``CPUFreq`` core
 uses frequencies for identifying operating performance points of CPUs and
 frequencies are involved in the user space interface exposed by it, so
 ``intel_pstate`` maps its internal representation of P-states to frequencies too
@@ -561,9 +563,9 @@ or to pin every task potentially sensitive to them to a specific CPU.]
 
 On the majority of systems supported by ``intel_pstate``, the ACPI tables
 provided by the platform firmware contain ``_PSS`` objects returning information
-that can be used for CPU performance scaling (refer to the `ACPI specification`_
+that can be used for CPU performance scaling (refer to the ACPI specification
-for details on the ``_PSS`` objects and the format of the information returned
+[3]_ for details on the ``_PSS`` objects and the format of the information
-by them).
+returned by them).
 
 The information returned by the ACPI ``_PSS`` objects is used by the
 ``acpi-cpufreq`` scaling driver.  On systems supported by ``intel_pstate``
@@ -728,6 +730,14 @@ P-state is called, the ``ftrace`` filter can be set to to
            <idle>-0     [000] ..s.  2537.654843: intel_pstate_set_pstate <-intel_pstate_timer_func
 
 
-.. _LCEU2015: http://events.linuxfoundation.org/sites/events/files/slides/LinuxConEurope_2015.pdf
+References
-.. _SDM: http://www.intel.com/content/www/us/en/architecture-and-technology/64-ia-32-architectures-software-developer-system-programming-manual-325384.html
+==========
-.. _ACPI specification: http://www.uefi.org/sites/default/files/resources/ACPI_6_1.pdf
+
+.. [1] Kristen Accardi, *Balancing Power and Performance in the Linux Kernel*,
+       http://events.linuxfoundation.org/sites/events/files/slides/LinuxConEurope_2015.pdf
+
+.. [2] *Intel® 64 and IA-32 Architectures Software Developer’s Manual Volume 3: System Programming Guide*,
+       http://www.intel.com/content/www/us/en/architecture-and-technology/64-ia-32-architectures-software-developer-system-programming-manual-325384.html
+
+.. [3] *Advanced Configuration and Power Interface Specification*,
+       https://uefi.org/sites/default/files/resources/ACPI_6_3_final_Jan30.pdf

Documentation/admin-guide/pm/sleep-states.rst

@@ -1,10 +1,14 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
 ===================
 System Sleep States
 ===================
 
-::
+:Copyright: |copy| 2017 Intel Corporation
+
+:Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
 
- Copyright (c) 2017 Intel Corp., Rafael J. Wysocki <rafael.j.wysocki@intel.com>
 
 Sleep states are global low-power states of the entire system in which user
 space code cannot be executed and the overall system activity is significantly

Documentation/admin-guide/pm/strategies.rst

@@ -1,10 +1,14 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
 ===========================
 Power Management Strategies
 ===========================
 
-::
+:Copyright: |copy| 2017 Intel Corporation
+
+:Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
 
- Copyright (c) 2017 Intel Corp., Rafael J. Wysocki <rafael.j.wysocki@intel.com>
 
 The Linux kernel supports two major high-level power management strategies.
 

Documentation/admin-guide/pm/system-wide.rst

@@ -1,3 +1,5 @@
+.. SPDX-License-Identifier: GPL-2.0
+
 ============================
 System-Wide Power Management
 ============================

Documentation/admin-guide/pm/working-state.rst

@@ -1,3 +1,5 @@
+.. SPDX-License-Identifier: GPL-2.0
+
 ==============================
 Working-State Power Management
 ==============================
@@ -8,3 +10,4 @@ Working-State Power Management
    cpuidle
    cpufreq
    intel_pstate
+   intel_epb

Documentation/arm64/cpu-feature-registers.txt

@@ -209,6 +209,22 @@ infrastructure:
      | AT                           | [35-32] |    y    |
      x--------------------------------------------------x
 
+  6) ID_AA64ZFR0_EL1 - SVE feature ID register 0
+
+     x--------------------------------------------------x
+     | Name                         |  bits   | visible |
+     |--------------------------------------------------|
+     | SM4                          | [43-40] |    y    |
+     |--------------------------------------------------|
+     | SHA3                         | [35-32] |    y    |
+     |--------------------------------------------------|
+     | BitPerm                      | [19-16] |    y    |
+     |--------------------------------------------------|
+     | AES                          | [7-4]   |    y    |
+     |--------------------------------------------------|
+     | SVEVer                       | [3-0]   |    y    |
+     x--------------------------------------------------x
+
 Appendix I: Example
 ---------------------------
 

Documentation/arm64/elf_hwcaps.txt

@@ -13,9 +13,9 @@ architected discovery mechanism available to userspace code at EL0. The
 kernel exposes the presence of these features to userspace through a set
 of flags called hwcaps, exposed in the auxilliary vector.
 
-Userspace software can test for features by acquiring the AT_HWCAP entry
+Userspace software can test for features by acquiring the AT_HWCAP or
-of the auxilliary vector, and testing whether the relevant flags are
+AT_HWCAP2 entry of the auxiliary vector, and testing whether the relevant
-set, e.g.
+flags are set, e.g.
 
 bool floating_point_is_present(void)
 {
@@ -135,6 +135,10 @@ HWCAP_DCPOP
 
     Functionality implied by ID_AA64ISAR1_EL1.DPB == 0b0001.
 
+HWCAP2_DCPODP
+
+    Functionality implied by ID_AA64ISAR1_EL1.DPB == 0b0010.
+
 HWCAP_SHA3
 
     Functionality implied by ID_AA64ISAR0_EL1.SHA3 == 0b0001.
@@ -159,6 +163,30 @@ HWCAP_SVE
 
     Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001.
 
+HWCAP2_SVE2
+
+    Functionality implied by ID_AA64ZFR0_EL1.SVEVer == 0b0001.
+
+HWCAP2_SVEAES
+
+    Functionality implied by ID_AA64ZFR0_EL1.AES == 0b0001.
+
+HWCAP2_SVEPMULL
+
+    Functionality implied by ID_AA64ZFR0_EL1.AES == 0b0010.
+
+HWCAP2_SVEBITPERM
+
+    Functionality implied by ID_AA64ZFR0_EL1.BitPerm == 0b0001.
+
+HWCAP2_SVESHA3
+
+    Functionality implied by ID_AA64ZFR0_EL1.SHA3 == 0b0001.
+
+HWCAP2_SVESM4
+
+    Functionality implied by ID_AA64ZFR0_EL1.SM4 == 0b0001.
+
 HWCAP_ASIMDFHM
 
    Functionality implied by ID_AA64ISAR0_EL1.FHM == 0b0001.
@@ -194,3 +222,10 @@ HWCAP_PACG
     Functionality implied by ID_AA64ISAR1_EL1.GPA == 0b0001 or
     ID_AA64ISAR1_EL1.GPI == 0b0001, as described by
     Documentation/arm64/pointer-authentication.txt.
+
+
+4. Unused AT_HWCAP bits
+-----------------------
+
+For interoperation with userspace, the kernel guarantees that bits 62
+and 63 of AT_HWCAP will always be returned as 0.

Documentation/arm64/perf.txt

@@ -0,0 +1,85 @@
+Perf Event Attributes
+=====================
+
+Author: Andrew Murray <andrew.murray@arm.com>
+Date: 2019-03-06
+
+exclude_user
+------------
+
+This attribute excludes userspace.
+
+Userspace always runs at EL0 and thus this attribute will exclude EL0.
+
+
+exclude_kernel
+--------------
+
+This attribute excludes the kernel.
+
+The kernel runs at EL2 with VHE and EL1 without. Guest kernels always run
+at EL1.
+
+For the host this attribute will exclude EL1 and additionally EL2 on a VHE
+system.
+
+For the guest this attribute will exclude EL1. Please note that EL2 is
+never counted within a guest.
+
+
+exclude_hv
+----------
+
+This attribute excludes the hypervisor.
+
+For a VHE host this attribute is ignored as we consider the host kernel to
+be the hypervisor.
+
+For a non-VHE host this attribute will exclude EL2 as we consider the
+hypervisor to be any code that runs at EL2 which is predominantly used for
+guest/host transitions.
+
+For the guest this attribute has no effect. Please note that EL2 is
+never counted within a guest.
+
+
+exclude_host / exclude_guest
+----------------------------
+
+These attributes exclude the KVM host and guest, respectively.
+
+The KVM host may run at EL0 (userspace), EL1 (non-VHE kernel) and EL2 (VHE
+kernel or non-VHE hypervisor).
+
+The KVM guest may run at EL0 (userspace) and EL1 (kernel).
+
+Due to the overlapping exception levels between host and guests we cannot
+exclusively rely on the PMU's hardware exception filtering - therefore we
+must enable/disable counting on the entry and exit to the guest. This is
+performed differently on VHE and non-VHE systems.
+
+For non-VHE systems we exclude EL2 for exclude_host - upon entering and
+exiting the guest we disable/enable the event as appropriate based on the
+exclude_host and exclude_guest attributes.
+
+For VHE systems we exclude EL1 for exclude_guest and exclude both EL0,EL2
+for exclude_host. Upon entering and exiting the guest we modify the event
+to include/exclude EL0 as appropriate based on the exclude_host and
+exclude_guest attributes.
+
+The statements above also apply when these attributes are used within a
+non-VHE guest however please note that EL2 is never counted within a guest.
+
+
+Accuracy
+--------
+
+On non-VHE hosts we enable/disable counters on the entry/exit of host/guest
+transition at EL2 - however there is a period of time between
+enabling/disabling the counters and entering/exiting the guest. We are
+able to eliminate counters counting host events on the boundaries of guest
+entry/exit when counting guest events by filtering out EL2 for
+exclude_host. However when using !exclude_hv there is a small blackout
+window at the guest entry/exit where host events are not captured.
+
+On VHE systems there are no blackout windows.

Documentation/arm64/pointer-authentication.txt

@@ -87,7 +87,21 @@ used to get and set the keys for a thread.
 Virtualization
 --------------
 
-Pointer authentication is not currently supported in KVM guests. KVM
+Pointer authentication is enabled in KVM guest when each virtual cpu is
-will mask the feature bits from ID_AA64ISAR1_EL1, and attempted use of
+initialised by passing flags KVM_ARM_VCPU_PTRAUTH_[ADDRESS/GENERIC] and
-the feature will result in an UNDEFINED exception being injected into
+requesting these two separate cpu features to be enabled. The current KVM
-the guest.
+guest implementation works by enabling both features together, so both
+these userspace flags are checked before enabling pointer authentication.
+The separate userspace flag will allow to have no userspace ABI changes
+if support is added in the future to allow these two features to be
+enabled independently of one another.
+
+As Arm Architecture specifies that Pointer Authentication feature is
+implemented along with the VHE feature so KVM arm64 ptrauth code relies
+on VHE mode to be present.
+
+Additionally, when these vcpu feature flags are not set then KVM will
+filter out the Pointer Authentication system key registers from
+KVM_GET/SET_REG_* ioctls and mask those features from cpufeature ID
+register. Any attempt to use the Pointer Authentication instructions will
+result in an UNDEFINED exception being injected into the guest.

Documentation/arm64/silicon-errata.txt

@@ -61,6 +61,7 @@ stable kernels.
 | ARM            | Cortex-A76      | #1188873        | ARM64_ERRATUM_1188873       |
 | ARM            | Cortex-A76      | #1165522        | ARM64_ERRATUM_1165522       |
 | ARM            | Cortex-A76      | #1286807        | ARM64_ERRATUM_1286807       |
+| ARM            | Neoverse-N1     | #1188873        | ARM64_ERRATUM_1188873       |
 | ARM            | MMU-500         | #841119,#826419 | N/A                         |
 |                |                 |                 |                             |
 | Cavium         | ThunderX ITS    | #22375, #24313  | CAVIUM_ERRATUM_22375        |
@@ -77,6 +78,7 @@ stable kernels.
 | Hisilicon      | Hip0{5,6,7}     | #161010101      | HISILICON_ERRATUM_161010101 |
 | Hisilicon      | Hip0{6,7}       | #161010701      | N/A                         |
 | Hisilicon      | Hip07           | #161600802      | HISILICON_ERRATUM_161600802 |
+| Hisilicon      | Hip08 SMMU PMCG | #162001800      | N/A                         |
 |                |                 |                 |                             |
 | Qualcomm Tech. | Kryo/Falkor v1  | E1003           | QCOM_FALKOR_ERRATUM_1003    |
 | Qualcomm Tech. | Falkor v1       | E1009           | QCOM_FALKOR_ERRATUM_1009    |

Documentation/arm64/sve.txt

@@ -34,6 +34,23 @@ model features for SVE is included in Appendix A.
   following sections: software that needs to verify that those interfaces are
   present must check for HWCAP_SVE instead.
 
+* On hardware that supports the SVE2 extensions, HWCAP2_SVE2 will also
+  be reported in the AT_HWCAP2 aux vector entry.  In addition to this,
+  optional extensions to SVE2 may be reported by the presence of:
+
+	HWCAP2_SVE2
+	HWCAP2_SVEAES
+	HWCAP2_SVEPMULL
+	HWCAP2_SVEBITPERM
+	HWCAP2_SVESHA3
+	HWCAP2_SVESM4
+
+  This list may be extended over time as the SVE architecture evolves.
+
+  These extensions are also reported via the CPU ID register ID_AA64ZFR0_EL1,
+  which userspace can read using an MRS instruction.  See elf_hwcaps.txt and
+  cpu-feature-registers.txt for details.
+
 * Debuggers should restrict themselves to interacting with the target via the
   NT_ARM_SVE regset.  The recommended way of detecting support for this regset
   is to connect to a target process first and then attempt a

Documentation/atomic_bitops.txt

@@ -1,6 +1,6 @@
-
+=============
-On atomic bitops.
+Atomic bitops
-
+=============
 
 While our bitmap_{}() functions are non-atomic, we have a number of operations
 operating on single bits in a bitmap that are atomic.

Documentation/atomic_t.txt

@@ -56,6 +56,23 @@ Barriers:
   smp_mb__{before,after}_atomic()
 
 
+TYPES (signed vs unsigned)
+-----
+
+While atomic_t, atomic_long_t and atomic64_t use int, long and s64
+respectively (for hysterical raisins), the kernel uses -fno-strict-overflow
+(which implies -fwrapv) and defines signed overflow to behave like
+2s-complement.
+
+Therefore, an explicitly unsigned variant of the atomic ops is strictly
+unnecessary and we can simply cast, there is no UB.
+
+There was a bug in UBSAN prior to GCC-8 that would generate UB warnings for
+signed types.
+
+With this we also conform to the C/C++ _Atomic behaviour and things like
+P1236R1.
+
 
 SEMANTICS
 ---------

Documentation/block/bfq-iosched.txt

@@ -20,13 +20,26 @@ for that device, by setting low_latency to 0. See Section 3 for
 details on how to configure BFQ for the desired tradeoff between
 latency and throughput, or on how to maximize throughput.
 
-BFQ has a non-null overhead, which limits the maximum IOPS that a CPU
+As every I/O scheduler, BFQ adds some overhead to per-I/O-request
-can process for a device scheduled with BFQ. To give an idea of the
+processing. To give an idea of this overhead, the total,
-limits on slow or average CPUs, here are, first, the limits of BFQ for
+single-lock-protected, per-request processing time of BFQ---i.e., the
-three different CPUs, on, respectively, an average laptop, an old
+sum of the execution times of the request insertion, dispatch and
-desktop, and a cheap embedded system, in case full hierarchical
+completion hooks---is, e.g., 1.9 us on an Intel Core i7-2760QM@2.40GHz
-support is enabled (i.e., CONFIG_BFQ_GROUP_IOSCHED is set), but
+(dated CPU for notebooks; time measured with simple code
-CONFIG_DEBUG_BLK_CGROUP is not set (Section 4-2):
+instrumentation, and using the throughput-sync.sh script of the S
+suite [1], in performance-profiling mode). To put this result into
+context, the total, single-lock-protected, per-request execution time
+of the lightest I/O scheduler available in blk-mq, mq-deadline, is 0.7
+us (mq-deadline is ~800 LOC, against ~10500 LOC for BFQ).
+
+Scheduling overhead further limits the maximum IOPS that a CPU can
+process (already limited by the execution of the rest of the I/O
+stack). To give an idea of the limits with BFQ, on slow or average
+CPUs, here are, first, the limits of BFQ for three different CPUs, on,
+respectively, an average laptop, an old desktop, and a cheap embedded
+system, in case full hierarchical support is enabled (i.e.,
+CONFIG_BFQ_GROUP_IOSCHED is set), but CONFIG_DEBUG_BLK_CGROUP is not
+set (Section 4-2):
 - Intel i7-4850HQ: 400 KIOPS
 - AMD A8-3850: 250 KIOPS
 - ARM CortexTM-A53 Octa-core: 80 KIOPS
@@ -566,3 +579,5 @@ applications. Unset this tunable if you need/want to control weights.
     Slightly extended version:
     http://algogroup.unimore.it/people/paolo/disk_sched/bfq-v1-suite-
 							results.pdf
+
+[3] https://github.com/Algodev-github/S

Documentation/block/null_blk.txt

@@ -93,3 +93,7 @@ zoned=[0/1]: Default: 0
 
 zone_size=[MB]: Default: 256
   Per zone size when exposed as a zoned block device. Must be a power of two.
+
+zone_nr_conv=[nr_conv]: Default: 0
+  The number of conventional zones to create when block device is zoned.  If
+  zone_nr_conv >= nr_zones, it will be reduced to nr_zones - 1.

Documentation/bpf/bpf_design_QA.rst

@@ -85,8 +85,33 @@ Q: Can loops be supported in a safe way?
 A: It's not clear yet.
 
 BPF developers are trying to find a way to
-support bounded loops where the verifier can guarantee that
+support bounded loops.
-the program terminates in less than 4096 instructions.
+
+Q: What are the verifier limits?
+--------------------------------
+A: The only limit known to the user space is BPF_MAXINSNS (4096).
+It's the maximum number of instructions that the unprivileged bpf
+program can have. The verifier has various internal limits.
+Like the maximum number of instructions that can be explored during
+program analysis. Currently, that limit is set to 1 million.
+Which essentially means that the largest program can consist
+of 1 million NOP instructions. There is a limit to the maximum number
+of subsequent branches, a limit to the number of nested bpf-to-bpf
+calls, a limit to the number of the verifier states per instruction,
+a limit to the number of maps used by the program.
+All these limits can be hit with a sufficiently complex program.
+There are also non-numerical limits that can cause the program
+to be rejected. The verifier used to recognize only pointer + constant
+expressions. Now it can recognize pointer + bounded_register.
+bpf_lookup_map_elem(key) had a requirement that 'key' must be
+a pointer to the stack. Now, 'key' can be a pointer to map value.
+The verifier is steadily getting 'smarter'. The limits are
+being removed. The only way to know that the program is going to
+be accepted by the verifier is to try to load it.
+The bpf development process guarantees that the future kernel
+versions will accept all bpf programs that were accepted by
+the earlier versions.
+
 
 Instruction level questions
 ---------------------------

Documentation/bpf/btf.rst

@@ -82,6 +82,8 @@ sequentially and type id is assigned to each recognized type starting from id
     #define BTF_KIND_RESTRICT       11      /* Restrict     */
     #define BTF_KIND_FUNC           12      /* Function     */
     #define BTF_KIND_FUNC_PROTO     13      /* Function Proto       */
+    #define BTF_KIND_VAR            14      /* Variable     */
+    #define BTF_KIND_DATASEC        15      /* Section      */
 
 Note that the type section encodes debug info, not just pure types.
 ``BTF_KIND_FUNC`` is not a type, and it represents a defined subprogram.
@@ -393,6 +395,61 @@ refers to parameter type.
 If the function has variable arguments, the last parameter is encoded with
 ``name_off = 0`` and ``type = 0``.
 
+2.2.14 BTF_KIND_VAR
+~~~~~~~~~~~~~~~~~~~
+
+``struct btf_type`` encoding requirement:
+  * ``name_off``: offset to a valid C identifier
+  * ``info.kind_flag``: 0
+  * ``info.kind``: BTF_KIND_VAR
+  * ``info.vlen``: 0
+  * ``type``: the type of the variable
+
+``btf_type`` is followed by a single ``struct btf_variable`` with the
+following data::
+
+    struct btf_var {
+        __u32   linkage;
+    };
+
+``struct btf_var`` encoding:
+  * ``linkage``: currently only static variable 0, or globally allocated
+                 variable in ELF sections 1
+
+Not all type of global variables are supported by LLVM at this point.
+The following is currently available:
+
+  * static variables with or without section attributes
+  * global variables with section attributes
+
+The latter is for future extraction of map key/value type id's from a
+map definition.
+
+2.2.15 BTF_KIND_DATASEC
+~~~~~~~~~~~~~~~~~~~~~~~
+
+``struct btf_type`` encoding requirement:
+  * ``name_off``: offset to a valid name associated with a variable or
+                  one of .data/.bss/.rodata
+  * ``info.kind_flag``: 0
+  * ``info.kind``: BTF_KIND_DATASEC
+  * ``info.vlen``: # of variables
+  * ``size``: total section size in bytes (0 at compilation time, patched
+              to actual size by BPF loaders such as libbpf)
+
+``btf_type`` is followed by ``info.vlen`` number of ``struct btf_var_secinfo``.::
+
+    struct btf_var_secinfo {
+        __u32   type;
+        __u32   offset;
+        __u32   size;
+    };
+
+``struct btf_var_secinfo`` encoding:
+  * ``type``: the type of the BTF_KIND_VAR variable
+  * ``offset``: the in-section offset of the variable
+  * ``size``: the size of the variable in bytes
+
 3. BTF Kernel API
 *****************
 
@@ -521,6 +578,7 @@ For line_info, the line number and column number are defined as below:
     #define BPF_LINE_INFO_LINE_COL(line_col)        ((line_col) & 0x3ff)
 
 3.4 BPF_{PROG,MAP}_GET_NEXT_ID
+==============================
 
 In kernel, every loaded program, map or btf has a unique id. The id won't
 change during the lifetime of a program, map, or btf.
@@ -530,6 +588,7 @@ each command, to user space, for bpf program or maps, respectively, so an
 inspection tool can inspect all programs and maps.
 
 3.5 BPF_{PROG,MAP}_GET_FD_BY_ID
+===============================
 
 An introspection tool cannot use id to get details about program or maps.
 A file descriptor needs to be obtained first for reference-counting purpose.

Documentation/bpf/index.rst

@@ -36,6 +36,16 @@ Two sets of Questions and Answers (Q&A) are maintained.
    bpf_devel_QA
 
 
+Program types
+=============
+
+.. toctree::
+   :maxdepth: 1
+
+   prog_cgroup_sysctl
+   prog_flow_dissector
+
+
 .. Links:
 .. _Documentation/networking/filter.txt: ../networking/filter.txt
 .. _man-pages: https://www.kernel.org/doc/man-pages/

Documentation/bpf/prog_cgroup_sysctl.rst

@@ -0,0 +1,125 @@
+.. SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+===========================
+BPF_PROG_TYPE_CGROUP_SYSCTL
+===========================
+
+This document describes ``BPF_PROG_TYPE_CGROUP_SYSCTL`` program type that
+provides cgroup-bpf hook for sysctl.
+
+The hook has to be attached to a cgroup and will be called every time a
+process inside that cgroup tries to read from or write to sysctl knob in proc.
+
+1. Attach type
+**************
+
+``BPF_CGROUP_SYSCTL`` attach type has to be used to attach
+``BPF_PROG_TYPE_CGROUP_SYSCTL`` program to a cgroup.
+
+2. Context
+**********
+
+``BPF_PROG_TYPE_CGROUP_SYSCTL`` provides access to the following context from
+BPF program::
+
+    struct bpf_sysctl {
+        __u32 write;
+        __u32 file_pos;
+    };
+
+* ``write`` indicates whether sysctl value is being read (``0``) or written
+  (``1``). This field is read-only.
+
+* ``file_pos`` indicates file position sysctl is being accessed at, read
+  or written. This field is read-write. Writing to the field sets the starting
+  position in sysctl proc file ``read(2)`` will be reading from or ``write(2)``
+  will be writing to. Writing zero to the field can be used e.g. to override
+  whole sysctl value by ``bpf_sysctl_set_new_value()`` on ``write(2)`` even
+  when it's called by user space on ``file_pos > 0``. Writing non-zero
+  value to the field can be used to access part of sysctl value starting from
+  specified ``file_pos``. Not all sysctl support access with ``file_pos !=
+  0``, e.g. writes to numeric sysctl entries must always be at file position
+  ``0``. See also ``kernel.sysctl_writes_strict`` sysctl.
+
+See `linux/bpf.h`_ for more details on how context field can be accessed.
+
+3. Return code
+**************
+
+``BPF_PROG_TYPE_CGROUP_SYSCTL`` program must return one of the following
+return codes:
+
+* ``0`` means "reject access to sysctl";
+* ``1`` means "proceed with access".
+
+If program returns ``0`` user space will get ``-1`` from ``read(2)`` or
+``write(2)`` and ``errno`` will be set to ``EPERM``.
+
+4. Helpers
+**********
+
+Since sysctl knob is represented by a name and a value, sysctl specific BPF
+helpers focus on providing access to these properties:
+
+* ``bpf_sysctl_get_name()`` to get sysctl name as it is visible in
+  ``/proc/sys`` into provided by BPF program buffer;
+
+* ``bpf_sysctl_get_current_value()`` to get string value currently held by
+  sysctl into provided by BPF program buffer. This helper is available on both
+  ``read(2)`` from and ``write(2)`` to sysctl;
+
+* ``bpf_sysctl_get_new_value()`` to get new string value currently being
+  written to sysctl before actual write happens. This helper can be used only
+  on ``ctx->write == 1``;
+
+* ``bpf_sysctl_set_new_value()`` to override new string value currently being
+  written to sysctl before actual write happens. Sysctl value will be
+  overridden starting from the current ``ctx->file_pos``. If the whole value
+  has to be overridden BPF program can set ``file_pos`` to zero before calling
+  to the helper. This helper can be used only on ``ctx->write == 1``. New
+  string value set by the helper is treated and verified by kernel same way as
+  an equivalent string passed by user space.
+
+BPF program sees sysctl value same way as user space does in proc filesystem,
+i.e. as a string. Since many sysctl values represent an integer or a vector
+of integers, the following helpers can be used to get numeric value from the
+string:
+
+* ``bpf_strtol()`` to convert initial part of the string to long integer
+  similar to user space `strtol(3)`_;
+* ``bpf_strtoul()`` to convert initial part of the string to unsigned long
+  integer similar to user space `strtoul(3)`_;
+
+See `linux/bpf.h`_ for more details on helpers described here.
+
+5. Examples
+***********
+
+See `test_sysctl_prog.c`_ for an example of BPF program in C that access
+sysctl name and value, parses string value to get vector of integers and uses
+the result to make decision whether to allow or deny access to sysctl.
+
+6. Notes
+********
+
+``BPF_PROG_TYPE_CGROUP_SYSCTL`` is intended to be used in **trusted** root
+environment, for example to monitor sysctl usage or catch unreasonable values
+an application, running as root in a separate cgroup, is trying to set.
+
+Since `task_dfl_cgroup(current)` is called at `sys_read` / `sys_write` time it
+may return results different from that at `sys_open` time, i.e. process that
+opened sysctl file in proc filesystem may differ from process that is trying
+to read from / write to it and two such processes may run in different
+cgroups, what means ``BPF_PROG_TYPE_CGROUP_SYSCTL`` should not be used as a
+security mechanism to limit sysctl usage.
+
+As with any cgroup-bpf program additional care should be taken if an
+application running as root in a cgroup should not be allowed to
+detach/replace BPF program attached by administrator.
+
+.. Links
+.. _linux/bpf.h: ../../include/uapi/linux/bpf.h
+.. _strtol(3): http://man7.org/linux/man-pages/man3/strtol.3p.html
+.. _strtoul(3): http://man7.org/linux/man-pages/man3/strtoul.3p.html
+.. _test_sysctl_prog.c:
+   ../../tools/testing/selftests/bpf/progs/test_sysctl_prog.c

Documentation/bpf/prog_flow_dissector.rst

@@ -1,8 +1,8 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-==================
+============================
-BPF Flow Dissector
+BPF_PROG_TYPE_FLOW_DISSECTOR
-==================
+============================
 
 Overview
 ========

Documentation/clearing-warn-once.txt

@@ -1,5 +1,7 @@
+Clearing WARN_ONCE
+------------------
 
-WARN_ONCE / WARN_ON_ONCE only print a warning once.
+WARN_ONCE / WARN_ON_ONCE / printk_once only emit a message once.
 
 echo 1 > /sys/kernel/debug/clear_warn_once
 

Documentation/core-api/cachetlb.rst

@@ -101,16 +101,6 @@ changes occur:
 	translations for software managed TLB configurations.
 	The sparc64 port currently does this.
 
-6) ``void tlb_migrate_finish(struct mm_struct *mm)``
-
-	This interface is called at the end of an explicit
-	process migration. This interface provides a hook
-	to allow a platform to update TLB or context-specific
-	information for the address space.
-
-	The ia64 sn2 platform is one example of a platform
-	that uses this interface.
-
 Next, we have the cache flushing interfaces.  In general, when Linux
 is changing an existing virtual-->physical mapping to a new value,
 the sequence will be in one of the following forms::

Documentation/core-api/index.rst

@@ -22,7 +22,6 @@ Core utilities
    workqueue
    genericirq
    xarray
-   flexible-arrays
    librs
    genalloc
    errseq

Documentation/core-api/kernel-api.rst

@@ -147,10 +147,10 @@ Division Functions
 .. kernel-doc:: include/linux/math64.h
    :internal:
 
-.. kernel-doc:: lib/div64.c
+.. kernel-doc:: lib/math/div64.c
    :functions: div_s64_rem div64_u64_rem div64_u64 div64_s64
 
-.. kernel-doc:: lib/gcd.c
+.. kernel-doc:: lib/math/gcd.c
    :export:
 
 UUID/GUID

Documentation/core-api/printk-formats.rst

@@ -58,6 +58,14 @@ A raw pointer value may be printed with %p which will hash the address
 before printing. The kernel also supports extended specifiers for printing
 pointers of different types.
 
+Some of the extended specifiers print the data on the given address instead
+of printing the address itself. In this case, the following error messages
+might be printed instead of the unreachable information::
+
+	(null)	 data on plain NULL address
+	(efault) data on invalid address
+	(einval) invalid data on a valid address
+
 Plain Pointers
 --------------
 

Documentation/cputopology.txt

@@ -3,79 +3,79 @@ How CPU topology info is exported via sysfs
 ===========================================
 
 Export CPU topology info via sysfs. Items (attributes) are similar
-to /proc/cpuinfo output of some architectures:
+to /proc/cpuinfo output of some architectures.  They reside in
+/sys/devices/system/cpu/cpuX/topology/:
 
-1) /sys/devices/system/cpu/cpuX/topology/physical_package_id:
+physical_package_id:
 
 	physical package id of cpuX. Typically corresponds to a physical
 	socket number, but the actual value is architecture and platform
 	dependent.
 
-2) /sys/devices/system/cpu/cpuX/topology/core_id:
+core_id:
 
 	the CPU core ID of cpuX. Typically it is the hardware platform's
 	identifier (rather than the kernel's).  The actual value is
 	architecture and platform dependent.
 
-3) /sys/devices/system/cpu/cpuX/topology/book_id:
+book_id:
 
 	the book ID of cpuX. Typically it is the hardware platform's
 	identifier (rather than the kernel's).	The actual value is
 	architecture and platform dependent.
 
-4) /sys/devices/system/cpu/cpuX/topology/drawer_id:
+drawer_id:
 
 	the drawer ID of cpuX. Typically it is the hardware platform's
 	identifier (rather than the kernel's).	The actual value is
 	architecture and platform dependent.
 
-5) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
+thread_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
 	core as cpuX.
 
-6) /sys/devices/system/cpu/cpuX/topology/thread_siblings_list:
+thread_siblings_list:
 
 	human-readable list of cpuX's hardware threads within the same
 	core as cpuX.
 
-7) /sys/devices/system/cpu/cpuX/topology/core_siblings:
+core_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
 	physical_package_id.
 
-8) /sys/devices/system/cpu/cpuX/topology/core_siblings_list:
+core_siblings_list:
 
 	human-readable list of cpuX's hardware threads within the same
 	physical_package_id.
 
-9) /sys/devices/system/cpu/cpuX/topology/book_siblings:
+book_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
 	book_id.
 
-10) /sys/devices/system/cpu/cpuX/topology/book_siblings_list:
+book_siblings_list:
 
 	human-readable list of cpuX's hardware threads within the same
 	book_id.
 
-11) /sys/devices/system/cpu/cpuX/topology/drawer_siblings:
+drawer_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
 	drawer_id.
 
-12) /sys/devices/system/cpu/cpuX/topology/drawer_siblings_list:
+drawer_siblings_list:
 
 	human-readable list of cpuX's hardware threads within the same
 	drawer_id.
 
-To implement it in an architecture-neutral way, a new source file,
+Architecture-neutral, drivers/base/topology.c, exports these attributes.
-drivers/base/topology.c, is to export the 6 to 12 attributes. The book
+However, the book and drawer related sysfs files will only be created if
-and drawer related sysfs files will only be created if CONFIG_SCHED_BOOK
+CONFIG_SCHED_BOOK and CONFIG_SCHED_DRAWER are selected, respectively.
-and CONFIG_SCHED_DRAWER are selected.
 
-CONFIG_SCHED_BOOK and CONFIG_DRAWER are currently only used on s390, where
+CONFIG_SCHED_BOOK and CONFIG_SCHED_DRAWER are currently only used on s390,
-they reflect the cpu and cache hierarchy.
+where they reflect the cpu and cache hierarchy.
 
 For an architecture to support this feature, it must define some of
 these macros in include/asm-XXX/topology.h::
@@ -98,10 +98,10 @@ To be consistent on all architectures, include/linux/topology.h
 provides default definitions for any of the above macros that are
 not defined by include/asm-XXX/topology.h:
 
-1) physical_package_id: -1
+1) topology_physical_package_id: -1
-2) core_id: 0
+2) topology_core_id: 0
-3) sibling_cpumask: just the given CPU
+3) topology_sibling_cpumask: just the given CPU
-4) core_cpumask: just the given CPU
+4) topology_core_cpumask: just the given CPU
 
 For architectures that don't support books (CONFIG_SCHED_BOOK) there are no
 default definitions for topology_book_id() and topology_book_cpumask().

Documentation/crypto/api-samples.rst

@@ -133,7 +133,6 @@ Code Example For Use of Operational State Memory With SHASH
         if (!sdesc)
             return ERR_PTR(-ENOMEM);
         sdesc->shash.tfm = alg;
-        sdesc->shash.flags = 0x0;
         return sdesc;
     }
 

Documentation/dev-tools/gcov.rst

@@ -34,10 +34,6 @@ Configure the kernel with::
         CONFIG_DEBUG_FS=y
         CONFIG_GCOV_KERNEL=y
 
-select the gcc's gcov format, default is autodetect based on gcc version::
-
-        CONFIG_GCOV_FORMAT_AUTODETECT=y
-
 and to get coverage data for the entire kernel::
 
         CONFIG_GCOV_PROFILE_ALL=y
@@ -169,6 +165,20 @@ b) gcov is run on the BUILD machine
       [user@build] gcov -o /tmp/coverage/tmp/out/init main.c
 
 
+Note on compilers
+-----------------
+
+GCC and LLVM gcov tools are not necessarily compatible. Use gcov_ to work with
+GCC-generated .gcno and .gcda files, and use llvm-cov_ for Clang.
+
+.. _gcov: http://gcc.gnu.org/onlinedocs/gcc/Gcov.html
+.. _llvm-cov: https://llvm.org/docs/CommandGuide/llvm-cov.html
+
+Build differences between GCC and Clang gcov are handled by Kconfig. It
+automatically selects the appropriate gcov format depending on the detected
+toolchain.
+
+
 Troubleshooting
 ---------------
 

Documentation/dev-tools/kselftest.rst

@@ -7,6 +7,11 @@ directory. These are intended to be small tests to exercise individual code
 paths in the kernel. Tests are intended to be run after building, installing
 and booting a kernel.
 
+You can find additional information on Kselftest framework, how to
+write new tests using the framework on Kselftest wiki:
+
+https://kselftest.wiki.kernel.org/
+
 On some systems, hot-plug tests could hang forever waiting for cpu and
 memory to be ready to be offlined. A special hot-plug target is created
 to run the full range of hot-plug tests. In default mode, hot-plug tests run
@@ -14,6 +19,10 @@ in safe mode with a limited scope. In limited mode, cpu-hotplug test is
 run on a single cpu as opposed to all hotplug capable cpus, and memory
 hotplug test is run on 2% of hotplug capable memory instead of 10%.
 
+kselftest runs as a userspace process.  Tests that can be written/run in
+userspace may wish to use the `Test Harness`_.  Tests that need to be
+run in kernel space may wish to use a `Test Module`_.
+
 Running the selftests (hotplug tests are run in limited mode)
 =============================================================
 
@@ -31,17 +40,32 @@ To build and run the tests with a single command, use::
 
 Note that some tests will require root privileges.
 
-Build and run from user specific object directory (make O=dir)::
+Kselftest supports saving output files in a separate directory and then
+running tests. To locate output files in a separate directory two syntaxes
+are supported. In both cases the working directory must be the root of the
+kernel src. This is applicable to "Running a subset of selftests" section
+below.
+
+To build, save output files in a separate directory with O= ::
 
   $ make O=/tmp/kselftest kselftest
 
-Build and run KBUILD_OUTPUT directory (make KBUILD_OUTPUT=)::
+To build, save output files in a separate directory with KBUILD_OUTPUT ::
 
-  $ make KBUILD_OUTPUT=/tmp/kselftest kselftest
+  $ export KBUILD_OUTPUT=/tmp/kselftest; make kselftest
 
-The above commands run the tests and print pass/fail summary to make it
+The O= assignment takes precedence over the KBUILD_OUTPUT environment
-easier to understand the test results. Please find the detailed individual
+variable.
-test results for each test in /tmp/testname file(s).
+
+The above commands by default run the tests and print full pass/fail report.
+Kselftest supports "summary" option to make it easier to understand the test
+results. Please find the detailed individual test results for each test in
+/tmp/testname file(s) when summary option is specified. This is applicable
+to "Running a subset of selftests" section below.
+
+To run kselftest with summary option enabled ::
+
+  $ make summary=1 kselftest
 
 Running a subset of selftests
 =============================
@@ -57,17 +81,13 @@ You can specify multiple tests to build and run::
 
   $  make TARGETS="size timers" kselftest
 
-Build and run from user specific object directory (make O=dir)::
+To build, save output files in a separate directory with O= ::
 
   $ make O=/tmp/kselftest TARGETS="size timers" kselftest
 
-Build and run KBUILD_OUTPUT directory (make KBUILD_OUTPUT=)::
+To build, save output files in a separate directory with KBUILD_OUTPUT ::
 
-  $ make KBUILD_OUTPUT=/tmp/kselftest TARGETS="size timers" kselftest
+  $ export KBUILD_OUTPUT=/tmp/kselftest; make TARGETS="size timers" kselftest
-
-The above commands run the tests and print pass/fail summary to make it
-easier to understand the test results. Please find the detailed individual
-test results for each test in /tmp/testname file(s).
 
 See the top-level tools/testing/selftests/Makefile for the list of all
 possible targets.
@@ -161,11 +181,97 @@ Contributing new tests (details)
 
    e.g: tools/testing/selftests/android/config
 
+Test Module
+===========
+
+Kselftest tests the kernel from userspace.  Sometimes things need
+testing from within the kernel, one method of doing this is to create a
+test module.  We can tie the module into the kselftest framework by
+using a shell script test runner.  ``kselftest_module.sh`` is designed
+to facilitate this process.  There is also a header file provided to
+assist writing kernel modules that are for use with kselftest:
+
+- ``tools/testing/kselftest/kselftest_module.h``
+- ``tools/testing/kselftest/kselftest_module.sh``
+
+How to use
+----------
+
+Here we show the typical steps to create a test module and tie it into
+kselftest.  We use kselftests for lib/ as an example.
+
+1. Create the test module
+
+2. Create the test script that will run (load/unload) the module
+   e.g. ``tools/testing/selftests/lib/printf.sh``
+
+3. Add line to config file e.g. ``tools/testing/selftests/lib/config``
+
+4. Add test script to makefile  e.g. ``tools/testing/selftests/lib/Makefile``
+
+5. Verify it works:
+
+.. code-block:: sh
+
+   # Assumes you have booted a fresh build of this kernel tree
+   cd /path/to/linux/tree
+   make kselftest-merge
+   make modules
+   sudo make modules_install
+   make TARGETS=lib kselftest
+
+Example Module
+--------------
+
+A bare bones test module might look like this:
+
+.. code-block:: c
+
+   // SPDX-License-Identifier: GPL-2.0+
+
+   #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+   #include "../tools/testing/selftests/kselftest_module.h"
+
+   KSTM_MODULE_GLOBALS();
+
+   /*
+    * Kernel module for testing the foobinator
+    */
+
+   static int __init test_function()
+   {
+           ...
+   }
+
+   static void __init selftest(void)
+   {
+           KSTM_CHECK_ZERO(do_test_case("", 0));
+   }
+
+   KSTM_MODULE_LOADERS(test_foo);
+   MODULE_AUTHOR("John Developer <jd@fooman.org>");
+   MODULE_LICENSE("GPL");
+
+Example test script
+-------------------
+
+.. code-block:: sh
+
+    #!/bin/bash
+    # SPDX-License-Identifier: GPL-2.0+
+    $(dirname $0)/../kselftest_module.sh "foo" test_foo
+
+
 Test Harness
 ============
 
-The kselftest_harness.h file contains useful helpers to build tests.  The tests
+The kselftest_harness.h file contains useful helpers to build tests.  The
-from tools/testing/selftests/seccomp/seccomp_bpf.c can be used as example.
+test harness is for userspace testing, for kernel space testing see `Test
+Module`_ above.
+
+The tests from tools/testing/selftests/seccomp/seccomp_bpf.c can be used as
+example.
 
 Example
 -------

Documentation/device-mapper/dm-dust.txt

@@ -0,0 +1,272 @@
+dm-dust
+=======
+
+This target emulates the behavior of bad sectors at arbitrary
+locations, and the ability to enable the emulation of the failures
+at an arbitrary time.
+
+This target behaves similarly to a linear target.  At a given time,
+the user can send a message to the target to start failing read
+requests on specific blocks (to emulate the behavior of a hard disk
+drive with bad sectors).
+
+When the failure behavior is enabled (i.e.: when the output of
+"dmsetup status" displays "fail_read_on_bad_block"), reads of blocks
+in the "bad block list" will fail with EIO ("Input/output error").
+
+Writes of blocks in the "bad block list will result in the following:
+
+1. Remove the block from the "bad block list".
+2. Successfully complete the write.
+
+This emulates the "remapped sector" behavior of a drive with bad
+sectors.
+
+Normally, a drive that is encountering bad sectors will most likely
+encounter more bad sectors, at an unknown time or location.
+With dm-dust, the user can use the "addbadblock" and "removebadblock"
+messages to add arbitrary bad blocks at new locations, and the
+"enable" and "disable" messages to modulate the state of whether the
+configured "bad blocks" will be treated as bad, or bypassed.
+This allows the pre-writing of test data and metadata prior to
+simulating a "failure" event where bad sectors start to appear.
+
+Table parameters:
+-----------------
+<device_path> <offset> <blksz>
+
+Mandatory parameters:
+    <device_path>: path to the block device.
+    <offset>: offset to data area from start of device_path
+    <blksz>: block size in bytes
+	     (minimum 512, maximum 1073741824, must be a power of 2)
+
+Usage instructions:
+-------------------
+
+First, find the size (in 512-byte sectors) of the device to be used:
+
+$ sudo blockdev --getsz /dev/vdb1
+33552384
+
+Create the dm-dust device:
+(For a device with a block size of 512 bytes)
+$ sudo dmsetup create dust1 --table '0 33552384 dust /dev/vdb1 0 512'
+
+(For a device with a block size of 4096 bytes)
+$ sudo dmsetup create dust1 --table '0 33552384 dust /dev/vdb1 0 4096'
+
+Check the status of the read behavior ("bypass" indicates that all I/O
+will be passed through to the underlying device):
+$ sudo dmsetup status dust1
+0 33552384 dust 252:17 bypass
+
+$ sudo dd if=/dev/mapper/dust1 of=/dev/null bs=512 count=128 iflag=direct
+128+0 records in
+128+0 records out
+
+$ sudo dd if=/dev/zero of=/dev/mapper/dust1 bs=512 count=128 oflag=direct
+128+0 records in
+128+0 records out
+
+Adding and removing bad blocks:
+-------------------------------
+
+At any time (i.e.: whether the device has the "bad block" emulation
+enabled or disabled), bad blocks may be added or removed from the
+device via the "addbadblock" and "removebadblock" messages:
+
+$ sudo dmsetup message dust1 0 addbadblock 60
+kernel: device-mapper: dust: badblock added at block 60
+
+$ sudo dmsetup message dust1 0 addbadblock 67
+kernel: device-mapper: dust: badblock added at block 67
+
+$ sudo dmsetup message dust1 0 addbadblock 72
+kernel: device-mapper: dust: badblock added at block 72
+
+These bad blocks will be stored in the "bad block list".
+While the device is in "bypass" mode, reads and writes will succeed:
+
+$ sudo dmsetup status dust1
+0 33552384 dust 252:17 bypass
+
+Enabling block read failures:
+-----------------------------
+
+To enable the "fail read on bad block" behavior, send the "enable" message:
+
+$ sudo dmsetup message dust1 0 enable
+kernel: device-mapper: dust: enabling read failures on bad sectors
+
+$ sudo dmsetup status dust1
+0 33552384 dust 252:17 fail_read_on_bad_block
+
+With the device in "fail read on bad block" mode, attempting to read a
+block will encounter an "Input/output error":
+
+$ sudo dd if=/dev/mapper/dust1 of=/dev/null bs=512 count=1 skip=67 iflag=direct
+dd: error reading '/dev/mapper/dust1': Input/output error
+0+0 records in
+0+0 records out
+0 bytes copied, 0.00040651 s, 0.0 kB/s
+
+...and writing to the bad blocks will remove the blocks from the list,
+therefore emulating the "remap" behavior of hard disk drives:
+
+$ sudo dd if=/dev/zero of=/dev/mapper/dust1 bs=512 count=128 oflag=direct
+128+0 records in
+128+0 records out
+
+kernel: device-mapper: dust: block 60 removed from badblocklist by write
+kernel: device-mapper: dust: block 67 removed from badblocklist by write
+kernel: device-mapper: dust: block 72 removed from badblocklist by write
+kernel: device-mapper: dust: block 87 removed from badblocklist by write
+
+Bad block add/remove error handling:
+------------------------------------
+
+Attempting to add a bad block that already exists in the list will
+result in an "Invalid argument" error, as well as a helpful message:
+
+$ sudo dmsetup message dust1 0 addbadblock 88
+device-mapper: message ioctl on dust1  failed: Invalid argument
+kernel: device-mapper: dust: block 88 already in badblocklist
+
+Attempting to remove a bad block that doesn't exist in the list will
+result in an "Invalid argument" error, as well as a helpful message:
+
+$ sudo dmsetup message dust1 0 removebadblock 87
+device-mapper: message ioctl on dust1  failed: Invalid argument
+kernel: device-mapper: dust: block 87 not found in badblocklist
+
+Counting the number of bad blocks in the bad block list:
+--------------------------------------------------------
+
+To count the number of bad blocks configured in the device, run the
+following message command:
+
+$ sudo dmsetup message dust1 0 countbadblocks
+
+A message will print with the number of bad blocks currently
+configured on the device:
+
+kernel: device-mapper: dust: countbadblocks: 895 badblock(s) found
+
+Querying for specific bad blocks:
+---------------------------------
+
+To find out if a specific block is in the bad block list, run the
+following message command:
+
+$ sudo dmsetup message dust1 0 queryblock 72
+
+The following message will print if the block is in the list:
+device-mapper: dust: queryblock: block 72 found in badblocklist
+
+The following message will print if the block is in the list:
+device-mapper: dust: queryblock: block 72 not found in badblocklist
+
+The "queryblock" message command will work in both the "enabled"
+and "disabled" modes, allowing the verification of whether a block
+will be treated as "bad" without having to issue I/O to the device,
+or having to "enable" the bad block emulation.
+
+Clearing the bad block list:
+----------------------------
+
+To clear the bad block list (without needing to individually run
+a "removebadblock" message command for every block), run the
+following message command:
+
+$ sudo dmsetup message dust1 0 clearbadblocks
+
+After clearing the bad block list, the following message will appear:
+
+kernel: device-mapper: dust: clearbadblocks: badblocks cleared
+
+If there were no bad blocks to clear, the following message will
+appear:
+
+kernel: device-mapper: dust: clearbadblocks: no badblocks found
+
+Message commands list:
+----------------------
+
+Below is a list of the messages that can be sent to a dust device:
+
+Operations on blocks (requires a <blknum> argument):
+
+addbadblock <blknum>
+queryblock <blknum>
+removebadblock <blknum>
+
+...where <blknum> is a block number within range of the device
+  (corresponding to the block size of the device.)
+
+Single argument message commands:
+
+countbadblocks
+clearbadblocks
+disable
+enable
+quiet
+
+Device removal:
+---------------
+
+When finished, remove the device via the "dmsetup remove" command:
+
+$ sudo dmsetup remove dust1
+
+Quiet mode:
+-----------
+
+On test runs with many bad blocks, it may be desirable to avoid
+excessive logging (from bad blocks added, removed, or "remapped").
+This can be done by enabling "quiet mode" via the following message:
+
+$ sudo dmsetup message dust1 0 quiet
+
+This will suppress log messages from add / remove / removed by write
+operations.  Log messages from "countbadblocks" or "queryblock"
+message commands will still print in quiet mode.
+
+The status of quiet mode can be seen by running "dmsetup status":
+
+$ sudo dmsetup status dust1
+0 33552384 dust 252:17 fail_read_on_bad_block quiet
+
+To disable quiet mode, send the "quiet" message again:
+
+$ sudo dmsetup message dust1 0 quiet
+
+$ sudo dmsetup status dust1
+0 33552384 dust 252:17 fail_read_on_bad_block verbose
+
+(The presence of "verbose" indicates normal logging.)
+
+"Why not...?"
+-------------
+
+scsi_debug has a "medium error" mode that can fail reads on one
+specified sector (sector 0x1234, hardcoded in the source code), but
+it uses RAM for the persistent storage, which drastically decreases
+the potential device size.
+
+dm-flakey fails all I/O from all block locations at a specified time
+frequency, and not a given point in time.
+
+When a bad sector occurs on a hard disk drive, reads to that sector
+are failed by the device, usually resulting in an error code of EIO
+("I/O error") or ENODATA ("No data available").  However, a write to
+the sector may succeed, and result in the sector becoming readable
+after the device controller no longer experiences errors reading the
+sector (or after a reallocation of the sector).  However, there may
+be bad sectors that occur on the device in the future, in a different,
+unpredictable location.
+
+This target seeks to provide a device that can exhibit the behavior
+of a bad sector at a known sector location, at a known time, based
+on a large storage device (at least tens of gigabytes, not occupying
+system memory).

Documentation/device-mapper/dm-integrity.txt

@@ -21,6 +21,13 @@ mode it calculates and verifies the integrity tag internally. In this
 mode, the dm-integrity target can be used to detect silent data
 corruption on the disk or in the I/O path.
 
+There's an alternate mode of operation where dm-integrity uses bitmap
+instead of a journal. If a bit in the bitmap is 1, the corresponding
+region's data and integrity tags are not synchronized - if the machine
+crashes, the unsynchronized regions will be recalculated. The bitmap mode
+is faster than the journal mode, because we don't have to write the data
+twice, but it is also less reliable, because if data corruption happens
+when the machine crashes, it may not be detected.
 
 When loading the target for the first time, the kernel driver will format
 the device. But it will only format the device if the superblock contains
@@ -59,6 +66,10 @@ Target arguments:
 		either both data and tag or none of them are written. The
 		journaled mode degrades write throughput twice because the
 		data have to be written twice.
+	B - bitmap mode - data and metadata are written without any
+		synchronization, the driver maintains a bitmap of dirty
+		regions where data and metadata don't match. This mode can
+		only be used with internal hash.
 	R - recovery mode - in this mode, journal is not replayed,
 		checksums are not checked and writes to the device are not
 		allowed. This mode is useful for data recovery if the
@@ -79,6 +90,10 @@ interleave_sectors:number
 	a power of two. If the device is already formatted, the value from
 	the superblock is used.
 
+meta_device:device
+	Don't interleave the data and metadata on on device. Use a
+	separate device for metadata.
+
 buffer_sectors:number
 	The number of sectors in one buffer. The value is rounded down to
 	a power of two.
@@ -146,6 +161,15 @@ block_size:number
 	Supported values are 512, 1024, 2048 and 4096 bytes.  If not
 	specified the default block size is 512 bytes.
 
+sectors_per_bit:number
+	In the bitmap mode, this parameter specifies the number of
+	512-byte sectors that corresponds to one bitmap bit.
+
+bitmap_flush_interval:number
+	The bitmap flush interval in milliseconds. The metadata buffers
+	are synchronized when this interval expires.
+
+
 The journal mode (D/J), buffer_sectors, journal_watermark, commit_time can
 be changed when reloading the target (load an inactive table and swap the
 tables with suspend and resume). The other arguments should not be changed
@@ -167,7 +191,13 @@ The layout of the formatted block device:
 	  provides (i.e. the size of the device minus the size of all
 	  metadata and padding). The user of this target should not send
 	  bios that access data beyond the "provided data sectors" limit.
-	* flags - a flag is set if journal_mac is used
+	* flags
+	  SB_FLAG_HAVE_JOURNAL_MAC - a flag is set if journal_mac is used
+	  SB_FLAG_RECALCULATING - recalculating is in progress
+	  SB_FLAG_DIRTY_BITMAP - journal area contains the bitmap of dirty
+		blocks
+	* log2(sectors per block)
+	* a position where recalculating finished
 * journal
 	The journal is divided into sections, each section contains:
 	* metadata area (4kiB), it contains journal entries

Documentation/devicetree/bindings/arm/altera/socfpga-system.txt

@@ -11,3 +11,15 @@ Example:
 		reg = <0xffd08000 0x1000>;
 		cpu1-start-addr = <0xffd080c4>;
 	};
+
+ARM64 - Stratix10
+Required properties:
+- compatible : "altr,sys-mgr-s10"
+- reg : Should contain 1 register range(address and length)
+        for system manager register.
+
+Example:
+	 sysmgr@ffd12000 {
+		compatible = "altr,sys-mgr-s10";
+		reg = <0xffd12000 0x228>;
+	};

Documentation/devicetree/bindings/arm/amlogic.txt

@@ -110,6 +110,7 @@ Board compatible values (alphabetically, grouped by SoC):
 
   - "amlogic,u200" (Meson g12a s905d2)
   - "amediatech,x96-max" (Meson g12a s905x2)
+  - "seirobotics,sei510" (Meson g12a s905x2)
 
 Amlogic Meson Firmware registers Interface
 ------------------------------------------

Documentation/devicetree/bindings/arm/atmel-at91.txt

@@ -25,6 +25,7 @@ compatible: must be one of:
     o "atmel,at91sam9n12"
     o "atmel,at91sam9rl"
     o "atmel,at91sam9xe"
+    o "microchip,sam9x60"
  * "atmel,sama5" for SoCs using a Cortex-A5, shall be extended with the specific
    SoC family:
     o "atmel,sama5d2" shall be extended with the specific SoC compatible: