Merge 4.16-rc7 into char-misc-next

We want the hyperv fix in here for merging and testing.

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

Documentation/ABI/testing/sysfs-ata

@@ -1,110 +1,139 @@
 What:		/sys/class/ata_...
-Date:		August 2008
-Contact:	Gwendal Grignou<gwendal@google.com>
 Description:
-
-Provide a place in sysfs for storing the ATA topology of the system.  This allows
-retrieving various information about ATA objects.
+		Provide a place in sysfs for storing the ATA topology of the
+		system. This allows retrieving various information about ATA
+		objects.
 
 Files under /sys/class/ata_port
 -------------------------------
 
-	For each port, a directory ataX is created where X is the ata_port_id of
-	the port. The device parent is the ata host device.
+For each port, a directory ataX is created where X is the ata_port_id of the
+port. The device parent is the ata host device.
 
-idle_irq (read)
 
-	Number of IRQ received by the port while idle [some ata HBA only].
+What:		/sys/class/ata_port/ataX/nr_pmp_links
+What:		/sys/class/ata_port/ataX/idle_irq
+Date:		May, 2010
+KernelVersion:	v2.6.37
+Contact:	Gwendal Grignou <gwendal@chromium.org>
+Description:
+		nr_pmp_links:	(RO) If a SATA Port Multiplier (PM) is
+				connected, the number of links behind it.
 
-nr_pmp_links (read)
+		idle_irq:	(RO) Number of IRQ received by the port while
+				idle [some ata HBA only].
 
-	If a SATA Port Multiplier (PM) is connected, number of link behind it.
+
+What:		/sys/class/ata_port/ataX/port_no
+Date:		May, 2013
+KernelVersion:	v3.11
+Contact:	Gwendal Grignou <gwendal@chromium.org>
+Description:
+		(RO) Host local port number. While registering host controller,
+		port numbers are tracked based upon number of ports available on
+		the controller. This attribute is needed by udev for composing
+		persistent links in /dev/disk/by-path.
 
 Files under /sys/class/ata_link
 -------------------------------
 
-	Behind each port, there is a ata_link. If there is a SATA PM in the
-	topology, 15 ata_link objects are created.
-
-	If a link is behind a port, the directory name is linkX, where X is
-	ata_port_id of the port.
-	If a link is behind a PM, its name is linkX.Y where X is ata_port_id
-	of the parent port and Y the PM port.
+Behind each port, there is a ata_link. If there is a SATA PM in the topology, 15
+ata_link objects are created.
 
-hw_sata_spd_limit
+If a link is behind a port, the directory name is linkX, where X is ata_port_id
+of the port. If a link is behind a PM, its name is linkX.Y where X is
+ata_port_id of the parent port and Y the PM port.
 
-	Maximum speed supported by the connected SATA device.
 
-sata_spd_limit
+What:		/sys/class/ata_link/linkX[.Y]/hw_sata_spd_limit
+What:		/sys/class/ata_link/linkX[.Y]/sata_spd_limit
+What:		/sys/class/ata_link/linkX[.Y]/sata_spd
+Date:		May, 2010
+KernelVersion:	v2.6.37
+Contact:	Gwendal Grignou <gwendal@chromium.org>
+Description:
+		hw_sata_spd_limit:	(RO) Maximum speed supported by the
+					connected SATA device.
 
-	Maximum speed imposed by libata.
+		sata_spd_limit:		(RO) Maximum speed imposed by libata.
 
-sata_spd
+		sata_spd:		(RO) Current speed of the link
+					eg. 1.5, 3 Gbps etc.
 
-	Current speed of the link [1.5, 3Gps,...].
 
 Files under /sys/class/ata_device
 ---------------------------------
 
-	Behind each link, up to two ata device are created.
-	The name of the directory is devX[.Y].Z where:
-	- X is ata_port_id of the port where the device is connected,
-	- Y the port of the PM if any, and
-	- Z the device id: for PATA, there is usually 2 devices [0,1],
-	only 1 for SATA.
-
-class
-	Device class. Can be "ata" for disk, "atapi" for packet device,
-	"pmp" for PM, or "none" if no device was found behind the link.
-
-dma_mode
+Behind each link, up to two ata devices are created.
+The name of the directory is devX[.Y].Z where:
+- X is ata_port_id of the port where the device is connected,
+- Y the port of the PM if any, and
+- Z the device id: for PATA, there is usually 2 devices [0,1], only 1 for SATA.
+
+
+What:		/sys/class/ata_device/devX[.Y].Z/spdn_cnt
+What:		/sys/class/ata_device/devX[.Y].Z/gscr
+What:		/sys/class/ata_device/devX[.Y].Z/ering
+What:		/sys/class/ata_device/devX[.Y].Z/id
+What:		/sys/class/ata_device/devX[.Y].Z/pio_mode
+What:		/sys/class/ata_device/devX[.Y].Z/xfer_mode
+What:		/sys/class/ata_device/devX[.Y].Z/dma_mode
+What:		/sys/class/ata_device/devX[.Y].Z/class
+Date:		May, 2010
+KernelVersion:	v2.6.37
+Contact:	Gwendal Grignou <gwendal@chromium.org>
+Description:
+		spdn_cnt:	(RO) Number of times libata decided to lower the
+				speed of link due to errors.
 
-	Transfer modes supported by the device when in DMA mode.
-	Mostly used by PATA device.
+		gscr:		(RO) Cached result of the dump of PM GSCR
+				register. Valid registers are:
 
-pio_mode
+				0:      SATA_PMP_GSCR_PROD_ID,
+				1:	SATA_PMP_GSCR_REV,
+				2:      SATA_PMP_GSCR_PORT_INFO,
+				32:     SATA_PMP_GSCR_ERROR,
+				33:     SATA_PMP_GSCR_ERROR_EN,
+				64:     SATA_PMP_GSCR_FEAT,
+				96:     SATA_PMP_GSCR_FEAT_EN,
+				130:    SATA_PMP_GSCR_SII_GPIO
 
-	Transfer modes supported by the device when in PIO mode.
-	Mostly used by PATA device.
+				Only valid if the device is a PM.
 
-xfer_mode
+		ering:		(RO) Formatted output of the error ring of the
+				device.
 
-	Current transfer mode.
+		id:		(RO) Cached result of IDENTIFY command, as
+				described in ATA8 7.16 and 7.17. Only valid if
+				the device is not a PM.
 
-id
+		pio_mode:	(RO) Transfer modes supported by the device when
+				in PIO mode. Mostly used by PATA device.
 
-	Cached result of IDENTIFY command, as described in ATA8 7.16 and 7.17.
-	Only valid if the device is not a PM.
+		xfer_mode:	(RO) Current transfer mode
 
-gscr
+		dma_mode:	(RO) Transfer modes supported by the device when
+				in DMA mode. Mostly used by PATA device.
 
-	Cached result of the dump of PM GSCR register.
-	Valid registers are:
-	0: 	SATA_PMP_GSCR_PROD_ID,
-	1: 	SATA_PMP_GSCR_REV,
-	2: 	SATA_PMP_GSCR_PORT_INFO,
-	32:	SATA_PMP_GSCR_ERROR,
-	33:	SATA_PMP_GSCR_ERROR_EN,
-	64:	SATA_PMP_GSCR_FEAT,
-	96:	SATA_PMP_GSCR_FEAT_EN,
-	130:	SATA_PMP_GSCR_SII_GPIO
-	Only valid if the device is a PM.
+		class:		(RO) Device class. Can be "ata" for disk,
+				"atapi" for packet device, "pmp" for PM, or
+				"none" if no device was found behind the link.
 
-trim
 
-	Shows the DSM TRIM mode currently used by the device. Valid
-	values are:
-	unsupported:		Drive does not support DSM TRIM
-	unqueued:		Drive supports unqueued DSM TRIM only
-	queued:			Drive supports queued DSM TRIM
-	forced_unqueued:	Drive's queued DSM support is known to be
-				buggy and only unqueued TRIM commands
-				are sent
+What:		/sys/class/ata_device/devX[.Y].Z/trim
+Date:		May, 2015
+KernelVersion:	v4.10
+Contact:	Gwendal Grignou <gwendal@chromium.org>
+Description:
+		(RO) Shows the DSM TRIM mode currently used by the device. Valid
+		values are:
 
-spdn_cnt
+		unsupported:		Drive does not support DSM TRIM
 
-	Number of time libata decided to lower the speed of link due to errors.
+		unqueued:               Drive supports unqueued DSM TRIM only
 
-ering
+		queued:                 Drive supports queued DSM TRIM
 
-	Formatted output of the error ring of the device.
+		forced_unqueued:	Drive's queued DSM support is known to
+					be buggy and only unqueued TRIM commands
+					are sent

Documentation/ABI/testing/sysfs-block-device

@@ -0,0 +1,58 @@
+What:		/sys/block/*/device/sw_activity
+Date:		Jun, 2008
+KernelVersion:	v2.6.27
+Contact:	linux-ide@vger.kernel.org
+Description:
+		(RW) Used by drivers which support software controlled activity
+		LEDs.
+
+		It has the following valid values:
+
+		0	OFF - the LED is not activated on activity
+		1	BLINK_ON - the LED blinks on every 10ms when activity is
+			detected.
+		2	BLINK_OFF - the LED is on when idle, and blinks off
+			every 10ms when activity is detected.
+
+		Note that the user must turn sw_activity OFF it they wish to
+		control the activity LED via the em_message file.
+
+
+What:		/sys/block/*/device/unload_heads
+Date:		Sep, 2008
+KernelVersion:	v2.6.28
+Contact:	linux-ide@vger.kernel.org
+Description:
+		(RW) Hard disk shock protection
+
+		Writing an integer value to this file will take the heads of the
+		respective drive off the platter and block all I/O operations
+		for the specified number of milliseconds.
+
+		- If the device does not support the unload heads feature,
+		  access is denied with -EOPNOTSUPP.
+		- The maximal value accepted for a timeout is 30000
+		  milliseconds.
+		- A previously set timeout can be cancelled and disk can resume
+		  normal operation immediately by specifying a timeout of 0.
+		- Some hard drives only comply with an earlier version of the
+		  ATA standard, but support the unload feature nonetheless.
+		  There is no safe way Linux can detect these devices, so this
+		  is not enabled by default. If it is known that your device
+		  does support the unload feature, then you can tell the kernel
+		  to enable it by writing -1. It can be disabled again by
+		  writing -2.
+		- Values below -2 are rejected with -EINVAL
+
+		For more information, see
+		Documentation/laptops/disk-shock-protection.txt
+
+
+What:		/sys/block/*/device/ncq_prio_enable
+Date:		Oct, 2016
+KernelVersion:	v4.10
+Contact:	linux-ide@vger.kernel.org
+Description:
+		(RW) Write to the file to turn on or off the SATA ncq (native
+		command queueing) support. By default this feature is turned
+		off.

Documentation/ABI/testing/sysfs-class-scsi_host

@@ -27,3 +27,92 @@ Description:	This file contains the current status of the "SSD Smart Path"
 		the direct i/o path to physical devices.  This setting is
 		controller wide, affecting all configured logical drives on the
 		controller.  This file is readable and writable.
+
+What:		/sys/class/scsi_host/hostX/link_power_management_policy
+Date:		Oct, 2007
+KernelVersion:	v2.6.24
+Contact:	linux-ide@vger.kernel.org
+Description:
+		(RW) This parameter allows the user to read and set the link
+		(interface) power management.
+
+		There are four possible options:
+
+		min_power: Tell the controller to try to make the link use the
+		least possible power when possible. This may sacrifice some
+		performance due to increased latency when coming out of lower
+		power states.
+
+		max_performance: Generally, this means no power management.
+		Tell the controller to have performance be a priority over power
+		management.
+
+		medium_power: Tell the controller to enter a lower power state
+		when possible, but do not enter the lowest power state, thus
+		improving latency over min_power setting.
+
+		med_power_with_dipm: Identical to the existing medium_power
+		setting except that it enables dipm (device initiated power
+		management) on top, which makes it match the Windows IRST (Intel
+		Rapid Storage Technology) driver settings. This setting is also
+		close to min_power, except that:
+		a) It does not use host-initiated slumber mode, but it does
+		allow device-initiated slumber
+		b) It does not enable low power device sleep mode (DevSlp).
+
+What:		/sys/class/scsi_host/hostX/em_message
+What:		/sys/class/scsi_host/hostX/em_message_type
+Date:		Jun, 2008
+KernelVersion:	v2.6.27
+Contact:	linux-ide@vger.kernel.org
+Description:
+		em_message: (RW) Enclosure management support. For the LED
+		protocol, writes and reads correspond to the LED message format
+		as defined in the AHCI spec.
+
+		The user must turn sw_activity (under /sys/block/*/device/) OFF
+		it they wish to control the activity LED via the em_message
+		file.
+
+		em_message_type: (RO) Displays the current enclosure management
+		protocol that is being used by the driver (for eg. LED, SAF-TE,
+		SES-2, SGPIO etc).
+
+What:		/sys/class/scsi_host/hostX/ahci_port_cmd
+What:		/sys/class/scsi_host/hostX/ahci_host_caps
+What:		/sys/class/scsi_host/hostX/ahci_host_cap2
+Date:		Mar, 2010
+KernelVersion:	v2.6.35
+Contact:	linux-ide@vger.kernel.org
+Description:
+		[to be documented]
+
+What:		/sys/class/scsi_host/hostX/ahci_host_version
+Date:		Mar, 2010
+KernelVersion:	v2.6.35
+Contact:	linux-ide@vger.kernel.org
+Description:
+		(RO) Display the version of the AHCI spec implemented by the
+		host.
+
+What:		/sys/class/scsi_host/hostX/em_buffer
+Date:		Apr, 2010
+KernelVersion:	v2.6.35
+Contact:	linux-ide@vger.kernel.org
+Description:
+		(RW) Allows access to AHCI EM (enclosure management) buffer
+		directly if the host supports EM.
+
+		For eg. the AHCI driver supports SGPIO EM messages but the
+		SATA/AHCI specs do not define the SGPIO message format of the EM
+		buffer. Different hardware(HW) vendors may have different
+		definitions. With the em_buffer attribute, this issue can be
+		solved by allowing HW vendors to provide userland drivers and
+		tools for their SGPIO initiators.
+
+What:		/sys/class/scsi_host/hostX/em_message_supported
+Date:		Oct, 2009
+KernelVersion:	v2.6.39
+Contact:	linux-ide@vger.kernel.org
+Description:
+		(RO) Displays supported enclosure management message types.

Documentation/accelerators/ocxl.rst

@@ -152,6 +152,11 @@ OCXL_IOCTL_IRQ_SET_FD:
   Associate an event fd to an AFU interrupt so that the user process
   can be notified when the AFU sends an interrupt.
 
+OCXL_IOCTL_GET_METADATA:
+
+  Obtains configuration information from the card, such at the size of
+  MMIO areas, the AFU version, and the PASID for the current context.
+
 
 mmap
 ----

Documentation/devicetree/bindings/display/exynos/exynos_hdmi.txt

@@ -16,6 +16,7 @@ Required properties:
 - ddc: phandle to the hdmi ddc node
 - phy: phandle to the hdmi phy node
 - samsung,syscon-phandle: phandle for system controller node for PMU.
+- #sound-dai-cells: should be 0.
 
 Required properties for Exynos 4210, 4212, 5420 and 5433:
 - clocks: list of clock IDs from SoC clock driver.

Documentation/devicetree/bindings/dma/mv-xor-v2.txt

@@ -11,7 +11,11 @@ Required properties:
   interrupts.
 
 Optional properties:
-- clocks: Optional reference to the clock used by the XOR engine.
+- clocks: Optional reference to the clocks used by the XOR engine.
+- clock-names: mandatory if there is a second clock, in this case the
+   name must be "core" for the first clock and "reg" for the second
+   one
+
 
 Example:
 

Documentation/devicetree/bindings/iio/adc/sigma-delta-modulator.txt

@@ -3,11 +3,11 @@ Device-Tree bindings for sigma delta modulator
 Required properties:
 - compatible: should be "ads1201", "sd-modulator". "sd-modulator" can be use
 	as a generic SD modulator if modulator not specified in compatible list.
-- #io-channel-cells = <1>: See the IIO bindings section "IIO consumers".
+- #io-channel-cells = <0>: See the IIO bindings section "IIO consumers".
 
 Example node:
 
 	ads1202: adc@0 {
 		compatible = "sd-modulator";
-		#io-channel-cells = <1>;
+		#io-channel-cells = <0>;
 	};

Documentation/devicetree/bindings/net/dsa/marvell.txt

@@ -50,14 +50,15 @@ Example:
 			compatible = "marvell,mv88e6085";
 			reg = <0>;
 			reset-gpios = <&gpio5 1 GPIO_ACTIVE_LOW>;
-		};
-		mdio {
-			#address-cells = <1>;
-			#size-cells = <0>;
-			switch1phy0: switch1phy0@0 {
-				reg = <0>;
-				interrupt-parent = <&switch0>;
-				interrupts = <0 IRQ_TYPE_LEVEL_HIGH>;
+
+			mdio {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				switch1phy0: switch1phy0@0 {
+					reg = <0>;
+					interrupt-parent = <&switch0>;
+					interrupts = <0 IRQ_TYPE_LEVEL_HIGH>;
+				};
 			};
 		};
 	};
@@ -74,23 +75,24 @@ Example:
 			compatible = "marvell,mv88e6390";
 			reg = <0>;
 			reset-gpios = <&gpio5 1 GPIO_ACTIVE_LOW>;
-		};
-		mdio {
-			#address-cells = <1>;
-			#size-cells = <0>;
-			switch1phy0: switch1phy0@0 {
-				reg = <0>;
-				interrupt-parent = <&switch0>;
-				interrupts = <0 IRQ_TYPE_LEVEL_HIGH>;
+
+			mdio {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				switch1phy0: switch1phy0@0 {
+					reg = <0>;
+					interrupt-parent = <&switch0>;
+					interrupts = <0 IRQ_TYPE_LEVEL_HIGH>;
+				};
 			};
-		};
 
-		mdio1 {
-			compatible = "marvell,mv88e6xxx-mdio-external";
-			#address-cells = <1>;
-			#size-cells = <0>;
-			switch1phy9: switch1phy0@9 {
-				reg = <9>;
+			mdio1 {
+				compatible = "marvell,mv88e6xxx-mdio-external";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				switch1phy9: switch1phy0@9 {
+					reg = <9>;
+				};
 			};
 		};
 	};

Documentation/devicetree/bindings/net/renesas,ravb.txt

@@ -18,6 +18,7 @@ Required properties:
       - "renesas,etheravb-r8a7795" for the R8A7795 SoC.
       - "renesas,etheravb-r8a7796" for the R8A7796 SoC.
       - "renesas,etheravb-r8a77970" for the R8A77970 SoC.
+      - "renesas,etheravb-r8a77980" for the R8A77980 SoC.
       - "renesas,etheravb-r8a77995" for the R8A77995 SoC.
       - "renesas,etheravb-rcar-gen3" as a fallback for the above
 		R-Car Gen3 devices.
@@ -26,7 +27,11 @@ Required properties:
 	SoC-specific version corresponding to the platform first followed by
 	the generic version.
 
-- reg: offset and length of (1) the register block and (2) the stream buffer.
+- reg: Offset and length of (1) the register block and (2) the stream buffer.
+       The region for the register block is mandatory.
+       The region for the stream buffer is optional, as it is only present on
+       R-Car Gen2 and RZ/G1 SoCs, and on R-Car H3 (R8A7795), M3-W (R8A7796),
+       and M3-N (R8A77965).
 - interrupts: A list of interrupt-specifiers, one for each entry in
 	      interrupt-names.
 	      If interrupt-names is not present, an interrupt specifier

Documentation/devicetree/bindings/usb/dwc2.txt

@@ -19,7 +19,7 @@ Required properties:
   configured in FS mode;
   - "st,stm32f4x9-hsotg": The DWC2 USB HS controller instance in STM32F4x9 SoCs
   configured in HS mode;
-  - "st,stm32f7xx-hsotg": The DWC2 USB HS controller instance in STM32F7xx SoCs
+  - "st,stm32f7-hsotg": The DWC2 USB HS controller instance in STM32F7 SoCs
     configured in HS mode;
 - reg : Should contain 1 register range (address and length)
 - interrupts : Should contain 1 interrupt

Documentation/devicetree/bindings/usb/renesas_usb3.txt

@@ -4,6 +4,7 @@ Required properties:
   - compatible: Must contain one of the following:
 	- "renesas,r8a7795-usb3-peri"
 	- "renesas,r8a7796-usb3-peri"
+	- "renesas,r8a77965-usb3-peri"
 	- "renesas,rcar-gen3-usb3-peri" for a generic R-Car Gen3 compatible
 	  device
 

Documentation/devicetree/bindings/usb/renesas_usbhs.txt

@@ -12,6 +12,7 @@ Required properties:
 	- "renesas,usbhs-r8a7794" for r8a7794 (R-Car E2) compatible device
 	- "renesas,usbhs-r8a7795" for r8a7795 (R-Car H3) compatible device
 	- "renesas,usbhs-r8a7796" for r8a7796 (R-Car M3-W) compatible device
+	- "renesas,usbhs-r8a77965" for r8a77965 (R-Car M3-N) compatible device
 	- "renesas,usbhs-r8a77995" for r8a77995 (R-Car D3) compatible device
 	- "renesas,usbhs-r7s72100" for r7s72100 (RZ/A1) compatible device
 	- "renesas,rcar-gen2-usbhs" for R-Car Gen2 or RZ/G1 compatible devices

Documentation/devicetree/bindings/usb/usb-xhci.txt

@@ -13,6 +13,7 @@ Required properties:
     - "renesas,xhci-r8a7793" for r8a7793 SoC
     - "renesas,xhci-r8a7795" for r8a7795 SoC
     - "renesas,xhci-r8a7796" for r8a7796 SoC
+    - "renesas,xhci-r8a77965" for r8a77965 SoC
     - "renesas,rcar-gen2-xhci" for a generic R-Car Gen2 or RZ/G1 compatible
       device
     - "renesas,rcar-gen3-xhci" for a generic R-Car Gen3 compatible device

Documentation/ia64/serial.txt

@@ -111,7 +111,7 @@ TROUBLESHOOTING SERIAL CONSOLE PROBLEMS
 
 	- If you don't have an HCDP, the kernel doesn't know where
 	  your console lives until the driver discovers serial
-	  devices.  Use "console=uart, io,0x3f8" (or appropriate
+	  devices.  Use "console=uart,io,0x3f8" (or appropriate
 	  address for your machine).
 
     Kernel and init script output works fine, but no "login:" prompt:

Documentation/networking/segmentation-offloads.txt

@@ -20,8 +20,8 @@ TCP Segmentation Offload
 
 TCP segmentation allows a device to segment a single frame into multiple
 frames with a data payload size specified in skb_shinfo()->gso_size.
-When TCP segmentation requested the bit for either SKB_GSO_TCP or
-SKB_GSO_TCP6 should be set in skb_shinfo()->gso_type and
+When TCP segmentation requested the bit for either SKB_GSO_TCPV4 or
+SKB_GSO_TCPV6 should be set in skb_shinfo()->gso_type and
 skb_shinfo()->gso_size should be set to a non-zero value.
 
 TCP segmentation is dependent on support for the use of partial checksum
@@ -153,8 +153,18 @@ To signal this, gso_size is set to the special value GSO_BY_FRAGS.
 
 Therefore, any code in the core networking stack must be aware of the
 possibility that gso_size will be GSO_BY_FRAGS and handle that case
-appropriately. (For size checks, the skb_gso_validate_*_len family of
-helpers do this automatically.)
+appropriately.
+
+There are some helpers to make this easier:
+
+ - skb_is_gso(skb) && skb_is_gso_sctp(skb) is the best way to see if
+   an skb is an SCTP GSO skb.
+
+ - For size checks, the skb_gso_validate_*_len family of helpers correctly
+   considers GSO_BY_FRAGS.
+
+ - For manipulating packets, skb_increase_gso_size and skb_decrease_gso_size
+   will check for GSO_BY_FRAGS and WARN if asked to manipulate these skbs.
 
 This also affects drivers with the NETIF_F_FRAGLIST & NETIF_F_GSO_SCTP bits
 set. Note also that NETIF_F_GSO_SCTP is included in NETIF_F_GSO_SOFTWARE.

Documentation/sphinx/kerneldoc.py

@@ -36,8 +36,7 @@ import glob
 
 from docutils import nodes, statemachine
 from docutils.statemachine import ViewList
-from docutils.parsers.rst import directives
-from sphinx.util.compat import Directive
+from docutils.parsers.rst import directives, Directive
 from sphinx.ext.autodoc import AutodocReporter
 
 __version__  = '1.0'

MAINTAINERS

@@ -9925,6 +9925,13 @@ F:	Documentation/ABI/stable/sysfs-bus-nvmem
 F:	include/linux/nvmem-consumer.h
 F:	include/linux/nvmem-provider.h
 
+NXP SGTL5000 DRIVER
+M:	Fabio Estevam <fabio.estevam@nxp.com>
+L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
+S:	Maintained
+F:	Documentation/devicetree/bindings/sound/sgtl5000.txt
+F:	sound/soc/codecs/sgtl5000*
+
 NXP TDA998X DRM DRIVER
 M:	Russell King <linux@armlinux.org.uk>
 S:	Supported
@@ -10327,7 +10334,7 @@ F:	drivers/oprofile/
 F:	include/linux/oprofile.h
 
 ORACLE CLUSTER FILESYSTEM 2 (OCFS2)
-M:	Mark Fasheh <mfasheh@versity.com>
+M:	Mark Fasheh <mark@fasheh.com>
 M:	Joel Becker <jlbec@evilplan.org>
 L:	ocfs2-devel@oss.oracle.com (moderated for non-subscribers)
 W:	http://ocfs2.wiki.kernel.org
@@ -10837,6 +10844,7 @@ F:	drivers/platform/x86/peaq-wmi.c
 PER-CPU MEMORY ALLOCATOR
 M:	Tejun Heo <tj@kernel.org>
 M:	Christoph Lameter <cl@linux.com>
+M:	Dennis Zhou <dennisszhou@gmail.com>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu.git
 S:	Maintained
 F:	include/linux/percpu*.h
@@ -12107,6 +12115,7 @@ M:	Sylwester Nawrocki <s.nawrocki@samsung.com>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 S:	Supported
 F:	sound/soc/samsung/
+F:	Documentation/devicetree/bindings/sound/samsung*
 
 SAMSUNG EXYNOS PSEUDO RANDOM NUMBER GENERATOR (RNG) DRIVER
 M:	Krzysztof Kozlowski <krzk@kernel.org>

Makefile

@@ -2,7 +2,7 @@
 VERSION = 4
 PATCHLEVEL = 16
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc7
 NAME = Fearless Coyote
 
 # *DOCUMENTATION*
@@ -826,6 +826,15 @@ KBUILD_CFLAGS += $(call cc-disable-warning, pointer-sign)
 # disable invalid "can't wrap" optimizations for signed / pointers
 KBUILD_CFLAGS	+= $(call cc-option,-fno-strict-overflow)
 
+# clang sets -fmerge-all-constants by default as optimization, but this
+# is non-conforming behavior for C and in fact breaks the kernel, so we
+# need to disable it here generally.
+KBUILD_CFLAGS	+= $(call cc-option,-fno-merge-all-constants)
+
+# for gcc -fno-merge-all-constants disables everything, but it is fine
+# to have actual conforming behavior enabled.
+KBUILD_CFLAGS	+= $(call cc-option,-fmerge-constants)
+
 # Make sure -fstack-check isn't enabled (like gentoo apparently did)
 KBUILD_CFLAGS  += $(call cc-option,-fno-stack-check,)
 

arch/arm/mach-orion5x/Kconfig

@@ -58,7 +58,6 @@ config MACH_KUROBOX_PRO
 
 config MACH_DNS323
 	bool "D-Link DNS-323"
-	select GENERIC_NET_UTILS
 	select I2C_BOARDINFO if I2C
 	help
 	  Say 'Y' here if you want your kernel to support the
@@ -66,7 +65,6 @@ config MACH_DNS323
 
 config MACH_TS209
 	bool "QNAP TS-109/TS-209"
-	select GENERIC_NET_UTILS
 	help
 	  Say 'Y' here if you want your kernel to support the
 	  QNAP TS-109/TS-209 platform.
@@ -101,7 +99,6 @@ config MACH_LINKSTATION_LS_HGL
 
 config MACH_TS409
 	bool "QNAP TS-409"
-	select GENERIC_NET_UTILS
 	help
 	  Say 'Y' here if you want your kernel to support the
 	  QNAP TS-409 platform.

arch/arm/mach-orion5x/dns323-setup.c

@@ -173,10 +173,42 @@ static struct mv643xx_eth_platform_data dns323_eth_data = {
 	.phy_addr = MV643XX_ETH_PHY_ADDR(8),
 };
 
+/* dns323_parse_hex_*() taken from tsx09-common.c; should a common copy of these
+ * functions be kept somewhere?
+ */
+static int __init dns323_parse_hex_nibble(char n)
+{
+	if (n >= '0' && n <= '9')
+		return n - '0';
+
+	if (n >= 'A' && n <= 'F')
+		return n - 'A' + 10;
+
+	if (n >= 'a' && n <= 'f')
+		return n - 'a' + 10;
+
+	return -1;
+}
+
+static int __init dns323_parse_hex_byte(const char *b)
+{
+	int hi;
+	int lo;
+
+	hi = dns323_parse_hex_nibble(b[0]);
+	lo = dns323_parse_hex_nibble(b[1]);
+
+	if (hi < 0 || lo < 0)
+		return -1;
+
+	return (hi << 4) | lo;
+}
+
 static int __init dns323_read_mac_addr(void)
 {
 	u_int8_t addr[6];
-	void __iomem *mac_page;
+	int i;
+	char *mac_page;
 
 	/* MAC address is stored as a regular ol' string in /dev/mtdblock4
 	 * (0x007d0000-0x00800000) starting at offset 196480 (0x2ff80).
@@ -185,8 +217,23 @@ static int __init dns323_read_mac_addr(void)
 	if (!mac_page)
 		return -ENOMEM;
 
-	if (!mac_pton((__force const char *) mac_page, addr))
-		goto error_fail;
+	/* Sanity check the string we're looking at */
+	for (i = 0; i < 5; i++) {
+		if (*(mac_page + (i * 3) + 2) != ':') {
+			goto error_fail;
+		}
+	}
+
+	for (i = 0; i < 6; i++)	{
+		int byte;
+
+		byte = dns323_parse_hex_byte(mac_page + (i * 3));
+		if (byte < 0) {
+			goto error_fail;
+		}
+
+		addr[i] = byte;
+	}
 
 	iounmap(mac_page);
 	printk("DNS-323: Found ethernet MAC address: %pM\n", addr);

arch/arm/mach-orion5x/tsx09-common.c

@@ -53,12 +53,53 @@ struct mv643xx_eth_platform_data qnap_tsx09_eth_data = {
 	.phy_addr	= MV643XX_ETH_PHY_ADDR(8),
 };
 
+static int __init qnap_tsx09_parse_hex_nibble(char n)
+{
+	if (n >= '0' && n <= '9')
+		return n - '0';
+
+	if (n >= 'A' && n <= 'F')
+		return n - 'A' + 10;
+
+	if (n >= 'a' && n <= 'f')
+		return n - 'a' + 10;
+
+	return -1;
+}
+
+static int __init qnap_tsx09_parse_hex_byte(const char *b)
+{
+	int hi;
+	int lo;
+
+	hi = qnap_tsx09_parse_hex_nibble(b[0]);
+	lo = qnap_tsx09_parse_hex_nibble(b[1]);
+
+	if (hi < 0 || lo < 0)
+		return -1;
+
+	return (hi << 4) | lo;
+}
+
 static int __init qnap_tsx09_check_mac_addr(const char *addr_str)
 {
 	u_int8_t addr[6];
+	int i;
 
-	if (!mac_pton(addr_str, addr))
-		return -1;
+	for (i = 0; i < 6; i++) {
+		int byte;
+
+		/*
+		 * Enforce "xx:xx:xx:xx:xx:xx\n" format.
+		 */
+		if (addr_str[(i * 3) + 2] != ((i < 5) ? ':' : '\n'))
+			return -1;
+
+		byte = qnap_tsx09_parse_hex_byte(addr_str + (i * 3));
+		if (byte < 0)
+			return -1;
+		addr[i] = byte;
+	}
 
 	printk(KERN_INFO "tsx09: found ethernet mac address %pM\n", addr);
 
@@ -77,12 +118,12 @@ void __init qnap_tsx09_find_mac_addr(u32 mem_base, u32 size)
 	unsigned long addr;
 
 	for (addr = mem_base; addr < (mem_base + size); addr += 1024) {
-		void __iomem *nor_page;
+		char *nor_page;
 		int ret = 0;
 
 		nor_page = ioremap(addr, 1024);
 		if (nor_page != NULL) {
-			ret = qnap_tsx09_check_mac_addr((__force const char *)nor_page);
+			ret = qnap_tsx09_check_mac_addr(nor_page);
 			iounmap(nor_page);
 		}
 

arch/arm64/kernel/cpu_errata.c

@@ -178,7 +178,7 @@ static int enable_smccc_arch_workaround_1(void *data)
 	case PSCI_CONDUIT_HVC:
 		arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
 				  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
-		if (res.a0)
+		if ((int)res.a0 < 0)
 			return 0;
 		cb = call_hvc_arch_workaround_1;
 		smccc_start = __smccc_workaround_1_hvc_start;
@@ -188,7 +188,7 @@ static int enable_smccc_arch_workaround_1(void *data)
 	case PSCI_CONDUIT_SMC:
 		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
 				  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
-		if (res.a0)
+		if ((int)res.a0 < 0)
 			return 0;
 		cb = call_smc_arch_workaround_1;
 		smccc_start = __smccc_workaround_1_smc_start;

arch/arm64/kvm/guest.c

@@ -363,8 +363,6 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 {
 	int ret = 0;
 
-	vcpu_load(vcpu);
-
 	trace_kvm_set_guest_debug(vcpu, dbg->control);
 
 	if (dbg->control & ~KVM_GUESTDBG_VALID_MASK) {
@@ -386,7 +384,6 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 	}
 
 out:
-	vcpu_put(vcpu);
 	return ret;
 }
 

arch/arm64/mm/mmu.c

@@ -108,7 +108,7 @@ static bool pgattr_change_is_safe(u64 old, u64 new)
 	 * The following mapping attributes may be updated in live
 	 * kernel mappings without the need for break-before-make.
 	 */
-	static const pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE;
+	static const pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE | PTE_NG;
 
 	/* creating or taking down mappings is always safe */
 	if (old == 0 || new == 0)
@@ -118,9 +118,9 @@ static bool pgattr_change_is_safe(u64 old, u64 new)
 	if ((old | new) & PTE_CONT)
 		return false;
 
-	/* Transitioning from Global to Non-Global is safe */
-	if (((old ^ new) == PTE_NG) && (new & PTE_NG))
-		return true;
+	/* Transitioning from Non-Global to Global is unsafe */
+	if (old & ~new & PTE_NG)
+		return false;
 
 	return ((old ^ new) & ~mask) == 0;
 }
@@ -972,3 +972,13 @@ int pmd_clear_huge(pmd_t *pmdp)
 	pmd_clear(pmdp);
 	return 1;
 }
+
+int pud_free_pmd_page(pud_t *pud)
+{
+	return pud_none(*pud);
+}
+
+int pmd_free_pte_page(pmd_t *pmd)
+{
+	return pmd_none(*pmd);
+}

arch/h8300/include/asm/byteorder.h

@@ -2,7 +2,6 @@
 #ifndef __H8300_BYTEORDER_H__
 #define __H8300_BYTEORDER_H__
 
-#define __BIG_ENDIAN __ORDER_BIG_ENDIAN__
 #include <linux/byteorder/big_endian.h>
 
 #endif

arch/ia64/include/asm/atomic.h

@@ -66,38 +66,35 @@ ATOMIC_OPS(add, +)
 ATOMIC_OPS(sub, -)
 
 #ifdef __OPTIMIZE__
-#define __ia64_atomic_const(i)	__builtin_constant_p(i) ?		\
+#define __ia64_atomic_const(i)						\
+	static const int __ia64_atomic_p = __builtin_constant_p(i) ?	\
 		((i) == 1 || (i) == 4 || (i) == 8 || (i) == 16 ||	\
-		 (i) == -1 || (i) == -4 || (i) == -8 || (i) == -16) : 0
+		 (i) == -1 || (i) == -4 || (i) == -8 || (i) == -16) : 0;\
+	__ia64_atomic_p
+#else
+#define __ia64_atomic_const(i)	0
+#endif
 
-#define atomic_add_return(i, v)						\
+#define atomic_add_return(i,v)						\
 ({									\
-	int __i = (i);							\
-	static const int __ia64_atomic_p = __ia64_atomic_const(i);	\
-	__ia64_atomic_p ? ia64_fetch_and_add(__i, &(v)->counter) :	\
-				ia64_atomic_add(__i, v);		\
+	int __ia64_aar_i = (i);						\
+	__ia64_atomic_const(i)						\
+		? ia64_fetch_and_add(__ia64_aar_i, &(v)->counter)	\
+		: ia64_atomic_add(__ia64_aar_i, v);			\
 })
 
-#define atomic_sub_return(i, v)						\
+#define atomic_sub_return(i,v)						\
 ({									\
-	int __i = (i);							\
-	static const int __ia64_atomic_p = __ia64_atomic_const(i);	\
-	__ia64_atomic_p ? ia64_fetch_and_add(-__i, &(v)->counter) :	\
-				ia64_atomic_sub(__i, v);		\
+	int __ia64_asr_i = (i);						\
+	__ia64_atomic_const(i)						\
+		? ia64_fetch_and_add(-__ia64_asr_i, &(v)->counter)	\
+		: ia64_atomic_sub(__ia64_asr_i, v);			\
 })
-#else
-#define atomic_add_return(i, v)	ia64_atomic_add(i, v)
-#define atomic_sub_return(i, v)	ia64_atomic_sub(i, v)
-#endif
 
 #define atomic_fetch_add(i,v)						\
 ({									\
 	int __ia64_aar_i = (i);						\
-	(__builtin_constant_p(i)					\
-	 && (   (__ia64_aar_i ==  1) || (__ia64_aar_i ==   4)		\
-	     || (__ia64_aar_i ==  8) || (__ia64_aar_i ==  16)		\
-	     || (__ia64_aar_i == -1) || (__ia64_aar_i ==  -4)		\
-	     || (__ia64_aar_i == -8) || (__ia64_aar_i == -16)))		\
+	__ia64_atomic_const(i)						\
 		? ia64_fetchadd(__ia64_aar_i, &(v)->counter, acq)	\
 		: ia64_atomic_fetch_add(__ia64_aar_i, v);		\
 })
@@ -105,11 +102,7 @@ ATOMIC_OPS(sub, -)
 #define atomic_fetch_sub(i,v)						\
 ({									\
 	int __ia64_asr_i = (i);						\
-	(__builtin_constant_p(i)					\
-	 && (   (__ia64_asr_i ==   1) || (__ia64_asr_i ==   4)		\
-	     || (__ia64_asr_i ==   8) || (__ia64_asr_i ==  16)		\
-	     || (__ia64_asr_i ==  -1) || (__ia64_asr_i ==  -4)		\
-	     || (__ia64_asr_i ==  -8) || (__ia64_asr_i == -16)))	\
+	__ia64_atomic_const(i)						\
 		? ia64_fetchadd(-__ia64_asr_i, &(v)->counter, acq)	\
 		: ia64_atomic_fetch_sub(__ia64_asr_i, v);		\
 })
@@ -170,11 +163,7 @@ ATOMIC64_OPS(sub, -)
 #define atomic64_add_return(i,v)					\
 ({									\
 	long __ia64_aar_i = (i);					\
-	(__builtin_constant_p(i)					\
-	 && (   (__ia64_aar_i ==  1) || (__ia64_aar_i ==   4)		\
-	     || (__ia64_aar_i ==  8) || (__ia64_aar_i ==  16)		\
-	     || (__ia64_aar_i == -1) || (__ia64_aar_i ==  -4)		\
-	     || (__ia64_aar_i == -8) || (__ia64_aar_i == -16)))		\
+	__ia64_atomic_const(i)						\
 		? ia64_fetch_and_add(__ia64_aar_i, &(v)->counter)	\
 		: ia64_atomic64_add(__ia64_aar_i, v);			\
 })
@@ -182,11 +171,7 @@ ATOMIC64_OPS(sub, -)
 #define atomic64_sub_return(i,v)					\
 ({									\
 	long __ia64_asr_i = (i);					\
-	(__builtin_constant_p(i)					\
-	 && (   (__ia64_asr_i ==   1) || (__ia64_asr_i ==   4)		\
-	     || (__ia64_asr_i ==   8) || (__ia64_asr_i ==  16)		\
-	     || (__ia64_asr_i ==  -1) || (__ia64_asr_i ==  -4)		\
-	     || (__ia64_asr_i ==  -8) || (__ia64_asr_i == -16)))	\
+	__ia64_atomic_const(i)						\
 		? ia64_fetch_and_add(-__ia64_asr_i, &(v)->counter)	\
 		: ia64_atomic64_sub(__ia64_asr_i, v);			\
 })
@@ -194,11 +179,7 @@ ATOMIC64_OPS(sub, -)
 #define atomic64_fetch_add(i,v)						\
 ({									\
 	long __ia64_aar_i = (i);					\
-	(__builtin_constant_p(i)					\
-	 && (   (__ia64_aar_i ==  1) || (__ia64_aar_i ==   4)		\
-	     || (__ia64_aar_i ==  8) || (__ia64_aar_i ==  16)		\
-	     || (__ia64_aar_i == -1) || (__ia64_aar_i ==  -4)		\
-	     || (__ia64_aar_i == -8) || (__ia64_aar_i == -16)))		\
+	__ia64_atomic_const(i)						\
 		? ia64_fetchadd(__ia64_aar_i, &(v)->counter, acq)	\
 		: ia64_atomic64_fetch_add(__ia64_aar_i, v);		\
 })
@@ -206,11 +187,7 @@ ATOMIC64_OPS(sub, -)
 #define atomic64_fetch_sub(i,v)						\
 ({									\
 	long __ia64_asr_i = (i);					\
-	(__builtin_constant_p(i)					\
-	 && (   (__ia64_asr_i ==   1) || (__ia64_asr_i ==   4)		\
-	     || (__ia64_asr_i ==   8) || (__ia64_asr_i ==  16)		\
-	     || (__ia64_asr_i ==  -1) || (__ia64_asr_i ==  -4)		\
-	     || (__ia64_asr_i ==  -8) || (__ia64_asr_i == -16)))	\
+	__ia64_atomic_const(i)						\
 		? ia64_fetchadd(-__ia64_asr_i, &(v)->counter, acq)	\
 		: ia64_atomic64_fetch_sub(__ia64_asr_i, v);		\
 })

arch/ia64/kernel/err_inject.c

@@ -117,7 +117,7 @@ store_call_start(struct device *dev, struct device_attribute *attr,
 
 #ifdef ERR_INJ_DEBUG
 	printk(KERN_DEBUG "Returns: status=%d,\n", (int)status[cpu]);
-	printk(KERN_DEBUG "capapbilities=%lx,\n", capabilities[cpu]);
+	printk(KERN_DEBUG "capabilities=%lx,\n", capabilities[cpu]);
 	printk(KERN_DEBUG "resources=%lx\n", resources[cpu]);
 #endif
 	return size;
@@ -142,7 +142,7 @@ store_virtual_to_phys(struct device *dev, struct device_attribute *attr,
 	u64 virt_addr=simple_strtoull(buf, NULL, 16);
 	int ret;
 
-	ret = get_user_pages(virt_addr, 1, FOLL_WRITE, NULL, NULL);
+	ret = get_user_pages_fast(virt_addr, 1, FOLL_WRITE, NULL);
 	if (ret<=0) {
 #ifdef ERR_INJ_DEBUG
 		printk("Virtual address %lx is not existing.\n",virt_addr);

arch/ia64/scripts/unwcheck.py

@@ -16,7 +16,7 @@ import re
 import sys
 
 if len(sys.argv) != 2:
-    print "Usage: %s FILE" % sys.argv[0]
+    print("Usage: %s FILE" % sys.argv[0])
     sys.exit(2)
 
 readelf = os.getenv("READELF", "readelf")
@@ -29,7 +29,7 @@ def check_func (func, slots, rlen_sum):
         global num_errors
         num_errors += 1
         if not func: func = "[%#x-%#x]" % (start, end)
-        print "ERROR: %s: %lu slots, total region length = %lu" % (func, slots, rlen_sum)
+        print("ERROR: %s: %lu slots, total region length = %lu" % (func, slots, rlen_sum))
     return
 
 num_funcs = 0
@@ -43,23 +43,23 @@ for line in os.popen("%s -u %s" % (readelf, sys.argv[1])):
         check_func(func, slots, rlen_sum)
 
         func  = m.group(1)
-        start = long(m.group(2), 16)
-        end   = long(m.group(3), 16)
+        start = int(m.group(2), 16)
+        end   = int(m.group(3), 16)
         slots = 3 * (end - start) / 16
-        rlen_sum = 0L
+        rlen_sum = 0
         num_funcs += 1
     else:
         m = rlen_pattern.match(line)
         if m:
-            rlen_sum += long(m.group(1))
+            rlen_sum += int(m.group(1))
 check_func(func, slots, rlen_sum)
 
 if num_errors == 0:
-    print "No errors detected in %u functions." % num_funcs
+    print("No errors detected in %u functions." % num_funcs)
 else:
     if num_errors > 1:
         err="errors"
     else:
         err="error"
-    print "%u %s detected in %u functions." % (num_errors, err, num_funcs)
+    print("%u %s detected in %u functions." % (num_errors, err, num_funcs))
     sys.exit(1)

arch/microblaze/Kconfig

@@ -24,6 +24,7 @@ config MICROBLAZE
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER
+	select NO_BOOTMEM
 	select HAVE_MEMBLOCK
 	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_OPROFILE

arch/microblaze/Kconfig.platform

@@ -8,7 +8,6 @@ menu "Platform options"
 
 config OPT_LIB_FUNCTION
 	bool "Optimalized lib function"
-	depends on CPU_LITTLE_ENDIAN
 	default y
 	help
 	  Allows turn on optimalized library function (memcpy and memmove).
@@ -21,6 +20,7 @@ config OPT_LIB_FUNCTION
 config OPT_LIB_ASM
 	bool "Optimalized lib function ASM"
 	depends on OPT_LIB_FUNCTION && (XILINX_MICROBLAZE0_USE_BARREL = 1)
+	depends on CPU_BIG_ENDIAN
 	default n
 	help
 	  Allows turn on optimalized library function (memcpy and memmove).

arch/microblaze/include/asm/setup.h

@@ -44,7 +44,6 @@ void machine_shutdown(void);
 void machine_halt(void);
 void machine_power_off(void);
 
-extern void *alloc_maybe_bootmem(size_t size, gfp_t mask);
 extern void *zalloc_maybe_bootmem(size_t size, gfp_t mask);
 
 # endif /* __ASSEMBLY__ */

arch/microblaze/lib/fastcopy.S

@@ -29,10 +29,6 @@
  *	between mem locations with size of xfer spec'd in bytes
  */
 
-#ifdef __MICROBLAZEEL__
-#error Microblaze LE not support ASM optimized lib func. Disable OPT_LIB_ASM.
-#endif
-
 #include <linux/linkage.h>
 	.text
 	.globl	memcpy

arch/microblaze/mm/init.c

@@ -32,9 +32,6 @@ int mem_init_done;
 #ifndef CONFIG_MMU
 unsigned int __page_offset;
 EXPORT_SYMBOL(__page_offset);
-
-#else
-static int init_bootmem_done;
 #endif /* CONFIG_MMU */
 
 char *klimit = _end;
@@ -117,7 +114,6 @@ static void __init paging_init(void)
 
 void __init setup_memory(void)
 {
-	unsigned long map_size;
 	struct memblock_region *reg;
 
 #ifndef CONFIG_MMU
@@ -174,17 +170,6 @@ void __init setup_memory(void)
 	pr_info("%s: max_low_pfn: %#lx\n", __func__, max_low_pfn);
 	pr_info("%s: max_pfn: %#lx\n", __func__, max_pfn);
 
-	/*
-	 * Find an area to use for the bootmem bitmap.
-	 * We look for the first area which is at least
-	 * 128kB in length (128kB is enough for a bitmap
-	 * for 4GB of memory, using 4kB pages), plus 1 page
-	 * (in case the address isn't page-aligned).
-	 */
-	map_size = init_bootmem_node(NODE_DATA(0),
-		PFN_UP(TOPHYS((u32)klimit)), min_low_pfn, max_low_pfn);
-	memblock_reserve(PFN_UP(TOPHYS((u32)klimit)) << PAGE_SHIFT, map_size);
-
 	/* Add active regions with valid PFNs */
 	for_each_memblock(memory, reg) {
 		unsigned long start_pfn, end_pfn;
@@ -196,32 +181,9 @@ void __init setup_memory(void)
 				  &memblock.memory, 0);
 	}
 
-	/* free bootmem is whole main memory */
-	free_bootmem_with_active_regions(0, max_low_pfn);
-
-	/* reserve allocate blocks */
-	for_each_memblock(reserved, reg) {
-		unsigned long top = reg->base + reg->size - 1;
-
-		pr_debug("reserved - 0x%08x-0x%08x, %lx, %lx\n",
-			 (u32) reg->base, (u32) reg->size, top,
-						memory_start + lowmem_size - 1);
-
-		if (top <= (memory_start + lowmem_size - 1)) {
-			reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT);
-		} else if (reg->base < (memory_start + lowmem_size - 1)) {
-			unsigned long trunc_size = memory_start + lowmem_size -
-								reg->base;
-			reserve_bootmem(reg->base, trunc_size, BOOTMEM_DEFAULT);
-		}
-	}
-
 	/* XXX need to clip this if using highmem? */
 	sparse_memory_present_with_active_regions(0);
 
-#ifdef CONFIG_MMU
-	init_bootmem_done = 1;
-#endif
 	paging_init();
 }
 
@@ -398,30 +360,16 @@ asmlinkage void __init mmu_init(void)
 /* This is only called until mem_init is done. */
 void __init *early_get_page(void)
 {
-	void *p;
-	if (init_bootmem_done) {
-		p = alloc_bootmem_pages(PAGE_SIZE);
-	} else {
-		/*
-		 * Mem start + kernel_tlb -> here is limit
-		 * because of mem mapping from head.S
-		 */
-		p = __va(memblock_alloc_base(PAGE_SIZE, PAGE_SIZE,
-					memory_start + kernel_tlb));
-	}
-	return p;
+	/*
+	 * Mem start + kernel_tlb -> here is limit
+	 * because of mem mapping from head.S
+	 */
+	return __va(memblock_alloc_base(PAGE_SIZE, PAGE_SIZE,
+				memory_start + kernel_tlb));
 }
 
 #endif /* CONFIG_MMU */
 
-void * __ref alloc_maybe_bootmem(size_t size, gfp_t mask)
-{
-	if (mem_init_done)
-		return kmalloc(size, mask);
-	else
-		return alloc_bootmem(size);
-}
-
 void * __ref zalloc_maybe_bootmem(size_t size, gfp_t mask)
 {
 	void *p;

arch/mips/ath25/board.c

@@ -135,6 +135,8 @@ int __init ath25_find_config(phys_addr_t base, unsigned long size)
 	}
 
 	board_data = kzalloc(BOARD_CONFIG_BUFSZ, GFP_KERNEL);
+	if (!board_data)
+		goto error;
 	ath25_board.config = (struct ath25_boarddata *)board_data;
 	memcpy_fromio(board_data, bcfg, 0x100);
 	if (broken_boarddata) {

arch/mips/cavium-octeon/octeon-irq.c

@@ -2277,6 +2277,8 @@ static int __init octeon_irq_init_cib(struct device_node *ciu_node,
 	}
 
 	host_data = kzalloc(sizeof(*host_data), GFP_KERNEL);
+	if (!host_data)
+		return -ENOMEM;
 	raw_spin_lock_init(&host_data->lock);
 
 	addr = of_get_address(ciu_node, 0, NULL, NULL);

arch/mips/kernel/smp-bmips.c

@@ -168,11 +168,11 @@ static void bmips_prepare_cpus(unsigned int max_cpus)
 		return;
 	}
 
-	if (request_irq(IPI0_IRQ, bmips_ipi_interrupt, IRQF_PERCPU,
-			"smp_ipi0", NULL))
+	if (request_irq(IPI0_IRQ, bmips_ipi_interrupt,
+			IRQF_PERCPU | IRQF_NO_SUSPEND, "smp_ipi0", NULL))
 		panic("Can't request IPI0 interrupt");
-	if (request_irq(IPI1_IRQ, bmips_ipi_interrupt, IRQF_PERCPU,
-			"smp_ipi1", NULL))
+	if (request_irq(IPI1_IRQ, bmips_ipi_interrupt,
+			IRQF_PERCPU | IRQF_NO_SUSPEND, "smp_ipi1", NULL))
 		panic("Can't request IPI1 interrupt");
 }
 

arch/mips/lantiq/Kconfig

@@ -13,6 +13,8 @@ choice
 config SOC_AMAZON_SE
 	bool "Amazon SE"
 	select SOC_TYPE_XWAY
+	select MFD_SYSCON
+	select MFD_CORE
 
 config SOC_XWAY
 	bool "XWAY"

arch/mips/lantiq/xway/sysctrl.c

@@ -549,9 +549,9 @@ void __init ltq_soc_init(void)
 		clkdev_add_static(ltq_ar9_cpu_hz(), ltq_ar9_fpi_hz(),
 				ltq_ar9_fpi_hz(), CLOCK_250M);
 		clkdev_add_pmu("1f203018.usb2-phy", "phy", 1, 0, PMU_USB0_P);
-		clkdev_add_pmu("1e101000.usb", "otg", 1, 0, PMU_USB0);
+		clkdev_add_pmu("1e101000.usb", "otg", 1, 0, PMU_USB0 | PMU_AHBM);
 		clkdev_add_pmu("1f203034.usb2-phy", "phy", 1, 0, PMU_USB1_P);
-		clkdev_add_pmu("1e106000.usb", "otg", 1, 0, PMU_USB1);
+		clkdev_add_pmu("1e106000.usb", "otg", 1, 0, PMU_USB1 | PMU_AHBM);
 		clkdev_add_pmu("1e180000.etop", "switch", 1, 0, PMU_SWITCH);
 		clkdev_add_pmu("1e103000.sdio", NULL, 1, 0, PMU_SDIO);
 		clkdev_add_pmu("1e103100.deu", NULL, 1, 0, PMU_DEU);
@@ -560,7 +560,7 @@ void __init ltq_soc_init(void)
 	} else {
 		clkdev_add_static(ltq_danube_cpu_hz(), ltq_danube_fpi_hz(),
 				ltq_danube_fpi_hz(), ltq_danube_pp32_hz());
-		clkdev_add_pmu("1f203018.usb2-phy", "ctrl", 1, 0, PMU_USB0);
+		clkdev_add_pmu("1e101000.usb", "otg", 1, 0, PMU_USB0 | PMU_AHBM);
 		clkdev_add_pmu("1f203018.usb2-phy", "phy", 1, 0, PMU_USB0_P);
 		clkdev_add_pmu("1e103000.sdio", NULL, 1, 0, PMU_SDIO);
 		clkdev_add_pmu("1e103100.deu", NULL, 1, 0, PMU_DEU);

arch/mips/loongson64/Kconfig

@@ -7,6 +7,8 @@ choice
 config LEMOTE_FULOONG2E
 	bool "Lemote Fuloong(2e) mini-PC"
 	select ARCH_SPARSEMEM_ENABLE
+	select ARCH_MIGHT_HAVE_PC_PARPORT
+	select ARCH_MIGHT_HAVE_PC_SERIO
 	select CEVT_R4K
 	select CSRC_R4K
 	select SYS_HAS_CPU_LOONGSON2E
@@ -33,6 +35,8 @@ config LEMOTE_FULOONG2E
 config LEMOTE_MACH2F
 	bool "Lemote Loongson 2F family machines"
 	select ARCH_SPARSEMEM_ENABLE
+	select ARCH_MIGHT_HAVE_PC_PARPORT
+	select ARCH_MIGHT_HAVE_PC_SERIO
 	select BOARD_SCACHE
 	select BOOT_ELF32
 	select CEVT_R4K if ! MIPS_EXTERNAL_TIMER
@@ -62,6 +66,8 @@ config LEMOTE_MACH2F
 config LOONGSON_MACH3X
 	bool "Generic Loongson 3 family machines"
 	select ARCH_SPARSEMEM_ENABLE
+	select ARCH_MIGHT_HAVE_PC_PARPORT
+	select ARCH_MIGHT_HAVE_PC_SERIO
 	select GENERIC_ISA_DMA_SUPPORT_BROKEN
 	select BOOT_ELF32
 	select BOARD_SCACHE

arch/mips/ralink/mt7621.c

@@ -170,6 +170,28 @@ void prom_soc_init(struct ralink_soc_info *soc_info)
 	u32 n1;
 	u32 rev;
 
+	/* Early detection of CMP support */
+	mips_cm_probe();
+	mips_cpc_probe();
+
+	if (mips_cps_numiocu(0)) {
+		/*
+		 * mips_cm_probe() wipes out bootloader
+		 * config for CM regions and we have to configure them
+		 * again. This SoC cannot talk to pamlbus devices
+		 * witout proper iocu region set up.
+		 *
+		 * FIXME: it would be better to do this with values
+		 * from DT, but we need this very early because
+		 * without this we cannot talk to pretty much anything
+		 * including serial.
+		 */
+		write_gcr_reg0_base(MT7621_PALMBUS_BASE);
+		write_gcr_reg0_mask(~MT7621_PALMBUS_SIZE |
+				    CM_GCR_REGn_MASK_CMTGT_IOCU0);
+		__sync();
+	}
+
 	n0 = __raw_readl(sysc + SYSC_REG_CHIP_NAME0);
 	n1 = __raw_readl(sysc + SYSC_REG_CHIP_NAME1);
 
@@ -194,26 +216,6 @@ void prom_soc_init(struct ralink_soc_info *soc_info)
 
 	rt2880_pinmux_data = mt7621_pinmux_data;
 
-	/* Early detection of CMP support */
-	mips_cm_probe();
-	mips_cpc_probe();
-
-	if (mips_cps_numiocu(0)) {
-		/*
-		 * mips_cm_probe() wipes out bootloader
-		 * config for CM regions and we have to configure them
-		 * again. This SoC cannot talk to pamlbus devices
-		 * witout proper iocu region set up.
-		 *
-		 * FIXME: it would be better to do this with values
-		 * from DT, but we need this very early because
-		 * without this we cannot talk to pretty much anything
-		 * including serial.
-		 */
-		write_gcr_reg0_base(MT7621_PALMBUS_BASE);
-		write_gcr_reg0_mask(~MT7621_PALMBUS_SIZE |
-				    CM_GCR_REGn_MASK_CMTGT_IOCU0);
-	}
 
 	if (!register_cps_smp_ops())
 		return;

arch/mips/ralink/reset.c

@@ -96,16 +96,9 @@ static void ralink_restart(char *command)
 	unreachable();
 }
 
-static void ralink_halt(void)
-{
-	local_irq_disable();
-	unreachable();
-}
-
 static int __init mips_reboot_setup(void)
 {
 	_machine_restart = ralink_restart;
-	_machine_halt = ralink_halt;
 
 	return 0;
 }

arch/parisc/kernel/cache.c

@@ -543,7 +543,8 @@ void flush_cache_mm(struct mm_struct *mm)
 	   rp3440, etc.  So, avoid it if the mm isn't too big.  */
 	if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
 	    mm_total_size(mm) >= parisc_cache_flush_threshold) {
-		flush_tlb_all();
+		if (mm->context)
+			flush_tlb_all();
 		flush_cache_all();
 		return;
 	}
@@ -571,6 +572,8 @@ void flush_cache_mm(struct mm_struct *mm)
 			pfn = pte_pfn(*ptep);
 			if (!pfn_valid(pfn))
 				continue;
+			if (unlikely(mm->context))
+				flush_tlb_page(vma, addr);
 			__flush_cache_page(vma, addr, PFN_PHYS(pfn));
 		}
 	}
@@ -579,26 +582,46 @@ void flush_cache_mm(struct mm_struct *mm)
 void flush_cache_range(struct vm_area_struct *vma,
 		unsigned long start, unsigned long end)
 {
+	pgd_t *pgd;
+	unsigned long addr;
+
 	if ((!IS_ENABLED(CONFIG_SMP) || !arch_irqs_disabled()) &&
 	    end - start >= parisc_cache_flush_threshold) {
-		flush_tlb_range(vma, start, end);
+		if (vma->vm_mm->context)
+			flush_tlb_range(vma, start, end);
 		flush_cache_all();
 		return;
 	}
 
-	flush_user_dcache_range_asm(start, end);
-	if (vma->vm_flags & VM_EXEC)
-		flush_user_icache_range_asm(start, end);
-	flush_tlb_range(vma, start, end);
+	if (vma->vm_mm->context == mfsp(3)) {
+		flush_user_dcache_range_asm(start, end);
+		if (vma->vm_flags & VM_EXEC)
+			flush_user_icache_range_asm(start, end);
+		flush_tlb_range(vma, start, end);
+		return;
+	}
+
+	pgd = vma->vm_mm->pgd;
+	for (addr = vma->vm_start; addr < vma->vm_end; addr += PAGE_SIZE) {
+		unsigned long pfn;
+		pte_t *ptep = get_ptep(pgd, addr);
+		if (!ptep)
+			continue;
+		pfn = pte_pfn(*ptep);
+		if (pfn_valid(pfn)) {
+			if (unlikely(vma->vm_mm->context))
+				flush_tlb_page(vma, addr);
+			__flush_cache_page(vma, addr, PFN_PHYS(pfn));
+		}
+	}
 }
 
 void
 flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn)
 {
-	BUG_ON(!vma->vm_mm->context);
-
 	if (pfn_valid(pfn)) {
-		flush_tlb_page(vma, vmaddr);
+		if (likely(vma->vm_mm->context))
+			flush_tlb_page(vma, vmaddr);
 		__flush_cache_page(vma, vmaddr, PFN_PHYS(pfn));
 	}
 }

arch/powerpc/boot/Makefile

@@ -101,7 +101,8 @@ $(addprefix $(obj)/,$(zlib-y)): \
 libfdt       := fdt.c fdt_ro.c fdt_wip.c fdt_sw.c fdt_rw.c fdt_strerror.c
 libfdtheader := fdt.h libfdt.h libfdt_internal.h
 
-$(addprefix $(obj)/,$(libfdt) libfdt-wrapper.o simpleboot.o epapr.o opal.o): \
+$(addprefix $(obj)/,$(libfdt) libfdt-wrapper.o simpleboot.o epapr.o opal.o \
+	treeboot-akebono.o treeboot-currituck.o treeboot-iss4xx.o): \
 	$(addprefix $(obj)/,$(libfdtheader))
 
 src-wlib-y := string.S crt0.S stdio.c decompress.c main.c \

arch/powerpc/kernel/prom_init.c

@@ -874,7 +874,6 @@ struct ibm_arch_vec __cacheline_aligned ibm_architecture_vec = {
 		.mmu = 0,
 		.hash_ext = 0,
 		.radix_ext = 0,
-		.byte22 = 0,
 	},
 
 	/* option vector 6: IBM PAPR hints */

arch/powerpc/kvm/book3s_64_mmu_radix.c

@@ -195,6 +195,12 @@ static void kvmppc_pte_free(pte_t *ptep)
 	kmem_cache_free(kvm_pte_cache, ptep);
 }
 
+/* Like pmd_huge() and pmd_large(), but works regardless of config options */
+static inline int pmd_is_leaf(pmd_t pmd)
+{
+	return !!(pmd_val(pmd) & _PAGE_PTE);
+}
+
 static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
 			     unsigned int level, unsigned long mmu_seq)
 {
@@ -219,7 +225,7 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
 	else
 		new_pmd = pmd_alloc_one(kvm->mm, gpa);
 
-	if (level == 0 && !(pmd && pmd_present(*pmd)))
+	if (level == 0 && !(pmd && pmd_present(*pmd) && !pmd_is_leaf(*pmd)))
 		new_ptep = kvmppc_pte_alloc();
 
 	/* Check if we might have been invalidated; let the guest retry if so */
@@ -244,12 +250,30 @@ static int kvmppc_create_pte(struct kvm *kvm, pte_t pte, unsigned long gpa,
 		new_pmd = NULL;
 	}
 	pmd = pmd_offset(pud, gpa);
-	if (pmd_large(*pmd)) {
-		/* Someone else has instantiated a large page here; retry */
-		ret = -EAGAIN;
-		goto out_unlock;
-	}
-	if (level == 1 && !pmd_none(*pmd)) {
+	if (pmd_is_leaf(*pmd)) {
+		unsigned long lgpa = gpa & PMD_MASK;
+
+		/*
+		 * If we raced with another CPU which has just put
+		 * a 2MB pte in after we saw a pte page, try again.
+		 */
+		if (level == 0 && !new_ptep) {
+			ret = -EAGAIN;
+			goto out_unlock;
+		}
+		/* Valid 2MB page here already, remove it */
+		old = kvmppc_radix_update_pte(kvm, pmdp_ptep(pmd),
+					      ~0UL, 0, lgpa, PMD_SHIFT);
+		kvmppc_radix_tlbie_page(kvm, lgpa, PMD_SHIFT);
+		if (old & _PAGE_DIRTY) {
+			unsigned long gfn = lgpa >> PAGE_SHIFT;
+			struct kvm_memory_slot *memslot;
+			memslot = gfn_to_memslot(kvm, gfn);
+			if (memslot && memslot->dirty_bitmap)
+				kvmppc_update_dirty_map(memslot,
+							gfn, PMD_SIZE);
+		}
+	} else if (level == 1 && !pmd_none(*pmd)) {
 		/*
 		 * There's a page table page here, but we wanted
 		 * to install a large page.  Tell the caller and let
@@ -412,28 +436,24 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	} else {
 		page = pages[0];
 		pfn = page_to_pfn(page);
-		if (PageHuge(page)) {
-			page = compound_head(page);
-			pte_size <<= compound_order(page);
+		if (PageCompound(page)) {
+			pte_size <<= compound_order(compound_head(page));
 			/* See if we can insert a 2MB large-page PTE here */
 			if (pte_size >= PMD_SIZE &&
-			    (gpa & PMD_MASK & PAGE_MASK) ==
-			    (hva & PMD_MASK & PAGE_MASK)) {
+			    (gpa & (PMD_SIZE - PAGE_SIZE)) ==
+			    (hva & (PMD_SIZE - PAGE_SIZE))) {
 				level = 1;
 				pfn &= ~((PMD_SIZE >> PAGE_SHIFT) - 1);
 			}
 		}
 		/* See if we can provide write access */
 		if (writing) {
-			/*
-			 * We assume gup_fast has set dirty on the host PTE.
-			 */
 			pgflags |= _PAGE_WRITE;
 		} else {
 			local_irq_save(flags);
 			ptep = find_current_mm_pte(current->mm->pgd,
 						   hva, NULL, NULL);
-			if (ptep && pte_write(*ptep) && pte_dirty(*ptep))
+			if (ptep && pte_write(*ptep))
 				pgflags |= _PAGE_WRITE;
 			local_irq_restore(flags);
 		}
@@ -459,18 +479,15 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		pte = pfn_pte(pfn, __pgprot(pgflags));
 		ret = kvmppc_create_pte(kvm, pte, gpa, level, mmu_seq);
 	}
-	if (ret == 0 || ret == -EAGAIN)
-		ret = RESUME_GUEST;
 
 	if (page) {
-		/*
-		 * We drop pages[0] here, not page because page might
-		 * have been set to the head page of a compound, but
-		 * we have to drop the reference on the correct tail
-		 * page to match the get inside gup()
-		 */
-		put_page(pages[0]);
+		if (!ret && (pgflags & _PAGE_WRITE))
+			set_page_dirty_lock(page);
+		put_page(page);
 	}
+
+	if (ret == 0 || ret == -EAGAIN)
+		ret = RESUME_GUEST;
 	return ret;
 }
 
@@ -644,7 +661,7 @@ void kvmppc_free_radix(struct kvm *kvm)
 				continue;
 			pmd = pmd_offset(pud, 0);
 			for (im = 0; im < PTRS_PER_PMD; ++im, ++pmd) {
-				if (pmd_huge(*pmd)) {
+				if (pmd_is_leaf(*pmd)) {
 					pmd_clear(pmd);
 					continue;
 				}

arch/powerpc/kvm/book3s_hv.c

@@ -2885,7 +2885,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	 */
 	trace_hardirqs_on();
 
-	guest_enter();
+	guest_enter_irqoff();
 
 	srcu_idx = srcu_read_lock(&vc->kvm->srcu);
 
@@ -2893,8 +2893,6 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 
 	srcu_read_unlock(&vc->kvm->srcu, srcu_idx);
 
-	guest_exit();
-
 	trace_hardirqs_off();
 	set_irq_happened(trap);
 
@@ -2937,6 +2935,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	kvmppc_set_host_core(pcpu);
 
 	local_irq_enable();
+	guest_exit();
 
 	/* Let secondaries go back to the offline loop */
 	for (i = 0; i < controlled_threads; ++i) {
@@ -3656,15 +3655,17 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 		goto up_out;
 
 	psize = vma_kernel_pagesize(vma);
-	porder = __ilog2(psize);
 
 	up_read(&current->mm->mmap_sem);
 
 	/* We can handle 4k, 64k or 16M pages in the VRMA */
-	err = -EINVAL;
-	if (!(psize == 0x1000 || psize == 0x10000 ||
-	      psize == 0x1000000))
-		goto out_srcu;
+	if (psize >= 0x1000000)
+		psize = 0x1000000;
+	else if (psize >= 0x10000)
+		psize = 0x10000;
+	else
+		psize = 0x1000;
+	porder = __ilog2(psize);
 
 	senc = slb_pgsize_encoding(psize);
 	kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T |

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -320,7 +320,6 @@ kvm_novcpu_exit:
 	stw	r12, STACK_SLOT_TRAP(r1)
 	bl	kvmhv_commence_exit
 	nop
-	lwz	r12, STACK_SLOT_TRAP(r1)
 	b	kvmhv_switch_to_host
 
 /*
@@ -1220,6 +1219,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 
 secondary_too_late:
 	li	r12, 0
+	stw	r12, STACK_SLOT_TRAP(r1)
 	cmpdi	r4, 0
 	beq	11f
 	stw	r12, VCPU_TRAP(r4)
@@ -1558,12 +1558,12 @@ mc_cont:
 3:	stw	r5,VCPU_SLB_MAX(r9)
 
 guest_bypass:
+	stw	r12, STACK_SLOT_TRAP(r1)
 	mr 	r3, r12
 	/* Increment exit count, poke other threads to exit */
 	bl	kvmhv_commence_exit
 	nop
 	ld	r9, HSTATE_KVM_VCPU(r13)
-	lwz	r12, VCPU_TRAP(r9)
 
 	/* Stop others sending VCPU interrupts to this physical CPU */
 	li	r0, -1
@@ -1898,6 +1898,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_POWER9_DD1)
 	 * POWER7/POWER8 guest -> host partition switch code.
 	 * We don't have to lock against tlbies but we do
 	 * have to coordinate the hardware threads.
+	 * Here STACK_SLOT_TRAP(r1) contains the trap number.
 	 */
 kvmhv_switch_to_host:
 	/* Secondary threads wait for primary to do partition switch */
@@ -1950,12 +1951,12 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 
 	/* If HMI, call kvmppc_realmode_hmi_handler() */
+	lwz	r12, STACK_SLOT_TRAP(r1)
 	cmpwi	r12, BOOK3S_INTERRUPT_HMI
 	bne	27f
 	bl	kvmppc_realmode_hmi_handler
 	nop
 	cmpdi	r3, 0
-	li	r12, BOOK3S_INTERRUPT_HMI
 	/*
 	 * At this point kvmppc_realmode_hmi_handler may have resync-ed
 	 * the TB, and if it has, we must not subtract the guest timebase
@@ -2008,10 +2009,8 @@ BEGIN_FTR_SECTION
 	lwz	r8, KVM_SPLIT_DO_RESTORE(r3)
 	cmpwi	r8, 0
 	beq	47f
-	stw	r12, STACK_SLOT_TRAP(r1)
 	bl	kvmhv_p9_restore_lpcr
 	nop
-	lwz	r12, STACK_SLOT_TRAP(r1)
 	b	48f
 47:
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
@@ -2049,6 +2048,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
 	li	r0, KVM_GUEST_MODE_NONE
 	stb	r0, HSTATE_IN_GUEST(r13)
 
+	lwz	r12, STACK_SLOT_TRAP(r1)	/* return trap # in r12 */
 	ld	r0, SFS+PPC_LR_STKOFF(r1)
 	addi	r1, r1, SFS
 	mtlr	r0

arch/powerpc/kvm/powerpc.c

@@ -1345,7 +1345,7 @@ static int kvmppc_emulate_mmio_vsx_loadstore(struct kvm_vcpu *vcpu,
 int kvmppc_handle_load128_by2x64(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		unsigned int rt, int is_default_endian)
 {
-	enum emulation_result emulated;
+	enum emulation_result emulated = EMULATE_DONE;
 
 	while (vcpu->arch.mmio_vmx_copy_nums) {
 		emulated = __kvmppc_handle_load(run, vcpu, rt, 8,
@@ -1608,7 +1608,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 	kvm_sigset_deactivate(vcpu);
 
+#ifdef CONFIG_ALTIVEC
 out:
+#endif
 	vcpu_put(vcpu);
 	return r;
 }

arch/powerpc/net/bpf_jit_comp64.c

@@ -240,6 +240,7 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32
 	 *   goto out;
 	 */
 	PPC_LWZ(b2p[TMP_REG_1], b2p_bpf_array, offsetof(struct bpf_array, map.max_entries));
+	PPC_RLWINM(b2p_index, b2p_index, 0, 0, 31);
 	PPC_CMPLW(b2p_index, b2p[TMP_REG_1]);
 	PPC_BCC(COND_GE, out);
 

arch/s390/include/asm/mmu_context.h

@@ -63,6 +63,7 @@ static inline int init_new_context(struct task_struct *tsk,
 				   _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT;
 		/* pgd_alloc() did not account this pmd */
 		mm_inc_nr_pmds(mm);
+		mm_inc_nr_puds(mm);
 	}
 	crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm));
 	return 0;

arch/s390/kernel/entry.S

@@ -14,6 +14,7 @@
 #include <asm/processor.h>
 #include <asm/cache.h>
 #include <asm/ctl_reg.h>
+#include <asm/dwarf.h>
 #include <asm/errno.h>
 #include <asm/ptrace.h>
 #include <asm/thread_info.h>
@@ -230,7 +231,7 @@ _PIF_WORK	= (_PIF_PER_TRAP | _PIF_SYSCALL_RESTART)
 	.hidden \name
 	.type \name,@function
 \name:
-	.cfi_startproc
+	CFI_STARTPROC
 #ifdef CONFIG_HAVE_MARCH_Z10_FEATURES
 	exrl	0,0f
 #else
@@ -239,7 +240,7 @@ _PIF_WORK	= (_PIF_PER_TRAP | _PIF_SYSCALL_RESTART)
 #endif
 	j	.
 0:	br	\reg
-	.cfi_endproc
+	CFI_ENDPROC
 	.endm
 
 	GEN_BR_THUNK __s390x_indirect_jump_r1use_r9,%r9,%r1
@@ -426,13 +427,13 @@ ENTRY(system_call)
 	UPDATE_VTIME %r8,%r9,__LC_SYNC_ENTER_TIMER
 	BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP
 	stmg	%r0,%r7,__PT_R0(%r11)
-	# clear user controlled register to prevent speculative use
-	xgr	%r0,%r0
 	mvc	__PT_R8(64,%r11),__LC_SAVE_AREA_SYNC
 	mvc	__PT_PSW(16,%r11),__LC_SVC_OLD_PSW
 	mvc	__PT_INT_CODE(4,%r11),__LC_SVC_ILC
 	stg	%r14,__PT_FLAGS(%r11)
 .Lsysc_do_svc:
+	# clear user controlled register to prevent speculative use
+	xgr	%r0,%r0
 	# load address of system call table
 	lg	%r10,__THREAD_sysc_table(%r13,%r12)
 	llgh	%r8,__PT_INT_CODE+2(%r11)
@@ -1439,6 +1440,7 @@ cleanup_critical:
 	stg	%r15,__LC_SYSTEM_TIMER
 0:	# update accounting time stamp
 	mvc	__LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER
+	BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP
 	# set up saved register r11
 	lg	%r15,__LC_KERNEL_STACK
 	la	%r9,STACK_FRAME_OVERHEAD(%r15)

arch/s390/kernel/nospec-branch.c

@@ -2,8 +2,8 @@
 #include <linux/module.h>
 #include <asm/nospec-branch.h>
 
-int nospec_call_disable = IS_ENABLED(EXPOLINE_OFF);
-int nospec_return_disable = !IS_ENABLED(EXPOLINE_FULL);
+int nospec_call_disable = IS_ENABLED(CONFIG_EXPOLINE_OFF);
+int nospec_return_disable = !IS_ENABLED(CONFIG_EXPOLINE_FULL);
 
 static int __init nospectre_v2_setup_early(char *str)
 {

arch/s390/kvm/kvm-s390.c

@@ -86,6 +86,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "deliver_prefix_signal", VCPU_STAT(deliver_prefix_signal) },
 	{ "deliver_restart_signal", VCPU_STAT(deliver_restart_signal) },
 	{ "deliver_program_interruption", VCPU_STAT(deliver_program_int) },
+	{ "deliver_io_interrupt", VCPU_STAT(deliver_io_int) },
 	{ "exit_wait_state", VCPU_STAT(exit_wait_state) },
 	{ "instruction_epsw", VCPU_STAT(instruction_epsw) },
 	{ "instruction_gs", VCPU_STAT(instruction_gs) },
@@ -2146,6 +2147,7 @@ static void sca_add_vcpu(struct kvm_vcpu *vcpu)
 		/* we still need the basic sca for the ipte control */
 		vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32);
 		vcpu->arch.sie_block->scaol = (__u32)(__u64)sca;
+		return;
 	}
 	read_lock(&vcpu->kvm->arch.sca_lock);
 	if (vcpu->kvm->arch.use_esca) {

arch/sparc/mm/tlb.c

@@ -163,13 +163,10 @@ static void tlb_batch_pmd_scan(struct mm_struct *mm, unsigned long vaddr,
 	pte_unmap(pte);
 }
 
-void set_pmd_at(struct mm_struct *mm, unsigned long addr,
-		pmd_t *pmdp, pmd_t pmd)
-{
-	pmd_t orig = *pmdp;
-
-	*pmdp = pmd;
 
+static void __set_pmd_acct(struct mm_struct *mm, unsigned long addr,
+			   pmd_t orig, pmd_t pmd)
+{
 	if (mm == &init_mm)
 		return;
 
@@ -219,6 +216,15 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 	}
 }
 
+void set_pmd_at(struct mm_struct *mm, unsigned long addr,
+		pmd_t *pmdp, pmd_t pmd)
+{
+	pmd_t orig = *pmdp;
+
+	*pmdp = pmd;
+	__set_pmd_acct(mm, addr, orig, pmd);
+}
+
 static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
 		unsigned long address, pmd_t *pmdp, pmd_t pmd)
 {
@@ -227,6 +233,7 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
 	do {
 		old = *pmdp;
 	} while (cmpxchg64(&pmdp->pmd, old.pmd, pmd.pmd) != old.pmd);
+	__set_pmd_acct(vma->vm_mm, address, old, pmd);
 
 	return old;
 }

arch/x86/Kconfig

@@ -2307,7 +2307,7 @@ choice
 	  it can be used to assist security vulnerability exploitation.
 
 	  This setting can be changed at boot time via the kernel command
-	  line parameter vsyscall=[native|emulate|none].
+	  line parameter vsyscall=[emulate|none].
 
 	  On a system with recent enough glibc (2.14 or newer) and no
 	  static binaries, you can say None without a performance penalty
@@ -2315,15 +2315,6 @@ choice
 
 	  If unsure, select "Emulate".
 
-	config LEGACY_VSYSCALL_NATIVE
-		bool "Native"
-		help
-		  Actual executable code is located in the fixed vsyscall
-		  address mapping, implementing time() efficiently. Since
-		  this makes the mapping executable, it can be used during
-		  security vulnerability exploitation (traditionally as
-		  ROP gadgets). This configuration is not recommended.
-
 	config LEGACY_VSYSCALL_EMULATE
 		bool "Emulate"
 		help

arch/x86/Kconfig.cpu

@@ -315,19 +315,6 @@ config X86_L1_CACHE_SHIFT
 	default "4" if MELAN || M486 || MGEODEGX1
 	default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX
 
-config X86_PPRO_FENCE
-	bool "PentiumPro memory ordering errata workaround"
-	depends on M686 || M586MMX || M586TSC || M586 || M486 || MGEODEGX1
-	---help---
-	  Old PentiumPro multiprocessor systems had errata that could cause
-	  memory operations to violate the x86 ordering standard in rare cases.
-	  Enabling this option will attempt to work around some (but not all)
-	  occurrences of this problem, at the cost of much heavier spinlock and
-	  memory barrier operations.
-
-	  If unsure, say n here. Even distro kernels should think twice before
-	  enabling this: there are few systems, and an unlikely bug.
-
 config X86_F00F_BUG
 	def_bool y
 	depends on M586MMX || M586TSC || M586 || M486

arch/x86/Makefile

@@ -223,6 +223,15 @@ KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr)
 
 LDFLAGS := -m elf_$(UTS_MACHINE)
 
+#
+# The 64-bit kernel must be aligned to 2MB.  Pass -z max-page-size=0x200000 to
+# the linker to force 2MB page size regardless of the default page size used
+# by the linker.
+#
+ifdef CONFIG_X86_64
+LDFLAGS += $(call ld-option, -z max-page-size=0x200000)
+endif
+
 # Speed up the build
 KBUILD_CFLAGS += -pipe
 # Workaround for a gcc prelease that unfortunately was shipped in a suse release

arch/x86/boot/compressed/misc.c

@@ -309,6 +309,10 @@ static void parse_elf(void *output)
 
 		switch (phdr->p_type) {
 		case PT_LOAD:
+#ifdef CONFIG_X86_64
+			if ((phdr->p_align % 0x200000) != 0)
+				error("Alignment of LOAD segment isn't multiple of 2MB");
+#endif
 #ifdef CONFIG_RELOCATABLE
 			dest = output;
 			dest += (phdr->p_paddr - LOAD_PHYSICAL_ADDR);

arch/x86/entry/entry_64.S

@@ -1141,7 +1141,7 @@ apicinterrupt3 HYPERV_STIMER0_VECTOR \
 #endif /* CONFIG_HYPERV */
 
 idtentry debug			do_debug		has_error_code=0	paranoid=1 shift_ist=DEBUG_STACK
-idtentry int3			do_int3			has_error_code=0	paranoid=1 shift_ist=DEBUG_STACK
+idtentry int3			do_int3			has_error_code=0
 idtentry stack_segment		do_stack_segment	has_error_code=1
 
 #ifdef CONFIG_XEN

arch/x86/entry/entry_64_compat.S

@@ -363,9 +363,7 @@ ENTRY(entry_INT80_compat)
 	pushq	2*8(%rdi)		/* regs->ip */
 	pushq	1*8(%rdi)		/* regs->orig_ax */
 
-	movq	(%rdi), %rdi		/* restore %rdi */
-
-	pushq	%rdi			/* pt_regs->di */
+	pushq	(%rdi)			/* pt_regs->di */
 	pushq	%rsi			/* pt_regs->si */
 	pushq	%rdx			/* pt_regs->dx */
 	pushq	%rcx			/* pt_regs->cx */
@@ -406,15 +404,3 @@ ENTRY(entry_INT80_compat)
 	TRACE_IRQS_ON
 	jmp	swapgs_restore_regs_and_return_to_usermode
 END(entry_INT80_compat)
-
-ENTRY(stub32_clone)
-	/*
-	 * The 32-bit clone ABI is: clone(..., int tls_val, int *child_tidptr).
-	 * The 64-bit clone ABI is: clone(..., int *child_tidptr, int tls_val).
-	 *
-	 * The native 64-bit kernel's sys_clone() implements the latter,
-	 * so we need to swap arguments here before calling it:
-	 */
-	xchg	%r8, %rcx
-	jmp	sys_clone
-ENDPROC(stub32_clone)

arch/x86/entry/syscalls/syscall_32.tbl

@@ -8,12 +8,12 @@
 #
 0	i386	restart_syscall		sys_restart_syscall
 1	i386	exit			sys_exit
-2	i386	fork			sys_fork			sys_fork
+2	i386	fork			sys_fork
 3	i386	read			sys_read
 4	i386	write			sys_write
 5	i386	open			sys_open			compat_sys_open
 6	i386	close			sys_close
-7	i386	waitpid			sys_waitpid			sys32_waitpid
+7	i386	waitpid			sys_waitpid			compat_sys_x86_waitpid
 8	i386	creat			sys_creat
 9	i386	link			sys_link
 10	i386	unlink			sys_unlink
@@ -78,7 +78,7 @@
 69	i386	ssetmask		sys_ssetmask
 70	i386	setreuid		sys_setreuid16
 71	i386	setregid		sys_setregid16
-72	i386	sigsuspend		sys_sigsuspend			sys_sigsuspend
+72	i386	sigsuspend		sys_sigsuspend
 73	i386	sigpending		sys_sigpending			compat_sys_sigpending
 74	i386	sethostname		sys_sethostname
 75	i386	setrlimit		sys_setrlimit			compat_sys_setrlimit
@@ -96,7 +96,7 @@
 87	i386	swapon			sys_swapon
 88	i386	reboot			sys_reboot
 89	i386	readdir			sys_old_readdir			compat_sys_old_readdir
-90	i386	mmap			sys_old_mmap			sys32_mmap
+90	i386	mmap			sys_old_mmap			compat_sys_x86_mmap
 91	i386	munmap			sys_munmap
 92	i386	truncate		sys_truncate			compat_sys_truncate
 93	i386	ftruncate		sys_ftruncate			compat_sys_ftruncate
@@ -126,7 +126,7 @@
 117	i386	ipc			sys_ipc				compat_sys_ipc
 118	i386	fsync			sys_fsync
 119	i386	sigreturn		sys_sigreturn			sys32_sigreturn
-120	i386	clone			sys_clone			stub32_clone
+120	i386	clone			sys_clone			compat_sys_x86_clone
 121	i386	setdomainname		sys_setdomainname
 122	i386	uname			sys_newuname
 123	i386	modify_ldt		sys_modify_ldt
@@ -186,8 +186,8 @@
 177	i386	rt_sigtimedwait		sys_rt_sigtimedwait		compat_sys_rt_sigtimedwait
 178	i386	rt_sigqueueinfo		sys_rt_sigqueueinfo		compat_sys_rt_sigqueueinfo
 179	i386	rt_sigsuspend		sys_rt_sigsuspend
-180	i386	pread64			sys_pread64			sys32_pread
-181	i386	pwrite64		sys_pwrite64			sys32_pwrite
+180	i386	pread64			sys_pread64			compat_sys_x86_pread
+181	i386	pwrite64		sys_pwrite64			compat_sys_x86_pwrite
 182	i386	chown			sys_chown16
 183	i386	getcwd			sys_getcwd
 184	i386	capget			sys_capget
@@ -196,14 +196,14 @@
 187	i386	sendfile		sys_sendfile			compat_sys_sendfile
 188	i386	getpmsg
 189	i386	putpmsg
-190	i386	vfork			sys_vfork			sys_vfork
+190	i386	vfork			sys_vfork
 191	i386	ugetrlimit		sys_getrlimit			compat_sys_getrlimit
 192	i386	mmap2			sys_mmap_pgoff
-193	i386	truncate64		sys_truncate64			sys32_truncate64
-194	i386	ftruncate64		sys_ftruncate64			sys32_ftruncate64
-195	i386	stat64			sys_stat64			sys32_stat64
-196	i386	lstat64			sys_lstat64			sys32_lstat64
-197	i386	fstat64			sys_fstat64			sys32_fstat64
+193	i386	truncate64		sys_truncate64			compat_sys_x86_truncate64
+194	i386	ftruncate64		sys_ftruncate64			compat_sys_x86_ftruncate64
+195	i386	stat64			sys_stat64			compat_sys_x86_stat64
+196	i386	lstat64			sys_lstat64			compat_sys_x86_lstat64
+197	i386	fstat64			sys_fstat64			compat_sys_x86_fstat64
 198	i386	lchown32		sys_lchown
 199	i386	getuid32		sys_getuid
 200	i386	getgid32		sys_getgid
@@ -231,7 +231,7 @@
 # 222 is unused
 # 223 is unused
 224	i386	gettid			sys_gettid
-225	i386	readahead		sys_readahead			sys32_readahead
+225	i386	readahead		sys_readahead			compat_sys_x86_readahead
 226	i386	setxattr		sys_setxattr
 227	i386	lsetxattr		sys_lsetxattr
 228	i386	fsetxattr		sys_fsetxattr
@@ -256,7 +256,7 @@
 247	i386	io_getevents		sys_io_getevents		compat_sys_io_getevents
 248	i386	io_submit		sys_io_submit			compat_sys_io_submit
 249	i386	io_cancel		sys_io_cancel
-250	i386	fadvise64		sys_fadvise64			sys32_fadvise64
+250	i386	fadvise64		sys_fadvise64			compat_sys_x86_fadvise64
 # 251 is available for reuse (was briefly sys_set_zone_reclaim)
 252	i386	exit_group		sys_exit_group
 253	i386	lookup_dcookie		sys_lookup_dcookie		compat_sys_lookup_dcookie
@@ -278,7 +278,7 @@
 269	i386	fstatfs64		sys_fstatfs64			compat_sys_fstatfs64
 270	i386	tgkill			sys_tgkill
 271	i386	utimes			sys_utimes			compat_sys_utimes
-272	i386	fadvise64_64		sys_fadvise64_64		sys32_fadvise64_64
+272	i386	fadvise64_64		sys_fadvise64_64		compat_sys_x86_fadvise64_64
 273	i386	vserver
 274	i386	mbind			sys_mbind
 275	i386	get_mempolicy		sys_get_mempolicy		compat_sys_get_mempolicy
@@ -306,7 +306,7 @@
 297	i386	mknodat			sys_mknodat
 298	i386	fchownat		sys_fchownat
 299	i386	futimesat		sys_futimesat			compat_sys_futimesat
-300	i386	fstatat64		sys_fstatat64			sys32_fstatat
+300	i386	fstatat64		sys_fstatat64			compat_sys_x86_fstatat
 301	i386	unlinkat		sys_unlinkat
 302	i386	renameat		sys_renameat
 303	i386	linkat			sys_linkat
@@ -320,7 +320,7 @@
 311	i386	set_robust_list		sys_set_robust_list		compat_sys_set_robust_list
 312	i386	get_robust_list		sys_get_robust_list		compat_sys_get_robust_list
 313	i386	splice			sys_splice
-314	i386	sync_file_range		sys_sync_file_range		sys32_sync_file_range
+314	i386	sync_file_range		sys_sync_file_range		compat_sys_x86_sync_file_range
 315	i386	tee			sys_tee
 316	i386	vmsplice		sys_vmsplice			compat_sys_vmsplice
 317	i386	move_pages		sys_move_pages			compat_sys_move_pages
@@ -330,7 +330,7 @@
 321	i386	signalfd		sys_signalfd			compat_sys_signalfd
 322	i386	timerfd_create		sys_timerfd_create
 323	i386	eventfd			sys_eventfd
-324	i386	fallocate		sys_fallocate			sys32_fallocate
+324	i386	fallocate		sys_fallocate			compat_sys_x86_fallocate
 325	i386	timerfd_settime		sys_timerfd_settime		compat_sys_timerfd_settime
 326	i386	timerfd_gettime		sys_timerfd_gettime		compat_sys_timerfd_gettime
 327	i386	signalfd4		sys_signalfd4			compat_sys_signalfd4

arch/x86/entry/vdso/vdso32/vclock_gettime.c

@@ -5,8 +5,6 @@
 #undef CONFIG_OPTIMIZE_INLINING
 #endif
 
-#undef CONFIG_X86_PPRO_FENCE
-
 #ifdef CONFIG_X86_64
 
 /*

arch/x86/entry/vsyscall/vsyscall_64.c

@@ -42,10 +42,8 @@
 #define CREATE_TRACE_POINTS
 #include "vsyscall_trace.h"
 
-static enum { EMULATE, NATIVE, NONE } vsyscall_mode =
-#if defined(CONFIG_LEGACY_VSYSCALL_NATIVE)
-	NATIVE;
-#elif defined(CONFIG_LEGACY_VSYSCALL_NONE)
+static enum { EMULATE, NONE } vsyscall_mode =
+#ifdef CONFIG_LEGACY_VSYSCALL_NONE
 	NONE;
 #else
 	EMULATE;
@@ -56,8 +54,6 @@ static int __init vsyscall_setup(char *str)
 	if (str) {
 		if (!strcmp("emulate", str))
 			vsyscall_mode = EMULATE;
-		else if (!strcmp("native", str))
-			vsyscall_mode = NATIVE;
 		else if (!strcmp("none", str))
 			vsyscall_mode = NONE;
 		else
@@ -139,10 +135,6 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
 
 	WARN_ON_ONCE(address != regs->ip);
 
-	/* This should be unreachable in NATIVE mode. */
-	if (WARN_ON(vsyscall_mode == NATIVE))
-		return false;
-
 	if (vsyscall_mode == NONE) {
 		warn_bad_vsyscall(KERN_INFO, regs,
 				  "vsyscall attempted with vsyscall=none");
@@ -355,7 +347,7 @@ void __init set_vsyscall_pgtable_user_bits(pgd_t *root)
 	set_pgd(pgd, __pgd(pgd_val(*pgd) | _PAGE_USER));
 	p4d = p4d_offset(pgd, VSYSCALL_ADDR);
 #if CONFIG_PGTABLE_LEVELS >= 5
-	p4d->p4d |= _PAGE_USER;
+	set_p4d(p4d, __p4d(p4d_val(*p4d) | _PAGE_USER));
 #endif
 	pud = pud_offset(p4d, VSYSCALL_ADDR);
 	set_pud(pud, __pud(pud_val(*pud) | _PAGE_USER));
@@ -370,9 +362,7 @@ void __init map_vsyscall(void)
 
 	if (vsyscall_mode != NONE) {
 		__set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall,
-			     vsyscall_mode == NATIVE
-			     ? PAGE_KERNEL_VSYSCALL
-			     : PAGE_KERNEL_VVAR);
+			     PAGE_KERNEL_VVAR);
 		set_vsyscall_pgtable_user_bits(swapper_pg_dir);
 	}
 

arch/x86/events/core.c

@@ -2118,7 +2118,8 @@ static int x86_pmu_event_init(struct perf_event *event)
 			event->destroy(event);
 	}
 
-	if (READ_ONCE(x86_pmu.attr_rdpmc))
+	if (READ_ONCE(x86_pmu.attr_rdpmc) &&
+	    !(event->hw.flags & PERF_X86_EVENT_LARGE_PEBS))
 		event->hw.flags |= PERF_X86_EVENT_RDPMC_ALLOWED;
 
 	return err;

arch/x86/events/intel/core.c

@@ -2952,9 +2952,9 @@ static void intel_pebs_aliases_skl(struct perf_event *event)
 	return intel_pebs_aliases_precdist(event);
 }
 
-static unsigned long intel_pmu_free_running_flags(struct perf_event *event)
+static unsigned long intel_pmu_large_pebs_flags(struct perf_event *event)
 {
-	unsigned long flags = x86_pmu.free_running_flags;
+	unsigned long flags = x86_pmu.large_pebs_flags;
 
 	if (event->attr.use_clockid)
 		flags &= ~PERF_SAMPLE_TIME;
@@ -2976,8 +2976,8 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		if (!event->attr.freq) {
 			event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
 			if (!(event->attr.sample_type &
-			      ~intel_pmu_free_running_flags(event)))
-				event->hw.flags |= PERF_X86_EVENT_FREERUNNING;
+			      ~intel_pmu_large_pebs_flags(event)))
+				event->hw.flags |= PERF_X86_EVENT_LARGE_PEBS;
 		}
 		if (x86_pmu.pebs_aliases)
 			x86_pmu.pebs_aliases(event);
@@ -3194,7 +3194,7 @@ static unsigned bdw_limit_period(struct perf_event *event, unsigned left)
 			X86_CONFIG(.event=0xc0, .umask=0x01)) {
 		if (left < 128)
 			left = 128;
-		left &= ~0x3fu;
+		left &= ~0x3fULL;
 	}
 	return left;
 }
@@ -3460,7 +3460,7 @@ static __initconst const struct x86_pmu core_pmu = {
 	.event_map		= intel_pmu_event_map,
 	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
 	.apic			= 1,
-	.free_running_flags	= PEBS_FREERUNNING_FLAGS,
+	.large_pebs_flags	= LARGE_PEBS_FLAGS,
 
 	/*
 	 * Intel PMCs cannot be accessed sanely above 32-bit width,
@@ -3502,7 +3502,7 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.event_map		= intel_pmu_event_map,
 	.max_events		= ARRAY_SIZE(intel_perfmon_event_map),
 	.apic			= 1,
-	.free_running_flags	= PEBS_FREERUNNING_FLAGS,
+	.large_pebs_flags	= LARGE_PEBS_FLAGS,
 	/*
 	 * Intel PMCs cannot be accessed sanely above 32 bit width,
 	 * so we install an artificial 1<<31 period regardless of

arch/x86/events/intel/ds.c

@@ -935,7 +935,7 @@ void intel_pmu_pebs_add(struct perf_event *event)
 	bool needed_cb = pebs_needs_sched_cb(cpuc);
 
 	cpuc->n_pebs++;
-	if (hwc->flags & PERF_X86_EVENT_FREERUNNING)
+	if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
 		cpuc->n_large_pebs++;
 
 	pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
@@ -975,7 +975,7 @@ void intel_pmu_pebs_del(struct perf_event *event)
 	bool needed_cb = pebs_needs_sched_cb(cpuc);
 
 	cpuc->n_pebs--;
-	if (hwc->flags & PERF_X86_EVENT_FREERUNNING)
+	if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
 		cpuc->n_large_pebs--;
 
 	pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
@@ -1530,7 +1530,7 @@ void __init intel_ds_init(void)
 			x86_pmu.pebs_record_size =
 						sizeof(struct pebs_record_skl);
 			x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm;
-			x86_pmu.free_running_flags |= PERF_SAMPLE_TIME;
+			x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME;
 			break;
 
 		default:

arch/x86/events/intel/uncore_snbep.c

@@ -3343,6 +3343,7 @@ static struct extra_reg skx_uncore_cha_extra_regs[] = {
 	SNBEP_CBO_EVENT_EXTRA_REG(0x9134, 0xffff, 0x4),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x35, 0xff, 0x8),
 	SNBEP_CBO_EVENT_EXTRA_REG(0x36, 0xff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x38, 0xff, 0x3),
 	EVENT_EXTRA_END
 };
 
@@ -3562,24 +3563,27 @@ static struct intel_uncore_type *skx_msr_uncores[] = {
 	NULL,
 };
 
+/*
+ * To determine the number of CHAs, it should read bits 27:0 in the CAPID6
+ * register which located at Device 30, Function 3, Offset 0x9C. PCI ID 0x2083.
+ */
+#define SKX_CAPID6		0x9c
+#define SKX_CHA_BIT_MASK	GENMASK(27, 0)
+
 static int skx_count_chabox(void)
 {
-	struct pci_dev *chabox_dev = NULL;
-	int bus, count = 0;
+	struct pci_dev *dev = NULL;
+	u32 val = 0;
 
-	while (1) {
-		chabox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x208d, chabox_dev);
-		if (!chabox_dev)
-			break;
-		if (count == 0)
-			bus = chabox_dev->bus->number;
-		if (bus != chabox_dev->bus->number)
-			break;
-		count++;
-	}
+	dev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x2083, dev);
+	if (!dev)
+		goto out;
 
-	pci_dev_put(chabox_dev);
-	return count;
+	pci_read_config_dword(dev, SKX_CAPID6, &val);
+	val &= SKX_CHA_BIT_MASK;
+out:
+	pci_dev_put(dev);
+	return hweight32(val);
 }
 
 void skx_uncore_cpu_init(void)
@@ -3606,7 +3610,7 @@ static struct intel_uncore_type skx_uncore_imc = {
 };
 
 static struct attribute *skx_upi_uncore_formats_attr[] = {
-	&format_attr_event_ext.attr,
+	&format_attr_event.attr,
 	&format_attr_umask_ext.attr,
 	&format_attr_edge.attr,
 	&format_attr_inv.attr,

arch/x86/events/perf_event.h

@@ -69,7 +69,7 @@ struct event_constraint {
 #define PERF_X86_EVENT_RDPMC_ALLOWED	0x0100 /* grant rdpmc permission */
 #define PERF_X86_EVENT_EXCL_ACCT	0x0200 /* accounted EXCL event */
 #define PERF_X86_EVENT_AUTO_RELOAD	0x0400 /* use PEBS auto-reload */
-#define PERF_X86_EVENT_FREERUNNING	0x0800 /* use freerunning PEBS */
+#define PERF_X86_EVENT_LARGE_PEBS	0x0800 /* use large PEBS */
 
 
 struct amd_nb {
@@ -88,7 +88,7 @@ struct amd_nb {
  * REGS_USER can be handled for events limited to ring 3.
  *
  */
-#define PEBS_FREERUNNING_FLAGS \
+#define LARGE_PEBS_FLAGS \
 	(PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \
 	PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \
 	PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \
@@ -608,7 +608,7 @@ struct x86_pmu {
 	struct event_constraint *pebs_constraints;
 	void		(*pebs_aliases)(struct perf_event *event);
 	int 		max_pebs_events;
-	unsigned long	free_running_flags;
+	unsigned long	large_pebs_flags;
 
 	/*
 	 * Intel LBR

arch/x86/ia32/sys_ia32.c

@@ -51,15 +51,14 @@
 #define AA(__x)		((unsigned long)(__x))
 
 
-asmlinkage long sys32_truncate64(const char __user *filename,
-				 unsigned long offset_low,
-				 unsigned long offset_high)
+COMPAT_SYSCALL_DEFINE3(x86_truncate64, const char __user *, filename,
+		       unsigned long, offset_low, unsigned long, offset_high)
 {
        return sys_truncate(filename, ((loff_t) offset_high << 32) | offset_low);
 }
 
-asmlinkage long sys32_ftruncate64(unsigned int fd, unsigned long offset_low,
-				  unsigned long offset_high)
+COMPAT_SYSCALL_DEFINE3(x86_ftruncate64, unsigned int, fd,
+		       unsigned long, offset_low, unsigned long, offset_high)
 {
        return sys_ftruncate(fd, ((loff_t) offset_high << 32) | offset_low);
 }
@@ -96,8 +95,8 @@ static int cp_stat64(struct stat64 __user *ubuf, struct kstat *stat)
 	return 0;
 }
 
-asmlinkage long sys32_stat64(const char __user *filename,
-			     struct stat64 __user *statbuf)
+COMPAT_SYSCALL_DEFINE2(x86_stat64, const char __user *, filename,
+		       struct stat64 __user *, statbuf)
 {
 	struct kstat stat;
 	int ret = vfs_stat(filename, &stat);
@@ -107,8 +106,8 @@ asmlinkage long sys32_stat64(const char __user *filename,
 	return ret;
 }
 
-asmlinkage long sys32_lstat64(const char __user *filename,
-			      struct stat64 __user *statbuf)
+COMPAT_SYSCALL_DEFINE2(x86_lstat64, const char __user *, filename,
+		       struct stat64 __user *, statbuf)
 {
 	struct kstat stat;
 	int ret = vfs_lstat(filename, &stat);
@@ -117,7 +116,8 @@ asmlinkage long sys32_lstat64(const char __user *filename,
 	return ret;
 }
 
-asmlinkage long sys32_fstat64(unsigned int fd, struct stat64 __user *statbuf)
+COMPAT_SYSCALL_DEFINE2(x86_fstat64, unsigned int, fd,
+		       struct stat64 __user *, statbuf)
 {
 	struct kstat stat;
 	int ret = vfs_fstat(fd, &stat);
@@ -126,8 +126,9 @@ asmlinkage long sys32_fstat64(unsigned int fd, struct stat64 __user *statbuf)
 	return ret;
 }
 
-asmlinkage long sys32_fstatat(unsigned int dfd, const char __user *filename,
-			      struct stat64 __user *statbuf, int flag)
+COMPAT_SYSCALL_DEFINE4(x86_fstatat, unsigned int, dfd,
+		       const char __user *, filename,
+		       struct stat64 __user *, statbuf, int, flag)
 {
 	struct kstat stat;
 	int error;
@@ -153,7 +154,7 @@ struct mmap_arg_struct32 {
 	unsigned int offset;
 };
 
-asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *arg)
+COMPAT_SYSCALL_DEFINE1(x86_mmap, struct mmap_arg_struct32 __user *, arg)
 {
 	struct mmap_arg_struct32 a;
 
@@ -167,22 +168,22 @@ asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *arg)
 			       a.offset>>PAGE_SHIFT);
 }
 
-asmlinkage long sys32_waitpid(compat_pid_t pid, unsigned int __user *stat_addr,
-			      int options)
+COMPAT_SYSCALL_DEFINE3(x86_waitpid, compat_pid_t, pid, unsigned int __user *,
+		       stat_addr, int, options)
 {
 	return compat_sys_wait4(pid, stat_addr, options, NULL);
 }
 
 /* warning: next two assume little endian */
-asmlinkage long sys32_pread(unsigned int fd, char __user *ubuf, u32 count,
-			    u32 poslo, u32 poshi)
+COMPAT_SYSCALL_DEFINE5(x86_pread, unsigned int, fd, char __user *, ubuf,
+		       u32, count, u32, poslo, u32, poshi)
 {
 	return sys_pread64(fd, ubuf, count,
 			 ((loff_t)AA(poshi) << 32) | AA(poslo));
 }
 
-asmlinkage long sys32_pwrite(unsigned int fd, const char __user *ubuf,
-			     u32 count, u32 poslo, u32 poshi)
+COMPAT_SYSCALL_DEFINE5(x86_pwrite, unsigned int, fd, const char __user *, ubuf,
+		       u32, count, u32, poslo, u32, poshi)
 {
 	return sys_pwrite64(fd, ubuf, count,
 			  ((loff_t)AA(poshi) << 32) | AA(poslo));
@@ -193,8 +194,9 @@ asmlinkage long sys32_pwrite(unsigned int fd, const char __user *ubuf,
  * Some system calls that need sign extended arguments. This could be
  * done by a generic wrapper.
  */
-long sys32_fadvise64_64(int fd, __u32 offset_low, __u32 offset_high,
-			__u32 len_low, __u32 len_high, int advice)
+COMPAT_SYSCALL_DEFINE6(x86_fadvise64_64, int, fd, __u32, offset_low,
+		       __u32, offset_high, __u32, len_low, __u32, len_high,
+		       int, advice)
 {
 	return sys_fadvise64_64(fd,
 			       (((u64)offset_high)<<32) | offset_low,
@@ -202,31 +204,43 @@ long sys32_fadvise64_64(int fd, __u32 offset_low, __u32 offset_high,
 				advice);
 }
 
-asmlinkage ssize_t sys32_readahead(int fd, unsigned off_lo, unsigned off_hi,
-				   size_t count)
+COMPAT_SYSCALL_DEFINE4(x86_readahead, int, fd, unsigned int, off_lo,
+		       unsigned int, off_hi, size_t, count)
 {
 	return sys_readahead(fd, ((u64)off_hi << 32) | off_lo, count);
 }
 
-asmlinkage long sys32_sync_file_range(int fd, unsigned off_low, unsigned off_hi,
-				      unsigned n_low, unsigned n_hi,  int flags)
+COMPAT_SYSCALL_DEFINE6(x86_sync_file_range, int, fd, unsigned int, off_low,
+		       unsigned int, off_hi, unsigned int, n_low,
+		       unsigned int, n_hi, int, flags)
 {
 	return sys_sync_file_range(fd,
 				   ((u64)off_hi << 32) | off_low,
 				   ((u64)n_hi << 32) | n_low, flags);
 }
 
-asmlinkage long sys32_fadvise64(int fd, unsigned offset_lo, unsigned offset_hi,
-				size_t len, int advice)
+COMPAT_SYSCALL_DEFINE5(x86_fadvise64, int, fd, unsigned int, offset_lo,
+		       unsigned int, offset_hi, size_t, len, int, advice)
 {
 	return sys_fadvise64_64(fd, ((u64)offset_hi << 32) | offset_lo,
 				len, advice);
 }
 
-asmlinkage long sys32_fallocate(int fd, int mode, unsigned offset_lo,
-				unsigned offset_hi, unsigned len_lo,
-				unsigned len_hi)
+COMPAT_SYSCALL_DEFINE6(x86_fallocate, int, fd, int, mode,
+		       unsigned int, offset_lo, unsigned int, offset_hi,
+		       unsigned int, len_lo, unsigned int, len_hi)
 {
 	return sys_fallocate(fd, mode, ((u64)offset_hi << 32) | offset_lo,
 			     ((u64)len_hi << 32) | len_lo);
 }
+
+/*
+ * The 32-bit clone ABI is CONFIG_CLONE_BACKWARDS
+ */
+COMPAT_SYSCALL_DEFINE5(x86_clone, unsigned long, clone_flags,
+		       unsigned long, newsp, int __user *, parent_tidptr,
+		       unsigned long, tls_val, int __user *, child_tidptr)
+{
+	return sys_clone(clone_flags, newsp, parent_tidptr, child_tidptr,
+			tls_val);
+}

arch/x86/include/asm/barrier.h

@@ -52,11 +52,7 @@ static inline unsigned long array_index_mask_nospec(unsigned long index,
 #define barrier_nospec() alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, \
 					   "lfence", X86_FEATURE_LFENCE_RDTSC)
 
-#ifdef CONFIG_X86_PPRO_FENCE
-#define dma_rmb()	rmb()
-#else
 #define dma_rmb()	barrier()
-#endif
 #define dma_wmb()	barrier()
 
 #ifdef CONFIG_X86_32
@@ -68,30 +64,6 @@ static inline unsigned long array_index_mask_nospec(unsigned long index,
 #define __smp_wmb()	barrier()
 #define __smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0)
 
-#if defined(CONFIG_X86_PPRO_FENCE)
-
-/*
- * For this option x86 doesn't have a strong TSO memory
- * model and we should fall back to full barriers.
- */
-
-#define __smp_store_release(p, v)					\
-do {									\
-	compiletime_assert_atomic_type(*p);				\
-	__smp_mb();							\
-	WRITE_ONCE(*p, v);						\
-} while (0)
-
-#define __smp_load_acquire(p)						\
-({									\
-	typeof(*p) ___p1 = READ_ONCE(*p);				\
-	compiletime_assert_atomic_type(*p);				\
-	__smp_mb();							\
-	___p1;								\
-})
-
-#else /* regular x86 TSO memory ordering */
-
 #define __smp_store_release(p, v)					\
 do {									\
 	compiletime_assert_atomic_type(*p);				\
@@ -107,8 +79,6 @@ do {									\
 	___p1;								\
 })
 
-#endif
-
 /* Atomic operations are already serializing on x86 */
 #define __smp_mb__before_atomic()	barrier()
 #define __smp_mb__after_atomic()	barrier()

arch/x86/include/asm/cpufeatures.h

@@ -316,6 +316,7 @@
 #define X86_FEATURE_VPCLMULQDQ		(16*32+10) /* Carry-Less Multiplication Double Quadword */
 #define X86_FEATURE_AVX512_VNNI		(16*32+11) /* Vector Neural Network Instructions */
 #define X86_FEATURE_AVX512_BITALG	(16*32+12) /* Support for VPOPCNT[B,W] and VPSHUF-BITQMB instructions */
+#define X86_FEATURE_TME			(16*32+13) /* Intel Total Memory Encryption */
 #define X86_FEATURE_AVX512_VPOPCNTDQ	(16*32+14) /* POPCNT for vectors of DW/QW */
 #define X86_FEATURE_LA57		(16*32+16) /* 5-level page tables */
 #define X86_FEATURE_RDPID		(16*32+22) /* RDPID instruction */
@@ -328,6 +329,7 @@
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
 #define X86_FEATURE_AVX512_4VNNIW	(18*32+ 2) /* AVX-512 Neural Network Instructions */
 #define X86_FEATURE_AVX512_4FMAPS	(18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_ARCH_CAPABILITIES	(18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */

arch/x86/include/asm/io.h

@@ -232,21 +232,6 @@ extern void set_iounmap_nonlazy(void);
  */
 #define __ISA_IO_base ((char __iomem *)(PAGE_OFFSET))
 
-/*
- *	Cache management
- *
- *	This needed for two cases
- *	1. Out of order aware processors
- *	2. Accidentally out of order processors (PPro errata #51)
- */
-
-static inline void flush_write_buffers(void)
-{
-#if defined(CONFIG_X86_PPRO_FENCE)
-	asm volatile("lock; addl $0,0(%%esp)": : :"memory");
-#endif
-}
-
 #endif /* __KERNEL__ */
 
 extern void native_io_delay(void);

arch/x86/include/asm/microcode.h

@@ -39,6 +39,7 @@ struct device;
 
 enum ucode_state {
 	UCODE_OK	= 0,
+	UCODE_NEW,
 	UCODE_UPDATED,
 	UCODE_NFOUND,
 	UCODE_ERROR,

arch/x86/include/asm/nospec-branch.h

@@ -183,7 +183,10 @@
  * otherwise we'll run out of registers. We don't care about CET
  * here, anyway.
  */
-# define CALL_NOSPEC ALTERNATIVE("call *%[thunk_target]\n",	\
+# define CALL_NOSPEC						\
+	ALTERNATIVE(						\
+	ANNOTATE_RETPOLINE_SAFE					\
+	"call *%[thunk_target]\n",				\
 	"       jmp    904f;\n"					\
 	"       .align 16\n"					\
 	"901:	call   903f;\n"					\

arch/x86/include/asm/pgtable_types.h

@@ -174,7 +174,6 @@ enum page_cache_mode {
 #define __PAGE_KERNEL_RO		(__PAGE_KERNEL & ~_PAGE_RW)
 #define __PAGE_KERNEL_RX		(__PAGE_KERNEL_EXEC & ~_PAGE_RW)
 #define __PAGE_KERNEL_NOCACHE		(__PAGE_KERNEL | _PAGE_NOCACHE)
-#define __PAGE_KERNEL_VSYSCALL		(__PAGE_KERNEL_RX | _PAGE_USER)
 #define __PAGE_KERNEL_VVAR		(__PAGE_KERNEL_RO | _PAGE_USER)
 #define __PAGE_KERNEL_LARGE		(__PAGE_KERNEL | _PAGE_PSE)
 #define __PAGE_KERNEL_LARGE_EXEC	(__PAGE_KERNEL_EXEC | _PAGE_PSE)
@@ -206,7 +205,6 @@ enum page_cache_mode {
 #define PAGE_KERNEL_NOCACHE	__pgprot(__PAGE_KERNEL_NOCACHE | _PAGE_ENC)
 #define PAGE_KERNEL_LARGE	__pgprot(__PAGE_KERNEL_LARGE | _PAGE_ENC)
 #define PAGE_KERNEL_LARGE_EXEC	__pgprot(__PAGE_KERNEL_LARGE_EXEC | _PAGE_ENC)
-#define PAGE_KERNEL_VSYSCALL	__pgprot(__PAGE_KERNEL_VSYSCALL | _PAGE_ENC)
 #define PAGE_KERNEL_VVAR	__pgprot(__PAGE_KERNEL_VVAR | _PAGE_ENC)
 
 #define PAGE_KERNEL_IO		__pgprot(__PAGE_KERNEL_IO)

arch/x86/include/asm/sections.h

@@ -10,6 +10,7 @@ extern struct exception_table_entry __stop___ex_table[];
 
 #if defined(CONFIG_X86_64)
 extern char __end_rodata_hpage_align[];
+extern char __entry_trampoline_start[], __entry_trampoline_end[];
 #endif
 
 #endif	/* _ASM_X86_SECTIONS_H */

arch/x86/include/asm/sys_ia32.h

@@ -20,31 +20,43 @@
 #include <asm/ia32.h>
 
 /* ia32/sys_ia32.c */
-asmlinkage long sys32_truncate64(const char __user *, unsigned long, unsigned long);
-asmlinkage long sys32_ftruncate64(unsigned int, unsigned long, unsigned long);
+asmlinkage long compat_sys_x86_truncate64(const char __user *, unsigned long,
+					  unsigned long);
+asmlinkage long compat_sys_x86_ftruncate64(unsigned int, unsigned long,
+					   unsigned long);
 
-asmlinkage long sys32_stat64(const char __user *, struct stat64 __user *);
-asmlinkage long sys32_lstat64(const char __user *, struct stat64 __user *);
-asmlinkage long sys32_fstat64(unsigned int, struct stat64 __user *);
-asmlinkage long sys32_fstatat(unsigned int, const char __user *,
+asmlinkage long compat_sys_x86_stat64(const char __user *,
+				      struct stat64 __user *);
+asmlinkage long compat_sys_x86_lstat64(const char __user *,
+				       struct stat64 __user *);
+asmlinkage long compat_sys_x86_fstat64(unsigned int, struct stat64 __user *);
+asmlinkage long compat_sys_x86_fstatat(unsigned int, const char __user *,
 			      struct stat64 __user *, int);
 struct mmap_arg_struct32;
-asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *);
+asmlinkage long compat_sys_x86_mmap(struct mmap_arg_struct32 __user *);
 
-asmlinkage long sys32_waitpid(compat_pid_t, unsigned int __user *, int);
+asmlinkage long compat_sys_x86_waitpid(compat_pid_t, unsigned int __user *,
+				       int);
 
-asmlinkage long sys32_pread(unsigned int, char __user *, u32, u32, u32);
-asmlinkage long sys32_pwrite(unsigned int, const char __user *, u32, u32, u32);
+asmlinkage long compat_sys_x86_pread(unsigned int, char __user *, u32, u32,
+				     u32);
+asmlinkage long compat_sys_x86_pwrite(unsigned int, const char __user *, u32,
+				      u32, u32);
 
-long sys32_fadvise64_64(int, __u32, __u32, __u32, __u32, int);
-long sys32_vm86_warning(void);
+asmlinkage long compat_sys_x86_fadvise64_64(int, __u32, __u32, __u32, __u32,
+					    int);
 
-asmlinkage ssize_t sys32_readahead(int, unsigned, unsigned, size_t);
-asmlinkage long sys32_sync_file_range(int, unsigned, unsigned,
-				      unsigned, unsigned, int);
-asmlinkage long sys32_fadvise64(int, unsigned, unsigned, size_t, int);
-asmlinkage long sys32_fallocate(int, int, unsigned,
-				unsigned, unsigned, unsigned);
+asmlinkage ssize_t compat_sys_x86_readahead(int, unsigned int, unsigned int,
+					    size_t);
+asmlinkage long compat_sys_x86_sync_file_range(int, unsigned int, unsigned int,
+					       unsigned int, unsigned int,
+					       int);
+asmlinkage long compat_sys_x86_fadvise64(int, unsigned int, unsigned int,
+					 size_t, int);
+asmlinkage long compat_sys_x86_fallocate(int, int, unsigned int, unsigned int,
+					 unsigned int, unsigned int);
+asmlinkage long compat_sys_x86_clone(unsigned long, unsigned long, int __user *,
+				     unsigned long, int __user *);
 
 /* ia32/ia32_signal.c */
 asmlinkage long sys32_sigreturn(void);

arch/x86/include/asm/vmx.h

@@ -352,6 +352,7 @@ enum vmcs_field {
 #define INTR_TYPE_NMI_INTR		(2 << 8) /* NMI */
 #define INTR_TYPE_HARD_EXCEPTION	(3 << 8) /* processor exception */
 #define INTR_TYPE_SOFT_INTR             (4 << 8) /* software interrupt */
+#define INTR_TYPE_PRIV_SW_EXCEPTION	(5 << 8) /* ICE breakpoint - undocumented */
 #define INTR_TYPE_SOFT_EXCEPTION	(6 << 8) /* software exception */
 
 /* GUEST_INTERRUPTIBILITY_INFO flags. */

arch/x86/include/uapi/asm/mce.h

@@ -30,6 +30,7 @@ struct mce {
 	__u64 synd;	/* MCA_SYND MSR: only valid on SMCA systems */
 	__u64 ipid;	/* MCA_IPID MSR: only valid on SMCA systems */
 	__u64 ppin;	/* Protected Processor Inventory Number */
+	__u32 microcode;/* Microcode revision */
 };
 
 #define MCE_GET_RECORD_LEN   _IOR('M', 1, int)

arch/x86/kernel/cpu/intel.c

@@ -105,7 +105,7 @@ static void probe_xeon_phi_r3mwait(struct cpuinfo_x86 *c)
 /*
  * Early microcode releases for the Spectre v2 mitigation were broken.
  * Information taken from;
- * - https://newsroom.intel.com/wp-content/uploads/sites/11/2018/01/microcode-update-guidance.pdf
+ * - https://newsroom.intel.com/wp-content/uploads/sites/11/2018/03/microcode-update-guidance.pdf
  * - https://kb.vmware.com/s/article/52345
  * - Microcode revisions observed in the wild
  * - Release note from 20180108 microcode release
@@ -123,7 +123,6 @@ static const struct sku_microcode spectre_bad_microcodes[] = {
 	{ INTEL_FAM6_KABYLAKE_MOBILE,	0x09,	0x80 },
 	{ INTEL_FAM6_SKYLAKE_X,		0x03,	0x0100013e },
 	{ INTEL_FAM6_SKYLAKE_X,		0x04,	0x0200003c },
-	{ INTEL_FAM6_SKYLAKE_DESKTOP,	0x03,	0xc2 },
 	{ INTEL_FAM6_BROADWELL_CORE,	0x04,	0x28 },
 	{ INTEL_FAM6_BROADWELL_GT3E,	0x01,	0x1b },
 	{ INTEL_FAM6_BROADWELL_XEON_D,	0x02,	0x14 },
@@ -144,6 +143,13 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c)
 {
 	int i;
 
+	/*
+	 * We know that the hypervisor lie to us on the microcode version so
+	 * we may as well hope that it is running the correct version.
+	 */
+	if (cpu_has(c, X86_FEATURE_HYPERVISOR))
+		return false;
+
 	for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) {
 		if (c->x86_model == spectre_bad_microcodes[i].model &&
 		    c->x86_stepping == spectre_bad_microcodes[i].stepping)

arch/x86/kernel/cpu/mcheck/mce.c

@@ -56,6 +56,9 @@
 
 static DEFINE_MUTEX(mce_log_mutex);
 
+/* sysfs synchronization */
+static DEFINE_MUTEX(mce_sysfs_mutex);
+
 #define CREATE_TRACE_POINTS
 #include <trace/events/mce.h>
 
@@ -130,6 +133,8 @@ void mce_setup(struct mce *m)
 
 	if (this_cpu_has(X86_FEATURE_INTEL_PPIN))
 		rdmsrl(MSR_PPIN, m->ppin);
+
+	m->microcode = boot_cpu_data.microcode;
 }
 
 DEFINE_PER_CPU(struct mce, injectm);
@@ -262,7 +267,7 @@ static void __print_mce(struct mce *m)
 	 */
 	pr_emerg(HW_ERR "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x microcode %x\n",
 		m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid,
-		cpu_data(m->extcpu).microcode);
+		m->microcode);
 }
 
 static void print_mce(struct mce *m)
@@ -2086,6 +2091,7 @@ static ssize_t set_ignore_ce(struct device *s,
 	if (kstrtou64(buf, 0, &new) < 0)
 		return -EINVAL;
 
+	mutex_lock(&mce_sysfs_mutex);
 	if (mca_cfg.ignore_ce ^ !!new) {
 		if (new) {
 			/* disable ce features */
@@ -2098,6 +2104,8 @@ static ssize_t set_ignore_ce(struct device *s,
 			on_each_cpu(mce_enable_ce, (void *)1, 1);
 		}
 	}
+	mutex_unlock(&mce_sysfs_mutex);
+
 	return size;
 }
 
@@ -2110,6 +2118,7 @@ static ssize_t set_cmci_disabled(struct device *s,
 	if (kstrtou64(buf, 0, &new) < 0)
 		return -EINVAL;
 
+	mutex_lock(&mce_sysfs_mutex);
 	if (mca_cfg.cmci_disabled ^ !!new) {
 		if (new) {
 			/* disable cmci */
@@ -2121,6 +2130,8 @@ static ssize_t set_cmci_disabled(struct device *s,
 			on_each_cpu(mce_enable_ce, NULL, 1);
 		}
 	}
+	mutex_unlock(&mce_sysfs_mutex);
+
 	return size;
 }
 
@@ -2128,8 +2139,19 @@ static ssize_t store_int_with_restart(struct device *s,
 				      struct device_attribute *attr,
 				      const char *buf, size_t size)
 {
-	ssize_t ret = device_store_int(s, attr, buf, size);
+	unsigned long old_check_interval = check_interval;
+	ssize_t ret = device_store_ulong(s, attr, buf, size);
+
+	if (check_interval == old_check_interval)
+		return ret;
+
+	if (check_interval < 1)
+		check_interval = 1;
+
+	mutex_lock(&mce_sysfs_mutex);
 	mce_restart();
+	mutex_unlock(&mce_sysfs_mutex);
+
 	return ret;
 }
 

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

@@ -339,7 +339,7 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
 		return -EINVAL;
 
 	ret = load_microcode_amd(true, x86_family(cpuid_1_eax), desc.data, desc.size);
-	if (ret != UCODE_OK)
+	if (ret > UCODE_UPDATED)
 		return -EINVAL;
 
 	return 0;
@@ -683,27 +683,35 @@ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data,
 static enum ucode_state
 load_microcode_amd(bool save, u8 family, const u8 *data, size_t size)
 {
+	struct ucode_patch *p;
 	enum ucode_state ret;
 
 	/* free old equiv table */
 	free_equiv_cpu_table();
 
 	ret = __load_microcode_amd(family, data, size);
-
-	if (ret != UCODE_OK)
+	if (ret != UCODE_OK) {
 		cleanup();
+		return ret;
+	}
 
-#ifdef CONFIG_X86_32
-	/* save BSP's matching patch for early load */
-	if (save) {
-		struct ucode_patch *p = find_patch(0);
-		if (p) {
-			memset(amd_ucode_patch, 0, PATCH_MAX_SIZE);
-			memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data),
-							       PATCH_MAX_SIZE));
-		}
+	p = find_patch(0);
+	if (!p) {
+		return ret;
+	} else {
+		if (boot_cpu_data.microcode == p->patch_id)
+			return ret;
+
+		ret = UCODE_NEW;
 	}
-#endif
+
+	/* save BSP's matching patch for early load */
+	if (!save)
+		return ret;
+
+	memset(amd_ucode_patch, 0, PATCH_MAX_SIZE);
+	memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data), PATCH_MAX_SIZE));
+
 	return ret;
 }
 

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

@@ -22,13 +22,16 @@
 #define pr_fmt(fmt) "microcode: " fmt
 
 #include <linux/platform_device.h>
+#include <linux/stop_machine.h>
 #include <linux/syscore_ops.h>
 #include <linux/miscdevice.h>
 #include <linux/capability.h>
 #include <linux/firmware.h>
 #include <linux/kernel.h>
+#include <linux/delay.h>
 #include <linux/mutex.h>
 #include <linux/cpu.h>
+#include <linux/nmi.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
 
@@ -64,6 +67,11 @@ LIST_HEAD(microcode_cache);
  */
 static DEFINE_MUTEX(microcode_mutex);
 
+/*
+ * Serialize late loading so that CPUs get updated one-by-one.
+ */
+static DEFINE_SPINLOCK(update_lock);
+
 struct ucode_cpu_info		ucode_cpu_info[NR_CPUS];
 
 struct cpu_info_ctx {
@@ -373,26 +381,23 @@ static int collect_cpu_info(int cpu)
 	return ret;
 }
 
-struct apply_microcode_ctx {
-	enum ucode_state err;
-};
-
 static void apply_microcode_local(void *arg)
 {
-	struct apply_microcode_ctx *ctx = arg;
+	enum ucode_state *err = arg;
 
-	ctx->err = microcode_ops->apply_microcode(smp_processor_id());
+	*err = microcode_ops->apply_microcode(smp_processor_id());
 }
 
 static int apply_microcode_on_target(int cpu)
 {
-	struct apply_microcode_ctx ctx = { .err = 0 };
+	enum ucode_state err;
 	int ret;
 
-	ret = smp_call_function_single(cpu, apply_microcode_local, &ctx, 1);
-	if (!ret)
-		ret = ctx.err;
-
+	ret = smp_call_function_single(cpu, apply_microcode_local, &err, 1);
+	if (!ret) {
+		if (err == UCODE_ERROR)
+			ret = 1;
+	}
 	return ret;
 }
 
@@ -489,19 +494,114 @@ static void __exit microcode_dev_exit(void)
 /* fake device for request_firmware */
 static struct platform_device	*microcode_pdev;
 
-static enum ucode_state reload_for_cpu(int cpu)
+/*
+ * Late loading dance. Why the heavy-handed stomp_machine effort?
+ *
+ * - HT siblings must be idle and not execute other code while the other sibling
+ *   is loading microcode in order to avoid any negative interactions caused by
+ *   the loading.
+ *
+ * - In addition, microcode update on the cores must be serialized until this
+ *   requirement can be relaxed in the future. Right now, this is conservative
+ *   and good.
+ */
+#define SPINUNIT 100 /* 100 nsec */
+
+static int check_online_cpus(void)
 {
-	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-	enum ucode_state ustate;
+	if (num_online_cpus() == num_present_cpus())
+		return 0;
 
-	if (!uci->valid)
-		return UCODE_OK;
+	pr_err("Not all CPUs online, aborting microcode update.\n");
+
+	return -EINVAL;
+}
+
+static atomic_t late_cpus_in;
+static atomic_t late_cpus_out;
+
+static int __wait_for_cpus(atomic_t *t, long long timeout)
+{
+	int all_cpus = num_online_cpus();
+
+	atomic_inc(t);
 
-	ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev, true);
-	if (ustate != UCODE_OK)
-		return ustate;
+	while (atomic_read(t) < all_cpus) {
+		if (timeout < SPINUNIT) {
+			pr_err("Timeout while waiting for CPUs rendezvous, remaining: %d\n",
+				all_cpus - atomic_read(t));
+			return 1;
+		}
 
-	return apply_microcode_on_target(cpu);
+		ndelay(SPINUNIT);
+		timeout -= SPINUNIT;
+
+		touch_nmi_watchdog();
+	}
+	return 0;
+}
+
+/*
+ * Returns:
+ * < 0 - on error
+ *   0 - no update done
+ *   1 - microcode was updated
+ */
+static int __reload_late(void *info)
+{
+	int cpu = smp_processor_id();
+	enum ucode_state err;
+	int ret = 0;
+
+	/*
+	 * Wait for all CPUs to arrive. A load will not be attempted unless all
+	 * CPUs show up.
+	 * */
+	if (__wait_for_cpus(&late_cpus_in, NSEC_PER_SEC))
+		return -1;
+
+	spin_lock(&update_lock);
+	apply_microcode_local(&err);
+	spin_unlock(&update_lock);
+
+	if (err > UCODE_NFOUND) {
+		pr_warn("Error reloading microcode on CPU %d\n", cpu);
+		return -1;
+	/* siblings return UCODE_OK because their engine got updated already */
+	} else if (err == UCODE_UPDATED || err == UCODE_OK) {
+		ret = 1;
+	} else {
+		return ret;
+	}
+
+	/*
+	 * Increase the wait timeout to a safe value here since we're
+	 * serializing the microcode update and that could take a while on a
+	 * large number of CPUs. And that is fine as the *actual* timeout will
+	 * be determined by the last CPU finished updating and thus cut short.
+	 */
+	if (__wait_for_cpus(&late_cpus_out, NSEC_PER_SEC * num_online_cpus()))
+		panic("Timeout during microcode update!\n");
+
+	return ret;
+}
+
+/*
+ * Reload microcode late on all CPUs. Wait for a sec until they
+ * all gather together.
+ */
+static int microcode_reload_late(void)
+{
+	int ret;
+
+	atomic_set(&late_cpus_in,  0);
+	atomic_set(&late_cpus_out, 0);
+
+	ret = stop_machine_cpuslocked(__reload_late, NULL, cpu_online_mask);
+	if (ret > 0)
+		microcode_check();
+
+	return ret;
 }
 
 static ssize_t reload_store(struct device *dev,
@@ -509,10 +609,9 @@ static ssize_t reload_store(struct device *dev,
 			    const char *buf, size_t size)
 {
 	enum ucode_state tmp_ret = UCODE_OK;
-	bool do_callback = false;
+	int bsp = boot_cpu_data.cpu_index;
 	unsigned long val;
 	ssize_t ret = 0;
-	int cpu;
 
 	ret = kstrtoul(buf, 0, &val);
 	if (ret)
@@ -521,29 +620,24 @@ static ssize_t reload_store(struct device *dev,
 	if (val != 1)
 		return size;
 
-	get_online_cpus();
-	mutex_lock(&microcode_mutex);
-	for_each_online_cpu(cpu) {
-		tmp_ret = reload_for_cpu(cpu);
-		if (tmp_ret > UCODE_NFOUND) {
-			pr_warn("Error reloading microcode on CPU %d\n", cpu);
-
-			/* set retval for the first encountered reload error */
-			if (!ret)
-				ret = -EINVAL;
-		}
+	tmp_ret = microcode_ops->request_microcode_fw(bsp, &microcode_pdev->dev, true);
+	if (tmp_ret != UCODE_NEW)
+		return size;
 
-		if (tmp_ret == UCODE_UPDATED)
-			do_callback = true;
-	}
+	get_online_cpus();
 
-	if (!ret && do_callback)
-		microcode_check();
+	ret = check_online_cpus();
+	if (ret)
+		goto put;
 
+	mutex_lock(&microcode_mutex);
+	ret = microcode_reload_late();
 	mutex_unlock(&microcode_mutex);
+
+put:
 	put_online_cpus();
 
-	if (!ret)
+	if (ret >= 0)
 		ret = size;
 
 	return ret;
@@ -611,10 +705,8 @@ static enum ucode_state microcode_init_cpu(int cpu, bool refresh_fw)
 	if (system_state != SYSTEM_RUNNING)
 		return UCODE_NFOUND;
 
-	ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev,
-						     refresh_fw);
-
-	if (ustate == UCODE_OK) {
+	ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev, refresh_fw);
+	if (ustate == UCODE_NEW) {
 		pr_debug("CPU%d updated upon init\n", cpu);
 		apply_microcode_on_target(cpu);
 	}

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

@@ -589,6 +589,23 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
 	if (!mc)
 		return 0;
 
+	/*
+	 * Save us the MSR write below - which is a particular expensive
+	 * operation - when the other hyperthread has updated the microcode
+	 * already.
+	 */
+	rev = intel_get_microcode_revision();
+	if (rev >= mc->hdr.rev) {
+		uci->cpu_sig.rev = rev;
+		return UCODE_OK;
+	}
+
+	/*
+	 * Writeback and invalidate caches before updating microcode to avoid
+	 * internal issues depending on what the microcode is updating.
+	 */
+	native_wbinvd();
+
 	/* write microcode via MSR 0x79 */
 	native_wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);
 
@@ -774,9 +791,9 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
 
 static enum ucode_state apply_microcode_intel(int cpu)
 {
+	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	struct microcode_intel *mc;
-	struct ucode_cpu_info *uci;
-	struct cpuinfo_x86 *c;
 	static int prev_rev;
 	u32 rev;
 
@@ -784,15 +801,32 @@ static enum ucode_state apply_microcode_intel(int cpu)
 	if (WARN_ON(raw_smp_processor_id() != cpu))
 		return UCODE_ERROR;
 
-	uci = ucode_cpu_info + cpu;
-	mc = uci->mc;
+	/* Look for a newer patch in our cache: */
+	mc = find_patch(uci);
 	if (!mc) {
-		/* Look for a newer patch in our cache: */
-		mc = find_patch(uci);
+		mc = uci->mc;
 		if (!mc)
 			return UCODE_NFOUND;
 	}
 
+	/*
+	 * Save us the MSR write below - which is a particular expensive
+	 * operation - when the other hyperthread has updated the microcode
+	 * already.
+	 */
+	rev = intel_get_microcode_revision();
+	if (rev >= mc->hdr.rev) {
+		uci->cpu_sig.rev = rev;
+		c->microcode = rev;
+		return UCODE_OK;
+	}
+
+	/*
+	 * Writeback and invalidate caches before updating microcode to avoid
+	 * internal issues depending on what the microcode is updating.
+	 */
+	native_wbinvd();
+
 	/* write microcode via MSR 0x79 */
 	wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);
 
@@ -813,8 +847,6 @@ static enum ucode_state apply_microcode_intel(int cpu)
 		prev_rev = rev;
 	}
 
-	c = &cpu_data(cpu);
-
 	uci->cpu_sig.rev = rev;
 	c->microcode = rev;
 
@@ -830,6 +862,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 	unsigned int leftover = size;
 	unsigned int curr_mc_size = 0, new_mc_size = 0;
 	unsigned int csig, cpf;
+	enum ucode_state ret = UCODE_OK;
 
 	while (leftover) {
 		struct microcode_header_intel mc_header;
@@ -871,6 +904,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 			new_mc  = mc;
 			new_mc_size = mc_size;
 			mc = NULL;	/* trigger new vmalloc */
+			ret = UCODE_NEW;
 		}
 
 		ucode_ptr += mc_size;
@@ -900,7 +934,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 	pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n",
 		 cpu, new_rev, uci->cpu_sig.rev);
 
-	return UCODE_OK;
+	return ret;
 }
 
 static int get_ucode_fw(void *to, const void *from, size_t n)

arch/x86/kernel/idt.c

@@ -160,7 +160,6 @@ static const __initconst struct idt_data early_pf_idts[] = {
  */
 static const __initconst struct idt_data dbg_idts[] = {
 	INTG(X86_TRAP_DB,	debug),
-	INTG(X86_TRAP_BP,	int3),
 };
 #endif
 
@@ -183,7 +182,6 @@ gate_desc debug_idt_table[IDT_ENTRIES] __page_aligned_bss;
 static const __initconst struct idt_data ist_idts[] = {
 	ISTG(X86_TRAP_DB,	debug,		DEBUG_STACK),
 	ISTG(X86_TRAP_NMI,	nmi,		NMI_STACK),
-	SISTG(X86_TRAP_BP,	int3,		DEBUG_STACK),
 	ISTG(X86_TRAP_DF,	double_fault,	DOUBLEFAULT_STACK),
 #ifdef CONFIG_X86_MCE
 	ISTG(X86_TRAP_MC,	&machine_check,	MCE_STACK),

arch/x86/kernel/ioport.c

@@ -23,7 +23,7 @@
 /*
  * this changes the io permissions bitmap in the current task.
  */
-asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on)
+SYSCALL_DEFINE3(ioperm, unsigned long, from, unsigned long, num, int, turn_on)
 {
 	struct thread_struct *t = &current->thread;
 	struct tss_struct *tss;

arch/x86/kernel/kprobes/core.c

@@ -1168,10 +1168,18 @@ NOKPROBE_SYMBOL(longjmp_break_handler);
 
 bool arch_within_kprobe_blacklist(unsigned long addr)
 {
+	bool is_in_entry_trampoline_section = false;
+
+#ifdef CONFIG_X86_64
+	is_in_entry_trampoline_section =
+		(addr >= (unsigned long)__entry_trampoline_start &&
+		 addr < (unsigned long)__entry_trampoline_end);
+#endif
 	return  (addr >= (unsigned long)__kprobes_text_start &&
 		 addr < (unsigned long)__kprobes_text_end) ||
 		(addr >= (unsigned long)__entry_text_start &&
-		 addr < (unsigned long)__entry_text_end);
+		 addr < (unsigned long)__entry_text_end) ||
+		is_in_entry_trampoline_section;
 }
 
 int __init arch_init_kprobes(void)

arch/x86/kernel/pci-nommu.c

@@ -37,7 +37,6 @@ static dma_addr_t nommu_map_page(struct device *dev, struct page *page,
 	WARN_ON(size == 0);
 	if (!check_addr("map_single", dev, bus, size))
 		return NOMMU_MAPPING_ERROR;
-	flush_write_buffers();
 	return bus;
 }
 
@@ -72,25 +71,9 @@ static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg,
 			return 0;
 		s->dma_length = s->length;
 	}
-	flush_write_buffers();
 	return nents;
 }
 
-static void nommu_sync_single_for_device(struct device *dev,
-			dma_addr_t addr, size_t size,
-			enum dma_data_direction dir)
-{
-	flush_write_buffers();
-}
-
-
-static void nommu_sync_sg_for_device(struct device *dev,
-			struct scatterlist *sg, int nelems,
-			enum dma_data_direction dir)
-{
-	flush_write_buffers();
-}
-
 static int nommu_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
 	return dma_addr == NOMMU_MAPPING_ERROR;
@@ -101,8 +84,6 @@ const struct dma_map_ops nommu_dma_ops = {
 	.free			= dma_generic_free_coherent,
 	.map_sg			= nommu_map_sg,
 	.map_page		= nommu_map_page,
-	.sync_single_for_device = nommu_sync_single_for_device,
-	.sync_sg_for_device	= nommu_sync_sg_for_device,
 	.is_phys		= 1,
 	.mapping_error		= nommu_mapping_error,
 	.dma_supported		= x86_dma_supported,

arch/x86/kernel/signal_compat.c

@@ -43,6 +43,13 @@ static inline void signal_compat_build_tests(void)
 	BUILD_BUG_ON(offsetof(compat_siginfo_t, _sifields) != 3 * sizeof(int));
 #define CHECK_CSI_OFFSET(name)	  BUILD_BUG_ON(_sifields_offset != offsetof(compat_siginfo_t, _sifields.name))
 
+	BUILD_BUG_ON(offsetof(siginfo_t, si_signo) != 0);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_errno) != 4);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_code)  != 8);
+
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_signo) != 0);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_errno) != 4);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_code)  != 8);
 	 /*
 	 * Ensure that the size of each si_field never changes.
 	 * If it does, it is a sign that the
@@ -63,36 +70,94 @@ static inline void signal_compat_build_tests(void)
 	CHECK_CSI_SIZE  (_kill, 2*sizeof(int));
 	CHECK_SI_SIZE   (_kill, 2*sizeof(int));
 
+	BUILD_BUG_ON(offsetof(siginfo_t, si_pid) != 0x10);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_uid) != 0x14);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pid) != 0xC);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_uid) != 0x10);
+
 	CHECK_CSI_OFFSET(_timer);
 	CHECK_CSI_SIZE  (_timer, 3*sizeof(int));
 	CHECK_SI_SIZE   (_timer, 6*sizeof(int));
 
+	BUILD_BUG_ON(offsetof(siginfo_t, si_tid)     != 0x10);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_overrun) != 0x14);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_value)   != 0x18);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_tid)     != 0x0C);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_overrun) != 0x10);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_value)   != 0x14);
+
 	CHECK_CSI_OFFSET(_rt);
 	CHECK_CSI_SIZE  (_rt, 3*sizeof(int));
 	CHECK_SI_SIZE   (_rt, 4*sizeof(int));
 
+	BUILD_BUG_ON(offsetof(siginfo_t, si_pid)   != 0x10);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_uid)   != 0x14);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_value) != 0x18);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pid)   != 0x0C);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_uid)   != 0x10);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_value) != 0x14);
+
 	CHECK_CSI_OFFSET(_sigchld);
 	CHECK_CSI_SIZE  (_sigchld, 5*sizeof(int));
 	CHECK_SI_SIZE   (_sigchld, 8*sizeof(int));
 
+	BUILD_BUG_ON(offsetof(siginfo_t, si_pid)    != 0x10);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_uid)    != 0x14);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_status) != 0x18);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_utime)  != 0x20);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_stime)  != 0x28);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pid)    != 0x0C);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_uid)    != 0x10);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_status) != 0x14);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_utime)  != 0x18);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_stime)  != 0x1C);
+
 #ifdef CONFIG_X86_X32_ABI
 	CHECK_CSI_OFFSET(_sigchld_x32);
 	CHECK_CSI_SIZE  (_sigchld_x32, 7*sizeof(int));
 	/* no _sigchld_x32 in the generic siginfo_t */
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, _sifields._sigchld_x32._utime)  != 0x18);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, _sifields._sigchld_x32._stime)  != 0x20);
 #endif
 
 	CHECK_CSI_OFFSET(_sigfault);
 	CHECK_CSI_SIZE  (_sigfault, 4*sizeof(int));
 	CHECK_SI_SIZE   (_sigfault, 8*sizeof(int));
 
+	BUILD_BUG_ON(offsetof(siginfo_t, si_addr) != 0x10);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_addr) != 0x0C);
+
+	BUILD_BUG_ON(offsetof(siginfo_t, si_addr_lsb) != 0x18);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_addr_lsb) != 0x10);
+
+	BUILD_BUG_ON(offsetof(siginfo_t, si_lower) != 0x20);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_upper) != 0x28);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_lower) != 0x14);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_upper) != 0x18);
+
+	BUILD_BUG_ON(offsetof(siginfo_t, si_pkey) != 0x20);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pkey) != 0x14);
+
 	CHECK_CSI_OFFSET(_sigpoll);
 	CHECK_CSI_SIZE  (_sigpoll, 2*sizeof(int));
 	CHECK_SI_SIZE   (_sigpoll, 4*sizeof(int));
 
+	BUILD_BUG_ON(offsetof(siginfo_t, si_band)   != 0x10);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_fd)     != 0x18);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_band) != 0x0C);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_fd)   != 0x10);
+
 	CHECK_CSI_OFFSET(_sigsys);
 	CHECK_CSI_SIZE  (_sigsys, 3*sizeof(int));
 	CHECK_SI_SIZE   (_sigsys, 4*sizeof(int));
 
+	BUILD_BUG_ON(offsetof(siginfo_t, si_call_addr) != 0x10);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_syscall)   != 0x18);
+	BUILD_BUG_ON(offsetof(siginfo_t, si_arch)      != 0x1C);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_call_addr) != 0x0C);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_syscall)   != 0x10);
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, si_arch)      != 0x14);
+
 	/* any new si_fields should be added here */
 }
 

arch/x86/kernel/traps.c

@@ -577,7 +577,6 @@ do_general_protection(struct pt_regs *regs, long error_code)
 }
 NOKPROBE_SYMBOL(do_general_protection);
 
-/* May run on IST stack. */
 dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
 {
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -592,6 +591,13 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
 	if (poke_int3_handler(regs))
 		return;
 
+	/*
+	 * Use ist_enter despite the fact that we don't use an IST stack.
+	 * We can be called from a kprobe in non-CONTEXT_KERNEL kernel
+	 * mode or even during context tracking state changes.
+	 *
+	 * This means that we can't schedule.  That's okay.
+	 */
 	ist_enter(regs);
 	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
 #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
@@ -609,15 +615,10 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
 			SIGTRAP) == NOTIFY_STOP)
 		goto exit;
 
-	/*
-	 * Let others (NMI) know that the debug stack is in use
-	 * as we may switch to the interrupt stack.
-	 */
-	debug_stack_usage_inc();
 	cond_local_irq_enable(regs);
 	do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL);
 	cond_local_irq_disable(regs);
-	debug_stack_usage_dec();
+
 exit:
 	ist_exit(regs);
 }

arch/x86/kernel/vm86_32.c

@@ -727,7 +727,8 @@ void handle_vm86_fault(struct kernel_vm86_regs *regs, long error_code)
 	return;
 
 check_vip:
-	if (VEFLAGS & X86_EFLAGS_VIP) {
+	if ((VEFLAGS & (X86_EFLAGS_VIP | X86_EFLAGS_VIF)) ==
+	    (X86_EFLAGS_VIP | X86_EFLAGS_VIF)) {
 		save_v86_state(regs, VM86_STI);
 		return;
 	}

arch/x86/kernel/vmlinux.lds.S

@@ -118,9 +118,11 @@ SECTIONS
 
 #ifdef CONFIG_X86_64
 		. = ALIGN(PAGE_SIZE);
+		VMLINUX_SYMBOL(__entry_trampoline_start) = .;
 		_entry_trampoline = .;
 		*(.entry_trampoline)
 		. = ALIGN(PAGE_SIZE);
+		VMLINUX_SYMBOL(__entry_trampoline_end) = .;
 		ASSERT(. - _entry_trampoline == PAGE_SIZE, "entry trampoline is too big");
 #endif
 

arch/x86/kvm/mmu.c

@@ -2770,8 +2770,10 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 	else
 		pte_access &= ~ACC_WRITE_MASK;
 
+	if (!kvm_is_mmio_pfn(pfn))
+		spte |= shadow_me_mask;
+
 	spte |= (u64)pfn << PAGE_SHIFT;
-	spte |= shadow_me_mask;
 
 	if (pte_access & ACC_WRITE_MASK) {
 

arch/x86/kvm/vmx.c

@@ -1045,6 +1045,13 @@ static inline bool is_machine_check(u32 intr_info)
 		(INTR_TYPE_HARD_EXCEPTION | MC_VECTOR | INTR_INFO_VALID_MASK);
 }
 
+/* Undocumented: icebp/int1 */
+static inline bool is_icebp(u32 intr_info)
+{
+	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
+		== (INTR_TYPE_PRIV_SW_EXCEPTION | INTR_INFO_VALID_MASK);
+}
+
 static inline bool cpu_has_vmx_msr_bitmap(void)
 {
 	return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_USE_MSR_BITMAPS;
@@ -6179,7 +6186,7 @@ static int handle_exception(struct kvm_vcpu *vcpu)
 		      (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) {
 			vcpu->arch.dr6 &= ~15;
 			vcpu->arch.dr6 |= dr6 | DR6_RTM;
-			if (!(dr6 & ~DR6_RESERVED)) /* icebp */
+			if (is_icebp(intr_info))
 				skip_emulated_instruction(vcpu);
 
 			kvm_queue_exception(vcpu, DB_VECTOR);

arch/x86/mm/fault.c

@@ -330,7 +330,7 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (!pmd_k)
 		return -1;
 
-	if (pmd_huge(*pmd_k))
+	if (pmd_large(*pmd_k))
 		return 0;
 
 	pte_k = pte_offset_kernel(pmd_k, address);
@@ -475,7 +475,7 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (pud_none(*pud) || pud_pfn(*pud) != pud_pfn(*pud_ref))
 		BUG();
 
-	if (pud_huge(*pud))
+	if (pud_large(*pud))
 		return 0;
 
 	pmd = pmd_offset(pud, address);
@@ -486,7 +486,7 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (pmd_none(*pmd) || pmd_pfn(*pmd) != pmd_pfn(*pmd_ref))
 		BUG();
 
-	if (pmd_huge(*pmd))
+	if (pmd_large(*pmd))
 		return 0;
 
 	pte_ref = pte_offset_kernel(pmd_ref, address);

arch/x86/mm/init_64.c

@@ -800,17 +800,11 @@ int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
 
 #define PAGE_INUSE 0xFD
 
-static void __meminit free_pagetable(struct page *page, int order,
-		struct vmem_altmap *altmap)
+static void __meminit free_pagetable(struct page *page, int order)
 {
 	unsigned long magic;
 	unsigned int nr_pages = 1 << order;
 
-	if (altmap) {
-		vmem_altmap_free(altmap, nr_pages);
-		return;
-	}
-
 	/* bootmem page has reserved flag */
 	if (PageReserved(page)) {
 		__ClearPageReserved(page);
@@ -826,8 +820,16 @@ static void __meminit free_pagetable(struct page *page, int order,
 		free_pages((unsigned long)page_address(page), order);
 }
 
-static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd,
+static void __meminit free_hugepage_table(struct page *page,
 		struct vmem_altmap *altmap)
+{
+	if (altmap)
+		vmem_altmap_free(altmap, PMD_SIZE / PAGE_SIZE);
+	else
+		free_pagetable(page, get_order(PMD_SIZE));
+}
+
+static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd)
 {
 	pte_t *pte;
 	int i;
@@ -839,14 +841,13 @@ static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd,
 	}
 
 	/* free a pte talbe */
-	free_pagetable(pmd_page(*pmd), 0, altmap);
+	free_pagetable(pmd_page(*pmd), 0);
 	spin_lock(&init_mm.page_table_lock);
 	pmd_clear(pmd);
 	spin_unlock(&init_mm.page_table_lock);
 }
 
-static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud,
-		struct vmem_altmap *altmap)
+static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud)
 {
 	pmd_t *pmd;
 	int i;
@@ -858,14 +859,13 @@ static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud,
 	}
 
 	/* free a pmd talbe */
-	free_pagetable(pud_page(*pud), 0, altmap);
+	free_pagetable(pud_page(*pud), 0);
 	spin_lock(&init_mm.page_table_lock);
 	pud_clear(pud);
 	spin_unlock(&init_mm.page_table_lock);
 }
 
-static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d,
-		struct vmem_altmap *altmap)
+static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d)
 {
 	pud_t *pud;
 	int i;
@@ -877,7 +877,7 @@ static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d,
 	}
 
 	/* free a pud talbe */
-	free_pagetable(p4d_page(*p4d), 0, altmap);
+	free_pagetable(p4d_page(*p4d), 0);
 	spin_lock(&init_mm.page_table_lock);
 	p4d_clear(p4d);
 	spin_unlock(&init_mm.page_table_lock);
@@ -885,7 +885,7 @@ static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d,
 
 static void __meminit
 remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end,
-		 struct vmem_altmap *altmap, bool direct)
+		 bool direct)
 {
 	unsigned long next, pages = 0;
 	pte_t *pte;
@@ -916,7 +916,7 @@ remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end,
 			 * freed when offlining, or simplely not in use.
 			 */
 			if (!direct)
-				free_pagetable(pte_page(*pte), 0, altmap);
+				free_pagetable(pte_page(*pte), 0);
 
 			spin_lock(&init_mm.page_table_lock);
 			pte_clear(&init_mm, addr, pte);
@@ -939,7 +939,7 @@ remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end,
 
 			page_addr = page_address(pte_page(*pte));
 			if (!memchr_inv(page_addr, PAGE_INUSE, PAGE_SIZE)) {
-				free_pagetable(pte_page(*pte), 0, altmap);
+				free_pagetable(pte_page(*pte), 0);
 
 				spin_lock(&init_mm.page_table_lock);
 				pte_clear(&init_mm, addr, pte);
@@ -974,9 +974,8 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end,
 			if (IS_ALIGNED(addr, PMD_SIZE) &&
 			    IS_ALIGNED(next, PMD_SIZE)) {
 				if (!direct)
-					free_pagetable(pmd_page(*pmd),
-						       get_order(PMD_SIZE),
-						       altmap);
+					free_hugepage_table(pmd_page(*pmd),
+							    altmap);
 
 				spin_lock(&init_mm.page_table_lock);
 				pmd_clear(pmd);
@@ -989,9 +988,8 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end,
 				page_addr = page_address(pmd_page(*pmd));
 				if (!memchr_inv(page_addr, PAGE_INUSE,
 						PMD_SIZE)) {
-					free_pagetable(pmd_page(*pmd),
-						       get_order(PMD_SIZE),
-						       altmap);
+					free_hugepage_table(pmd_page(*pmd),
+							    altmap);
 
 					spin_lock(&init_mm.page_table_lock);
 					pmd_clear(pmd);
@@ -1003,8 +1001,8 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end,
 		}
 
 		pte_base = (pte_t *)pmd_page_vaddr(*pmd);
-		remove_pte_table(pte_base, addr, next, altmap, direct);
-		free_pte_table(pte_base, pmd, altmap);
+		remove_pte_table(pte_base, addr, next, direct);
+		free_pte_table(pte_base, pmd);
 	}
 
 	/* Call free_pmd_table() in remove_pud_table(). */
@@ -1033,8 +1031,7 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end,
 			    IS_ALIGNED(next, PUD_SIZE)) {
 				if (!direct)
 					free_pagetable(pud_page(*pud),
-						       get_order(PUD_SIZE),
-						       altmap);
+						       get_order(PUD_SIZE));
 
 				spin_lock(&init_mm.page_table_lock);
 				pud_clear(pud);
@@ -1048,8 +1045,7 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end,
 				if (!memchr_inv(page_addr, PAGE_INUSE,
 						PUD_SIZE)) {
 					free_pagetable(pud_page(*pud),
-						       get_order(PUD_SIZE),
-						       altmap);
+						       get_order(PUD_SIZE));
 
 					spin_lock(&init_mm.page_table_lock);
 					pud_clear(pud);
@@ -1062,7 +1058,7 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end,
 
 		pmd_base = pmd_offset(pud, 0);
 		remove_pmd_table(pmd_base, addr, next, direct, altmap);
-		free_pmd_table(pmd_base, pud, altmap);
+		free_pmd_table(pmd_base, pud);
 	}
 
 	if (direct)
@@ -1094,7 +1090,7 @@ remove_p4d_table(p4d_t *p4d_start, unsigned long addr, unsigned long end,
 		 * to adapt for boot-time switching between 4 and 5 level page tables.
 		 */
 		if (CONFIG_PGTABLE_LEVELS == 5)
-			free_pud_table(pud_base, p4d, altmap);
+			free_pud_table(pud_base, p4d);
 	}
 
 	if (direct)

arch/x86/mm/pgtable.c

@@ -702,4 +702,52 @@ int pmd_clear_huge(pmd_t *pmd)
 
 	return 0;
 }
+
+/**
+ * pud_free_pmd_page - Clear pud entry and free pmd page.
+ * @pud: Pointer to a PUD.
+ *
+ * Context: The pud range has been unmaped and TLB purged.
+ * Return: 1 if clearing the entry succeeded. 0 otherwise.
+ */
+int pud_free_pmd_page(pud_t *pud)
+{
+	pmd_t *pmd;
+	int i;
+
+	if (pud_none(*pud))
+		return 1;
+
+	pmd = (pmd_t *)pud_page_vaddr(*pud);
+
+	for (i = 0; i < PTRS_PER_PMD; i++)
+		if (!pmd_free_pte_page(&pmd[i]))
+			return 0;
+
+	pud_clear(pud);
+	free_page((unsigned long)pmd);
+
+	return 1;
+}
+
+/**
+ * pmd_free_pte_page - Clear pmd entry and free pte page.
+ * @pmd: Pointer to a PMD.
+ *
+ * Context: The pmd range has been unmaped and TLB purged.
+ * Return: 1 if clearing the entry succeeded. 0 otherwise.
+ */
+int pmd_free_pte_page(pmd_t *pmd)
+{
+	pte_t *pte;
+
+	if (pmd_none(*pmd))
+		return 1;
+
+	pte = (pte_t *)pmd_page_vaddr(*pmd);
+	pmd_clear(pmd);
+	free_page((unsigned long)pte);
+
+	return 1;
+}
 #endif	/* CONFIG_HAVE_ARCH_HUGE_VMAP */

arch/x86/mm/pti.c

@@ -332,7 +332,7 @@ static void __init pti_clone_user_shared(void)
 }
 
 /*
- * Clone the ESPFIX P4D into the user space visinble page table
+ * Clone the ESPFIX P4D into the user space visible page table
  */
 static void __init pti_setup_espfix64(void)
 {

arch/x86/net/bpf_jit_comp.c

@@ -1188,7 +1188,7 @@ skip_init_addrs:
 	 * may converge on the last pass. In such case do one more
 	 * pass to emit the final image
 	 */
-	for (pass = 0; pass < 10 || image; pass++) {
+	for (pass = 0; pass < 20 || image; pass++) {
 		proglen = do_jit(prog, addrs, image, oldproglen, &ctx);
 		if (proglen <= 0) {
 			image = NULL;
@@ -1215,6 +1215,7 @@ skip_init_addrs:
 			}
 		}
 		oldproglen = proglen;
+		cond_resched();
 	}
 
 	if (bpf_jit_enable > 1)

arch/x86/platform/efi/efi_64.c

@@ -227,7 +227,7 @@ int __init efi_alloc_page_tables(void)
 	if (!pud) {
 		if (CONFIG_PGTABLE_LEVELS > 4)
 			free_page((unsigned long) pgd_page_vaddr(*pgd));
-		free_page((unsigned long)efi_pgd);
+		free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER);
 		return -ENOMEM;
 	}