BackMerge tag 'v4.12-rc5' into drm-next

Linux 4.12-rc5 for nouveau fixes

Documentation/admin-guide/kernel-parameters.txt

@@ -866,6 +866,15 @@
 
 	dscc4.setup=	[NET]
 
+	dt_cpu_ftrs=	[PPC]
+			Format: {"off" | "known"}
+			Control how the dt_cpu_ftrs device-tree binding is
+			used for CPU feature discovery and setup (if it
+			exists).
+			off: Do not use it, fall back to legacy cpu table.
+			known: Do not pass through unknown features to guests
+			or userspace, only those that the kernel is aware of.
+
 	dump_apple_properties	[X86]
 			Dump name and content of EFI device properties on
 			x86 Macs.  Useful for driver authors to determine

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

@@ -26,6 +26,10 @@ Optional properties:
 - interrupt-controller	: Indicates the switch is itself an interrupt
 			  controller. This is used for the PHY interrupts.
 #interrupt-cells = <2>	: Controller uses two cells, number and flag
+- eeprom-length		: Set to the length of an EEPROM connected to the
+			  switch. Must be set if the switch can not detect
+			  the presence and/or size of a connected EEPROM,
+			  otherwise optional.
 - mdio			: Container of PHY and devices on the switches MDIO
 			  bus.
 - mdio?		: Container of PHYs and devices on the external MDIO

Documentation/devicetree/bindings/pinctrl/pinctrl-bindings.txt

@@ -247,7 +247,6 @@ bias-bus-hold		- latch weakly
 bias-pull-up		- pull up the pin
 bias-pull-down		- pull down the pin
 bias-pull-pin-default	- use pin-default pull state
-bi-directional		- pin supports simultaneous input/output operations
 drive-push-pull		- drive actively high and low
 drive-open-drain	- drive with open drain
 drive-open-source	- drive with open source
@@ -260,7 +259,6 @@ input-debounce		- debounce mode with debound time X
 power-source		- select between different power supplies
 low-power-enable	- enable low power mode
 low-power-disable	- disable low power mode
-output-enable		- enable output on pin regardless of output value
 output-low		- set the pin to output mode with low level
 output-high		- set the pin to output mode with high level
 slew-rate		- set the slew rate

Documentation/devicetree/bindings/usb/dwc2.txt

@@ -10,6 +10,7 @@ Required properties:
   - "rockchip,rk3288-usb", "rockchip,rk3066-usb", "snps,dwc2": for rk3288 Soc;
   - "lantiq,arx100-usb": The DWC2 USB controller instance in Lantiq ARX SoCs;
   - "lantiq,xrx200-usb": The DWC2 USB controller instance in Lantiq XRX SoCs;
+  - "amlogic,meson8-usb": The DWC2 USB controller instance in Amlogic Meson8 SoCs;
   - "amlogic,meson8b-usb": The DWC2 USB controller instance in Amlogic Meson8b SoCs;
   - "amlogic,meson-gxbb-usb": The DWC2 USB controller instance in Amlogic S905 SoCs;
   - "amcc,dwc-otg": The DWC2 USB controller instance in AMCC Canyonlands 460EX SoCs;

Documentation/networking/dpaa.txt

@@ -0,0 +1,194 @@
+The QorIQ DPAA Ethernet Driver
+==============================
+
+Authors:
+Madalin Bucur <madalin.bucur@nxp.com>
+Camelia Groza <camelia.groza@nxp.com>
+
+Contents
+========
+
+	- DPAA Ethernet Overview
+	- DPAA Ethernet Supported SoCs
+	- Configuring DPAA Ethernet in your kernel
+	- DPAA Ethernet Frame Processing
+	- DPAA Ethernet Features
+	- Debugging
+
+DPAA Ethernet Overview
+======================
+
+DPAA stands for Data Path Acceleration Architecture and it is a
+set of networking acceleration IPs that are available on several
+generations of SoCs, both on PowerPC and ARM64.
+
+The Freescale DPAA architecture consists of a series of hardware blocks
+that support Ethernet connectivity. The Ethernet driver depends upon the
+following drivers in the Linux kernel:
+
+ - Peripheral Access Memory Unit (PAMU) (* needed only for PPC platforms)
+    drivers/iommu/fsl_*
+ - Frame Manager (FMan)
+    drivers/net/ethernet/freescale/fman
+ - Queue Manager (QMan), Buffer Manager (BMan)
+    drivers/soc/fsl/qbman
+
+A simplified view of the dpaa_eth interfaces mapped to FMan MACs:
+
+  dpaa_eth       /eth0\     ...       /ethN\
+  driver        |      |             |      |
+  -------------   ----   -----------   ----   -------------
+       -Ports  / Tx  Rx \    ...    / Tx  Rx \
+  FMan        |          |         |          |
+       -MACs  |   MAC0   |         |   MACN   |
+             /   dtsec0   \  ...  /   dtsecN   \ (or tgec)
+            /              \     /              \(or memac)
+  ---------  --------------  ---  --------------  ---------
+      FMan, FMan Port, FMan SP, FMan MURAM drivers
+  ---------------------------------------------------------
+      FMan HW blocks: MURAM, MACs, Ports, SP
+  ---------------------------------------------------------
+
+The dpaa_eth relation to the QMan, BMan and FMan:
+              ________________________________
+  dpaa_eth   /            eth0                \
+  driver    /                                  \
+  ---------   -^-   -^-   -^-   ---    ---------
+  QMan driver / \   / \   / \  \   /  | BMan    |
+             |Rx | |Rx | |Tx | |Tx |  | driver  |
+  ---------  |Dfl| |Err| |Cnf| |FQs|  |         |
+  QMan HW    |FQ | |FQ | |FQs| |   |  |         |
+             /   \ /   \ /   \  \ /   |         |
+  ---------   ---   ---   ---   -v-    ---------
+            |        FMan QMI         |         |
+            | FMan HW       FMan BMI  | BMan HW |
+              -----------------------   --------
+
+where the acronyms used above (and in the code) are:
+DPAA = Data Path Acceleration Architecture
+FMan = DPAA Frame Manager
+QMan = DPAA Queue Manager
+BMan = DPAA Buffers Manager
+QMI = QMan interface in FMan
+BMI = BMan interface in FMan
+FMan SP = FMan Storage Profiles
+MURAM = Multi-user RAM in FMan
+FQ = QMan Frame Queue
+Rx Dfl FQ = default reception FQ
+Rx Err FQ = Rx error frames FQ
+Tx Cnf FQ = Tx confirmation FQs
+Tx FQs = transmission frame queues
+dtsec = datapath three speed Ethernet controller (10/100/1000 Mbps)
+tgec = ten gigabit Ethernet controller (10 Gbps)
+memac = multirate Ethernet MAC (10/100/1000/10000)
+
+DPAA Ethernet Supported SoCs
+============================
+
+The DPAA drivers enable the Ethernet controllers present on the following SoCs:
+
+# PPC
+P1023
+P2041
+P3041
+P4080
+P5020
+P5040
+T1023
+T1024
+T1040
+T1042
+T2080
+T4240
+B4860
+
+# ARM
+LS1043A
+LS1046A
+
+Configuring DPAA Ethernet in your kernel
+========================================
+
+To enable the DPAA Ethernet driver, the following Kconfig options are required:
+
+# common for arch/arm64 and arch/powerpc platforms
+CONFIG_FSL_DPAA=y
+CONFIG_FSL_FMAN=y
+CONFIG_FSL_DPAA_ETH=y
+CONFIG_FSL_XGMAC_MDIO=y
+
+# for arch/powerpc only
+CONFIG_FSL_PAMU=y
+
+# common options needed for the PHYs used on the RDBs
+CONFIG_VITESSE_PHY=y
+CONFIG_REALTEK_PHY=y
+CONFIG_AQUANTIA_PHY=y
+
+DPAA Ethernet Frame Processing
+==============================
+
+On Rx, buffers for the incoming frames are retrieved from one of the three
+existing buffers pools. The driver initializes and seeds these, each with
+buffers of different sizes: 1KB, 2KB and 4KB.
+
+On Tx, all transmitted frames are returned to the driver through Tx
+confirmation frame queues. The driver is then responsible for freeing the
+buffers. In order to do this properly, a backpointer is added to the buffer
+before transmission that points to the skb. When the buffer returns to the
+driver on a confirmation FQ, the skb can be correctly consumed.
+
+DPAA Ethernet Features
+======================
+
+Currently the DPAA Ethernet driver enables the basic features required for
+a Linux Ethernet driver. The support for advanced features will be added
+gradually.
+
+The driver has Rx and Tx checksum offloading for UDP and TCP. Currently the Rx
+checksum offload feature is enabled by default and cannot be controlled through
+ethtool.
+
+The driver has support for multiple prioritized Tx traffic classes. Priorities
+range from 0 (lowest) to 3 (highest). These are mapped to HW workqueues with
+strict priority levels. Each traffic class contains NR_CPU TX queues. By
+default, only one traffic class is enabled and the lowest priority Tx queues
+are used. Higher priority traffic classes can be enabled with the mqprio
+qdisc. For example, all four traffic classes are enabled on an interface with
+the following command. Furthermore, skb priority levels are mapped to traffic
+classes as follows:
+
+	* priorities 0 to 3 - traffic class 0 (low priority)
+	* priorities 4 to 7 - traffic class 1 (medium-low priority)
+	* priorities 8 to 11 - traffic class 2 (medium-high priority)
+	* priorities 12 to 15 - traffic class 3 (high priority)
+
+tc qdisc add dev <int> root handle 1: \
+	 mqprio num_tc 4 map 0 0 0 0 1 1 1 1 2 2 2 2 3 3 3 3 hw 1
+
+Debugging
+=========
+
+The following statistics are exported for each interface through ethtool:
+
+	- interrupt count per CPU
+	- Rx packets count per CPU
+	- Tx packets count per CPU
+	- Tx confirmed packets count per CPU
+	- Tx S/G frames count per CPU
+	- Tx error count per CPU
+	- Rx error count per CPU
+	- Rx error count per type
+	- congestion related statistics:
+		- congestion status
+		- time spent in congestion
+		- number of time the device entered congestion
+		- dropped packets count per cause
+
+The driver also exports the following information in sysfs:
+
+	- the FQ IDs for each FQ type
+	/sys/devices/platform/dpaa-ethernet.0/net/<int>/fqids
+
+	- the IDs of the buffer pools in use
+	/sys/devices/platform/dpaa-ethernet.0/net/<int>/bpids

Documentation/networking/tcp.txt

@@ -1,7 +1,7 @@
 TCP protocol
 ============
 
-Last updated: 9 February 2008
+Last updated: 3 June 2017
 
 Contents
 ========
@@ -29,18 +29,19 @@ As of 2.6.13, Linux supports pluggable congestion control algorithms.
 A congestion control mechanism can be registered through functions in
 tcp_cong.c. The functions used by the congestion control mechanism are
 registered via passing a tcp_congestion_ops struct to
-tcp_register_congestion_control. As a minimum name, ssthresh,
-cong_avoid must be valid.
+tcp_register_congestion_control. As a minimum, the congestion control
+mechanism must provide a valid name and must implement either ssthresh,
+cong_avoid and undo_cwnd hooks or the "omnipotent" cong_control hook.
 
 Private data for a congestion control mechanism is stored in tp->ca_priv.
 tcp_ca(tp) returns a pointer to this space.  This is preallocated space - it
 is important to check the size of your private data will fit this space, or
-alternatively space could be allocated elsewhere and a pointer to it could
+alternatively, space could be allocated elsewhere and a pointer to it could
 be stored here.
 
 There are three kinds of congestion control algorithms currently: The
 simplest ones are derived from TCP reno (highspeed, scalable) and just
-provide an alternative the congestion window calculation. More complex
+provide an alternative congestion window calculation. More complex
 ones like BIC try to look at other events to provide better
 heuristics.  There are also round trip time based algorithms like
 Vegas and Westwood+.
@@ -49,21 +50,15 @@ Good TCP congestion control is a complex problem because the algorithm
 needs to maintain fairness and performance. Please review current
 research and RFC's before developing new modules.
 
-The method that is used to determine which congestion control mechanism is
-determined by the setting of the sysctl net.ipv4.tcp_congestion_control.
-The default congestion control will be the last one registered (LIFO);
-so if you built everything as modules, the default will be reno. If you
-build with the defaults from Kconfig, then CUBIC will be builtin (not a
-module) and it will end up the default.
+The default congestion control mechanism is chosen based on the
+DEFAULT_TCP_CONG Kconfig parameter. If you really want a particular default
+value then you can set it using sysctl net.ipv4.tcp_congestion_control. The
+module will be autoloaded if needed and you will get the expected protocol. If
+you ask for an unknown congestion method, then the sysctl attempt will fail.
 
-If you really want a particular default value then you will need
-to set it with the sysctl.  If you use a sysctl, the module will be autoloaded
-if needed and you will get the expected protocol. If you ask for an
-unknown congestion method, then the sysctl attempt will fail.
-
-If you remove a tcp congestion control module, then you will get the next
+If you remove a TCP congestion control module, then you will get the next
 available one. Since reno cannot be built as a module, and cannot be
-deleted, it will always be available.
+removed, it will always be available.
 
 How the new TCP output machine [nyi] works.
 ===========================================

MAINTAINERS

@@ -1172,7 +1172,7 @@ N:	clps711x
 
 ARM/CIRRUS LOGIC EP93XX ARM ARCHITECTURE
 M:	Hartley Sweeten <hsweeten@visionengravers.com>
-M:	Ryan Mallon <rmallon@gmail.com>
+M:	Alexander Sverdlin <alexander.sverdlin@gmail.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	arch/arm/mach-ep93xx/
@@ -1489,13 +1489,15 @@ M:	Gregory Clement <gregory.clement@free-electrons.com>
 M:	Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
-F:	arch/arm/mach-mvebu/
-F:	drivers/rtc/rtc-armada38x.c
 F:	arch/arm/boot/dts/armada*
 F:	arch/arm/boot/dts/kirkwood*
+F:	arch/arm/configs/mvebu_*_defconfig
+F:	arch/arm/mach-mvebu/
 F:	arch/arm64/boot/dts/marvell/armada*
 F:	drivers/cpufreq/mvebu-cpufreq.c
-F:	arch/arm/configs/mvebu_*_defconfig
+F:	drivers/irqchip/irq-armada-370-xp.c
+F:	drivers/irqchip/irq-mvebu-*
+F:	drivers/rtc/rtc-armada38x.c
 
 ARM/Marvell Berlin SoC support
 M:	Jisheng Zhang <jszhang@marvell.com>
@@ -1721,7 +1723,6 @@ N:	rockchip
 ARM/SAMSUNG EXYNOS ARM ARCHITECTURES
 M:	Kukjin Kim <kgene@kernel.org>
 M:	Krzysztof Kozlowski <krzk@kernel.org>
-R:	Javier Martinez Canillas <javier@osg.samsung.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 L:	linux-samsung-soc@vger.kernel.org (moderated for non-subscribers)
 Q:	https://patchwork.kernel.org/project/linux-samsung-soc/list/
@@ -1829,7 +1830,6 @@ F:	drivers/edac/altera_edac.
 ARM/STI ARCHITECTURE
 M:	Patrice Chotard <patrice.chotard@st.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-L:	kernel@stlinux.com
 W:	http://www.stlinux.com
 S:	Maintained
 F:	arch/arm/mach-sti/
@@ -5641,7 +5641,7 @@ F:	scripts/get_maintainer.pl
 
 GENWQE (IBM Generic Workqueue Card)
 M:	Frank Haverkamp <haver@linux.vnet.ibm.com>
-M:	Gabriel Krisman Bertazi <krisman@linux.vnet.ibm.com>
+M:	Guilherme G. Piccoli <gpiccoli@linux.vnet.ibm.com>
 S:	Supported
 F:	drivers/misc/genwqe/
 
@@ -5686,7 +5686,6 @@ F:	tools/testing/selftests/gpio/
 
 GPIO SUBSYSTEM
 M:	Linus Walleij <linus.walleij@linaro.org>
-M:	Alexandre Courbot <gnurou@gmail.com>
 L:	linux-gpio@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio.git
 S:	Maintained
@@ -7726,7 +7725,7 @@ F:	drivers/platform/x86/hp_accel.c
 
 LIVE PATCHING
 M:	Josh Poimboeuf <jpoimboe@redhat.com>
-M:	Jessica Yu <jeyu@redhat.com>
+M:	Jessica Yu <jeyu@kernel.org>
 M:	Jiri Kosina <jikos@kernel.org>
 M:	Miroslav Benes <mbenes@suse.cz>
 R:	Petr Mladek <pmladek@suse.com>
@@ -8527,7 +8526,7 @@ S:	Odd Fixes
 F:	drivers/media/radio/radio-miropcm20*
 
 MELLANOX MLX4 core VPI driver
-M:	Yishai Hadas <yishaih@mellanox.com>
+M:	Tariq Toukan <tariqt@mellanox.com>
 L:	netdev@vger.kernel.org
 L:	linux-rdma@vger.kernel.org
 W:	http://www.mellanox.com
@@ -8535,7 +8534,6 @@ Q:	http://patchwork.ozlabs.org/project/netdev/list/
 S:	Supported
 F:	drivers/net/ethernet/mellanox/mlx4/
 F:	include/linux/mlx4/
-F:	include/uapi/rdma/mlx4-abi.h
 
 MELLANOX MLX4 IB driver
 M:	Yishai Hadas <yishaih@mellanox.com>
@@ -8545,6 +8543,7 @@ Q:	http://patchwork.kernel.org/project/linux-rdma/list/
 S:	Supported
 F:	drivers/infiniband/hw/mlx4/
 F:	include/linux/mlx4/
+F:	include/uapi/rdma/mlx4-abi.h
 
 MELLANOX MLX5 core VPI driver
 M:	Saeed Mahameed <saeedm@mellanox.com>
@@ -8557,7 +8556,6 @@ Q:	http://patchwork.ozlabs.org/project/netdev/list/
 S:	Supported
 F:	drivers/net/ethernet/mellanox/mlx5/core/
 F:	include/linux/mlx5/
-F:	include/uapi/rdma/mlx5-abi.h
 
 MELLANOX MLX5 IB driver
 M:	Matan Barak <matanb@mellanox.com>
@@ -8568,6 +8566,7 @@ Q:	http://patchwork.kernel.org/project/linux-rdma/list/
 S:	Supported
 F:	drivers/infiniband/hw/mlx5/
 F:	include/linux/mlx5/
+F:	include/uapi/rdma/mlx5-abi.h
 
 MELEXIS MLX90614 DRIVER
 M:	Crt Mori <cmo@melexis.com>
@@ -8607,7 +8606,7 @@ S:	Maintained
 F:	drivers/media/dvb-frontends/mn88473*
 
 MODULE SUPPORT
-M:	Jessica Yu <jeyu@redhat.com>
+M:	Jessica Yu <jeyu@kernel.org>
 M:	Rusty Russell <rusty@rustcorp.com.au>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jeyu/linux.git modules-next
 S:	Maintained
@@ -10469,7 +10468,7 @@ S:	Orphan
 
 PXA RTC DRIVER
 M:	Robert Jarzmik <robert.jarzmik@free.fr>
-L:	rtc-linux@googlegroups.com
+L:	linux-rtc@vger.kernel.org
 S:	Maintained
 
 QAT DRIVER
@@ -10776,7 +10775,7 @@ X:	kernel/torture.c
 REAL TIME CLOCK (RTC) SUBSYSTEM
 M:	Alessandro Zummo <a.zummo@towertech.it>
 M:	Alexandre Belloni <alexandre.belloni@free-electrons.com>
-L:	rtc-linux@googlegroups.com
+L:	linux-rtc@vger.kernel.org
 Q:	http://patchwork.ozlabs.org/project/rtc-linux/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/abelloni/linux.git
 S:	Maintained
@@ -11287,7 +11286,6 @@ F:	drivers/media/rc/serial_ir.c
 
 STI CEC DRIVER
 M:	Benjamin Gaignard <benjamin.gaignard@linaro.org>
-L:	kernel@stlinux.com
 S:	Maintained
 F:	drivers/staging/media/st-cec/
 F:	Documentation/devicetree/bindings/media/stih-cec.txt
@@ -11797,6 +11795,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/nsekhar/linux-davinci.git
 S:	Supported
 F:	arch/arm/mach-davinci/
 F:	drivers/i2c/busses/i2c-davinci.c
+F:	arch/arm/boot/dts/da850*
 
 TI DAVINCI SERIES MEDIA DRIVER
 M:	"Lad, Prabhakar" <prabhakar.csengg@gmail.com>
@@ -13880,7 +13879,7 @@ S:	Odd fixes
 F:	drivers/net/wireless/wl3501*
 
 WOLFSON MICROELECTRONICS DRIVERS
-L:	patches@opensource.wolfsonmicro.com
+L:	patches@opensource.cirrus.com
 T:	git https://github.com/CirrusLogic/linux-drivers.git
 W:	https://github.com/CirrusLogic/linux-drivers/wiki
 S:	Supported

Makefile

@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 12
 SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc5
 NAME = Fearless Coyote
 
 # *DOCUMENTATION*

arch/arm/boot/compressed/efi-header.S

@@ -17,14 +17,12 @@
 		@ there.
 		.inst	'M' | ('Z' << 8) | (0x1310 << 16)   @ tstne r0, #0x4d000
 #else
-		mov	r0, r0
+		W(mov)	r0, r0
 #endif
 		.endm
 
 		.macro	__EFI_HEADER
 #ifdef CONFIG_EFI_STUB
-		b	__efi_start
-
 		.set	start_offset, __efi_start - start
 		.org	start + 0x3c
 		@

arch/arm/boot/compressed/head.S

@@ -130,19 +130,22 @@ start:
 		.rept	7
 		__nop
 		.endr
-   ARM(		mov	r0, r0		)
-   ARM(		b	1f		)
- THUMB(		badr	r12, 1f		)
- THUMB(		bx	r12		)
+#ifndef CONFIG_THUMB2_KERNEL
+		mov	r0, r0
+#else
+ AR_CLASS(	sub	pc, pc, #3	)	@ A/R: switch to Thumb2 mode
+  M_CLASS(	nop.w			)	@ M: already in Thumb2 mode
+		.thumb
+#endif
+		W(b)	1f
 
 		.word	_magic_sig	@ Magic numbers to help the loader
 		.word	_magic_start	@ absolute load/run zImage address
 		.word	_magic_end	@ zImage end address
 		.word	0x04030201	@ endianness flag
 
- THUMB(		.thumb			)
-1:		__EFI_HEADER
-
+		__EFI_HEADER
+1:
  ARM_BE8(	setend	be		)	@ go BE8 if compiled for BE8
  AR_CLASS(	mrs	r9, cpsr	)
 #ifdef CONFIG_ARM_VIRT_EXT

arch/arm/boot/dts/bcm283x.dtsi

@@ -3,6 +3,11 @@
 #include <dt-bindings/clock/bcm2835-aux.h>
 #include <dt-bindings/gpio/gpio.h>
 
+/* firmware-provided startup stubs live here, where the secondary CPUs are
+ * spinning.
+ */
+/memreserve/ 0x00000000 0x00001000;
+
 /* This include file covers the common peripherals and configuration between
  * bcm2835 and bcm2836 implementations, leaving the CPU configuration to
  * bcm2835.dtsi and bcm2836.dtsi.

arch/arm/boot/dts/imx6ul-14x14-evk.dts

@@ -120,10 +120,16 @@
 
 		ethphy0: ethernet-phy@2 {
 			reg = <2>;
+			micrel,led-mode = <1>;
+			clocks = <&clks IMX6UL_CLK_ENET_REF>;
+			clock-names = "rmii-ref";
 		};
 
 		ethphy1: ethernet-phy@1 {
 			reg = <1>;
+			micrel,led-mode = <1>;
+			clocks = <&clks IMX6UL_CLK_ENET2_REF>;
+			clock-names = "rmii-ref";
 		};
 	};
 };

arch/arm/boot/dts/keystone-k2l-netcp.dtsi

@@ -137,8 +137,8 @@ netcp: netcp@26000000 {
 	/* NetCP address range */
 	ranges = <0 0x26000000 0x1000000>;
 
-	clocks = <&clkpa>, <&clkcpgmac>, <&chipclk12>, <&clkosr>;
-	clock-names = "pa_clk", "ethss_clk", "cpts", "osr_clk";
+	clocks = <&clkpa>, <&clkcpgmac>, <&chipclk12>;
+	clock-names = "pa_clk", "ethss_clk", "cpts";
 	dma-coherent;
 
 	ti,navigator-dmas = <&dma_gbe 0>,

arch/arm/boot/dts/keystone-k2l.dtsi

@@ -232,6 +232,14 @@
 			};
 		};
 
+		osr: sram@70000000 {
+			compatible = "mmio-sram";
+			reg = <0x70000000 0x10000>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			clocks = <&clkosr>;
+		};
+
 		dspgpio0: keystone_dsp_gpio@02620240 {
 			compatible = "ti,keystone-dsp-gpio";
 			gpio-controller;

arch/arm/boot/dts/versatile-pb.dts

@@ -1,4 +1,4 @@
-#include <versatile-ab.dts>
+#include "versatile-ab.dts"
 
 / {
 	model = "ARM Versatile PB";

arch/arm/common/mcpm_entry.c

@@ -235,7 +235,7 @@ int mcpm_cpu_power_up(unsigned int cpu, unsigned int cluster)
 	return ret;
 }
 
-typedef void (*phys_reset_t)(unsigned long);
+typedef typeof(cpu_reset) phys_reset_t;
 
 void mcpm_cpu_power_down(void)
 {
@@ -300,7 +300,7 @@ void mcpm_cpu_power_down(void)
 	 * on the CPU.
 	 */
 	phys_reset = (phys_reset_t)(unsigned long)__pa_symbol(cpu_reset);
-	phys_reset(__pa_symbol(mcpm_entry_point));
+	phys_reset(__pa_symbol(mcpm_entry_point), false);
 
 	/* should never get here */
 	BUG();
@@ -389,7 +389,7 @@ static int __init nocache_trampoline(unsigned long _arg)
 	__mcpm_cpu_down(cpu, cluster);
 
 	phys_reset = (phys_reset_t)(unsigned long)__pa_symbol(cpu_reset);
-	phys_reset(__pa_symbol(mcpm_entry_point));
+	phys_reset(__pa_symbol(mcpm_entry_point), false);
 	BUG();
 }
 

arch/arm/include/asm/device.h

@@ -19,7 +19,8 @@ struct dev_archdata {
 #ifdef CONFIG_XEN
 	const struct dma_map_ops *dev_dma_ops;
 #endif
-	bool dma_coherent;
+	unsigned int dma_coherent:1;
+	unsigned int dma_ops_setup:1;
 };
 
 struct omap_device;

arch/arm/include/asm/pgtable-nommu.h

@@ -66,6 +66,7 @@ typedef pte_t *pte_addr_t;
 #define pgprot_noncached(prot)	(prot)
 #define pgprot_writecombine(prot) (prot)
 #define pgprot_dmacoherent(prot) (prot)
+#define pgprot_device(prot)	(prot)
 
 
 /*

arch/arm/kvm/init.S

@@ -104,7 +104,6 @@ __do_hyp_init:
 	@  - Write permission implies XN: disabled
 	@  - Instruction cache: enabled
 	@  - Data/Unified cache: enabled
-	@  - Memory alignment checks: enabled
 	@  - MMU: enabled (this code must be run from an identity mapping)
 	mrc	p15, 4, r0, c1, c0, 0	@ HSCR
 	ldr	r2, =HSCTLR_MASK
@@ -112,8 +111,8 @@ __do_hyp_init:
 	mrc	p15, 0, r1, c1, c0, 0	@ SCTLR
 	ldr	r2, =(HSCTLR_EE | HSCTLR_FI | HSCTLR_I | HSCTLR_C)
 	and	r1, r1, r2
- ARM(	ldr	r2, =(HSCTLR_M | HSCTLR_A)			)
- THUMB(	ldr	r2, =(HSCTLR_M | HSCTLR_A | HSCTLR_TE)		)
+ ARM(	ldr	r2, =(HSCTLR_M)					)
+ THUMB(	ldr	r2, =(HSCTLR_M | HSCTLR_TE)			)
 	orr	r1, r1, r2
 	orr	r0, r0, r1
 	mcr	p15, 4, r0, c1, c0, 0	@ HSCR

arch/arm/mach-at91/Kconfig

@@ -1,6 +1,7 @@
 menuconfig ARCH_AT91
 	bool "Atmel SoCs"
 	depends on ARCH_MULTI_V4T || ARCH_MULTI_V5 || ARCH_MULTI_V7
+	select ARM_CPU_SUSPEND if PM
 	select COMMON_CLK_AT91
 	select GPIOLIB
 	select PINCTRL

arch/arm/mach-davinci/pm.c

@@ -153,7 +153,8 @@ int __init davinci_pm_init(void)
 	davinci_sram_suspend = sram_alloc(davinci_cpu_suspend_sz, NULL);
 	if (!davinci_sram_suspend) {
 		pr_err("PM: cannot allocate SRAM memory\n");
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto no_sram_mem;
 	}
 
 	davinci_sram_push(davinci_sram_suspend, davinci_cpu_suspend,
@@ -161,6 +162,10 @@ int __init davinci_pm_init(void)
 
 	suspend_set_ops(&davinci_pm_ops);
 
+	return 0;
+
+no_sram_mem:
+	iounmap(pm_config.ddrpsc_reg_base);
 no_ddrpsc_mem:
 	iounmap(pm_config.ddrpll_reg_base);
 no_ddrpll_mem:

arch/arm/mm/dma-mapping.c

@@ -2311,7 +2311,14 @@ int arm_iommu_attach_device(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(arm_iommu_attach_device);
 
-static void __arm_iommu_detach_device(struct device *dev)
+/**
+ * arm_iommu_detach_device
+ * @dev: valid struct device pointer
+ *
+ * Detaches the provided device from a previously attached map.
+ * This voids the dma operations (dma_map_ops pointer)
+ */
+void arm_iommu_detach_device(struct device *dev)
 {
 	struct dma_iommu_mapping *mapping;
 
@@ -2324,22 +2331,10 @@ static void __arm_iommu_detach_device(struct device *dev)
 	iommu_detach_device(mapping->domain, dev);
 	kref_put(&mapping->kref, release_iommu_mapping);
 	to_dma_iommu_mapping(dev) = NULL;
+	set_dma_ops(dev, NULL);
 
 	pr_debug("Detached IOMMU controller from %s device.\n", dev_name(dev));
 }
-
-/**
- * arm_iommu_detach_device
- * @dev: valid struct device pointer
- *
- * Detaches the provided device from a previously attached map.
- * This voids the dma operations (dma_map_ops pointer)
- */
-void arm_iommu_detach_device(struct device *dev)
-{
-	__arm_iommu_detach_device(dev);
-	set_dma_ops(dev, NULL);
-}
 EXPORT_SYMBOL_GPL(arm_iommu_detach_device);
 
 static const struct dma_map_ops *arm_get_iommu_dma_map_ops(bool coherent)
@@ -2379,7 +2374,7 @@ static void arm_teardown_iommu_dma_ops(struct device *dev)
 	if (!mapping)
 		return;
 
-	__arm_iommu_detach_device(dev);
+	arm_iommu_detach_device(dev);
 	arm_iommu_release_mapping(mapping);
 }
 
@@ -2430,9 +2425,13 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 		dev->dma_ops = xen_dma_ops;
 	}
 #endif
+	dev->archdata.dma_ops_setup = true;
 }
 
 void arch_teardown_dma_ops(struct device *dev)
 {
+	if (!dev->archdata.dma_ops_setup)
+		return;
+
 	arm_teardown_iommu_dma_ops(dev);
 }

arch/arm64/Kconfig

@@ -1084,10 +1084,6 @@ config SYSVIPC_COMPAT
 	def_bool y
 	depends on COMPAT && SYSVIPC
 
-config KEYS_COMPAT
-	def_bool y
-	depends on COMPAT && KEYS
-
 endmenu
 
 menu "Power management options"

arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi

@@ -231,8 +231,7 @@
 			cpm_crypto: crypto@800000 {
 				compatible = "inside-secure,safexcel-eip197";
 				reg = <0x800000 0x200000>;
-				interrupts = <GIC_SPI 34 (IRQ_TYPE_EDGE_RISING
-				| IRQ_TYPE_LEVEL_HIGH)>,
+				interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 56 IRQ_TYPE_LEVEL_HIGH>,

arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi

@@ -221,8 +221,7 @@
 			cps_crypto: crypto@800000 {
 				compatible = "inside-secure,safexcel-eip197";
 				reg = <0x800000 0x200000>;
-				interrupts = <GIC_SPI 34 (IRQ_TYPE_EDGE_RISING
-				| IRQ_TYPE_LEVEL_HIGH)>,
+				interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 278 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 279 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 280 IRQ_TYPE_LEVEL_HIGH>,

arch/arm64/configs/defconfig

@@ -68,6 +68,7 @@ CONFIG_PCIE_QCOM=y
 CONFIG_PCIE_ARMADA_8K=y
 CONFIG_PCI_AARDVARK=y
 CONFIG_PCIE_RCAR=y
+CONFIG_PCIE_ROCKCHIP=m
 CONFIG_PCI_HOST_GENERIC=y
 CONFIG_PCI_XGENE=y
 CONFIG_ARM64_VA_BITS_48=y
@@ -208,6 +209,8 @@ CONFIG_BRCMFMAC=m
 CONFIG_WL18XX=m
 CONFIG_WLCORE_SDIO=m
 CONFIG_INPUT_EVDEV=y
+CONFIG_KEYBOARD_ADC=m
+CONFIG_KEYBOARD_CROS_EC=y
 CONFIG_KEYBOARD_GPIO=y
 CONFIG_INPUT_MISC=y
 CONFIG_INPUT_PM8941_PWRKEY=y
@@ -263,6 +266,7 @@ CONFIG_SPI_MESON_SPIFC=m
 CONFIG_SPI_ORION=y
 CONFIG_SPI_PL022=y
 CONFIG_SPI_QUP=y
+CONFIG_SPI_ROCKCHIP=y
 CONFIG_SPI_S3C64XX=y
 CONFIG_SPI_SPIDEV=m
 CONFIG_SPMI=y
@@ -292,6 +296,7 @@ CONFIG_THERMAL_GOV_POWER_ALLOCATOR=y
 CONFIG_CPU_THERMAL=y
 CONFIG_THERMAL_EMULATION=y
 CONFIG_EXYNOS_THERMAL=y
+CONFIG_ROCKCHIP_THERMAL=m
 CONFIG_WATCHDOG=y
 CONFIG_S3C2410_WATCHDOG=y
 CONFIG_MESON_GXBB_WATCHDOG=m
@@ -300,12 +305,14 @@ CONFIG_RENESAS_WDT=y
 CONFIG_BCM2835_WDT=y
 CONFIG_MFD_CROS_EC=y
 CONFIG_MFD_CROS_EC_I2C=y
+CONFIG_MFD_CROS_EC_SPI=y
 CONFIG_MFD_EXYNOS_LPASS=m
 CONFIG_MFD_HI655X_PMIC=y
 CONFIG_MFD_MAX77620=y
 CONFIG_MFD_SPMI_PMIC=y
 CONFIG_MFD_RK808=y
 CONFIG_MFD_SEC_CORE=y
+CONFIG_REGULATOR_FAN53555=y
 CONFIG_REGULATOR_FIXED_VOLTAGE=y
 CONFIG_REGULATOR_GPIO=y
 CONFIG_REGULATOR_HI655X=y
@@ -473,8 +480,10 @@ CONFIG_ARCH_TEGRA_186_SOC=y
 CONFIG_EXTCON_USB_GPIO=y
 CONFIG_IIO=y
 CONFIG_EXYNOS_ADC=y
+CONFIG_ROCKCHIP_SARADC=m
 CONFIG_PWM=y
 CONFIG_PWM_BCM2835=m
+CONFIG_PWM_CROS_EC=m
 CONFIG_PWM_MESON=m
 CONFIG_PWM_ROCKCHIP=y
 CONFIG_PWM_SAMSUNG=y
@@ -484,6 +493,7 @@ CONFIG_PHY_HI6220_USB=y
 CONFIG_PHY_SUN4I_USB=y
 CONFIG_PHY_ROCKCHIP_INNO_USB2=y
 CONFIG_PHY_ROCKCHIP_EMMC=y
+CONFIG_PHY_ROCKCHIP_PCIE=m
 CONFIG_PHY_XGENE=y
 CONFIG_PHY_TEGRA_XUSB=y
 CONFIG_ARM_SCPI_PROTOCOL=y

arch/arm64/include/asm/acpi.h

@@ -23,9 +23,9 @@
 #define ACPI_MADT_GICC_LENGTH	\
 	(acpi_gbl_FADT.header.revision < 6 ? 76 : 80)
 
-#define BAD_MADT_GICC_ENTRY(entry, end)						\
-	(!(entry) || (unsigned long)(entry) + sizeof(*(entry)) > (end) ||	\
-	 (entry)->header.length != ACPI_MADT_GICC_LENGTH)
+#define BAD_MADT_GICC_ENTRY(entry, end)					\
+	(!(entry) || (entry)->header.length != ACPI_MADT_GICC_LENGTH ||	\
+	(unsigned long)(entry) + ACPI_MADT_GICC_LENGTH > (end))
 
 /* Basic configuration for ACPI */
 #ifdef	CONFIG_ACPI

arch/arm64/include/asm/sysreg.h

@@ -286,6 +286,10 @@
 #define SCTLR_ELx_A	(1 << 1)
 #define SCTLR_ELx_M	1
 
+#define SCTLR_EL2_RES1	((1 << 4)  | (1 << 5)  | (1 << 11) | (1 << 16) | \
+			 (1 << 16) | (1 << 18) | (1 << 22) | (1 << 23) | \
+			 (1 << 28) | (1 << 29))
+
 #define SCTLR_ELx_FLAGS	(SCTLR_ELx_M | SCTLR_ELx_A | SCTLR_ELx_C | \
 			 SCTLR_ELx_SA | SCTLR_ELx_I)
 

arch/arm64/kernel/pci.c

@@ -191,8 +191,10 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
 		return NULL;
 
 	root_ops = kzalloc_node(sizeof(*root_ops), GFP_KERNEL, node);
-	if (!root_ops)
+	if (!root_ops) {
+		kfree(ri);
 		return NULL;
+	}
 
 	ri->cfg = pci_acpi_setup_ecam_mapping(root);
 	if (!ri->cfg) {

arch/arm64/kvm/hyp-init.S

@@ -106,10 +106,13 @@ __do_hyp_init:
 	tlbi	alle2
 	dsb	sy
 
-	mrs	x4, sctlr_el2
-	and	x4, x4, #SCTLR_ELx_EE	// preserve endianness of EL2
-	ldr	x5, =SCTLR_ELx_FLAGS
-	orr	x4, x4, x5
+	/*
+	 * Preserve all the RES1 bits while setting the default flags,
+	 * as well as the EE bit on BE. Drop the A flag since the compiler
+	 * is allowed to generate unaligned accesses.
+	 */
+	ldr	x4, =(SCTLR_EL2_RES1 | (SCTLR_ELx_FLAGS & ~SCTLR_ELx_A))
+CPU_BE(	orr	x4, x4, #SCTLR_ELx_EE)
 	msr	sctlr_el2, x4
 	isb
 

arch/arm64/kvm/vgic-sys-reg-v3.c

@@ -65,8 +65,8 @@ static bool access_gic_ctlr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		 * Here set VMCR.CTLR in ICC_CTLR_EL1 layout.
 		 * The vgic_set_vmcr() will convert to ICH_VMCR layout.
 		 */
-		vmcr.ctlr = val & ICC_CTLR_EL1_CBPR_MASK;
-		vmcr.ctlr |= val & ICC_CTLR_EL1_EOImode_MASK;
+		vmcr.cbpr = (val & ICC_CTLR_EL1_CBPR_MASK) >> ICC_CTLR_EL1_CBPR_SHIFT;
+		vmcr.eoim = (val & ICC_CTLR_EL1_EOImode_MASK) >> ICC_CTLR_EL1_EOImode_SHIFT;
 		vgic_set_vmcr(vcpu, &vmcr);
 	} else {
 		val = 0;
@@ -83,8 +83,8 @@ static bool access_gic_ctlr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		 * The VMCR.CTLR value is in ICC_CTLR_EL1 layout.
 		 * Extract it directly using ICC_CTLR_EL1 reg definitions.
 		 */
-		val |= vmcr.ctlr & ICC_CTLR_EL1_CBPR_MASK;
-		val |= vmcr.ctlr & ICC_CTLR_EL1_EOImode_MASK;
+		val |= (vmcr.cbpr << ICC_CTLR_EL1_CBPR_SHIFT) & ICC_CTLR_EL1_CBPR_MASK;
+		val |= (vmcr.eoim << ICC_CTLR_EL1_EOImode_SHIFT) & ICC_CTLR_EL1_EOImode_MASK;
 
 		p->regval = val;
 	}
@@ -135,7 +135,7 @@ static bool access_gic_bpr1(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		p->regval = 0;
 
 	vgic_get_vmcr(vcpu, &vmcr);
-	if (!((vmcr.ctlr & ICH_VMCR_CBPR_MASK) >> ICH_VMCR_CBPR_SHIFT)) {
+	if (!vmcr.cbpr) {
 		if (p->is_write) {
 			vmcr.abpr = (p->regval & ICC_BPR1_EL1_MASK) >>
 				     ICC_BPR1_EL1_SHIFT;

arch/frv/include/asm/timex.h

@@ -16,5 +16,11 @@ static inline cycles_t get_cycles(void)
 #define vxtime_lock()		do {} while (0)
 #define vxtime_unlock()		do {} while (0)
 
+/* This attribute is used in include/linux/jiffies.h alongside with
+ * __cacheline_aligned_in_smp. It is assumed that __cacheline_aligned_in_smp
+ * for frv does not contain another section specification.
+ */
+#define __jiffy_arch_data	__attribute__((__section__(".data")))
+
 #endif
 

arch/hexagon/mm/uaccess.c

@@ -37,15 +37,14 @@ __kernel_size_t __clear_user_hexagon(void __user *dest, unsigned long count)
 	long uncleared;
 
 	while (count > PAGE_SIZE) {
-		uncleared = __copy_to_user_hexagon(dest, &empty_zero_page,
-						PAGE_SIZE);
+		uncleared = raw_copy_to_user(dest, &empty_zero_page, PAGE_SIZE);
 		if (uncleared)
 			return count - (PAGE_SIZE - uncleared);
 		count -= PAGE_SIZE;
 		dest += PAGE_SIZE;
 	}
 	if (count)
-		count = __copy_to_user_hexagon(dest, &empty_zero_page, count);
+		count = raw_copy_to_user(dest, &empty_zero_page, count);
 
 	return count;
 }

arch/mips/kernel/process.c

@@ -120,7 +120,6 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long usp,
 	struct thread_info *ti = task_thread_info(p);
 	struct pt_regs *childregs, *regs = current_pt_regs();
 	unsigned long childksp;
-	p->set_child_tid = p->clear_child_tid = NULL;
 
 	childksp = (unsigned long)task_stack_page(p) + THREAD_SIZE - 32;
 

arch/openrisc/kernel/process.c

@@ -167,8 +167,6 @@ copy_thread(unsigned long clone_flags, unsigned long usp,
 
 	top_of_kernel_stack = sp;
 
-	p->set_child_tid = p->clear_child_tid = NULL;
-
 	/* Locate userspace context on stack... */
 	sp -= STACK_FRAME_OVERHEAD;	/* redzone */
 	sp -= sizeof(struct pt_regs);

arch/powerpc/Kconfig

@@ -380,22 +380,6 @@ source "arch/powerpc/platforms/Kconfig"
 
 menu "Kernel options"
 
-config PPC_DT_CPU_FTRS
-	bool "Device-tree based CPU feature discovery & setup"
-	depends on PPC_BOOK3S_64
-	default n
-	help
-	  This enables code to use a new device tree binding for describing CPU
-	  compatibility and features. Saying Y here will attempt to use the new
-	  binding if the firmware provides it. Currently only the skiboot
-	  firmware provides this binding.
-	  If you're not sure say Y.
-
-config PPC_CPUFEATURES_ENABLE_UNKNOWN
-	bool "cpufeatures pass through unknown features to guest/userspace"
-	depends on PPC_DT_CPU_FTRS
-	default y
-
 config HIGHMEM
 	bool "High memory support"
 	depends on PPC32
@@ -1215,11 +1199,6 @@ source "arch/powerpc/Kconfig.debug"
 
 source "security/Kconfig"
 
-config KEYS_COMPAT
-	bool
-	depends on COMPAT && KEYS
-	default y
-
 source "crypto/Kconfig"
 
 config PPC_LIB_RHEAP

arch/powerpc/include/asm/book3s/64/hash-4k.h

@@ -8,7 +8,7 @@
 #define H_PTE_INDEX_SIZE  9
 #define H_PMD_INDEX_SIZE  7
 #define H_PUD_INDEX_SIZE  9
-#define H_PGD_INDEX_SIZE  12
+#define H_PGD_INDEX_SIZE  9
 
 #ifndef __ASSEMBLY__
 #define H_PTE_TABLE_SIZE	(sizeof(pte_t) << H_PTE_INDEX_SIZE)

arch/powerpc/include/asm/cputable.h

@@ -214,7 +214,6 @@ enum {
 #define CPU_FTR_DAWR			LONG_ASM_CONST(0x0400000000000000)
 #define CPU_FTR_DABRX			LONG_ASM_CONST(0x0800000000000000)
 #define CPU_FTR_PMAO_BUG		LONG_ASM_CONST(0x1000000000000000)
-#define CPU_FTR_SUBCORE			LONG_ASM_CONST(0x2000000000000000)
 #define CPU_FTR_POWER9_DD1		LONG_ASM_CONST(0x4000000000000000)
 
 #ifndef __ASSEMBLY__
@@ -463,7 +462,7 @@ enum {
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
 	    CPU_FTR_ICSWX | CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
 	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \
-	    CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_SUBCORE)
+	    CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP)
 #define CPU_FTRS_POWER8E (CPU_FTRS_POWER8 | CPU_FTR_PMAO_BUG)
 #define CPU_FTRS_POWER8_DD1 (CPU_FTRS_POWER8 & ~CPU_FTR_DBELL)
 #define CPU_FTRS_POWER9 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \

arch/powerpc/include/asm/processor.h

@@ -110,13 +110,18 @@ void release_thread(struct task_struct *);
 #define TASK_SIZE_128TB (0x0000800000000000UL)
 #define TASK_SIZE_512TB (0x0002000000000000UL)
 
-#ifdef CONFIG_PPC_BOOK3S_64
+/*
+ * For now 512TB is only supported with book3s and 64K linux page size.
+ */
+#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_64K_PAGES)
 /*
  * Max value currently used:
  */
-#define TASK_SIZE_USER64	TASK_SIZE_512TB
+#define TASK_SIZE_USER64		TASK_SIZE_512TB
+#define DEFAULT_MAP_WINDOW_USER64	TASK_SIZE_128TB
 #else
-#define TASK_SIZE_USER64	TASK_SIZE_64TB
+#define TASK_SIZE_USER64		TASK_SIZE_64TB
+#define DEFAULT_MAP_WINDOW_USER64	TASK_SIZE_64TB
 #endif
 
 /*
@@ -132,7 +137,7 @@ void release_thread(struct task_struct *);
  * space during mmap's.
  */
 #define TASK_UNMAPPED_BASE_USER32 (PAGE_ALIGN(TASK_SIZE_USER32 / 4))
-#define TASK_UNMAPPED_BASE_USER64 (PAGE_ALIGN(TASK_SIZE_128TB / 4))
+#define TASK_UNMAPPED_BASE_USER64 (PAGE_ALIGN(DEFAULT_MAP_WINDOW_USER64 / 4))
 
 #define TASK_UNMAPPED_BASE ((is_32bit_task()) ? \
 		TASK_UNMAPPED_BASE_USER32 : TASK_UNMAPPED_BASE_USER64 )
@@ -143,21 +148,15 @@ void release_thread(struct task_struct *);
  * with 128TB and conditionally enable upto 512TB
  */
 #ifdef CONFIG_PPC_BOOK3S_64
-#define DEFAULT_MAP_WINDOW	((is_32bit_task()) ? \
-				 TASK_SIZE_USER32 : TASK_SIZE_128TB)
+#define DEFAULT_MAP_WINDOW	((is_32bit_task()) ?			\
+				 TASK_SIZE_USER32 : DEFAULT_MAP_WINDOW_USER64)
 #else
 #define DEFAULT_MAP_WINDOW	TASK_SIZE
 #endif
 
 #ifdef __powerpc64__
 
-#ifdef CONFIG_PPC_BOOK3S_64
-/* Limit stack to 128TB */
-#define STACK_TOP_USER64 TASK_SIZE_128TB
-#else
-#define STACK_TOP_USER64 TASK_SIZE_USER64
-#endif
-
+#define STACK_TOP_USER64 DEFAULT_MAP_WINDOW_USER64
 #define STACK_TOP_USER32 TASK_SIZE_USER32
 
 #define STACK_TOP (is_32bit_task() ? \

arch/powerpc/include/asm/topology.h

@@ -44,8 +44,22 @@ extern void __init dump_numa_cpu_topology(void);
 extern int sysfs_add_device_to_node(struct device *dev, int nid);
 extern void sysfs_remove_device_from_node(struct device *dev, int nid);
 
+static inline int early_cpu_to_node(int cpu)
+{
+	int nid;
+
+	nid = numa_cpu_lookup_table[cpu];
+
+	/*
+	 * Fall back to node 0 if nid is unset (it should be, except bugs).
+	 * This allows callers to safely do NODE_DATA(early_cpu_to_node(cpu)).
+	 */
+	return (nid < 0) ? 0 : nid;
+}
 #else
 
+static inline int early_cpu_to_node(int cpu) { return 0; }
+
 static inline void dump_numa_cpu_topology(void) {}
 
 static inline int sysfs_add_device_to_node(struct device *dev, int nid)

arch/powerpc/kernel/dt_cpu_ftrs.c

@@ -8,6 +8,7 @@
 #include <linux/export.h>
 #include <linux/init.h>
 #include <linux/jump_label.h>
+#include <linux/libfdt.h>
 #include <linux/memblock.h>
 #include <linux/printk.h>
 #include <linux/sched.h>
@@ -642,7 +643,6 @@ static struct dt_cpu_feature_match __initdata
 	{"processor-control-facility", feat_enable_dbell, CPU_FTR_DBELL},
 	{"processor-control-facility-v3", feat_enable_dbell, CPU_FTR_DBELL},
 	{"processor-utilization-of-resources-register", feat_enable_purr, 0},
-	{"subcore", feat_enable, CPU_FTR_SUBCORE},
 	{"no-execute", feat_enable, 0},
 	{"strong-access-ordering", feat_enable, CPU_FTR_SAO},
 	{"cache-inhibited-large-page", feat_enable_large_ci, 0},
@@ -671,12 +671,24 @@ static struct dt_cpu_feature_match __initdata
 	{"wait-v3", feat_enable, 0},
 };
 
-/* XXX: how to configure this? Default + boot time? */
-#ifdef CONFIG_PPC_CPUFEATURES_ENABLE_UNKNOWN
-#define CPU_FEATURE_ENABLE_UNKNOWN 1
-#else
-#define CPU_FEATURE_ENABLE_UNKNOWN 0
-#endif
+static bool __initdata using_dt_cpu_ftrs;
+static bool __initdata enable_unknown = true;
+
+static int __init dt_cpu_ftrs_parse(char *str)
+{
+	if (!str)
+		return 0;
+
+	if (!strcmp(str, "off"))
+		using_dt_cpu_ftrs = false;
+	else if (!strcmp(str, "known"))
+		enable_unknown = false;
+	else
+		return 1;
+
+	return 0;
+}
+early_param("dt_cpu_ftrs", dt_cpu_ftrs_parse);
 
 static void __init cpufeatures_setup_start(u32 isa)
 {
@@ -707,7 +719,7 @@ static bool __init cpufeatures_process_feature(struct dt_cpu_feature *f)
 		}
 	}
 
-	if (!known && CPU_FEATURE_ENABLE_UNKNOWN) {
+	if (!known && enable_unknown) {
 		if (!feat_try_enable_unknown(f)) {
 			pr_info("not enabling: %s (unknown and unsupported by kernel)\n",
 				f->name);
@@ -756,6 +768,26 @@ static void __init cpufeatures_setup_finished(void)
 		cur_cpu_spec->cpu_features, cur_cpu_spec->mmu_features);
 }
 
+static int __init disabled_on_cmdline(void)
+{
+	unsigned long root, chosen;
+	const char *p;
+
+	root = of_get_flat_dt_root();
+	chosen = of_get_flat_dt_subnode_by_name(root, "chosen");
+	if (chosen == -FDT_ERR_NOTFOUND)
+		return false;
+
+	p = of_get_flat_dt_prop(chosen, "bootargs", NULL);
+	if (!p)
+		return false;
+
+	if (strstr(p, "dt_cpu_ftrs=off"))
+		return true;
+
+	return false;
+}
+
 static int __init fdt_find_cpu_features(unsigned long node, const char *uname,
 					int depth, void *data)
 {
@@ -766,8 +798,6 @@ static int __init fdt_find_cpu_features(unsigned long node, const char *uname,
 	return 0;
 }
 
-static bool __initdata using_dt_cpu_ftrs = false;
-
 bool __init dt_cpu_ftrs_in_use(void)
 {
 	return using_dt_cpu_ftrs;
@@ -775,6 +805,8 @@ bool __init dt_cpu_ftrs_in_use(void)
 
 bool __init dt_cpu_ftrs_init(void *fdt)
 {
+	using_dt_cpu_ftrs = false;
+
 	/* Setup and verify the FDT, if it fails we just bail */
 	if (!early_init_dt_verify(fdt))
 		return false;
@@ -782,6 +814,9 @@ bool __init dt_cpu_ftrs_init(void *fdt)
 	if (!of_scan_flat_dt(fdt_find_cpu_features, NULL))
 		return false;
 
+	if (disabled_on_cmdline())
+		return false;
+
 	cpufeatures_setup_cpu();
 
 	using_dt_cpu_ftrs = true;
@@ -1027,5 +1062,8 @@ static int __init dt_cpu_ftrs_scan_callback(unsigned long node, const char
 
 void __init dt_cpu_ftrs_scan(void)
 {
+	if (!using_dt_cpu_ftrs)
+		return;
+
 	of_scan_flat_dt(dt_cpu_ftrs_scan_callback, NULL);
 }

arch/powerpc/kernel/process.c

@@ -1666,6 +1666,7 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 #ifdef CONFIG_VSX
 	current->thread.used_vsr = 0;
 #endif
+	current->thread.load_fp = 0;
 	memset(&current->thread.fp_state, 0, sizeof(current->thread.fp_state));
 	current->thread.fp_save_area = NULL;
 #ifdef CONFIG_ALTIVEC
@@ -1674,6 +1675,7 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 	current->thread.vr_save_area = NULL;
 	current->thread.vrsave = 0;
 	current->thread.used_vr = 0;
+	current->thread.load_vec = 0;
 #endif /* CONFIG_ALTIVEC */
 #ifdef CONFIG_SPE
 	memset(current->thread.evr, 0, sizeof(current->thread.evr));
@@ -1685,6 +1687,7 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 	current->thread.tm_tfhar = 0;
 	current->thread.tm_texasr = 0;
 	current->thread.tm_tfiar = 0;
+	current->thread.load_tm = 0;
 #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
 }
 EXPORT_SYMBOL(start_thread);

arch/powerpc/kernel/setup-common.c

@@ -928,7 +928,7 @@ void __init setup_arch(char **cmdline_p)
 
 #ifdef CONFIG_PPC_MM_SLICES
 #ifdef CONFIG_PPC64
-	init_mm.context.addr_limit = TASK_SIZE_128TB;
+	init_mm.context.addr_limit = DEFAULT_MAP_WINDOW_USER64;
 #else
 #error	"context.addr_limit not initialized."
 #endif

arch/powerpc/kernel/setup_64.c

@@ -661,7 +661,7 @@ void __init emergency_stack_init(void)
 
 static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
 {
-	return __alloc_bootmem_node(NODE_DATA(cpu_to_node(cpu)), size, align,
+	return __alloc_bootmem_node(NODE_DATA(early_cpu_to_node(cpu)), size, align,
 				    __pa(MAX_DMA_ADDRESS));
 }
 
@@ -672,7 +672,7 @@ static void __init pcpu_fc_free(void *ptr, size_t size)
 
 static int pcpu_cpu_distance(unsigned int from, unsigned int to)
 {
-	if (cpu_to_node(from) == cpu_to_node(to))
+	if (early_cpu_to_node(from) == early_cpu_to_node(to))
 		return LOCAL_DISTANCE;
 	else
 		return REMOTE_DISTANCE;

arch/powerpc/mm/mmu_context_book3s64.c

@@ -99,7 +99,7 @@ static int hash__init_new_context(struct mm_struct *mm)
 	 * mm->context.addr_limit. Default to max task size so that we copy the
 	 * default values to paca which will help us to handle slb miss early.
 	 */
-	mm->context.addr_limit = TASK_SIZE_128TB;
+	mm->context.addr_limit = DEFAULT_MAP_WINDOW_USER64;
 
 	/*
 	 * The old code would re-promote on fork, we don't do that when using

arch/powerpc/perf/power9-pmu.c

@@ -402,7 +402,7 @@ static struct power_pmu power9_isa207_pmu = {
 	.name			= "POWER9",
 	.n_counter		= MAX_PMU_COUNTERS,
 	.add_fields		= ISA207_ADD_FIELDS,
-	.test_adder		= ISA207_TEST_ADDER,
+	.test_adder		= P9_DD1_TEST_ADDER,
 	.compute_mmcr		= isa207_compute_mmcr,
 	.config_bhrb		= power9_config_bhrb,
 	.bhrb_filter_map	= power9_bhrb_filter_map,
@@ -421,7 +421,7 @@ static struct power_pmu power9_pmu = {
 	.name			= "POWER9",
 	.n_counter		= MAX_PMU_COUNTERS,
 	.add_fields		= ISA207_ADD_FIELDS,
-	.test_adder		= P9_DD1_TEST_ADDER,
+	.test_adder		= ISA207_TEST_ADDER,
 	.compute_mmcr		= isa207_compute_mmcr,
 	.config_bhrb		= power9_config_bhrb,
 	.bhrb_filter_map	= power9_bhrb_filter_map,

arch/powerpc/platforms/Kconfig

@@ -59,6 +59,17 @@ config PPC_OF_BOOT_TRAMPOLINE
 
 	  In case of doubt, say Y
 
+config PPC_DT_CPU_FTRS
+	bool "Device-tree based CPU feature discovery & setup"
+	depends on PPC_BOOK3S_64
+	default y
+	help
+	  This enables code to use a new device tree binding for describing CPU
+	  compatibility and features. Saying Y here will attempt to use the new
+	  binding if the firmware provides it. Currently only the skiboot
+	  firmware provides this binding.
+	  If you're not sure say Y.
+
 config UDBG_RTAS_CONSOLE
 	bool "RTAS based debug console"
 	depends on PPC_RTAS

arch/powerpc/platforms/cell/spufs/coredump.c

@@ -175,6 +175,8 @@ static int spufs_arch_write_note(struct spu_context *ctx, int i,
 	skip = roundup(cprm->pos - total + sz, 4) - cprm->pos;
 	if (!dump_skip(cprm, skip))
 		goto Eio;
+
+	rc = 0;
 out:
 	free_page((unsigned long)buf);
 	return rc;

arch/powerpc/platforms/powernv/subcore.c

@@ -407,7 +407,13 @@ static DEVICE_ATTR(subcores_per_core, 0644,
 
 static int subcore_init(void)
 {
-	if (!cpu_has_feature(CPU_FTR_SUBCORE))
+	unsigned pvr_ver;
+
+	pvr_ver = PVR_VER(mfspr(SPRN_PVR));
+
+	if (pvr_ver != PVR_POWER8 &&
+	    pvr_ver != PVR_POWER8E &&
+	    pvr_ver != PVR_POWER8NVL)
 		return 0;
 
 	/*

arch/powerpc/platforms/pseries/hotplug-memory.c

@@ -124,6 +124,7 @@ static struct property *dlpar_clone_drconf_property(struct device_node *dn)
 	for (i = 0; i < num_lmbs; i++) {
 		lmbs[i].base_addr = be64_to_cpu(lmbs[i].base_addr);
 		lmbs[i].drc_index = be32_to_cpu(lmbs[i].drc_index);
+		lmbs[i].aa_index = be32_to_cpu(lmbs[i].aa_index);
 		lmbs[i].flags = be32_to_cpu(lmbs[i].flags);
 	}
 
@@ -147,6 +148,7 @@ static void dlpar_update_drconf_property(struct device_node *dn,
 	for (i = 0; i < num_lmbs; i++) {
 		lmbs[i].base_addr = cpu_to_be64(lmbs[i].base_addr);
 		lmbs[i].drc_index = cpu_to_be32(lmbs[i].drc_index);
+		lmbs[i].aa_index = cpu_to_be32(lmbs[i].aa_index);
 		lmbs[i].flags = cpu_to_be32(lmbs[i].flags);
 	}
 

arch/powerpc/sysdev/simple_gpio.c

@@ -75,7 +75,8 @@ static int u8_gpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
 
 static void u8_gpio_save_regs(struct of_mm_gpio_chip *mm_gc)
 {
-	struct u8_gpio_chip *u8_gc = gpiochip_get_data(&mm_gc->gc);
+	struct u8_gpio_chip *u8_gc =
+		container_of(mm_gc, struct u8_gpio_chip, mm_gc);
 
 	u8_gc->data = in_8(mm_gc->regs);
 }

arch/s390/Kconfig

@@ -363,9 +363,6 @@ config COMPAT
 config SYSVIPC_COMPAT
 	def_bool y if COMPAT && SYSVIPC
 
-config KEYS_COMPAT
-	def_bool y if COMPAT && KEYS
-
 config SMP
 	def_bool y
 	prompt "Symmetric multi-processing support"

arch/s390/include/asm/kvm_host.h

@@ -541,7 +541,6 @@ struct kvm_s390_float_interrupt {
 	struct mutex ais_lock;
 	u8 simm;
 	u8 nimm;
-	int ais_enabled;
 };
 
 struct kvm_hw_wp_info_arch {

arch/s390/kvm/interrupt.c

@@ -2160,7 +2160,7 @@ static int modify_ais_mode(struct kvm *kvm, struct kvm_device_attr *attr)
 	struct kvm_s390_ais_req req;
 	int ret = 0;
 
-	if (!fi->ais_enabled)
+	if (!test_kvm_facility(kvm, 72))
 		return -ENOTSUPP;
 
 	if (copy_from_user(&req, (void __user *)attr->addr, sizeof(req)))
@@ -2204,7 +2204,7 @@ static int kvm_s390_inject_airq(struct kvm *kvm,
 	};
 	int ret = 0;
 
-	if (!fi->ais_enabled || !adapter->suppressible)
+	if (!test_kvm_facility(kvm, 72) || !adapter->suppressible)
 		return kvm_s390_inject_vm(kvm, &s390int);
 
 	mutex_lock(&fi->ais_lock);

arch/s390/kvm/kvm-s390.c

@@ -558,7 +558,6 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 		} else {
 			set_kvm_facility(kvm->arch.model.fac_mask, 72);
 			set_kvm_facility(kvm->arch.model.fac_list, 72);
-			kvm->arch.float_int.ais_enabled = 1;
 			r = 0;
 		}
 		mutex_unlock(&kvm->lock);
@@ -1533,7 +1532,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	mutex_init(&kvm->arch.float_int.ais_lock);
 	kvm->arch.float_int.simm = 0;
 	kvm->arch.float_int.nimm = 0;
-	kvm->arch.float_int.ais_enabled = 0;
 	spin_lock_init(&kvm->arch.float_int.lock);
 	for (i = 0; i < FIRQ_LIST_COUNT; i++)
 		INIT_LIST_HEAD(&kvm->arch.float_int.lists[i]);

arch/sparc/Kconfig

@@ -192,9 +192,9 @@ config NR_CPUS
 	int "Maximum number of CPUs"
 	depends on SMP
 	range 2 32 if SPARC32
-	range 2 1024 if SPARC64
+	range 2 4096 if SPARC64
 	default 32 if SPARC32
-	default 64 if SPARC64
+	default 4096 if SPARC64
 
 source kernel/Kconfig.hz
 
@@ -295,9 +295,13 @@ config NUMA
 	depends on SPARC64 && SMP
 
 config NODES_SHIFT
-	int
-	default "4"
+	int "Maximum NUMA Nodes (as a power of 2)"
+	range 4 5 if SPARC64
+	default "5"
 	depends on NEED_MULTIPLE_NODES
+	help
+	  Specify the maximum number of NUMA Nodes available on the target
+	  system.  Increases memory reserved to accommodate various tables.
 
 # Some NUMA nodes have memory ranges that span
 # other nodes.  Even though a pfn is valid and
@@ -573,9 +577,6 @@ config SYSVIPC_COMPAT
 	depends on COMPAT && SYSVIPC
 	default y
 
-config KEYS_COMPAT
-	def_bool y if COMPAT && KEYS
-
 endmenu
 
 source "net/Kconfig"

arch/sparc/include/asm/mmu_64.h

@@ -52,7 +52,7 @@
 #define CTX_NR_MASK		TAG_CONTEXT_BITS
 #define CTX_HW_MASK		(CTX_NR_MASK | CTX_PGSZ_MASK)
 
-#define CTX_FIRST_VERSION	((_AC(1,UL) << CTX_VERSION_SHIFT) + _AC(1,UL))
+#define CTX_FIRST_VERSION	BIT(CTX_VERSION_SHIFT)
 #define CTX_VALID(__ctx)	\
 	 (!(((__ctx.sparc64_ctx_val) ^ tlb_context_cache) & CTX_VERSION_MASK))
 #define CTX_HWBITS(__ctx)	((__ctx.sparc64_ctx_val) & CTX_HW_MASK)

arch/sparc/include/asm/mmu_context_64.h

@@ -19,13 +19,8 @@ extern spinlock_t ctx_alloc_lock;
 extern unsigned long tlb_context_cache;
 extern unsigned long mmu_context_bmap[];
 
+DECLARE_PER_CPU(struct mm_struct *, per_cpu_secondary_mm);
 void get_new_mmu_context(struct mm_struct *mm);
-#ifdef CONFIG_SMP
-void smp_new_mmu_context_version(void);
-#else
-#define smp_new_mmu_context_version() do { } while (0)
-#endif
-
 int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
 void destroy_context(struct mm_struct *mm);
 
@@ -76,8 +71,9 @@ void __flush_tlb_mm(unsigned long, unsigned long);
 static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, struct task_struct *tsk)
 {
 	unsigned long ctx_valid, flags;
-	int cpu;
+	int cpu = smp_processor_id();
 
+	per_cpu(per_cpu_secondary_mm, cpu) = mm;
 	if (unlikely(mm == &init_mm))
 		return;
 
@@ -123,7 +119,6 @@ static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, str
 	 * for the first time, we must flush that context out of the
 	 * local TLB.
 	 */
-	cpu = smp_processor_id();
 	if (!ctx_valid || !cpumask_test_cpu(cpu, mm_cpumask(mm))) {
 		cpumask_set_cpu(cpu, mm_cpumask(mm));
 		__flush_tlb_mm(CTX_HWBITS(mm->context),
@@ -133,26 +128,7 @@ static inline void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm, str
 }
 
 #define deactivate_mm(tsk,mm)	do { } while (0)
-
-/* Activate a new MM instance for the current task. */
-static inline void activate_mm(struct mm_struct *active_mm, struct mm_struct *mm)
-{
-	unsigned long flags;
-	int cpu;
-
-	spin_lock_irqsave(&mm->context.lock, flags);
-	if (!CTX_VALID(mm->context))
-		get_new_mmu_context(mm);
-	cpu = smp_processor_id();
-	if (!cpumask_test_cpu(cpu, mm_cpumask(mm)))
-		cpumask_set_cpu(cpu, mm_cpumask(mm));
-
-	load_secondary_context(mm);
-	__flush_tlb_mm(CTX_HWBITS(mm->context), SECONDARY_CONTEXT);
-	tsb_context_switch(mm);
-	spin_unlock_irqrestore(&mm->context.lock, flags);
-}
-
+#define activate_mm(active_mm, mm) switch_mm(active_mm, mm, NULL)
 #endif /* !(__ASSEMBLY__) */
 
 #endif /* !(__SPARC64_MMU_CONTEXT_H) */

arch/sparc/include/asm/pil.h

@@ -20,7 +20,6 @@
 #define PIL_SMP_CALL_FUNC	1
 #define PIL_SMP_RECEIVE_SIGNAL	2
 #define PIL_SMP_CAPTURE		3
-#define PIL_SMP_CTX_NEW_VERSION	4
 #define PIL_DEVICE_IRQ		5
 #define PIL_SMP_CALL_FUNC_SNGL	6
 #define PIL_DEFERRED_PCR_WORK	7

arch/sparc/include/asm/vio.h

@@ -327,6 +327,7 @@ struct vio_dev {
 	int			compat_len;
 
 	u64			dev_no;
+	u64			id;
 
 	unsigned long		channel_id;
 

arch/sparc/kernel/ds.c

@@ -909,7 +909,7 @@ static int register_services(struct ds_info *dp)
 		pbuf.req.handle = cp->handle;
 		pbuf.req.major = 1;
 		pbuf.req.minor = 0;
-		strcpy(pbuf.req.svc_id, cp->service_id);
+		strcpy(pbuf.id_buf, cp->service_id);
 
 		err = __ds_send(lp, &pbuf, msg_len);
 		if (err > 0)

arch/sparc/kernel/irq_64.c

@@ -1034,17 +1034,26 @@ static void __init init_cpu_send_mondo_info(struct trap_per_cpu *tb)
 {
 #ifdef CONFIG_SMP
 	unsigned long page;
+	void *mondo, *p;
 
-	BUILD_BUG_ON((NR_CPUS * sizeof(u16)) > (PAGE_SIZE - 64));
+	BUILD_BUG_ON((NR_CPUS * sizeof(u16)) > PAGE_SIZE);
+
+	/* Make sure mondo block is 64byte aligned */
+	p = kzalloc(127, GFP_KERNEL);
+	if (!p) {
+		prom_printf("SUN4V: Error, cannot allocate mondo block.\n");
+		prom_halt();
+	}
+	mondo = (void *)(((unsigned long)p + 63) & ~0x3f);
+	tb->cpu_mondo_block_pa = __pa(mondo);
 
 	page = get_zeroed_page(GFP_KERNEL);
 	if (!page) {
-		prom_printf("SUN4V: Error, cannot allocate cpu mondo page.\n");
+		prom_printf("SUN4V: Error, cannot allocate cpu list page.\n");
 		prom_halt();
 	}
 
-	tb->cpu_mondo_block_pa = __pa(page);
-	tb->cpu_list_pa = __pa(page + 64);
+	tb->cpu_list_pa = __pa(page);
 #endif
 }
 

arch/sparc/kernel/kernel.h

@@ -37,7 +37,6 @@ void handle_stdfmna(struct pt_regs *regs, unsigned long sfar, unsigned long sfsr
 /* smp_64.c */
 void __irq_entry smp_call_function_client(int irq, struct pt_regs *regs);
 void __irq_entry smp_call_function_single_client(int irq, struct pt_regs *regs);
-void __irq_entry smp_new_mmu_context_version_client(int irq, struct pt_regs *regs);
 void __irq_entry smp_penguin_jailcell(int irq, struct pt_regs *regs);
 void __irq_entry smp_receive_signal_client(int irq, struct pt_regs *regs);
 

arch/sparc/kernel/smp_64.c

@@ -964,37 +964,6 @@ void flush_dcache_page_all(struct mm_struct *mm, struct page *page)
 	preempt_enable();
 }
 
-void __irq_entry smp_new_mmu_context_version_client(int irq, struct pt_regs *regs)
-{
-	struct mm_struct *mm;
-	unsigned long flags;
-
-	clear_softint(1 << irq);
-
-	/* See if we need to allocate a new TLB context because
-	 * the version of the one we are using is now out of date.
-	 */
-	mm = current->active_mm;
-	if (unlikely(!mm || (mm == &init_mm)))
-		return;
-
-	spin_lock_irqsave(&mm->context.lock, flags);
-
-	if (unlikely(!CTX_VALID(mm->context)))
-		get_new_mmu_context(mm);
-
-	spin_unlock_irqrestore(&mm->context.lock, flags);
-
-	load_secondary_context(mm);
-	__flush_tlb_mm(CTX_HWBITS(mm->context),
-		       SECONDARY_CONTEXT);
-}
-
-void smp_new_mmu_context_version(void)
-{
-	smp_cross_call(&xcall_new_mmu_context_version, 0, 0, 0);
-}
-
 #ifdef CONFIG_KGDB
 void kgdb_roundup_cpus(unsigned long flags)
 {

arch/sparc/kernel/tsb.S

@@ -455,13 +455,16 @@ __tsb_context_switch:
 	.type	copy_tsb,#function
 copy_tsb:		/* %o0=old_tsb_base, %o1=old_tsb_size
 			 * %o2=new_tsb_base, %o3=new_tsb_size
+			 * %o4=page_size_shift
 			 */
 	sethi		%uhi(TSB_PASS_BITS), %g7
 	srlx		%o3, 4, %o3
-	add		%o0, %o1, %g1	/* end of old tsb */
+	add		%o0, %o1, %o1	/* end of old tsb */
 	sllx		%g7, 32, %g7
 	sub		%o3, 1, %o3	/* %o3 == new tsb hash mask */
 
+	mov		%o4, %g1	/* page_size_shift */
+
 661:	prefetcha	[%o0] ASI_N, #one_read
 	.section	.tsb_phys_patch, "ax"
 	.word		661b
@@ -486,9 +489,9 @@ copy_tsb:		/* %o0=old_tsb_base, %o1=old_tsb_size
 	/* This can definitely be computed faster... */
 	srlx		%o0, 4, %o5	/* Build index */
 	and		%o5, 511, %o5	/* Mask index */
-	sllx		%o5, PAGE_SHIFT, %o5 /* Put into vaddr position */
+	sllx		%o5, %g1, %o5	/* Put into vaddr position */
 	or		%o4, %o5, %o4	/* Full VADDR. */
-	srlx		%o4, PAGE_SHIFT, %o4 /* Shift down to create index */
+	srlx		%o4, %g1, %o4	/* Shift down to create index */
 	and		%o4, %o3, %o4	/* Mask with new_tsb_nents-1 */
 	sllx		%o4, 4, %o4	/* Shift back up into tsb ent offset */
 	TSB_STORE(%o2 + %o4, %g2)	/* Store TAG */
@@ -496,7 +499,7 @@ copy_tsb:		/* %o0=old_tsb_base, %o1=old_tsb_size
 	TSB_STORE(%o2 + %o4, %g3)	/* Store TTE */
 
 80:	add		%o0, 16, %o0
-	cmp		%o0, %g1
+	cmp		%o0, %o1
 	bne,pt		%xcc, 90b
 	 nop
 

arch/sparc/kernel/ttable_64.S

@@ -50,7 +50,7 @@ tl0_resv03e:	BTRAP(0x3e) BTRAP(0x3f) BTRAP(0x40)
 tl0_irq1:	TRAP_IRQ(smp_call_function_client, 1)
 tl0_irq2:	TRAP_IRQ(smp_receive_signal_client, 2)
 tl0_irq3:	TRAP_IRQ(smp_penguin_jailcell, 3)
-tl0_irq4:	TRAP_IRQ(smp_new_mmu_context_version_client, 4)
+tl0_irq4:       BTRAP(0x44)
 #else
 tl0_irq1:	BTRAP(0x41)
 tl0_irq2:	BTRAP(0x42)

arch/sparc/kernel/vio.c

@@ -302,13 +302,16 @@ static struct vio_dev *vio_create_one(struct mdesc_handle *hp, u64 mp,
 	if (!id) {
 		dev_set_name(&vdev->dev, "%s", bus_id_name);
 		vdev->dev_no = ~(u64)0;
+		vdev->id = ~(u64)0;
 	} else if (!cfg_handle) {
 		dev_set_name(&vdev->dev, "%s-%llu", bus_id_name, *id);
 		vdev->dev_no = *id;
+		vdev->id = ~(u64)0;
 	} else {
 		dev_set_name(&vdev->dev, "%s-%llu-%llu", bus_id_name,
 			     *cfg_handle, *id);
 		vdev->dev_no = *cfg_handle;
+		vdev->id = *id;
 	}
 
 	vdev->dev.parent = parent;
@@ -351,27 +354,84 @@ static void vio_add(struct mdesc_handle *hp, u64 node)
 	(void) vio_create_one(hp, node, &root_vdev->dev);
 }
 
+struct vio_md_node_query {
+	const char *type;
+	u64 dev_no;
+	u64 id;
+};
+
 static int vio_md_node_match(struct device *dev, void *arg)
 {
+	struct vio_md_node_query *query = (struct vio_md_node_query *) arg;
 	struct vio_dev *vdev = to_vio_dev(dev);
 
-	if (vdev->mp == (u64) arg)
-		return 1;
+	if (vdev->dev_no != query->dev_no)
+		return 0;
+	if (vdev->id != query->id)
+		return 0;
+	if (strcmp(vdev->type, query->type))
+		return 0;
 
-	return 0;
+	return 1;
 }
 
 static void vio_remove(struct mdesc_handle *hp, u64 node)
 {
+	const char *type;
+	const u64 *id, *cfg_handle;
+	u64 a;
+	struct vio_md_node_query query;
 	struct device *dev;
 
-	dev = device_find_child(&root_vdev->dev, (void *) node,
+	type = mdesc_get_property(hp, node, "device-type", NULL);
+	if (!type) {
+		type = mdesc_get_property(hp, node, "name", NULL);
+		if (!type)
+			type = mdesc_node_name(hp, node);
+	}
+
+	query.type = type;
+
+	id = mdesc_get_property(hp, node, "id", NULL);
+	cfg_handle = NULL;
+	mdesc_for_each_arc(a, hp, node, MDESC_ARC_TYPE_BACK) {
+		u64 target;
+
+		target = mdesc_arc_target(hp, a);
+		cfg_handle = mdesc_get_property(hp, target,
+						"cfg-handle", NULL);
+		if (cfg_handle)
+			break;
+	}
+
+	if (!id) {
+		query.dev_no = ~(u64)0;
+		query.id = ~(u64)0;
+	} else if (!cfg_handle) {
+		query.dev_no = *id;
+		query.id = ~(u64)0;
+	} else {
+		query.dev_no = *cfg_handle;
+		query.id = *id;
+	}
+
+	dev = device_find_child(&root_vdev->dev, &query,
 				vio_md_node_match);
 	if (dev) {
 		printk(KERN_INFO "VIO: Removing device %s\n", dev_name(dev));
 
 		device_unregister(dev);
 		put_device(dev);
+	} else {
+		if (!id)
+			printk(KERN_ERR "VIO: Removed unknown %s node.\n",
+			       type);
+		else if (!cfg_handle)
+			printk(KERN_ERR "VIO: Removed unknown %s node %llu.\n",
+			       type, *id);
+		else
+			printk(KERN_ERR "VIO: Removed unknown %s node %llu-%llu.\n",
+			       type, *cfg_handle, *id);
 	}
 }
 

arch/sparc/lib/Makefile

@@ -15,6 +15,7 @@ lib-$(CONFIG_SPARC32) += copy_user.o locks.o
 lib-$(CONFIG_SPARC64) += atomic_64.o
 lib-$(CONFIG_SPARC32) += lshrdi3.o ashldi3.o
 lib-$(CONFIG_SPARC32) += muldi3.o bitext.o cmpdi2.o
+lib-$(CONFIG_SPARC64) += multi3.o
 
 lib-$(CONFIG_SPARC64) += copy_page.o clear_page.o bzero.o
 lib-$(CONFIG_SPARC64) += csum_copy.o csum_copy_from_user.o csum_copy_to_user.o

arch/sparc/lib/multi3.S

@@ -0,0 +1,35 @@
+#include <linux/linkage.h>
+#include <asm/export.h>
+
+	.text
+	.align	4
+ENTRY(__multi3) /* %o0 = u, %o1 = v */
+	mov	%o1, %g1
+	srl	%o3, 0, %g4
+	mulx	%g4, %g1, %o1
+	srlx	%g1, 0x20, %g3
+	mulx	%g3, %g4, %g5
+	sllx	%g5, 0x20, %o5
+	srl	%g1, 0, %g4
+	sub	%o1, %o5, %o5
+	srlx	%o5, 0x20, %o5
+	addcc	%g5, %o5, %g5
+	srlx	%o3, 0x20, %o5
+	mulx	%g4, %o5, %g4
+	mulx	%g3, %o5, %o5
+	sethi	%hi(0x80000000), %g3
+	addcc	%g5, %g4, %g5
+	srlx	%g5, 0x20, %g5
+	add	%g3, %g3, %g3
+	movcc	%xcc, %g0, %g3
+	addcc	%o5, %g5, %o5
+	sllx	%g4, 0x20, %g4
+	add	%o1, %g4, %o1
+	add	%o5, %g3, %g2
+	mulx	%g1, %o2, %g1
+	add	%g1, %g2, %g1
+	mulx	%o0, %o3, %o0
+	retl
+	 add	%g1, %o0, %o0
+ENDPROC(__multi3)
+EXPORT_SYMBOL(__multi3)

arch/sparc/mm/init_64.c

@@ -358,7 +358,8 @@ static int __init setup_hugepagesz(char *string)
 	}
 
 	if ((hv_pgsz_mask & cpu_pgsz_mask) == 0U) {
-		pr_warn("hugepagesz=%llu not supported by MMU.\n",
+		hugetlb_bad_size();
+		pr_err("hugepagesz=%llu not supported by MMU.\n",
 			hugepage_size);
 		goto out;
 	}
@@ -706,10 +707,58 @@ EXPORT_SYMBOL(__flush_dcache_range);
 
 /* get_new_mmu_context() uses "cache + 1".  */
 DEFINE_SPINLOCK(ctx_alloc_lock);
-unsigned long tlb_context_cache = CTX_FIRST_VERSION - 1;
+unsigned long tlb_context_cache = CTX_FIRST_VERSION;
 #define MAX_CTX_NR	(1UL << CTX_NR_BITS)
 #define CTX_BMAP_SLOTS	BITS_TO_LONGS(MAX_CTX_NR)
 DECLARE_BITMAP(mmu_context_bmap, MAX_CTX_NR);
+DEFINE_PER_CPU(struct mm_struct *, per_cpu_secondary_mm) = {0};
+
+static void mmu_context_wrap(void)
+{
+	unsigned long old_ver = tlb_context_cache & CTX_VERSION_MASK;
+	unsigned long new_ver, new_ctx, old_ctx;
+	struct mm_struct *mm;
+	int cpu;
+
+	bitmap_zero(mmu_context_bmap, 1 << CTX_NR_BITS);
+
+	/* Reserve kernel context */
+	set_bit(0, mmu_context_bmap);
+
+	new_ver = (tlb_context_cache & CTX_VERSION_MASK) + CTX_FIRST_VERSION;
+	if (unlikely(new_ver == 0))
+		new_ver = CTX_FIRST_VERSION;
+	tlb_context_cache = new_ver;
+
+	/*
+	 * Make sure that any new mm that are added into per_cpu_secondary_mm,
+	 * are going to go through get_new_mmu_context() path.
+	 */
+	mb();
+
+	/*
+	 * Updated versions to current on those CPUs that had valid secondary
+	 * contexts
+	 */
+	for_each_online_cpu(cpu) {
+		/*
+		 * If a new mm is stored after we took this mm from the array,
+		 * it will go into get_new_mmu_context() path, because we
+		 * already bumped the version in tlb_context_cache.
+		 */
+		mm = per_cpu(per_cpu_secondary_mm, cpu);
+
+		if (unlikely(!mm || mm == &init_mm))
+			continue;
+
+		old_ctx = mm->context.sparc64_ctx_val;
+		if (likely((old_ctx & CTX_VERSION_MASK) == old_ver)) {
+			new_ctx = (old_ctx & ~CTX_VERSION_MASK) | new_ver;
+			set_bit(new_ctx & CTX_NR_MASK, mmu_context_bmap);
+			mm->context.sparc64_ctx_val = new_ctx;
+		}
+	}
+}
 
 /* Caller does TLB context flushing on local CPU if necessary.
  * The caller also ensures that CTX_VALID(mm->context) is false.
@@ -725,48 +774,30 @@ void get_new_mmu_context(struct mm_struct *mm)
 {
 	unsigned long ctx, new_ctx;
 	unsigned long orig_pgsz_bits;
-	int new_version;
 
 	spin_lock(&ctx_alloc_lock);
+retry:
+	/* wrap might have happened, test again if our context became valid */
+	if (unlikely(CTX_VALID(mm->context)))
+		goto out;
 	orig_pgsz_bits = (mm->context.sparc64_ctx_val & CTX_PGSZ_MASK);
 	ctx = (tlb_context_cache + 1) & CTX_NR_MASK;
 	new_ctx = find_next_zero_bit(mmu_context_bmap, 1 << CTX_NR_BITS, ctx);
-	new_version = 0;
 	if (new_ctx >= (1 << CTX_NR_BITS)) {
 		new_ctx = find_next_zero_bit(mmu_context_bmap, ctx, 1);
 		if (new_ctx >= ctx) {
-			int i;
-			new_ctx = (tlb_context_cache & CTX_VERSION_MASK) +
-				CTX_FIRST_VERSION;
-			if (new_ctx == 1)
-				new_ctx = CTX_FIRST_VERSION;
-
-			/* Don't call memset, for 16 entries that's just
-			 * plain silly...
-			 */
-			mmu_context_bmap[0] = 3;
-			mmu_context_bmap[1] = 0;
-			mmu_context_bmap[2] = 0;
-			mmu_context_bmap[3] = 0;
-			for (i = 4; i < CTX_BMAP_SLOTS; i += 4) {
-				mmu_context_bmap[i + 0] = 0;
-				mmu_context_bmap[i + 1] = 0;
-				mmu_context_bmap[i + 2] = 0;
-				mmu_context_bmap[i + 3] = 0;
-			}
-			new_version = 1;
-			goto out;
+			mmu_context_wrap();
+			goto retry;
 		}
 	}
+	if (mm->context.sparc64_ctx_val)
+		cpumask_clear(mm_cpumask(mm));
 	mmu_context_bmap[new_ctx>>6] |= (1UL << (new_ctx & 63));
 	new_ctx |= (tlb_context_cache & CTX_VERSION_MASK);
-out:
 	tlb_context_cache = new_ctx;
 	mm->context.sparc64_ctx_val = new_ctx | orig_pgsz_bits;
+out:
 	spin_unlock(&ctx_alloc_lock);
-
-	if (unlikely(new_version))
-		smp_new_mmu_context_version();
 }
 
 static int numa_enabled = 1;

arch/sparc/mm/tsb.c

@@ -496,7 +496,8 @@ retry_tsb_alloc:
 		extern void copy_tsb(unsigned long old_tsb_base,
 				     unsigned long old_tsb_size,
 				     unsigned long new_tsb_base,
-				     unsigned long new_tsb_size);
+				     unsigned long new_tsb_size,
+				     unsigned long page_size_shift);
 		unsigned long old_tsb_base = (unsigned long) old_tsb;
 		unsigned long new_tsb_base = (unsigned long) new_tsb;
 
@@ -504,7 +505,9 @@ retry_tsb_alloc:
 			old_tsb_base = __pa(old_tsb_base);
 			new_tsb_base = __pa(new_tsb_base);
 		}
-		copy_tsb(old_tsb_base, old_size, new_tsb_base, new_size);
+		copy_tsb(old_tsb_base, old_size, new_tsb_base, new_size,
+			tsb_index == MM_TSB_BASE ?
+			PAGE_SHIFT : REAL_HPAGE_SHIFT);
 	}
 
 	mm->context.tsb_block[tsb_index].tsb = new_tsb;

arch/sparc/mm/ultra.S

@@ -971,11 +971,6 @@ xcall_capture:
 	wr		%g0, (1 << PIL_SMP_CAPTURE), %set_softint
 	retry
 
-	.globl		xcall_new_mmu_context_version
-xcall_new_mmu_context_version:
-	wr		%g0, (1 << PIL_SMP_CTX_NEW_VERSION), %set_softint
-	retry
-
 #ifdef CONFIG_KGDB
 	.globl		xcall_kgdb_capture
 xcall_kgdb_capture:

arch/x86/Kconfig

@@ -2776,10 +2776,6 @@ config COMPAT_FOR_U64_ALIGNMENT
 config SYSVIPC_COMPAT
 	def_bool y
 	depends on SYSVIPC
-
-config KEYS_COMPAT
-	def_bool y
-	depends on KEYS
 endif
 
 endmenu

arch/x86/kernel/cpu/cyrix.c

@@ -255,6 +255,7 @@ static void init_cyrix(struct cpuinfo_x86 *c)
 		break;
 
 	case 4: /* MediaGX/GXm or Geode GXM/GXLV/GX1 */
+	case 11: /* GX1 with inverted Device ID */
 #ifdef CONFIG_PCI
 	{
 		u32 vendor, device;

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

@@ -320,7 +320,7 @@ void load_ucode_amd_ap(unsigned int cpuid_1_eax)
 }
 
 static enum ucode_state
-load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size);
+load_microcode_amd(bool save, u8 family, const u8 *data, size_t size);
 
 int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
 {
@@ -338,8 +338,7 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
 	if (!desc.mc)
 		return -EINVAL;
 
-	ret = load_microcode_amd(smp_processor_id(), x86_family(cpuid_1_eax),
-				 desc.data, desc.size);
+	ret = load_microcode_amd(true, x86_family(cpuid_1_eax), desc.data, desc.size);
 	if (ret != UCODE_OK)
 		return -EINVAL;
 
@@ -675,7 +674,7 @@ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data,
 }
 
 static enum ucode_state
-load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size)
+load_microcode_amd(bool save, u8 family, const u8 *data, size_t size)
 {
 	enum ucode_state ret;
 
@@ -689,8 +688,8 @@ load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size)
 
 #ifdef CONFIG_X86_32
 	/* save BSP's matching patch for early load */
-	if (cpu_data(cpu).cpu_index == boot_cpu_data.cpu_index) {
-		struct ucode_patch *p = find_patch(cpu);
+	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),
@@ -722,11 +721,12 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device,
 {
 	char fw_name[36] = "amd-ucode/microcode_amd.bin";
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
+	bool bsp = c->cpu_index == boot_cpu_data.cpu_index;
 	enum ucode_state ret = UCODE_NFOUND;
 	const struct firmware *fw;
 
 	/* reload ucode container only on the boot cpu */
-	if (!refresh_fw || c->cpu_index != boot_cpu_data.cpu_index)
+	if (!refresh_fw || !bsp)
 		return UCODE_OK;
 
 	if (c->x86 >= 0x15)
@@ -743,7 +743,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device,
 		goto fw_release;
 	}
 
-	ret = load_microcode_amd(cpu, c->x86, fw->data, fw->size);
+	ret = load_microcode_amd(bsp, c->x86, fw->data, fw->size);
 
  fw_release:
 	release_firmware(fw);

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

@@ -619,6 +619,9 @@ int __init save_microcode_in_initrd_intel(void)
 
 	show_saved_mc();
 
+	/* initrd is going away, clear patch ptr. */
+	intel_ucode_patch = NULL;
+
 	return 0;
 }
 

arch/x86/kernel/kvm.c

@@ -161,8 +161,8 @@ void kvm_async_pf_task_wait(u32 token)
 			 */
 			rcu_irq_exit();
 			native_safe_halt();
-			rcu_irq_enter();
 			local_irq_disable();
+			rcu_irq_enter();
 		}
 	}
 	if (!n.halted)

arch/x86/kernel/process_32.c

@@ -78,7 +78,7 @@ void __show_regs(struct pt_regs *regs, int all)
 
 	printk(KERN_DEFAULT "EIP: %pS\n", (void *)regs->ip);
 	printk(KERN_DEFAULT "EFLAGS: %08lx CPU: %d\n", regs->flags,
-		smp_processor_id());
+		raw_smp_processor_id());
 
 	printk(KERN_DEFAULT "EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n",
 		regs->ax, regs->bx, regs->cx, regs->dx);

arch/x86/kvm/cpuid.c

@@ -780,18 +780,20 @@ out:
 static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i)
 {
 	struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i];
-	int j, nent = vcpu->arch.cpuid_nent;
+	struct kvm_cpuid_entry2 *ej;
+	int j = i;
+	int nent = vcpu->arch.cpuid_nent;
 
 	e->flags &= ~KVM_CPUID_FLAG_STATE_READ_NEXT;
 	/* when no next entry is found, the current entry[i] is reselected */
-	for (j = i + 1; ; j = (j + 1) % nent) {
-		struct kvm_cpuid_entry2 *ej = &vcpu->arch.cpuid_entries[j];
-		if (ej->function == e->function) {
-			ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
-			return j;
-		}
-	}
-	return 0; /* silence gcc, even though control never reaches here */
+	do {
+		j = (j + 1) % nent;
+		ej = &vcpu->arch.cpuid_entries[j];
+	} while (ej->function != e->function);
+
+	ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
+
+	return j;
 }
 
 /* find an entry with matching function, matching index (if needed), and that

arch/x86/kvm/lapic.c

@@ -1495,8 +1495,10 @@ EXPORT_SYMBOL_GPL(kvm_lapic_hv_timer_in_use);
 
 static void cancel_hv_timer(struct kvm_lapic *apic)
 {
+	preempt_disable();
 	kvm_x86_ops->cancel_hv_timer(apic->vcpu);
 	apic->lapic_timer.hv_timer_in_use = false;
+	preempt_enable();
 }
 
 static bool start_hv_timer(struct kvm_lapic *apic)
@@ -1934,7 +1936,8 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
 	for (i = 0; i < KVM_APIC_LVT_NUM; i++)
 		kvm_lapic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED);
 	apic_update_lvtt(apic);
-	if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_LINT0_REENABLED))
+	if (kvm_vcpu_is_reset_bsp(vcpu) &&
+	    kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_LINT0_REENABLED))
 		kvm_lapic_set_reg(apic, APIC_LVT0,
 			     SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT));
 	apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0));

arch/x86/kvm/mmu.c

@@ -3698,12 +3698,15 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
 	return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
 }
 
-static bool can_do_async_pf(struct kvm_vcpu *vcpu)
+bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu)
 {
 	if (unlikely(!lapic_in_kernel(vcpu) ||
 		     kvm_event_needs_reinjection(vcpu)))
 		return false;
 
+	if (is_guest_mode(vcpu))
+		return false;
+
 	return kvm_x86_ops->interrupt_allowed(vcpu);
 }
 
@@ -3719,7 +3722,7 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
 	if (!async)
 		return false; /* *pfn has correct page already */
 
-	if (!prefault && can_do_async_pf(vcpu)) {
+	if (!prefault && kvm_can_do_async_pf(vcpu)) {
 		trace_kvm_try_async_get_page(gva, gfn);
 		if (kvm_find_async_pf_gfn(vcpu, gfn)) {
 			trace_kvm_async_pf_doublefault(gva, gfn);

arch/x86/kvm/mmu.h

@@ -76,6 +76,7 @@ int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct);
 void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu);
 void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
 			     bool accessed_dirty);
+bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu);
 
 static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
 {

arch/x86/kvm/svm.c

@@ -1807,7 +1807,7 @@ static void svm_get_segment(struct kvm_vcpu *vcpu,
 	 * AMD's VMCB does not have an explicit unusable field, so emulate it
 	 * for cross vendor migration purposes by "not present"
 	 */
-	var->unusable = !var->present || (var->type == 0);
+	var->unusable = !var->present;
 
 	switch (seg) {
 	case VCPU_SREG_TR:
@@ -1840,6 +1840,7 @@ static void svm_get_segment(struct kvm_vcpu *vcpu,
 		 */
 		if (var->unusable)
 			var->db = 0;
+		/* This is symmetric with svm_set_segment() */
 		var->dpl = to_svm(vcpu)->vmcb->save.cpl;
 		break;
 	}
@@ -1980,18 +1981,14 @@ static void svm_set_segment(struct kvm_vcpu *vcpu,
 	s->base = var->base;
 	s->limit = var->limit;
 	s->selector = var->selector;
-	if (var->unusable)
-		s->attrib = 0;
-	else {
-		s->attrib = (var->type & SVM_SELECTOR_TYPE_MASK);
-		s->attrib |= (var->s & 1) << SVM_SELECTOR_S_SHIFT;
-		s->attrib |= (var->dpl & 3) << SVM_SELECTOR_DPL_SHIFT;
-		s->attrib |= (var->present & 1) << SVM_SELECTOR_P_SHIFT;
-		s->attrib |= (var->avl & 1) << SVM_SELECTOR_AVL_SHIFT;
-		s->attrib |= (var->l & 1) << SVM_SELECTOR_L_SHIFT;
-		s->attrib |= (var->db & 1) << SVM_SELECTOR_DB_SHIFT;
-		s->attrib |= (var->g & 1) << SVM_SELECTOR_G_SHIFT;
-	}
+	s->attrib = (var->type & SVM_SELECTOR_TYPE_MASK);
+	s->attrib |= (var->s & 1) << SVM_SELECTOR_S_SHIFT;
+	s->attrib |= (var->dpl & 3) << SVM_SELECTOR_DPL_SHIFT;
+	s->attrib |= ((var->present & 1) && !var->unusable) << SVM_SELECTOR_P_SHIFT;
+	s->attrib |= (var->avl & 1) << SVM_SELECTOR_AVL_SHIFT;
+	s->attrib |= (var->l & 1) << SVM_SELECTOR_L_SHIFT;
+	s->attrib |= (var->db & 1) << SVM_SELECTOR_DB_SHIFT;
+	s->attrib |= (var->g & 1) << SVM_SELECTOR_G_SHIFT;
 
 	/*
 	 * This is always accurate, except if SYSRET returned to a segment
@@ -2000,7 +1997,8 @@ static void svm_set_segment(struct kvm_vcpu *vcpu,
 	 * would entail passing the CPL to userspace and back.
 	 */
 	if (seg == VCPU_SREG_SS)
-		svm->vmcb->save.cpl = (s->attrib >> SVM_SELECTOR_DPL_SHIFT) & 3;
+		/* This is symmetric with svm_get_segment() */
+		svm->vmcb->save.cpl = (var->dpl & 3);
 
 	mark_dirty(svm->vmcb, VMCB_SEG);
 }

arch/x86/kvm/vmx.c

@@ -2425,7 +2425,7 @@ static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned nr)
 	if (!(vmcs12->exception_bitmap & (1u << nr)))
 		return 0;
 
-	nested_vmx_vmexit(vcpu, to_vmx(vcpu)->exit_reason,
+	nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
 			  vmcs_read32(VM_EXIT_INTR_INFO),
 			  vmcs_readl(EXIT_QUALIFICATION));
 	return 1;
@@ -6914,97 +6914,21 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-/*
- * This function performs the various checks including
- * - if it's 4KB aligned
- * - No bits beyond the physical address width are set
- * - Returns 0 on success or else 1
- * (Intel SDM Section 30.3)
- */
-static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason,
-				  gpa_t *vmpointer)
+static int nested_vmx_get_vmptr(struct kvm_vcpu *vcpu, gpa_t *vmpointer)
 {
 	gva_t gva;
-	gpa_t vmptr;
 	struct x86_exception e;
-	struct page *page;
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	int maxphyaddr = cpuid_maxphyaddr(vcpu);
 
 	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
 			vmcs_read32(VMX_INSTRUCTION_INFO), false, &gva))
 		return 1;
 
-	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr,
-				sizeof(vmptr), &e)) {
+	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, vmpointer,
+				sizeof(*vmpointer), &e)) {
 		kvm_inject_page_fault(vcpu, &e);
 		return 1;
 	}
 
-	switch (exit_reason) {
-	case EXIT_REASON_VMON:
-		/*
-		 * SDM 3: 24.11.5
-		 * The first 4 bytes of VMXON region contain the supported
-		 * VMCS revision identifier
-		 *
-		 * Note - IA32_VMX_BASIC[48] will never be 1
-		 * for the nested case;
-		 * which replaces physical address width with 32
-		 *
-		 */
-		if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) {
-			nested_vmx_failInvalid(vcpu);
-			return kvm_skip_emulated_instruction(vcpu);
-		}
-
-		page = nested_get_page(vcpu, vmptr);
-		if (page == NULL) {
-			nested_vmx_failInvalid(vcpu);
-			return kvm_skip_emulated_instruction(vcpu);
-		}
-		if (*(u32 *)kmap(page) != VMCS12_REVISION) {
-			kunmap(page);
-			nested_release_page_clean(page);
-			nested_vmx_failInvalid(vcpu);
-			return kvm_skip_emulated_instruction(vcpu);
-		}
-		kunmap(page);
-		nested_release_page_clean(page);
-		vmx->nested.vmxon_ptr = vmptr;
-		break;
-	case EXIT_REASON_VMCLEAR:
-		if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) {
-			nested_vmx_failValid(vcpu,
-					     VMXERR_VMCLEAR_INVALID_ADDRESS);
-			return kvm_skip_emulated_instruction(vcpu);
-		}
-
-		if (vmptr == vmx->nested.vmxon_ptr) {
-			nested_vmx_failValid(vcpu,
-					     VMXERR_VMCLEAR_VMXON_POINTER);
-			return kvm_skip_emulated_instruction(vcpu);
-		}
-		break;
-	case EXIT_REASON_VMPTRLD:
-		if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) {
-			nested_vmx_failValid(vcpu,
-					     VMXERR_VMPTRLD_INVALID_ADDRESS);
-			return kvm_skip_emulated_instruction(vcpu);
-		}
-
-		if (vmptr == vmx->nested.vmxon_ptr) {
-			nested_vmx_failValid(vcpu,
-					     VMXERR_VMPTRLD_VMXON_POINTER);
-			return kvm_skip_emulated_instruction(vcpu);
-		}
-		break;
-	default:
-		return 1; /* shouldn't happen */
-	}
-
-	if (vmpointer)
-		*vmpointer = vmptr;
 	return 0;
 }
 
@@ -7066,6 +6990,8 @@ out_msr_bitmap:
 static int handle_vmon(struct kvm_vcpu *vcpu)
 {
 	int ret;
+	gpa_t vmptr;
+	struct page *page;
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	const u64 VMXON_NEEDED_FEATURES = FEATURE_CONTROL_LOCKED
 		| FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
@@ -7095,9 +7021,37 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 		return 1;
 	}
 
-	if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMON, NULL))
+	if (nested_vmx_get_vmptr(vcpu, &vmptr))
 		return 1;
- 
+
+	/*
+	 * SDM 3: 24.11.5
+	 * The first 4 bytes of VMXON region contain the supported
+	 * VMCS revision identifier
+	 *
+	 * Note - IA32_VMX_BASIC[48] will never be 1 for the nested case;
+	 * which replaces physical address width with 32
+	 */
+	if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) {
+		nested_vmx_failInvalid(vcpu);
+		return kvm_skip_emulated_instruction(vcpu);
+	}
+
+	page = nested_get_page(vcpu, vmptr);
+	if (page == NULL) {
+		nested_vmx_failInvalid(vcpu);
+		return kvm_skip_emulated_instruction(vcpu);
+	}
+	if (*(u32 *)kmap(page) != VMCS12_REVISION) {
+		kunmap(page);
+		nested_release_page_clean(page);
+		nested_vmx_failInvalid(vcpu);
+		return kvm_skip_emulated_instruction(vcpu);
+	}
+	kunmap(page);
+	nested_release_page_clean(page);
+
+	vmx->nested.vmxon_ptr = vmptr;
 	ret = enter_vmx_operation(vcpu);
 	if (ret)
 		return ret;
@@ -7213,9 +7167,19 @@ static int handle_vmclear(struct kvm_vcpu *vcpu)
 	if (!nested_vmx_check_permission(vcpu))
 		return 1;
 
-	if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMCLEAR, &vmptr))
+	if (nested_vmx_get_vmptr(vcpu, &vmptr))
 		return 1;
 
+	if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) {
+		nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_INVALID_ADDRESS);
+		return kvm_skip_emulated_instruction(vcpu);
+	}
+
+	if (vmptr == vmx->nested.vmxon_ptr) {
+		nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_VMXON_POINTER);
+		return kvm_skip_emulated_instruction(vcpu);
+	}
+
 	if (vmptr == vmx->nested.current_vmptr)
 		nested_release_vmcs12(vmx);
 
@@ -7545,9 +7509,19 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 	if (!nested_vmx_check_permission(vcpu))
 		return 1;
 
-	if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMPTRLD, &vmptr))
+	if (nested_vmx_get_vmptr(vcpu, &vmptr))
 		return 1;
 
+	if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) {
+		nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_INVALID_ADDRESS);
+		return kvm_skip_emulated_instruction(vcpu);
+	}
+
+	if (vmptr == vmx->nested.vmxon_ptr) {
+		nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_VMXON_POINTER);
+		return kvm_skip_emulated_instruction(vcpu);
+	}
+
 	if (vmx->nested.current_vmptr != vmptr) {
 		struct vmcs12 *new_vmcs12;
 		struct page *page;
@@ -7913,11 +7887,13 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu,
 {
 	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
 	int cr = exit_qualification & 15;
-	int reg = (exit_qualification >> 8) & 15;
-	unsigned long val = kvm_register_readl(vcpu, reg);
+	int reg;
+	unsigned long val;
 
 	switch ((exit_qualification >> 4) & 3) {
 	case 0: /* mov to cr */
+		reg = (exit_qualification >> 8) & 15;
+		val = kvm_register_readl(vcpu, reg);
 		switch (cr) {
 		case 0:
 			if (vmcs12->cr0_guest_host_mask &
@@ -7972,6 +7948,7 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu,
 		 * lmsw can change bits 1..3 of cr0, and only set bit 0 of
 		 * cr0. Other attempted changes are ignored, with no exit.
 		 */
+		val = (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f;
 		if (vmcs12->cr0_guest_host_mask & 0xe &
 		    (val ^ vmcs12->cr0_read_shadow))
 			return true;

arch/x86/kvm/x86.c

@@ -8394,10 +8394,13 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.pv.pv_unhalted)
 		return true;
 
-	if (atomic_read(&vcpu->arch.nmi_queued))
+	if (kvm_test_request(KVM_REQ_NMI, vcpu) ||
+	    (vcpu->arch.nmi_pending &&
+	     kvm_x86_ops->nmi_allowed(vcpu)))
 		return true;
 
-	if (kvm_test_request(KVM_REQ_SMI, vcpu))
+	if (kvm_test_request(KVM_REQ_SMI, vcpu) ||
+	    (vcpu->arch.smi_pending && !is_smm(vcpu)))
 		return true;
 
 	if (kvm_arch_interrupt_allowed(vcpu) &&
@@ -8604,8 +8607,7 @@ bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu)
 	if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED))
 		return true;
 	else
-		return !kvm_event_needs_reinjection(vcpu) &&
-			kvm_x86_ops->interrupt_allowed(vcpu);
+		return kvm_can_do_async_pf(vcpu);
 }
 
 void kvm_arch_start_assignment(struct kvm *kvm)

arch/x86/mm/pat.c

@@ -65,11 +65,9 @@ static int __init nopat(char *str)
 }
 early_param("nopat", nopat);
 
-static bool __read_mostly __pat_initialized = false;
-
 bool pat_enabled(void)
 {
-	return __pat_initialized;
+	return !!__pat_enabled;
 }
 EXPORT_SYMBOL_GPL(pat_enabled);
 
@@ -227,14 +225,13 @@ static void pat_bsp_init(u64 pat)
 	}
 
 	wrmsrl(MSR_IA32_CR_PAT, pat);
-	__pat_initialized = true;
 
 	__init_cache_modes(pat);
 }
 
 static void pat_ap_init(u64 pat)
 {
-	if (!this_cpu_has(X86_FEATURE_PAT)) {
+	if (!boot_cpu_has(X86_FEATURE_PAT)) {
 		/*
 		 * If this happens we are on a secondary CPU, but switched to
 		 * PAT on the boot CPU. We have no way to undo PAT.
@@ -309,7 +306,7 @@ void pat_init(void)
 	u64 pat;
 	struct cpuinfo_x86 *c = &boot_cpu_data;
 
-	if (!__pat_enabled) {
+	if (!pat_enabled()) {
 		init_cache_modes();
 		return;
 	}

arch/x86/platform/efi/efi.c

@@ -828,9 +828,11 @@ static void __init kexec_enter_virtual_mode(void)
 
 	/*
 	 * We don't do virtual mode, since we don't do runtime services, on
-	 * non-native EFI
+	 * non-native EFI. With efi=old_map, we don't do runtime services in
+	 * kexec kernel because in the initial boot something else might
+	 * have been mapped at these virtual addresses.
 	 */
-	if (!efi_is_native()) {
+	if (!efi_is_native() || efi_enabled(EFI_OLD_MEMMAP)) {
 		efi_memmap_unmap();
 		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
 		return;

arch/x86/platform/efi/efi_64.c

@@ -71,11 +71,13 @@ static void __init early_code_mapping_set_exec(int executable)
 
 pgd_t * __init efi_call_phys_prolog(void)
 {
-	unsigned long vaddress;
-	pgd_t *save_pgd;
+	unsigned long vaddr, addr_pgd, addr_p4d, addr_pud;
+	pgd_t *save_pgd, *pgd_k, *pgd_efi;
+	p4d_t *p4d, *p4d_k, *p4d_efi;
+	pud_t *pud;
 
 	int pgd;
-	int n_pgds;
+	int n_pgds, i, j;
 
 	if (!efi_enabled(EFI_OLD_MEMMAP)) {
 		save_pgd = (pgd_t *)read_cr3();
@@ -88,10 +90,49 @@ pgd_t * __init efi_call_phys_prolog(void)
 	n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT), PGDIR_SIZE);
 	save_pgd = kmalloc_array(n_pgds, sizeof(*save_pgd), GFP_KERNEL);
 
+	/*
+	 * Build 1:1 identity mapping for efi=old_map usage. Note that
+	 * PAGE_OFFSET is PGDIR_SIZE aligned when KASLR is disabled, while
+	 * it is PUD_SIZE ALIGNED with KASLR enabled. So for a given physical
+	 * address X, the pud_index(X) != pud_index(__va(X)), we can only copy
+	 * PUD entry of __va(X) to fill in pud entry of X to build 1:1 mapping.
+	 * This means here we can only reuse the PMD tables of the direct mapping.
+	 */
 	for (pgd = 0; pgd < n_pgds; pgd++) {
-		save_pgd[pgd] = *pgd_offset_k(pgd * PGDIR_SIZE);
-		vaddress = (unsigned long)__va(pgd * PGDIR_SIZE);
-		set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), *pgd_offset_k(vaddress));
+		addr_pgd = (unsigned long)(pgd * PGDIR_SIZE);
+		vaddr = (unsigned long)__va(pgd * PGDIR_SIZE);
+		pgd_efi = pgd_offset_k(addr_pgd);
+		save_pgd[pgd] = *pgd_efi;
+
+		p4d = p4d_alloc(&init_mm, pgd_efi, addr_pgd);
+		if (!p4d) {
+			pr_err("Failed to allocate p4d table!\n");
+			goto out;
+		}
+
+		for (i = 0; i < PTRS_PER_P4D; i++) {
+			addr_p4d = addr_pgd + i * P4D_SIZE;
+			p4d_efi = p4d + p4d_index(addr_p4d);
+
+			pud = pud_alloc(&init_mm, p4d_efi, addr_p4d);
+			if (!pud) {
+				pr_err("Failed to allocate pud table!\n");
+				goto out;
+			}
+
+			for (j = 0; j < PTRS_PER_PUD; j++) {
+				addr_pud = addr_p4d + j * PUD_SIZE;
+
+				if (addr_pud > (max_pfn << PAGE_SHIFT))
+					break;
+
+				vaddr = (unsigned long)__va(addr_pud);
+
+				pgd_k = pgd_offset_k(vaddr);
+				p4d_k = p4d_offset(pgd_k, vaddr);
+				pud[j] = *pud_offset(p4d_k, vaddr);
+			}
+		}
 	}
 out:
 	__flush_tlb_all();
@@ -104,8 +145,11 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd)
 	/*
 	 * After the lock is released, the original page table is restored.
 	 */
-	int pgd_idx;
+	int pgd_idx, i;
 	int nr_pgds;
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
 
 	if (!efi_enabled(EFI_OLD_MEMMAP)) {
 		write_cr3((unsigned long)save_pgd);
@@ -115,9 +159,28 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd)
 
 	nr_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE);
 
-	for (pgd_idx = 0; pgd_idx < nr_pgds; pgd_idx++)
+	for (pgd_idx = 0; pgd_idx < nr_pgds; pgd_idx++) {
+		pgd = pgd_offset_k(pgd_idx * PGDIR_SIZE);
 		set_pgd(pgd_offset_k(pgd_idx * PGDIR_SIZE), save_pgd[pgd_idx]);
 
+		if (!(pgd_val(*pgd) & _PAGE_PRESENT))
+			continue;
+
+		for (i = 0; i < PTRS_PER_P4D; i++) {
+			p4d = p4d_offset(pgd,
+					 pgd_idx * PGDIR_SIZE + i * P4D_SIZE);
+
+			if (!(p4d_val(*p4d) & _PAGE_PRESENT))
+				continue;
+
+			pud = (pud_t *)p4d_page_vaddr(*p4d);
+			pud_free(&init_mm, pud);
+		}
+
+		p4d = (p4d_t *)pgd_page_vaddr(*pgd);
+		p4d_free(&init_mm, p4d);
+	}
+
 	kfree(save_pgd);
 
 	__flush_tlb_all();

arch/x86/platform/efi/quirks.c

@@ -360,6 +360,9 @@ void __init efi_free_boot_services(void)
 		free_bootmem_late(start, size);
 	}
 
+	if (!num_entries)
+		return;
+
 	new_size = efi.memmap.desc_size * num_entries;
 	new_phys = efi_memmap_alloc(num_entries);
 	if (!new_phys) {

block/bfq-cgroup.c

@@ -52,7 +52,7 @@ BFQG_FLAG_FNS(idling)
 BFQG_FLAG_FNS(empty)
 #undef BFQG_FLAG_FNS
 
-/* This should be called with the queue_lock held. */
+/* This should be called with the scheduler lock held. */
 static void bfqg_stats_update_group_wait_time(struct bfqg_stats *stats)
 {
 	unsigned long long now;
@@ -67,7 +67,7 @@ static void bfqg_stats_update_group_wait_time(struct bfqg_stats *stats)
 	bfqg_stats_clear_waiting(stats);
 }
 
-/* This should be called with the queue_lock held. */
+/* This should be called with the scheduler lock held. */
 static void bfqg_stats_set_start_group_wait_time(struct bfq_group *bfqg,
 						 struct bfq_group *curr_bfqg)
 {
@@ -81,7 +81,7 @@ static void bfqg_stats_set_start_group_wait_time(struct bfq_group *bfqg,
 	bfqg_stats_mark_waiting(stats);
 }
 
-/* This should be called with the queue_lock held. */
+/* This should be called with the scheduler lock held. */
 static void bfqg_stats_end_empty_time(struct bfqg_stats *stats)
 {
 	unsigned long long now;
@@ -203,12 +203,30 @@ struct bfq_group *bfqq_group(struct bfq_queue *bfqq)
 
 static void bfqg_get(struct bfq_group *bfqg)
 {
-	return blkg_get(bfqg_to_blkg(bfqg));
+	bfqg->ref++;
 }
 
 void bfqg_put(struct bfq_group *bfqg)
 {
-	return blkg_put(bfqg_to_blkg(bfqg));
+	bfqg->ref--;
+
+	if (bfqg->ref == 0)
+		kfree(bfqg);
+}
+
+static void bfqg_and_blkg_get(struct bfq_group *bfqg)
+{
+	/* see comments in bfq_bic_update_cgroup for why refcounting bfqg */
+	bfqg_get(bfqg);
+
+	blkg_get(bfqg_to_blkg(bfqg));
+}
+
+void bfqg_and_blkg_put(struct bfq_group *bfqg)
+{
+	bfqg_put(bfqg);
+
+	blkg_put(bfqg_to_blkg(bfqg));
 }
 
 void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
@@ -312,7 +330,11 @@ void bfq_init_entity(struct bfq_entity *entity, struct bfq_group *bfqg)
 	if (bfqq) {
 		bfqq->ioprio = bfqq->new_ioprio;
 		bfqq->ioprio_class = bfqq->new_ioprio_class;
-		bfqg_get(bfqg);
+		/*
+		 * Make sure that bfqg and its associated blkg do not
+		 * disappear before entity.
+		 */
+		bfqg_and_blkg_get(bfqg);
 	}
 	entity->parent = bfqg->my_entity; /* NULL for root group */
 	entity->sched_data = &bfqg->sched_data;
@@ -399,6 +421,8 @@ struct blkg_policy_data *bfq_pd_alloc(gfp_t gfp, int node)
 		return NULL;
 	}
 
+	/* see comments in bfq_bic_update_cgroup for why refcounting */
+	bfqg_get(bfqg);
 	return &bfqg->pd;
 }
 
@@ -426,7 +450,7 @@ void bfq_pd_free(struct blkg_policy_data *pd)
 	struct bfq_group *bfqg = pd_to_bfqg(pd);
 
 	bfqg_stats_exit(&bfqg->stats);
-	return kfree(bfqg);
+	bfqg_put(bfqg);
 }
 
 void bfq_pd_reset_stats(struct blkg_policy_data *pd)
@@ -496,9 +520,10 @@ struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
  * Move @bfqq to @bfqg, deactivating it from its old group and reactivating
  * it on the new one.  Avoid putting the entity on the old group idle tree.
  *
- * Must be called under the queue lock; the cgroup owning @bfqg must
- * not disappear (by now this just means that we are called under
- * rcu_read_lock()).
+ * Must be called under the scheduler lock, to make sure that the blkg
+ * owning @bfqg does not disappear (see comments in
+ * bfq_bic_update_cgroup on guaranteeing the consistency of blkg
+ * objects).
  */
 void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		   struct bfq_group *bfqg)
@@ -519,16 +544,12 @@ void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		bfq_deactivate_bfqq(bfqd, bfqq, false, false);
 	else if (entity->on_st)
 		bfq_put_idle_entity(bfq_entity_service_tree(entity), entity);
-	bfqg_put(bfqq_group(bfqq));
+	bfqg_and_blkg_put(bfqq_group(bfqq));
 
-	/*
-	 * Here we use a reference to bfqg.  We don't need a refcounter
-	 * as the cgroup reference will not be dropped, so that its
-	 * destroy() callback will not be invoked.
-	 */
 	entity->parent = bfqg->my_entity;
 	entity->sched_data = &bfqg->sched_data;
-	bfqg_get(bfqg);
+	/* pin down bfqg and its associated blkg  */
+	bfqg_and_blkg_get(bfqg);
 
 	if (bfq_bfqq_busy(bfqq)) {
 		bfq_pos_tree_add_move(bfqd, bfqq);
@@ -545,8 +566,9 @@ void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
  * @bic: the bic to move.
  * @blkcg: the blk-cgroup to move to.
  *
- * Move bic to blkcg, assuming that bfqd->queue is locked; the caller
- * has to make sure that the reference to cgroup is valid across the call.
+ * Move bic to blkcg, assuming that bfqd->lock is held; which makes
+ * sure that the reference to cgroup is valid across the call (see
+ * comments in bfq_bic_update_cgroup on this issue)
  *
  * NOTE: an alternative approach might have been to store the current
  * cgroup in bfqq and getting a reference to it, reducing the lookup
@@ -604,6 +626,57 @@ void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio)
 		goto out;
 
 	bfqg = __bfq_bic_change_cgroup(bfqd, bic, bio_blkcg(bio));
+	/*
+	 * Update blkg_path for bfq_log_* functions. We cache this
+	 * path, and update it here, for the following
+	 * reasons. Operations on blkg objects in blk-cgroup are
+	 * protected with the request_queue lock, and not with the
+	 * lock that protects the instances of this scheduler
+	 * (bfqd->lock). This exposes BFQ to the following sort of
+	 * race.
+	 *
+	 * The blkg_lookup performed in bfq_get_queue, protected
+	 * through rcu, may happen to return the address of a copy of
+	 * the original blkg. If this is the case, then the
+	 * bfqg_and_blkg_get performed in bfq_get_queue, to pin down
+	 * the blkg, is useless: it does not prevent blk-cgroup code
+	 * from destroying both the original blkg and all objects
+	 * directly or indirectly referred by the copy of the
+	 * blkg.
+	 *
+	 * On the bright side, destroy operations on a blkg invoke, as
+	 * a first step, hooks of the scheduler associated with the
+	 * blkg. And these hooks are executed with bfqd->lock held for
+	 * BFQ. As a consequence, for any blkg associated with the
+	 * request queue this instance of the scheduler is attached
+	 * to, we are guaranteed that such a blkg is not destroyed, and
+	 * that all the pointers it contains are consistent, while we
+	 * are holding bfqd->lock. A blkg_lookup performed with
+	 * bfqd->lock held then returns a fully consistent blkg, which
+	 * remains consistent until this lock is held.
+	 *
+	 * Thanks to the last fact, and to the fact that: (1) bfqg has
+	 * been obtained through a blkg_lookup in the above
+	 * assignment, and (2) bfqd->lock is being held, here we can
+	 * safely use the policy data for the involved blkg (i.e., the
+	 * field bfqg->pd) to get to the blkg associated with bfqg,
+	 * and then we can safely use any field of blkg. After we
+	 * release bfqd->lock, even just getting blkg through this
+	 * bfqg may cause dangling references to be traversed, as
+	 * bfqg->pd may not exist any more.
+	 *
+	 * In view of the above facts, here we cache, in the bfqg, any
+	 * blkg data we may need for this bic, and for its associated
+	 * bfq_queue. As of now, we need to cache only the path of the
+	 * blkg, which is used in the bfq_log_* functions.
+	 *
+	 * Finally, note that bfqg itself needs to be protected from
+	 * destruction on the blkg_free of the original blkg (which
+	 * invokes bfq_pd_free). We use an additional private
+	 * refcounter for bfqg, to let it disappear only after no
+	 * bfq_queue refers to it any longer.
+	 */
+	blkg_path(bfqg_to_blkg(bfqg), bfqg->blkg_path, sizeof(bfqg->blkg_path));
 	bic->blkcg_serial_nr = serial_nr;
 out:
 	rcu_read_unlock();
@@ -640,8 +713,6 @@ static void bfq_reparent_leaf_entity(struct bfq_data *bfqd,
  * @bfqd: the device data structure with the root group.
  * @bfqg: the group to move from.
  * @st: the service tree with the entities.
- *
- * Needs queue_lock to be taken and reference to be valid over the call.
  */
 static void bfq_reparent_active_entities(struct bfq_data *bfqd,
 					 struct bfq_group *bfqg,
@@ -692,8 +763,7 @@ void bfq_pd_offline(struct blkg_policy_data *pd)
 		/*
 		 * The idle tree may still contain bfq_queues belonging
 		 * to exited task because they never migrated to a different
-		 * cgroup from the one being destroyed now.  No one else
-		 * can access them so it's safe to act without any lock.
+		 * cgroup from the one being destroyed now.
 		 */
 		bfq_flush_idle_tree(st);
 

block/bfq-iosched.c

@@ -3665,7 +3665,7 @@ void bfq_put_queue(struct bfq_queue *bfqq)
 
 	kmem_cache_free(bfq_pool, bfqq);
 #ifdef CONFIG_BFQ_GROUP_IOSCHED
-	bfqg_put(bfqg);
+	bfqg_and_blkg_put(bfqg);
 #endif
 }
 

block/bfq-iosched.h

@@ -759,6 +759,12 @@ struct bfq_group {
 	/* must be the first member */
 	struct blkg_policy_data pd;
 
+	/* cached path for this blkg (see comments in bfq_bic_update_cgroup) */
+	char blkg_path[128];
+
+	/* reference counter (see comments in bfq_bic_update_cgroup) */
+	int ref;
+
 	struct bfq_entity entity;
 	struct bfq_sched_data sched_data;
 
@@ -838,7 +844,7 @@ struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
 struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
 struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
 struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node);
-void bfqg_put(struct bfq_group *bfqg);
+void bfqg_and_blkg_put(struct bfq_group *bfqg);
 
 #ifdef CONFIG_BFQ_GROUP_IOSCHED
 extern struct cftype bfq_blkcg_legacy_files[];
@@ -910,20 +916,13 @@ void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq);
 struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
 
 #define bfq_log_bfqq(bfqd, bfqq, fmt, args...)	do {			\
-	char __pbuf[128];						\
-									\
-	blkg_path(bfqg_to_blkg(bfqq_group(bfqq)), __pbuf, sizeof(__pbuf)); \
-	blk_add_trace_msg((bfqd)->queue, "bfq%d%c %s " fmt, (bfqq)->pid, \
+	blk_add_trace_msg((bfqd)->queue, "bfq%d%c %s " fmt, (bfqq)->pid,\
 			bfq_bfqq_sync((bfqq)) ? 'S' : 'A',		\
-			  __pbuf, ##args);				\
+			bfqq_group(bfqq)->blkg_path, ##args);		\
 } while (0)
 
-#define bfq_log_bfqg(bfqd, bfqg, fmt, args...)	do {			\
-	char __pbuf[128];						\
-									\
-	blkg_path(bfqg_to_blkg(bfqg), __pbuf, sizeof(__pbuf));		\
-	blk_add_trace_msg((bfqd)->queue, "%s " fmt, __pbuf, ##args);	\
-} while (0)
+#define bfq_log_bfqg(bfqd, bfqg, fmt, args...)	\
+	blk_add_trace_msg((bfqd)->queue, "%s " fmt, (bfqg)->blkg_path, ##args)
 
 #else /* CONFIG_BFQ_GROUP_IOSCHED */
 

block/bio-integrity.c

@@ -175,6 +175,9 @@ bool bio_integrity_enabled(struct bio *bio)
 	if (bio_op(bio) != REQ_OP_READ && bio_op(bio) != REQ_OP_WRITE)
 		return false;
 
+	if (!bio_sectors(bio))
+		return false;
+
 	/* Already protected? */
 	if (bio_integrity(bio))
 		return false;

block/blk-cgroup.c

@@ -74,7 +74,7 @@ static void blkg_free(struct blkcg_gq *blkg)
 			blkcg_policy[i]->pd_free_fn(blkg->pd[i]);
 
 	if (blkg->blkcg != &blkcg_root)
-		blk_exit_rl(&blkg->rl);
+		blk_exit_rl(blkg->q, &blkg->rl);
 
 	blkg_rwstat_exit(&blkg->stat_ios);
 	blkg_rwstat_exit(&blkg->stat_bytes);

block/blk-core.c

@@ -648,13 +648,19 @@ int blk_init_rl(struct request_list *rl, struct request_queue *q,
 	if (!rl->rq_pool)
 		return -ENOMEM;
 
+	if (rl != &q->root_rl)
+		WARN_ON_ONCE(!blk_get_queue(q));
+
 	return 0;
 }
 
-void blk_exit_rl(struct request_list *rl)
+void blk_exit_rl(struct request_queue *q, struct request_list *rl)
 {
-	if (rl->rq_pool)
+	if (rl->rq_pool) {
 		mempool_destroy(rl->rq_pool);
+		if (rl != &q->root_rl)
+			blk_put_queue(q);
+	}
 }
 
 struct request_queue *blk_alloc_queue(gfp_t gfp_mask)

block/blk-mq.c

@@ -1461,22 +1461,28 @@ static blk_qc_t request_to_qc_t(struct blk_mq_hw_ctx *hctx, struct request *rq)
 	return blk_tag_to_qc_t(rq->internal_tag, hctx->queue_num, true);
 }
 
-static void __blk_mq_try_issue_directly(struct request *rq, blk_qc_t *cookie,
-				      bool may_sleep)
+static void __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
+					struct request *rq,
+					blk_qc_t *cookie, bool may_sleep)
 {
 	struct request_queue *q = rq->q;
 	struct blk_mq_queue_data bd = {
 		.rq = rq,
 		.last = true,
 	};
-	struct blk_mq_hw_ctx *hctx;
 	blk_qc_t new_cookie;
 	int ret;
+	bool run_queue = true;
+
+	if (blk_mq_hctx_stopped(hctx)) {
+		run_queue = false;
+		goto insert;
+	}
 
 	if (q->elevator)
 		goto insert;
 
-	if (!blk_mq_get_driver_tag(rq, &hctx, false))
+	if (!blk_mq_get_driver_tag(rq, NULL, false))
 		goto insert;
 
 	new_cookie = request_to_qc_t(hctx, rq);
@@ -1500,7 +1506,7 @@ static void __blk_mq_try_issue_directly(struct request *rq, blk_qc_t *cookie,
 
 	__blk_mq_requeue_request(rq);
 insert:
-	blk_mq_sched_insert_request(rq, false, true, false, may_sleep);
+	blk_mq_sched_insert_request(rq, false, run_queue, false, may_sleep);
 }
 
 static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
@@ -1508,7 +1514,7 @@ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 {
 	if (!(hctx->flags & BLK_MQ_F_BLOCKING)) {
 		rcu_read_lock();
-		__blk_mq_try_issue_directly(rq, cookie, false);
+		__blk_mq_try_issue_directly(hctx, rq, cookie, false);
 		rcu_read_unlock();
 	} else {
 		unsigned int srcu_idx;
@@ -1516,7 +1522,7 @@ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 		might_sleep();
 
 		srcu_idx = srcu_read_lock(&hctx->queue_rq_srcu);
-		__blk_mq_try_issue_directly(rq, cookie, true);
+		__blk_mq_try_issue_directly(hctx, rq, cookie, true);
 		srcu_read_unlock(&hctx->queue_rq_srcu, srcu_idx);
 	}
 }
@@ -1619,9 +1625,12 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 
 		blk_mq_put_ctx(data.ctx);
 
-		if (same_queue_rq)
+		if (same_queue_rq) {
+			data.hctx = blk_mq_map_queue(q,
+					same_queue_rq->mq_ctx->cpu);
 			blk_mq_try_issue_directly(data.hctx, same_queue_rq,
 					&cookie);
+		}
 	} else if (q->nr_hw_queues > 1 && is_sync) {
 		blk_mq_put_ctx(data.ctx);
 		blk_mq_bio_to_request(rq, bio);
@@ -2641,7 +2650,8 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
 	return ret;
 }
 
-void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)
+static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
+							int nr_hw_queues)
 {
 	struct request_queue *q;
 
@@ -2665,6 +2675,13 @@ void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)
 	list_for_each_entry(q, &set->tag_list, tag_set_list)
 		blk_mq_unfreeze_queue(q);
 }
+
+void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)
+{
+	mutex_lock(&set->tag_list_lock);
+	__blk_mq_update_nr_hw_queues(set, nr_hw_queues);
+	mutex_unlock(&set->tag_list_lock);
+}
 EXPORT_SYMBOL_GPL(blk_mq_update_nr_hw_queues);
 
 /* Enable polling stats and return whether they were already enabled. */

block/blk-sysfs.c

@@ -809,7 +809,7 @@ static void blk_release_queue(struct kobject *kobj)
 
 	blk_free_queue_stats(q->stats);
 
-	blk_exit_rl(&q->root_rl);
+	blk_exit_rl(q, &q->root_rl);
 
 	if (q->queue_tags)
 		__blk_queue_free_tags(q);

block/blk-throttle.c

@@ -27,6 +27,13 @@ static int throtl_quantum = 32;
 #define MIN_THROTL_IOPS (10)
 #define DFL_LATENCY_TARGET (-1L)
 #define DFL_IDLE_THRESHOLD (0)
+#define DFL_HD_BASELINE_LATENCY (4000L) /* 4ms */
+#define LATENCY_FILTERED_SSD (0)
+/*
+ * For HD, very small latency comes from sequential IO. Such IO is helpless to
+ * help determine if its IO is impacted by others, hence we ignore the IO
+ */
+#define LATENCY_FILTERED_HD (1000L) /* 1ms */
 
 #define SKIP_LATENCY (((u64)1) << BLK_STAT_RES_SHIFT)
 
@@ -212,6 +219,7 @@ struct throtl_data
 	struct avg_latency_bucket avg_buckets[LATENCY_BUCKET_SIZE];
 	struct latency_bucket __percpu *latency_buckets;
 	unsigned long last_calculate_time;
+	unsigned long filtered_latency;
 
 	bool track_bio_latency;
 };
@@ -698,7 +706,7 @@ static void throtl_dequeue_tg(struct throtl_grp *tg)
 static void throtl_schedule_pending_timer(struct throtl_service_queue *sq,
 					  unsigned long expires)
 {
-	unsigned long max_expire = jiffies + 8 * sq_to_tg(sq)->td->throtl_slice;
+	unsigned long max_expire = jiffies + 8 * sq_to_td(sq)->throtl_slice;
 
 	/*
 	 * Since we are adjusting the throttle limit dynamically, the sleep
@@ -2281,7 +2289,7 @@ void blk_throtl_bio_endio(struct bio *bio)
 		throtl_track_latency(tg->td, blk_stat_size(&bio->bi_issue_stat),
 			bio_op(bio), lat);
 
-	if (tg->latency_target) {
+	if (tg->latency_target && lat >= tg->td->filtered_latency) {
 		int bucket;
 		unsigned int threshold;
 
@@ -2417,14 +2425,20 @@ void blk_throtl_exit(struct request_queue *q)
 void blk_throtl_register_queue(struct request_queue *q)
 {
 	struct throtl_data *td;
+	int i;
 
 	td = q->td;
 	BUG_ON(!td);
 
-	if (blk_queue_nonrot(q))
+	if (blk_queue_nonrot(q)) {
 		td->throtl_slice = DFL_THROTL_SLICE_SSD;
-	else
+		td->filtered_latency = LATENCY_FILTERED_SSD;
+	} else {
 		td->throtl_slice = DFL_THROTL_SLICE_HD;
+		td->filtered_latency = LATENCY_FILTERED_HD;
+		for (i = 0; i < LATENCY_BUCKET_SIZE; i++)
+			td->avg_buckets[i].latency = DFL_HD_BASELINE_LATENCY;
+	}
 #ifndef CONFIG_BLK_DEV_THROTTLING_LOW
 	/* if no low limit, use previous default */
 	td->throtl_slice = DFL_THROTL_SLICE_HD;

block/blk.h

@@ -59,7 +59,7 @@ void blk_free_flush_queue(struct blk_flush_queue *q);
 
 int blk_init_rl(struct request_list *rl, struct request_queue *q,
 		gfp_t gfp_mask);
-void blk_exit_rl(struct request_list *rl);
+void blk_exit_rl(struct request_queue *q, struct request_list *rl);
 void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 			struct bio *bio);
 void blk_queue_bypass_start(struct request_queue *q);

block/cfq-iosched.c

@@ -38,9 +38,13 @@ static const u64 cfq_target_latency = (u64)NSEC_PER_SEC * 3/10; /* 300 ms */
 static const int cfq_hist_divisor = 4;
 
 /*
- * offset from end of service tree
+ * offset from end of queue service tree for idle class
  */
 #define CFQ_IDLE_DELAY		(NSEC_PER_SEC / 5)
+/* offset from end of group service tree under time slice mode */
+#define CFQ_SLICE_MODE_GROUP_DELAY (NSEC_PER_SEC / 5)
+/* offset from end of group service under IOPS mode */
+#define CFQ_IOPS_MODE_GROUP_DELAY (HZ / 5)
 
 /*
  * below this threshold, we consider thinktime immediate
@@ -1362,6 +1366,14 @@ cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
 	cfqg->vfraction = max_t(unsigned, vfr, 1);
 }
 
+static inline u64 cfq_get_cfqg_vdisktime_delay(struct cfq_data *cfqd)
+{
+	if (!iops_mode(cfqd))
+		return CFQ_SLICE_MODE_GROUP_DELAY;
+	else
+		return CFQ_IOPS_MODE_GROUP_DELAY;
+}
+
 static void
 cfq_group_notify_queue_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
 {
@@ -1381,7 +1393,8 @@ cfq_group_notify_queue_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
 	n = rb_last(&st->rb);
 	if (n) {
 		__cfqg = rb_entry_cfqg(n);
-		cfqg->vdisktime = __cfqg->vdisktime + CFQ_IDLE_DELAY;
+		cfqg->vdisktime = __cfqg->vdisktime +
+			cfq_get_cfqg_vdisktime_delay(cfqd);
 	} else
 		cfqg->vdisktime = st->min_vdisktime;
 	cfq_group_service_tree_add(st, cfqg);