Merge git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next
diff --git a/Documentation/ABI/testing/sysfs-class-net-cdc_ncm b/Documentation/ABI/testing/sysfs-class-net-cdc_ncm
index 5cedf72d..f7be0e8 100644
--- a/Documentation/ABI/testing/sysfs-class-net-cdc_ncm
+++ b/Documentation/ABI/testing/sysfs-class-net-cdc_ncm
@@ -19,6 +19,25 @@
 		Set to 0 to pad all frames. Set greater than tx_max to
 		disable all padding.
 
+What:		/sys/class/net/<iface>/cdc_ncm/ndp_to_end
+Date:		Dec 2015
+KernelVersion:	4.5
+Contact:	Bjørn Mork <bjorn@mork.no>
+Description:
+		Boolean attribute showing the status of the "NDP to
+		end" quirk.  Defaults to 'N', except for devices
+		already known to need it enabled.
+
+		The "NDP to end" quirk makes the driver place the NDP
+		(the packet index table) after the payload.  The NCM
+		specification does not mandate this, but some devices
+		are known to be more restrictive. Write 'Y' to this
+		attribute for temporary testing of a suspect device
+		failing to work with the default driver settings.
+
+		A device entry should be added to the driver if this
+		quirk is found to be required.
+
 What:		/sys/class/net/<iface>/cdc_ncm/rx_max
 Date:		May 2014
 KernelVersion:	3.16
diff --git a/Documentation/ABI/testing/sysfs-class-net-qmi b/Documentation/ABI/testing/sysfs-class-net-qmi
new file mode 100644
index 0000000..fa5a00b
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-net-qmi
@@ -0,0 +1,23 @@
+What:		/sys/class/net/<iface>/qmi/raw_ip
+Date:		Dec 2015
+KernelVersion:	4.4
+Contact:	Bjørn Mork <bjorn@mork.no>
+Description:
+		Boolean.  Default: 'N'
+
+		Set this to 'Y' to change the network device link
+		framing from '802.3' to 'raw-ip'.
+
+		The netdev will change to reflect the link framing
+		mode.  The netdev is an ordinary ethernet device in
+		'802.3' mode, and the driver expects to exchange
+		frames with an ethernet header over the USB link. The
+		netdev is a headerless p-t-p device in 'raw-ip' mode,
+		and the driver expects to echange IPv4 or IPv6 packets
+		without any L2 header over the USB link.
+
+		Userspace is in full control of firmware configuration
+		through the delegation of the QMI protocol. Userspace
+		is responsible for coordination of driver and firmware
+		link framing mode, changing this setting to 'Y' if the
+		firmware is configured for 'raw-ip' mode.
diff --git a/Documentation/IPMI.txt b/Documentation/IPMI.txt
index 31d1d65..c0d8788 100644
--- a/Documentation/IPMI.txt
+++ b/Documentation/IPMI.txt
@@ -587,7 +587,7 @@
 
   modprobe ipmi_watchdog timeout=<t> pretimeout=<t> action=<action type>
       preaction=<preaction type> preop=<preop type> start_now=x
-      nowayout=x ifnum_to_use=n
+      nowayout=x ifnum_to_use=n panic_wdt_timeout=<t>
 
 ifnum_to_use specifies which interface the watchdog timer should use.
 The default is -1, which means to pick the first one registered.
@@ -597,7 +597,9 @@
 occur (if pretimeout is zero, then pretimeout will not be enabled).  Note
 that the pretimeout is the time before the final timeout.  So if the
 timeout is 50 seconds and the pretimeout is 10 seconds, then the pretimeout
-will occur in 40 second (10 seconds before the timeout).
+will occur in 40 second (10 seconds before the timeout). The panic_wdt_timeout
+is the value of timeout which is set on kernel panic, in order to let actions
+such as kdump to occur during panic.
 
 The action may be "reset", "power_cycle", or "power_off", and
 specifies what to do when the timer times out, and defaults to
@@ -634,6 +636,7 @@
 	ipmi_watchdog.preop=<preop type>
 	ipmi_watchdog.start_now=x
 	ipmi_watchdog.nowayout=x
+	ipmi_watchdog.panic_wdt_timeout=<t>
 
 The options are the same as the module parameter options.
 
diff --git a/Documentation/arm/keystone/Overview.txt b/Documentation/arm/keystone/Overview.txt
index f17bc4c..400c0c2 100644
--- a/Documentation/arm/keystone/Overview.txt
+++ b/Documentation/arm/keystone/Overview.txt
@@ -49,24 +49,6 @@
 The device tree documentation for the keystone machines are located at
         Documentation/devicetree/bindings/arm/keystone/keystone.txt
 
-Known issues & workaround
--------------------------
-
-Some of the device drivers used on keystone are re-used from that from
-DaVinci and other TI SoCs. These device drivers may use clock APIs directly.
-Some of the keystone specific drivers such as netcp uses run time power
-management API instead to enable clock. As this API has limitations on
-keystone, following workaround is needed to boot Linux.
-
-   Add 'clk_ignore_unused' to the bootargs env variable in u-boot. Otherwise
-   clock frameworks will try to disable clocks that are unused and disable
-   the hardware. This is because netcp related power domain and clock
-   domains are enabled in u-boot as run time power management API currently
-   doesn't enable clocks for netcp due to a limitation. This workaround is
-   expected to be removed in the future when proper API support becomes
-   available. Until then, this work around is needed.
-
-
 Document Author
 ---------------
 Murali Karicheri <m-karicheri2@ti.com>
diff --git a/Documentation/block/null_blk.txt b/Documentation/block/null_blk.txt
index 2f6c6ff..d8880ca 100644
--- a/Documentation/block/null_blk.txt
+++ b/Documentation/block/null_blk.txt
@@ -70,3 +70,6 @@
      parameter.
   1: The multi-queue block layer is instantiated with a hardware dispatch
      queue for each CPU node in the system.
+
+use_lightnvm=[0/1]: Default: 0
+  Register device with LightNVM. Requires blk-mq to be used.
diff --git a/Documentation/devicetree/bindings/gpio/gpio-mpc8xxx.txt b/Documentation/devicetree/bindings/gpio/gpio-mpc8xxx.txt
index f2455c5..120bc49 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-mpc8xxx.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-mpc8xxx.txt
@@ -11,6 +11,10 @@
       0 = active high
       1 = active low
 
+Optional properties:
+- little-endian : GPIO registers are used as little endian. If not
+                  present registers are used as big endian by default.
+
 Example:
 
 gpio0: gpio@1100 {
diff --git a/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt b/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
index f5a8ca2..aeea50c 100644
--- a/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
+++ b/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt
@@ -8,6 +8,11 @@
 - phy-mode: See ethernet.txt file in the same directory
 - clocks: a pointer to the reference clock for this device.
 
+Optional properties:
+- tx-csum-limit: maximum mtu supported by port that allow TX checksum.
+  Value is presented in bytes. If not used, by default 1600B is set for
+  "marvell,armada-370-neta" and 9800B for others.
+
 Example:
 
 ethernet@d0070000 {
@@ -15,6 +20,7 @@
 	reg = <0xd0070000 0x2500>;
 	interrupts = <8>;
 	clocks = <&gate_clk 4>;
+	tx-csum-limit = <9800>
 	status = "okay";
 	phy = <&phy0>;
 	phy-mode = "rgmii-id";
diff --git a/Documentation/devicetree/bindings/net/renesas,ravb.txt b/Documentation/devicetree/bindings/net/renesas,ravb.txt
index b486f3f..81a9f9e 100644
--- a/Documentation/devicetree/bindings/net/renesas,ravb.txt
+++ b/Documentation/devicetree/bindings/net/renesas,ravb.txt
@@ -5,8 +5,18 @@
 
 Required properties:
 - compatible: "renesas,etheravb-r8a7790" if the device is a part of R8A7790 SoC.
+	      "renesas,etheravb-r8a7791" if the device is a part of R8A7791 SoC.
+	      "renesas,etheravb-r8a7792" if the device is a part of R8A7792 SoC.
+	      "renesas,etheravb-r8a7793" if the device is a part of R8A7793 SoC.
 	      "renesas,etheravb-r8a7794" if the device is a part of R8A7794 SoC.
 	      "renesas,etheravb-r8a7795" if the device is a part of R8A7795 SoC.
+	      "renesas,etheravb-rcar-gen2" for generic R-Car Gen 2 compatible interface.
+	      "renesas,etheravb-rcar-gen3" for generic R-Car Gen 3 compatible interface.
+
+	      When compatible with the generic version, nodes must list the
+	      SoC-specific version corresponding to the platform first
+	      followed by the generic version.
+
 - reg: offset and length of (1) the register block and (2) the stream buffer.
 - interrupts: A list of interrupt-specifiers, one for each entry in
 	      interrupt-names.
@@ -37,7 +47,7 @@
 Example:
 
 	ethernet@e6800000 {
-		compatible = "renesas,etheravb-r8a7795";
+		compatible = "renesas,etheravb-r8a7795", "renesas,etheravb-rcar-gen3";
 		reg = <0 0xe6800000 0 0x800>, <0 0xe6a00000 0 0x10000>;
 		interrupt-parent = <&gic>;
 		interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/Documentation/devicetree/bindings/thermal/rockchip-thermal.txt b/Documentation/devicetree/bindings/thermal/rockchip-thermal.txt
index b38200d..0dfa60d 100644
--- a/Documentation/devicetree/bindings/thermal/rockchip-thermal.txt
+++ b/Documentation/devicetree/bindings/thermal/rockchip-thermal.txt
@@ -1,7 +1,9 @@
 * Temperature Sensor ADC (TSADC) on rockchip SoCs
 
 Required properties:
-- compatible : "rockchip,rk3288-tsadc"
+- compatible : should be "rockchip,<name>-tsadc"
+   "rockchip,rk3288-tsadc": found on RK3288 SoCs
+   "rockchip,rk3368-tsadc": found on RK3368 SoCs
 - reg : physical base address of the controller and length of memory mapped
 	region.
 - interrupts : The interrupt number to the cpu. The interrupt specifier format
diff --git a/Documentation/fault-injection/notifier-error-inject.txt b/Documentation/fault-injection/notifier-error-inject.txt
index 09adabe..83d3f4e 100644
--- a/Documentation/fault-injection/notifier-error-inject.txt
+++ b/Documentation/fault-injection/notifier-error-inject.txt
@@ -10,6 +10,7 @@
  * PM notifier
  * Memory hotplug notifier
  * powerpc pSeries reconfig notifier
+ * Netdevice notifier
 
 CPU notifier error injection module
 -----------------------------------
@@ -87,6 +88,30 @@
  * PSERIES_DRCONF_MEM_ADD
  * PSERIES_DRCONF_MEM_REMOVE
 
+Netdevice notifier error injection module
+----------------------------------------------
+This feature is controlled through debugfs interface
+/sys/kernel/debug/notifier-error-inject/netdev/actions/<notifier event>/error
+
+Netdevice notifier events which can be failed are:
+
+ * NETDEV_REGISTER
+ * NETDEV_CHANGEMTU
+ * NETDEV_CHANGENAME
+ * NETDEV_PRE_UP
+ * NETDEV_PRE_TYPE_CHANGE
+ * NETDEV_POST_INIT
+ * NETDEV_PRECHANGEMTU
+ * NETDEV_PRECHANGEUPPER
+ * NETDEV_CHANGEUPPER
+
+Example: Inject netdevice mtu change error (-22 == -EINVAL)
+
+	# cd /sys/kernel/debug/notifier-error-inject/netdev
+	# echo -22 > actions/NETDEV_CHANGEMTU/error
+	# ip link set eth0 mtu 1024
+	RTNETLINK answers: Invalid argument
+
 For more usage examples
 -----------------------
 There are tools/testing/selftests using the notifier error injection features
diff --git a/Documentation/i2c/busses/i2c-i801 b/Documentation/i2c/busses/i2c-i801
index 6a4b1af..1bba38d 100644
--- a/Documentation/i2c/busses/i2c-i801
+++ b/Documentation/i2c/busses/i2c-i801
@@ -32,6 +32,7 @@
   * Intel Sunrise Point-LP (PCH)
   * Intel DNV (SOC)
   * Intel Broxton (SOC)
+  * Intel Lewisburg (PCH)
    Datasheets: Publicly available at the Intel website
 
 On Intel Patsburg and later chipsets, both the normal host SMBus controller
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index f8aae63..742f69d 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1583,9 +1583,6 @@
 		hwp_only
 			Only load intel_pstate on systems which support
 			hardware P state control (HWP) if available.
-		no_acpi
-			Don't use ACPI processor performance control objects
-			_PSS and _PPC specified limits.
 
 	intremap=	[X86-64, Intel-IOMMU]
 			on	enable Interrupt Remapping (default)
diff --git a/MAINTAINERS b/MAINTAINERS
index ea17512..b6f6c8a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -318,7 +318,7 @@
 L:	linux-acpi@vger.kernel.org
 W:	https://01.org/linux-acpi
 S:	Supported
-F:	drivers/acpi/video.c
+F:	drivers/acpi/acpi_video.c
 
 ACPI WMI DRIVER
 L:	platform-driver-x86@vger.kernel.org
@@ -388,7 +388,7 @@
 L:	linux-wireless@vger.kernel.org
 W:	http://wireless.kernel.org/
 S:	Orphan
-F:	drivers/net/wireless/adm8211.*
+F:	drivers/net/wireless/admtek/adm8211.*
 
 ADP1653 FLASH CONTROLLER DRIVER
 M:	Sakari Ailus <sakari.ailus@iki.fi>
@@ -1847,7 +1847,7 @@
 F:	drivers/net/wireless/ath/ath6kl/
 
 WILOCITY WIL6210 WIRELESS DRIVER
-M:	Vladimir Kondratiev <qca_vkondrat@qca.qualcomm.com>
+M:	Maya Erez <qca_merez@qca.qualcomm.com>
 L:	linux-wireless@vger.kernel.org
 L:	wil6210@qca.qualcomm.com
 S:	Supported
@@ -1931,7 +1931,7 @@
 F:	drivers/i2c/busses/i2c-at91.c
 
 ATMEL ISI DRIVER
-M:	Josh Wu <josh.wu@atmel.com>
+M:	Ludovic Desroches <ludovic.desroches@atmel.com>
 L:	linux-media@vger.kernel.org
 S:	Supported
 F:	drivers/media/platform/soc_camera/atmel-isi.c
@@ -1950,7 +1950,8 @@
 F:	drivers/net/ethernet/cadence/
 
 ATMEL NAND DRIVER
-M:	Josh Wu <josh.wu@atmel.com>
+M:	Wenyou Yang <wenyou.yang@atmel.com>
+M:	Josh Wu <rainyfeeling@outlook.com>
 L:	linux-mtd@lists.infradead.org
 S:	Supported
 F:	drivers/mtd/nand/atmel_nand*
@@ -1992,7 +1993,7 @@
 W:	http://www.thekelleys.org.uk/atmel
 W:	http://atmelwlandriver.sourceforge.net/
 S:	Maintained
-F:	drivers/net/wireless/atmel*
+F:	drivers/net/wireless/atmel/atmel*
 
 ATMEL MAXTOUCH DRIVER
 M:	Nick Dyer <nick.dyer@itdev.co.uk>
@@ -2081,7 +2082,7 @@
 L:	b43-dev@lists.infradead.org
 W:	http://wireless.kernel.org/en/users/Drivers/b43
 S:	Odd Fixes
-F:	drivers/net/wireless/b43/
+F:	drivers/net/wireless/broadcom/b43/
 
 B43LEGACY WIRELESS DRIVER
 M:	Larry Finger <Larry.Finger@lwfinger.net>
@@ -2089,7 +2090,7 @@
 L:	b43-dev@lists.infradead.org
 W:	http://wireless.kernel.org/en/users/Drivers/b43
 S:	Maintained
-F:	drivers/net/wireless/b43legacy/
+F:	drivers/net/wireless/broadcom/b43legacy/
 
 BACKLIGHT CLASS/SUBSYSTEM
 M:	Jingoo Han <jingoohan1@gmail.com>
@@ -2391,7 +2392,7 @@
 L:	linux-wireless@vger.kernel.org
 L:	brcm80211-dev-list@broadcom.com
 S:	Supported
-F:	drivers/net/wireless/brcm80211/
+F:	drivers/net/wireless/broadcom/brcm80211/
 
 BROADCOM BNX2FC 10 GIGABIT FCOE DRIVER
 M:	QLogic-Storage-Upstream@qlogic.com
@@ -2449,7 +2450,9 @@
 
 BROADCOM STB NAND FLASH DRIVER
 M:	Brian Norris <computersforpeace@gmail.com>
+M:	Kamal Dasu <kdasu.kdev@gmail.com>
 L:	linux-mtd@lists.infradead.org
+L:	bcm-kernel-feedback-list@broadcom.com
 S:	Maintained
 F:	drivers/mtd/nand/brcmnand/
 
@@ -2929,10 +2932,9 @@
 F:	drivers/platform/x86/compal-laptop.c
 
 CONEXANT ACCESSRUNNER USB DRIVER
-M:	Simon Arlott <cxacru@fire.lp0.eu>
 L:	accessrunner-general@lists.sourceforge.net
 W:	http://accessrunner.sourceforge.net/
-S:	Maintained
+S:	Orphan
 F:	drivers/usb/atm/cxacru.c
 
 CONFIGFS
@@ -2973,6 +2975,7 @@
 CONTROL GROUP - MEMORY RESOURCE CONTROLLER (MEMCG)
 M:	Johannes Weiner <hannes@cmpxchg.org>
 M:	Michal Hocko <mhocko@kernel.org>
+M:	Vladimir Davydov <vdavydov@virtuozzo.com>
 L:	cgroups@vger.kernel.org
 L:	linux-mm@kvack.org
 S:	Maintained
@@ -3101,7 +3104,7 @@
 CW1200 WLAN driver
 M:	Solomon Peachy <pizza@shaftnet.org>
 S:	Maintained
-F:	drivers/net/wireless/cw1200/
+F:	drivers/net/wireless/st/cw1200/
 
 CX18 VIDEO4LINUX DRIVER
 M:	Andy Walls <awalls@md.metrocast.net>
@@ -4409,6 +4412,7 @@
 
 FPGA MANAGER FRAMEWORK
 M:	Alan Tull <atull@opensource.altera.com>
+R:	Moritz Fischer <moritz.fischer@ettus.com>
 S:	Maintained
 F:	drivers/fpga/
 F:	include/linux/fpga/fpga-mgr.h
@@ -5041,7 +5045,7 @@
 L:	linux-wireless@vger.kernel.org
 W:	http://hostap.epitest.fi/
 S:	Maintained
-F:	drivers/net/wireless/hostap/
+F:	drivers/net/wireless/intersil/hostap/
 
 HP COMPAQ TC1100 TABLET WMI EXTRAS DRIVER
 L:	platform-driver-x86@vger.kernel.org
@@ -5609,7 +5613,7 @@
 S:	Maintained
 F:	Documentation/networking/README.ipw2100
 F:	Documentation/networking/README.ipw2200
-F:	drivers/net/wireless/ipw2x00/
+F:	drivers/net/wireless/intel/ipw2x00/
 
 INTEL(R) TRACE HUB
 M:	Alexander Shishkin <alexander.shishkin@linux.intel.com>
@@ -5643,7 +5647,7 @@
 M:	Stanislaw Gruszka <sgruszka@redhat.com>
 L:	linux-wireless@vger.kernel.org
 S:	Supported
-F:	drivers/net/wireless/iwlegacy/
+F:	drivers/net/wireless/intel/iwlegacy/
 
 INTEL WIRELESS WIFI LINK (iwlwifi)
 M:	Johannes Berg <johannes.berg@intel.com>
@@ -5653,7 +5657,7 @@
 W:	http://intellinuxwireless.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/iwlwifi/iwlwifi.git
 S:	Supported
-F:	drivers/net/wireless/iwlwifi/
+F:	drivers/net/wireless/intel/iwlwifi/
 
 INTEL MANAGEMENT ENGINE (mei)
 M:	Tomas Winkler <tomas.winkler@intel.com>
@@ -6364,6 +6368,7 @@
 LIGHTNVM PLATFORM SUPPORT
 M:	Matias Bjorling <mb@lightnvm.io>
 W:	http://github/OpenChannelSSD
+L:	linux-block@vger.kernel.org
 S:	Maintained
 F:	drivers/lightnvm/
 F:	include/linux/lightnvm.h
@@ -6703,7 +6708,7 @@
 MARVELL LIBERTAS WIRELESS DRIVER
 L:	libertas-dev@lists.infradead.org
 S:	Orphan
-F:	drivers/net/wireless/libertas/
+F:	drivers/net/wireless/marvell/libertas/
 
 MARVELL MV643XX ETHERNET DRIVER
 M:	Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
@@ -6723,13 +6728,13 @@
 M:	Nishant Sarmukadam <nishants@marvell.com>
 L:	linux-wireless@vger.kernel.org
 S:	Maintained
-F:	drivers/net/wireless/mwifiex/
+F:	drivers/net/wireless/marvell/mwifiex/
 
 MARVELL MWL8K WIRELESS DRIVER
 M:	Lennert Buytenhek <buytenh@wantstofly.org>
 L:	linux-wireless@vger.kernel.org
 S:	Odd Fixes
-F:	drivers/net/wireless/mwl8k.c
+F:	drivers/net/wireless/marvell/mwl8k.c
 
 MARVELL SOC MMC/SD/SDIO CONTROLLER DRIVER
 M:	Nicolas Pitre <nico@fluxnic.net>
@@ -7364,6 +7369,13 @@
 F:	include/uapi/linux/netrom.h
 F:	net/netrom/
 
+NETRONOME ETHERNET DRIVERS
+M:	Jakub Kicinski <jakub.kicinski@netronome.com>
+M:	Rolf Neugebauer <rolf.neugebauer@netronome.com>
+L:	oss-drivers@netronome.com
+S:	Maintained
+F:	drivers/net/ethernet/netronome/
+
 NETWORK BLOCK DEVICE (NBD)
 M:	Markus Pargmann <mpa@pengutronix.de>
 S:	Maintained
@@ -7902,6 +7914,18 @@
 F:	net/openvswitch/
 F:	include/uapi/linux/openvswitch.h
 
+OPERATING PERFORMANCE POINTS (OPP)
+M:	Viresh Kumar <vireshk@kernel.org>
+M:	Nishanth Menon <nm@ti.com>
+M:	Stephen Boyd <sboyd@codeaurora.org>
+L:	linux-pm@vger.kernel.org
+S:	Maintained
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/vireshk/pm.git
+F:	drivers/base/power/opp/
+F:	include/linux/pm_opp.h
+F:	Documentation/power/opp.txt
+F:	Documentation/devicetree/bindings/opp/
+
 OPL4 DRIVER
 M:	Clemens Ladisch <clemens@ladisch.de>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
@@ -7933,7 +7957,7 @@
 W:	http://wireless.kernel.org/en/users/Drivers/orinoco
 W:	http://www.nongnu.org/orinoco/
 S:	Orphan
-F:	drivers/net/wireless/orinoco/
+F:	drivers/net/wireless/intersil/orinoco/
 
 OSD LIBRARY and FILESYSTEM
 M:	Boaz Harrosh <ooo@electrozaur.com>
@@ -7959,7 +7983,7 @@
 L:	linux-wireless@vger.kernel.org
 W:	http://wireless.kernel.org/en/users/Drivers/p54
 S:	Maintained
-F:	drivers/net/wireless/p54/
+F:	drivers/net/wireless/intersil/p54/
 
 PA SEMI ETHERNET DRIVER
 M:	Olof Johansson <olof@lixom.net>
@@ -8270,7 +8294,7 @@
 F:	kernel/delayacct.c
 
 PERFORMANCE EVENTS SUBSYSTEM
-M:	Peter Zijlstra <a.p.zijlstra@chello.nl>
+M:	Peter Zijlstra <peterz@infradead.org>
 M:	Ingo Molnar <mingo@redhat.com>
 M:	Arnaldo Carvalho de Melo <acme@kernel.org>
 L:	linux-kernel@vger.kernel.org
@@ -8501,7 +8525,7 @@
 L:	linux-wireless@vger.kernel.org
 W:	http://wireless.kernel.org/en/users/Drivers/p54
 S:	Obsolete
-F:	drivers/net/wireless/prism54/
+F:	drivers/net/wireless/intersil/prism54/
 
 PS3 NETWORK SUPPORT
 M:	Geoff Levand <geoff@infradead.org>
@@ -8804,7 +8828,7 @@
 M:	Helmut Schaa <helmut.schaa@googlemail.com>
 L:	linux-wireless@vger.kernel.org
 S:	Maintained
-F:	drivers/net/wireless/rt2x00/
+F:	drivers/net/wireless/ralink/rt2x00/
 
 RAMDISK RAM BLOCK DEVICE DRIVER
 M:	Jens Axboe <axboe@kernel.dk>
@@ -9038,7 +9062,7 @@
 W:	http://wireless.kernel.org/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-testing.git
 S:	Orphan
-F:	drivers/net/wireless/rtl818x/rtl8180/
+F:	drivers/net/wireless/realtek/rtl818x/rtl8180/
 
 RTL8187 WIRELESS DRIVER
 M:	Herton Ronaldo Krzesinski <herton@canonical.com>
@@ -9048,7 +9072,7 @@
 W:	http://wireless.kernel.org/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-testing.git
 S:	Maintained
-F:	drivers/net/wireless/rtl818x/rtl8187/
+F:	drivers/net/wireless/realtek/rtl818x/rtl8187/
 
 RTL8192CE WIRELESS DRIVER
 M:	Larry Finger <Larry.Finger@lwfinger.net>
@@ -9057,8 +9081,8 @@
 W:	http://wireless.kernel.org/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-testing.git
 S:	Maintained
-F:	drivers/net/wireless/rtlwifi/
-F:	drivers/net/wireless/rtlwifi/rtl8192ce/
+F:	drivers/net/wireless/realtek/rtlwifi/
+F:	drivers/net/wireless/realtek/rtlwifi/rtl8192ce/
 
 RTL8XXXU WIRELESS DRIVER (rtl8xxxu)
 M:	Jes Sorensen <Jes.Sorensen@redhat.com>
@@ -9315,7 +9339,6 @@
 F:	include/linux/platform_data/i2c-designware.h
 
 SYNOPSYS DESIGNWARE MMC/SD/SDIO DRIVER
-M:	Seungwon Jeon <tgih.jun@samsung.com>
 M:	Jaehoon Chung <jh80.chung@samsung.com>
 L:	linux-mmc@vger.kernel.org
 S:	Maintained
@@ -9412,8 +9435,10 @@
 
 SCSI SUBSYSTEM
 M:	"James E.J. Bottomley" <JBottomley@odin.com>
-L:	linux-scsi@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi.git
+M:	"Martin K. Petersen" <martin.petersen@oracle.com>
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mkp/scsi.git
+L:	linux-scsi@vger.kernel.org
 S:	Maintained
 F:	drivers/scsi/
 F:	include/scsi/
@@ -10888,9 +10913,9 @@
 F:	drivers/media/tuners/tua9001*
 
 TULIP NETWORK DRIVERS
-M:	Grant Grundler <grundler@parisc-linux.org>
 L:	netdev@vger.kernel.org
-S:	Maintained
+L:	linux-parisc@vger.kernel.org
+S:	Orphan
 F:	drivers/net/ethernet/dec/tulip/
 
 TUN/TAP driver
@@ -11159,6 +11184,13 @@
 S:	Supported
 F:	drivers/usb/class/usblp.c
 
+USB QMI WWAN NETWORK DRIVER
+M:	Bjørn Mork <bjorn@mork.no>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	Documentation/ABI/testing/sysfs-class-net-qmi
+F:	drivers/net/usb/qmi_wwan.c
+
 USB RTL8150 DRIVER
 M:	Petko Manolov <petkan@nucleusys.com>
 L:	linux-usb@vger.kernel.org
@@ -11255,7 +11287,7 @@
 L:	linux-wireless@vger.kernel.org
 W:	http://linux-lc100020.sourceforge.net
 S:	Orphan
-F:	drivers/net/wireless/zd1201.*
+F:	drivers/net/wireless/zydas/zd1201.*
 
 USB ZR364XX DRIVER
 M:	Antoine Jacquet <royale@zerezo.com>
@@ -11886,7 +11918,7 @@
 L:	linux-wireless@vger.kernel.org
 L:	zd1211-devs@lists.sourceforge.net (subscribers-only)
 S:	Maintained
-F:	drivers/net/wireless/zd1211rw/
+F:	drivers/net/wireless/zydas/zd1211rw/
 
 ZPOOL COMPRESSED PAGE STORAGE API
 M:	Dan Streetman <ddstreet@ieee.org>
diff --git a/Makefile b/Makefile
index 3a0234f..bc0165d 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 4
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc5
 NAME = Blurry Fish Butt
 
 # *DOCUMENTATION*
diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig
index c92c0ef..f1ac981 100644
--- a/arch/arc/configs/axs101_defconfig
+++ b/arch/arc/configs/axs101_defconfig
@@ -1,4 +1,4 @@
-CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_CROSS_COMPILE="arc-linux-"
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig
index cfac24e..323486d 100644
--- a/arch/arc/configs/axs103_defconfig
+++ b/arch/arc/configs/axs103_defconfig
@@ -1,4 +1,4 @@
-CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_CROSS_COMPILE="arc-linux-"
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig
index 9922a11..66191cd 100644
--- a/arch/arc/configs/axs103_smp_defconfig
+++ b/arch/arc/configs/axs103_smp_defconfig
@@ -1,4 +1,4 @@
-CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_CROSS_COMPILE="arc-linux-"
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
diff --git a/arch/arc/configs/nsim_hs_defconfig b/arch/arc/configs/nsim_hs_defconfig
index f761a7c..f68838e 100644
--- a/arch/arc/configs/nsim_hs_defconfig
+++ b/arch/arc/configs/nsim_hs_defconfig
@@ -1,4 +1,4 @@
-CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_CROSS_COMPILE="arc-linux-"
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
diff --git a/arch/arc/configs/nsim_hs_smp_defconfig b/arch/arc/configs/nsim_hs_smp_defconfig
index dc6f74f..96bd1c2 100644
--- a/arch/arc/configs/nsim_hs_smp_defconfig
+++ b/arch/arc/configs/nsim_hs_smp_defconfig
@@ -1,4 +1,4 @@
-CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_CROSS_COMPILE="arc-linux-"
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig
index 3fef0a2..fcae666 100644
--- a/arch/arc/configs/nsimosci_hs_defconfig
+++ b/arch/arc/configs/nsimosci_hs_defconfig
@@ -1,4 +1,4 @@
-CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_CROSS_COMPILE="arc-linux-"
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig
index 5178483..b01b659 100644
--- a/arch/arc/configs/nsimosci_hs_smp_defconfig
+++ b/arch/arc/configs/nsimosci_hs_smp_defconfig
@@ -1,4 +1,4 @@
-CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_CROSS_COMPILE="arc-linux-"
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
diff --git a/arch/arc/configs/vdk_hs38_defconfig b/arch/arc/configs/vdk_hs38_defconfig
index ef35ef3..a07f20d 100644
--- a/arch/arc/configs/vdk_hs38_defconfig
+++ b/arch/arc/configs/vdk_hs38_defconfig
@@ -1,4 +1,4 @@
-CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_CROSS_COMPILE="arc-linux-"
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_CROSS_MEMORY_ATTACH is not set
diff --git a/arch/arc/configs/vdk_hs38_smp_defconfig b/arch/arc/configs/vdk_hs38_smp_defconfig
index 634509e..f36c047 100644
--- a/arch/arc/configs/vdk_hs38_smp_defconfig
+++ b/arch/arc/configs/vdk_hs38_smp_defconfig
@@ -1,4 +1,4 @@
-CONFIG_CROSS_COMPILE="arc-linux-uclibc-"
+CONFIG_CROSS_COMPILE="arc-linux-"
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_DEFAULT_HOSTNAME="ARCLinux"
 # CONFIG_CROSS_MEMORY_ATTACH is not set
diff --git a/arch/arc/include/asm/irqflags-arcv2.h b/arch/arc/include/asm/irqflags-arcv2.h
index ad481c2..258b0e5 100644
--- a/arch/arc/include/asm/irqflags-arcv2.h
+++ b/arch/arc/include/asm/irqflags-arcv2.h
@@ -37,6 +37,9 @@
 #define ISA_INIT_STATUS_BITS	(STATUS_IE_MASK | STATUS_AD_MASK | \
 					(ARCV2_IRQ_DEF_PRIO << 1))
 
+/* SLEEP needs default irq priority (<=) which can interrupt the doze */
+#define ISA_SLEEP_ARG		(0x10 | ARCV2_IRQ_DEF_PRIO)
+
 #ifndef __ASSEMBLY__
 
 /*
diff --git a/arch/arc/include/asm/irqflags-compact.h b/arch/arc/include/asm/irqflags-compact.h
index d8c6081..c1d3645 100644
--- a/arch/arc/include/asm/irqflags-compact.h
+++ b/arch/arc/include/asm/irqflags-compact.h
@@ -43,6 +43,8 @@
 
 #define ISA_INIT_STATUS_BITS	STATUS_IE_MASK
 
+#define ISA_SLEEP_ARG		0x3
+
 #ifndef __ASSEMBLY__
 
 /******************************************************************
diff --git a/arch/arc/kernel/ctx_sw.c b/arch/arc/kernel/ctx_sw.c
index c14a5be..5d446df 100644
--- a/arch/arc/kernel/ctx_sw.c
+++ b/arch/arc/kernel/ctx_sw.c
@@ -58,8 +58,6 @@
 		"st      sp, [r24]       \n\t"
 #endif
 
-		"sync   \n\t"
-
 		/*
 		 * setup _current_task with incoming tsk.
 		 * optionally, set r25 to that as well
diff --git a/arch/arc/kernel/ctx_sw_asm.S b/arch/arc/kernel/ctx_sw_asm.S
index e248594..e6890b1 100644
--- a/arch/arc/kernel/ctx_sw_asm.S
+++ b/arch/arc/kernel/ctx_sw_asm.S
@@ -44,9 +44,6 @@
 	* don't need to do anything special to return it
 	*/
 
-	/* hardware memory barrier */
-	sync
-
 	/*
 	 * switch to new task, contained in r1
 	 * Temp reg r3 is required to get the ptr to store val
diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index 91d5a0f..a3f750e 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -44,11 +44,10 @@
 void arch_cpu_idle(void)
 {
 	/* sleep, but enable all interrupts before committing */
-	if (is_isa_arcompact()) {
-		__asm__("sleep 0x3");
-	} else {
-		__asm__("sleep 0x10");
-	}
+	__asm__ __volatile__(
+		"sleep %0	\n"
+		:
+		:"I"(ISA_SLEEP_ARG)); /* can't be "r" has to be embedded const */
 }
 
 asmlinkage void ret_from_fork(void);
diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c
index 93c6ea5..7352475 100644
--- a/arch/arc/kernel/unwind.c
+++ b/arch/arc/kernel/unwind.c
@@ -986,42 +986,13 @@
 							    (const u8 *)(fde +
 									 1) +
 							    *fde, ptrType);
-				if (pc >= endLoc)
+				if (pc >= endLoc) {
 					fde = NULL;
-			} else
-				fde = NULL;
-		}
-		if (fde == NULL) {
-			for (fde = table->address, tableSize = table->size;
-			     cie = NULL, tableSize > sizeof(*fde)
-			     && tableSize - sizeof(*fde) >= *fde;
-			     tableSize -= sizeof(*fde) + *fde,
-			     fde += 1 + *fde / sizeof(*fde)) {
-				cie = cie_for_fde(fde, table);
-				if (cie == &bad_cie) {
 					cie = NULL;
-					break;
 				}
-				if (cie == NULL
-				    || cie == &not_fde
-				    || (ptrType = fde_pointer_type(cie)) < 0)
-					continue;
-				ptr = (const u8 *)(fde + 2);
-				startLoc = read_pointer(&ptr,
-							(const u8 *)(fde + 1) +
-							*fde, ptrType);
-				if (!startLoc)
-					continue;
-				if (!(ptrType & DW_EH_PE_indirect))
-					ptrType &=
-					    DW_EH_PE_FORM | DW_EH_PE_signed;
-				endLoc =
-				    startLoc + read_pointer(&ptr,
-							    (const u8 *)(fde +
-									 1) +
-							    *fde, ptrType);
-				if (pc >= startLoc && pc < endLoc)
-					break;
+			} else {
+				fde = NULL;
+				cie = NULL;
 			}
 		}
 	}
diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c
index 0ee7398..daf2bf5 100644
--- a/arch/arc/mm/tlb.c
+++ b/arch/arc/mm/tlb.c
@@ -619,10 +619,10 @@
 
 		int dirty = !test_and_set_bit(PG_dc_clean, &page->flags);
 		if (dirty) {
-			/* wback + inv dcache lines */
+			/* wback + inv dcache lines (K-mapping) */
 			__flush_dcache_page(paddr, paddr);
 
-			/* invalidate any existing icache lines */
+			/* invalidate any existing icache lines (U-mapping) */
 			if (vma->vm_flags & VM_EXEC)
 				__inv_icache_page(paddr, vaddr);
 		}
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 0365cbb..34e1569 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -76,6 +76,8 @@
 	select IRQ_FORCED_THREADING
 	select MODULES_USE_ELF_REL
 	select NO_BOOTMEM
+	select OF_EARLY_FLATTREE if OF
+	select OF_RESERVED_MEM if OF
 	select OLD_SIGACTION
 	select OLD_SIGSUSPEND3
 	select PERF_USE_VMALLOC
@@ -1822,8 +1824,6 @@
 	bool "Flattened Device Tree support"
 	select IRQ_DOMAIN
 	select OF
-	select OF_EARLY_FLATTREE
-	select OF_RESERVED_MEM
 	help
 	  Include support for flattened device tree machine descriptions.
 
diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi
index d83ff9c..de8791a 100644
--- a/arch/arm/boot/dts/am4372.dtsi
+++ b/arch/arm/boot/dts/am4372.dtsi
@@ -74,7 +74,7 @@
 		reg = <0x48240200 0x100>;
 		interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>;
 		interrupt-parent = <&gic>;
-		clocks = <&dpll_mpu_m2_ck>;
+		clocks = <&mpu_periphclk>;
 	};
 
 	local_timer: timer@48240600 {
@@ -82,7 +82,7 @@
 		reg = <0x48240600 0x100>;
 		interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_HIGH>;
 		interrupt-parent = <&gic>;
-		clocks = <&dpll_mpu_m2_ck>;
+		clocks = <&mpu_periphclk>;
 	};
 
 	l2-cache-controller@48242000 {
diff --git a/arch/arm/boot/dts/am43xx-clocks.dtsi b/arch/arm/boot/dts/am43xx-clocks.dtsi
index cc88728..a38af2b 100644
--- a/arch/arm/boot/dts/am43xx-clocks.dtsi
+++ b/arch/arm/boot/dts/am43xx-clocks.dtsi
@@ -259,6 +259,14 @@
 		ti,invert-autoidle-bit;
 	};
 
+	mpu_periphclk: mpu_periphclk {
+		#clock-cells = <0>;
+		compatible = "fixed-factor-clock";
+		clocks = <&dpll_mpu_m2_ck>;
+		clock-mult = <1>;
+		clock-div = <2>;
+	};
+
 	dpll_ddr_ck: dpll_ddr_ck {
 		#clock-cells = <0>;
 		compatible = "ti,am3-dpll-clock";
diff --git a/arch/arm/boot/dts/am57xx-beagle-x15.dts b/arch/arm/boot/dts/am57xx-beagle-x15.dts
index d9ba6b8..00352e7 100644
--- a/arch/arm/boot/dts/am57xx-beagle-x15.dts
+++ b/arch/arm/boot/dts/am57xx-beagle-x15.dts
@@ -604,6 +604,7 @@
 		reg = <0x6f>;
 		interrupts-extended = <&crossbar_mpu GIC_SPI 2 IRQ_TYPE_EDGE_RISING>,
 				      <&dra7_pmx_core 0x424>;
+		interrupt-names = "irq", "wakeup";
 
 		pinctrl-names = "default";
 		pinctrl-0 = <&mcp79410_pins_default>;
diff --git a/arch/arm/boot/dts/animeo_ip.dts b/arch/arm/boot/dts/animeo_ip.dts
index 4e0ad3b..0962f2f 100644
--- a/arch/arm/boot/dts/animeo_ip.dts
+++ b/arch/arm/boot/dts/animeo_ip.dts
@@ -155,21 +155,21 @@
 			label = "keyswitch_in";
 			gpios = <&pioB 1 GPIO_ACTIVE_HIGH>;
 			linux,code = <28>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 		error_in {
 			label = "error_in";
 			gpios = <&pioB 2 GPIO_ACTIVE_HIGH>;
 			linux,code = <29>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 		btn {
 			label = "btn";
 			gpios = <&pioC 23 GPIO_ACTIVE_HIGH>;
 			linux,code = <31>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/armada-38x.dtsi b/arch/arm/boot/dts/armada-38x.dtsi
index c6a0e9d..e8b7f67 100644
--- a/arch/arm/boot/dts/armada-38x.dtsi
+++ b/arch/arm/boot/dts/armada-38x.dtsi
@@ -498,6 +498,7 @@
 				reg = <0x70000 0x4000>;
 				interrupts-extended = <&mpic 8>;
 				clocks = <&gateclk 4>;
+				tx-csum-limit = <9800>;
 				status = "disabled";
 			};
 
diff --git a/arch/arm/boot/dts/at91-foxg20.dts b/arch/arm/boot/dts/at91-foxg20.dts
index f89598a..6bf873e 100644
--- a/arch/arm/boot/dts/at91-foxg20.dts
+++ b/arch/arm/boot/dts/at91-foxg20.dts
@@ -159,7 +159,7 @@
 			label = "Button";
 			gpios = <&pioC 4 GPIO_ACTIVE_LOW>;
 			linux,code = <0x103>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/at91-kizbox.dts b/arch/arm/boot/dts/at91-kizbox.dts
index bf18ece..229e989 100644
--- a/arch/arm/boot/dts/at91-kizbox.dts
+++ b/arch/arm/boot/dts/at91-kizbox.dts
@@ -24,15 +24,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <18432000>;
-		};
-
 		main_xtal {
 			clock-frequency = <18432000>;
 		};
@@ -94,14 +85,14 @@
 			label = "PB_RST";
 			gpios = <&pioB 30 GPIO_ACTIVE_HIGH>;
 			linux,code = <0x100>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 		user {
 			label = "PB_USER";
 			gpios = <&pioB 31 GPIO_ACTIVE_HIGH>;
 			linux,code = <0x101>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/at91-kizbox2.dts b/arch/arm/boot/dts/at91-kizbox2.dts
index f0b1563..50a1456 100644
--- a/arch/arm/boot/dts/at91-kizbox2.dts
+++ b/arch/arm/boot/dts/at91-kizbox2.dts
@@ -171,21 +171,21 @@
 			label = "PB_PROG";
 			gpios = <&pioE 27 GPIO_ACTIVE_LOW>;
 			linux,code = <0x102>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 		reset {
 			label = "PB_RST";
 			gpios = <&pioE 29 GPIO_ACTIVE_LOW>;
 			linux,code = <0x100>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 		user {
 			label = "PB_USER";
 			gpios = <&pioE 31 GPIO_ACTIVE_HIGH>;
 			linux,code = <0x101>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/at91-kizboxmini.dts b/arch/arm/boot/dts/at91-kizboxmini.dts
index 9f72b49..9682d10 100644
--- a/arch/arm/boot/dts/at91-kizboxmini.dts
+++ b/arch/arm/boot/dts/at91-kizboxmini.dts
@@ -98,14 +98,14 @@
 			label = "PB_PROG";
 			gpios = <&pioC 17 GPIO_ACTIVE_LOW>;
 			linux,code = <0x102>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 		reset {
 			label = "PB_RST";
 			gpios = <&pioC 16 GPIO_ACTIVE_LOW>;
 			linux,code = <0x100>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/at91-qil_a9260.dts b/arch/arm/boot/dts/at91-qil_a9260.dts
index a9aef53..4f2eebf 100644
--- a/arch/arm/boot/dts/at91-qil_a9260.dts
+++ b/arch/arm/boot/dts/at91-qil_a9260.dts
@@ -183,7 +183,7 @@
 			label = "user_pb";
 			gpios = <&pioB 10 GPIO_ACTIVE_LOW>;
 			linux,code = <28>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/at91-sama5d2_xplained.dts b/arch/arm/boot/dts/at91-sama5d2_xplained.dts
index e07c2b2..e74df32 100644
--- a/arch/arm/boot/dts/at91-sama5d2_xplained.dts
+++ b/arch/arm/boot/dts/at91-sama5d2_xplained.dts
@@ -45,6 +45,7 @@
 /dts-v1/;
 #include "sama5d2.dtsi"
 #include "sama5d2-pinfunc.h"
+#include <dt-bindings/mfd/atmel-flexcom.h>
 
 / {
 	model = "Atmel SAMA5D2 Xplained";
@@ -59,15 +60,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <12000000>;
-		};
-
 		slow_xtal {
 			clock-frequency = <32768>;
 		};
@@ -91,6 +83,22 @@
 			status = "okay";
 		};
 
+		sdmmc0: sdio-host@a0000000 {
+			bus-width = <8>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_sdmmc0_default>;
+			non-removable;
+			mmc-ddr-1_8v;
+			status = "okay";
+		};
+
+		sdmmc1: sdio-host@b0000000 {
+			bus-width = <4>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&pinctrl_sdmmc1_default>;
+			status = "okay"; /* conflict with qspi0 */
+		};
+
 		apb {
 			spi0: spi@f8000000 {
 				pinctrl-names = "default";
@@ -176,17 +184,55 @@
 							regulator-name = "VDD_SDHC_1V8";
 							regulator-min-microvolt = <1800000>;
 							regulator-max-microvolt = <1800000>;
+							regulator-always-on;
 						};
 					};
 				};
 			};
 
+			flx0: flexcom@f8034000 {
+				atmel,flexcom-mode = <ATMEL_FLEXCOM_MODE_USART>;
+				status = "disabled"; /* conflict with ISC_D2 & ISC_D3 data pins */
+
+				uart5: serial@200 {
+					compatible = "atmel,at91sam9260-usart";
+					reg = <0x200 0x200>;
+					interrupts = <19 IRQ_TYPE_LEVEL_HIGH 7>;
+					clocks = <&flx0_clk>;
+					clock-names = "usart";
+					pinctrl-names = "default";
+					pinctrl-0 = <&pinctrl_flx0_default>;
+					atmel,fifo-size = <32>;
+					status = "okay";
+				};
+			};
+
 			uart3: serial@fc008000 {
 				pinctrl-names = "default";
 				pinctrl-0 = <&pinctrl_uart3_default>;
 				status = "okay";
 			};
 
+			flx4: flexcom@fc018000 {
+				atmel,flexcom-mode = <ATMEL_FLEXCOM_MODE_TWI>;
+				status = "okay";
+
+				i2c2: i2c@600 {
+					compatible = "atmel,sama5d2-i2c";
+					reg = <0x600 0x200>;
+					interrupts = <23 IRQ_TYPE_LEVEL_HIGH 7>;
+					dmas = <0>, <0>;
+					dma-names = "tx", "rx";
+					#address-cells = <1>;
+					#size-cells = <0>;
+					clocks = <&flx4_clk>;
+					pinctrl-names = "default";
+					pinctrl-0 = <&pinctrl_flx4_default>;
+					atmel,fifo-size = <16>;
+					status = "okay";
+				};
+			};
+
 			i2c1: i2c@fc028000 {
 				dmas = <0>, <0>;
 				pinctrl-names = "default";
@@ -201,6 +247,18 @@
 			};
 
 			pinctrl@fc038000 {
+				pinctrl_flx0_default: flx0_default {
+					pinmux = <PIN_PB28__FLEXCOM0_IO0>,
+						 <PIN_PB29__FLEXCOM0_IO1>;
+					bias-disable;
+				};
+
+				pinctrl_flx4_default: flx4_default {
+					pinmux = <PIN_PD12__FLEXCOM4_IO0>,
+						 <PIN_PD13__FLEXCOM4_IO1>;
+					bias-disable;
+				};
+
 				pinctrl_i2c0_default: i2c0_default {
 					pinmux = <PIN_PD21__TWD0>,
 						 <PIN_PD22__TWCK0>;
@@ -227,6 +285,46 @@
 					bias-disable;
 				};
 
+				pinctrl_sdmmc0_default: sdmmc0_default {
+					cmd_data {
+						pinmux = <PIN_PA1__SDMMC0_CMD>,
+							 <PIN_PA2__SDMMC0_DAT0>,
+							 <PIN_PA3__SDMMC0_DAT1>,
+							 <PIN_PA4__SDMMC0_DAT2>,
+							 <PIN_PA5__SDMMC0_DAT3>,
+							 <PIN_PA6__SDMMC0_DAT4>,
+							 <PIN_PA7__SDMMC0_DAT5>,
+							 <PIN_PA8__SDMMC0_DAT6>,
+							 <PIN_PA9__SDMMC0_DAT7>;
+						bias-pull-up;
+					};
+
+					ck_cd_rstn_vddsel {
+						pinmux = <PIN_PA0__SDMMC0_CK>,
+							 <PIN_PA10__SDMMC0_RSTN>,
+							 <PIN_PA11__SDMMC0_VDDSEL>,
+							 <PIN_PA13__SDMMC0_CD>;
+						bias-disable;
+					};
+				};
+
+				pinctrl_sdmmc1_default: sdmmc1_default {
+					cmd_data {
+						pinmux = <PIN_PA28__SDMMC1_CMD>,
+							 <PIN_PA18__SDMMC1_DAT0>,
+							 <PIN_PA19__SDMMC1_DAT1>,
+							 <PIN_PA20__SDMMC1_DAT2>,
+							 <PIN_PA21__SDMMC1_DAT3>;
+						bias-pull-up;
+					};
+
+					conf-ck_cd {
+						pinmux = <PIN_PA22__SDMMC1_CK>,
+							 <PIN_PA30__SDMMC1_CD>;
+						bias-disable;
+					};
+				};
+
 				pinctrl_spi0_default: spi0_default {
 					pinmux = <PIN_PA14__SPI0_SPCK>,
 						 <PIN_PA15__SPI0_MOSI>,
diff --git a/arch/arm/boot/dts/at91-sama5d3_xplained.dts b/arch/arm/boot/dts/at91-sama5d3_xplained.dts
index 8488ac5..ff888d2 100644
--- a/arch/arm/boot/dts/at91-sama5d3_xplained.dts
+++ b/arch/arm/boot/dts/at91-sama5d3_xplained.dts
@@ -315,7 +315,7 @@
 			label = "PB_USER";
 			gpios = <&pioE 29 GPIO_ACTIVE_LOW>;
 			linux,code = <0x104>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/at91-sama5d4_xplained.dts b/arch/arm/boot/dts/at91-sama5d4_xplained.dts
index 45371a1..131614f 100644
--- a/arch/arm/boot/dts/at91-sama5d4_xplained.dts
+++ b/arch/arm/boot/dts/at91-sama5d4_xplained.dts
@@ -50,7 +50,6 @@
 	compatible = "atmel,sama5d4-xplained", "atmel,sama5d4", "atmel,sama5";
 
 	chosen {
-		bootargs = "ignore_loglevel earlyprintk";
 		stdout-path = "serial0:115200n8";
 	};
 
@@ -59,15 +58,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <12000000>;
-		};
-
 		slow_xtal {
 			clock-frequency = <32768>;
 		};
@@ -235,7 +225,7 @@
 			label = "pb_user1";
 			gpios = <&pioE 8 GPIO_ACTIVE_HIGH>;
 			linux,code = <0x100>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/at91-sama5d4ek.dts b/arch/arm/boot/dts/at91-sama5d4ek.dts
index 6d272c0..2d4a331 100644
--- a/arch/arm/boot/dts/at91-sama5d4ek.dts
+++ b/arch/arm/boot/dts/at91-sama5d4ek.dts
@@ -50,7 +50,6 @@
 	compatible = "atmel,sama5d4ek", "atmel,sama5d4", "atmel,sama5";
 
 	chosen {
-		bootargs = "ignore_loglevel earlyprintk";
 		stdout-path = "serial0:115200n8";
 	};
 
@@ -59,15 +58,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <12000000>;
-		};
-
 		slow_xtal {
 			clock-frequency = <32768>;
 		};
@@ -304,7 +294,7 @@
 			label = "pb_user1";
 			gpios = <&pioE 13 GPIO_ACTIVE_HIGH>;
 			linux,code = <0x100>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/at91rm9200ek.dts b/arch/arm/boot/dts/at91rm9200ek.dts
index 8dab4b7..f90e1c2 100644
--- a/arch/arm/boot/dts/at91rm9200ek.dts
+++ b/arch/arm/boot/dts/at91rm9200ek.dts
@@ -21,15 +21,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <18432000>;
-		};
-
 		slow_xtal {
 			clock-frequency = <32768>;
 		};
diff --git a/arch/arm/boot/dts/at91sam9261ek.dts b/arch/arm/boot/dts/at91sam9261ek.dts
index 2e92ac0..55bd51f 100644
--- a/arch/arm/boot/dts/at91sam9261ek.dts
+++ b/arch/arm/boot/dts/at91sam9261ek.dts
@@ -22,15 +22,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <18432000>;
-		};
-
 		slow_xtal {
 			clock-frequency = <32768>;
 		};
@@ -149,7 +140,7 @@
 					ti,debounce-tol = /bits/ 16 <65535>;
 					ti,debounce-max = /bits/ 16 <1>;
 
-					linux,wakeup;
+					wakeup-source;
 				};
 			};
 
@@ -193,28 +184,28 @@
 			label = "button_0";
 			gpios = <&pioA 27 GPIO_ACTIVE_LOW>;
 			linux,code = <256>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 		button_1 {
 			label = "button_1";
 			gpios = <&pioA 26 GPIO_ACTIVE_LOW>;
 			linux,code = <257>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 		button_2 {
 			label = "button_2";
 			gpios = <&pioA 25 GPIO_ACTIVE_LOW>;
 			linux,code = <258>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 		button_3 {
 			label = "button_3";
 			gpios = <&pioA 24 GPIO_ACTIVE_LOW>;
 			linux,code = <259>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/at91sam9263ek.dts b/arch/arm/boot/dts/at91sam9263ek.dts
index 2338127..59df9d7 100644
--- a/arch/arm/boot/dts/at91sam9263ek.dts
+++ b/arch/arm/boot/dts/at91sam9263ek.dts
@@ -22,15 +22,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <16367660>;
-		};
-
 		slow_xtal {
 			clock-frequency = <32768>;
 		};
@@ -213,14 +204,14 @@
 			label = "left_click";
 			gpios = <&pioC 5 GPIO_ACTIVE_LOW>;
 			linux,code = <272>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 		right_click {
 			label = "right_click";
 			gpios = <&pioC 4 GPIO_ACTIVE_LOW>;
 			linux,code = <273>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/at91sam9g20ek_common.dtsi b/arch/arm/boot/dts/at91sam9g20ek_common.dtsi
index 57548a2..e9cc99b 100644
--- a/arch/arm/boot/dts/at91sam9g20ek_common.dtsi
+++ b/arch/arm/boot/dts/at91sam9g20ek_common.dtsi
@@ -19,15 +19,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <18432000>;
-		};
-
 		slow_xtal {
 			clock-frequency = <32768>;
 		};
@@ -206,14 +197,14 @@
 			label = "Button 3";
 			gpios = <&pioA 30 GPIO_ACTIVE_LOW>;
 			linux,code = <0x103>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 		btn4 {
 			label = "Button 4";
 			gpios = <&pioA 31 GPIO_ACTIVE_LOW>;
 			linux,code = <0x104>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/at91sam9m10g45ek.dts b/arch/arm/boot/dts/at91sam9m10g45ek.dts
index 9d16ef8..2400c99 100644
--- a/arch/arm/boot/dts/at91sam9m10g45ek.dts
+++ b/arch/arm/boot/dts/at91sam9m10g45ek.dts
@@ -24,15 +24,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <12000000>;
-		};
-
 		slow_xtal {
 		      clock-frequency = <32768>;
 		};
@@ -323,14 +314,14 @@
 			label = "left_click";
 			gpios = <&pioB 6 GPIO_ACTIVE_LOW>;
 			linux,code = <272>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 		right_click {
 			label = "right_click";
 			gpios = <&pioB 7 GPIO_ACTIVE_LOW>;
 			linux,code = <273>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 		left {
diff --git a/arch/arm/boot/dts/at91sam9n12ek.dts b/arch/arm/boot/dts/at91sam9n12ek.dts
index acf3451..ca4ddf8 100644
--- a/arch/arm/boot/dts/at91sam9n12ek.dts
+++ b/arch/arm/boot/dts/at91sam9n12ek.dts
@@ -23,15 +23,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <16000000>;
-		};
-
 		slow_xtal {
 			clock-frequency = <32768>;
 		};
@@ -219,7 +210,7 @@
 			label = "Enter";
 			gpios = <&pioB 3 GPIO_ACTIVE_LOW>;
 			linux,code = <28>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/at91sam9rlek.dts b/arch/arm/boot/dts/at91sam9rlek.dts
index 558c9f2..f10566f 100644
--- a/arch/arm/boot/dts/at91sam9rlek.dts
+++ b/arch/arm/boot/dts/at91sam9rlek.dts
@@ -22,15 +22,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <12000000>;
-		};
-
 		slow_xtal {
 			clock-frequency = <32768>;
 		};
@@ -225,14 +216,14 @@
 			label = "right_click";
 			gpios = <&pioB 0 GPIO_ACTIVE_LOW>;
 			linux,code = <273>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 
 		left_click {
 			label = "left_click";
 			gpios = <&pioB 1 GPIO_ACTIVE_LOW>;
 			linux,code = <272>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/at91sam9x5cm.dtsi b/arch/arm/boot/dts/at91sam9x5cm.dtsi
index 26112eb..b098ad8 100644
--- a/arch/arm/boot/dts/at91sam9x5cm.dtsi
+++ b/arch/arm/boot/dts/at91sam9x5cm.dtsi
@@ -13,17 +13,6 @@
 	};
 
 	clocks {
-		#address-cells = <1>;
-		#size-cells = <1>;
-		ranges;
-
-		main_clock: clock@0 {
-			compatible = "atmel,osc", "fixed-clock";
-			clock-frequency = <12000000>;
-		};
-	};
-
-	clocks {
 		slow_xtal {
 			clock-frequency = <32768>;
 		};
diff --git a/arch/arm/boot/dts/berlin2q.dtsi b/arch/arm/boot/dts/berlin2q.dtsi
index 8ea177f..fb1da99 100644
--- a/arch/arm/boot/dts/berlin2q.dtsi
+++ b/arch/arm/boot/dts/berlin2q.dtsi
@@ -118,7 +118,8 @@
 		sdhci0: sdhci@ab0000 {
 			compatible = "mrvl,pxav3-mmc";
 			reg = <0xab0000 0x200>;
-			clocks = <&chip_clk CLKID_SDIO1XIN>;
+			clocks = <&chip_clk CLKID_SDIO1XIN>, <&chip_clk CLKID_SDIO>;
+			clock-names = "io", "core";
 			interrupts = <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>;
 			status = "disabled";
 		};
@@ -126,7 +127,8 @@
 		sdhci1: sdhci@ab0800 {
 			compatible = "mrvl,pxav3-mmc";
 			reg = <0xab0800 0x200>;
-			clocks = <&chip_clk CLKID_SDIO1XIN>;
+			clocks = <&chip_clk CLKID_SDIO1XIN>, <&chip_clk CLKID_SDIO>;
+			clock-names = "io", "core";
 			interrupts = <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>;
 			status = "disabled";
 		};
@@ -135,7 +137,7 @@
 			compatible = "mrvl,pxav3-mmc";
 			reg = <0xab1000 0x200>;
 			interrupts = <GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&chip_clk CLKID_NFC_ECC>, <&chip_clk CLKID_NFC>;
+			clocks = <&chip_clk CLKID_NFC_ECC>, <&chip_clk CLKID_SDIO>;
 			clock-names = "io", "core";
 			status = "disabled";
 		};
diff --git a/arch/arm/boot/dts/dm816x.dtsi b/arch/arm/boot/dts/dm816x.dtsi
index 3c99cfa..eee636d 100644
--- a/arch/arm/boot/dts/dm816x.dtsi
+++ b/arch/arm/boot/dts/dm816x.dtsi
@@ -218,6 +218,7 @@
 			reg = <0x480c8000 0x2000>;
 			interrupts = <77>;
 			ti,hwmods = "mailbox";
+			#mbox-cells = <1>;
 			ti,mbox-num-users = <4>;
 			ti,mbox-num-fifos = <12>;
 			mbox_dsp: mbox_dsp {
@@ -279,8 +280,11 @@
 			ti,spi-num-cs = <4>;
 			ti,hwmods = "mcspi1";
 			dmas = <&edma 16 &edma 17
-				&edma 18 &edma 19>;
-			dma-names = "tx0", "rx0", "tx1", "rx1";
+				&edma 18 &edma 19
+				&edma 20 &edma 21
+				&edma 22 &edma 23>;
+			dma-names = "tx0", "rx0", "tx1", "rx1",
+				    "tx2", "rx2", "tx3", "rx3";
 		};
 
 		mmc1: mmc@48060000 {
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index bc672fb..fe99231 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -1459,8 +1459,8 @@
 			interrupt-names = "tx", "rx";
 			dmas = <&sdma_xbar 133>, <&sdma_xbar 132>;
 			dma-names = "tx", "rx";
-			clocks = <&mcasp3_ahclkx_mux>;
-			clock-names = "fck";
+			clocks = <&mcasp3_aux_gfclk_mux>, <&mcasp3_ahclkx_mux>;
+			clock-names = "fck", "ahclkx";
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/imx27.dtsi b/arch/arm/boot/dts/imx27.dtsi
index feb9d34..f818ea4 100644
--- a/arch/arm/boot/dts/imx27.dtsi
+++ b/arch/arm/boot/dts/imx27.dtsi
@@ -486,7 +486,10 @@
 				compatible = "fsl,imx27-usb";
 				reg = <0x10024000 0x200>;
 				interrupts = <56>;
-				clocks = <&clks IMX27_CLK_USB_IPG_GATE>;
+				clocks = <&clks IMX27_CLK_USB_IPG_GATE>,
+					<&clks IMX27_CLK_USB_AHB_GATE>,
+					<&clks IMX27_CLK_USB_DIV>;
+				clock-names = "ipg", "ahb", "per";
 				fsl,usbmisc = <&usbmisc 0>;
 				status = "disabled";
 			};
@@ -495,7 +498,10 @@
 				compatible = "fsl,imx27-usb";
 				reg = <0x10024200 0x200>;
 				interrupts = <54>;
-				clocks = <&clks IMX27_CLK_USB_IPG_GATE>;
+				clocks = <&clks IMX27_CLK_USB_IPG_GATE>,
+					<&clks IMX27_CLK_USB_AHB_GATE>,
+					<&clks IMX27_CLK_USB_DIV>;
+				clock-names = "ipg", "ahb", "per";
 				fsl,usbmisc = <&usbmisc 1>;
 				dr_mode = "host";
 				status = "disabled";
@@ -505,7 +511,10 @@
 				compatible = "fsl,imx27-usb";
 				reg = <0x10024400 0x200>;
 				interrupts = <55>;
-				clocks = <&clks IMX27_CLK_USB_IPG_GATE>;
+				clocks = <&clks IMX27_CLK_USB_IPG_GATE>,
+					<&clks IMX27_CLK_USB_AHB_GATE>,
+					<&clks IMX27_CLK_USB_DIV>;
+				clock-names = "ipg", "ahb", "per";
 				fsl,usbmisc = <&usbmisc 2>;
 				dr_mode = "host";
 				status = "disabled";
@@ -515,7 +524,6 @@
 				#index-cells = <1>;
 				compatible = "fsl,imx27-usbmisc";
 				reg = <0x10024600 0x200>;
-				clocks = <&clks IMX27_CLK_USB_AHB_GATE>;
 			};
 
 			sahara2: sahara@10025000 {
diff --git a/arch/arm/boot/dts/k2l-netcp.dtsi b/arch/arm/boot/dts/k2l-netcp.dtsi
index 01aef23..5acbd0d 100644
--- a/arch/arm/boot/dts/k2l-netcp.dtsi
+++ b/arch/arm/boot/dts/k2l-netcp.dtsi
@@ -137,7 +137,7 @@
 	/* NetCP address range */
 	ranges = <0 0x26000000 0x1000000>;
 
-	clocks = <&papllclk>, <&clkcpgmac>, <&chipclk12>;
+	clocks = <&clkosr>, <&papllclk>, <&clkcpgmac>, <&chipclk12>;
 	dma-coherent;
 
 	ti,navigator-dmas = <&dma_gbe 0>,
diff --git a/arch/arm/boot/dts/kirkwood-ts219.dtsi b/arch/arm/boot/dts/kirkwood-ts219.dtsi
index c56ab6b..0e46560 100644
--- a/arch/arm/boot/dts/kirkwood-ts219.dtsi
+++ b/arch/arm/boot/dts/kirkwood-ts219.dtsi
@@ -40,7 +40,7 @@
 		};
 		poweroff@12100 {
 			compatible = "qnap,power-off";
-			reg = <0x12000 0x100>;
+			reg = <0x12100 0x100>;
 			clocks = <&gate_clk 7>;
 		};
 		spi@10600 {
diff --git a/arch/arm/boot/dts/rk3288-veyron-minnie.dts b/arch/arm/boot/dts/rk3288-veyron-minnie.dts
index 8fd8ef2..85f0373 100644
--- a/arch/arm/boot/dts/rk3288-veyron-minnie.dts
+++ b/arch/arm/boot/dts/rk3288-veyron-minnie.dts
@@ -86,6 +86,10 @@
 	};
 };
 
+&emmc {
+	/delete-property/mmc-hs200-1_8v;
+};
+
 &gpio_keys {
 	pinctrl-0 = <&pwr_key_l &ap_lid_int_l &volum_down_l &volum_up_l>;
 
diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi
index 6a79c9c..04ea209 100644
--- a/arch/arm/boot/dts/rk3288.dtsi
+++ b/arch/arm/boot/dts/rk3288.dtsi
@@ -452,8 +452,10 @@
 		clock-names = "tsadc", "apb_pclk";
 		resets = <&cru SRST_TSADC>;
 		reset-names = "tsadc-apb";
-		pinctrl-names = "default";
-		pinctrl-0 = <&otp_out>;
+		pinctrl-names = "init", "default", "sleep";
+		pinctrl-0 = <&otp_gpio>;
+		pinctrl-1 = <&otp_out>;
+		pinctrl-2 = <&otp_gpio>;
 		#thermal-sensor-cells = <1>;
 		rockchip,hw-tshut-temp = <95000>;
 		status = "disabled";
@@ -1395,6 +1397,10 @@
 		};
 
 		tsadc {
+			otp_gpio: otp-gpio {
+				rockchip,pins = <0 10 RK_FUNC_GPIO &pcfg_pull_none>;
+			};
+
 			otp_out: otp-out {
 				rockchip,pins = <0 10 RK_FUNC_1 &pcfg_pull_none>;
 			};
diff --git a/arch/arm/boot/dts/sama5d35ek.dts b/arch/arm/boot/dts/sama5d35ek.dts
index d9a9aca..e812f5c 100644
--- a/arch/arm/boot/dts/sama5d35ek.dts
+++ b/arch/arm/boot/dts/sama5d35ek.dts
@@ -49,7 +49,7 @@
 			label = "pb_user1";
 			gpios = <&pioE 27 GPIO_ACTIVE_HIGH>;
 			linux,code = <0x100>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/sama5d4.dtsi b/arch/arm/boot/dts/sama5d4.dtsi
index 15bbaf6..2193637 100644
--- a/arch/arm/boot/dts/sama5d4.dtsi
+++ b/arch/arm/boot/dts/sama5d4.dtsi
@@ -1300,7 +1300,7 @@
 			};
 
 			watchdog@fc068640 {
-				compatible = "atmel,at91sam9260-wdt";
+				compatible = "atmel,sama5d4-wdt";
 				reg = <0xfc068640 0x10>;
 				clocks = <&clk32k>;
 				status = "disabled";
diff --git a/arch/arm/boot/dts/usb_a9260_common.dtsi b/arch/arm/boot/dts/usb_a9260_common.dtsi
index 12edafe..9beea89 100644
--- a/arch/arm/boot/dts/usb_a9260_common.dtsi
+++ b/arch/arm/boot/dts/usb_a9260_common.dtsi
@@ -115,7 +115,7 @@
 			label = "user_pb";
 			gpios = <&pioB 10 GPIO_ACTIVE_LOW>;
 			linux,code = <28>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/usb_a9263.dts b/arch/arm/boot/dts/usb_a9263.dts
index 68c0de3..8cc6edb 100644
--- a/arch/arm/boot/dts/usb_a9263.dts
+++ b/arch/arm/boot/dts/usb_a9263.dts
@@ -143,7 +143,7 @@
 			label = "user_pb";
 			gpios = <&pioB 10 GPIO_ACTIVE_LOW>;
 			linux,code = <28>;
-			gpio-key,wakeup;
+			wakeup-source;
 		};
 	};
 
diff --git a/arch/arm/boot/dts/vf610-colibri.dtsi b/arch/arm/boot/dts/vf610-colibri.dtsi
index 19fe045..2d7eab7 100644
--- a/arch/arm/boot/dts/vf610-colibri.dtsi
+++ b/arch/arm/boot/dts/vf610-colibri.dtsi
@@ -18,8 +18,3 @@
 		reg = <0x80000000 0x10000000>;
 	};
 };
-
-&L2 {
-	arm,data-latency = <2 1 2>;
-	arm,tag-latency = <3 2 3>;
-};
diff --git a/arch/arm/boot/dts/vf610.dtsi b/arch/arm/boot/dts/vf610.dtsi
index 5f8eb1b..58bc6e4 100644
--- a/arch/arm/boot/dts/vf610.dtsi
+++ b/arch/arm/boot/dts/vf610.dtsi
@@ -19,7 +19,7 @@
 		reg = <0x40006000 0x1000>;
 		cache-unified;
 		cache-level = <2>;
-		arm,data-latency = <1 1 1>;
+		arm,data-latency = <3 3 3>;
 		arm,tag-latency = <2 2 2>;
 	};
 };
diff --git a/arch/arm/boot/dts/vfxxx.dtsi b/arch/arm/boot/dts/vfxxx.dtsi
index 6736bae..3cd1b27 100644
--- a/arch/arm/boot/dts/vfxxx.dtsi
+++ b/arch/arm/boot/dts/vfxxx.dtsi
@@ -158,7 +158,7 @@
 				interrupts = <67 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks VF610_CLK_DSPI0>;
 				clock-names = "dspi";
-				spi-num-chipselects = <5>;
+				spi-num-chipselects = <6>;
 				status = "disabled";
 			};
 
@@ -170,7 +170,7 @@
 				interrupts = <68 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks VF610_CLK_DSPI1>;
 				clock-names = "dspi";
-				spi-num-chipselects = <5>;
+				spi-num-chipselects = <4>;
 				status = "disabled";
 			};
 
@@ -178,8 +178,10 @@
 				compatible = "fsl,vf610-sai";
 				reg = <0x40031000 0x1000>;
 				interrupts = <86 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks VF610_CLK_SAI2>;
-				clock-names = "sai";
+				clocks = <&clks VF610_CLK_SAI2>,
+					<&clks VF610_CLK_SAI2_DIV>,
+					<&clks 0>, <&clks 0>;
+				clock-names = "bus", "mclk1", "mclk2", "mclk3";
 				dma-names = "tx", "rx";
 				dmas = <&edma0 0 21>,
 					<&edma0 0 20>;
@@ -461,6 +463,8 @@
 				clock-names = "adc";
 				#io-channel-cells = <1>;
 				status = "disabled";
+				fsl,adck-max-frequency = <30000000>, <40000000>,
+							<20000000>;
 			};
 
 			esdhc0: esdhc@400b1000 {
@@ -472,8 +476,6 @@
 					<&clks VF610_CLK_ESDHC0>;
 				clock-names = "ipg", "ahb", "per";
 				status = "disabled";
-				fsl,adck-max-frequency = <30000000>, <40000000>,
-							<20000000>;
 			};
 
 			esdhc1: esdhc@400b2000 {
diff --git a/arch/arm/configs/at91_dt_defconfig b/arch/arm/configs/at91_dt_defconfig
index 1b1e5ac..e4b1be6 100644
--- a/arch/arm/configs/at91_dt_defconfig
+++ b/arch/arm/configs/at91_dt_defconfig
@@ -125,7 +125,6 @@
 # CONFIG_HWMON is not set
 CONFIG_WATCHDOG=y
 CONFIG_AT91SAM9X_WATCHDOG=y
-CONFIG_SSB=m
 CONFIG_MFD_ATMEL_HLCDC=y
 CONFIG_REGULATOR=y
 CONFIG_REGULATOR_FIXED_VOLTAGE=y
diff --git a/arch/arm/configs/sama5_defconfig b/arch/arm/configs/sama5_defconfig
index a0c57ac..63f7e6c 100644
--- a/arch/arm/configs/sama5_defconfig
+++ b/arch/arm/configs/sama5_defconfig
@@ -129,7 +129,6 @@
 CONFIG_POWER_SUPPLY=y
 CONFIG_POWER_RESET=y
 # CONFIG_HWMON is not set
-CONFIG_SSB=m
 CONFIG_MFD_ATMEL_FLEXCOM=y
 CONFIG_REGULATOR=y
 CONFIG_REGULATOR_FIXED_VOLTAGE=y
diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h
index 6607d97..7da5503 100644
--- a/arch/arm/include/asm/arch_gicv3.h
+++ b/arch/arm/include/asm/arch_gicv3.h
@@ -21,6 +21,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/io.h>
+#include <asm/barrier.h>
 
 #define __ACCESS_CP15(CRn, Op1, CRm, Op2)	p15, Op1, %0, CRn, CRm, Op2
 #define __ACCESS_CP15_64(Op1, CRm)		p15, Op1, %Q0, %R0, CRm
diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h
index be1d07d..1bd9510 100644
--- a/arch/arm/include/asm/irq.h
+++ b/arch/arm/include/asm/irq.h
@@ -40,6 +40,11 @@
 #define arch_trigger_all_cpu_backtrace(x) arch_trigger_all_cpu_backtrace(x)
 #endif
 
+static inline int nr_legacy_irqs(void)
+{
+	return NR_IRQS_LEGACY;
+}
+
 #endif
 
 #endif
diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
index a9c80a2..3095df0 100644
--- a/arch/arm/include/asm/kvm_emulate.h
+++ b/arch/arm/include/asm/kvm_emulate.h
@@ -28,6 +28,18 @@
 unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num);
 unsigned long *vcpu_spsr(struct kvm_vcpu *vcpu);
 
+static inline unsigned long vcpu_get_reg(struct kvm_vcpu *vcpu,
+					 u8 reg_num)
+{
+	return *vcpu_reg(vcpu, reg_num);
+}
+
+static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num,
+				unsigned long val)
+{
+	*vcpu_reg(vcpu, reg_num) = val;
+}
+
 bool kvm_condition_valid(struct kvm_vcpu *vcpu);
 void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr);
 void kvm_inject_undefined(struct kvm_vcpu *vcpu);
diff --git a/arch/arm/include/uapi/asm/unistd.h b/arch/arm/include/uapi/asm/unistd.h
index 7a2a32a..ede692f 100644
--- a/arch/arm/include/uapi/asm/unistd.h
+++ b/arch/arm/include/uapi/asm/unistd.h
@@ -416,6 +416,7 @@
 #define __NR_execveat			(__NR_SYSCALL_BASE+387)
 #define __NR_userfaultfd		(__NR_SYSCALL_BASE+388)
 #define __NR_membarrier			(__NR_SYSCALL_BASE+389)
+#define __NR_mlock2			(__NR_SYSCALL_BASE+390)
 
 /*
  * The following SWIs are ARM private.
diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c
index 6551d28..066f7f9 100644
--- a/arch/arm/kernel/bios32.c
+++ b/arch/arm/kernel/bios32.c
@@ -17,11 +17,6 @@
 #include <asm/mach/pci.h>
 
 static int debug_pci;
-static resource_size_t (*align_resource)(struct pci_dev *dev,
-		  const struct resource *res,
-		  resource_size_t start,
-		  resource_size_t size,
-		  resource_size_t align) = NULL;
 
 /*
  * We can't use pci_get_device() here since we are
@@ -461,7 +456,6 @@
 		sys->busnr   = busnr;
 		sys->swizzle = hw->swizzle;
 		sys->map_irq = hw->map_irq;
-		align_resource = hw->align_resource;
 		INIT_LIST_HEAD(&sys->resources);
 
 		if (hw->private_data)
@@ -470,6 +464,8 @@
 		ret = hw->setup(nr, sys);
 
 		if (ret > 0) {
+			struct pci_host_bridge *host_bridge;
+
 			ret = pcibios_init_resources(nr, sys);
 			if (ret)  {
 				kfree(sys);
@@ -491,6 +487,9 @@
 			busnr = sys->bus->busn_res.end + 1;
 
 			list_add(&sys->node, head);
+
+			host_bridge = pci_find_host_bridge(sys->bus);
+			host_bridge->align_resource = hw->align_resource;
 		} else {
 			kfree(sys);
 			if (ret < 0)
@@ -578,14 +577,18 @@
 {
 	struct pci_dev *dev = data;
 	resource_size_t start = res->start;
+	struct pci_host_bridge *host_bridge;
 
 	if (res->flags & IORESOURCE_IO && start & 0x300)
 		start = (start + 0x3ff) & ~0x3ff;
 
 	start = (start + align - 1) & ~(align - 1);
 
-	if (align_resource)
-		return align_resource(dev, res, start, size, align);
+	host_bridge = pci_find_host_bridge(dev->bus);
+
+	if (host_bridge->align_resource)
+		return host_bridge->align_resource(dev, res,
+				start, size, align);
 
 	return start;
 }
diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S
index fde6c88..ac368bb 100644
--- a/arch/arm/kernel/calls.S
+++ b/arch/arm/kernel/calls.S
@@ -399,6 +399,7 @@
 		CALL(sys_execveat)
 		CALL(sys_userfaultfd)
 		CALL(sys_membarrier)
+		CALL(sys_mlock2)
 #ifndef syscalls_counted
 .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
 #define syscalls_counted
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index eab83b2..e06fd29 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -564,17 +564,12 @@
 			vcpu_sleep(vcpu);
 
 		/*
-		 * Disarming the background timer must be done in a
-		 * preemptible context, as this call may sleep.
-		 */
-		kvm_timer_flush_hwstate(vcpu);
-
-		/*
 		 * Preparing the interrupts to be injected also
 		 * involves poking the GIC, which must be done in a
 		 * non-preemptible context.
 		 */
 		preempt_disable();
+		kvm_timer_flush_hwstate(vcpu);
 		kvm_vgic_flush_hwstate(vcpu);
 
 		local_irq_disable();
diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c
index 974b1c6..3a10c9f 100644
--- a/arch/arm/kvm/mmio.c
+++ b/arch/arm/kvm/mmio.c
@@ -115,7 +115,7 @@
 		trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr,
 			       data);
 		data = vcpu_data_host_to_guest(vcpu, data, len);
-		*vcpu_reg(vcpu, vcpu->arch.mmio_decode.rt) = data;
+		vcpu_set_reg(vcpu, vcpu->arch.mmio_decode.rt, data);
 	}
 
 	return 0;
@@ -186,7 +186,8 @@
 	rt = vcpu->arch.mmio_decode.rt;
 
 	if (is_write) {
-		data = vcpu_data_guest_to_host(vcpu, *vcpu_reg(vcpu, rt), len);
+		data = vcpu_data_guest_to_host(vcpu, vcpu_get_reg(vcpu, rt),
+					       len);
 
 		trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, len, fault_ipa, data);
 		mmio_write_buf(data_buf, len, data);
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 6984342..61d96a6 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -98,6 +98,11 @@
 	__kvm_flush_dcache_pud(pud);
 }
 
+static bool kvm_is_device_pfn(unsigned long pfn)
+{
+	return !pfn_valid(pfn);
+}
+
 /**
  * stage2_dissolve_pmd() - clear and flush huge PMD entry
  * @kvm:	pointer to kvm structure.
@@ -213,7 +218,7 @@
 			kvm_tlb_flush_vmid_ipa(kvm, addr);
 
 			/* No need to invalidate the cache for device mappings */
-			if ((pte_val(old_pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE)
+			if (!kvm_is_device_pfn(pte_pfn(old_pte)))
 				kvm_flush_dcache_pte(old_pte);
 
 			put_page(virt_to_page(pte));
@@ -305,8 +310,7 @@
 
 	pte = pte_offset_kernel(pmd, addr);
 	do {
-		if (!pte_none(*pte) &&
-		    (pte_val(*pte) & PAGE_S2_DEVICE) != PAGE_S2_DEVICE)
+		if (!pte_none(*pte) && !kvm_is_device_pfn(pte_pfn(*pte)))
 			kvm_flush_dcache_pte(*pte);
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 }
@@ -1037,11 +1041,6 @@
 	return kvm_vcpu_dabt_iswrite(vcpu);
 }
 
-static bool kvm_is_device_pfn(unsigned long pfn)
-{
-	return !pfn_valid(pfn);
-}
-
 /**
  * stage2_wp_ptes - write protect PMD range
  * @pmd:	pointer to pmd entry
diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index 0b55696..a9b3b90 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -75,7 +75,7 @@
 	unsigned long context_id;
 	phys_addr_t target_pc;
 
-	cpu_id = *vcpu_reg(source_vcpu, 1) & MPIDR_HWID_BITMASK;
+	cpu_id = vcpu_get_reg(source_vcpu, 1) & MPIDR_HWID_BITMASK;
 	if (vcpu_mode_is_32bit(source_vcpu))
 		cpu_id &= ~((u32) 0);
 
@@ -94,8 +94,8 @@
 			return PSCI_RET_INVALID_PARAMS;
 	}
 
-	target_pc = *vcpu_reg(source_vcpu, 2);
-	context_id = *vcpu_reg(source_vcpu, 3);
+	target_pc = vcpu_get_reg(source_vcpu, 2);
+	context_id = vcpu_get_reg(source_vcpu, 3);
 
 	kvm_reset_vcpu(vcpu);
 
@@ -114,7 +114,7 @@
 	 * NOTE: We always update r0 (or x0) because for PSCI v0.1
 	 * the general puspose registers are undefined upon CPU_ON.
 	 */
-	*vcpu_reg(vcpu, 0) = context_id;
+	vcpu_set_reg(vcpu, 0, context_id);
 	vcpu->arch.power_off = false;
 	smp_mb();		/* Make sure the above is visible */
 
@@ -134,8 +134,8 @@
 	struct kvm *kvm = vcpu->kvm;
 	struct kvm_vcpu *tmp;
 
-	target_affinity = *vcpu_reg(vcpu, 1);
-	lowest_affinity_level = *vcpu_reg(vcpu, 2);
+	target_affinity = vcpu_get_reg(vcpu, 1);
+	lowest_affinity_level = vcpu_get_reg(vcpu, 2);
 
 	/* Determine target affinity mask */
 	target_affinity_mask = psci_affinity_mask(lowest_affinity_level);
@@ -209,7 +209,7 @@
 static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu)
 {
 	int ret = 1;
-	unsigned long psci_fn = *vcpu_reg(vcpu, 0) & ~((u32) 0);
+	unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0);
 	unsigned long val;
 
 	switch (psci_fn) {
@@ -273,13 +273,13 @@
 		break;
 	}
 
-	*vcpu_reg(vcpu, 0) = val;
+	vcpu_set_reg(vcpu, 0, val);
 	return ret;
 }
 
 static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu)
 {
-	unsigned long psci_fn = *vcpu_reg(vcpu, 0) & ~((u32) 0);
+	unsigned long psci_fn = vcpu_get_reg(vcpu, 0) & ~((u32) 0);
 	unsigned long val;
 
 	switch (psci_fn) {
@@ -295,7 +295,7 @@
 		break;
 	}
 
-	*vcpu_reg(vcpu, 0) = val;
+	vcpu_set_reg(vcpu, 0, val);
 	return 1;
 }
 
diff --git a/arch/arm/mach-at91/Kconfig b/arch/arm/mach-at91/Kconfig
index 9267300..28656c2 100644
--- a/arch/arm/mach-at91/Kconfig
+++ b/arch/arm/mach-at91/Kconfig
@@ -4,7 +4,6 @@
 	select ARCH_REQUIRE_GPIOLIB
 	select COMMON_CLK_AT91
 	select PINCTRL
-	select PINCTRL_AT91
 	select SOC_BUS
 
 if ARCH_AT91
@@ -17,6 +16,7 @@
 	select HAVE_AT91_USB_CLK
 	select HAVE_AT91_H32MX
 	select HAVE_AT91_GENERATED_CLK
+	select PINCTRL_AT91PIO4
 	help
 	  Select this if ou are using one of Atmel's SAMA5D2 family SoC.
 
@@ -27,6 +27,7 @@
 	select HAVE_AT91_UTMI
 	select HAVE_AT91_SMD
 	select HAVE_AT91_USB_CLK
+	select PINCTRL_AT91
 	help
 	  Select this if you are using one of Atmel's SAMA5D3 family SoC.
 	  This support covers SAMA5D31, SAMA5D33, SAMA5D34, SAMA5D35, SAMA5D36.
@@ -40,6 +41,7 @@
 	select HAVE_AT91_SMD
 	select HAVE_AT91_USB_CLK
 	select HAVE_AT91_H32MX
+	select PINCTRL_AT91
 	help
 	  Select this if you are using one of Atmel's SAMA5D4 family SoC.
 
@@ -50,6 +52,7 @@
 	select CPU_ARM920T
 	select HAVE_AT91_USB_CLK
 	select MIGHT_HAVE_PCI
+	select PINCTRL_AT91
 	select SOC_SAM_V4_V5
 	select SRAM if PM
 	help
@@ -65,6 +68,7 @@
 	select HAVE_AT91_UTMI
 	select HAVE_FB_ATMEL
 	select MEMORY
+	select PINCTRL_AT91
 	select SOC_SAM_V4_V5
 	select SRAM if PM
 	help
diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c
index 80e277c..23726fb 100644
--- a/arch/arm/mach-at91/pm.c
+++ b/arch/arm/mach-at91/pm.c
@@ -41,8 +41,10 @@
  * implementation should be moved down into the pinctrl driver and get
  * called as part of the generic suspend/resume path.
  */
+#ifdef CONFIG_PINCTRL_AT91
 extern void at91_pinctrl_gpio_suspend(void);
 extern void at91_pinctrl_gpio_resume(void);
+#endif
 
 static struct {
 	unsigned long uhp_udp_mask;
@@ -151,8 +153,9 @@
 
 static int at91_pm_enter(suspend_state_t state)
 {
+#ifdef CONFIG_PINCTRL_AT91
 	at91_pinctrl_gpio_suspend();
-
+#endif
 	switch (state) {
 	/*
 	 * Suspend-to-RAM is like STANDBY plus slow clock mode, so
@@ -192,7 +195,9 @@
 error:
 	target_state = PM_SUSPEND_ON;
 
+#ifdef CONFIG_PINCTRL_AT91
 	at91_pinctrl_gpio_resume();
+#endif
 	return 0;
 }
 
diff --git a/arch/arm/mach-dove/include/mach/entry-macro.S b/arch/arm/mach-dove/include/mach/entry-macro.S
index 72d622b..df1d44b 100644
--- a/arch/arm/mach-dove/include/mach/entry-macro.S
+++ b/arch/arm/mach-dove/include/mach/entry-macro.S
@@ -18,13 +18,13 @@
 	@ check low interrupts
 	ldr	\irqstat, [\base, #IRQ_CAUSE_LOW_OFF]
 	ldr	\tmp, [\base, #IRQ_MASK_LOW_OFF]
-	mov	\irqnr, #31
+	mov	\irqnr, #32
 	ands	\irqstat, \irqstat, \tmp
 
 	@ if no low interrupts set, check high interrupts
 	ldreq	\irqstat, [\base, #IRQ_CAUSE_HIGH_OFF]
 	ldreq	\tmp, [\base, #IRQ_MASK_HIGH_OFF]
-	moveq	\irqnr, #63
+	moveq	\irqnr, #64
 	andeqs	\irqstat, \irqstat, \tmp
 
 	@ find first active interrupt source
diff --git a/arch/arm/mach-exynos/pmu.c b/arch/arm/mach-exynos/pmu.c
index de68938..c21e41d 100644
--- a/arch/arm/mach-exynos/pmu.c
+++ b/arch/arm/mach-exynos/pmu.c
@@ -748,8 +748,12 @@
 void exynos_sys_powerdown_conf(enum sys_powerdown mode)
 {
 	unsigned int i;
+	const struct exynos_pmu_data *pmu_data;
 
-	const struct exynos_pmu_data *pmu_data = pmu_context->pmu_data;
+	if (!pmu_context)
+		return;
+
+	pmu_data = pmu_context->pmu_data;
 
 	if (pmu_data->powerdown_conf)
 		pmu_data->powerdown_conf(mode);
diff --git a/arch/arm/mach-imx/gpc.c b/arch/arm/mach-imx/gpc.c
index 8e7976a..cfc696b 100644
--- a/arch/arm/mach-imx/gpc.c
+++ b/arch/arm/mach-imx/gpc.c
@@ -177,6 +177,7 @@
 	.irq_unmask		= imx_gpc_irq_unmask,
 	.irq_retrigger		= irq_chip_retrigger_hierarchy,
 	.irq_set_wake		= imx_gpc_irq_set_wake,
+	.irq_set_type           = irq_chip_set_type_parent,
 #ifdef CONFIG_SMP
 	.irq_set_affinity	= irq_chip_set_affinity_parent,
 #endif
diff --git a/arch/arm/mach-ixp4xx/include/mach/io.h b/arch/arm/mach-ixp4xx/include/mach/io.h
index b024390..7a0c13b 100644
--- a/arch/arm/mach-ixp4xx/include/mach/io.h
+++ b/arch/arm/mach-ixp4xx/include/mach/io.h
@@ -143,7 +143,7 @@
 		writel(*vaddr++, bus_addr);
 }
 
-static inline unsigned char __indirect_readb(const volatile void __iomem *p)
+static inline u8 __indirect_readb(const volatile void __iomem *p)
 {
 	u32 addr = (u32)p;
 	u32 n, byte_enables, data;
@@ -166,7 +166,7 @@
 		*vaddr++ = readb(bus_addr);
 }
 
-static inline unsigned short __indirect_readw(const volatile void __iomem *p)
+static inline u16 __indirect_readw(const volatile void __iomem *p)
 {
 	u32 addr = (u32)p;
 	u32 n, byte_enables, data;
@@ -189,7 +189,7 @@
 		*vaddr++ = readw(bus_addr);
 }
 
-static inline unsigned long __indirect_readl(const volatile void __iomem *p)
+static inline u32 __indirect_readl(const volatile void __iomem *p)
 {
 	u32 addr = (__force u32)p;
 	u32 data;
@@ -350,7 +350,7 @@
 					((unsigned long)p <= (PIO_MASK + PIO_OFFSET)))
 
 #define	ioread8(p)			ioread8(p)
-static inline unsigned int ioread8(const void __iomem *addr)
+static inline u8 ioread8(const void __iomem *addr)
 {
 	unsigned long port = (unsigned long __force)addr;
 	if (__is_io_address(port))
@@ -378,7 +378,7 @@
 }
 
 #define	ioread16(p)			ioread16(p)
-static inline unsigned int ioread16(const void __iomem *addr)
+static inline u16 ioread16(const void __iomem *addr)
 {
 	unsigned long port = (unsigned long __force)addr;
 	if (__is_io_address(port))
@@ -407,7 +407,7 @@
 }
 
 #define	ioread32(p)			ioread32(p)
-static inline unsigned int ioread32(const void __iomem *addr)
+static inline u32 ioread32(const void __iomem *addr)
 {
 	unsigned long port = (unsigned long __force)addr;
 	if (__is_io_address(port))
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index 5076d3f..4b4371d 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -121,6 +121,7 @@
 	select NEON if CPU_V7
 	select PM
 	select REGULATOR
+	select REGULATOR_FIXED_VOLTAGE
 	select TWL4030_CORE if ARCH_OMAP3 || ARCH_OMAP4
 	select TWL4030_POWER if ARCH_OMAP3 || ARCH_OMAP4
 	select VFP
@@ -201,7 +202,6 @@
 	depends on ARCH_OMAP3
 	default y
 	select OMAP_PACKAGE_CBB
-	select REGULATOR_FIXED_VOLTAGE if REGULATOR
 
 config MACH_NOKIA_N810
        bool
diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c
index 5305ec7..79e1f87 100644
--- a/arch/arm/mach-omap2/omap-smp.c
+++ b/arch/arm/mach-omap2/omap-smp.c
@@ -143,9 +143,9 @@
 		 * Ensure that CPU power state is set to ON to avoid CPU
 		 * powerdomain transition on wfi
 		 */
-		clkdm_wakeup(cpu1_clkdm);
-		omap_set_pwrdm_state(cpu1_pwrdm, PWRDM_POWER_ON);
-		clkdm_allow_idle(cpu1_clkdm);
+		clkdm_wakeup_nolock(cpu1_clkdm);
+		pwrdm_set_next_pwrst(cpu1_pwrdm, PWRDM_POWER_ON);
+		clkdm_allow_idle_nolock(cpu1_clkdm);
 
 		if (IS_PM44XX_ERRATUM(PM_OMAP4_ROM_SMP_BOOT_ERRATUM_GICD)) {
 			while (gic_dist_disabled()) {
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index cc8a987..48495ad 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -890,6 +890,36 @@
 	return ret;
 }
 
+static void _enable_optional_clocks(struct omap_hwmod *oh)
+{
+	struct omap_hwmod_opt_clk *oc;
+	int i;
+
+	pr_debug("omap_hwmod: %s: enabling optional clocks\n", oh->name);
+
+	for (i = oh->opt_clks_cnt, oc = oh->opt_clks; i > 0; i--, oc++)
+		if (oc->_clk) {
+			pr_debug("omap_hwmod: enable %s:%s\n", oc->role,
+				 __clk_get_name(oc->_clk));
+			clk_enable(oc->_clk);
+		}
+}
+
+static void _disable_optional_clocks(struct omap_hwmod *oh)
+{
+	struct omap_hwmod_opt_clk *oc;
+	int i;
+
+	pr_debug("omap_hwmod: %s: disabling optional clocks\n", oh->name);
+
+	for (i = oh->opt_clks_cnt, oc = oh->opt_clks; i > 0; i--, oc++)
+		if (oc->_clk) {
+			pr_debug("omap_hwmod: disable %s:%s\n", oc->role,
+				 __clk_get_name(oc->_clk));
+			clk_disable(oc->_clk);
+		}
+}
+
 /**
  * _enable_clocks - enable hwmod main clock and interface clocks
  * @oh: struct omap_hwmod *
@@ -917,6 +947,9 @@
 			clk_enable(os->_clk);
 	}
 
+	if (oh->flags & HWMOD_OPT_CLKS_NEEDED)
+		_enable_optional_clocks(oh);
+
 	/* The opt clocks are controlled by the device driver. */
 
 	return 0;
@@ -948,41 +981,14 @@
 			clk_disable(os->_clk);
 	}
 
+	if (oh->flags & HWMOD_OPT_CLKS_NEEDED)
+		_disable_optional_clocks(oh);
+
 	/* The opt clocks are controlled by the device driver. */
 
 	return 0;
 }
 
-static void _enable_optional_clocks(struct omap_hwmod *oh)
-{
-	struct omap_hwmod_opt_clk *oc;
-	int i;
-
-	pr_debug("omap_hwmod: %s: enabling optional clocks\n", oh->name);
-
-	for (i = oh->opt_clks_cnt, oc = oh->opt_clks; i > 0; i--, oc++)
-		if (oc->_clk) {
-			pr_debug("omap_hwmod: enable %s:%s\n", oc->role,
-				 __clk_get_name(oc->_clk));
-			clk_enable(oc->_clk);
-		}
-}
-
-static void _disable_optional_clocks(struct omap_hwmod *oh)
-{
-	struct omap_hwmod_opt_clk *oc;
-	int i;
-
-	pr_debug("omap_hwmod: %s: disabling optional clocks\n", oh->name);
-
-	for (i = oh->opt_clks_cnt, oc = oh->opt_clks; i > 0; i--, oc++)
-		if (oc->_clk) {
-			pr_debug("omap_hwmod: disable %s:%s\n", oc->role,
-				 __clk_get_name(oc->_clk));
-			clk_disable(oc->_clk);
-		}
-}
-
 /**
  * _omap4_enable_module - enable CLKCTRL modulemode on OMAP4
  * @oh: struct omap_hwmod *
diff --git a/arch/arm/mach-omap2/omap_hwmod.h b/arch/arm/mach-omap2/omap_hwmod.h
index ca6df1a..76bce11 100644
--- a/arch/arm/mach-omap2/omap_hwmod.h
+++ b/arch/arm/mach-omap2/omap_hwmod.h
@@ -523,6 +523,8 @@
  * HWMOD_RECONFIG_IO_CHAIN: omap_hwmod code needs to reconfigure wake-up 
  *     events by calling _reconfigure_io_chain() when a device is enabled
  *     or idled.
+ * HWMOD_OPT_CLKS_NEEDED: The optional clocks are needed for the module to
+ *     operate and they need to be handled at the same time as the main_clk.
  */
 #define HWMOD_SWSUP_SIDLE			(1 << 0)
 #define HWMOD_SWSUP_MSTANDBY			(1 << 1)
@@ -538,6 +540,7 @@
 #define HWMOD_FORCE_MSTANDBY			(1 << 11)
 #define HWMOD_SWSUP_SIDLE_ACT			(1 << 12)
 #define HWMOD_RECONFIG_IO_CHAIN			(1 << 13)
+#define HWMOD_OPT_CLKS_NEEDED			(1 << 14)
 
 /*
  * omap_hwmod._int_flags definitions
diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
index 51d1ecb..ee4e044 100644
--- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
@@ -1298,6 +1298,44 @@
 };
 
 /*
+ * 'mcasp' class
+ *
+ */
+static struct omap_hwmod_class_sysconfig dra7xx_mcasp_sysc = {
+	.sysc_offs	= 0x0004,
+	.sysc_flags	= SYSC_HAS_SIDLEMODE,
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART),
+	.sysc_fields	= &omap_hwmod_sysc_type3,
+};
+
+static struct omap_hwmod_class dra7xx_mcasp_hwmod_class = {
+	.name	= "mcasp",
+	.sysc	= &dra7xx_mcasp_sysc,
+};
+
+/* mcasp3 */
+static struct omap_hwmod_opt_clk mcasp3_opt_clks[] = {
+	{ .role = "ahclkx", .clk = "mcasp3_ahclkx_mux" },
+};
+
+static struct omap_hwmod dra7xx_mcasp3_hwmod = {
+	.name		= "mcasp3",
+	.class		= &dra7xx_mcasp_hwmod_class,
+	.clkdm_name	= "l4per2_clkdm",
+	.main_clk	= "mcasp3_aux_gfclk_mux",
+	.flags		= HWMOD_OPT_CLKS_NEEDED,
+	.prcm = {
+		.omap4 = {
+			.clkctrl_offs = DRA7XX_CM_L4PER2_MCASP3_CLKCTRL_OFFSET,
+			.context_offs = DRA7XX_RM_L4PER2_MCASP3_CONTEXT_OFFSET,
+			.modulemode   = MODULEMODE_SWCTRL,
+		},
+	},
+	.opt_clks	= mcasp3_opt_clks,
+	.opt_clks_cnt	= ARRAY_SIZE(mcasp3_opt_clks),
+};
+
+/*
  * 'mmc' class
  *
  */
@@ -2566,6 +2604,22 @@
 	.user		= OCP_USER_MPU | OCP_USER_SDMA,
 };
 
+/* l4_per2 -> mcasp3 */
+static struct omap_hwmod_ocp_if dra7xx_l4_per2__mcasp3 = {
+	.master		= &dra7xx_l4_per2_hwmod,
+	.slave		= &dra7xx_mcasp3_hwmod,
+	.clk		= "l4_root_clk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
+/* l3_main_1 -> mcasp3 */
+static struct omap_hwmod_ocp_if dra7xx_l3_main_1__mcasp3 = {
+	.master		= &dra7xx_l3_main_1_hwmod,
+	.slave		= &dra7xx_mcasp3_hwmod,
+	.clk		= "l3_iclk_div",
+	.user		= OCP_USER_MPU | OCP_USER_SDMA,
+};
+
 /* l4_per1 -> elm */
 static struct omap_hwmod_ocp_if dra7xx_l4_per1__elm = {
 	.master		= &dra7xx_l4_per1_hwmod,
@@ -3308,6 +3362,8 @@
 	&dra7xx_l4_wkup__dcan1,
 	&dra7xx_l4_per2__dcan2,
 	&dra7xx_l4_per2__cpgmac0,
+	&dra7xx_l4_per2__mcasp3,
+	&dra7xx_l3_main_1__mcasp3,
 	&dra7xx_gmac__mdio,
 	&dra7xx_l4_cfg__dma_system,
 	&dra7xx_l3_main_1__dss,
diff --git a/arch/arm/mach-omap2/omap_hwmod_81xx_data.c b/arch/arm/mach-omap2/omap_hwmod_81xx_data.c
index b1288f5..6256052 100644
--- a/arch/arm/mach-omap2/omap_hwmod_81xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_81xx_data.c
@@ -144,6 +144,7 @@
 	.name		= "l4_ls",
 	.clkdm_name	= "alwon_l3s_clkdm",
 	.class		= &l4_hwmod_class,
+	.flags		= HWMOD_NO_IDLEST,
 };
 
 /*
@@ -155,6 +156,7 @@
 	.name		= "l4_hs",
 	.clkdm_name	= "alwon_l3_med_clkdm",
 	.class		= &l4_hwmod_class,
+	.flags		= HWMOD_NO_IDLEST,
 };
 
 /* L3 slow -> L4 ls peripheral interface running at 125MHz */
@@ -850,6 +852,7 @@
 	.name		= "emac0",
 	.clkdm_name	= "alwon_ethernet_clkdm",
 	.class		= &dm816x_emac_hwmod_class,
+	.flags		= HWMOD_NO_IDLEST,
 };
 
 static struct omap_hwmod_ocp_if dm81xx_l4_hs__emac0 = {
diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c
index 1dfe346..5814477 100644
--- a/arch/arm/mach-omap2/pdata-quirks.c
+++ b/arch/arm/mach-omap2/pdata-quirks.c
@@ -24,9 +24,6 @@
 #include <linux/platform_data/iommu-omap.h>
 #include <linux/platform_data/wkup_m3.h>
 
-#include <asm/siginfo.h>
-#include <asm/signal.h>
-
 #include "common.h"
 #include "common-board-devices.h"
 #include "dss-common.h"
@@ -385,29 +382,6 @@
 }
 #endif /* CONFIG_ARCH_OMAP3 */
 
-#ifdef CONFIG_SOC_TI81XX
-static int fault_fixed_up;
-
-static int t410_abort_handler(unsigned long addr, unsigned int fsr,
-			      struct pt_regs *regs)
-{
-	if ((fsr == 0x406 || fsr == 0xc06) && !fault_fixed_up) {
-		pr_warn("External imprecise Data abort at addr=%#lx, fsr=%#x ignored.\n",
-			addr, fsr);
-		fault_fixed_up = 1;
-		return 0;
-	}
-
-	return 1;
-}
-
-static void __init t410_abort_init(void)
-{
-	hook_fault_code(16 + 6, t410_abort_handler, SIGBUS, BUS_OBJERR,
-			"imprecise external abort");
-}
-#endif
-
 #if defined(CONFIG_ARCH_OMAP4) || defined(CONFIG_SOC_OMAP5)
 static struct iommu_platform_data omap4_iommu_pdata = {
 	.reset_name = "mmu_cache",
@@ -536,9 +510,6 @@
 	{ "openpandora,omap3-pandora-600mhz", omap3_pandora_legacy_init, },
 	{ "openpandora,omap3-pandora-1ghz", omap3_pandora_legacy_init, },
 #endif
-#ifdef CONFIG_SOC_TI81XX
-	{ "hp,t410", t410_abort_init, },
-#endif
 #ifdef CONFIG_SOC_OMAP5
 	{ "ti,omap5-uevm", omap5_uevm_legacy_init, },
 #endif
diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c
index 87b98bf9..2dbd378 100644
--- a/arch/arm/mach-omap2/pm34xx.c
+++ b/arch/arm/mach-omap2/pm34xx.c
@@ -301,11 +301,11 @@
 	if (omap_irq_pending())
 		return;
 
-	trace_cpu_idle(1, smp_processor_id());
+	trace_cpu_idle_rcuidle(1, smp_processor_id());
 
 	omap_sram_idle();
 
-	trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
+	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 }
 
 #ifdef CONFIG_SUSPEND
diff --git a/arch/arm/mach-orion5x/include/mach/entry-macro.S b/arch/arm/mach-orion5x/include/mach/entry-macro.S
index 79eb502..73919a3 100644
--- a/arch/arm/mach-orion5x/include/mach/entry-macro.S
+++ b/arch/arm/mach-orion5x/include/mach/entry-macro.S
@@ -21,5 +21,5 @@
 	@ find cause bits that are unmasked
 	ands	\irqstat, \irqstat, \tmp	@ clear Z flag if any
 	clzne	\irqnr,	\irqstat		@ calc irqnr
-	rsbne	\irqnr, \irqnr, #31
+	rsbne	\irqnr, \irqnr, #32
 	.endm
diff --git a/arch/arm/mach-pxa/ezx.c b/arch/arm/mach-pxa/ezx.c
index 9a9c15b..7c0d561 100644
--- a/arch/arm/mach-pxa/ezx.c
+++ b/arch/arm/mach-pxa/ezx.c
@@ -889,6 +889,7 @@
 
 	pxa_set_keypad_info(&e680_keypad_platform_data);
 
+	pwm_add_table(ezx_pwm_lookup, ARRAY_SIZE(ezx_pwm_lookup));
 	platform_add_devices(ARRAY_AND_SIZE(ezx_devices));
 	platform_add_devices(ARRAY_AND_SIZE(e680_devices));
 }
@@ -956,6 +957,7 @@
 
 	pxa_set_keypad_info(&a1200_keypad_platform_data);
 
+	pwm_add_table(ezx_pwm_lookup, ARRAY_SIZE(ezx_pwm_lookup));
 	platform_add_devices(ARRAY_AND_SIZE(ezx_devices));
 	platform_add_devices(ARRAY_AND_SIZE(a1200_devices));
 }
@@ -1148,6 +1150,7 @@
 		platform_device_register(&a910_camera);
 	}
 
+	pwm_add_table(ezx_pwm_lookup, ARRAY_SIZE(ezx_pwm_lookup));
 	platform_add_devices(ARRAY_AND_SIZE(ezx_devices));
 	platform_add_devices(ARRAY_AND_SIZE(a910_devices));
 }
@@ -1215,6 +1218,7 @@
 
 	pxa_set_keypad_info(&e6_keypad_platform_data);
 
+	pwm_add_table(ezx_pwm_lookup, ARRAY_SIZE(ezx_pwm_lookup));
 	platform_add_devices(ARRAY_AND_SIZE(ezx_devices));
 	platform_add_devices(ARRAY_AND_SIZE(e6_devices));
 }
@@ -1256,6 +1260,7 @@
 
 	pxa_set_keypad_info(&e2_keypad_platform_data);
 
+	pwm_add_table(ezx_pwm_lookup, ARRAY_SIZE(ezx_pwm_lookup));
 	platform_add_devices(ARRAY_AND_SIZE(ezx_devices));
 	platform_add_devices(ARRAY_AND_SIZE(e2_devices));
 }
diff --git a/arch/arm/mach-pxa/palm27x.c b/arch/arm/mach-pxa/palm27x.c
index 13eba2b..8fbfb10 100644
--- a/arch/arm/mach-pxa/palm27x.c
+++ b/arch/arm/mach-pxa/palm27x.c
@@ -344,7 +344,7 @@
 {
 	palm_bl_power	= bl;
 	palm_lcd_power	= lcd;
-	pwm_add_lookup(palm27x_pwm_lookup, ARRAY_SIZE(palm27x_pwm_lookup));
+	pwm_add_table(palm27x_pwm_lookup, ARRAY_SIZE(palm27x_pwm_lookup));
 	platform_device_register(&palm27x_backlight);
 }
 #endif
diff --git a/arch/arm/mach-pxa/palmtc.c b/arch/arm/mach-pxa/palmtc.c
index aebf6de..0b5c387 100644
--- a/arch/arm/mach-pxa/palmtc.c
+++ b/arch/arm/mach-pxa/palmtc.c
@@ -169,7 +169,7 @@
 #if defined(CONFIG_BACKLIGHT_PWM) || defined(CONFIG_BACKLIGHT_PWM_MODULE)
 static struct pwm_lookup palmtc_pwm_lookup[] = {
 	PWM_LOOKUP("pxa25x-pwm.1", 0, "pwm-backlight.0", NULL, PALMTC_PERIOD_NS,
-		   PWM_PERIOD_NORMAL),
+		   PWM_POLARITY_NORMAL),
 };
 
 static struct platform_pwm_backlight_data palmtc_backlight_data = {
diff --git a/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c b/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c
index a19460e..b355fca 100644
--- a/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c
+++ b/arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c
@@ -20,7 +20,7 @@
 #include <plat/cpu.h>
 #include <plat/cpu-freq-core.h>
 
-static struct cpufreq_frequency_table s3c2440_plls_12[] __initdata = {
+static struct cpufreq_frequency_table s3c2440_plls_12[] = {
 	{ .frequency = 75000000,	.driver_data = PLLVAL(0x75, 3, 3),  }, 	/* FVco 600.000000 */
 	{ .frequency = 80000000,	.driver_data = PLLVAL(0x98, 4, 3),  }, 	/* FVco 640.000000 */
 	{ .frequency = 90000000,	.driver_data = PLLVAL(0x70, 2, 3),  }, 	/* FVco 720.000000 */
diff --git a/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c b/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c
index 1191b29..be9a248 100644
--- a/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c
+++ b/arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c
@@ -20,7 +20,7 @@
 #include <plat/cpu.h>
 #include <plat/cpu-freq-core.h>
 
-static struct cpufreq_frequency_table s3c2440_plls_169344[] __initdata = {
+static struct cpufreq_frequency_table s3c2440_plls_169344[] = {
 	{ .frequency = 78019200,	.driver_data = PLLVAL(121, 5, 3), 	}, 	/* FVco 624.153600 */
 	{ .frequency = 84067200,	.driver_data = PLLVAL(131, 5, 3), 	}, 	/* FVco 672.537600 */
 	{ .frequency = 90115200,	.driver_data = PLLVAL(141, 5, 3), 	}, 	/* FVco 720.921600 */
diff --git a/arch/arm/mach-shmobile/setup-r8a7793.c b/arch/arm/mach-shmobile/setup-r8a7793.c
index 1d2825c..5fce87f 100644
--- a/arch/arm/mach-shmobile/setup-r8a7793.c
+++ b/arch/arm/mach-shmobile/setup-r8a7793.c
@@ -19,7 +19,7 @@
 #include "common.h"
 #include "rcar-gen2.h"
 
-static const char *r8a7793_boards_compat_dt[] __initconst = {
+static const char * const r8a7793_boards_compat_dt[] __initconst = {
 	"renesas,r8a7793",
 	NULL,
 };
diff --git a/arch/arm/mach-zx/Kconfig b/arch/arm/mach-zx/Kconfig
index 7fdc5bf..446334a 100644
--- a/arch/arm/mach-zx/Kconfig
+++ b/arch/arm/mach-zx/Kconfig
@@ -13,7 +13,7 @@
 	select ARM_GLOBAL_TIMER
 	select HAVE_ARM_SCU if SMP
 	select HAVE_ARM_TWD if SMP
-	select PM_GENERIC_DOMAINS
+	select PM_GENERIC_DOMAINS if PM
 	help
 	  Support for ZTE ZX296702 SoC which is a dual core CortexA9MP
 endif
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 9ac16a4..871f217 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -49,7 +49,7 @@
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_BITREVERSE
 	select HAVE_ARCH_JUMP_LABEL
-	select HAVE_ARCH_KASAN if SPARSEMEM_VMEMMAP
+	select HAVE_ARCH_KASAN if SPARSEMEM_VMEMMAP && !(ARM64_16K_PAGES && ARM64_VA_BITS_48)
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
@@ -316,6 +316,27 @@
 
 	  If unsure, say Y.
 
+config ARM64_ERRATUM_834220
+	bool "Cortex-A57: 834220: Stage 2 translation fault might be incorrectly reported in presence of a Stage 1 fault"
+	depends on KVM
+	default y
+	help
+	  This option adds an alternative code sequence to work around ARM
+	  erratum 834220 on Cortex-A57 parts up to r1p2.
+
+	  Affected Cortex-A57 parts might report a Stage 2 translation
+	  fault as the result of a Stage 1 fault for load crossing a
+	  page boundary when there is a permission or device memory
+	  alignment fault at Stage 1 and a translation fault at Stage 2.
+
+	  The workaround is to verify that the Stage 1 translation
+	  doesn't generate a fault before handling the Stage 2 fault.
+	  Please note that this does not necessarily enable the workaround,
+	  as it depends on the alternative framework, which will only patch
+	  the kernel if an affected CPU is detected.
+
+	  If unsure, say Y.
+
 config ARM64_ERRATUM_845719
 	bool "Cortex-A53: 845719: a load might read incorrect data"
 	depends on COMPAT
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi
index e81cd48..925552e 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi
@@ -269,6 +269,7 @@
 			clock-frequency = <0>;	/* Updated by bootloader */
 			voltage-ranges = <1800 1800 3300 3300>;
 			sdhci,auto-cmd12;
+			little-endian;
 			bus-width = <4>;
 		};
 
@@ -277,6 +278,7 @@
 			reg = <0x0 0x2300000 0x0 0x10000>;
 			interrupts = <0 36 0x4>; /* Level high type */
 			gpio-controller;
+			little-endian;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -287,6 +289,7 @@
 			reg = <0x0 0x2310000 0x0 0x10000>;
 			interrupts = <0 36 0x4>; /* Level high type */
 			gpio-controller;
+			little-endian;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -297,6 +300,7 @@
 			reg = <0x0 0x2320000 0x0 0x10000>;
 			interrupts = <0 37 0x4>; /* Level high type */
 			gpio-controller;
+			little-endian;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -307,6 +311,7 @@
 			reg = <0x0 0x2330000 0x0 0x10000>;
 			interrupts = <0 37 0x4>; /* Level high type */
 			gpio-controller;
+			little-endian;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
diff --git a/arch/arm64/crypto/aes-ce-cipher.c b/arch/arm64/crypto/aes-ce-cipher.c
index ce47792..f7bd9bf 100644
--- a/arch/arm64/crypto/aes-ce-cipher.c
+++ b/arch/arm64/crypto/aes-ce-cipher.c
@@ -237,7 +237,7 @@
 static struct crypto_alg aes_alg = {
 	.cra_name		= "aes",
 	.cra_driver_name	= "aes-ce",
-	.cra_priority		= 300,
+	.cra_priority		= 250,
 	.cra_flags		= CRYPTO_ALG_TYPE_CIPHER,
 	.cra_blocksize		= AES_BLOCK_SIZE,
 	.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h
index 030cdcb..2731d3b 100644
--- a/arch/arm64/include/asm/arch_gicv3.h
+++ b/arch/arm64/include/asm/arch_gicv3.h
@@ -77,6 +77,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/stringify.h>
+#include <asm/barrier.h>
 
 /*
  * Low-level accessors
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 624f967..9622eb4 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -64,27 +64,31 @@
 
 #define smp_load_acquire(p)						\
 ({									\
-	typeof(*p) ___p1;						\
+	union { typeof(*p) __val; char __c[1]; } __u;			\
 	compiletime_assert_atomic_type(*p);				\
 	switch (sizeof(*p)) {						\
 	case 1:								\
 		asm volatile ("ldarb %w0, %1"				\
-			: "=r" (___p1) : "Q" (*p) : "memory");		\
+			: "=r" (*(__u8 *)__u.__c)			\
+			: "Q" (*p) : "memory");				\
 		break;							\
 	case 2:								\
 		asm volatile ("ldarh %w0, %1"				\
-			: "=r" (___p1) : "Q" (*p) : "memory");		\
+			: "=r" (*(__u16 *)__u.__c)			\
+			: "Q" (*p) : "memory");				\
 		break;							\
 	case 4:								\
 		asm volatile ("ldar %w0, %1"				\
-			: "=r" (___p1) : "Q" (*p) : "memory");		\
+			: "=r" (*(__u32 *)__u.__c)			\
+			: "Q" (*p) : "memory");				\
 		break;							\
 	case 8:								\
 		asm volatile ("ldar %0, %1"				\
-			: "=r" (___p1) : "Q" (*p) : "memory");		\
+			: "=r" (*(__u64 *)__u.__c)			\
+			: "Q" (*p) : "memory");				\
 		break;							\
 	}								\
-	___p1;								\
+	__u.__val;							\
 })
 
 #define read_barrier_depends()		do { } while(0)
diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h
index 7fbed69..eb8432b 100644
--- a/arch/arm64/include/asm/compat.h
+++ b/arch/arm64/include/asm/compat.h
@@ -23,7 +23,6 @@
  */
 #include <linux/types.h>
 #include <linux/sched.h>
-#include <linux/ptrace.h>
 
 #define COMPAT_USER_HZ		100
 #ifdef __AARCH64EB__
@@ -234,7 +233,7 @@
 	return (u32)(unsigned long)uptr;
 }
 
-#define compat_user_stack_pointer() (user_stack_pointer(current_pt_regs()))
+#define compat_user_stack_pointer() (user_stack_pointer(task_pt_regs(current)))
 
 static inline void __user *arch_compat_alloc_user_space(long len)
 {
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 11d5bb0f..8f271b8 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -29,8 +29,9 @@
 #define ARM64_HAS_PAN				4
 #define ARM64_HAS_LSE_ATOMICS			5
 #define ARM64_WORKAROUND_CAVIUM_23154		6
+#define ARM64_WORKAROUND_834220			7
 
-#define ARM64_NCAPS				7
+#define ARM64_NCAPS				8
 
 #ifndef __ASSEMBLY__
 
@@ -46,8 +47,12 @@
 #define FTR_STRICT	true	/* SANITY check strict matching required */
 #define FTR_NONSTRICT	false	/* SANITY check ignored */
 
+#define FTR_SIGNED	true	/* Value should be treated as signed */
+#define FTR_UNSIGNED	false	/* Value should be treated as unsigned */
+
 struct arm64_ftr_bits {
-	bool		strict;	  /* CPU Sanity check: strict matching required ? */
+	bool		sign;	/* Value is signed ? */
+	bool		strict;	/* CPU Sanity check: strict matching required ? */
 	enum ftr_type	type;
 	u8		shift;
 	u8		width;
@@ -123,6 +128,18 @@
 	return cpuid_feature_extract_field_width(features, field, 4);
 }
 
+static inline unsigned int __attribute_const__
+cpuid_feature_extract_unsigned_field_width(u64 features, int field, int width)
+{
+	return (u64)(features << (64 - width - field)) >> (64 - width);
+}
+
+static inline unsigned int __attribute_const__
+cpuid_feature_extract_unsigned_field(u64 features, int field)
+{
+	return cpuid_feature_extract_unsigned_field_width(features, field, 4);
+}
+
 static inline u64 arm64_ftr_mask(struct arm64_ftr_bits *ftrp)
 {
 	return (u64)GENMASK(ftrp->shift + ftrp->width - 1, ftrp->shift);
@@ -130,7 +147,9 @@
 
 static inline s64 arm64_ftr_value(struct arm64_ftr_bits *ftrp, u64 val)
 {
-	return cpuid_feature_extract_field_width(val, ftrp->shift, ftrp->width);
+	return ftrp->sign ?
+		cpuid_feature_extract_field_width(val, ftrp->shift, ftrp->width) :
+		cpuid_feature_extract_unsigned_field_width(val, ftrp->shift, ftrp->width);
 }
 
 static inline bool id_aa64mmfr0_mixed_endian_el0(u64 mmfr0)
diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h
index 54d0ead..61e08f3 100644
--- a/arch/arm64/include/asm/dma-mapping.h
+++ b/arch/arm64/include/asm/dma-mapping.h
@@ -18,7 +18,6 @@
 
 #ifdef __KERNEL__
 
-#include <linux/acpi.h>
 #include <linux/types.h>
 #include <linux/vmalloc.h>
 
@@ -26,22 +25,16 @@
 #include <asm/xen/hypervisor.h>
 
 #define DMA_ERROR_CODE	(~(dma_addr_t)0)
-extern struct dma_map_ops *dma_ops;
 extern struct dma_map_ops dummy_dma_ops;
 
 static inline struct dma_map_ops *__generic_dma_ops(struct device *dev)
 {
-	if (unlikely(!dev))
-		return dma_ops;
-	else if (dev->archdata.dma_ops)
+	if (dev && dev->archdata.dma_ops)
 		return dev->archdata.dma_ops;
-	else if (acpi_disabled)
-		return dma_ops;
 
 	/*
-	 * When ACPI is enabled, if arch_set_dma_ops is not called,
-	 * we will disable device DMA capability by setting it
-	 * to dummy_dma_ops.
+	 * We expect no ISA devices, and all other DMA masters are expected to
+	 * have someone call arch_setup_dma_ops at device creation time.
 	 */
 	return &dummy_dma_ops;
 }
diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h
index e54415e..9732908 100644
--- a/arch/arm64/include/asm/hw_breakpoint.h
+++ b/arch/arm64/include/asm/hw_breakpoint.h
@@ -138,16 +138,18 @@
 /* Determine number of BRP registers available. */
 static inline int get_num_brps(void)
 {
+	u64 dfr0 = read_system_reg(SYS_ID_AA64DFR0_EL1);
 	return 1 +
-		cpuid_feature_extract_field(read_system_reg(SYS_ID_AA64DFR0_EL1),
+		cpuid_feature_extract_unsigned_field(dfr0,
 						ID_AA64DFR0_BRPS_SHIFT);
 }
 
 /* Determine number of WRP registers available. */
 static inline int get_num_wrps(void)
 {
+	u64 dfr0 = read_system_reg(SYS_ID_AA64DFR0_EL1);
 	return 1 +
-		cpuid_feature_extract_field(read_system_reg(SYS_ID_AA64DFR0_EL1),
+		cpuid_feature_extract_unsigned_field(dfr0,
 						ID_AA64DFR0_WRPS_SHIFT);
 }
 
diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h
index 23eb450..8e8d306 100644
--- a/arch/arm64/include/asm/irq.h
+++ b/arch/arm64/include/asm/irq.h
@@ -7,4 +7,9 @@
 
 extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
 
+static inline int nr_legacy_irqs(void)
+{
+	return 0;
+}
+
 #endif
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 17e92f0..25a4021 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -99,12 +99,22 @@
 	*vcpu_cpsr(vcpu) |= COMPAT_PSR_T_BIT;
 }
 
-static inline unsigned long *vcpu_reg(const struct kvm_vcpu *vcpu, u8 reg_num)
+/*
+ * vcpu_get_reg and vcpu_set_reg should always be passed a register number
+ * coming from a read of ESR_EL2. Otherwise, it may give the wrong result on
+ * AArch32 with banked registers.
+ */
+static inline unsigned long vcpu_get_reg(const struct kvm_vcpu *vcpu,
+					 u8 reg_num)
 {
-	if (vcpu_mode_is_32bit(vcpu))
-		return vcpu_reg32(vcpu, reg_num);
+	return (reg_num == 31) ? 0 : vcpu_gp_regs(vcpu)->regs.regs[reg_num];
+}
 
-	return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.regs[reg_num];
+static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num,
+				unsigned long val)
+{
+	if (reg_num != 31)
+		vcpu_gp_regs(vcpu)->regs.regs[reg_num] = val;
 }
 
 /* Get vcpu SPSR for current mode */
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index c0e8789..2416578 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -101,7 +101,7 @@
 #define destroy_context(mm)		do { } while(0)
 void check_and_switch_context(struct mm_struct *mm, unsigned int cpu);
 
-#define init_new_context(tsk,mm)	({ atomic64_set(&mm->context.id, 0); 0; })
+#define init_new_context(tsk,mm)	({ atomic64_set(&(mm)->context.id, 0); 0; })
 
 /*
  * This is called when "tsk" is about to enter lazy TLB mode.
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 9819a94..63f52b5 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -81,6 +81,7 @@
 
 #define PAGE_KERNEL		__pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE)
 #define PAGE_KERNEL_RO		__pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
+#define PAGE_KERNEL_ROX	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
 #define PAGE_KERNEL_EXEC	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE)
 #define PAGE_KERNEL_EXEC_CONT	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT)
 
@@ -275,10 +276,14 @@
 	 * hardware updates of the pte (ptep_set_access_flags safely changes
 	 * valid ptes without going through an invalid entry).
 	 */
-	if (IS_ENABLED(CONFIG_DEBUG_VM) && IS_ENABLED(CONFIG_ARM64_HW_AFDBM) &&
-	    pte_valid(*ptep)) {
-		BUG_ON(!pte_young(pte));
-		BUG_ON(pte_write(*ptep) && !pte_dirty(pte));
+	if (IS_ENABLED(CONFIG_ARM64_HW_AFDBM) &&
+	    pte_valid(*ptep) && pte_valid(pte)) {
+		VM_WARN_ONCE(!pte_young(pte),
+			     "%s: racy access flag clearing: 0x%016llx -> 0x%016llx",
+			     __func__, pte_val(*ptep), pte_val(pte));
+		VM_WARN_ONCE(pte_write(*ptep) && !pte_dirty(pte),
+			     "%s: racy dirty state clearing: 0x%016llx -> 0x%016llx",
+			     __func__, pte_val(*ptep), pte_val(pte));
 	}
 
 	set_pte(ptep, pte);
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 24926f2..feb6b4e 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -75,6 +75,15 @@
 			   (1 << MIDR_VARIANT_SHIFT) | 2),
 	},
 #endif
+#ifdef CONFIG_ARM64_ERRATUM_834220
+	{
+	/* Cortex-A57 r0p0 - r1p2 */
+		.desc = "ARM erratum 834220",
+		.capability = ARM64_WORKAROUND_834220,
+		MIDR_RANGE(MIDR_CORTEX_A57, 0x00,
+			   (1 << MIDR_VARIANT_SHIFT) | 2),
+	},
+#endif
 #ifdef CONFIG_ARM64_ERRATUM_845719
 	{
 	/* Cortex-A53 r0p[01234] */
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index c8cf892..0669c63 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -44,8 +44,9 @@
 
 DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
 
-#define ARM64_FTR_BITS(STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \
+#define __ARM64_FTR_BITS(SIGNED, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \
 	{						\
+		.sign = SIGNED,				\
 		.strict = STRICT,			\
 		.type = TYPE,				\
 		.shift = SHIFT,				\
@@ -53,6 +54,14 @@
 		.safe_val = SAFE_VAL,			\
 	}
 
+/* Define a feature with signed values */
+#define ARM64_FTR_BITS(STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \
+	__ARM64_FTR_BITS(FTR_SIGNED, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL)
+
+/* Define a feature with unsigned value */
+#define U_ARM64_FTR_BITS(STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \
+	__ARM64_FTR_BITS(FTR_UNSIGNED, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL)
+
 #define ARM64_FTR_END					\
 	{						\
 		.width = 0,				\
@@ -99,7 +108,7 @@
 	 * Differing PARange is fine as long as all peripherals and memory are mapped
 	 * within the minimum PARange of all CPUs
 	 */
-	ARM64_FTR_BITS(FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_PARANGE_SHIFT, 4, 0),
+	U_ARM64_FTR_BITS(FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_PARANGE_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
@@ -115,18 +124,18 @@
 };
 
 static struct arm64_ftr_bits ftr_ctr[] = {
-	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 31, 1, 1),	/* RAO */
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 31, 1, 1),	/* RAO */
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 28, 3, 0),
-	ARM64_FTR_BITS(FTR_STRICT, FTR_HIGHER_SAFE, 24, 4, 0),	/* CWG */
-	ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0),	/* ERG */
-	ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 1),	/* DminLine */
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_HIGHER_SAFE, 24, 4, 0),	/* CWG */
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0),	/* ERG */
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 1),	/* DminLine */
 	/*
 	 * Linux can handle differing I-cache policies. Userspace JITs will
 	 * make use of *minLine
 	 */
-	ARM64_FTR_BITS(FTR_NONSTRICT, FTR_EXACT, 14, 2, 0),	/* L1Ip */
+	U_ARM64_FTR_BITS(FTR_NONSTRICT, FTR_EXACT, 14, 2, 0),	/* L1Ip */
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 10, 0),	/* RAZ */
-	ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0),	/* IminLine */
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0),	/* IminLine */
 	ARM64_FTR_END,
 };
 
@@ -144,12 +153,12 @@
 
 static struct arm64_ftr_bits ftr_id_aa64dfr0[] = {
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0),
-	ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_CTX_CMPS_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_WRPS_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_BRPS_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_PMUVER_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_TRACEVER_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_DEBUGVER_SHIFT, 4, 0x6),
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_CTX_CMPS_SHIFT, 4, 0),
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_WRPS_SHIFT, 4, 0),
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_BRPS_SHIFT, 4, 0),
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_PMUVER_SHIFT, 4, 0),
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_TRACEVER_SHIFT, 4, 0),
+	U_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64DFR0_DEBUGVER_SHIFT, 4, 0x6),
 	ARM64_FTR_END,
 };
 
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 706679d..212ae63 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -30,6 +30,7 @@
 #include <linux/seq_file.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
+#include <linux/delay.h>
 
 /*
  * In case the boot CPU is hotpluggable, we record its initial state and
@@ -112,6 +113,10 @@
 		 */
 		seq_printf(m, "processor\t: %d\n", i);
 
+		seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
+			   loops_per_jiffy / (500000UL/HZ),
+			   loops_per_jiffy / (5000UL/HZ) % 100);
+
 		/*
 		 * Dump out the common processor features in a single line.
 		 * Userspace should read the hwcaps with getauxval(AT_HWCAP)
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index de46b50..4eeb171 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -127,7 +127,11 @@
 	table_size = sizeof(efi_config_table_64_t) * efi.systab->nr_tables;
 	config_tables = early_memremap(efi_to_phys(efi.systab->tables),
 				       table_size);
-
+	if (config_tables == NULL) {
+		pr_warn("Unable to map EFI config table array.\n");
+		retval = -ENOMEM;
+		goto out;
+	}
 	retval = efi_config_parse_tables(config_tables, efi.systab->nr_tables,
 					 sizeof(efi_config_table_64_t), NULL);
 
@@ -209,6 +213,14 @@
 			 PAGE_ALIGN(params.mmap_size + (params.mmap & ~PAGE_MASK)));
 	memmap.phys_map = params.mmap;
 	memmap.map = early_memremap(params.mmap, params.mmap_size);
+	if (memmap.map == NULL) {
+		/*
+		* If we are booting via UEFI, the UEFI memory map is the only
+		* description of memory we have, so there is little point in
+		* proceeding if we cannot access it.
+		*/
+		panic("Unable to map EFI memory map.\n");
+	}
 	memmap.map_end = memmap.map + params.mmap_size;
 	memmap.desc_size = params.desc_size;
 	memmap.desc_version = params.desc_ver;
@@ -224,8 +236,9 @@
 {
 	efi_memory_desc_t *md;
 
+	init_new_context(NULL, &efi_mm);
+
 	for_each_efi_memory_desc(&memmap, md) {
-		u64 paddr, npages, size;
 		pgprot_t prot;
 
 		if (!(md->attribute & EFI_MEMORY_RUNTIME))
@@ -233,11 +246,6 @@
 		if (md->virt_addr == 0)
 			return false;
 
-		paddr = md->phys_addr;
-		npages = md->num_pages;
-		memrange_efi_to_native(&paddr, &npages);
-		size = npages << PAGE_SHIFT;
-
 		pr_info("  EFI remap 0x%016llx => %p\n",
 			md->phys_addr, (void *)md->virt_addr);
 
@@ -254,7 +262,9 @@
 		else
 			prot = PAGE_KERNEL;
 
-		create_pgd_mapping(&efi_mm, paddr, md->virt_addr, size, prot);
+		create_pgd_mapping(&efi_mm, md->phys_addr, md->virt_addr,
+				   md->num_pages << EFI_PAGE_SHIFT, 
+				   __pgprot(pgprot_val(prot) | PTE_NG));
 	}
 	return true;
 }
@@ -270,12 +280,12 @@
 
 	if (!efi_enabled(EFI_BOOT)) {
 		pr_info("EFI services will not be available.\n");
-		return -1;
+		return 0;
 	}
 
 	if (efi_runtime_disabled()) {
 		pr_info("EFI runtime services will be disabled.\n");
-		return -1;
+		return 0;
 	}
 
 	pr_info("Remapping and enabling EFI services.\n");
@@ -285,7 +295,7 @@
 						   mapsize);
 	if (!memmap.map) {
 		pr_err("Failed to remap EFI memory map\n");
-		return -1;
+		return -ENOMEM;
 	}
 	memmap.map_end = memmap.map + mapsize;
 	efi.memmap = &memmap;
@@ -294,13 +304,13 @@
 						   sizeof(efi_system_table_t));
 	if (!efi.systab) {
 		pr_err("Failed to remap EFI System Table\n");
-		return -1;
+		return -ENOMEM;
 	}
 	set_bit(EFI_SYSTEM_TABLES, &efi.flags);
 
 	if (!efi_virtmap_init()) {
 		pr_err("No UEFI virtual mapping was installed -- runtime services will not be available\n");
-		return -1;
+		return -ENOMEM;
 	}
 
 	/* Set up runtime services function pointers */
@@ -329,14 +339,7 @@
 
 static void efi_set_pgd(struct mm_struct *mm)
 {
-	if (mm == &init_mm)
-		cpu_set_reserved_ttbr0();
-	else
-		cpu_switch_mm(mm->pgd, mm);
-
-	local_flush_tlb_all();
-	if (icache_is_aivivt())
-		__local_flush_icache_all();
+	switch_mm(NULL, mm, NULL);
 }
 
 void efi_virtmap_load(void)
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index fce95e1..1095aa4 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -1,3 +1,4 @@
+#include <linux/ftrace.h>
 #include <linux/percpu.h>
 #include <linux/slab.h>
 #include <asm/cacheflush.h>
@@ -71,6 +72,13 @@
 	local_dbg_save(flags);
 
 	/*
+	 * Function graph tracer state gets incosistent when the kernel
+	 * calls functions that never return (aka suspend finishers) hence
+	 * disable graph tracing during their execution.
+	 */
+	pause_graph_tracing();
+
+	/*
 	 * mm context saved on the stack, it will be restored when
 	 * the cpu comes out of reset through the identity mapped
 	 * page tables, so that the thread address space is properly
@@ -111,6 +119,8 @@
 			hw_breakpoint_restore(NULL);
 	}
 
+	unpause_graph_tracing();
+
 	/*
 	 * Restore pstate flags. OS lock and mdscr have been already
 	 * restored, so from this point onwards, debugging is fully
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 1ee2c39..71426a7 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -5,6 +5,7 @@
  */
 
 #include <asm-generic/vmlinux.lds.h>
+#include <asm/cache.h>
 #include <asm/kernel-pgtable.h>
 #include <asm/thread_info.h>
 #include <asm/memory.h>
@@ -140,7 +141,7 @@
 		ARM_EXIT_KEEP(EXIT_DATA)
 	}
 
-	PERCPU_SECTION(64)
+	PERCPU_SECTION(L1_CACHE_BYTES)
 
 	. = ALIGN(PAGE_SIZE);
 	__init_end = .;
@@ -158,7 +159,7 @@
 	. = ALIGN(PAGE_SIZE);
 	_data = .;
 	_sdata = .;
-	RW_DATA_SECTION(64, PAGE_SIZE, THREAD_SIZE)
+	RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
 	PECOFF_EDATA_PADDING
 	_edata = .;
 
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 68a0759..15f0477 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -37,7 +37,7 @@
 {
 	int ret;
 
-	trace_kvm_hvc_arm64(*vcpu_pc(vcpu), *vcpu_reg(vcpu, 0),
+	trace_kvm_hvc_arm64(*vcpu_pc(vcpu), vcpu_get_reg(vcpu, 0),
 			    kvm_vcpu_hvc_get_imm(vcpu));
 
 	ret = kvm_psci_call(vcpu);
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 1599701..86c2898 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -864,6 +864,10 @@
 ENDPROC(__kvm_flush_vm_context)
 
 __kvm_hyp_panic:
+	// Stash PAR_EL1 before corrupting it in __restore_sysregs
+	mrs	x0, par_el1
+	push	x0, xzr
+
 	// Guess the context by looking at VTTBR:
 	// If zero, then we're already a host.
 	// Otherwise restore a minimal host context before panicing.
@@ -898,7 +902,7 @@
 	mrs	x3, esr_el2
 	mrs	x4, far_el2
 	mrs	x5, hpfar_el2
-	mrs	x6, par_el1
+	pop	x6, xzr		// active context PAR_EL1
 	mrs	x7, tpidr_el2
 
 	mov	lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\
@@ -914,7 +918,7 @@
 ENDPROC(__kvm_hyp_panic)
 
 __hyp_panic_str:
-	.ascii	"HYP panic:\nPS:%08x PC:%p ESR:%p\nFAR:%p HPFAR:%p PAR:%p\nVCPU:%p\n\0"
+	.ascii	"HYP panic:\nPS:%08x PC:%016x ESR:%08x\nFAR:%016x HPFAR:%016x PAR:%016x\nVCPU:%p\n\0"
 
 	.align	2
 
@@ -1015,9 +1019,15 @@
 	b.ne	1f		// Not an abort we care about
 
 	/* This is an abort. Check for permission fault */
+alternative_if_not ARM64_WORKAROUND_834220
 	and	x2, x1, #ESR_ELx_FSC_TYPE
 	cmp	x2, #FSC_PERM
 	b.ne	1f		// Not a permission fault
+alternative_else
+	nop			// Use the permission fault path to
+	nop			// check for a valid S1 translation,
+	nop			// regardless of the ESR value.
+alternative_endif
 
 	/*
 	 * Check for Stage-1 page table walk, which is guaranteed
diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c
index 85c5715..648112e 100644
--- a/arch/arm64/kvm/inject_fault.c
+++ b/arch/arm64/kvm/inject_fault.c
@@ -48,7 +48,7 @@
 
 	/* Note: These now point to the banked copies */
 	*vcpu_spsr(vcpu) = new_spsr_value;
-	*vcpu_reg(vcpu, 14) = *vcpu_pc(vcpu) + return_offset;
+	*vcpu_reg32(vcpu, 14) = *vcpu_pc(vcpu) + return_offset;
 
 	/* Branch to exception vector */
 	if (sctlr & (1 << 13))
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 87a64e8..d2650e8 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -78,7 +78,7 @@
  * See note at ARMv7 ARM B1.14.4 (TL;DR: S/W ops are not easily virtualized).
  */
 static bool access_dcsw(struct kvm_vcpu *vcpu,
-			const struct sys_reg_params *p,
+			struct sys_reg_params *p,
 			const struct sys_reg_desc *r)
 {
 	if (!p->is_write)
@@ -94,21 +94,19 @@
  * sys_regs and leave it in complete control of the caches.
  */
 static bool access_vm_reg(struct kvm_vcpu *vcpu,
-			  const struct sys_reg_params *p,
+			  struct sys_reg_params *p,
 			  const struct sys_reg_desc *r)
 {
-	unsigned long val;
 	bool was_enabled = vcpu_has_cache_enabled(vcpu);
 
 	BUG_ON(!p->is_write);
 
-	val = *vcpu_reg(vcpu, p->Rt);
 	if (!p->is_aarch32) {
-		vcpu_sys_reg(vcpu, r->reg) = val;
+		vcpu_sys_reg(vcpu, r->reg) = p->regval;
 	} else {
 		if (!p->is_32bit)
-			vcpu_cp15_64_high(vcpu, r->reg) = val >> 32;
-		vcpu_cp15_64_low(vcpu, r->reg) = val & 0xffffffffUL;
+			vcpu_cp15_64_high(vcpu, r->reg) = upper_32_bits(p->regval);
+		vcpu_cp15_64_low(vcpu, r->reg) = lower_32_bits(p->regval);
 	}
 
 	kvm_toggle_cache(vcpu, was_enabled);
@@ -122,22 +120,19 @@
  * for both AArch64 and AArch32 accesses.
  */
 static bool access_gic_sgi(struct kvm_vcpu *vcpu,
-			   const struct sys_reg_params *p,
+			   struct sys_reg_params *p,
 			   const struct sys_reg_desc *r)
 {
-	u64 val;
-
 	if (!p->is_write)
 		return read_from_write_only(vcpu, p);
 
-	val = *vcpu_reg(vcpu, p->Rt);
-	vgic_v3_dispatch_sgi(vcpu, val);
+	vgic_v3_dispatch_sgi(vcpu, p->regval);
 
 	return true;
 }
 
 static bool trap_raz_wi(struct kvm_vcpu *vcpu,
-			const struct sys_reg_params *p,
+			struct sys_reg_params *p,
 			const struct sys_reg_desc *r)
 {
 	if (p->is_write)
@@ -147,19 +142,19 @@
 }
 
 static bool trap_oslsr_el1(struct kvm_vcpu *vcpu,
-			   const struct sys_reg_params *p,
+			   struct sys_reg_params *p,
 			   const struct sys_reg_desc *r)
 {
 	if (p->is_write) {
 		return ignore_write(vcpu, p);
 	} else {
-		*vcpu_reg(vcpu, p->Rt) = (1 << 3);
+		p->regval = (1 << 3);
 		return true;
 	}
 }
 
 static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu,
-				   const struct sys_reg_params *p,
+				   struct sys_reg_params *p,
 				   const struct sys_reg_desc *r)
 {
 	if (p->is_write) {
@@ -167,7 +162,7 @@
 	} else {
 		u32 val;
 		asm volatile("mrs %0, dbgauthstatus_el1" : "=r" (val));
-		*vcpu_reg(vcpu, p->Rt) = val;
+		p->regval = val;
 		return true;
 	}
 }
@@ -200,17 +195,17 @@
  *   now use the debug registers.
  */
 static bool trap_debug_regs(struct kvm_vcpu *vcpu,
-			    const struct sys_reg_params *p,
+			    struct sys_reg_params *p,
 			    const struct sys_reg_desc *r)
 {
 	if (p->is_write) {
-		vcpu_sys_reg(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt);
+		vcpu_sys_reg(vcpu, r->reg) = p->regval;
 		vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
 	} else {
-		*vcpu_reg(vcpu, p->Rt) = vcpu_sys_reg(vcpu, r->reg);
+		p->regval = vcpu_sys_reg(vcpu, r->reg);
 	}
 
-	trace_trap_reg(__func__, r->reg, p->is_write, *vcpu_reg(vcpu, p->Rt));
+	trace_trap_reg(__func__, r->reg, p->is_write, p->regval);
 
 	return true;
 }
@@ -225,10 +220,10 @@
  * hyp.S code switches between host and guest values in future.
  */
 static inline void reg_to_dbg(struct kvm_vcpu *vcpu,
-			      const struct sys_reg_params *p,
+			      struct sys_reg_params *p,
 			      u64 *dbg_reg)
 {
-	u64 val = *vcpu_reg(vcpu, p->Rt);
+	u64 val = p->regval;
 
 	if (p->is_32bit) {
 		val &= 0xffffffffUL;
@@ -240,19 +235,16 @@
 }
 
 static inline void dbg_to_reg(struct kvm_vcpu *vcpu,
-			      const struct sys_reg_params *p,
+			      struct sys_reg_params *p,
 			      u64 *dbg_reg)
 {
-	u64 val = *dbg_reg;
-
+	p->regval = *dbg_reg;
 	if (p->is_32bit)
-		val &= 0xffffffffUL;
-
-	*vcpu_reg(vcpu, p->Rt) = val;
+		p->regval &= 0xffffffffUL;
 }
 
 static inline bool trap_bvr(struct kvm_vcpu *vcpu,
-			    const struct sys_reg_params *p,
+			    struct sys_reg_params *p,
 			    const struct sys_reg_desc *rd)
 {
 	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg];
@@ -294,7 +286,7 @@
 }
 
 static inline bool trap_bcr(struct kvm_vcpu *vcpu,
-			    const struct sys_reg_params *p,
+			    struct sys_reg_params *p,
 			    const struct sys_reg_desc *rd)
 {
 	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg];
@@ -337,7 +329,7 @@
 }
 
 static inline bool trap_wvr(struct kvm_vcpu *vcpu,
-			    const struct sys_reg_params *p,
+			    struct sys_reg_params *p,
 			    const struct sys_reg_desc *rd)
 {
 	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg];
@@ -380,7 +372,7 @@
 }
 
 static inline bool trap_wcr(struct kvm_vcpu *vcpu,
-			    const struct sys_reg_params *p,
+			    struct sys_reg_params *p,
 			    const struct sys_reg_desc *rd)
 {
 	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg];
@@ -687,7 +679,7 @@
 };
 
 static bool trap_dbgidr(struct kvm_vcpu *vcpu,
-			const struct sys_reg_params *p,
+			struct sys_reg_params *p,
 			const struct sys_reg_desc *r)
 {
 	if (p->is_write) {
@@ -697,23 +689,23 @@
 		u64 pfr = read_system_reg(SYS_ID_AA64PFR0_EL1);
 		u32 el3 = !!cpuid_feature_extract_field(pfr, ID_AA64PFR0_EL3_SHIFT);
 
-		*vcpu_reg(vcpu, p->Rt) = ((((dfr >> ID_AA64DFR0_WRPS_SHIFT) & 0xf) << 28) |
-					  (((dfr >> ID_AA64DFR0_BRPS_SHIFT) & 0xf) << 24) |
-					  (((dfr >> ID_AA64DFR0_CTX_CMPS_SHIFT) & 0xf) << 20) |
-					  (6 << 16) | (el3 << 14) | (el3 << 12));
+		p->regval = ((((dfr >> ID_AA64DFR0_WRPS_SHIFT) & 0xf) << 28) |
+			     (((dfr >> ID_AA64DFR0_BRPS_SHIFT) & 0xf) << 24) |
+			     (((dfr >> ID_AA64DFR0_CTX_CMPS_SHIFT) & 0xf) << 20)
+			     | (6 << 16) | (el3 << 14) | (el3 << 12));
 		return true;
 	}
 }
 
 static bool trap_debug32(struct kvm_vcpu *vcpu,
-			 const struct sys_reg_params *p,
+			 struct sys_reg_params *p,
 			 const struct sys_reg_desc *r)
 {
 	if (p->is_write) {
-		vcpu_cp14(vcpu, r->reg) = *vcpu_reg(vcpu, p->Rt);
+		vcpu_cp14(vcpu, r->reg) = p->regval;
 		vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
 	} else {
-		*vcpu_reg(vcpu, p->Rt) = vcpu_cp14(vcpu, r->reg);
+		p->regval = vcpu_cp14(vcpu, r->reg);
 	}
 
 	return true;
@@ -731,7 +723,7 @@
  */
 
 static inline bool trap_xvr(struct kvm_vcpu *vcpu,
-			    const struct sys_reg_params *p,
+			    struct sys_reg_params *p,
 			    const struct sys_reg_desc *rd)
 {
 	u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg];
@@ -740,12 +732,12 @@
 		u64 val = *dbg_reg;
 
 		val &= 0xffffffffUL;
-		val |= *vcpu_reg(vcpu, p->Rt) << 32;
+		val |= p->regval << 32;
 		*dbg_reg = val;
 
 		vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY;
 	} else {
-		*vcpu_reg(vcpu, p->Rt) = *dbg_reg >> 32;
+		p->regval = *dbg_reg >> 32;
 	}
 
 	trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg);
@@ -991,7 +983,7 @@
  * Return 0 if the access has been handled, and -1 if not.
  */
 static int emulate_cp(struct kvm_vcpu *vcpu,
-		      const struct sys_reg_params *params,
+		      struct sys_reg_params *params,
 		      const struct sys_reg_desc *table,
 		      size_t num)
 {
@@ -1062,12 +1054,12 @@
 {
 	struct sys_reg_params params;
 	u32 hsr = kvm_vcpu_get_hsr(vcpu);
+	int Rt = (hsr >> 5) & 0xf;
 	int Rt2 = (hsr >> 10) & 0xf;
 
 	params.is_aarch32 = true;
 	params.is_32bit = false;
 	params.CRm = (hsr >> 1) & 0xf;
-	params.Rt = (hsr >> 5) & 0xf;
 	params.is_write = ((hsr & 1) == 0);
 
 	params.Op0 = 0;
@@ -1076,15 +1068,12 @@
 	params.CRn = 0;
 
 	/*
-	 * Massive hack here. Store Rt2 in the top 32bits so we only
-	 * have one register to deal with. As we use the same trap
+	 * Make a 64-bit value out of Rt and Rt2. As we use the same trap
 	 * backends between AArch32 and AArch64, we get away with it.
 	 */
 	if (params.is_write) {
-		u64 val = *vcpu_reg(vcpu, params.Rt);
-		val &= 0xffffffff;
-		val |= *vcpu_reg(vcpu, Rt2) << 32;
-		*vcpu_reg(vcpu, params.Rt) = val;
+		params.regval = vcpu_get_reg(vcpu, Rt) & 0xffffffff;
+		params.regval |= vcpu_get_reg(vcpu, Rt2) << 32;
 	}
 
 	if (!emulate_cp(vcpu, &params, target_specific, nr_specific))
@@ -1095,11 +1084,10 @@
 	unhandled_cp_access(vcpu, &params);
 
 out:
-	/* Do the opposite hack for the read side */
+	/* Split up the value between registers for the read side */
 	if (!params.is_write) {
-		u64 val = *vcpu_reg(vcpu, params.Rt);
-		val >>= 32;
-		*vcpu_reg(vcpu, Rt2) = val;
+		vcpu_set_reg(vcpu, Rt, lower_32_bits(params.regval));
+		vcpu_set_reg(vcpu, Rt2, upper_32_bits(params.regval));
 	}
 
 	return 1;
@@ -1118,21 +1106,24 @@
 {
 	struct sys_reg_params params;
 	u32 hsr = kvm_vcpu_get_hsr(vcpu);
+	int Rt  = (hsr >> 5) & 0xf;
 
 	params.is_aarch32 = true;
 	params.is_32bit = true;
 	params.CRm = (hsr >> 1) & 0xf;
-	params.Rt  = (hsr >> 5) & 0xf;
+	params.regval = vcpu_get_reg(vcpu, Rt);
 	params.is_write = ((hsr & 1) == 0);
 	params.CRn = (hsr >> 10) & 0xf;
 	params.Op0 = 0;
 	params.Op1 = (hsr >> 14) & 0x7;
 	params.Op2 = (hsr >> 17) & 0x7;
 
-	if (!emulate_cp(vcpu, &params, target_specific, nr_specific))
+	if (!emulate_cp(vcpu, &params, target_specific, nr_specific) ||
+	    !emulate_cp(vcpu, &params, global, nr_global)) {
+		if (!params.is_write)
+			vcpu_set_reg(vcpu, Rt, params.regval);
 		return 1;
-	if (!emulate_cp(vcpu, &params, global, nr_global))
-		return 1;
+	}
 
 	unhandled_cp_access(vcpu, &params);
 	return 1;
@@ -1175,7 +1166,7 @@
 }
 
 static int emulate_sys_reg(struct kvm_vcpu *vcpu,
-			   const struct sys_reg_params *params)
+			   struct sys_reg_params *params)
 {
 	size_t num;
 	const struct sys_reg_desc *table, *r;
@@ -1230,6 +1221,8 @@
 {
 	struct sys_reg_params params;
 	unsigned long esr = kvm_vcpu_get_hsr(vcpu);
+	int Rt = (esr >> 5) & 0x1f;
+	int ret;
 
 	trace_kvm_handle_sys_reg(esr);
 
@@ -1240,10 +1233,14 @@
 	params.CRn = (esr >> 10) & 0xf;
 	params.CRm = (esr >> 1) & 0xf;
 	params.Op2 = (esr >> 17) & 0x7;
-	params.Rt = (esr >> 5) & 0x1f;
+	params.regval = vcpu_get_reg(vcpu, Rt);
 	params.is_write = !(esr & 1);
 
-	return emulate_sys_reg(vcpu, &params);
+	ret = emulate_sys_reg(vcpu, &params);
+
+	if (!params.is_write)
+		vcpu_set_reg(vcpu, Rt, params.regval);
+	return ret;
 }
 
 /******************************************************************************
diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h
index eaa324e..dbbb01c 100644
--- a/arch/arm64/kvm/sys_regs.h
+++ b/arch/arm64/kvm/sys_regs.h
@@ -28,7 +28,7 @@
 	u8	CRn;
 	u8	CRm;
 	u8	Op2;
-	u8	Rt;
+	u64	regval;
 	bool	is_write;
 	bool	is_aarch32;
 	bool	is_32bit;	/* Only valid if is_aarch32 is true */
@@ -44,7 +44,7 @@
 
 	/* Trapped access from guest, if non-NULL. */
 	bool (*access)(struct kvm_vcpu *,
-		       const struct sys_reg_params *,
+		       struct sys_reg_params *,
 		       const struct sys_reg_desc *);
 
 	/* Initialization for vcpu. */
@@ -77,9 +77,9 @@
 }
 
 static inline bool read_zero(struct kvm_vcpu *vcpu,
-			     const struct sys_reg_params *p)
+			     struct sys_reg_params *p)
 {
-	*vcpu_reg(vcpu, p->Rt) = 0;
+	p->regval = 0;
 	return true;
 }
 
diff --git a/arch/arm64/kvm/sys_regs_generic_v8.c b/arch/arm64/kvm/sys_regs_generic_v8.c
index 1e45768..ed90578 100644
--- a/arch/arm64/kvm/sys_regs_generic_v8.c
+++ b/arch/arm64/kvm/sys_regs_generic_v8.c
@@ -31,13 +31,13 @@
 #include "sys_regs.h"
 
 static bool access_actlr(struct kvm_vcpu *vcpu,
-			 const struct sys_reg_params *p,
+			 struct sys_reg_params *p,
 			 const struct sys_reg_desc *r)
 {
 	if (p->is_write)
 		return ignore_write(vcpu, p);
 
-	*vcpu_reg(vcpu, p->Rt) = vcpu_sys_reg(vcpu, ACTLR_EL1);
+	p->regval = vcpu_sys_reg(vcpu, ACTLR_EL1);
 	return true;
 }
 
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index f636a26..e87f53f 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -76,13 +76,28 @@
 		__flush_icache_all();
 }
 
-static int is_reserved_asid(u64 asid)
+static bool check_update_reserved_asid(u64 asid, u64 newasid)
 {
 	int cpu;
-	for_each_possible_cpu(cpu)
-		if (per_cpu(reserved_asids, cpu) == asid)
-			return 1;
-	return 0;
+	bool hit = false;
+
+	/*
+	 * Iterate over the set of reserved ASIDs looking for a match.
+	 * If we find one, then we can update our mm to use newasid
+	 * (i.e. the same ASID in the current generation) but we can't
+	 * exit the loop early, since we need to ensure that all copies
+	 * of the old ASID are updated to reflect the mm. Failure to do
+	 * so could result in us missing the reserved ASID in a future
+	 * generation.
+	 */
+	for_each_possible_cpu(cpu) {
+		if (per_cpu(reserved_asids, cpu) == asid) {
+			hit = true;
+			per_cpu(reserved_asids, cpu) = newasid;
+		}
+	}
+
+	return hit;
 }
 
 static u64 new_context(struct mm_struct *mm, unsigned int cpu)
@@ -92,12 +107,14 @@
 	u64 generation = atomic64_read(&asid_generation);
 
 	if (asid != 0) {
+		u64 newasid = generation | (asid & ~ASID_MASK);
+
 		/*
 		 * If our current ASID was active during a rollover, we
 		 * can continue to use it and this was just a false alarm.
 		 */
-		if (is_reserved_asid(asid))
-			return generation | (asid & ~ASID_MASK);
+		if (check_update_reserved_asid(asid, newasid))
+			return newasid;
 
 		/*
 		 * We had a valid ASID in a previous life, so try to re-use
@@ -105,7 +122,7 @@
 		 */
 		asid &= ~ASID_MASK;
 		if (!__test_and_set_bit(asid, asid_map))
-			goto bump_gen;
+			return newasid;
 	}
 
 	/*
@@ -129,10 +146,7 @@
 set_asid:
 	__set_bit(asid, asid_map);
 	cur_idx = asid;
-
-bump_gen:
-	asid |= generation;
-	return asid;
+	return asid | generation;
 }
 
 void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 131a199..7963aa4 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -18,6 +18,7 @@
  */
 
 #include <linux/gfp.h>
+#include <linux/acpi.h>
 #include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/genalloc.h>
@@ -28,9 +29,6 @@
 
 #include <asm/cacheflush.h>
 
-struct dma_map_ops *dma_ops;
-EXPORT_SYMBOL(dma_ops);
-
 static pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot,
 				 bool coherent)
 {
@@ -515,13 +513,7 @@
 
 static int __init arm64_dma_init(void)
 {
-	int ret;
-
-	dma_ops = &swiotlb_dma_ops;
-
-	ret = atomic_pool_init();
-
-	return ret;
+	return atomic_pool_init();
 }
 arch_initcall(arm64_dma_init);
 
@@ -552,10 +544,14 @@
 {
 	bool coherent = is_device_dma_coherent(dev);
 	int ioprot = dma_direction_to_prot(DMA_BIDIRECTIONAL, coherent);
+	size_t iosize = size;
 	void *addr;
 
 	if (WARN(!dev, "cannot create IOMMU mapping for unknown device\n"))
 		return NULL;
+
+	size = PAGE_ALIGN(size);
+
 	/*
 	 * Some drivers rely on this, and we probably don't want the
 	 * possibility of stale kernel data being read by devices anyway.
@@ -566,7 +562,7 @@
 		struct page **pages;
 		pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, coherent);
 
-		pages = iommu_dma_alloc(dev, size, gfp, ioprot,	handle,
+		pages = iommu_dma_alloc(dev, iosize, gfp, ioprot, handle,
 					flush_page);
 		if (!pages)
 			return NULL;
@@ -574,7 +570,7 @@
 		addr = dma_common_pages_remap(pages, size, VM_USERMAP, prot,
 					      __builtin_return_address(0));
 		if (!addr)
-			iommu_dma_free(dev, pages, size, handle);
+			iommu_dma_free(dev, pages, iosize, handle);
 	} else {
 		struct page *page;
 		/*
@@ -591,7 +587,7 @@
 		if (!addr)
 			return NULL;
 
-		*handle = iommu_dma_map_page(dev, page, 0, size, ioprot);
+		*handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot);
 		if (iommu_dma_mapping_error(dev, *handle)) {
 			if (coherent)
 				__free_pages(page, get_order(size));
@@ -606,6 +602,9 @@
 static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 			       dma_addr_t handle, struct dma_attrs *attrs)
 {
+	size_t iosize = size;
+
+	size = PAGE_ALIGN(size);
 	/*
 	 * @cpu_addr will be one of 3 things depending on how it was allocated:
 	 * - A remapped array of pages from iommu_dma_alloc(), for all
@@ -617,17 +616,17 @@
 	 * Hence how dodgy the below logic looks...
 	 */
 	if (__in_atomic_pool(cpu_addr, size)) {
-		iommu_dma_unmap_page(dev, handle, size, 0, NULL);
+		iommu_dma_unmap_page(dev, handle, iosize, 0, NULL);
 		__free_from_pool(cpu_addr, size);
 	} else if (is_vmalloc_addr(cpu_addr)){
 		struct vm_struct *area = find_vm_area(cpu_addr);
 
 		if (WARN_ON(!area || !area->pages))
 			return;
-		iommu_dma_free(dev, area->pages, size, &handle);
+		iommu_dma_free(dev, area->pages, iosize, &handle);
 		dma_common_free_remap(cpu_addr, size, VM_USERMAP);
 	} else {
-		iommu_dma_unmap_page(dev, handle, size, 0, NULL);
+		iommu_dma_unmap_page(dev, handle, iosize, 0, NULL);
 		__free_pages(virt_to_page(cpu_addr), get_order(size));
 	}
 }
@@ -984,8 +983,8 @@
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 			struct iommu_ops *iommu, bool coherent)
 {
-	if (!acpi_disabled && !dev->archdata.dma_ops)
-		dev->archdata.dma_ops = dma_ops;
+	if (!dev->archdata.dma_ops)
+		dev->archdata.dma_ops = &swiotlb_dma_ops;
 
 	dev->archdata.dma_coherent = coherent;
 	__iommu_setup_dma_ops(dev, dma_base, size, iommu);
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 19211c4..92ddac1 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -393,16 +393,16 @@
 	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 1 translation fault"	},
 	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 2 translation fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_MAPERR,	"level 3 translation fault"	},
-	{ do_bad,		SIGBUS,  0,		"reserved access flag fault"	},
+	{ do_bad,		SIGBUS,  0,		"unknown 8"			},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 1 access flag fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 access flag fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 access flag fault"	},
-	{ do_bad,		SIGBUS,  0,		"reserved permission fault"	},
+	{ do_bad,		SIGBUS,  0,		"unknown 12"			},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 1 permission fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 permission fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 permission fault"	},
 	{ do_bad,		SIGBUS,  0,		"synchronous external abort"	},
-	{ do_bad,		SIGBUS,  0,		"asynchronous external abort"	},
+	{ do_bad,		SIGBUS,  0,		"unknown 17"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 18"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 19"			},
 	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
@@ -410,16 +410,16 @@
 	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
 	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
 	{ do_bad,		SIGBUS,  0,		"synchronous parity error"	},
-	{ do_bad,		SIGBUS,  0,		"asynchronous parity error"	},
+	{ do_bad,		SIGBUS,  0,		"unknown 25"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 26"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 27"			},
-	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk" },
-	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk" },
-	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk" },
-	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk" },
+	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
+	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
+	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
+	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
 	{ do_bad,		SIGBUS,  0,		"unknown 32"			},
 	{ do_bad,		SIGBUS,  BUS_ADRALN,	"alignment fault"		},
-	{ do_bad,		SIGBUS,  0,		"debug event"			},
+	{ do_bad,		SIGBUS,  0,		"unknown 34"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 35"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 36"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 37"			},
@@ -433,21 +433,21 @@
 	{ do_bad,		SIGBUS,  0,		"unknown 45"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 46"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 47"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 48"			},
+	{ do_bad,		SIGBUS,  0,		"TLB conflict abort"		},
 	{ do_bad,		SIGBUS,  0,		"unknown 49"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 50"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 51"			},
 	{ do_bad,		SIGBUS,  0,		"implementation fault (lockdown abort)" },
-	{ do_bad,		SIGBUS,  0,		"unknown 53"			},
+	{ do_bad,		SIGBUS,  0,		"implementation fault (unsupported exclusive)" },
 	{ do_bad,		SIGBUS,  0,		"unknown 54"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 55"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 56"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 57"			},
-	{ do_bad,		SIGBUS,  0,		"implementation fault (coprocessor abort)" },
+	{ do_bad,		SIGBUS,  0,		"unknown 58" 			},
 	{ do_bad,		SIGBUS,  0,		"unknown 59"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 60"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 61"			},
-	{ do_bad,		SIGBUS,  0,		"unknown 62"			},
+	{ do_bad,		SIGBUS,  0,		"section domain fault"		},
+	{ do_bad,		SIGBUS,  0,		"page domain fault"		},
 	{ do_bad,		SIGBUS,  0,		"unknown 63"			},
 };
 
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index e3f563c..873e363 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -64,8 +64,12 @@
 
 static void __init *early_alloc(unsigned long sz)
 {
-	void *ptr = __va(memblock_alloc(sz, sz));
-	BUG_ON(!ptr);
+	phys_addr_t phys;
+	void *ptr;
+
+	phys = memblock_alloc(sz, sz);
+	BUG_ON(!phys);
+	ptr = __va(phys);
 	memset(ptr, 0, sz);
 	return ptr;
 }
@@ -81,55 +85,19 @@
 	do {
 		/*
 		 * Need to have the least restrictive permissions available
-		 * permissions will be fixed up later. Default the new page
-		 * range as contiguous ptes.
+		 * permissions will be fixed up later
 		 */
-		set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC_CONT));
+		set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC));
 		pfn++;
 	} while (pte++, i++, i < PTRS_PER_PTE);
 }
 
-/*
- * Given a PTE with the CONT bit set, determine where the CONT range
- * starts, and clear the entire range of PTE CONT bits.
- */
-static void clear_cont_pte_range(pte_t *pte, unsigned long addr)
-{
-	int i;
-
-	pte -= CONT_RANGE_OFFSET(addr);
-	for (i = 0; i < CONT_PTES; i++) {
-		set_pte(pte, pte_mknoncont(*pte));
-		pte++;
-	}
-	flush_tlb_all();
-}
-
-/*
- * Given a range of PTEs set the pfn and provided page protection flags
- */
-static void __populate_init_pte(pte_t *pte, unsigned long addr,
-				unsigned long end, phys_addr_t phys,
-				pgprot_t prot)
-{
-	unsigned long pfn = __phys_to_pfn(phys);
-
-	do {
-		/* clear all the bits except the pfn, then apply the prot */
-		set_pte(pte, pfn_pte(pfn, prot));
-		pte++;
-		pfn++;
-		addr += PAGE_SIZE;
-	} while (addr != end);
-}
-
 static void alloc_init_pte(pmd_t *pmd, unsigned long addr,
-				  unsigned long end, phys_addr_t phys,
+				  unsigned long end, unsigned long pfn,
 				  pgprot_t prot,
 				  void *(*alloc)(unsigned long size))
 {
 	pte_t *pte;
-	unsigned long next;
 
 	if (pmd_none(*pmd) || pmd_sect(*pmd)) {
 		pte = alloc(PTRS_PER_PTE * sizeof(pte_t));
@@ -142,27 +110,9 @@
 
 	pte = pte_offset_kernel(pmd, addr);
 	do {
-		next = min(end, (addr + CONT_SIZE) & CONT_MASK);
-		if (((addr | next | phys) & ~CONT_MASK) == 0) {
-			/* a block of CONT_PTES  */
-			__populate_init_pte(pte, addr, next, phys,
-					    __pgprot(pgprot_val(prot) | PTE_CONT));
-		} else {
-			/*
-			 * If the range being split is already inside of a
-			 * contiguous range but this PTE isn't going to be
-			 * contiguous, then we want to unmark the adjacent
-			 * ranges, then update the portion of the range we
-			 * are interrested in.
-			 */
-			 clear_cont_pte_range(pte, addr);
-			 __populate_init_pte(pte, addr, next, phys, prot);
-		}
-
-		pte += (next - addr) >> PAGE_SHIFT;
-		phys += next - addr;
-		addr = next;
-	} while (addr != end);
+		set_pte(pte, pfn_pte(pfn, prot));
+		pfn++;
+	} while (pte++, addr += PAGE_SIZE, addr != end);
 }
 
 static void split_pud(pud_t *old_pud, pmd_t *pmd)
@@ -223,7 +173,8 @@
 				}
 			}
 		} else {
-			alloc_init_pte(pmd, addr, next, phys, prot, alloc);
+			alloc_init_pte(pmd, addr, next, __phys_to_pfn(phys),
+				       prot, alloc);
 		}
 		phys += next - addr;
 	} while (pmd++, addr = next, addr != end);
@@ -362,8 +313,8 @@
 	 * for now. This will get more fine grained later once all memory
 	 * is mapped
 	 */
-	unsigned long kernel_x_start = round_down(__pa(_stext), SECTION_SIZE);
-	unsigned long kernel_x_end = round_up(__pa(__init_end), SECTION_SIZE);
+	unsigned long kernel_x_start = round_down(__pa(_stext), SWAPPER_BLOCK_SIZE);
+	unsigned long kernel_x_end = round_up(__pa(__init_end), SWAPPER_BLOCK_SIZE);
 
 	if (end < kernel_x_start) {
 		create_mapping(start, __phys_to_virt(start),
@@ -451,18 +402,18 @@
 {
 #ifdef CONFIG_DEBUG_RODATA
 	/* now that we are actually fully mapped, make the start/end more fine grained */
-	if (!IS_ALIGNED((unsigned long)_stext, SECTION_SIZE)) {
+	if (!IS_ALIGNED((unsigned long)_stext, SWAPPER_BLOCK_SIZE)) {
 		unsigned long aligned_start = round_down(__pa(_stext),
-							SECTION_SIZE);
+							 SWAPPER_BLOCK_SIZE);
 
 		create_mapping(aligned_start, __phys_to_virt(aligned_start),
 				__pa(_stext) - aligned_start,
 				PAGE_KERNEL);
 	}
 
-	if (!IS_ALIGNED((unsigned long)__init_end, SECTION_SIZE)) {
+	if (!IS_ALIGNED((unsigned long)__init_end, SWAPPER_BLOCK_SIZE)) {
 		unsigned long aligned_end = round_up(__pa(__init_end),
-							SECTION_SIZE);
+							  SWAPPER_BLOCK_SIZE);
 		create_mapping(__pa(__init_end), (unsigned long)__init_end,
 				aligned_end - __pa(__init_end),
 				PAGE_KERNEL);
@@ -475,7 +426,7 @@
 {
 	create_mapping_late(__pa(_stext), (unsigned long)_stext,
 				(unsigned long)_etext - (unsigned long)_stext,
-				PAGE_KERNEL_EXEC | PTE_RDONLY);
+				PAGE_KERNEL_ROX);
 
 }
 #endif
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index d6a53ef..b162ad7 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -139,6 +139,12 @@
 /* Stack must be multiples of 16B */
 #define STACK_ALIGN(sz) (((sz) + 15) & ~15)
 
+#define _STACK_SIZE \
+	(MAX_BPF_STACK \
+	 + 4 /* extra for skb_copy_bits buffer */)
+
+#define STACK_SIZE STACK_ALIGN(_STACK_SIZE)
+
 static void build_prologue(struct jit_ctx *ctx)
 {
 	const u8 r6 = bpf2a64[BPF_REG_6];
@@ -150,10 +156,6 @@
 	const u8 rx = bpf2a64[BPF_REG_X];
 	const u8 tmp1 = bpf2a64[TMP_REG_1];
 	const u8 tmp2 = bpf2a64[TMP_REG_2];
-	int stack_size = MAX_BPF_STACK;
-
-	stack_size += 4; /* extra for skb_copy_bits buffer */
-	stack_size = STACK_ALIGN(stack_size);
 
 	/*
 	 * BPF prog stack layout
@@ -165,12 +167,13 @@
 	 *                        | ... | callee saved registers
 	 *                        +-----+
 	 *                        |     | x25/x26
-	 * BPF fp register => -80:+-----+
+	 * BPF fp register => -80:+-----+ <= (BPF_FP)
 	 *                        |     |
 	 *                        | ... | BPF prog stack
 	 *                        |     |
-	 *                        |     |
-	 * current A64_SP =>      +-----+
+	 *                        +-----+ <= (BPF_FP - MAX_BPF_STACK)
+	 *                        |RSVD | JIT scratchpad
+	 * current A64_SP =>      +-----+ <= (BPF_FP - STACK_SIZE)
 	 *                        |     |
 	 *                        | ... | Function call stack
 	 *                        |     |
@@ -196,7 +199,7 @@
 	emit(A64_MOV(1, fp, A64_SP), ctx);
 
 	/* Set up function call stack */
-	emit(A64_SUB_I(1, A64_SP, A64_SP, stack_size), ctx);
+	emit(A64_SUB_I(1, A64_SP, A64_SP, STACK_SIZE), ctx);
 
 	/* Clear registers A and X */
 	emit_a64_mov_i64(ra, 0, ctx);
@@ -213,13 +216,9 @@
 	const u8 fp = bpf2a64[BPF_REG_FP];
 	const u8 tmp1 = bpf2a64[TMP_REG_1];
 	const u8 tmp2 = bpf2a64[TMP_REG_2];
-	int stack_size = MAX_BPF_STACK;
-
-	stack_size += 4; /* extra for skb_copy_bits buffer */
-	stack_size = STACK_ALIGN(stack_size);
 
 	/* We're done with BPF stack */
-	emit(A64_ADD_I(1, A64_SP, A64_SP, stack_size), ctx);
+	emit(A64_ADD_I(1, A64_SP, A64_SP, STACK_SIZE), ctx);
 
 	/* Restore fs (x25) and x26 */
 	emit(A64_POP(fp, A64_R(26), A64_SP), ctx);
@@ -591,7 +590,25 @@
 	case BPF_ST | BPF_MEM | BPF_H:
 	case BPF_ST | BPF_MEM | BPF_B:
 	case BPF_ST | BPF_MEM | BPF_DW:
-		goto notyet;
+		/* Load imm to a register then store it */
+		ctx->tmp_used = 1;
+		emit_a64_mov_i(1, tmp2, off, ctx);
+		emit_a64_mov_i(1, tmp, imm, ctx);
+		switch (BPF_SIZE(code)) {
+		case BPF_W:
+			emit(A64_STR32(tmp, dst, tmp2), ctx);
+			break;
+		case BPF_H:
+			emit(A64_STRH(tmp, dst, tmp2), ctx);
+			break;
+		case BPF_B:
+			emit(A64_STRB(tmp, dst, tmp2), ctx);
+			break;
+		case BPF_DW:
+			emit(A64_STR64(tmp, dst, tmp2), ctx);
+			break;
+		}
+		break;
 
 	/* STX: *(size *)(dst + off) = src */
 	case BPF_STX | BPF_MEM | BPF_W:
@@ -658,7 +675,7 @@
 			return -EINVAL;
 		}
 		emit_a64_mov_i64(r3, size, ctx);
-		emit(A64_ADD_I(1, r4, fp, MAX_BPF_STACK), ctx);
+		emit(A64_SUB_I(1, r4, fp, STACK_SIZE), ctx);
 		emit_a64_mov_i64(r5, (unsigned long)bpf_load_pointer, ctx);
 		emit(A64_PUSH(A64_FP, A64_LR, A64_SP), ctx);
 		emit(A64_MOV(1, A64_FP, A64_SP), ctx);
diff --git a/arch/blackfin/kernel/perf_event.c b/arch/blackfin/kernel/perf_event.c
index 1e9c8b0..170d786 100644
--- a/arch/blackfin/kernel/perf_event.c
+++ b/arch/blackfin/kernel/perf_event.c
@@ -14,7 +14,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *
  * ppc:
diff --git a/arch/m68k/coldfire/m54xx.c b/arch/m68k/coldfire/m54xx.c
index f7836c6..c32f767 100644
--- a/arch/m68k/coldfire/m54xx.c
+++ b/arch/m68k/coldfire/m54xx.c
@@ -98,7 +98,7 @@
 	memstart = PAGE_ALIGN(_ramstart);
 	min_low_pfn = PFN_DOWN(_rambase);
 	start_pfn = PFN_DOWN(memstart);
-	max_low_pfn = PFN_DOWN(_ramend);
+	max_pfn = max_low_pfn = PFN_DOWN(_ramend);
 	high_memory = (void *)_ramend;
 
 	m68k_virt_to_node_shift = fls(_ramend - _rambase - 1) - 6;
diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h
index 0793a7f..f9d96bf 100644
--- a/arch/m68k/include/asm/unistd.h
+++ b/arch/m68k/include/asm/unistd.h
@@ -4,7 +4,7 @@
 #include <uapi/asm/unistd.h>
 
 
-#define NR_syscalls		375
+#define NR_syscalls		376
 
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_OLD_STAT
diff --git a/arch/m68k/include/uapi/asm/unistd.h b/arch/m68k/include/uapi/asm/unistd.h
index 5e6fae6..36cf129 100644
--- a/arch/m68k/include/uapi/asm/unistd.h
+++ b/arch/m68k/include/uapi/asm/unistd.h
@@ -380,5 +380,6 @@
 #define __NR_sendmmsg		372
 #define __NR_userfaultfd	373
 #define __NR_membarrier		374
+#define __NR_mlock2		375
 
 #endif /* _UAPI_ASM_M68K_UNISTD_H_ */
diff --git a/arch/m68k/kernel/setup_no.c b/arch/m68k/kernel/setup_no.c
index 88c27d9..76b9113 100644
--- a/arch/m68k/kernel/setup_no.c
+++ b/arch/m68k/kernel/setup_no.c
@@ -238,11 +238,14 @@
 	 * Give all the memory to the bootmap allocator, tell it to put the
 	 * boot mem_map at the start of memory.
 	 */
+	min_low_pfn = PFN_DOWN(memory_start);
+	max_pfn = max_low_pfn = PFN_DOWN(memory_end);
+
 	bootmap_size = init_bootmem_node(
 			NODE_DATA(0),
-			memory_start >> PAGE_SHIFT, /* map goes here */
-			PAGE_OFFSET >> PAGE_SHIFT,	/* 0 on coldfire */
-			memory_end >> PAGE_SHIFT);
+			min_low_pfn,		/* map goes here */
+			PFN_DOWN(PAGE_OFFSET),
+			max_pfn);
 	/*
 	 * Free the usable memory, we have to make sure we do not free
 	 * the bootmem bitmap so we then reserve it after freeing it :-)
diff --git a/arch/m68k/kernel/syscalltable.S b/arch/m68k/kernel/syscalltable.S
index 5dd0e80..282cd90 100644
--- a/arch/m68k/kernel/syscalltable.S
+++ b/arch/m68k/kernel/syscalltable.S
@@ -395,3 +395,4 @@
 	.long sys_sendmmsg
 	.long sys_userfaultfd
 	.long sys_membarrier
+	.long sys_mlock2		/* 375 */
diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c
index b958916..8f37fdd 100644
--- a/arch/m68k/mm/motorola.c
+++ b/arch/m68k/mm/motorola.c
@@ -250,7 +250,7 @@
 	high_memory = phys_to_virt(max_addr);
 
 	min_low_pfn = availmem >> PAGE_SHIFT;
-	max_low_pfn = max_addr >> PAGE_SHIFT;
+	max_pfn = max_low_pfn = max_addr >> PAGE_SHIFT;
 
 	for (i = 0; i < m68k_num_memory; i++) {
 		addr = m68k_memory[i].addr;
diff --git a/arch/m68k/sun3/config.c b/arch/m68k/sun3/config.c
index a8b942b..2a5f43a 100644
--- a/arch/m68k/sun3/config.c
+++ b/arch/m68k/sun3/config.c
@@ -118,13 +118,13 @@
 	memory_end = memory_end & PAGE_MASK;
 
 	start_page = __pa(memory_start) >> PAGE_SHIFT;
-	num_pages = __pa(memory_end) >> PAGE_SHIFT;
+	max_pfn = num_pages = __pa(memory_end) >> PAGE_SHIFT;
 
 	high_memory = (void *)memory_end;
 	availmem = memory_start;
 
 	m68k_setup_node(0);
-	availmem += init_bootmem_node(NODE_DATA(0), start_page, 0, num_pages);
+	availmem += init_bootmem(start_page, num_pages);
 	availmem = (availmem + (PAGE_SIZE-1)) & PAGE_MASK;
 
 	free_bootmem(__pa(availmem), memory_end - (availmem));
diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c
index 1ba2120..8755d61 100644
--- a/arch/mips/ath79/setup.c
+++ b/arch/mips/ath79/setup.c
@@ -216,9 +216,9 @@
 					   AR71XX_RESET_SIZE);
 	ath79_pll_base = ioremap_nocache(AR71XX_PLL_BASE,
 					 AR71XX_PLL_SIZE);
+	ath79_detect_sys_type();
 	ath79_ddr_ctrl_init();
 
-	ath79_detect_sys_type();
 	if (mips_machtype != ATH79_MACH_GENERIC_OF)
 		detect_memory_region(0, ATH79_MEM_SIZE_MIN, ATH79_MEM_SIZE_MAX);
 
@@ -281,3 +281,8 @@
 	     "Generic",
 	     "Generic AR71XX/AR724X/AR913X based board",
 	     ath79_generic_init);
+
+MIPS_MACHINE(ATH79_MACH_GENERIC_OF,
+	     "DTB",
+	     "Generic AR71XX/AR724X/AR913X based board (DT)",
+	     NULL);
diff --git a/arch/mips/boot/dts/qca/ar9132.dtsi b/arch/mips/boot/dts/qca/ar9132.dtsi
index fb7734e..13d0439 100644
--- a/arch/mips/boot/dts/qca/ar9132.dtsi
+++ b/arch/mips/boot/dts/qca/ar9132.dtsi
@@ -107,7 +107,7 @@
 			miscintc: interrupt-controller@18060010 {
 				compatible = "qca,ar9132-misc-intc",
 					   "qca,ar7100-misc-intc";
-				reg = <0x18060010 0x4>;
+				reg = <0x18060010 0x8>;
 
 				interrupt-parent = <&cpuintc>;
 				interrupts = <6>;
diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h
index ad1fccd..2046c02 100644
--- a/arch/mips/include/asm/page.h
+++ b/arch/mips/include/asm/page.h
@@ -200,8 +200,9 @@
 {
 	/* avoid <linux/mm.h> include hell */
 	extern unsigned long max_mapnr;
+	unsigned long pfn_offset = ARCH_PFN_OFFSET;
 
-	return pfn >= ARCH_PFN_OFFSET && pfn < max_mapnr;
+	return pfn >= pfn_offset && pfn < max_mapnr;
 }
 
 #elif defined(CONFIG_SPARSEMEM)
diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c
index d5fa3ea..41b1b09 100644
--- a/arch/mips/kvm/emulate.c
+++ b/arch/mips/kvm/emulate.c
@@ -1581,7 +1581,7 @@
 
 	base = (inst >> 21) & 0x1f;
 	op_inst = (inst >> 16) & 0x1f;
-	offset = inst & 0xffff;
+	offset = (int16_t)inst;
 	cache = (inst >> 16) & 0x3;
 	op = (inst >> 18) & 0x7;
 
diff --git a/arch/mips/kvm/locore.S b/arch/mips/kvm/locore.S
index 7bab3a4..7e22108 100644
--- a/arch/mips/kvm/locore.S
+++ b/arch/mips/kvm/locore.S
@@ -157,9 +157,11 @@
 
 FEXPORT(__kvm_mips_load_asid)
 	/* Set the ASID for the Guest Kernel */
-	INT_SLL	t0, t0, 1	/* with kseg0 @ 0x40000000, kernel */
-			        /* addresses shift to 0x80000000 */
-	bltz	t0, 1f		/* If kernel */
+	PTR_L	t0, VCPU_COP0(k1)
+	LONG_L	t0, COP0_STATUS(t0)
+	andi	t0, KSU_USER | ST0_ERL | ST0_EXL
+	xori	t0, KSU_USER
+	bnez	t0, 1f		/* If kernel */
 	 INT_ADDIU t1, k1, VCPU_GUEST_KERNEL_ASID  /* (BD)  */
 	INT_ADDIU t1, k1, VCPU_GUEST_USER_ASID    /* else user */
 1:
@@ -474,9 +476,11 @@
 	mtc0	t0, CP0_EPC
 
 	/* Set the ASID for the Guest Kernel */
-	INT_SLL	t0, t0, 1	/* with kseg0 @ 0x40000000, kernel */
-				/* addresses shift to 0x80000000 */
-	bltz	t0, 1f		/* If kernel */
+	PTR_L	t0, VCPU_COP0(k1)
+	LONG_L	t0, COP0_STATUS(t0)
+	andi	t0, KSU_USER | ST0_ERL | ST0_EXL
+	xori	t0, KSU_USER
+	bnez	t0, 1f		/* If kernel */
 	 INT_ADDIU t1, k1, VCPU_GUEST_KERNEL_ASID  /* (BD)  */
 	INT_ADDIU t1, k1, VCPU_GUEST_USER_ASID    /* else user */
 1:
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 49ff3bf..b9b803f 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -279,7 +279,7 @@
 
 	if (!gebase) {
 		err = -ENOMEM;
-		goto out_free_cpu;
+		goto out_uninit_cpu;
 	}
 	kvm_debug("Allocated %d bytes for KVM Exception Handlers @ %p\n",
 		  ALIGN(size, PAGE_SIZE), gebase);
@@ -343,6 +343,9 @@
 out_free_gebase:
 	kfree(gebase);
 
+out_uninit_cpu:
+	kvm_vcpu_uninit(vcpu);
+
 out_free_cpu:
 	kfree(vcpu);
 
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
index d8117be..730d394 100644
--- a/arch/mips/mm/dma-default.c
+++ b/arch/mips/mm/dma-default.c
@@ -145,7 +145,7 @@
 
 	gfp = massage_gfp_flags(dev, gfp);
 
-	if (IS_ENABLED(CONFIG_DMA_CMA) && !(gfp & GFP_ATOMIC))
+	if (IS_ENABLED(CONFIG_DMA_CMA) && gfpflags_allow_blocking(gfp))
 		page = dma_alloc_from_contiguous(dev,
 					count, get_order(size));
 	if (!page)
diff --git a/arch/mips/pci/pci-rt2880.c b/arch/mips/pci/pci-rt2880.c
index 8a97802..dbbeccc 100644
--- a/arch/mips/pci/pci-rt2880.c
+++ b/arch/mips/pci/pci-rt2880.c
@@ -11,6 +11,7 @@
  *  by the Free Software Foundation.
  */
 
+#include <linux/delay.h>
 #include <linux/types.h>
 #include <linux/pci.h>
 #include <linux/io.h>
@@ -232,8 +233,7 @@
 	ioport_resource.end = RT2880_PCI_IO_BASE + RT2880_PCI_IO_SIZE - 1;
 
 	rt2880_pci_reg_write(0, RT2880_PCI_REG_PCICFG_ADDR);
-	for (i = 0; i < 0xfffff; i++)
-		;
+	udelay(1);
 
 	rt2880_pci_reg_write(0x79, RT2880_PCI_REG_ARBCTL);
 	rt2880_pci_reg_write(0x07FF0001, RT2880_PCI_REG_BAR0SETUP_ADDR);
diff --git a/arch/mips/pmcs-msp71xx/msp_setup.c b/arch/mips/pmcs-msp71xx/msp_setup.c
index 4f925e0..78b2ef4 100644
--- a/arch/mips/pmcs-msp71xx/msp_setup.c
+++ b/arch/mips/pmcs-msp71xx/msp_setup.c
@@ -10,6 +10,8 @@
  * option) any later version.
  */
 
+#include <linux/delay.h>
+
 #include <asm/bootinfo.h>
 #include <asm/cacheflush.h>
 #include <asm/idle.h>
@@ -77,7 +79,7 @@
 	 */
 
 	/* Wait a bit for the DDRC to settle */
-	for (i = 0; i < 100000000; i++);
+	mdelay(125);
 
 #if defined(CONFIG_PMC_MSP7120_GW)
 	/*
diff --git a/arch/mips/sni/reset.c b/arch/mips/sni/reset.c
index 244f942..db8f88b 100644
--- a/arch/mips/sni/reset.c
+++ b/arch/mips/sni/reset.c
@@ -3,6 +3,8 @@
  *
  *  Reset a SNI machine.
  */
+#include <linux/delay.h>
+
 #include <asm/io.h>
 #include <asm/reboot.h>
 #include <asm/sni.h>
@@ -32,9 +34,9 @@
 	for (;;) {
 		for (i = 0; i < 100; i++) {
 			kb_wait();
-			for (j = 0; j < 100000 ; j++)
-				/* nothing */;
+			udelay(50);
 			outb_p(0xfe, 0x64);	 /* pulse reset low */
+			udelay(50);
 		}
 	}
 }
diff --git a/arch/mn10300/Kconfig b/arch/mn10300/Kconfig
index 4434b54..78ae555 100644
--- a/arch/mn10300/Kconfig
+++ b/arch/mn10300/Kconfig
@@ -1,6 +1,7 @@
 config MN10300
 	def_bool y
 	select HAVE_OPROFILE
+	select HAVE_UID16
 	select GENERIC_IRQ_SHOW
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select HAVE_ARCH_TRACEHOOK
@@ -37,9 +38,6 @@
 config NUMA
 	def_bool n
 
-config UID16
-	def_bool y
-
 config RWSEM_GENERIC_SPINLOCK
 	def_bool y
 
diff --git a/arch/nios2/mm/cacheflush.c b/arch/nios2/mm/cacheflush.c
index 223cdcc..87bf88e 100644
--- a/arch/nios2/mm/cacheflush.c
+++ b/arch/nios2/mm/cacheflush.c
@@ -23,22 +23,6 @@
 	end += (cpuinfo.dcache_line_size - 1);
 	end &= ~(cpuinfo.dcache_line_size - 1);
 
-	for (addr = start; addr < end; addr += cpuinfo.dcache_line_size) {
-		__asm__ __volatile__ ("   flushda 0(%0)\n"
-					: /* Outputs */
-					: /* Inputs  */ "r"(addr)
-					/* : No clobber */);
-	}
-}
-
-static void __flush_dcache_all(unsigned long start, unsigned long end)
-{
-	unsigned long addr;
-
-	start &= ~(cpuinfo.dcache_line_size - 1);
-	end += (cpuinfo.dcache_line_size - 1);
-	end &= ~(cpuinfo.dcache_line_size - 1);
-
 	if (end > start + cpuinfo.dcache_size)
 		end = start + cpuinfo.dcache_size;
 
@@ -112,7 +96,7 @@
 
 void flush_cache_all(void)
 {
-	__flush_dcache_all(0, cpuinfo.dcache_size);
+	__flush_dcache(0, cpuinfo.dcache_size);
 	__flush_icache(0, cpuinfo.icache_size);
 }
 
@@ -182,7 +166,7 @@
 	 */
 	unsigned long start = (unsigned long)page_address(page);
 
-	__flush_dcache_all(start, start + PAGE_SIZE);
+	__flush_dcache(start, start + PAGE_SIZE);
 }
 
 void flush_dcache_page(struct page *page)
@@ -268,7 +252,7 @@
 {
 	flush_cache_page(vma, user_vaddr, page_to_pfn(page));
 	memcpy(dst, src, len);
-	__flush_dcache_all((unsigned long)src, (unsigned long)src + len);
+	__flush_dcache((unsigned long)src, (unsigned long)src + len);
 	if (vma->vm_flags & VM_EXEC)
 		__flush_icache((unsigned long)src, (unsigned long)src + len);
 }
@@ -279,7 +263,7 @@
 {
 	flush_cache_page(vma, user_vaddr, page_to_pfn(page));
 	memcpy(dst, src, len);
-	__flush_dcache_all((unsigned long)dst, (unsigned long)dst + len);
+	__flush_dcache((unsigned long)dst, (unsigned long)dst + len);
 	if (vma->vm_flags & VM_EXEC)
 		__flush_icache((unsigned long)dst, (unsigned long)dst + len);
 }
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index c365469..729f891 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -108,6 +108,9 @@
 	default 3 if 64BIT && PARISC_PAGE_SIZE_4KB
 	default 2
 
+config SYS_SUPPORTS_HUGETLBFS
+	def_bool y if PA20
+
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h
new file mode 100644
index 0000000..7d56a9c
--- /dev/null
+++ b/arch/parisc/include/asm/hugetlb.h
@@ -0,0 +1,85 @@
+#ifndef _ASM_PARISC64_HUGETLB_H
+#define _ASM_PARISC64_HUGETLB_H
+
+#include <asm/page.h>
+#include <asm-generic/hugetlb.h>
+
+
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+		     pte_t *ptep, pte_t pte);
+
+pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep);
+
+static inline int is_hugepage_only_range(struct mm_struct *mm,
+					 unsigned long addr,
+					 unsigned long len) {
+	return 0;
+}
+
+/*
+ * If the arch doesn't supply something else, assume that hugepage
+ * size aligned regions are ok without further preparation.
+ */
+static inline int prepare_hugepage_range(struct file *file,
+			unsigned long addr, unsigned long len)
+{
+	if (len & ~HPAGE_MASK)
+		return -EINVAL;
+	if (addr & ~HPAGE_MASK)
+		return -EINVAL;
+	return 0;
+}
+
+static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
+					  unsigned long addr, unsigned long end,
+					  unsigned long floor,
+					  unsigned long ceiling)
+{
+	free_pgd_range(tlb, addr, end, floor, ceiling);
+}
+
+static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep)
+{
+}
+
+static inline int huge_pte_none(pte_t pte)
+{
+	return pte_none(pte);
+}
+
+static inline pte_t huge_pte_wrprotect(pte_t pte)
+{
+	return pte_wrprotect(pte);
+}
+
+static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
+					   unsigned long addr, pte_t *ptep)
+{
+	pte_t old_pte = *ptep;
+	set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte));
+}
+
+static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+					     unsigned long addr, pte_t *ptep,
+					     pte_t pte, int dirty)
+{
+	int changed = !pte_same(*ptep, pte);
+	if (changed) {
+		set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+		flush_tlb_page(vma, addr);
+	}
+	return changed;
+}
+
+static inline pte_t huge_ptep_get(pte_t *ptep)
+{
+	return *ptep;
+}
+
+static inline void arch_clear_hugepage_flags(struct page *page)
+{
+}
+
+#endif /* _ASM_PARISC64_HUGETLB_H */
diff --git a/arch/parisc/include/asm/page.h b/arch/parisc/include/asm/page.h
index 60d5d17..80e742a 100644
--- a/arch/parisc/include/asm/page.h
+++ b/arch/parisc/include/asm/page.h
@@ -145,11 +145,22 @@
 #endif /* CONFIG_DISCONTIGMEM */
 
 #ifdef CONFIG_HUGETLB_PAGE
-#define HPAGE_SHIFT		22	/* 4MB (is this fixed?) */
+#define HPAGE_SHIFT		PMD_SHIFT /* fixed for transparent huge pages */
 #define HPAGE_SIZE      	((1UL) << HPAGE_SHIFT)
 #define HPAGE_MASK		(~(HPAGE_SIZE - 1))
 #define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
+
+#if defined(CONFIG_64BIT) && defined(CONFIG_PARISC_PAGE_SIZE_4KB)
+# define REAL_HPAGE_SHIFT	20 /* 20 = 1MB */
+# define _HUGE_PAGE_SIZE_ENCODING_DEFAULT _PAGE_SIZE_ENCODING_1M
+#elif !defined(CONFIG_64BIT) && defined(CONFIG_PARISC_PAGE_SIZE_4KB)
+# define REAL_HPAGE_SHIFT	22 /* 22 = 4MB */
+# define _HUGE_PAGE_SIZE_ENCODING_DEFAULT _PAGE_SIZE_ENCODING_4M
+#else
+# define REAL_HPAGE_SHIFT	24 /* 24 = 16MB */
+# define _HUGE_PAGE_SIZE_ENCODING_DEFAULT _PAGE_SIZE_ENCODING_16M
 #endif
+#endif /* CONFIG_HUGETLB_PAGE */
 
 #define virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
 
diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h
index 3edbb9f..f2fd327 100644
--- a/arch/parisc/include/asm/pgalloc.h
+++ b/arch/parisc/include/asm/pgalloc.h
@@ -35,7 +35,7 @@
 				        PxD_FLAG_VALID | 
 					PxD_FLAG_ATTACHED) 
 			+ (__u32)(__pa((unsigned long)pgd) >> PxD_VALUE_SHIFT));
-		/* The first pmd entry also is marked with _PAGE_GATEWAY as
+		/* The first pmd entry also is marked with PxD_FLAG_ATTACHED as
 		 * a signal that this pmd may not be freed */
 		__pgd_val_set(*pgd, PxD_FLAG_ATTACHED);
 #endif
diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h
index f93c4a4..291cee2 100644
--- a/arch/parisc/include/asm/pgtable.h
+++ b/arch/parisc/include/asm/pgtable.h
@@ -83,7 +83,11 @@
 	printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, (unsigned long)pgd_val(e))
 
 /* This is the size of the initially mapped kernel memory */
-#define KERNEL_INITIAL_ORDER	24	/* 0 to 1<<24 = 16MB */
+#ifdef CONFIG_64BIT
+#define KERNEL_INITIAL_ORDER	25	/* 1<<25 = 32MB */
+#else
+#define KERNEL_INITIAL_ORDER	24	/* 1<<24 = 16MB */
+#endif
 #define KERNEL_INITIAL_SIZE	(1 << KERNEL_INITIAL_ORDER)
 
 #if CONFIG_PGTABLE_LEVELS == 3
@@ -167,7 +171,7 @@
 #define _PAGE_NO_CACHE_BIT 24   /* (0x080) Uncached Page (U bit) */
 #define _PAGE_ACCESSED_BIT 23   /* (0x100) Software: Page Accessed */
 #define _PAGE_PRESENT_BIT  22   /* (0x200) Software: translation valid */
-/* bit 21 was formerly the FLUSH bit but is now unused */
+#define _PAGE_HPAGE_BIT    21   /* (0x400) Software: Huge Page */
 #define _PAGE_USER_BIT     20   /* (0x800) Software: User accessible page */
 
 /* N.B. The bits are defined in terms of a 32 bit word above, so the */
@@ -194,6 +198,7 @@
 #define _PAGE_NO_CACHE (1 << xlate_pabit(_PAGE_NO_CACHE_BIT))
 #define _PAGE_ACCESSED (1 << xlate_pabit(_PAGE_ACCESSED_BIT))
 #define _PAGE_PRESENT  (1 << xlate_pabit(_PAGE_PRESENT_BIT))
+#define _PAGE_HUGE     (1 << xlate_pabit(_PAGE_HPAGE_BIT))
 #define _PAGE_USER     (1 << xlate_pabit(_PAGE_USER_BIT))
 
 #define _PAGE_TABLE	(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE |  _PAGE_DIRTY | _PAGE_ACCESSED)
@@ -217,7 +222,7 @@
 #define PxD_FLAG_VALID    (1 << xlate_pabit(_PxD_VALID_BIT))
 #define PxD_FLAG_MASK     (0xf)
 #define PxD_FLAG_SHIFT    (4)
-#define PxD_VALUE_SHIFT   (8) /* (PAGE_SHIFT-PxD_FLAG_SHIFT) */
+#define PxD_VALUE_SHIFT   (PFN_PTE_SHIFT-PxD_FLAG_SHIFT)
 
 #ifndef __ASSEMBLY__
 
@@ -363,6 +368,19 @@
 static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 
 /*
+ * Huge pte definitions.
+ */
+#ifdef CONFIG_HUGETLB_PAGE
+#define pte_huge(pte)           (pte_val(pte) & _PAGE_HUGE)
+#define pte_mkhuge(pte)         (__pte(pte_val(pte) | \
+				 (parisc_requires_coherency() ? 0 : _PAGE_HUGE)))
+#else
+#define pte_huge(pte)           (0)
+#define pte_mkhuge(pte)         (pte)
+#endif
+
+
+/*
  * Conversion functions: convert a page and protection to a page entry,
  * and a page entry and page directory to the page they refer to.
  */
@@ -410,8 +428,9 @@
 /* Find an entry in the second-level page table.. */
 
 #if CONFIG_PGTABLE_LEVELS == 3
+#define pmd_index(addr)         (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
 #define pmd_offset(dir,address) \
-((pmd_t *) pgd_page_vaddr(*(dir)) + (((address)>>PMD_SHIFT) & (PTRS_PER_PMD-1)))
+((pmd_t *) pgd_page_vaddr(*(dir)) + pmd_index(address))
 #else
 #define pmd_offset(dir,addr) ((pmd_t *) dir)
 #endif
diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h
index 54adb60..7e759ec 100644
--- a/arch/parisc/include/asm/processor.h
+++ b/arch/parisc/include/asm/processor.h
@@ -192,33 +192,6 @@
  */
 typedef unsigned int elf_caddr_t;
 
-#define start_thread_som(regs, new_pc, new_sp) do {	\
-	unsigned long *sp = (unsigned long *)new_sp;	\
-	__u32 spaceid = (__u32)current->mm->context;	\
-	unsigned long pc = (unsigned long)new_pc;	\
-	/* offset pc for priv. level */			\
-	pc |= 3;					\
-							\
-	regs->iasq[0] = spaceid;			\
-	regs->iasq[1] = spaceid;			\
-	regs->iaoq[0] = pc;				\
-	regs->iaoq[1] = pc + 4;                         \
-	regs->sr[2] = LINUX_GATEWAY_SPACE;              \
-	regs->sr[3] = 0xffff;				\
-	regs->sr[4] = spaceid;				\
-	regs->sr[5] = spaceid;				\
-	regs->sr[6] = spaceid;				\
-	regs->sr[7] = spaceid;				\
-	regs->gr[ 0] = USER_PSW;                        \
-	regs->gr[30] = ((new_sp)+63)&~63;		\
-	regs->gr[31] = pc;				\
-							\
-	get_user(regs->gr[26],&sp[0]);			\
-	get_user(regs->gr[25],&sp[-1]); 		\
-	get_user(regs->gr[24],&sp[-2]); 		\
-	get_user(regs->gr[23],&sp[-3]); 		\
-} while(0)
-
 /* The ELF abi wants things done a "wee bit" differently than
  * som does.  Supporting this behavior here avoids
  * having our own version of create_elf_tables.
diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h
index ecc3ae1..dd4d187 100644
--- a/arch/parisc/include/uapi/asm/mman.h
+++ b/arch/parisc/include/uapi/asm/mman.h
@@ -49,16 +49,6 @@
 #define MADV_DONTFORK	10		/* don't inherit across fork */
 #define MADV_DOFORK	11		/* do inherit across fork */
 
-/* The range 12-64 is reserved for page size specification. */
-#define MADV_4K_PAGES   12              /* Use 4K pages  */
-#define MADV_16K_PAGES  14              /* Use 16K pages */
-#define MADV_64K_PAGES  16              /* Use 64K pages */
-#define MADV_256K_PAGES 18              /* Use 256K pages */
-#define MADV_1M_PAGES   20              /* Use 1 Megabyte pages */
-#define MADV_4M_PAGES   22              /* Use 4 Megabyte pages */
-#define MADV_16M_PAGES  24              /* Use 16 Megabyte pages */
-#define MADV_64M_PAGES  26              /* Use 64 Megabyte pages */
-
 #define MADV_MERGEABLE   65		/* KSM may merge identical pages */
 #define MADV_UNMERGEABLE 66		/* KSM may not merge identical pages */
 
diff --git a/arch/parisc/include/uapi/asm/unistd.h b/arch/parisc/include/uapi/asm/unistd.h
index 3317038..35bdccb 100644
--- a/arch/parisc/include/uapi/asm/unistd.h
+++ b/arch/parisc/include/uapi/asm/unistd.h
@@ -360,8 +360,9 @@
 #define __NR_execveat		(__NR_Linux + 342)
 #define __NR_membarrier		(__NR_Linux + 343)
 #define __NR_userfaultfd	(__NR_Linux + 344)
+#define __NR_mlock2		(__NR_Linux + 345)
 
-#define __NR_Linux_syscalls	(__NR_userfaultfd + 1)
+#define __NR_Linux_syscalls	(__NR_mlock2 + 1)
 
 
 #define __IGNORE_select		/* newselect */
diff --git a/arch/parisc/kernel/asm-offsets.c b/arch/parisc/kernel/asm-offsets.c
index 59001ce..d2f6257 100644
--- a/arch/parisc/kernel/asm-offsets.c
+++ b/arch/parisc/kernel/asm-offsets.c
@@ -290,6 +290,14 @@
 	DEFINE(ASM_PFN_PTE_SHIFT, PFN_PTE_SHIFT);
 	DEFINE(ASM_PT_INITIAL, PT_INITIAL);
 	BLANK();
+	/* HUGEPAGE_SIZE is only used in vmlinux.lds.S to align kernel text
+	 * and kernel data on physical huge pages */
+#ifdef CONFIG_HUGETLB_PAGE
+	DEFINE(HUGEPAGE_SIZE, 1UL << REAL_HPAGE_SHIFT);
+#else
+	DEFINE(HUGEPAGE_SIZE, PAGE_SIZE);
+#endif
+	BLANK();
 	DEFINE(EXCDATA_IP, offsetof(struct exception_data, fault_ip));
 	DEFINE(EXCDATA_SPACE, offsetof(struct exception_data, fault_space));
 	DEFINE(EXCDATA_ADDR, offsetof(struct exception_data, fault_addr));
diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S
index c5ef408..623496c 100644
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -502,21 +502,38 @@
 	STREG		\pte,0(\ptp)
 	.endm
 
+	/* We have (depending on the page size):
+	 * - 38 to 52-bit Physical Page Number
+	 * - 12 to 26-bit page offset
+	 */
 	/* bitshift difference between a PFN (based on kernel's PAGE_SIZE)
 	 * to a CPU TLB 4k PFN (4k => 12 bits to shift) */
-	#define PAGE_ADD_SHIFT  (PAGE_SHIFT-12)
+	#define PAGE_ADD_SHIFT		(PAGE_SHIFT-12)
+	#define PAGE_ADD_HUGE_SHIFT	(REAL_HPAGE_SHIFT-12)
 
 	/* Drop prot bits and convert to page addr for iitlbt and idtlbt */
-	.macro		convert_for_tlb_insert20 pte
+	.macro		convert_for_tlb_insert20 pte,tmp
+#ifdef CONFIG_HUGETLB_PAGE
+	copy		\pte,\tmp
+	extrd,u		\tmp,(63-ASM_PFN_PTE_SHIFT)+(63-58)+PAGE_ADD_SHIFT,\
+				64-PAGE_SHIFT-PAGE_ADD_SHIFT,\pte
+
+	depdi		_PAGE_SIZE_ENCODING_DEFAULT,63,\
+				(63-58)+PAGE_ADD_SHIFT,\pte
+	extrd,u,*=	\tmp,_PAGE_HPAGE_BIT+32,1,%r0
+	depdi		_HUGE_PAGE_SIZE_ENCODING_DEFAULT,63,\
+				(63-58)+PAGE_ADD_HUGE_SHIFT,\pte
+#else /* Huge pages disabled */
 	extrd,u		\pte,(63-ASM_PFN_PTE_SHIFT)+(63-58)+PAGE_ADD_SHIFT,\
 				64-PAGE_SHIFT-PAGE_ADD_SHIFT,\pte
 	depdi		_PAGE_SIZE_ENCODING_DEFAULT,63,\
 				(63-58)+PAGE_ADD_SHIFT,\pte
+#endif
 	.endm
 
 	/* Convert the pte and prot to tlb insertion values.  How
 	 * this happens is quite subtle, read below */
-	.macro		make_insert_tlb	spc,pte,prot
+	.macro		make_insert_tlb	spc,pte,prot,tmp
 	space_to_prot   \spc \prot        /* create prot id from space */
 	/* The following is the real subtlety.  This is depositing
 	 * T <-> _PAGE_REFTRAP
@@ -553,7 +570,7 @@
 	depdi		1,12,1,\prot
 
 	/* Drop prot bits and convert to page addr for iitlbt and idtlbt */
-	convert_for_tlb_insert20 \pte
+	convert_for_tlb_insert20 \pte \tmp
 	.endm
 
 	/* Identical macro to make_insert_tlb above, except it
@@ -646,17 +663,12 @@
 
 
 	/*
-	 * Align fault_vector_20 on 4K boundary so that both
-	 * fault_vector_11 and fault_vector_20 are on the
-	 * same page. This is only necessary as long as we
-	 * write protect the kernel text, which we may stop
-	 * doing once we use large page translations to cover
-	 * the static part of the kernel address space.
+	 * Fault_vectors are architecturally required to be aligned on a 2K
+	 * boundary
 	 */
 
 	.text
-
-	.align 4096
+	.align 2048
 
 ENTRY(fault_vector_20)
 	/* First vector is invalid (0) */
@@ -1147,7 +1159,7 @@
 	tlb_lock	spc,ptp,pte,t0,t1,dtlb_check_alias_20w
 	update_accessed	ptp,pte,t0,t1
 
-	make_insert_tlb	spc,pte,prot
+	make_insert_tlb	spc,pte,prot,t1
 	
 	idtlbt          pte,prot
 
@@ -1173,7 +1185,7 @@
 	tlb_lock	spc,ptp,pte,t0,t1,nadtlb_check_alias_20w
 	update_accessed	ptp,pte,t0,t1
 
-	make_insert_tlb	spc,pte,prot
+	make_insert_tlb	spc,pte,prot,t1
 
 	idtlbt          pte,prot
 
@@ -1267,7 +1279,7 @@
 	tlb_lock	spc,ptp,pte,t0,t1,dtlb_check_alias_20
 	update_accessed	ptp,pte,t0,t1
 
-	make_insert_tlb	spc,pte,prot
+	make_insert_tlb	spc,pte,prot,t1
 
 	f_extend	pte,t1
 
@@ -1295,7 +1307,7 @@
 	tlb_lock	spc,ptp,pte,t0,t1,nadtlb_check_alias_20
 	update_accessed	ptp,pte,t0,t1
 
-	make_insert_tlb	spc,pte,prot
+	make_insert_tlb	spc,pte,prot,t1
 
 	f_extend	pte,t1
 	
@@ -1404,7 +1416,7 @@
 	tlb_lock	spc,ptp,pte,t0,t1,itlb_fault
 	update_accessed	ptp,pte,t0,t1
 
-	make_insert_tlb	spc,pte,prot
+	make_insert_tlb	spc,pte,prot,t1
 	
 	iitlbt          pte,prot
 
@@ -1428,7 +1440,7 @@
 	tlb_lock	spc,ptp,pte,t0,t1,naitlb_check_alias_20w
 	update_accessed	ptp,pte,t0,t1
 
-	make_insert_tlb	spc,pte,prot
+	make_insert_tlb	spc,pte,prot,t1
 
 	iitlbt          pte,prot
 
@@ -1514,7 +1526,7 @@
 	tlb_lock	spc,ptp,pte,t0,t1,itlb_fault
 	update_accessed	ptp,pte,t0,t1
 
-	make_insert_tlb	spc,pte,prot
+	make_insert_tlb	spc,pte,prot,t1
 
 	f_extend	pte,t1
 
@@ -1534,7 +1546,7 @@
 	tlb_lock	spc,ptp,pte,t0,t1,naitlb_check_alias_20
 	update_accessed	ptp,pte,t0,t1
 
-	make_insert_tlb	spc,pte,prot
+	make_insert_tlb	spc,pte,prot,t1
 
 	f_extend	pte,t1
 
@@ -1566,7 +1578,7 @@
 	tlb_lock	spc,ptp,pte,t0,t1,dbit_fault
 	update_dirty	ptp,pte,t1
 
-	make_insert_tlb	spc,pte,prot
+	make_insert_tlb	spc,pte,prot,t1
 		
 	idtlbt          pte,prot
 
@@ -1610,7 +1622,7 @@
 	tlb_lock	spc,ptp,pte,t0,t1,dbit_fault
 	update_dirty	ptp,pte,t1
 
-	make_insert_tlb	spc,pte,prot
+	make_insert_tlb	spc,pte,prot,t1
 
 	f_extend	pte,t1
 	
diff --git a/arch/parisc/kernel/head.S b/arch/parisc/kernel/head.S
index e7d6452..75aa0db 100644
--- a/arch/parisc/kernel/head.S
+++ b/arch/parisc/kernel/head.S
@@ -69,7 +69,7 @@
 	stw,ma          %arg2,4(%r1)
 	stw,ma          %arg3,4(%r1)
 
-	/* Initialize startup VM. Just map first 8/16 MB of memory */
+	/* Initialize startup VM. Just map first 16/32 MB of memory */
 	load32		PA(swapper_pg_dir),%r4
 	mtctl		%r4,%cr24	/* Initialize kernel root pointer */
 	mtctl		%r4,%cr25	/* Initialize user root pointer */
@@ -107,7 +107,7 @@
 	/* Now initialize the PTEs themselves.  We use RWX for
 	 * everything ... it will get remapped correctly later */
 	ldo		0+_PAGE_KERNEL_RWX(%r0),%r3 /* Hardwired 0 phys addr start */
-	ldi		(1<<(KERNEL_INITIAL_ORDER-PAGE_SHIFT)),%r11 /* PFN count */
+	load32		(1<<(KERNEL_INITIAL_ORDER-PAGE_SHIFT)),%r11 /* PFN count */
 	load32		PA(pg0),%r1
 
 $pgt_fill_loop:
diff --git a/arch/parisc/kernel/pci.c b/arch/parisc/kernel/pci.c
index 64f2764..c99f3dd 100644
--- a/arch/parisc/kernel/pci.c
+++ b/arch/parisc/kernel/pci.c
@@ -171,24 +171,6 @@
 }
 
 
-void __init pcibios_init_bus(struct pci_bus *bus)
-{
-	struct pci_dev *dev = bus->self;
-	unsigned short bridge_ctl;
-
-	/* We deal only with pci controllers and pci-pci bridges. */
-	if (!dev || (dev->class >> 8) != PCI_CLASS_BRIDGE_PCI)
-		return;
-
-	/* PCI-PCI bridge - set the cache line and default latency
-	   (32) for primary and secondary buses. */
-	pci_write_config_byte(dev, PCI_SEC_LATENCY_TIMER, 32);
-
-	pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &bridge_ctl);
-	bridge_ctl |= PCI_BRIDGE_CTL_PARITY | PCI_BRIDGE_CTL_SERR;
-	pci_write_config_word(dev, PCI_BRIDGE_CONTROL, bridge_ctl);
-}
-
 /*
  * pcibios align resources() is called every time generic PCI code
  * wants to generate a new address. The process of looking for
diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c
index 72a3c65..f7ea626 100644
--- a/arch/parisc/kernel/setup.c
+++ b/arch/parisc/kernel/setup.c
@@ -130,7 +130,16 @@
 	printk(KERN_INFO "The 32-bit Kernel has started...\n");
 #endif
 
-	printk(KERN_INFO "Default page size is %dKB.\n", (int)(PAGE_SIZE / 1024));
+	printk(KERN_INFO "Kernel default page size is %d KB. Huge pages ",
+		(int)(PAGE_SIZE / 1024));
+#ifdef CONFIG_HUGETLB_PAGE
+	printk(KERN_CONT "enabled with %d MB physical and %d MB virtual size",
+		 1 << (REAL_HPAGE_SHIFT - 20), 1 << (HPAGE_SHIFT - 20));
+#else
+	printk(KERN_CONT "disabled");
+#endif
+	printk(KERN_CONT ".\n");
+
 
 	pdc_console_init();
 
@@ -377,6 +386,7 @@
 void start_parisc(void)
 {
 	extern void start_kernel(void);
+	extern void early_trap_init(void);
 
 	int ret, cpunum;
 	struct pdc_coproc_cfg coproc_cfg;
@@ -397,6 +407,8 @@
 		panic("must have an fpu to boot linux");
 	}
 
+	early_trap_init(); /* initialize checksum of fault_vector */
+
 	start_kernel();
 	// not reached
 }
diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S
index 0b8d26d..3fbd725 100644
--- a/arch/parisc/kernel/syscall.S
+++ b/arch/parisc/kernel/syscall.S
@@ -369,7 +369,7 @@
 	ldo	-16(%r30),%r29			/* Reference param save area */
 #endif
 	ldo	TASK_REGS(%r1),%r26
-	bl	do_syscall_trace_exit,%r2
+	BL	do_syscall_trace_exit,%r2
 	STREG   %r28,TASK_PT_GR28(%r1)          /* save return value now */
 	ldo     -THREAD_SZ_ALGN-FRAME_SIZE(%r30),%r1      /* get task ptr */
 	LDREG	TI_TASK(%r1), %r1
@@ -390,7 +390,7 @@
 #ifdef CONFIG_64BIT
 	ldo	-16(%r30),%r29			/* Reference param save area */
 #endif
-	bl	do_syscall_trace_exit,%r2
+	BL	do_syscall_trace_exit,%r2
 	ldo	TASK_REGS(%r1),%r26
 
 	ldil	L%syscall_exit_rfi,%r1
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index 78c3ef8..d4ffcfb 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -440,6 +440,7 @@
 	ENTRY_COMP(execveat)
 	ENTRY_SAME(membarrier)
 	ENTRY_SAME(userfaultfd)
+	ENTRY_SAME(mlock2)		/* 345 */
 
 
 .ifne (. - 90b) - (__NR_Linux_syscalls * (91b - 90b))
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index b99b39f..553b098 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -807,7 +807,7 @@
 }
 
 
-int __init check_ivt(void *iva)
+void __init initialize_ivt(const void *iva)
 {
 	extern u32 os_hpmc_size;
 	extern const u32 os_hpmc[];
@@ -818,8 +818,8 @@
 	u32 *hpmcp;
 	u32 length;
 
-	if (strcmp((char *)iva, "cows can fly"))
-		return -1;
+	if (strcmp((const char *)iva, "cows can fly"))
+		panic("IVT invalid");
 
 	ivap = (u32 *)iva;
 
@@ -839,28 +839,23 @@
 	    check += ivap[i];
 
 	ivap[5] = -check;
-
-	return 0;
 }
 	
+
+/* early_trap_init() is called before we set up kernel mappings and
+ * write-protect the kernel */
+void  __init early_trap_init(void)
+{
+	extern const void fault_vector_20;
+
 #ifndef CONFIG_64BIT
-extern const void fault_vector_11;
+	extern const void fault_vector_11;
+	initialize_ivt(&fault_vector_11);
 #endif
-extern const void fault_vector_20;
+
+	initialize_ivt(&fault_vector_20);
+}
 
 void __init trap_init(void)
 {
-	void *iva;
-
-	if (boot_cpu_data.cpu_type >= pcxu)
-		iva = (void *) &fault_vector_20;
-	else
-#ifdef CONFIG_64BIT
-		panic("Can't boot 64-bit OS on PA1.1 processor!");
-#else
-		iva = (void *) &fault_vector_11;
-#endif
-
-	if (check_ivt(iva))
-		panic("IVT invalid");
 }
diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S
index 0dacc5c..308f290 100644
--- a/arch/parisc/kernel/vmlinux.lds.S
+++ b/arch/parisc/kernel/vmlinux.lds.S
@@ -60,7 +60,7 @@
 		EXIT_DATA
 	}
 	PERCPU_SECTION(8)
-	. = ALIGN(PAGE_SIZE);
+	. = ALIGN(HUGEPAGE_SIZE);
 	__init_end = .;
 	/* freed after init ends here */
 
@@ -116,7 +116,7 @@
 	 * that we can properly leave these
 	 * as writable
 	 */
-	. = ALIGN(PAGE_SIZE);
+	. = ALIGN(HUGEPAGE_SIZE);
 	data_start = .;
 
 	EXCEPTION_TABLE(8)
@@ -135,8 +135,11 @@
 	_edata = .;
 
 	/* BSS */
-	BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 8)
+	BSS_SECTION(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE)
 
+	/* bootmap is allocated in setup_bootmem() directly behind bss. */
+
+	. = ALIGN(HUGEPAGE_SIZE);
 	_end = . ;
 
 	STABS_DEBUG
diff --git a/arch/parisc/mm/Makefile b/arch/parisc/mm/Makefile
index 758ceef..134393d 100644
--- a/arch/parisc/mm/Makefile
+++ b/arch/parisc/mm/Makefile
@@ -3,3 +3,4 @@
 #
 
 obj-y	 := init.o fault.o ioremap.o
+obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c
new file mode 100644
index 0000000..f6fdc77
--- /dev/null
+++ b/arch/parisc/mm/hugetlbpage.c
@@ -0,0 +1,161 @@
+/*
+ * PARISC64 Huge TLB page support.
+ *
+ * This parisc implementation is heavily based on the SPARC and x86 code.
+ *
+ * Copyright (C) 2015 Helge Deller <deller@gmx.de>
+ */
+
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+#include <linux/pagemap.h>
+#include <linux/sysctl.h>
+
+#include <asm/mman.h>
+#include <asm/pgalloc.h>
+#include <asm/tlb.h>
+#include <asm/tlbflush.h>
+#include <asm/cacheflush.h>
+#include <asm/mmu_context.h>
+
+
+unsigned long
+hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
+		unsigned long len, unsigned long pgoff, unsigned long flags)
+{
+	struct hstate *h = hstate_file(file);
+
+	if (len & ~huge_page_mask(h))
+		return -EINVAL;
+	if (len > TASK_SIZE)
+		return -ENOMEM;
+
+	if (flags & MAP_FIXED)
+		if (prepare_hugepage_range(file, addr, len))
+			return -EINVAL;
+
+	if (addr)
+		addr = ALIGN(addr, huge_page_size(h));
+
+	/* we need to make sure the colouring is OK */
+	return arch_get_unmapped_area(file, addr, len, pgoff, flags);
+}
+
+
+pte_t *huge_pte_alloc(struct mm_struct *mm,
+			unsigned long addr, unsigned long sz)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte = NULL;
+
+	/* We must align the address, because our caller will run
+	 * set_huge_pte_at() on whatever we return, which writes out
+	 * all of the sub-ptes for the hugepage range.  So we have
+	 * to give it the first such sub-pte.
+	 */
+	addr &= HPAGE_MASK;
+
+	pgd = pgd_offset(mm, addr);
+	pud = pud_alloc(mm, pgd, addr);
+	if (pud) {
+		pmd = pmd_alloc(mm, pud, addr);
+		if (pmd)
+			pte = pte_alloc_map(mm, NULL, pmd, addr);
+	}
+	return pte;
+}
+
+pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte = NULL;
+
+	addr &= HPAGE_MASK;
+
+	pgd = pgd_offset(mm, addr);
+	if (!pgd_none(*pgd)) {
+		pud = pud_offset(pgd, addr);
+		if (!pud_none(*pud)) {
+			pmd = pmd_offset(pud, addr);
+			if (!pmd_none(*pmd))
+				pte = pte_offset_map(pmd, addr);
+		}
+	}
+	return pte;
+}
+
+/* Purge data and instruction TLB entries.  Must be called holding
+ * the pa_tlb_lock.  The TLB purge instructions are slow on SMP
+ * machines since the purge must be broadcast to all CPUs.
+ */
+static inline void purge_tlb_entries_huge(struct mm_struct *mm, unsigned long addr)
+{
+	int i;
+
+	/* We may use multiple physical huge pages (e.g. 2x1 MB) to emulate
+	 * Linux standard huge pages (e.g. 2 MB) */
+	BUILD_BUG_ON(REAL_HPAGE_SHIFT > HPAGE_SHIFT);
+
+	addr &= HPAGE_MASK;
+	addr |= _HUGE_PAGE_SIZE_ENCODING_DEFAULT;
+
+	for (i = 0; i < (1 << (HPAGE_SHIFT-REAL_HPAGE_SHIFT)); i++) {
+		mtsp(mm->context, 1);
+		pdtlb(addr);
+		if (unlikely(split_tlb))
+			pitlb(addr);
+		addr += (1UL << REAL_HPAGE_SHIFT);
+	}
+}
+
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+		     pte_t *ptep, pte_t entry)
+{
+	unsigned long addr_start;
+	int i;
+
+	addr &= HPAGE_MASK;
+	addr_start = addr;
+
+	for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
+		/* Directly write pte entry.  We could call set_pte_at(mm, addr, ptep, entry)
+		 * instead, but then we get double locking on pa_tlb_lock. */
+		*ptep = entry;
+		ptep++;
+
+		/* Drop the PAGE_SIZE/non-huge tlb entry */
+		purge_tlb_entries(mm, addr);
+
+		addr += PAGE_SIZE;
+		pte_val(entry) += PAGE_SIZE;
+	}
+
+	purge_tlb_entries_huge(mm, addr_start);
+}
+
+
+pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep)
+{
+	pte_t entry;
+
+	entry = *ptep;
+	set_huge_pte_at(mm, addr, ptep, __pte(0));
+
+	return entry;
+}
+
+int pmd_huge(pmd_t pmd)
+{
+	return 0;
+}
+
+int pud_huge(pud_t pud)
+{
+	return 0;
+}
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index c5fec48..1b366c4 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -409,15 +409,11 @@
 	unsigned long vaddr;
 	unsigned long ro_start;
 	unsigned long ro_end;
-	unsigned long fv_addr;
-	unsigned long gw_addr;
-	extern const unsigned long fault_vector_20;
-	extern void * const linux_gateway_page;
+	unsigned long kernel_end;
 
 	ro_start = __pa((unsigned long)_text);
 	ro_end   = __pa((unsigned long)&data_start);
-	fv_addr  = __pa((unsigned long)&fault_vector_20) & PAGE_MASK;
-	gw_addr  = __pa((unsigned long)&linux_gateway_page) & PAGE_MASK;
+	kernel_end  = __pa((unsigned long)&_end);
 
 	end_paddr = start_paddr + size;
 
@@ -475,24 +471,25 @@
 			for (tmp2 = start_pte; tmp2 < PTRS_PER_PTE; tmp2++, pg_table++) {
 				pte_t pte;
 
-				/*
-				 * Map the fault vector writable so we can
-				 * write the HPMC checksum.
-				 */
 				if (force)
 					pte =  __mk_pte(address, pgprot);
-				else if (parisc_text_address(vaddr) &&
-					 address != fv_addr)
+				else if (parisc_text_address(vaddr)) {
 					pte = __mk_pte(address, PAGE_KERNEL_EXEC);
+					if (address >= ro_start && address < kernel_end)
+						pte = pte_mkhuge(pte);
+				}
 				else
 #if defined(CONFIG_PARISC_PAGE_SIZE_4KB)
-				if (address >= ro_start && address < ro_end
-							&& address != fv_addr
-							&& address != gw_addr)
-					pte = __mk_pte(address, PAGE_KERNEL_RO);
-				else
+				if (address >= ro_start && address < ro_end) {
+					pte = __mk_pte(address, PAGE_KERNEL_EXEC);
+					pte = pte_mkhuge(pte);
+				} else
 #endif
+				{
 					pte = __mk_pte(address, pgprot);
+					if (address >= ro_start && address < kernel_end)
+						pte = pte_mkhuge(pte);
+				}
 
 				if (address >= end_paddr) {
 					if (force)
@@ -536,15 +533,12 @@
 
 	/* force the kernel to see the new TLB entries */
 	__flush_tlb_range(0, init_begin, init_end);
-	/* Attempt to catch anyone trying to execute code here
-	 * by filling the page with BRK insns.
-	 */
-	memset((void *)init_begin, 0x00, init_end - init_begin);
+
 	/* finally dump all the instructions which were cached, since the
 	 * pages are no-longer executable */
 	flush_icache_range(init_begin, init_end);
 	
-	free_initmem_default(-1);
+	free_initmem_default(POISON_FREE_INITMEM);
 
 	/* set up a new led state on systems shipped LED State panel */
 	pdc_chassis_send_status(PDC_CHASSIS_DIRECT_BCOMPLETE);
@@ -728,8 +722,8 @@
 		unsigned long size;
 
 		start_paddr = pmem_ranges[range].start_pfn << PAGE_SHIFT;
-		end_paddr = start_paddr + (pmem_ranges[range].pages << PAGE_SHIFT);
 		size = pmem_ranges[range].pages << PAGE_SHIFT;
+		end_paddr = start_paddr + size;
 
 		map_pages((unsigned long)__va(start_paddr), start_paddr,
 			  size, PAGE_KERNEL, 0);
diff --git a/arch/powerpc/boot/dts/sbc8641d.dts b/arch/powerpc/boot/dts/sbc8641d.dts
index 631ede7..68f0ed7 100644
--- a/arch/powerpc/boot/dts/sbc8641d.dts
+++ b/arch/powerpc/boot/dts/sbc8641d.dts
@@ -227,23 +227,15 @@
 				reg = <0x520 0x20>;
 
 				phy0: ethernet-phy@1f {
-					interrupt-parent = <&mpic>;
-					interrupts = <10 1>;
 					reg = <0x1f>;
 				};
 				phy1: ethernet-phy@0 {
-					interrupt-parent = <&mpic>;
-					interrupts = <10 1>;
 					reg = <0>;
 				};
 				phy2: ethernet-phy@1 {
-					interrupt-parent = <&mpic>;
-					interrupts = <10 1>;
 					reg = <1>;
 				};
 				phy3: ethernet-phy@2 {
-					interrupt-parent = <&mpic>;
-					interrupts = <10 1>;
 					reg = <2>;
 				};
 				tbi0: tbi-phy@11 {
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index a908ada..2220f7a 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -108,6 +108,7 @@
 #define MSR_TS_T	__MASK(MSR_TS_T_LG)	/*  Transaction Transactional */
 #define MSR_TS_MASK	(MSR_TS_T | MSR_TS_S)   /* Transaction State bits */
 #define MSR_TM_ACTIVE(x) (((x) & MSR_TS_MASK) != 0) /* Transaction active? */
+#define MSR_TM_RESV(x) (((x) & MSR_TS_MASK) == MSR_TS_MASK) /* Reserved */
 #define MSR_TM_TRANSACTIONAL(x)	(((x) & MSR_TS_MASK) == MSR_TS_T)
 #define MSR_TM_SUSPENDED(x)	(((x) & MSR_TS_MASK) == MSR_TS_S)
 
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index c9e26cb..f2b0b1b 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -382,3 +382,4 @@
 SYSCALL(shmdt)
 SYSCALL(shmget)
 COMPAT_SYS(shmctl)
+SYSCALL(mlock2)
diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index 6d8f802..4b6b8ac 100644
--- a/arch/powerpc/include/asm/unistd.h
+++ b/arch/powerpc/include/asm/unistd.h
@@ -12,7 +12,7 @@
 #include <uapi/asm/unistd.h>
 
 
-#define __NR_syscalls		378
+#define __NR_syscalls		379
 
 #define __NR__exit __NR_exit
 #define NR_syscalls	__NR_syscalls
diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h
index 81579e9..1effea5 100644
--- a/arch/powerpc/include/uapi/asm/unistd.h
+++ b/arch/powerpc/include/uapi/asm/unistd.h
@@ -400,5 +400,6 @@
 #define __NR_shmdt		375
 #define __NR_shmget		376
 #define __NR_shmctl		377
+#define __NR_mlock2		378
 
 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 80dfe89..8d14feb 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -590,16 +590,10 @@
 	eeh_ops->configure_bridge(pe);
 	eeh_pe_restore_bars(pe);
 
-	/*
-	 * If it's PHB PE, the frozen state on all available PEs should have
-	 * been cleared by the PHB reset. Otherwise, we unfreeze the PE and its
-	 * child PEs because they might be in frozen state.
-	 */
-	if (!(pe->type & EEH_PE_PHB)) {
-		rc = eeh_clear_pe_frozen_state(pe, false);
-		if (rc)
-			return rc;
-	}
+	/* Clear frozen state */
+	rc = eeh_clear_pe_frozen_state(pe, false);
+	if (rc)
+		return rc;
 
 	/* Give the system 5 seconds to finish running the user-space
 	 * hotplug shutdown scripts, e.g. ifdown for ethernet.  Yes,
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 75b6676..646bf4d 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -551,6 +551,24 @@
 		msr_diff &= MSR_FP | MSR_VEC | MSR_VSX | MSR_FE0 | MSR_FE1;
 	}
 
+	/*
+	 * Use the current MSR TM suspended bit to track if we have
+	 * checkpointed state outstanding.
+	 * On signal delivery, we'd normally reclaim the checkpointed
+	 * state to obtain stack pointer (see:get_tm_stackpointer()).
+	 * This will then directly return to userspace without going
+	 * through __switch_to(). However, if the stack frame is bad,
+	 * we need to exit this thread which calls __switch_to() which
+	 * will again attempt to reclaim the already saved tm state.
+	 * Hence we need to check that we've not already reclaimed
+	 * this state.
+	 * We do this using the current MSR, rather tracking it in
+	 * some specific thread_struct bit, as it has the additional
+	 * benifit of checking for a potential TM bad thing exception.
+	 */
+	if (!MSR_TM_SUSPENDED(mfmsr()))
+		return;
+
 	tm_reclaim(thr, thr->regs->msr, cause);
 
 	/* Having done the reclaim, we now have the checkpointed
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 0dbee46..ef7c24e 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -875,6 +875,15 @@
 		return 1;
 #endif /* CONFIG_SPE */
 
+	/* Get the top half of the MSR from the user context */
+	if (__get_user(msr_hi, &tm_sr->mc_gregs[PT_MSR]))
+		return 1;
+	msr_hi <<= 32;
+	/* If TM bits are set to the reserved value, it's an invalid context */
+	if (MSR_TM_RESV(msr_hi))
+		return 1;
+	/* Pull in the MSR TM bits from the user context */
+	regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr_hi & MSR_TS_MASK);
 	/* Now, recheckpoint.  This loads up all of the checkpointed (older)
 	 * registers, including FP and V[S]Rs.  After recheckpointing, the
 	 * transactional versions should be loaded.
@@ -884,11 +893,6 @@
 	current->thread.tm_texasr |= TEXASR_FS;
 	/* This loads the checkpointed FP/VEC state, if used */
 	tm_recheckpoint(&current->thread, msr);
-	/* Get the top half of the MSR */
-	if (__get_user(msr_hi, &tm_sr->mc_gregs[PT_MSR]))
-		return 1;
-	/* Pull in MSR TM from user context */
-	regs->msr = (regs->msr & ~MSR_TS_MASK) | ((msr_hi<<32) & MSR_TS_MASK);
 
 	/* This loads the speculative FP/VEC state, if used */
 	if (msr & MSR_FP) {
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index 20756df..c676ece 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -438,6 +438,10 @@
 
 	/* get MSR separately, transfer the LE bit if doing signal return */
 	err |= __get_user(msr, &sc->gp_regs[PT_MSR]);
+	/* Don't allow reserved mode. */
+	if (MSR_TM_RESV(msr))
+		return -EINVAL;
+
 	/* pull in MSR TM from user context */
 	regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr & MSR_TS_MASK);
 
diff --git a/arch/powerpc/platforms/powernv/opal-irqchip.c b/arch/powerpc/platforms/powernv/opal-irqchip.c
index 6ccfb6c..0a00e2a 100644
--- a/arch/powerpc/platforms/powernv/opal-irqchip.c
+++ b/arch/powerpc/platforms/powernv/opal-irqchip.c
@@ -43,11 +43,34 @@
 static unsigned int *opal_irqs;
 
 static void opal_handle_irq_work(struct irq_work *work);
-static __be64 last_outstanding_events;
+static u64 last_outstanding_events;
 static struct irq_work opal_event_irq_work = {
 	.func = opal_handle_irq_work,
 };
 
+void opal_handle_events(uint64_t events)
+{
+	int virq, hwirq = 0;
+	u64 mask = opal_event_irqchip.mask;
+
+	if (!in_irq() && (events & mask)) {
+		last_outstanding_events = events;
+		irq_work_queue(&opal_event_irq_work);
+		return;
+	}
+
+	while (events & mask) {
+		hwirq = fls64(events) - 1;
+		if (BIT_ULL(hwirq) & mask) {
+			virq = irq_find_mapping(opal_event_irqchip.domain,
+						hwirq);
+			if (virq)
+				generic_handle_irq(virq);
+		}
+		events &= ~BIT_ULL(hwirq);
+	}
+}
+
 static void opal_event_mask(struct irq_data *d)
 {
 	clear_bit(d->hwirq, &opal_event_irqchip.mask);
@@ -55,12 +78,12 @@
 
 static void opal_event_unmask(struct irq_data *d)
 {
+	__be64 events;
+
 	set_bit(d->hwirq, &opal_event_irqchip.mask);
 
-	opal_poll_events(&last_outstanding_events);
-	if (last_outstanding_events & opal_event_irqchip.mask)
-		/* Need to retrigger the interrupt */
-		irq_work_queue(&opal_event_irq_work);
+	opal_poll_events(&events);
+	opal_handle_events(be64_to_cpu(events));
 }
 
 static int opal_event_set_type(struct irq_data *d, unsigned int flow_type)
@@ -96,29 +119,6 @@
 	return 0;
 }
 
-void opal_handle_events(uint64_t events)
-{
-	int virq, hwirq = 0;
-	u64 mask = opal_event_irqchip.mask;
-
-	if (!in_irq() && (events & mask)) {
-		last_outstanding_events = events;
-		irq_work_queue(&opal_event_irq_work);
-		return;
-	}
-
-	while (events & mask) {
-		hwirq = fls64(events) - 1;
-		if (BIT_ULL(hwirq) & mask) {
-			virq = irq_find_mapping(opal_event_irqchip.domain,
-						hwirq);
-			if (virq)
-				generic_handle_irq(virq);
-		}
-		events &= ~BIT_ULL(hwirq);
-	}
-}
-
 static irqreturn_t opal_interrupt(int irq, void *data)
 {
 	__be64 events;
@@ -131,7 +131,7 @@
 
 static void opal_handle_irq_work(struct irq_work *work)
 {
-	opal_handle_events(be64_to_cpu(last_outstanding_events));
+	opal_handle_events(last_outstanding_events);
 }
 
 static int opal_event_match(struct irq_domain *h, struct device_node *node,
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 373e323..6a75352 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -1030,8 +1030,7 @@
 				   src_id, 0);
 
 	/* sending vcpu invalid */
-	if (src_id >= KVM_MAX_VCPUS ||
-	    kvm_get_vcpu(vcpu->kvm, src_id) == NULL)
+	if (kvm_get_vcpu_by_id(vcpu->kvm, src_id) == NULL)
 		return -EINVAL;
 
 	if (sclp.has_sigpif)
@@ -1110,6 +1109,10 @@
 	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY,
 				   irq->u.emerg.code, 0);
 
+	/* sending vcpu invalid */
+	if (kvm_get_vcpu_by_id(vcpu->kvm, irq->u.emerg.code) == NULL)
+		return -EINVAL;
+
 	set_bit(irq->u.emerg.code, li->sigp_emerg_pending);
 	set_bit(IRQ_PEND_EXT_EMERGENCY, &li->pending_irqs);
 	atomic_or(CPUSTAT_EXT_INT, li->cpuflags);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 8fe2f1c..8465892 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -342,12 +342,16 @@
 		r = 0;
 		break;
 	case KVM_CAP_S390_VECTOR_REGISTERS:
-		if (MACHINE_HAS_VX) {
+		mutex_lock(&kvm->lock);
+		if (atomic_read(&kvm->online_vcpus)) {
+			r = -EBUSY;
+		} else if (MACHINE_HAS_VX) {
 			set_kvm_facility(kvm->arch.model.fac->mask, 129);
 			set_kvm_facility(kvm->arch.model.fac->list, 129);
 			r = 0;
 		} else
 			r = -EINVAL;
+		mutex_unlock(&kvm->lock);
 		VM_EVENT(kvm, 3, "ENABLE: CAP_S390_VECTOR_REGISTERS %s",
 			 r ? "(not available)" : "(success)");
 		break;
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 77191b8..d76b51c 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -660,7 +660,7 @@
 
 	kvm_s390_get_regs_rre(vcpu, &reg1, &reg2);
 
-	if (!MACHINE_HAS_PFMF)
+	if (!test_kvm_facility(vcpu->kvm, 8))
 		return kvm_s390_inject_program_int(vcpu, PGM_OPERATION);
 
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index da690b6..77c22d6 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -291,12 +291,8 @@
 			   u16 cpu_addr, u32 parameter, u64 *status_reg)
 {
 	int rc;
-	struct kvm_vcpu *dst_vcpu;
+	struct kvm_vcpu *dst_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, cpu_addr);
 
-	if (cpu_addr >= KVM_MAX_VCPUS)
-		return SIGP_CC_NOT_OPERATIONAL;
-
-	dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
 	if (!dst_vcpu)
 		return SIGP_CC_NOT_OPERATIONAL;
 
@@ -478,7 +474,7 @@
 	trace_kvm_s390_handle_sigp_pei(vcpu, order_code, cpu_addr);
 
 	if (order_code == SIGP_EXTERNAL_CALL) {
-		dest_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
+		dest_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, cpu_addr);
 		BUG_ON(dest_vcpu == NULL);
 
 		kvm_s390_vcpu_wakeup(dest_vcpu);
diff --git a/arch/sh/include/uapi/asm/unistd_64.h b/arch/sh/include/uapi/asm/unistd_64.h
index e6820c8..47ebd5b 100644
--- a/arch/sh/include/uapi/asm/unistd_64.h
+++ b/arch/sh/include/uapi/asm/unistd_64.h
@@ -278,7 +278,7 @@
 #define __NR_fsetxattr		256
 #define __NR_getxattr		257
 #define __NR_lgetxattr		258
-#define __NR_fgetxattr		269
+#define __NR_fgetxattr		259
 #define __NR_listxattr		260
 #define __NR_llistxattr		261
 #define __NR_flistxattr		262
diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c
index 7cfd7f1..4dca183 100644
--- a/arch/sh/kernel/perf_event.c
+++ b/arch/sh/kernel/perf_event.c
@@ -10,7 +10,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *
  * ppc:
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index b0da5ae..3091267 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -9,7 +9,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  */
 
 #include <linux/perf_event.h>
diff --git a/arch/tile/kernel/perf_event.c b/arch/tile/kernel/perf_event.c
index bb509ce..8767060 100644
--- a/arch/tile/kernel/perf_event.c
+++ b/arch/tile/kernel/perf_event.c
@@ -21,7 +21,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *  Copyright (C) 2009 Google, Inc., Stephane Eranian
  */
diff --git a/arch/um/Makefile b/arch/um/Makefile
index 25ed409..e3abe6f 100644
--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -131,7 +131,7 @@
 # The wrappers will select whether using "malloc" or the kernel allocator.
 LINK_WRAPS = -Wl,--wrap,malloc -Wl,--wrap,free -Wl,--wrap,calloc
 
-LD_FLAGS_CMDLINE = $(foreach opt,$(LDFLAGS),-Wl,$(opt)) -lrt
+LD_FLAGS_CMDLINE = $(foreach opt,$(LDFLAGS),-Wl,$(opt))
 
 # Used by link-vmlinux.sh which has special support for um link
 export CFLAGS_vmlinux := $(LINK-y) $(LINK_WRAPS) $(LD_FLAGS_CMDLINE)
diff --git a/arch/um/drivers/net_user.c b/arch/um/drivers/net_user.c
index e697a41..e9f8445 100644
--- a/arch/um/drivers/net_user.c
+++ b/arch/um/drivers/net_user.c
@@ -249,21 +249,23 @@
 
 char *split_if_spec(char *str, ...)
 {
-	char **arg, *end;
+	char **arg, *end, *ret = NULL;
 	va_list ap;
 
 	va_start(ap, str);
 	while ((arg = va_arg(ap, char **)) != NULL) {
 		if (*str == '\0')
-			return NULL;
+			goto out;
 		end = strchr(str, ',');
 		if (end != str)
 			*arg = str;
 		if (end == NULL)
-			return NULL;
+			goto out;
 		*end++ = '\0';
 		str = end;
 	}
+	ret = str;
+out:
 	va_end(ap);
-	return str;
+	return ret;
 }
diff --git a/arch/um/kernel/signal.c b/arch/um/kernel/signal.c
index 57acbd6..fc8be0e 100644
--- a/arch/um/kernel/signal.c
+++ b/arch/um/kernel/signal.c
@@ -69,7 +69,7 @@
 	struct ksignal ksig;
 	int handled_sig = 0;
 
-	while (get_signal(&ksig)) {
+	if (get_signal(&ksig)) {
 		handled_sig = 1;
 		/* Whee!  Actually deliver the signal.  */
 		handle_signal(&ksig, regs);
diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index 0033e96..9011a88 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -23,7 +23,6 @@
 #include <stdarg.h>
 #include <linux/types.h>
 #include <linux/edd.h>
-#include <asm/boot.h>
 #include <asm/setup.h>
 #include "bitops.h"
 #include "ctype.h"
diff --git a/arch/x86/boot/video-mode.c b/arch/x86/boot/video-mode.c
index aa8a96b..95c7a81 100644
--- a/arch/x86/boot/video-mode.c
+++ b/arch/x86/boot/video-mode.c
@@ -19,6 +19,8 @@
 #include "video.h"
 #include "vesa.h"
 
+#include <uapi/asm/boot.h>
+
 /*
  * Common variables
  */
diff --git a/arch/x86/boot/video.c b/arch/x86/boot/video.c
index 05111bb..77780e3 100644
--- a/arch/x86/boot/video.c
+++ b/arch/x86/boot/video.c
@@ -13,6 +13,8 @@
  * Select video mode
  */
 
+#include <uapi/asm/boot.h>
+
 #include "boot.h"
 #include "video.h"
 #include "vesa.h"
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 53616ca..a55697d 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -509,6 +509,17 @@
 	 * tracking that we're in kernel mode.
 	 */
 	SWAPGS
+
+	/*
+	 * We need to tell lockdep that IRQs are off.  We can't do this until
+	 * we fix gsbase, and we should do it before enter_from_user_mode
+	 * (which can take locks).  Since TRACE_IRQS_OFF idempotent,
+	 * the simplest way to handle it is to just call it twice if
+	 * we enter from user mode.  There's no reason to optimize this since
+	 * TRACE_IRQS_OFF is a no-op if lockdep is off.
+	 */
+	TRACE_IRQS_OFF
+
 #ifdef CONFIG_CONTEXT_TRACKING
 	call enter_from_user_mode
 #endif
@@ -1049,12 +1060,18 @@
 	SWAPGS
 
 .Lerror_entry_from_usermode_after_swapgs:
+	/*
+	 * We need to tell lockdep that IRQs are off.  We can't do this until
+	 * we fix gsbase, and we should do it before enter_from_user_mode
+	 * (which can take locks).
+	 */
+	TRACE_IRQS_OFF
 #ifdef CONFIG_CONTEXT_TRACKING
 	call enter_from_user_mode
 #endif
+	ret
 
 .Lerror_entry_done:
-
 	TRACE_IRQS_OFF
 	ret
 
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 9f39056..690b402 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -35,7 +35,7 @@
 #define MSR_IA32_PERFCTR0		0x000000c1
 #define MSR_IA32_PERFCTR1		0x000000c2
 #define MSR_FSB_FREQ			0x000000cd
-#define MSR_NHM_PLATFORM_INFO		0x000000ce
+#define MSR_PLATFORM_INFO		0x000000ce
 
 #define MSR_NHM_SNB_PKG_CST_CFG_CTL	0x000000e2
 #define NHM_C3_AUTO_DEMOTE		(1UL << 25)
@@ -44,7 +44,6 @@
 #define SNB_C1_AUTO_UNDEMOTE		(1UL << 27)
 #define SNB_C3_AUTO_UNDEMOTE		(1UL << 28)
 
-#define MSR_PLATFORM_INFO		0x000000ce
 #define MSR_MTRRcap			0x000000fe
 #define MSR_IA32_BBL_CR_CTL		0x00000119
 #define MSR_IA32_BBL_CR_CTL3		0x0000011e
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index c5b7fb2..cc071c6 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -9,20 +9,22 @@
 #define PAGE_SIZE	(_AC(1,UL) << PAGE_SHIFT)
 #define PAGE_MASK	(~(PAGE_SIZE-1))
 
-#define __PHYSICAL_MASK		((phys_addr_t)((1ULL << __PHYSICAL_MASK_SHIFT) - 1))
-#define __VIRTUAL_MASK		((1UL << __VIRTUAL_MASK_SHIFT) - 1)
-
-/* Cast PAGE_MASK to a signed type so that it is sign-extended if
-   virtual addresses are 32-bits but physical addresses are larger
-   (ie, 32-bit PAE). */
-#define PHYSICAL_PAGE_MASK	(((signed long)PAGE_MASK) & __PHYSICAL_MASK)
-
 #define PMD_PAGE_SIZE		(_AC(1, UL) << PMD_SHIFT)
 #define PMD_PAGE_MASK		(~(PMD_PAGE_SIZE-1))
 
 #define PUD_PAGE_SIZE		(_AC(1, UL) << PUD_SHIFT)
 #define PUD_PAGE_MASK		(~(PUD_PAGE_SIZE-1))
 
+#define __PHYSICAL_MASK		((phys_addr_t)((1ULL << __PHYSICAL_MASK_SHIFT) - 1))
+#define __VIRTUAL_MASK		((1UL << __VIRTUAL_MASK_SHIFT) - 1)
+
+/* Cast *PAGE_MASK to a signed type so that it is sign-extended if
+   virtual addresses are 32-bits but physical addresses are larger
+   (ie, 32-bit PAE). */
+#define PHYSICAL_PAGE_MASK	(((signed long)PAGE_MASK) & __PHYSICAL_MASK)
+#define PHYSICAL_PMD_PAGE_MASK	(((signed long)PMD_PAGE_MASK) & __PHYSICAL_MASK)
+#define PHYSICAL_PUD_PAGE_MASK	(((signed long)PUD_PAGE_MASK) & __PHYSICAL_MASK)
+
 #define HPAGE_SHIFT		PMD_SHIFT
 #define HPAGE_SIZE		(_AC(1,UL) << HPAGE_SHIFT)
 #define HPAGE_MASK		(~(HPAGE_SIZE - 1))
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index dd5b0aa..a471cad 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -279,17 +279,14 @@
 static inline pudval_t pud_pfn_mask(pud_t pud)
 {
 	if (native_pud_val(pud) & _PAGE_PSE)
-		return PUD_PAGE_MASK & PHYSICAL_PAGE_MASK;
+		return PHYSICAL_PUD_PAGE_MASK;
 	else
 		return PTE_PFN_MASK;
 }
 
 static inline pudval_t pud_flags_mask(pud_t pud)
 {
-	if (native_pud_val(pud) & _PAGE_PSE)
-		return ~(PUD_PAGE_MASK & (pudval_t)PHYSICAL_PAGE_MASK);
-	else
-		return ~PTE_PFN_MASK;
+	return ~pud_pfn_mask(pud);
 }
 
 static inline pudval_t pud_flags(pud_t pud)
@@ -300,17 +297,14 @@
 static inline pmdval_t pmd_pfn_mask(pmd_t pmd)
 {
 	if (native_pmd_val(pmd) & _PAGE_PSE)
-		return PMD_PAGE_MASK & PHYSICAL_PAGE_MASK;
+		return PHYSICAL_PMD_PAGE_MASK;
 	else
 		return PTE_PFN_MASK;
 }
 
 static inline pmdval_t pmd_flags_mask(pmd_t pmd)
 {
-	if (native_pmd_val(pmd) & _PAGE_PSE)
-		return ~(PMD_PAGE_MASK & (pmdval_t)PHYSICAL_PAGE_MASK);
-	else
-		return ~PTE_PFN_MASK;
+	return ~pmd_pfn_mask(pmd);
 }
 
 static inline pmdval_t pmd_flags(pmd_t pmd)
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 48d34d2..cd0fc0c 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -1,7 +1,6 @@
 #ifndef _ASM_X86_PLATFORM_H
 #define _ASM_X86_PLATFORM_H
 
-#include <asm/pgtable_types.h>
 #include <asm/bootparam.h>
 
 struct mpc_bus;
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 4ddd780..c2b7522 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -273,10 +273,9 @@
 
 static __always_inline void setup_smap(struct cpuinfo_x86 *c)
 {
-	unsigned long eflags;
+	unsigned long eflags = native_save_fl();
 
 	/* This should have been cleared long ago */
-	raw_local_save_flags(eflags);
 	BUG_ON(eflags & X86_EFLAGS_AC);
 
 	if (cpu_has(c, X86_FEATURE_SMAP)) {
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 7fc27f1..b3e94ef 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -698,3 +698,4 @@
 	return error;
 
 }
+late_initcall(microcode_init);
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 4562cf0..2bf79d7 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -5,7 +5,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *  Copyright (C) 2009 Google, Inc., Stephane Eranian
  *
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 499f533..d0e35eb 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -5,7 +5,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *  Copyright (C) 2009 Google, Inc., Stephane Eranian
  *
@@ -387,7 +387,7 @@
 /* Check flags and event code/umask, and set the HSW N/A flag */
 #define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(code, n) \
 	__EVENT_CONSTRAINT(code, n, 			\
-			  INTEL_ARCH_EVENT_MASK|INTEL_ARCH_EVENT_MASK, \
+			  INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
 			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_NA_HSW)
 
 
@@ -627,6 +627,7 @@
 	u64 lbr_from[MAX_LBR_ENTRIES];
 	u64 lbr_to[MAX_LBR_ENTRIES];
 	u64 lbr_info[MAX_LBR_ENTRIES];
+	int tos;
 	int lbr_callstack_users;
 	int lbr_stack_state;
 };
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index f63360b..e2a4300 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -232,7 +232,7 @@
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
 	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
 	FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
-	INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.* */
+	INTEL_UEVENT_CONSTRAINT(0x148, 0x4),	/* L1D_PEND_MISS.PENDING */
 	INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
 	INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
 	/* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
index 377e8f8..a316ca9 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
@@ -298,7 +298,7 @@
 static inline struct perf_cgroup *event_to_cgroup(struct perf_event *event)
 {
 	if (event->attach_state & PERF_ATTACH_TASK)
-		return perf_cgroup_from_task(event->hw.target);
+		return perf_cgroup_from_task(event->hw.target, event->ctx);
 
 	return event->cgrp;
 }
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index bfd0b71..659f01e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -239,7 +239,7 @@
 	}
 
 	mask = x86_pmu.lbr_nr - 1;
-	tos = intel_pmu_lbr_tos();
+	tos = task_ctx->tos;
 	for (i = 0; i < tos; i++) {
 		lbr_idx = (tos - i) & mask;
 		wrmsrl(x86_pmu.lbr_from + lbr_idx, task_ctx->lbr_from[i]);
@@ -247,6 +247,7 @@
 		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
 			wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
 	}
+	wrmsrl(x86_pmu.lbr_tos, tos);
 	task_ctx->lbr_stack_state = LBR_NONE;
 }
 
@@ -270,6 +271,7 @@
 		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
 			rdmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
 	}
+	task_ctx->tos = tos;
 	task_ctx->lbr_stack_state = LBR_VALID;
 }
 
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index ef29b74..31c6a60 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -385,20 +385,19 @@
  */
 void fpu__init_prepare_fx_sw_frame(void)
 {
-	int fsave_header_size = sizeof(struct fregs_state);
 	int size = xstate_size + FP_XSTATE_MAGIC2_SIZE;
 
-	if (config_enabled(CONFIG_X86_32))
-		size += fsave_header_size;
-
 	fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1;
 	fx_sw_reserved.extended_size = size;
 	fx_sw_reserved.xfeatures = xfeatures_mask;
 	fx_sw_reserved.xstate_size = xstate_size;
 
-	if (config_enabled(CONFIG_IA32_EMULATION)) {
+	if (config_enabled(CONFIG_IA32_EMULATION) ||
+	    config_enabled(CONFIG_X86_32)) {
+		int fsave_header_size = sizeof(struct fregs_state);
+
 		fx_sw_reserved_ia32 = fx_sw_reserved;
-		fx_sw_reserved_ia32.extended_size += fsave_header_size;
+		fx_sw_reserved_ia32.extended_size = size + fsave_header_size;
 	}
 }
 
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 6454f27..70fc312 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -694,7 +694,6 @@
 	if (!boot_cpu_has(X86_FEATURE_XSAVE))
 		return NULL;
 
-	xsave = &current->thread.fpu.state.xsave;
 	/*
 	 * We should not ever be requesting features that we
 	 * have not enabled.  Remember that pcntxt_mask is
diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c
index dc5fa6a..3512ba6 100644
--- a/arch/x86/kernel/irq_work.c
+++ b/arch/x86/kernel/irq_work.c
@@ -1,7 +1,7 @@
 /*
  * x86 specific code for irq_work
  *
- * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra
  */
 
 #include <linux/kernel.h>
diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S
index 94ea120..87e1762 100644
--- a/arch/x86/kernel/mcount_64.S
+++ b/arch/x86/kernel/mcount_64.S
@@ -278,6 +278,12 @@
 	/* save_mcount_regs fills in first two parameters */
 	save_mcount_regs
 
+	/*
+	 * When DYNAMIC_FTRACE is not defined, ARCH_SUPPORTS_FTRACE_OPS is not
+	 * set (see include/asm/ftrace.h and include/linux/ftrace.h).  Only the
+	 * ip and parent ip are used and the list function is called when
+	 * function tracing is enabled.
+	 */
 	call   *ftrace_trace_function
 
 	restore_mcount_regs
diff --git a/arch/x86/kernel/pmem.c b/arch/x86/kernel/pmem.c
index 4f00b63..14415af 100644
--- a/arch/x86/kernel/pmem.c
+++ b/arch/x86/kernel/pmem.c
@@ -4,10 +4,22 @@
  */
 #include <linux/platform_device.h>
 #include <linux/module.h>
+#include <linux/ioport.h>
+
+static int found(u64 start, u64 end, void *data)
+{
+	return 1;
+}
 
 static __init int register_e820_pmem(void)
 {
+	char *pmem = "Persistent Memory (legacy)";
 	struct platform_device *pdev;
+	int rc;
+
+	rc = walk_iomem_res(pmem, IORESOURCE_MEM, 0, -1, NULL, found);
+	if (rc <= 0)
+		return 0;
 
 	/*
 	 * See drivers/nvdimm/e820.c for the implementation, this is
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 29db25f..d2bbe34 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1250,8 +1250,6 @@
 	if (efi_enabled(EFI_BOOT))
 		efi_apply_memmap_quirks();
 #endif
-
-	microcode_init();
 }
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index b7ffb7c..cb6282c 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -690,12 +690,15 @@
 	signal_setup_done(failed, ksig, stepping);
 }
 
-#ifdef CONFIG_X86_32
-#define NR_restart_syscall	__NR_restart_syscall
-#else /* !CONFIG_X86_32 */
-#define NR_restart_syscall	\
-	test_thread_flag(TIF_IA32) ? __NR_ia32_restart_syscall : __NR_restart_syscall
-#endif /* CONFIG_X86_32 */
+static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs)
+{
+#if defined(CONFIG_X86_32) || !defined(CONFIG_X86_64)
+	return __NR_restart_syscall;
+#else /* !CONFIG_X86_32 && CONFIG_X86_64 */
+	return test_thread_flag(TIF_IA32) ? __NR_ia32_restart_syscall :
+		__NR_restart_syscall | (regs->orig_ax & __X32_SYSCALL_BIT);
+#endif /* CONFIG_X86_32 || !CONFIG_X86_64 */
+}
 
 /*
  * Note that 'init' is a special process: it doesn't get signals it doesn't
@@ -724,7 +727,7 @@
 			break;
 
 		case -ERESTART_RESTARTBLOCK:
-			regs->ax = NR_restart_syscall;
+			regs->ax = get_nr_restart_syscall(regs);
 			regs->ip -= 2;
 			break;
 		}
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 892ee2e5..fbabe4f 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -509,7 +509,7 @@
  */
 #define UDELAY_10MS_DEFAULT 10000
 
-static unsigned int init_udelay = INT_MAX;
+static unsigned int init_udelay = UINT_MAX;
 
 static int __init cpu_init_udelay(char *str)
 {
@@ -522,14 +522,15 @@
 static void __init smp_quirk_init_udelay(void)
 {
 	/* if cmdline changed it from default, leave it alone */
-	if (init_udelay != INT_MAX)
+	if (init_udelay != UINT_MAX)
 		return;
 
 	/* if modern processor, use no delay */
 	if (((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 == 6)) ||
-	    ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF)))
+	    ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF))) {
 		init_udelay = 0;
-
+		return;
+	}
 	/* else, use legacy delay */
 	init_udelay = UDELAY_10MS_DEFAULT;
 }
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 87acc52..af823a3 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -7394,11 +7394,6 @@
 
 	switch (type) {
 	case VMX_VPID_EXTENT_ALL_CONTEXT:
-		if (get_vmcs12(vcpu)->virtual_processor_id == 0) {
-			nested_vmx_failValid(vcpu,
-				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
-			return 1;
-		}
 		__vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02);
 		nested_vmx_succeed(vcpu);
 		break;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 00462bd..eed3228 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2763,6 +2763,26 @@
 	return 0;
 }
 
+static int kvm_cpu_accept_dm_intr(struct kvm_vcpu *vcpu)
+{
+	return (!lapic_in_kernel(vcpu) ||
+		kvm_apic_accept_pic_intr(vcpu));
+}
+
+/*
+ * if userspace requested an interrupt window, check that the
+ * interrupt window is open.
+ *
+ * No need to exit to userspace if we already have an interrupt queued.
+ */
+static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu)
+{
+	return kvm_arch_interrupt_allowed(vcpu) &&
+		!kvm_cpu_has_interrupt(vcpu) &&
+		!kvm_event_needs_reinjection(vcpu) &&
+		kvm_cpu_accept_dm_intr(vcpu);
+}
+
 static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
 				    struct kvm_interrupt *irq)
 {
@@ -2786,6 +2806,7 @@
 		return -EEXIST;
 
 	vcpu->arch.pending_external_vector = irq->irq;
+	kvm_make_request(KVM_REQ_EVENT, vcpu);
 	return 0;
 }
 
@@ -5910,23 +5931,10 @@
 	return emulator_write_emulated(ctxt, rip, instruction, 3, NULL);
 }
 
-/*
- * Check if userspace requested an interrupt window, and that the
- * interrupt window is open.
- *
- * No need to exit to userspace if we already have an interrupt queued.
- */
 static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu)
 {
-	if (!vcpu->run->request_interrupt_window || pic_in_kernel(vcpu->kvm))
-		return false;
-
-	if (kvm_cpu_has_interrupt(vcpu))
-		return false;
-
-	return (irqchip_split(vcpu->kvm)
-		? kvm_apic_accept_pic_intr(vcpu)
-		: kvm_arch_interrupt_allowed(vcpu));
+	return vcpu->run->request_interrupt_window &&
+		likely(!pic_in_kernel(vcpu->kvm));
 }
 
 static void post_kvm_run_save(struct kvm_vcpu *vcpu)
@@ -5937,17 +5945,9 @@
 	kvm_run->flags = is_smm(vcpu) ? KVM_RUN_X86_SMM : 0;
 	kvm_run->cr8 = kvm_get_cr8(vcpu);
 	kvm_run->apic_base = kvm_get_apic_base(vcpu);
-	if (!irqchip_in_kernel(vcpu->kvm))
-		kvm_run->ready_for_interrupt_injection =
-			kvm_arch_interrupt_allowed(vcpu) &&
-			!kvm_cpu_has_interrupt(vcpu) &&
-			!kvm_event_needs_reinjection(vcpu);
-	else if (!pic_in_kernel(vcpu->kvm))
-		kvm_run->ready_for_interrupt_injection =
-			kvm_apic_accept_pic_intr(vcpu) &&
-			!kvm_cpu_has_interrupt(vcpu);
-	else
-		kvm_run->ready_for_interrupt_injection = 1;
+	kvm_run->ready_for_interrupt_injection =
+		pic_in_kernel(vcpu->kvm) ||
+		kvm_vcpu_ready_for_interrupt_injection(vcpu);
 }
 
 static void update_cr8_intercept(struct kvm_vcpu *vcpu)
@@ -6360,8 +6360,10 @@
 static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 {
 	int r;
-	bool req_int_win = !lapic_in_kernel(vcpu) &&
-		vcpu->run->request_interrupt_window;
+	bool req_int_win =
+		dm_request_for_irq_injection(vcpu) &&
+		kvm_cpu_accept_dm_intr(vcpu);
+
 	bool req_immediate_exit = false;
 
 	if (vcpu->requests) {
@@ -6663,7 +6665,8 @@
 		if (kvm_cpu_has_pending_timer(vcpu))
 			kvm_inject_pending_timer_irqs(vcpu);
 
-		if (dm_request_for_irq_injection(vcpu)) {
+		if (dm_request_for_irq_injection(vcpu) &&
+			kvm_vcpu_ready_for_interrupt_injection(vcpu)) {
 			r = 0;
 			vcpu->run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN;
 			++vcpu->stat.request_irq_exits;
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index b0ae85f..b2fd67d 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -101,19 +101,19 @@
 	switch (type) {
 	case REG_TYPE_RM:
 		regno = X86_MODRM_RM(insn->modrm.value);
-		if (X86_REX_B(insn->rex_prefix.value) == 1)
+		if (X86_REX_B(insn->rex_prefix.value))
 			regno += 8;
 		break;
 
 	case REG_TYPE_INDEX:
 		regno = X86_SIB_INDEX(insn->sib.value);
-		if (X86_REX_X(insn->rex_prefix.value) == 1)
+		if (X86_REX_X(insn->rex_prefix.value))
 			regno += 8;
 		break;
 
 	case REG_TYPE_BASE:
 		regno = X86_SIB_BASE(insn->sib.value);
-		if (X86_REX_B(insn->rex_prefix.value) == 1)
+		if (X86_REX_B(insn->rex_prefix.value))
 			regno += 8;
 		break;
 
@@ -586,6 +586,29 @@
 }
 
 /*
+ * We only want to do a 4-byte get_user() on 32-bit.  Otherwise,
+ * we might run off the end of the bounds table if we are on
+ * a 64-bit kernel and try to get 8 bytes.
+ */
+int get_user_bd_entry(struct mm_struct *mm, unsigned long *bd_entry_ret,
+		long __user *bd_entry_ptr)
+{
+	u32 bd_entry_32;
+	int ret;
+
+	if (is_64bit_mm(mm))
+		return get_user(*bd_entry_ret, bd_entry_ptr);
+
+	/*
+	 * Note that get_user() uses the type of the *pointer* to
+	 * establish the size of the get, not the destination.
+	 */
+	ret = get_user(bd_entry_32, (u32 __user *)bd_entry_ptr);
+	*bd_entry_ret = bd_entry_32;
+	return ret;
+}
+
+/*
  * Get the base of bounds tables pointed by specific bounds
  * directory entry.
  */
@@ -605,7 +628,7 @@
 		int need_write = 0;
 
 		pagefault_disable();
-		ret = get_user(bd_entry, bd_entry_ptr);
+		ret = get_user_bd_entry(mm, &bd_entry, bd_entry_ptr);
 		pagefault_enable();
 		if (!ret)
 			break;
@@ -700,11 +723,23 @@
  */
 static inline unsigned long bd_entry_virt_space(struct mm_struct *mm)
 {
-	unsigned long long virt_space = (1ULL << boot_cpu_data.x86_virt_bits);
-	if (is_64bit_mm(mm))
-		return virt_space / MPX_BD_NR_ENTRIES_64;
-	else
-		return virt_space / MPX_BD_NR_ENTRIES_32;
+	unsigned long long virt_space;
+	unsigned long long GB = (1ULL << 30);
+
+	/*
+	 * This covers 32-bit emulation as well as 32-bit kernels
+	 * running on 64-bit harware.
+	 */
+	if (!is_64bit_mm(mm))
+		return (4ULL * GB) / MPX_BD_NR_ENTRIES_32;
+
+	/*
+	 * 'x86_virt_bits' returns what the hardware is capable
+	 * of, and returns the full >32-bit adddress space when
+	 * running 32-bit kernels on 64-bit hardware.
+	 */
+	virt_space = (1ULL << boot_cpu_data.x86_virt_bits);
+	return virt_space / MPX_BD_NR_ENTRIES_64;
 }
 
 /*
diff --git a/arch/x86/pci/bus_numa.c b/arch/x86/pci/bus_numa.c
index 7bcf06a..6eb3c8a 100644
--- a/arch/x86/pci/bus_numa.c
+++ b/arch/x86/pci/bus_numa.c
@@ -50,18 +50,9 @@
 	if (!found)
 		pci_add_resource(resources, &info->busn);
 
-	list_for_each_entry(root_res, &info->resources, list) {
-		struct resource *res;
-		struct resource *root;
+	list_for_each_entry(root_res, &info->resources, list)
+		pci_add_resource(resources, &root_res->res);
 
-		res = &root_res->res;
-		pci_add_resource(resources, res);
-		if (res->flags & IORESOURCE_IO)
-			root = &ioport_resource;
-		else
-			root = &iomem_resource;
-		insert_resource(root, res);
-	}
 	return;
 
 default_resources:
diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c
index 06934a8..e5f854c 100644
--- a/arch/x86/um/signal.c
+++ b/arch/x86/um/signal.c
@@ -211,7 +211,7 @@
 		if (err)
 			return 1;
 
-		err = convert_fxsr_from_user(&fpx, sc.fpstate);
+		err = convert_fxsr_from_user(&fpx, (void *)sc.fpstate);
 		if (err)
 			return 1;
 
@@ -227,7 +227,7 @@
 	{
 		struct user_i387_struct fp;
 
-		err = copy_from_user(&fp, sc.fpstate,
+		err = copy_from_user(&fp, (void *)sc.fpstate,
 				     sizeof(struct user_i387_struct));
 		if (err)
 			return 1;
@@ -291,7 +291,7 @@
 #endif
 #undef PUTREG
 	sc.oldmask = mask;
-	sc.fpstate = to_fp;
+	sc.fpstate = (unsigned long)to_fp;
 
 	err = copy_to_user(to, &sc, sizeof(struct sigcontext));
 	if (err)
@@ -468,12 +468,10 @@
 	struct sigframe __user *frame = (struct sigframe __user *)(sp - 8);
 	sigset_t set;
 	struct sigcontext __user *sc = &frame->sc;
-	unsigned long __user *oldmask = &sc->oldmask;
-	unsigned long __user *extramask = frame->extramask;
 	int sig_size = (_NSIG_WORDS - 1) * sizeof(unsigned long);
 
-	if (copy_from_user(&set.sig[0], oldmask, sizeof(set.sig[0])) ||
-	    copy_from_user(&set.sig[1], extramask, sig_size))
+	if (copy_from_user(&set.sig[0], (void *)sc->oldmask, sizeof(set.sig[0])) ||
+	    copy_from_user(&set.sig[1], frame->extramask, sig_size))
 		goto segfault;
 
 	set_current_blocked(&set);
@@ -505,6 +503,7 @@
 {
 	struct rt_sigframe __user *frame;
 	int err = 0, sig = ksig->sig;
+	unsigned long fp_to;
 
 	frame = (struct rt_sigframe __user *)
 		round_down(stack_top - sizeof(struct rt_sigframe), 16);
@@ -526,7 +525,10 @@
 	err |= __save_altstack(&frame->uc.uc_stack, PT_REGS_SP(regs));
 	err |= copy_sc_to_user(&frame->uc.uc_mcontext, &frame->fpstate, regs,
 			       set->sig[0]);
-	err |= __put_user(&frame->fpstate, &frame->uc.uc_mcontext.fpstate);
+
+	fp_to = (unsigned long)&frame->fpstate;
+
+	err |= __put_user(fp_to, &frame->uc.uc_mcontext.fpstate);
 	if (sizeof(*set) == 16) {
 		err |= __put_user(set->sig[0], &frame->uc.uc_sigmask.sig[0]);
 		err |= __put_user(set->sig[1], &frame->uc.uc_sigmask.sig[1]);
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 5bcdfc1..5a37188 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1127,15 +1127,15 @@
  * of the main cic data structures.  For now we allow a task to change
  * its cgroup only if it's the only owner of its ioc.
  */
-static int blkcg_can_attach(struct cgroup_subsys_state *css,
-			    struct cgroup_taskset *tset)
+static int blkcg_can_attach(struct cgroup_taskset *tset)
 {
 	struct task_struct *task;
+	struct cgroup_subsys_state *dst_css;
 	struct io_context *ioc;
 	int ret = 0;
 
 	/* task_lock() is needed to avoid races with exit_io_context() */
-	cgroup_taskset_for_each(task, tset) {
+	cgroup_taskset_for_each(task, dst_css, tset) {
 		task_lock(task);
 		ioc = task->io_context;
 		if (ioc && atomic_read(&ioc->nr_tasks) > 1)
diff --git a/block/blk-core.c b/block/blk-core.c
index 5131993b..3636be4 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2114,7 +2114,8 @@
 EXPORT_SYMBOL(submit_bio);
 
 /**
- * blk_rq_check_limits - Helper function to check a request for the queue limit
+ * blk_cloned_rq_check_limits - Helper function to check a cloned request
+ *                              for new the queue limits
  * @q:  the queue
  * @rq: the request being checked
  *
@@ -2125,20 +2126,13 @@
  *    after it is inserted to @q, it should be checked against @q before
  *    the insertion using this generic function.
  *
- *    This function should also be useful for request stacking drivers
- *    in some cases below, so export this function.
  *    Request stacking drivers like request-based dm may change the queue
- *    limits while requests are in the queue (e.g. dm's table swapping).
- *    Such request stacking drivers should check those requests against
- *    the new queue limits again when they dispatch those requests,
- *    although such checkings are also done against the old queue limits
- *    when submitting requests.
+ *    limits when retrying requests on other queues. Those requests need
+ *    to be checked against the new queue limits again during dispatch.
  */
-int blk_rq_check_limits(struct request_queue *q, struct request *rq)
+static int blk_cloned_rq_check_limits(struct request_queue *q,
+				      struct request *rq)
 {
-	if (!rq_mergeable(rq))
-		return 0;
-
 	if (blk_rq_sectors(rq) > blk_queue_get_max_sectors(q, rq->cmd_flags)) {
 		printk(KERN_ERR "%s: over max size limit.\n", __func__);
 		return -EIO;
@@ -2158,7 +2152,6 @@
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(blk_rq_check_limits);
 
 /**
  * blk_insert_cloned_request - Helper for stacking drivers to submit a request
@@ -2170,7 +2163,7 @@
 	unsigned long flags;
 	int where = ELEVATOR_INSERT_BACK;
 
-	if (blk_rq_check_limits(q, rq))
+	if (blk_cloned_rq_check_limits(q, rq))
 		return -EIO;
 
 	if (rq->rq_disk &&
@@ -3412,6 +3405,9 @@
 {
 	int ret = 0;
 
+	if (!q->dev)
+		return ret;
+
 	spin_lock_irq(q->queue_lock);
 	if (q->nr_pending) {
 		ret = -EBUSY;
@@ -3439,6 +3435,9 @@
  */
 void blk_post_runtime_suspend(struct request_queue *q, int err)
 {
+	if (!q->dev)
+		return;
+
 	spin_lock_irq(q->queue_lock);
 	if (!err) {
 		q->rpm_status = RPM_SUSPENDED;
@@ -3463,6 +3462,9 @@
  */
 void blk_pre_runtime_resume(struct request_queue *q)
 {
+	if (!q->dev)
+		return;
+
 	spin_lock_irq(q->queue_lock);
 	q->rpm_status = RPM_RESUMING;
 	spin_unlock_irq(q->queue_lock);
@@ -3485,6 +3487,9 @@
  */
 void blk_post_runtime_resume(struct request_queue *q, int err)
 {
+	if (!q->dev)
+		return;
+
 	spin_lock_irq(q->queue_lock);
 	if (!err) {
 		q->rpm_status = RPM_ACTIVE;
diff --git a/block/blk-merge.c b/block/blk-merge.c
index de5716d8..e01405a 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -76,6 +76,9 @@
 	struct bio_vec bv, bvprv, *bvprvp = NULL;
 	struct bvec_iter iter;
 	unsigned seg_size = 0, nsegs = 0, sectors = 0;
+	unsigned front_seg_size = bio->bi_seg_front_size;
+	bool do_split = true;
+	struct bio *new = NULL;
 
 	bio_for_each_segment(bv, bio, iter) {
 		if (sectors + (bv.bv_len >> 9) > queue_max_sectors(q))
@@ -98,8 +101,11 @@
 
 			seg_size += bv.bv_len;
 			bvprv = bv;
-			bvprvp = &bv;
+			bvprvp = &bvprv;
 			sectors += bv.bv_len >> 9;
+
+			if (nsegs == 1 && seg_size > front_seg_size)
+				front_seg_size = seg_size;
 			continue;
 		}
 new_segment:
@@ -108,16 +114,29 @@
 
 		nsegs++;
 		bvprv = bv;
-		bvprvp = &bv;
+		bvprvp = &bvprv;
 		seg_size = bv.bv_len;
 		sectors += bv.bv_len >> 9;
+
+		if (nsegs == 1 && seg_size > front_seg_size)
+			front_seg_size = seg_size;
 	}
 
-	*segs = nsegs;
-	return NULL;
+	do_split = false;
 split:
 	*segs = nsegs;
-	return bio_split(bio, sectors, GFP_NOIO, bs);
+
+	if (do_split) {
+		new = bio_split(bio, sectors, GFP_NOIO, bs);
+		if (new)
+			bio = new;
+	}
+
+	bio->bi_seg_front_size = front_seg_size;
+	if (seg_size > bio->bi_seg_back_size)
+		bio->bi_seg_back_size = seg_size;
+
+	return do_split ? new : NULL;
 }
 
 void blk_queue_split(struct request_queue *q, struct bio **bio,
@@ -412,6 +431,12 @@
 	if (sg)
 		sg_mark_end(sg);
 
+	/*
+	 * Something must have been wrong if the figured number of
+	 * segment is bigger than number of req's physical segments
+	 */
+	WARN_ON(nsegs > rq->nr_phys_segments);
+
 	return nsegs;
 }
 EXPORT_SYMBOL(blk_rq_map_sg);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 3ae09de..6d6f8fe 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1291,15 +1291,16 @@
 		blk_mq_bio_to_request(rq, bio);
 
 		/*
-		 * we do limited pluging. If bio can be merged, do merge.
+		 * We do limited pluging. If the bio can be merged, do that.
 		 * Otherwise the existing request in the plug list will be
 		 * issued. So the plug list will have one request at most
 		 */
 		if (plug) {
 			/*
 			 * The plug list might get flushed before this. If that
-			 * happens, same_queue_rq is invalid and plug list is empty
-			 **/
+			 * happens, same_queue_rq is invalid and plug list is
+			 * empty
+			 */
 			if (same_queue_rq && !list_empty(&plug->mq_list)) {
 				old_rq = same_queue_rq;
 				list_del_init(&old_rq->queuelist);
@@ -1380,12 +1381,15 @@
 		blk_mq_bio_to_request(rq, bio);
 		if (!request_count)
 			trace_block_plug(q);
-		else if (request_count >= BLK_MAX_REQUEST_COUNT) {
+
+		blk_mq_put_ctx(data.ctx);
+
+		if (request_count >= BLK_MAX_REQUEST_COUNT) {
 			blk_flush_plug_list(plug, false);
 			trace_block_plug(q);
 		}
+
 		list_add_tail(&rq->queuelist, &plug->mq_list);
-		blk_mq_put_ctx(data.ctx);
 		return cookie;
 	}
 
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 7d8f129..dd49735 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -91,7 +91,8 @@
 	lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
 	lim->virt_boundary_mask = 0;
 	lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
-	lim->max_sectors = lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS;
+	lim->max_sectors = lim->max_dev_sectors = lim->max_hw_sectors =
+		BLK_SAFE_MAX_SECTORS;
 	lim->chunk_sectors = 0;
 	lim->max_write_same_sectors = 0;
 	lim->max_discard_sectors = 0;
@@ -127,6 +128,7 @@
 	lim->max_hw_sectors = UINT_MAX;
 	lim->max_segment_size = UINT_MAX;
 	lim->max_sectors = UINT_MAX;
+	lim->max_dev_sectors = UINT_MAX;
 	lim->max_write_same_sectors = UINT_MAX;
 }
 EXPORT_SYMBOL(blk_set_stacking_limits);
@@ -214,8 +216,8 @@
 EXPORT_SYMBOL(blk_queue_bounce_limit);
 
 /**
- * blk_limits_max_hw_sectors - set hard and soft limit of max sectors for request
- * @limits: the queue limits
+ * blk_queue_max_hw_sectors - set max sectors for a request for this queue
+ * @q:  the request queue for the device
  * @max_hw_sectors:  max hardware sectors in the usual 512b unit
  *
  * Description:
@@ -224,13 +226,19 @@
  *    the device driver based upon the capabilities of the I/O
  *    controller.
  *
+ *    max_dev_sectors is a hard limit imposed by the storage device for
+ *    READ/WRITE requests. It is set by the disk driver.
+ *
  *    max_sectors is a soft limit imposed by the block layer for
  *    filesystem type requests.  This value can be overridden on a
  *    per-device basis in /sys/block/<device>/queue/max_sectors_kb.
  *    The soft limit can not exceed max_hw_sectors.
  **/
-void blk_limits_max_hw_sectors(struct queue_limits *limits, unsigned int max_hw_sectors)
+void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_sectors)
 {
+	struct queue_limits *limits = &q->limits;
+	unsigned int max_sectors;
+
 	if ((max_hw_sectors << 9) < PAGE_CACHE_SIZE) {
 		max_hw_sectors = 1 << (PAGE_CACHE_SHIFT - 9);
 		printk(KERN_INFO "%s: set to minimum %d\n",
@@ -238,22 +246,9 @@
 	}
 
 	limits->max_hw_sectors = max_hw_sectors;
-	limits->max_sectors = min_t(unsigned int, max_hw_sectors,
-				    BLK_DEF_MAX_SECTORS);
-}
-EXPORT_SYMBOL(blk_limits_max_hw_sectors);
-
-/**
- * blk_queue_max_hw_sectors - set max sectors for a request for this queue
- * @q:  the request queue for the device
- * @max_hw_sectors:  max hardware sectors in the usual 512b unit
- *
- * Description:
- *    See description for blk_limits_max_hw_sectors().
- **/
-void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_sectors)
-{
-	blk_limits_max_hw_sectors(&q->limits, max_hw_sectors);
+	max_sectors = min_not_zero(max_hw_sectors, limits->max_dev_sectors);
+	max_sectors = min_t(unsigned int, max_sectors, BLK_DEF_MAX_SECTORS);
+	limits->max_sectors = max_sectors;
 }
 EXPORT_SYMBOL(blk_queue_max_hw_sectors);
 
@@ -527,6 +522,7 @@
 
 	t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors);
 	t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors);
+	t->max_dev_sectors = min_not_zero(t->max_dev_sectors, b->max_dev_sectors);
 	t->max_write_same_sectors = min(t->max_write_same_sectors,
 					b->max_write_same_sectors);
 	t->bounce_pfn = min_not_zero(t->bounce_pfn, b->bounce_pfn);
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 565b8da..e140cc4 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -205,6 +205,9 @@
 	if (ret < 0)
 		return ret;
 
+	max_hw_sectors_kb = min_not_zero(max_hw_sectors_kb, (unsigned long)
+					 q->limits.max_dev_sectors >> 1);
+
 	if (max_sectors_kb > max_hw_sectors_kb || max_sectors_kb < page_kb)
 		return -EINVAL;
 
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index 246dfb1..aa40aa9 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -158,11 +158,13 @@
 {
 	if (blk_mark_rq_complete(req))
 		return;
-	blk_delete_timer(req);
-	if (req->q->mq_ops)
+
+	if (req->q->mq_ops) {
 		blk_mq_rq_timed_out(req, false);
-	else
+	} else {
+		blk_delete_timer(req);
 		blk_rq_timed_out(req);
+	}
 }
 EXPORT_SYMBOL_GPL(blk_abort_request);
 
diff --git a/block/blk.h b/block/blk.h
index da722eb..c43926d 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -72,8 +72,6 @@
 void __blk_queue_free_tags(struct request_queue *q);
 bool __blk_end_bidi_request(struct request *rq, int error,
 			    unsigned int nr_bytes, unsigned int bidi_bytes);
-int blk_queue_enter(struct request_queue *q, gfp_t gfp);
-void blk_queue_exit(struct request_queue *q);
 void blk_freeze_queue(struct request_queue *q);
 
 static inline void blk_queue_enter_live(struct request_queue *q)
diff --git a/block/noop-iosched.c b/block/noop-iosched.c
index 3de89d4..a163c48 100644
--- a/block/noop-iosched.c
+++ b/block/noop-iosched.c
@@ -21,10 +21,10 @@
 static int noop_dispatch(struct request_queue *q, int force)
 {
 	struct noop_data *nd = q->elevator->elevator_data;
+	struct request *rq;
 
-	if (!list_empty(&nd->queue)) {
-		struct request *rq;
-		rq = list_entry(nd->queue.next, struct request, queuelist);
+	rq = list_first_entry_or_null(&nd->queue, struct request, queuelist);
+	if (rq) {
 		list_del_init(&rq->queuelist);
 		elv_dispatch_sort(q, rq);
 		return 1;
@@ -46,7 +46,7 @@
 
 	if (rq->queuelist.prev == &nd->queue)
 		return NULL;
-	return list_entry(rq->queuelist.prev, struct request, queuelist);
+	return list_prev_entry(rq, queuelist);
 }
 
 static struct request *
@@ -56,7 +56,7 @@
 
 	if (rq->queuelist.next == &nd->queue)
 		return NULL;
-	return list_entry(rq->queuelist.next, struct request, queuelist);
+	return list_next_entry(rq, queuelist);
 }
 
 static int noop_init_queue(struct request_queue *q, struct elevator_type *e)
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 3b03015..746935a 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -397,7 +397,7 @@
 	struct hd_struct *part;
 	int res;
 
-	if (bdev->bd_part_count)
+	if (bdev->bd_part_count || bdev->bd_super)
 		return -EBUSY;
 	res = invalidate_partition(disk, 0);
 	if (res)
diff --git a/block/partitions/mac.c b/block/partitions/mac.c
index c2c48ec..621317a 100644
--- a/block/partitions/mac.c
+++ b/block/partitions/mac.c
@@ -32,7 +32,7 @@
 	Sector sect;
 	unsigned char *data;
 	int slot, blocks_in_map;
-	unsigned secsize;
+	unsigned secsize, datasize, partoffset;
 #ifdef CONFIG_PPC_PMAC
 	int found_root = 0;
 	int found_root_goodness = 0;
@@ -50,10 +50,14 @@
 	}
 	secsize = be16_to_cpu(md->block_size);
 	put_dev_sector(sect);
-	data = read_part_sector(state, secsize/512, &sect);
+	datasize = round_down(secsize, 512);
+	data = read_part_sector(state, datasize / 512, &sect);
 	if (!data)
 		return -1;
-	part = (struct mac_partition *) (data + secsize%512);
+	partoffset = secsize % 512;
+	if (partoffset + sizeof(*part) > datasize)
+		return -1;
+	part = (struct mac_partition *) (data + partoffset);
 	if (be16_to_cpu(part->signature) != MAC_PARTITION_MAGIC) {
 		put_dev_sector(sect);
 		return 0;		/* not a MacOS disk */
diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c
index 0aa6fdf..23525c2 100644
--- a/crypto/algif_aead.c
+++ b/crypto/algif_aead.c
@@ -106,7 +106,7 @@
 
 	rcu_read_lock();
 	wq = rcu_dereference(sk->sk_wq);
-	if (wq_has_sleeper(wq))
+	if (skwq_has_sleeper(wq))
 		wake_up_interruptible_sync_poll(&wq->wait, POLLIN |
 							   POLLRDNORM |
 							   POLLRDBAND);
@@ -125,7 +125,7 @@
 	if (flags & MSG_DONTWAIT)
 		return -EAGAIN;
 
-	set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+	sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 
 	for (;;) {
 		if (signal_pending(current))
@@ -139,7 +139,7 @@
 	}
 	finish_wait(sk_sleep(sk), &wait);
 
-	clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+	sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 
 	return err;
 }
@@ -157,7 +157,7 @@
 
 	rcu_read_lock();
 	wq = rcu_dereference(sk->sk_wq);
-	if (wq_has_sleeper(wq))
+	if (skwq_has_sleeper(wq))
 		wake_up_interruptible_sync_poll(&wq->wait, POLLOUT |
 							   POLLRDNORM |
 							   POLLRDBAND);
diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c
index af31a0e..caf58b4 100644
--- a/crypto/algif_skcipher.c
+++ b/crypto/algif_skcipher.c
@@ -212,7 +212,7 @@
 	if (flags & MSG_DONTWAIT)
 		return -EAGAIN;
 
-	set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+	sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
 	for (;;) {
 		if (signal_pending(current))
@@ -238,7 +238,7 @@
 
 	rcu_read_lock();
 	wq = rcu_dereference(sk->sk_wq);
-	if (wq_has_sleeper(wq))
+	if (skwq_has_sleeper(wq))
 		wake_up_interruptible_sync_poll(&wq->wait, POLLIN |
 							   POLLRDNORM |
 							   POLLRDBAND);
@@ -258,7 +258,7 @@
 		return -EAGAIN;
 	}
 
-	set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+	sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 
 	for (;;) {
 		if (signal_pending(current))
@@ -272,7 +272,7 @@
 	}
 	finish_wait(sk_sleep(sk), &wait);
 
-	clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+	sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
 
 	return err;
 }
@@ -288,7 +288,7 @@
 
 	rcu_read_lock();
 	wq = rcu_dereference(sk->sk_wq);
-	if (wq_has_sleeper(wq))
+	if (skwq_has_sleeper(wq))
 		wake_up_interruptible_sync_poll(&wq->wait, POLLOUT |
 							   POLLRDNORM |
 							   POLLRDBAND);
diff --git a/drivers/Makefile b/drivers/Makefile
index 73d0391..795d0ca 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -63,6 +63,7 @@
 obj-$(CONFIG_FB_INTEL)          += video/fbdev/intelfb/
 
 obj-$(CONFIG_PARPORT)		+= parport/
+obj-$(CONFIG_NVM)		+= lightnvm/
 obj-y				+= base/ block/ misc/ mfd/ nfc/
 obj-$(CONFIG_LIBNVDIMM)		+= nvdimm/
 obj-$(CONFIG_DMA_SHARED_BUFFER) += dma-buf/
@@ -70,7 +71,6 @@
 obj-y				+= macintosh/
 obj-$(CONFIG_IDE)		+= ide/
 obj-$(CONFIG_SCSI)		+= scsi/
-obj-$(CONFIG_NVM)		+= lightnvm/
 obj-y				+= nvme/
 obj-$(CONFIG_ATA)		+= ata/
 obj-$(CONFIG_TARGET_CORE)	+= target/
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 25dbb76..5eef4cb 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -58,10 +58,10 @@
 	bool
 
 config ACPI_DEBUGGER
-	bool "In-kernel debugger (EXPERIMENTAL)"
+	bool "AML debugger interface (EXPERIMENTAL)"
 	select ACPI_DEBUG
 	help
-	  Enable in-kernel debugging facilities: statistics, internal
+	  Enable in-kernel debugging of AML facilities: statistics, internal
 	  object dump, single step control method execution.
 	  This is still under development, currently enabling this only
 	  results in the compilation of the ACPICA debugger files.
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index 3c083d2..6730f96 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -304,7 +304,7 @@
 
 static int register_pcc_channel(int pcc_subspace_idx)
 {
-	struct acpi_pcct_subspace *cppc_ss;
+	struct acpi_pcct_hw_reduced *cppc_ss;
 	unsigned int len;
 
 	if (pcc_subspace_idx >= 0) {
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index f61a7c8..b420fb4 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -1103,7 +1103,7 @@
 	}
 
 err_exit:
-	if (result && q)
+	if (result)
 		acpi_ec_delete_query(q);
 	if (data)
 		*data = value;
diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c
index f7dab53..e7ed39b 100644
--- a/drivers/acpi/nfit.c
+++ b/drivers/acpi/nfit.c
@@ -233,11 +233,12 @@
 		struct nfit_table_prev *prev,
 		struct acpi_nfit_system_address *spa)
 {
+	size_t length = min_t(size_t, sizeof(*spa), spa->header.length);
 	struct device *dev = acpi_desc->dev;
 	struct nfit_spa *nfit_spa;
 
 	list_for_each_entry(nfit_spa, &prev->spas, list) {
-		if (memcmp(nfit_spa->spa, spa, sizeof(*spa)) == 0) {
+		if (memcmp(nfit_spa->spa, spa, length) == 0) {
 			list_move_tail(&nfit_spa->list, &acpi_desc->spas);
 			return true;
 		}
@@ -259,11 +260,12 @@
 		struct nfit_table_prev *prev,
 		struct acpi_nfit_memory_map *memdev)
 {
+	size_t length = min_t(size_t, sizeof(*memdev), memdev->header.length);
 	struct device *dev = acpi_desc->dev;
 	struct nfit_memdev *nfit_memdev;
 
 	list_for_each_entry(nfit_memdev, &prev->memdevs, list)
-		if (memcmp(nfit_memdev->memdev, memdev, sizeof(*memdev)) == 0) {
+		if (memcmp(nfit_memdev->memdev, memdev, length) == 0) {
 			list_move_tail(&nfit_memdev->list, &acpi_desc->memdevs);
 			return true;
 		}
@@ -284,11 +286,12 @@
 		struct nfit_table_prev *prev,
 		struct acpi_nfit_control_region *dcr)
 {
+	size_t length = min_t(size_t, sizeof(*dcr), dcr->header.length);
 	struct device *dev = acpi_desc->dev;
 	struct nfit_dcr *nfit_dcr;
 
 	list_for_each_entry(nfit_dcr, &prev->dcrs, list)
-		if (memcmp(nfit_dcr->dcr, dcr, sizeof(*dcr)) == 0) {
+		if (memcmp(nfit_dcr->dcr, dcr, length) == 0) {
 			list_move_tail(&nfit_dcr->list, &acpi_desc->dcrs);
 			return true;
 		}
@@ -308,11 +311,12 @@
 		struct nfit_table_prev *prev,
 		struct acpi_nfit_data_region *bdw)
 {
+	size_t length = min_t(size_t, sizeof(*bdw), bdw->header.length);
 	struct device *dev = acpi_desc->dev;
 	struct nfit_bdw *nfit_bdw;
 
 	list_for_each_entry(nfit_bdw, &prev->bdws, list)
-		if (memcmp(nfit_bdw->bdw, bdw, sizeof(*bdw)) == 0) {
+		if (memcmp(nfit_bdw->bdw, bdw, length) == 0) {
 			list_move_tail(&nfit_bdw->list, &acpi_desc->bdws);
 			return true;
 		}
@@ -332,11 +336,12 @@
 		struct nfit_table_prev *prev,
 		struct acpi_nfit_interleave *idt)
 {
+	size_t length = min_t(size_t, sizeof(*idt), idt->header.length);
 	struct device *dev = acpi_desc->dev;
 	struct nfit_idt *nfit_idt;
 
 	list_for_each_entry(nfit_idt, &prev->idts, list)
-		if (memcmp(nfit_idt->idt, idt, sizeof(*idt)) == 0) {
+		if (memcmp(nfit_idt->idt, idt, length) == 0) {
 			list_move_tail(&nfit_idt->list, &acpi_desc->idts);
 			return true;
 		}
@@ -356,11 +361,12 @@
 		struct nfit_table_prev *prev,
 		struct acpi_nfit_flush_address *flush)
 {
+	size_t length = min_t(size_t, sizeof(*flush), flush->header.length);
 	struct device *dev = acpi_desc->dev;
 	struct nfit_flush *nfit_flush;
 
 	list_for_each_entry(nfit_flush, &prev->flushes, list)
-		if (memcmp(nfit_flush->flush, flush, sizeof(*flush)) == 0) {
+		if (memcmp(nfit_flush->flush, flush, length) == 0) {
 			list_move_tail(&nfit_flush->list, &acpi_desc->flushes);
 			return true;
 		}
@@ -655,7 +661,7 @@
 	struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus);
 	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
 
-	return sprintf(buf, "%d\n", acpi_desc->nfit->header.revision);
+	return sprintf(buf, "%d\n", acpi_desc->acpi_header.revision);
 }
 static DEVICE_ATTR_RO(revision);
 
@@ -1652,7 +1658,6 @@
 
 	data = (u8 *) acpi_desc->nfit;
 	end = data + sz;
-	data += sizeof(struct acpi_table_nfit);
 	while (!IS_ERR_OR_NULL(data))
 		data = add_table(acpi_desc, &prev, data, end);
 
@@ -1748,13 +1753,29 @@
 		return PTR_ERR(acpi_desc);
 	}
 
-	acpi_desc->nfit = (struct acpi_table_nfit *) tbl;
+	/*
+	 * Save the acpi header for later and then skip it,
+	 * making nfit point to the first nfit table header.
+	 */
+	acpi_desc->acpi_header = *tbl;
+	acpi_desc->nfit = (void *) tbl + sizeof(struct acpi_table_nfit);
+	sz -= sizeof(struct acpi_table_nfit);
 
 	/* Evaluate _FIT and override with that if present */
 	status = acpi_evaluate_object(adev->handle, "_FIT", NULL, &buf);
 	if (ACPI_SUCCESS(status) && buf.length > 0) {
-		acpi_desc->nfit = (struct acpi_table_nfit *)buf.pointer;
-		sz = buf.length;
+		union acpi_object *obj;
+		/*
+		 * Adjust for the acpi_object header of the _FIT
+		 */
+		obj = buf.pointer;
+		if (obj->type == ACPI_TYPE_BUFFER) {
+			acpi_desc->nfit =
+				(struct acpi_nfit_header *)obj->buffer.pointer;
+			sz = obj->buffer.length;
+		} else
+			dev_dbg(dev, "%s invalid type %d, ignoring _FIT\n",
+				 __func__, (int) obj->type);
 	}
 
 	rc = acpi_nfit_init(acpi_desc, sz);
@@ -1777,7 +1798,8 @@
 {
 	struct acpi_nfit_desc *acpi_desc = dev_get_drvdata(&adev->dev);
 	struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER, NULL };
-	struct acpi_table_nfit *nfit_saved;
+	struct acpi_nfit_header *nfit_saved;
+	union acpi_object *obj;
 	struct device *dev = &adev->dev;
 	acpi_status status;
 	int ret;
@@ -1808,12 +1830,19 @@
 	}
 
 	nfit_saved = acpi_desc->nfit;
-	acpi_desc->nfit = (struct acpi_table_nfit *)buf.pointer;
-	ret = acpi_nfit_init(acpi_desc, buf.length);
-	if (!ret) {
-		/* Merge failed, restore old nfit, and exit */
-		acpi_desc->nfit = nfit_saved;
-		dev_err(dev, "failed to merge updated NFIT\n");
+	obj = buf.pointer;
+	if (obj->type == ACPI_TYPE_BUFFER) {
+		acpi_desc->nfit =
+			(struct acpi_nfit_header *)obj->buffer.pointer;
+		ret = acpi_nfit_init(acpi_desc, obj->buffer.length);
+		if (ret) {
+			/* Merge failed, restore old nfit, and exit */
+			acpi_desc->nfit = nfit_saved;
+			dev_err(dev, "failed to merge updated NFIT\n");
+		}
+	} else {
+		/* Bad _FIT, restore old nfit */
+		dev_err(dev, "Invalid _FIT\n");
 	}
 	kfree(buf.pointer);
 
diff --git a/drivers/acpi/nfit.h b/drivers/acpi/nfit.h
index 2ea5c07..3d549a3 100644
--- a/drivers/acpi/nfit.h
+++ b/drivers/acpi/nfit.h
@@ -96,7 +96,8 @@
 
 struct acpi_nfit_desc {
 	struct nvdimm_bus_descriptor nd_desc;
-	struct acpi_table_nfit *nfit;
+	struct acpi_table_header acpi_header;
+	struct acpi_nfit_header *nfit;
 	struct mutex spa_map_mutex;
 	struct mutex init_mutex;
 	struct list_head spa_maps;
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index 850d7bf..ae3fe4e 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -768,6 +768,13 @@
 		else
 			continue;
 
+		/*
+		 * Some legacy x86 host bridge drivers use iomem_resource and
+		 * ioport_resource as default resource pool, skip it.
+		 */
+		if (res == root)
+			continue;
+
 		conflict = insert_resource_conflict(root, res);
 		if (conflict) {
 			dev_info(&info->bridge->dev,
diff --git a/drivers/acpi/sbshc.c b/drivers/acpi/sbshc.c
index bf034f8..2fa8304 100644
--- a/drivers/acpi/sbshc.c
+++ b/drivers/acpi/sbshc.c
@@ -14,7 +14,6 @@
 #include <linux/delay.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
-#include <linux/dmi.h>
 #include "sbshc.h"
 
 #define PREFIX "ACPI: "
@@ -30,6 +29,7 @@
 	u8 query_bit;
 	smbus_alarm_callback callback;
 	void *context;
+	bool done;
 };
 
 static int acpi_smbus_hc_add(struct acpi_device *device);
@@ -88,8 +88,6 @@
 	ACPI_SMB_ALARM_DATA = 0x26,	/* 2 bytes alarm data */
 };
 
-static bool macbook;
-
 static inline int smb_hc_read(struct acpi_smb_hc *hc, u8 address, u8 *data)
 {
 	return ec_read(hc->offset + address, data);
@@ -100,27 +98,11 @@
 	return ec_write(hc->offset + address, data);
 }
 
-static inline int smb_check_done(struct acpi_smb_hc *hc)
-{
-	union acpi_smb_status status = {.raw = 0};
-	smb_hc_read(hc, ACPI_SMB_STATUS, &status.raw);
-	return status.fields.done && (status.fields.status == SMBUS_OK);
-}
-
 static int wait_transaction_complete(struct acpi_smb_hc *hc, int timeout)
 {
-	if (wait_event_timeout(hc->wait, smb_check_done(hc),
-			       msecs_to_jiffies(timeout)))
+	if (wait_event_timeout(hc->wait, hc->done, msecs_to_jiffies(timeout)))
 		return 0;
-	/*
-	 * After the timeout happens, OS will try to check the status of SMbus.
-	 * If the status is what OS expected, it will be regarded as the bogus
-	 * timeout.
-	 */
-	if (smb_check_done(hc))
-		return 0;
-	else
-		return -ETIME;
+	return -ETIME;
 }
 
 static int acpi_smbus_transaction(struct acpi_smb_hc *hc, u8 protocol,
@@ -135,8 +117,7 @@
 	}
 
 	mutex_lock(&hc->lock);
-	if (macbook)
-		udelay(5);
+	hc->done = false;
 	if (smb_hc_read(hc, ACPI_SMB_PROTOCOL, &temp))
 		goto end;
 	if (temp) {
@@ -235,8 +216,10 @@
 	if (smb_hc_read(hc, ACPI_SMB_STATUS, &status.raw))
 		return 0;
 	/* Check if it is only a completion notify */
-	if (status.fields.done)
+	if (status.fields.done && status.fields.status == SMBUS_OK) {
+		hc->done = true;
 		wake_up(&hc->wait);
+	}
 	if (!status.fields.alarm)
 		return 0;
 	mutex_lock(&hc->lock);
@@ -262,29 +245,12 @@
 			      acpi_handle handle, acpi_ec_query_func func,
 			      void *data);
 
-static int macbook_dmi_match(const struct dmi_system_id *d)
-{
-	pr_debug("Detected MacBook, enabling workaround\n");
-	macbook = true;
-	return 0;
-}
-
-static struct dmi_system_id acpi_smbus_dmi_table[] = {
-	{ macbook_dmi_match, "Apple MacBook", {
-	  DMI_MATCH(DMI_BOARD_VENDOR, "Apple"),
-	  DMI_MATCH(DMI_PRODUCT_NAME, "MacBook") },
-	},
-	{ },
-};
-
 static int acpi_smbus_hc_add(struct acpi_device *device)
 {
 	int status;
 	unsigned long long val;
 	struct acpi_smb_hc *hc;
 
-	dmi_check_system(acpi_smbus_dmi_table);
-
 	if (!device)
 		return -EINVAL;
 
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index ff02bb4..cdfbcc5 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -314,16 +314,6 @@
 	{ PCI_VDEVICE(INTEL, 0x1f37), board_ahci_avn }, /* Avoton RAID */
 	{ PCI_VDEVICE(INTEL, 0x1f3e), board_ahci_avn }, /* Avoton RAID */
 	{ PCI_VDEVICE(INTEL, 0x1f3f), board_ahci_avn }, /* Avoton RAID */
-	{ PCI_VDEVICE(INTEL, 0xa182), board_ahci }, /* Lewisburg AHCI*/
-	{ PCI_VDEVICE(INTEL, 0xa202), board_ahci }, /* Lewisburg AHCI*/
-	{ PCI_VDEVICE(INTEL, 0xa184), board_ahci }, /* Lewisburg RAID*/
-	{ PCI_VDEVICE(INTEL, 0xa204), board_ahci }, /* Lewisburg RAID*/
-	{ PCI_VDEVICE(INTEL, 0xa186), board_ahci }, /* Lewisburg RAID*/
-	{ PCI_VDEVICE(INTEL, 0xa206), board_ahci }, /* Lewisburg RAID*/
-	{ PCI_VDEVICE(INTEL, 0x2822), board_ahci }, /* Lewisburg RAID*/
-	{ PCI_VDEVICE(INTEL, 0x2826), board_ahci }, /* Lewisburg RAID*/
-	{ PCI_VDEVICE(INTEL, 0xa18e), board_ahci }, /* Lewisburg RAID*/
-	{ PCI_VDEVICE(INTEL, 0xa20e), board_ahci }, /* Lewisburg RAID*/
 	{ PCI_VDEVICE(INTEL, 0x2823), board_ahci }, /* Wellsburg RAID */
 	{ PCI_VDEVICE(INTEL, 0x2827), board_ahci }, /* Wellsburg RAID */
 	{ PCI_VDEVICE(INTEL, 0x8d02), board_ahci }, /* Wellsburg AHCI */
@@ -350,10 +340,22 @@
 	{ PCI_VDEVICE(INTEL, 0x9d03), board_ahci }, /* Sunrise Point-LP AHCI */
 	{ PCI_VDEVICE(INTEL, 0x9d05), board_ahci }, /* Sunrise Point-LP RAID */
 	{ PCI_VDEVICE(INTEL, 0x9d07), board_ahci }, /* Sunrise Point-LP RAID */
+	{ PCI_VDEVICE(INTEL, 0xa102), board_ahci }, /* Sunrise Point-H AHCI */
 	{ PCI_VDEVICE(INTEL, 0xa103), board_ahci }, /* Sunrise Point-H AHCI */
 	{ PCI_VDEVICE(INTEL, 0xa105), board_ahci }, /* Sunrise Point-H RAID */
+	{ PCI_VDEVICE(INTEL, 0xa106), board_ahci }, /* Sunrise Point-H RAID */
 	{ PCI_VDEVICE(INTEL, 0xa107), board_ahci }, /* Sunrise Point-H RAID */
 	{ PCI_VDEVICE(INTEL, 0xa10f), board_ahci }, /* Sunrise Point-H RAID */
+	{ PCI_VDEVICE(INTEL, 0x2822), board_ahci }, /* Lewisburg RAID*/
+	{ PCI_VDEVICE(INTEL, 0x2826), board_ahci }, /* Lewisburg RAID*/
+	{ PCI_VDEVICE(INTEL, 0xa182), board_ahci }, /* Lewisburg AHCI*/
+	{ PCI_VDEVICE(INTEL, 0xa184), board_ahci }, /* Lewisburg RAID*/
+	{ PCI_VDEVICE(INTEL, 0xa186), board_ahci }, /* Lewisburg RAID*/
+	{ PCI_VDEVICE(INTEL, 0xa18e), board_ahci }, /* Lewisburg RAID*/
+	{ PCI_VDEVICE(INTEL, 0xa202), board_ahci }, /* Lewisburg AHCI*/
+	{ PCI_VDEVICE(INTEL, 0xa204), board_ahci }, /* Lewisburg RAID*/
+	{ PCI_VDEVICE(INTEL, 0xa206), board_ahci }, /* Lewisburg RAID*/
+	{ PCI_VDEVICE(INTEL, 0xa20e), board_ahci }, /* Lewisburg RAID*/
 
 	/* JMicron 360/1/3/5/6, match class to avoid IDE function */
 	{ PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID,
diff --git a/drivers/ata/ahci_mvebu.c b/drivers/ata/ahci_mvebu.c
index 8490d37..f7a7fa8 100644
--- a/drivers/ata/ahci_mvebu.c
+++ b/drivers/ata/ahci_mvebu.c
@@ -62,6 +62,7 @@
 	writel(0x80, hpriv->mmio + AHCI_VENDOR_SPECIFIC_0_DATA);
 }
 
+#ifdef CONFIG_PM_SLEEP
 static int ahci_mvebu_suspend(struct platform_device *pdev, pm_message_t state)
 {
 	return ahci_platform_suspend_host(&pdev->dev);
@@ -81,6 +82,10 @@
 
 	return ahci_platform_resume_host(&pdev->dev);
 }
+#else
+#define ahci_mvebu_suspend NULL
+#define ahci_mvebu_resume NULL
+#endif
 
 static const struct ata_port_info ahci_mvebu_port_info = {
 	.flags	   = AHCI_FLAG_COMMON,
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index 096064c..4665512 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -1273,6 +1273,15 @@
 	ata_tf_to_fis(tf, pmp, is_cmd, fis);
 	ahci_fill_cmd_slot(pp, 0, cmd_fis_len | flags | (pmp << 12));
 
+	/* set port value for softreset of Port Multiplier */
+	if (pp->fbs_enabled && pp->fbs_last_dev != pmp) {
+		tmp = readl(port_mmio + PORT_FBS);
+		tmp &= ~(PORT_FBS_DEV_MASK | PORT_FBS_DEC);
+		tmp |= pmp << PORT_FBS_DEV_OFFSET;
+		writel(tmp, port_mmio + PORT_FBS);
+		pp->fbs_last_dev = pmp;
+	}
+
 	/* issue & wait */
 	writel(1, port_mmio + PORT_CMD_ISSUE);
 
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index cb0508a..961acc7 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -1505,12 +1505,20 @@
 unsigned int ata_read_log_page(struct ata_device *dev, u8 log,
 			       u8 page, void *buf, unsigned int sectors)
 {
+	unsigned long ap_flags = dev->link->ap->flags;
 	struct ata_taskfile tf;
 	unsigned int err_mask;
 	bool dma = false;
 
 	DPRINTK("read log page - log 0x%x, page 0x%x\n", log, page);
 
+	/*
+	 * Return error without actually issuing the command on controllers
+	 * which e.g. lockup on a read log page.
+	 */
+	if (ap_flags & ATA_FLAG_NO_LOG_PAGE)
+		return AC_ERR_DEV;
+
 retry:
 	ata_tf_init(dev, &tf);
 	if (dev->dma_mode && ata_id_has_read_log_dma_ext(dev->id) &&
diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c
index 5389579..a723ae9 100644
--- a/drivers/ata/sata_fsl.c
+++ b/drivers/ata/sata_fsl.c
@@ -45,7 +45,8 @@
 	SATA_FSL_MAX_PRD_DIRECT	= 16,	/* Direct PRDT entries */
 
 	SATA_FSL_HOST_FLAGS	= (ATA_FLAG_SATA | ATA_FLAG_PIO_DMA |
-				ATA_FLAG_PMP | ATA_FLAG_NCQ | ATA_FLAG_AN),
+				   ATA_FLAG_PMP | ATA_FLAG_NCQ |
+				   ATA_FLAG_AN | ATA_FLAG_NO_LOG_PAGE),
 
 	SATA_FSL_MAX_CMDS	= SATA_FSL_QUEUE_DEPTH,
 	SATA_FSL_CMD_HDR_SIZE	= 16,	/* 4 DWORDS */
diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c
index dea6edc..29bcff0 100644
--- a/drivers/ata/sata_sil.c
+++ b/drivers/ata/sata_sil.c
@@ -630,6 +630,9 @@
 	unsigned int n, quirks = 0;
 	unsigned char model_num[ATA_ID_PROD_LEN + 1];
 
+	/* This controller doesn't support trim */
+	dev->horkage |= ATA_HORKAGE_NOTRIM;
+
 	ata_id_c_string(dev->id, model_num, ATA_ID_PROD, sizeof(model_num));
 
 	for (n = 0; sil_blacklist[n].product; n++)
diff --git a/drivers/atm/solos-pci.c b/drivers/atm/solos-pci.c
index 3d7fb65..0c2b4ba0 100644
--- a/drivers/atm/solos-pci.c
+++ b/drivers/atm/solos-pci.c
@@ -347,8 +347,8 @@
  */       
 static int process_status(struct solos_card *card, int port, struct sk_buff *skb)
 {
-	char *str, *end, *state_str, *snr, *attn;
-	int ver, rate_up, rate_down;
+	char *str, *state_str, *snr, *attn;
+	int ver, rate_up, rate_down, err;
 
 	if (!card->atmdev[port])
 		return -ENODEV;
@@ -357,7 +357,11 @@
 	if (!str)
 		return -EIO;
 
-	ver = simple_strtol(str, NULL, 10);
+	err = kstrtoint(str, 10, &ver);
+	if (err) {
+		dev_warn(&card->dev->dev, "Unexpected status interrupt version\n");
+		return err;
+	}
 	if (ver < 1) {
 		dev_warn(&card->dev->dev, "Unexpected status interrupt version %d\n",
 			 ver);
@@ -373,16 +377,16 @@
 		return 0;
 	}
 
-	rate_down = simple_strtol(str, &end, 10);
-	if (*end)
-		return -EIO;
+	err = kstrtoint(str, 10, &rate_down);
+	if (err)
+		return err;
 
 	str = next_string(skb);
 	if (!str)
 		return -EIO;
-	rate_up = simple_strtol(str, &end, 10);
-	if (*end)
-		return -EIO;
+	err = kstrtoint(str, 10, &rate_up);
+	if (err)
+		return err;
 
 	state_str = next_string(skb);
 	if (!state_str)
@@ -417,7 +421,7 @@
 	struct solos_param *prm;
 	unsigned long flags;
 	int cmdpid;
-	int found = 0;
+	int found = 0, err;
 
 	if (skb->len < 7)
 		return 0;
@@ -428,7 +432,9 @@
 	    skb->data[6] != '\n')
 		return 0;
 
-	cmdpid = simple_strtol(&skb->data[1], NULL, 10);
+	err = kstrtoint(&skb->data[1], 10, &cmdpid);
+	if (err)
+		return err;
 
 	spin_lock_irqsave(&card->param_queue_lock, flags);
 	list_for_each_entry(prm, &card->param_queue, list) {
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 2804aed..25425d3 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -303,6 +303,10 @@
 	if (mem->state == MEM_OFFLINE)
 		return 0;
 
+	/* Can't offline block with non-present sections */
+	if (mem->section_count != sections_per_block)
+		return -EINVAL;
+
 	return memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE);
 }
 
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index e03b1ad..167418e 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -1775,10 +1775,10 @@
 	}
 
 	pd = of_genpd_get_from_provider(&pd_args);
+	of_node_put(pd_args.np);
 	if (IS_ERR(pd)) {
 		dev_dbg(dev, "%s() failed to find PM domain: %ld\n",
 			__func__, PTR_ERR(pd));
-		of_node_put(dev->of_node);
 		return -EPROBE_DEFER;
 	}
 
@@ -1796,7 +1796,6 @@
 	if (ret < 0) {
 		dev_err(dev, "failed to add to PM domain %s: %d",
 			pd->name, ret);
-		of_node_put(dev->of_node);
 		goto out;
 	}
 
diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c
index e60dd12..1e937ac 100644
--- a/drivers/base/power/domain_governor.c
+++ b/drivers/base/power/domain_governor.c
@@ -160,9 +160,6 @@
 		struct gpd_timing_data *td;
 		s64 constraint_ns;
 
-		if (!pdd->dev->driver)
-			continue;
-
 		/*
 		 * Check if the device is allowed to be off long enough for the
 		 * domain to turn off and on (that's how much time it will
diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c
index eb6e674..0d77cd6 100644
--- a/drivers/base/power/wakeirq.c
+++ b/drivers/base/power/wakeirq.c
@@ -68,6 +68,9 @@
 	struct wake_irq *wirq;
 	int err;
 
+	if (irq < 0)
+		return -EINVAL;
+
 	wirq = kzalloc(sizeof(*wirq), GFP_KERNEL);
 	if (!wirq)
 		return -ENOMEM;
@@ -167,6 +170,9 @@
 	struct wake_irq *wirq;
 	int err;
 
+	if (irq < 0)
+		return -EINVAL;
+
 	wirq = kzalloc(sizeof(*wirq), GFP_KERNEL);
 	if (!wirq)
 		return -ENOMEM;
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index a28a562..3457ac8 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -3810,7 +3810,6 @@
 	sector_t capacity;
 	unsigned int index = 0;
 	struct kobject *kobj;
-	unsigned char thd_name[16];
 
 	if (dd->disk)
 		goto skip_create_disk; /* hw init done, before rebuild */
@@ -3958,10 +3957,9 @@
 	}
 
 start_service_thread:
-	sprintf(thd_name, "mtip_svc_thd_%02d", index);
 	dd->mtip_svc_handler = kthread_create_on_node(mtip_service_thread,
-						dd, dd->numa_node, "%s",
-						thd_name);
+						dd, dd->numa_node,
+						"mtip_svc_thd_%02d", index);
 
 	if (IS_ERR(dd->mtip_svc_handler)) {
 		dev_err(&dd->pdev->dev, "service thread failed to start\n");
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 6255d1c..8162475 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -8,6 +8,7 @@
 #include <linux/slab.h>
 #include <linux/blk-mq.h>
 #include <linux/hrtimer.h>
+#include <linux/lightnvm.h>
 
 struct nullb_cmd {
 	struct list_head list;
@@ -17,6 +18,7 @@
 	struct bio *bio;
 	unsigned int tag;
 	struct nullb_queue *nq;
+	struct hrtimer timer;
 };
 
 struct nullb_queue {
@@ -39,23 +41,14 @@
 
 	struct nullb_queue *queues;
 	unsigned int nr_queues;
+	char disk_name[DISK_NAME_LEN];
 };
 
 static LIST_HEAD(nullb_list);
 static struct mutex lock;
 static int null_major;
 static int nullb_indexes;
-
-struct completion_queue {
-	struct llist_head list;
-	struct hrtimer timer;
-};
-
-/*
- * These are per-cpu for now, they will need to be configured by the
- * complete_queues parameter and appropriately mapped.
- */
-static DEFINE_PER_CPU(struct completion_queue, completion_queues);
+static struct kmem_cache *ppa_cache;
 
 enum {
 	NULL_IRQ_NONE		= 0,
@@ -119,6 +112,10 @@
 module_param(nr_devices, int, S_IRUGO);
 MODULE_PARM_DESC(nr_devices, "Number of devices to register");
 
+static bool use_lightnvm;
+module_param(use_lightnvm, bool, S_IRUGO);
+MODULE_PARM_DESC(use_lightnvm, "Register as a LightNVM device");
+
 static int irqmode = NULL_IRQ_SOFTIRQ;
 
 static int null_set_irqmode(const char *str, const struct kernel_param *kp)
@@ -135,8 +132,8 @@
 device_param_cb(irqmode, &null_irqmode_param_ops, &irqmode, S_IRUGO);
 MODULE_PARM_DESC(irqmode, "IRQ completion handler. 0-none, 1-softirq, 2-timer");
 
-static int completion_nsec = 10000;
-module_param(completion_nsec, int, S_IRUGO);
+static unsigned long completion_nsec = 10000;
+module_param(completion_nsec, ulong, S_IRUGO);
 MODULE_PARM_DESC(completion_nsec, "Time in ns to complete a request in hardware. Default: 10,000ns");
 
 static int hw_queue_depth = 64;
@@ -173,6 +170,8 @@
 	put_tag(cmd->nq, cmd->tag);
 }
 
+static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer);
+
 static struct nullb_cmd *__alloc_cmd(struct nullb_queue *nq)
 {
 	struct nullb_cmd *cmd;
@@ -183,6 +182,11 @@
 		cmd = &nq->cmds[tag];
 		cmd->tag = tag;
 		cmd->nq = nq;
+		if (irqmode == NULL_IRQ_TIMER) {
+			hrtimer_init(&cmd->timer, CLOCK_MONOTONIC,
+				     HRTIMER_MODE_REL);
+			cmd->timer.function = null_cmd_timer_expired;
+		}
 		return cmd;
 	}
 
@@ -213,6 +217,8 @@
 
 static void end_cmd(struct nullb_cmd *cmd)
 {
+	struct request_queue *q = NULL;
+
 	switch (queue_mode)  {
 	case NULL_Q_MQ:
 		blk_mq_end_request(cmd->rq, 0);
@@ -223,55 +229,37 @@
 		break;
 	case NULL_Q_BIO:
 		bio_endio(cmd->bio);
-		break;
+		goto free_cmd;
 	}
 
+	if (cmd->rq)
+		q = cmd->rq->q;
+
+	/* Restart queue if needed, as we are freeing a tag */
+	if (q && !q->mq_ops && blk_queue_stopped(q)) {
+		unsigned long flags;
+
+		spin_lock_irqsave(q->queue_lock, flags);
+		if (blk_queue_stopped(q))
+			blk_start_queue(q);
+		spin_unlock_irqrestore(q->queue_lock, flags);
+	}
+free_cmd:
 	free_cmd(cmd);
 }
 
 static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer)
 {
-	struct completion_queue *cq;
-	struct llist_node *entry;
-	struct nullb_cmd *cmd;
-
-	cq = &per_cpu(completion_queues, smp_processor_id());
-
-	while ((entry = llist_del_all(&cq->list)) != NULL) {
-		entry = llist_reverse_order(entry);
-		do {
-			struct request_queue *q = NULL;
-
-			cmd = container_of(entry, struct nullb_cmd, ll_list);
-			entry = entry->next;
-			if (cmd->rq)
-				q = cmd->rq->q;
-			end_cmd(cmd);
-
-			if (q && !q->mq_ops && blk_queue_stopped(q)) {
-				spin_lock(q->queue_lock);
-				if (blk_queue_stopped(q))
-					blk_start_queue(q);
-				spin_unlock(q->queue_lock);
-			}
-		} while (entry);
-	}
+	end_cmd(container_of(timer, struct nullb_cmd, timer));
 
 	return HRTIMER_NORESTART;
 }
 
 static void null_cmd_end_timer(struct nullb_cmd *cmd)
 {
-	struct completion_queue *cq = &per_cpu(completion_queues, get_cpu());
+	ktime_t kt = ktime_set(0, completion_nsec);
 
-	cmd->ll_list.next = NULL;
-	if (llist_add(&cmd->ll_list, &cq->list)) {
-		ktime_t kt = ktime_set(0, completion_nsec);
-
-		hrtimer_start(&cq->timer, kt, HRTIMER_MODE_REL_PINNED);
-	}
-
-	put_cpu();
+	hrtimer_start(&cmd->timer, kt, HRTIMER_MODE_REL);
 }
 
 static void null_softirq_done_fn(struct request *rq)
@@ -369,6 +357,10 @@
 {
 	struct nullb_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
 
+	if (irqmode == NULL_IRQ_TIMER) {
+		hrtimer_init(&cmd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+		cmd->timer.function = null_cmd_timer_expired;
+	}
 	cmd->rq = bd->rq;
 	cmd->nq = hctx->driver_data;
 
@@ -427,15 +419,157 @@
 {
 	list_del_init(&nullb->list);
 
-	del_gendisk(nullb->disk);
+	if (use_lightnvm)
+		nvm_unregister(nullb->disk_name);
+	else
+		del_gendisk(nullb->disk);
 	blk_cleanup_queue(nullb->q);
 	if (queue_mode == NULL_Q_MQ)
 		blk_mq_free_tag_set(&nullb->tag_set);
-	put_disk(nullb->disk);
+	if (!use_lightnvm)
+		put_disk(nullb->disk);
 	cleanup_queues(nullb);
 	kfree(nullb);
 }
 
+#ifdef CONFIG_NVM
+
+static void null_lnvm_end_io(struct request *rq, int error)
+{
+	struct nvm_rq *rqd = rq->end_io_data;
+	struct nvm_dev *dev = rqd->dev;
+
+	dev->mt->end_io(rqd, error);
+
+	blk_put_request(rq);
+}
+
+static int null_lnvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd)
+{
+	struct request_queue *q = dev->q;
+	struct request *rq;
+	struct bio *bio = rqd->bio;
+
+	rq = blk_mq_alloc_request(q, bio_rw(bio), GFP_KERNEL, 0);
+	if (IS_ERR(rq))
+		return -ENOMEM;
+
+	rq->cmd_type = REQ_TYPE_DRV_PRIV;
+	rq->__sector = bio->bi_iter.bi_sector;
+	rq->ioprio = bio_prio(bio);
+
+	if (bio_has_data(bio))
+		rq->nr_phys_segments = bio_phys_segments(q, bio);
+
+	rq->__data_len = bio->bi_iter.bi_size;
+	rq->bio = rq->biotail = bio;
+
+	rq->end_io_data = rqd;
+
+	blk_execute_rq_nowait(q, NULL, rq, 0, null_lnvm_end_io);
+
+	return 0;
+}
+
+static int null_lnvm_id(struct nvm_dev *dev, struct nvm_id *id)
+{
+	sector_t size = gb * 1024 * 1024 * 1024ULL;
+	sector_t blksize;
+	struct nvm_id_group *grp;
+
+	id->ver_id = 0x1;
+	id->vmnt = 0;
+	id->cgrps = 1;
+	id->cap = 0x3;
+	id->dom = 0x1;
+
+	id->ppaf.blk_offset = 0;
+	id->ppaf.blk_len = 16;
+	id->ppaf.pg_offset = 16;
+	id->ppaf.pg_len = 16;
+	id->ppaf.sect_offset = 32;
+	id->ppaf.sect_len = 8;
+	id->ppaf.pln_offset = 40;
+	id->ppaf.pln_len = 8;
+	id->ppaf.lun_offset = 48;
+	id->ppaf.lun_len = 8;
+	id->ppaf.ch_offset = 56;
+	id->ppaf.ch_len = 8;
+
+	do_div(size, bs); /* convert size to pages */
+	do_div(size, 256); /* concert size to pgs pr blk */
+	grp = &id->groups[0];
+	grp->mtype = 0;
+	grp->fmtype = 0;
+	grp->num_ch = 1;
+	grp->num_pg = 256;
+	blksize = size;
+	do_div(size, (1 << 16));
+	grp->num_lun = size + 1;
+	do_div(blksize, grp->num_lun);
+	grp->num_blk = blksize;
+	grp->num_pln = 1;
+
+	grp->fpg_sz = bs;
+	grp->csecs = bs;
+	grp->trdt = 25000;
+	grp->trdm = 25000;
+	grp->tprt = 500000;
+	grp->tprm = 500000;
+	grp->tbet = 1500000;
+	grp->tbem = 1500000;
+	grp->mpos = 0x010101; /* single plane rwe */
+	grp->cpar = hw_queue_depth;
+
+	return 0;
+}
+
+static void *null_lnvm_create_dma_pool(struct nvm_dev *dev, char *name)
+{
+	mempool_t *virtmem_pool;
+
+	virtmem_pool = mempool_create_slab_pool(64, ppa_cache);
+	if (!virtmem_pool) {
+		pr_err("null_blk: Unable to create virtual memory pool\n");
+		return NULL;
+	}
+
+	return virtmem_pool;
+}
+
+static void null_lnvm_destroy_dma_pool(void *pool)
+{
+	mempool_destroy(pool);
+}
+
+static void *null_lnvm_dev_dma_alloc(struct nvm_dev *dev, void *pool,
+				gfp_t mem_flags, dma_addr_t *dma_handler)
+{
+	return mempool_alloc(pool, mem_flags);
+}
+
+static void null_lnvm_dev_dma_free(void *pool, void *entry,
+							dma_addr_t dma_handler)
+{
+	mempool_free(entry, pool);
+}
+
+static struct nvm_dev_ops null_lnvm_dev_ops = {
+	.identity		= null_lnvm_id,
+	.submit_io		= null_lnvm_submit_io,
+
+	.create_dma_pool	= null_lnvm_create_dma_pool,
+	.destroy_dma_pool	= null_lnvm_destroy_dma_pool,
+	.dev_dma_alloc		= null_lnvm_dev_dma_alloc,
+	.dev_dma_free		= null_lnvm_dev_dma_free,
+
+	/* Simulate nvme protocol restriction */
+	.max_phys_sect		= 64,
+};
+#else
+static struct nvm_dev_ops null_lnvm_dev_ops;
+#endif /* CONFIG_NVM */
+
 static int null_open(struct block_device *bdev, fmode_t mode)
 {
 	return 0;
@@ -575,11 +709,6 @@
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, nullb->q);
 	queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, nullb->q);
 
-	disk = nullb->disk = alloc_disk_node(1, home_node);
-	if (!disk) {
-		rv = -ENOMEM;
-		goto out_cleanup_blk_queue;
-	}
 
 	mutex_lock(&lock);
 	list_add_tail(&nullb->list, &nullb_list);
@@ -589,6 +718,21 @@
 	blk_queue_logical_block_size(nullb->q, bs);
 	blk_queue_physical_block_size(nullb->q, bs);
 
+	sprintf(nullb->disk_name, "nullb%d", nullb->index);
+
+	if (use_lightnvm) {
+		rv = nvm_register(nullb->q, nullb->disk_name,
+							&null_lnvm_dev_ops);
+		if (rv)
+			goto out_cleanup_blk_queue;
+		goto done;
+	}
+
+	disk = nullb->disk = alloc_disk_node(1, home_node);
+	if (!disk) {
+		rv = -ENOMEM;
+		goto out_cleanup_lightnvm;
+	}
 	size = gb * 1024 * 1024 * 1024ULL;
 	set_capacity(disk, size >> 9);
 
@@ -598,10 +742,15 @@
 	disk->fops		= &null_fops;
 	disk->private_data	= nullb;
 	disk->queue		= nullb->q;
-	sprintf(disk->disk_name, "nullb%d", nullb->index);
+	strncpy(disk->disk_name, nullb->disk_name, DISK_NAME_LEN);
+
 	add_disk(disk);
+done:
 	return 0;
 
+out_cleanup_lightnvm:
+	if (use_lightnvm)
+		nvm_unregister(nullb->disk_name);
 out_cleanup_blk_queue:
 	blk_cleanup_queue(nullb->q);
 out_cleanup_tags:
@@ -617,7 +766,9 @@
 
 static int __init null_init(void)
 {
+	int ret = 0;
 	unsigned int i;
+	struct nullb *nullb;
 
 	if (bs > PAGE_SIZE) {
 		pr_warn("null_blk: invalid block size\n");
@@ -625,6 +776,18 @@
 		bs = PAGE_SIZE;
 	}
 
+	if (use_lightnvm && bs != 4096) {
+		pr_warn("null_blk: LightNVM only supports 4k block size\n");
+		pr_warn("null_blk: defaults block size to 4k\n");
+		bs = 4096;
+	}
+
+	if (use_lightnvm && queue_mode != NULL_Q_MQ) {
+		pr_warn("null_blk: LightNVM only supported for blk-mq\n");
+		pr_warn("null_blk: defaults queue mode to blk-mq\n");
+		queue_mode = NULL_Q_MQ;
+	}
+
 	if (queue_mode == NULL_Q_MQ && use_per_node_hctx) {
 		if (submit_queues < nr_online_nodes) {
 			pr_warn("null_blk: submit_queues param is set to %u.",
@@ -638,32 +801,38 @@
 
 	mutex_init(&lock);
 
-	/* Initialize a separate list for each CPU for issuing softirqs */
-	for_each_possible_cpu(i) {
-		struct completion_queue *cq = &per_cpu(completion_queues, i);
-
-		init_llist_head(&cq->list);
-
-		if (irqmode != NULL_IRQ_TIMER)
-			continue;
-
-		hrtimer_init(&cq->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-		cq->timer.function = null_cmd_timer_expired;
-	}
-
 	null_major = register_blkdev(0, "nullb");
 	if (null_major < 0)
 		return null_major;
 
-	for (i = 0; i < nr_devices; i++) {
-		if (null_add_dev()) {
-			unregister_blkdev(null_major, "nullb");
-			return -EINVAL;
+	if (use_lightnvm) {
+		ppa_cache = kmem_cache_create("ppa_cache", 64 * sizeof(u64),
+								0, 0, NULL);
+		if (!ppa_cache) {
+			pr_err("null_blk: unable to create ppa cache\n");
+			ret = -ENOMEM;
+			goto err_ppa;
 		}
 	}
 
+	for (i = 0; i < nr_devices; i++) {
+		ret = null_add_dev();
+		if (ret)
+			goto err_dev;
+	}
+
 	pr_info("null: module loaded\n");
 	return 0;
+
+err_dev:
+	while (!list_empty(&nullb_list)) {
+		nullb = list_entry(nullb_list.next, struct nullb, list);
+		null_del_dev(nullb);
+	}
+	kmem_cache_destroy(ppa_cache);
+err_ppa:
+	unregister_blkdev(null_major, "nullb");
+	return ret;
 }
 
 static void __exit null_exit(void)
@@ -678,6 +847,8 @@
 		null_del_dev(nullb);
 	}
 	mutex_unlock(&lock);
+
+	kmem_cache_destroy(ppa_cache);
 }
 
 module_init(null_init);
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 235708c..81ea69f 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -3442,6 +3442,7 @@
 		goto err_rq;
 	}
 	img_request->rq = rq;
+	snapc = NULL; /* img_request consumes a ref */
 
 	if (op_type == OBJ_OP_DISCARD)
 		result = rbd_img_request_fill(img_request, OBJ_REQUEST_NODATA,
diff --git a/drivers/bus/omap-ocp2scp.c b/drivers/bus/omap-ocp2scp.c
index 9f18569..bf500e0 100644
--- a/drivers/bus/omap-ocp2scp.c
+++ b/drivers/bus/omap-ocp2scp.c
@@ -117,7 +117,7 @@
 
 module_platform_driver(omap_ocp2scp_driver);
 
-MODULE_ALIAS("platform: omap-ocp2scp");
+MODULE_ALIAS("platform:omap-ocp2scp");
 MODULE_AUTHOR("Texas Instruments Inc.");
 MODULE_DESCRIPTION("OMAP OCP2SCP driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index 654f6f3..4cc72fa 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -412,18 +412,42 @@
 	return rv;
 }
 
-static void start_check_enables(struct smi_info *smi_info)
+static void smi_mod_timer(struct smi_info *smi_info, unsigned long new_val)
+{
+	smi_info->last_timeout_jiffies = jiffies;
+	mod_timer(&smi_info->si_timer, new_val);
+	smi_info->timer_running = true;
+}
+
+/*
+ * Start a new message and (re)start the timer and thread.
+ */
+static void start_new_msg(struct smi_info *smi_info, unsigned char *msg,
+			  unsigned int size)
+{
+	smi_mod_timer(smi_info, jiffies + SI_TIMEOUT_JIFFIES);
+
+	if (smi_info->thread)
+		wake_up_process(smi_info->thread);
+
+	smi_info->handlers->start_transaction(smi_info->si_sm, msg, size);
+}
+
+static void start_check_enables(struct smi_info *smi_info, bool start_timer)
 {
 	unsigned char msg[2];
 
 	msg[0] = (IPMI_NETFN_APP_REQUEST << 2);
 	msg[1] = IPMI_GET_BMC_GLOBAL_ENABLES_CMD;
 
-	smi_info->handlers->start_transaction(smi_info->si_sm, msg, 2);
+	if (start_timer)
+		start_new_msg(smi_info, msg, 2);
+	else
+		smi_info->handlers->start_transaction(smi_info->si_sm, msg, 2);
 	smi_info->si_state = SI_CHECKING_ENABLES;
 }
 
-static void start_clear_flags(struct smi_info *smi_info)
+static void start_clear_flags(struct smi_info *smi_info, bool start_timer)
 {
 	unsigned char msg[3];
 
@@ -432,7 +456,10 @@
 	msg[1] = IPMI_CLEAR_MSG_FLAGS_CMD;
 	msg[2] = WDT_PRE_TIMEOUT_INT;
 
-	smi_info->handlers->start_transaction(smi_info->si_sm, msg, 3);
+	if (start_timer)
+		start_new_msg(smi_info, msg, 3);
+	else
+		smi_info->handlers->start_transaction(smi_info->si_sm, msg, 3);
 	smi_info->si_state = SI_CLEARING_FLAGS;
 }
 
@@ -442,10 +469,8 @@
 	smi_info->curr_msg->data[1] = IPMI_GET_MSG_CMD;
 	smi_info->curr_msg->data_size = 2;
 
-	smi_info->handlers->start_transaction(
-		smi_info->si_sm,
-		smi_info->curr_msg->data,
-		smi_info->curr_msg->data_size);
+	start_new_msg(smi_info, smi_info->curr_msg->data,
+		      smi_info->curr_msg->data_size);
 	smi_info->si_state = SI_GETTING_MESSAGES;
 }
 
@@ -455,20 +480,11 @@
 	smi_info->curr_msg->data[1] = IPMI_READ_EVENT_MSG_BUFFER_CMD;
 	smi_info->curr_msg->data_size = 2;
 
-	smi_info->handlers->start_transaction(
-		smi_info->si_sm,
-		smi_info->curr_msg->data,
-		smi_info->curr_msg->data_size);
+	start_new_msg(smi_info, smi_info->curr_msg->data,
+		      smi_info->curr_msg->data_size);
 	smi_info->si_state = SI_GETTING_EVENTS;
 }
 
-static void smi_mod_timer(struct smi_info *smi_info, unsigned long new_val)
-{
-	smi_info->last_timeout_jiffies = jiffies;
-	mod_timer(&smi_info->si_timer, new_val);
-	smi_info->timer_running = true;
-}
-
 /*
  * When we have a situtaion where we run out of memory and cannot
  * allocate messages, we just leave them in the BMC and run the system
@@ -478,11 +494,11 @@
  * Note that we cannot just use disable_irq(), since the interrupt may
  * be shared.
  */
-static inline bool disable_si_irq(struct smi_info *smi_info)
+static inline bool disable_si_irq(struct smi_info *smi_info, bool start_timer)
 {
 	if ((smi_info->irq) && (!smi_info->interrupt_disabled)) {
 		smi_info->interrupt_disabled = true;
-		start_check_enables(smi_info);
+		start_check_enables(smi_info, start_timer);
 		return true;
 	}
 	return false;
@@ -492,7 +508,7 @@
 {
 	if ((smi_info->irq) && (smi_info->interrupt_disabled)) {
 		smi_info->interrupt_disabled = false;
-		start_check_enables(smi_info);
+		start_check_enables(smi_info, true);
 		return true;
 	}
 	return false;
@@ -510,7 +526,7 @@
 
 	msg = ipmi_alloc_smi_msg();
 	if (!msg) {
-		if (!disable_si_irq(smi_info))
+		if (!disable_si_irq(smi_info, true))
 			smi_info->si_state = SI_NORMAL;
 	} else if (enable_si_irq(smi_info)) {
 		ipmi_free_smi_msg(msg);
@@ -526,7 +542,7 @@
 		/* Watchdog pre-timeout */
 		smi_inc_stat(smi_info, watchdog_pretimeouts);
 
-		start_clear_flags(smi_info);
+		start_clear_flags(smi_info, true);
 		smi_info->msg_flags &= ~WDT_PRE_TIMEOUT_INT;
 		if (smi_info->intf)
 			ipmi_smi_watchdog_pretimeout(smi_info->intf);
@@ -879,8 +895,7 @@
 			msg[0] = (IPMI_NETFN_APP_REQUEST << 2);
 			msg[1] = IPMI_GET_MSG_FLAGS_CMD;
 
-			smi_info->handlers->start_transaction(
-				smi_info->si_sm, msg, 2);
+			start_new_msg(smi_info, msg, 2);
 			smi_info->si_state = SI_GETTING_FLAGS;
 			goto restart;
 		}
@@ -910,7 +925,7 @@
 		 * disable and messages disabled.
 		 */
 		if (smi_info->supports_event_msg_buff || smi_info->irq) {
-			start_check_enables(smi_info);
+			start_check_enables(smi_info, true);
 		} else {
 			smi_info->curr_msg = alloc_msg_handle_irq(smi_info);
 			if (!smi_info->curr_msg)
@@ -920,6 +935,13 @@
 		}
 		goto restart;
 	}
+
+	if (si_sm_result == SI_SM_IDLE && smi_info->timer_running) {
+		/* Ok it if fails, the timer will just go off. */
+		if (del_timer(&smi_info->si_timer))
+			smi_info->timer_running = false;
+	}
+
  out:
 	return si_sm_result;
 }
@@ -1208,14 +1230,14 @@
 
 	new_smi->intf = intf;
 
-	/* Try to claim any interrupts. */
-	if (new_smi->irq_setup)
-		new_smi->irq_setup(new_smi);
-
 	/* Set up the timer that drives the interface. */
 	setup_timer(&new_smi->si_timer, smi_timeout, (long)new_smi);
 	smi_mod_timer(new_smi, jiffies + SI_TIMEOUT_JIFFIES);
 
+	/* Try to claim any interrupts. */
+	if (new_smi->irq_setup)
+		new_smi->irq_setup(new_smi);
+
 	/*
 	 * Check if the user forcefully enabled the daemon.
 	 */
@@ -2560,6 +2582,7 @@
 	  .data = (void *)(unsigned long) SI_BT },
 	{},
 };
+MODULE_DEVICE_TABLE(of, of_ipmi_match);
 
 static int of_ipmi_probe(struct platform_device *dev)
 {
@@ -2646,7 +2669,6 @@
 	}
 	return 0;
 }
-MODULE_DEVICE_TABLE(of, of_ipmi_match);
 #else
 #define of_ipmi_match NULL
 static int of_ipmi_probe(struct platform_device *dev)
@@ -3613,7 +3635,7 @@
 	 * Start clearing the flags before we enable interrupts or the
 	 * timer to avoid racing with the timer.
 	 */
-	start_clear_flags(new_smi);
+	start_clear_flags(new_smi, false);
 
 	/*
 	 * IRQ is defined to be set when non-zero.  req_events will
@@ -3908,7 +3930,7 @@
 		poll(to_clean);
 		schedule_timeout_uninterruptible(1);
 	}
-	disable_si_irq(to_clean);
+	disable_si_irq(to_clean, false);
 	while (to_clean->curr_msg || (to_clean->si_state != SI_NORMAL)) {
 		poll(to_clean);
 		schedule_timeout_uninterruptible(1);
diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c
index 0ac3bd1..096f0ce 100644
--- a/drivers/char/ipmi/ipmi_watchdog.c
+++ b/drivers/char/ipmi/ipmi_watchdog.c
@@ -153,6 +153,9 @@
 /* The pre-timeout is disabled by default. */
 static int pretimeout;
 
+/* Default timeout to set on panic */
+static int panic_wdt_timeout = 255;
+
 /* Default action is to reset the board on a timeout. */
 static unsigned char action_val = WDOG_TIMEOUT_RESET;
 
@@ -293,6 +296,9 @@
 module_param(pretimeout, timeout, 0644);
 MODULE_PARM_DESC(pretimeout, "Pretimeout value in seconds.");
 
+module_param(panic_wdt_timeout, timeout, 0644);
+MODULE_PARM_DESC(timeout, "Timeout value on kernel panic in seconds.");
+
 module_param_cb(action, &param_ops_str, action_op, 0644);
 MODULE_PARM_DESC(action, "Timeout action. One of: "
 		 "reset, none, power_cycle, power_off.");
@@ -1189,7 +1195,7 @@
 		/* Make sure we do this only once. */
 		panic_event_handled = 1;
 
-		timeout = 255;
+		timeout = panic_wdt_timeout;
 		pretimeout = 0;
 		panic_halt_ipmi_set_timeout();
 	}
diff --git a/drivers/clk/clk-gpio.c b/drivers/clk/clk-gpio.c
index 10819e2..335322d 100644
--- a/drivers/clk/clk-gpio.c
+++ b/drivers/clk/clk-gpio.c
@@ -209,6 +209,8 @@
 
 struct clk_gpio_delayed_register_data {
 	const char *gpio_name;
+	int num_parents;
+	const char **parent_names;
 	struct device_node *node;
 	struct mutex lock;
 	struct clk *clk;
@@ -222,8 +224,6 @@
 {
 	struct clk_gpio_delayed_register_data *data = _data;
 	struct clk *clk;
-	const char **parent_names;
-	int i, num_parents;
 	int gpio;
 	enum of_gpio_flags of_flags;
 
@@ -248,26 +248,14 @@
 		return ERR_PTR(gpio);
 	}
 
-	num_parents = of_clk_get_parent_count(data->node);
-
-	parent_names = kcalloc(num_parents, sizeof(char *), GFP_KERNEL);
-	if (!parent_names) {
-		clk = ERR_PTR(-ENOMEM);
-		goto out;
-	}
-
-	for (i = 0; i < num_parents; i++)
-		parent_names[i] = of_clk_get_parent_name(data->node, i);
-
-	clk = data->clk_register_get(data->node->name, parent_names,
-			num_parents, gpio, of_flags & OF_GPIO_ACTIVE_LOW);
+	clk = data->clk_register_get(data->node->name, data->parent_names,
+			data->num_parents, gpio, of_flags & OF_GPIO_ACTIVE_LOW);
 	if (IS_ERR(clk))
 		goto out;
 
 	data->clk = clk;
 out:
 	mutex_unlock(&data->lock);
-	kfree(parent_names);
 
 	return clk;
 }
@@ -296,11 +284,24 @@
 				unsigned gpio, bool active_low))
 {
 	struct clk_gpio_delayed_register_data *data;
+	const char **parent_names;
+	int i, num_parents;
 
 	data = kzalloc(sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return;
 
+	num_parents = of_clk_get_parent_count(node);
+
+	parent_names = kcalloc(num_parents, sizeof(char *), GFP_KERNEL);
+	if (!parent_names)
+		return;
+
+	for (i = 0; i < num_parents; i++)
+		parent_names[i] = of_clk_get_parent_name(node, i);
+
+	data->num_parents = num_parents;
+	data->parent_names = parent_names;
 	data->node = node;
 	data->gpio_name = gpio_name;
 	data->clk_register_get = clk_register_get;
diff --git a/drivers/clk/clk-qoriq.c b/drivers/clk/clk-qoriq.c
index 1ab0fb8..7bc1c45 100644
--- a/drivers/clk/clk-qoriq.c
+++ b/drivers/clk/clk-qoriq.c
@@ -778,8 +778,10 @@
 	 */
 	clksel = (cg_in(cg, hwc->reg) & CLKSEL_MASK) >> CLKSEL_SHIFT;
 	div = get_pll_div(cg, hwc, clksel);
-	if (!div)
+	if (!div) {
+		kfree(hwc);
 		return NULL;
+	}
 
 	pct80_rate = clk_get_rate(div->clk);
 	pct80_rate *= 8;
diff --git a/drivers/clk/clk-scpi.c b/drivers/clk/clk-scpi.c
index 0b501a9..cd0f272 100644
--- a/drivers/clk/clk-scpi.c
+++ b/drivers/clk/clk-scpi.c
@@ -292,6 +292,7 @@
 		ret = scpi_clk_add(dev, child, match);
 		if (ret) {
 			scpi_clocks_remove(pdev);
+			of_node_put(child);
 			return ret;
 		}
 	}
diff --git a/drivers/clk/imx/clk-pllv1.c b/drivers/clk/imx/clk-pllv1.c
index 8564e43..82fe366 100644
--- a/drivers/clk/imx/clk-pllv1.c
+++ b/drivers/clk/imx/clk-pllv1.c
@@ -52,7 +52,7 @@
 		unsigned long parent_rate)
 {
 	struct clk_pllv1 *pll = to_clk_pllv1(hw);
-	long long ll;
+	unsigned long long ull;
 	int mfn_abs;
 	unsigned int mfi, mfn, mfd, pd;
 	u32 reg;
@@ -94,16 +94,16 @@
 	rate = parent_rate * 2;
 	rate /= pd + 1;
 
-	ll = (unsigned long long)rate * mfn_abs;
+	ull = (unsigned long long)rate * mfn_abs;
 
-	do_div(ll, mfd + 1);
+	do_div(ull, mfd + 1);
 
 	if (mfn_is_negative(pll, mfn))
-		ll = -ll;
+		ull = (rate * mfi) - ull;
+	else
+		ull = (rate * mfi) + ull;
 
-	ll = (rate * mfi) + ll;
-
-	return ll;
+	return ull;
 }
 
 static struct clk_ops clk_pllv1_ops = {
diff --git a/drivers/clk/imx/clk-pllv2.c b/drivers/clk/imx/clk-pllv2.c
index b18f875..4aeda56 100644
--- a/drivers/clk/imx/clk-pllv2.c
+++ b/drivers/clk/imx/clk-pllv2.c
@@ -79,7 +79,7 @@
 {
 	long mfi, mfn, mfd, pdf, ref_clk;
 	unsigned long dbl;
-	s64 temp;
+	u64 temp;
 
 	dbl = dp_ctl & MXC_PLL_DP_CTL_DPDCK0_2_EN;
 
@@ -98,8 +98,9 @@
 	temp = (u64) ref_clk * abs(mfn);
 	do_div(temp, mfd + 1);
 	if (mfn < 0)
-		temp = -temp;
-	temp = (ref_clk * mfi) + temp;
+		temp = (ref_clk * mfi) - temp;
+	else
+		temp = (ref_clk * mfi) + temp;
 
 	return temp;
 }
@@ -126,7 +127,7 @@
 {
 	u32 reg;
 	long mfi, pdf, mfn, mfd = 999999;
-	s64 temp64;
+	u64 temp64;
 	unsigned long quad_parent_rate;
 
 	quad_parent_rate = 4 * parent_rate;
diff --git a/drivers/clk/imx/clk-vf610.c b/drivers/clk/imx/clk-vf610.c
index d1b1c95..0a94d96 100644
--- a/drivers/clk/imx/clk-vf610.c
+++ b/drivers/clk/imx/clk-vf610.c
@@ -335,22 +335,22 @@
 	clk[VF610_CLK_SAI0_SEL] = imx_clk_mux("sai0_sel", CCM_CSCMR1, 0, 2, sai_sels, 4);
 	clk[VF610_CLK_SAI0_EN] = imx_clk_gate("sai0_en", "sai0_sel", CCM_CSCDR1, 16);
 	clk[VF610_CLK_SAI0_DIV] = imx_clk_divider("sai0_div", "sai0_en", CCM_CSCDR1, 0, 4);
-	clk[VF610_CLK_SAI0] = imx_clk_gate2("sai0", "sai0_div", CCM_CCGR0, CCM_CCGRx_CGn(15));
+	clk[VF610_CLK_SAI0] = imx_clk_gate2("sai0", "ipg_bus", CCM_CCGR0, CCM_CCGRx_CGn(15));
 
 	clk[VF610_CLK_SAI1_SEL] = imx_clk_mux("sai1_sel", CCM_CSCMR1, 2, 2, sai_sels, 4);
 	clk[VF610_CLK_SAI1_EN] = imx_clk_gate("sai1_en", "sai1_sel", CCM_CSCDR1, 17);
 	clk[VF610_CLK_SAI1_DIV] = imx_clk_divider("sai1_div", "sai1_en", CCM_CSCDR1, 4, 4);
-	clk[VF610_CLK_SAI1] = imx_clk_gate2("sai1", "sai1_div", CCM_CCGR1, CCM_CCGRx_CGn(0));
+	clk[VF610_CLK_SAI1] = imx_clk_gate2("sai1", "ipg_bus", CCM_CCGR1, CCM_CCGRx_CGn(0));
 
 	clk[VF610_CLK_SAI2_SEL] = imx_clk_mux("sai2_sel", CCM_CSCMR1, 4, 2, sai_sels, 4);
 	clk[VF610_CLK_SAI2_EN] = imx_clk_gate("sai2_en", "sai2_sel", CCM_CSCDR1, 18);
 	clk[VF610_CLK_SAI2_DIV] = imx_clk_divider("sai2_div", "sai2_en", CCM_CSCDR1, 8, 4);
-	clk[VF610_CLK_SAI2] = imx_clk_gate2("sai2", "sai2_div", CCM_CCGR1, CCM_CCGRx_CGn(1));
+	clk[VF610_CLK_SAI2] = imx_clk_gate2("sai2", "ipg_bus", CCM_CCGR1, CCM_CCGRx_CGn(1));
 
 	clk[VF610_CLK_SAI3_SEL] = imx_clk_mux("sai3_sel", CCM_CSCMR1, 6, 2, sai_sels, 4);
 	clk[VF610_CLK_SAI3_EN] = imx_clk_gate("sai3_en", "sai3_sel", CCM_CSCDR1, 19);
 	clk[VF610_CLK_SAI3_DIV] = imx_clk_divider("sai3_div", "sai3_en", CCM_CSCDR1, 12, 4);
-	clk[VF610_CLK_SAI3] = imx_clk_gate2("sai3", "sai3_div", CCM_CCGR1, CCM_CCGRx_CGn(2));
+	clk[VF610_CLK_SAI3] = imx_clk_gate2("sai3", "ipg_bus", CCM_CCGR1, CCM_CCGRx_CGn(2));
 
 	clk[VF610_CLK_NFC_SEL] = imx_clk_mux("nfc_sel", CCM_CSCMR1, 12, 2, nfc_sels, 4);
 	clk[VF610_CLK_NFC_EN] = imx_clk_gate("nfc_en", "nfc_sel", CCM_CSCDR2, 9);
diff --git a/drivers/clk/mmp/clk-mmp2.c b/drivers/clk/mmp/clk-mmp2.c
index 09d2832..71fd293 100644
--- a/drivers/clk/mmp/clk-mmp2.c
+++ b/drivers/clk/mmp/clk-mmp2.c
@@ -9,6 +9,7 @@
  * warranty of any kind, whether express or implied.
  */
 
+#include <linux/clk.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/spinlock.h>
diff --git a/drivers/clk/mmp/clk-pxa168.c b/drivers/clk/mmp/clk-pxa168.c
index 93e967c..7524491 100644
--- a/drivers/clk/mmp/clk-pxa168.c
+++ b/drivers/clk/mmp/clk-pxa168.c
@@ -9,6 +9,7 @@
  * warranty of any kind, whether express or implied.
  */
 
+#include <linux/clk.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/spinlock.h>
diff --git a/drivers/clk/mmp/clk-pxa910.c b/drivers/clk/mmp/clk-pxa910.c
index 993abcd..37ba04b 100644
--- a/drivers/clk/mmp/clk-pxa910.c
+++ b/drivers/clk/mmp/clk-pxa910.c
@@ -9,6 +9,7 @@
  * warranty of any kind, whether express or implied.
  */
 
+#include <linux/clk.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/spinlock.h>
diff --git a/drivers/clk/sunxi/clk-a10-pll2.c b/drivers/clk/sunxi/clk-a10-pll2.c
index 5484c31..0ee1f36 100644
--- a/drivers/clk/sunxi/clk-a10-pll2.c
+++ b/drivers/clk/sunxi/clk-a10-pll2.c
@@ -41,15 +41,10 @@
 
 #define SUN4I_PLL2_OUTPUTS		4
 
-struct sun4i_pll2_data {
-	u32	post_div_offset;
-	u32	pre_div_flags;
-};
-
 static DEFINE_SPINLOCK(sun4i_a10_pll2_lock);
 
 static void __init sun4i_pll2_setup(struct device_node *node,
-				    struct sun4i_pll2_data *data)
+				    int post_div_offset)
 {
 	const char *clk_name = node->name, *parent;
 	struct clk **clks, *base_clk, *prediv_clk;
@@ -76,7 +71,7 @@
 					  parent, 0, reg,
 					  SUN4I_PLL2_PRE_DIV_SHIFT,
 					  SUN4I_PLL2_PRE_DIV_WIDTH,
-					  data->pre_div_flags,
+					  CLK_DIVIDER_ONE_BASED | CLK_DIVIDER_ALLOW_ZERO,
 					  &sun4i_a10_pll2_lock);
 	if (!prediv_clk) {
 		pr_err("Couldn't register the prediv clock\n");
@@ -127,7 +122,7 @@
 	 */
 	val = readl(reg);
 	val &= ~(SUN4I_PLL2_POST_DIV_MASK << SUN4I_PLL2_POST_DIV_SHIFT);
-	val |= (SUN4I_PLL2_POST_DIV_VALUE - data->post_div_offset) << SUN4I_PLL2_POST_DIV_SHIFT;
+	val |= (SUN4I_PLL2_POST_DIV_VALUE - post_div_offset) << SUN4I_PLL2_POST_DIV_SHIFT;
 	writel(val, reg);
 
 	of_property_read_string_index(node, "clock-output-names",
@@ -191,25 +186,17 @@
 	iounmap(reg);
 }
 
-static struct sun4i_pll2_data sun4i_a10_pll2_data = {
-	.pre_div_flags	= CLK_DIVIDER_ONE_BASED | CLK_DIVIDER_ALLOW_ZERO,
-};
-
 static void __init sun4i_a10_pll2_setup(struct device_node *node)
 {
-	sun4i_pll2_setup(node, &sun4i_a10_pll2_data);
+	sun4i_pll2_setup(node, 0);
 }
 
 CLK_OF_DECLARE(sun4i_a10_pll2, "allwinner,sun4i-a10-pll2-clk",
 	       sun4i_a10_pll2_setup);
 
-static struct sun4i_pll2_data sun5i_a13_pll2_data = {
-	.post_div_offset	= 1,
-};
-
 static void __init sun5i_a13_pll2_setup(struct device_node *node)
 {
-	sun4i_pll2_setup(node, &sun5i_a13_pll2_data);
+	sun4i_pll2_setup(node, 1);
 }
 
 CLK_OF_DECLARE(sun5i_a13_pll2, "allwinner,sun5i-a13-pll2-clk",
diff --git a/drivers/clk/ti/clk-816x.c b/drivers/clk/ti/clk-816x.c
index 1dfad0c..2a5d84f 100644
--- a/drivers/clk/ti/clk-816x.c
+++ b/drivers/clk/ti/clk-816x.c
@@ -20,6 +20,8 @@
 	DT_CLK(NULL, "sys_clkin", "sys_clkin_ck"),
 	DT_CLK(NULL, "timer_sys_ck", "sys_clkin_ck"),
 	DT_CLK(NULL, "sys_32k_ck", "sys_32k_ck"),
+	DT_CLK(NULL, "timer_32k_ck", "sysclk18_ck"),
+	DT_CLK(NULL, "timer_ext_ck", "tclkin_ck"),
 	DT_CLK(NULL, "mpu_ck", "mpu_ck"),
 	DT_CLK(NULL, "timer1_fck", "timer1_fck"),
 	DT_CLK(NULL, "timer2_fck", "timer2_fck"),
diff --git a/drivers/clk/ti/clkt_dpll.c b/drivers/clk/ti/clkt_dpll.c
index 9023ca9..b5cc6f6 100644
--- a/drivers/clk/ti/clkt_dpll.c
+++ b/drivers/clk/ti/clkt_dpll.c
@@ -240,7 +240,7 @@
  */
 unsigned long omap2_get_dpll_rate(struct clk_hw_omap *clk)
 {
-	long long dpll_clk;
+	u64 dpll_clk;
 	u32 dpll_mult, dpll_div, v;
 	struct dpll_data *dd;
 
@@ -262,7 +262,7 @@
 	dpll_div = v & dd->div1_mask;
 	dpll_div >>= __ffs(dd->div1_mask);
 
-	dpll_clk = (long long)clk_get_rate(dd->clk_ref) * dpll_mult;
+	dpll_clk = (u64)clk_get_rate(dd->clk_ref) * dpll_mult;
 	do_div(dpll_clk, dpll_div + 1);
 
 	return dpll_clk;
diff --git a/drivers/clk/ti/divider.c b/drivers/clk/ti/divider.c
index 5b17268..df25583 100644
--- a/drivers/clk/ti/divider.c
+++ b/drivers/clk/ti/divider.c
@@ -214,7 +214,6 @@
 {
 	struct clk_divider *divider;
 	unsigned int div, value;
-	unsigned long flags = 0;
 	u32 val;
 
 	if (!hw || !rate)
@@ -228,9 +227,6 @@
 	if (value > div_mask(divider))
 		value = div_mask(divider);
 
-	if (divider->lock)
-		spin_lock_irqsave(divider->lock, flags);
-
 	if (divider->flags & CLK_DIVIDER_HIWORD_MASK) {
 		val = div_mask(divider) << (divider->shift + 16);
 	} else {
@@ -240,9 +236,6 @@
 	val |= value << divider->shift;
 	ti_clk_ll_ops->clk_writel(val, divider->reg);
 
-	if (divider->lock)
-		spin_unlock_irqrestore(divider->lock, flags);
-
 	return 0;
 }
 
@@ -256,8 +249,7 @@
 				     const char *parent_name,
 				     unsigned long flags, void __iomem *reg,
 				     u8 shift, u8 width, u8 clk_divider_flags,
-				     const struct clk_div_table *table,
-				     spinlock_t *lock)
+				     const struct clk_div_table *table)
 {
 	struct clk_divider *div;
 	struct clk *clk;
@@ -288,7 +280,6 @@
 	div->shift = shift;
 	div->width = width;
 	div->flags = clk_divider_flags;
-	div->lock = lock;
 	div->hw.init = &init;
 	div->table = table;
 
@@ -421,7 +412,7 @@
 
 	clk = _register_divider(NULL, setup->name, div->parent,
 				flags, (void __iomem *)reg, div->bit_shift,
-				width, div_flags, table, NULL);
+				width, div_flags, table);
 
 	if (IS_ERR(clk))
 		kfree(table);
@@ -584,8 +575,7 @@
 		goto cleanup;
 
 	clk = _register_divider(NULL, node->name, parent_name, flags, reg,
-				shift, width, clk_divider_flags, table,
-				NULL);
+				shift, width, clk_divider_flags, table);
 
 	if (!IS_ERR(clk)) {
 		of_clk_add_provider(node, of_clk_src_simple_get, clk);
diff --git a/drivers/clk/ti/fapll.c b/drivers/clk/ti/fapll.c
index f4b2e98..66a0d0e 100644
--- a/drivers/clk/ti/fapll.c
+++ b/drivers/clk/ti/fapll.c
@@ -168,7 +168,7 @@
 {
 	struct fapll_data *fd = to_fapll(hw);
 	u32 fapll_n, fapll_p, v;
-	long long rate;
+	u64 rate;
 
 	if (ti_fapll_clock_is_bypass(fd))
 		return parent_rate;
@@ -314,7 +314,7 @@
 {
 	struct fapll_synth *synth = to_synth(hw);
 	u32 synth_div_m;
-	long long rate;
+	u64 rate;
 
 	/* The audio_pll_clk1 is hardwired to produce 32.768KiHz clock */
 	if (!synth->div)
diff --git a/drivers/clk/ti/mux.c b/drivers/clk/ti/mux.c
index 69f08a1..dab9ba8 100644
--- a/drivers/clk/ti/mux.c
+++ b/drivers/clk/ti/mux.c
@@ -69,7 +69,6 @@
 {
 	struct clk_mux *mux = to_clk_mux(hw);
 	u32 val;
-	unsigned long flags = 0;
 
 	if (mux->table) {
 		index = mux->table[index];
@@ -81,9 +80,6 @@
 			index++;
 	}
 
-	if (mux->lock)
-		spin_lock_irqsave(mux->lock, flags);
-
 	if (mux->flags & CLK_MUX_HIWORD_MASK) {
 		val = mux->mask << (mux->shift + 16);
 	} else {
@@ -93,9 +89,6 @@
 	val |= index << mux->shift;
 	ti_clk_ll_ops->clk_writel(val, mux->reg);
 
-	if (mux->lock)
-		spin_unlock_irqrestore(mux->lock, flags);
-
 	return 0;
 }
 
@@ -109,7 +102,7 @@
 				 const char **parent_names, u8 num_parents,
 				 unsigned long flags, void __iomem *reg,
 				 u8 shift, u32 mask, u8 clk_mux_flags,
-				 u32 *table, spinlock_t *lock)
+				 u32 *table)
 {
 	struct clk_mux *mux;
 	struct clk *clk;
@@ -133,7 +126,6 @@
 	mux->shift = shift;
 	mux->mask = mask;
 	mux->flags = clk_mux_flags;
-	mux->lock = lock;
 	mux->table = table;
 	mux->hw.init = &init;
 
@@ -175,7 +167,7 @@
 
 	return _register_mux(NULL, setup->name, mux->parents, mux->num_parents,
 			     flags, (void __iomem *)reg, mux->bit_shift, mask,
-			     mux_flags, NULL, NULL);
+			     mux_flags, NULL);
 }
 
 /**
@@ -227,8 +219,7 @@
 	mask = (1 << fls(mask)) - 1;
 
 	clk = _register_mux(NULL, node->name, parent_names, num_parents,
-			    flags, reg, shift, mask, clk_mux_flags, NULL,
-			    NULL);
+			    flags, reg, shift, mask, clk_mux_flags, NULL);
 
 	if (!IS_ERR(clk))
 		of_clk_add_provider(node, of_clk_src_simple_get, clk);
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 71cfdf7..2eb5f0e 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -1,4 +1,5 @@
 menu "Clock Source drivers"
+	depends on !ARCH_USES_GETTIMEOFFSET
 
 config CLKSRC_OF
 	bool
diff --git a/drivers/clocksource/fsl_ftm_timer.c b/drivers/clocksource/fsl_ftm_timer.c
index 10202f1..517e1c7 100644
--- a/drivers/clocksource/fsl_ftm_timer.c
+++ b/drivers/clocksource/fsl_ftm_timer.c
@@ -203,7 +203,7 @@
 	int err;
 
 	ftm_writel(0x00, priv->clkevt_base + FTM_CNTIN);
-	ftm_writel(~0UL, priv->clkevt_base + FTM_MOD);
+	ftm_writel(~0u, priv->clkevt_base + FTM_MOD);
 
 	ftm_reset_counter(priv->clkevt_base);
 
@@ -230,7 +230,7 @@
 	int err;
 
 	ftm_writel(0x00, priv->clksrc_base + FTM_CNTIN);
-	ftm_writel(~0UL, priv->clksrc_base + FTM_MOD);
+	ftm_writel(~0u, priv->clksrc_base + FTM_MOD);
 
 	ftm_reset_counter(priv->clksrc_base);
 
diff --git a/drivers/clocksource/mmio.c b/drivers/clocksource/mmio.c
index 1593ade..c4f7d7a 100644
--- a/drivers/clocksource/mmio.c
+++ b/drivers/clocksource/mmio.c
@@ -55,7 +55,7 @@
 {
 	struct clocksource_mmio *cs;
 
-	if (bits > 32 || bits < 16)
+	if (bits > 64 || bits < 16)
 		return -EINVAL;
 
 	cs = kzalloc(sizeof(struct clocksource_mmio), GFP_KERNEL);
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 1582c1c..235a1ba 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -84,6 +84,7 @@
 config ARM_MT8173_CPUFREQ
 	bool "Mediatek MT8173 CPUFreq support"
 	depends on ARCH_MEDIATEK && REGULATOR
+	depends on ARM64 || (ARM_CPU_TOPOLOGY && COMPILE_TEST)
 	depends on !CPU_THERMAL || THERMAL=y
 	select PM_OPP
 	help
@@ -201,7 +202,7 @@
 
 config ARM_SCPI_CPUFREQ
         tristate "SCPI based CPUfreq driver"
-	depends on ARM_BIG_LITTLE_CPUFREQ && ARM_SCPI_PROTOCOL
+	depends on ARM_BIG_LITTLE_CPUFREQ && ARM_SCPI_PROTOCOL && COMMON_CLK_SCPI
         help
 	  This adds the CPUfreq driver support for ARM big.LITTLE platforms
 	  using SCPI protocol for CPU power management.
diff --git a/drivers/cpufreq/Kconfig.x86 b/drivers/cpufreq/Kconfig.x86
index adbd1de..c59bdcb 100644
--- a/drivers/cpufreq/Kconfig.x86
+++ b/drivers/cpufreq/Kconfig.x86
@@ -5,7 +5,6 @@
 config X86_INTEL_PSTATE
        bool "Intel P state control"
        depends on X86
-       select ACPI_PROCESSOR if ACPI
        help
           This driver provides a P state for Intel core processors.
 	  The driver implements an internal governor and will become
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index e8cb334..7c0bdfb 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -98,10 +98,11 @@
 	policy->max = cpu->perf_caps.highest_perf;
 	policy->cpuinfo.min_freq = policy->min;
 	policy->cpuinfo.max_freq = policy->max;
+	policy->shared_type = cpu->shared_type;
 
 	if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY)
 		cpumask_copy(policy->cpus, cpu->shared_cpu_map);
-	else {
+	else if (policy->shared_type == CPUFREQ_SHARED_TYPE_ALL) {
 		/* Support only SW_ANY for now. */
 		pr_debug("Unsupported CPU co-ord type\n");
 		return -EFAULT;
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 7c48e73..8412ce5 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -976,10 +976,14 @@
 
 	new_policy.governor = gov;
 
-	/* Use the default policy if its valid. */
-	if (cpufreq_driver->setpolicy)
-		cpufreq_parse_governor(gov->name, &new_policy.policy, NULL);
-
+	/* Use the default policy if there is no last_policy. */
+	if (cpufreq_driver->setpolicy) {
+		if (policy->last_policy)
+			new_policy.policy = policy->last_policy;
+		else
+			cpufreq_parse_governor(gov->name, &new_policy.policy,
+					       NULL);
+	}
 	/* set default policy */
 	return cpufreq_set_policy(policy, &new_policy);
 }
@@ -1330,6 +1334,8 @@
 		if (has_target())
 			strncpy(policy->last_governor, policy->governor->name,
 				CPUFREQ_NAME_LEN);
+		else
+			policy->last_policy = policy->policy;
 	} else if (cpu == policy->cpu) {
 		/* Nominate new CPU */
 		policy->cpu = cpumask_any(policy->cpus);
@@ -1401,13 +1407,10 @@
 	}
 
 	cpumask_clear_cpu(cpu, policy->real_cpus);
-
-	if (cpumask_empty(policy->real_cpus)) {
-		cpufreq_policy_free(policy, true);
-		return;
-	}
-
 	remove_cpu_dev_symlink(policy, cpu);
+
+	if (cpumask_empty(policy->real_cpus))
+		cpufreq_policy_free(policy, true);
 }
 
 static void handle_update(struct work_struct *work)
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 2e31d09..4d07cbd 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -34,14 +34,10 @@
 #include <asm/cpu_device_id.h>
 #include <asm/cpufeature.h>
 
-#if IS_ENABLED(CONFIG_ACPI)
-#include <acpi/processor.h>
-#endif
-
-#define BYT_RATIOS		0x66a
-#define BYT_VIDS		0x66b
-#define BYT_TURBO_RATIOS	0x66c
-#define BYT_TURBO_VIDS		0x66d
+#define ATOM_RATIOS		0x66a
+#define ATOM_VIDS		0x66b
+#define ATOM_TURBO_RATIOS	0x66c
+#define ATOM_TURBO_VIDS		0x66d
 
 #define FRAC_BITS 8
 #define int_tofp(X) ((int64_t)(X) << FRAC_BITS)
@@ -117,9 +113,6 @@
 	u64	prev_mperf;
 	u64	prev_tsc;
 	struct sample sample;
-#if IS_ENABLED(CONFIG_ACPI)
-	struct acpi_processor_performance acpi_perf_data;
-#endif
 };
 
 static struct cpudata **all_cpu_data;
@@ -150,7 +143,6 @@
 static struct pstate_adjust_policy pid_params;
 static struct pstate_funcs pstate_funcs;
 static int hwp_active;
-static int no_acpi_perf;
 
 struct perf_limits {
 	int no_turbo;
@@ -163,8 +155,6 @@
 	int max_sysfs_pct;
 	int min_policy_pct;
 	int min_sysfs_pct;
-	int max_perf_ctl;
-	int min_perf_ctl;
 };
 
 static struct perf_limits performance_limits = {
@@ -191,8 +181,6 @@
 	.max_sysfs_pct = 100,
 	.min_policy_pct = 0,
 	.min_sysfs_pct = 0,
-	.max_perf_ctl = 0,
-	.min_perf_ctl = 0,
 };
 
 #ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE
@@ -201,153 +189,6 @@
 static struct perf_limits *limits = &powersave_limits;
 #endif
 
-#if IS_ENABLED(CONFIG_ACPI)
-/*
- * The max target pstate ratio is a 8 bit value in both PLATFORM_INFO MSR and
- * in TURBO_RATIO_LIMIT MSR, which pstate driver stores in max_pstate and
- * max_turbo_pstate fields. The PERF_CTL MSR contains 16 bit value for P state
- * ratio, out of it only high 8 bits are used. For example 0x1700 is setting
- * target ratio 0x17. The _PSS control value stores in a format which can be
- * directly written to PERF_CTL MSR. But in intel_pstate driver this shift
- * occurs during write to PERF_CTL (E.g. for cores core_set_pstate()).
- * This function converts the _PSS control value to intel pstate driver format
- * for comparison and assignment.
- */
-static int convert_to_native_pstate_format(struct cpudata *cpu, int index)
-{
-	return cpu->acpi_perf_data.states[index].control >> 8;
-}
-
-static int intel_pstate_init_perf_limits(struct cpufreq_policy *policy)
-{
-	struct cpudata *cpu;
-	int ret;
-	bool turbo_absent = false;
-	int max_pstate_index;
-	int min_pss_ctl, max_pss_ctl, turbo_pss_ctl;
-	int i;
-
-	cpu = all_cpu_data[policy->cpu];
-
-	pr_debug("intel_pstate: default limits 0x%x 0x%x 0x%x\n",
-		 cpu->pstate.min_pstate, cpu->pstate.max_pstate,
-		 cpu->pstate.turbo_pstate);
-
-	if (!cpu->acpi_perf_data.shared_cpu_map &&
-	    zalloc_cpumask_var_node(&cpu->acpi_perf_data.shared_cpu_map,
-				    GFP_KERNEL, cpu_to_node(policy->cpu))) {
-		return -ENOMEM;
-	}
-
-	ret = acpi_processor_register_performance(&cpu->acpi_perf_data,
-						  policy->cpu);
-	if (ret)
-		return ret;
-
-	/*
-	 * Check if the control value in _PSS is for PERF_CTL MSR, which should
-	 * guarantee that the states returned by it map to the states in our
-	 * list directly.
-	 */
-	if (cpu->acpi_perf_data.control_register.space_id !=
-						ACPI_ADR_SPACE_FIXED_HARDWARE)
-		return -EIO;
-
-	pr_debug("intel_pstate: CPU%u - ACPI _PSS perf data\n", policy->cpu);
-	for (i = 0; i < cpu->acpi_perf_data.state_count; i++)
-		pr_debug("     %cP%d: %u MHz, %u mW, 0x%x\n",
-			 (i == cpu->acpi_perf_data.state ? '*' : ' '), i,
-			 (u32) cpu->acpi_perf_data.states[i].core_frequency,
-			 (u32) cpu->acpi_perf_data.states[i].power,
-			 (u32) cpu->acpi_perf_data.states[i].control);
-
-	/*
-	 * If there is only one entry _PSS, simply ignore _PSS and continue as
-	 * usual without taking _PSS into account
-	 */
-	if (cpu->acpi_perf_data.state_count < 2)
-		return 0;
-
-	turbo_pss_ctl = convert_to_native_pstate_format(cpu, 0);
-	min_pss_ctl = convert_to_native_pstate_format(cpu,
-					cpu->acpi_perf_data.state_count - 1);
-	/* Check if there is a turbo freq in _PSS */
-	if (turbo_pss_ctl <= cpu->pstate.max_pstate &&
-	    turbo_pss_ctl > cpu->pstate.min_pstate) {
-		pr_debug("intel_pstate: no turbo range exists in _PSS\n");
-		limits->no_turbo = limits->turbo_disabled = 1;
-		cpu->pstate.turbo_pstate = cpu->pstate.max_pstate;
-		turbo_absent = true;
-	}
-
-	/* Check if the max non turbo p state < Intel P state max */
-	max_pstate_index = turbo_absent ? 0 : 1;
-	max_pss_ctl = convert_to_native_pstate_format(cpu, max_pstate_index);
-	if (max_pss_ctl < cpu->pstate.max_pstate &&
-	    max_pss_ctl > cpu->pstate.min_pstate)
-		cpu->pstate.max_pstate = max_pss_ctl;
-
-	/* check If min perf > Intel P State min */
-	if (min_pss_ctl > cpu->pstate.min_pstate &&
-	    min_pss_ctl < cpu->pstate.max_pstate) {
-		cpu->pstate.min_pstate = min_pss_ctl;
-		policy->cpuinfo.min_freq = min_pss_ctl * cpu->pstate.scaling;
-	}
-
-	if (turbo_absent)
-		policy->cpuinfo.max_freq = cpu->pstate.max_pstate *
-						cpu->pstate.scaling;
-	else {
-		policy->cpuinfo.max_freq = cpu->pstate.turbo_pstate *
-						cpu->pstate.scaling;
-		/*
-		 * The _PSS table doesn't contain whole turbo frequency range.
-		 * This just contains +1 MHZ above the max non turbo frequency,
-		 * with control value corresponding to max turbo ratio. But
-		 * when cpufreq set policy is called, it will call with this
-		 * max frequency, which will cause a reduced performance as
-		 * this driver uses real max turbo frequency as the max
-		 * frequeny. So correct this frequency in _PSS table to
-		 * correct max turbo frequency based on the turbo ratio.
-		 * Also need to convert to MHz as _PSS freq is in MHz.
-		 */
-		cpu->acpi_perf_data.states[0].core_frequency =
-						turbo_pss_ctl * 100;
-	}
-
-	pr_debug("intel_pstate: Updated limits using _PSS 0x%x 0x%x 0x%x\n",
-		 cpu->pstate.min_pstate, cpu->pstate.max_pstate,
-		 cpu->pstate.turbo_pstate);
-	pr_debug("intel_pstate: policy max_freq=%d Khz min_freq = %d KHz\n",
-		 policy->cpuinfo.max_freq, policy->cpuinfo.min_freq);
-
-	return 0;
-}
-
-static int intel_pstate_exit_perf_limits(struct cpufreq_policy *policy)
-{
-	struct cpudata *cpu;
-
-	if (!no_acpi_perf)
-		return 0;
-
-	cpu = all_cpu_data[policy->cpu];
-	acpi_processor_unregister_performance(policy->cpu);
-	return 0;
-}
-
-#else
-static int intel_pstate_init_perf_limits(struct cpufreq_policy *policy)
-{
-	return 0;
-}
-
-static int intel_pstate_exit_perf_limits(struct cpufreq_policy *policy)
-{
-	return 0;
-}
-#endif
-
 static inline void pid_reset(struct _pid *pid, int setpoint, int busy,
 			     int deadband, int integral) {
 	pid->setpoint = setpoint;
@@ -687,31 +528,31 @@
 	wrmsrl_on_cpu(cpudata->cpu, MSR_PM_ENABLE, 0x1);
 }
 
-static int byt_get_min_pstate(void)
+static int atom_get_min_pstate(void)
 {
 	u64 value;
 
-	rdmsrl(BYT_RATIOS, value);
+	rdmsrl(ATOM_RATIOS, value);
 	return (value >> 8) & 0x7F;
 }
 
-static int byt_get_max_pstate(void)
+static int atom_get_max_pstate(void)
 {
 	u64 value;
 
-	rdmsrl(BYT_RATIOS, value);
+	rdmsrl(ATOM_RATIOS, value);
 	return (value >> 16) & 0x7F;
 }
 
-static int byt_get_turbo_pstate(void)
+static int atom_get_turbo_pstate(void)
 {
 	u64 value;
 
-	rdmsrl(BYT_TURBO_RATIOS, value);
+	rdmsrl(ATOM_TURBO_RATIOS, value);
 	return value & 0x7F;
 }
 
-static void byt_set_pstate(struct cpudata *cpudata, int pstate)
+static void atom_set_pstate(struct cpudata *cpudata, int pstate)
 {
 	u64 val;
 	int32_t vid_fp;
@@ -736,27 +577,42 @@
 	wrmsrl_on_cpu(cpudata->cpu, MSR_IA32_PERF_CTL, val);
 }
 
-#define BYT_BCLK_FREQS 5
-static int byt_freq_table[BYT_BCLK_FREQS] = { 833, 1000, 1333, 1167, 800};
-
-static int byt_get_scaling(void)
+static int silvermont_get_scaling(void)
 {
 	u64 value;
 	int i;
+	/* Defined in Table 35-6 from SDM (Sept 2015) */
+	static int silvermont_freq_table[] = {
+		83300, 100000, 133300, 116700, 80000};
 
 	rdmsrl(MSR_FSB_FREQ, value);
-	i = value & 0x3;
+	i = value & 0x7;
+	WARN_ON(i > 4);
 
-	BUG_ON(i > BYT_BCLK_FREQS);
-
-	return byt_freq_table[i] * 100;
+	return silvermont_freq_table[i];
 }
 
-static void byt_get_vid(struct cpudata *cpudata)
+static int airmont_get_scaling(void)
+{
+	u64 value;
+	int i;
+	/* Defined in Table 35-10 from SDM (Sept 2015) */
+	static int airmont_freq_table[] = {
+		83300, 100000, 133300, 116700, 80000,
+		93300, 90000, 88900, 87500};
+
+	rdmsrl(MSR_FSB_FREQ, value);
+	i = value & 0xF;
+	WARN_ON(i > 8);
+
+	return airmont_freq_table[i];
+}
+
+static void atom_get_vid(struct cpudata *cpudata)
 {
 	u64 value;
 
-	rdmsrl(BYT_VIDS, value);
+	rdmsrl(ATOM_VIDS, value);
 	cpudata->vid.min = int_tofp((value >> 8) & 0x7f);
 	cpudata->vid.max = int_tofp((value >> 16) & 0x7f);
 	cpudata->vid.ratio = div_fp(
@@ -764,7 +620,7 @@
 		int_tofp(cpudata->pstate.max_pstate -
 			cpudata->pstate.min_pstate));
 
-	rdmsrl(BYT_TURBO_VIDS, value);
+	rdmsrl(ATOM_TURBO_VIDS, value);
 	cpudata->vid.turbo = value & 0x7f;
 }
 
@@ -885,7 +741,7 @@
 	},
 };
 
-static struct cpu_defaults byt_params = {
+static struct cpu_defaults silvermont_params = {
 	.pid_policy = {
 		.sample_rate_ms = 10,
 		.deadband = 0,
@@ -895,13 +751,33 @@
 		.i_gain_pct = 4,
 	},
 	.funcs = {
-		.get_max = byt_get_max_pstate,
-		.get_max_physical = byt_get_max_pstate,
-		.get_min = byt_get_min_pstate,
-		.get_turbo = byt_get_turbo_pstate,
-		.set = byt_set_pstate,
-		.get_scaling = byt_get_scaling,
-		.get_vid = byt_get_vid,
+		.get_max = atom_get_max_pstate,
+		.get_max_physical = atom_get_max_pstate,
+		.get_min = atom_get_min_pstate,
+		.get_turbo = atom_get_turbo_pstate,
+		.set = atom_set_pstate,
+		.get_scaling = silvermont_get_scaling,
+		.get_vid = atom_get_vid,
+	},
+};
+
+static struct cpu_defaults airmont_params = {
+	.pid_policy = {
+		.sample_rate_ms = 10,
+		.deadband = 0,
+		.setpoint = 60,
+		.p_gain_pct = 14,
+		.d_gain_pct = 0,
+		.i_gain_pct = 4,
+	},
+	.funcs = {
+		.get_max = atom_get_max_pstate,
+		.get_max_physical = atom_get_max_pstate,
+		.get_min = atom_get_min_pstate,
+		.get_turbo = atom_get_turbo_pstate,
+		.set = atom_set_pstate,
+		.get_scaling = airmont_get_scaling,
+		.get_vid = atom_get_vid,
 	},
 };
 
@@ -938,23 +814,12 @@
 	 * policy, or by cpu specific default values determined through
 	 * experimentation.
 	 */
-	if (limits->max_perf_ctl && limits->max_sysfs_pct >=
-						limits->max_policy_pct) {
-		*max = limits->max_perf_ctl;
-	} else {
-		max_perf_adj = fp_toint(mul_fp(int_tofp(max_perf),
-					limits->max_perf));
-		*max = clamp_t(int, max_perf_adj, cpu->pstate.min_pstate,
-			       cpu->pstate.turbo_pstate);
-	}
+	max_perf_adj = fp_toint(mul_fp(int_tofp(max_perf), limits->max_perf));
+	*max = clamp_t(int, max_perf_adj,
+			cpu->pstate.min_pstate, cpu->pstate.turbo_pstate);
 
-	if (limits->min_perf_ctl) {
-		*min = limits->min_perf_ctl;
-	} else {
-		min_perf = fp_toint(mul_fp(int_tofp(max_perf),
-				    limits->min_perf));
-		*min = clamp_t(int, min_perf, cpu->pstate.min_pstate, max_perf);
-	}
+	min_perf = fp_toint(mul_fp(int_tofp(max_perf), limits->min_perf));
+	*min = clamp_t(int, min_perf, cpu->pstate.min_pstate, max_perf);
 }
 
 static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate, bool force)
@@ -1153,7 +1018,7 @@
 static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
 	ICPU(0x2a, core_params),
 	ICPU(0x2d, core_params),
-	ICPU(0x37, byt_params),
+	ICPU(0x37, silvermont_params),
 	ICPU(0x3a, core_params),
 	ICPU(0x3c, core_params),
 	ICPU(0x3d, core_params),
@@ -1162,7 +1027,7 @@
 	ICPU(0x45, core_params),
 	ICPU(0x46, core_params),
 	ICPU(0x47, core_params),
-	ICPU(0x4c, byt_params),
+	ICPU(0x4c, airmont_params),
 	ICPU(0x4e, core_params),
 	ICPU(0x4f, core_params),
 	ICPU(0x5e, core_params),
@@ -1229,12 +1094,6 @@
 
 static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 {
-#if IS_ENABLED(CONFIG_ACPI)
-	struct cpudata *cpu;
-	int i;
-#endif
-	pr_debug("intel_pstate: %s max %u policy->max %u\n", __func__,
-		 policy->cpuinfo.max_freq, policy->max);
 	if (!policy->cpuinfo.max_freq)
 		return -ENODEV;
 
@@ -1242,6 +1101,8 @@
 	    policy->max >= policy->cpuinfo.max_freq) {
 		pr_debug("intel_pstate: set performance\n");
 		limits = &performance_limits;
+		if (hwp_active)
+			intel_pstate_hwp_set();
 		return 0;
 	}
 
@@ -1249,7 +1110,8 @@
 	limits = &powersave_limits;
 	limits->min_policy_pct = (policy->min * 100) / policy->cpuinfo.max_freq;
 	limits->min_policy_pct = clamp_t(int, limits->min_policy_pct, 0 , 100);
-	limits->max_policy_pct = (policy->max * 100) / policy->cpuinfo.max_freq;
+	limits->max_policy_pct = DIV_ROUND_UP(policy->max * 100,
+					      policy->cpuinfo.max_freq);
 	limits->max_policy_pct = clamp_t(int, limits->max_policy_pct, 0 , 100);
 
 	/* Normalize user input to [min_policy_pct, max_policy_pct] */
@@ -1261,6 +1123,7 @@
 				   limits->max_sysfs_pct);
 	limits->max_perf_pct = max(limits->min_policy_pct,
 				   limits->max_perf_pct);
+	limits->max_perf = round_up(limits->max_perf, 8);
 
 	/* Make sure min_perf_pct <= max_perf_pct */
 	limits->min_perf_pct = min(limits->max_perf_pct, limits->min_perf_pct);
@@ -1270,23 +1133,6 @@
 	limits->max_perf = div_fp(int_tofp(limits->max_perf_pct),
 				  int_tofp(100));
 
-#if IS_ENABLED(CONFIG_ACPI)
-	cpu = all_cpu_data[policy->cpu];
-	for (i = 0; i < cpu->acpi_perf_data.state_count; i++) {
-		int control;
-
-		control = convert_to_native_pstate_format(cpu, i);
-		if (control * cpu->pstate.scaling == policy->max)
-			limits->max_perf_ctl = control;
-		if (control * cpu->pstate.scaling == policy->min)
-			limits->min_perf_ctl = control;
-	}
-
-	pr_debug("intel_pstate: max %u policy_max %u perf_ctl [0x%x-0x%x]\n",
-		 policy->cpuinfo.max_freq, policy->max, limits->min_perf_ctl,
-		 limits->max_perf_ctl);
-#endif
-
 	if (hwp_active)
 		intel_pstate_hwp_set();
 
@@ -1341,30 +1187,18 @@
 	policy->cpuinfo.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling;
 	policy->cpuinfo.max_freq =
 		cpu->pstate.turbo_pstate * cpu->pstate.scaling;
-	if (!no_acpi_perf)
-		intel_pstate_init_perf_limits(policy);
-	/*
-	 * If there is no acpi perf data or error, we ignore and use Intel P
-	 * state calculated limits, So this is not fatal error.
-	 */
 	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
 	cpumask_set_cpu(policy->cpu, policy->cpus);
 
 	return 0;
 }
 
-static int intel_pstate_cpu_exit(struct cpufreq_policy *policy)
-{
-	return intel_pstate_exit_perf_limits(policy);
-}
-
 static struct cpufreq_driver intel_pstate_driver = {
 	.flags		= CPUFREQ_CONST_LOOPS,
 	.verify		= intel_pstate_verify_policy,
 	.setpolicy	= intel_pstate_set_policy,
 	.get		= intel_pstate_get,
 	.init		= intel_pstate_cpu_init,
-	.exit		= intel_pstate_cpu_exit,
 	.stop_cpu	= intel_pstate_stop_cpu,
 	.name		= "intel_pstate",
 };
@@ -1406,6 +1240,7 @@
 }
 
 #if IS_ENABLED(CONFIG_ACPI)
+#include <acpi/processor.h>
 
 static bool intel_pstate_no_acpi_pss(void)
 {
@@ -1601,9 +1436,6 @@
 		force_load = 1;
 	if (!strcmp(str, "hwp_only"))
 		hwp_only = 1;
-	if (!strcmp(str, "no_acpi"))
-		no_acpi_perf = 1;
-
 	return 0;
 }
 early_param("intel_pstate", intel_pstate_setup);
diff --git a/drivers/cpufreq/s3c24xx-cpufreq.c b/drivers/cpufreq/s3c24xx-cpufreq.c
index 733aa51..68ef8fd 100644
--- a/drivers/cpufreq/s3c24xx-cpufreq.c
+++ b/drivers/cpufreq/s3c24xx-cpufreq.c
@@ -648,7 +648,7 @@
  *
  * Register the given set of PLLs with the system.
  */
-int __init s3c_plltab_register(struct cpufreq_frequency_table *plls,
+int s3c_plltab_register(struct cpufreq_frequency_table *plls,
 			       unsigned int plls_no)
 {
 	struct cpufreq_frequency_table *vals;
diff --git a/drivers/crypto/nx/nx-aes-ccm.c b/drivers/crypto/nx/nx-aes-ccm.c
index 73ef499..7038f36 100644
--- a/drivers/crypto/nx/nx-aes-ccm.c
+++ b/drivers/crypto/nx/nx-aes-ccm.c
@@ -409,7 +409,7 @@
 		processed += to_process;
 	} while (processed < nbytes);
 
-	rc = memcmp(csbcpb->cpb.aes_ccm.out_pat_or_mac, priv->oauth_tag,
+	rc = crypto_memneq(csbcpb->cpb.aes_ccm.out_pat_or_mac, priv->oauth_tag,
 		    authsize) ? -EBADMSG : 0;
 out:
 	spin_unlock_irqrestore(&nx_ctx->lock, irq_flags);
diff --git a/drivers/crypto/nx/nx-aes-gcm.c b/drivers/crypto/nx/nx-aes-gcm.c
index eee624f..abd465f 100644
--- a/drivers/crypto/nx/nx-aes-gcm.c
+++ b/drivers/crypto/nx/nx-aes-gcm.c
@@ -21,6 +21,7 @@
 
 #include <crypto/internal/aead.h>
 #include <crypto/aes.h>
+#include <crypto/algapi.h>
 #include <crypto/scatterwalk.h>
 #include <linux/module.h>
 #include <linux/types.h>
@@ -418,7 +419,7 @@
 			itag, req->src, req->assoclen + nbytes,
 			crypto_aead_authsize(crypto_aead_reqtfm(req)),
 			SCATTERWALK_FROM_SG);
-		rc = memcmp(itag, otag,
+		rc = crypto_memneq(itag, otag,
 			    crypto_aead_authsize(crypto_aead_reqtfm(req))) ?
 		     -EBADMSG : 0;
 	}
diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c
index 46f531e..b6f9f42 100644
--- a/drivers/crypto/talitos.c
+++ b/drivers/crypto/talitos.c
@@ -977,7 +977,7 @@
 		} else
 			oicv = (char *)&edesc->link_tbl[0];
 
-		err = memcmp(oicv, icv, authsize) ? -EBADMSG : 0;
+		err = crypto_memneq(oicv, icv, authsize) ? -EBADMSG : 0;
 	}
 
 	kfree(edesc);
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index 4e55239..53d22eb 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -729,8 +729,8 @@
 		return NULL;
 
 	dev_info(chan2dev(chan),
-		 "%s: src=0x%08x, dest=0x%08x, numf=%d, frame_size=%d, flags=0x%lx\n",
-		__func__, xt->src_start, xt->dst_start, xt->numf,
+		 "%s: src=%pad, dest=%pad, numf=%d, frame_size=%d, flags=0x%lx\n",
+		__func__, &xt->src_start, &xt->dst_start, xt->numf,
 		xt->frame_size, flags);
 
 	/*
@@ -824,8 +824,8 @@
 	u32			ctrla;
 	u32			ctrlb;
 
-	dev_vdbg(chan2dev(chan), "prep_dma_memcpy: d0x%x s0x%x l0x%zx f0x%lx\n",
-			dest, src, len, flags);
+	dev_vdbg(chan2dev(chan), "prep_dma_memcpy: d%pad s%pad l0x%zx f0x%lx\n",
+			&dest, &src, len, flags);
 
 	if (unlikely(!len)) {
 		dev_dbg(chan2dev(chan), "prep_dma_memcpy: length is zero!\n");
@@ -938,8 +938,8 @@
 	void __iomem		*vaddr;
 	dma_addr_t		paddr;
 
-	dev_vdbg(chan2dev(chan), "%s: d0x%x v0x%x l0x%zx f0x%lx\n", __func__,
-		dest, value, len, flags);
+	dev_vdbg(chan2dev(chan), "%s: d%pad v0x%x l0x%zx f0x%lx\n", __func__,
+		&dest, value, len, flags);
 
 	if (unlikely(!len)) {
 		dev_dbg(chan2dev(chan), "%s: length is zero!\n", __func__);
@@ -1022,8 +1022,8 @@
 		dma_addr_t dest = sg_dma_address(sg);
 		size_t len = sg_dma_len(sg);
 
-		dev_vdbg(chan2dev(chan), "%s: d0x%08x, l0x%zx\n",
-			 __func__, dest, len);
+		dev_vdbg(chan2dev(chan), "%s: d%pad, l0x%zx\n",
+			 __func__, &dest, len);
 
 		if (!is_dma_fill_aligned(chan->device, dest, 0, len)) {
 			dev_err(chan2dev(chan), "%s: buffer is not aligned\n",
@@ -1439,9 +1439,9 @@
 	unsigned int		periods = buf_len / period_len;
 	unsigned int		i;
 
-	dev_vdbg(chan2dev(chan), "prep_dma_cyclic: %s buf@0x%08x - %d (%d/%d)\n",
+	dev_vdbg(chan2dev(chan), "prep_dma_cyclic: %s buf@%pad - %d (%d/%d)\n",
 			direction == DMA_MEM_TO_DEV ? "TO DEVICE" : "FROM DEVICE",
-			buf_addr,
+			&buf_addr,
 			periods, buf_len, period_len);
 
 	if (unlikely(!atslave || !buf_len || !period_len)) {
diff --git a/drivers/dma/at_hdmac_regs.h b/drivers/dma/at_hdmac_regs.h
index d1cfc8c..7f58f06 100644
--- a/drivers/dma/at_hdmac_regs.h
+++ b/drivers/dma/at_hdmac_regs.h
@@ -385,9 +385,9 @@
 static void atc_dump_lli(struct at_dma_chan *atchan, struct at_lli *lli)
 {
 	dev_crit(chan2dev(&atchan->chan_common),
-		 "  desc: s0x%x d0x%x ctrl0x%x:0x%x l0x%x\n",
-		 lli->saddr, lli->daddr,
-		 lli->ctrla, lli->ctrlb, lli->dscr);
+		 "  desc: s%pad d%pad ctrl0x%x:0x%x l0x%pad\n",
+		 &lli->saddr, &lli->daddr,
+		 lli->ctrla, lli->ctrlb, &lli->dscr);
 }
 
 
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index b5e132d..7f039de 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -920,8 +920,8 @@
 	desc->lld.mbr_cfg = chan_cc;
 
 	dev_dbg(chan2dev(chan),
-		"%s: lld: mbr_sa=0x%08x, mbr_da=0x%08x, mbr_ubc=0x%08x, mbr_cfg=0x%08x\n",
-		__func__, desc->lld.mbr_sa, desc->lld.mbr_da,
+		"%s: lld: mbr_sa=%pad, mbr_da=%pad, mbr_ubc=0x%08x, mbr_cfg=0x%08x\n",
+		__func__, &desc->lld.mbr_sa, &desc->lld.mbr_da,
 		desc->lld.mbr_ubc, desc->lld.mbr_cfg);
 
 	/* Chain lld. */
@@ -953,8 +953,8 @@
 	if ((xt->numf > 1) && (xt->frame_size > 1))
 		return NULL;
 
-	dev_dbg(chan2dev(chan), "%s: src=0x%08x, dest=0x%08x, numf=%d, frame_size=%d, flags=0x%lx\n",
-		__func__, xt->src_start, xt->dst_start,	xt->numf,
+	dev_dbg(chan2dev(chan), "%s: src=%pad, dest=%pad, numf=%d, frame_size=%d, flags=0x%lx\n",
+		__func__, &xt->src_start, &xt->dst_start,	xt->numf,
 		xt->frame_size, flags);
 
 	src_addr = xt->src_start;
@@ -1179,8 +1179,8 @@
 	desc->lld.mbr_cfg = chan_cc;
 
 	dev_dbg(chan2dev(chan),
-		"%s: lld: mbr_da=0x%08x, mbr_ds=0x%08x, mbr_ubc=0x%08x, mbr_cfg=0x%08x\n",
-		__func__, desc->lld.mbr_da, desc->lld.mbr_ds, desc->lld.mbr_ubc,
+		"%s: lld: mbr_da=%pad, mbr_ds=%pad, mbr_ubc=0x%08x, mbr_cfg=0x%08x\n",
+		__func__, &desc->lld.mbr_da, &desc->lld.mbr_ds, desc->lld.mbr_ubc,
 		desc->lld.mbr_cfg);
 
 	return desc;
@@ -1193,8 +1193,8 @@
 	struct at_xdmac_chan	*atchan = to_at_xdmac_chan(chan);
 	struct at_xdmac_desc	*desc;
 
-	dev_dbg(chan2dev(chan), "%s: dest=0x%08x, len=%d, pattern=0x%x, flags=0x%lx\n",
-		__func__, dest, len, value, flags);
+	dev_dbg(chan2dev(chan), "%s: dest=%pad, len=%d, pattern=0x%x, flags=0x%lx\n",
+		__func__, &dest, len, value, flags);
 
 	if (unlikely(!len))
 		return NULL;
@@ -1229,8 +1229,8 @@
 
 	/* Prepare descriptors. */
 	for_each_sg(sgl, sg, sg_len, i) {
-		dev_dbg(chan2dev(chan), "%s: dest=0x%08x, len=%d, pattern=0x%x, flags=0x%lx\n",
-			__func__, sg_dma_address(sg), sg_dma_len(sg),
+		dev_dbg(chan2dev(chan), "%s: dest=%pad, len=%d, pattern=0x%x, flags=0x%lx\n",
+			__func__, &sg_dma_address(sg), sg_dma_len(sg),
 			value, flags);
 		desc = at_xdmac_memset_create_desc(chan, atchan,
 						   sg_dma_address(sg),
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
index 6b03e4e..0675e26 100644
--- a/drivers/dma/edma.c
+++ b/drivers/dma/edma.c
@@ -107,7 +107,7 @@
 
 /* CCCFG register */
 #define GET_NUM_DMACH(x)	(x & 0x7) /* bits 0-2 */
-#define GET_NUM_QDMACH(x)	(x & 0x70 >> 4) /* bits 4-6 */
+#define GET_NUM_QDMACH(x)	((x & 0x70) >> 4) /* bits 4-6 */
 #define GET_NUM_PAENTRY(x)	((x & 0x7000) >> 12) /* bits 12-14 */
 #define GET_NUM_EVQUE(x)	((x & 0x70000) >> 16) /* bits 16-18 */
 #define GET_NUM_REGN(x)		((x & 0x300000) >> 20) /* bits 20-21 */
@@ -1565,7 +1565,7 @@
 	struct platform_device *tc_pdev;
 	int ret;
 
-	if (!tc)
+	if (!IS_ENABLED(CONFIG_OF) || !tc)
 		return;
 
 	tc_pdev = of_find_device_by_node(tc->node);
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 7058d58..0f6fd42 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -1462,7 +1462,7 @@
 
 #define EVENT_REMAP_CELLS 3
 
-static int __init sdma_event_remap(struct sdma_engine *sdma)
+static int sdma_event_remap(struct sdma_engine *sdma)
 {
 	struct device_node *np = sdma->dev->of_node;
 	struct device_node *gpr_np = of_parse_phandle(np, "gpr", 0);
diff --git a/drivers/dma/sh/usb-dmac.c b/drivers/dma/sh/usb-dmac.c
index ebd8a5f..f1bcc2a 100644
--- a/drivers/dma/sh/usb-dmac.c
+++ b/drivers/dma/sh/usb-dmac.c
@@ -679,8 +679,11 @@
 	struct usb_dmac *dmac = dev_get_drvdata(dev);
 	int i;
 
-	for (i = 0; i < dmac->n_channels; ++i)
+	for (i = 0; i < dmac->n_channels; ++i) {
+		if (!dmac->channels[i].iomem)
+			break;
 		usb_dmac_chan_halt(&dmac->channels[i]);
+	}
 
 	return 0;
 }
@@ -799,11 +802,10 @@
 	ret = pm_runtime_get_sync(&pdev->dev);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "runtime PM get sync failed (%d)\n", ret);
-		return ret;
+		goto error_pm;
 	}
 
 	ret = usb_dmac_init(dmac);
-	pm_runtime_put(&pdev->dev);
 
 	if (ret) {
 		dev_err(&pdev->dev, "failed to reset device\n");
@@ -851,10 +853,13 @@
 	if (ret < 0)
 		goto error;
 
+	pm_runtime_put(&pdev->dev);
 	return 0;
 
 error:
 	of_dma_controller_free(pdev->dev.of_node);
+	pm_runtime_put(&pdev->dev);
+error_pm:
 	pm_runtime_disable(&pdev->dev);
 	return ret;
 }
diff --git a/drivers/fpga/fpga-mgr.c b/drivers/fpga/fpga-mgr.c
index a24f5cb..953dc91 100644
--- a/drivers/fpga/fpga-mgr.c
+++ b/drivers/fpga/fpga-mgr.c
@@ -122,12 +122,10 @@
 	}
 
 	ret = fpga_mgr_buf_load(mgr, flags, fw->data, fw->size);
-	if (ret)
-		return ret;
 
 	release_firmware(fw);
 
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(fpga_mgr_firmware_load);
 
@@ -256,7 +254,6 @@
 		      void *priv)
 {
 	struct fpga_manager *mgr;
-	const char *dt_label;
 	int id, ret;
 
 	if (!mops || !mops->write_init || !mops->write ||
@@ -300,11 +297,9 @@
 	mgr->dev.id = id;
 	dev_set_drvdata(dev, mgr);
 
-	dt_label = of_get_property(mgr->dev.of_node, "label", NULL);
-	if (dt_label)
-		ret = dev_set_name(&mgr->dev, "%s", dt_label);
-	else
-		ret = dev_set_name(&mgr->dev, "fpga%d", id);
+	ret = dev_set_name(&mgr->dev, "fpga%d", id);
+	if (ret)
+		goto error_device;
 
 	ret = device_add(&mgr->dev);
 	if (ret)
diff --git a/drivers/gpio/gpio-74xx-mmio.c b/drivers/gpio/gpio-74xx-mmio.c
index 6ed7c0f..6b18682 100644
--- a/drivers/gpio/gpio-74xx-mmio.c
+++ b/drivers/gpio/gpio-74xx-mmio.c
@@ -113,13 +113,16 @@
 
 static int mmio_74xx_gpio_probe(struct platform_device *pdev)
 {
-	const struct of_device_id *of_id =
-		of_match_device(mmio_74xx_gpio_ids, &pdev->dev);
+	const struct of_device_id *of_id;
 	struct mmio_74xx_gpio_priv *priv;
 	struct resource *res;
 	void __iomem *dat;
 	int err;
 
+	of_id = of_match_device(mmio_74xx_gpio_ids, &pdev->dev);
+	if (!of_id)
+		return -ENODEV;
+
 	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c
index 56d2d02..f7fbb46 100644
--- a/drivers/gpio/gpio-omap.c
+++ b/drivers/gpio/gpio-omap.c
@@ -1122,8 +1122,6 @@
 	/* MPUIO is a bit different, reading IRQ status clears it */
 	if (bank->is_mpuio) {
 		irqc->irq_ack = dummy_irq_chip.irq_ack;
-		irqc->irq_mask = irq_gc_mask_set_bit;
-		irqc->irq_unmask = irq_gc_mask_clr_bit;
 		if (!bank->regs->wkup_en)
 			irqc->irq_set_wake = NULL;
 	}
diff --git a/drivers/gpio/gpio-palmas.c b/drivers/gpio/gpio-palmas.c
index 171a638..52b447c 100644
--- a/drivers/gpio/gpio-palmas.c
+++ b/drivers/gpio/gpio-palmas.c
@@ -167,6 +167,8 @@
 	const struct palmas_device_data *dev_data;
 
 	match = of_match_device(of_palmas_gpio_match, &pdev->dev);
+	if (!match)
+		return -ENODEV;
 	dev_data = match->data;
 	if (!dev_data)
 		dev_data = &palmas_dev_data;
diff --git a/drivers/gpio/gpio-syscon.c b/drivers/gpio/gpio-syscon.c
index 045a952..7b25fdf 100644
--- a/drivers/gpio/gpio-syscon.c
+++ b/drivers/gpio/gpio-syscon.c
@@ -187,11 +187,15 @@
 static int syscon_gpio_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	const struct of_device_id *of_id = of_match_device(syscon_gpio_ids, dev);
+	const struct of_device_id *of_id;
 	struct syscon_gpio_priv *priv;
 	struct device_node *np = dev->of_node;
 	int ret;
 
+	of_id = of_match_device(syscon_gpio_ids, dev);
+	if (!of_id)
+		return -ENODEV;
+
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c
index 027e5f4..896bf29 100644
--- a/drivers/gpio/gpio-tegra.c
+++ b/drivers/gpio/gpio-tegra.c
@@ -375,6 +375,60 @@
 }
 #endif
 
+#ifdef	CONFIG_DEBUG_FS
+
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+static int dbg_gpio_show(struct seq_file *s, void *unused)
+{
+	int i;
+	int j;
+
+	for (i = 0; i < tegra_gpio_bank_count; i++) {
+		for (j = 0; j < 4; j++) {
+			int gpio = tegra_gpio_compose(i, j, 0);
+			seq_printf(s,
+				"%d:%d %02x %02x %02x %02x %02x %02x %06x\n",
+				i, j,
+				tegra_gpio_readl(GPIO_CNF(gpio)),
+				tegra_gpio_readl(GPIO_OE(gpio)),
+				tegra_gpio_readl(GPIO_OUT(gpio)),
+				tegra_gpio_readl(GPIO_IN(gpio)),
+				tegra_gpio_readl(GPIO_INT_STA(gpio)),
+				tegra_gpio_readl(GPIO_INT_ENB(gpio)),
+				tegra_gpio_readl(GPIO_INT_LVL(gpio)));
+		}
+	}
+	return 0;
+}
+
+static int dbg_gpio_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, dbg_gpio_show, &inode->i_private);
+}
+
+static const struct file_operations debug_fops = {
+	.open		= dbg_gpio_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static void tegra_gpio_debuginit(void)
+{
+	(void) debugfs_create_file("tegra_gpio", S_IRUGO,
+					NULL, NULL, &debug_fops);
+}
+
+#else
+
+static inline void tegra_gpio_debuginit(void)
+{
+}
+
+#endif
+
 static struct irq_chip tegra_gpio_irq_chip = {
 	.name		= "GPIO",
 	.irq_ack	= tegra_gpio_irq_ack,
@@ -519,6 +573,8 @@
 			spin_lock_init(&bank->lvl_lock[j]);
 	}
 
+	tegra_gpio_debuginit();
+
 	return 0;
 }
 
@@ -536,52 +592,3 @@
 	return platform_driver_register(&tegra_gpio_driver);
 }
 postcore_initcall(tegra_gpio_init);
-
-#ifdef	CONFIG_DEBUG_FS
-
-#include <linux/debugfs.h>
-#include <linux/seq_file.h>
-
-static int dbg_gpio_show(struct seq_file *s, void *unused)
-{
-	int i;
-	int j;
-
-	for (i = 0; i < tegra_gpio_bank_count; i++) {
-		for (j = 0; j < 4; j++) {
-			int gpio = tegra_gpio_compose(i, j, 0);
-			seq_printf(s,
-				"%d:%d %02x %02x %02x %02x %02x %02x %06x\n",
-				i, j,
-				tegra_gpio_readl(GPIO_CNF(gpio)),
-				tegra_gpio_readl(GPIO_OE(gpio)),
-				tegra_gpio_readl(GPIO_OUT(gpio)),
-				tegra_gpio_readl(GPIO_IN(gpio)),
-				tegra_gpio_readl(GPIO_INT_STA(gpio)),
-				tegra_gpio_readl(GPIO_INT_ENB(gpio)),
-				tegra_gpio_readl(GPIO_INT_LVL(gpio)));
-		}
-	}
-	return 0;
-}
-
-static int dbg_gpio_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, dbg_gpio_show, &inode->i_private);
-}
-
-static const struct file_operations debug_fops = {
-	.open		= dbg_gpio_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-static int __init tegra_gpio_debuginit(void)
-{
-	(void) debugfs_create_file("tegra_gpio", S_IRUGO,
-					NULL, NULL, &debug_fops);
-	return 0;
-}
-late_initcall(tegra_gpio_debuginit);
-#endif
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index a18f00f..2a91f32 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -233,7 +233,7 @@
 		for (i = 0; i != chip->ngpio; ++i) {
 			struct gpio_desc *gpio = &chip->desc[i];
 
-			if (!gpio->name)
+			if (!gpio->name || !name)
 				continue;
 
 			if (!strcmp(gpio->name, name)) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 615ce6d..5a5f04d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -389,7 +389,6 @@
  * Fences.
  */
 struct amdgpu_fence_driver {
-	struct amdgpu_ring		*ring;
 	uint64_t			gpu_addr;
 	volatile uint32_t		*cpu_addr;
 	/* sync_seq is protected by ring emission lock */
@@ -398,7 +397,7 @@
 	bool				initialized;
 	struct amdgpu_irq_src		*irq_src;
 	unsigned			irq_type;
-	struct delayed_work             lockup_work;
+	struct timer_list		fallback_timer;
 	wait_queue_head_t		fence_queue;
 };
 
@@ -497,6 +496,7 @@
 
 /* bo virtual addresses in a specific vm */
 struct amdgpu_bo_va {
+	struct mutex		        mutex;
 	/* protected by bo being reserved */
 	struct list_head		bo_list;
 	struct fence		        *last_pt_update;
@@ -539,6 +539,7 @@
 	/* Constant after initialization */
 	struct amdgpu_device		*adev;
 	struct drm_gem_object		gem_base;
+	struct amdgpu_bo		*parent;
 
 	struct ttm_bo_kmap_obj		dma_buf_vmap;
 	pid_t				pid;
@@ -917,8 +918,8 @@
 #define AMDGPU_VM_FAULT_STOP_ALWAYS	2
 
 struct amdgpu_vm_pt {
-	struct amdgpu_bo		*bo;
-	uint64_t			addr;
+	struct amdgpu_bo	*bo;
+	uint64_t		addr;
 };
 
 struct amdgpu_vm_id {
@@ -926,13 +927,9 @@
 	uint64_t		pd_gpu_addr;
 	/* last flushed PD/PT update */
 	struct fence	        *flushed_updates;
-	/* last use of vmid */
-	struct fence		*last_id_use;
 };
 
 struct amdgpu_vm {
-	struct mutex		mutex;
-
 	struct rb_root		va;
 
 	/* protecting invalidated */
@@ -957,24 +954,72 @@
 
 	/* for id and flush management per ring */
 	struct amdgpu_vm_id	ids[AMDGPU_MAX_RINGS];
+	/* for interval tree */
+	spinlock_t		it_lock;
+	/* protecting freed */
+	spinlock_t		freed_lock;
 };
 
 struct amdgpu_vm_manager {
-	struct fence			*active[AMDGPU_NUM_VM];
-	uint32_t			max_pfn;
+	struct {
+		struct fence	*active;
+		atomic_long_t	owner;
+	} ids[AMDGPU_NUM_VM];
+
+	uint32_t				max_pfn;
 	/* number of VMIDs */
-	unsigned			nvm;
+	unsigned				nvm;
 	/* vram base address for page table entry  */
-	u64				vram_base_offset;
+	u64					vram_base_offset;
 	/* is vm enabled? */
-	bool				enabled;
-	/* for hw to save the PD addr on suspend/resume */
-	uint32_t			saved_table_addr[AMDGPU_NUM_VM];
+	bool					enabled;
 	/* vm pte handling */
 	const struct amdgpu_vm_pte_funcs        *vm_pte_funcs;
 	struct amdgpu_ring                      *vm_pte_funcs_ring;
 };
 
+void amdgpu_vm_manager_fini(struct amdgpu_device *adev);
+int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm);
+void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm);
+struct amdgpu_bo_list_entry *amdgpu_vm_get_bos(struct amdgpu_device *adev,
+					       struct amdgpu_vm *vm,
+					       struct list_head *head);
+int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
+		      struct amdgpu_sync *sync);
+void amdgpu_vm_flush(struct amdgpu_ring *ring,
+		     struct amdgpu_vm *vm,
+		     struct fence *updates);
+void amdgpu_vm_fence(struct amdgpu_device *adev,
+		     struct amdgpu_vm *vm,
+		     struct fence *fence);
+uint64_t amdgpu_vm_map_gart(struct amdgpu_device *adev, uint64_t addr);
+int amdgpu_vm_update_page_directory(struct amdgpu_device *adev,
+				    struct amdgpu_vm *vm);
+int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
+			  struct amdgpu_vm *vm);
+int amdgpu_vm_clear_invalids(struct amdgpu_device *adev, struct amdgpu_vm *vm,
+			     struct amdgpu_sync *sync);
+int amdgpu_vm_bo_update(struct amdgpu_device *adev,
+			struct amdgpu_bo_va *bo_va,
+			struct ttm_mem_reg *mem);
+void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev,
+			     struct amdgpu_bo *bo);
+struct amdgpu_bo_va *amdgpu_vm_bo_find(struct amdgpu_vm *vm,
+				       struct amdgpu_bo *bo);
+struct amdgpu_bo_va *amdgpu_vm_bo_add(struct amdgpu_device *adev,
+				      struct amdgpu_vm *vm,
+				      struct amdgpu_bo *bo);
+int amdgpu_vm_bo_map(struct amdgpu_device *adev,
+		     struct amdgpu_bo_va *bo_va,
+		     uint64_t addr, uint64_t offset,
+		     uint64_t size, uint32_t flags);
+int amdgpu_vm_bo_unmap(struct amdgpu_device *adev,
+		       struct amdgpu_bo_va *bo_va,
+		       uint64_t addr);
+void amdgpu_vm_bo_rmv(struct amdgpu_device *adev,
+		      struct amdgpu_bo_va *bo_va);
+int amdgpu_vm_free_job(struct amdgpu_job *job);
+
 /*
  * context related structures
  */
@@ -1211,6 +1256,7 @@
 	/* relocations */
 	struct amdgpu_bo_list_entry	*vm_bos;
 	struct list_head	validated;
+	struct fence		*fence;
 
 	struct amdgpu_ib	*ibs;
 	uint32_t		num_ibs;
@@ -1226,7 +1272,7 @@
 	struct amdgpu_device	*adev;
 	struct amdgpu_ib	*ibs;
 	uint32_t		num_ibs;
-	struct mutex            job_lock;
+	void			*owner;
 	struct amdgpu_user_fence uf;
 	int (*free_job)(struct amdgpu_job *job);
 };
@@ -2257,11 +2303,6 @@
 bool amdgpu_card_posted(struct amdgpu_device *adev);
 void amdgpu_update_display_priority(struct amdgpu_device *adev);
 bool amdgpu_boot_test_post_card(struct amdgpu_device *adev);
-struct amdgpu_cs_parser *amdgpu_cs_parser_create(struct amdgpu_device *adev,
-						 struct drm_file *filp,
-						 struct amdgpu_ctx *ctx,
-						 struct amdgpu_ib *ibs,
-						 uint32_t num_ibs);
 
 int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data);
 int amdgpu_cs_get_ring(struct amdgpu_device *adev, u32 ip_type,
@@ -2319,49 +2360,6 @@
 			     unsigned long arg);
 
 /*
- * vm
- */
-int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm);
-void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm);
-struct amdgpu_bo_list_entry *amdgpu_vm_get_bos(struct amdgpu_device *adev,
-					  struct amdgpu_vm *vm,
-					  struct list_head *head);
-int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
-		      struct amdgpu_sync *sync);
-void amdgpu_vm_flush(struct amdgpu_ring *ring,
-		     struct amdgpu_vm *vm,
-		     struct fence *updates);
-void amdgpu_vm_fence(struct amdgpu_device *adev,
-		     struct amdgpu_vm *vm,
-		     struct amdgpu_fence *fence);
-uint64_t amdgpu_vm_map_gart(struct amdgpu_device *adev, uint64_t addr);
-int amdgpu_vm_update_page_directory(struct amdgpu_device *adev,
-				    struct amdgpu_vm *vm);
-int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
-				struct amdgpu_vm *vm);
-int amdgpu_vm_clear_invalids(struct amdgpu_device *adev,
-				struct amdgpu_vm *vm, struct amdgpu_sync *sync);
-int amdgpu_vm_bo_update(struct amdgpu_device *adev,
-			struct amdgpu_bo_va *bo_va,
-			struct ttm_mem_reg *mem);
-void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev,
-			     struct amdgpu_bo *bo);
-struct amdgpu_bo_va *amdgpu_vm_bo_find(struct amdgpu_vm *vm,
-				       struct amdgpu_bo *bo);
-struct amdgpu_bo_va *amdgpu_vm_bo_add(struct amdgpu_device *adev,
-				      struct amdgpu_vm *vm,
-				      struct amdgpu_bo *bo);
-int amdgpu_vm_bo_map(struct amdgpu_device *adev,
-		     struct amdgpu_bo_va *bo_va,
-		     uint64_t addr, uint64_t offset,
-		     uint64_t size, uint32_t flags);
-int amdgpu_vm_bo_unmap(struct amdgpu_device *adev,
-		       struct amdgpu_bo_va *bo_va,
-		       uint64_t addr);
-void amdgpu_vm_bo_rmv(struct amdgpu_device *adev,
-		      struct amdgpu_bo_va *bo_va);
-int amdgpu_vm_free_job(struct amdgpu_job *job);
-/*
  * functions used by amdgpu_encoder.c
  */
 struct amdgpu_afmt_acr {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index dfc4d02..4f352ec 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -127,30 +127,6 @@
 	return 0;
 }
 
-struct amdgpu_cs_parser *amdgpu_cs_parser_create(struct amdgpu_device *adev,
-                                               struct drm_file *filp,
-                                               struct amdgpu_ctx *ctx,
-                                               struct amdgpu_ib *ibs,
-                                               uint32_t num_ibs)
-{
-	struct amdgpu_cs_parser *parser;
-	int i;
-
-	parser = kzalloc(sizeof(struct amdgpu_cs_parser), GFP_KERNEL);
-	if (!parser)
-		return NULL;
-
-	parser->adev = adev;
-	parser->filp = filp;
-	parser->ctx = ctx;
-	parser->ibs = ibs;
-	parser->num_ibs = num_ibs;
-	for (i = 0; i < num_ibs; i++)
-		ibs[i].ctx = ctx;
-
-	return parser;
-}
-
 int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
 {
 	union drm_amdgpu_cs *cs = data;
@@ -246,6 +222,8 @@
 				}
 
 				p->uf.bo = gem_to_amdgpu_bo(gobj);
+				amdgpu_bo_ref(p->uf.bo);
+				drm_gem_object_unreference_unlocked(gobj);
 				p->uf.offset = fence_data->offset;
 			} else {
 				ret = -EINVAL;
@@ -463,8 +441,18 @@
 	return (int)la->robj->tbo.num_pages - (int)lb->robj->tbo.num_pages;
 }
 
-static void amdgpu_cs_parser_fini_early(struct amdgpu_cs_parser *parser, int error, bool backoff)
+/**
+ * cs_parser_fini() - clean parser states
+ * @parser:	parser structure holding parsing context.
+ * @error:	error number
+ *
+ * If error is set than unvalidate buffer, otherwise just free memory
+ * used by parsing context.
+ **/
+static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error, bool backoff)
 {
+	unsigned i;
+
 	if (!error) {
 		/* Sort the buffer list from the smallest to largest buffer,
 		 * which affects the order of buffers in the LRU list.
@@ -479,17 +467,14 @@
 		list_sort(NULL, &parser->validated, cmp_size_smaller_first);
 
 		ttm_eu_fence_buffer_objects(&parser->ticket,
-				&parser->validated,
-				&parser->ibs[parser->num_ibs-1].fence->base);
+					    &parser->validated,
+					    parser->fence);
 	} else if (backoff) {
 		ttm_eu_backoff_reservation(&parser->ticket,
 					   &parser->validated);
 	}
-}
+	fence_put(parser->fence);
 
-static void amdgpu_cs_parser_fini_late(struct amdgpu_cs_parser *parser)
-{
-	unsigned i;
 	if (parser->ctx)
 		amdgpu_ctx_put(parser->ctx);
 	if (parser->bo_list)
@@ -499,31 +484,12 @@
 	for (i = 0; i < parser->nchunks; i++)
 		drm_free_large(parser->chunks[i].kdata);
 	kfree(parser->chunks);
-	if (!amdgpu_enable_scheduler)
-	{
-		if (parser->ibs)
-			for (i = 0; i < parser->num_ibs; i++)
-				amdgpu_ib_free(parser->adev, &parser->ibs[i]);
-		kfree(parser->ibs);
-		if (parser->uf.bo)
-			drm_gem_object_unreference_unlocked(&parser->uf.bo->gem_base);
-	}
-
-	kfree(parser);
-}
-
-/**
- * cs_parser_fini() - clean parser states
- * @parser:	parser structure holding parsing context.
- * @error:	error number
- *
- * If error is set than unvalidate buffer, otherwise just free memory
- * used by parsing context.
- **/
-static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error, bool backoff)
-{
-       amdgpu_cs_parser_fini_early(parser, error, backoff);
-       amdgpu_cs_parser_fini_late(parser);
+	if (parser->ibs)
+		for (i = 0; i < parser->num_ibs; i++)
+			amdgpu_ib_free(parser->adev, &parser->ibs[i]);
+	kfree(parser->ibs);
+	if (parser->uf.bo)
+		amdgpu_bo_unref(&parser->uf.bo);
 }
 
 static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p,
@@ -610,15 +576,9 @@
 	}
 
 	r = amdgpu_bo_vm_update_pte(parser, vm);
-	if (r) {
-		goto out;
-	}
-	amdgpu_cs_sync_rings(parser);
-	if (!amdgpu_enable_scheduler)
-		r = amdgpu_ib_schedule(adev, parser->num_ibs, parser->ibs,
-				       parser->filp);
+	if (!r)
+		amdgpu_cs_sync_rings(parser);
 
-out:
 	return r;
 }
 
@@ -818,7 +778,7 @@
 			amdgpu_ib_free(job->adev, &job->ibs[i]);
 	kfree(job->ibs);
 	if (job->uf.bo)
-		drm_gem_object_unreference_unlocked(&job->uf.bo->gem_base);
+		amdgpu_bo_unref(&job->uf.bo);
 	return 0;
 }
 
@@ -826,38 +786,35 @@
 {
 	struct amdgpu_device *adev = dev->dev_private;
 	union drm_amdgpu_cs *cs = data;
-	struct amdgpu_fpriv *fpriv = filp->driver_priv;
-	struct amdgpu_vm *vm = &fpriv->vm;
-	struct amdgpu_cs_parser *parser;
+	struct amdgpu_cs_parser parser = {};
 	bool reserved_buffers = false;
 	int i, r;
 
 	if (!adev->accel_working)
 		return -EBUSY;
 
-	parser = amdgpu_cs_parser_create(adev, filp, NULL, NULL, 0);
-	if (!parser)
-		return -ENOMEM;
-	r = amdgpu_cs_parser_init(parser, data);
+	parser.adev = adev;
+	parser.filp = filp;
+
+	r = amdgpu_cs_parser_init(&parser, data);
 	if (r) {
 		DRM_ERROR("Failed to initialize parser !\n");
-		amdgpu_cs_parser_fini(parser, r, false);
+		amdgpu_cs_parser_fini(&parser, r, false);
 		r = amdgpu_cs_handle_lockup(adev, r);
 		return r;
 	}
-	mutex_lock(&vm->mutex);
-	r = amdgpu_cs_parser_relocs(parser);
+	r = amdgpu_cs_parser_relocs(&parser);
 	if (r == -ENOMEM)
 		DRM_ERROR("Not enough memory for command submission!\n");
 	else if (r && r != -ERESTARTSYS)
 		DRM_ERROR("Failed to process the buffer list %d!\n", r);
 	else if (!r) {
 		reserved_buffers = true;
-		r = amdgpu_cs_ib_fill(adev, parser);
+		r = amdgpu_cs_ib_fill(adev, &parser);
 	}
 
 	if (!r) {
-		r = amdgpu_cs_dependencies(adev, parser);
+		r = amdgpu_cs_dependencies(adev, &parser);
 		if (r)
 			DRM_ERROR("Failed in the dependencies handling %d!\n", r);
 	}
@@ -865,63 +822,71 @@
 	if (r)
 		goto out;
 
-	for (i = 0; i < parser->num_ibs; i++)
-		trace_amdgpu_cs(parser, i);
+	for (i = 0; i < parser.num_ibs; i++)
+		trace_amdgpu_cs(&parser, i);
 
-	r = amdgpu_cs_ib_vm_chunk(adev, parser);
+	r = amdgpu_cs_ib_vm_chunk(adev, &parser);
 	if (r)
 		goto out;
 
-	if (amdgpu_enable_scheduler && parser->num_ibs) {
+	if (amdgpu_enable_scheduler && parser.num_ibs) {
+		struct amdgpu_ring * ring = parser.ibs->ring;
+		struct amd_sched_fence *fence;
 		struct amdgpu_job *job;
-		struct amdgpu_ring * ring =  parser->ibs->ring;
+
 		job = kzalloc(sizeof(struct amdgpu_job), GFP_KERNEL);
 		if (!job) {
 			r = -ENOMEM;
 			goto out;
 		}
+
 		job->base.sched = &ring->sched;
-		job->base.s_entity = &parser->ctx->rings[ring->idx].entity;
-		job->adev = parser->adev;
-		job->ibs = parser->ibs;
-		job->num_ibs = parser->num_ibs;
-		job->base.owner = parser->filp;
-		mutex_init(&job->job_lock);
+		job->base.s_entity = &parser.ctx->rings[ring->idx].entity;
+		job->adev = parser.adev;
+		job->owner = parser.filp;
+		job->free_job = amdgpu_cs_free_job;
+
+		job->ibs = parser.ibs;
+		job->num_ibs = parser.num_ibs;
+		parser.ibs = NULL;
+		parser.num_ibs = 0;
+
 		if (job->ibs[job->num_ibs - 1].user) {
-			memcpy(&job->uf,  &parser->uf,
-			       sizeof(struct amdgpu_user_fence));
+			job->uf = parser.uf;
 			job->ibs[job->num_ibs - 1].user = &job->uf;
+			parser.uf.bo = NULL;
 		}
 
-		job->free_job = amdgpu_cs_free_job;
-		mutex_lock(&job->job_lock);
-		r = amd_sched_entity_push_job(&job->base);
-		if (r) {
-			mutex_unlock(&job->job_lock);
+		fence = amd_sched_fence_create(job->base.s_entity,
+					       parser.filp);
+		if (!fence) {
+			r = -ENOMEM;
 			amdgpu_cs_free_job(job);
 			kfree(job);
 			goto out;
 		}
-		cs->out.handle =
-			amdgpu_ctx_add_fence(parser->ctx, ring,
-					     &job->base.s_fence->base);
-		parser->ibs[parser->num_ibs - 1].sequence = cs->out.handle;
+		job->base.s_fence = fence;
+		parser.fence = fence_get(&fence->base);
 
-		list_sort(NULL, &parser->validated, cmp_size_smaller_first);
-		ttm_eu_fence_buffer_objects(&parser->ticket,
-				&parser->validated,
-				&job->base.s_fence->base);
+		cs->out.handle = amdgpu_ctx_add_fence(parser.ctx, ring,
+						      &fence->base);
+		job->ibs[job->num_ibs - 1].sequence = cs->out.handle;
 
-		mutex_unlock(&job->job_lock);
-		amdgpu_cs_parser_fini_late(parser);
-		mutex_unlock(&vm->mutex);
-		return 0;
+		trace_amdgpu_cs_ioctl(job);
+		amd_sched_entity_push_job(&job->base);
+
+	} else {
+		struct amdgpu_fence *fence;
+
+		r = amdgpu_ib_schedule(adev, parser.num_ibs, parser.ibs,
+				       parser.filp);
+		fence = parser.ibs[parser.num_ibs - 1].fence;
+		parser.fence = fence_get(&fence->base);
+		cs->out.handle = parser.ibs[parser.num_ibs - 1].sequence;
 	}
 
-	cs->out.handle = parser->ibs[parser->num_ibs - 1].sequence;
 out:
-	amdgpu_cs_parser_fini(parser, r, reserved_buffers);
-	mutex_unlock(&vm->mutex);
+	amdgpu_cs_parser_fini(&parser, r, reserved_buffers);
 	r = amdgpu_cs_handle_lockup(adev, r);
 	return r;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index e173a5a..5580d34 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -73,6 +73,8 @@
 	struct drm_crtc *crtc = &amdgpuCrtc->base;
 	unsigned long flags;
 	unsigned i;
+	int vpos, hpos, stat, min_udelay;
+	struct drm_vblank_crtc *vblank = &crtc->dev->vblank[work->crtc_id];
 
 	amdgpu_flip_wait_fence(adev, &work->excl);
 	for (i = 0; i < work->shared_count; ++i)
@@ -81,6 +83,41 @@
 	/* We borrow the event spin lock for protecting flip_status */
 	spin_lock_irqsave(&crtc->dev->event_lock, flags);
 
+	/* If this happens to execute within the "virtually extended" vblank
+	 * interval before the start of the real vblank interval then it needs
+	 * to delay programming the mmio flip until the real vblank is entered.
+	 * This prevents completing a flip too early due to the way we fudge
+	 * our vblank counter and vblank timestamps in order to work around the
+	 * problem that the hw fires vblank interrupts before actual start of
+	 * vblank (when line buffer refilling is done for a frame). It
+	 * complements the fudging logic in amdgpu_get_crtc_scanoutpos() for
+	 * timestamping and amdgpu_get_vblank_counter_kms() for vblank counts.
+	 *
+	 * In practice this won't execute very often unless on very fast
+	 * machines because the time window for this to happen is very small.
+	 */
+	for (;;) {
+		/* GET_DISTANCE_TO_VBLANKSTART returns distance to real vblank
+		 * start in hpos, and to the "fudged earlier" vblank start in
+		 * vpos.
+		 */
+		stat = amdgpu_get_crtc_scanoutpos(adev->ddev, work->crtc_id,
+						  GET_DISTANCE_TO_VBLANKSTART,
+						  &vpos, &hpos, NULL, NULL,
+						  &crtc->hwmode);
+
+		if ((stat & (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE)) !=
+		    (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE) ||
+		    !(vpos >= 0 && hpos <= 0))
+			break;
+
+		/* Sleep at least until estimated real start of hw vblank */
+		spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
+		min_udelay = (-hpos + 1) * max(vblank->linedur_ns / 1000, 5);
+		usleep_range(min_udelay, 2 * min_udelay);
+		spin_lock_irqsave(&crtc->dev->event_lock, flags);
+	};
+
 	/* do the flip (mmio) */
 	adev->mode_info.funcs->page_flip(adev, work->crtc_id, work->base);
 	/* set the flip status */
@@ -109,7 +146,7 @@
 	} else
 		DRM_ERROR("failed to reserve buffer after flip\n");
 
-	drm_gem_object_unreference_unlocked(&work->old_rbo->gem_base);
+	amdgpu_bo_unref(&work->old_rbo);
 	kfree(work->shared);
 	kfree(work);
 }
@@ -148,8 +185,8 @@
 	obj = old_amdgpu_fb->obj;
 
 	/* take a reference to the old object */
-	drm_gem_object_reference(obj);
 	work->old_rbo = gem_to_amdgpu_bo(obj);
+	amdgpu_bo_ref(work->old_rbo);
 
 	new_amdgpu_fb = to_amdgpu_framebuffer(fb);
 	obj = new_amdgpu_fb->obj;
@@ -222,7 +259,7 @@
 	amdgpu_bo_unreserve(new_rbo);
 
 cleanup:
-	drm_gem_object_unreference_unlocked(&work->old_rbo->gem_base);
+	amdgpu_bo_unref(&work->old_rbo);
 	fence_put(work->excl);
 	for (i = 0; i < work->shared_count; ++i)
 		fence_put(work->shared[i]);
@@ -712,6 +749,15 @@
  * \param dev Device to query.
  * \param pipe Crtc to query.
  * \param flags Flags from caller (DRM_CALLED_FROM_VBLIRQ or 0).
+ *              For driver internal use only also supports these flags:
+ *
+ *              USE_REAL_VBLANKSTART to use the real start of vblank instead
+ *              of a fudged earlier start of vblank.
+ *
+ *              GET_DISTANCE_TO_VBLANKSTART to return distance to the
+ *              fudged earlier start of vblank in *vpos and the distance
+ *              to true start of vblank in *hpos.
+ *
  * \param *vpos Location where vertical scanout position should be stored.
  * \param *hpos Location where horizontal scanout position should go.
  * \param *stime Target location for timestamp taken immediately before
@@ -776,10 +822,40 @@
 		vbl_end = 0;
 	}
 
+	/* Called from driver internal vblank counter query code? */
+	if (flags & GET_DISTANCE_TO_VBLANKSTART) {
+	    /* Caller wants distance from real vbl_start in *hpos */
+	    *hpos = *vpos - vbl_start;
+	}
+
+	/* Fudge vblank to start a few scanlines earlier to handle the
+	 * problem that vblank irqs fire a few scanlines before start
+	 * of vblank. Some driver internal callers need the true vblank
+	 * start to be used and signal this via the USE_REAL_VBLANKSTART flag.
+	 *
+	 * The cause of the "early" vblank irq is that the irq is triggered
+	 * by the line buffer logic when the line buffer read position enters
+	 * the vblank, whereas our crtc scanout position naturally lags the
+	 * line buffer read position.
+	 */
+	if (!(flags & USE_REAL_VBLANKSTART))
+		vbl_start -= adev->mode_info.crtcs[pipe]->lb_vblank_lead_lines;
+
 	/* Test scanout position against vblank region. */
 	if ((*vpos < vbl_start) && (*vpos >= vbl_end))
 		in_vbl = false;
 
+	/* In vblank? */
+	if (in_vbl)
+	    ret |= DRM_SCANOUTPOS_IN_VBLANK;
+
+	/* Called from driver internal vblank counter query code? */
+	if (flags & GET_DISTANCE_TO_VBLANKSTART) {
+		/* Caller wants distance from fudged earlier vbl_start */
+		*vpos -= vbl_start;
+		return ret;
+	}
+
 	/* Check if inside vblank area and apply corrective offsets:
 	 * vpos will then be >=0 in video scanout area, but negative
 	 * within vblank area, counting down the number of lines until
@@ -795,32 +871,6 @@
 	/* Correct for shifted end of vbl at vbl_end. */
 	*vpos = *vpos - vbl_end;
 
-	/* In vblank? */
-	if (in_vbl)
-		ret |= DRM_SCANOUTPOS_IN_VBLANK;
-
-	/* Is vpos outside nominal vblank area, but less than
-	 * 1/100 of a frame height away from start of vblank?
-	 * If so, assume this isn't a massively delayed vblank
-	 * interrupt, but a vblank interrupt that fired a few
-	 * microseconds before true start of vblank. Compensate
-	 * by adding a full frame duration to the final timestamp.
-	 * Happens, e.g., on ATI R500, R600.
-	 *
-	 * We only do this if DRM_CALLED_FROM_VBLIRQ.
-	 */
-	if ((flags & DRM_CALLED_FROM_VBLIRQ) && !in_vbl) {
-		vbl_start = mode->crtc_vdisplay;
-		vtotal = mode->crtc_vtotal;
-
-		if (vbl_start - *vpos < vtotal / 100) {
-			*vpos -= vtotal;
-
-			/* Signal this correction as "applied". */
-			ret |= 0x8;
-		}
-	}
-
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 257d722..3671f9f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -47,6 +47,9 @@
  * that the the relevant GPU caches have been flushed.
  */
 
+static struct kmem_cache *amdgpu_fence_slab;
+static atomic_t amdgpu_fence_slab_ref = ATOMIC_INIT(0);
+
 /**
  * amdgpu_fence_write - write a fence value
  *
@@ -85,24 +88,6 @@
 }
 
 /**
- * amdgpu_fence_schedule_check - schedule lockup check
- *
- * @ring: pointer to struct amdgpu_ring
- *
- * Queues a delayed work item to check for lockups.
- */
-static void amdgpu_fence_schedule_check(struct amdgpu_ring *ring)
-{
-	/*
-	 * Do not reset the timer here with mod_delayed_work,
-	 * this can livelock in an interaction with TTM delayed destroy.
-	 */
-	queue_delayed_work(system_power_efficient_wq,
-		&ring->fence_drv.lockup_work,
-		AMDGPU_FENCE_JIFFIES_TIMEOUT);
-}
-
-/**
  * amdgpu_fence_emit - emit a fence on the requested ring
  *
  * @ring: ring the fence is associated with
@@ -118,7 +103,7 @@
 	struct amdgpu_device *adev = ring->adev;
 
 	/* we are protected by the ring emission mutex */
-	*fence = kmalloc(sizeof(struct amdgpu_fence), GFP_KERNEL);
+	*fence = kmem_cache_alloc(amdgpu_fence_slab, GFP_KERNEL);
 	if ((*fence) == NULL) {
 		return -ENOMEM;
 	}
@@ -132,11 +117,23 @@
 	amdgpu_ring_emit_fence(ring, ring->fence_drv.gpu_addr,
 			       (*fence)->seq,
 			       AMDGPU_FENCE_FLAG_INT);
-	trace_amdgpu_fence_emit(ring->adev->ddev, ring->idx, (*fence)->seq);
 	return 0;
 }
 
 /**
+ * amdgpu_fence_schedule_fallback - schedule fallback check
+ *
+ * @ring: pointer to struct amdgpu_ring
+ *
+ * Start a timer as fallback to our interrupts.
+ */
+static void amdgpu_fence_schedule_fallback(struct amdgpu_ring *ring)
+{
+	mod_timer(&ring->fence_drv.fallback_timer,
+		  jiffies + AMDGPU_FENCE_JIFFIES_TIMEOUT);
+}
+
+/**
  * amdgpu_fence_activity - check for fence activity
  *
  * @ring: pointer to struct amdgpu_ring
@@ -202,33 +199,12 @@
 	} while (atomic64_xchg(&ring->fence_drv.last_seq, seq) > seq);
 
 	if (seq < last_emitted)
-		amdgpu_fence_schedule_check(ring);
+		amdgpu_fence_schedule_fallback(ring);
 
 	return wake;
 }
 
 /**
- * amdgpu_fence_check_lockup - check for hardware lockup
- *
- * @work: delayed work item
- *
- * Checks for fence activity and if there is none probe
- * the hardware if a lockup occured.
- */
-static void amdgpu_fence_check_lockup(struct work_struct *work)
-{
-	struct amdgpu_fence_driver *fence_drv;
-	struct amdgpu_ring *ring;
-
-	fence_drv = container_of(work, struct amdgpu_fence_driver,
-				lockup_work.work);
-	ring = fence_drv->ring;
-
-	if (amdgpu_fence_activity(ring))
-		wake_up_all(&ring->fence_drv.fence_queue);
-}
-
-/**
  * amdgpu_fence_process - process a fence
  *
  * @adev: amdgpu_device pointer
@@ -244,6 +220,20 @@
 }
 
 /**
+ * amdgpu_fence_fallback - fallback for hardware interrupts
+ *
+ * @work: delayed work item
+ *
+ * Checks for fence activity.
+ */
+static void amdgpu_fence_fallback(unsigned long arg)
+{
+	struct amdgpu_ring *ring = (void *)arg;
+
+	amdgpu_fence_process(ring);
+}
+
+/**
  * amdgpu_fence_seq_signaled - check if a fence sequence number has signaled
  *
  * @ring: ring the fence is associated with
@@ -290,7 +280,7 @@
 	if (atomic64_read(&ring->fence_drv.last_seq) >= seq)
 		return 0;
 
-	amdgpu_fence_schedule_check(ring);
+	amdgpu_fence_schedule_fallback(ring);
 	wait_event(ring->fence_drv.fence_queue, (
 		   (signaled = amdgpu_fence_seq_signaled(ring, seq))));
 
@@ -491,9 +481,8 @@
 	atomic64_set(&ring->fence_drv.last_seq, 0);
 	ring->fence_drv.initialized = false;
 
-	INIT_DELAYED_WORK(&ring->fence_drv.lockup_work,
-			amdgpu_fence_check_lockup);
-	ring->fence_drv.ring = ring;
+	setup_timer(&ring->fence_drv.fallback_timer, amdgpu_fence_fallback,
+		    (unsigned long)ring);
 
 	init_waitqueue_head(&ring->fence_drv.fence_queue);
 
@@ -536,6 +525,13 @@
  */
 int amdgpu_fence_driver_init(struct amdgpu_device *adev)
 {
+	if (atomic_inc_return(&amdgpu_fence_slab_ref) == 1) {
+		amdgpu_fence_slab = kmem_cache_create(
+			"amdgpu_fence", sizeof(struct amdgpu_fence), 0,
+			SLAB_HWCACHE_ALIGN, NULL);
+		if (!amdgpu_fence_slab)
+			return -ENOMEM;
+	}
 	if (amdgpu_debugfs_fence_init(adev))
 		dev_err(adev->dev, "fence debugfs file creation failed\n");
 
@@ -554,9 +550,12 @@
 {
 	int i, r;
 
+	if (atomic_dec_and_test(&amdgpu_fence_slab_ref))
+		kmem_cache_destroy(amdgpu_fence_slab);
 	mutex_lock(&adev->ring_lock);
 	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
 		struct amdgpu_ring *ring = adev->rings[i];
+
 		if (!ring || !ring->fence_drv.initialized)
 			continue;
 		r = amdgpu_fence_wait_empty(ring);
@@ -568,6 +567,7 @@
 		amdgpu_irq_put(adev, ring->fence_drv.irq_src,
 			       ring->fence_drv.irq_type);
 		amd_sched_fini(&ring->sched);
+		del_timer_sync(&ring->fence_drv.fallback_timer);
 		ring->fence_drv.initialized = false;
 	}
 	mutex_unlock(&adev->ring_lock);
@@ -751,18 +751,25 @@
 	fence->fence_wake.func = amdgpu_fence_check_signaled;
 	__add_wait_queue(&ring->fence_drv.fence_queue, &fence->fence_wake);
 	fence_get(f);
-	amdgpu_fence_schedule_check(ring);
+	if (!timer_pending(&ring->fence_drv.fallback_timer))
+		amdgpu_fence_schedule_fallback(ring);
 	FENCE_TRACE(&fence->base, "armed on ring %i!\n", ring->idx);
 	return true;
 }
 
+static void amdgpu_fence_release(struct fence *f)
+{
+	struct amdgpu_fence *fence = to_amdgpu_fence(f);
+	kmem_cache_free(amdgpu_fence_slab, fence);
+}
+
 const struct fence_ops amdgpu_fence_ops = {
 	.get_driver_name = amdgpu_fence_get_driver_name,
 	.get_timeline_name = amdgpu_fence_get_timeline_name,
 	.enable_signaling = amdgpu_fence_enable_signaling,
 	.signaled = amdgpu_fence_is_signaled,
 	.wait = fence_default_wait,
-	.release = NULL,
+	.release = amdgpu_fence_release,
 };
 
 /*
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 0873328..9c253c5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -115,12 +115,9 @@
 	struct amdgpu_vm *vm = &fpriv->vm;
 	struct amdgpu_bo_va *bo_va;
 	int r;
-	mutex_lock(&vm->mutex);
 	r = amdgpu_bo_reserve(rbo, false);
-	if (r) {
-		mutex_unlock(&vm->mutex);
+	if (r)
 		return r;
-	}
 
 	bo_va = amdgpu_vm_bo_find(vm, rbo);
 	if (!bo_va) {
@@ -129,7 +126,6 @@
 		++bo_va->ref_count;
 	}
 	amdgpu_bo_unreserve(rbo);
-	mutex_unlock(&vm->mutex);
 	return 0;
 }
 
@@ -142,10 +138,8 @@
 	struct amdgpu_vm *vm = &fpriv->vm;
 	struct amdgpu_bo_va *bo_va;
 	int r;
-	mutex_lock(&vm->mutex);
 	r = amdgpu_bo_reserve(rbo, true);
 	if (r) {
-		mutex_unlock(&vm->mutex);
 		dev_err(adev->dev, "leaking bo va because "
 			"we fail to reserve bo (%d)\n", r);
 		return;
@@ -157,7 +151,6 @@
 		}
 	}
 	amdgpu_bo_unreserve(rbo);
-	mutex_unlock(&vm->mutex);
 }
 
 static int amdgpu_gem_handle_lockup(struct amdgpu_device *adev, int r)
@@ -242,8 +235,9 @@
 	    AMDGPU_GEM_USERPTR_REGISTER))
 		return -EINVAL;
 
-	if (!(args->flags & AMDGPU_GEM_USERPTR_ANONONLY) ||
-		   !(args->flags & AMDGPU_GEM_USERPTR_REGISTER)) {
+	if (!(args->flags & AMDGPU_GEM_USERPTR_READONLY) && (
+	     !(args->flags & AMDGPU_GEM_USERPTR_ANONONLY) ||
+	     !(args->flags & AMDGPU_GEM_USERPTR_REGISTER))) {
 
 		/* if we want to write to it we must require anonymous
 		   memory and install a MMU notifier */
@@ -483,6 +477,17 @@
 		if (domain == AMDGPU_GEM_DOMAIN_CPU)
 			goto error_unreserve;
 	}
+	list_for_each_entry(entry, &duplicates, head) {
+		domain = amdgpu_mem_type_to_domain(entry->bo->mem.mem_type);
+		/* if anything is swapped out don't swap it in here,
+		   just abort and wait for the next CS */
+		if (domain == AMDGPU_GEM_DOMAIN_CPU)
+			goto error_unreserve;
+	}
+
+	r = amdgpu_vm_update_page_directory(adev, bo_va->vm);
+	if (r)
+		goto error_unreserve;
 
 	r = amdgpu_vm_clear_freed(adev, bo_va->vm);
 	if (r)
@@ -512,6 +517,9 @@
 	struct amdgpu_fpriv *fpriv = filp->driver_priv;
 	struct amdgpu_bo *rbo;
 	struct amdgpu_bo_va *bo_va;
+	struct ttm_validate_buffer tv, tv_pd;
+	struct ww_acquire_ctx ticket;
+	struct list_head list, duplicates;
 	uint32_t invalid_flags, va_flags = 0;
 	int r = 0;
 
@@ -547,19 +555,28 @@
 	gobj = drm_gem_object_lookup(dev, filp, args->handle);
 	if (gobj == NULL)
 		return -ENOENT;
-	mutex_lock(&fpriv->vm.mutex);
 	rbo = gem_to_amdgpu_bo(gobj);
-	r = amdgpu_bo_reserve(rbo, false);
+	INIT_LIST_HEAD(&list);
+	INIT_LIST_HEAD(&duplicates);
+	tv.bo = &rbo->tbo;
+	tv.shared = true;
+	list_add(&tv.head, &list);
+
+	if (args->operation == AMDGPU_VA_OP_MAP) {
+		tv_pd.bo = &fpriv->vm.page_directory->tbo;
+		tv_pd.shared = true;
+		list_add(&tv_pd.head, &list);
+	}
+	r = ttm_eu_reserve_buffers(&ticket, &list, true, &duplicates);
 	if (r) {
-		mutex_unlock(&fpriv->vm.mutex);
 		drm_gem_object_unreference_unlocked(gobj);
 		return r;
 	}
 
 	bo_va = amdgpu_vm_bo_find(&fpriv->vm, rbo);
 	if (!bo_va) {
-		amdgpu_bo_unreserve(rbo);
-		mutex_unlock(&fpriv->vm.mutex);
+		ttm_eu_backoff_reservation(&ticket, &list);
+		drm_gem_object_unreference_unlocked(gobj);
 		return -ENOENT;
 	}
 
@@ -581,10 +598,10 @@
 	default:
 		break;
 	}
-
+	ttm_eu_backoff_reservation(&ticket, &list);
 	if (!r && !(args->flags & AMDGPU_VM_DELAY_UPDATE))
 		amdgpu_gem_va_update_vm(adev, bo_va, args->operation);
-	mutex_unlock(&fpriv->vm.mutex);
+
 	drm_gem_object_unreference_unlocked(gobj);
 	return r;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index e659877..9e25eda 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -62,7 +62,7 @@
 	int r;
 
 	if (size) {
-		r = amdgpu_sa_bo_new(adev, &adev->ring_tmp_bo,
+		r = amdgpu_sa_bo_new(&adev->ring_tmp_bo,
 				      &ib->sa_bo, size, 256);
 		if (r) {
 			dev_err(adev->dev, "failed to get a new IB (%d)\n", r);
@@ -216,7 +216,7 @@
 	}
 
 	if (ib->vm)
-		amdgpu_vm_fence(adev, ib->vm, ib->fence);
+		amdgpu_vm_fence(adev, ib->vm, &ib->fence->base);
 
 	amdgpu_ring_unlock_commit(ring);
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 1618e22..e23843f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -611,13 +611,59 @@
 u32 amdgpu_get_vblank_counter_kms(struct drm_device *dev, unsigned int pipe)
 {
 	struct amdgpu_device *adev = dev->dev_private;
+	int vpos, hpos, stat;
+	u32 count;
 
 	if (pipe >= adev->mode_info.num_crtc) {
 		DRM_ERROR("Invalid crtc %u\n", pipe);
 		return -EINVAL;
 	}
 
-	return amdgpu_display_vblank_get_counter(adev, pipe);
+	/* The hw increments its frame counter at start of vsync, not at start
+	 * of vblank, as is required by DRM core vblank counter handling.
+	 * Cook the hw count here to make it appear to the caller as if it
+	 * incremented at start of vblank. We measure distance to start of
+	 * vblank in vpos. vpos therefore will be >= 0 between start of vblank
+	 * and start of vsync, so vpos >= 0 means to bump the hw frame counter
+	 * result by 1 to give the proper appearance to caller.
+	 */
+	if (adev->mode_info.crtcs[pipe]) {
+		/* Repeat readout if needed to provide stable result if
+		 * we cross start of vsync during the queries.
+		 */
+		do {
+			count = amdgpu_display_vblank_get_counter(adev, pipe);
+			/* Ask amdgpu_get_crtc_scanoutpos to return vpos as
+			 * distance to start of vblank, instead of regular
+			 * vertical scanout pos.
+			 */
+			stat = amdgpu_get_crtc_scanoutpos(
+				dev, pipe, GET_DISTANCE_TO_VBLANKSTART,
+				&vpos, &hpos, NULL, NULL,
+				&adev->mode_info.crtcs[pipe]->base.hwmode);
+		} while (count != amdgpu_display_vblank_get_counter(adev, pipe));
+
+		if (((stat & (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE)) !=
+		    (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE))) {
+			DRM_DEBUG_VBL("Query failed! stat %d\n", stat);
+		} else {
+			DRM_DEBUG_VBL("crtc %d: dist from vblank start %d\n",
+				      pipe, vpos);
+
+			/* Bump counter if we are at >= leading edge of vblank,
+			 * but before vsync where vpos would turn negative and
+			 * the hw counter really increments.
+			 */
+			if (vpos >= 0)
+				count++;
+		}
+	} else {
+		/* Fallback to use value as is. */
+		count = amdgpu_display_vblank_get_counter(adev, pipe);
+		DRM_DEBUG_VBL("NULL mode info! Returned count may be wrong.\n");
+	}
+
+	return count;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
index b62c171..064ebb3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
@@ -407,6 +407,7 @@
 	u32 line_time;
 	u32 wm_low;
 	u32 wm_high;
+	u32 lb_vblank_lead_lines;
 	struct drm_display_mode hw_mode;
 };
 
@@ -528,6 +529,10 @@
 #define ENCODER_MODE_IS_DP(em) (((em) == ATOM_ENCODER_MODE_DP) || \
 				((em) == ATOM_ENCODER_MODE_DP_MST))
 
+/* Driver internal use only flags of amdgpu_get_crtc_scanoutpos() */
+#define USE_REAL_VBLANKSTART 		(1 << 30)
+#define GET_DISTANCE_TO_VBLANKSTART	(1 << 31)
+
 void amdgpu_link_encoder_connector(struct drm_device *dev);
 
 struct drm_connector *
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 0d52438..c3ce103 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -100,6 +100,7 @@
 	list_del_init(&bo->list);
 	mutex_unlock(&bo->adev->gem.mutex);
 	drm_gem_object_release(&bo->gem_base);
+	amdgpu_bo_unref(&bo->parent);
 	kfree(bo->metadata);
 	kfree(bo);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
index 3c2ff45..ea756e7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
@@ -189,10 +189,9 @@
 				      struct amdgpu_sa_manager *sa_manager);
 int amdgpu_sa_bo_manager_suspend(struct amdgpu_device *adev,
 					struct amdgpu_sa_manager *sa_manager);
-int amdgpu_sa_bo_new(struct amdgpu_device *adev,
-			    struct amdgpu_sa_manager *sa_manager,
-			    struct amdgpu_sa_bo **sa_bo,
-			    unsigned size, unsigned align);
+int amdgpu_sa_bo_new(struct amdgpu_sa_manager *sa_manager,
+		     struct amdgpu_sa_bo **sa_bo,
+		     unsigned size, unsigned align);
 void amdgpu_sa_bo_free(struct amdgpu_device *adev,
 			      struct amdgpu_sa_bo **sa_bo,
 			      struct fence *fence);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
index 0212b31..8b88edb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
@@ -311,8 +311,7 @@
 	return false;
 }
 
-int amdgpu_sa_bo_new(struct amdgpu_device *adev,
-		     struct amdgpu_sa_manager *sa_manager,
+int amdgpu_sa_bo_new(struct amdgpu_sa_manager *sa_manager,
 		     struct amdgpu_sa_bo **sa_bo,
 		     unsigned size, unsigned align)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
index dcf4a8a..438c052 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c
@@ -26,6 +26,7 @@
 #include <linux/sched.h>
 #include <drm/drmP.h>
 #include "amdgpu.h"
+#include "amdgpu_trace.h"
 
 static struct fence *amdgpu_sched_dependency(struct amd_sched_job *sched_job)
 {
@@ -44,11 +45,8 @@
 		return NULL;
 	}
 	job = to_amdgpu_job(sched_job);
-	mutex_lock(&job->job_lock);
-	r = amdgpu_ib_schedule(job->adev,
-			       job->num_ibs,
-			       job->ibs,
-			       job->base.owner);
+	trace_amdgpu_sched_run_job(job);
+	r = amdgpu_ib_schedule(job->adev, job->num_ibs, job->ibs, job->owner);
 	if (r) {
 		DRM_ERROR("Error scheduling IBs (%d)\n", r);
 		goto err;
@@ -61,8 +59,6 @@
 	if (job->free_job)
 		job->free_job(job);
 
-	mutex_unlock(&job->job_lock);
-	fence_put(&job->base.s_fence->base);
 	kfree(job);
 	return fence ? &fence->base : NULL;
 }
@@ -88,21 +84,19 @@
 			return -ENOMEM;
 		job->base.sched = &ring->sched;
 		job->base.s_entity = &adev->kernel_ctx.rings[ring->idx].entity;
+		job->base.s_fence = amd_sched_fence_create(job->base.s_entity, owner);
+		if (!job->base.s_fence) {
+			kfree(job);
+			return -ENOMEM;
+		}
+		*f = fence_get(&job->base.s_fence->base);
+
 		job->adev = adev;
 		job->ibs = ibs;
 		job->num_ibs = num_ibs;
-		job->base.owner = owner;
-		mutex_init(&job->job_lock);
+		job->owner = owner;
 		job->free_job = free_job;
-		mutex_lock(&job->job_lock);
-		r = amd_sched_entity_push_job(&job->base);
-		if (r) {
-			mutex_unlock(&job->job_lock);
-			kfree(job);
-			return r;
-		}
-		*f = fence_get(&job->base.s_fence->base);
-		mutex_unlock(&job->job_lock);
+		amd_sched_entity_push_job(&job->base);
 	} else {
 		r = amdgpu_ib_schedule(adev, num_ibs, ibs, owner);
 		if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_semaphore.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_semaphore.c
index ff3ca52..1caaf20 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_semaphore.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_semaphore.c
@@ -40,7 +40,7 @@
 	if (*semaphore == NULL) {
 		return -ENOMEM;
 	}
-	r = amdgpu_sa_bo_new(adev, &adev->ring_tmp_bo,
+	r = amdgpu_sa_bo_new(&adev->ring_tmp_bo,
 			     &(*semaphore)->sa_bo, 8, 8);
 	if (r) {
 		kfree(*semaphore);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
index a6697fd..dd005c3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
@@ -302,8 +302,14 @@
 			return -EINVAL;
 		}
 
-		if (amdgpu_enable_scheduler || !amdgpu_enable_semaphores ||
-		    (count >= AMDGPU_NUM_SYNCS)) {
+		if (amdgpu_enable_scheduler || !amdgpu_enable_semaphores) {
+			r = fence_wait(&fence->base, true);
+			if (r)
+				return r;
+			continue;
+		}
+
+		if (count >= AMDGPU_NUM_SYNCS) {
 			/* not enough room, wait manually */
 			r = fence_wait(&fence->base, false);
 			if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
index 76ecbaf..8f9834ab 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
@@ -48,6 +48,57 @@
 		      __entry->fences)
 );
 
+TRACE_EVENT(amdgpu_cs_ioctl,
+	    TP_PROTO(struct amdgpu_job *job),
+	    TP_ARGS(job),
+	    TP_STRUCT__entry(
+			     __field(struct amdgpu_device *, adev)
+			     __field(struct amd_sched_job *, sched_job)
+			     __field(struct amdgpu_ib *, ib)
+			     __field(struct fence *, fence)
+			     __field(char *, ring_name)
+			     __field(u32, num_ibs)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->adev = job->adev;
+			   __entry->sched_job = &job->base;
+			   __entry->ib = job->ibs;
+			   __entry->fence = &job->base.s_fence->base;
+			   __entry->ring_name = job->ibs[0].ring->name;
+			   __entry->num_ibs = job->num_ibs;
+			   ),
+	    TP_printk("adev=%p, sched_job=%p, first ib=%p, sched fence=%p, ring name:%s, num_ibs:%u",
+		      __entry->adev, __entry->sched_job, __entry->ib,
+		      __entry->fence, __entry->ring_name, __entry->num_ibs)
+);
+
+TRACE_EVENT(amdgpu_sched_run_job,
+	    TP_PROTO(struct amdgpu_job *job),
+	    TP_ARGS(job),
+	    TP_STRUCT__entry(
+			     __field(struct amdgpu_device *, adev)
+			     __field(struct amd_sched_job *, sched_job)
+			     __field(struct amdgpu_ib *, ib)
+			     __field(struct fence *, fence)
+			     __field(char *, ring_name)
+			     __field(u32, num_ibs)
+			     ),
+
+	    TP_fast_assign(
+			   __entry->adev = job->adev;
+			   __entry->sched_job = &job->base;
+			   __entry->ib = job->ibs;
+			   __entry->fence = &job->base.s_fence->base;
+			   __entry->ring_name = job->ibs[0].ring->name;
+			   __entry->num_ibs = job->num_ibs;
+			   ),
+	    TP_printk("adev=%p, sched_job=%p, first ib=%p, sched fence=%p, ring name:%s, num_ibs:%u",
+		      __entry->adev, __entry->sched_job, __entry->ib,
+		      __entry->fence, __entry->ring_name, __entry->num_ibs)
+);
+
+
 TRACE_EVENT(amdgpu_vm_grab_id,
 	    TP_PROTO(unsigned vmid, int ring),
 	    TP_ARGS(vmid, ring),
@@ -196,49 +247,6 @@
 	    TP_printk("list=%p, bo=%p", __entry->list, __entry->bo)
 );
 
-DECLARE_EVENT_CLASS(amdgpu_fence_request,
-
-	    TP_PROTO(struct drm_device *dev, int ring, u32 seqno),
-
-	    TP_ARGS(dev, ring, seqno),
-
-	    TP_STRUCT__entry(
-			     __field(u32, dev)
-			     __field(int, ring)
-			     __field(u32, seqno)
-			     ),
-
-	    TP_fast_assign(
-			   __entry->dev = dev->primary->index;
-			   __entry->ring = ring;
-			   __entry->seqno = seqno;
-			   ),
-
-	    TP_printk("dev=%u, ring=%d, seqno=%u",
-		      __entry->dev, __entry->ring, __entry->seqno)
-);
-
-DEFINE_EVENT(amdgpu_fence_request, amdgpu_fence_emit,
-
-	    TP_PROTO(struct drm_device *dev, int ring, u32 seqno),
-
-	    TP_ARGS(dev, ring, seqno)
-);
-
-DEFINE_EVENT(amdgpu_fence_request, amdgpu_fence_wait_begin,
-
-	    TP_PROTO(struct drm_device *dev, int ring, u32 seqno),
-
-	    TP_ARGS(dev, ring, seqno)
-);
-
-DEFINE_EVENT(amdgpu_fence_request, amdgpu_fence_wait_end,
-
-	    TP_PROTO(struct drm_device *dev, int ring, u32 seqno),
-
-	    TP_ARGS(dev, ring, seqno)
-);
-
 DECLARE_EVENT_CLASS(amdgpu_semaphore_request,
 
 	    TP_PROTO(int ring, struct amdgpu_semaphore *sem),
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 81bb8e9..8a1752f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -587,9 +587,13 @@
 	uint32_t flags = amdgpu_ttm_tt_pte_flags(gtt->adev, ttm, bo_mem);
 	int r;
 
-	if (gtt->userptr)
-		amdgpu_ttm_tt_pin_userptr(ttm);
-
+	if (gtt->userptr) {
+		r = amdgpu_ttm_tt_pin_userptr(ttm);
+		if (r) {
+			DRM_ERROR("failed to pin userptr\n");
+			return r;
+		}
+	}
 	gtt->offset = (unsigned long)(bo_mem->start << PAGE_SHIFT);
 	if (!ttm->num_pages) {
 		WARN(1, "nothing to bind %lu pages for mreg %p back %p!\n",
@@ -797,11 +801,12 @@
 	if (mem && mem->mem_type != TTM_PL_SYSTEM)
 		flags |= AMDGPU_PTE_VALID;
 
-	if (mem && mem->mem_type == TTM_PL_TT)
+	if (mem && mem->mem_type == TTM_PL_TT) {
 		flags |= AMDGPU_PTE_SYSTEM;
 
-	if (!ttm || ttm->caching_state == tt_cached)
-		flags |= AMDGPU_PTE_SNOOPED;
+		if (ttm->caching_state == tt_cached)
+			flags |= AMDGPU_PTE_SNOOPED;
+	}
 
 	if (adev->asic_type >= CHIP_TOPAZ)
 		flags |= AMDGPU_PTE_EXECUTABLE;
@@ -1073,10 +1078,10 @@
 	ret = drm_mm_dump_table(m, mm);
 	spin_unlock(&glob->lru_lock);
 	if (ttm_pl == TTM_PL_VRAM)
-		seq_printf(m, "man size:%llu pages, ram usage:%luMB, vis usage:%luMB\n",
+		seq_printf(m, "man size:%llu pages, ram usage:%lluMB, vis usage:%lluMB\n",
 			   adev->mman.bdev.man[ttm_pl].size,
-			   atomic64_read(&adev->vram_usage) >> 20,
-			   atomic64_read(&adev->vram_vis_usage) >> 20);
+			   (u64)atomic64_read(&adev->vram_usage) >> 20,
+			   (u64)atomic64_read(&adev->vram_vis_usage) >> 20);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index 03f0c3b..a745eee 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -392,7 +392,10 @@
 	ib->ptr[ib->length_dw++] = 0x00000001; /* session cmd */
 	ib->ptr[ib->length_dw++] = handle;
 
-	ib->ptr[ib->length_dw++] = 0x00000030; /* len */
+	if ((ring->adev->vce.fw_version >> 24) >= 52)
+		ib->ptr[ib->length_dw++] = 0x00000040; /* len */
+	else
+		ib->ptr[ib->length_dw++] = 0x00000030; /* len */
 	ib->ptr[ib->length_dw++] = 0x01000001; /* create cmd */
 	ib->ptr[ib->length_dw++] = 0x00000000;
 	ib->ptr[ib->length_dw++] = 0x00000042;
@@ -404,6 +407,12 @@
 	ib->ptr[ib->length_dw++] = 0x00000100;
 	ib->ptr[ib->length_dw++] = 0x0000000c;
 	ib->ptr[ib->length_dw++] = 0x00000000;
+	if ((ring->adev->vce.fw_version >> 24) >= 52) {
+		ib->ptr[ib->length_dw++] = 0x00000000;
+		ib->ptr[ib->length_dw++] = 0x00000000;
+		ib->ptr[ib->length_dw++] = 0x00000000;
+		ib->ptr[ib->length_dw++] = 0x00000000;
+	}
 
 	ib->ptr[ib->length_dw++] = 0x00000014; /* len */
 	ib->ptr[ib->length_dw++] = 0x05000005; /* feedback buffer */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 633a32a..b53d273 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -143,10 +143,15 @@
 	unsigned i;
 
 	/* check if the id is still valid */
-	if (vm_id->id && vm_id->last_id_use &&
-	    vm_id->last_id_use == adev->vm_manager.active[vm_id->id]) {
-		trace_amdgpu_vm_grab_id(vm_id->id, ring->idx);
-		return 0;
+	if (vm_id->id) {
+		unsigned id = vm_id->id;
+		long owner;
+
+		owner = atomic_long_read(&adev->vm_manager.ids[id].owner);
+		if (owner == (long)vm) {
+			trace_amdgpu_vm_grab_id(vm_id->id, ring->idx);
+			return 0;
+		}
 	}
 
 	/* we definately need to flush */
@@ -154,7 +159,7 @@
 
 	/* skip over VMID 0, since it is the system VM */
 	for (i = 1; i < adev->vm_manager.nvm; ++i) {
-		struct fence *fence = adev->vm_manager.active[i];
+		struct fence *fence = adev->vm_manager.ids[i].active;
 		struct amdgpu_ring *fring;
 
 		if (fence == NULL) {
@@ -176,7 +181,7 @@
 		if (choices[i]) {
 			struct fence *fence;
 
-			fence  = adev->vm_manager.active[choices[i]];
+			fence  = adev->vm_manager.ids[choices[i]].active;
 			vm_id->id = choices[i];
 
 			trace_amdgpu_vm_grab_id(choices[i], ring->idx);
@@ -207,24 +212,21 @@
 	uint64_t pd_addr = amdgpu_bo_gpu_offset(vm->page_directory);
 	struct amdgpu_vm_id *vm_id = &vm->ids[ring->idx];
 	struct fence *flushed_updates = vm_id->flushed_updates;
-	bool is_earlier = false;
+	bool is_later;
 
-	if (flushed_updates && updates) {
-		BUG_ON(flushed_updates->context != updates->context);
-		is_earlier = (updates->seqno - flushed_updates->seqno <=
-			      INT_MAX) ? true : false;
-	}
+	if (!flushed_updates)
+		is_later = true;
+	else if (!updates)
+		is_later = false;
+	else
+		is_later = fence_is_later(updates, flushed_updates);
 
-	if (pd_addr != vm_id->pd_gpu_addr || !flushed_updates ||
-	    is_earlier) {
-
+	if (pd_addr != vm_id->pd_gpu_addr || is_later) {
 		trace_amdgpu_vm_flush(pd_addr, ring->idx, vm_id->id);
-		if (is_earlier) {
+		if (is_later) {
 			vm_id->flushed_updates = fence_get(updates);
 			fence_put(flushed_updates);
 		}
-		if (!flushed_updates)
-			vm_id->flushed_updates = fence_get(updates);
 		vm_id->pd_gpu_addr = pd_addr;
 		amdgpu_ring_emit_vm_flush(ring, vm_id->id, vm_id->pd_gpu_addr);
 	}
@@ -244,16 +246,14 @@
  */
 void amdgpu_vm_fence(struct amdgpu_device *adev,
 		     struct amdgpu_vm *vm,
-		     struct amdgpu_fence *fence)
+		     struct fence *fence)
 {
-	unsigned ridx = fence->ring->idx;
-	unsigned vm_id = vm->ids[ridx].id;
+	struct amdgpu_ring *ring = amdgpu_ring_from_fence(fence);
+	unsigned vm_id = vm->ids[ring->idx].id;
 
-	fence_put(adev->vm_manager.active[vm_id]);
-	adev->vm_manager.active[vm_id] = fence_get(&fence->base);
-
-	fence_put(vm->ids[ridx].last_id_use);
-	vm->ids[ridx].last_id_use = fence_get(&fence->base);
+	fence_put(adev->vm_manager.ids[vm_id].active);
+	adev->vm_manager.ids[vm_id].active = fence_get(fence);
+	atomic_long_set(&adev->vm_manager.ids[vm_id].owner, (long)vm);
 }
 
 /**
@@ -332,6 +332,8 @@
  *
  * @adev: amdgpu_device pointer
  * @bo: bo to clear
+ *
+ * need to reserve bo first before calling it.
  */
 static int amdgpu_vm_clear_bo(struct amdgpu_device *adev,
 			      struct amdgpu_bo *bo)
@@ -343,24 +345,20 @@
 	uint64_t addr;
 	int r;
 
-	r = amdgpu_bo_reserve(bo, false);
-	if (r)
-		return r;
-
 	r = reservation_object_reserve_shared(bo->tbo.resv);
 	if (r)
 		return r;
 
 	r = ttm_bo_validate(&bo->tbo, &bo->placement, true, false);
 	if (r)
-		goto error_unreserve;
+		goto error;
 
 	addr = amdgpu_bo_gpu_offset(bo);
 	entries = amdgpu_bo_size(bo) / 8;
 
 	ib = kzalloc(sizeof(struct amdgpu_ib), GFP_KERNEL);
 	if (!ib)
-		goto error_unreserve;
+		goto error;
 
 	r = amdgpu_ib_get(ring, NULL, entries * 2 + 64, ib);
 	if (r)
@@ -378,16 +376,14 @@
 	if (!r)
 		amdgpu_bo_fence(bo, fence, true);
 	fence_put(fence);
-	if (amdgpu_enable_scheduler) {
-		amdgpu_bo_unreserve(bo);
+	if (amdgpu_enable_scheduler)
 		return 0;
-	}
+
 error_free:
 	amdgpu_ib_free(adev, ib);
 	kfree(ib);
 
-error_unreserve:
-	amdgpu_bo_unreserve(bo);
+error:
 	return r;
 }
 
@@ -889,17 +885,21 @@
 	struct amdgpu_bo_va_mapping *mapping;
 	int r;
 
+	spin_lock(&vm->freed_lock);
 	while (!list_empty(&vm->freed)) {
 		mapping = list_first_entry(&vm->freed,
 			struct amdgpu_bo_va_mapping, list);
 		list_del(&mapping->list);
-
+		spin_unlock(&vm->freed_lock);
 		r = amdgpu_vm_bo_update_mapping(adev, vm, mapping, 0, 0, NULL);
 		kfree(mapping);
 		if (r)
 			return r;
 
+		spin_lock(&vm->freed_lock);
 	}
+	spin_unlock(&vm->freed_lock);
+
 	return 0;
 
 }
@@ -926,8 +926,9 @@
 		bo_va = list_first_entry(&vm->invalidated,
 			struct amdgpu_bo_va, vm_status);
 		spin_unlock(&vm->status_lock);
-
+		mutex_lock(&bo_va->mutex);
 		r = amdgpu_vm_bo_update(adev, bo_va, NULL);
+		mutex_unlock(&bo_va->mutex);
 		if (r)
 			return r;
 
@@ -971,7 +972,7 @@
 	INIT_LIST_HEAD(&bo_va->valids);
 	INIT_LIST_HEAD(&bo_va->invalids);
 	INIT_LIST_HEAD(&bo_va->vm_status);
-
+	mutex_init(&bo_va->mutex);
 	list_add_tail(&bo_va->bo_list, &bo->va);
 
 	return bo_va;
@@ -989,7 +990,7 @@
  * Add a mapping of the BO at the specefied addr into the VM.
  * Returns 0 for success, error for failure.
  *
- * Object has to be reserved and gets unreserved by this function!
+ * Object has to be reserved and unreserved outside!
  */
 int amdgpu_vm_bo_map(struct amdgpu_device *adev,
 		     struct amdgpu_bo_va *bo_va,
@@ -1005,30 +1006,27 @@
 
 	/* validate the parameters */
 	if (saddr & AMDGPU_GPU_PAGE_MASK || offset & AMDGPU_GPU_PAGE_MASK ||
-	    size == 0 || size & AMDGPU_GPU_PAGE_MASK) {
-		amdgpu_bo_unreserve(bo_va->bo);
+	    size == 0 || size & AMDGPU_GPU_PAGE_MASK)
 		return -EINVAL;
-	}
 
 	/* make sure object fit at this offset */
 	eaddr = saddr + size;
-	if ((saddr >= eaddr) || (offset + size > amdgpu_bo_size(bo_va->bo))) {
-		amdgpu_bo_unreserve(bo_va->bo);
+	if ((saddr >= eaddr) || (offset + size > amdgpu_bo_size(bo_va->bo)))
 		return -EINVAL;
-	}
 
 	last_pfn = eaddr / AMDGPU_GPU_PAGE_SIZE;
 	if (last_pfn > adev->vm_manager.max_pfn) {
 		dev_err(adev->dev, "va above limit (0x%08X > 0x%08X)\n",
 			last_pfn, adev->vm_manager.max_pfn);
-		amdgpu_bo_unreserve(bo_va->bo);
 		return -EINVAL;
 	}
 
 	saddr /= AMDGPU_GPU_PAGE_SIZE;
 	eaddr /= AMDGPU_GPU_PAGE_SIZE;
 
+	spin_lock(&vm->it_lock);
 	it = interval_tree_iter_first(&vm->va, saddr, eaddr - 1);
+	spin_unlock(&vm->it_lock);
 	if (it) {
 		struct amdgpu_bo_va_mapping *tmp;
 		tmp = container_of(it, struct amdgpu_bo_va_mapping, it);
@@ -1036,14 +1034,12 @@
 		dev_err(adev->dev, "bo %p va 0x%010Lx-0x%010Lx conflict with "
 			"0x%010lx-0x%010lx\n", bo_va->bo, saddr, eaddr,
 			tmp->it.start, tmp->it.last + 1);
-		amdgpu_bo_unreserve(bo_va->bo);
 		r = -EINVAL;
 		goto error;
 	}
 
 	mapping = kmalloc(sizeof(*mapping), GFP_KERNEL);
 	if (!mapping) {
-		amdgpu_bo_unreserve(bo_va->bo);
 		r = -ENOMEM;
 		goto error;
 	}
@@ -1054,8 +1050,12 @@
 	mapping->offset = offset;
 	mapping->flags = flags;
 
+	mutex_lock(&bo_va->mutex);
 	list_add(&mapping->list, &bo_va->invalids);
+	mutex_unlock(&bo_va->mutex);
+	spin_lock(&vm->it_lock);
 	interval_tree_insert(&mapping->it, &vm->va);
+	spin_unlock(&vm->it_lock);
 	trace_amdgpu_vm_bo_map(bo_va, mapping);
 
 	/* Make sure the page tables are allocated */
@@ -1067,8 +1067,6 @@
 	if (eaddr > vm->max_pde_used)
 		vm->max_pde_used = eaddr;
 
-	amdgpu_bo_unreserve(bo_va->bo);
-
 	/* walk over the address space and allocate the page tables */
 	for (pt_idx = saddr; pt_idx <= eaddr; ++pt_idx) {
 		struct reservation_object *resv = vm->page_directory->tbo.resv;
@@ -1077,16 +1075,19 @@
 		if (vm->page_tables[pt_idx].bo)
 			continue;
 
-		ww_mutex_lock(&resv->lock, NULL);
 		r = amdgpu_bo_create(adev, AMDGPU_VM_PTE_COUNT * 8,
 				     AMDGPU_GPU_PAGE_SIZE, true,
 				     AMDGPU_GEM_DOMAIN_VRAM,
 				     AMDGPU_GEM_CREATE_NO_CPU_ACCESS,
 				     NULL, resv, &pt);
-		ww_mutex_unlock(&resv->lock);
 		if (r)
 			goto error_free;
 
+		/* Keep a reference to the page table to avoid freeing
+		 * them up in the wrong order.
+		 */
+		pt->parent = amdgpu_bo_ref(vm->page_directory);
+
 		r = amdgpu_vm_clear_bo(adev, pt);
 		if (r) {
 			amdgpu_bo_unref(&pt);
@@ -1101,7 +1102,9 @@
 
 error_free:
 	list_del(&mapping->list);
+	spin_lock(&vm->it_lock);
 	interval_tree_remove(&mapping->it, &vm->va);
+	spin_unlock(&vm->it_lock);
 	trace_amdgpu_vm_bo_unmap(bo_va, mapping);
 	kfree(mapping);
 
@@ -1119,7 +1122,7 @@
  * Remove a mapping of the BO at the specefied addr from the VM.
  * Returns 0 for success, error for failure.
  *
- * Object has to be reserved and gets unreserved by this function!
+ * Object has to be reserved and unreserved outside!
  */
 int amdgpu_vm_bo_unmap(struct amdgpu_device *adev,
 		       struct amdgpu_bo_va *bo_va,
@@ -1130,7 +1133,7 @@
 	bool valid = true;
 
 	saddr /= AMDGPU_GPU_PAGE_SIZE;
-
+	mutex_lock(&bo_va->mutex);
 	list_for_each_entry(mapping, &bo_va->valids, list) {
 		if (mapping->it.start == saddr)
 			break;
@@ -1145,20 +1148,24 @@
 		}
 
 		if (&mapping->list == &bo_va->invalids) {
-			amdgpu_bo_unreserve(bo_va->bo);
+			mutex_unlock(&bo_va->mutex);
 			return -ENOENT;
 		}
 	}
-
+	mutex_unlock(&bo_va->mutex);
 	list_del(&mapping->list);
+	spin_lock(&vm->it_lock);
 	interval_tree_remove(&mapping->it, &vm->va);
+	spin_unlock(&vm->it_lock);
 	trace_amdgpu_vm_bo_unmap(bo_va, mapping);
 
-	if (valid)
+	if (valid) {
+		spin_lock(&vm->freed_lock);
 		list_add(&mapping->list, &vm->freed);
-	else
+		spin_unlock(&vm->freed_lock);
+	} else {
 		kfree(mapping);
-	amdgpu_bo_unreserve(bo_va->bo);
+	}
 
 	return 0;
 }
@@ -1187,17 +1194,23 @@
 
 	list_for_each_entry_safe(mapping, next, &bo_va->valids, list) {
 		list_del(&mapping->list);
+		spin_lock(&vm->it_lock);
 		interval_tree_remove(&mapping->it, &vm->va);
+		spin_unlock(&vm->it_lock);
 		trace_amdgpu_vm_bo_unmap(bo_va, mapping);
+		spin_lock(&vm->freed_lock);
 		list_add(&mapping->list, &vm->freed);
+		spin_unlock(&vm->freed_lock);
 	}
 	list_for_each_entry_safe(mapping, next, &bo_va->invalids, list) {
 		list_del(&mapping->list);
+		spin_lock(&vm->it_lock);
 		interval_tree_remove(&mapping->it, &vm->va);
+		spin_unlock(&vm->it_lock);
 		kfree(mapping);
 	}
-
 	fence_put(bo_va->last_pt_update);
+	mutex_destroy(&bo_va->mutex);
 	kfree(bo_va);
 }
 
@@ -1241,15 +1254,14 @@
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 		vm->ids[i].id = 0;
 		vm->ids[i].flushed_updates = NULL;
-		vm->ids[i].last_id_use = NULL;
 	}
-	mutex_init(&vm->mutex);
 	vm->va = RB_ROOT;
 	spin_lock_init(&vm->status_lock);
 	INIT_LIST_HEAD(&vm->invalidated);
 	INIT_LIST_HEAD(&vm->cleared);
 	INIT_LIST_HEAD(&vm->freed);
-
+	spin_lock_init(&vm->it_lock);
+	spin_lock_init(&vm->freed_lock);
 	pd_size = amdgpu_vm_directory_size(adev);
 	pd_entries = amdgpu_vm_num_pdes(adev);
 
@@ -1269,8 +1281,14 @@
 			     NULL, NULL, &vm->page_directory);
 	if (r)
 		return r;
-
+	r = amdgpu_bo_reserve(vm->page_directory, false);
+	if (r) {
+		amdgpu_bo_unref(&vm->page_directory);
+		vm->page_directory = NULL;
+		return r;
+	}
 	r = amdgpu_vm_clear_bo(adev, vm->page_directory);
+	amdgpu_bo_unreserve(vm->page_directory);
 	if (r) {
 		amdgpu_bo_unref(&vm->page_directory);
 		vm->page_directory = NULL;
@@ -1313,11 +1331,27 @@
 
 	amdgpu_bo_unref(&vm->page_directory);
 	fence_put(vm->page_directory_fence);
-
 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
+		unsigned id = vm->ids[i].id;
+
+		atomic_long_cmpxchg(&adev->vm_manager.ids[id].owner,
+				    (long)vm, 0);
 		fence_put(vm->ids[i].flushed_updates);
-		fence_put(vm->ids[i].last_id_use);
 	}
 
-	mutex_destroy(&vm->mutex);
+}
+
+/**
+ * amdgpu_vm_manager_fini - cleanup VM manager
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Cleanup the VM manager and free resources.
+ */
+void amdgpu_vm_manager_fini(struct amdgpu_device *adev)
+{
+	unsigned i;
+
+	for (i = 0; i < AMDGPU_NUM_VM; ++i)
+		fence_put(adev->vm_manager.ids[i].active);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
index a1a35a5..57a2e34 100644
--- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
@@ -6569,12 +6569,12 @@
 		switch (state) {
 		case AMDGPU_IRQ_STATE_DISABLE:
 			cg_thermal_int = RREG32_SMC(ixCG_THERMAL_INT);
-			cg_thermal_int &= ~CG_THERMAL_INT_CTRL__THERM_INTH_MASK_MASK;
+			cg_thermal_int |= CG_THERMAL_INT_CTRL__THERM_INTH_MASK_MASK;
 			WREG32_SMC(ixCG_THERMAL_INT, cg_thermal_int);
 			break;
 		case AMDGPU_IRQ_STATE_ENABLE:
 			cg_thermal_int = RREG32_SMC(ixCG_THERMAL_INT);
-			cg_thermal_int |= CG_THERMAL_INT_CTRL__THERM_INTH_MASK_MASK;
+			cg_thermal_int &= ~CG_THERMAL_INT_CTRL__THERM_INTH_MASK_MASK;
 			WREG32_SMC(ixCG_THERMAL_INT, cg_thermal_int);
 			break;
 		default:
@@ -6586,12 +6586,12 @@
 		switch (state) {
 		case AMDGPU_IRQ_STATE_DISABLE:
 			cg_thermal_int = RREG32_SMC(ixCG_THERMAL_INT);
-			cg_thermal_int &= ~CG_THERMAL_INT_CTRL__THERM_INTL_MASK_MASK;
+			cg_thermal_int |= CG_THERMAL_INT_CTRL__THERM_INTL_MASK_MASK;
 			WREG32_SMC(ixCG_THERMAL_INT, cg_thermal_int);
 			break;
 		case AMDGPU_IRQ_STATE_ENABLE:
 			cg_thermal_int = RREG32_SMC(ixCG_THERMAL_INT);
-			cg_thermal_int |= CG_THERMAL_INT_CTRL__THERM_INTL_MASK_MASK;
+			cg_thermal_int &= ~CG_THERMAL_INT_CTRL__THERM_INTL_MASK_MASK;
 			WREG32_SMC(ixCG_THERMAL_INT, cg_thermal_int);
 			break;
 		default:
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index cb0f774..4dcc8fb 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -1250,7 +1250,7 @@
 	u32 pixel_period;
 	u32 line_time = 0;
 	u32 latency_watermark_a = 0, latency_watermark_b = 0;
-	u32 tmp, wm_mask;
+	u32 tmp, wm_mask, lb_vblank_lead_lines = 0;
 
 	if (amdgpu_crtc->base.enabled && num_heads && mode) {
 		pixel_period = 1000000 / (u32)mode->clock;
@@ -1333,6 +1333,7 @@
 		    (adev->mode_info.disp_priority == 2)) {
 			DRM_DEBUG_KMS("force priority to high\n");
 		}
+		lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode->crtc_hdisplay);
 	}
 
 	/* select wm A */
@@ -1357,6 +1358,8 @@
 	amdgpu_crtc->line_time = line_time;
 	amdgpu_crtc->wm_high = latency_watermark_a;
 	amdgpu_crtc->wm_low = latency_watermark_b;
+	/* Save number of lines the linebuffer leads before the scanout */
+	amdgpu_crtc->lb_vblank_lead_lines = lb_vblank_lead_lines;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index 5af3721..8f1e511 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -1238,7 +1238,7 @@
 	u32 pixel_period;
 	u32 line_time = 0;
 	u32 latency_watermark_a = 0, latency_watermark_b = 0;
-	u32 tmp, wm_mask;
+	u32 tmp, wm_mask, lb_vblank_lead_lines = 0;
 
 	if (amdgpu_crtc->base.enabled && num_heads && mode) {
 		pixel_period = 1000000 / (u32)mode->clock;
@@ -1321,6 +1321,7 @@
 		    (adev->mode_info.disp_priority == 2)) {
 			DRM_DEBUG_KMS("force priority to high\n");
 		}
+		lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode->crtc_hdisplay);
 	}
 
 	/* select wm A */
@@ -1345,6 +1346,8 @@
 	amdgpu_crtc->line_time = line_time;
 	amdgpu_crtc->wm_high = latency_watermark_a;
 	amdgpu_crtc->wm_low = latency_watermark_b;
+	/* Save number of lines the linebuffer leads before the scanout */
+	amdgpu_crtc->lb_vblank_lead_lines = lb_vblank_lead_lines;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index 4f7b49a..42d954d 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -1193,7 +1193,7 @@
 	u32 pixel_period;
 	u32 line_time = 0;
 	u32 latency_watermark_a = 0, latency_watermark_b = 0;
-	u32 tmp, wm_mask;
+	u32 tmp, wm_mask, lb_vblank_lead_lines = 0;
 
 	if (amdgpu_crtc->base.enabled && num_heads && mode) {
 		pixel_period = 1000000 / (u32)mode->clock;
@@ -1276,6 +1276,7 @@
 		    (adev->mode_info.disp_priority == 2)) {
 			DRM_DEBUG_KMS("force priority to high\n");
 		}
+		lb_vblank_lead_lines = DIV_ROUND_UP(lb_size, mode->crtc_hdisplay);
 	}
 
 	/* select wm A */
@@ -1302,6 +1303,8 @@
 	amdgpu_crtc->line_time = line_time;
 	amdgpu_crtc->wm_high = latency_watermark_a;
 	amdgpu_crtc->wm_low = latency_watermark_b;
+	/* Save number of lines the linebuffer leads before the scanout */
+	amdgpu_crtc->lb_vblank_lead_lines = lb_vblank_lead_lines;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 6776cf7..e1dcab9 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -268,7 +268,6 @@
 	mmCGTT_CP_CLK_CTRL, 0xffffffff, 0x00000100,
 	mmCGTT_CPC_CLK_CTRL, 0xffffffff, 0x00000100,
 	mmCGTT_CPF_CLK_CTRL, 0xffffffff, 0x40000100,
-	mmCGTT_DRM_CLK_CTRL0, 0xffffffff, 0x00600100,
 	mmCGTT_GDS_CLK_CTRL, 0xffffffff, 0x00000100,
 	mmCGTT_IA_CLK_CTRL, 0xffffffff, 0x06000100,
 	mmCGTT_PA_CLK_CTRL, 0xffffffff, 0x00000100,
@@ -296,10 +295,6 @@
 	mmCGTS_SM_CTRL_REG, 0xffffffff, 0x96e00200,
 	mmCP_RB_WPTR_POLL_CNTL, 0xffffffff, 0x00900100,
 	mmRLC_CGCG_CGLS_CTRL, 0xffffffff, 0x0020003c,
-	mmPCIE_INDEX, 0xffffffff, 0x0140001c,
-	mmPCIE_DATA, 0x000f0000, 0x00000000,
-	mmCGTT_DRM_CLK_CTRL0, 0xff000fff, 0x00000100,
-	mmHDP_XDP_CGTT_BLK_CTRL, 0xc0000fff, 0x00000104,
 	mmCP_MEM_SLP_CNTL, 0x00000001, 0x00000001,
 };
 
@@ -1000,7 +995,7 @@
 		adev->gfx.config.max_cu_per_sh = 16;
 		adev->gfx.config.max_sh_per_se = 1;
 		adev->gfx.config.max_backends_per_se = 4;
-		adev->gfx.config.max_texture_channel_caches = 8;
+		adev->gfx.config.max_texture_channel_caches = 16;
 		adev->gfx.config.max_gprs = 256;
 		adev->gfx.config.max_gs_threads = 32;
 		adev->gfx.config.max_hw_contexts = 8;
@@ -1613,6 +1608,296 @@
 			WREG32(mmGB_MACROTILE_MODE0 + reg_offset, gb_tile_moden);
 		}
 	case CHIP_FIJI:
+		for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++) {
+			switch (reg_offset) {
+			case 0:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING));
+				break;
+			case 1:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						TILE_SPLIT(ADDR_SURF_TILE_SPLIT_128B) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING));
+				break;
+			case 2:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING));
+				break;
+			case 3:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING));
+				break;
+			case 4:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						TILE_SPLIT(ADDR_SURF_TILE_SPLIT_2KB) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING));
+				break;
+			case 5:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						TILE_SPLIT(ADDR_SURF_TILE_SPLIT_2KB) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING));
+				break;
+			case 6:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						TILE_SPLIT(ADDR_SURF_TILE_SPLIT_2KB) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING));
+				break;
+			case 7:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P4_16x16) |
+						TILE_SPLIT(ADDR_SURF_TILE_SPLIT_2KB) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DEPTH_MICRO_TILING));
+				break;
+			case 8:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_LINEAR_ALIGNED) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16));
+				break;
+			case 9:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DISPLAY_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2));
+				break;
+			case 10:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DISPLAY_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2));
+				break;
+			case 11:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DISPLAY_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_8));
+				break;
+			case 12:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P4_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_DISPLAY_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_8));
+				break;
+			case 13:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2));
+				break;
+			case 14:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2));
+				break;
+			case 15:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_3D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2));
+				break;
+			case 16:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_8));
+				break;
+			case 17:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P4_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_8));
+				break;
+			case 18:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THICK) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1));
+				break;
+			case 19:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THICK) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1));
+				break;
+			case 20:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THICK) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1));
+				break;
+			case 21:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_3D_TILED_THICK) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1));
+				break;
+			case 22:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THICK) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1));
+				break;
+			case 23:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THICK) |
+						PIPE_CONFIG(ADDR_SURF_P4_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1));
+				break;
+			case 24:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THICK) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THIN_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1));
+				break;
+			case 25:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_XTHICK) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1));
+				break;
+			case 26:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_3D_TILED_XTHICK) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_THICK_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_1));
+				break;
+			case 27:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_ROTATED_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2));
+				break;
+			case 28:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_ROTATED_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_2));
+				break;
+			case 29:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P16_32x32_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_ROTATED_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_8));
+				break;
+			case 30:
+				gb_tile_moden = (ARRAY_MODE(ARRAY_PRT_TILED_THIN1) |
+						PIPE_CONFIG(ADDR_SURF_P4_16x16) |
+						MICRO_TILE_MODE_NEW(ADDR_SURF_ROTATED_MICRO_TILING) |
+						SAMPLE_SPLIT(ADDR_SURF_SAMPLE_SPLIT_8));
+				break;
+			default:
+				gb_tile_moden = 0;
+				break;
+			}
+			adev->gfx.config.tile_mode_array[reg_offset] = gb_tile_moden;
+			WREG32(mmGB_TILE_MODE0 + reg_offset, gb_tile_moden);
+		}
+		for (reg_offset = 0; reg_offset < num_secondary_tile_mode_states; reg_offset++) {
+			switch (reg_offset) {
+			case 0:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 1:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 2:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 3:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 4:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 5:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 6:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 8:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_8) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 9:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 10:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 11:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 12:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 13:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2) |
+						NUM_BANKS(ADDR_SURF_8_BANK));
+				break;
+			case 14:
+				gb_tile_moden = (BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+						BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+						MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1) |
+						NUM_BANKS(ADDR_SURF_4_BANK));
+				break;
+			case 7:
+				/* unused idx */
+				continue;
+			default:
+				gb_tile_moden = 0;
+				break;
+			}
+			adev->gfx.config.macrotile_mode_array[reg_offset] = gb_tile_moden;
+			WREG32(mmGB_MACROTILE_MODE0 + reg_offset, gb_tile_moden);
+		}
+		break;
 	case CHIP_TONGA:
 		for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++) {
 			switch (reg_offset) {
@@ -2971,10 +3256,13 @@
 	amdgpu_ring_write(ring, mmPA_SC_RASTER_CONFIG - PACKET3_SET_CONTEXT_REG_START);
 	switch (adev->asic_type) {
 	case CHIP_TONGA:
-	case CHIP_FIJI:
 		amdgpu_ring_write(ring, 0x16000012);
 		amdgpu_ring_write(ring, 0x0000002A);
 		break;
+	case CHIP_FIJI:
+		amdgpu_ring_write(ring, 0x3a00161a);
+		amdgpu_ring_write(ring, 0x0000002e);
+		break;
 	case CHIP_TOPAZ:
 	case CHIP_CARRIZO:
 		amdgpu_ring_write(ring, 0x00000002);
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index 85bbcdc..ed8abb5 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -40,7 +40,7 @@
 static void gmc_v7_0_set_gart_funcs(struct amdgpu_device *adev);
 static void gmc_v7_0_set_irq_funcs(struct amdgpu_device *adev);
 
-MODULE_FIRMWARE("radeon/boniare_mc.bin");
+MODULE_FIRMWARE("radeon/bonaire_mc.bin");
 MODULE_FIRMWARE("radeon/hawaii_mc.bin");
 
 /**
@@ -501,6 +501,7 @@
 	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, ENABLE_L2_PDE0_CACHE_LRU_UPDATE_BY_WRITE, 1);
 	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, EFFECTIVE_L2_QUEUE_SIZE, 7);
 	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, CONTEXT1_IDENTITY_ACCESS_MODE, 1);
+	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, ENABLE_DEFAULT_PAGE_OUT_TO_SYSTEM_MEMORY, 1);
 	WREG32(mmVM_L2_CNTL, tmp);
 	tmp = REG_SET_FIELD(0, VM_L2_CNTL2, INVALIDATE_ALL_L1_TLBS, 1);
 	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL2, INVALIDATE_L2_CACHE, 1);
@@ -512,7 +513,7 @@
 	WREG32(mmVM_L2_CNTL3, tmp);
 	/* setup context0 */
 	WREG32(mmVM_CONTEXT0_PAGE_TABLE_START_ADDR, adev->mc.gtt_start >> 12);
-	WREG32(mmVM_CONTEXT0_PAGE_TABLE_END_ADDR, (adev->mc.gtt_end >> 12) - 1);
+	WREG32(mmVM_CONTEXT0_PAGE_TABLE_END_ADDR, adev->mc.gtt_end >> 12);
 	WREG32(mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR, adev->gart.table_addr >> 12);
 	WREG32(mmVM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR,
 			(u32)(adev->dummy_page.addr >> 12));
@@ -960,12 +961,10 @@
 
 static int gmc_v7_0_sw_fini(void *handle)
 {
-	int i;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	if (adev->vm_manager.enabled) {
-		for (i = 0; i < AMDGPU_NUM_VM; ++i)
-			fence_put(adev->vm_manager.active[i]);
+		amdgpu_vm_manager_fini(adev);
 		gmc_v7_0_vm_fini(adev);
 		adev->vm_manager.enabled = false;
 	}
@@ -1010,12 +1009,10 @@
 
 static int gmc_v7_0_suspend(void *handle)
 {
-	int i;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	if (adev->vm_manager.enabled) {
-		for (i = 0; i < AMDGPU_NUM_VM; ++i)
-			fence_put(adev->vm_manager.active[i]);
+		amdgpu_vm_manager_fini(adev);
 		gmc_v7_0_vm_fini(adev);
 		adev->vm_manager.enabled = false;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index 1bcc4e7..d390284 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -629,6 +629,7 @@
 	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, ENABLE_L2_PDE0_CACHE_LRU_UPDATE_BY_WRITE, 1);
 	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, EFFECTIVE_L2_QUEUE_SIZE, 7);
 	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, CONTEXT1_IDENTITY_ACCESS_MODE, 1);
+	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL, ENABLE_DEFAULT_PAGE_OUT_TO_SYSTEM_MEMORY, 1);
 	WREG32(mmVM_L2_CNTL, tmp);
 	tmp = RREG32(mmVM_L2_CNTL2);
 	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL2, INVALIDATE_ALL_L1_TLBS, 1);
@@ -656,7 +657,7 @@
 	WREG32(mmVM_L2_CNTL4, tmp);
 	/* setup context0 */
 	WREG32(mmVM_CONTEXT0_PAGE_TABLE_START_ADDR, adev->mc.gtt_start >> 12);
-	WREG32(mmVM_CONTEXT0_PAGE_TABLE_END_ADDR, (adev->mc.gtt_end >> 12) - 1);
+	WREG32(mmVM_CONTEXT0_PAGE_TABLE_END_ADDR, adev->mc.gtt_end >> 12);
 	WREG32(mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR, adev->gart.table_addr >> 12);
 	WREG32(mmVM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR,
 			(u32)(adev->dummy_page.addr >> 12));
@@ -979,12 +980,10 @@
 
 static int gmc_v8_0_sw_fini(void *handle)
 {
-	int i;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	if (adev->vm_manager.enabled) {
-		for (i = 0; i < AMDGPU_NUM_VM; ++i)
-			fence_put(adev->vm_manager.active[i]);
+		amdgpu_vm_manager_fini(adev);
 		gmc_v8_0_vm_fini(adev);
 		adev->vm_manager.enabled = false;
 	}
@@ -1031,12 +1030,10 @@
 
 static int gmc_v8_0_suspend(void *handle)
 {
-	int i;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	if (adev->vm_manager.enabled) {
-		for (i = 0; i < AMDGPU_NUM_VM; ++i)
-			fence_put(adev->vm_manager.active[i]);
+		amdgpu_vm_manager_fini(adev);
 		gmc_v8_0_vm_fini(adev);
 		adev->vm_manager.enabled = false;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index 6a52db6..370c6c9 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -40,6 +40,9 @@
 
 #define GRBM_GFX_INDEX__VCE_INSTANCE__SHIFT	0x04
 #define GRBM_GFX_INDEX__VCE_INSTANCE_MASK	0x10
+#define mmVCE_LMI_VCPU_CACHE_40BIT_BAR0 	0x8616
+#define mmVCE_LMI_VCPU_CACHE_40BIT_BAR1 	0x8617
+#define mmVCE_LMI_VCPU_CACHE_40BIT_BAR2 	0x8618
 
 #define VCE_V3_0_FW_SIZE	(384 * 1024)
 #define VCE_V3_0_STACK_SIZE	(64 * 1024)
@@ -130,9 +133,11 @@
 
 		/* set BUSY flag */
 		WREG32_P(mmVCE_STATUS, 1, ~1);
-
-		WREG32_P(mmVCE_VCPU_CNTL, VCE_VCPU_CNTL__CLK_EN_MASK,
-			~VCE_VCPU_CNTL__CLK_EN_MASK);
+		if (adev->asic_type >= CHIP_STONEY)
+			WREG32_P(mmVCE_VCPU_CNTL, 1, ~0x200001);
+		else
+			WREG32_P(mmVCE_VCPU_CNTL, VCE_VCPU_CNTL__CLK_EN_MASK,
+				~VCE_VCPU_CNTL__CLK_EN_MASK);
 
 		WREG32_P(mmVCE_SOFT_RESET,
 			 VCE_SOFT_RESET__ECPU_SOFT_RESET_MASK,
@@ -391,8 +396,12 @@
 	WREG32(mmVCE_LMI_SWAP_CNTL, 0);
 	WREG32(mmVCE_LMI_SWAP_CNTL1, 0);
 	WREG32(mmVCE_LMI_VM_CTRL, 0);
-
-	WREG32(mmVCE_LMI_VCPU_CACHE_40BIT_BAR, (adev->vce.gpu_addr >> 8));
+	if (adev->asic_type >= CHIP_STONEY) {
+		WREG32(mmVCE_LMI_VCPU_CACHE_40BIT_BAR0, (adev->vce.gpu_addr >> 8));
+		WREG32(mmVCE_LMI_VCPU_CACHE_40BIT_BAR1, (adev->vce.gpu_addr >> 8));
+		WREG32(mmVCE_LMI_VCPU_CACHE_40BIT_BAR2, (adev->vce.gpu_addr >> 8));
+	} else
+		WREG32(mmVCE_LMI_VCPU_CACHE_40BIT_BAR, (adev->vce.gpu_addr >> 8));
 	offset = AMDGPU_VCE_FIRMWARE_OFFSET;
 	size = VCE_V3_0_FW_SIZE;
 	WREG32(mmVCE_VCPU_CACHE_OFFSET0, offset & 0x7fffffff);
@@ -576,6 +585,11 @@
 				      struct amdgpu_iv_entry *entry)
 {
 	DRM_DEBUG("IH: VCE\n");
+
+	WREG32_P(mmVCE_SYS_INT_STATUS,
+		VCE_SYS_INT_STATUS__VCE_SYS_INT_TRAP_INTERRUPT_INT_MASK,
+		~VCE_SYS_INT_STATUS__VCE_SYS_INT_TRAP_INTERRUPT_INT_MASK);
+
 	switch (entry->src_data) {
 	case 0:
 		amdgpu_fence_process(&adev->vce.ring[0]);
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h b/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h
index 144f50a..c89dc77 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h
+++ b/drivers/gpu/drm/amd/scheduler/gpu_sched_trace.h
@@ -16,6 +16,8 @@
 	    TP_ARGS(sched_job),
 	    TP_STRUCT__entry(
 			     __field(struct amd_sched_entity *, entity)
+			     __field(struct amd_sched_job *, sched_job)
+			     __field(struct fence *, fence)
 			     __field(const char *, name)
 			     __field(u32, job_count)
 			     __field(int, hw_job_count)
@@ -23,16 +25,32 @@
 
 	    TP_fast_assign(
 			   __entry->entity = sched_job->s_entity;
+			   __entry->sched_job = sched_job;
+			   __entry->fence = &sched_job->s_fence->base;
 			   __entry->name = sched_job->sched->name;
 			   __entry->job_count = kfifo_len(
 				   &sched_job->s_entity->job_queue) / sizeof(sched_job);
 			   __entry->hw_job_count = atomic_read(
 				   &sched_job->sched->hw_rq_count);
 			   ),
-	    TP_printk("entity=%p, ring=%s, job count:%u, hw job count:%d",
-		      __entry->entity, __entry->name, __entry->job_count,
-		      __entry->hw_job_count)
+	    TP_printk("entity=%p, sched job=%p, fence=%p, ring=%s, job count:%u, hw job count:%d",
+		      __entry->entity, __entry->sched_job, __entry->fence, __entry->name,
+		      __entry->job_count, __entry->hw_job_count)
 );
+
+TRACE_EVENT(amd_sched_process_job,
+	    TP_PROTO(struct amd_sched_fence *fence),
+	    TP_ARGS(fence),
+	    TP_STRUCT__entry(
+		    __field(struct fence *, fence)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->fence = &fence->base;
+		    ),
+	    TP_printk("fence=%p signaled", __entry->fence)
+);
+
 #endif
 
 /* This part must be outside protection */
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
index 89619a5..3a4820e 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
@@ -30,10 +30,12 @@
 #define CREATE_TRACE_POINTS
 #include "gpu_sched_trace.h"
 
-static struct amd_sched_job *
-amd_sched_entity_pop_job(struct amd_sched_entity *entity);
+static bool amd_sched_entity_is_ready(struct amd_sched_entity *entity);
 static void amd_sched_wakeup(struct amd_gpu_scheduler *sched);
 
+struct kmem_cache *sched_fence_slab;
+atomic_t sched_fence_slab_ref = ATOMIC_INIT(0);
+
 /* Initialize a given run queue struct */
 static void amd_sched_rq_init(struct amd_sched_rq *rq)
 {
@@ -61,36 +63,36 @@
 }
 
 /**
- * Select next job from a specified run queue with round robin policy.
- * Return NULL if nothing available.
+ * Select an entity which could provide a job to run
+ *
+ * @rq		The run queue to check.
+ *
+ * Try to find a ready entity, returns NULL if none found.
  */
-static struct amd_sched_job *
-amd_sched_rq_select_job(struct amd_sched_rq *rq)
+static struct amd_sched_entity *
+amd_sched_rq_select_entity(struct amd_sched_rq *rq)
 {
 	struct amd_sched_entity *entity;
-	struct amd_sched_job *sched_job;
 
 	spin_lock(&rq->lock);
 
 	entity = rq->current_entity;
 	if (entity) {
 		list_for_each_entry_continue(entity, &rq->entities, list) {
-			sched_job = amd_sched_entity_pop_job(entity);
-			if (sched_job) {
+			if (amd_sched_entity_is_ready(entity)) {
 				rq->current_entity = entity;
 				spin_unlock(&rq->lock);
-				return sched_job;
+				return entity;
 			}
 		}
 	}
 
 	list_for_each_entry(entity, &rq->entities, list) {
 
-		sched_job = amd_sched_entity_pop_job(entity);
-		if (sched_job) {
+		if (amd_sched_entity_is_ready(entity)) {
 			rq->current_entity = entity;
 			spin_unlock(&rq->lock);
-			return sched_job;
+			return entity;
 		}
 
 		if (entity == rq->current_entity)
@@ -174,6 +176,24 @@
 }
 
 /**
+ * Check if entity is ready
+ *
+ * @entity	The pointer to a valid scheduler entity
+ *
+ * Return true if entity could provide a job.
+ */
+static bool amd_sched_entity_is_ready(struct amd_sched_entity *entity)
+{
+	if (kfifo_is_empty(&entity->job_queue))
+		return false;
+
+	if (ACCESS_ONCE(entity->dependency))
+		return false;
+
+	return true;
+}
+
+/**
  * Destroy a context entity
  *
  * @sched       Pointer to scheduler instance
@@ -208,32 +228,53 @@
 	amd_sched_wakeup(entity->sched);
 }
 
+static bool amd_sched_entity_add_dependency_cb(struct amd_sched_entity *entity)
+{
+	struct amd_gpu_scheduler *sched = entity->sched;
+	struct fence * fence = entity->dependency;
+	struct amd_sched_fence *s_fence;
+
+	if (fence->context == entity->fence_context) {
+		/* We can ignore fences from ourself */
+		fence_put(entity->dependency);
+		return false;
+	}
+
+	s_fence = to_amd_sched_fence(fence);
+	if (s_fence && s_fence->sched == sched) {
+		/* Fence is from the same scheduler */
+		if (test_bit(AMD_SCHED_FENCE_SCHEDULED_BIT, &fence->flags)) {
+			/* Ignore it when it is already scheduled */
+			fence_put(entity->dependency);
+			return false;
+		}
+
+		/* Wait for fence to be scheduled */
+		entity->cb.func = amd_sched_entity_wakeup;
+		list_add_tail(&entity->cb.node, &s_fence->scheduled_cb);
+		return true;
+	}
+
+	if (!fence_add_callback(entity->dependency, &entity->cb,
+				amd_sched_entity_wakeup))
+		return true;
+
+	fence_put(entity->dependency);
+	return false;
+}
+
 static struct amd_sched_job *
 amd_sched_entity_pop_job(struct amd_sched_entity *entity)
 {
 	struct amd_gpu_scheduler *sched = entity->sched;
 	struct amd_sched_job *sched_job;
 
-	if (ACCESS_ONCE(entity->dependency))
-		return NULL;
-
 	if (!kfifo_out_peek(&entity->job_queue, &sched_job, sizeof(sched_job)))
 		return NULL;
 
-	while ((entity->dependency = sched->ops->dependency(sched_job))) {
-
-		if (entity->dependency->context == entity->fence_context) {
-			/* We can ignore fences from ourself */
-			fence_put(entity->dependency);
-			continue;
-		}
-
-		if (fence_add_callback(entity->dependency, &entity->cb,
-				       amd_sched_entity_wakeup))
-			fence_put(entity->dependency);
-		else
+	while ((entity->dependency = sched->ops->dependency(sched_job)))
+		if (amd_sched_entity_add_dependency_cb(entity))
 			return NULL;
-	}
 
 	return sched_job;
 }
@@ -247,6 +288,7 @@
  */
 static bool amd_sched_entity_in(struct amd_sched_job *sched_job)
 {
+	struct amd_gpu_scheduler *sched = sched_job->sched;
 	struct amd_sched_entity *entity = sched_job->s_entity;
 	bool added, first = false;
 
@@ -261,7 +303,7 @@
 
 	/* first job wakes up scheduler */
 	if (first)
-		amd_sched_wakeup(sched_job->sched);
+		amd_sched_wakeup(sched);
 
 	return added;
 }
@@ -273,22 +315,13 @@
  *
  * Returns 0 for success, negative error code otherwise.
  */
-int amd_sched_entity_push_job(struct amd_sched_job *sched_job)
+void amd_sched_entity_push_job(struct amd_sched_job *sched_job)
 {
 	struct amd_sched_entity *entity = sched_job->s_entity;
-	struct amd_sched_fence *fence = amd_sched_fence_create(
-		entity, sched_job->owner);
 
-	if (!fence)
-		return -ENOMEM;
-
-	fence_get(&fence->base);
-	sched_job->s_fence = fence;
-
+	trace_amd_sched_job(sched_job);
 	wait_event(entity->sched->job_scheduled,
 		   amd_sched_entity_in(sched_job));
-	trace_amd_sched_job(sched_job);
-	return 0;
 }
 
 /**
@@ -310,22 +343,22 @@
 }
 
 /**
- * Select next to run
+ * Select next entity to process
 */
-static struct amd_sched_job *
-amd_sched_select_job(struct amd_gpu_scheduler *sched)
+static struct amd_sched_entity *
+amd_sched_select_entity(struct amd_gpu_scheduler *sched)
 {
-	struct amd_sched_job *sched_job;
+	struct amd_sched_entity *entity;
 
 	if (!amd_sched_ready(sched))
 		return NULL;
 
 	/* Kernel run queue has higher priority than normal run queue*/
-	sched_job = amd_sched_rq_select_job(&sched->kernel_rq);
-	if (sched_job == NULL)
-		sched_job = amd_sched_rq_select_job(&sched->sched_rq);
+	entity = amd_sched_rq_select_entity(&sched->kernel_rq);
+	if (entity == NULL)
+		entity = amd_sched_rq_select_entity(&sched->sched_rq);
 
-	return sched_job;
+	return entity;
 }
 
 static void amd_sched_process_job(struct fence *f, struct fence_cb *cb)
@@ -343,6 +376,7 @@
 		list_del_init(&s_fence->list);
 		spin_unlock_irqrestore(&sched->fence_list_lock, flags);
 	}
+	trace_amd_sched_process_job(s_fence);
 	fence_put(&s_fence->base);
 	wake_up_interruptible(&sched->wake_up_worker);
 }
@@ -386,13 +420,16 @@
 		unsigned long flags;
 
 		wait_event_interruptible(sched->wake_up_worker,
-			kthread_should_stop() ||
-			(sched_job = amd_sched_select_job(sched)));
+			(entity = amd_sched_select_entity(sched)) ||
+			kthread_should_stop());
 
+		if (!entity)
+			continue;
+
+		sched_job = amd_sched_entity_pop_job(entity);
 		if (!sched_job)
 			continue;
 
-		entity = sched_job->s_entity;
 		s_fence = sched_job->s_fence;
 
 		if (sched->timeout != MAX_SCHEDULE_TIMEOUT) {
@@ -405,6 +442,7 @@
 
 		atomic_inc(&sched->hw_rq_count);
 		fence = sched->ops->run_job(sched_job);
+		amd_sched_fence_scheduled(s_fence);
 		if (fence) {
 			r = fence_add_callback(fence, &s_fence->cb,
 					       amd_sched_process_job);
@@ -450,6 +488,13 @@
 	init_waitqueue_head(&sched->wake_up_worker);
 	init_waitqueue_head(&sched->job_scheduled);
 	atomic_set(&sched->hw_rq_count, 0);
+	if (atomic_inc_return(&sched_fence_slab_ref) == 1) {
+		sched_fence_slab = kmem_cache_create(
+			"amd_sched_fence", sizeof(struct amd_sched_fence), 0,
+			SLAB_HWCACHE_ALIGN, NULL);
+		if (!sched_fence_slab)
+			return -ENOMEM;
+	}
 
 	/* Each scheduler will run on a seperate kernel thread */
 	sched->thread = kthread_run(amd_sched_main, sched, sched->name);
@@ -470,4 +515,6 @@
 {
 	if (sched->thread)
 		kthread_stop(sched->thread);
+	if (atomic_dec_and_test(&sched_fence_slab_ref))
+		kmem_cache_destroy(sched_fence_slab);
 }
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
index 929e9ac..a0f0ae5 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
+++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.h
@@ -27,9 +27,14 @@
 #include <linux/kfifo.h>
 #include <linux/fence.h>
 
+#define AMD_SCHED_FENCE_SCHEDULED_BIT	FENCE_FLAG_USER_BITS
+
 struct amd_gpu_scheduler;
 struct amd_sched_rq;
 
+extern struct kmem_cache *sched_fence_slab;
+extern atomic_t sched_fence_slab_ref;
+
 /**
  * A scheduler entity is a wrapper around a job queue or a group
  * of other entities. Entities take turns emitting jobs from their 
@@ -65,6 +70,7 @@
 struct amd_sched_fence {
 	struct fence                    base;
 	struct fence_cb                 cb;
+	struct list_head		scheduled_cb;
 	struct amd_gpu_scheduler	*sched;
 	spinlock_t			lock;
 	void                            *owner;
@@ -76,7 +82,6 @@
 	struct amd_gpu_scheduler        *sched;
 	struct amd_sched_entity         *s_entity;
 	struct amd_sched_fence          *s_fence;
-	void		                *owner;
 };
 
 extern const struct fence_ops amd_sched_fence_ops;
@@ -128,11 +133,11 @@
 			  uint32_t jobs);
 void amd_sched_entity_fini(struct amd_gpu_scheduler *sched,
 			   struct amd_sched_entity *entity);
-int amd_sched_entity_push_job(struct amd_sched_job *sched_job);
+void amd_sched_entity_push_job(struct amd_sched_job *sched_job);
 
 struct amd_sched_fence *amd_sched_fence_create(
 	struct amd_sched_entity *s_entity, void *owner);
+void amd_sched_fence_scheduled(struct amd_sched_fence *fence);
 void amd_sched_fence_signal(struct amd_sched_fence *fence);
 
-
 #endif
diff --git a/drivers/gpu/drm/amd/scheduler/sched_fence.c b/drivers/gpu/drm/amd/scheduler/sched_fence.c
index d802638..87c78ee 100644
--- a/drivers/gpu/drm/amd/scheduler/sched_fence.c
+++ b/drivers/gpu/drm/amd/scheduler/sched_fence.c
@@ -32,9 +32,11 @@
 	struct amd_sched_fence *fence = NULL;
 	unsigned seq;
 
-	fence = kzalloc(sizeof(struct amd_sched_fence), GFP_KERNEL);
+	fence = kmem_cache_zalloc(sched_fence_slab, GFP_KERNEL);
 	if (fence == NULL)
 		return NULL;
+
+	INIT_LIST_HEAD(&fence->scheduled_cb);
 	fence->owner = owner;
 	fence->sched = s_entity->sched;
 	spin_lock_init(&fence->lock);
@@ -55,6 +57,17 @@
 		FENCE_TRACE(&fence->base, "was already signaled\n");
 }
 
+void amd_sched_fence_scheduled(struct amd_sched_fence *s_fence)
+{
+	struct fence_cb *cur, *tmp;
+
+	set_bit(AMD_SCHED_FENCE_SCHEDULED_BIT, &s_fence->base.flags);
+	list_for_each_entry_safe(cur, tmp, &s_fence->scheduled_cb, node) {
+		list_del_init(&cur->node);
+		cur->func(&s_fence->base, cur);
+	}
+}
+
 static const char *amd_sched_fence_get_driver_name(struct fence *fence)
 {
 	return "amd_sched";
@@ -71,11 +84,17 @@
 	return true;
 }
 
+static void amd_sched_fence_release(struct fence *f)
+{
+	struct amd_sched_fence *fence = to_amd_sched_fence(f);
+	kmem_cache_free(sched_fence_slab, fence);
+}
+
 const struct fence_ops amd_sched_fence_ops = {
 	.get_driver_name = amd_sched_fence_get_driver_name,
 	.get_timeline_name = amd_sched_fence_get_timeline_name,
 	.enable_signaling = amd_sched_fence_enable_signaling,
 	.signaled = NULL,
 	.wait = fence_default_wait,
-	.release = NULL,
+	.release = amd_sched_fence_release,
 };
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 7bb3845..aeee083 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -1432,6 +1432,45 @@
 	return ret;
 }
 
+/**
+ * drm_atomic_update_old_fb -- Unset old_fb pointers and set plane->fb pointers.
+ *
+ * @dev: drm device to check.
+ * @plane_mask: plane mask for planes that were updated.
+ * @ret: return value, can be -EDEADLK for a retry.
+ *
+ * Before doing an update plane->old_fb is set to plane->fb,
+ * but before dropping the locks old_fb needs to be set to NULL
+ * and plane->fb updated. This is a common operation for each
+ * atomic update, so this call is split off as a helper.
+ */
+void drm_atomic_clean_old_fb(struct drm_device *dev,
+			     unsigned plane_mask,
+			     int ret)
+{
+	struct drm_plane *plane;
+
+	/* if succeeded, fixup legacy plane crtc/fb ptrs before dropping
+	 * locks (ie. while it is still safe to deref plane->state).  We
+	 * need to do this here because the driver entry points cannot
+	 * distinguish between legacy and atomic ioctls.
+	 */
+	drm_for_each_plane_mask(plane, dev, plane_mask) {
+		if (ret == 0) {
+			struct drm_framebuffer *new_fb = plane->state->fb;
+			if (new_fb)
+				drm_framebuffer_reference(new_fb);
+			plane->fb = new_fb;
+			plane->crtc = plane->state->crtc;
+
+			if (plane->old_fb)
+				drm_framebuffer_unreference(plane->old_fb);
+		}
+		plane->old_fb = NULL;
+	}
+}
+EXPORT_SYMBOL(drm_atomic_clean_old_fb);
+
 int drm_mode_atomic_ioctl(struct drm_device *dev,
 			  void *data, struct drm_file *file_priv)
 {
@@ -1446,7 +1485,7 @@
 	struct drm_plane *plane;
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *crtc_state;
-	unsigned plane_mask = 0;
+	unsigned plane_mask;
 	int ret = 0;
 	unsigned int i, j;
 
@@ -1486,6 +1525,7 @@
 	state->allow_modeset = !!(arg->flags & DRM_MODE_ATOMIC_ALLOW_MODESET);
 
 retry:
+	plane_mask = 0;
 	copied_objs = 0;
 	copied_props = 0;
 
@@ -1576,24 +1616,7 @@
 	}
 
 out:
-	/* if succeeded, fixup legacy plane crtc/fb ptrs before dropping
-	 * locks (ie. while it is still safe to deref plane->state).  We
-	 * need to do this here because the driver entry points cannot
-	 * distinguish between legacy and atomic ioctls.
-	 */
-	drm_for_each_plane_mask(plane, dev, plane_mask) {
-		if (ret == 0) {
-			struct drm_framebuffer *new_fb = plane->state->fb;
-			if (new_fb)
-				drm_framebuffer_reference(new_fb);
-			plane->fb = new_fb;
-			plane->crtc = plane->state->crtc;
-
-			if (plane->old_fb)
-				drm_framebuffer_unreference(plane->old_fb);
-		}
-		plane->old_fb = NULL;
-	}
+	drm_atomic_clean_old_fb(dev, plane_mask, ret);
 
 	if (ret && arg->flags & DRM_MODE_PAGE_FLIP_EVENT) {
 		/*
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 0c6f621..e5aec45 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -210,6 +210,14 @@
 		return -EINVAL;
 	}
 
+	if (!drm_encoder_crtc_ok(new_encoder, connector_state->crtc)) {
+		DRM_DEBUG_ATOMIC("[ENCODER:%d:%s] incompatible with [CRTC:%d]\n",
+				 new_encoder->base.id,
+				 new_encoder->name,
+				 connector_state->crtc->base.id);
+		return -EINVAL;
+	}
+
 	if (new_encoder == connector_state->best_encoder) {
 		DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] keeps [ENCODER:%d:%s], now on [CRTC:%d]\n",
 				 connector->base.id,
@@ -1553,6 +1561,9 @@
 		goto fail;
 	}
 
+	if (plane_state->crtc && (plane == plane->crtc->cursor))
+		plane_state->state->legacy_cursor_update = true;
+
 	ret = __drm_atomic_helper_disable_plane(plane, plane_state);
 	if (ret != 0)
 		goto fail;
@@ -1605,9 +1616,6 @@
 	plane_state->src_h = 0;
 	plane_state->src_w = 0;
 
-	if (plane->crtc && (plane == plane->crtc->cursor))
-		plane_state->state->legacy_cursor_update = true;
-
 	return 0;
 }
 
@@ -1741,6 +1749,7 @@
 	struct drm_crtc_state *crtc_state;
 	struct drm_plane_state *primary_state;
 	struct drm_crtc *crtc = set->crtc;
+	int hdisplay, vdisplay;
 	int ret;
 
 	crtc_state = drm_atomic_get_crtc_state(state, crtc);
@@ -1783,19 +1792,21 @@
 	if (ret != 0)
 		return ret;
 
+	drm_crtc_get_hv_timing(set->mode, &hdisplay, &vdisplay);
+
 	drm_atomic_set_fb_for_plane(primary_state, set->fb);
 	primary_state->crtc_x = 0;
 	primary_state->crtc_y = 0;
-	primary_state->crtc_h = set->mode->vdisplay;
-	primary_state->crtc_w = set->mode->hdisplay;
+	primary_state->crtc_h = vdisplay;
+	primary_state->crtc_w = hdisplay;
 	primary_state->src_x = set->x << 16;
 	primary_state->src_y = set->y << 16;
 	if (primary_state->rotation & (BIT(DRM_ROTATE_90) | BIT(DRM_ROTATE_270))) {
-		primary_state->src_h = set->mode->hdisplay << 16;
-		primary_state->src_w = set->mode->vdisplay << 16;
+		primary_state->src_h = hdisplay << 16;
+		primary_state->src_w = vdisplay << 16;
 	} else {
-		primary_state->src_h = set->mode->vdisplay << 16;
-		primary_state->src_w = set->mode->hdisplay << 16;
+		primary_state->src_h = vdisplay << 16;
+		primary_state->src_w = hdisplay << 16;
 	}
 
 commit:
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 9362609..7dd6728 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -160,6 +160,11 @@
 		goto out_unlock;
 	}
 
+	if (!file_priv->allowed_master) {
+		ret = drm_new_set_master(dev, file_priv);
+		goto out_unlock;
+	}
+
 	file_priv->minor->master = drm_master_get(file_priv->master);
 	file_priv->is_master = 1;
 	if (dev->driver->master_set) {
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index e673c13..69cbab5 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -342,6 +342,7 @@
 	struct drm_plane *plane;
 	struct drm_atomic_state *state;
 	int i, ret;
+	unsigned plane_mask;
 
 	state = drm_atomic_state_alloc(dev);
 	if (!state)
@@ -349,11 +350,10 @@
 
 	state->acquire_ctx = dev->mode_config.acquire_ctx;
 retry:
+	plane_mask = 0;
 	drm_for_each_plane(plane, dev) {
 		struct drm_plane_state *plane_state;
 
-		plane->old_fb = plane->fb;
-
 		plane_state = drm_atomic_get_plane_state(state, plane);
 		if (IS_ERR(plane_state)) {
 			ret = PTR_ERR(plane_state);
@@ -362,6 +362,9 @@
 
 		plane_state->rotation = BIT(DRM_ROTATE_0);
 
+		plane->old_fb = plane->fb;
+		plane_mask |= 1 << drm_plane_index(plane);
+
 		/* disable non-primary: */
 		if (plane->type == DRM_PLANE_TYPE_PRIMARY)
 			continue;
@@ -382,19 +385,7 @@
 	ret = drm_atomic_commit(state);
 
 fail:
-	drm_for_each_plane(plane, dev) {
-		if (ret == 0) {
-			struct drm_framebuffer *new_fb = plane->state->fb;
-			if (new_fb)
-				drm_framebuffer_reference(new_fb);
-			plane->fb = new_fb;
-			plane->crtc = plane->state->crtc;
-
-			if (plane->old_fb)
-				drm_framebuffer_unreference(plane->old_fb);
-		}
-		plane->old_fb = NULL;
-	}
+	drm_atomic_clean_old_fb(dev, plane_mask, ret);
 
 	if (ret == -EDEADLK)
 		goto backoff;
@@ -1236,7 +1227,9 @@
 	struct drm_fb_helper *fb_helper = info->par;
 	struct drm_device *dev = fb_helper->dev;
 	struct drm_atomic_state *state;
+	struct drm_plane *plane;
 	int i, ret;
+	unsigned plane_mask;
 
 	state = drm_atomic_state_alloc(dev);
 	if (!state)
@@ -1244,19 +1237,22 @@
 
 	state->acquire_ctx = dev->mode_config.acquire_ctx;
 retry:
+	plane_mask = 0;
 	for(i = 0; i < fb_helper->crtc_count; i++) {
 		struct drm_mode_set *mode_set;
 
 		mode_set = &fb_helper->crtc_info[i].mode_set;
 
-		mode_set->crtc->primary->old_fb = mode_set->crtc->primary->fb;
-
 		mode_set->x = var->xoffset;
 		mode_set->y = var->yoffset;
 
 		ret = __drm_atomic_helper_set_config(mode_set, state);
 		if (ret != 0)
 			goto fail;
+
+		plane = mode_set->crtc->primary;
+		plane_mask |= drm_plane_index(plane);
+		plane->old_fb = plane->fb;
 	}
 
 	ret = drm_atomic_commit(state);
@@ -1268,26 +1264,7 @@
 
 
 fail:
-	for(i = 0; i < fb_helper->crtc_count; i++) {
-		struct drm_mode_set *mode_set;
-		struct drm_plane *plane;
-
-		mode_set = &fb_helper->crtc_info[i].mode_set;
-		plane = mode_set->crtc->primary;
-
-		if (ret == 0) {
-			struct drm_framebuffer *new_fb = plane->state->fb;
-
-			if (new_fb)
-				drm_framebuffer_reference(new_fb);
-			plane->fb = new_fb;
-			plane->crtc = plane->state->crtc;
-
-			if (plane->old_fb)
-				drm_framebuffer_unreference(plane->old_fb);
-		}
-		plane->old_fb = NULL;
-	}
+	drm_atomic_clean_old_fb(dev, plane_mask, ret);
 
 	if (ret == -EDEADLK)
 		goto backoff;
diff --git a/drivers/gpu/drm/drm_fops.c b/drivers/gpu/drm/drm_fops.c
index c59ce4d..6b5625e 100644
--- a/drivers/gpu/drm/drm_fops.c
+++ b/drivers/gpu/drm/drm_fops.c
@@ -126,6 +126,60 @@
 }
 
 /**
+ * drm_new_set_master - Allocate a new master object and become master for the
+ * associated master realm.
+ *
+ * @dev: The associated device.
+ * @fpriv: File private identifying the client.
+ *
+ * This function must be called with dev::struct_mutex held.
+ * Returns negative error code on failure. Zero on success.
+ */
+int drm_new_set_master(struct drm_device *dev, struct drm_file *fpriv)
+{
+	struct drm_master *old_master;
+	int ret;
+
+	lockdep_assert_held_once(&dev->master_mutex);
+
+	/* create a new master */
+	fpriv->minor->master = drm_master_create(fpriv->minor);
+	if (!fpriv->minor->master)
+		return -ENOMEM;
+
+	/* take another reference for the copy in the local file priv */
+	old_master = fpriv->master;
+	fpriv->master = drm_master_get(fpriv->minor->master);
+
+	if (dev->driver->master_create) {
+		ret = dev->driver->master_create(dev, fpriv->master);
+		if (ret)
+			goto out_err;
+	}
+	if (dev->driver->master_set) {
+		ret = dev->driver->master_set(dev, fpriv, true);
+		if (ret)
+			goto out_err;
+	}
+
+	fpriv->is_master = 1;
+	fpriv->allowed_master = 1;
+	fpriv->authenticated = 1;
+	if (old_master)
+		drm_master_put(&old_master);
+
+	return 0;
+
+out_err:
+	/* drop both references and restore old master on failure */
+	drm_master_put(&fpriv->minor->master);
+	drm_master_put(&fpriv->master);
+	fpriv->master = old_master;
+
+	return ret;
+}
+
+/**
  * Called whenever a process opens /dev/drm.
  *
  * \param filp file pointer.
@@ -189,35 +243,9 @@
 	mutex_lock(&dev->master_mutex);
 	if (drm_is_primary_client(priv) && !priv->minor->master) {
 		/* create a new master */
-		priv->minor->master = drm_master_create(priv->minor);
-		if (!priv->minor->master) {
-			ret = -ENOMEM;
+		ret = drm_new_set_master(dev, priv);
+		if (ret)
 			goto out_close;
-		}
-
-		priv->is_master = 1;
-		/* take another reference for the copy in the local file priv */
-		priv->master = drm_master_get(priv->minor->master);
-		priv->authenticated = 1;
-
-		if (dev->driver->master_create) {
-			ret = dev->driver->master_create(dev, priv->master);
-			if (ret) {
-				/* drop both references if this fails */
-				drm_master_put(&priv->minor->master);
-				drm_master_put(&priv->master);
-				goto out_close;
-			}
-		}
-		if (dev->driver->master_set) {
-			ret = dev->driver->master_set(dev, priv, true);
-			if (ret) {
-				/* drop both references if this fails */
-				drm_master_put(&priv->minor->master);
-				drm_master_put(&priv->master);
-				goto out_close;
-			}
-		}
 	} else if (drm_is_primary_client(priv)) {
 		/* get a reference to the master */
 		priv->master = drm_master_get(priv->minor->master);
diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index 2151ea5..607f493 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -980,7 +980,8 @@
 		struct drm_pending_vblank_event *e,
 		unsigned long seq, struct timeval *now)
 {
-	WARN_ON_SMP(!spin_is_locked(&dev->event_lock));
+	assert_spin_locked(&dev->event_lock);
+
 	e->event.sequence = seq;
 	e->event.tv_sec = now->tv_sec;
 	e->event.tv_usec = now->tv_usec;
@@ -993,6 +994,57 @@
 }
 
 /**
+ * drm_arm_vblank_event - arm vblank event after pageflip
+ * @dev: DRM device
+ * @pipe: CRTC index
+ * @e: the event to prepare to send
+ *
+ * A lot of drivers need to generate vblank events for the very next vblank
+ * interrupt. For example when the page flip interrupt happens when the page
+ * flip gets armed, but not when it actually executes within the next vblank
+ * period. This helper function implements exactly the required vblank arming
+ * behaviour.
+ *
+ * Caller must hold event lock. Caller must also hold a vblank reference for
+ * the event @e, which will be dropped when the next vblank arrives.
+ *
+ * This is the legacy version of drm_crtc_arm_vblank_event().
+ */
+void drm_arm_vblank_event(struct drm_device *dev, unsigned int pipe,
+			  struct drm_pending_vblank_event *e)
+{
+	assert_spin_locked(&dev->event_lock);
+
+	e->pipe = pipe;
+	e->event.sequence = drm_vblank_count(dev, pipe);
+	list_add_tail(&e->base.link, &dev->vblank_event_list);
+}
+EXPORT_SYMBOL(drm_arm_vblank_event);
+
+/**
+ * drm_crtc_arm_vblank_event - arm vblank event after pageflip
+ * @crtc: the source CRTC of the vblank event
+ * @e: the event to send
+ *
+ * A lot of drivers need to generate vblank events for the very next vblank
+ * interrupt. For example when the page flip interrupt happens when the page
+ * flip gets armed, but not when it actually executes within the next vblank
+ * period. This helper function implements exactly the required vblank arming
+ * behaviour.
+ *
+ * Caller must hold event lock. Caller must also hold a vblank reference for
+ * the event @e, which will be dropped when the next vblank arrives.
+ *
+ * This is the native KMS version of drm_arm_vblank_event().
+ */
+void drm_crtc_arm_vblank_event(struct drm_crtc *crtc,
+			       struct drm_pending_vblank_event *e)
+{
+	drm_arm_vblank_event(crtc->dev, drm_crtc_index(crtc), e);
+}
+EXPORT_SYMBOL(drm_crtc_arm_vblank_event);
+
+/**
  * drm_send_vblank_event - helper to send vblank event after pageflip
  * @dev: DRM device
  * @pipe: CRTC index
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index a3b22bd..8aab974 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -2734,6 +2734,8 @@
 		return "AUX_C";
 	case POWER_DOMAIN_AUX_D:
 		return "AUX_D";
+	case POWER_DOMAIN_GMBUS:
+		return "GMBUS";
 	case POWER_DOMAIN_INIT:
 		return "INIT";
 	default:
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 8afda45..a01e515 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -199,6 +199,7 @@
 	POWER_DOMAIN_AUX_B,
 	POWER_DOMAIN_AUX_C,
 	POWER_DOMAIN_AUX_D,
+	POWER_DOMAIN_GMBUS,
 	POWER_DOMAIN_INIT,
 
 	POWER_DOMAIN_NUM,
@@ -351,6 +352,8 @@
 	/* hsw/bdw */
 	DPLL_ID_WRPLL1 = 0,
 	DPLL_ID_WRPLL2 = 1,
+	DPLL_ID_SPLL = 2,
+
 	/* skl */
 	DPLL_ID_SKL_DPLL1 = 0,
 	DPLL_ID_SKL_DPLL2 = 1,
@@ -367,6 +370,7 @@
 
 	/* hsw, bdw */
 	uint32_t wrpll;
+	uint32_t spll;
 
 	/* skl */
 	/*
@@ -2648,6 +2652,7 @@
 	int enable_cmd_parser;
 	/* leave bools at the end to not create holes */
 	bool enable_hangcheck;
+	bool fastboot;
 	bool prefault_disable;
 	bool load_detect_test;
 	bool reset;
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 5cf4a19..32e6aad 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1210,8 +1210,16 @@
 	if (i915_gem_request_completed(req, true))
 		return 0;
 
-	timeout_expire = timeout ?
-		jiffies + nsecs_to_jiffies_timeout((u64)*timeout) : 0;
+	timeout_expire = 0;
+	if (timeout) {
+		if (WARN_ON(*timeout < 0))
+			return -EINVAL;
+
+		if (*timeout == 0)
+			return -ETIME;
+
+		timeout_expire = jiffies + nsecs_to_jiffies_timeout(*timeout);
+	}
 
 	if (INTEL_INFO(dev_priv)->gen >= 6)
 		gen6_rps_boost(dev_priv, rps, req->emitted_jiffies);
@@ -3809,6 +3817,7 @@
 int i915_gem_set_caching_ioctl(struct drm_device *dev, void *data,
 			       struct drm_file *file)
 {
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_caching *args = data;
 	struct drm_i915_gem_object *obj;
 	enum i915_cache_level level;
@@ -3837,9 +3846,11 @@
 		return -EINVAL;
 	}
 
+	intel_runtime_pm_get(dev_priv);
+
 	ret = i915_mutex_lock_interruptible(dev);
 	if (ret)
-		return ret;
+		goto rpm_put;
 
 	obj = to_intel_bo(drm_gem_object_lookup(dev, file, args->handle));
 	if (&obj->base == NULL) {
@@ -3852,6 +3863,9 @@
 	drm_gem_object_unreference(&obj->base);
 unlock:
 	mutex_unlock(&dev->struct_mutex);
+rpm_put:
+	intel_runtime_pm_put(dev_priv);
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_gem_fence.c b/drivers/gpu/drm/i915/i915_gem_fence.c
index 40a10b2..f010391 100644
--- a/drivers/gpu/drm/i915/i915_gem_fence.c
+++ b/drivers/gpu/drm/i915/i915_gem_fence.c
@@ -642,11 +642,10 @@
 		}
 
 		/* check for L-shaped memory aka modified enhanced addressing */
-		if (IS_GEN4(dev)) {
-			uint32_t ddc2 = I915_READ(DCC2);
-
-			if (!(ddc2 & DCC2_MODIFIED_ENHANCED_DISABLE))
-				dev_priv->quirks |= QUIRK_PIN_SWIZZLED_PAGES;
+		if (IS_GEN4(dev) &&
+		    !(I915_READ(DCC2) & DCC2_MODIFIED_ENHANCED_DISABLE)) {
+			swizzle_x = I915_BIT_6_SWIZZLE_UNKNOWN;
+			swizzle_y = I915_BIT_6_SWIZZLE_UNKNOWN;
 		}
 
 		if (dcc == 0xffffffff) {
@@ -675,16 +674,35 @@
 		 * matching, which was the case for the swizzling required in
 		 * the table above, or from the 1-ch value being less than
 		 * the minimum size of a rank.
+		 *
+		 * Reports indicate that the swizzling actually
+		 * varies depending upon page placement inside the
+		 * channels, i.e. we see swizzled pages where the
+		 * banks of memory are paired and unswizzled on the
+		 * uneven portion, so leave that as unknown.
 		 */
-		if (I915_READ16(C0DRB3) != I915_READ16(C1DRB3)) {
-			swizzle_x = I915_BIT_6_SWIZZLE_NONE;
-			swizzle_y = I915_BIT_6_SWIZZLE_NONE;
-		} else {
+		if (I915_READ16(C0DRB3) == I915_READ16(C1DRB3)) {
 			swizzle_x = I915_BIT_6_SWIZZLE_9_10;
 			swizzle_y = I915_BIT_6_SWIZZLE_9;
 		}
 	}
 
+	if (swizzle_x == I915_BIT_6_SWIZZLE_UNKNOWN ||
+	    swizzle_y == I915_BIT_6_SWIZZLE_UNKNOWN) {
+		/* Userspace likes to explode if it sees unknown swizzling,
+		 * so lie. We will finish the lie when reporting through
+		 * the get-tiling-ioctl by reporting the physical swizzle
+		 * mode as unknown instead.
+		 *
+		 * As we don't strictly know what the swizzling is, it may be
+		 * bit17 dependent, and so we need to also prevent the pages
+		 * from being moved.
+		 */
+		dev_priv->quirks |= QUIRK_PIN_SWIZZLED_PAGES;
+		swizzle_x = I915_BIT_6_SWIZZLE_NONE;
+		swizzle_y = I915_BIT_6_SWIZZLE_NONE;
+	}
+
 	dev_priv->mm.bit_6_swizzle_x = swizzle_x;
 	dev_priv->mm.bit_6_swizzle_y = swizzle_y;
 }
diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c
index 96bb238..4be13a5 100644
--- a/drivers/gpu/drm/i915/i915_params.c
+++ b/drivers/gpu/drm/i915/i915_params.c
@@ -40,6 +40,7 @@
 	.preliminary_hw_support = IS_ENABLED(CONFIG_DRM_I915_PRELIMINARY_HW_SUPPORT),
 	.disable_power_well = -1,
 	.enable_ips = 1,
+	.fastboot = 0,
 	.prefault_disable = 0,
 	.load_detect_test = 0,
 	.reset = true,
@@ -133,6 +134,10 @@
 module_param_named_unsafe(enable_ips, i915.enable_ips, int, 0600);
 MODULE_PARM_DESC(enable_ips, "Enable IPS (default: true)");
 
+module_param_named(fastboot, i915.fastboot, bool, 0600);
+MODULE_PARM_DESC(fastboot,
+	"Try to skip unnecessary mode sets at boot time (default: false)");
+
 module_param_named_unsafe(prefault_disable, i915.prefault_disable, bool, 0600);
 MODULE_PARM_DESC(prefault_disable,
 	"Disable page prefaulting for pread/pwrite/reloc (default:false). "
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index b84aaa0..6a2c76e 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -138,18 +138,6 @@
 	pipe_config->base.adjusted_mode.flags |= intel_crt_get_flags(encoder);
 }
 
-static void hsw_crt_pre_enable(struct intel_encoder *encoder)
-{
-	struct drm_device *dev = encoder->base.dev;